diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,222244 @@ +{ + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 3.0, + "global_step": 36816, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 1.9999456757931336e-05, + "loss": 1.2361, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 1.999891351586267e-05, + "loss": 1.1413, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 1.9998370273794004e-05, + "loss": 1.2536, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 1.999782703172534e-05, + "loss": 1.1075, + "step": 4 + }, + { + "epoch": 0.0, + "learning_rate": 1.9997283789656673e-05, + "loss": 1.2021, + "step": 5 + }, + { + "epoch": 0.0, + "learning_rate": 1.9996740547588007e-05, + "loss": 1.1316, + "step": 6 + }, + { + "epoch": 0.0, + "learning_rate": 1.999619730551934e-05, + "loss": 1.1255, + "step": 7 + }, + { + "epoch": 0.0, + "learning_rate": 1.9995654063450675e-05, + "loss": 1.0903, + "step": 8 + }, + { + "epoch": 0.0, + "learning_rate": 1.999511082138201e-05, + "loss": 1.1597, + "step": 9 + }, + { + "epoch": 0.0, + "learning_rate": 1.9994567579313344e-05, + "loss": 1.065, + "step": 10 + }, + { + "epoch": 0.0, + "learning_rate": 1.9994024337244678e-05, + "loss": 1.1086, + "step": 11 + }, + { + "epoch": 0.0, + "learning_rate": 1.9993481095176012e-05, + "loss": 1.125, + "step": 12 + }, + { + "epoch": 0.0, + "learning_rate": 1.9992937853107347e-05, + "loss": 1.0834, + "step": 13 + }, + { + "epoch": 0.0, + "learning_rate": 1.999239461103868e-05, + "loss": 1.0929, + "step": 14 + }, + { + "epoch": 0.0, + "learning_rate": 1.9991851368970015e-05, + "loss": 1.1156, + "step": 15 + }, + { + "epoch": 0.0, + "learning_rate": 1.999130812690135e-05, + "loss": 1.1337, + "step": 16 + }, + { + "epoch": 0.0, + "learning_rate": 1.9990764884832684e-05, + "loss": 1.0822, + "step": 17 + }, + { + "epoch": 0.0, + "learning_rate": 1.9990221642764018e-05, + "loss": 1.092, + "step": 18 + }, + { + "epoch": 0.0, + "learning_rate": 1.9989678400695352e-05, + "loss": 1.0787, + "step": 19 + }, + { + "epoch": 0.0, + "learning_rate": 1.9989135158626686e-05, + "loss": 1.1323, + "step": 20 + }, + { + "epoch": 0.0, + "learning_rate": 1.998859191655802e-05, + "loss": 1.0115, + "step": 21 + }, + { + "epoch": 0.0, + "learning_rate": 1.9988048674489355e-05, + "loss": 1.1405, + "step": 22 + }, + { + "epoch": 0.0, + "learning_rate": 1.998750543242069e-05, + "loss": 1.1435, + "step": 23 + }, + { + "epoch": 0.0, + "learning_rate": 1.9986962190352023e-05, + "loss": 1.145, + "step": 24 + }, + { + "epoch": 0.0, + "learning_rate": 1.9986418948283357e-05, + "loss": 1.1548, + "step": 25 + }, + { + "epoch": 0.0, + "learning_rate": 1.998587570621469e-05, + "loss": 1.0931, + "step": 26 + }, + { + "epoch": 0.0, + "learning_rate": 1.9985332464146026e-05, + "loss": 1.1732, + "step": 27 + }, + { + "epoch": 0.0, + "learning_rate": 1.998478922207736e-05, + "loss": 1.1304, + "step": 28 + }, + { + "epoch": 0.0, + "learning_rate": 1.9984245980008694e-05, + "loss": 1.1627, + "step": 29 + }, + { + "epoch": 0.0, + "learning_rate": 1.998370273794003e-05, + "loss": 1.0682, + "step": 30 + }, + { + "epoch": 0.0, + "learning_rate": 1.9983159495871363e-05, + "loss": 1.0882, + "step": 31 + }, + { + "epoch": 0.0, + "learning_rate": 1.9982616253802697e-05, + "loss": 1.1584, + "step": 32 + }, + { + "epoch": 0.0, + "learning_rate": 1.998207301173403e-05, + "loss": 1.1029, + "step": 33 + }, + { + "epoch": 0.0, + "learning_rate": 1.9981529769665365e-05, + "loss": 1.0731, + "step": 34 + }, + { + "epoch": 0.0, + "learning_rate": 1.99809865275967e-05, + "loss": 1.0915, + "step": 35 + }, + { + "epoch": 0.0, + "learning_rate": 1.9980443285528034e-05, + "loss": 1.0836, + "step": 36 + }, + { + "epoch": 0.0, + "learning_rate": 1.9979900043459368e-05, + "loss": 1.1154, + "step": 37 + }, + { + "epoch": 0.0, + "learning_rate": 1.9979356801390702e-05, + "loss": 1.0904, + "step": 38 + }, + { + "epoch": 0.0, + "learning_rate": 1.9978813559322033e-05, + "loss": 1.0804, + "step": 39 + }, + { + "epoch": 0.0, + "learning_rate": 1.997827031725337e-05, + "loss": 1.1069, + "step": 40 + }, + { + "epoch": 0.0, + "learning_rate": 1.9977727075184702e-05, + "loss": 1.0731, + "step": 41 + }, + { + "epoch": 0.0, + "learning_rate": 1.997718383311604e-05, + "loss": 1.0849, + "step": 42 + }, + { + "epoch": 0.0, + "learning_rate": 1.997664059104737e-05, + "loss": 1.0334, + "step": 43 + }, + { + "epoch": 0.0, + "learning_rate": 1.9976097348978708e-05, + "loss": 1.0479, + "step": 44 + }, + { + "epoch": 0.0, + "learning_rate": 1.997555410691004e-05, + "loss": 1.0791, + "step": 45 + }, + { + "epoch": 0.0, + "learning_rate": 1.9975010864841376e-05, + "loss": 1.092, + "step": 46 + }, + { + "epoch": 0.0, + "learning_rate": 1.9974467622772707e-05, + "loss": 1.049, + "step": 47 + }, + { + "epoch": 0.0, + "learning_rate": 1.9973924380704045e-05, + "loss": 1.0939, + "step": 48 + }, + { + "epoch": 0.0, + "learning_rate": 1.9973381138635376e-05, + "loss": 1.0531, + "step": 49 + }, + { + "epoch": 0.0, + "learning_rate": 1.9972837896566713e-05, + "loss": 1.0441, + "step": 50 + }, + { + "epoch": 0.0, + "learning_rate": 1.9972294654498044e-05, + "loss": 1.0721, + "step": 51 + }, + { + "epoch": 0.0, + "learning_rate": 1.997175141242938e-05, + "loss": 1.0478, + "step": 52 + }, + { + "epoch": 0.0, + "learning_rate": 1.9971208170360712e-05, + "loss": 1.0782, + "step": 53 + }, + { + "epoch": 0.0, + "learning_rate": 1.997066492829205e-05, + "loss": 1.0, + "step": 54 + }, + { + "epoch": 0.0, + "learning_rate": 1.9970121686223384e-05, + "loss": 1.0205, + "step": 55 + }, + { + "epoch": 0.0, + "learning_rate": 1.996957844415472e-05, + "loss": 1.0438, + "step": 56 + }, + { + "epoch": 0.0, + "learning_rate": 1.9969035202086053e-05, + "loss": 0.9825, + "step": 57 + }, + { + "epoch": 0.0, + "learning_rate": 1.9968491960017384e-05, + "loss": 1.0347, + "step": 58 + }, + { + "epoch": 0.0, + "learning_rate": 1.996794871794872e-05, + "loss": 1.0313, + "step": 59 + }, + { + "epoch": 0.0, + "learning_rate": 1.9967405475880052e-05, + "loss": 1.0288, + "step": 60 + }, + { + "epoch": 0.0, + "learning_rate": 1.996686223381139e-05, + "loss": 1.0563, + "step": 61 + }, + { + "epoch": 0.01, + "learning_rate": 1.996631899174272e-05, + "loss": 1.052, + "step": 62 + }, + { + "epoch": 0.01, + "learning_rate": 1.9965775749674058e-05, + "loss": 1.0875, + "step": 63 + }, + { + "epoch": 0.01, + "learning_rate": 1.996523250760539e-05, + "loss": 1.081, + "step": 64 + }, + { + "epoch": 0.01, + "learning_rate": 1.9964689265536727e-05, + "loss": 1.061, + "step": 65 + }, + { + "epoch": 0.01, + "learning_rate": 1.9964146023468057e-05, + "loss": 1.0253, + "step": 66 + }, + { + "epoch": 0.01, + "learning_rate": 1.9963602781399395e-05, + "loss": 0.9843, + "step": 67 + }, + { + "epoch": 0.01, + "learning_rate": 1.9963059539330726e-05, + "loss": 1.0146, + "step": 68 + }, + { + "epoch": 0.01, + "learning_rate": 1.9962516297262064e-05, + "loss": 1.0488, + "step": 69 + }, + { + "epoch": 0.01, + "learning_rate": 1.9961973055193394e-05, + "loss": 0.9695, + "step": 70 + }, + { + "epoch": 0.01, + "learning_rate": 1.9961429813124732e-05, + "loss": 0.9802, + "step": 71 + }, + { + "epoch": 0.01, + "learning_rate": 1.9960886571056063e-05, + "loss": 0.9087, + "step": 72 + }, + { + "epoch": 0.01, + "learning_rate": 1.99603433289874e-05, + "loss": 1.0068, + "step": 73 + }, + { + "epoch": 0.01, + "learning_rate": 1.995980008691873e-05, + "loss": 1.0637, + "step": 74 + }, + { + "epoch": 0.01, + "learning_rate": 1.995925684485007e-05, + "loss": 0.9004, + "step": 75 + }, + { + "epoch": 0.01, + "learning_rate": 1.99587136027814e-05, + "loss": 1.0233, + "step": 76 + }, + { + "epoch": 0.01, + "learning_rate": 1.9958170360712734e-05, + "loss": 0.987, + "step": 77 + }, + { + "epoch": 0.01, + "learning_rate": 1.9957627118644068e-05, + "loss": 0.9887, + "step": 78 + }, + { + "epoch": 0.01, + "learning_rate": 1.9957083876575402e-05, + "loss": 0.9941, + "step": 79 + }, + { + "epoch": 0.01, + "learning_rate": 1.9956540634506737e-05, + "loss": 0.8732, + "step": 80 + }, + { + "epoch": 0.01, + "learning_rate": 1.995599739243807e-05, + "loss": 0.9403, + "step": 81 + }, + { + "epoch": 0.01, + "learning_rate": 1.9955454150369405e-05, + "loss": 0.9657, + "step": 82 + }, + { + "epoch": 0.01, + "learning_rate": 1.995491090830074e-05, + "loss": 1.0249, + "step": 83 + }, + { + "epoch": 0.01, + "learning_rate": 1.9954367666232074e-05, + "loss": 0.967, + "step": 84 + }, + { + "epoch": 0.01, + "learning_rate": 1.9953824424163408e-05, + "loss": 1.0971, + "step": 85 + }, + { + "epoch": 0.01, + "learning_rate": 1.9953281182094742e-05, + "loss": 1.1337, + "step": 86 + }, + { + "epoch": 0.01, + "learning_rate": 1.9952737940026076e-05, + "loss": 0.9055, + "step": 87 + }, + { + "epoch": 0.01, + "learning_rate": 1.995219469795741e-05, + "loss": 1.0445, + "step": 88 + }, + { + "epoch": 0.01, + "learning_rate": 1.9951651455888745e-05, + "loss": 0.9619, + "step": 89 + }, + { + "epoch": 0.01, + "learning_rate": 1.995110821382008e-05, + "loss": 0.8078, + "step": 90 + }, + { + "epoch": 0.01, + "learning_rate": 1.9950564971751413e-05, + "loss": 1.2404, + "step": 91 + }, + { + "epoch": 0.01, + "learning_rate": 1.995002172968275e-05, + "loss": 1.0549, + "step": 92 + }, + { + "epoch": 0.01, + "learning_rate": 1.994947848761408e-05, + "loss": 1.0637, + "step": 93 + }, + { + "epoch": 0.01, + "learning_rate": 1.994893524554542e-05, + "loss": 1.0223, + "step": 94 + }, + { + "epoch": 0.01, + "learning_rate": 1.994839200347675e-05, + "loss": 0.8362, + "step": 95 + }, + { + "epoch": 0.01, + "learning_rate": 1.9947848761408084e-05, + "loss": 1.0547, + "step": 96 + }, + { + "epoch": 0.01, + "learning_rate": 1.994730551933942e-05, + "loss": 0.8864, + "step": 97 + }, + { + "epoch": 0.01, + "learning_rate": 1.9946762277270753e-05, + "loss": 0.9003, + "step": 98 + }, + { + "epoch": 0.01, + "learning_rate": 1.9946219035202087e-05, + "loss": 0.9887, + "step": 99 + }, + { + "epoch": 0.01, + "learning_rate": 1.994567579313342e-05, + "loss": 1.0225, + "step": 100 + }, + { + "epoch": 0.01, + "learning_rate": 1.9945132551064756e-05, + "loss": 1.0057, + "step": 101 + }, + { + "epoch": 0.01, + "learning_rate": 1.994458930899609e-05, + "loss": 0.8976, + "step": 102 + }, + { + "epoch": 0.01, + "learning_rate": 1.9944046066927424e-05, + "loss": 0.8849, + "step": 103 + }, + { + "epoch": 0.01, + "learning_rate": 1.9943502824858758e-05, + "loss": 0.9782, + "step": 104 + }, + { + "epoch": 0.01, + "learning_rate": 1.9942959582790092e-05, + "loss": 0.9324, + "step": 105 + }, + { + "epoch": 0.01, + "learning_rate": 1.9942416340721427e-05, + "loss": 0.9749, + "step": 106 + }, + { + "epoch": 0.01, + "learning_rate": 1.994187309865276e-05, + "loss": 1.0104, + "step": 107 + }, + { + "epoch": 0.01, + "learning_rate": 1.9941329856584095e-05, + "loss": 0.8695, + "step": 108 + }, + { + "epoch": 0.01, + "learning_rate": 1.994078661451543e-05, + "loss": 0.9987, + "step": 109 + }, + { + "epoch": 0.01, + "learning_rate": 1.9940243372446764e-05, + "loss": 0.8843, + "step": 110 + }, + { + "epoch": 0.01, + "learning_rate": 1.9939700130378098e-05, + "loss": 0.8557, + "step": 111 + }, + { + "epoch": 0.01, + "learning_rate": 1.9939156888309432e-05, + "loss": 0.9427, + "step": 112 + }, + { + "epoch": 0.01, + "learning_rate": 1.9938613646240766e-05, + "loss": 0.862, + "step": 113 + }, + { + "epoch": 0.01, + "learning_rate": 1.99380704041721e-05, + "loss": 0.8548, + "step": 114 + }, + { + "epoch": 0.01, + "learning_rate": 1.9937527162103435e-05, + "loss": 0.8898, + "step": 115 + }, + { + "epoch": 0.01, + "learning_rate": 1.993698392003477e-05, + "loss": 0.9405, + "step": 116 + }, + { + "epoch": 0.01, + "learning_rate": 1.9936440677966103e-05, + "loss": 0.8948, + "step": 117 + }, + { + "epoch": 0.01, + "learning_rate": 1.9935897435897437e-05, + "loss": 0.9571, + "step": 118 + }, + { + "epoch": 0.01, + "learning_rate": 1.993535419382877e-05, + "loss": 0.8828, + "step": 119 + }, + { + "epoch": 0.01, + "learning_rate": 1.9934810951760106e-05, + "loss": 0.9856, + "step": 120 + }, + { + "epoch": 0.01, + "learning_rate": 1.993426770969144e-05, + "loss": 0.904, + "step": 121 + }, + { + "epoch": 0.01, + "learning_rate": 1.9933724467622774e-05, + "loss": 1.0001, + "step": 122 + }, + { + "epoch": 0.01, + "learning_rate": 1.993318122555411e-05, + "loss": 0.9568, + "step": 123 + }, + { + "epoch": 0.01, + "learning_rate": 1.9932637983485443e-05, + "loss": 0.8208, + "step": 124 + }, + { + "epoch": 0.01, + "learning_rate": 1.9932094741416777e-05, + "loss": 0.964, + "step": 125 + }, + { + "epoch": 0.01, + "learning_rate": 1.993155149934811e-05, + "loss": 1.0285, + "step": 126 + }, + { + "epoch": 0.01, + "learning_rate": 1.9931008257279446e-05, + "loss": 0.7415, + "step": 127 + }, + { + "epoch": 0.01, + "learning_rate": 1.993046501521078e-05, + "loss": 0.7452, + "step": 128 + }, + { + "epoch": 0.01, + "learning_rate": 1.9929921773142114e-05, + "loss": 0.8334, + "step": 129 + }, + { + "epoch": 0.01, + "learning_rate": 1.9929378531073448e-05, + "loss": 0.9496, + "step": 130 + }, + { + "epoch": 0.01, + "learning_rate": 1.9928835289004782e-05, + "loss": 0.9215, + "step": 131 + }, + { + "epoch": 0.01, + "learning_rate": 1.9928292046936117e-05, + "loss": 0.7893, + "step": 132 + }, + { + "epoch": 0.01, + "learning_rate": 1.992774880486745e-05, + "loss": 0.8567, + "step": 133 + }, + { + "epoch": 0.01, + "learning_rate": 1.9927205562798785e-05, + "loss": 0.7553, + "step": 134 + }, + { + "epoch": 0.01, + "learning_rate": 1.992666232073012e-05, + "loss": 0.8809, + "step": 135 + }, + { + "epoch": 0.01, + "learning_rate": 1.9926119078661454e-05, + "loss": 0.9166, + "step": 136 + }, + { + "epoch": 0.01, + "learning_rate": 1.9925575836592788e-05, + "loss": 1.0125, + "step": 137 + }, + { + "epoch": 0.01, + "learning_rate": 1.9925032594524122e-05, + "loss": 0.9403, + "step": 138 + }, + { + "epoch": 0.01, + "learning_rate": 1.9924489352455456e-05, + "loss": 0.795, + "step": 139 + }, + { + "epoch": 0.01, + "learning_rate": 1.992394611038679e-05, + "loss": 1.0916, + "step": 140 + }, + { + "epoch": 0.01, + "learning_rate": 1.9923402868318125e-05, + "loss": 0.9971, + "step": 141 + }, + { + "epoch": 0.01, + "learning_rate": 1.992285962624946e-05, + "loss": 0.791, + "step": 142 + }, + { + "epoch": 0.01, + "learning_rate": 1.9922316384180793e-05, + "loss": 0.7922, + "step": 143 + }, + { + "epoch": 0.01, + "learning_rate": 1.9921773142112127e-05, + "loss": 0.7871, + "step": 144 + }, + { + "epoch": 0.01, + "learning_rate": 1.992122990004346e-05, + "loss": 0.8624, + "step": 145 + }, + { + "epoch": 0.01, + "learning_rate": 1.9920686657974796e-05, + "loss": 0.9386, + "step": 146 + }, + { + "epoch": 0.01, + "learning_rate": 1.992014341590613e-05, + "loss": 0.8874, + "step": 147 + }, + { + "epoch": 0.01, + "learning_rate": 1.9919600173837464e-05, + "loss": 0.906, + "step": 148 + }, + { + "epoch": 0.01, + "learning_rate": 1.99190569317688e-05, + "loss": 0.997, + "step": 149 + }, + { + "epoch": 0.01, + "learning_rate": 1.9918513689700133e-05, + "loss": 0.8414, + "step": 150 + }, + { + "epoch": 0.01, + "learning_rate": 1.9917970447631467e-05, + "loss": 0.7943, + "step": 151 + }, + { + "epoch": 0.01, + "learning_rate": 1.99174272055628e-05, + "loss": 0.8006, + "step": 152 + }, + { + "epoch": 0.01, + "learning_rate": 1.9916883963494132e-05, + "loss": 0.8886, + "step": 153 + }, + { + "epoch": 0.01, + "learning_rate": 1.991634072142547e-05, + "loss": 0.8664, + "step": 154 + }, + { + "epoch": 0.01, + "learning_rate": 1.99157974793568e-05, + "loss": 0.8159, + "step": 155 + }, + { + "epoch": 0.01, + "learning_rate": 1.9915254237288138e-05, + "loss": 0.7381, + "step": 156 + }, + { + "epoch": 0.01, + "learning_rate": 1.991471099521947e-05, + "loss": 0.9337, + "step": 157 + }, + { + "epoch": 0.01, + "learning_rate": 1.9914167753150807e-05, + "loss": 0.7965, + "step": 158 + }, + { + "epoch": 0.01, + "learning_rate": 1.9913624511082138e-05, + "loss": 0.8798, + "step": 159 + }, + { + "epoch": 0.01, + "learning_rate": 1.9913081269013475e-05, + "loss": 0.8992, + "step": 160 + }, + { + "epoch": 0.01, + "learning_rate": 1.9912538026944806e-05, + "loss": 0.794, + "step": 161 + }, + { + "epoch": 0.01, + "learning_rate": 1.9911994784876144e-05, + "loss": 0.7868, + "step": 162 + }, + { + "epoch": 0.01, + "learning_rate": 1.9911451542807478e-05, + "loss": 0.8345, + "step": 163 + }, + { + "epoch": 0.01, + "learning_rate": 1.9910908300738812e-05, + "loss": 0.8684, + "step": 164 + }, + { + "epoch": 0.01, + "learning_rate": 1.9910365058670146e-05, + "loss": 1.0885, + "step": 165 + }, + { + "epoch": 0.01, + "learning_rate": 1.990982181660148e-05, + "loss": 0.8551, + "step": 166 + }, + { + "epoch": 0.01, + "learning_rate": 1.9909278574532815e-05, + "loss": 0.7152, + "step": 167 + }, + { + "epoch": 0.01, + "learning_rate": 1.990873533246415e-05, + "loss": 1.1125, + "step": 168 + }, + { + "epoch": 0.01, + "learning_rate": 1.9908192090395483e-05, + "loss": 0.9408, + "step": 169 + }, + { + "epoch": 0.01, + "learning_rate": 1.9907648848326817e-05, + "loss": 0.9064, + "step": 170 + }, + { + "epoch": 0.01, + "learning_rate": 1.990710560625815e-05, + "loss": 0.9165, + "step": 171 + }, + { + "epoch": 0.01, + "learning_rate": 1.9906562364189483e-05, + "loss": 0.9455, + "step": 172 + }, + { + "epoch": 0.01, + "learning_rate": 1.990601912212082e-05, + "loss": 0.7726, + "step": 173 + }, + { + "epoch": 0.01, + "learning_rate": 1.990547588005215e-05, + "loss": 0.9852, + "step": 174 + }, + { + "epoch": 0.01, + "learning_rate": 1.990493263798349e-05, + "loss": 0.8031, + "step": 175 + }, + { + "epoch": 0.01, + "learning_rate": 1.990438939591482e-05, + "loss": 0.7509, + "step": 176 + }, + { + "epoch": 0.01, + "learning_rate": 1.9903846153846157e-05, + "loss": 0.7701, + "step": 177 + }, + { + "epoch": 0.01, + "learning_rate": 1.9903302911777488e-05, + "loss": 0.8205, + "step": 178 + }, + { + "epoch": 0.01, + "learning_rate": 1.9902759669708826e-05, + "loss": 0.9775, + "step": 179 + }, + { + "epoch": 0.01, + "learning_rate": 1.9902216427640156e-05, + "loss": 0.7722, + "step": 180 + }, + { + "epoch": 0.01, + "learning_rate": 1.9901673185571494e-05, + "loss": 0.851, + "step": 181 + }, + { + "epoch": 0.01, + "learning_rate": 1.9901129943502825e-05, + "loss": 0.8374, + "step": 182 + }, + { + "epoch": 0.01, + "learning_rate": 1.9900586701434162e-05, + "loss": 0.871, + "step": 183 + }, + { + "epoch": 0.01, + "learning_rate": 1.9900043459365493e-05, + "loss": 0.7405, + "step": 184 + }, + { + "epoch": 0.02, + "learning_rate": 1.989950021729683e-05, + "loss": 0.8785, + "step": 185 + }, + { + "epoch": 0.02, + "learning_rate": 1.9898956975228162e-05, + "loss": 0.7537, + "step": 186 + }, + { + "epoch": 0.02, + "learning_rate": 1.98984137331595e-05, + "loss": 0.9207, + "step": 187 + }, + { + "epoch": 0.02, + "learning_rate": 1.989787049109083e-05, + "loss": 0.7224, + "step": 188 + }, + { + "epoch": 0.02, + "learning_rate": 1.9897327249022168e-05, + "loss": 0.7836, + "step": 189 + }, + { + "epoch": 0.02, + "learning_rate": 1.98967840069535e-05, + "loss": 1.1885, + "step": 190 + }, + { + "epoch": 0.02, + "learning_rate": 1.9896240764884833e-05, + "loss": 0.7702, + "step": 191 + }, + { + "epoch": 0.02, + "learning_rate": 1.9895697522816167e-05, + "loss": 0.9196, + "step": 192 + }, + { + "epoch": 0.02, + "learning_rate": 1.98951542807475e-05, + "loss": 0.7691, + "step": 193 + }, + { + "epoch": 0.02, + "learning_rate": 1.9894611038678836e-05, + "loss": 0.8681, + "step": 194 + }, + { + "epoch": 0.02, + "learning_rate": 1.989406779661017e-05, + "loss": 0.8799, + "step": 195 + }, + { + "epoch": 0.02, + "learning_rate": 1.9893524554541504e-05, + "loss": 0.7631, + "step": 196 + }, + { + "epoch": 0.02, + "learning_rate": 1.9892981312472838e-05, + "loss": 0.7167, + "step": 197 + }, + { + "epoch": 0.02, + "learning_rate": 1.9892438070404173e-05, + "loss": 1.0347, + "step": 198 + }, + { + "epoch": 0.02, + "learning_rate": 1.9891894828335507e-05, + "loss": 0.7422, + "step": 199 + }, + { + "epoch": 0.02, + "learning_rate": 1.9891351586266844e-05, + "loss": 0.8179, + "step": 200 + }, + { + "epoch": 0.02, + "learning_rate": 1.9890808344198175e-05, + "loss": 0.9887, + "step": 201 + }, + { + "epoch": 0.02, + "learning_rate": 1.9890265102129513e-05, + "loss": 0.758, + "step": 202 + }, + { + "epoch": 0.02, + "learning_rate": 1.9889721860060844e-05, + "loss": 0.8058, + "step": 203 + }, + { + "epoch": 0.02, + "learning_rate": 1.988917861799218e-05, + "loss": 0.8537, + "step": 204 + }, + { + "epoch": 0.02, + "learning_rate": 1.9888635375923512e-05, + "loss": 0.7165, + "step": 205 + }, + { + "epoch": 0.02, + "learning_rate": 1.988809213385485e-05, + "loss": 0.9672, + "step": 206 + }, + { + "epoch": 0.02, + "learning_rate": 1.988754889178618e-05, + "loss": 0.837, + "step": 207 + }, + { + "epoch": 0.02, + "learning_rate": 1.9887005649717518e-05, + "loss": 0.831, + "step": 208 + }, + { + "epoch": 0.02, + "learning_rate": 1.988646240764885e-05, + "loss": 0.7337, + "step": 209 + }, + { + "epoch": 0.02, + "learning_rate": 1.9885919165580183e-05, + "loss": 0.909, + "step": 210 + }, + { + "epoch": 0.02, + "learning_rate": 1.9885375923511518e-05, + "loss": 0.8982, + "step": 211 + }, + { + "epoch": 0.02, + "learning_rate": 1.9884832681442852e-05, + "loss": 0.8102, + "step": 212 + }, + { + "epoch": 0.02, + "learning_rate": 1.9884289439374186e-05, + "loss": 0.8551, + "step": 213 + }, + { + "epoch": 0.02, + "learning_rate": 1.988374619730552e-05, + "loss": 0.6812, + "step": 214 + }, + { + "epoch": 0.02, + "learning_rate": 1.9883202955236854e-05, + "loss": 0.9283, + "step": 215 + }, + { + "epoch": 0.02, + "learning_rate": 1.988265971316819e-05, + "loss": 0.876, + "step": 216 + }, + { + "epoch": 0.02, + "learning_rate": 1.9882116471099523e-05, + "loss": 0.9083, + "step": 217 + }, + { + "epoch": 0.02, + "learning_rate": 1.9881573229030857e-05, + "loss": 0.6692, + "step": 218 + }, + { + "epoch": 0.02, + "learning_rate": 1.988102998696219e-05, + "loss": 0.6703, + "step": 219 + }, + { + "epoch": 0.02, + "learning_rate": 1.9880486744893526e-05, + "loss": 0.6685, + "step": 220 + }, + { + "epoch": 0.02, + "learning_rate": 1.987994350282486e-05, + "loss": 0.7924, + "step": 221 + }, + { + "epoch": 0.02, + "learning_rate": 1.9879400260756194e-05, + "loss": 0.7155, + "step": 222 + }, + { + "epoch": 0.02, + "learning_rate": 1.9878857018687528e-05, + "loss": 0.8826, + "step": 223 + }, + { + "epoch": 0.02, + "learning_rate": 1.9878313776618863e-05, + "loss": 0.8265, + "step": 224 + }, + { + "epoch": 0.02, + "learning_rate": 1.9877770534550197e-05, + "loss": 0.5999, + "step": 225 + }, + { + "epoch": 0.02, + "learning_rate": 1.987722729248153e-05, + "loss": 0.6787, + "step": 226 + }, + { + "epoch": 0.02, + "learning_rate": 1.9876684050412865e-05, + "loss": 0.9791, + "step": 227 + }, + { + "epoch": 0.02, + "learning_rate": 1.98761408083442e-05, + "loss": 0.6703, + "step": 228 + }, + { + "epoch": 0.02, + "learning_rate": 1.9875597566275534e-05, + "loss": 0.9606, + "step": 229 + }, + { + "epoch": 0.02, + "learning_rate": 1.9875054324206868e-05, + "loss": 0.7758, + "step": 230 + }, + { + "epoch": 0.02, + "learning_rate": 1.9874511082138202e-05, + "loss": 0.8737, + "step": 231 + }, + { + "epoch": 0.02, + "learning_rate": 1.9873967840069536e-05, + "loss": 0.7034, + "step": 232 + }, + { + "epoch": 0.02, + "learning_rate": 1.987342459800087e-05, + "loss": 0.9797, + "step": 233 + }, + { + "epoch": 0.02, + "learning_rate": 1.9872881355932205e-05, + "loss": 0.5927, + "step": 234 + }, + { + "epoch": 0.02, + "learning_rate": 1.987233811386354e-05, + "loss": 0.7227, + "step": 235 + }, + { + "epoch": 0.02, + "learning_rate": 1.9871794871794873e-05, + "loss": 0.8585, + "step": 236 + }, + { + "epoch": 0.02, + "learning_rate": 1.9871251629726207e-05, + "loss": 0.6172, + "step": 237 + }, + { + "epoch": 0.02, + "learning_rate": 1.9870708387657542e-05, + "loss": 0.8129, + "step": 238 + }, + { + "epoch": 0.02, + "learning_rate": 1.9870165145588876e-05, + "loss": 0.9095, + "step": 239 + }, + { + "epoch": 0.02, + "learning_rate": 1.986962190352021e-05, + "loss": 0.6492, + "step": 240 + }, + { + "epoch": 0.02, + "learning_rate": 1.9869078661451544e-05, + "loss": 0.7003, + "step": 241 + }, + { + "epoch": 0.02, + "learning_rate": 1.986853541938288e-05, + "loss": 0.883, + "step": 242 + }, + { + "epoch": 0.02, + "learning_rate": 1.9867992177314213e-05, + "loss": 0.8862, + "step": 243 + }, + { + "epoch": 0.02, + "learning_rate": 1.9867448935245547e-05, + "loss": 0.6033, + "step": 244 + }, + { + "epoch": 0.02, + "learning_rate": 1.986690569317688e-05, + "loss": 0.6449, + "step": 245 + }, + { + "epoch": 0.02, + "learning_rate": 1.9866362451108216e-05, + "loss": 0.8985, + "step": 246 + }, + { + "epoch": 0.02, + "learning_rate": 1.986581920903955e-05, + "loss": 0.7548, + "step": 247 + }, + { + "epoch": 0.02, + "learning_rate": 1.9865275966970884e-05, + "loss": 0.7803, + "step": 248 + }, + { + "epoch": 0.02, + "learning_rate": 1.9864732724902218e-05, + "loss": 0.6449, + "step": 249 + }, + { + "epoch": 0.02, + "learning_rate": 1.9864189482833552e-05, + "loss": 0.7681, + "step": 250 + }, + { + "epoch": 0.02, + "eval_accuracy": 0.6900662251655629, + "eval_loss": 0.7300400137901306, + "eval_runtime": 22.0829, + "eval_samples_per_second": 444.461, + "eval_steps_per_second": 3.487, + "step": 250 + }, + { + "epoch": 0.02, + "learning_rate": 1.9863646240764887e-05, + "loss": 0.9803, + "step": 251 + }, + { + "epoch": 0.02, + "learning_rate": 1.986310299869622e-05, + "loss": 0.6699, + "step": 252 + }, + { + "epoch": 0.02, + "learning_rate": 1.9862559756627555e-05, + "loss": 0.8609, + "step": 253 + }, + { + "epoch": 0.02, + "learning_rate": 1.986201651455889e-05, + "loss": 0.9203, + "step": 254 + }, + { + "epoch": 0.02, + "learning_rate": 1.9861473272490224e-05, + "loss": 0.7862, + "step": 255 + }, + { + "epoch": 0.02, + "learning_rate": 1.9860930030421558e-05, + "loss": 0.8642, + "step": 256 + }, + { + "epoch": 0.02, + "learning_rate": 1.9860386788352892e-05, + "loss": 0.7131, + "step": 257 + }, + { + "epoch": 0.02, + "learning_rate": 1.9859843546284226e-05, + "loss": 0.7109, + "step": 258 + }, + { + "epoch": 0.02, + "learning_rate": 1.985930030421556e-05, + "loss": 0.7201, + "step": 259 + }, + { + "epoch": 0.02, + "learning_rate": 1.9858757062146895e-05, + "loss": 0.8511, + "step": 260 + }, + { + "epoch": 0.02, + "learning_rate": 1.985821382007823e-05, + "loss": 0.7901, + "step": 261 + }, + { + "epoch": 0.02, + "learning_rate": 1.9857670578009563e-05, + "loss": 0.8022, + "step": 262 + }, + { + "epoch": 0.02, + "learning_rate": 1.9857127335940897e-05, + "loss": 0.5882, + "step": 263 + }, + { + "epoch": 0.02, + "learning_rate": 1.9856584093872232e-05, + "loss": 0.8088, + "step": 264 + }, + { + "epoch": 0.02, + "learning_rate": 1.9856040851803566e-05, + "loss": 0.7057, + "step": 265 + }, + { + "epoch": 0.02, + "learning_rate": 1.98554976097349e-05, + "loss": 0.8611, + "step": 266 + }, + { + "epoch": 0.02, + "learning_rate": 1.985495436766623e-05, + "loss": 0.6969, + "step": 267 + }, + { + "epoch": 0.02, + "learning_rate": 1.985441112559757e-05, + "loss": 0.6093, + "step": 268 + }, + { + "epoch": 0.02, + "learning_rate": 1.98538678835289e-05, + "loss": 0.6539, + "step": 269 + }, + { + "epoch": 0.02, + "learning_rate": 1.9853324641460237e-05, + "loss": 0.7438, + "step": 270 + }, + { + "epoch": 0.02, + "learning_rate": 1.985278139939157e-05, + "loss": 0.8373, + "step": 271 + }, + { + "epoch": 0.02, + "learning_rate": 1.9852238157322906e-05, + "loss": 0.6291, + "step": 272 + }, + { + "epoch": 0.02, + "learning_rate": 1.985169491525424e-05, + "loss": 0.867, + "step": 273 + }, + { + "epoch": 0.02, + "learning_rate": 1.9851151673185574e-05, + "loss": 0.7564, + "step": 274 + }, + { + "epoch": 0.02, + "learning_rate": 1.9850608431116908e-05, + "loss": 0.7434, + "step": 275 + }, + { + "epoch": 0.02, + "learning_rate": 1.9850065189048242e-05, + "loss": 0.6696, + "step": 276 + }, + { + "epoch": 0.02, + "learning_rate": 1.9849521946979577e-05, + "loss": 0.6768, + "step": 277 + }, + { + "epoch": 0.02, + "learning_rate": 1.984897870491091e-05, + "loss": 0.7563, + "step": 278 + }, + { + "epoch": 0.02, + "learning_rate": 1.9848435462842245e-05, + "loss": 0.8436, + "step": 279 + }, + { + "epoch": 0.02, + "learning_rate": 1.984789222077358e-05, + "loss": 0.6888, + "step": 280 + }, + { + "epoch": 0.02, + "learning_rate": 1.9847348978704914e-05, + "loss": 0.7609, + "step": 281 + }, + { + "epoch": 0.02, + "learning_rate": 1.9846805736636248e-05, + "loss": 0.9214, + "step": 282 + }, + { + "epoch": 0.02, + "learning_rate": 1.9846262494567582e-05, + "loss": 0.6908, + "step": 283 + }, + { + "epoch": 0.02, + "learning_rate": 1.9845719252498916e-05, + "loss": 0.7739, + "step": 284 + }, + { + "epoch": 0.02, + "learning_rate": 1.984517601043025e-05, + "loss": 0.7183, + "step": 285 + }, + { + "epoch": 0.02, + "learning_rate": 1.984463276836158e-05, + "loss": 0.6685, + "step": 286 + }, + { + "epoch": 0.02, + "learning_rate": 1.984408952629292e-05, + "loss": 0.7953, + "step": 287 + }, + { + "epoch": 0.02, + "learning_rate": 1.984354628422425e-05, + "loss": 0.7565, + "step": 288 + }, + { + "epoch": 0.02, + "learning_rate": 1.9843003042155587e-05, + "loss": 0.6124, + "step": 289 + }, + { + "epoch": 0.02, + "learning_rate": 1.984245980008692e-05, + "loss": 0.7843, + "step": 290 + }, + { + "epoch": 0.02, + "learning_rate": 1.9841916558018256e-05, + "loss": 0.6882, + "step": 291 + }, + { + "epoch": 0.02, + "learning_rate": 1.9841373315949587e-05, + "loss": 0.7067, + "step": 292 + }, + { + "epoch": 0.02, + "learning_rate": 1.9840830073880924e-05, + "loss": 0.6197, + "step": 293 + }, + { + "epoch": 0.02, + "learning_rate": 1.9840286831812255e-05, + "loss": 0.6436, + "step": 294 + }, + { + "epoch": 0.02, + "learning_rate": 1.9839743589743593e-05, + "loss": 0.7491, + "step": 295 + }, + { + "epoch": 0.02, + "learning_rate": 1.9839200347674924e-05, + "loss": 0.6979, + "step": 296 + }, + { + "epoch": 0.02, + "learning_rate": 1.983865710560626e-05, + "loss": 0.7317, + "step": 297 + }, + { + "epoch": 0.02, + "learning_rate": 1.9838113863537592e-05, + "loss": 0.8445, + "step": 298 + }, + { + "epoch": 0.02, + "learning_rate": 1.983757062146893e-05, + "loss": 0.6775, + "step": 299 + }, + { + "epoch": 0.02, + "learning_rate": 1.983702737940026e-05, + "loss": 0.6602, + "step": 300 + }, + { + "epoch": 0.02, + "learning_rate": 1.9836484137331598e-05, + "loss": 0.6817, + "step": 301 + }, + { + "epoch": 0.02, + "learning_rate": 1.983594089526293e-05, + "loss": 0.6051, + "step": 302 + }, + { + "epoch": 0.02, + "learning_rate": 1.9835397653194267e-05, + "loss": 0.8434, + "step": 303 + }, + { + "epoch": 0.02, + "learning_rate": 1.9834854411125598e-05, + "loss": 0.5729, + "step": 304 + }, + { + "epoch": 0.02, + "learning_rate": 1.9834311169056932e-05, + "loss": 0.9013, + "step": 305 + }, + { + "epoch": 0.02, + "learning_rate": 1.9833767926988266e-05, + "loss": 0.8052, + "step": 306 + }, + { + "epoch": 0.03, + "learning_rate": 1.98332246849196e-05, + "loss": 0.7457, + "step": 307 + }, + { + "epoch": 0.03, + "learning_rate": 1.9832681442850938e-05, + "loss": 0.7791, + "step": 308 + }, + { + "epoch": 0.03, + "learning_rate": 1.983213820078227e-05, + "loss": 0.5341, + "step": 309 + }, + { + "epoch": 0.03, + "learning_rate": 1.9831594958713606e-05, + "loss": 0.8178, + "step": 310 + }, + { + "epoch": 0.03, + "learning_rate": 1.9831051716644937e-05, + "loss": 0.8537, + "step": 311 + }, + { + "epoch": 0.03, + "learning_rate": 1.9830508474576275e-05, + "loss": 0.9952, + "step": 312 + }, + { + "epoch": 0.03, + "learning_rate": 1.9829965232507606e-05, + "loss": 0.6259, + "step": 313 + }, + { + "epoch": 0.03, + "learning_rate": 1.9829421990438943e-05, + "loss": 0.9248, + "step": 314 + }, + { + "epoch": 0.03, + "learning_rate": 1.9828878748370274e-05, + "loss": 0.8696, + "step": 315 + }, + { + "epoch": 0.03, + "learning_rate": 1.9828335506301612e-05, + "loss": 0.8679, + "step": 316 + }, + { + "epoch": 0.03, + "learning_rate": 1.9827792264232943e-05, + "loss": 0.6445, + "step": 317 + }, + { + "epoch": 0.03, + "learning_rate": 1.982724902216428e-05, + "loss": 0.714, + "step": 318 + }, + { + "epoch": 0.03, + "learning_rate": 1.982670578009561e-05, + "loss": 0.7797, + "step": 319 + }, + { + "epoch": 0.03, + "learning_rate": 1.982616253802695e-05, + "loss": 0.8714, + "step": 320 + }, + { + "epoch": 0.03, + "learning_rate": 1.982561929595828e-05, + "loss": 0.8408, + "step": 321 + }, + { + "epoch": 0.03, + "learning_rate": 1.9825076053889617e-05, + "loss": 0.7293, + "step": 322 + }, + { + "epoch": 0.03, + "learning_rate": 1.9824532811820948e-05, + "loss": 0.5362, + "step": 323 + }, + { + "epoch": 0.03, + "learning_rate": 1.9823989569752282e-05, + "loss": 0.8123, + "step": 324 + }, + { + "epoch": 0.03, + "learning_rate": 1.9823446327683616e-05, + "loss": 1.0432, + "step": 325 + }, + { + "epoch": 0.03, + "learning_rate": 1.982290308561495e-05, + "loss": 0.7437, + "step": 326 + }, + { + "epoch": 0.03, + "learning_rate": 1.9822359843546285e-05, + "loss": 0.6503, + "step": 327 + }, + { + "epoch": 0.03, + "learning_rate": 1.982181660147762e-05, + "loss": 0.804, + "step": 328 + }, + { + "epoch": 0.03, + "learning_rate": 1.9821273359408953e-05, + "loss": 0.7143, + "step": 329 + }, + { + "epoch": 0.03, + "learning_rate": 1.9820730117340288e-05, + "loss": 0.852, + "step": 330 + }, + { + "epoch": 0.03, + "learning_rate": 1.9820186875271622e-05, + "loss": 0.6282, + "step": 331 + }, + { + "epoch": 0.03, + "learning_rate": 1.9819643633202956e-05, + "loss": 0.6539, + "step": 332 + }, + { + "epoch": 0.03, + "learning_rate": 1.981910039113429e-05, + "loss": 0.6911, + "step": 333 + }, + { + "epoch": 0.03, + "learning_rate": 1.9818557149065624e-05, + "loss": 0.5965, + "step": 334 + }, + { + "epoch": 0.03, + "learning_rate": 1.981801390699696e-05, + "loss": 0.6933, + "step": 335 + }, + { + "epoch": 0.03, + "learning_rate": 1.9817470664928293e-05, + "loss": 0.9643, + "step": 336 + }, + { + "epoch": 0.03, + "learning_rate": 1.9816927422859627e-05, + "loss": 0.6225, + "step": 337 + }, + { + "epoch": 0.03, + "learning_rate": 1.981638418079096e-05, + "loss": 0.7217, + "step": 338 + }, + { + "epoch": 0.03, + "learning_rate": 1.9815840938722296e-05, + "loss": 0.7064, + "step": 339 + }, + { + "epoch": 0.03, + "learning_rate": 1.981529769665363e-05, + "loss": 0.6711, + "step": 340 + }, + { + "epoch": 0.03, + "learning_rate": 1.9814754454584964e-05, + "loss": 0.7387, + "step": 341 + }, + { + "epoch": 0.03, + "learning_rate": 1.98142112125163e-05, + "loss": 0.7857, + "step": 342 + }, + { + "epoch": 0.03, + "learning_rate": 1.9813667970447633e-05, + "loss": 0.8362, + "step": 343 + }, + { + "epoch": 0.03, + "learning_rate": 1.9813124728378967e-05, + "loss": 0.7445, + "step": 344 + }, + { + "epoch": 0.03, + "learning_rate": 1.98125814863103e-05, + "loss": 0.7378, + "step": 345 + }, + { + "epoch": 0.03, + "learning_rate": 1.9812038244241635e-05, + "loss": 0.783, + "step": 346 + }, + { + "epoch": 0.03, + "learning_rate": 1.981149500217297e-05, + "loss": 0.6446, + "step": 347 + }, + { + "epoch": 0.03, + "learning_rate": 1.9810951760104304e-05, + "loss": 0.6904, + "step": 348 + }, + { + "epoch": 0.03, + "learning_rate": 1.9810408518035638e-05, + "loss": 1.0616, + "step": 349 + }, + { + "epoch": 0.03, + "learning_rate": 1.9809865275966972e-05, + "loss": 0.4595, + "step": 350 + }, + { + "epoch": 0.03, + "learning_rate": 1.9809322033898306e-05, + "loss": 0.7128, + "step": 351 + }, + { + "epoch": 0.03, + "learning_rate": 1.980877879182964e-05, + "loss": 0.6523, + "step": 352 + }, + { + "epoch": 0.03, + "learning_rate": 1.9808235549760975e-05, + "loss": 0.5864, + "step": 353 + }, + { + "epoch": 0.03, + "learning_rate": 1.980769230769231e-05, + "loss": 0.6995, + "step": 354 + }, + { + "epoch": 0.03, + "learning_rate": 1.9807149065623643e-05, + "loss": 0.7703, + "step": 355 + }, + { + "epoch": 0.03, + "learning_rate": 1.9806605823554978e-05, + "loss": 0.7071, + "step": 356 + }, + { + "epoch": 0.03, + "learning_rate": 1.9806062581486312e-05, + "loss": 0.7023, + "step": 357 + }, + { + "epoch": 0.03, + "learning_rate": 1.9805519339417646e-05, + "loss": 0.6546, + "step": 358 + }, + { + "epoch": 0.03, + "learning_rate": 1.980497609734898e-05, + "loss": 0.4423, + "step": 359 + }, + { + "epoch": 0.03, + "learning_rate": 1.9804432855280314e-05, + "loss": 0.629, + "step": 360 + }, + { + "epoch": 0.03, + "learning_rate": 1.980388961321165e-05, + "loss": 0.6205, + "step": 361 + }, + { + "epoch": 0.03, + "learning_rate": 1.9803346371142983e-05, + "loss": 0.607, + "step": 362 + }, + { + "epoch": 0.03, + "learning_rate": 1.9802803129074317e-05, + "loss": 0.6556, + "step": 363 + }, + { + "epoch": 0.03, + "learning_rate": 1.980225988700565e-05, + "loss": 0.8462, + "step": 364 + }, + { + "epoch": 0.03, + "learning_rate": 1.9801716644936986e-05, + "loss": 0.4445, + "step": 365 + }, + { + "epoch": 0.03, + "learning_rate": 1.980117340286832e-05, + "loss": 0.8247, + "step": 366 + }, + { + "epoch": 0.03, + "learning_rate": 1.9800630160799654e-05, + "loss": 0.7514, + "step": 367 + }, + { + "epoch": 0.03, + "learning_rate": 1.980008691873099e-05, + "loss": 0.5586, + "step": 368 + }, + { + "epoch": 0.03, + "learning_rate": 1.9799543676662323e-05, + "loss": 0.5623, + "step": 369 + }, + { + "epoch": 0.03, + "learning_rate": 1.9799000434593657e-05, + "loss": 0.7091, + "step": 370 + }, + { + "epoch": 0.03, + "learning_rate": 1.979845719252499e-05, + "loss": 0.5635, + "step": 371 + }, + { + "epoch": 0.03, + "learning_rate": 1.9797913950456325e-05, + "loss": 0.7408, + "step": 372 + }, + { + "epoch": 0.03, + "learning_rate": 1.979737070838766e-05, + "loss": 0.689, + "step": 373 + }, + { + "epoch": 0.03, + "learning_rate": 1.9796827466318994e-05, + "loss": 0.8272, + "step": 374 + }, + { + "epoch": 0.03, + "learning_rate": 1.9796284224250328e-05, + "loss": 0.7764, + "step": 375 + }, + { + "epoch": 0.03, + "learning_rate": 1.9795740982181662e-05, + "loss": 0.7204, + "step": 376 + }, + { + "epoch": 0.03, + "learning_rate": 1.9795197740112996e-05, + "loss": 0.5198, + "step": 377 + }, + { + "epoch": 0.03, + "learning_rate": 1.979465449804433e-05, + "loss": 0.8022, + "step": 378 + }, + { + "epoch": 0.03, + "learning_rate": 1.9794111255975665e-05, + "loss": 0.9071, + "step": 379 + }, + { + "epoch": 0.03, + "learning_rate": 1.9793568013907e-05, + "loss": 0.7847, + "step": 380 + }, + { + "epoch": 0.03, + "learning_rate": 1.9793024771838333e-05, + "loss": 0.5623, + "step": 381 + }, + { + "epoch": 0.03, + "learning_rate": 1.9792481529769668e-05, + "loss": 0.5361, + "step": 382 + }, + { + "epoch": 0.03, + "learning_rate": 1.9791938287701002e-05, + "loss": 0.8713, + "step": 383 + }, + { + "epoch": 0.03, + "learning_rate": 1.9791395045632336e-05, + "loss": 0.9373, + "step": 384 + }, + { + "epoch": 0.03, + "learning_rate": 1.979085180356367e-05, + "loss": 1.0454, + "step": 385 + }, + { + "epoch": 0.03, + "learning_rate": 1.9790308561495004e-05, + "loss": 0.7797, + "step": 386 + }, + { + "epoch": 0.03, + "learning_rate": 1.978976531942634e-05, + "loss": 0.5922, + "step": 387 + }, + { + "epoch": 0.03, + "learning_rate": 1.9789222077357673e-05, + "loss": 0.7548, + "step": 388 + }, + { + "epoch": 0.03, + "learning_rate": 1.9788678835289007e-05, + "loss": 0.7508, + "step": 389 + }, + { + "epoch": 0.03, + "learning_rate": 1.978813559322034e-05, + "loss": 0.6476, + "step": 390 + }, + { + "epoch": 0.03, + "learning_rate": 1.9787592351151676e-05, + "loss": 0.5668, + "step": 391 + }, + { + "epoch": 0.03, + "learning_rate": 1.978704910908301e-05, + "loss": 0.5656, + "step": 392 + }, + { + "epoch": 0.03, + "learning_rate": 1.9786505867014344e-05, + "loss": 0.4735, + "step": 393 + }, + { + "epoch": 0.03, + "learning_rate": 1.978596262494568e-05, + "loss": 0.7537, + "step": 394 + }, + { + "epoch": 0.03, + "learning_rate": 1.9785419382877013e-05, + "loss": 0.5782, + "step": 395 + }, + { + "epoch": 0.03, + "learning_rate": 1.9784876140808347e-05, + "loss": 0.7598, + "step": 396 + }, + { + "epoch": 0.03, + "learning_rate": 1.978433289873968e-05, + "loss": 1.0561, + "step": 397 + }, + { + "epoch": 0.03, + "learning_rate": 1.9783789656671015e-05, + "loss": 0.7728, + "step": 398 + }, + { + "epoch": 0.03, + "learning_rate": 1.978324641460235e-05, + "loss": 0.689, + "step": 399 + }, + { + "epoch": 0.03, + "learning_rate": 1.978270317253368e-05, + "loss": 0.7866, + "step": 400 + }, + { + "epoch": 0.03, + "learning_rate": 1.9782159930465018e-05, + "loss": 0.6704, + "step": 401 + }, + { + "epoch": 0.03, + "learning_rate": 1.978161668839635e-05, + "loss": 0.6829, + "step": 402 + }, + { + "epoch": 0.03, + "learning_rate": 1.9781073446327686e-05, + "loss": 0.6823, + "step": 403 + }, + { + "epoch": 0.03, + "learning_rate": 1.9780530204259017e-05, + "loss": 0.5876, + "step": 404 + }, + { + "epoch": 0.03, + "learning_rate": 1.9779986962190355e-05, + "loss": 0.6992, + "step": 405 + }, + { + "epoch": 0.03, + "learning_rate": 1.9779443720121686e-05, + "loss": 0.5999, + "step": 406 + }, + { + "epoch": 0.03, + "learning_rate": 1.9778900478053023e-05, + "loss": 0.6776, + "step": 407 + }, + { + "epoch": 0.03, + "learning_rate": 1.9778357235984354e-05, + "loss": 0.6727, + "step": 408 + }, + { + "epoch": 0.03, + "learning_rate": 1.9777813993915692e-05, + "loss": 0.6992, + "step": 409 + }, + { + "epoch": 0.03, + "learning_rate": 1.9777270751847023e-05, + "loss": 0.6279, + "step": 410 + }, + { + "epoch": 0.03, + "learning_rate": 1.977672750977836e-05, + "loss": 0.6942, + "step": 411 + }, + { + "epoch": 0.03, + "learning_rate": 1.977618426770969e-05, + "loss": 0.604, + "step": 412 + }, + { + "epoch": 0.03, + "learning_rate": 1.977564102564103e-05, + "loss": 0.5131, + "step": 413 + }, + { + "epoch": 0.03, + "learning_rate": 1.977509778357236e-05, + "loss": 0.8341, + "step": 414 + }, + { + "epoch": 0.03, + "learning_rate": 1.9774554541503697e-05, + "loss": 0.6828, + "step": 415 + }, + { + "epoch": 0.03, + "learning_rate": 1.977401129943503e-05, + "loss": 0.7258, + "step": 416 + }, + { + "epoch": 0.03, + "learning_rate": 1.9773468057366366e-05, + "loss": 0.5248, + "step": 417 + }, + { + "epoch": 0.03, + "learning_rate": 1.97729248152977e-05, + "loss": 0.7579, + "step": 418 + }, + { + "epoch": 0.03, + "learning_rate": 1.977238157322903e-05, + "loss": 0.678, + "step": 419 + }, + { + "epoch": 0.03, + "learning_rate": 1.9771838331160368e-05, + "loss": 0.6224, + "step": 420 + }, + { + "epoch": 0.03, + "learning_rate": 1.97712950890917e-05, + "loss": 0.6278, + "step": 421 + }, + { + "epoch": 0.03, + "learning_rate": 1.9770751847023037e-05, + "loss": 0.6973, + "step": 422 + }, + { + "epoch": 0.03, + "learning_rate": 1.9770208604954368e-05, + "loss": 0.5828, + "step": 423 + }, + { + "epoch": 0.03, + "learning_rate": 1.9769665362885705e-05, + "loss": 0.8476, + "step": 424 + }, + { + "epoch": 0.03, + "learning_rate": 1.9769122120817036e-05, + "loss": 0.6724, + "step": 425 + }, + { + "epoch": 0.03, + "learning_rate": 1.9768578878748374e-05, + "loss": 0.6743, + "step": 426 + }, + { + "epoch": 0.03, + "learning_rate": 1.9768035636679705e-05, + "loss": 0.689, + "step": 427 + }, + { + "epoch": 0.03, + "learning_rate": 1.9767492394611042e-05, + "loss": 0.5958, + "step": 428 + }, + { + "epoch": 0.03, + "learning_rate": 1.9766949152542373e-05, + "loss": 0.801, + "step": 429 + }, + { + "epoch": 0.04, + "learning_rate": 1.976640591047371e-05, + "loss": 0.7288, + "step": 430 + }, + { + "epoch": 0.04, + "learning_rate": 1.976586266840504e-05, + "loss": 0.761, + "step": 431 + }, + { + "epoch": 0.04, + "learning_rate": 1.976531942633638e-05, + "loss": 0.9252, + "step": 432 + }, + { + "epoch": 0.04, + "learning_rate": 1.976477618426771e-05, + "loss": 0.5619, + "step": 433 + }, + { + "epoch": 0.04, + "learning_rate": 1.9764232942199048e-05, + "loss": 0.552, + "step": 434 + }, + { + "epoch": 0.04, + "learning_rate": 1.976368970013038e-05, + "loss": 0.6894, + "step": 435 + }, + { + "epoch": 0.04, + "learning_rate": 1.9763146458061716e-05, + "loss": 0.7731, + "step": 436 + }, + { + "epoch": 0.04, + "learning_rate": 1.9762603215993047e-05, + "loss": 0.7857, + "step": 437 + }, + { + "epoch": 0.04, + "learning_rate": 1.976205997392438e-05, + "loss": 0.506, + "step": 438 + }, + { + "epoch": 0.04, + "learning_rate": 1.9761516731855715e-05, + "loss": 0.848, + "step": 439 + }, + { + "epoch": 0.04, + "learning_rate": 1.976097348978705e-05, + "loss": 0.7993, + "step": 440 + }, + { + "epoch": 0.04, + "learning_rate": 1.9760430247718384e-05, + "loss": 0.6354, + "step": 441 + }, + { + "epoch": 0.04, + "learning_rate": 1.9759887005649718e-05, + "loss": 0.7054, + "step": 442 + }, + { + "epoch": 0.04, + "learning_rate": 1.9759343763581052e-05, + "loss": 0.7895, + "step": 443 + }, + { + "epoch": 0.04, + "learning_rate": 1.9758800521512386e-05, + "loss": 0.7552, + "step": 444 + }, + { + "epoch": 0.04, + "learning_rate": 1.975825727944372e-05, + "loss": 0.7685, + "step": 445 + }, + { + "epoch": 0.04, + "learning_rate": 1.9757714037375055e-05, + "loss": 0.5818, + "step": 446 + }, + { + "epoch": 0.04, + "learning_rate": 1.975717079530639e-05, + "loss": 0.7124, + "step": 447 + }, + { + "epoch": 0.04, + "learning_rate": 1.9756627553237723e-05, + "loss": 0.7611, + "step": 448 + }, + { + "epoch": 0.04, + "learning_rate": 1.9756084311169058e-05, + "loss": 0.7777, + "step": 449 + }, + { + "epoch": 0.04, + "learning_rate": 1.9755541069100392e-05, + "loss": 0.8726, + "step": 450 + }, + { + "epoch": 0.04, + "learning_rate": 1.9754997827031726e-05, + "loss": 0.8369, + "step": 451 + }, + { + "epoch": 0.04, + "learning_rate": 1.975445458496306e-05, + "loss": 0.7389, + "step": 452 + }, + { + "epoch": 0.04, + "learning_rate": 1.9753911342894398e-05, + "loss": 0.7606, + "step": 453 + }, + { + "epoch": 0.04, + "learning_rate": 1.975336810082573e-05, + "loss": 0.7867, + "step": 454 + }, + { + "epoch": 0.04, + "learning_rate": 1.9752824858757066e-05, + "loss": 0.7206, + "step": 455 + }, + { + "epoch": 0.04, + "learning_rate": 1.9752281616688397e-05, + "loss": 0.6797, + "step": 456 + }, + { + "epoch": 0.04, + "learning_rate": 1.975173837461973e-05, + "loss": 0.3584, + "step": 457 + }, + { + "epoch": 0.04, + "learning_rate": 1.9751195132551066e-05, + "loss": 0.4861, + "step": 458 + }, + { + "epoch": 0.04, + "learning_rate": 1.97506518904824e-05, + "loss": 0.7057, + "step": 459 + }, + { + "epoch": 0.04, + "learning_rate": 1.9750108648413734e-05, + "loss": 0.7861, + "step": 460 + }, + { + "epoch": 0.04, + "learning_rate": 1.974956540634507e-05, + "loss": 0.6964, + "step": 461 + }, + { + "epoch": 0.04, + "learning_rate": 1.9749022164276403e-05, + "loss": 0.8115, + "step": 462 + }, + { + "epoch": 0.04, + "learning_rate": 1.9748478922207737e-05, + "loss": 0.6457, + "step": 463 + }, + { + "epoch": 0.04, + "learning_rate": 1.974793568013907e-05, + "loss": 0.7062, + "step": 464 + }, + { + "epoch": 0.04, + "learning_rate": 1.9747392438070405e-05, + "loss": 0.6909, + "step": 465 + }, + { + "epoch": 0.04, + "learning_rate": 1.974684919600174e-05, + "loss": 0.6131, + "step": 466 + }, + { + "epoch": 0.04, + "learning_rate": 1.9746305953933074e-05, + "loss": 0.7563, + "step": 467 + }, + { + "epoch": 0.04, + "learning_rate": 1.9745762711864408e-05, + "loss": 0.6435, + "step": 468 + }, + { + "epoch": 0.04, + "learning_rate": 1.9745219469795742e-05, + "loss": 0.7767, + "step": 469 + }, + { + "epoch": 0.04, + "learning_rate": 1.9744676227727076e-05, + "loss": 0.8398, + "step": 470 + }, + { + "epoch": 0.04, + "learning_rate": 1.974413298565841e-05, + "loss": 0.8664, + "step": 471 + }, + { + "epoch": 0.04, + "learning_rate": 1.9743589743589745e-05, + "loss": 0.7152, + "step": 472 + }, + { + "epoch": 0.04, + "learning_rate": 1.974304650152108e-05, + "loss": 0.6809, + "step": 473 + }, + { + "epoch": 0.04, + "learning_rate": 1.9742503259452413e-05, + "loss": 0.5297, + "step": 474 + }, + { + "epoch": 0.04, + "learning_rate": 1.9741960017383748e-05, + "loss": 0.5892, + "step": 475 + }, + { + "epoch": 0.04, + "learning_rate": 1.9741416775315082e-05, + "loss": 0.4586, + "step": 476 + }, + { + "epoch": 0.04, + "learning_rate": 1.9740873533246416e-05, + "loss": 0.5694, + "step": 477 + }, + { + "epoch": 0.04, + "learning_rate": 1.974033029117775e-05, + "loss": 0.6983, + "step": 478 + }, + { + "epoch": 0.04, + "learning_rate": 1.9739787049109085e-05, + "loss": 0.6022, + "step": 479 + }, + { + "epoch": 0.04, + "learning_rate": 1.973924380704042e-05, + "loss": 0.6764, + "step": 480 + }, + { + "epoch": 0.04, + "learning_rate": 1.9738700564971753e-05, + "loss": 0.7204, + "step": 481 + }, + { + "epoch": 0.04, + "learning_rate": 1.9738157322903087e-05, + "loss": 0.4812, + "step": 482 + }, + { + "epoch": 0.04, + "learning_rate": 1.973761408083442e-05, + "loss": 0.4899, + "step": 483 + }, + { + "epoch": 0.04, + "learning_rate": 1.9737070838765756e-05, + "loss": 0.4671, + "step": 484 + }, + { + "epoch": 0.04, + "learning_rate": 1.973652759669709e-05, + "loss": 0.6352, + "step": 485 + }, + { + "epoch": 0.04, + "learning_rate": 1.9735984354628424e-05, + "loss": 0.4492, + "step": 486 + }, + { + "epoch": 0.04, + "learning_rate": 1.973544111255976e-05, + "loss": 0.6185, + "step": 487 + }, + { + "epoch": 0.04, + "learning_rate": 1.9734897870491093e-05, + "loss": 0.4863, + "step": 488 + }, + { + "epoch": 0.04, + "learning_rate": 1.9734354628422427e-05, + "loss": 0.7641, + "step": 489 + }, + { + "epoch": 0.04, + "learning_rate": 1.973381138635376e-05, + "loss": 0.7428, + "step": 490 + }, + { + "epoch": 0.04, + "learning_rate": 1.9733268144285095e-05, + "loss": 0.5593, + "step": 491 + }, + { + "epoch": 0.04, + "learning_rate": 1.973272490221643e-05, + "loss": 0.5981, + "step": 492 + }, + { + "epoch": 0.04, + "learning_rate": 1.9732181660147764e-05, + "loss": 0.6674, + "step": 493 + }, + { + "epoch": 0.04, + "learning_rate": 1.9731638418079098e-05, + "loss": 0.712, + "step": 494 + }, + { + "epoch": 0.04, + "learning_rate": 1.9731095176010432e-05, + "loss": 0.6107, + "step": 495 + }, + { + "epoch": 0.04, + "learning_rate": 1.9730551933941766e-05, + "loss": 0.5568, + "step": 496 + }, + { + "epoch": 0.04, + "learning_rate": 1.97300086918731e-05, + "loss": 0.6482, + "step": 497 + }, + { + "epoch": 0.04, + "learning_rate": 1.9729465449804435e-05, + "loss": 0.4964, + "step": 498 + }, + { + "epoch": 0.04, + "learning_rate": 1.972892220773577e-05, + "loss": 0.6023, + "step": 499 + }, + { + "epoch": 0.04, + "learning_rate": 1.9728378965667103e-05, + "loss": 0.5951, + "step": 500 + }, + { + "epoch": 0.04, + "eval_accuracy": 0.7279673968415691, + "eval_loss": 0.667560338973999, + "eval_runtime": 22.3192, + "eval_samples_per_second": 439.755, + "eval_steps_per_second": 3.45, + "step": 500 + }, + { + "epoch": 0.04, + "learning_rate": 1.9727835723598438e-05, + "loss": 0.7112, + "step": 501 + }, + { + "epoch": 0.04, + "learning_rate": 1.9727292481529772e-05, + "loss": 0.9364, + "step": 502 + }, + { + "epoch": 0.04, + "learning_rate": 1.9726749239461106e-05, + "loss": 1.0185, + "step": 503 + }, + { + "epoch": 0.04, + "learning_rate": 1.972620599739244e-05, + "loss": 1.0874, + "step": 504 + }, + { + "epoch": 0.04, + "learning_rate": 1.9725662755323775e-05, + "loss": 0.9754, + "step": 505 + }, + { + "epoch": 0.04, + "learning_rate": 1.972511951325511e-05, + "loss": 0.7123, + "step": 506 + }, + { + "epoch": 0.04, + "learning_rate": 1.9724576271186443e-05, + "loss": 0.7691, + "step": 507 + }, + { + "epoch": 0.04, + "learning_rate": 1.9724033029117777e-05, + "loss": 0.9262, + "step": 508 + }, + { + "epoch": 0.04, + "learning_rate": 1.972348978704911e-05, + "loss": 0.527, + "step": 509 + }, + { + "epoch": 0.04, + "learning_rate": 1.9722946544980446e-05, + "loss": 0.7026, + "step": 510 + }, + { + "epoch": 0.04, + "learning_rate": 1.972240330291178e-05, + "loss": 0.5652, + "step": 511 + }, + { + "epoch": 0.04, + "learning_rate": 1.9721860060843114e-05, + "loss": 0.7351, + "step": 512 + }, + { + "epoch": 0.04, + "learning_rate": 1.972131681877445e-05, + "loss": 0.5063, + "step": 513 + }, + { + "epoch": 0.04, + "learning_rate": 1.972077357670578e-05, + "loss": 0.7402, + "step": 514 + }, + { + "epoch": 0.04, + "learning_rate": 1.9720230334637117e-05, + "loss": 0.8544, + "step": 515 + }, + { + "epoch": 0.04, + "learning_rate": 1.9719687092568448e-05, + "loss": 0.8122, + "step": 516 + }, + { + "epoch": 0.04, + "learning_rate": 1.9719143850499785e-05, + "loss": 0.7134, + "step": 517 + }, + { + "epoch": 0.04, + "learning_rate": 1.9718600608431116e-05, + "loss": 0.6467, + "step": 518 + }, + { + "epoch": 0.04, + "learning_rate": 1.9718057366362454e-05, + "loss": 0.3976, + "step": 519 + }, + { + "epoch": 0.04, + "learning_rate": 1.9717514124293785e-05, + "loss": 0.642, + "step": 520 + }, + { + "epoch": 0.04, + "learning_rate": 1.9716970882225122e-05, + "loss": 0.5669, + "step": 521 + }, + { + "epoch": 0.04, + "learning_rate": 1.9716427640156453e-05, + "loss": 0.7472, + "step": 522 + }, + { + "epoch": 0.04, + "learning_rate": 1.971588439808779e-05, + "loss": 0.6743, + "step": 523 + }, + { + "epoch": 0.04, + "learning_rate": 1.9715341156019125e-05, + "loss": 0.6235, + "step": 524 + }, + { + "epoch": 0.04, + "learning_rate": 1.971479791395046e-05, + "loss": 0.625, + "step": 525 + }, + { + "epoch": 0.04, + "learning_rate": 1.9714254671881793e-05, + "loss": 0.6251, + "step": 526 + }, + { + "epoch": 0.04, + "learning_rate": 1.9713711429813128e-05, + "loss": 0.5398, + "step": 527 + }, + { + "epoch": 0.04, + "learning_rate": 1.9713168187744462e-05, + "loss": 0.6666, + "step": 528 + }, + { + "epoch": 0.04, + "learning_rate": 1.9712624945675796e-05, + "loss": 0.9195, + "step": 529 + }, + { + "epoch": 0.04, + "learning_rate": 1.971208170360713e-05, + "loss": 0.6219, + "step": 530 + }, + { + "epoch": 0.04, + "learning_rate": 1.9711538461538465e-05, + "loss": 0.7601, + "step": 531 + }, + { + "epoch": 0.04, + "learning_rate": 1.97109952194698e-05, + "loss": 0.7153, + "step": 532 + }, + { + "epoch": 0.04, + "learning_rate": 1.971045197740113e-05, + "loss": 0.5615, + "step": 533 + }, + { + "epoch": 0.04, + "learning_rate": 1.9709908735332467e-05, + "loss": 0.5523, + "step": 534 + }, + { + "epoch": 0.04, + "learning_rate": 1.9709365493263798e-05, + "loss": 0.452, + "step": 535 + }, + { + "epoch": 0.04, + "learning_rate": 1.9708822251195136e-05, + "loss": 0.5117, + "step": 536 + }, + { + "epoch": 0.04, + "learning_rate": 1.9708279009126466e-05, + "loss": 0.6033, + "step": 537 + }, + { + "epoch": 0.04, + "learning_rate": 1.9707735767057804e-05, + "loss": 0.7552, + "step": 538 + }, + { + "epoch": 0.04, + "learning_rate": 1.9707192524989135e-05, + "loss": 0.5985, + "step": 539 + }, + { + "epoch": 0.04, + "learning_rate": 1.9706649282920473e-05, + "loss": 0.539, + "step": 540 + }, + { + "epoch": 0.04, + "learning_rate": 1.9706106040851803e-05, + "loss": 0.5464, + "step": 541 + }, + { + "epoch": 0.04, + "learning_rate": 1.970556279878314e-05, + "loss": 0.5173, + "step": 542 + }, + { + "epoch": 0.04, + "learning_rate": 1.9705019556714472e-05, + "loss": 1.0477, + "step": 543 + }, + { + "epoch": 0.04, + "learning_rate": 1.970447631464581e-05, + "loss": 0.6325, + "step": 544 + }, + { + "epoch": 0.04, + "learning_rate": 1.970393307257714e-05, + "loss": 0.8009, + "step": 545 + }, + { + "epoch": 0.04, + "learning_rate": 1.9703389830508478e-05, + "loss": 0.9291, + "step": 546 + }, + { + "epoch": 0.04, + "learning_rate": 1.970284658843981e-05, + "loss": 0.6964, + "step": 547 + }, + { + "epoch": 0.04, + "learning_rate": 1.9702303346371146e-05, + "loss": 0.6352, + "step": 548 + }, + { + "epoch": 0.04, + "learning_rate": 1.9701760104302477e-05, + "loss": 0.7077, + "step": 549 + }, + { + "epoch": 0.04, + "learning_rate": 1.9701216862233815e-05, + "loss": 0.4822, + "step": 550 + }, + { + "epoch": 0.04, + "learning_rate": 1.9700673620165146e-05, + "loss": 0.6762, + "step": 551 + }, + { + "epoch": 0.04, + "learning_rate": 1.970013037809648e-05, + "loss": 0.8356, + "step": 552 + }, + { + "epoch": 0.05, + "learning_rate": 1.9699587136027814e-05, + "loss": 0.6773, + "step": 553 + }, + { + "epoch": 0.05, + "learning_rate": 1.969904389395915e-05, + "loss": 0.5769, + "step": 554 + }, + { + "epoch": 0.05, + "learning_rate": 1.9698500651890483e-05, + "loss": 0.5754, + "step": 555 + }, + { + "epoch": 0.05, + "learning_rate": 1.9697957409821817e-05, + "loss": 0.777, + "step": 556 + }, + { + "epoch": 0.05, + "learning_rate": 1.969741416775315e-05, + "loss": 1.0215, + "step": 557 + }, + { + "epoch": 0.05, + "learning_rate": 1.9696870925684485e-05, + "loss": 0.7264, + "step": 558 + }, + { + "epoch": 0.05, + "learning_rate": 1.969632768361582e-05, + "loss": 0.7704, + "step": 559 + }, + { + "epoch": 0.05, + "learning_rate": 1.9695784441547154e-05, + "loss": 0.7202, + "step": 560 + }, + { + "epoch": 0.05, + "learning_rate": 1.969524119947849e-05, + "loss": 0.5052, + "step": 561 + }, + { + "epoch": 0.05, + "learning_rate": 1.9694697957409822e-05, + "loss": 0.8848, + "step": 562 + }, + { + "epoch": 0.05, + "learning_rate": 1.969415471534116e-05, + "loss": 0.4963, + "step": 563 + }, + { + "epoch": 0.05, + "learning_rate": 1.969361147327249e-05, + "loss": 0.5514, + "step": 564 + }, + { + "epoch": 0.05, + "learning_rate": 1.969306823120383e-05, + "loss": 0.6518, + "step": 565 + }, + { + "epoch": 0.05, + "learning_rate": 1.969252498913516e-05, + "loss": 0.6305, + "step": 566 + }, + { + "epoch": 0.05, + "learning_rate": 1.9691981747066497e-05, + "loss": 0.7421, + "step": 567 + }, + { + "epoch": 0.05, + "learning_rate": 1.9691438504997828e-05, + "loss": 0.6698, + "step": 568 + }, + { + "epoch": 0.05, + "learning_rate": 1.9690895262929165e-05, + "loss": 0.6506, + "step": 569 + }, + { + "epoch": 0.05, + "learning_rate": 1.9690352020860496e-05, + "loss": 0.6368, + "step": 570 + }, + { + "epoch": 0.05, + "learning_rate": 1.968980877879183e-05, + "loss": 0.6664, + "step": 571 + }, + { + "epoch": 0.05, + "learning_rate": 1.9689265536723165e-05, + "loss": 0.9282, + "step": 572 + }, + { + "epoch": 0.05, + "learning_rate": 1.96887222946545e-05, + "loss": 0.7998, + "step": 573 + }, + { + "epoch": 0.05, + "learning_rate": 1.9688179052585833e-05, + "loss": 0.8224, + "step": 574 + }, + { + "epoch": 0.05, + "learning_rate": 1.9687635810517167e-05, + "loss": 0.7012, + "step": 575 + }, + { + "epoch": 0.05, + "learning_rate": 1.96870925684485e-05, + "loss": 0.7629, + "step": 576 + }, + { + "epoch": 0.05, + "learning_rate": 1.9686549326379836e-05, + "loss": 0.5599, + "step": 577 + }, + { + "epoch": 0.05, + "learning_rate": 1.968600608431117e-05, + "loss": 0.5798, + "step": 578 + }, + { + "epoch": 0.05, + "learning_rate": 1.9685462842242504e-05, + "loss": 0.5638, + "step": 579 + }, + { + "epoch": 0.05, + "learning_rate": 1.968491960017384e-05, + "loss": 0.5503, + "step": 580 + }, + { + "epoch": 0.05, + "learning_rate": 1.9684376358105173e-05, + "loss": 0.6437, + "step": 581 + }, + { + "epoch": 0.05, + "learning_rate": 1.9683833116036507e-05, + "loss": 0.6527, + "step": 582 + }, + { + "epoch": 0.05, + "learning_rate": 1.968328987396784e-05, + "loss": 0.787, + "step": 583 + }, + { + "epoch": 0.05, + "learning_rate": 1.9682746631899175e-05, + "loss": 1.0122, + "step": 584 + }, + { + "epoch": 0.05, + "learning_rate": 1.968220338983051e-05, + "loss": 0.7009, + "step": 585 + }, + { + "epoch": 0.05, + "learning_rate": 1.9681660147761844e-05, + "loss": 0.7542, + "step": 586 + }, + { + "epoch": 0.05, + "learning_rate": 1.9681116905693178e-05, + "loss": 0.7228, + "step": 587 + }, + { + "epoch": 0.05, + "learning_rate": 1.9680573663624512e-05, + "loss": 0.5553, + "step": 588 + }, + { + "epoch": 0.05, + "learning_rate": 1.9680030421555846e-05, + "loss": 0.5851, + "step": 589 + }, + { + "epoch": 0.05, + "learning_rate": 1.967948717948718e-05, + "loss": 0.754, + "step": 590 + }, + { + "epoch": 0.05, + "learning_rate": 1.9678943937418515e-05, + "loss": 0.7605, + "step": 591 + }, + { + "epoch": 0.05, + "learning_rate": 1.967840069534985e-05, + "loss": 0.5922, + "step": 592 + }, + { + "epoch": 0.05, + "learning_rate": 1.9677857453281183e-05, + "loss": 0.7331, + "step": 593 + }, + { + "epoch": 0.05, + "learning_rate": 1.9677314211212518e-05, + "loss": 0.6993, + "step": 594 + }, + { + "epoch": 0.05, + "learning_rate": 1.9676770969143852e-05, + "loss": 0.6655, + "step": 595 + }, + { + "epoch": 0.05, + "learning_rate": 1.9676227727075186e-05, + "loss": 0.4977, + "step": 596 + }, + { + "epoch": 0.05, + "learning_rate": 1.967568448500652e-05, + "loss": 0.8267, + "step": 597 + }, + { + "epoch": 0.05, + "learning_rate": 1.9675141242937855e-05, + "loss": 0.8443, + "step": 598 + }, + { + "epoch": 0.05, + "learning_rate": 1.967459800086919e-05, + "loss": 0.7182, + "step": 599 + }, + { + "epoch": 0.05, + "learning_rate": 1.9674054758800523e-05, + "loss": 0.5812, + "step": 600 + }, + { + "epoch": 0.05, + "learning_rate": 1.9673511516731857e-05, + "loss": 0.6159, + "step": 601 + }, + { + "epoch": 0.05, + "learning_rate": 1.967296827466319e-05, + "loss": 0.6691, + "step": 602 + }, + { + "epoch": 0.05, + "learning_rate": 1.9672425032594526e-05, + "loss": 0.5479, + "step": 603 + }, + { + "epoch": 0.05, + "learning_rate": 1.967188179052586e-05, + "loss": 0.5907, + "step": 604 + }, + { + "epoch": 0.05, + "learning_rate": 1.9671338548457194e-05, + "loss": 0.8359, + "step": 605 + }, + { + "epoch": 0.05, + "learning_rate": 1.967079530638853e-05, + "loss": 0.6169, + "step": 606 + }, + { + "epoch": 0.05, + "learning_rate": 1.9670252064319863e-05, + "loss": 0.596, + "step": 607 + }, + { + "epoch": 0.05, + "learning_rate": 1.9669708822251197e-05, + "loss": 0.612, + "step": 608 + }, + { + "epoch": 0.05, + "learning_rate": 1.966916558018253e-05, + "loss": 0.5902, + "step": 609 + }, + { + "epoch": 0.05, + "learning_rate": 1.9668622338113865e-05, + "loss": 0.6074, + "step": 610 + }, + { + "epoch": 0.05, + "learning_rate": 1.96680790960452e-05, + "loss": 0.5326, + "step": 611 + }, + { + "epoch": 0.05, + "learning_rate": 1.9667535853976534e-05, + "loss": 0.5052, + "step": 612 + }, + { + "epoch": 0.05, + "learning_rate": 1.9666992611907868e-05, + "loss": 0.7437, + "step": 613 + }, + { + "epoch": 0.05, + "learning_rate": 1.9666449369839202e-05, + "loss": 0.4305, + "step": 614 + }, + { + "epoch": 0.05, + "learning_rate": 1.9665906127770536e-05, + "loss": 0.7103, + "step": 615 + }, + { + "epoch": 0.05, + "learning_rate": 1.966536288570187e-05, + "loss": 0.766, + "step": 616 + }, + { + "epoch": 0.05, + "learning_rate": 1.9664819643633205e-05, + "loss": 0.6555, + "step": 617 + }, + { + "epoch": 0.05, + "learning_rate": 1.966427640156454e-05, + "loss": 0.5725, + "step": 618 + }, + { + "epoch": 0.05, + "learning_rate": 1.9663733159495873e-05, + "loss": 0.5811, + "step": 619 + }, + { + "epoch": 0.05, + "learning_rate": 1.9663189917427208e-05, + "loss": 0.6118, + "step": 620 + }, + { + "epoch": 0.05, + "learning_rate": 1.9662646675358542e-05, + "loss": 0.7033, + "step": 621 + }, + { + "epoch": 0.05, + "learning_rate": 1.9662103433289876e-05, + "loss": 0.5744, + "step": 622 + }, + { + "epoch": 0.05, + "learning_rate": 1.966156019122121e-05, + "loss": 0.7268, + "step": 623 + }, + { + "epoch": 0.05, + "learning_rate": 1.9661016949152545e-05, + "loss": 0.4759, + "step": 624 + }, + { + "epoch": 0.05, + "learning_rate": 1.966047370708388e-05, + "loss": 0.5961, + "step": 625 + }, + { + "epoch": 0.05, + "learning_rate": 1.9659930465015213e-05, + "loss": 0.668, + "step": 626 + }, + { + "epoch": 0.05, + "learning_rate": 1.9659387222946547e-05, + "loss": 0.5684, + "step": 627 + }, + { + "epoch": 0.05, + "learning_rate": 1.9658843980877878e-05, + "loss": 0.747, + "step": 628 + }, + { + "epoch": 0.05, + "learning_rate": 1.9658300738809216e-05, + "loss": 0.7079, + "step": 629 + }, + { + "epoch": 0.05, + "learning_rate": 1.9657757496740547e-05, + "loss": 0.6669, + "step": 630 + }, + { + "epoch": 0.05, + "learning_rate": 1.9657214254671884e-05, + "loss": 0.782, + "step": 631 + }, + { + "epoch": 0.05, + "learning_rate": 1.965667101260322e-05, + "loss": 0.9202, + "step": 632 + }, + { + "epoch": 0.05, + "learning_rate": 1.9656127770534553e-05, + "loss": 0.3878, + "step": 633 + }, + { + "epoch": 0.05, + "learning_rate": 1.9655584528465887e-05, + "loss": 0.5373, + "step": 634 + }, + { + "epoch": 0.05, + "learning_rate": 1.965504128639722e-05, + "loss": 0.6987, + "step": 635 + }, + { + "epoch": 0.05, + "learning_rate": 1.9654498044328555e-05, + "loss": 0.9625, + "step": 636 + }, + { + "epoch": 0.05, + "learning_rate": 1.965395480225989e-05, + "loss": 0.4174, + "step": 637 + }, + { + "epoch": 0.05, + "learning_rate": 1.9653411560191224e-05, + "loss": 0.7611, + "step": 638 + }, + { + "epoch": 0.05, + "learning_rate": 1.9652868318122558e-05, + "loss": 0.7333, + "step": 639 + }, + { + "epoch": 0.05, + "learning_rate": 1.9652325076053892e-05, + "loss": 0.3586, + "step": 640 + }, + { + "epoch": 0.05, + "learning_rate": 1.9651781833985226e-05, + "loss": 0.7532, + "step": 641 + }, + { + "epoch": 0.05, + "learning_rate": 1.965123859191656e-05, + "loss": 0.5331, + "step": 642 + }, + { + "epoch": 0.05, + "learning_rate": 1.9650695349847895e-05, + "loss": 0.8586, + "step": 643 + }, + { + "epoch": 0.05, + "learning_rate": 1.965015210777923e-05, + "loss": 0.7459, + "step": 644 + }, + { + "epoch": 0.05, + "learning_rate": 1.9649608865710563e-05, + "loss": 0.7824, + "step": 645 + }, + { + "epoch": 0.05, + "learning_rate": 1.9649065623641898e-05, + "loss": 0.8483, + "step": 646 + }, + { + "epoch": 0.05, + "learning_rate": 1.964852238157323e-05, + "loss": 0.7531, + "step": 647 + }, + { + "epoch": 0.05, + "learning_rate": 1.9647979139504566e-05, + "loss": 0.6327, + "step": 648 + }, + { + "epoch": 0.05, + "learning_rate": 1.9647435897435897e-05, + "loss": 0.9705, + "step": 649 + }, + { + "epoch": 0.05, + "learning_rate": 1.9646892655367235e-05, + "loss": 0.7427, + "step": 650 + }, + { + "epoch": 0.05, + "learning_rate": 1.9646349413298565e-05, + "loss": 0.9226, + "step": 651 + }, + { + "epoch": 0.05, + "learning_rate": 1.9645806171229903e-05, + "loss": 0.7407, + "step": 652 + }, + { + "epoch": 0.05, + "learning_rate": 1.9645262929161234e-05, + "loss": 0.8454, + "step": 653 + }, + { + "epoch": 0.05, + "learning_rate": 1.964471968709257e-05, + "loss": 0.6844, + "step": 654 + }, + { + "epoch": 0.05, + "learning_rate": 1.9644176445023902e-05, + "loss": 0.6736, + "step": 655 + }, + { + "epoch": 0.05, + "learning_rate": 1.964363320295524e-05, + "loss": 0.6804, + "step": 656 + }, + { + "epoch": 0.05, + "learning_rate": 1.964308996088657e-05, + "loss": 0.6792, + "step": 657 + }, + { + "epoch": 0.05, + "learning_rate": 1.964254671881791e-05, + "loss": 0.4993, + "step": 658 + }, + { + "epoch": 0.05, + "learning_rate": 1.964200347674924e-05, + "loss": 0.5388, + "step": 659 + }, + { + "epoch": 0.05, + "learning_rate": 1.9641460234680577e-05, + "loss": 0.6673, + "step": 660 + }, + { + "epoch": 0.05, + "learning_rate": 1.9640916992611908e-05, + "loss": 0.6699, + "step": 661 + }, + { + "epoch": 0.05, + "learning_rate": 1.9640373750543245e-05, + "loss": 0.5675, + "step": 662 + }, + { + "epoch": 0.05, + "learning_rate": 1.9639830508474576e-05, + "loss": 0.6536, + "step": 663 + }, + { + "epoch": 0.05, + "learning_rate": 1.9639287266405914e-05, + "loss": 0.9363, + "step": 664 + }, + { + "epoch": 0.05, + "learning_rate": 1.9638744024337245e-05, + "loss": 0.5159, + "step": 665 + }, + { + "epoch": 0.05, + "learning_rate": 1.963820078226858e-05, + "loss": 0.7236, + "step": 666 + }, + { + "epoch": 0.05, + "learning_rate": 1.9637657540199913e-05, + "loss": 0.7929, + "step": 667 + }, + { + "epoch": 0.05, + "learning_rate": 1.9637114298131247e-05, + "loss": 0.5275, + "step": 668 + }, + { + "epoch": 0.05, + "learning_rate": 1.9636571056062585e-05, + "loss": 0.3758, + "step": 669 + }, + { + "epoch": 0.05, + "learning_rate": 1.9636027813993916e-05, + "loss": 0.6246, + "step": 670 + }, + { + "epoch": 0.05, + "learning_rate": 1.9635484571925253e-05, + "loss": 0.4726, + "step": 671 + }, + { + "epoch": 0.05, + "learning_rate": 1.9634941329856584e-05, + "loss": 0.787, + "step": 672 + }, + { + "epoch": 0.05, + "learning_rate": 1.9634398087787922e-05, + "loss": 0.5952, + "step": 673 + }, + { + "epoch": 0.05, + "learning_rate": 1.9633854845719253e-05, + "loss": 0.5041, + "step": 674 + }, + { + "epoch": 0.06, + "learning_rate": 1.963331160365059e-05, + "loss": 0.6895, + "step": 675 + }, + { + "epoch": 0.06, + "learning_rate": 1.963276836158192e-05, + "loss": 0.5924, + "step": 676 + }, + { + "epoch": 0.06, + "learning_rate": 1.963222511951326e-05, + "loss": 0.5221, + "step": 677 + }, + { + "epoch": 0.06, + "learning_rate": 1.963168187744459e-05, + "loss": 0.7633, + "step": 678 + }, + { + "epoch": 0.06, + "learning_rate": 1.9631138635375927e-05, + "loss": 0.6329, + "step": 679 + }, + { + "epoch": 0.06, + "learning_rate": 1.9630595393307258e-05, + "loss": 0.6236, + "step": 680 + }, + { + "epoch": 0.06, + "learning_rate": 1.9630052151238596e-05, + "loss": 0.8251, + "step": 681 + }, + { + "epoch": 0.06, + "learning_rate": 1.9629508909169927e-05, + "loss": 0.6583, + "step": 682 + }, + { + "epoch": 0.06, + "learning_rate": 1.9628965667101264e-05, + "loss": 0.7033, + "step": 683 + }, + { + "epoch": 0.06, + "learning_rate": 1.9628422425032595e-05, + "loss": 0.7345, + "step": 684 + }, + { + "epoch": 0.06, + "learning_rate": 1.962787918296393e-05, + "loss": 0.5459, + "step": 685 + }, + { + "epoch": 0.06, + "learning_rate": 1.9627335940895263e-05, + "loss": 0.6488, + "step": 686 + }, + { + "epoch": 0.06, + "learning_rate": 1.9626792698826598e-05, + "loss": 0.576, + "step": 687 + }, + { + "epoch": 0.06, + "learning_rate": 1.9626249456757932e-05, + "loss": 0.5163, + "step": 688 + }, + { + "epoch": 0.06, + "learning_rate": 1.9625706214689266e-05, + "loss": 0.4676, + "step": 689 + }, + { + "epoch": 0.06, + "learning_rate": 1.96251629726206e-05, + "loss": 0.6457, + "step": 690 + }, + { + "epoch": 0.06, + "learning_rate": 1.9624619730551935e-05, + "loss": 0.7348, + "step": 691 + }, + { + "epoch": 0.06, + "learning_rate": 1.962407648848327e-05, + "loss": 0.6388, + "step": 692 + }, + { + "epoch": 0.06, + "learning_rate": 1.9623533246414603e-05, + "loss": 0.5723, + "step": 693 + }, + { + "epoch": 0.06, + "learning_rate": 1.9622990004345937e-05, + "loss": 0.6846, + "step": 694 + }, + { + "epoch": 0.06, + "learning_rate": 1.962244676227727e-05, + "loss": 0.6066, + "step": 695 + }, + { + "epoch": 0.06, + "learning_rate": 1.9621903520208606e-05, + "loss": 0.4701, + "step": 696 + }, + { + "epoch": 0.06, + "learning_rate": 1.962136027813994e-05, + "loss": 0.5486, + "step": 697 + }, + { + "epoch": 0.06, + "learning_rate": 1.9620817036071274e-05, + "loss": 0.5478, + "step": 698 + }, + { + "epoch": 0.06, + "learning_rate": 1.962027379400261e-05, + "loss": 0.4205, + "step": 699 + }, + { + "epoch": 0.06, + "learning_rate": 1.9619730551933943e-05, + "loss": 0.5412, + "step": 700 + }, + { + "epoch": 0.06, + "learning_rate": 1.9619187309865277e-05, + "loss": 0.63, + "step": 701 + }, + { + "epoch": 0.06, + "learning_rate": 1.961864406779661e-05, + "loss": 0.7051, + "step": 702 + }, + { + "epoch": 0.06, + "learning_rate": 1.9618100825727945e-05, + "loss": 0.8904, + "step": 703 + }, + { + "epoch": 0.06, + "learning_rate": 1.961755758365928e-05, + "loss": 0.6807, + "step": 704 + }, + { + "epoch": 0.06, + "learning_rate": 1.9617014341590614e-05, + "loss": 0.843, + "step": 705 + }, + { + "epoch": 0.06, + "learning_rate": 1.9616471099521948e-05, + "loss": 0.8537, + "step": 706 + }, + { + "epoch": 0.06, + "learning_rate": 1.9615927857453282e-05, + "loss": 0.5718, + "step": 707 + }, + { + "epoch": 0.06, + "learning_rate": 1.9615384615384617e-05, + "loss": 0.5054, + "step": 708 + }, + { + "epoch": 0.06, + "learning_rate": 1.961484137331595e-05, + "loss": 0.38, + "step": 709 + }, + { + "epoch": 0.06, + "learning_rate": 1.9614298131247285e-05, + "loss": 0.5757, + "step": 710 + }, + { + "epoch": 0.06, + "learning_rate": 1.961375488917862e-05, + "loss": 0.5462, + "step": 711 + }, + { + "epoch": 0.06, + "learning_rate": 1.9613211647109953e-05, + "loss": 0.8634, + "step": 712 + }, + { + "epoch": 0.06, + "learning_rate": 1.9612668405041288e-05, + "loss": 0.6201, + "step": 713 + }, + { + "epoch": 0.06, + "learning_rate": 1.9612125162972622e-05, + "loss": 0.6691, + "step": 714 + }, + { + "epoch": 0.06, + "learning_rate": 1.9611581920903956e-05, + "loss": 0.7718, + "step": 715 + }, + { + "epoch": 0.06, + "learning_rate": 1.961103867883529e-05, + "loss": 0.4618, + "step": 716 + }, + { + "epoch": 0.06, + "learning_rate": 1.9610495436766625e-05, + "loss": 0.8687, + "step": 717 + }, + { + "epoch": 0.06, + "learning_rate": 1.960995219469796e-05, + "loss": 0.9503, + "step": 718 + }, + { + "epoch": 0.06, + "learning_rate": 1.9609408952629293e-05, + "loss": 0.4214, + "step": 719 + }, + { + "epoch": 0.06, + "learning_rate": 1.9608865710560627e-05, + "loss": 0.8823, + "step": 720 + }, + { + "epoch": 0.06, + "learning_rate": 1.960832246849196e-05, + "loss": 0.5794, + "step": 721 + }, + { + "epoch": 0.06, + "learning_rate": 1.9607779226423296e-05, + "loss": 0.7299, + "step": 722 + }, + { + "epoch": 0.06, + "learning_rate": 1.960723598435463e-05, + "loss": 0.7517, + "step": 723 + }, + { + "epoch": 0.06, + "learning_rate": 1.9606692742285964e-05, + "loss": 0.5698, + "step": 724 + }, + { + "epoch": 0.06, + "learning_rate": 1.96061495002173e-05, + "loss": 0.7074, + "step": 725 + }, + { + "epoch": 0.06, + "learning_rate": 1.9605606258148633e-05, + "loss": 0.8223, + "step": 726 + }, + { + "epoch": 0.06, + "learning_rate": 1.9605063016079967e-05, + "loss": 0.4713, + "step": 727 + }, + { + "epoch": 0.06, + "learning_rate": 1.96045197740113e-05, + "loss": 0.6659, + "step": 728 + }, + { + "epoch": 0.06, + "learning_rate": 1.9603976531942635e-05, + "loss": 0.5814, + "step": 729 + }, + { + "epoch": 0.06, + "learning_rate": 1.960343328987397e-05, + "loss": 0.5326, + "step": 730 + }, + { + "epoch": 0.06, + "learning_rate": 1.9602890047805304e-05, + "loss": 0.5287, + "step": 731 + }, + { + "epoch": 0.06, + "learning_rate": 1.9602346805736638e-05, + "loss": 0.6265, + "step": 732 + }, + { + "epoch": 0.06, + "learning_rate": 1.9601803563667972e-05, + "loss": 0.5733, + "step": 733 + }, + { + "epoch": 0.06, + "learning_rate": 1.9601260321599307e-05, + "loss": 0.8394, + "step": 734 + }, + { + "epoch": 0.06, + "learning_rate": 1.960071707953064e-05, + "loss": 0.4926, + "step": 735 + }, + { + "epoch": 0.06, + "learning_rate": 1.9600173837461975e-05, + "loss": 0.8684, + "step": 736 + }, + { + "epoch": 0.06, + "learning_rate": 1.959963059539331e-05, + "loss": 0.7316, + "step": 737 + }, + { + "epoch": 0.06, + "learning_rate": 1.9599087353324643e-05, + "loss": 0.8387, + "step": 738 + }, + { + "epoch": 0.06, + "learning_rate": 1.9598544111255978e-05, + "loss": 0.5154, + "step": 739 + }, + { + "epoch": 0.06, + "learning_rate": 1.9598000869187312e-05, + "loss": 0.5699, + "step": 740 + }, + { + "epoch": 0.06, + "learning_rate": 1.9597457627118646e-05, + "loss": 0.6827, + "step": 741 + }, + { + "epoch": 0.06, + "learning_rate": 1.959691438504998e-05, + "loss": 0.8984, + "step": 742 + }, + { + "epoch": 0.06, + "learning_rate": 1.9596371142981315e-05, + "loss": 0.4523, + "step": 743 + }, + { + "epoch": 0.06, + "learning_rate": 1.959582790091265e-05, + "loss": 0.6467, + "step": 744 + }, + { + "epoch": 0.06, + "learning_rate": 1.9595284658843983e-05, + "loss": 0.7377, + "step": 745 + }, + { + "epoch": 0.06, + "learning_rate": 1.9594741416775317e-05, + "loss": 0.6295, + "step": 746 + }, + { + "epoch": 0.06, + "learning_rate": 1.959419817470665e-05, + "loss": 0.7641, + "step": 747 + }, + { + "epoch": 0.06, + "learning_rate": 1.9593654932637986e-05, + "loss": 0.6961, + "step": 748 + }, + { + "epoch": 0.06, + "learning_rate": 1.959311169056932e-05, + "loss": 0.556, + "step": 749 + }, + { + "epoch": 0.06, + "learning_rate": 1.9592568448500654e-05, + "loss": 0.6761, + "step": 750 + }, + { + "epoch": 0.06, + "eval_accuracy": 0.7399898115129904, + "eval_loss": 0.6263986825942993, + "eval_runtime": 22.2451, + "eval_samples_per_second": 441.22, + "eval_steps_per_second": 3.461, + "step": 750 + }, + { + "epoch": 0.06, + "learning_rate": 1.959202520643199e-05, + "loss": 0.5466, + "step": 751 + }, + { + "epoch": 0.06, + "learning_rate": 1.9591481964363323e-05, + "loss": 0.6721, + "step": 752 + }, + { + "epoch": 0.06, + "learning_rate": 1.9590938722294657e-05, + "loss": 0.7045, + "step": 753 + }, + { + "epoch": 0.06, + "learning_rate": 1.959039548022599e-05, + "loss": 0.5183, + "step": 754 + }, + { + "epoch": 0.06, + "learning_rate": 1.9589852238157325e-05, + "loss": 0.5654, + "step": 755 + }, + { + "epoch": 0.06, + "learning_rate": 1.958930899608866e-05, + "loss": 0.7939, + "step": 756 + }, + { + "epoch": 0.06, + "learning_rate": 1.9588765754019994e-05, + "loss": 0.6849, + "step": 757 + }, + { + "epoch": 0.06, + "learning_rate": 1.9588222511951328e-05, + "loss": 0.8148, + "step": 758 + }, + { + "epoch": 0.06, + "learning_rate": 1.9587679269882662e-05, + "loss": 0.5829, + "step": 759 + }, + { + "epoch": 0.06, + "learning_rate": 1.9587136027813997e-05, + "loss": 0.8231, + "step": 760 + }, + { + "epoch": 0.06, + "learning_rate": 1.9586592785745327e-05, + "loss": 0.637, + "step": 761 + }, + { + "epoch": 0.06, + "learning_rate": 1.9586049543676665e-05, + "loss": 0.6072, + "step": 762 + }, + { + "epoch": 0.06, + "learning_rate": 1.9585506301607996e-05, + "loss": 0.6819, + "step": 763 + }, + { + "epoch": 0.06, + "learning_rate": 1.9584963059539333e-05, + "loss": 0.7416, + "step": 764 + }, + { + "epoch": 0.06, + "learning_rate": 1.9584419817470664e-05, + "loss": 0.6053, + "step": 765 + }, + { + "epoch": 0.06, + "learning_rate": 1.9583876575402002e-05, + "loss": 0.6926, + "step": 766 + }, + { + "epoch": 0.06, + "learning_rate": 1.9583333333333333e-05, + "loss": 0.5123, + "step": 767 + }, + { + "epoch": 0.06, + "learning_rate": 1.958279009126467e-05, + "loss": 0.8372, + "step": 768 + }, + { + "epoch": 0.06, + "learning_rate": 1.9582246849196e-05, + "loss": 0.7687, + "step": 769 + }, + { + "epoch": 0.06, + "learning_rate": 1.958170360712734e-05, + "loss": 0.4283, + "step": 770 + }, + { + "epoch": 0.06, + "learning_rate": 1.958116036505867e-05, + "loss": 0.3922, + "step": 771 + }, + { + "epoch": 0.06, + "learning_rate": 1.9580617122990007e-05, + "loss": 0.6364, + "step": 772 + }, + { + "epoch": 0.06, + "learning_rate": 1.9580073880921338e-05, + "loss": 0.6181, + "step": 773 + }, + { + "epoch": 0.06, + "learning_rate": 1.9579530638852676e-05, + "loss": 0.7285, + "step": 774 + }, + { + "epoch": 0.06, + "learning_rate": 1.9578987396784007e-05, + "loss": 0.7714, + "step": 775 + }, + { + "epoch": 0.06, + "learning_rate": 1.9578444154715344e-05, + "loss": 0.5998, + "step": 776 + }, + { + "epoch": 0.06, + "learning_rate": 1.957790091264668e-05, + "loss": 0.7579, + "step": 777 + }, + { + "epoch": 0.06, + "learning_rate": 1.9577357670578013e-05, + "loss": 0.7286, + "step": 778 + }, + { + "epoch": 0.06, + "learning_rate": 1.9576814428509347e-05, + "loss": 0.6914, + "step": 779 + }, + { + "epoch": 0.06, + "learning_rate": 1.9576271186440678e-05, + "loss": 0.783, + "step": 780 + }, + { + "epoch": 0.06, + "learning_rate": 1.9575727944372015e-05, + "loss": 0.4694, + "step": 781 + }, + { + "epoch": 0.06, + "learning_rate": 1.9575184702303346e-05, + "loss": 0.6576, + "step": 782 + }, + { + "epoch": 0.06, + "learning_rate": 1.9574641460234684e-05, + "loss": 0.7959, + "step": 783 + }, + { + "epoch": 0.06, + "learning_rate": 1.9574098218166015e-05, + "loss": 0.6341, + "step": 784 + }, + { + "epoch": 0.06, + "learning_rate": 1.9573554976097352e-05, + "loss": 0.6234, + "step": 785 + }, + { + "epoch": 0.06, + "learning_rate": 1.9573011734028683e-05, + "loss": 0.6176, + "step": 786 + }, + { + "epoch": 0.06, + "learning_rate": 1.957246849196002e-05, + "loss": 0.5324, + "step": 787 + }, + { + "epoch": 0.06, + "learning_rate": 1.957192524989135e-05, + "loss": 0.8756, + "step": 788 + }, + { + "epoch": 0.06, + "learning_rate": 1.957138200782269e-05, + "loss": 0.6274, + "step": 789 + }, + { + "epoch": 0.06, + "learning_rate": 1.957083876575402e-05, + "loss": 0.7408, + "step": 790 + }, + { + "epoch": 0.06, + "learning_rate": 1.9570295523685358e-05, + "loss": 0.6076, + "step": 791 + }, + { + "epoch": 0.06, + "learning_rate": 1.956975228161669e-05, + "loss": 0.7789, + "step": 792 + }, + { + "epoch": 0.06, + "learning_rate": 1.9569209039548026e-05, + "loss": 0.6716, + "step": 793 + }, + { + "epoch": 0.06, + "learning_rate": 1.9568665797479357e-05, + "loss": 0.6273, + "step": 794 + }, + { + "epoch": 0.06, + "learning_rate": 1.9568122555410695e-05, + "loss": 0.6989, + "step": 795 + }, + { + "epoch": 0.06, + "learning_rate": 1.9567579313342025e-05, + "loss": 0.6115, + "step": 796 + }, + { + "epoch": 0.06, + "learning_rate": 1.9567036071273363e-05, + "loss": 0.5865, + "step": 797 + }, + { + "epoch": 0.07, + "learning_rate": 1.9566492829204694e-05, + "loss": 0.6142, + "step": 798 + }, + { + "epoch": 0.07, + "learning_rate": 1.9565949587136028e-05, + "loss": 0.5675, + "step": 799 + }, + { + "epoch": 0.07, + "learning_rate": 1.9565406345067362e-05, + "loss": 0.83, + "step": 800 + }, + { + "epoch": 0.07, + "learning_rate": 1.9564863102998697e-05, + "loss": 0.7159, + "step": 801 + }, + { + "epoch": 0.07, + "learning_rate": 1.956431986093003e-05, + "loss": 0.5742, + "step": 802 + }, + { + "epoch": 0.07, + "learning_rate": 1.9563776618861365e-05, + "loss": 0.6823, + "step": 803 + }, + { + "epoch": 0.07, + "learning_rate": 1.95632333767927e-05, + "loss": 0.6568, + "step": 804 + }, + { + "epoch": 0.07, + "learning_rate": 1.9562690134724034e-05, + "loss": 0.5469, + "step": 805 + }, + { + "epoch": 0.07, + "learning_rate": 1.9562146892655368e-05, + "loss": 0.5174, + "step": 806 + }, + { + "epoch": 0.07, + "learning_rate": 1.9561603650586702e-05, + "loss": 0.6399, + "step": 807 + }, + { + "epoch": 0.07, + "learning_rate": 1.9561060408518036e-05, + "loss": 0.6368, + "step": 808 + }, + { + "epoch": 0.07, + "learning_rate": 1.956051716644937e-05, + "loss": 0.4471, + "step": 809 + }, + { + "epoch": 0.07, + "learning_rate": 1.9559973924380705e-05, + "loss": 0.5826, + "step": 810 + }, + { + "epoch": 0.07, + "learning_rate": 1.955943068231204e-05, + "loss": 0.5804, + "step": 811 + }, + { + "epoch": 0.07, + "learning_rate": 1.9558887440243377e-05, + "loss": 0.5329, + "step": 812 + }, + { + "epoch": 0.07, + "learning_rate": 1.9558344198174707e-05, + "loss": 0.8601, + "step": 813 + }, + { + "epoch": 0.07, + "learning_rate": 1.9557800956106045e-05, + "loss": 0.5647, + "step": 814 + }, + { + "epoch": 0.07, + "learning_rate": 1.9557257714037376e-05, + "loss": 0.7732, + "step": 815 + }, + { + "epoch": 0.07, + "learning_rate": 1.9556714471968713e-05, + "loss": 0.5032, + "step": 816 + }, + { + "epoch": 0.07, + "learning_rate": 1.9556171229900044e-05, + "loss": 0.6098, + "step": 817 + }, + { + "epoch": 0.07, + "learning_rate": 1.955562798783138e-05, + "loss": 0.5576, + "step": 818 + }, + { + "epoch": 0.07, + "learning_rate": 1.9555084745762713e-05, + "loss": 0.8917, + "step": 819 + }, + { + "epoch": 0.07, + "learning_rate": 1.9554541503694047e-05, + "loss": 0.6588, + "step": 820 + }, + { + "epoch": 0.07, + "learning_rate": 1.955399826162538e-05, + "loss": 0.504, + "step": 821 + }, + { + "epoch": 0.07, + "learning_rate": 1.9553455019556715e-05, + "loss": 0.7772, + "step": 822 + }, + { + "epoch": 0.07, + "learning_rate": 1.955291177748805e-05, + "loss": 0.6048, + "step": 823 + }, + { + "epoch": 0.07, + "learning_rate": 1.9552368535419384e-05, + "loss": 0.5585, + "step": 824 + }, + { + "epoch": 0.07, + "learning_rate": 1.9551825293350718e-05, + "loss": 0.7414, + "step": 825 + }, + { + "epoch": 0.07, + "learning_rate": 1.9551282051282052e-05, + "loss": 0.7966, + "step": 826 + }, + { + "epoch": 0.07, + "learning_rate": 1.9550738809213387e-05, + "loss": 0.4888, + "step": 827 + }, + { + "epoch": 0.07, + "learning_rate": 1.955019556714472e-05, + "loss": 0.5637, + "step": 828 + }, + { + "epoch": 0.07, + "learning_rate": 1.9549652325076055e-05, + "loss": 0.7434, + "step": 829 + }, + { + "epoch": 0.07, + "learning_rate": 1.954910908300739e-05, + "loss": 0.5604, + "step": 830 + }, + { + "epoch": 0.07, + "learning_rate": 1.9548565840938724e-05, + "loss": 0.4602, + "step": 831 + }, + { + "epoch": 0.07, + "learning_rate": 1.9548022598870058e-05, + "loss": 0.6391, + "step": 832 + }, + { + "epoch": 0.07, + "learning_rate": 1.9547479356801392e-05, + "loss": 0.787, + "step": 833 + }, + { + "epoch": 0.07, + "learning_rate": 1.9546936114732726e-05, + "loss": 0.5392, + "step": 834 + }, + { + "epoch": 0.07, + "learning_rate": 1.954639287266406e-05, + "loss": 0.8338, + "step": 835 + }, + { + "epoch": 0.07, + "learning_rate": 1.9545849630595395e-05, + "loss": 0.6259, + "step": 836 + }, + { + "epoch": 0.07, + "learning_rate": 1.954530638852673e-05, + "loss": 1.0129, + "step": 837 + }, + { + "epoch": 0.07, + "learning_rate": 1.9544763146458063e-05, + "loss": 0.6355, + "step": 838 + }, + { + "epoch": 0.07, + "learning_rate": 1.9544219904389397e-05, + "loss": 0.4366, + "step": 839 + }, + { + "epoch": 0.07, + "learning_rate": 1.954367666232073e-05, + "loss": 0.3747, + "step": 840 + }, + { + "epoch": 0.07, + "learning_rate": 1.9543133420252066e-05, + "loss": 0.819, + "step": 841 + }, + { + "epoch": 0.07, + "learning_rate": 1.95425901781834e-05, + "loss": 0.7221, + "step": 842 + }, + { + "epoch": 0.07, + "learning_rate": 1.9542046936114734e-05, + "loss": 0.7499, + "step": 843 + }, + { + "epoch": 0.07, + "learning_rate": 1.954150369404607e-05, + "loss": 0.7068, + "step": 844 + }, + { + "epoch": 0.07, + "learning_rate": 1.9540960451977403e-05, + "loss": 0.5838, + "step": 845 + }, + { + "epoch": 0.07, + "learning_rate": 1.9540417209908737e-05, + "loss": 0.631, + "step": 846 + }, + { + "epoch": 0.07, + "learning_rate": 1.953987396784007e-05, + "loss": 0.6436, + "step": 847 + }, + { + "epoch": 0.07, + "learning_rate": 1.9539330725771405e-05, + "loss": 0.7839, + "step": 848 + }, + { + "epoch": 0.07, + "learning_rate": 1.953878748370274e-05, + "loss": 0.3938, + "step": 849 + }, + { + "epoch": 0.07, + "learning_rate": 1.9538244241634074e-05, + "loss": 0.3637, + "step": 850 + }, + { + "epoch": 0.07, + "learning_rate": 1.9537700999565408e-05, + "loss": 0.5203, + "step": 851 + }, + { + "epoch": 0.07, + "learning_rate": 1.9537157757496742e-05, + "loss": 0.6882, + "step": 852 + }, + { + "epoch": 0.07, + "learning_rate": 1.9536614515428077e-05, + "loss": 0.9495, + "step": 853 + }, + { + "epoch": 0.07, + "learning_rate": 1.953607127335941e-05, + "loss": 0.5083, + "step": 854 + }, + { + "epoch": 0.07, + "learning_rate": 1.9535528031290745e-05, + "loss": 0.5517, + "step": 855 + }, + { + "epoch": 0.07, + "learning_rate": 1.953498478922208e-05, + "loss": 0.7432, + "step": 856 + }, + { + "epoch": 0.07, + "learning_rate": 1.9534441547153413e-05, + "loss": 0.5881, + "step": 857 + }, + { + "epoch": 0.07, + "learning_rate": 1.9533898305084748e-05, + "loss": 0.7869, + "step": 858 + }, + { + "epoch": 0.07, + "learning_rate": 1.9533355063016082e-05, + "loss": 0.572, + "step": 859 + }, + { + "epoch": 0.07, + "learning_rate": 1.9532811820947416e-05, + "loss": 0.6408, + "step": 860 + }, + { + "epoch": 0.07, + "learning_rate": 1.953226857887875e-05, + "loss": 0.7597, + "step": 861 + }, + { + "epoch": 0.07, + "learning_rate": 1.9531725336810085e-05, + "loss": 0.8198, + "step": 862 + }, + { + "epoch": 0.07, + "learning_rate": 1.953118209474142e-05, + "loss": 0.6825, + "step": 863 + }, + { + "epoch": 0.07, + "learning_rate": 1.9530638852672753e-05, + "loss": 0.7816, + "step": 864 + }, + { + "epoch": 0.07, + "learning_rate": 1.9530095610604087e-05, + "loss": 0.6414, + "step": 865 + }, + { + "epoch": 0.07, + "learning_rate": 1.952955236853542e-05, + "loss": 0.6454, + "step": 866 + }, + { + "epoch": 0.07, + "learning_rate": 1.9529009126466756e-05, + "loss": 0.6968, + "step": 867 + }, + { + "epoch": 0.07, + "learning_rate": 1.952846588439809e-05, + "loss": 0.6493, + "step": 868 + }, + { + "epoch": 0.07, + "learning_rate": 1.9527922642329424e-05, + "loss": 0.5444, + "step": 869 + }, + { + "epoch": 0.07, + "learning_rate": 1.952737940026076e-05, + "loss": 0.8929, + "step": 870 + }, + { + "epoch": 0.07, + "learning_rate": 1.9526836158192093e-05, + "loss": 0.5051, + "step": 871 + }, + { + "epoch": 0.07, + "learning_rate": 1.9526292916123427e-05, + "loss": 0.8146, + "step": 872 + }, + { + "epoch": 0.07, + "learning_rate": 1.952574967405476e-05, + "loss": 0.5299, + "step": 873 + }, + { + "epoch": 0.07, + "learning_rate": 1.9525206431986095e-05, + "loss": 0.5129, + "step": 874 + }, + { + "epoch": 0.07, + "learning_rate": 1.9524663189917426e-05, + "loss": 0.4928, + "step": 875 + }, + { + "epoch": 0.07, + "learning_rate": 1.9524119947848764e-05, + "loss": 0.5073, + "step": 876 + }, + { + "epoch": 0.07, + "learning_rate": 1.9523576705780095e-05, + "loss": 0.5701, + "step": 877 + }, + { + "epoch": 0.07, + "learning_rate": 1.9523033463711432e-05, + "loss": 0.5769, + "step": 878 + }, + { + "epoch": 0.07, + "learning_rate": 1.9522490221642763e-05, + "loss": 0.8367, + "step": 879 + }, + { + "epoch": 0.07, + "learning_rate": 1.95219469795741e-05, + "loss": 0.5158, + "step": 880 + }, + { + "epoch": 0.07, + "learning_rate": 1.952140373750543e-05, + "loss": 0.5274, + "step": 881 + }, + { + "epoch": 0.07, + "learning_rate": 1.952086049543677e-05, + "loss": 0.6887, + "step": 882 + }, + { + "epoch": 0.07, + "learning_rate": 1.95203172533681e-05, + "loss": 0.5296, + "step": 883 + }, + { + "epoch": 0.07, + "learning_rate": 1.9519774011299438e-05, + "loss": 0.7264, + "step": 884 + }, + { + "epoch": 0.07, + "learning_rate": 1.9519230769230772e-05, + "loss": 0.6627, + "step": 885 + }, + { + "epoch": 0.07, + "learning_rate": 1.9518687527162106e-05, + "loss": 0.4402, + "step": 886 + }, + { + "epoch": 0.07, + "learning_rate": 1.951814428509344e-05, + "loss": 0.7424, + "step": 887 + }, + { + "epoch": 0.07, + "learning_rate": 1.9517601043024775e-05, + "loss": 0.6063, + "step": 888 + }, + { + "epoch": 0.07, + "learning_rate": 1.951705780095611e-05, + "loss": 0.9082, + "step": 889 + }, + { + "epoch": 0.07, + "learning_rate": 1.9516514558887443e-05, + "loss": 0.5613, + "step": 890 + }, + { + "epoch": 0.07, + "learning_rate": 1.9515971316818777e-05, + "loss": 0.5306, + "step": 891 + }, + { + "epoch": 0.07, + "learning_rate": 1.951542807475011e-05, + "loss": 0.6226, + "step": 892 + }, + { + "epoch": 0.07, + "learning_rate": 1.9514884832681446e-05, + "loss": 0.6811, + "step": 893 + }, + { + "epoch": 0.07, + "learning_rate": 1.9514341590612777e-05, + "loss": 0.6155, + "step": 894 + }, + { + "epoch": 0.07, + "learning_rate": 1.9513798348544114e-05, + "loss": 0.9578, + "step": 895 + }, + { + "epoch": 0.07, + "learning_rate": 1.9513255106475445e-05, + "loss": 0.8234, + "step": 896 + }, + { + "epoch": 0.07, + "learning_rate": 1.9512711864406783e-05, + "loss": 0.4359, + "step": 897 + }, + { + "epoch": 0.07, + "learning_rate": 1.9512168622338114e-05, + "loss": 0.6426, + "step": 898 + }, + { + "epoch": 0.07, + "learning_rate": 1.951162538026945e-05, + "loss": 0.8927, + "step": 899 + }, + { + "epoch": 0.07, + "learning_rate": 1.9511082138200782e-05, + "loss": 0.5801, + "step": 900 + }, + { + "epoch": 0.07, + "learning_rate": 1.951053889613212e-05, + "loss": 0.9222, + "step": 901 + }, + { + "epoch": 0.07, + "learning_rate": 1.950999565406345e-05, + "loss": 0.6145, + "step": 902 + }, + { + "epoch": 0.07, + "learning_rate": 1.9509452411994788e-05, + "loss": 0.7746, + "step": 903 + }, + { + "epoch": 0.07, + "learning_rate": 1.950890916992612e-05, + "loss": 0.6477, + "step": 904 + }, + { + "epoch": 0.07, + "learning_rate": 1.9508365927857457e-05, + "loss": 0.7773, + "step": 905 + }, + { + "epoch": 0.07, + "learning_rate": 1.9507822685788787e-05, + "loss": 0.6019, + "step": 906 + }, + { + "epoch": 0.07, + "learning_rate": 1.9507279443720125e-05, + "loss": 0.4714, + "step": 907 + }, + { + "epoch": 0.07, + "learning_rate": 1.9506736201651456e-05, + "loss": 0.6141, + "step": 908 + }, + { + "epoch": 0.07, + "learning_rate": 1.9506192959582793e-05, + "loss": 0.5809, + "step": 909 + }, + { + "epoch": 0.07, + "learning_rate": 1.9505649717514124e-05, + "loss": 0.8569, + "step": 910 + }, + { + "epoch": 0.07, + "learning_rate": 1.9505106475445462e-05, + "loss": 0.7409, + "step": 911 + }, + { + "epoch": 0.07, + "learning_rate": 1.9504563233376793e-05, + "loss": 0.5276, + "step": 912 + }, + { + "epoch": 0.07, + "learning_rate": 1.9504019991308127e-05, + "loss": 0.6129, + "step": 913 + }, + { + "epoch": 0.07, + "learning_rate": 1.950347674923946e-05, + "loss": 0.5832, + "step": 914 + }, + { + "epoch": 0.07, + "learning_rate": 1.9502933507170795e-05, + "loss": 0.5539, + "step": 915 + }, + { + "epoch": 0.07, + "learning_rate": 1.950239026510213e-05, + "loss": 0.4687, + "step": 916 + }, + { + "epoch": 0.07, + "learning_rate": 1.9501847023033464e-05, + "loss": 0.7253, + "step": 917 + }, + { + "epoch": 0.07, + "learning_rate": 1.9501303780964798e-05, + "loss": 0.6272, + "step": 918 + }, + { + "epoch": 0.07, + "learning_rate": 1.9500760538896132e-05, + "loss": 0.4604, + "step": 919 + }, + { + "epoch": 0.07, + "learning_rate": 1.950021729682747e-05, + "loss": 0.6929, + "step": 920 + }, + { + "epoch": 0.08, + "learning_rate": 1.94996740547588e-05, + "loss": 0.5588, + "step": 921 + }, + { + "epoch": 0.08, + "learning_rate": 1.949913081269014e-05, + "loss": 0.5865, + "step": 922 + }, + { + "epoch": 0.08, + "learning_rate": 1.949858757062147e-05, + "loss": 0.8661, + "step": 923 + }, + { + "epoch": 0.08, + "learning_rate": 1.9498044328552807e-05, + "loss": 0.5382, + "step": 924 + }, + { + "epoch": 0.08, + "learning_rate": 1.9497501086484138e-05, + "loss": 0.6303, + "step": 925 + }, + { + "epoch": 0.08, + "learning_rate": 1.9496957844415475e-05, + "loss": 0.5183, + "step": 926 + }, + { + "epoch": 0.08, + "learning_rate": 1.9496414602346806e-05, + "loss": 0.5164, + "step": 927 + }, + { + "epoch": 0.08, + "learning_rate": 1.9495871360278144e-05, + "loss": 0.4383, + "step": 928 + }, + { + "epoch": 0.08, + "learning_rate": 1.9495328118209475e-05, + "loss": 0.6473, + "step": 929 + }, + { + "epoch": 0.08, + "learning_rate": 1.9494784876140812e-05, + "loss": 0.5649, + "step": 930 + }, + { + "epoch": 0.08, + "learning_rate": 1.9494241634072143e-05, + "loss": 0.7985, + "step": 931 + }, + { + "epoch": 0.08, + "learning_rate": 1.9493698392003477e-05, + "loss": 0.4734, + "step": 932 + }, + { + "epoch": 0.08, + "learning_rate": 1.949315514993481e-05, + "loss": 0.4791, + "step": 933 + }, + { + "epoch": 0.08, + "learning_rate": 1.9492611907866146e-05, + "loss": 0.6881, + "step": 934 + }, + { + "epoch": 0.08, + "learning_rate": 1.949206866579748e-05, + "loss": 0.5307, + "step": 935 + }, + { + "epoch": 0.08, + "learning_rate": 1.9491525423728814e-05, + "loss": 0.6627, + "step": 936 + }, + { + "epoch": 0.08, + "learning_rate": 1.949098218166015e-05, + "loss": 0.7071, + "step": 937 + }, + { + "epoch": 0.08, + "learning_rate": 1.9490438939591483e-05, + "loss": 0.8398, + "step": 938 + }, + { + "epoch": 0.08, + "learning_rate": 1.9489895697522817e-05, + "loss": 0.7155, + "step": 939 + }, + { + "epoch": 0.08, + "learning_rate": 1.948935245545415e-05, + "loss": 0.4405, + "step": 940 + }, + { + "epoch": 0.08, + "learning_rate": 1.9488809213385485e-05, + "loss": 0.4862, + "step": 941 + }, + { + "epoch": 0.08, + "learning_rate": 1.948826597131682e-05, + "loss": 0.6459, + "step": 942 + }, + { + "epoch": 0.08, + "learning_rate": 1.9487722729248154e-05, + "loss": 0.6995, + "step": 943 + }, + { + "epoch": 0.08, + "learning_rate": 1.9487179487179488e-05, + "loss": 0.4701, + "step": 944 + }, + { + "epoch": 0.08, + "learning_rate": 1.9486636245110822e-05, + "loss": 0.5246, + "step": 945 + }, + { + "epoch": 0.08, + "learning_rate": 1.9486093003042157e-05, + "loss": 0.5997, + "step": 946 + }, + { + "epoch": 0.08, + "learning_rate": 1.948554976097349e-05, + "loss": 0.7988, + "step": 947 + }, + { + "epoch": 0.08, + "learning_rate": 1.9485006518904825e-05, + "loss": 0.7597, + "step": 948 + }, + { + "epoch": 0.08, + "learning_rate": 1.948446327683616e-05, + "loss": 0.5892, + "step": 949 + }, + { + "epoch": 0.08, + "learning_rate": 1.9483920034767494e-05, + "loss": 0.5638, + "step": 950 + }, + { + "epoch": 0.08, + "learning_rate": 1.9483376792698828e-05, + "loss": 0.5051, + "step": 951 + }, + { + "epoch": 0.08, + "learning_rate": 1.9482833550630162e-05, + "loss": 0.5266, + "step": 952 + }, + { + "epoch": 0.08, + "learning_rate": 1.9482290308561496e-05, + "loss": 0.592, + "step": 953 + }, + { + "epoch": 0.08, + "learning_rate": 1.948174706649283e-05, + "loss": 0.5285, + "step": 954 + }, + { + "epoch": 0.08, + "learning_rate": 1.9481203824424165e-05, + "loss": 0.8228, + "step": 955 + }, + { + "epoch": 0.08, + "learning_rate": 1.94806605823555e-05, + "loss": 0.7575, + "step": 956 + }, + { + "epoch": 0.08, + "learning_rate": 1.9480117340286833e-05, + "loss": 0.5928, + "step": 957 + }, + { + "epoch": 0.08, + "learning_rate": 1.9479574098218167e-05, + "loss": 0.4928, + "step": 958 + }, + { + "epoch": 0.08, + "learning_rate": 1.94790308561495e-05, + "loss": 0.6916, + "step": 959 + }, + { + "epoch": 0.08, + "learning_rate": 1.9478487614080836e-05, + "loss": 0.3147, + "step": 960 + }, + { + "epoch": 0.08, + "learning_rate": 1.947794437201217e-05, + "loss": 0.5206, + "step": 961 + }, + { + "epoch": 0.08, + "learning_rate": 1.9477401129943504e-05, + "loss": 0.3484, + "step": 962 + }, + { + "epoch": 0.08, + "learning_rate": 1.947685788787484e-05, + "loss": 0.5063, + "step": 963 + }, + { + "epoch": 0.08, + "learning_rate": 1.9476314645806173e-05, + "loss": 0.6278, + "step": 964 + }, + { + "epoch": 0.08, + "learning_rate": 1.9475771403737507e-05, + "loss": 0.6409, + "step": 965 + }, + { + "epoch": 0.08, + "learning_rate": 1.947522816166884e-05, + "loss": 0.7332, + "step": 966 + }, + { + "epoch": 0.08, + "learning_rate": 1.9474684919600175e-05, + "loss": 0.7036, + "step": 967 + }, + { + "epoch": 0.08, + "learning_rate": 1.947414167753151e-05, + "loss": 0.5742, + "step": 968 + }, + { + "epoch": 0.08, + "learning_rate": 1.9473598435462844e-05, + "loss": 0.6161, + "step": 969 + }, + { + "epoch": 0.08, + "learning_rate": 1.9473055193394178e-05, + "loss": 0.6494, + "step": 970 + }, + { + "epoch": 0.08, + "learning_rate": 1.9472511951325512e-05, + "loss": 0.7987, + "step": 971 + }, + { + "epoch": 0.08, + "learning_rate": 1.9471968709256847e-05, + "loss": 0.7463, + "step": 972 + }, + { + "epoch": 0.08, + "learning_rate": 1.947142546718818e-05, + "loss": 0.5677, + "step": 973 + }, + { + "epoch": 0.08, + "learning_rate": 1.9470882225119515e-05, + "loss": 0.4164, + "step": 974 + }, + { + "epoch": 0.08, + "learning_rate": 1.947033898305085e-05, + "loss": 0.6362, + "step": 975 + }, + { + "epoch": 0.08, + "learning_rate": 1.9469795740982184e-05, + "loss": 0.741, + "step": 976 + }, + { + "epoch": 0.08, + "learning_rate": 1.9469252498913518e-05, + "loss": 0.6508, + "step": 977 + }, + { + "epoch": 0.08, + "learning_rate": 1.9468709256844852e-05, + "loss": 0.6207, + "step": 978 + }, + { + "epoch": 0.08, + "learning_rate": 1.9468166014776186e-05, + "loss": 0.8243, + "step": 979 + }, + { + "epoch": 0.08, + "learning_rate": 1.946762277270752e-05, + "loss": 0.5206, + "step": 980 + }, + { + "epoch": 0.08, + "learning_rate": 1.9467079530638855e-05, + "loss": 0.3869, + "step": 981 + }, + { + "epoch": 0.08, + "learning_rate": 1.946653628857019e-05, + "loss": 0.4865, + "step": 982 + }, + { + "epoch": 0.08, + "learning_rate": 1.9465993046501523e-05, + "loss": 0.4708, + "step": 983 + }, + { + "epoch": 0.08, + "learning_rate": 1.9465449804432857e-05, + "loss": 0.5978, + "step": 984 + }, + { + "epoch": 0.08, + "learning_rate": 1.946490656236419e-05, + "loss": 0.8679, + "step": 985 + }, + { + "epoch": 0.08, + "learning_rate": 1.9464363320295526e-05, + "loss": 0.4266, + "step": 986 + }, + { + "epoch": 0.08, + "learning_rate": 1.946382007822686e-05, + "loss": 0.9584, + "step": 987 + }, + { + "epoch": 0.08, + "learning_rate": 1.9463276836158194e-05, + "loss": 0.6056, + "step": 988 + }, + { + "epoch": 0.08, + "learning_rate": 1.9462733594089525e-05, + "loss": 0.7478, + "step": 989 + }, + { + "epoch": 0.08, + "learning_rate": 1.9462190352020863e-05, + "loss": 0.6121, + "step": 990 + }, + { + "epoch": 0.08, + "learning_rate": 1.9461647109952194e-05, + "loss": 0.5885, + "step": 991 + }, + { + "epoch": 0.08, + "learning_rate": 1.946110386788353e-05, + "loss": 0.3132, + "step": 992 + }, + { + "epoch": 0.08, + "learning_rate": 1.9460560625814865e-05, + "loss": 0.7227, + "step": 993 + }, + { + "epoch": 0.08, + "learning_rate": 1.94600173837462e-05, + "loss": 0.5109, + "step": 994 + }, + { + "epoch": 0.08, + "learning_rate": 1.9459474141677534e-05, + "loss": 0.7871, + "step": 995 + }, + { + "epoch": 0.08, + "learning_rate": 1.9458930899608868e-05, + "loss": 0.7888, + "step": 996 + }, + { + "epoch": 0.08, + "learning_rate": 1.9458387657540202e-05, + "loss": 0.6419, + "step": 997 + }, + { + "epoch": 0.08, + "learning_rate": 1.9457844415471537e-05, + "loss": 0.4249, + "step": 998 + }, + { + "epoch": 0.08, + "learning_rate": 1.945730117340287e-05, + "loss": 0.5916, + "step": 999 + }, + { + "epoch": 0.08, + "learning_rate": 1.9456757931334205e-05, + "loss": 0.3585, + "step": 1000 + }, + { + "epoch": 0.08, + "eval_accuracy": 0.7632195618950586, + "eval_loss": 0.589742124080658, + "eval_runtime": 22.2801, + "eval_samples_per_second": 440.528, + "eval_steps_per_second": 3.456, + "step": 1000 + }, + { + "epoch": 0.08, + "learning_rate": 1.945621468926554e-05, + "loss": 0.6206, + "step": 1001 + }, + { + "epoch": 0.08, + "learning_rate": 1.9455671447196874e-05, + "loss": 0.3245, + "step": 1002 + }, + { + "epoch": 0.08, + "learning_rate": 1.9455128205128208e-05, + "loss": 0.7279, + "step": 1003 + }, + { + "epoch": 0.08, + "learning_rate": 1.9454584963059542e-05, + "loss": 0.4747, + "step": 1004 + }, + { + "epoch": 0.08, + "learning_rate": 1.9454041720990876e-05, + "loss": 0.4231, + "step": 1005 + }, + { + "epoch": 0.08, + "learning_rate": 1.945349847892221e-05, + "loss": 0.5041, + "step": 1006 + }, + { + "epoch": 0.08, + "learning_rate": 1.9452955236853545e-05, + "loss": 0.5652, + "step": 1007 + }, + { + "epoch": 0.08, + "learning_rate": 1.9452411994784876e-05, + "loss": 0.413, + "step": 1008 + }, + { + "epoch": 0.08, + "learning_rate": 1.9451868752716213e-05, + "loss": 0.4796, + "step": 1009 + }, + { + "epoch": 0.08, + "learning_rate": 1.9451325510647544e-05, + "loss": 0.5108, + "step": 1010 + }, + { + "epoch": 0.08, + "learning_rate": 1.945078226857888e-05, + "loss": 0.3875, + "step": 1011 + }, + { + "epoch": 0.08, + "learning_rate": 1.9450239026510212e-05, + "loss": 0.6101, + "step": 1012 + }, + { + "epoch": 0.08, + "learning_rate": 1.944969578444155e-05, + "loss": 0.5209, + "step": 1013 + }, + { + "epoch": 0.08, + "learning_rate": 1.944915254237288e-05, + "loss": 0.4489, + "step": 1014 + }, + { + "epoch": 0.08, + "learning_rate": 1.944860930030422e-05, + "loss": 0.5318, + "step": 1015 + }, + { + "epoch": 0.08, + "learning_rate": 1.944806605823555e-05, + "loss": 0.608, + "step": 1016 + }, + { + "epoch": 0.08, + "learning_rate": 1.9447522816166887e-05, + "loss": 0.5977, + "step": 1017 + }, + { + "epoch": 0.08, + "learning_rate": 1.9446979574098218e-05, + "loss": 0.8179, + "step": 1018 + }, + { + "epoch": 0.08, + "learning_rate": 1.9446436332029555e-05, + "loss": 0.7417, + "step": 1019 + }, + { + "epoch": 0.08, + "learning_rate": 1.9445893089960886e-05, + "loss": 0.914, + "step": 1020 + }, + { + "epoch": 0.08, + "learning_rate": 1.9445349847892224e-05, + "loss": 0.8656, + "step": 1021 + }, + { + "epoch": 0.08, + "learning_rate": 1.9444806605823555e-05, + "loss": 0.5443, + "step": 1022 + }, + { + "epoch": 0.08, + "learning_rate": 1.9444263363754892e-05, + "loss": 0.7303, + "step": 1023 + }, + { + "epoch": 0.08, + "learning_rate": 1.9443720121686223e-05, + "loss": 0.7842, + "step": 1024 + }, + { + "epoch": 0.08, + "learning_rate": 1.944317687961756e-05, + "loss": 0.541, + "step": 1025 + }, + { + "epoch": 0.08, + "learning_rate": 1.944263363754889e-05, + "loss": 0.6668, + "step": 1026 + }, + { + "epoch": 0.08, + "learning_rate": 1.9442090395480226e-05, + "loss": 0.9182, + "step": 1027 + }, + { + "epoch": 0.08, + "learning_rate": 1.9441547153411564e-05, + "loss": 0.8654, + "step": 1028 + }, + { + "epoch": 0.08, + "learning_rate": 1.9441003911342894e-05, + "loss": 0.5578, + "step": 1029 + }, + { + "epoch": 0.08, + "learning_rate": 1.9440460669274232e-05, + "loss": 0.6758, + "step": 1030 + }, + { + "epoch": 0.08, + "learning_rate": 1.9439917427205563e-05, + "loss": 0.5114, + "step": 1031 + }, + { + "epoch": 0.08, + "learning_rate": 1.94393741851369e-05, + "loss": 0.5072, + "step": 1032 + }, + { + "epoch": 0.08, + "learning_rate": 1.943883094306823e-05, + "loss": 0.582, + "step": 1033 + }, + { + "epoch": 0.08, + "learning_rate": 1.943828770099957e-05, + "loss": 0.7532, + "step": 1034 + }, + { + "epoch": 0.08, + "learning_rate": 1.94377444589309e-05, + "loss": 0.5497, + "step": 1035 + }, + { + "epoch": 0.08, + "learning_rate": 1.9437201216862237e-05, + "loss": 0.4923, + "step": 1036 + }, + { + "epoch": 0.08, + "learning_rate": 1.9436657974793568e-05, + "loss": 0.6951, + "step": 1037 + }, + { + "epoch": 0.08, + "learning_rate": 1.9436114732724906e-05, + "loss": 0.4787, + "step": 1038 + }, + { + "epoch": 0.08, + "learning_rate": 1.9435571490656237e-05, + "loss": 0.6984, + "step": 1039 + }, + { + "epoch": 0.08, + "learning_rate": 1.9435028248587574e-05, + "loss": 0.484, + "step": 1040 + }, + { + "epoch": 0.08, + "learning_rate": 1.9434485006518905e-05, + "loss": 0.3913, + "step": 1041 + }, + { + "epoch": 0.08, + "learning_rate": 1.9433941764450243e-05, + "loss": 0.6229, + "step": 1042 + }, + { + "epoch": 0.08, + "learning_rate": 1.9433398522381574e-05, + "loss": 0.4428, + "step": 1043 + }, + { + "epoch": 0.09, + "learning_rate": 1.943285528031291e-05, + "loss": 0.5069, + "step": 1044 + }, + { + "epoch": 0.09, + "learning_rate": 1.9432312038244242e-05, + "loss": 0.3565, + "step": 1045 + }, + { + "epoch": 0.09, + "learning_rate": 1.9431768796175576e-05, + "loss": 0.6949, + "step": 1046 + }, + { + "epoch": 0.09, + "learning_rate": 1.943122555410691e-05, + "loss": 0.4489, + "step": 1047 + }, + { + "epoch": 0.09, + "learning_rate": 1.9430682312038245e-05, + "loss": 0.651, + "step": 1048 + }, + { + "epoch": 0.09, + "learning_rate": 1.943013906996958e-05, + "loss": 0.5514, + "step": 1049 + }, + { + "epoch": 0.09, + "learning_rate": 1.9429595827900913e-05, + "loss": 0.4562, + "step": 1050 + }, + { + "epoch": 0.09, + "learning_rate": 1.9429052585832247e-05, + "loss": 0.7158, + "step": 1051 + }, + { + "epoch": 0.09, + "learning_rate": 1.942850934376358e-05, + "loss": 0.7097, + "step": 1052 + }, + { + "epoch": 0.09, + "learning_rate": 1.9427966101694916e-05, + "loss": 0.5317, + "step": 1053 + }, + { + "epoch": 0.09, + "learning_rate": 1.942742285962625e-05, + "loss": 0.7139, + "step": 1054 + }, + { + "epoch": 0.09, + "learning_rate": 1.9426879617557584e-05, + "loss": 0.3883, + "step": 1055 + }, + { + "epoch": 0.09, + "learning_rate": 1.942633637548892e-05, + "loss": 0.7948, + "step": 1056 + }, + { + "epoch": 0.09, + "learning_rate": 1.9425793133420253e-05, + "loss": 0.4511, + "step": 1057 + }, + { + "epoch": 0.09, + "learning_rate": 1.9425249891351587e-05, + "loss": 0.8331, + "step": 1058 + }, + { + "epoch": 0.09, + "learning_rate": 1.942470664928292e-05, + "loss": 0.7341, + "step": 1059 + }, + { + "epoch": 0.09, + "learning_rate": 1.9424163407214256e-05, + "loss": 0.5378, + "step": 1060 + }, + { + "epoch": 0.09, + "learning_rate": 1.942362016514559e-05, + "loss": 0.4575, + "step": 1061 + }, + { + "epoch": 0.09, + "learning_rate": 1.9423076923076924e-05, + "loss": 0.7384, + "step": 1062 + }, + { + "epoch": 0.09, + "learning_rate": 1.9422533681008258e-05, + "loss": 0.6523, + "step": 1063 + }, + { + "epoch": 0.09, + "learning_rate": 1.9421990438939592e-05, + "loss": 0.5481, + "step": 1064 + }, + { + "epoch": 0.09, + "learning_rate": 1.9421447196870927e-05, + "loss": 0.5671, + "step": 1065 + }, + { + "epoch": 0.09, + "learning_rate": 1.942090395480226e-05, + "loss": 0.543, + "step": 1066 + }, + { + "epoch": 0.09, + "learning_rate": 1.9420360712733595e-05, + "loss": 0.3061, + "step": 1067 + }, + { + "epoch": 0.09, + "learning_rate": 1.941981747066493e-05, + "loss": 0.5092, + "step": 1068 + }, + { + "epoch": 0.09, + "learning_rate": 1.9419274228596264e-05, + "loss": 0.7934, + "step": 1069 + }, + { + "epoch": 0.09, + "learning_rate": 1.9418730986527598e-05, + "loss": 0.7239, + "step": 1070 + }, + { + "epoch": 0.09, + "learning_rate": 1.9418187744458932e-05, + "loss": 0.2617, + "step": 1071 + }, + { + "epoch": 0.09, + "learning_rate": 1.9417644502390266e-05, + "loss": 0.7028, + "step": 1072 + }, + { + "epoch": 0.09, + "learning_rate": 1.94171012603216e-05, + "loss": 0.6127, + "step": 1073 + }, + { + "epoch": 0.09, + "learning_rate": 1.9416558018252935e-05, + "loss": 0.5904, + "step": 1074 + }, + { + "epoch": 0.09, + "learning_rate": 1.941601477618427e-05, + "loss": 0.781, + "step": 1075 + }, + { + "epoch": 0.09, + "learning_rate": 1.9415471534115603e-05, + "loss": 0.6968, + "step": 1076 + }, + { + "epoch": 0.09, + "learning_rate": 1.9414928292046937e-05, + "loss": 0.571, + "step": 1077 + }, + { + "epoch": 0.09, + "learning_rate": 1.941438504997827e-05, + "loss": 0.6004, + "step": 1078 + }, + { + "epoch": 0.09, + "learning_rate": 1.9413841807909606e-05, + "loss": 0.6544, + "step": 1079 + }, + { + "epoch": 0.09, + "learning_rate": 1.941329856584094e-05, + "loss": 0.6472, + "step": 1080 + }, + { + "epoch": 0.09, + "learning_rate": 1.9412755323772274e-05, + "loss": 0.5941, + "step": 1081 + }, + { + "epoch": 0.09, + "learning_rate": 1.941221208170361e-05, + "loss": 0.5985, + "step": 1082 + }, + { + "epoch": 0.09, + "learning_rate": 1.9411668839634943e-05, + "loss": 0.4854, + "step": 1083 + }, + { + "epoch": 0.09, + "learning_rate": 1.9411125597566277e-05, + "loss": 0.5224, + "step": 1084 + }, + { + "epoch": 0.09, + "learning_rate": 1.941058235549761e-05, + "loss": 0.8573, + "step": 1085 + }, + { + "epoch": 0.09, + "learning_rate": 1.9410039113428946e-05, + "loss": 0.4953, + "step": 1086 + }, + { + "epoch": 0.09, + "learning_rate": 1.940949587136028e-05, + "loss": 0.5644, + "step": 1087 + }, + { + "epoch": 0.09, + "learning_rate": 1.9408952629291614e-05, + "loss": 0.5015, + "step": 1088 + }, + { + "epoch": 0.09, + "learning_rate": 1.9408409387222948e-05, + "loss": 0.6187, + "step": 1089 + }, + { + "epoch": 0.09, + "learning_rate": 1.9407866145154282e-05, + "loss": 0.8715, + "step": 1090 + }, + { + "epoch": 0.09, + "learning_rate": 1.9407322903085617e-05, + "loss": 0.7602, + "step": 1091 + }, + { + "epoch": 0.09, + "learning_rate": 1.940677966101695e-05, + "loss": 0.6125, + "step": 1092 + }, + { + "epoch": 0.09, + "learning_rate": 1.9406236418948285e-05, + "loss": 0.7029, + "step": 1093 + }, + { + "epoch": 0.09, + "learning_rate": 1.940569317687962e-05, + "loss": 0.5427, + "step": 1094 + }, + { + "epoch": 0.09, + "learning_rate": 1.9405149934810954e-05, + "loss": 0.5164, + "step": 1095 + }, + { + "epoch": 0.09, + "learning_rate": 1.9404606692742288e-05, + "loss": 0.7099, + "step": 1096 + }, + { + "epoch": 0.09, + "learning_rate": 1.9404063450673622e-05, + "loss": 0.6927, + "step": 1097 + }, + { + "epoch": 0.09, + "learning_rate": 1.9403520208604956e-05, + "loss": 0.793, + "step": 1098 + }, + { + "epoch": 0.09, + "learning_rate": 1.940297696653629e-05, + "loss": 0.4171, + "step": 1099 + }, + { + "epoch": 0.09, + "learning_rate": 1.9402433724467625e-05, + "loss": 0.5365, + "step": 1100 + }, + { + "epoch": 0.09, + "learning_rate": 1.940189048239896e-05, + "loss": 0.4074, + "step": 1101 + }, + { + "epoch": 0.09, + "learning_rate": 1.9401347240330293e-05, + "loss": 0.8029, + "step": 1102 + }, + { + "epoch": 0.09, + "learning_rate": 1.9400803998261627e-05, + "loss": 0.6572, + "step": 1103 + }, + { + "epoch": 0.09, + "learning_rate": 1.940026075619296e-05, + "loss": 0.6846, + "step": 1104 + }, + { + "epoch": 0.09, + "learning_rate": 1.9399717514124296e-05, + "loss": 0.7278, + "step": 1105 + }, + { + "epoch": 0.09, + "learning_rate": 1.939917427205563e-05, + "loss": 0.451, + "step": 1106 + }, + { + "epoch": 0.09, + "learning_rate": 1.9398631029986964e-05, + "loss": 0.5042, + "step": 1107 + }, + { + "epoch": 0.09, + "learning_rate": 1.93980877879183e-05, + "loss": 0.2999, + "step": 1108 + }, + { + "epoch": 0.09, + "learning_rate": 1.9397544545849633e-05, + "loss": 0.6876, + "step": 1109 + }, + { + "epoch": 0.09, + "learning_rate": 1.9397001303780967e-05, + "loss": 0.7171, + "step": 1110 + }, + { + "epoch": 0.09, + "learning_rate": 1.93964580617123e-05, + "loss": 0.7092, + "step": 1111 + }, + { + "epoch": 0.09, + "learning_rate": 1.9395914819643636e-05, + "loss": 0.5563, + "step": 1112 + }, + { + "epoch": 0.09, + "learning_rate": 1.939537157757497e-05, + "loss": 0.4297, + "step": 1113 + }, + { + "epoch": 0.09, + "learning_rate": 1.9394828335506304e-05, + "loss": 0.5744, + "step": 1114 + }, + { + "epoch": 0.09, + "learning_rate": 1.9394285093437638e-05, + "loss": 0.7018, + "step": 1115 + }, + { + "epoch": 0.09, + "learning_rate": 1.9393741851368972e-05, + "loss": 0.7797, + "step": 1116 + }, + { + "epoch": 0.09, + "learning_rate": 1.9393198609300307e-05, + "loss": 0.7898, + "step": 1117 + }, + { + "epoch": 0.09, + "learning_rate": 1.939265536723164e-05, + "loss": 0.5725, + "step": 1118 + }, + { + "epoch": 0.09, + "learning_rate": 1.9392112125162975e-05, + "loss": 0.6793, + "step": 1119 + }, + { + "epoch": 0.09, + "learning_rate": 1.939156888309431e-05, + "loss": 0.8657, + "step": 1120 + }, + { + "epoch": 0.09, + "learning_rate": 1.9391025641025644e-05, + "loss": 0.5215, + "step": 1121 + }, + { + "epoch": 0.09, + "learning_rate": 1.9390482398956974e-05, + "loss": 0.5512, + "step": 1122 + }, + { + "epoch": 0.09, + "learning_rate": 1.9389939156888312e-05, + "loss": 0.8888, + "step": 1123 + }, + { + "epoch": 0.09, + "learning_rate": 1.9389395914819643e-05, + "loss": 0.9266, + "step": 1124 + }, + { + "epoch": 0.09, + "learning_rate": 1.938885267275098e-05, + "loss": 0.6474, + "step": 1125 + }, + { + "epoch": 0.09, + "learning_rate": 1.938830943068231e-05, + "loss": 0.5387, + "step": 1126 + }, + { + "epoch": 0.09, + "learning_rate": 1.938776618861365e-05, + "loss": 0.4315, + "step": 1127 + }, + { + "epoch": 0.09, + "learning_rate": 1.938722294654498e-05, + "loss": 0.7242, + "step": 1128 + }, + { + "epoch": 0.09, + "learning_rate": 1.9386679704476317e-05, + "loss": 0.8273, + "step": 1129 + }, + { + "epoch": 0.09, + "learning_rate": 1.9386136462407648e-05, + "loss": 0.4343, + "step": 1130 + }, + { + "epoch": 0.09, + "learning_rate": 1.9385593220338986e-05, + "loss": 0.6616, + "step": 1131 + }, + { + "epoch": 0.09, + "learning_rate": 1.9385049978270317e-05, + "loss": 0.6885, + "step": 1132 + }, + { + "epoch": 0.09, + "learning_rate": 1.9384506736201654e-05, + "loss": 0.6977, + "step": 1133 + }, + { + "epoch": 0.09, + "learning_rate": 1.9383963494132985e-05, + "loss": 0.4877, + "step": 1134 + }, + { + "epoch": 0.09, + "learning_rate": 1.9383420252064323e-05, + "loss": 0.4705, + "step": 1135 + }, + { + "epoch": 0.09, + "learning_rate": 1.9382877009995657e-05, + "loss": 0.8739, + "step": 1136 + }, + { + "epoch": 0.09, + "learning_rate": 1.938233376792699e-05, + "loss": 0.4915, + "step": 1137 + }, + { + "epoch": 0.09, + "learning_rate": 1.9381790525858326e-05, + "loss": 0.7394, + "step": 1138 + }, + { + "epoch": 0.09, + "learning_rate": 1.938124728378966e-05, + "loss": 0.5393, + "step": 1139 + }, + { + "epoch": 0.09, + "learning_rate": 1.9380704041720994e-05, + "loss": 0.5671, + "step": 1140 + }, + { + "epoch": 0.09, + "learning_rate": 1.9380160799652325e-05, + "loss": 0.5368, + "step": 1141 + }, + { + "epoch": 0.09, + "learning_rate": 1.9379617557583662e-05, + "loss": 0.5832, + "step": 1142 + }, + { + "epoch": 0.09, + "learning_rate": 1.9379074315514993e-05, + "loss": 0.6723, + "step": 1143 + }, + { + "epoch": 0.09, + "learning_rate": 1.937853107344633e-05, + "loss": 0.6481, + "step": 1144 + }, + { + "epoch": 0.09, + "learning_rate": 1.9377987831377662e-05, + "loss": 0.7374, + "step": 1145 + }, + { + "epoch": 0.09, + "learning_rate": 1.9377444589309e-05, + "loss": 0.9031, + "step": 1146 + }, + { + "epoch": 0.09, + "learning_rate": 1.937690134724033e-05, + "loss": 0.5178, + "step": 1147 + }, + { + "epoch": 0.09, + "learning_rate": 1.9376358105171668e-05, + "loss": 0.4873, + "step": 1148 + }, + { + "epoch": 0.09, + "learning_rate": 1.9375814863103e-05, + "loss": 0.4529, + "step": 1149 + }, + { + "epoch": 0.09, + "learning_rate": 1.9375271621034336e-05, + "loss": 0.7294, + "step": 1150 + }, + { + "epoch": 0.09, + "learning_rate": 1.9374728378965667e-05, + "loss": 0.6552, + "step": 1151 + }, + { + "epoch": 0.09, + "learning_rate": 1.9374185136897005e-05, + "loss": 0.5767, + "step": 1152 + }, + { + "epoch": 0.09, + "learning_rate": 1.9373641894828336e-05, + "loss": 0.6654, + "step": 1153 + }, + { + "epoch": 0.09, + "learning_rate": 1.9373098652759673e-05, + "loss": 0.7053, + "step": 1154 + }, + { + "epoch": 0.09, + "learning_rate": 1.9372555410691004e-05, + "loss": 0.6056, + "step": 1155 + }, + { + "epoch": 0.09, + "learning_rate": 1.937201216862234e-05, + "loss": 0.7567, + "step": 1156 + }, + { + "epoch": 0.09, + "learning_rate": 1.9371468926553672e-05, + "loss": 0.7456, + "step": 1157 + }, + { + "epoch": 0.09, + "learning_rate": 1.937092568448501e-05, + "loss": 0.4868, + "step": 1158 + }, + { + "epoch": 0.09, + "learning_rate": 1.937038244241634e-05, + "loss": 0.4024, + "step": 1159 + }, + { + "epoch": 0.09, + "learning_rate": 1.936983920034768e-05, + "loss": 0.6605, + "step": 1160 + }, + { + "epoch": 0.09, + "learning_rate": 1.936929595827901e-05, + "loss": 0.682, + "step": 1161 + }, + { + "epoch": 0.09, + "learning_rate": 1.9368752716210344e-05, + "loss": 0.5014, + "step": 1162 + }, + { + "epoch": 0.09, + "learning_rate": 1.9368209474141678e-05, + "loss": 0.6417, + "step": 1163 + }, + { + "epoch": 0.09, + "learning_rate": 1.9367666232073012e-05, + "loss": 0.6281, + "step": 1164 + }, + { + "epoch": 0.09, + "learning_rate": 1.9367122990004346e-05, + "loss": 0.6535, + "step": 1165 + }, + { + "epoch": 0.1, + "learning_rate": 1.936657974793568e-05, + "loss": 0.458, + "step": 1166 + }, + { + "epoch": 0.1, + "learning_rate": 1.9366036505867015e-05, + "loss": 0.5862, + "step": 1167 + }, + { + "epoch": 0.1, + "learning_rate": 1.936549326379835e-05, + "loss": 0.5165, + "step": 1168 + }, + { + "epoch": 0.1, + "learning_rate": 1.9364950021729683e-05, + "loss": 0.634, + "step": 1169 + }, + { + "epoch": 0.1, + "learning_rate": 1.9364406779661017e-05, + "loss": 0.5778, + "step": 1170 + }, + { + "epoch": 0.1, + "learning_rate": 1.9363863537592352e-05, + "loss": 0.556, + "step": 1171 + }, + { + "epoch": 0.1, + "learning_rate": 1.9363320295523686e-05, + "loss": 0.554, + "step": 1172 + }, + { + "epoch": 0.1, + "learning_rate": 1.9362777053455024e-05, + "loss": 0.5501, + "step": 1173 + }, + { + "epoch": 0.1, + "learning_rate": 1.9362233811386354e-05, + "loss": 0.8742, + "step": 1174 + }, + { + "epoch": 0.1, + "learning_rate": 1.9361690569317692e-05, + "loss": 0.6219, + "step": 1175 + }, + { + "epoch": 0.1, + "learning_rate": 1.9361147327249023e-05, + "loss": 0.5972, + "step": 1176 + }, + { + "epoch": 0.1, + "learning_rate": 1.936060408518036e-05, + "loss": 0.4328, + "step": 1177 + }, + { + "epoch": 0.1, + "learning_rate": 1.936006084311169e-05, + "loss": 0.5576, + "step": 1178 + }, + { + "epoch": 0.1, + "learning_rate": 1.935951760104303e-05, + "loss": 0.3757, + "step": 1179 + }, + { + "epoch": 0.1, + "learning_rate": 1.935897435897436e-05, + "loss": 0.4968, + "step": 1180 + }, + { + "epoch": 0.1, + "learning_rate": 1.9358431116905694e-05, + "loss": 0.6056, + "step": 1181 + }, + { + "epoch": 0.1, + "learning_rate": 1.9357887874837028e-05, + "loss": 0.4848, + "step": 1182 + }, + { + "epoch": 0.1, + "learning_rate": 1.9357344632768362e-05, + "loss": 0.7664, + "step": 1183 + }, + { + "epoch": 0.1, + "learning_rate": 1.9356801390699697e-05, + "loss": 0.989, + "step": 1184 + }, + { + "epoch": 0.1, + "learning_rate": 1.935625814863103e-05, + "loss": 0.5183, + "step": 1185 + }, + { + "epoch": 0.1, + "learning_rate": 1.9355714906562365e-05, + "loss": 0.5134, + "step": 1186 + }, + { + "epoch": 0.1, + "learning_rate": 1.93551716644937e-05, + "loss": 0.6612, + "step": 1187 + }, + { + "epoch": 0.1, + "learning_rate": 1.9354628422425034e-05, + "loss": 0.7194, + "step": 1188 + }, + { + "epoch": 0.1, + "learning_rate": 1.9354085180356368e-05, + "loss": 0.5155, + "step": 1189 + }, + { + "epoch": 0.1, + "learning_rate": 1.9353541938287702e-05, + "loss": 0.7665, + "step": 1190 + }, + { + "epoch": 0.1, + "learning_rate": 1.9352998696219036e-05, + "loss": 0.7799, + "step": 1191 + }, + { + "epoch": 0.1, + "learning_rate": 1.935245545415037e-05, + "loss": 0.5714, + "step": 1192 + }, + { + "epoch": 0.1, + "learning_rate": 1.9351912212081705e-05, + "loss": 0.2878, + "step": 1193 + }, + { + "epoch": 0.1, + "learning_rate": 1.935136897001304e-05, + "loss": 0.7468, + "step": 1194 + }, + { + "epoch": 0.1, + "learning_rate": 1.9350825727944373e-05, + "loss": 0.6126, + "step": 1195 + }, + { + "epoch": 0.1, + "learning_rate": 1.9350282485875707e-05, + "loss": 0.6041, + "step": 1196 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349739243807042e-05, + "loss": 0.4368, + "step": 1197 + }, + { + "epoch": 0.1, + "learning_rate": 1.9349196001738376e-05, + "loss": 0.8515, + "step": 1198 + }, + { + "epoch": 0.1, + "learning_rate": 1.934865275966971e-05, + "loss": 0.374, + "step": 1199 + }, + { + "epoch": 0.1, + "learning_rate": 1.9348109517601044e-05, + "loss": 0.8332, + "step": 1200 + }, + { + "epoch": 0.1, + "learning_rate": 1.934756627553238e-05, + "loss": 0.6691, + "step": 1201 + }, + { + "epoch": 0.1, + "learning_rate": 1.9347023033463713e-05, + "loss": 0.6579, + "step": 1202 + }, + { + "epoch": 0.1, + "learning_rate": 1.9346479791395047e-05, + "loss": 0.6445, + "step": 1203 + }, + { + "epoch": 0.1, + "learning_rate": 1.934593654932638e-05, + "loss": 0.5471, + "step": 1204 + }, + { + "epoch": 0.1, + "learning_rate": 1.9345393307257716e-05, + "loss": 0.492, + "step": 1205 + }, + { + "epoch": 0.1, + "learning_rate": 1.934485006518905e-05, + "loss": 0.5918, + "step": 1206 + }, + { + "epoch": 0.1, + "learning_rate": 1.9344306823120384e-05, + "loss": 0.502, + "step": 1207 + }, + { + "epoch": 0.1, + "learning_rate": 1.9343763581051718e-05, + "loss": 0.6219, + "step": 1208 + }, + { + "epoch": 0.1, + "learning_rate": 1.9343220338983052e-05, + "loss": 0.5991, + "step": 1209 + }, + { + "epoch": 0.1, + "learning_rate": 1.9342677096914387e-05, + "loss": 0.543, + "step": 1210 + }, + { + "epoch": 0.1, + "learning_rate": 1.934213385484572e-05, + "loss": 0.7046, + "step": 1211 + }, + { + "epoch": 0.1, + "learning_rate": 1.9341590612777055e-05, + "loss": 0.7643, + "step": 1212 + }, + { + "epoch": 0.1, + "learning_rate": 1.934104737070839e-05, + "loss": 0.7554, + "step": 1213 + }, + { + "epoch": 0.1, + "learning_rate": 1.9340504128639724e-05, + "loss": 0.6427, + "step": 1214 + }, + { + "epoch": 0.1, + "learning_rate": 1.9339960886571058e-05, + "loss": 0.4957, + "step": 1215 + }, + { + "epoch": 0.1, + "learning_rate": 1.9339417644502392e-05, + "loss": 0.6135, + "step": 1216 + }, + { + "epoch": 0.1, + "learning_rate": 1.9338874402433726e-05, + "loss": 0.3757, + "step": 1217 + }, + { + "epoch": 0.1, + "learning_rate": 1.933833116036506e-05, + "loss": 0.8907, + "step": 1218 + }, + { + "epoch": 0.1, + "learning_rate": 1.9337787918296395e-05, + "loss": 0.5362, + "step": 1219 + }, + { + "epoch": 0.1, + "learning_rate": 1.933724467622773e-05, + "loss": 0.8098, + "step": 1220 + }, + { + "epoch": 0.1, + "learning_rate": 1.9336701434159063e-05, + "loss": 0.5494, + "step": 1221 + }, + { + "epoch": 0.1, + "learning_rate": 1.9336158192090397e-05, + "loss": 0.6101, + "step": 1222 + }, + { + "epoch": 0.1, + "learning_rate": 1.9335614950021732e-05, + "loss": 0.4752, + "step": 1223 + }, + { + "epoch": 0.1, + "learning_rate": 1.9335071707953066e-05, + "loss": 0.5257, + "step": 1224 + }, + { + "epoch": 0.1, + "learning_rate": 1.93345284658844e-05, + "loss": 0.5216, + "step": 1225 + }, + { + "epoch": 0.1, + "learning_rate": 1.9333985223815734e-05, + "loss": 0.7064, + "step": 1226 + }, + { + "epoch": 0.1, + "learning_rate": 1.933344198174707e-05, + "loss": 0.7524, + "step": 1227 + }, + { + "epoch": 0.1, + "learning_rate": 1.9332898739678403e-05, + "loss": 0.9497, + "step": 1228 + }, + { + "epoch": 0.1, + "learning_rate": 1.9332355497609737e-05, + "loss": 0.5575, + "step": 1229 + }, + { + "epoch": 0.1, + "learning_rate": 1.933181225554107e-05, + "loss": 0.6844, + "step": 1230 + }, + { + "epoch": 0.1, + "learning_rate": 1.9331269013472406e-05, + "loss": 0.6267, + "step": 1231 + }, + { + "epoch": 0.1, + "learning_rate": 1.933072577140374e-05, + "loss": 0.4928, + "step": 1232 + }, + { + "epoch": 0.1, + "learning_rate": 1.9330182529335074e-05, + "loss": 0.5025, + "step": 1233 + }, + { + "epoch": 0.1, + "learning_rate": 1.9329639287266408e-05, + "loss": 0.6032, + "step": 1234 + }, + { + "epoch": 0.1, + "learning_rate": 1.9329096045197742e-05, + "loss": 0.504, + "step": 1235 + }, + { + "epoch": 0.1, + "learning_rate": 1.9328552803129077e-05, + "loss": 0.3931, + "step": 1236 + }, + { + "epoch": 0.1, + "learning_rate": 1.932800956106041e-05, + "loss": 0.7326, + "step": 1237 + }, + { + "epoch": 0.1, + "learning_rate": 1.9327466318991742e-05, + "loss": 0.5873, + "step": 1238 + }, + { + "epoch": 0.1, + "learning_rate": 1.932692307692308e-05, + "loss": 0.4407, + "step": 1239 + }, + { + "epoch": 0.1, + "learning_rate": 1.932637983485441e-05, + "loss": 0.4965, + "step": 1240 + }, + { + "epoch": 0.1, + "learning_rate": 1.9325836592785748e-05, + "loss": 0.5974, + "step": 1241 + }, + { + "epoch": 0.1, + "learning_rate": 1.932529335071708e-05, + "loss": 0.5708, + "step": 1242 + }, + { + "epoch": 0.1, + "learning_rate": 1.9324750108648416e-05, + "loss": 0.4534, + "step": 1243 + }, + { + "epoch": 0.1, + "learning_rate": 1.932420686657975e-05, + "loss": 0.5736, + "step": 1244 + }, + { + "epoch": 0.1, + "learning_rate": 1.9323663624511085e-05, + "loss": 0.723, + "step": 1245 + }, + { + "epoch": 0.1, + "learning_rate": 1.932312038244242e-05, + "loss": 0.6638, + "step": 1246 + }, + { + "epoch": 0.1, + "learning_rate": 1.9322577140373753e-05, + "loss": 0.67, + "step": 1247 + }, + { + "epoch": 0.1, + "learning_rate": 1.9322033898305087e-05, + "loss": 0.3431, + "step": 1248 + }, + { + "epoch": 0.1, + "learning_rate": 1.9321490656236422e-05, + "loss": 0.5145, + "step": 1249 + }, + { + "epoch": 0.1, + "learning_rate": 1.9320947414167756e-05, + "loss": 0.5987, + "step": 1250 + }, + { + "epoch": 0.1, + "eval_accuracy": 0.7777890983188996, + "eval_loss": 0.5644528269767761, + "eval_runtime": 22.2242, + "eval_samples_per_second": 441.635, + "eval_steps_per_second": 3.465, + "step": 1250 + }, + { + "epoch": 0.1, + "learning_rate": 1.932040417209909e-05, + "loss": 0.5857, + "step": 1251 + }, + { + "epoch": 0.1, + "learning_rate": 1.9319860930030424e-05, + "loss": 0.5692, + "step": 1252 + }, + { + "epoch": 0.1, + "learning_rate": 1.931931768796176e-05, + "loss": 0.4871, + "step": 1253 + }, + { + "epoch": 0.1, + "learning_rate": 1.9318774445893093e-05, + "loss": 0.5829, + "step": 1254 + }, + { + "epoch": 0.1, + "learning_rate": 1.9318231203824427e-05, + "loss": 0.5723, + "step": 1255 + }, + { + "epoch": 0.1, + "learning_rate": 1.931768796175576e-05, + "loss": 0.552, + "step": 1256 + }, + { + "epoch": 0.1, + "learning_rate": 1.9317144719687092e-05, + "loss": 0.7541, + "step": 1257 + }, + { + "epoch": 0.1, + "learning_rate": 1.931660147761843e-05, + "loss": 0.7154, + "step": 1258 + }, + { + "epoch": 0.1, + "learning_rate": 1.931605823554976e-05, + "loss": 0.6163, + "step": 1259 + }, + { + "epoch": 0.1, + "learning_rate": 1.9315514993481098e-05, + "loss": 0.569, + "step": 1260 + }, + { + "epoch": 0.1, + "learning_rate": 1.931497175141243e-05, + "loss": 0.5366, + "step": 1261 + }, + { + "epoch": 0.1, + "learning_rate": 1.9314428509343767e-05, + "loss": 0.4588, + "step": 1262 + }, + { + "epoch": 0.1, + "learning_rate": 1.9313885267275098e-05, + "loss": 0.5974, + "step": 1263 + }, + { + "epoch": 0.1, + "learning_rate": 1.9313342025206435e-05, + "loss": 0.5063, + "step": 1264 + }, + { + "epoch": 0.1, + "learning_rate": 1.9312798783137766e-05, + "loss": 0.5309, + "step": 1265 + }, + { + "epoch": 0.1, + "learning_rate": 1.9312255541069104e-05, + "loss": 0.642, + "step": 1266 + }, + { + "epoch": 0.1, + "learning_rate": 1.9311712299000434e-05, + "loss": 0.3882, + "step": 1267 + }, + { + "epoch": 0.1, + "learning_rate": 1.9311169056931772e-05, + "loss": 0.547, + "step": 1268 + }, + { + "epoch": 0.1, + "learning_rate": 1.9310625814863103e-05, + "loss": 0.5729, + "step": 1269 + }, + { + "epoch": 0.1, + "learning_rate": 1.931008257279444e-05, + "loss": 0.6571, + "step": 1270 + }, + { + "epoch": 0.1, + "learning_rate": 1.930953933072577e-05, + "loss": 0.5522, + "step": 1271 + }, + { + "epoch": 0.1, + "learning_rate": 1.930899608865711e-05, + "loss": 0.7557, + "step": 1272 + }, + { + "epoch": 0.1, + "learning_rate": 1.930845284658844e-05, + "loss": 0.532, + "step": 1273 + }, + { + "epoch": 0.1, + "learning_rate": 1.9307909604519777e-05, + "loss": 0.537, + "step": 1274 + }, + { + "epoch": 0.1, + "learning_rate": 1.930736636245111e-05, + "loss": 0.395, + "step": 1275 + }, + { + "epoch": 0.1, + "learning_rate": 1.9306823120382443e-05, + "loss": 0.6806, + "step": 1276 + }, + { + "epoch": 0.1, + "learning_rate": 1.9306279878313777e-05, + "loss": 0.9269, + "step": 1277 + }, + { + "epoch": 0.1, + "learning_rate": 1.930573663624511e-05, + "loss": 0.8018, + "step": 1278 + }, + { + "epoch": 0.1, + "learning_rate": 1.9305193394176445e-05, + "loss": 0.5995, + "step": 1279 + }, + { + "epoch": 0.1, + "learning_rate": 1.930465015210778e-05, + "loss": 0.4104, + "step": 1280 + }, + { + "epoch": 0.1, + "learning_rate": 1.9304106910039117e-05, + "loss": 0.6036, + "step": 1281 + }, + { + "epoch": 0.1, + "learning_rate": 1.9303563667970448e-05, + "loss": 0.5679, + "step": 1282 + }, + { + "epoch": 0.1, + "learning_rate": 1.9303020425901786e-05, + "loss": 0.7165, + "step": 1283 + }, + { + "epoch": 0.1, + "learning_rate": 1.9302477183833116e-05, + "loss": 0.4492, + "step": 1284 + }, + { + "epoch": 0.1, + "learning_rate": 1.9301933941764454e-05, + "loss": 0.778, + "step": 1285 + }, + { + "epoch": 0.1, + "learning_rate": 1.9301390699695785e-05, + "loss": 0.612, + "step": 1286 + }, + { + "epoch": 0.1, + "learning_rate": 1.9300847457627122e-05, + "loss": 0.7005, + "step": 1287 + }, + { + "epoch": 0.1, + "learning_rate": 1.9300304215558453e-05, + "loss": 0.6385, + "step": 1288 + }, + { + "epoch": 0.11, + "learning_rate": 1.929976097348979e-05, + "loss": 0.4993, + "step": 1289 + }, + { + "epoch": 0.11, + "learning_rate": 1.9299217731421122e-05, + "loss": 0.6537, + "step": 1290 + }, + { + "epoch": 0.11, + "learning_rate": 1.929867448935246e-05, + "loss": 0.8114, + "step": 1291 + }, + { + "epoch": 0.11, + "learning_rate": 1.929813124728379e-05, + "loss": 0.6452, + "step": 1292 + }, + { + "epoch": 0.11, + "learning_rate": 1.9297588005215128e-05, + "loss": 0.6189, + "step": 1293 + }, + { + "epoch": 0.11, + "learning_rate": 1.929704476314646e-05, + "loss": 0.6238, + "step": 1294 + }, + { + "epoch": 0.11, + "learning_rate": 1.9296501521077793e-05, + "loss": 0.4631, + "step": 1295 + }, + { + "epoch": 0.11, + "learning_rate": 1.9295958279009127e-05, + "loss": 0.4902, + "step": 1296 + }, + { + "epoch": 0.11, + "learning_rate": 1.929541503694046e-05, + "loss": 0.426, + "step": 1297 + }, + { + "epoch": 0.11, + "learning_rate": 1.9294871794871796e-05, + "loss": 0.6049, + "step": 1298 + }, + { + "epoch": 0.11, + "learning_rate": 1.929432855280313e-05, + "loss": 0.4335, + "step": 1299 + }, + { + "epoch": 0.11, + "learning_rate": 1.9293785310734464e-05, + "loss": 0.5495, + "step": 1300 + }, + { + "epoch": 0.11, + "learning_rate": 1.9293242068665798e-05, + "loss": 0.5979, + "step": 1301 + }, + { + "epoch": 0.11, + "learning_rate": 1.9292698826597133e-05, + "loss": 0.5574, + "step": 1302 + }, + { + "epoch": 0.11, + "learning_rate": 1.9292155584528467e-05, + "loss": 0.4294, + "step": 1303 + }, + { + "epoch": 0.11, + "learning_rate": 1.92916123424598e-05, + "loss": 0.6887, + "step": 1304 + }, + { + "epoch": 0.11, + "learning_rate": 1.9291069100391135e-05, + "loss": 0.7058, + "step": 1305 + }, + { + "epoch": 0.11, + "learning_rate": 1.929052585832247e-05, + "loss": 0.6838, + "step": 1306 + }, + { + "epoch": 0.11, + "learning_rate": 1.9289982616253804e-05, + "loss": 0.548, + "step": 1307 + }, + { + "epoch": 0.11, + "learning_rate": 1.9289439374185138e-05, + "loss": 0.582, + "step": 1308 + }, + { + "epoch": 0.11, + "learning_rate": 1.9288896132116472e-05, + "loss": 0.9555, + "step": 1309 + }, + { + "epoch": 0.11, + "learning_rate": 1.9288352890047806e-05, + "loss": 0.2935, + "step": 1310 + }, + { + "epoch": 0.11, + "learning_rate": 1.928780964797914e-05, + "loss": 0.8134, + "step": 1311 + }, + { + "epoch": 0.11, + "learning_rate": 1.9287266405910475e-05, + "loss": 0.6783, + "step": 1312 + }, + { + "epoch": 0.11, + "learning_rate": 1.928672316384181e-05, + "loss": 0.5204, + "step": 1313 + }, + { + "epoch": 0.11, + "learning_rate": 1.9286179921773143e-05, + "loss": 0.502, + "step": 1314 + }, + { + "epoch": 0.11, + "learning_rate": 1.9285636679704478e-05, + "loss": 0.6265, + "step": 1315 + }, + { + "epoch": 0.11, + "learning_rate": 1.9285093437635812e-05, + "loss": 0.5671, + "step": 1316 + }, + { + "epoch": 0.11, + "learning_rate": 1.9284550195567146e-05, + "loss": 0.4639, + "step": 1317 + }, + { + "epoch": 0.11, + "learning_rate": 1.928400695349848e-05, + "loss": 0.5446, + "step": 1318 + }, + { + "epoch": 0.11, + "learning_rate": 1.9283463711429814e-05, + "loss": 0.6749, + "step": 1319 + }, + { + "epoch": 0.11, + "learning_rate": 1.928292046936115e-05, + "loss": 0.7047, + "step": 1320 + }, + { + "epoch": 0.11, + "learning_rate": 1.9282377227292483e-05, + "loss": 0.6725, + "step": 1321 + }, + { + "epoch": 0.11, + "learning_rate": 1.9281833985223817e-05, + "loss": 0.596, + "step": 1322 + }, + { + "epoch": 0.11, + "learning_rate": 1.928129074315515e-05, + "loss": 0.766, + "step": 1323 + }, + { + "epoch": 0.11, + "learning_rate": 1.9280747501086486e-05, + "loss": 0.6951, + "step": 1324 + }, + { + "epoch": 0.11, + "learning_rate": 1.928020425901782e-05, + "loss": 0.5169, + "step": 1325 + }, + { + "epoch": 0.11, + "learning_rate": 1.9279661016949154e-05, + "loss": 0.8392, + "step": 1326 + }, + { + "epoch": 0.11, + "learning_rate": 1.9279117774880488e-05, + "loss": 0.8493, + "step": 1327 + }, + { + "epoch": 0.11, + "learning_rate": 1.9278574532811823e-05, + "loss": 0.558, + "step": 1328 + }, + { + "epoch": 0.11, + "learning_rate": 1.9278031290743157e-05, + "loss": 0.5819, + "step": 1329 + }, + { + "epoch": 0.11, + "learning_rate": 1.927748804867449e-05, + "loss": 0.6954, + "step": 1330 + }, + { + "epoch": 0.11, + "learning_rate": 1.9276944806605825e-05, + "loss": 0.7829, + "step": 1331 + }, + { + "epoch": 0.11, + "learning_rate": 1.927640156453716e-05, + "loss": 0.5345, + "step": 1332 + }, + { + "epoch": 0.11, + "learning_rate": 1.9275858322468494e-05, + "loss": 0.4824, + "step": 1333 + }, + { + "epoch": 0.11, + "learning_rate": 1.9275315080399828e-05, + "loss": 0.5506, + "step": 1334 + }, + { + "epoch": 0.11, + "learning_rate": 1.9274771838331162e-05, + "loss": 0.7442, + "step": 1335 + }, + { + "epoch": 0.11, + "learning_rate": 1.9274228596262496e-05, + "loss": 0.3481, + "step": 1336 + }, + { + "epoch": 0.11, + "learning_rate": 1.927368535419383e-05, + "loss": 0.517, + "step": 1337 + }, + { + "epoch": 0.11, + "learning_rate": 1.9273142112125165e-05, + "loss": 0.5045, + "step": 1338 + }, + { + "epoch": 0.11, + "learning_rate": 1.92725988700565e-05, + "loss": 0.5083, + "step": 1339 + }, + { + "epoch": 0.11, + "learning_rate": 1.9272055627987833e-05, + "loss": 0.4747, + "step": 1340 + }, + { + "epoch": 0.11, + "learning_rate": 1.9271512385919168e-05, + "loss": 0.8445, + "step": 1341 + }, + { + "epoch": 0.11, + "learning_rate": 1.9270969143850502e-05, + "loss": 0.723, + "step": 1342 + }, + { + "epoch": 0.11, + "learning_rate": 1.9270425901781836e-05, + "loss": 0.6449, + "step": 1343 + }, + { + "epoch": 0.11, + "learning_rate": 1.926988265971317e-05, + "loss": 0.6059, + "step": 1344 + }, + { + "epoch": 0.11, + "learning_rate": 1.9269339417644504e-05, + "loss": 0.5109, + "step": 1345 + }, + { + "epoch": 0.11, + "learning_rate": 1.926879617557584e-05, + "loss": 0.6653, + "step": 1346 + }, + { + "epoch": 0.11, + "learning_rate": 1.9268252933507173e-05, + "loss": 0.5524, + "step": 1347 + }, + { + "epoch": 0.11, + "learning_rate": 1.9267709691438507e-05, + "loss": 0.4873, + "step": 1348 + }, + { + "epoch": 0.11, + "learning_rate": 1.926716644936984e-05, + "loss": 0.4244, + "step": 1349 + }, + { + "epoch": 0.11, + "learning_rate": 1.9266623207301176e-05, + "loss": 0.7961, + "step": 1350 + }, + { + "epoch": 0.11, + "learning_rate": 1.926607996523251e-05, + "loss": 0.6787, + "step": 1351 + }, + { + "epoch": 0.11, + "learning_rate": 1.9265536723163844e-05, + "loss": 0.7313, + "step": 1352 + }, + { + "epoch": 0.11, + "learning_rate": 1.9264993481095178e-05, + "loss": 0.7601, + "step": 1353 + }, + { + "epoch": 0.11, + "learning_rate": 1.9264450239026513e-05, + "loss": 0.5373, + "step": 1354 + }, + { + "epoch": 0.11, + "learning_rate": 1.9263906996957847e-05, + "loss": 0.4623, + "step": 1355 + }, + { + "epoch": 0.11, + "learning_rate": 1.926336375488918e-05, + "loss": 0.5269, + "step": 1356 + }, + { + "epoch": 0.11, + "learning_rate": 1.9262820512820515e-05, + "loss": 0.5069, + "step": 1357 + }, + { + "epoch": 0.11, + "learning_rate": 1.926227727075185e-05, + "loss": 0.5997, + "step": 1358 + }, + { + "epoch": 0.11, + "learning_rate": 1.9261734028683184e-05, + "loss": 0.5861, + "step": 1359 + }, + { + "epoch": 0.11, + "learning_rate": 1.9261190786614518e-05, + "loss": 0.4741, + "step": 1360 + }, + { + "epoch": 0.11, + "learning_rate": 1.9260647544545852e-05, + "loss": 0.4867, + "step": 1361 + }, + { + "epoch": 0.11, + "learning_rate": 1.9260104302477186e-05, + "loss": 0.3155, + "step": 1362 + }, + { + "epoch": 0.11, + "learning_rate": 1.925956106040852e-05, + "loss": 0.7292, + "step": 1363 + }, + { + "epoch": 0.11, + "learning_rate": 1.9259017818339855e-05, + "loss": 0.6705, + "step": 1364 + }, + { + "epoch": 0.11, + "learning_rate": 1.925847457627119e-05, + "loss": 0.2976, + "step": 1365 + }, + { + "epoch": 0.11, + "learning_rate": 1.9257931334202523e-05, + "loss": 0.6375, + "step": 1366 + }, + { + "epoch": 0.11, + "learning_rate": 1.9257388092133858e-05, + "loss": 0.416, + "step": 1367 + }, + { + "epoch": 0.11, + "learning_rate": 1.9256844850065192e-05, + "loss": 0.5378, + "step": 1368 + }, + { + "epoch": 0.11, + "learning_rate": 1.9256301607996526e-05, + "loss": 0.4532, + "step": 1369 + }, + { + "epoch": 0.11, + "learning_rate": 1.925575836592786e-05, + "loss": 0.5253, + "step": 1370 + }, + { + "epoch": 0.11, + "learning_rate": 1.925521512385919e-05, + "loss": 0.7605, + "step": 1371 + }, + { + "epoch": 0.11, + "learning_rate": 1.925467188179053e-05, + "loss": 0.5332, + "step": 1372 + }, + { + "epoch": 0.11, + "learning_rate": 1.925412863972186e-05, + "loss": 0.5713, + "step": 1373 + }, + { + "epoch": 0.11, + "learning_rate": 1.9253585397653197e-05, + "loss": 0.4887, + "step": 1374 + }, + { + "epoch": 0.11, + "learning_rate": 1.9253042155584528e-05, + "loss": 0.6122, + "step": 1375 + }, + { + "epoch": 0.11, + "learning_rate": 1.9252498913515866e-05, + "loss": 0.5057, + "step": 1376 + }, + { + "epoch": 0.11, + "learning_rate": 1.9251955671447196e-05, + "loss": 0.5078, + "step": 1377 + }, + { + "epoch": 0.11, + "learning_rate": 1.9251412429378534e-05, + "loss": 0.2481, + "step": 1378 + }, + { + "epoch": 0.11, + "learning_rate": 1.9250869187309865e-05, + "loss": 0.5096, + "step": 1379 + }, + { + "epoch": 0.11, + "learning_rate": 1.9250325945241203e-05, + "loss": 0.8285, + "step": 1380 + }, + { + "epoch": 0.11, + "learning_rate": 1.9249782703172533e-05, + "loss": 0.4766, + "step": 1381 + }, + { + "epoch": 0.11, + "learning_rate": 1.924923946110387e-05, + "loss": 0.5116, + "step": 1382 + }, + { + "epoch": 0.11, + "learning_rate": 1.9248696219035202e-05, + "loss": 0.5709, + "step": 1383 + }, + { + "epoch": 0.11, + "learning_rate": 1.924815297696654e-05, + "loss": 0.461, + "step": 1384 + }, + { + "epoch": 0.11, + "learning_rate": 1.924760973489787e-05, + "loss": 0.6054, + "step": 1385 + }, + { + "epoch": 0.11, + "learning_rate": 1.9247066492829208e-05, + "loss": 0.6004, + "step": 1386 + }, + { + "epoch": 0.11, + "learning_rate": 1.924652325076054e-05, + "loss": 0.9656, + "step": 1387 + }, + { + "epoch": 0.11, + "learning_rate": 1.9245980008691876e-05, + "loss": 0.5561, + "step": 1388 + }, + { + "epoch": 0.11, + "learning_rate": 1.924543676662321e-05, + "loss": 0.6676, + "step": 1389 + }, + { + "epoch": 0.11, + "learning_rate": 1.924489352455454e-05, + "loss": 0.5073, + "step": 1390 + }, + { + "epoch": 0.11, + "learning_rate": 1.924435028248588e-05, + "loss": 0.4744, + "step": 1391 + }, + { + "epoch": 0.11, + "learning_rate": 1.924380704041721e-05, + "loss": 0.4292, + "step": 1392 + }, + { + "epoch": 0.11, + "learning_rate": 1.9243263798348548e-05, + "loss": 0.7105, + "step": 1393 + }, + { + "epoch": 0.11, + "learning_rate": 1.924272055627988e-05, + "loss": 0.4644, + "step": 1394 + }, + { + "epoch": 0.11, + "learning_rate": 1.9242177314211216e-05, + "loss": 0.5103, + "step": 1395 + }, + { + "epoch": 0.11, + "learning_rate": 1.9241634072142547e-05, + "loss": 0.5031, + "step": 1396 + }, + { + "epoch": 0.11, + "learning_rate": 1.9241090830073884e-05, + "loss": 0.6106, + "step": 1397 + }, + { + "epoch": 0.11, + "learning_rate": 1.9240547588005215e-05, + "loss": 0.6582, + "step": 1398 + }, + { + "epoch": 0.11, + "learning_rate": 1.9240004345936553e-05, + "loss": 0.5677, + "step": 1399 + }, + { + "epoch": 0.11, + "learning_rate": 1.9239461103867884e-05, + "loss": 0.5808, + "step": 1400 + }, + { + "epoch": 0.11, + "learning_rate": 1.923891786179922e-05, + "loss": 0.4358, + "step": 1401 + }, + { + "epoch": 0.11, + "learning_rate": 1.9238374619730552e-05, + "loss": 0.6025, + "step": 1402 + }, + { + "epoch": 0.11, + "learning_rate": 1.923783137766189e-05, + "loss": 0.8745, + "step": 1403 + }, + { + "epoch": 0.11, + "learning_rate": 1.923728813559322e-05, + "loss": 0.5981, + "step": 1404 + }, + { + "epoch": 0.11, + "learning_rate": 1.9236744893524558e-05, + "loss": 0.5617, + "step": 1405 + }, + { + "epoch": 0.11, + "learning_rate": 1.923620165145589e-05, + "loss": 0.3188, + "step": 1406 + }, + { + "epoch": 0.11, + "learning_rate": 1.9235658409387227e-05, + "loss": 0.4749, + "step": 1407 + }, + { + "epoch": 0.11, + "learning_rate": 1.9235115167318558e-05, + "loss": 0.5932, + "step": 1408 + }, + { + "epoch": 0.11, + "learning_rate": 1.9234571925249892e-05, + "loss": 0.522, + "step": 1409 + }, + { + "epoch": 0.11, + "learning_rate": 1.9234028683181226e-05, + "loss": 0.6794, + "step": 1410 + }, + { + "epoch": 0.11, + "learning_rate": 1.923348544111256e-05, + "loss": 0.4237, + "step": 1411 + }, + { + "epoch": 0.12, + "learning_rate": 1.9232942199043895e-05, + "loss": 0.7226, + "step": 1412 + }, + { + "epoch": 0.12, + "learning_rate": 1.923239895697523e-05, + "loss": 0.5049, + "step": 1413 + }, + { + "epoch": 0.12, + "learning_rate": 1.9231855714906563e-05, + "loss": 0.8157, + "step": 1414 + }, + { + "epoch": 0.12, + "learning_rate": 1.9231312472837897e-05, + "loss": 0.5324, + "step": 1415 + }, + { + "epoch": 0.12, + "learning_rate": 1.923076923076923e-05, + "loss": 0.9086, + "step": 1416 + }, + { + "epoch": 0.12, + "learning_rate": 1.9230225988700566e-05, + "loss": 0.4774, + "step": 1417 + }, + { + "epoch": 0.12, + "learning_rate": 1.92296827466319e-05, + "loss": 0.4557, + "step": 1418 + }, + { + "epoch": 0.12, + "learning_rate": 1.9229139504563234e-05, + "loss": 0.3214, + "step": 1419 + }, + { + "epoch": 0.12, + "learning_rate": 1.922859626249457e-05, + "loss": 0.7989, + "step": 1420 + }, + { + "epoch": 0.12, + "learning_rate": 1.9228053020425903e-05, + "loss": 0.8306, + "step": 1421 + }, + { + "epoch": 0.12, + "learning_rate": 1.9227509778357237e-05, + "loss": 0.5342, + "step": 1422 + }, + { + "epoch": 0.12, + "learning_rate": 1.922696653628857e-05, + "loss": 0.4689, + "step": 1423 + }, + { + "epoch": 0.12, + "learning_rate": 1.9226423294219905e-05, + "loss": 0.6241, + "step": 1424 + }, + { + "epoch": 0.12, + "learning_rate": 1.922588005215124e-05, + "loss": 0.7644, + "step": 1425 + }, + { + "epoch": 0.12, + "learning_rate": 1.9225336810082577e-05, + "loss": 0.8703, + "step": 1426 + }, + { + "epoch": 0.12, + "learning_rate": 1.9224793568013908e-05, + "loss": 0.5111, + "step": 1427 + }, + { + "epoch": 0.12, + "learning_rate": 1.9224250325945242e-05, + "loss": 0.5671, + "step": 1428 + }, + { + "epoch": 0.12, + "learning_rate": 1.9223707083876576e-05, + "loss": 0.4906, + "step": 1429 + }, + { + "epoch": 0.12, + "learning_rate": 1.922316384180791e-05, + "loss": 0.7521, + "step": 1430 + }, + { + "epoch": 0.12, + "learning_rate": 1.9222620599739245e-05, + "loss": 0.6136, + "step": 1431 + }, + { + "epoch": 0.12, + "learning_rate": 1.922207735767058e-05, + "loss": 0.6108, + "step": 1432 + }, + { + "epoch": 0.12, + "learning_rate": 1.9221534115601913e-05, + "loss": 0.7222, + "step": 1433 + }, + { + "epoch": 0.12, + "learning_rate": 1.9220990873533248e-05, + "loss": 0.5872, + "step": 1434 + }, + { + "epoch": 0.12, + "learning_rate": 1.9220447631464582e-05, + "loss": 0.7917, + "step": 1435 + }, + { + "epoch": 0.12, + "learning_rate": 1.9219904389395916e-05, + "loss": 0.5502, + "step": 1436 + }, + { + "epoch": 0.12, + "learning_rate": 1.921936114732725e-05, + "loss": 0.7474, + "step": 1437 + }, + { + "epoch": 0.12, + "learning_rate": 1.9218817905258585e-05, + "loss": 0.588, + "step": 1438 + }, + { + "epoch": 0.12, + "learning_rate": 1.921827466318992e-05, + "loss": 0.3446, + "step": 1439 + }, + { + "epoch": 0.12, + "learning_rate": 1.9217731421121253e-05, + "loss": 0.636, + "step": 1440 + }, + { + "epoch": 0.12, + "learning_rate": 1.9217188179052587e-05, + "loss": 0.6596, + "step": 1441 + }, + { + "epoch": 0.12, + "learning_rate": 1.921664493698392e-05, + "loss": 0.5759, + "step": 1442 + }, + { + "epoch": 0.12, + "learning_rate": 1.9216101694915256e-05, + "loss": 0.4952, + "step": 1443 + }, + { + "epoch": 0.12, + "learning_rate": 1.921555845284659e-05, + "loss": 0.7719, + "step": 1444 + }, + { + "epoch": 0.12, + "learning_rate": 1.9215015210777924e-05, + "loss": 0.4576, + "step": 1445 + }, + { + "epoch": 0.12, + "learning_rate": 1.921447196870926e-05, + "loss": 0.5981, + "step": 1446 + }, + { + "epoch": 0.12, + "learning_rate": 1.9213928726640593e-05, + "loss": 0.5881, + "step": 1447 + }, + { + "epoch": 0.12, + "learning_rate": 1.9213385484571927e-05, + "loss": 0.5879, + "step": 1448 + }, + { + "epoch": 0.12, + "learning_rate": 1.921284224250326e-05, + "loss": 0.6785, + "step": 1449 + }, + { + "epoch": 0.12, + "learning_rate": 1.9212299000434595e-05, + "loss": 0.5262, + "step": 1450 + }, + { + "epoch": 0.12, + "learning_rate": 1.921175575836593e-05, + "loss": 0.5576, + "step": 1451 + }, + { + "epoch": 0.12, + "learning_rate": 1.9211212516297264e-05, + "loss": 0.5421, + "step": 1452 + }, + { + "epoch": 0.12, + "learning_rate": 1.9210669274228598e-05, + "loss": 0.5182, + "step": 1453 + }, + { + "epoch": 0.12, + "learning_rate": 1.9210126032159932e-05, + "loss": 0.6761, + "step": 1454 + }, + { + "epoch": 0.12, + "learning_rate": 1.9209582790091266e-05, + "loss": 0.4552, + "step": 1455 + }, + { + "epoch": 0.12, + "learning_rate": 1.92090395480226e-05, + "loss": 0.6874, + "step": 1456 + }, + { + "epoch": 0.12, + "learning_rate": 1.9208496305953935e-05, + "loss": 0.6327, + "step": 1457 + }, + { + "epoch": 0.12, + "learning_rate": 1.920795306388527e-05, + "loss": 0.3636, + "step": 1458 + }, + { + "epoch": 0.12, + "learning_rate": 1.9207409821816603e-05, + "loss": 0.9172, + "step": 1459 + }, + { + "epoch": 0.12, + "learning_rate": 1.9206866579747938e-05, + "loss": 0.5228, + "step": 1460 + }, + { + "epoch": 0.12, + "learning_rate": 1.9206323337679272e-05, + "loss": 0.7991, + "step": 1461 + }, + { + "epoch": 0.12, + "learning_rate": 1.9205780095610606e-05, + "loss": 0.5875, + "step": 1462 + }, + { + "epoch": 0.12, + "learning_rate": 1.920523685354194e-05, + "loss": 0.4356, + "step": 1463 + }, + { + "epoch": 0.12, + "learning_rate": 1.9204693611473274e-05, + "loss": 0.4489, + "step": 1464 + }, + { + "epoch": 0.12, + "learning_rate": 1.920415036940461e-05, + "loss": 0.6051, + "step": 1465 + }, + { + "epoch": 0.12, + "learning_rate": 1.9203607127335943e-05, + "loss": 0.4677, + "step": 1466 + }, + { + "epoch": 0.12, + "learning_rate": 1.9203063885267277e-05, + "loss": 0.6465, + "step": 1467 + }, + { + "epoch": 0.12, + "learning_rate": 1.920252064319861e-05, + "loss": 0.4389, + "step": 1468 + }, + { + "epoch": 0.12, + "learning_rate": 1.9201977401129946e-05, + "loss": 0.4557, + "step": 1469 + }, + { + "epoch": 0.12, + "learning_rate": 1.920143415906128e-05, + "loss": 0.7105, + "step": 1470 + }, + { + "epoch": 0.12, + "learning_rate": 1.9200890916992614e-05, + "loss": 0.6588, + "step": 1471 + }, + { + "epoch": 0.12, + "learning_rate": 1.920034767492395e-05, + "loss": 0.5143, + "step": 1472 + }, + { + "epoch": 0.12, + "learning_rate": 1.9199804432855283e-05, + "loss": 0.7725, + "step": 1473 + }, + { + "epoch": 0.12, + "learning_rate": 1.9199261190786617e-05, + "loss": 0.6182, + "step": 1474 + }, + { + "epoch": 0.12, + "learning_rate": 1.919871794871795e-05, + "loss": 0.5629, + "step": 1475 + }, + { + "epoch": 0.12, + "learning_rate": 1.9198174706649285e-05, + "loss": 1.0256, + "step": 1476 + }, + { + "epoch": 0.12, + "learning_rate": 1.919763146458062e-05, + "loss": 0.5352, + "step": 1477 + }, + { + "epoch": 0.12, + "learning_rate": 1.9197088222511954e-05, + "loss": 0.8398, + "step": 1478 + }, + { + "epoch": 0.12, + "learning_rate": 1.9196544980443288e-05, + "loss": 0.431, + "step": 1479 + }, + { + "epoch": 0.12, + "learning_rate": 1.9196001738374622e-05, + "loss": 0.4519, + "step": 1480 + }, + { + "epoch": 0.12, + "learning_rate": 1.9195458496305956e-05, + "loss": 0.4582, + "step": 1481 + }, + { + "epoch": 0.12, + "learning_rate": 1.919491525423729e-05, + "loss": 0.4439, + "step": 1482 + }, + { + "epoch": 0.12, + "learning_rate": 1.9194372012168625e-05, + "loss": 0.5484, + "step": 1483 + }, + { + "epoch": 0.12, + "learning_rate": 1.919382877009996e-05, + "loss": 0.418, + "step": 1484 + }, + { + "epoch": 0.12, + "learning_rate": 1.919328552803129e-05, + "loss": 0.5164, + "step": 1485 + }, + { + "epoch": 0.12, + "learning_rate": 1.9192742285962628e-05, + "loss": 0.5604, + "step": 1486 + }, + { + "epoch": 0.12, + "learning_rate": 1.919219904389396e-05, + "loss": 0.6261, + "step": 1487 + }, + { + "epoch": 0.12, + "learning_rate": 1.9191655801825296e-05, + "loss": 0.8268, + "step": 1488 + }, + { + "epoch": 0.12, + "learning_rate": 1.9191112559756627e-05, + "loss": 0.718, + "step": 1489 + }, + { + "epoch": 0.12, + "learning_rate": 1.9190569317687964e-05, + "loss": 0.6387, + "step": 1490 + }, + { + "epoch": 0.12, + "learning_rate": 1.9190026075619295e-05, + "loss": 0.5248, + "step": 1491 + }, + { + "epoch": 0.12, + "learning_rate": 1.9189482833550633e-05, + "loss": 0.4955, + "step": 1492 + }, + { + "epoch": 0.12, + "learning_rate": 1.9188939591481964e-05, + "loss": 0.6148, + "step": 1493 + }, + { + "epoch": 0.12, + "learning_rate": 1.91883963494133e-05, + "loss": 0.5335, + "step": 1494 + }, + { + "epoch": 0.12, + "learning_rate": 1.9187853107344632e-05, + "loss": 0.6401, + "step": 1495 + }, + { + "epoch": 0.12, + "learning_rate": 1.918730986527597e-05, + "loss": 0.5769, + "step": 1496 + }, + { + "epoch": 0.12, + "learning_rate": 1.9186766623207304e-05, + "loss": 0.5411, + "step": 1497 + }, + { + "epoch": 0.12, + "learning_rate": 1.918622338113864e-05, + "loss": 0.5629, + "step": 1498 + }, + { + "epoch": 0.12, + "learning_rate": 1.9185680139069973e-05, + "loss": 0.9022, + "step": 1499 + }, + { + "epoch": 0.12, + "learning_rate": 1.9185136897001307e-05, + "loss": 0.5483, + "step": 1500 + }, + { + "epoch": 0.12, + "eval_accuracy": 0.7811512990320937, + "eval_loss": 0.5577018857002258, + "eval_runtime": 22.2537, + "eval_samples_per_second": 441.051, + "eval_steps_per_second": 3.46, + "step": 1500 + }, + { + "epoch": 0.12, + "learning_rate": 1.918459365493264e-05, + "loss": 0.5276, + "step": 1501 + }, + { + "epoch": 0.12, + "learning_rate": 1.9184050412863975e-05, + "loss": 0.608, + "step": 1502 + }, + { + "epoch": 0.12, + "learning_rate": 1.918350717079531e-05, + "loss": 0.5554, + "step": 1503 + }, + { + "epoch": 0.12, + "learning_rate": 1.918296392872664e-05, + "loss": 0.4913, + "step": 1504 + }, + { + "epoch": 0.12, + "learning_rate": 1.9182420686657978e-05, + "loss": 0.4684, + "step": 1505 + }, + { + "epoch": 0.12, + "learning_rate": 1.918187744458931e-05, + "loss": 0.699, + "step": 1506 + }, + { + "epoch": 0.12, + "learning_rate": 1.9181334202520646e-05, + "loss": 0.8055, + "step": 1507 + }, + { + "epoch": 0.12, + "learning_rate": 1.9180790960451977e-05, + "loss": 0.75, + "step": 1508 + }, + { + "epoch": 0.12, + "learning_rate": 1.9180247718383315e-05, + "loss": 0.4246, + "step": 1509 + }, + { + "epoch": 0.12, + "learning_rate": 1.9179704476314646e-05, + "loss": 0.6593, + "step": 1510 + }, + { + "epoch": 0.12, + "learning_rate": 1.9179161234245983e-05, + "loss": 0.5251, + "step": 1511 + }, + { + "epoch": 0.12, + "learning_rate": 1.9178617992177314e-05, + "loss": 0.4421, + "step": 1512 + }, + { + "epoch": 0.12, + "learning_rate": 1.9178074750108652e-05, + "loss": 0.5745, + "step": 1513 + }, + { + "epoch": 0.12, + "learning_rate": 1.9177531508039983e-05, + "loss": 0.4938, + "step": 1514 + }, + { + "epoch": 0.12, + "learning_rate": 1.917698826597132e-05, + "loss": 0.4747, + "step": 1515 + }, + { + "epoch": 0.12, + "learning_rate": 1.917644502390265e-05, + "loss": 0.5908, + "step": 1516 + }, + { + "epoch": 0.12, + "learning_rate": 1.917590178183399e-05, + "loss": 0.5602, + "step": 1517 + }, + { + "epoch": 0.12, + "learning_rate": 1.917535853976532e-05, + "loss": 0.8426, + "step": 1518 + }, + { + "epoch": 0.12, + "learning_rate": 1.9174815297696657e-05, + "loss": 0.8475, + "step": 1519 + }, + { + "epoch": 0.12, + "learning_rate": 1.9174272055627988e-05, + "loss": 0.524, + "step": 1520 + }, + { + "epoch": 0.12, + "learning_rate": 1.9173728813559326e-05, + "loss": 0.3639, + "step": 1521 + }, + { + "epoch": 0.12, + "learning_rate": 1.9173185571490656e-05, + "loss": 0.4538, + "step": 1522 + }, + { + "epoch": 0.12, + "learning_rate": 1.917264232942199e-05, + "loss": 0.8569, + "step": 1523 + }, + { + "epoch": 0.12, + "learning_rate": 1.9172099087353325e-05, + "loss": 0.7227, + "step": 1524 + }, + { + "epoch": 0.12, + "learning_rate": 1.917155584528466e-05, + "loss": 0.6329, + "step": 1525 + }, + { + "epoch": 0.12, + "learning_rate": 1.9171012603215993e-05, + "loss": 0.5398, + "step": 1526 + }, + { + "epoch": 0.12, + "learning_rate": 1.9170469361147328e-05, + "loss": 0.5774, + "step": 1527 + }, + { + "epoch": 0.12, + "learning_rate": 1.9169926119078662e-05, + "loss": 0.6557, + "step": 1528 + }, + { + "epoch": 0.12, + "learning_rate": 1.9169382877009996e-05, + "loss": 0.4647, + "step": 1529 + }, + { + "epoch": 0.12, + "learning_rate": 1.916883963494133e-05, + "loss": 0.6876, + "step": 1530 + }, + { + "epoch": 0.12, + "learning_rate": 1.9168296392872665e-05, + "loss": 0.5143, + "step": 1531 + }, + { + "epoch": 0.12, + "learning_rate": 1.9167753150804e-05, + "loss": 0.6401, + "step": 1532 + }, + { + "epoch": 0.12, + "learning_rate": 1.9167209908735333e-05, + "loss": 0.6432, + "step": 1533 + }, + { + "epoch": 0.12, + "learning_rate": 1.916666666666667e-05, + "loss": 0.4564, + "step": 1534 + }, + { + "epoch": 0.13, + "learning_rate": 1.9166123424598e-05, + "loss": 0.5363, + "step": 1535 + }, + { + "epoch": 0.13, + "learning_rate": 1.916558018252934e-05, + "loss": 0.8398, + "step": 1536 + }, + { + "epoch": 0.13, + "learning_rate": 1.916503694046067e-05, + "loss": 0.6172, + "step": 1537 + }, + { + "epoch": 0.13, + "learning_rate": 1.9164493698392008e-05, + "loss": 0.3068, + "step": 1538 + }, + { + "epoch": 0.13, + "learning_rate": 1.916395045632334e-05, + "loss": 0.6077, + "step": 1539 + }, + { + "epoch": 0.13, + "learning_rate": 1.9163407214254676e-05, + "loss": 0.5825, + "step": 1540 + }, + { + "epoch": 0.13, + "learning_rate": 1.9162863972186007e-05, + "loss": 0.6346, + "step": 1541 + }, + { + "epoch": 0.13, + "learning_rate": 1.916232073011734e-05, + "loss": 0.7291, + "step": 1542 + }, + { + "epoch": 0.13, + "learning_rate": 1.9161777488048675e-05, + "loss": 0.6474, + "step": 1543 + }, + { + "epoch": 0.13, + "learning_rate": 1.916123424598001e-05, + "loss": 0.5445, + "step": 1544 + }, + { + "epoch": 0.13, + "learning_rate": 1.9160691003911344e-05, + "loss": 0.7174, + "step": 1545 + }, + { + "epoch": 0.13, + "learning_rate": 1.9160147761842678e-05, + "loss": 0.5617, + "step": 1546 + }, + { + "epoch": 0.13, + "learning_rate": 1.9159604519774012e-05, + "loss": 0.4521, + "step": 1547 + }, + { + "epoch": 0.13, + "learning_rate": 1.9159061277705346e-05, + "loss": 0.6516, + "step": 1548 + }, + { + "epoch": 0.13, + "learning_rate": 1.915851803563668e-05, + "loss": 0.4621, + "step": 1549 + }, + { + "epoch": 0.13, + "learning_rate": 1.9157974793568015e-05, + "loss": 0.6519, + "step": 1550 + }, + { + "epoch": 0.13, + "learning_rate": 1.915743155149935e-05, + "loss": 0.491, + "step": 1551 + }, + { + "epoch": 0.13, + "learning_rate": 1.9156888309430683e-05, + "loss": 0.5231, + "step": 1552 + }, + { + "epoch": 0.13, + "learning_rate": 1.9156345067362018e-05, + "loss": 0.5283, + "step": 1553 + }, + { + "epoch": 0.13, + "learning_rate": 1.9155801825293352e-05, + "loss": 0.3841, + "step": 1554 + }, + { + "epoch": 0.13, + "learning_rate": 1.9155258583224686e-05, + "loss": 0.6534, + "step": 1555 + }, + { + "epoch": 0.13, + "learning_rate": 1.915471534115602e-05, + "loss": 0.5697, + "step": 1556 + }, + { + "epoch": 0.13, + "learning_rate": 1.9154172099087355e-05, + "loss": 0.646, + "step": 1557 + }, + { + "epoch": 0.13, + "learning_rate": 1.915362885701869e-05, + "loss": 0.5023, + "step": 1558 + }, + { + "epoch": 0.13, + "learning_rate": 1.9153085614950023e-05, + "loss": 0.6912, + "step": 1559 + }, + { + "epoch": 0.13, + "learning_rate": 1.9152542372881357e-05, + "loss": 0.7176, + "step": 1560 + }, + { + "epoch": 0.13, + "learning_rate": 1.915199913081269e-05, + "loss": 0.4756, + "step": 1561 + }, + { + "epoch": 0.13, + "learning_rate": 1.9151455888744026e-05, + "loss": 0.5735, + "step": 1562 + }, + { + "epoch": 0.13, + "learning_rate": 1.915091264667536e-05, + "loss": 0.8229, + "step": 1563 + }, + { + "epoch": 0.13, + "learning_rate": 1.9150369404606694e-05, + "loss": 0.5123, + "step": 1564 + }, + { + "epoch": 0.13, + "learning_rate": 1.914982616253803e-05, + "loss": 0.4953, + "step": 1565 + }, + { + "epoch": 0.13, + "learning_rate": 1.9149282920469363e-05, + "loss": 0.7009, + "step": 1566 + }, + { + "epoch": 0.13, + "learning_rate": 1.9148739678400697e-05, + "loss": 0.4042, + "step": 1567 + }, + { + "epoch": 0.13, + "learning_rate": 1.914819643633203e-05, + "loss": 0.5018, + "step": 1568 + }, + { + "epoch": 0.13, + "learning_rate": 1.9147653194263365e-05, + "loss": 0.693, + "step": 1569 + }, + { + "epoch": 0.13, + "learning_rate": 1.91471099521947e-05, + "loss": 0.5539, + "step": 1570 + }, + { + "epoch": 0.13, + "learning_rate": 1.9146566710126034e-05, + "loss": 0.4219, + "step": 1571 + }, + { + "epoch": 0.13, + "learning_rate": 1.9146023468057368e-05, + "loss": 0.404, + "step": 1572 + }, + { + "epoch": 0.13, + "learning_rate": 1.9145480225988702e-05, + "loss": 0.4174, + "step": 1573 + }, + { + "epoch": 0.13, + "learning_rate": 1.9144936983920036e-05, + "loss": 0.6907, + "step": 1574 + }, + { + "epoch": 0.13, + "learning_rate": 1.914439374185137e-05, + "loss": 0.6311, + "step": 1575 + }, + { + "epoch": 0.13, + "learning_rate": 1.9143850499782705e-05, + "loss": 0.3815, + "step": 1576 + }, + { + "epoch": 0.13, + "learning_rate": 1.914330725771404e-05, + "loss": 0.4979, + "step": 1577 + }, + { + "epoch": 0.13, + "learning_rate": 1.9142764015645373e-05, + "loss": 0.8332, + "step": 1578 + }, + { + "epoch": 0.13, + "learning_rate": 1.9142220773576708e-05, + "loss": 0.5368, + "step": 1579 + }, + { + "epoch": 0.13, + "learning_rate": 1.9141677531508042e-05, + "loss": 0.5639, + "step": 1580 + }, + { + "epoch": 0.13, + "learning_rate": 1.9141134289439376e-05, + "loss": 0.7687, + "step": 1581 + }, + { + "epoch": 0.13, + "learning_rate": 1.914059104737071e-05, + "loss": 0.5246, + "step": 1582 + }, + { + "epoch": 0.13, + "learning_rate": 1.9140047805302045e-05, + "loss": 0.4671, + "step": 1583 + }, + { + "epoch": 0.13, + "learning_rate": 1.913950456323338e-05, + "loss": 0.4278, + "step": 1584 + }, + { + "epoch": 0.13, + "learning_rate": 1.9138961321164713e-05, + "loss": 0.6332, + "step": 1585 + }, + { + "epoch": 0.13, + "learning_rate": 1.9138418079096047e-05, + "loss": 0.7786, + "step": 1586 + }, + { + "epoch": 0.13, + "learning_rate": 1.913787483702738e-05, + "loss": 0.4115, + "step": 1587 + }, + { + "epoch": 0.13, + "learning_rate": 1.9137331594958716e-05, + "loss": 0.5311, + "step": 1588 + }, + { + "epoch": 0.13, + "learning_rate": 1.913678835289005e-05, + "loss": 0.6896, + "step": 1589 + }, + { + "epoch": 0.13, + "learning_rate": 1.9136245110821384e-05, + "loss": 0.5623, + "step": 1590 + }, + { + "epoch": 0.13, + "learning_rate": 1.913570186875272e-05, + "loss": 0.6079, + "step": 1591 + }, + { + "epoch": 0.13, + "learning_rate": 1.9135158626684053e-05, + "loss": 0.4355, + "step": 1592 + }, + { + "epoch": 0.13, + "learning_rate": 1.9134615384615387e-05, + "loss": 0.5213, + "step": 1593 + }, + { + "epoch": 0.13, + "learning_rate": 1.913407214254672e-05, + "loss": 0.6607, + "step": 1594 + }, + { + "epoch": 0.13, + "learning_rate": 1.9133528900478055e-05, + "loss": 0.731, + "step": 1595 + }, + { + "epoch": 0.13, + "learning_rate": 1.913298565840939e-05, + "loss": 0.7925, + "step": 1596 + }, + { + "epoch": 0.13, + "learning_rate": 1.9132442416340724e-05, + "loss": 0.673, + "step": 1597 + }, + { + "epoch": 0.13, + "learning_rate": 1.9131899174272058e-05, + "loss": 0.6588, + "step": 1598 + }, + { + "epoch": 0.13, + "learning_rate": 1.913135593220339e-05, + "loss": 0.6996, + "step": 1599 + }, + { + "epoch": 0.13, + "learning_rate": 1.9130812690134726e-05, + "loss": 0.395, + "step": 1600 + }, + { + "epoch": 0.13, + "learning_rate": 1.9130269448066057e-05, + "loss": 0.4982, + "step": 1601 + }, + { + "epoch": 0.13, + "learning_rate": 1.9129726205997395e-05, + "loss": 0.553, + "step": 1602 + }, + { + "epoch": 0.13, + "learning_rate": 1.9129182963928726e-05, + "loss": 0.7848, + "step": 1603 + }, + { + "epoch": 0.13, + "learning_rate": 1.9128639721860063e-05, + "loss": 0.8085, + "step": 1604 + }, + { + "epoch": 0.13, + "learning_rate": 1.9128096479791398e-05, + "loss": 0.5613, + "step": 1605 + }, + { + "epoch": 0.13, + "learning_rate": 1.9127553237722732e-05, + "loss": 0.5566, + "step": 1606 + }, + { + "epoch": 0.13, + "learning_rate": 1.9127009995654066e-05, + "loss": 0.6788, + "step": 1607 + }, + { + "epoch": 0.13, + "learning_rate": 1.91264667535854e-05, + "loss": 0.5042, + "step": 1608 + }, + { + "epoch": 0.13, + "learning_rate": 1.9125923511516735e-05, + "loss": 0.5898, + "step": 1609 + }, + { + "epoch": 0.13, + "learning_rate": 1.912538026944807e-05, + "loss": 0.7356, + "step": 1610 + }, + { + "epoch": 0.13, + "learning_rate": 1.9124837027379403e-05, + "loss": 0.6591, + "step": 1611 + }, + { + "epoch": 0.13, + "learning_rate": 1.9124293785310737e-05, + "loss": 0.6666, + "step": 1612 + }, + { + "epoch": 0.13, + "learning_rate": 1.912375054324207e-05, + "loss": 0.5657, + "step": 1613 + }, + { + "epoch": 0.13, + "learning_rate": 1.9123207301173406e-05, + "loss": 0.5778, + "step": 1614 + }, + { + "epoch": 0.13, + "learning_rate": 1.912266405910474e-05, + "loss": 0.3975, + "step": 1615 + }, + { + "epoch": 0.13, + "learning_rate": 1.9122120817036074e-05, + "loss": 0.763, + "step": 1616 + }, + { + "epoch": 0.13, + "learning_rate": 1.912157757496741e-05, + "loss": 0.4127, + "step": 1617 + }, + { + "epoch": 0.13, + "learning_rate": 1.912103433289874e-05, + "loss": 0.5878, + "step": 1618 + }, + { + "epoch": 0.13, + "learning_rate": 1.9120491090830077e-05, + "loss": 0.7057, + "step": 1619 + }, + { + "epoch": 0.13, + "learning_rate": 1.9119947848761408e-05, + "loss": 1.0252, + "step": 1620 + }, + { + "epoch": 0.13, + "learning_rate": 1.9119404606692745e-05, + "loss": 0.2606, + "step": 1621 + }, + { + "epoch": 0.13, + "learning_rate": 1.9118861364624076e-05, + "loss": 0.3317, + "step": 1622 + }, + { + "epoch": 0.13, + "learning_rate": 1.9118318122555414e-05, + "loss": 0.6469, + "step": 1623 + }, + { + "epoch": 0.13, + "learning_rate": 1.9117774880486745e-05, + "loss": 0.6355, + "step": 1624 + }, + { + "epoch": 0.13, + "learning_rate": 1.9117231638418082e-05, + "loss": 0.7909, + "step": 1625 + }, + { + "epoch": 0.13, + "learning_rate": 1.9116688396349413e-05, + "loss": 0.4116, + "step": 1626 + }, + { + "epoch": 0.13, + "learning_rate": 1.911614515428075e-05, + "loss": 0.4224, + "step": 1627 + }, + { + "epoch": 0.13, + "learning_rate": 1.911560191221208e-05, + "loss": 0.6446, + "step": 1628 + }, + { + "epoch": 0.13, + "learning_rate": 1.911505867014342e-05, + "loss": 0.4371, + "step": 1629 + }, + { + "epoch": 0.13, + "learning_rate": 1.911451542807475e-05, + "loss": 0.4741, + "step": 1630 + }, + { + "epoch": 0.13, + "learning_rate": 1.9113972186006088e-05, + "loss": 0.3937, + "step": 1631 + }, + { + "epoch": 0.13, + "learning_rate": 1.911342894393742e-05, + "loss": 0.7184, + "step": 1632 + }, + { + "epoch": 0.13, + "learning_rate": 1.9112885701868756e-05, + "loss": 0.5004, + "step": 1633 + }, + { + "epoch": 0.13, + "learning_rate": 1.9112342459800087e-05, + "loss": 0.7336, + "step": 1634 + }, + { + "epoch": 0.13, + "learning_rate": 1.9111799217731425e-05, + "loss": 0.4949, + "step": 1635 + }, + { + "epoch": 0.13, + "learning_rate": 1.9111255975662755e-05, + "loss": 0.8193, + "step": 1636 + }, + { + "epoch": 0.13, + "learning_rate": 1.911071273359409e-05, + "loss": 0.3938, + "step": 1637 + }, + { + "epoch": 0.13, + "learning_rate": 1.9110169491525424e-05, + "loss": 0.5056, + "step": 1638 + }, + { + "epoch": 0.13, + "learning_rate": 1.9109626249456758e-05, + "loss": 0.4234, + "step": 1639 + }, + { + "epoch": 0.13, + "learning_rate": 1.9109083007388092e-05, + "loss": 0.6304, + "step": 1640 + }, + { + "epoch": 0.13, + "learning_rate": 1.9108539765319427e-05, + "loss": 0.6361, + "step": 1641 + }, + { + "epoch": 0.13, + "learning_rate": 1.9107996523250764e-05, + "loss": 0.3909, + "step": 1642 + }, + { + "epoch": 0.13, + "learning_rate": 1.9107453281182095e-05, + "loss": 0.3719, + "step": 1643 + }, + { + "epoch": 0.13, + "learning_rate": 1.9106910039113433e-05, + "loss": 0.5892, + "step": 1644 + }, + { + "epoch": 0.13, + "learning_rate": 1.9106366797044763e-05, + "loss": 0.3789, + "step": 1645 + }, + { + "epoch": 0.13, + "learning_rate": 1.91058235549761e-05, + "loss": 0.9452, + "step": 1646 + }, + { + "epoch": 0.13, + "learning_rate": 1.9105280312907432e-05, + "loss": 0.4302, + "step": 1647 + }, + { + "epoch": 0.13, + "learning_rate": 1.910473707083877e-05, + "loss": 0.4651, + "step": 1648 + }, + { + "epoch": 0.13, + "learning_rate": 1.91041938287701e-05, + "loss": 0.8509, + "step": 1649 + }, + { + "epoch": 0.13, + "learning_rate": 1.9103650586701438e-05, + "loss": 0.7113, + "step": 1650 + }, + { + "epoch": 0.13, + "learning_rate": 1.910310734463277e-05, + "loss": 0.5508, + "step": 1651 + }, + { + "epoch": 0.13, + "learning_rate": 1.9102564102564106e-05, + "loss": 0.3914, + "step": 1652 + }, + { + "epoch": 0.13, + "learning_rate": 1.9102020860495437e-05, + "loss": 0.6323, + "step": 1653 + }, + { + "epoch": 0.13, + "learning_rate": 1.9101477618426775e-05, + "loss": 0.4762, + "step": 1654 + }, + { + "epoch": 0.13, + "learning_rate": 1.9100934376358106e-05, + "loss": 0.955, + "step": 1655 + }, + { + "epoch": 0.13, + "learning_rate": 1.910039113428944e-05, + "loss": 0.7495, + "step": 1656 + }, + { + "epoch": 0.14, + "learning_rate": 1.9099847892220774e-05, + "loss": 0.4397, + "step": 1657 + }, + { + "epoch": 0.14, + "learning_rate": 1.909930465015211e-05, + "loss": 0.6212, + "step": 1658 + }, + { + "epoch": 0.14, + "learning_rate": 1.9098761408083443e-05, + "loss": 0.7101, + "step": 1659 + }, + { + "epoch": 0.14, + "learning_rate": 1.9098218166014777e-05, + "loss": 0.4154, + "step": 1660 + }, + { + "epoch": 0.14, + "learning_rate": 1.909767492394611e-05, + "loss": 0.4629, + "step": 1661 + }, + { + "epoch": 0.14, + "learning_rate": 1.9097131681877445e-05, + "loss": 0.4509, + "step": 1662 + }, + { + "epoch": 0.14, + "learning_rate": 1.909658843980878e-05, + "loss": 0.4826, + "step": 1663 + }, + { + "epoch": 0.14, + "learning_rate": 1.9096045197740114e-05, + "loss": 0.3799, + "step": 1664 + }, + { + "epoch": 0.14, + "learning_rate": 1.9095501955671448e-05, + "loss": 0.4911, + "step": 1665 + }, + { + "epoch": 0.14, + "learning_rate": 1.9094958713602782e-05, + "loss": 0.5117, + "step": 1666 + }, + { + "epoch": 0.14, + "learning_rate": 1.9094415471534117e-05, + "loss": 0.5432, + "step": 1667 + }, + { + "epoch": 0.14, + "learning_rate": 1.909387222946545e-05, + "loss": 0.6444, + "step": 1668 + }, + { + "epoch": 0.14, + "learning_rate": 1.9093328987396785e-05, + "loss": 0.885, + "step": 1669 + }, + { + "epoch": 0.14, + "learning_rate": 1.909278574532812e-05, + "loss": 0.6121, + "step": 1670 + }, + { + "epoch": 0.14, + "learning_rate": 1.9092242503259453e-05, + "loss": 0.2577, + "step": 1671 + }, + { + "epoch": 0.14, + "learning_rate": 1.9091699261190788e-05, + "loss": 0.4468, + "step": 1672 + }, + { + "epoch": 0.14, + "learning_rate": 1.9091156019122122e-05, + "loss": 0.4922, + "step": 1673 + }, + { + "epoch": 0.14, + "learning_rate": 1.9090612777053456e-05, + "loss": 0.4486, + "step": 1674 + }, + { + "epoch": 0.14, + "learning_rate": 1.909006953498479e-05, + "loss": 0.6201, + "step": 1675 + }, + { + "epoch": 0.14, + "learning_rate": 1.9089526292916125e-05, + "loss": 1.0144, + "step": 1676 + }, + { + "epoch": 0.14, + "learning_rate": 1.908898305084746e-05, + "loss": 0.9384, + "step": 1677 + }, + { + "epoch": 0.14, + "learning_rate": 1.9088439808778793e-05, + "loss": 0.9029, + "step": 1678 + }, + { + "epoch": 0.14, + "learning_rate": 1.9087896566710127e-05, + "loss": 0.6662, + "step": 1679 + }, + { + "epoch": 0.14, + "learning_rate": 1.908735332464146e-05, + "loss": 0.3916, + "step": 1680 + }, + { + "epoch": 0.14, + "learning_rate": 1.9086810082572796e-05, + "loss": 0.5105, + "step": 1681 + }, + { + "epoch": 0.14, + "learning_rate": 1.908626684050413e-05, + "loss": 0.5447, + "step": 1682 + }, + { + "epoch": 0.14, + "learning_rate": 1.9085723598435464e-05, + "loss": 0.3713, + "step": 1683 + }, + { + "epoch": 0.14, + "learning_rate": 1.90851803563668e-05, + "loss": 0.6935, + "step": 1684 + }, + { + "epoch": 0.14, + "learning_rate": 1.9084637114298133e-05, + "loss": 0.6033, + "step": 1685 + }, + { + "epoch": 0.14, + "learning_rate": 1.9084093872229467e-05, + "loss": 0.5965, + "step": 1686 + }, + { + "epoch": 0.14, + "learning_rate": 1.90835506301608e-05, + "loss": 0.3676, + "step": 1687 + }, + { + "epoch": 0.14, + "learning_rate": 1.9083007388092135e-05, + "loss": 0.5197, + "step": 1688 + }, + { + "epoch": 0.14, + "learning_rate": 1.908246414602347e-05, + "loss": 0.542, + "step": 1689 + }, + { + "epoch": 0.14, + "learning_rate": 1.9081920903954804e-05, + "loss": 0.7114, + "step": 1690 + }, + { + "epoch": 0.14, + "learning_rate": 1.9081377661886138e-05, + "loss": 0.516, + "step": 1691 + }, + { + "epoch": 0.14, + "learning_rate": 1.9080834419817472e-05, + "loss": 0.3686, + "step": 1692 + }, + { + "epoch": 0.14, + "learning_rate": 1.9080291177748807e-05, + "loss": 0.6329, + "step": 1693 + }, + { + "epoch": 0.14, + "learning_rate": 1.907974793568014e-05, + "loss": 0.4677, + "step": 1694 + }, + { + "epoch": 0.14, + "learning_rate": 1.9079204693611475e-05, + "loss": 0.5591, + "step": 1695 + }, + { + "epoch": 0.14, + "learning_rate": 1.907866145154281e-05, + "loss": 0.3347, + "step": 1696 + }, + { + "epoch": 0.14, + "learning_rate": 1.9078118209474143e-05, + "loss": 0.6172, + "step": 1697 + }, + { + "epoch": 0.14, + "learning_rate": 1.9077574967405478e-05, + "loss": 0.5583, + "step": 1698 + }, + { + "epoch": 0.14, + "learning_rate": 1.9077031725336812e-05, + "loss": 0.6818, + "step": 1699 + }, + { + "epoch": 0.14, + "learning_rate": 1.9076488483268146e-05, + "loss": 0.5377, + "step": 1700 + }, + { + "epoch": 0.14, + "learning_rate": 1.907594524119948e-05, + "loss": 0.5048, + "step": 1701 + }, + { + "epoch": 0.14, + "learning_rate": 1.9075401999130815e-05, + "loss": 0.769, + "step": 1702 + }, + { + "epoch": 0.14, + "learning_rate": 1.907485875706215e-05, + "loss": 0.4393, + "step": 1703 + }, + { + "epoch": 0.14, + "learning_rate": 1.9074315514993483e-05, + "loss": 0.4571, + "step": 1704 + }, + { + "epoch": 0.14, + "learning_rate": 1.9073772272924817e-05, + "loss": 0.7227, + "step": 1705 + }, + { + "epoch": 0.14, + "learning_rate": 1.907322903085615e-05, + "loss": 0.8721, + "step": 1706 + }, + { + "epoch": 0.14, + "learning_rate": 1.9072685788787486e-05, + "loss": 0.8199, + "step": 1707 + }, + { + "epoch": 0.14, + "learning_rate": 1.907214254671882e-05, + "loss": 0.7713, + "step": 1708 + }, + { + "epoch": 0.14, + "learning_rate": 1.9071599304650154e-05, + "loss": 0.6245, + "step": 1709 + }, + { + "epoch": 0.14, + "learning_rate": 1.907105606258149e-05, + "loss": 0.5551, + "step": 1710 + }, + { + "epoch": 0.14, + "learning_rate": 1.9070512820512823e-05, + "loss": 0.584, + "step": 1711 + }, + { + "epoch": 0.14, + "learning_rate": 1.9069969578444157e-05, + "loss": 0.5754, + "step": 1712 + }, + { + "epoch": 0.14, + "learning_rate": 1.906942633637549e-05, + "loss": 0.4779, + "step": 1713 + }, + { + "epoch": 0.14, + "learning_rate": 1.9068883094306825e-05, + "loss": 0.731, + "step": 1714 + }, + { + "epoch": 0.14, + "learning_rate": 1.906833985223816e-05, + "loss": 0.427, + "step": 1715 + }, + { + "epoch": 0.14, + "learning_rate": 1.9067796610169494e-05, + "loss": 0.5842, + "step": 1716 + }, + { + "epoch": 0.14, + "learning_rate": 1.9067253368100828e-05, + "loss": 0.652, + "step": 1717 + }, + { + "epoch": 0.14, + "learning_rate": 1.9066710126032162e-05, + "loss": 0.5781, + "step": 1718 + }, + { + "epoch": 0.14, + "learning_rate": 1.9066166883963497e-05, + "loss": 0.4461, + "step": 1719 + }, + { + "epoch": 0.14, + "learning_rate": 1.906562364189483e-05, + "loss": 0.5674, + "step": 1720 + }, + { + "epoch": 0.14, + "learning_rate": 1.9065080399826165e-05, + "loss": 0.6462, + "step": 1721 + }, + { + "epoch": 0.14, + "learning_rate": 1.90645371577575e-05, + "loss": 0.5017, + "step": 1722 + }, + { + "epoch": 0.14, + "learning_rate": 1.9063993915688833e-05, + "loss": 0.449, + "step": 1723 + }, + { + "epoch": 0.14, + "learning_rate": 1.9063450673620168e-05, + "loss": 0.396, + "step": 1724 + }, + { + "epoch": 0.14, + "learning_rate": 1.9062907431551502e-05, + "loss": 0.3983, + "step": 1725 + }, + { + "epoch": 0.14, + "learning_rate": 1.9062364189482836e-05, + "loss": 0.6554, + "step": 1726 + }, + { + "epoch": 0.14, + "learning_rate": 1.906182094741417e-05, + "loss": 0.5711, + "step": 1727 + }, + { + "epoch": 0.14, + "learning_rate": 1.9061277705345505e-05, + "loss": 0.5558, + "step": 1728 + }, + { + "epoch": 0.14, + "learning_rate": 1.906073446327684e-05, + "loss": 0.6741, + "step": 1729 + }, + { + "epoch": 0.14, + "learning_rate": 1.9060191221208173e-05, + "loss": 0.6511, + "step": 1730 + }, + { + "epoch": 0.14, + "learning_rate": 1.9059647979139507e-05, + "loss": 0.4485, + "step": 1731 + }, + { + "epoch": 0.14, + "learning_rate": 1.9059104737070838e-05, + "loss": 0.45, + "step": 1732 + }, + { + "epoch": 0.14, + "learning_rate": 1.9058561495002176e-05, + "loss": 0.6557, + "step": 1733 + }, + { + "epoch": 0.14, + "learning_rate": 1.9058018252933507e-05, + "loss": 0.5897, + "step": 1734 + }, + { + "epoch": 0.14, + "learning_rate": 1.9057475010864844e-05, + "loss": 0.5383, + "step": 1735 + }, + { + "epoch": 0.14, + "learning_rate": 1.9056931768796175e-05, + "loss": 0.456, + "step": 1736 + }, + { + "epoch": 0.14, + "learning_rate": 1.9056388526727513e-05, + "loss": 0.572, + "step": 1737 + }, + { + "epoch": 0.14, + "learning_rate": 1.9055845284658844e-05, + "loss": 0.7482, + "step": 1738 + }, + { + "epoch": 0.14, + "learning_rate": 1.905530204259018e-05, + "loss": 0.7573, + "step": 1739 + }, + { + "epoch": 0.14, + "learning_rate": 1.9054758800521512e-05, + "loss": 0.622, + "step": 1740 + }, + { + "epoch": 0.14, + "learning_rate": 1.905421555845285e-05, + "loss": 0.4233, + "step": 1741 + }, + { + "epoch": 0.14, + "learning_rate": 1.905367231638418e-05, + "loss": 0.609, + "step": 1742 + }, + { + "epoch": 0.14, + "learning_rate": 1.9053129074315518e-05, + "loss": 0.5005, + "step": 1743 + }, + { + "epoch": 0.14, + "learning_rate": 1.905258583224685e-05, + "loss": 0.4257, + "step": 1744 + }, + { + "epoch": 0.14, + "learning_rate": 1.9052042590178187e-05, + "loss": 0.5804, + "step": 1745 + }, + { + "epoch": 0.14, + "learning_rate": 1.9051499348109517e-05, + "loss": 0.6525, + "step": 1746 + }, + { + "epoch": 0.14, + "learning_rate": 1.9050956106040855e-05, + "loss": 0.4221, + "step": 1747 + }, + { + "epoch": 0.14, + "learning_rate": 1.9050412863972186e-05, + "loss": 0.6163, + "step": 1748 + }, + { + "epoch": 0.14, + "learning_rate": 1.9049869621903523e-05, + "loss": 0.705, + "step": 1749 + }, + { + "epoch": 0.14, + "learning_rate": 1.9049326379834858e-05, + "loss": 0.6213, + "step": 1750 + }, + { + "epoch": 0.14, + "eval_accuracy": 0.7866530820173204, + "eval_loss": 0.536614179611206, + "eval_runtime": 22.304, + "eval_samples_per_second": 440.055, + "eval_steps_per_second": 3.452, + "step": 1750 + }, + { + "epoch": 0.14, + "learning_rate": 1.904878313776619e-05, + "loss": 0.5631, + "step": 1751 + }, + { + "epoch": 0.14, + "learning_rate": 1.9048239895697526e-05, + "loss": 0.422, + "step": 1752 + }, + { + "epoch": 0.14, + "learning_rate": 1.9047696653628857e-05, + "loss": 0.6372, + "step": 1753 + }, + { + "epoch": 0.14, + "learning_rate": 1.9047153411560195e-05, + "loss": 0.9194, + "step": 1754 + }, + { + "epoch": 0.14, + "learning_rate": 1.9046610169491525e-05, + "loss": 0.5803, + "step": 1755 + }, + { + "epoch": 0.14, + "learning_rate": 1.9046066927422863e-05, + "loss": 0.3775, + "step": 1756 + }, + { + "epoch": 0.14, + "learning_rate": 1.9045523685354194e-05, + "loss": 0.4575, + "step": 1757 + }, + { + "epoch": 0.14, + "learning_rate": 1.904498044328553e-05, + "loss": 0.4108, + "step": 1758 + }, + { + "epoch": 0.14, + "learning_rate": 1.9044437201216862e-05, + "loss": 0.6679, + "step": 1759 + }, + { + "epoch": 0.14, + "learning_rate": 1.90438939591482e-05, + "loss": 0.6466, + "step": 1760 + }, + { + "epoch": 0.14, + "learning_rate": 1.904335071707953e-05, + "loss": 0.434, + "step": 1761 + }, + { + "epoch": 0.14, + "learning_rate": 1.904280747501087e-05, + "loss": 0.3698, + "step": 1762 + }, + { + "epoch": 0.14, + "learning_rate": 1.90422642329422e-05, + "loss": 0.331, + "step": 1763 + }, + { + "epoch": 0.14, + "learning_rate": 1.9041720990873537e-05, + "loss": 0.4747, + "step": 1764 + }, + { + "epoch": 0.14, + "learning_rate": 1.9041177748804868e-05, + "loss": 0.4068, + "step": 1765 + }, + { + "epoch": 0.14, + "learning_rate": 1.9040634506736205e-05, + "loss": 0.4529, + "step": 1766 + }, + { + "epoch": 0.14, + "learning_rate": 1.9040091264667536e-05, + "loss": 0.5747, + "step": 1767 + }, + { + "epoch": 0.14, + "learning_rate": 1.9039548022598874e-05, + "loss": 0.685, + "step": 1768 + }, + { + "epoch": 0.14, + "learning_rate": 1.9039004780530205e-05, + "loss": 0.5365, + "step": 1769 + }, + { + "epoch": 0.14, + "learning_rate": 1.903846153846154e-05, + "loss": 0.2469, + "step": 1770 + }, + { + "epoch": 0.14, + "learning_rate": 1.9037918296392873e-05, + "loss": 0.6757, + "step": 1771 + }, + { + "epoch": 0.14, + "learning_rate": 1.9037375054324207e-05, + "loss": 0.4533, + "step": 1772 + }, + { + "epoch": 0.14, + "learning_rate": 1.903683181225554e-05, + "loss": 0.6088, + "step": 1773 + }, + { + "epoch": 0.14, + "learning_rate": 1.9036288570186876e-05, + "loss": 0.66, + "step": 1774 + }, + { + "epoch": 0.14, + "learning_rate": 1.903574532811821e-05, + "loss": 0.6192, + "step": 1775 + }, + { + "epoch": 0.14, + "learning_rate": 1.9035202086049544e-05, + "loss": 0.3496, + "step": 1776 + }, + { + "epoch": 0.14, + "learning_rate": 1.903465884398088e-05, + "loss": 0.247, + "step": 1777 + }, + { + "epoch": 0.14, + "learning_rate": 1.9034115601912213e-05, + "loss": 0.7745, + "step": 1778 + }, + { + "epoch": 0.14, + "learning_rate": 1.9033572359843547e-05, + "loss": 0.5246, + "step": 1779 + }, + { + "epoch": 0.15, + "learning_rate": 1.903302911777488e-05, + "loss": 0.4874, + "step": 1780 + }, + { + "epoch": 0.15, + "learning_rate": 1.9032485875706215e-05, + "loss": 0.4294, + "step": 1781 + }, + { + "epoch": 0.15, + "learning_rate": 1.903194263363755e-05, + "loss": 0.3992, + "step": 1782 + }, + { + "epoch": 0.15, + "learning_rate": 1.9031399391568884e-05, + "loss": 0.5391, + "step": 1783 + }, + { + "epoch": 0.15, + "learning_rate": 1.9030856149500218e-05, + "loss": 0.4985, + "step": 1784 + }, + { + "epoch": 0.15, + "learning_rate": 1.9030312907431552e-05, + "loss": 0.6868, + "step": 1785 + }, + { + "epoch": 0.15, + "learning_rate": 1.9029769665362887e-05, + "loss": 0.6158, + "step": 1786 + }, + { + "epoch": 0.15, + "learning_rate": 1.9029226423294224e-05, + "loss": 0.5743, + "step": 1787 + }, + { + "epoch": 0.15, + "learning_rate": 1.9028683181225555e-05, + "loss": 0.5195, + "step": 1788 + }, + { + "epoch": 0.15, + "learning_rate": 1.902813993915689e-05, + "loss": 0.4266, + "step": 1789 + }, + { + "epoch": 0.15, + "learning_rate": 1.9027596697088223e-05, + "loss": 0.6132, + "step": 1790 + }, + { + "epoch": 0.15, + "learning_rate": 1.9027053455019558e-05, + "loss": 0.5922, + "step": 1791 + }, + { + "epoch": 0.15, + "learning_rate": 1.9026510212950892e-05, + "loss": 0.5317, + "step": 1792 + }, + { + "epoch": 0.15, + "learning_rate": 1.9025966970882226e-05, + "loss": 0.6591, + "step": 1793 + }, + { + "epoch": 0.15, + "learning_rate": 1.902542372881356e-05, + "loss": 0.5575, + "step": 1794 + }, + { + "epoch": 0.15, + "learning_rate": 1.9024880486744895e-05, + "loss": 0.5939, + "step": 1795 + }, + { + "epoch": 0.15, + "learning_rate": 1.902433724467623e-05, + "loss": 0.5703, + "step": 1796 + }, + { + "epoch": 0.15, + "learning_rate": 1.9023794002607563e-05, + "loss": 0.4113, + "step": 1797 + }, + { + "epoch": 0.15, + "learning_rate": 1.9023250760538897e-05, + "loss": 0.539, + "step": 1798 + }, + { + "epoch": 0.15, + "learning_rate": 1.902270751847023e-05, + "loss": 0.3564, + "step": 1799 + }, + { + "epoch": 0.15, + "learning_rate": 1.9022164276401566e-05, + "loss": 0.4359, + "step": 1800 + }, + { + "epoch": 0.15, + "learning_rate": 1.90216210343329e-05, + "loss": 0.5204, + "step": 1801 + }, + { + "epoch": 0.15, + "learning_rate": 1.9021077792264234e-05, + "loss": 0.3806, + "step": 1802 + }, + { + "epoch": 0.15, + "learning_rate": 1.902053455019557e-05, + "loss": 0.6031, + "step": 1803 + }, + { + "epoch": 0.15, + "learning_rate": 1.9019991308126903e-05, + "loss": 0.7085, + "step": 1804 + }, + { + "epoch": 0.15, + "learning_rate": 1.9019448066058237e-05, + "loss": 0.4898, + "step": 1805 + }, + { + "epoch": 0.15, + "learning_rate": 1.901890482398957e-05, + "loss": 0.9354, + "step": 1806 + }, + { + "epoch": 0.15, + "learning_rate": 1.9018361581920905e-05, + "loss": 0.7232, + "step": 1807 + }, + { + "epoch": 0.15, + "learning_rate": 1.901781833985224e-05, + "loss": 0.951, + "step": 1808 + }, + { + "epoch": 0.15, + "learning_rate": 1.9017275097783574e-05, + "loss": 0.9358, + "step": 1809 + }, + { + "epoch": 0.15, + "learning_rate": 1.9016731855714908e-05, + "loss": 0.4222, + "step": 1810 + }, + { + "epoch": 0.15, + "learning_rate": 1.9016188613646242e-05, + "loss": 0.6997, + "step": 1811 + }, + { + "epoch": 0.15, + "learning_rate": 1.9015645371577577e-05, + "loss": 0.5974, + "step": 1812 + }, + { + "epoch": 0.15, + "learning_rate": 1.901510212950891e-05, + "loss": 0.4442, + "step": 1813 + }, + { + "epoch": 0.15, + "learning_rate": 1.9014558887440245e-05, + "loss": 0.6209, + "step": 1814 + }, + { + "epoch": 0.15, + "learning_rate": 1.901401564537158e-05, + "loss": 0.6887, + "step": 1815 + }, + { + "epoch": 0.15, + "learning_rate": 1.9013472403302913e-05, + "loss": 0.7165, + "step": 1816 + }, + { + "epoch": 0.15, + "learning_rate": 1.9012929161234248e-05, + "loss": 0.6581, + "step": 1817 + }, + { + "epoch": 0.15, + "learning_rate": 1.9012385919165582e-05, + "loss": 0.5406, + "step": 1818 + }, + { + "epoch": 0.15, + "learning_rate": 1.9011842677096916e-05, + "loss": 0.4764, + "step": 1819 + }, + { + "epoch": 0.15, + "learning_rate": 1.901129943502825e-05, + "loss": 0.383, + "step": 1820 + }, + { + "epoch": 0.15, + "learning_rate": 1.9010756192959585e-05, + "loss": 0.4017, + "step": 1821 + }, + { + "epoch": 0.15, + "learning_rate": 1.901021295089092e-05, + "loss": 0.4642, + "step": 1822 + }, + { + "epoch": 0.15, + "learning_rate": 1.9009669708822253e-05, + "loss": 0.3597, + "step": 1823 + }, + { + "epoch": 0.15, + "learning_rate": 1.9009126466753587e-05, + "loss": 0.531, + "step": 1824 + }, + { + "epoch": 0.15, + "learning_rate": 1.900858322468492e-05, + "loss": 0.3552, + "step": 1825 + }, + { + "epoch": 0.15, + "learning_rate": 1.9008039982616256e-05, + "loss": 0.5875, + "step": 1826 + }, + { + "epoch": 0.15, + "learning_rate": 1.900749674054759e-05, + "loss": 0.7446, + "step": 1827 + }, + { + "epoch": 0.15, + "learning_rate": 1.9006953498478924e-05, + "loss": 0.3486, + "step": 1828 + }, + { + "epoch": 0.15, + "learning_rate": 1.900641025641026e-05, + "loss": 0.7442, + "step": 1829 + }, + { + "epoch": 0.15, + "learning_rate": 1.9005867014341593e-05, + "loss": 0.5396, + "step": 1830 + }, + { + "epoch": 0.15, + "learning_rate": 1.9005323772272927e-05, + "loss": 0.5451, + "step": 1831 + }, + { + "epoch": 0.15, + "learning_rate": 1.900478053020426e-05, + "loss": 0.5473, + "step": 1832 + }, + { + "epoch": 0.15, + "learning_rate": 1.9004237288135595e-05, + "loss": 0.669, + "step": 1833 + }, + { + "epoch": 0.15, + "learning_rate": 1.900369404606693e-05, + "loss": 0.5667, + "step": 1834 + }, + { + "epoch": 0.15, + "learning_rate": 1.9003150803998264e-05, + "loss": 0.5029, + "step": 1835 + }, + { + "epoch": 0.15, + "learning_rate": 1.9002607561929598e-05, + "loss": 0.6398, + "step": 1836 + }, + { + "epoch": 0.15, + "learning_rate": 1.9002064319860932e-05, + "loss": 0.5084, + "step": 1837 + }, + { + "epoch": 0.15, + "learning_rate": 1.9001521077792267e-05, + "loss": 0.6144, + "step": 1838 + }, + { + "epoch": 0.15, + "learning_rate": 1.90009778357236e-05, + "loss": 0.5306, + "step": 1839 + }, + { + "epoch": 0.15, + "learning_rate": 1.9000434593654935e-05, + "loss": 0.4176, + "step": 1840 + }, + { + "epoch": 0.15, + "learning_rate": 1.899989135158627e-05, + "loss": 0.487, + "step": 1841 + }, + { + "epoch": 0.15, + "learning_rate": 1.8999348109517603e-05, + "loss": 0.5775, + "step": 1842 + }, + { + "epoch": 0.15, + "learning_rate": 1.8998804867448938e-05, + "loss": 0.6603, + "step": 1843 + }, + { + "epoch": 0.15, + "learning_rate": 1.8998261625380272e-05, + "loss": 0.3703, + "step": 1844 + }, + { + "epoch": 0.15, + "learning_rate": 1.8997718383311606e-05, + "loss": 0.3573, + "step": 1845 + }, + { + "epoch": 0.15, + "learning_rate": 1.8997175141242937e-05, + "loss": 0.7266, + "step": 1846 + }, + { + "epoch": 0.15, + "learning_rate": 1.8996631899174275e-05, + "loss": 0.6577, + "step": 1847 + }, + { + "epoch": 0.15, + "learning_rate": 1.8996088657105605e-05, + "loss": 0.56, + "step": 1848 + }, + { + "epoch": 0.15, + "learning_rate": 1.8995545415036943e-05, + "loss": 0.5243, + "step": 1849 + }, + { + "epoch": 0.15, + "learning_rate": 1.8995002172968274e-05, + "loss": 0.3638, + "step": 1850 + }, + { + "epoch": 0.15, + "learning_rate": 1.899445893089961e-05, + "loss": 0.6478, + "step": 1851 + }, + { + "epoch": 0.15, + "learning_rate": 1.8993915688830942e-05, + "loss": 0.1981, + "step": 1852 + }, + { + "epoch": 0.15, + "learning_rate": 1.899337244676228e-05, + "loss": 0.5545, + "step": 1853 + }, + { + "epoch": 0.15, + "learning_rate": 1.899282920469361e-05, + "loss": 0.5906, + "step": 1854 + }, + { + "epoch": 0.15, + "learning_rate": 1.899228596262495e-05, + "loss": 0.8699, + "step": 1855 + }, + { + "epoch": 0.15, + "learning_rate": 1.899174272055628e-05, + "loss": 0.4905, + "step": 1856 + }, + { + "epoch": 0.15, + "learning_rate": 1.8991199478487617e-05, + "loss": 0.7616, + "step": 1857 + }, + { + "epoch": 0.15, + "learning_rate": 1.899065623641895e-05, + "loss": 0.468, + "step": 1858 + }, + { + "epoch": 0.15, + "learning_rate": 1.8990112994350285e-05, + "loss": 0.2614, + "step": 1859 + }, + { + "epoch": 0.15, + "learning_rate": 1.898956975228162e-05, + "loss": 0.4582, + "step": 1860 + }, + { + "epoch": 0.15, + "learning_rate": 1.8989026510212954e-05, + "loss": 0.6098, + "step": 1861 + }, + { + "epoch": 0.15, + "learning_rate": 1.8988483268144288e-05, + "loss": 0.7575, + "step": 1862 + }, + { + "epoch": 0.15, + "learning_rate": 1.8987940026075622e-05, + "loss": 0.5164, + "step": 1863 + }, + { + "epoch": 0.15, + "learning_rate": 1.8987396784006957e-05, + "loss": 0.3955, + "step": 1864 + }, + { + "epoch": 0.15, + "learning_rate": 1.8986853541938287e-05, + "loss": 0.5136, + "step": 1865 + }, + { + "epoch": 0.15, + "learning_rate": 1.8986310299869625e-05, + "loss": 0.7013, + "step": 1866 + }, + { + "epoch": 0.15, + "learning_rate": 1.8985767057800956e-05, + "loss": 0.4428, + "step": 1867 + }, + { + "epoch": 0.15, + "learning_rate": 1.8985223815732293e-05, + "loss": 0.4026, + "step": 1868 + }, + { + "epoch": 0.15, + "learning_rate": 1.8984680573663624e-05, + "loss": 0.7126, + "step": 1869 + }, + { + "epoch": 0.15, + "learning_rate": 1.8984137331594962e-05, + "loss": 0.5665, + "step": 1870 + }, + { + "epoch": 0.15, + "learning_rate": 1.8983594089526293e-05, + "loss": 0.4888, + "step": 1871 + }, + { + "epoch": 0.15, + "learning_rate": 1.898305084745763e-05, + "loss": 0.7884, + "step": 1872 + }, + { + "epoch": 0.15, + "learning_rate": 1.898250760538896e-05, + "loss": 0.5324, + "step": 1873 + }, + { + "epoch": 0.15, + "learning_rate": 1.89819643633203e-05, + "loss": 0.3899, + "step": 1874 + }, + { + "epoch": 0.15, + "learning_rate": 1.898142112125163e-05, + "loss": 0.4409, + "step": 1875 + }, + { + "epoch": 0.15, + "learning_rate": 1.8980877879182967e-05, + "loss": 0.6108, + "step": 1876 + }, + { + "epoch": 0.15, + "learning_rate": 1.8980334637114298e-05, + "loss": 0.387, + "step": 1877 + }, + { + "epoch": 0.15, + "learning_rate": 1.8979791395045636e-05, + "loss": 0.643, + "step": 1878 + }, + { + "epoch": 0.15, + "learning_rate": 1.8979248152976967e-05, + "loss": 0.3547, + "step": 1879 + }, + { + "epoch": 0.15, + "learning_rate": 1.8978704910908304e-05, + "loss": 0.4574, + "step": 1880 + }, + { + "epoch": 0.15, + "learning_rate": 1.8978161668839635e-05, + "loss": 0.3243, + "step": 1881 + }, + { + "epoch": 0.15, + "learning_rate": 1.8977618426770973e-05, + "loss": 0.3308, + "step": 1882 + }, + { + "epoch": 0.15, + "learning_rate": 1.8977075184702304e-05, + "loss": 0.4836, + "step": 1883 + }, + { + "epoch": 0.15, + "learning_rate": 1.8976531942633638e-05, + "loss": 0.3899, + "step": 1884 + }, + { + "epoch": 0.15, + "learning_rate": 1.8975988700564972e-05, + "loss": 0.829, + "step": 1885 + }, + { + "epoch": 0.15, + "learning_rate": 1.8975445458496306e-05, + "loss": 0.7623, + "step": 1886 + }, + { + "epoch": 0.15, + "learning_rate": 1.897490221642764e-05, + "loss": 0.4944, + "step": 1887 + }, + { + "epoch": 0.15, + "learning_rate": 1.8974358974358975e-05, + "loss": 0.5475, + "step": 1888 + }, + { + "epoch": 0.15, + "learning_rate": 1.897381573229031e-05, + "loss": 0.5213, + "step": 1889 + }, + { + "epoch": 0.15, + "learning_rate": 1.8973272490221643e-05, + "loss": 0.3968, + "step": 1890 + }, + { + "epoch": 0.15, + "learning_rate": 1.8972729248152977e-05, + "loss": 0.2822, + "step": 1891 + }, + { + "epoch": 0.15, + "learning_rate": 1.897218600608431e-05, + "loss": 0.6474, + "step": 1892 + }, + { + "epoch": 0.15, + "learning_rate": 1.8971642764015646e-05, + "loss": 0.5921, + "step": 1893 + }, + { + "epoch": 0.15, + "learning_rate": 1.897109952194698e-05, + "loss": 0.4514, + "step": 1894 + }, + { + "epoch": 0.15, + "learning_rate": 1.8970556279878318e-05, + "loss": 0.5853, + "step": 1895 + }, + { + "epoch": 0.15, + "learning_rate": 1.897001303780965e-05, + "loss": 0.3232, + "step": 1896 + }, + { + "epoch": 0.15, + "learning_rate": 1.8969469795740986e-05, + "loss": 0.6875, + "step": 1897 + }, + { + "epoch": 0.15, + "learning_rate": 1.8968926553672317e-05, + "loss": 0.3646, + "step": 1898 + }, + { + "epoch": 0.15, + "learning_rate": 1.8968383311603655e-05, + "loss": 0.6244, + "step": 1899 + }, + { + "epoch": 0.15, + "learning_rate": 1.8967840069534985e-05, + "loss": 0.4278, + "step": 1900 + }, + { + "epoch": 0.15, + "learning_rate": 1.8967296827466323e-05, + "loss": 0.3461, + "step": 1901 + }, + { + "epoch": 0.15, + "learning_rate": 1.8966753585397654e-05, + "loss": 0.4305, + "step": 1902 + }, + { + "epoch": 0.16, + "learning_rate": 1.8966210343328988e-05, + "loss": 0.6947, + "step": 1903 + }, + { + "epoch": 0.16, + "learning_rate": 1.8965667101260322e-05, + "loss": 0.3943, + "step": 1904 + }, + { + "epoch": 0.16, + "learning_rate": 1.8965123859191657e-05, + "loss": 0.5369, + "step": 1905 + }, + { + "epoch": 0.16, + "learning_rate": 1.896458061712299e-05, + "loss": 0.7436, + "step": 1906 + }, + { + "epoch": 0.16, + "learning_rate": 1.8964037375054325e-05, + "loss": 0.6077, + "step": 1907 + }, + { + "epoch": 0.16, + "learning_rate": 1.896349413298566e-05, + "loss": 0.5266, + "step": 1908 + }, + { + "epoch": 0.16, + "learning_rate": 1.8962950890916994e-05, + "loss": 0.4512, + "step": 1909 + }, + { + "epoch": 0.16, + "learning_rate": 1.8962407648848328e-05, + "loss": 0.7711, + "step": 1910 + }, + { + "epoch": 0.16, + "learning_rate": 1.8961864406779662e-05, + "loss": 0.532, + "step": 1911 + }, + { + "epoch": 0.16, + "learning_rate": 1.8961321164710996e-05, + "loss": 0.6734, + "step": 1912 + }, + { + "epoch": 0.16, + "learning_rate": 1.896077792264233e-05, + "loss": 0.4369, + "step": 1913 + }, + { + "epoch": 0.16, + "learning_rate": 1.8960234680573665e-05, + "loss": 0.5395, + "step": 1914 + }, + { + "epoch": 0.16, + "learning_rate": 1.8959691438505e-05, + "loss": 0.5573, + "step": 1915 + }, + { + "epoch": 0.16, + "learning_rate": 1.8959148196436333e-05, + "loss": 0.5844, + "step": 1916 + }, + { + "epoch": 0.16, + "learning_rate": 1.8958604954367667e-05, + "loss": 0.4868, + "step": 1917 + }, + { + "epoch": 0.16, + "learning_rate": 1.8958061712299e-05, + "loss": 0.7194, + "step": 1918 + }, + { + "epoch": 0.16, + "learning_rate": 1.8957518470230336e-05, + "loss": 0.8459, + "step": 1919 + }, + { + "epoch": 0.16, + "learning_rate": 1.895697522816167e-05, + "loss": 0.4855, + "step": 1920 + }, + { + "epoch": 0.16, + "learning_rate": 1.8956431986093004e-05, + "loss": 0.4645, + "step": 1921 + }, + { + "epoch": 0.16, + "learning_rate": 1.895588874402434e-05, + "loss": 0.2765, + "step": 1922 + }, + { + "epoch": 0.16, + "learning_rate": 1.8955345501955673e-05, + "loss": 0.5177, + "step": 1923 + }, + { + "epoch": 0.16, + "learning_rate": 1.8954802259887007e-05, + "loss": 0.2998, + "step": 1924 + }, + { + "epoch": 0.16, + "learning_rate": 1.895425901781834e-05, + "loss": 0.5077, + "step": 1925 + }, + { + "epoch": 0.16, + "learning_rate": 1.8953715775749675e-05, + "loss": 0.7293, + "step": 1926 + }, + { + "epoch": 0.16, + "learning_rate": 1.895317253368101e-05, + "loss": 0.4739, + "step": 1927 + }, + { + "epoch": 0.16, + "learning_rate": 1.8952629291612344e-05, + "loss": 0.3614, + "step": 1928 + }, + { + "epoch": 0.16, + "learning_rate": 1.8952086049543678e-05, + "loss": 0.5612, + "step": 1929 + }, + { + "epoch": 0.16, + "learning_rate": 1.8951542807475012e-05, + "loss": 0.476, + "step": 1930 + }, + { + "epoch": 0.16, + "learning_rate": 1.8950999565406347e-05, + "loss": 0.8187, + "step": 1931 + }, + { + "epoch": 0.16, + "learning_rate": 1.895045632333768e-05, + "loss": 0.5253, + "step": 1932 + }, + { + "epoch": 0.16, + "learning_rate": 1.8949913081269015e-05, + "loss": 0.5797, + "step": 1933 + }, + { + "epoch": 0.16, + "learning_rate": 1.894936983920035e-05, + "loss": 0.3582, + "step": 1934 + }, + { + "epoch": 0.16, + "learning_rate": 1.8948826597131684e-05, + "loss": 0.7392, + "step": 1935 + }, + { + "epoch": 0.16, + "learning_rate": 1.8948283355063018e-05, + "loss": 0.3669, + "step": 1936 + }, + { + "epoch": 0.16, + "learning_rate": 1.8947740112994352e-05, + "loss": 0.4639, + "step": 1937 + }, + { + "epoch": 0.16, + "learning_rate": 1.8947196870925686e-05, + "loss": 0.6411, + "step": 1938 + }, + { + "epoch": 0.16, + "learning_rate": 1.894665362885702e-05, + "loss": 0.5188, + "step": 1939 + }, + { + "epoch": 0.16, + "learning_rate": 1.8946110386788355e-05, + "loss": 0.5786, + "step": 1940 + }, + { + "epoch": 0.16, + "learning_rate": 1.894556714471969e-05, + "loss": 0.6096, + "step": 1941 + }, + { + "epoch": 0.16, + "learning_rate": 1.8945023902651023e-05, + "loss": 0.6595, + "step": 1942 + }, + { + "epoch": 0.16, + "learning_rate": 1.8944480660582357e-05, + "loss": 0.5077, + "step": 1943 + }, + { + "epoch": 0.16, + "learning_rate": 1.894393741851369e-05, + "loss": 0.8113, + "step": 1944 + }, + { + "epoch": 0.16, + "learning_rate": 1.8943394176445026e-05, + "loss": 0.7321, + "step": 1945 + }, + { + "epoch": 0.16, + "learning_rate": 1.894285093437636e-05, + "loss": 0.346, + "step": 1946 + }, + { + "epoch": 0.16, + "learning_rate": 1.8942307692307694e-05, + "loss": 0.4135, + "step": 1947 + }, + { + "epoch": 0.16, + "learning_rate": 1.894176445023903e-05, + "loss": 0.4953, + "step": 1948 + }, + { + "epoch": 0.16, + "learning_rate": 1.8941221208170363e-05, + "loss": 0.5137, + "step": 1949 + }, + { + "epoch": 0.16, + "learning_rate": 1.8940677966101697e-05, + "loss": 0.4841, + "step": 1950 + }, + { + "epoch": 0.16, + "learning_rate": 1.894013472403303e-05, + "loss": 0.5938, + "step": 1951 + }, + { + "epoch": 0.16, + "learning_rate": 1.8939591481964365e-05, + "loss": 0.7682, + "step": 1952 + }, + { + "epoch": 0.16, + "learning_rate": 1.89390482398957e-05, + "loss": 0.3909, + "step": 1953 + }, + { + "epoch": 0.16, + "learning_rate": 1.8938504997827034e-05, + "loss": 0.4566, + "step": 1954 + }, + { + "epoch": 0.16, + "learning_rate": 1.8937961755758368e-05, + "loss": 0.7222, + "step": 1955 + }, + { + "epoch": 0.16, + "learning_rate": 1.8937418513689702e-05, + "loss": 0.4374, + "step": 1956 + }, + { + "epoch": 0.16, + "learning_rate": 1.8936875271621037e-05, + "loss": 0.4469, + "step": 1957 + }, + { + "epoch": 0.16, + "learning_rate": 1.893633202955237e-05, + "loss": 0.3966, + "step": 1958 + }, + { + "epoch": 0.16, + "learning_rate": 1.8935788787483705e-05, + "loss": 0.5803, + "step": 1959 + }, + { + "epoch": 0.16, + "learning_rate": 1.8935245545415036e-05, + "loss": 0.9109, + "step": 1960 + }, + { + "epoch": 0.16, + "learning_rate": 1.8934702303346374e-05, + "loss": 0.5208, + "step": 1961 + }, + { + "epoch": 0.16, + "learning_rate": 1.8934159061277704e-05, + "loss": 0.6096, + "step": 1962 + }, + { + "epoch": 0.16, + "learning_rate": 1.8933615819209042e-05, + "loss": 0.5503, + "step": 1963 + }, + { + "epoch": 0.16, + "learning_rate": 1.8933072577140373e-05, + "loss": 0.6458, + "step": 1964 + }, + { + "epoch": 0.16, + "learning_rate": 1.893252933507171e-05, + "loss": 0.4286, + "step": 1965 + }, + { + "epoch": 0.16, + "learning_rate": 1.8931986093003045e-05, + "loss": 0.5163, + "step": 1966 + }, + { + "epoch": 0.16, + "learning_rate": 1.893144285093438e-05, + "loss": 0.5697, + "step": 1967 + }, + { + "epoch": 0.16, + "learning_rate": 1.8930899608865713e-05, + "loss": 0.6581, + "step": 1968 + }, + { + "epoch": 0.16, + "learning_rate": 1.8930356366797047e-05, + "loss": 0.5938, + "step": 1969 + }, + { + "epoch": 0.16, + "learning_rate": 1.892981312472838e-05, + "loss": 0.4945, + "step": 1970 + }, + { + "epoch": 0.16, + "learning_rate": 1.8929269882659716e-05, + "loss": 0.6494, + "step": 1971 + }, + { + "epoch": 0.16, + "learning_rate": 1.892872664059105e-05, + "loss": 0.4512, + "step": 1972 + }, + { + "epoch": 0.16, + "learning_rate": 1.8928183398522384e-05, + "loss": 0.4296, + "step": 1973 + }, + { + "epoch": 0.16, + "learning_rate": 1.892764015645372e-05, + "loss": 0.5323, + "step": 1974 + }, + { + "epoch": 0.16, + "learning_rate": 1.8927096914385053e-05, + "loss": 0.4721, + "step": 1975 + }, + { + "epoch": 0.16, + "learning_rate": 1.8926553672316387e-05, + "loss": 0.6028, + "step": 1976 + }, + { + "epoch": 0.16, + "learning_rate": 1.892601043024772e-05, + "loss": 0.2057, + "step": 1977 + }, + { + "epoch": 0.16, + "learning_rate": 1.8925467188179055e-05, + "loss": 0.5028, + "step": 1978 + }, + { + "epoch": 0.16, + "learning_rate": 1.8924923946110386e-05, + "loss": 0.4802, + "step": 1979 + }, + { + "epoch": 0.16, + "learning_rate": 1.8924380704041724e-05, + "loss": 0.3983, + "step": 1980 + }, + { + "epoch": 0.16, + "learning_rate": 1.8923837461973055e-05, + "loss": 0.67, + "step": 1981 + }, + { + "epoch": 0.16, + "learning_rate": 1.8923294219904392e-05, + "loss": 0.4324, + "step": 1982 + }, + { + "epoch": 0.16, + "learning_rate": 1.8922750977835723e-05, + "loss": 0.6363, + "step": 1983 + }, + { + "epoch": 0.16, + "learning_rate": 1.892220773576706e-05, + "loss": 0.4715, + "step": 1984 + }, + { + "epoch": 0.16, + "learning_rate": 1.892166449369839e-05, + "loss": 0.5887, + "step": 1985 + }, + { + "epoch": 0.16, + "learning_rate": 1.892112125162973e-05, + "loss": 0.5197, + "step": 1986 + }, + { + "epoch": 0.16, + "learning_rate": 1.892057800956106e-05, + "loss": 0.4748, + "step": 1987 + }, + { + "epoch": 0.16, + "learning_rate": 1.8920034767492398e-05, + "loss": 0.3905, + "step": 1988 + }, + { + "epoch": 0.16, + "learning_rate": 1.891949152542373e-05, + "loss": 0.4648, + "step": 1989 + }, + { + "epoch": 0.16, + "learning_rate": 1.8918948283355066e-05, + "loss": 0.6509, + "step": 1990 + }, + { + "epoch": 0.16, + "learning_rate": 1.8918405041286397e-05, + "loss": 0.6117, + "step": 1991 + }, + { + "epoch": 0.16, + "learning_rate": 1.8917861799217735e-05, + "loss": 0.5163, + "step": 1992 + }, + { + "epoch": 0.16, + "learning_rate": 1.8917318557149066e-05, + "loss": 0.7541, + "step": 1993 + }, + { + "epoch": 0.16, + "learning_rate": 1.8916775315080403e-05, + "loss": 0.804, + "step": 1994 + }, + { + "epoch": 0.16, + "learning_rate": 1.8916232073011734e-05, + "loss": 0.4217, + "step": 1995 + }, + { + "epoch": 0.16, + "learning_rate": 1.891568883094307e-05, + "loss": 0.3721, + "step": 1996 + }, + { + "epoch": 0.16, + "learning_rate": 1.8915145588874402e-05, + "loss": 0.45, + "step": 1997 + }, + { + "epoch": 0.16, + "learning_rate": 1.8914602346805737e-05, + "loss": 0.4054, + "step": 1998 + }, + { + "epoch": 0.16, + "learning_rate": 1.891405910473707e-05, + "loss": 0.317, + "step": 1999 + }, + { + "epoch": 0.16, + "learning_rate": 1.8913515862668405e-05, + "loss": 0.2757, + "step": 2000 + }, + { + "epoch": 0.16, + "eval_accuracy": 0.7902190524707081, + "eval_loss": 0.5320990085601807, + "eval_runtime": 22.3341, + "eval_samples_per_second": 439.463, + "eval_steps_per_second": 3.448, + "step": 2000 + }, + { + "epoch": 0.16, + "learning_rate": 1.891297262059974e-05, + "loss": 0.5637, + "step": 2001 + }, + { + "epoch": 0.16, + "learning_rate": 1.8912429378531074e-05, + "loss": 0.5712, + "step": 2002 + }, + { + "epoch": 0.16, + "learning_rate": 1.891188613646241e-05, + "loss": 0.6583, + "step": 2003 + }, + { + "epoch": 0.16, + "learning_rate": 1.8911342894393742e-05, + "loss": 0.6463, + "step": 2004 + }, + { + "epoch": 0.16, + "learning_rate": 1.891079965232508e-05, + "loss": 0.5722, + "step": 2005 + }, + { + "epoch": 0.16, + "learning_rate": 1.891025641025641e-05, + "loss": 0.5355, + "step": 2006 + }, + { + "epoch": 0.16, + "learning_rate": 1.8909713168187748e-05, + "loss": 0.4207, + "step": 2007 + }, + { + "epoch": 0.16, + "learning_rate": 1.890916992611908e-05, + "loss": 0.6428, + "step": 2008 + }, + { + "epoch": 0.16, + "learning_rate": 1.8908626684050417e-05, + "loss": 0.493, + "step": 2009 + }, + { + "epoch": 0.16, + "learning_rate": 1.8908083441981747e-05, + "loss": 0.5184, + "step": 2010 + }, + { + "epoch": 0.16, + "learning_rate": 1.8907540199913085e-05, + "loss": 0.6323, + "step": 2011 + }, + { + "epoch": 0.16, + "learning_rate": 1.8906996957844416e-05, + "loss": 0.5425, + "step": 2012 + }, + { + "epoch": 0.16, + "learning_rate": 1.8906453715775754e-05, + "loss": 0.6481, + "step": 2013 + }, + { + "epoch": 0.16, + "learning_rate": 1.8905910473707084e-05, + "loss": 0.5174, + "step": 2014 + }, + { + "epoch": 0.16, + "learning_rate": 1.8905367231638422e-05, + "loss": 0.5306, + "step": 2015 + }, + { + "epoch": 0.16, + "learning_rate": 1.8904823989569753e-05, + "loss": 0.4173, + "step": 2016 + }, + { + "epoch": 0.16, + "learning_rate": 1.8904280747501087e-05, + "loss": 0.3708, + "step": 2017 + }, + { + "epoch": 0.16, + "learning_rate": 1.890373750543242e-05, + "loss": 0.5969, + "step": 2018 + }, + { + "epoch": 0.16, + "learning_rate": 1.8903194263363756e-05, + "loss": 0.4519, + "step": 2019 + }, + { + "epoch": 0.16, + "learning_rate": 1.890265102129509e-05, + "loss": 0.4411, + "step": 2020 + }, + { + "epoch": 0.16, + "learning_rate": 1.8902107779226424e-05, + "loss": 0.5908, + "step": 2021 + }, + { + "epoch": 0.16, + "learning_rate": 1.8901564537157758e-05, + "loss": 0.4982, + "step": 2022 + }, + { + "epoch": 0.16, + "learning_rate": 1.8901021295089092e-05, + "loss": 0.6487, + "step": 2023 + }, + { + "epoch": 0.16, + "learning_rate": 1.8900478053020427e-05, + "loss": 0.623, + "step": 2024 + }, + { + "epoch": 0.17, + "learning_rate": 1.889993481095176e-05, + "loss": 0.4421, + "step": 2025 + }, + { + "epoch": 0.17, + "learning_rate": 1.8899391568883095e-05, + "loss": 0.7431, + "step": 2026 + }, + { + "epoch": 0.17, + "learning_rate": 1.889884832681443e-05, + "loss": 0.6443, + "step": 2027 + }, + { + "epoch": 0.17, + "learning_rate": 1.8898305084745764e-05, + "loss": 0.4775, + "step": 2028 + }, + { + "epoch": 0.17, + "learning_rate": 1.8897761842677098e-05, + "loss": 0.593, + "step": 2029 + }, + { + "epoch": 0.17, + "learning_rate": 1.8897218600608432e-05, + "loss": 0.5343, + "step": 2030 + }, + { + "epoch": 0.17, + "learning_rate": 1.8896675358539766e-05, + "loss": 0.8827, + "step": 2031 + }, + { + "epoch": 0.17, + "learning_rate": 1.88961321164711e-05, + "loss": 0.6236, + "step": 2032 + }, + { + "epoch": 0.17, + "learning_rate": 1.8895588874402435e-05, + "loss": 0.5094, + "step": 2033 + }, + { + "epoch": 0.17, + "learning_rate": 1.889504563233377e-05, + "loss": 0.6237, + "step": 2034 + }, + { + "epoch": 0.17, + "learning_rate": 1.8894502390265103e-05, + "loss": 0.4792, + "step": 2035 + }, + { + "epoch": 0.17, + "learning_rate": 1.8893959148196437e-05, + "loss": 0.7327, + "step": 2036 + }, + { + "epoch": 0.17, + "learning_rate": 1.889341590612777e-05, + "loss": 0.6745, + "step": 2037 + }, + { + "epoch": 0.17, + "learning_rate": 1.8892872664059106e-05, + "loss": 0.5461, + "step": 2038 + }, + { + "epoch": 0.17, + "learning_rate": 1.889232942199044e-05, + "loss": 0.7023, + "step": 2039 + }, + { + "epoch": 0.17, + "learning_rate": 1.8891786179921774e-05, + "loss": 0.4017, + "step": 2040 + }, + { + "epoch": 0.17, + "learning_rate": 1.889124293785311e-05, + "loss": 0.6048, + "step": 2041 + }, + { + "epoch": 0.17, + "learning_rate": 1.8890699695784443e-05, + "loss": 0.5098, + "step": 2042 + }, + { + "epoch": 0.17, + "learning_rate": 1.8890156453715777e-05, + "loss": 0.578, + "step": 2043 + }, + { + "epoch": 0.17, + "learning_rate": 1.888961321164711e-05, + "loss": 0.4285, + "step": 2044 + }, + { + "epoch": 0.17, + "learning_rate": 1.8889069969578446e-05, + "loss": 0.5294, + "step": 2045 + }, + { + "epoch": 0.17, + "learning_rate": 1.888852672750978e-05, + "loss": 0.4885, + "step": 2046 + }, + { + "epoch": 0.17, + "learning_rate": 1.8887983485441114e-05, + "loss": 0.438, + "step": 2047 + }, + { + "epoch": 0.17, + "learning_rate": 1.8887440243372448e-05, + "loss": 0.4562, + "step": 2048 + }, + { + "epoch": 0.17, + "learning_rate": 1.8886897001303782e-05, + "loss": 0.5015, + "step": 2049 + }, + { + "epoch": 0.17, + "learning_rate": 1.8886353759235117e-05, + "loss": 0.7962, + "step": 2050 + }, + { + "epoch": 0.17, + "learning_rate": 1.888581051716645e-05, + "loss": 0.7666, + "step": 2051 + }, + { + "epoch": 0.17, + "learning_rate": 1.8885267275097785e-05, + "loss": 0.4968, + "step": 2052 + }, + { + "epoch": 0.17, + "learning_rate": 1.888472403302912e-05, + "loss": 0.5567, + "step": 2053 + }, + { + "epoch": 0.17, + "learning_rate": 1.8884180790960454e-05, + "loss": 0.72, + "step": 2054 + }, + { + "epoch": 0.17, + "learning_rate": 1.8883637548891788e-05, + "loss": 0.5601, + "step": 2055 + }, + { + "epoch": 0.17, + "learning_rate": 1.8883094306823122e-05, + "loss": 0.7163, + "step": 2056 + }, + { + "epoch": 0.17, + "learning_rate": 1.8882551064754456e-05, + "loss": 0.7248, + "step": 2057 + }, + { + "epoch": 0.17, + "learning_rate": 1.888200782268579e-05, + "loss": 0.7492, + "step": 2058 + }, + { + "epoch": 0.17, + "learning_rate": 1.8881464580617125e-05, + "loss": 0.4449, + "step": 2059 + }, + { + "epoch": 0.17, + "learning_rate": 1.888092133854846e-05, + "loss": 0.4633, + "step": 2060 + }, + { + "epoch": 0.17, + "learning_rate": 1.8880378096479793e-05, + "loss": 0.4123, + "step": 2061 + }, + { + "epoch": 0.17, + "learning_rate": 1.8879834854411127e-05, + "loss": 0.5576, + "step": 2062 + }, + { + "epoch": 0.17, + "learning_rate": 1.887929161234246e-05, + "loss": 0.8262, + "step": 2063 + }, + { + "epoch": 0.17, + "learning_rate": 1.8878748370273796e-05, + "loss": 0.5409, + "step": 2064 + }, + { + "epoch": 0.17, + "learning_rate": 1.887820512820513e-05, + "loss": 0.6526, + "step": 2065 + }, + { + "epoch": 0.17, + "learning_rate": 1.8877661886136464e-05, + "loss": 0.5218, + "step": 2066 + }, + { + "epoch": 0.17, + "learning_rate": 1.88771186440678e-05, + "loss": 0.9004, + "step": 2067 + }, + { + "epoch": 0.17, + "learning_rate": 1.8876575401999133e-05, + "loss": 0.6824, + "step": 2068 + }, + { + "epoch": 0.17, + "learning_rate": 1.8876032159930467e-05, + "loss": 0.4963, + "step": 2069 + }, + { + "epoch": 0.17, + "learning_rate": 1.88754889178618e-05, + "loss": 0.5325, + "step": 2070 + }, + { + "epoch": 0.17, + "learning_rate": 1.8874945675793135e-05, + "loss": 0.6292, + "step": 2071 + }, + { + "epoch": 0.17, + "learning_rate": 1.887440243372447e-05, + "loss": 0.6382, + "step": 2072 + }, + { + "epoch": 0.17, + "learning_rate": 1.8873859191655804e-05, + "loss": 0.5702, + "step": 2073 + }, + { + "epoch": 0.17, + "learning_rate": 1.8873315949587138e-05, + "loss": 0.4034, + "step": 2074 + }, + { + "epoch": 0.17, + "learning_rate": 1.8872772707518472e-05, + "loss": 0.5171, + "step": 2075 + }, + { + "epoch": 0.17, + "learning_rate": 1.8872229465449807e-05, + "loss": 0.5466, + "step": 2076 + }, + { + "epoch": 0.17, + "learning_rate": 1.887168622338114e-05, + "loss": 0.325, + "step": 2077 + }, + { + "epoch": 0.17, + "learning_rate": 1.8871142981312475e-05, + "loss": 0.7416, + "step": 2078 + }, + { + "epoch": 0.17, + "learning_rate": 1.887059973924381e-05, + "loss": 0.3858, + "step": 2079 + }, + { + "epoch": 0.17, + "learning_rate": 1.8870056497175144e-05, + "loss": 0.6887, + "step": 2080 + }, + { + "epoch": 0.17, + "learning_rate": 1.8869513255106478e-05, + "loss": 0.4375, + "step": 2081 + }, + { + "epoch": 0.17, + "learning_rate": 1.8868970013037812e-05, + "loss": 0.3705, + "step": 2082 + }, + { + "epoch": 0.17, + "learning_rate": 1.8868426770969146e-05, + "loss": 0.5322, + "step": 2083 + }, + { + "epoch": 0.17, + "learning_rate": 1.886788352890048e-05, + "loss": 0.4739, + "step": 2084 + }, + { + "epoch": 0.17, + "learning_rate": 1.8867340286831815e-05, + "loss": 0.4713, + "step": 2085 + }, + { + "epoch": 0.17, + "learning_rate": 1.886679704476315e-05, + "loss": 0.6027, + "step": 2086 + }, + { + "epoch": 0.17, + "learning_rate": 1.8866253802694483e-05, + "loss": 0.9749, + "step": 2087 + }, + { + "epoch": 0.17, + "learning_rate": 1.8865710560625817e-05, + "loss": 0.4427, + "step": 2088 + }, + { + "epoch": 0.17, + "learning_rate": 1.886516731855715e-05, + "loss": 0.7029, + "step": 2089 + }, + { + "epoch": 0.17, + "learning_rate": 1.8864624076488486e-05, + "loss": 0.6048, + "step": 2090 + }, + { + "epoch": 0.17, + "learning_rate": 1.886408083441982e-05, + "loss": 0.5565, + "step": 2091 + }, + { + "epoch": 0.17, + "learning_rate": 1.8863537592351154e-05, + "loss": 0.4885, + "step": 2092 + }, + { + "epoch": 0.17, + "learning_rate": 1.8862994350282485e-05, + "loss": 0.6148, + "step": 2093 + }, + { + "epoch": 0.17, + "learning_rate": 1.8862451108213823e-05, + "loss": 0.5962, + "step": 2094 + }, + { + "epoch": 0.17, + "learning_rate": 1.8861907866145154e-05, + "loss": 0.5725, + "step": 2095 + }, + { + "epoch": 0.17, + "learning_rate": 1.886136462407649e-05, + "loss": 0.5664, + "step": 2096 + }, + { + "epoch": 0.17, + "learning_rate": 1.8860821382007822e-05, + "loss": 0.5817, + "step": 2097 + }, + { + "epoch": 0.17, + "learning_rate": 1.886027813993916e-05, + "loss": 0.5528, + "step": 2098 + }, + { + "epoch": 0.17, + "learning_rate": 1.885973489787049e-05, + "loss": 0.53, + "step": 2099 + }, + { + "epoch": 0.17, + "learning_rate": 1.8859191655801828e-05, + "loss": 0.3289, + "step": 2100 + }, + { + "epoch": 0.17, + "learning_rate": 1.885864841373316e-05, + "loss": 0.4528, + "step": 2101 + }, + { + "epoch": 0.17, + "learning_rate": 1.8858105171664497e-05, + "loss": 0.5609, + "step": 2102 + }, + { + "epoch": 0.17, + "learning_rate": 1.8857561929595827e-05, + "loss": 0.5703, + "step": 2103 + }, + { + "epoch": 0.17, + "learning_rate": 1.8857018687527165e-05, + "loss": 0.7937, + "step": 2104 + }, + { + "epoch": 0.17, + "learning_rate": 1.8856475445458496e-05, + "loss": 0.3947, + "step": 2105 + }, + { + "epoch": 0.17, + "learning_rate": 1.8855932203389834e-05, + "loss": 0.5738, + "step": 2106 + }, + { + "epoch": 0.17, + "learning_rate": 1.8855388961321164e-05, + "loss": 0.6985, + "step": 2107 + }, + { + "epoch": 0.17, + "learning_rate": 1.8854845719252502e-05, + "loss": 0.2979, + "step": 2108 + }, + { + "epoch": 0.17, + "learning_rate": 1.8854302477183833e-05, + "loss": 0.5056, + "step": 2109 + }, + { + "epoch": 0.17, + "learning_rate": 1.885375923511517e-05, + "loss": 0.5073, + "step": 2110 + }, + { + "epoch": 0.17, + "learning_rate": 1.8853215993046505e-05, + "loss": 0.5825, + "step": 2111 + }, + { + "epoch": 0.17, + "learning_rate": 1.8852672750977836e-05, + "loss": 0.891, + "step": 2112 + }, + { + "epoch": 0.17, + "learning_rate": 1.8852129508909173e-05, + "loss": 0.5788, + "step": 2113 + }, + { + "epoch": 0.17, + "learning_rate": 1.8851586266840504e-05, + "loss": 0.5267, + "step": 2114 + }, + { + "epoch": 0.17, + "learning_rate": 1.885104302477184e-05, + "loss": 0.5166, + "step": 2115 + }, + { + "epoch": 0.17, + "learning_rate": 1.8850499782703172e-05, + "loss": 0.7263, + "step": 2116 + }, + { + "epoch": 0.17, + "learning_rate": 1.884995654063451e-05, + "loss": 0.5482, + "step": 2117 + }, + { + "epoch": 0.17, + "learning_rate": 1.884941329856584e-05, + "loss": 0.5857, + "step": 2118 + }, + { + "epoch": 0.17, + "learning_rate": 1.884887005649718e-05, + "loss": 0.4322, + "step": 2119 + }, + { + "epoch": 0.17, + "learning_rate": 1.884832681442851e-05, + "loss": 0.6257, + "step": 2120 + }, + { + "epoch": 0.17, + "learning_rate": 1.8847783572359847e-05, + "loss": 0.5779, + "step": 2121 + }, + { + "epoch": 0.17, + "learning_rate": 1.8847240330291178e-05, + "loss": 0.6371, + "step": 2122 + }, + { + "epoch": 0.17, + "learning_rate": 1.8846697088222515e-05, + "loss": 0.6067, + "step": 2123 + }, + { + "epoch": 0.17, + "learning_rate": 1.8846153846153846e-05, + "loss": 0.4377, + "step": 2124 + }, + { + "epoch": 0.17, + "learning_rate": 1.8845610604085184e-05, + "loss": 0.4593, + "step": 2125 + }, + { + "epoch": 0.17, + "learning_rate": 1.8845067362016515e-05, + "loss": 0.504, + "step": 2126 + }, + { + "epoch": 0.17, + "learning_rate": 1.8844524119947852e-05, + "loss": 0.8046, + "step": 2127 + }, + { + "epoch": 0.17, + "learning_rate": 1.8843980877879183e-05, + "loss": 0.3378, + "step": 2128 + }, + { + "epoch": 0.17, + "learning_rate": 1.884343763581052e-05, + "loss": 0.6304, + "step": 2129 + }, + { + "epoch": 0.17, + "learning_rate": 1.8842894393741852e-05, + "loss": 0.5854, + "step": 2130 + }, + { + "epoch": 0.17, + "learning_rate": 1.8842351151673186e-05, + "loss": 0.4486, + "step": 2131 + }, + { + "epoch": 0.17, + "learning_rate": 1.884180790960452e-05, + "loss": 0.8341, + "step": 2132 + }, + { + "epoch": 0.17, + "learning_rate": 1.8841264667535854e-05, + "loss": 0.7257, + "step": 2133 + }, + { + "epoch": 0.17, + "learning_rate": 1.884072142546719e-05, + "loss": 0.414, + "step": 2134 + }, + { + "epoch": 0.17, + "learning_rate": 1.8840178183398523e-05, + "loss": 0.7041, + "step": 2135 + }, + { + "epoch": 0.17, + "learning_rate": 1.8839634941329857e-05, + "loss": 0.511, + "step": 2136 + }, + { + "epoch": 0.17, + "learning_rate": 1.883909169926119e-05, + "loss": 0.6275, + "step": 2137 + }, + { + "epoch": 0.17, + "learning_rate": 1.8838548457192526e-05, + "loss": 0.3389, + "step": 2138 + }, + { + "epoch": 0.17, + "learning_rate": 1.883800521512386e-05, + "loss": 0.7347, + "step": 2139 + }, + { + "epoch": 0.17, + "learning_rate": 1.8837461973055194e-05, + "loss": 0.4433, + "step": 2140 + }, + { + "epoch": 0.17, + "learning_rate": 1.8836918730986528e-05, + "loss": 0.7671, + "step": 2141 + }, + { + "epoch": 0.17, + "learning_rate": 1.8836375488917862e-05, + "loss": 0.4755, + "step": 2142 + }, + { + "epoch": 0.17, + "learning_rate": 1.8835832246849197e-05, + "loss": 0.4536, + "step": 2143 + }, + { + "epoch": 0.17, + "learning_rate": 1.883528900478053e-05, + "loss": 0.7599, + "step": 2144 + }, + { + "epoch": 0.17, + "learning_rate": 1.8834745762711865e-05, + "loss": 0.7262, + "step": 2145 + }, + { + "epoch": 0.17, + "learning_rate": 1.88342025206432e-05, + "loss": 0.4978, + "step": 2146 + }, + { + "epoch": 0.17, + "learning_rate": 1.8833659278574534e-05, + "loss": 0.5078, + "step": 2147 + }, + { + "epoch": 0.18, + "learning_rate": 1.883311603650587e-05, + "loss": 0.5019, + "step": 2148 + }, + { + "epoch": 0.18, + "learning_rate": 1.8832572794437202e-05, + "loss": 0.668, + "step": 2149 + }, + { + "epoch": 0.18, + "learning_rate": 1.8832029552368536e-05, + "loss": 0.5424, + "step": 2150 + }, + { + "epoch": 0.18, + "learning_rate": 1.883148631029987e-05, + "loss": 0.5674, + "step": 2151 + }, + { + "epoch": 0.18, + "learning_rate": 1.8830943068231205e-05, + "loss": 0.7226, + "step": 2152 + }, + { + "epoch": 0.18, + "learning_rate": 1.883039982616254e-05, + "loss": 0.3594, + "step": 2153 + }, + { + "epoch": 0.18, + "learning_rate": 1.8829856584093873e-05, + "loss": 0.6939, + "step": 2154 + }, + { + "epoch": 0.18, + "learning_rate": 1.8829313342025207e-05, + "loss": 0.3807, + "step": 2155 + }, + { + "epoch": 0.18, + "learning_rate": 1.8828770099956542e-05, + "loss": 0.4542, + "step": 2156 + }, + { + "epoch": 0.18, + "learning_rate": 1.8828226857887876e-05, + "loss": 0.5577, + "step": 2157 + }, + { + "epoch": 0.18, + "learning_rate": 1.882768361581921e-05, + "loss": 0.2756, + "step": 2158 + }, + { + "epoch": 0.18, + "learning_rate": 1.8827140373750544e-05, + "loss": 0.601, + "step": 2159 + }, + { + "epoch": 0.18, + "learning_rate": 1.882659713168188e-05, + "loss": 0.5754, + "step": 2160 + }, + { + "epoch": 0.18, + "learning_rate": 1.8826053889613213e-05, + "loss": 0.5603, + "step": 2161 + }, + { + "epoch": 0.18, + "learning_rate": 1.8825510647544547e-05, + "loss": 0.7202, + "step": 2162 + }, + { + "epoch": 0.18, + "learning_rate": 1.882496740547588e-05, + "loss": 0.4036, + "step": 2163 + }, + { + "epoch": 0.18, + "learning_rate": 1.8824424163407216e-05, + "loss": 0.6254, + "step": 2164 + }, + { + "epoch": 0.18, + "learning_rate": 1.882388092133855e-05, + "loss": 0.3796, + "step": 2165 + }, + { + "epoch": 0.18, + "learning_rate": 1.8823337679269884e-05, + "loss": 0.6297, + "step": 2166 + }, + { + "epoch": 0.18, + "learning_rate": 1.8822794437201218e-05, + "loss": 0.4523, + "step": 2167 + }, + { + "epoch": 0.18, + "learning_rate": 1.8822251195132552e-05, + "loss": 0.5772, + "step": 2168 + }, + { + "epoch": 0.18, + "learning_rate": 1.8821707953063887e-05, + "loss": 0.7298, + "step": 2169 + }, + { + "epoch": 0.18, + "learning_rate": 1.882116471099522e-05, + "loss": 0.4073, + "step": 2170 + }, + { + "epoch": 0.18, + "learning_rate": 1.8820621468926555e-05, + "loss": 0.3465, + "step": 2171 + }, + { + "epoch": 0.18, + "learning_rate": 1.882007822685789e-05, + "loss": 0.4462, + "step": 2172 + }, + { + "epoch": 0.18, + "learning_rate": 1.8819534984789224e-05, + "loss": 0.5449, + "step": 2173 + }, + { + "epoch": 0.18, + "learning_rate": 1.8818991742720558e-05, + "loss": 0.6433, + "step": 2174 + }, + { + "epoch": 0.18, + "learning_rate": 1.8818448500651892e-05, + "loss": 0.7673, + "step": 2175 + }, + { + "epoch": 0.18, + "learning_rate": 1.8817905258583226e-05, + "loss": 0.3784, + "step": 2176 + }, + { + "epoch": 0.18, + "learning_rate": 1.881736201651456e-05, + "loss": 0.3382, + "step": 2177 + }, + { + "epoch": 0.18, + "learning_rate": 1.8816818774445895e-05, + "loss": 0.7185, + "step": 2178 + }, + { + "epoch": 0.18, + "learning_rate": 1.881627553237723e-05, + "loss": 0.7683, + "step": 2179 + }, + { + "epoch": 0.18, + "learning_rate": 1.8815732290308563e-05, + "loss": 0.4716, + "step": 2180 + }, + { + "epoch": 0.18, + "learning_rate": 1.8815189048239897e-05, + "loss": 0.403, + "step": 2181 + }, + { + "epoch": 0.18, + "learning_rate": 1.8814645806171232e-05, + "loss": 0.7328, + "step": 2182 + }, + { + "epoch": 0.18, + "learning_rate": 1.8814102564102566e-05, + "loss": 0.6745, + "step": 2183 + }, + { + "epoch": 0.18, + "learning_rate": 1.88135593220339e-05, + "loss": 0.5851, + "step": 2184 + }, + { + "epoch": 0.18, + "learning_rate": 1.8813016079965234e-05, + "loss": 0.4231, + "step": 2185 + }, + { + "epoch": 0.18, + "learning_rate": 1.881247283789657e-05, + "loss": 0.5629, + "step": 2186 + }, + { + "epoch": 0.18, + "learning_rate": 1.8811929595827903e-05, + "loss": 0.5314, + "step": 2187 + }, + { + "epoch": 0.18, + "learning_rate": 1.8811386353759237e-05, + "loss": 0.3785, + "step": 2188 + }, + { + "epoch": 0.18, + "learning_rate": 1.881084311169057e-05, + "loss": 0.6404, + "step": 2189 + }, + { + "epoch": 0.18, + "learning_rate": 1.8810299869621906e-05, + "loss": 0.4684, + "step": 2190 + }, + { + "epoch": 0.18, + "learning_rate": 1.880975662755324e-05, + "loss": 0.865, + "step": 2191 + }, + { + "epoch": 0.18, + "learning_rate": 1.8809213385484574e-05, + "loss": 0.7706, + "step": 2192 + }, + { + "epoch": 0.18, + "learning_rate": 1.8808670143415908e-05, + "loss": 0.9221, + "step": 2193 + }, + { + "epoch": 0.18, + "learning_rate": 1.8808126901347242e-05, + "loss": 0.4993, + "step": 2194 + }, + { + "epoch": 0.18, + "learning_rate": 1.8807583659278577e-05, + "loss": 0.4508, + "step": 2195 + }, + { + "epoch": 0.18, + "learning_rate": 1.880704041720991e-05, + "loss": 0.751, + "step": 2196 + }, + { + "epoch": 0.18, + "learning_rate": 1.8806497175141245e-05, + "loss": 0.8282, + "step": 2197 + }, + { + "epoch": 0.18, + "learning_rate": 1.880595393307258e-05, + "loss": 0.4572, + "step": 2198 + }, + { + "epoch": 0.18, + "learning_rate": 1.8805410691003914e-05, + "loss": 0.5739, + "step": 2199 + }, + { + "epoch": 0.18, + "learning_rate": 1.8804867448935248e-05, + "loss": 0.7668, + "step": 2200 + }, + { + "epoch": 0.18, + "learning_rate": 1.8804324206866582e-05, + "loss": 0.2876, + "step": 2201 + }, + { + "epoch": 0.18, + "learning_rate": 1.8803780964797916e-05, + "loss": 0.4872, + "step": 2202 + }, + { + "epoch": 0.18, + "learning_rate": 1.880323772272925e-05, + "loss": 0.4418, + "step": 2203 + }, + { + "epoch": 0.18, + "learning_rate": 1.8802694480660585e-05, + "loss": 0.8024, + "step": 2204 + }, + { + "epoch": 0.18, + "learning_rate": 1.880215123859192e-05, + "loss": 0.6341, + "step": 2205 + }, + { + "epoch": 0.18, + "learning_rate": 1.8801607996523253e-05, + "loss": 0.594, + "step": 2206 + }, + { + "epoch": 0.18, + "learning_rate": 1.8801064754454584e-05, + "loss": 0.5879, + "step": 2207 + }, + { + "epoch": 0.18, + "learning_rate": 1.880052151238592e-05, + "loss": 0.2736, + "step": 2208 + }, + { + "epoch": 0.18, + "learning_rate": 1.8799978270317253e-05, + "loss": 0.6075, + "step": 2209 + }, + { + "epoch": 0.18, + "learning_rate": 1.879943502824859e-05, + "loss": 0.4301, + "step": 2210 + }, + { + "epoch": 0.18, + "learning_rate": 1.879889178617992e-05, + "loss": 0.5103, + "step": 2211 + }, + { + "epoch": 0.18, + "learning_rate": 1.879834854411126e-05, + "loss": 0.5715, + "step": 2212 + }, + { + "epoch": 0.18, + "learning_rate": 1.879780530204259e-05, + "loss": 0.9095, + "step": 2213 + }, + { + "epoch": 0.18, + "learning_rate": 1.8797262059973927e-05, + "loss": 0.4968, + "step": 2214 + }, + { + "epoch": 0.18, + "learning_rate": 1.8796718817905258e-05, + "loss": 0.3721, + "step": 2215 + }, + { + "epoch": 0.18, + "learning_rate": 1.8796175575836596e-05, + "loss": 0.4918, + "step": 2216 + }, + { + "epoch": 0.18, + "learning_rate": 1.8795632333767926e-05, + "loss": 0.6651, + "step": 2217 + }, + { + "epoch": 0.18, + "learning_rate": 1.8795089091699264e-05, + "loss": 0.312, + "step": 2218 + }, + { + "epoch": 0.18, + "learning_rate": 1.8794545849630598e-05, + "loss": 0.5011, + "step": 2219 + }, + { + "epoch": 0.18, + "learning_rate": 1.8794002607561932e-05, + "loss": 0.8691, + "step": 2220 + }, + { + "epoch": 0.18, + "learning_rate": 1.8793459365493267e-05, + "loss": 0.5529, + "step": 2221 + }, + { + "epoch": 0.18, + "learning_rate": 1.87929161234246e-05, + "loss": 0.6509, + "step": 2222 + }, + { + "epoch": 0.18, + "learning_rate": 1.8792372881355935e-05, + "loss": 0.4303, + "step": 2223 + }, + { + "epoch": 0.18, + "learning_rate": 1.879182963928727e-05, + "loss": 0.5236, + "step": 2224 + }, + { + "epoch": 0.18, + "learning_rate": 1.8791286397218604e-05, + "loss": 0.5271, + "step": 2225 + }, + { + "epoch": 0.18, + "learning_rate": 1.8790743155149934e-05, + "loss": 0.3517, + "step": 2226 + }, + { + "epoch": 0.18, + "learning_rate": 1.8790199913081272e-05, + "loss": 0.827, + "step": 2227 + }, + { + "epoch": 0.18, + "learning_rate": 1.8789656671012603e-05, + "loss": 0.3768, + "step": 2228 + }, + { + "epoch": 0.18, + "learning_rate": 1.878911342894394e-05, + "loss": 0.338, + "step": 2229 + }, + { + "epoch": 0.18, + "learning_rate": 1.878857018687527e-05, + "loss": 0.3581, + "step": 2230 + }, + { + "epoch": 0.18, + "learning_rate": 1.878802694480661e-05, + "loss": 0.8368, + "step": 2231 + }, + { + "epoch": 0.18, + "learning_rate": 1.878748370273794e-05, + "loss": 0.5634, + "step": 2232 + }, + { + "epoch": 0.18, + "learning_rate": 1.8786940460669277e-05, + "loss": 0.4458, + "step": 2233 + }, + { + "epoch": 0.18, + "learning_rate": 1.8786397218600608e-05, + "loss": 0.6947, + "step": 2234 + }, + { + "epoch": 0.18, + "learning_rate": 1.8785853976531946e-05, + "loss": 0.83, + "step": 2235 + }, + { + "epoch": 0.18, + "learning_rate": 1.8785310734463277e-05, + "loss": 0.7312, + "step": 2236 + }, + { + "epoch": 0.18, + "learning_rate": 1.8784767492394614e-05, + "loss": 0.4046, + "step": 2237 + }, + { + "epoch": 0.18, + "learning_rate": 1.8784224250325945e-05, + "loss": 0.4241, + "step": 2238 + }, + { + "epoch": 0.18, + "learning_rate": 1.8783681008257283e-05, + "loss": 0.5011, + "step": 2239 + }, + { + "epoch": 0.18, + "learning_rate": 1.8783137766188614e-05, + "loss": 0.5787, + "step": 2240 + }, + { + "epoch": 0.18, + "learning_rate": 1.878259452411995e-05, + "loss": 0.5606, + "step": 2241 + }, + { + "epoch": 0.18, + "learning_rate": 1.8782051282051282e-05, + "loss": 0.4721, + "step": 2242 + }, + { + "epoch": 0.18, + "learning_rate": 1.878150803998262e-05, + "loss": 0.662, + "step": 2243 + }, + { + "epoch": 0.18, + "learning_rate": 1.878096479791395e-05, + "loss": 0.5964, + "step": 2244 + }, + { + "epoch": 0.18, + "learning_rate": 1.8780421555845285e-05, + "loss": 0.6476, + "step": 2245 + }, + { + "epoch": 0.18, + "learning_rate": 1.877987831377662e-05, + "loss": 0.4125, + "step": 2246 + }, + { + "epoch": 0.18, + "learning_rate": 1.8779335071707953e-05, + "loss": 0.6561, + "step": 2247 + }, + { + "epoch": 0.18, + "learning_rate": 1.8778791829639288e-05, + "loss": 0.5416, + "step": 2248 + }, + { + "epoch": 0.18, + "learning_rate": 1.8778248587570622e-05, + "loss": 0.561, + "step": 2249 + }, + { + "epoch": 0.18, + "learning_rate": 1.8777705345501956e-05, + "loss": 0.4836, + "step": 2250 + }, + { + "epoch": 0.18, + "eval_accuracy": 0.7948038716250637, + "eval_loss": 0.5140156149864197, + "eval_runtime": 22.3112, + "eval_samples_per_second": 439.914, + "eval_steps_per_second": 3.451, + "step": 2250 + }, + { + "epoch": 0.18, + "learning_rate": 1.877716210343329e-05, + "loss": 0.7704, + "step": 2251 + }, + { + "epoch": 0.18, + "learning_rate": 1.8776618861364624e-05, + "loss": 0.6455, + "step": 2252 + }, + { + "epoch": 0.18, + "learning_rate": 1.877607561929596e-05, + "loss": 0.4992, + "step": 2253 + }, + { + "epoch": 0.18, + "learning_rate": 1.8775532377227296e-05, + "loss": 0.4464, + "step": 2254 + }, + { + "epoch": 0.18, + "learning_rate": 1.8774989135158627e-05, + "loss": 0.5439, + "step": 2255 + }, + { + "epoch": 0.18, + "learning_rate": 1.8774445893089965e-05, + "loss": 0.2248, + "step": 2256 + }, + { + "epoch": 0.18, + "learning_rate": 1.8773902651021296e-05, + "loss": 0.4244, + "step": 2257 + }, + { + "epoch": 0.18, + "learning_rate": 1.8773359408952633e-05, + "loss": 0.5628, + "step": 2258 + }, + { + "epoch": 0.18, + "learning_rate": 1.8772816166883964e-05, + "loss": 0.8734, + "step": 2259 + }, + { + "epoch": 0.18, + "learning_rate": 1.87722729248153e-05, + "loss": 0.3824, + "step": 2260 + }, + { + "epoch": 0.18, + "learning_rate": 1.8771729682746633e-05, + "loss": 0.4348, + "step": 2261 + }, + { + "epoch": 0.18, + "learning_rate": 1.877118644067797e-05, + "loss": 0.5576, + "step": 2262 + }, + { + "epoch": 0.18, + "learning_rate": 1.87706431986093e-05, + "loss": 0.3858, + "step": 2263 + }, + { + "epoch": 0.18, + "learning_rate": 1.8770099956540635e-05, + "loss": 0.811, + "step": 2264 + }, + { + "epoch": 0.18, + "learning_rate": 1.876955671447197e-05, + "loss": 0.4648, + "step": 2265 + }, + { + "epoch": 0.18, + "learning_rate": 1.8769013472403304e-05, + "loss": 0.4912, + "step": 2266 + }, + { + "epoch": 0.18, + "learning_rate": 1.8768470230334638e-05, + "loss": 0.6307, + "step": 2267 + }, + { + "epoch": 0.18, + "learning_rate": 1.8767926988265972e-05, + "loss": 0.5858, + "step": 2268 + }, + { + "epoch": 0.18, + "learning_rate": 1.8767383746197306e-05, + "loss": 0.4338, + "step": 2269 + }, + { + "epoch": 0.18, + "learning_rate": 1.876684050412864e-05, + "loss": 0.5775, + "step": 2270 + }, + { + "epoch": 0.19, + "learning_rate": 1.8766297262059975e-05, + "loss": 0.5767, + "step": 2271 + }, + { + "epoch": 0.19, + "learning_rate": 1.876575401999131e-05, + "loss": 0.4796, + "step": 2272 + }, + { + "epoch": 0.19, + "learning_rate": 1.8765210777922643e-05, + "loss": 0.4319, + "step": 2273 + }, + { + "epoch": 0.19, + "learning_rate": 1.8764667535853978e-05, + "loss": 0.5519, + "step": 2274 + }, + { + "epoch": 0.19, + "learning_rate": 1.8764124293785312e-05, + "loss": 0.4915, + "step": 2275 + }, + { + "epoch": 0.19, + "learning_rate": 1.8763581051716646e-05, + "loss": 0.5742, + "step": 2276 + }, + { + "epoch": 0.19, + "learning_rate": 1.876303780964798e-05, + "loss": 0.6615, + "step": 2277 + }, + { + "epoch": 0.19, + "learning_rate": 1.8762494567579314e-05, + "loss": 0.6254, + "step": 2278 + }, + { + "epoch": 0.19, + "learning_rate": 1.876195132551065e-05, + "loss": 0.9353, + "step": 2279 + }, + { + "epoch": 0.19, + "learning_rate": 1.8761408083441983e-05, + "loss": 0.4734, + "step": 2280 + }, + { + "epoch": 0.19, + "learning_rate": 1.8760864841373317e-05, + "loss": 0.5092, + "step": 2281 + }, + { + "epoch": 0.19, + "learning_rate": 1.876032159930465e-05, + "loss": 0.8177, + "step": 2282 + }, + { + "epoch": 0.19, + "learning_rate": 1.8759778357235986e-05, + "loss": 0.4584, + "step": 2283 + }, + { + "epoch": 0.19, + "learning_rate": 1.875923511516732e-05, + "loss": 0.5169, + "step": 2284 + }, + { + "epoch": 0.19, + "learning_rate": 1.8758691873098654e-05, + "loss": 0.6236, + "step": 2285 + }, + { + "epoch": 0.19, + "learning_rate": 1.8758148631029988e-05, + "loss": 0.402, + "step": 2286 + }, + { + "epoch": 0.19, + "learning_rate": 1.8757605388961323e-05, + "loss": 0.6824, + "step": 2287 + }, + { + "epoch": 0.19, + "learning_rate": 1.8757062146892657e-05, + "loss": 0.4845, + "step": 2288 + }, + { + "epoch": 0.19, + "learning_rate": 1.875651890482399e-05, + "loss": 0.7766, + "step": 2289 + }, + { + "epoch": 0.19, + "learning_rate": 1.8755975662755325e-05, + "loss": 0.4872, + "step": 2290 + }, + { + "epoch": 0.19, + "learning_rate": 1.875543242068666e-05, + "loss": 0.3449, + "step": 2291 + }, + { + "epoch": 0.19, + "learning_rate": 1.8754889178617994e-05, + "loss": 0.5292, + "step": 2292 + }, + { + "epoch": 0.19, + "learning_rate": 1.8754345936549328e-05, + "loss": 0.597, + "step": 2293 + }, + { + "epoch": 0.19, + "learning_rate": 1.8753802694480662e-05, + "loss": 0.669, + "step": 2294 + }, + { + "epoch": 0.19, + "learning_rate": 1.8753259452411996e-05, + "loss": 0.774, + "step": 2295 + }, + { + "epoch": 0.19, + "learning_rate": 1.875271621034333e-05, + "loss": 0.5188, + "step": 2296 + }, + { + "epoch": 0.19, + "learning_rate": 1.8752172968274665e-05, + "loss": 0.6168, + "step": 2297 + }, + { + "epoch": 0.19, + "learning_rate": 1.8751629726206e-05, + "loss": 0.4864, + "step": 2298 + }, + { + "epoch": 0.19, + "learning_rate": 1.8751086484137333e-05, + "loss": 0.4434, + "step": 2299 + }, + { + "epoch": 0.19, + "learning_rate": 1.8750543242068668e-05, + "loss": 0.6617, + "step": 2300 + }, + { + "epoch": 0.19, + "learning_rate": 1.8750000000000002e-05, + "loss": 0.4033, + "step": 2301 + }, + { + "epoch": 0.19, + "learning_rate": 1.8749456757931336e-05, + "loss": 0.3619, + "step": 2302 + }, + { + "epoch": 0.19, + "learning_rate": 1.874891351586267e-05, + "loss": 0.5611, + "step": 2303 + }, + { + "epoch": 0.19, + "learning_rate": 1.8748370273794004e-05, + "loss": 0.8143, + "step": 2304 + }, + { + "epoch": 0.19, + "learning_rate": 1.874782703172534e-05, + "loss": 0.8044, + "step": 2305 + }, + { + "epoch": 0.19, + "learning_rate": 1.8747283789656673e-05, + "loss": 0.4506, + "step": 2306 + }, + { + "epoch": 0.19, + "learning_rate": 1.8746740547588007e-05, + "loss": 0.5083, + "step": 2307 + }, + { + "epoch": 0.19, + "learning_rate": 1.874619730551934e-05, + "loss": 0.6235, + "step": 2308 + }, + { + "epoch": 0.19, + "learning_rate": 1.8745654063450676e-05, + "loss": 0.7925, + "step": 2309 + }, + { + "epoch": 0.19, + "learning_rate": 1.874511082138201e-05, + "loss": 0.769, + "step": 2310 + }, + { + "epoch": 0.19, + "learning_rate": 1.8744567579313344e-05, + "loss": 0.7454, + "step": 2311 + }, + { + "epoch": 0.19, + "learning_rate": 1.8744024337244678e-05, + "loss": 0.5655, + "step": 2312 + }, + { + "epoch": 0.19, + "learning_rate": 1.8743481095176013e-05, + "loss": 0.5097, + "step": 2313 + }, + { + "epoch": 0.19, + "learning_rate": 1.8742937853107347e-05, + "loss": 0.6338, + "step": 2314 + }, + { + "epoch": 0.19, + "learning_rate": 1.874239461103868e-05, + "loss": 0.3869, + "step": 2315 + }, + { + "epoch": 0.19, + "learning_rate": 1.8741851368970015e-05, + "loss": 0.5994, + "step": 2316 + }, + { + "epoch": 0.19, + "learning_rate": 1.874130812690135e-05, + "loss": 0.4435, + "step": 2317 + }, + { + "epoch": 0.19, + "learning_rate": 1.8740764884832684e-05, + "loss": 0.6865, + "step": 2318 + }, + { + "epoch": 0.19, + "learning_rate": 1.8740221642764018e-05, + "loss": 0.6575, + "step": 2319 + }, + { + "epoch": 0.19, + "learning_rate": 1.8739678400695352e-05, + "loss": 0.7186, + "step": 2320 + }, + { + "epoch": 0.19, + "learning_rate": 1.8739135158626683e-05, + "loss": 0.4177, + "step": 2321 + }, + { + "epoch": 0.19, + "learning_rate": 1.873859191655802e-05, + "loss": 0.7148, + "step": 2322 + }, + { + "epoch": 0.19, + "learning_rate": 1.873804867448935e-05, + "loss": 0.3949, + "step": 2323 + }, + { + "epoch": 0.19, + "learning_rate": 1.873750543242069e-05, + "loss": 0.8369, + "step": 2324 + }, + { + "epoch": 0.19, + "learning_rate": 1.873696219035202e-05, + "loss": 0.7993, + "step": 2325 + }, + { + "epoch": 0.19, + "learning_rate": 1.8736418948283358e-05, + "loss": 0.6542, + "step": 2326 + }, + { + "epoch": 0.19, + "learning_rate": 1.8735875706214692e-05, + "loss": 0.5937, + "step": 2327 + }, + { + "epoch": 0.19, + "learning_rate": 1.8735332464146026e-05, + "loss": 0.5574, + "step": 2328 + }, + { + "epoch": 0.19, + "learning_rate": 1.873478922207736e-05, + "loss": 0.4233, + "step": 2329 + }, + { + "epoch": 0.19, + "learning_rate": 1.8734245980008694e-05, + "loss": 0.5047, + "step": 2330 + }, + { + "epoch": 0.19, + "learning_rate": 1.873370273794003e-05, + "loss": 0.3514, + "step": 2331 + }, + { + "epoch": 0.19, + "learning_rate": 1.8733159495871363e-05, + "loss": 0.4819, + "step": 2332 + }, + { + "epoch": 0.19, + "learning_rate": 1.8732616253802697e-05, + "loss": 0.3386, + "step": 2333 + }, + { + "epoch": 0.19, + "learning_rate": 1.873207301173403e-05, + "loss": 0.3813, + "step": 2334 + }, + { + "epoch": 0.19, + "learning_rate": 1.8731529769665366e-05, + "loss": 0.4179, + "step": 2335 + }, + { + "epoch": 0.19, + "learning_rate": 1.87309865275967e-05, + "loss": 0.5702, + "step": 2336 + }, + { + "epoch": 0.19, + "learning_rate": 1.8730443285528034e-05, + "loss": 0.4311, + "step": 2337 + }, + { + "epoch": 0.19, + "learning_rate": 1.8729900043459368e-05, + "loss": 0.7276, + "step": 2338 + }, + { + "epoch": 0.19, + "learning_rate": 1.8729356801390703e-05, + "loss": 0.4423, + "step": 2339 + }, + { + "epoch": 0.19, + "learning_rate": 1.8728813559322033e-05, + "loss": 0.6782, + "step": 2340 + }, + { + "epoch": 0.19, + "learning_rate": 1.872827031725337e-05, + "loss": 0.4126, + "step": 2341 + }, + { + "epoch": 0.19, + "learning_rate": 1.8727727075184702e-05, + "loss": 0.5833, + "step": 2342 + }, + { + "epoch": 0.19, + "learning_rate": 1.872718383311604e-05, + "loss": 0.5624, + "step": 2343 + }, + { + "epoch": 0.19, + "learning_rate": 1.872664059104737e-05, + "loss": 0.6539, + "step": 2344 + }, + { + "epoch": 0.19, + "learning_rate": 1.8726097348978708e-05, + "loss": 0.2945, + "step": 2345 + }, + { + "epoch": 0.19, + "learning_rate": 1.872555410691004e-05, + "loss": 0.4427, + "step": 2346 + }, + { + "epoch": 0.19, + "learning_rate": 1.8725010864841376e-05, + "loss": 0.5052, + "step": 2347 + }, + { + "epoch": 0.19, + "learning_rate": 1.8724467622772707e-05, + "loss": 0.3157, + "step": 2348 + }, + { + "epoch": 0.19, + "learning_rate": 1.8723924380704045e-05, + "loss": 0.394, + "step": 2349 + }, + { + "epoch": 0.19, + "learning_rate": 1.8723381138635376e-05, + "loss": 0.6717, + "step": 2350 + }, + { + "epoch": 0.19, + "learning_rate": 1.8722837896566713e-05, + "loss": 0.4744, + "step": 2351 + }, + { + "epoch": 0.19, + "learning_rate": 1.8722294654498044e-05, + "loss": 0.4224, + "step": 2352 + }, + { + "epoch": 0.19, + "learning_rate": 1.8721751412429382e-05, + "loss": 0.4392, + "step": 2353 + }, + { + "epoch": 0.19, + "learning_rate": 1.8721208170360713e-05, + "loss": 0.553, + "step": 2354 + }, + { + "epoch": 0.19, + "learning_rate": 1.872066492829205e-05, + "loss": 0.7181, + "step": 2355 + }, + { + "epoch": 0.19, + "learning_rate": 1.872012168622338e-05, + "loss": 0.4607, + "step": 2356 + }, + { + "epoch": 0.19, + "learning_rate": 1.871957844415472e-05, + "loss": 0.4493, + "step": 2357 + }, + { + "epoch": 0.19, + "learning_rate": 1.871903520208605e-05, + "loss": 0.366, + "step": 2358 + }, + { + "epoch": 0.19, + "learning_rate": 1.8718491960017384e-05, + "loss": 0.846, + "step": 2359 + }, + { + "epoch": 0.19, + "learning_rate": 1.8717948717948718e-05, + "loss": 0.6314, + "step": 2360 + }, + { + "epoch": 0.19, + "learning_rate": 1.8717405475880052e-05, + "loss": 0.4802, + "step": 2361 + }, + { + "epoch": 0.19, + "learning_rate": 1.871686223381139e-05, + "loss": 0.6184, + "step": 2362 + }, + { + "epoch": 0.19, + "learning_rate": 1.871631899174272e-05, + "loss": 0.6256, + "step": 2363 + }, + { + "epoch": 0.19, + "learning_rate": 1.8715775749674058e-05, + "loss": 0.334, + "step": 2364 + }, + { + "epoch": 0.19, + "learning_rate": 1.871523250760539e-05, + "loss": 0.5558, + "step": 2365 + }, + { + "epoch": 0.19, + "learning_rate": 1.8714689265536727e-05, + "loss": 0.584, + "step": 2366 + }, + { + "epoch": 0.19, + "learning_rate": 1.8714146023468058e-05, + "loss": 0.4277, + "step": 2367 + }, + { + "epoch": 0.19, + "learning_rate": 1.8713602781399395e-05, + "loss": 0.8909, + "step": 2368 + }, + { + "epoch": 0.19, + "learning_rate": 1.8713059539330726e-05, + "loss": 0.7522, + "step": 2369 + }, + { + "epoch": 0.19, + "learning_rate": 1.8712516297262064e-05, + "loss": 0.5791, + "step": 2370 + }, + { + "epoch": 0.19, + "learning_rate": 1.8711973055193394e-05, + "loss": 0.8662, + "step": 2371 + }, + { + "epoch": 0.19, + "learning_rate": 1.8711429813124732e-05, + "loss": 0.4111, + "step": 2372 + }, + { + "epoch": 0.19, + "learning_rate": 1.8710886571056063e-05, + "loss": 0.4296, + "step": 2373 + }, + { + "epoch": 0.19, + "learning_rate": 1.87103433289874e-05, + "loss": 0.5514, + "step": 2374 + }, + { + "epoch": 0.19, + "learning_rate": 1.870980008691873e-05, + "loss": 0.5253, + "step": 2375 + }, + { + "epoch": 0.19, + "learning_rate": 1.870925684485007e-05, + "loss": 0.5422, + "step": 2376 + }, + { + "epoch": 0.19, + "learning_rate": 1.87087136027814e-05, + "loss": 0.4844, + "step": 2377 + }, + { + "epoch": 0.19, + "learning_rate": 1.8708170360712734e-05, + "loss": 0.5582, + "step": 2378 + }, + { + "epoch": 0.19, + "learning_rate": 1.870762711864407e-05, + "loss": 0.603, + "step": 2379 + }, + { + "epoch": 0.19, + "learning_rate": 1.8707083876575403e-05, + "loss": 0.4892, + "step": 2380 + }, + { + "epoch": 0.19, + "learning_rate": 1.8706540634506737e-05, + "loss": 0.567, + "step": 2381 + }, + { + "epoch": 0.19, + "learning_rate": 1.870599739243807e-05, + "loss": 0.7418, + "step": 2382 + }, + { + "epoch": 0.19, + "learning_rate": 1.8705454150369405e-05, + "loss": 0.6102, + "step": 2383 + }, + { + "epoch": 0.19, + "learning_rate": 1.870491090830074e-05, + "loss": 0.5515, + "step": 2384 + }, + { + "epoch": 0.19, + "learning_rate": 1.8704367666232074e-05, + "loss": 0.4779, + "step": 2385 + }, + { + "epoch": 0.19, + "learning_rate": 1.8703824424163408e-05, + "loss": 0.4746, + "step": 2386 + }, + { + "epoch": 0.19, + "learning_rate": 1.8703281182094742e-05, + "loss": 0.8552, + "step": 2387 + }, + { + "epoch": 0.19, + "learning_rate": 1.8702737940026076e-05, + "loss": 0.6063, + "step": 2388 + }, + { + "epoch": 0.19, + "learning_rate": 1.870219469795741e-05, + "loss": 0.4868, + "step": 2389 + }, + { + "epoch": 0.19, + "learning_rate": 1.8701651455888745e-05, + "loss": 0.3253, + "step": 2390 + }, + { + "epoch": 0.19, + "learning_rate": 1.870110821382008e-05, + "loss": 0.6141, + "step": 2391 + }, + { + "epoch": 0.19, + "learning_rate": 1.8700564971751413e-05, + "loss": 0.6517, + "step": 2392 + }, + { + "epoch": 0.19, + "learning_rate": 1.8700021729682748e-05, + "loss": 0.6027, + "step": 2393 + }, + { + "epoch": 0.2, + "learning_rate": 1.8699478487614082e-05, + "loss": 0.4459, + "step": 2394 + }, + { + "epoch": 0.2, + "learning_rate": 1.8698935245545416e-05, + "loss": 0.5958, + "step": 2395 + }, + { + "epoch": 0.2, + "learning_rate": 1.869839200347675e-05, + "loss": 0.5797, + "step": 2396 + }, + { + "epoch": 0.2, + "learning_rate": 1.8697848761408084e-05, + "loss": 0.7513, + "step": 2397 + }, + { + "epoch": 0.2, + "learning_rate": 1.869730551933942e-05, + "loss": 0.8542, + "step": 2398 + }, + { + "epoch": 0.2, + "learning_rate": 1.8696762277270753e-05, + "loss": 0.3819, + "step": 2399 + }, + { + "epoch": 0.2, + "learning_rate": 1.8696219035202087e-05, + "loss": 0.5894, + "step": 2400 + }, + { + "epoch": 0.2, + "learning_rate": 1.869567579313342e-05, + "loss": 0.4095, + "step": 2401 + }, + { + "epoch": 0.2, + "learning_rate": 1.8695132551064756e-05, + "loss": 0.6257, + "step": 2402 + }, + { + "epoch": 0.2, + "learning_rate": 1.869458930899609e-05, + "loss": 0.5812, + "step": 2403 + }, + { + "epoch": 0.2, + "learning_rate": 1.8694046066927424e-05, + "loss": 0.442, + "step": 2404 + }, + { + "epoch": 0.2, + "learning_rate": 1.869350282485876e-05, + "loss": 0.5756, + "step": 2405 + }, + { + "epoch": 0.2, + "learning_rate": 1.8692959582790093e-05, + "loss": 0.447, + "step": 2406 + }, + { + "epoch": 0.2, + "learning_rate": 1.8692416340721427e-05, + "loss": 0.5761, + "step": 2407 + }, + { + "epoch": 0.2, + "learning_rate": 1.869187309865276e-05, + "loss": 0.5127, + "step": 2408 + }, + { + "epoch": 0.2, + "learning_rate": 1.8691329856584095e-05, + "loss": 0.2887, + "step": 2409 + }, + { + "epoch": 0.2, + "learning_rate": 1.869078661451543e-05, + "loss": 0.3027, + "step": 2410 + }, + { + "epoch": 0.2, + "learning_rate": 1.8690243372446764e-05, + "loss": 0.4632, + "step": 2411 + }, + { + "epoch": 0.2, + "learning_rate": 1.8689700130378098e-05, + "loss": 0.428, + "step": 2412 + }, + { + "epoch": 0.2, + "learning_rate": 1.8689156888309432e-05, + "loss": 0.5456, + "step": 2413 + }, + { + "epoch": 0.2, + "learning_rate": 1.8688613646240766e-05, + "loss": 0.5825, + "step": 2414 + }, + { + "epoch": 0.2, + "learning_rate": 1.86880704041721e-05, + "loss": 0.4913, + "step": 2415 + }, + { + "epoch": 0.2, + "learning_rate": 1.8687527162103435e-05, + "loss": 0.4916, + "step": 2416 + }, + { + "epoch": 0.2, + "learning_rate": 1.868698392003477e-05, + "loss": 0.4415, + "step": 2417 + }, + { + "epoch": 0.2, + "learning_rate": 1.8686440677966103e-05, + "loss": 0.5697, + "step": 2418 + }, + { + "epoch": 0.2, + "learning_rate": 1.8685897435897438e-05, + "loss": 0.5724, + "step": 2419 + }, + { + "epoch": 0.2, + "learning_rate": 1.8685354193828772e-05, + "loss": 0.987, + "step": 2420 + }, + { + "epoch": 0.2, + "learning_rate": 1.8684810951760106e-05, + "loss": 0.7536, + "step": 2421 + }, + { + "epoch": 0.2, + "learning_rate": 1.868426770969144e-05, + "loss": 0.6765, + "step": 2422 + }, + { + "epoch": 0.2, + "learning_rate": 1.8683724467622774e-05, + "loss": 0.5165, + "step": 2423 + }, + { + "epoch": 0.2, + "learning_rate": 1.868318122555411e-05, + "loss": 0.303, + "step": 2424 + }, + { + "epoch": 0.2, + "learning_rate": 1.8682637983485443e-05, + "loss": 0.7074, + "step": 2425 + }, + { + "epoch": 0.2, + "learning_rate": 1.8682094741416777e-05, + "loss": 0.5843, + "step": 2426 + }, + { + "epoch": 0.2, + "learning_rate": 1.868155149934811e-05, + "loss": 0.6225, + "step": 2427 + }, + { + "epoch": 0.2, + "learning_rate": 1.8681008257279446e-05, + "loss": 0.5155, + "step": 2428 + }, + { + "epoch": 0.2, + "learning_rate": 1.868046501521078e-05, + "loss": 0.5166, + "step": 2429 + }, + { + "epoch": 0.2, + "learning_rate": 1.8679921773142114e-05, + "loss": 0.5361, + "step": 2430 + }, + { + "epoch": 0.2, + "learning_rate": 1.867937853107345e-05, + "loss": 0.4561, + "step": 2431 + }, + { + "epoch": 0.2, + "learning_rate": 1.8678835289004783e-05, + "loss": 0.81, + "step": 2432 + }, + { + "epoch": 0.2, + "learning_rate": 1.8678292046936117e-05, + "loss": 0.4888, + "step": 2433 + }, + { + "epoch": 0.2, + "learning_rate": 1.867774880486745e-05, + "loss": 0.8336, + "step": 2434 + }, + { + "epoch": 0.2, + "learning_rate": 1.8677205562798785e-05, + "loss": 0.8066, + "step": 2435 + }, + { + "epoch": 0.2, + "learning_rate": 1.867666232073012e-05, + "loss": 0.7611, + "step": 2436 + }, + { + "epoch": 0.2, + "learning_rate": 1.8676119078661454e-05, + "loss": 0.4895, + "step": 2437 + }, + { + "epoch": 0.2, + "learning_rate": 1.8675575836592788e-05, + "loss": 0.3854, + "step": 2438 + }, + { + "epoch": 0.2, + "learning_rate": 1.8675032594524122e-05, + "loss": 0.5174, + "step": 2439 + }, + { + "epoch": 0.2, + "learning_rate": 1.8674489352455456e-05, + "loss": 0.6008, + "step": 2440 + }, + { + "epoch": 0.2, + "learning_rate": 1.867394611038679e-05, + "loss": 0.5864, + "step": 2441 + }, + { + "epoch": 0.2, + "learning_rate": 1.8673402868318125e-05, + "loss": 0.496, + "step": 2442 + }, + { + "epoch": 0.2, + "learning_rate": 1.867285962624946e-05, + "loss": 0.618, + "step": 2443 + }, + { + "epoch": 0.2, + "learning_rate": 1.8672316384180793e-05, + "loss": 0.3983, + "step": 2444 + }, + { + "epoch": 0.2, + "learning_rate": 1.8671773142112128e-05, + "loss": 0.8152, + "step": 2445 + }, + { + "epoch": 0.2, + "learning_rate": 1.8671229900043462e-05, + "loss": 0.4097, + "step": 2446 + }, + { + "epoch": 0.2, + "learning_rate": 1.8670686657974796e-05, + "loss": 0.3714, + "step": 2447 + }, + { + "epoch": 0.2, + "learning_rate": 1.867014341590613e-05, + "loss": 0.5835, + "step": 2448 + }, + { + "epoch": 0.2, + "learning_rate": 1.8669600173837464e-05, + "loss": 0.6633, + "step": 2449 + }, + { + "epoch": 0.2, + "learning_rate": 1.86690569317688e-05, + "loss": 0.5035, + "step": 2450 + }, + { + "epoch": 0.2, + "learning_rate": 1.8668513689700133e-05, + "loss": 0.6396, + "step": 2451 + }, + { + "epoch": 0.2, + "learning_rate": 1.8667970447631467e-05, + "loss": 0.3384, + "step": 2452 + }, + { + "epoch": 0.2, + "learning_rate": 1.86674272055628e-05, + "loss": 0.4856, + "step": 2453 + }, + { + "epoch": 0.2, + "learning_rate": 1.8666883963494132e-05, + "loss": 0.5968, + "step": 2454 + }, + { + "epoch": 0.2, + "learning_rate": 1.866634072142547e-05, + "loss": 0.5275, + "step": 2455 + }, + { + "epoch": 0.2, + "learning_rate": 1.86657974793568e-05, + "loss": 0.2361, + "step": 2456 + }, + { + "epoch": 0.2, + "learning_rate": 1.866525423728814e-05, + "loss": 0.5693, + "step": 2457 + }, + { + "epoch": 0.2, + "learning_rate": 1.866471099521947e-05, + "loss": 0.6351, + "step": 2458 + }, + { + "epoch": 0.2, + "learning_rate": 1.8664167753150807e-05, + "loss": 0.4778, + "step": 2459 + }, + { + "epoch": 0.2, + "learning_rate": 1.8663624511082138e-05, + "loss": 0.5602, + "step": 2460 + }, + { + "epoch": 0.2, + "learning_rate": 1.8663081269013475e-05, + "loss": 0.5652, + "step": 2461 + }, + { + "epoch": 0.2, + "learning_rate": 1.8662538026944806e-05, + "loss": 0.6244, + "step": 2462 + }, + { + "epoch": 0.2, + "learning_rate": 1.8661994784876144e-05, + "loss": 0.8253, + "step": 2463 + }, + { + "epoch": 0.2, + "learning_rate": 1.8661451542807475e-05, + "loss": 0.5199, + "step": 2464 + }, + { + "epoch": 0.2, + "learning_rate": 1.8660908300738812e-05, + "loss": 0.5325, + "step": 2465 + }, + { + "epoch": 0.2, + "learning_rate": 1.8660365058670143e-05, + "loss": 0.6313, + "step": 2466 + }, + { + "epoch": 0.2, + "learning_rate": 1.865982181660148e-05, + "loss": 0.6486, + "step": 2467 + }, + { + "epoch": 0.2, + "learning_rate": 1.865927857453281e-05, + "loss": 0.3439, + "step": 2468 + }, + { + "epoch": 0.2, + "learning_rate": 1.865873533246415e-05, + "loss": 0.5182, + "step": 2469 + }, + { + "epoch": 0.2, + "learning_rate": 1.8658192090395483e-05, + "loss": 0.4581, + "step": 2470 + }, + { + "epoch": 0.2, + "learning_rate": 1.8657648848326818e-05, + "loss": 0.5199, + "step": 2471 + }, + { + "epoch": 0.2, + "learning_rate": 1.8657105606258152e-05, + "loss": 0.5687, + "step": 2472 + }, + { + "epoch": 0.2, + "learning_rate": 1.8656562364189483e-05, + "loss": 0.5053, + "step": 2473 + }, + { + "epoch": 0.2, + "learning_rate": 1.865601912212082e-05, + "loss": 0.4924, + "step": 2474 + }, + { + "epoch": 0.2, + "learning_rate": 1.865547588005215e-05, + "loss": 0.4654, + "step": 2475 + }, + { + "epoch": 0.2, + "learning_rate": 1.865493263798349e-05, + "loss": 0.7189, + "step": 2476 + }, + { + "epoch": 0.2, + "learning_rate": 1.865438939591482e-05, + "loss": 0.5681, + "step": 2477 + }, + { + "epoch": 0.2, + "learning_rate": 1.8653846153846157e-05, + "loss": 0.7129, + "step": 2478 + }, + { + "epoch": 0.2, + "learning_rate": 1.8653302911777488e-05, + "loss": 0.5475, + "step": 2479 + }, + { + "epoch": 0.2, + "learning_rate": 1.8652759669708826e-05, + "loss": 0.4385, + "step": 2480 + }, + { + "epoch": 0.2, + "learning_rate": 1.8652216427640156e-05, + "loss": 0.3654, + "step": 2481 + }, + { + "epoch": 0.2, + "learning_rate": 1.8651673185571494e-05, + "loss": 0.4692, + "step": 2482 + }, + { + "epoch": 0.2, + "learning_rate": 1.8651129943502825e-05, + "loss": 0.6462, + "step": 2483 + }, + { + "epoch": 0.2, + "learning_rate": 1.8650586701434163e-05, + "loss": 0.8749, + "step": 2484 + }, + { + "epoch": 0.2, + "learning_rate": 1.8650043459365493e-05, + "loss": 0.8166, + "step": 2485 + }, + { + "epoch": 0.2, + "learning_rate": 1.864950021729683e-05, + "loss": 0.4112, + "step": 2486 + }, + { + "epoch": 0.2, + "learning_rate": 1.8648956975228162e-05, + "loss": 0.6607, + "step": 2487 + }, + { + "epoch": 0.2, + "learning_rate": 1.86484137331595e-05, + "loss": 0.6119, + "step": 2488 + }, + { + "epoch": 0.2, + "learning_rate": 1.864787049109083e-05, + "loss": 0.3621, + "step": 2489 + }, + { + "epoch": 0.2, + "learning_rate": 1.8647327249022168e-05, + "loss": 0.5901, + "step": 2490 + }, + { + "epoch": 0.2, + "learning_rate": 1.86467840069535e-05, + "loss": 0.7022, + "step": 2491 + }, + { + "epoch": 0.2, + "learning_rate": 1.8646240764884833e-05, + "loss": 0.6619, + "step": 2492 + }, + { + "epoch": 0.2, + "learning_rate": 1.8645697522816167e-05, + "loss": 0.6257, + "step": 2493 + }, + { + "epoch": 0.2, + "learning_rate": 1.86451542807475e-05, + "loss": 0.4284, + "step": 2494 + }, + { + "epoch": 0.2, + "learning_rate": 1.8644611038678836e-05, + "loss": 0.6969, + "step": 2495 + }, + { + "epoch": 0.2, + "learning_rate": 1.864406779661017e-05, + "loss": 0.6138, + "step": 2496 + }, + { + "epoch": 0.2, + "learning_rate": 1.8643524554541504e-05, + "loss": 0.6506, + "step": 2497 + }, + { + "epoch": 0.2, + "learning_rate": 1.864298131247284e-05, + "loss": 0.529, + "step": 2498 + }, + { + "epoch": 0.2, + "learning_rate": 1.8642438070404173e-05, + "loss": 0.7303, + "step": 2499 + }, + { + "epoch": 0.2, + "learning_rate": 1.8641894828335507e-05, + "loss": 0.3597, + "step": 2500 + }, + { + "epoch": 0.2, + "eval_accuracy": 0.7886907794192562, + "eval_loss": 0.5339555740356445, + "eval_runtime": 22.3101, + "eval_samples_per_second": 439.935, + "eval_steps_per_second": 3.451, + "step": 2500 + }, + { + "epoch": 0.2, + "learning_rate": 1.864135158626684e-05, + "loss": 0.6494, + "step": 2501 + }, + { + "epoch": 0.2, + "learning_rate": 1.8640808344198175e-05, + "loss": 0.4719, + "step": 2502 + }, + { + "epoch": 0.2, + "learning_rate": 1.864026510212951e-05, + "loss": 0.7139, + "step": 2503 + }, + { + "epoch": 0.2, + "learning_rate": 1.8639721860060844e-05, + "loss": 0.6002, + "step": 2504 + }, + { + "epoch": 0.2, + "learning_rate": 1.8639178617992178e-05, + "loss": 0.6235, + "step": 2505 + }, + { + "epoch": 0.2, + "learning_rate": 1.8638635375923512e-05, + "loss": 0.3957, + "step": 2506 + }, + { + "epoch": 0.2, + "learning_rate": 1.863809213385485e-05, + "loss": 0.5588, + "step": 2507 + }, + { + "epoch": 0.2, + "learning_rate": 1.863754889178618e-05, + "loss": 0.4552, + "step": 2508 + }, + { + "epoch": 0.2, + "learning_rate": 1.863700564971752e-05, + "loss": 0.8466, + "step": 2509 + }, + { + "epoch": 0.2, + "learning_rate": 1.863646240764885e-05, + "loss": 0.4164, + "step": 2510 + }, + { + "epoch": 0.2, + "learning_rate": 1.8635919165580183e-05, + "loss": 0.8729, + "step": 2511 + }, + { + "epoch": 0.2, + "learning_rate": 1.8635375923511518e-05, + "loss": 0.5222, + "step": 2512 + }, + { + "epoch": 0.2, + "learning_rate": 1.8634832681442852e-05, + "loss": 0.5799, + "step": 2513 + }, + { + "epoch": 0.2, + "learning_rate": 1.8634289439374186e-05, + "loss": 0.6518, + "step": 2514 + }, + { + "epoch": 0.2, + "learning_rate": 1.863374619730552e-05, + "loss": 0.3753, + "step": 2515 + }, + { + "epoch": 0.21, + "learning_rate": 1.8633202955236855e-05, + "loss": 0.4965, + "step": 2516 + }, + { + "epoch": 0.21, + "learning_rate": 1.863265971316819e-05, + "loss": 0.7562, + "step": 2517 + }, + { + "epoch": 0.21, + "learning_rate": 1.8632116471099523e-05, + "loss": 0.4688, + "step": 2518 + }, + { + "epoch": 0.21, + "learning_rate": 1.8631573229030857e-05, + "loss": 0.4672, + "step": 2519 + }, + { + "epoch": 0.21, + "learning_rate": 1.863102998696219e-05, + "loss": 0.5949, + "step": 2520 + }, + { + "epoch": 0.21, + "learning_rate": 1.8630486744893526e-05, + "loss": 0.6165, + "step": 2521 + }, + { + "epoch": 0.21, + "learning_rate": 1.862994350282486e-05, + "loss": 0.5352, + "step": 2522 + }, + { + "epoch": 0.21, + "learning_rate": 1.8629400260756194e-05, + "loss": 0.5972, + "step": 2523 + }, + { + "epoch": 0.21, + "learning_rate": 1.862885701868753e-05, + "loss": 0.5176, + "step": 2524 + }, + { + "epoch": 0.21, + "learning_rate": 1.8628313776618863e-05, + "loss": 0.7313, + "step": 2525 + }, + { + "epoch": 0.21, + "learning_rate": 1.8627770534550197e-05, + "loss": 0.4449, + "step": 2526 + }, + { + "epoch": 0.21, + "learning_rate": 1.862722729248153e-05, + "loss": 0.4758, + "step": 2527 + }, + { + "epoch": 0.21, + "learning_rate": 1.8626684050412865e-05, + "loss": 0.5054, + "step": 2528 + }, + { + "epoch": 0.21, + "learning_rate": 1.86261408083442e-05, + "loss": 0.6686, + "step": 2529 + }, + { + "epoch": 0.21, + "learning_rate": 1.8625597566275534e-05, + "loss": 0.4678, + "step": 2530 + }, + { + "epoch": 0.21, + "learning_rate": 1.8625054324206868e-05, + "loss": 0.5039, + "step": 2531 + }, + { + "epoch": 0.21, + "learning_rate": 1.8624511082138202e-05, + "loss": 0.6729, + "step": 2532 + }, + { + "epoch": 0.21, + "learning_rate": 1.8623967840069536e-05, + "loss": 0.664, + "step": 2533 + }, + { + "epoch": 0.21, + "learning_rate": 1.862342459800087e-05, + "loss": 0.6776, + "step": 2534 + }, + { + "epoch": 0.21, + "learning_rate": 1.8622881355932205e-05, + "loss": 0.7445, + "step": 2535 + }, + { + "epoch": 0.21, + "learning_rate": 1.862233811386354e-05, + "loss": 0.6019, + "step": 2536 + }, + { + "epoch": 0.21, + "learning_rate": 1.8621794871794873e-05, + "loss": 0.4897, + "step": 2537 + }, + { + "epoch": 0.21, + "learning_rate": 1.8621251629726208e-05, + "loss": 0.4584, + "step": 2538 + }, + { + "epoch": 0.21, + "learning_rate": 1.8620708387657542e-05, + "loss": 0.6843, + "step": 2539 + }, + { + "epoch": 0.21, + "learning_rate": 1.8620165145588876e-05, + "loss": 0.5313, + "step": 2540 + }, + { + "epoch": 0.21, + "learning_rate": 1.861962190352021e-05, + "loss": 0.4826, + "step": 2541 + }, + { + "epoch": 0.21, + "learning_rate": 1.8619078661451545e-05, + "loss": 0.6027, + "step": 2542 + }, + { + "epoch": 0.21, + "learning_rate": 1.861853541938288e-05, + "loss": 0.5589, + "step": 2543 + }, + { + "epoch": 0.21, + "learning_rate": 1.8617992177314213e-05, + "loss": 0.4983, + "step": 2544 + }, + { + "epoch": 0.21, + "learning_rate": 1.8617448935245547e-05, + "loss": 0.6814, + "step": 2545 + }, + { + "epoch": 0.21, + "learning_rate": 1.861690569317688e-05, + "loss": 0.6231, + "step": 2546 + }, + { + "epoch": 0.21, + "learning_rate": 1.8616362451108216e-05, + "loss": 0.4195, + "step": 2547 + }, + { + "epoch": 0.21, + "learning_rate": 1.861581920903955e-05, + "loss": 0.4312, + "step": 2548 + }, + { + "epoch": 0.21, + "learning_rate": 1.8615275966970884e-05, + "loss": 0.439, + "step": 2549 + }, + { + "epoch": 0.21, + "learning_rate": 1.861473272490222e-05, + "loss": 0.6426, + "step": 2550 + }, + { + "epoch": 0.21, + "learning_rate": 1.8614189482833553e-05, + "loss": 0.3766, + "step": 2551 + }, + { + "epoch": 0.21, + "learning_rate": 1.8613646240764887e-05, + "loss": 0.4984, + "step": 2552 + }, + { + "epoch": 0.21, + "learning_rate": 1.861310299869622e-05, + "loss": 0.5401, + "step": 2553 + }, + { + "epoch": 0.21, + "learning_rate": 1.8612559756627555e-05, + "loss": 0.824, + "step": 2554 + }, + { + "epoch": 0.21, + "learning_rate": 1.861201651455889e-05, + "loss": 0.6693, + "step": 2555 + }, + { + "epoch": 0.21, + "learning_rate": 1.8611473272490224e-05, + "loss": 0.4513, + "step": 2556 + }, + { + "epoch": 0.21, + "learning_rate": 1.8610930030421558e-05, + "loss": 0.4091, + "step": 2557 + }, + { + "epoch": 0.21, + "learning_rate": 1.8610386788352892e-05, + "loss": 0.5025, + "step": 2558 + }, + { + "epoch": 0.21, + "learning_rate": 1.8609843546284226e-05, + "loss": 0.4653, + "step": 2559 + }, + { + "epoch": 0.21, + "learning_rate": 1.860930030421556e-05, + "loss": 0.4702, + "step": 2560 + }, + { + "epoch": 0.21, + "learning_rate": 1.8608757062146895e-05, + "loss": 0.8024, + "step": 2561 + }, + { + "epoch": 0.21, + "learning_rate": 1.860821382007823e-05, + "loss": 0.5796, + "step": 2562 + }, + { + "epoch": 0.21, + "learning_rate": 1.8607670578009563e-05, + "loss": 0.76, + "step": 2563 + }, + { + "epoch": 0.21, + "learning_rate": 1.8607127335940898e-05, + "loss": 0.5869, + "step": 2564 + }, + { + "epoch": 0.21, + "learning_rate": 1.8606584093872232e-05, + "loss": 0.6451, + "step": 2565 + }, + { + "epoch": 0.21, + "learning_rate": 1.8606040851803566e-05, + "loss": 0.5708, + "step": 2566 + }, + { + "epoch": 0.21, + "learning_rate": 1.86054976097349e-05, + "loss": 0.3982, + "step": 2567 + }, + { + "epoch": 0.21, + "learning_rate": 1.860495436766623e-05, + "loss": 0.5503, + "step": 2568 + }, + { + "epoch": 0.21, + "learning_rate": 1.860441112559757e-05, + "loss": 0.6941, + "step": 2569 + }, + { + "epoch": 0.21, + "learning_rate": 1.86038678835289e-05, + "loss": 0.7129, + "step": 2570 + }, + { + "epoch": 0.21, + "learning_rate": 1.8603324641460237e-05, + "loss": 0.5556, + "step": 2571 + }, + { + "epoch": 0.21, + "learning_rate": 1.8602781399391568e-05, + "loss": 0.6053, + "step": 2572 + }, + { + "epoch": 0.21, + "learning_rate": 1.8602238157322906e-05, + "loss": 0.3434, + "step": 2573 + }, + { + "epoch": 0.21, + "learning_rate": 1.8601694915254237e-05, + "loss": 0.4342, + "step": 2574 + }, + { + "epoch": 0.21, + "learning_rate": 1.8601151673185574e-05, + "loss": 0.7221, + "step": 2575 + }, + { + "epoch": 0.21, + "learning_rate": 1.8600608431116905e-05, + "loss": 0.4957, + "step": 2576 + }, + { + "epoch": 0.21, + "learning_rate": 1.8600065189048243e-05, + "loss": 0.5209, + "step": 2577 + }, + { + "epoch": 0.21, + "learning_rate": 1.8599521946979577e-05, + "loss": 0.6944, + "step": 2578 + }, + { + "epoch": 0.21, + "learning_rate": 1.859897870491091e-05, + "loss": 0.3484, + "step": 2579 + }, + { + "epoch": 0.21, + "learning_rate": 1.8598435462842245e-05, + "loss": 0.5764, + "step": 2580 + }, + { + "epoch": 0.21, + "learning_rate": 1.859789222077358e-05, + "loss": 0.4193, + "step": 2581 + }, + { + "epoch": 0.21, + "learning_rate": 1.8597348978704914e-05, + "loss": 0.4852, + "step": 2582 + }, + { + "epoch": 0.21, + "learning_rate": 1.8596805736636248e-05, + "loss": 0.5601, + "step": 2583 + }, + { + "epoch": 0.21, + "learning_rate": 1.8596262494567582e-05, + "loss": 0.5375, + "step": 2584 + }, + { + "epoch": 0.21, + "learning_rate": 1.8595719252498916e-05, + "loss": 0.4878, + "step": 2585 + }, + { + "epoch": 0.21, + "learning_rate": 1.859517601043025e-05, + "loss": 0.5291, + "step": 2586 + }, + { + "epoch": 0.21, + "learning_rate": 1.859463276836158e-05, + "loss": 0.5613, + "step": 2587 + }, + { + "epoch": 0.21, + "learning_rate": 1.859408952629292e-05, + "loss": 0.5367, + "step": 2588 + }, + { + "epoch": 0.21, + "learning_rate": 1.859354628422425e-05, + "loss": 0.5934, + "step": 2589 + }, + { + "epoch": 0.21, + "learning_rate": 1.8593003042155588e-05, + "loss": 0.5126, + "step": 2590 + }, + { + "epoch": 0.21, + "learning_rate": 1.859245980008692e-05, + "loss": 0.5269, + "step": 2591 + }, + { + "epoch": 0.21, + "learning_rate": 1.8591916558018256e-05, + "loss": 0.741, + "step": 2592 + }, + { + "epoch": 0.21, + "learning_rate": 1.8591373315949587e-05, + "loss": 0.2966, + "step": 2593 + }, + { + "epoch": 0.21, + "learning_rate": 1.8590830073880925e-05, + "loss": 0.4483, + "step": 2594 + }, + { + "epoch": 0.21, + "learning_rate": 1.8590286831812255e-05, + "loss": 0.7129, + "step": 2595 + }, + { + "epoch": 0.21, + "learning_rate": 1.8589743589743593e-05, + "loss": 0.4096, + "step": 2596 + }, + { + "epoch": 0.21, + "learning_rate": 1.8589200347674924e-05, + "loss": 0.358, + "step": 2597 + }, + { + "epoch": 0.21, + "learning_rate": 1.858865710560626e-05, + "loss": 0.4241, + "step": 2598 + }, + { + "epoch": 0.21, + "learning_rate": 1.8588113863537592e-05, + "loss": 0.4538, + "step": 2599 + }, + { + "epoch": 0.21, + "learning_rate": 1.858757062146893e-05, + "loss": 0.4302, + "step": 2600 + }, + { + "epoch": 0.21, + "learning_rate": 1.858702737940026e-05, + "loss": 0.35, + "step": 2601 + }, + { + "epoch": 0.21, + "learning_rate": 1.85864841373316e-05, + "loss": 0.4824, + "step": 2602 + }, + { + "epoch": 0.21, + "learning_rate": 1.858594089526293e-05, + "loss": 0.4591, + "step": 2603 + }, + { + "epoch": 0.21, + "learning_rate": 1.8585397653194267e-05, + "loss": 0.7112, + "step": 2604 + }, + { + "epoch": 0.21, + "learning_rate": 1.8584854411125598e-05, + "loss": 0.657, + "step": 2605 + }, + { + "epoch": 0.21, + "learning_rate": 1.8584311169056932e-05, + "loss": 0.5838, + "step": 2606 + }, + { + "epoch": 0.21, + "learning_rate": 1.8583767926988266e-05, + "loss": 0.7453, + "step": 2607 + }, + { + "epoch": 0.21, + "learning_rate": 1.85832246849196e-05, + "loss": 0.5157, + "step": 2608 + }, + { + "epoch": 0.21, + "learning_rate": 1.8582681442850935e-05, + "loss": 0.3446, + "step": 2609 + }, + { + "epoch": 0.21, + "learning_rate": 1.858213820078227e-05, + "loss": 0.4133, + "step": 2610 + }, + { + "epoch": 0.21, + "learning_rate": 1.8581594958713603e-05, + "loss": 0.6308, + "step": 2611 + }, + { + "epoch": 0.21, + "learning_rate": 1.8581051716644937e-05, + "loss": 0.4949, + "step": 2612 + }, + { + "epoch": 0.21, + "learning_rate": 1.858050847457627e-05, + "loss": 0.666, + "step": 2613 + }, + { + "epoch": 0.21, + "learning_rate": 1.8579965232507606e-05, + "loss": 0.6558, + "step": 2614 + }, + { + "epoch": 0.21, + "learning_rate": 1.8579421990438943e-05, + "loss": 0.7118, + "step": 2615 + }, + { + "epoch": 0.21, + "learning_rate": 1.8578878748370274e-05, + "loss": 0.5613, + "step": 2616 + }, + { + "epoch": 0.21, + "learning_rate": 1.8578335506301612e-05, + "loss": 0.6086, + "step": 2617 + }, + { + "epoch": 0.21, + "learning_rate": 1.8577792264232943e-05, + "loss": 0.691, + "step": 2618 + }, + { + "epoch": 0.21, + "learning_rate": 1.857724902216428e-05, + "loss": 0.3755, + "step": 2619 + }, + { + "epoch": 0.21, + "learning_rate": 1.857670578009561e-05, + "loss": 0.5441, + "step": 2620 + }, + { + "epoch": 0.21, + "learning_rate": 1.857616253802695e-05, + "loss": 0.4921, + "step": 2621 + }, + { + "epoch": 0.21, + "learning_rate": 1.857561929595828e-05, + "loss": 0.6744, + "step": 2622 + }, + { + "epoch": 0.21, + "learning_rate": 1.8575076053889617e-05, + "loss": 0.8282, + "step": 2623 + }, + { + "epoch": 0.21, + "learning_rate": 1.8574532811820948e-05, + "loss": 0.7067, + "step": 2624 + }, + { + "epoch": 0.21, + "learning_rate": 1.8573989569752282e-05, + "loss": 0.6183, + "step": 2625 + }, + { + "epoch": 0.21, + "learning_rate": 1.8573446327683617e-05, + "loss": 0.3985, + "step": 2626 + }, + { + "epoch": 0.21, + "learning_rate": 1.857290308561495e-05, + "loss": 0.4681, + "step": 2627 + }, + { + "epoch": 0.21, + "learning_rate": 1.8572359843546285e-05, + "loss": 0.491, + "step": 2628 + }, + { + "epoch": 0.21, + "learning_rate": 1.857181660147762e-05, + "loss": 0.698, + "step": 2629 + }, + { + "epoch": 0.21, + "learning_rate": 1.8571273359408953e-05, + "loss": 0.6399, + "step": 2630 + }, + { + "epoch": 0.21, + "learning_rate": 1.8570730117340288e-05, + "loss": 0.4648, + "step": 2631 + }, + { + "epoch": 0.21, + "learning_rate": 1.8570186875271622e-05, + "loss": 0.5924, + "step": 2632 + }, + { + "epoch": 0.21, + "learning_rate": 1.8569643633202956e-05, + "loss": 0.5593, + "step": 2633 + }, + { + "epoch": 0.21, + "learning_rate": 1.856910039113429e-05, + "loss": 0.7934, + "step": 2634 + }, + { + "epoch": 0.21, + "learning_rate": 1.8568557149065625e-05, + "loss": 0.4889, + "step": 2635 + }, + { + "epoch": 0.21, + "learning_rate": 1.856801390699696e-05, + "loss": 0.2574, + "step": 2636 + }, + { + "epoch": 0.21, + "learning_rate": 1.8567470664928293e-05, + "loss": 0.6459, + "step": 2637 + }, + { + "epoch": 0.21, + "learning_rate": 1.8566927422859627e-05, + "loss": 0.6193, + "step": 2638 + }, + { + "epoch": 0.22, + "learning_rate": 1.856638418079096e-05, + "loss": 0.5482, + "step": 2639 + }, + { + "epoch": 0.22, + "learning_rate": 1.8565840938722296e-05, + "loss": 0.5947, + "step": 2640 + }, + { + "epoch": 0.22, + "learning_rate": 1.856529769665363e-05, + "loss": 0.5719, + "step": 2641 + }, + { + "epoch": 0.22, + "learning_rate": 1.8564754454584964e-05, + "loss": 0.6458, + "step": 2642 + }, + { + "epoch": 0.22, + "learning_rate": 1.85642112125163e-05, + "loss": 0.7189, + "step": 2643 + }, + { + "epoch": 0.22, + "learning_rate": 1.8563667970447633e-05, + "loss": 0.9127, + "step": 2644 + }, + { + "epoch": 0.22, + "learning_rate": 1.8563124728378967e-05, + "loss": 0.6189, + "step": 2645 + }, + { + "epoch": 0.22, + "learning_rate": 1.85625814863103e-05, + "loss": 0.5645, + "step": 2646 + }, + { + "epoch": 0.22, + "learning_rate": 1.8562038244241635e-05, + "loss": 0.5949, + "step": 2647 + }, + { + "epoch": 0.22, + "learning_rate": 1.856149500217297e-05, + "loss": 0.4825, + "step": 2648 + }, + { + "epoch": 0.22, + "learning_rate": 1.8560951760104304e-05, + "loss": 0.5431, + "step": 2649 + }, + { + "epoch": 0.22, + "learning_rate": 1.8560408518035638e-05, + "loss": 0.5628, + "step": 2650 + }, + { + "epoch": 0.22, + "learning_rate": 1.8559865275966972e-05, + "loss": 0.497, + "step": 2651 + }, + { + "epoch": 0.22, + "learning_rate": 1.8559322033898307e-05, + "loss": 0.6118, + "step": 2652 + }, + { + "epoch": 0.22, + "learning_rate": 1.855877879182964e-05, + "loss": 0.3784, + "step": 2653 + }, + { + "epoch": 0.22, + "learning_rate": 1.8558235549760975e-05, + "loss": 0.3836, + "step": 2654 + }, + { + "epoch": 0.22, + "learning_rate": 1.855769230769231e-05, + "loss": 0.5043, + "step": 2655 + }, + { + "epoch": 0.22, + "learning_rate": 1.8557149065623643e-05, + "loss": 0.435, + "step": 2656 + }, + { + "epoch": 0.22, + "learning_rate": 1.8556605823554978e-05, + "loss": 0.3005, + "step": 2657 + }, + { + "epoch": 0.22, + "learning_rate": 1.8556062581486312e-05, + "loss": 0.6305, + "step": 2658 + }, + { + "epoch": 0.22, + "learning_rate": 1.8555519339417646e-05, + "loss": 0.5131, + "step": 2659 + }, + { + "epoch": 0.22, + "learning_rate": 1.855497609734898e-05, + "loss": 0.3271, + "step": 2660 + }, + { + "epoch": 0.22, + "learning_rate": 1.8554432855280315e-05, + "loss": 0.5938, + "step": 2661 + }, + { + "epoch": 0.22, + "learning_rate": 1.855388961321165e-05, + "loss": 0.3125, + "step": 2662 + }, + { + "epoch": 0.22, + "learning_rate": 1.8553346371142983e-05, + "loss": 0.6866, + "step": 2663 + }, + { + "epoch": 0.22, + "learning_rate": 1.8552803129074317e-05, + "loss": 0.5379, + "step": 2664 + }, + { + "epoch": 0.22, + "learning_rate": 1.855225988700565e-05, + "loss": 0.6097, + "step": 2665 + }, + { + "epoch": 0.22, + "learning_rate": 1.8551716644936986e-05, + "loss": 0.4967, + "step": 2666 + }, + { + "epoch": 0.22, + "learning_rate": 1.855117340286832e-05, + "loss": 0.6169, + "step": 2667 + }, + { + "epoch": 0.22, + "learning_rate": 1.8550630160799654e-05, + "loss": 0.5364, + "step": 2668 + }, + { + "epoch": 0.22, + "learning_rate": 1.855008691873099e-05, + "loss": 0.5852, + "step": 2669 + }, + { + "epoch": 0.22, + "learning_rate": 1.8549543676662323e-05, + "loss": 0.5123, + "step": 2670 + }, + { + "epoch": 0.22, + "learning_rate": 1.8549000434593657e-05, + "loss": 0.5589, + "step": 2671 + }, + { + "epoch": 0.22, + "learning_rate": 1.854845719252499e-05, + "loss": 0.5711, + "step": 2672 + }, + { + "epoch": 0.22, + "learning_rate": 1.8547913950456325e-05, + "loss": 0.7819, + "step": 2673 + }, + { + "epoch": 0.22, + "learning_rate": 1.854737070838766e-05, + "loss": 0.8252, + "step": 2674 + }, + { + "epoch": 0.22, + "learning_rate": 1.8546827466318994e-05, + "loss": 0.5153, + "step": 2675 + }, + { + "epoch": 0.22, + "learning_rate": 1.8546284224250328e-05, + "loss": 0.6041, + "step": 2676 + }, + { + "epoch": 0.22, + "learning_rate": 1.8545740982181662e-05, + "loss": 0.6026, + "step": 2677 + }, + { + "epoch": 0.22, + "learning_rate": 1.8545197740112996e-05, + "loss": 0.403, + "step": 2678 + }, + { + "epoch": 0.22, + "learning_rate": 1.854465449804433e-05, + "loss": 0.4575, + "step": 2679 + }, + { + "epoch": 0.22, + "learning_rate": 1.8544111255975665e-05, + "loss": 0.4073, + "step": 2680 + }, + { + "epoch": 0.22, + "learning_rate": 1.8543568013907e-05, + "loss": 0.6982, + "step": 2681 + }, + { + "epoch": 0.22, + "learning_rate": 1.854302477183833e-05, + "loss": 0.5827, + "step": 2682 + }, + { + "epoch": 0.22, + "learning_rate": 1.8542481529769668e-05, + "loss": 0.6838, + "step": 2683 + }, + { + "epoch": 0.22, + "learning_rate": 1.8541938287701e-05, + "loss": 0.7191, + "step": 2684 + }, + { + "epoch": 0.22, + "learning_rate": 1.8541395045632336e-05, + "loss": 0.7521, + "step": 2685 + }, + { + "epoch": 0.22, + "learning_rate": 1.854085180356367e-05, + "loss": 0.4235, + "step": 2686 + }, + { + "epoch": 0.22, + "learning_rate": 1.8540308561495005e-05, + "loss": 0.7443, + "step": 2687 + }, + { + "epoch": 0.22, + "learning_rate": 1.853976531942634e-05, + "loss": 0.4656, + "step": 2688 + }, + { + "epoch": 0.22, + "learning_rate": 1.8539222077357673e-05, + "loss": 0.564, + "step": 2689 + }, + { + "epoch": 0.22, + "learning_rate": 1.8538678835289007e-05, + "loss": 0.5927, + "step": 2690 + }, + { + "epoch": 0.22, + "learning_rate": 1.853813559322034e-05, + "loss": 0.3383, + "step": 2691 + }, + { + "epoch": 0.22, + "learning_rate": 1.8537592351151676e-05, + "loss": 0.6656, + "step": 2692 + }, + { + "epoch": 0.22, + "learning_rate": 1.853704910908301e-05, + "loss": 0.7665, + "step": 2693 + }, + { + "epoch": 0.22, + "learning_rate": 1.8536505867014344e-05, + "loss": 0.8959, + "step": 2694 + }, + { + "epoch": 0.22, + "learning_rate": 1.853596262494568e-05, + "loss": 0.5503, + "step": 2695 + }, + { + "epoch": 0.22, + "learning_rate": 1.8535419382877013e-05, + "loss": 0.7989, + "step": 2696 + }, + { + "epoch": 0.22, + "learning_rate": 1.8534876140808347e-05, + "loss": 0.7353, + "step": 2697 + }, + { + "epoch": 0.22, + "learning_rate": 1.853433289873968e-05, + "loss": 0.8128, + "step": 2698 + }, + { + "epoch": 0.22, + "learning_rate": 1.8533789656671015e-05, + "loss": 0.3568, + "step": 2699 + }, + { + "epoch": 0.22, + "learning_rate": 1.853324641460235e-05, + "loss": 0.6693, + "step": 2700 + }, + { + "epoch": 0.22, + "learning_rate": 1.853270317253368e-05, + "loss": 0.4275, + "step": 2701 + }, + { + "epoch": 0.22, + "learning_rate": 1.8532159930465018e-05, + "loss": 0.6053, + "step": 2702 + }, + { + "epoch": 0.22, + "learning_rate": 1.853161668839635e-05, + "loss": 0.4184, + "step": 2703 + }, + { + "epoch": 0.22, + "learning_rate": 1.8531073446327686e-05, + "loss": 0.3233, + "step": 2704 + }, + { + "epoch": 0.22, + "learning_rate": 1.8530530204259017e-05, + "loss": 0.4065, + "step": 2705 + }, + { + "epoch": 0.22, + "learning_rate": 1.8529986962190355e-05, + "loss": 0.4042, + "step": 2706 + }, + { + "epoch": 0.22, + "learning_rate": 1.8529443720121686e-05, + "loss": 0.7593, + "step": 2707 + }, + { + "epoch": 0.22, + "learning_rate": 1.8528900478053023e-05, + "loss": 0.5352, + "step": 2708 + }, + { + "epoch": 0.22, + "learning_rate": 1.8528357235984354e-05, + "loss": 0.5539, + "step": 2709 + }, + { + "epoch": 0.22, + "learning_rate": 1.8527813993915692e-05, + "loss": 0.4458, + "step": 2710 + }, + { + "epoch": 0.22, + "learning_rate": 1.8527270751847023e-05, + "loss": 0.7111, + "step": 2711 + }, + { + "epoch": 0.22, + "learning_rate": 1.852672750977836e-05, + "loss": 0.5096, + "step": 2712 + }, + { + "epoch": 0.22, + "learning_rate": 1.852618426770969e-05, + "loss": 0.5674, + "step": 2713 + }, + { + "epoch": 0.22, + "learning_rate": 1.852564102564103e-05, + "loss": 0.6187, + "step": 2714 + }, + { + "epoch": 0.22, + "learning_rate": 1.852509778357236e-05, + "loss": 0.6378, + "step": 2715 + }, + { + "epoch": 0.22, + "learning_rate": 1.8524554541503697e-05, + "loss": 0.5146, + "step": 2716 + }, + { + "epoch": 0.22, + "learning_rate": 1.8524011299435028e-05, + "loss": 0.7474, + "step": 2717 + }, + { + "epoch": 0.22, + "learning_rate": 1.8523468057366366e-05, + "loss": 0.5878, + "step": 2718 + }, + { + "epoch": 0.22, + "learning_rate": 1.8522924815297697e-05, + "loss": 0.6672, + "step": 2719 + }, + { + "epoch": 0.22, + "learning_rate": 1.852238157322903e-05, + "loss": 0.5851, + "step": 2720 + }, + { + "epoch": 0.22, + "learning_rate": 1.8521838331160365e-05, + "loss": 0.6479, + "step": 2721 + }, + { + "epoch": 0.22, + "learning_rate": 1.85212950890917e-05, + "loss": 0.6241, + "step": 2722 + }, + { + "epoch": 0.22, + "learning_rate": 1.8520751847023037e-05, + "loss": 0.5328, + "step": 2723 + }, + { + "epoch": 0.22, + "learning_rate": 1.8520208604954368e-05, + "loss": 0.6296, + "step": 2724 + }, + { + "epoch": 0.22, + "learning_rate": 1.8519665362885705e-05, + "loss": 0.5513, + "step": 2725 + }, + { + "epoch": 0.22, + "learning_rate": 1.8519122120817036e-05, + "loss": 0.6385, + "step": 2726 + }, + { + "epoch": 0.22, + "learning_rate": 1.8518578878748374e-05, + "loss": 0.5052, + "step": 2727 + }, + { + "epoch": 0.22, + "learning_rate": 1.8518035636679705e-05, + "loss": 0.4778, + "step": 2728 + }, + { + "epoch": 0.22, + "learning_rate": 1.8517492394611042e-05, + "loss": 0.7221, + "step": 2729 + }, + { + "epoch": 0.22, + "learning_rate": 1.8516949152542373e-05, + "loss": 0.5742, + "step": 2730 + }, + { + "epoch": 0.22, + "learning_rate": 1.851640591047371e-05, + "loss": 0.6226, + "step": 2731 + }, + { + "epoch": 0.22, + "learning_rate": 1.851586266840504e-05, + "loss": 0.5873, + "step": 2732 + }, + { + "epoch": 0.22, + "learning_rate": 1.851531942633638e-05, + "loss": 0.6694, + "step": 2733 + }, + { + "epoch": 0.22, + "learning_rate": 1.851477618426771e-05, + "loss": 0.5048, + "step": 2734 + }, + { + "epoch": 0.22, + "learning_rate": 1.8514232942199048e-05, + "loss": 0.5558, + "step": 2735 + }, + { + "epoch": 0.22, + "learning_rate": 1.851368970013038e-05, + "loss": 0.5596, + "step": 2736 + }, + { + "epoch": 0.22, + "learning_rate": 1.8513146458061716e-05, + "loss": 0.4873, + "step": 2737 + }, + { + "epoch": 0.22, + "learning_rate": 1.8512603215993047e-05, + "loss": 0.5697, + "step": 2738 + }, + { + "epoch": 0.22, + "learning_rate": 1.851205997392438e-05, + "loss": 0.5544, + "step": 2739 + }, + { + "epoch": 0.22, + "learning_rate": 1.8511516731855715e-05, + "loss": 0.512, + "step": 2740 + }, + { + "epoch": 0.22, + "learning_rate": 1.851097348978705e-05, + "loss": 0.6576, + "step": 2741 + }, + { + "epoch": 0.22, + "learning_rate": 1.8510430247718384e-05, + "loss": 0.4118, + "step": 2742 + }, + { + "epoch": 0.22, + "learning_rate": 1.8509887005649718e-05, + "loss": 0.4977, + "step": 2743 + }, + { + "epoch": 0.22, + "learning_rate": 1.8509343763581052e-05, + "loss": 0.3664, + "step": 2744 + }, + { + "epoch": 0.22, + "learning_rate": 1.8508800521512387e-05, + "loss": 0.4746, + "step": 2745 + }, + { + "epoch": 0.22, + "learning_rate": 1.850825727944372e-05, + "loss": 0.6882, + "step": 2746 + }, + { + "epoch": 0.22, + "learning_rate": 1.8507714037375055e-05, + "loss": 0.7637, + "step": 2747 + }, + { + "epoch": 0.22, + "learning_rate": 1.850717079530639e-05, + "loss": 0.2554, + "step": 2748 + }, + { + "epoch": 0.22, + "learning_rate": 1.8506627553237723e-05, + "loss": 0.442, + "step": 2749 + }, + { + "epoch": 0.22, + "learning_rate": 1.8506084311169058e-05, + "loss": 0.6308, + "step": 2750 + }, + { + "epoch": 0.22, + "eval_accuracy": 0.8015282730514519, + "eval_loss": 0.5033699870109558, + "eval_runtime": 22.3078, + "eval_samples_per_second": 439.981, + "eval_steps_per_second": 3.452, + "step": 2750 + }, + { + "epoch": 0.22, + "learning_rate": 1.8505541069100392e-05, + "loss": 0.4437, + "step": 2751 + }, + { + "epoch": 0.22, + "learning_rate": 1.8504997827031726e-05, + "loss": 0.411, + "step": 2752 + }, + { + "epoch": 0.22, + "learning_rate": 1.850445458496306e-05, + "loss": 0.5273, + "step": 2753 + }, + { + "epoch": 0.22, + "learning_rate": 1.8503911342894395e-05, + "loss": 0.5955, + "step": 2754 + }, + { + "epoch": 0.22, + "learning_rate": 1.850336810082573e-05, + "loss": 0.4021, + "step": 2755 + }, + { + "epoch": 0.22, + "learning_rate": 1.8502824858757063e-05, + "loss": 0.3259, + "step": 2756 + }, + { + "epoch": 0.22, + "learning_rate": 1.8502281616688397e-05, + "loss": 0.5407, + "step": 2757 + }, + { + "epoch": 0.22, + "learning_rate": 1.850173837461973e-05, + "loss": 0.3464, + "step": 2758 + }, + { + "epoch": 0.22, + "learning_rate": 1.8501195132551066e-05, + "loss": 0.6189, + "step": 2759 + }, + { + "epoch": 0.22, + "learning_rate": 1.85006518904824e-05, + "loss": 0.5067, + "step": 2760 + }, + { + "epoch": 0.22, + "learning_rate": 1.8500108648413734e-05, + "loss": 0.4683, + "step": 2761 + }, + { + "epoch": 0.23, + "learning_rate": 1.849956540634507e-05, + "loss": 0.5746, + "step": 2762 + }, + { + "epoch": 0.23, + "learning_rate": 1.8499022164276403e-05, + "loss": 0.6887, + "step": 2763 + }, + { + "epoch": 0.23, + "learning_rate": 1.8498478922207737e-05, + "loss": 0.6098, + "step": 2764 + }, + { + "epoch": 0.23, + "learning_rate": 1.849793568013907e-05, + "loss": 0.3348, + "step": 2765 + }, + { + "epoch": 0.23, + "learning_rate": 1.8497392438070405e-05, + "loss": 0.6231, + "step": 2766 + }, + { + "epoch": 0.23, + "learning_rate": 1.849684919600174e-05, + "loss": 0.4934, + "step": 2767 + }, + { + "epoch": 0.23, + "learning_rate": 1.8496305953933074e-05, + "loss": 0.5527, + "step": 2768 + }, + { + "epoch": 0.23, + "learning_rate": 1.8495762711864408e-05, + "loss": 0.5738, + "step": 2769 + }, + { + "epoch": 0.23, + "learning_rate": 1.8495219469795742e-05, + "loss": 0.6982, + "step": 2770 + }, + { + "epoch": 0.23, + "learning_rate": 1.8494676227727077e-05, + "loss": 0.6537, + "step": 2771 + }, + { + "epoch": 0.23, + "learning_rate": 1.849413298565841e-05, + "loss": 0.6592, + "step": 2772 + }, + { + "epoch": 0.23, + "learning_rate": 1.8493589743589745e-05, + "loss": 0.2314, + "step": 2773 + }, + { + "epoch": 0.23, + "learning_rate": 1.849304650152108e-05, + "loss": 0.7627, + "step": 2774 + }, + { + "epoch": 0.23, + "learning_rate": 1.8492503259452413e-05, + "loss": 0.2403, + "step": 2775 + }, + { + "epoch": 0.23, + "learning_rate": 1.8491960017383748e-05, + "loss": 0.621, + "step": 2776 + }, + { + "epoch": 0.23, + "learning_rate": 1.8491416775315082e-05, + "loss": 0.5648, + "step": 2777 + }, + { + "epoch": 0.23, + "learning_rate": 1.8490873533246416e-05, + "loss": 0.5014, + "step": 2778 + }, + { + "epoch": 0.23, + "learning_rate": 1.849033029117775e-05, + "loss": 0.4126, + "step": 2779 + }, + { + "epoch": 0.23, + "learning_rate": 1.8489787049109085e-05, + "loss": 0.5066, + "step": 2780 + }, + { + "epoch": 0.23, + "learning_rate": 1.848924380704042e-05, + "loss": 0.4414, + "step": 2781 + }, + { + "epoch": 0.23, + "learning_rate": 1.8488700564971753e-05, + "loss": 0.4594, + "step": 2782 + }, + { + "epoch": 0.23, + "learning_rate": 1.8488157322903087e-05, + "loss": 0.5304, + "step": 2783 + }, + { + "epoch": 0.23, + "learning_rate": 1.848761408083442e-05, + "loss": 0.5339, + "step": 2784 + }, + { + "epoch": 0.23, + "learning_rate": 1.8487070838765756e-05, + "loss": 0.7031, + "step": 2785 + }, + { + "epoch": 0.23, + "learning_rate": 1.848652759669709e-05, + "loss": 0.5186, + "step": 2786 + }, + { + "epoch": 0.23, + "learning_rate": 1.8485984354628424e-05, + "loss": 0.5693, + "step": 2787 + }, + { + "epoch": 0.23, + "learning_rate": 1.848544111255976e-05, + "loss": 0.766, + "step": 2788 + }, + { + "epoch": 0.23, + "learning_rate": 1.8484897870491093e-05, + "loss": 0.418, + "step": 2789 + }, + { + "epoch": 0.23, + "learning_rate": 1.8484354628422427e-05, + "loss": 0.3898, + "step": 2790 + }, + { + "epoch": 0.23, + "learning_rate": 1.848381138635376e-05, + "loss": 0.699, + "step": 2791 + }, + { + "epoch": 0.23, + "learning_rate": 1.8483268144285095e-05, + "loss": 0.4719, + "step": 2792 + }, + { + "epoch": 0.23, + "learning_rate": 1.848272490221643e-05, + "loss": 0.44, + "step": 2793 + }, + { + "epoch": 0.23, + "learning_rate": 1.8482181660147764e-05, + "loss": 0.6032, + "step": 2794 + }, + { + "epoch": 0.23, + "learning_rate": 1.8481638418079098e-05, + "loss": 0.7474, + "step": 2795 + }, + { + "epoch": 0.23, + "learning_rate": 1.8481095176010432e-05, + "loss": 0.6287, + "step": 2796 + }, + { + "epoch": 0.23, + "learning_rate": 1.8480551933941767e-05, + "loss": 0.7634, + "step": 2797 + }, + { + "epoch": 0.23, + "learning_rate": 1.84800086918731e-05, + "loss": 0.5942, + "step": 2798 + }, + { + "epoch": 0.23, + "learning_rate": 1.8479465449804435e-05, + "loss": 0.3778, + "step": 2799 + }, + { + "epoch": 0.23, + "learning_rate": 1.847892220773577e-05, + "loss": 0.5211, + "step": 2800 + }, + { + "epoch": 0.23, + "learning_rate": 1.8478378965667103e-05, + "loss": 0.5381, + "step": 2801 + }, + { + "epoch": 0.23, + "learning_rate": 1.8477835723598438e-05, + "loss": 0.6708, + "step": 2802 + }, + { + "epoch": 0.23, + "learning_rate": 1.8477292481529772e-05, + "loss": 0.6454, + "step": 2803 + }, + { + "epoch": 0.23, + "learning_rate": 1.8476749239461106e-05, + "loss": 0.4782, + "step": 2804 + }, + { + "epoch": 0.23, + "learning_rate": 1.847620599739244e-05, + "loss": 0.4424, + "step": 2805 + }, + { + "epoch": 0.23, + "learning_rate": 1.8475662755323775e-05, + "loss": 0.5087, + "step": 2806 + }, + { + "epoch": 0.23, + "learning_rate": 1.847511951325511e-05, + "loss": 0.4703, + "step": 2807 + }, + { + "epoch": 0.23, + "learning_rate": 1.8474576271186443e-05, + "loss": 0.5759, + "step": 2808 + }, + { + "epoch": 0.23, + "learning_rate": 1.8474033029117777e-05, + "loss": 0.452, + "step": 2809 + }, + { + "epoch": 0.23, + "learning_rate": 1.847348978704911e-05, + "loss": 0.5592, + "step": 2810 + }, + { + "epoch": 0.23, + "learning_rate": 1.8472946544980446e-05, + "loss": 0.5507, + "step": 2811 + }, + { + "epoch": 0.23, + "learning_rate": 1.847240330291178e-05, + "loss": 0.5542, + "step": 2812 + }, + { + "epoch": 0.23, + "learning_rate": 1.8471860060843114e-05, + "loss": 0.5621, + "step": 2813 + }, + { + "epoch": 0.23, + "learning_rate": 1.847131681877445e-05, + "loss": 0.4689, + "step": 2814 + }, + { + "epoch": 0.23, + "learning_rate": 1.847077357670578e-05, + "loss": 0.6164, + "step": 2815 + }, + { + "epoch": 0.23, + "learning_rate": 1.8470230334637117e-05, + "loss": 0.7467, + "step": 2816 + }, + { + "epoch": 0.23, + "learning_rate": 1.8469687092568448e-05, + "loss": 0.4677, + "step": 2817 + }, + { + "epoch": 0.23, + "learning_rate": 1.8469143850499785e-05, + "loss": 0.4924, + "step": 2818 + }, + { + "epoch": 0.23, + "learning_rate": 1.8468600608431116e-05, + "loss": 0.3336, + "step": 2819 + }, + { + "epoch": 0.23, + "learning_rate": 1.8468057366362454e-05, + "loss": 0.4354, + "step": 2820 + }, + { + "epoch": 0.23, + "learning_rate": 1.8467514124293785e-05, + "loss": 0.3448, + "step": 2821 + }, + { + "epoch": 0.23, + "learning_rate": 1.8466970882225122e-05, + "loss": 0.6445, + "step": 2822 + }, + { + "epoch": 0.23, + "learning_rate": 1.8466427640156453e-05, + "loss": 0.6246, + "step": 2823 + }, + { + "epoch": 0.23, + "learning_rate": 1.846588439808779e-05, + "loss": 0.504, + "step": 2824 + }, + { + "epoch": 0.23, + "learning_rate": 1.846534115601912e-05, + "loss": 0.6716, + "step": 2825 + }, + { + "epoch": 0.23, + "learning_rate": 1.846479791395046e-05, + "loss": 0.4119, + "step": 2826 + }, + { + "epoch": 0.23, + "learning_rate": 1.846425467188179e-05, + "loss": 0.4966, + "step": 2827 + }, + { + "epoch": 0.23, + "learning_rate": 1.8463711429813128e-05, + "loss": 0.7266, + "step": 2828 + }, + { + "epoch": 0.23, + "learning_rate": 1.846316818774446e-05, + "loss": 0.7997, + "step": 2829 + }, + { + "epoch": 0.23, + "learning_rate": 1.8462624945675796e-05, + "loss": 0.4633, + "step": 2830 + }, + { + "epoch": 0.23, + "learning_rate": 1.846208170360713e-05, + "loss": 0.5722, + "step": 2831 + }, + { + "epoch": 0.23, + "learning_rate": 1.8461538461538465e-05, + "loss": 0.3425, + "step": 2832 + }, + { + "epoch": 0.23, + "learning_rate": 1.84609952194698e-05, + "loss": 0.4977, + "step": 2833 + }, + { + "epoch": 0.23, + "learning_rate": 1.846045197740113e-05, + "loss": 0.5634, + "step": 2834 + }, + { + "epoch": 0.23, + "learning_rate": 1.8459908735332467e-05, + "loss": 0.6086, + "step": 2835 + }, + { + "epoch": 0.23, + "learning_rate": 1.8459365493263798e-05, + "loss": 0.6108, + "step": 2836 + }, + { + "epoch": 0.23, + "learning_rate": 1.8458822251195136e-05, + "loss": 0.6164, + "step": 2837 + }, + { + "epoch": 0.23, + "learning_rate": 1.8458279009126467e-05, + "loss": 0.4844, + "step": 2838 + }, + { + "epoch": 0.23, + "learning_rate": 1.8457735767057804e-05, + "loss": 0.7749, + "step": 2839 + }, + { + "epoch": 0.23, + "learning_rate": 1.8457192524989135e-05, + "loss": 0.5347, + "step": 2840 + }, + { + "epoch": 0.23, + "learning_rate": 1.8456649282920473e-05, + "loss": 0.5011, + "step": 2841 + }, + { + "epoch": 0.23, + "learning_rate": 1.8456106040851804e-05, + "loss": 0.3653, + "step": 2842 + }, + { + "epoch": 0.23, + "learning_rate": 1.845556279878314e-05, + "loss": 0.4427, + "step": 2843 + }, + { + "epoch": 0.23, + "learning_rate": 1.8455019556714472e-05, + "loss": 0.5379, + "step": 2844 + }, + { + "epoch": 0.23, + "learning_rate": 1.845447631464581e-05, + "loss": 0.6661, + "step": 2845 + }, + { + "epoch": 0.23, + "learning_rate": 1.845393307257714e-05, + "loss": 0.4414, + "step": 2846 + }, + { + "epoch": 0.23, + "learning_rate": 1.8453389830508478e-05, + "loss": 0.5243, + "step": 2847 + }, + { + "epoch": 0.23, + "learning_rate": 1.845284658843981e-05, + "loss": 0.4894, + "step": 2848 + }, + { + "epoch": 0.23, + "learning_rate": 1.8452303346371147e-05, + "loss": 0.3868, + "step": 2849 + }, + { + "epoch": 0.23, + "learning_rate": 1.8451760104302477e-05, + "loss": 0.6724, + "step": 2850 + }, + { + "epoch": 0.23, + "learning_rate": 1.8451216862233815e-05, + "loss": 0.561, + "step": 2851 + }, + { + "epoch": 0.23, + "learning_rate": 1.8450673620165146e-05, + "loss": 0.5467, + "step": 2852 + }, + { + "epoch": 0.23, + "learning_rate": 1.845013037809648e-05, + "loss": 0.5232, + "step": 2853 + }, + { + "epoch": 0.23, + "learning_rate": 1.8449587136027814e-05, + "loss": 0.8068, + "step": 2854 + }, + { + "epoch": 0.23, + "learning_rate": 1.844904389395915e-05, + "loss": 0.3208, + "step": 2855 + }, + { + "epoch": 0.23, + "learning_rate": 1.8448500651890483e-05, + "loss": 0.7372, + "step": 2856 + }, + { + "epoch": 0.23, + "learning_rate": 1.8447957409821817e-05, + "loss": 0.6704, + "step": 2857 + }, + { + "epoch": 0.23, + "learning_rate": 1.844741416775315e-05, + "loss": 0.6237, + "step": 2858 + }, + { + "epoch": 0.23, + "learning_rate": 1.8446870925684485e-05, + "loss": 0.5614, + "step": 2859 + }, + { + "epoch": 0.23, + "learning_rate": 1.844632768361582e-05, + "loss": 0.2386, + "step": 2860 + }, + { + "epoch": 0.23, + "learning_rate": 1.8445784441547154e-05, + "loss": 0.733, + "step": 2861 + }, + { + "epoch": 0.23, + "learning_rate": 1.8445241199478488e-05, + "loss": 0.3797, + "step": 2862 + }, + { + "epoch": 0.23, + "learning_rate": 1.8444697957409822e-05, + "loss": 0.6867, + "step": 2863 + }, + { + "epoch": 0.23, + "learning_rate": 1.8444154715341157e-05, + "loss": 0.5644, + "step": 2864 + }, + { + "epoch": 0.23, + "learning_rate": 1.844361147327249e-05, + "loss": 0.7686, + "step": 2865 + }, + { + "epoch": 0.23, + "learning_rate": 1.8443068231203825e-05, + "loss": 0.4128, + "step": 2866 + }, + { + "epoch": 0.23, + "learning_rate": 1.844252498913516e-05, + "loss": 0.4123, + "step": 2867 + }, + { + "epoch": 0.23, + "learning_rate": 1.8441981747066497e-05, + "loss": 0.8312, + "step": 2868 + }, + { + "epoch": 0.23, + "learning_rate": 1.8441438504997828e-05, + "loss": 0.3716, + "step": 2869 + }, + { + "epoch": 0.23, + "learning_rate": 1.8440895262929165e-05, + "loss": 0.3622, + "step": 2870 + }, + { + "epoch": 0.23, + "learning_rate": 1.8440352020860496e-05, + "loss": 0.4245, + "step": 2871 + }, + { + "epoch": 0.23, + "learning_rate": 1.843980877879183e-05, + "loss": 0.4147, + "step": 2872 + }, + { + "epoch": 0.23, + "learning_rate": 1.8439265536723165e-05, + "loss": 0.4692, + "step": 2873 + }, + { + "epoch": 0.23, + "learning_rate": 1.84387222946545e-05, + "loss": 0.5599, + "step": 2874 + }, + { + "epoch": 0.23, + "learning_rate": 1.8438179052585833e-05, + "loss": 0.7731, + "step": 2875 + }, + { + "epoch": 0.23, + "learning_rate": 1.8437635810517167e-05, + "loss": 0.3973, + "step": 2876 + }, + { + "epoch": 0.23, + "learning_rate": 1.84370925684485e-05, + "loss": 0.7379, + "step": 2877 + }, + { + "epoch": 0.23, + "learning_rate": 1.8436549326379836e-05, + "loss": 0.3383, + "step": 2878 + }, + { + "epoch": 0.23, + "learning_rate": 1.843600608431117e-05, + "loss": 0.5926, + "step": 2879 + }, + { + "epoch": 0.23, + "learning_rate": 1.8435462842242504e-05, + "loss": 0.3769, + "step": 2880 + }, + { + "epoch": 0.23, + "learning_rate": 1.843491960017384e-05, + "loss": 0.4313, + "step": 2881 + }, + { + "epoch": 0.23, + "learning_rate": 1.8434376358105173e-05, + "loss": 0.679, + "step": 2882 + }, + { + "epoch": 0.23, + "learning_rate": 1.8433833116036507e-05, + "loss": 0.5383, + "step": 2883 + }, + { + "epoch": 0.24, + "learning_rate": 1.843328987396784e-05, + "loss": 0.6544, + "step": 2884 + }, + { + "epoch": 0.24, + "learning_rate": 1.8432746631899175e-05, + "loss": 0.3725, + "step": 2885 + }, + { + "epoch": 0.24, + "learning_rate": 1.843220338983051e-05, + "loss": 0.7897, + "step": 2886 + }, + { + "epoch": 0.24, + "learning_rate": 1.8431660147761844e-05, + "loss": 0.3594, + "step": 2887 + }, + { + "epoch": 0.24, + "learning_rate": 1.8431116905693178e-05, + "loss": 0.522, + "step": 2888 + }, + { + "epoch": 0.24, + "learning_rate": 1.8430573663624512e-05, + "loss": 0.7733, + "step": 2889 + }, + { + "epoch": 0.24, + "learning_rate": 1.8430030421555847e-05, + "loss": 0.5067, + "step": 2890 + }, + { + "epoch": 0.24, + "learning_rate": 1.842948717948718e-05, + "loss": 0.3532, + "step": 2891 + }, + { + "epoch": 0.24, + "learning_rate": 1.8428943937418515e-05, + "loss": 0.8176, + "step": 2892 + }, + { + "epoch": 0.24, + "learning_rate": 1.842840069534985e-05, + "loss": 0.8642, + "step": 2893 + }, + { + "epoch": 0.24, + "learning_rate": 1.8427857453281184e-05, + "loss": 0.4436, + "step": 2894 + }, + { + "epoch": 0.24, + "learning_rate": 1.8427314211212518e-05, + "loss": 0.376, + "step": 2895 + }, + { + "epoch": 0.24, + "learning_rate": 1.8426770969143852e-05, + "loss": 0.424, + "step": 2896 + }, + { + "epoch": 0.24, + "learning_rate": 1.8426227727075186e-05, + "loss": 0.5988, + "step": 2897 + }, + { + "epoch": 0.24, + "learning_rate": 1.842568448500652e-05, + "loss": 0.5569, + "step": 2898 + }, + { + "epoch": 0.24, + "learning_rate": 1.8425141242937855e-05, + "loss": 0.5504, + "step": 2899 + }, + { + "epoch": 0.24, + "learning_rate": 1.842459800086919e-05, + "loss": 0.3595, + "step": 2900 + }, + { + "epoch": 0.24, + "learning_rate": 1.8424054758800523e-05, + "loss": 0.3919, + "step": 2901 + }, + { + "epoch": 0.24, + "learning_rate": 1.8423511516731857e-05, + "loss": 0.7216, + "step": 2902 + }, + { + "epoch": 0.24, + "learning_rate": 1.842296827466319e-05, + "loss": 0.6977, + "step": 2903 + }, + { + "epoch": 0.24, + "learning_rate": 1.8422425032594526e-05, + "loss": 0.4398, + "step": 2904 + }, + { + "epoch": 0.24, + "learning_rate": 1.842188179052586e-05, + "loss": 0.4199, + "step": 2905 + }, + { + "epoch": 0.24, + "learning_rate": 1.8421338548457194e-05, + "loss": 0.4949, + "step": 2906 + }, + { + "epoch": 0.24, + "learning_rate": 1.842079530638853e-05, + "loss": 0.6063, + "step": 2907 + }, + { + "epoch": 0.24, + "learning_rate": 1.8420252064319863e-05, + "loss": 0.4589, + "step": 2908 + }, + { + "epoch": 0.24, + "learning_rate": 1.8419708822251197e-05, + "loss": 0.6269, + "step": 2909 + }, + { + "epoch": 0.24, + "learning_rate": 1.841916558018253e-05, + "loss": 0.4793, + "step": 2910 + }, + { + "epoch": 0.24, + "learning_rate": 1.8418622338113865e-05, + "loss": 0.3347, + "step": 2911 + }, + { + "epoch": 0.24, + "learning_rate": 1.84180790960452e-05, + "loss": 0.715, + "step": 2912 + }, + { + "epoch": 0.24, + "learning_rate": 1.8417535853976534e-05, + "loss": 0.4742, + "step": 2913 + }, + { + "epoch": 0.24, + "learning_rate": 1.8416992611907868e-05, + "loss": 0.698, + "step": 2914 + }, + { + "epoch": 0.24, + "learning_rate": 1.8416449369839202e-05, + "loss": 0.5117, + "step": 2915 + }, + { + "epoch": 0.24, + "learning_rate": 1.8415906127770537e-05, + "loss": 0.5516, + "step": 2916 + }, + { + "epoch": 0.24, + "learning_rate": 1.841536288570187e-05, + "loss": 0.6503, + "step": 2917 + }, + { + "epoch": 0.24, + "learning_rate": 1.8414819643633205e-05, + "loss": 0.7091, + "step": 2918 + }, + { + "epoch": 0.24, + "learning_rate": 1.841427640156454e-05, + "loss": 0.5125, + "step": 2919 + }, + { + "epoch": 0.24, + "learning_rate": 1.8413733159495874e-05, + "loss": 0.7712, + "step": 2920 + }, + { + "epoch": 0.24, + "learning_rate": 1.8413189917427208e-05, + "loss": 0.5709, + "step": 2921 + }, + { + "epoch": 0.24, + "learning_rate": 1.8412646675358542e-05, + "loss": 0.5272, + "step": 2922 + }, + { + "epoch": 0.24, + "learning_rate": 1.8412103433289876e-05, + "loss": 0.6346, + "step": 2923 + }, + { + "epoch": 0.24, + "learning_rate": 1.841156019122121e-05, + "loss": 0.5062, + "step": 2924 + }, + { + "epoch": 0.24, + "learning_rate": 1.8411016949152545e-05, + "loss": 0.7661, + "step": 2925 + }, + { + "epoch": 0.24, + "learning_rate": 1.841047370708388e-05, + "loss": 0.6009, + "step": 2926 + }, + { + "epoch": 0.24, + "learning_rate": 1.8409930465015213e-05, + "loss": 0.4755, + "step": 2927 + }, + { + "epoch": 0.24, + "learning_rate": 1.8409387222946547e-05, + "loss": 0.5383, + "step": 2928 + }, + { + "epoch": 0.24, + "learning_rate": 1.8408843980877878e-05, + "loss": 0.4982, + "step": 2929 + }, + { + "epoch": 0.24, + "learning_rate": 1.8408300738809216e-05, + "loss": 0.6218, + "step": 2930 + }, + { + "epoch": 0.24, + "learning_rate": 1.8407757496740547e-05, + "loss": 0.6277, + "step": 2931 + }, + { + "epoch": 0.24, + "learning_rate": 1.8407214254671884e-05, + "loss": 0.5148, + "step": 2932 + }, + { + "epoch": 0.24, + "learning_rate": 1.8406671012603215e-05, + "loss": 0.6599, + "step": 2933 + }, + { + "epoch": 0.24, + "learning_rate": 1.8406127770534553e-05, + "loss": 0.532, + "step": 2934 + }, + { + "epoch": 0.24, + "learning_rate": 1.8405584528465884e-05, + "loss": 0.4403, + "step": 2935 + }, + { + "epoch": 0.24, + "learning_rate": 1.840504128639722e-05, + "loss": 0.9603, + "step": 2936 + }, + { + "epoch": 0.24, + "learning_rate": 1.8404498044328552e-05, + "loss": 0.4903, + "step": 2937 + }, + { + "epoch": 0.24, + "learning_rate": 1.840395480225989e-05, + "loss": 0.5922, + "step": 2938 + }, + { + "epoch": 0.24, + "learning_rate": 1.8403411560191224e-05, + "loss": 0.9107, + "step": 2939 + }, + { + "epoch": 0.24, + "learning_rate": 1.8402868318122558e-05, + "loss": 0.4442, + "step": 2940 + }, + { + "epoch": 0.24, + "learning_rate": 1.8402325076053892e-05, + "loss": 0.4089, + "step": 2941 + }, + { + "epoch": 0.24, + "learning_rate": 1.8401781833985227e-05, + "loss": 0.3418, + "step": 2942 + }, + { + "epoch": 0.24, + "learning_rate": 1.840123859191656e-05, + "loss": 0.6885, + "step": 2943 + }, + { + "epoch": 0.24, + "learning_rate": 1.8400695349847895e-05, + "loss": 0.6415, + "step": 2944 + }, + { + "epoch": 0.24, + "learning_rate": 1.840015210777923e-05, + "loss": 0.7141, + "step": 2945 + }, + { + "epoch": 0.24, + "learning_rate": 1.8399608865710564e-05, + "loss": 0.5058, + "step": 2946 + }, + { + "epoch": 0.24, + "learning_rate": 1.8399065623641898e-05, + "loss": 0.3939, + "step": 2947 + }, + { + "epoch": 0.24, + "learning_rate": 1.839852238157323e-05, + "loss": 0.4765, + "step": 2948 + }, + { + "epoch": 0.24, + "learning_rate": 1.8397979139504566e-05, + "loss": 0.5264, + "step": 2949 + }, + { + "epoch": 0.24, + "learning_rate": 1.8397435897435897e-05, + "loss": 0.641, + "step": 2950 + }, + { + "epoch": 0.24, + "learning_rate": 1.8396892655367235e-05, + "loss": 0.511, + "step": 2951 + }, + { + "epoch": 0.24, + "learning_rate": 1.8396349413298566e-05, + "loss": 0.3741, + "step": 2952 + }, + { + "epoch": 0.24, + "learning_rate": 1.8395806171229903e-05, + "loss": 0.6023, + "step": 2953 + }, + { + "epoch": 0.24, + "learning_rate": 1.8395262929161234e-05, + "loss": 0.5643, + "step": 2954 + }, + { + "epoch": 0.24, + "learning_rate": 1.839471968709257e-05, + "loss": 0.5089, + "step": 2955 + }, + { + "epoch": 0.24, + "learning_rate": 1.8394176445023902e-05, + "loss": 0.6105, + "step": 2956 + }, + { + "epoch": 0.24, + "learning_rate": 1.839363320295524e-05, + "loss": 0.4397, + "step": 2957 + }, + { + "epoch": 0.24, + "learning_rate": 1.839308996088657e-05, + "loss": 0.4342, + "step": 2958 + }, + { + "epoch": 0.24, + "learning_rate": 1.839254671881791e-05, + "loss": 0.7138, + "step": 2959 + }, + { + "epoch": 0.24, + "learning_rate": 1.839200347674924e-05, + "loss": 0.5666, + "step": 2960 + }, + { + "epoch": 0.24, + "learning_rate": 1.8391460234680577e-05, + "loss": 0.4739, + "step": 2961 + }, + { + "epoch": 0.24, + "learning_rate": 1.8390916992611908e-05, + "loss": 0.3166, + "step": 2962 + }, + { + "epoch": 0.24, + "learning_rate": 1.8390373750543245e-05, + "loss": 0.4421, + "step": 2963 + }, + { + "epoch": 0.24, + "learning_rate": 1.8389830508474576e-05, + "loss": 0.5278, + "step": 2964 + }, + { + "epoch": 0.24, + "learning_rate": 1.8389287266405914e-05, + "loss": 0.356, + "step": 2965 + }, + { + "epoch": 0.24, + "learning_rate": 1.8388744024337245e-05, + "loss": 0.4296, + "step": 2966 + }, + { + "epoch": 0.24, + "learning_rate": 1.838820078226858e-05, + "loss": 0.3447, + "step": 2967 + }, + { + "epoch": 0.24, + "learning_rate": 1.8387657540199913e-05, + "loss": 0.6522, + "step": 2968 + }, + { + "epoch": 0.24, + "learning_rate": 1.8387114298131247e-05, + "loss": 0.6019, + "step": 2969 + }, + { + "epoch": 0.24, + "learning_rate": 1.838657105606258e-05, + "loss": 0.7225, + "step": 2970 + }, + { + "epoch": 0.24, + "learning_rate": 1.8386027813993916e-05, + "loss": 0.6319, + "step": 2971 + }, + { + "epoch": 0.24, + "learning_rate": 1.838548457192525e-05, + "loss": 0.5843, + "step": 2972 + }, + { + "epoch": 0.24, + "learning_rate": 1.8384941329856584e-05, + "loss": 0.5633, + "step": 2973 + }, + { + "epoch": 0.24, + "learning_rate": 1.838439808778792e-05, + "loss": 0.7394, + "step": 2974 + }, + { + "epoch": 0.24, + "learning_rate": 1.8383854845719253e-05, + "loss": 0.5023, + "step": 2975 + }, + { + "epoch": 0.24, + "learning_rate": 1.838331160365059e-05, + "loss": 0.5403, + "step": 2976 + }, + { + "epoch": 0.24, + "learning_rate": 1.838276836158192e-05, + "loss": 0.4112, + "step": 2977 + }, + { + "epoch": 0.24, + "learning_rate": 1.838222511951326e-05, + "loss": 0.609, + "step": 2978 + }, + { + "epoch": 0.24, + "learning_rate": 1.838168187744459e-05, + "loss": 0.4329, + "step": 2979 + }, + { + "epoch": 0.24, + "learning_rate": 1.8381138635375927e-05, + "loss": 0.2941, + "step": 2980 + }, + { + "epoch": 0.24, + "learning_rate": 1.8380595393307258e-05, + "loss": 0.5627, + "step": 2981 + }, + { + "epoch": 0.24, + "learning_rate": 1.8380052151238596e-05, + "loss": 0.7796, + "step": 2982 + }, + { + "epoch": 0.24, + "learning_rate": 1.8379508909169927e-05, + "loss": 0.6096, + "step": 2983 + }, + { + "epoch": 0.24, + "learning_rate": 1.8378965667101264e-05, + "loss": 0.5351, + "step": 2984 + }, + { + "epoch": 0.24, + "learning_rate": 1.8378422425032595e-05, + "loss": 0.2492, + "step": 2985 + }, + { + "epoch": 0.24, + "learning_rate": 1.837787918296393e-05, + "loss": 0.551, + "step": 2986 + }, + { + "epoch": 0.24, + "learning_rate": 1.8377335940895264e-05, + "loss": 0.5239, + "step": 2987 + }, + { + "epoch": 0.24, + "learning_rate": 1.8376792698826598e-05, + "loss": 0.5739, + "step": 2988 + }, + { + "epoch": 0.24, + "learning_rate": 1.8376249456757932e-05, + "loss": 0.4865, + "step": 2989 + }, + { + "epoch": 0.24, + "learning_rate": 1.8375706214689266e-05, + "loss": 0.5295, + "step": 2990 + }, + { + "epoch": 0.24, + "learning_rate": 1.83751629726206e-05, + "loss": 0.5263, + "step": 2991 + }, + { + "epoch": 0.24, + "learning_rate": 1.8374619730551935e-05, + "loss": 0.667, + "step": 2992 + }, + { + "epoch": 0.24, + "learning_rate": 1.837407648848327e-05, + "loss": 0.6505, + "step": 2993 + }, + { + "epoch": 0.24, + "learning_rate": 1.8373533246414603e-05, + "loss": 0.6023, + "step": 2994 + }, + { + "epoch": 0.24, + "learning_rate": 1.8372990004345937e-05, + "loss": 0.4527, + "step": 2995 + }, + { + "epoch": 0.24, + "learning_rate": 1.837244676227727e-05, + "loss": 0.8306, + "step": 2996 + }, + { + "epoch": 0.24, + "learning_rate": 1.8371903520208606e-05, + "loss": 0.4106, + "step": 2997 + }, + { + "epoch": 0.24, + "learning_rate": 1.837136027813994e-05, + "loss": 0.3875, + "step": 2998 + }, + { + "epoch": 0.24, + "learning_rate": 1.8370817036071274e-05, + "loss": 0.4655, + "step": 2999 + }, + { + "epoch": 0.24, + "learning_rate": 1.837027379400261e-05, + "loss": 0.5205, + "step": 3000 + }, + { + "epoch": 0.24, + "eval_accuracy": 0.7918492103922568, + "eval_loss": 0.5234928131103516, + "eval_runtime": 22.2087, + "eval_samples_per_second": 441.943, + "eval_steps_per_second": 3.467, + "step": 3000 + }, + { + "epoch": 0.24, + "learning_rate": 1.8369730551933943e-05, + "loss": 0.7297, + "step": 3001 + }, + { + "epoch": 0.24, + "learning_rate": 1.8369187309865277e-05, + "loss": 0.3612, + "step": 3002 + }, + { + "epoch": 0.24, + "learning_rate": 1.836864406779661e-05, + "loss": 0.5215, + "step": 3003 + }, + { + "epoch": 0.24, + "learning_rate": 1.8368100825727945e-05, + "loss": 0.595, + "step": 3004 + }, + { + "epoch": 0.24, + "learning_rate": 1.836755758365928e-05, + "loss": 0.6373, + "step": 3005 + }, + { + "epoch": 0.24, + "learning_rate": 1.8367014341590614e-05, + "loss": 0.3147, + "step": 3006 + }, + { + "epoch": 0.25, + "learning_rate": 1.8366471099521948e-05, + "loss": 0.4903, + "step": 3007 + }, + { + "epoch": 0.25, + "learning_rate": 1.8365927857453282e-05, + "loss": 0.4484, + "step": 3008 + }, + { + "epoch": 0.25, + "learning_rate": 1.8365384615384617e-05, + "loss": 0.3606, + "step": 3009 + }, + { + "epoch": 0.25, + "learning_rate": 1.836484137331595e-05, + "loss": 0.6985, + "step": 3010 + }, + { + "epoch": 0.25, + "learning_rate": 1.8364298131247285e-05, + "loss": 0.5763, + "step": 3011 + }, + { + "epoch": 0.25, + "learning_rate": 1.836375488917862e-05, + "loss": 0.5664, + "step": 3012 + }, + { + "epoch": 0.25, + "learning_rate": 1.8363211647109954e-05, + "loss": 0.7689, + "step": 3013 + }, + { + "epoch": 0.25, + "learning_rate": 1.8362668405041288e-05, + "loss": 0.678, + "step": 3014 + }, + { + "epoch": 0.25, + "learning_rate": 1.8362125162972622e-05, + "loss": 0.4496, + "step": 3015 + }, + { + "epoch": 0.25, + "learning_rate": 1.8361581920903956e-05, + "loss": 0.6918, + "step": 3016 + }, + { + "epoch": 0.25, + "learning_rate": 1.836103867883529e-05, + "loss": 0.5018, + "step": 3017 + }, + { + "epoch": 0.25, + "learning_rate": 1.8360495436766625e-05, + "loss": 0.3962, + "step": 3018 + }, + { + "epoch": 0.25, + "learning_rate": 1.835995219469796e-05, + "loss": 0.4037, + "step": 3019 + }, + { + "epoch": 0.25, + "learning_rate": 1.8359408952629293e-05, + "loss": 0.5449, + "step": 3020 + }, + { + "epoch": 0.25, + "learning_rate": 1.8358865710560627e-05, + "loss": 0.5766, + "step": 3021 + }, + { + "epoch": 0.25, + "learning_rate": 1.835832246849196e-05, + "loss": 0.4036, + "step": 3022 + }, + { + "epoch": 0.25, + "learning_rate": 1.8357779226423296e-05, + "loss": 0.33, + "step": 3023 + }, + { + "epoch": 0.25, + "learning_rate": 1.835723598435463e-05, + "loss": 0.603, + "step": 3024 + }, + { + "epoch": 0.25, + "learning_rate": 1.8356692742285964e-05, + "loss": 0.4396, + "step": 3025 + }, + { + "epoch": 0.25, + "learning_rate": 1.83561495002173e-05, + "loss": 0.6111, + "step": 3026 + }, + { + "epoch": 0.25, + "learning_rate": 1.8355606258148633e-05, + "loss": 0.6031, + "step": 3027 + }, + { + "epoch": 0.25, + "learning_rate": 1.8355063016079967e-05, + "loss": 0.4332, + "step": 3028 + }, + { + "epoch": 0.25, + "learning_rate": 1.83545197740113e-05, + "loss": 0.6588, + "step": 3029 + }, + { + "epoch": 0.25, + "learning_rate": 1.8353976531942635e-05, + "loss": 0.3749, + "step": 3030 + }, + { + "epoch": 0.25, + "learning_rate": 1.835343328987397e-05, + "loss": 0.4911, + "step": 3031 + }, + { + "epoch": 0.25, + "learning_rate": 1.8352890047805304e-05, + "loss": 0.751, + "step": 3032 + }, + { + "epoch": 0.25, + "learning_rate": 1.8352346805736638e-05, + "loss": 0.4418, + "step": 3033 + }, + { + "epoch": 0.25, + "learning_rate": 1.8351803563667972e-05, + "loss": 0.4286, + "step": 3034 + }, + { + "epoch": 0.25, + "learning_rate": 1.8351260321599307e-05, + "loss": 0.5965, + "step": 3035 + }, + { + "epoch": 0.25, + "learning_rate": 1.835071707953064e-05, + "loss": 0.2937, + "step": 3036 + }, + { + "epoch": 0.25, + "learning_rate": 1.8350173837461975e-05, + "loss": 0.5958, + "step": 3037 + }, + { + "epoch": 0.25, + "learning_rate": 1.834963059539331e-05, + "loss": 0.3748, + "step": 3038 + }, + { + "epoch": 0.25, + "learning_rate": 1.8349087353324644e-05, + "loss": 0.3895, + "step": 3039 + }, + { + "epoch": 0.25, + "learning_rate": 1.8348544111255978e-05, + "loss": 0.6328, + "step": 3040 + }, + { + "epoch": 0.25, + "learning_rate": 1.8348000869187312e-05, + "loss": 0.3312, + "step": 3041 + }, + { + "epoch": 0.25, + "learning_rate": 1.8347457627118646e-05, + "loss": 0.8607, + "step": 3042 + }, + { + "epoch": 0.25, + "learning_rate": 1.8346914385049977e-05, + "loss": 1.0088, + "step": 3043 + }, + { + "epoch": 0.25, + "learning_rate": 1.8346371142981315e-05, + "loss": 0.534, + "step": 3044 + }, + { + "epoch": 0.25, + "learning_rate": 1.8345827900912646e-05, + "loss": 0.4514, + "step": 3045 + }, + { + "epoch": 0.25, + "learning_rate": 1.8345284658843983e-05, + "loss": 0.4527, + "step": 3046 + }, + { + "epoch": 0.25, + "learning_rate": 1.8344741416775317e-05, + "loss": 0.544, + "step": 3047 + }, + { + "epoch": 0.25, + "learning_rate": 1.834419817470665e-05, + "loss": 0.4909, + "step": 3048 + }, + { + "epoch": 0.25, + "learning_rate": 1.8343654932637986e-05, + "loss": 0.5739, + "step": 3049 + }, + { + "epoch": 0.25, + "learning_rate": 1.834311169056932e-05, + "loss": 0.4857, + "step": 3050 + }, + { + "epoch": 0.25, + "learning_rate": 1.8342568448500654e-05, + "loss": 0.6615, + "step": 3051 + }, + { + "epoch": 0.25, + "learning_rate": 1.834202520643199e-05, + "loss": 0.4824, + "step": 3052 + }, + { + "epoch": 0.25, + "learning_rate": 1.8341481964363323e-05, + "loss": 0.5377, + "step": 3053 + }, + { + "epoch": 0.25, + "learning_rate": 1.8340938722294657e-05, + "loss": 0.4067, + "step": 3054 + }, + { + "epoch": 0.25, + "learning_rate": 1.834039548022599e-05, + "loss": 0.3885, + "step": 3055 + }, + { + "epoch": 0.25, + "learning_rate": 1.8339852238157325e-05, + "loss": 0.5571, + "step": 3056 + }, + { + "epoch": 0.25, + "learning_rate": 1.833930899608866e-05, + "loss": 0.7396, + "step": 3057 + }, + { + "epoch": 0.25, + "learning_rate": 1.8338765754019994e-05, + "loss": 0.4235, + "step": 3058 + }, + { + "epoch": 0.25, + "learning_rate": 1.8338222511951328e-05, + "loss": 0.4825, + "step": 3059 + }, + { + "epoch": 0.25, + "learning_rate": 1.8337679269882662e-05, + "loss": 0.4299, + "step": 3060 + }, + { + "epoch": 0.25, + "learning_rate": 1.8337136027813997e-05, + "loss": 0.5058, + "step": 3061 + }, + { + "epoch": 0.25, + "learning_rate": 1.8336592785745327e-05, + "loss": 0.7049, + "step": 3062 + }, + { + "epoch": 0.25, + "learning_rate": 1.8336049543676665e-05, + "loss": 0.453, + "step": 3063 + }, + { + "epoch": 0.25, + "learning_rate": 1.8335506301607996e-05, + "loss": 0.2335, + "step": 3064 + }, + { + "epoch": 0.25, + "learning_rate": 1.8334963059539334e-05, + "loss": 0.7141, + "step": 3065 + }, + { + "epoch": 0.25, + "learning_rate": 1.8334419817470664e-05, + "loss": 0.4722, + "step": 3066 + }, + { + "epoch": 0.25, + "learning_rate": 1.8333876575402002e-05, + "loss": 0.7498, + "step": 3067 + }, + { + "epoch": 0.25, + "learning_rate": 1.8333333333333333e-05, + "loss": 0.5242, + "step": 3068 + }, + { + "epoch": 0.25, + "learning_rate": 1.833279009126467e-05, + "loss": 0.4583, + "step": 3069 + }, + { + "epoch": 0.25, + "learning_rate": 1.8332246849196e-05, + "loss": 0.5053, + "step": 3070 + }, + { + "epoch": 0.25, + "learning_rate": 1.833170360712734e-05, + "loss": 0.5955, + "step": 3071 + }, + { + "epoch": 0.25, + "learning_rate": 1.833116036505867e-05, + "loss": 0.3407, + "step": 3072 + }, + { + "epoch": 0.25, + "learning_rate": 1.8330617122990007e-05, + "loss": 0.3577, + "step": 3073 + }, + { + "epoch": 0.25, + "learning_rate": 1.8330073880921338e-05, + "loss": 0.7827, + "step": 3074 + }, + { + "epoch": 0.25, + "learning_rate": 1.8329530638852676e-05, + "loss": 0.3981, + "step": 3075 + }, + { + "epoch": 0.25, + "learning_rate": 1.8328987396784007e-05, + "loss": 0.6319, + "step": 3076 + }, + { + "epoch": 0.25, + "learning_rate": 1.8328444154715344e-05, + "loss": 0.4235, + "step": 3077 + }, + { + "epoch": 0.25, + "learning_rate": 1.8327900912646675e-05, + "loss": 0.4465, + "step": 3078 + }, + { + "epoch": 0.25, + "learning_rate": 1.8327357670578013e-05, + "loss": 0.7503, + "step": 3079 + }, + { + "epoch": 0.25, + "learning_rate": 1.8326814428509344e-05, + "loss": 0.4629, + "step": 3080 + }, + { + "epoch": 0.25, + "learning_rate": 1.8326271186440678e-05, + "loss": 0.6668, + "step": 3081 + }, + { + "epoch": 0.25, + "learning_rate": 1.8325727944372012e-05, + "loss": 0.6904, + "step": 3082 + }, + { + "epoch": 0.25, + "learning_rate": 1.8325184702303346e-05, + "loss": 0.4347, + "step": 3083 + }, + { + "epoch": 0.25, + "learning_rate": 1.8324641460234684e-05, + "loss": 0.4942, + "step": 3084 + }, + { + "epoch": 0.25, + "learning_rate": 1.8324098218166015e-05, + "loss": 0.7865, + "step": 3085 + }, + { + "epoch": 0.25, + "learning_rate": 1.8323554976097352e-05, + "loss": 0.5027, + "step": 3086 + }, + { + "epoch": 0.25, + "learning_rate": 1.8323011734028683e-05, + "loss": 0.5405, + "step": 3087 + }, + { + "epoch": 0.25, + "learning_rate": 1.832246849196002e-05, + "loss": 0.4501, + "step": 3088 + }, + { + "epoch": 0.25, + "learning_rate": 1.8321925249891352e-05, + "loss": 0.41, + "step": 3089 + }, + { + "epoch": 0.25, + "learning_rate": 1.832138200782269e-05, + "loss": 0.7372, + "step": 3090 + }, + { + "epoch": 0.25, + "learning_rate": 1.832083876575402e-05, + "loss": 0.4111, + "step": 3091 + }, + { + "epoch": 0.25, + "learning_rate": 1.8320295523685358e-05, + "loss": 0.5554, + "step": 3092 + }, + { + "epoch": 0.25, + "learning_rate": 1.831975228161669e-05, + "loss": 0.4976, + "step": 3093 + }, + { + "epoch": 0.25, + "learning_rate": 1.8319209039548026e-05, + "loss": 0.5947, + "step": 3094 + }, + { + "epoch": 0.25, + "learning_rate": 1.8318665797479357e-05, + "loss": 0.6262, + "step": 3095 + }, + { + "epoch": 0.25, + "learning_rate": 1.8318122555410695e-05, + "loss": 0.4049, + "step": 3096 + }, + { + "epoch": 0.25, + "learning_rate": 1.8317579313342026e-05, + "loss": 0.7174, + "step": 3097 + }, + { + "epoch": 0.25, + "learning_rate": 1.8317036071273363e-05, + "loss": 0.6281, + "step": 3098 + }, + { + "epoch": 0.25, + "learning_rate": 1.8316492829204694e-05, + "loss": 0.6021, + "step": 3099 + }, + { + "epoch": 0.25, + "learning_rate": 1.8315949587136028e-05, + "loss": 0.4865, + "step": 3100 + }, + { + "epoch": 0.25, + "learning_rate": 1.8315406345067362e-05, + "loss": 0.6331, + "step": 3101 + }, + { + "epoch": 0.25, + "learning_rate": 1.8314863102998697e-05, + "loss": 0.6555, + "step": 3102 + }, + { + "epoch": 0.25, + "learning_rate": 1.831431986093003e-05, + "loss": 0.4998, + "step": 3103 + }, + { + "epoch": 0.25, + "learning_rate": 1.8313776618861365e-05, + "loss": 0.5008, + "step": 3104 + }, + { + "epoch": 0.25, + "learning_rate": 1.83132333767927e-05, + "loss": 0.4434, + "step": 3105 + }, + { + "epoch": 0.25, + "learning_rate": 1.8312690134724034e-05, + "loss": 0.3308, + "step": 3106 + }, + { + "epoch": 0.25, + "learning_rate": 1.8312146892655368e-05, + "loss": 0.4537, + "step": 3107 + }, + { + "epoch": 0.25, + "learning_rate": 1.8311603650586702e-05, + "loss": 0.5753, + "step": 3108 + }, + { + "epoch": 0.25, + "learning_rate": 1.8311060408518036e-05, + "loss": 0.6525, + "step": 3109 + }, + { + "epoch": 0.25, + "learning_rate": 1.831051716644937e-05, + "loss": 0.6602, + "step": 3110 + }, + { + "epoch": 0.25, + "learning_rate": 1.8309973924380705e-05, + "loss": 0.5462, + "step": 3111 + }, + { + "epoch": 0.25, + "learning_rate": 1.830943068231204e-05, + "loss": 0.3216, + "step": 3112 + }, + { + "epoch": 0.25, + "learning_rate": 1.8308887440243373e-05, + "loss": 0.7655, + "step": 3113 + }, + { + "epoch": 0.25, + "learning_rate": 1.8308344198174707e-05, + "loss": 0.4947, + "step": 3114 + }, + { + "epoch": 0.25, + "learning_rate": 1.830780095610604e-05, + "loss": 0.3942, + "step": 3115 + }, + { + "epoch": 0.25, + "learning_rate": 1.8307257714037376e-05, + "loss": 0.2828, + "step": 3116 + }, + { + "epoch": 0.25, + "learning_rate": 1.830671447196871e-05, + "loss": 0.4785, + "step": 3117 + }, + { + "epoch": 0.25, + "learning_rate": 1.8306171229900044e-05, + "loss": 0.4739, + "step": 3118 + }, + { + "epoch": 0.25, + "learning_rate": 1.830562798783138e-05, + "loss": 0.5168, + "step": 3119 + }, + { + "epoch": 0.25, + "learning_rate": 1.8305084745762713e-05, + "loss": 0.615, + "step": 3120 + }, + { + "epoch": 0.25, + "learning_rate": 1.8304541503694047e-05, + "loss": 0.609, + "step": 3121 + }, + { + "epoch": 0.25, + "learning_rate": 1.830399826162538e-05, + "loss": 0.9011, + "step": 3122 + }, + { + "epoch": 0.25, + "learning_rate": 1.8303455019556716e-05, + "loss": 0.3602, + "step": 3123 + }, + { + "epoch": 0.25, + "learning_rate": 1.830291177748805e-05, + "loss": 0.3823, + "step": 3124 + }, + { + "epoch": 0.25, + "learning_rate": 1.8302368535419384e-05, + "loss": 0.3247, + "step": 3125 + }, + { + "epoch": 0.25, + "learning_rate": 1.8301825293350718e-05, + "loss": 0.7071, + "step": 3126 + }, + { + "epoch": 0.25, + "learning_rate": 1.8301282051282052e-05, + "loss": 0.4119, + "step": 3127 + }, + { + "epoch": 0.25, + "learning_rate": 1.8300738809213387e-05, + "loss": 0.4672, + "step": 3128 + }, + { + "epoch": 0.25, + "learning_rate": 1.830019556714472e-05, + "loss": 0.5904, + "step": 3129 + }, + { + "epoch": 0.26, + "learning_rate": 1.8299652325076055e-05, + "loss": 0.3151, + "step": 3130 + }, + { + "epoch": 0.26, + "learning_rate": 1.829910908300739e-05, + "loss": 0.4838, + "step": 3131 + }, + { + "epoch": 0.26, + "learning_rate": 1.8298565840938724e-05, + "loss": 0.5454, + "step": 3132 + }, + { + "epoch": 0.26, + "learning_rate": 1.8298022598870058e-05, + "loss": 0.4349, + "step": 3133 + }, + { + "epoch": 0.26, + "learning_rate": 1.8297479356801392e-05, + "loss": 0.7373, + "step": 3134 + }, + { + "epoch": 0.26, + "learning_rate": 1.8296936114732726e-05, + "loss": 0.4183, + "step": 3135 + }, + { + "epoch": 0.26, + "learning_rate": 1.829639287266406e-05, + "loss": 0.5395, + "step": 3136 + }, + { + "epoch": 0.26, + "learning_rate": 1.8295849630595395e-05, + "loss": 0.5696, + "step": 3137 + }, + { + "epoch": 0.26, + "learning_rate": 1.829530638852673e-05, + "loss": 0.6302, + "step": 3138 + }, + { + "epoch": 0.26, + "learning_rate": 1.8294763146458063e-05, + "loss": 0.3428, + "step": 3139 + }, + { + "epoch": 0.26, + "learning_rate": 1.8294219904389397e-05, + "loss": 0.7541, + "step": 3140 + }, + { + "epoch": 0.26, + "learning_rate": 1.829367666232073e-05, + "loss": 0.4613, + "step": 3141 + }, + { + "epoch": 0.26, + "learning_rate": 1.8293133420252066e-05, + "loss": 0.5112, + "step": 3142 + }, + { + "epoch": 0.26, + "learning_rate": 1.82925901781834e-05, + "loss": 0.7526, + "step": 3143 + }, + { + "epoch": 0.26, + "learning_rate": 1.8292046936114734e-05, + "loss": 0.3785, + "step": 3144 + }, + { + "epoch": 0.26, + "learning_rate": 1.829150369404607e-05, + "loss": 0.4722, + "step": 3145 + }, + { + "epoch": 0.26, + "learning_rate": 1.8290960451977403e-05, + "loss": 0.5876, + "step": 3146 + }, + { + "epoch": 0.26, + "learning_rate": 1.8290417209908737e-05, + "loss": 0.6839, + "step": 3147 + }, + { + "epoch": 0.26, + "learning_rate": 1.828987396784007e-05, + "loss": 0.6428, + "step": 3148 + }, + { + "epoch": 0.26, + "learning_rate": 1.8289330725771406e-05, + "loss": 0.5116, + "step": 3149 + }, + { + "epoch": 0.26, + "learning_rate": 1.828878748370274e-05, + "loss": 0.5698, + "step": 3150 + }, + { + "epoch": 0.26, + "learning_rate": 1.8288244241634074e-05, + "loss": 0.3817, + "step": 3151 + }, + { + "epoch": 0.26, + "learning_rate": 1.8287700999565408e-05, + "loss": 0.6068, + "step": 3152 + }, + { + "epoch": 0.26, + "learning_rate": 1.8287157757496742e-05, + "loss": 0.6029, + "step": 3153 + }, + { + "epoch": 0.26, + "learning_rate": 1.8286614515428077e-05, + "loss": 0.5335, + "step": 3154 + }, + { + "epoch": 0.26, + "learning_rate": 1.828607127335941e-05, + "loss": 0.8313, + "step": 3155 + }, + { + "epoch": 0.26, + "learning_rate": 1.8285528031290745e-05, + "loss": 0.5576, + "step": 3156 + }, + { + "epoch": 0.26, + "learning_rate": 1.828498478922208e-05, + "loss": 0.4991, + "step": 3157 + }, + { + "epoch": 0.26, + "learning_rate": 1.8284441547153414e-05, + "loss": 0.3845, + "step": 3158 + }, + { + "epoch": 0.26, + "learning_rate": 1.8283898305084748e-05, + "loss": 0.5047, + "step": 3159 + }, + { + "epoch": 0.26, + "learning_rate": 1.8283355063016082e-05, + "loss": 0.6013, + "step": 3160 + }, + { + "epoch": 0.26, + "learning_rate": 1.8282811820947416e-05, + "loss": 0.6787, + "step": 3161 + }, + { + "epoch": 0.26, + "learning_rate": 1.828226857887875e-05, + "loss": 0.5841, + "step": 3162 + }, + { + "epoch": 0.26, + "learning_rate": 1.8281725336810085e-05, + "loss": 0.5143, + "step": 3163 + }, + { + "epoch": 0.26, + "learning_rate": 1.828118209474142e-05, + "loss": 0.2802, + "step": 3164 + }, + { + "epoch": 0.26, + "learning_rate": 1.8280638852672753e-05, + "loss": 0.7484, + "step": 3165 + }, + { + "epoch": 0.26, + "learning_rate": 1.8280095610604087e-05, + "loss": 0.5373, + "step": 3166 + }, + { + "epoch": 0.26, + "learning_rate": 1.827955236853542e-05, + "loss": 0.4348, + "step": 3167 + }, + { + "epoch": 0.26, + "learning_rate": 1.8279009126466756e-05, + "loss": 0.548, + "step": 3168 + }, + { + "epoch": 0.26, + "learning_rate": 1.827846588439809e-05, + "loss": 0.946, + "step": 3169 + }, + { + "epoch": 0.26, + "learning_rate": 1.8277922642329424e-05, + "loss": 0.4881, + "step": 3170 + }, + { + "epoch": 0.26, + "learning_rate": 1.827737940026076e-05, + "loss": 0.5067, + "step": 3171 + }, + { + "epoch": 0.26, + "learning_rate": 1.8276836158192093e-05, + "loss": 0.6137, + "step": 3172 + }, + { + "epoch": 0.26, + "learning_rate": 1.8276292916123427e-05, + "loss": 0.6357, + "step": 3173 + }, + { + "epoch": 0.26, + "learning_rate": 1.827574967405476e-05, + "loss": 0.4814, + "step": 3174 + }, + { + "epoch": 0.26, + "learning_rate": 1.8275206431986096e-05, + "loss": 0.6945, + "step": 3175 + }, + { + "epoch": 0.26, + "learning_rate": 1.8274663189917426e-05, + "loss": 0.4711, + "step": 3176 + }, + { + "epoch": 0.26, + "learning_rate": 1.8274119947848764e-05, + "loss": 0.4725, + "step": 3177 + }, + { + "epoch": 0.26, + "learning_rate": 1.8273576705780095e-05, + "loss": 0.5566, + "step": 3178 + }, + { + "epoch": 0.26, + "learning_rate": 1.8273033463711432e-05, + "loss": 0.5107, + "step": 3179 + }, + { + "epoch": 0.26, + "learning_rate": 1.8272490221642763e-05, + "loss": 0.5721, + "step": 3180 + }, + { + "epoch": 0.26, + "learning_rate": 1.82719469795741e-05, + "loss": 0.5537, + "step": 3181 + }, + { + "epoch": 0.26, + "learning_rate": 1.8271403737505432e-05, + "loss": 0.581, + "step": 3182 + }, + { + "epoch": 0.26, + "learning_rate": 1.827086049543677e-05, + "loss": 0.4808, + "step": 3183 + }, + { + "epoch": 0.26, + "learning_rate": 1.82703172533681e-05, + "loss": 0.3015, + "step": 3184 + }, + { + "epoch": 0.26, + "learning_rate": 1.8269774011299438e-05, + "loss": 0.709, + "step": 3185 + }, + { + "epoch": 0.26, + "learning_rate": 1.826923076923077e-05, + "loss": 0.4996, + "step": 3186 + }, + { + "epoch": 0.26, + "learning_rate": 1.8268687527162106e-05, + "loss": 0.288, + "step": 3187 + }, + { + "epoch": 0.26, + "learning_rate": 1.8268144285093437e-05, + "loss": 0.6265, + "step": 3188 + }, + { + "epoch": 0.26, + "learning_rate": 1.8267601043024775e-05, + "loss": 0.5442, + "step": 3189 + }, + { + "epoch": 0.26, + "learning_rate": 1.8267057800956106e-05, + "loss": 0.4233, + "step": 3190 + }, + { + "epoch": 0.26, + "learning_rate": 1.8266514558887443e-05, + "loss": 0.3385, + "step": 3191 + }, + { + "epoch": 0.26, + "learning_rate": 1.8265971316818777e-05, + "loss": 0.5131, + "step": 3192 + }, + { + "epoch": 0.26, + "learning_rate": 1.826542807475011e-05, + "loss": 0.3397, + "step": 3193 + }, + { + "epoch": 0.26, + "learning_rate": 1.8264884832681446e-05, + "loss": 0.5298, + "step": 3194 + }, + { + "epoch": 0.26, + "learning_rate": 1.8264341590612777e-05, + "loss": 0.4339, + "step": 3195 + }, + { + "epoch": 0.26, + "learning_rate": 1.8263798348544114e-05, + "loss": 0.3275, + "step": 3196 + }, + { + "epoch": 0.26, + "learning_rate": 1.8263255106475445e-05, + "loss": 0.6656, + "step": 3197 + }, + { + "epoch": 0.26, + "learning_rate": 1.8262711864406783e-05, + "loss": 0.488, + "step": 3198 + }, + { + "epoch": 0.26, + "learning_rate": 1.8262168622338114e-05, + "loss": 0.4485, + "step": 3199 + }, + { + "epoch": 0.26, + "learning_rate": 1.826162538026945e-05, + "loss": 0.4345, + "step": 3200 + }, + { + "epoch": 0.26, + "learning_rate": 1.8261082138200782e-05, + "loss": 0.559, + "step": 3201 + }, + { + "epoch": 0.26, + "learning_rate": 1.826053889613212e-05, + "loss": 0.8498, + "step": 3202 + }, + { + "epoch": 0.26, + "learning_rate": 1.825999565406345e-05, + "loss": 0.426, + "step": 3203 + }, + { + "epoch": 0.26, + "learning_rate": 1.8259452411994788e-05, + "loss": 0.3811, + "step": 3204 + }, + { + "epoch": 0.26, + "learning_rate": 1.825890916992612e-05, + "loss": 0.3544, + "step": 3205 + }, + { + "epoch": 0.26, + "learning_rate": 1.8258365927857457e-05, + "loss": 0.5794, + "step": 3206 + }, + { + "epoch": 0.26, + "learning_rate": 1.8257822685788788e-05, + "loss": 0.3911, + "step": 3207 + }, + { + "epoch": 0.26, + "learning_rate": 1.8257279443720125e-05, + "loss": 0.7892, + "step": 3208 + }, + { + "epoch": 0.26, + "learning_rate": 1.8256736201651456e-05, + "loss": 0.8063, + "step": 3209 + }, + { + "epoch": 0.26, + "learning_rate": 1.8256192959582794e-05, + "loss": 0.4484, + "step": 3210 + }, + { + "epoch": 0.26, + "learning_rate": 1.8255649717514124e-05, + "loss": 0.4483, + "step": 3211 + }, + { + "epoch": 0.26, + "learning_rate": 1.8255106475445462e-05, + "loss": 0.7488, + "step": 3212 + }, + { + "epoch": 0.26, + "learning_rate": 1.8254563233376793e-05, + "loss": 0.4893, + "step": 3213 + }, + { + "epoch": 0.26, + "learning_rate": 1.8254019991308127e-05, + "loss": 0.533, + "step": 3214 + }, + { + "epoch": 0.26, + "learning_rate": 1.825347674923946e-05, + "loss": 0.8523, + "step": 3215 + }, + { + "epoch": 0.26, + "learning_rate": 1.8252933507170796e-05, + "loss": 0.5499, + "step": 3216 + }, + { + "epoch": 0.26, + "learning_rate": 1.825239026510213e-05, + "loss": 0.7442, + "step": 3217 + }, + { + "epoch": 0.26, + "learning_rate": 1.8251847023033464e-05, + "loss": 0.6656, + "step": 3218 + }, + { + "epoch": 0.26, + "learning_rate": 1.8251303780964798e-05, + "loss": 0.4401, + "step": 3219 + }, + { + "epoch": 0.26, + "learning_rate": 1.8250760538896133e-05, + "loss": 0.497, + "step": 3220 + }, + { + "epoch": 0.26, + "learning_rate": 1.8250217296827467e-05, + "loss": 0.6379, + "step": 3221 + }, + { + "epoch": 0.26, + "learning_rate": 1.82496740547588e-05, + "loss": 0.4745, + "step": 3222 + }, + { + "epoch": 0.26, + "learning_rate": 1.8249130812690135e-05, + "loss": 0.4274, + "step": 3223 + }, + { + "epoch": 0.26, + "learning_rate": 1.824858757062147e-05, + "loss": 0.6924, + "step": 3224 + }, + { + "epoch": 0.26, + "learning_rate": 1.8248044328552804e-05, + "loss": 0.7329, + "step": 3225 + }, + { + "epoch": 0.26, + "learning_rate": 1.8247501086484138e-05, + "loss": 0.5687, + "step": 3226 + }, + { + "epoch": 0.26, + "learning_rate": 1.8246957844415472e-05, + "loss": 0.5126, + "step": 3227 + }, + { + "epoch": 0.26, + "learning_rate": 1.8246414602346806e-05, + "loss": 0.4512, + "step": 3228 + }, + { + "epoch": 0.26, + "learning_rate": 1.8245871360278144e-05, + "loss": 0.6043, + "step": 3229 + }, + { + "epoch": 0.26, + "learning_rate": 1.8245328118209475e-05, + "loss": 0.5204, + "step": 3230 + }, + { + "epoch": 0.26, + "learning_rate": 1.8244784876140812e-05, + "loss": 0.3912, + "step": 3231 + }, + { + "epoch": 0.26, + "learning_rate": 1.8244241634072143e-05, + "loss": 0.3807, + "step": 3232 + }, + { + "epoch": 0.26, + "learning_rate": 1.8243698392003478e-05, + "loss": 0.4582, + "step": 3233 + }, + { + "epoch": 0.26, + "learning_rate": 1.8243155149934812e-05, + "loss": 0.4356, + "step": 3234 + }, + { + "epoch": 0.26, + "learning_rate": 1.8242611907866146e-05, + "loss": 0.676, + "step": 3235 + }, + { + "epoch": 0.26, + "learning_rate": 1.824206866579748e-05, + "loss": 0.3641, + "step": 3236 + }, + { + "epoch": 0.26, + "learning_rate": 1.8241525423728814e-05, + "loss": 0.6523, + "step": 3237 + }, + { + "epoch": 0.26, + "learning_rate": 1.824098218166015e-05, + "loss": 0.4552, + "step": 3238 + }, + { + "epoch": 0.26, + "learning_rate": 1.8240438939591483e-05, + "loss": 0.4378, + "step": 3239 + }, + { + "epoch": 0.26, + "learning_rate": 1.8239895697522817e-05, + "loss": 0.7026, + "step": 3240 + }, + { + "epoch": 0.26, + "learning_rate": 1.823935245545415e-05, + "loss": 0.3626, + "step": 3241 + }, + { + "epoch": 0.26, + "learning_rate": 1.8238809213385486e-05, + "loss": 0.4365, + "step": 3242 + }, + { + "epoch": 0.26, + "learning_rate": 1.823826597131682e-05, + "loss": 0.7188, + "step": 3243 + }, + { + "epoch": 0.26, + "learning_rate": 1.8237722729248154e-05, + "loss": 0.4289, + "step": 3244 + }, + { + "epoch": 0.26, + "learning_rate": 1.8237179487179488e-05, + "loss": 0.6278, + "step": 3245 + }, + { + "epoch": 0.26, + "learning_rate": 1.8236636245110823e-05, + "loss": 0.6209, + "step": 3246 + }, + { + "epoch": 0.26, + "learning_rate": 1.8236093003042157e-05, + "loss": 0.5663, + "step": 3247 + }, + { + "epoch": 0.26, + "learning_rate": 1.823554976097349e-05, + "loss": 0.63, + "step": 3248 + }, + { + "epoch": 0.26, + "learning_rate": 1.8235006518904825e-05, + "loss": 0.4927, + "step": 3249 + }, + { + "epoch": 0.26, + "learning_rate": 1.823446327683616e-05, + "loss": 0.4386, + "step": 3250 + }, + { + "epoch": 0.26, + "eval_accuracy": 0.7938869077941926, + "eval_loss": 0.5241982936859131, + "eval_runtime": 22.2693, + "eval_samples_per_second": 440.742, + "eval_steps_per_second": 3.458, + "step": 3250 + }, + { + "epoch": 0.26, + "learning_rate": 1.8233920034767494e-05, + "loss": 0.6192, + "step": 3251 + }, + { + "epoch": 0.26, + "learning_rate": 1.8233376792698828e-05, + "loss": 0.4146, + "step": 3252 + }, + { + "epoch": 0.27, + "learning_rate": 1.8232833550630162e-05, + "loss": 0.3993, + "step": 3253 + }, + { + "epoch": 0.27, + "learning_rate": 1.8232290308561496e-05, + "loss": 0.6864, + "step": 3254 + }, + { + "epoch": 0.27, + "learning_rate": 1.823174706649283e-05, + "loss": 0.3452, + "step": 3255 + }, + { + "epoch": 0.27, + "learning_rate": 1.8231203824424165e-05, + "loss": 0.6776, + "step": 3256 + }, + { + "epoch": 0.27, + "learning_rate": 1.82306605823555e-05, + "loss": 0.4698, + "step": 3257 + }, + { + "epoch": 0.27, + "learning_rate": 1.8230117340286833e-05, + "loss": 0.4531, + "step": 3258 + }, + { + "epoch": 0.27, + "learning_rate": 1.8229574098218168e-05, + "loss": 0.3536, + "step": 3259 + }, + { + "epoch": 0.27, + "learning_rate": 1.8229030856149502e-05, + "loss": 0.4309, + "step": 3260 + }, + { + "epoch": 0.27, + "learning_rate": 1.8228487614080836e-05, + "loss": 0.3385, + "step": 3261 + }, + { + "epoch": 0.27, + "learning_rate": 1.822794437201217e-05, + "loss": 0.4856, + "step": 3262 + }, + { + "epoch": 0.27, + "learning_rate": 1.8227401129943504e-05, + "loss": 0.7157, + "step": 3263 + }, + { + "epoch": 0.27, + "learning_rate": 1.822685788787484e-05, + "loss": 0.4734, + "step": 3264 + }, + { + "epoch": 0.27, + "learning_rate": 1.8226314645806173e-05, + "loss": 0.3596, + "step": 3265 + }, + { + "epoch": 0.27, + "learning_rate": 1.8225771403737507e-05, + "loss": 0.6516, + "step": 3266 + }, + { + "epoch": 0.27, + "learning_rate": 1.822522816166884e-05, + "loss": 0.4447, + "step": 3267 + }, + { + "epoch": 0.27, + "learning_rate": 1.8224684919600176e-05, + "loss": 0.614, + "step": 3268 + }, + { + "epoch": 0.27, + "learning_rate": 1.822414167753151e-05, + "loss": 0.7168, + "step": 3269 + }, + { + "epoch": 0.27, + "learning_rate": 1.8223598435462844e-05, + "loss": 0.4639, + "step": 3270 + }, + { + "epoch": 0.27, + "learning_rate": 1.8223055193394178e-05, + "loss": 0.6484, + "step": 3271 + }, + { + "epoch": 0.27, + "learning_rate": 1.8222511951325512e-05, + "loss": 0.6844, + "step": 3272 + }, + { + "epoch": 0.27, + "learning_rate": 1.8221968709256847e-05, + "loss": 0.2582, + "step": 3273 + }, + { + "epoch": 0.27, + "learning_rate": 1.822142546718818e-05, + "loss": 0.3787, + "step": 3274 + }, + { + "epoch": 0.27, + "learning_rate": 1.8220882225119515e-05, + "loss": 0.6109, + "step": 3275 + }, + { + "epoch": 0.27, + "learning_rate": 1.822033898305085e-05, + "loss": 0.4421, + "step": 3276 + }, + { + "epoch": 0.27, + "learning_rate": 1.8219795740982184e-05, + "loss": 0.9141, + "step": 3277 + }, + { + "epoch": 0.27, + "learning_rate": 1.8219252498913518e-05, + "loss": 0.4008, + "step": 3278 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218709256844852e-05, + "loss": 0.5582, + "step": 3279 + }, + { + "epoch": 0.27, + "learning_rate": 1.8218166014776186e-05, + "loss": 0.4942, + "step": 3280 + }, + { + "epoch": 0.27, + "learning_rate": 1.821762277270752e-05, + "loss": 0.3955, + "step": 3281 + }, + { + "epoch": 0.27, + "learning_rate": 1.8217079530638855e-05, + "loss": 0.4477, + "step": 3282 + }, + { + "epoch": 0.27, + "learning_rate": 1.821653628857019e-05, + "loss": 0.4175, + "step": 3283 + }, + { + "epoch": 0.27, + "learning_rate": 1.8215993046501523e-05, + "loss": 0.4349, + "step": 3284 + }, + { + "epoch": 0.27, + "learning_rate": 1.8215449804432857e-05, + "loss": 0.5363, + "step": 3285 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214906562364192e-05, + "loss": 0.4072, + "step": 3286 + }, + { + "epoch": 0.27, + "learning_rate": 1.8214363320295526e-05, + "loss": 0.4481, + "step": 3287 + }, + { + "epoch": 0.27, + "learning_rate": 1.821382007822686e-05, + "loss": 0.5909, + "step": 3288 + }, + { + "epoch": 0.27, + "learning_rate": 1.8213276836158194e-05, + "loss": 0.8422, + "step": 3289 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212733594089525e-05, + "loss": 0.5196, + "step": 3290 + }, + { + "epoch": 0.27, + "learning_rate": 1.8212190352020863e-05, + "loss": 0.4098, + "step": 3291 + }, + { + "epoch": 0.27, + "learning_rate": 1.8211647109952194e-05, + "loss": 0.4281, + "step": 3292 + }, + { + "epoch": 0.27, + "learning_rate": 1.821110386788353e-05, + "loss": 0.463, + "step": 3293 + }, + { + "epoch": 0.27, + "learning_rate": 1.8210560625814862e-05, + "loss": 0.43, + "step": 3294 + }, + { + "epoch": 0.27, + "learning_rate": 1.82100173837462e-05, + "loss": 0.5258, + "step": 3295 + }, + { + "epoch": 0.27, + "learning_rate": 1.820947414167753e-05, + "loss": 0.6134, + "step": 3296 + }, + { + "epoch": 0.27, + "learning_rate": 1.8208930899608868e-05, + "loss": 0.3942, + "step": 3297 + }, + { + "epoch": 0.27, + "learning_rate": 1.82083876575402e-05, + "loss": 0.5387, + "step": 3298 + }, + { + "epoch": 0.27, + "learning_rate": 1.8207844415471537e-05, + "loss": 0.4629, + "step": 3299 + }, + { + "epoch": 0.27, + "learning_rate": 1.820730117340287e-05, + "loss": 0.6553, + "step": 3300 + }, + { + "epoch": 0.27, + "learning_rate": 1.8206757931334205e-05, + "loss": 0.6911, + "step": 3301 + }, + { + "epoch": 0.27, + "learning_rate": 1.820621468926554e-05, + "loss": 0.644, + "step": 3302 + }, + { + "epoch": 0.27, + "learning_rate": 1.8205671447196874e-05, + "loss": 0.2321, + "step": 3303 + }, + { + "epoch": 0.27, + "learning_rate": 1.8205128205128208e-05, + "loss": 0.351, + "step": 3304 + }, + { + "epoch": 0.27, + "learning_rate": 1.8204584963059542e-05, + "loss": 0.5931, + "step": 3305 + }, + { + "epoch": 0.27, + "learning_rate": 1.8204041720990876e-05, + "loss": 0.6832, + "step": 3306 + }, + { + "epoch": 0.27, + "learning_rate": 1.820349847892221e-05, + "loss": 0.5654, + "step": 3307 + }, + { + "epoch": 0.27, + "learning_rate": 1.8202955236853545e-05, + "loss": 0.5358, + "step": 3308 + }, + { + "epoch": 0.27, + "learning_rate": 1.8202411994784876e-05, + "loss": 0.4073, + "step": 3309 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201868752716213e-05, + "loss": 0.3311, + "step": 3310 + }, + { + "epoch": 0.27, + "learning_rate": 1.8201325510647544e-05, + "loss": 0.6271, + "step": 3311 + }, + { + "epoch": 0.27, + "learning_rate": 1.8200782268578882e-05, + "loss": 0.4829, + "step": 3312 + }, + { + "epoch": 0.27, + "learning_rate": 1.8200239026510213e-05, + "loss": 0.6623, + "step": 3313 + }, + { + "epoch": 0.27, + "learning_rate": 1.819969578444155e-05, + "loss": 0.4337, + "step": 3314 + }, + { + "epoch": 0.27, + "learning_rate": 1.819915254237288e-05, + "loss": 0.5237, + "step": 3315 + }, + { + "epoch": 0.27, + "learning_rate": 1.819860930030422e-05, + "loss": 0.63, + "step": 3316 + }, + { + "epoch": 0.27, + "learning_rate": 1.819806605823555e-05, + "loss": 0.4862, + "step": 3317 + }, + { + "epoch": 0.27, + "learning_rate": 1.8197522816166887e-05, + "loss": 0.4692, + "step": 3318 + }, + { + "epoch": 0.27, + "learning_rate": 1.8196979574098218e-05, + "loss": 0.693, + "step": 3319 + }, + { + "epoch": 0.27, + "learning_rate": 1.8196436332029556e-05, + "loss": 0.4289, + "step": 3320 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195893089960886e-05, + "loss": 0.6334, + "step": 3321 + }, + { + "epoch": 0.27, + "learning_rate": 1.8195349847892224e-05, + "loss": 0.595, + "step": 3322 + }, + { + "epoch": 0.27, + "learning_rate": 1.8194806605823555e-05, + "loss": 0.8322, + "step": 3323 + }, + { + "epoch": 0.27, + "learning_rate": 1.8194263363754892e-05, + "loss": 0.587, + "step": 3324 + }, + { + "epoch": 0.27, + "learning_rate": 1.8193720121686223e-05, + "loss": 0.6111, + "step": 3325 + }, + { + "epoch": 0.27, + "learning_rate": 1.819317687961756e-05, + "loss": 0.5221, + "step": 3326 + }, + { + "epoch": 0.27, + "learning_rate": 1.8192633637548892e-05, + "loss": 0.4678, + "step": 3327 + }, + { + "epoch": 0.27, + "learning_rate": 1.8192090395480226e-05, + "loss": 0.6405, + "step": 3328 + }, + { + "epoch": 0.27, + "learning_rate": 1.819154715341156e-05, + "loss": 0.3788, + "step": 3329 + }, + { + "epoch": 0.27, + "learning_rate": 1.8191003911342894e-05, + "loss": 0.5443, + "step": 3330 + }, + { + "epoch": 0.27, + "learning_rate": 1.819046066927423e-05, + "loss": 0.6465, + "step": 3331 + }, + { + "epoch": 0.27, + "learning_rate": 1.8189917427205563e-05, + "loss": 0.4126, + "step": 3332 + }, + { + "epoch": 0.27, + "learning_rate": 1.8189374185136897e-05, + "loss": 0.4722, + "step": 3333 + }, + { + "epoch": 0.27, + "learning_rate": 1.818883094306823e-05, + "loss": 0.5607, + "step": 3334 + }, + { + "epoch": 0.27, + "learning_rate": 1.8188287700999566e-05, + "loss": 0.5662, + "step": 3335 + }, + { + "epoch": 0.27, + "learning_rate": 1.81877444589309e-05, + "loss": 0.6018, + "step": 3336 + }, + { + "epoch": 0.27, + "learning_rate": 1.8187201216862237e-05, + "loss": 0.4816, + "step": 3337 + }, + { + "epoch": 0.27, + "learning_rate": 1.818665797479357e-05, + "loss": 0.4684, + "step": 3338 + }, + { + "epoch": 0.27, + "learning_rate": 1.8186114732724906e-05, + "loss": 0.3986, + "step": 3339 + }, + { + "epoch": 0.27, + "learning_rate": 1.8185571490656237e-05, + "loss": 0.4061, + "step": 3340 + }, + { + "epoch": 0.27, + "learning_rate": 1.8185028248587574e-05, + "loss": 0.6108, + "step": 3341 + }, + { + "epoch": 0.27, + "learning_rate": 1.8184485006518905e-05, + "loss": 0.4596, + "step": 3342 + }, + { + "epoch": 0.27, + "learning_rate": 1.8183941764450243e-05, + "loss": 0.4883, + "step": 3343 + }, + { + "epoch": 0.27, + "learning_rate": 1.8183398522381574e-05, + "loss": 0.3605, + "step": 3344 + }, + { + "epoch": 0.27, + "learning_rate": 1.818285528031291e-05, + "loss": 0.6096, + "step": 3345 + }, + { + "epoch": 0.27, + "learning_rate": 1.8182312038244242e-05, + "loss": 0.5967, + "step": 3346 + }, + { + "epoch": 0.27, + "learning_rate": 1.8181768796175576e-05, + "loss": 0.4872, + "step": 3347 + }, + { + "epoch": 0.27, + "learning_rate": 1.818122555410691e-05, + "loss": 0.5107, + "step": 3348 + }, + { + "epoch": 0.27, + "learning_rate": 1.8180682312038245e-05, + "loss": 0.5921, + "step": 3349 + }, + { + "epoch": 0.27, + "learning_rate": 1.818013906996958e-05, + "loss": 0.5066, + "step": 3350 + }, + { + "epoch": 0.27, + "learning_rate": 1.8179595827900913e-05, + "loss": 0.6013, + "step": 3351 + }, + { + "epoch": 0.27, + "learning_rate": 1.8179052585832248e-05, + "loss": 0.422, + "step": 3352 + }, + { + "epoch": 0.27, + "learning_rate": 1.8178509343763582e-05, + "loss": 0.4032, + "step": 3353 + }, + { + "epoch": 0.27, + "learning_rate": 1.8177966101694916e-05, + "loss": 0.4217, + "step": 3354 + }, + { + "epoch": 0.27, + "learning_rate": 1.817742285962625e-05, + "loss": 0.4719, + "step": 3355 + }, + { + "epoch": 0.27, + "learning_rate": 1.8176879617557584e-05, + "loss": 0.5601, + "step": 3356 + }, + { + "epoch": 0.27, + "learning_rate": 1.817633637548892e-05, + "loss": 0.6587, + "step": 3357 + }, + { + "epoch": 0.27, + "learning_rate": 1.8175793133420253e-05, + "loss": 0.7532, + "step": 3358 + }, + { + "epoch": 0.27, + "learning_rate": 1.8175249891351587e-05, + "loss": 0.5878, + "step": 3359 + }, + { + "epoch": 0.27, + "learning_rate": 1.817470664928292e-05, + "loss": 0.3985, + "step": 3360 + }, + { + "epoch": 0.27, + "learning_rate": 1.8174163407214256e-05, + "loss": 0.5145, + "step": 3361 + }, + { + "epoch": 0.27, + "learning_rate": 1.817362016514559e-05, + "loss": 0.4316, + "step": 3362 + }, + { + "epoch": 0.27, + "learning_rate": 1.8173076923076924e-05, + "loss": 0.3402, + "step": 3363 + }, + { + "epoch": 0.27, + "learning_rate": 1.817253368100826e-05, + "loss": 0.6273, + "step": 3364 + }, + { + "epoch": 0.27, + "learning_rate": 1.8171990438939593e-05, + "loss": 0.4624, + "step": 3365 + }, + { + "epoch": 0.27, + "learning_rate": 1.8171447196870927e-05, + "loss": 0.4984, + "step": 3366 + }, + { + "epoch": 0.27, + "learning_rate": 1.817090395480226e-05, + "loss": 0.5667, + "step": 3367 + }, + { + "epoch": 0.27, + "learning_rate": 1.8170360712733595e-05, + "loss": 0.7272, + "step": 3368 + }, + { + "epoch": 0.27, + "learning_rate": 1.816981747066493e-05, + "loss": 0.6549, + "step": 3369 + }, + { + "epoch": 0.27, + "learning_rate": 1.8169274228596264e-05, + "loss": 0.5989, + "step": 3370 + }, + { + "epoch": 0.27, + "learning_rate": 1.8168730986527598e-05, + "loss": 0.4638, + "step": 3371 + }, + { + "epoch": 0.27, + "learning_rate": 1.8168187744458932e-05, + "loss": 0.466, + "step": 3372 + }, + { + "epoch": 0.27, + "learning_rate": 1.8167644502390266e-05, + "loss": 0.4345, + "step": 3373 + }, + { + "epoch": 0.27, + "learning_rate": 1.81671012603216e-05, + "loss": 0.5491, + "step": 3374 + }, + { + "epoch": 0.28, + "learning_rate": 1.8166558018252935e-05, + "loss": 0.6719, + "step": 3375 + }, + { + "epoch": 0.28, + "learning_rate": 1.816601477618427e-05, + "loss": 0.5695, + "step": 3376 + }, + { + "epoch": 0.28, + "learning_rate": 1.8165471534115603e-05, + "loss": 0.4982, + "step": 3377 + }, + { + "epoch": 0.28, + "learning_rate": 1.8164928292046938e-05, + "loss": 0.4817, + "step": 3378 + }, + { + "epoch": 0.28, + "learning_rate": 1.8164385049978272e-05, + "loss": 0.5911, + "step": 3379 + }, + { + "epoch": 0.28, + "learning_rate": 1.8163841807909606e-05, + "loss": 0.6572, + "step": 3380 + }, + { + "epoch": 0.28, + "learning_rate": 1.816329856584094e-05, + "loss": 0.6026, + "step": 3381 + }, + { + "epoch": 0.28, + "learning_rate": 1.8162755323772274e-05, + "loss": 0.617, + "step": 3382 + }, + { + "epoch": 0.28, + "learning_rate": 1.816221208170361e-05, + "loss": 0.8063, + "step": 3383 + }, + { + "epoch": 0.28, + "learning_rate": 1.8161668839634943e-05, + "loss": 0.58, + "step": 3384 + }, + { + "epoch": 0.28, + "learning_rate": 1.8161125597566277e-05, + "loss": 0.4245, + "step": 3385 + }, + { + "epoch": 0.28, + "learning_rate": 1.816058235549761e-05, + "loss": 0.3334, + "step": 3386 + }, + { + "epoch": 0.28, + "learning_rate": 1.8160039113428946e-05, + "loss": 0.6414, + "step": 3387 + }, + { + "epoch": 0.28, + "learning_rate": 1.815949587136028e-05, + "loss": 0.5406, + "step": 3388 + }, + { + "epoch": 0.28, + "learning_rate": 1.8158952629291614e-05, + "loss": 0.5776, + "step": 3389 + }, + { + "epoch": 0.28, + "learning_rate": 1.815840938722295e-05, + "loss": 0.3988, + "step": 3390 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157866145154283e-05, + "loss": 0.4757, + "step": 3391 + }, + { + "epoch": 0.28, + "learning_rate": 1.8157322903085617e-05, + "loss": 0.5703, + "step": 3392 + }, + { + "epoch": 0.28, + "learning_rate": 1.815677966101695e-05, + "loss": 0.5616, + "step": 3393 + }, + { + "epoch": 0.28, + "learning_rate": 1.8156236418948285e-05, + "loss": 0.5599, + "step": 3394 + }, + { + "epoch": 0.28, + "learning_rate": 1.815569317687962e-05, + "loss": 0.5823, + "step": 3395 + }, + { + "epoch": 0.28, + "learning_rate": 1.8155149934810954e-05, + "loss": 0.5325, + "step": 3396 + }, + { + "epoch": 0.28, + "learning_rate": 1.8154606692742288e-05, + "loss": 0.5051, + "step": 3397 + }, + { + "epoch": 0.28, + "learning_rate": 1.8154063450673622e-05, + "loss": 0.501, + "step": 3398 + }, + { + "epoch": 0.28, + "learning_rate": 1.8153520208604956e-05, + "loss": 0.5085, + "step": 3399 + }, + { + "epoch": 0.28, + "learning_rate": 1.815297696653629e-05, + "loss": 0.7633, + "step": 3400 + }, + { + "epoch": 0.28, + "learning_rate": 1.8152433724467625e-05, + "loss": 0.3958, + "step": 3401 + }, + { + "epoch": 0.28, + "learning_rate": 1.815189048239896e-05, + "loss": 0.5103, + "step": 3402 + }, + { + "epoch": 0.28, + "learning_rate": 1.8151347240330293e-05, + "loss": 0.3793, + "step": 3403 + }, + { + "epoch": 0.28, + "learning_rate": 1.8150803998261624e-05, + "loss": 0.4646, + "step": 3404 + }, + { + "epoch": 0.28, + "learning_rate": 1.8150260756192962e-05, + "loss": 0.7496, + "step": 3405 + }, + { + "epoch": 0.28, + "learning_rate": 1.8149717514124293e-05, + "loss": 0.5489, + "step": 3406 + }, + { + "epoch": 0.28, + "learning_rate": 1.814917427205563e-05, + "loss": 0.6024, + "step": 3407 + }, + { + "epoch": 0.28, + "learning_rate": 1.8148631029986964e-05, + "loss": 0.4801, + "step": 3408 + }, + { + "epoch": 0.28, + "learning_rate": 1.81480877879183e-05, + "loss": 0.732, + "step": 3409 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147544545849633e-05, + "loss": 0.4818, + "step": 3410 + }, + { + "epoch": 0.28, + "learning_rate": 1.8147001303780967e-05, + "loss": 0.671, + "step": 3411 + }, + { + "epoch": 0.28, + "learning_rate": 1.81464580617123e-05, + "loss": 0.4529, + "step": 3412 + }, + { + "epoch": 0.28, + "learning_rate": 1.8145914819643636e-05, + "loss": 0.4787, + "step": 3413 + }, + { + "epoch": 0.28, + "learning_rate": 1.814537157757497e-05, + "loss": 0.5582, + "step": 3414 + }, + { + "epoch": 0.28, + "learning_rate": 1.8144828335506304e-05, + "loss": 0.4894, + "step": 3415 + }, + { + "epoch": 0.28, + "learning_rate": 1.814428509343764e-05, + "loss": 0.5706, + "step": 3416 + }, + { + "epoch": 0.28, + "learning_rate": 1.8143741851368973e-05, + "loss": 0.4236, + "step": 3417 + }, + { + "epoch": 0.28, + "learning_rate": 1.8143198609300307e-05, + "loss": 0.8371, + "step": 3418 + }, + { + "epoch": 0.28, + "learning_rate": 1.814265536723164e-05, + "loss": 0.7089, + "step": 3419 + }, + { + "epoch": 0.28, + "learning_rate": 1.8142112125162975e-05, + "loss": 0.4115, + "step": 3420 + }, + { + "epoch": 0.28, + "learning_rate": 1.814156888309431e-05, + "loss": 0.6956, + "step": 3421 + }, + { + "epoch": 0.28, + "learning_rate": 1.8141025641025644e-05, + "loss": 0.5271, + "step": 3422 + }, + { + "epoch": 0.28, + "learning_rate": 1.8140482398956975e-05, + "loss": 0.5836, + "step": 3423 + }, + { + "epoch": 0.28, + "learning_rate": 1.8139939156888312e-05, + "loss": 0.6959, + "step": 3424 + }, + { + "epoch": 0.28, + "learning_rate": 1.8139395914819643e-05, + "loss": 0.5395, + "step": 3425 + }, + { + "epoch": 0.28, + "learning_rate": 1.813885267275098e-05, + "loss": 0.4822, + "step": 3426 + }, + { + "epoch": 0.28, + "learning_rate": 1.813830943068231e-05, + "loss": 0.5624, + "step": 3427 + }, + { + "epoch": 0.28, + "learning_rate": 1.813776618861365e-05, + "loss": 0.7054, + "step": 3428 + }, + { + "epoch": 0.28, + "learning_rate": 1.813722294654498e-05, + "loss": 0.4312, + "step": 3429 + }, + { + "epoch": 0.28, + "learning_rate": 1.8136679704476318e-05, + "loss": 0.679, + "step": 3430 + }, + { + "epoch": 0.28, + "learning_rate": 1.813613646240765e-05, + "loss": 0.5435, + "step": 3431 + }, + { + "epoch": 0.28, + "learning_rate": 1.8135593220338986e-05, + "loss": 0.3477, + "step": 3432 + }, + { + "epoch": 0.28, + "learning_rate": 1.8135049978270317e-05, + "loss": 0.3187, + "step": 3433 + }, + { + "epoch": 0.28, + "learning_rate": 1.8134506736201654e-05, + "loss": 0.5842, + "step": 3434 + }, + { + "epoch": 0.28, + "learning_rate": 1.8133963494132985e-05, + "loss": 0.4783, + "step": 3435 + }, + { + "epoch": 0.28, + "learning_rate": 1.8133420252064323e-05, + "loss": 0.5428, + "step": 3436 + }, + { + "epoch": 0.28, + "learning_rate": 1.8132877009995654e-05, + "loss": 0.3252, + "step": 3437 + }, + { + "epoch": 0.28, + "learning_rate": 1.813233376792699e-05, + "loss": 0.3652, + "step": 3438 + }, + { + "epoch": 0.28, + "learning_rate": 1.8131790525858322e-05, + "loss": 0.7247, + "step": 3439 + }, + { + "epoch": 0.28, + "learning_rate": 1.813124728378966e-05, + "loss": 0.5564, + "step": 3440 + }, + { + "epoch": 0.28, + "learning_rate": 1.813070404172099e-05, + "loss": 0.373, + "step": 3441 + }, + { + "epoch": 0.28, + "learning_rate": 1.8130160799652325e-05, + "loss": 0.7406, + "step": 3442 + }, + { + "epoch": 0.28, + "learning_rate": 1.812961755758366e-05, + "loss": 0.5664, + "step": 3443 + }, + { + "epoch": 0.28, + "learning_rate": 1.8129074315514993e-05, + "loss": 0.7213, + "step": 3444 + }, + { + "epoch": 0.28, + "learning_rate": 1.812853107344633e-05, + "loss": 0.346, + "step": 3445 + }, + { + "epoch": 0.28, + "learning_rate": 1.8127987831377662e-05, + "loss": 0.6527, + "step": 3446 + }, + { + "epoch": 0.28, + "learning_rate": 1.8127444589309e-05, + "loss": 0.7651, + "step": 3447 + }, + { + "epoch": 0.28, + "learning_rate": 1.812690134724033e-05, + "loss": 0.5541, + "step": 3448 + }, + { + "epoch": 0.28, + "learning_rate": 1.8126358105171668e-05, + "loss": 0.5918, + "step": 3449 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125814863103e-05, + "loss": 0.3819, + "step": 3450 + }, + { + "epoch": 0.28, + "learning_rate": 1.8125271621034336e-05, + "loss": 0.7698, + "step": 3451 + }, + { + "epoch": 0.28, + "learning_rate": 1.8124728378965667e-05, + "loss": 0.5706, + "step": 3452 + }, + { + "epoch": 0.28, + "learning_rate": 1.8124185136897005e-05, + "loss": 0.5116, + "step": 3453 + }, + { + "epoch": 0.28, + "learning_rate": 1.8123641894828336e-05, + "loss": 0.5477, + "step": 3454 + }, + { + "epoch": 0.28, + "learning_rate": 1.8123098652759673e-05, + "loss": 0.4163, + "step": 3455 + }, + { + "epoch": 0.28, + "learning_rate": 1.8122555410691004e-05, + "loss": 0.5614, + "step": 3456 + }, + { + "epoch": 0.28, + "learning_rate": 1.8122012168622342e-05, + "loss": 0.5831, + "step": 3457 + }, + { + "epoch": 0.28, + "learning_rate": 1.8121468926553673e-05, + "loss": 0.343, + "step": 3458 + }, + { + "epoch": 0.28, + "learning_rate": 1.812092568448501e-05, + "loss": 0.3698, + "step": 3459 + }, + { + "epoch": 0.28, + "learning_rate": 1.812038244241634e-05, + "loss": 0.5522, + "step": 3460 + }, + { + "epoch": 0.28, + "learning_rate": 1.811983920034768e-05, + "loss": 0.4145, + "step": 3461 + }, + { + "epoch": 0.28, + "learning_rate": 1.811929595827901e-05, + "loss": 0.5246, + "step": 3462 + }, + { + "epoch": 0.28, + "learning_rate": 1.8118752716210344e-05, + "loss": 0.6788, + "step": 3463 + }, + { + "epoch": 0.28, + "learning_rate": 1.8118209474141678e-05, + "loss": 0.6646, + "step": 3464 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117666232073012e-05, + "loss": 0.5635, + "step": 3465 + }, + { + "epoch": 0.28, + "learning_rate": 1.8117122990004346e-05, + "loss": 0.5445, + "step": 3466 + }, + { + "epoch": 0.28, + "learning_rate": 1.811657974793568e-05, + "loss": 0.5574, + "step": 3467 + }, + { + "epoch": 0.28, + "learning_rate": 1.8116036505867015e-05, + "loss": 0.3096, + "step": 3468 + }, + { + "epoch": 0.28, + "learning_rate": 1.811549326379835e-05, + "loss": 0.4796, + "step": 3469 + }, + { + "epoch": 0.28, + "learning_rate": 1.8114950021729683e-05, + "loss": 0.4268, + "step": 3470 + }, + { + "epoch": 0.28, + "learning_rate": 1.8114406779661018e-05, + "loss": 0.4353, + "step": 3471 + }, + { + "epoch": 0.28, + "learning_rate": 1.8113863537592352e-05, + "loss": 0.3881, + "step": 3472 + }, + { + "epoch": 0.28, + "learning_rate": 1.8113320295523686e-05, + "loss": 0.4237, + "step": 3473 + }, + { + "epoch": 0.28, + "learning_rate": 1.811277705345502e-05, + "loss": 0.6235, + "step": 3474 + }, + { + "epoch": 0.28, + "learning_rate": 1.8112233811386355e-05, + "loss": 0.6202, + "step": 3475 + }, + { + "epoch": 0.28, + "learning_rate": 1.811169056931769e-05, + "loss": 0.5719, + "step": 3476 + }, + { + "epoch": 0.28, + "learning_rate": 1.8111147327249023e-05, + "loss": 0.5184, + "step": 3477 + }, + { + "epoch": 0.28, + "learning_rate": 1.8110604085180357e-05, + "loss": 0.6274, + "step": 3478 + }, + { + "epoch": 0.28, + "learning_rate": 1.811006084311169e-05, + "loss": 0.5738, + "step": 3479 + }, + { + "epoch": 0.28, + "learning_rate": 1.8109517601043026e-05, + "loss": 0.9121, + "step": 3480 + }, + { + "epoch": 0.28, + "learning_rate": 1.810897435897436e-05, + "loss": 0.4281, + "step": 3481 + }, + { + "epoch": 0.28, + "learning_rate": 1.8108431116905694e-05, + "loss": 0.3625, + "step": 3482 + }, + { + "epoch": 0.28, + "learning_rate": 1.810788787483703e-05, + "loss": 0.4165, + "step": 3483 + }, + { + "epoch": 0.28, + "learning_rate": 1.8107344632768363e-05, + "loss": 0.4698, + "step": 3484 + }, + { + "epoch": 0.28, + "learning_rate": 1.8106801390699697e-05, + "loss": 0.5699, + "step": 3485 + }, + { + "epoch": 0.28, + "learning_rate": 1.810625814863103e-05, + "loss": 0.6573, + "step": 3486 + }, + { + "epoch": 0.28, + "learning_rate": 1.8105714906562365e-05, + "loss": 0.6817, + "step": 3487 + }, + { + "epoch": 0.28, + "learning_rate": 1.81051716644937e-05, + "loss": 0.4555, + "step": 3488 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104628422425034e-05, + "loss": 0.6155, + "step": 3489 + }, + { + "epoch": 0.28, + "learning_rate": 1.8104085180356368e-05, + "loss": 0.7395, + "step": 3490 + }, + { + "epoch": 0.28, + "learning_rate": 1.8103541938287702e-05, + "loss": 0.4841, + "step": 3491 + }, + { + "epoch": 0.28, + "learning_rate": 1.8102998696219036e-05, + "loss": 0.4489, + "step": 3492 + }, + { + "epoch": 0.28, + "learning_rate": 1.810245545415037e-05, + "loss": 0.468, + "step": 3493 + }, + { + "epoch": 0.28, + "learning_rate": 1.8101912212081705e-05, + "loss": 0.5431, + "step": 3494 + }, + { + "epoch": 0.28, + "learning_rate": 1.810136897001304e-05, + "loss": 0.5702, + "step": 3495 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100825727944373e-05, + "loss": 0.4745, + "step": 3496 + }, + { + "epoch": 0.28, + "learning_rate": 1.8100282485875708e-05, + "loss": 0.3686, + "step": 3497 + }, + { + "epoch": 0.29, + "learning_rate": 1.8099739243807042e-05, + "loss": 0.8084, + "step": 3498 + }, + { + "epoch": 0.29, + "learning_rate": 1.8099196001738376e-05, + "loss": 0.5694, + "step": 3499 + }, + { + "epoch": 0.29, + "learning_rate": 1.809865275966971e-05, + "loss": 0.4598, + "step": 3500 + }, + { + "epoch": 0.29, + "eval_accuracy": 0.8066225165562914, + "eval_loss": 0.4969218075275421, + "eval_runtime": 22.2576, + "eval_samples_per_second": 440.974, + "eval_steps_per_second": 3.459, + "step": 3500 + }, + { + "epoch": 0.29, + "learning_rate": 1.8098109517601045e-05, + "loss": 0.2625, + "step": 3501 + }, + { + "epoch": 0.29, + "learning_rate": 1.809756627553238e-05, + "loss": 0.676, + "step": 3502 + }, + { + "epoch": 0.29, + "learning_rate": 1.8097023033463713e-05, + "loss": 0.6788, + "step": 3503 + }, + { + "epoch": 0.29, + "learning_rate": 1.8096479791395047e-05, + "loss": 0.3782, + "step": 3504 + }, + { + "epoch": 0.29, + "learning_rate": 1.809593654932638e-05, + "loss": 0.4023, + "step": 3505 + }, + { + "epoch": 0.29, + "learning_rate": 1.8095393307257716e-05, + "loss": 0.6728, + "step": 3506 + }, + { + "epoch": 0.29, + "learning_rate": 1.809485006518905e-05, + "loss": 0.6324, + "step": 3507 + }, + { + "epoch": 0.29, + "learning_rate": 1.8094306823120384e-05, + "loss": 0.2798, + "step": 3508 + }, + { + "epoch": 0.29, + "learning_rate": 1.809376358105172e-05, + "loss": 0.6274, + "step": 3509 + }, + { + "epoch": 0.29, + "learning_rate": 1.8093220338983053e-05, + "loss": 0.3852, + "step": 3510 + }, + { + "epoch": 0.29, + "learning_rate": 1.8092677096914387e-05, + "loss": 0.6203, + "step": 3511 + }, + { + "epoch": 0.29, + "learning_rate": 1.809213385484572e-05, + "loss": 0.3675, + "step": 3512 + }, + { + "epoch": 0.29, + "learning_rate": 1.8091590612777055e-05, + "loss": 0.4809, + "step": 3513 + }, + { + "epoch": 0.29, + "learning_rate": 1.809104737070839e-05, + "loss": 0.607, + "step": 3514 + }, + { + "epoch": 0.29, + "learning_rate": 1.8090504128639724e-05, + "loss": 0.8168, + "step": 3515 + }, + { + "epoch": 0.29, + "learning_rate": 1.8089960886571058e-05, + "loss": 0.5426, + "step": 3516 + }, + { + "epoch": 0.29, + "learning_rate": 1.8089417644502392e-05, + "loss": 0.5183, + "step": 3517 + }, + { + "epoch": 0.29, + "learning_rate": 1.8088874402433726e-05, + "loss": 0.4909, + "step": 3518 + }, + { + "epoch": 0.29, + "learning_rate": 1.808833116036506e-05, + "loss": 0.3442, + "step": 3519 + }, + { + "epoch": 0.29, + "learning_rate": 1.8087787918296395e-05, + "loss": 0.4882, + "step": 3520 + }, + { + "epoch": 0.29, + "learning_rate": 1.808724467622773e-05, + "loss": 0.5483, + "step": 3521 + }, + { + "epoch": 0.29, + "learning_rate": 1.8086701434159063e-05, + "loss": 0.4526, + "step": 3522 + }, + { + "epoch": 0.29, + "learning_rate": 1.8086158192090398e-05, + "loss": 0.5854, + "step": 3523 + }, + { + "epoch": 0.29, + "learning_rate": 1.8085614950021732e-05, + "loss": 0.4488, + "step": 3524 + }, + { + "epoch": 0.29, + "learning_rate": 1.8085071707953066e-05, + "loss": 0.7612, + "step": 3525 + }, + { + "epoch": 0.29, + "learning_rate": 1.80845284658844e-05, + "loss": 0.404, + "step": 3526 + }, + { + "epoch": 0.29, + "learning_rate": 1.8083985223815735e-05, + "loss": 0.7118, + "step": 3527 + }, + { + "epoch": 0.29, + "learning_rate": 1.808344198174707e-05, + "loss": 0.4501, + "step": 3528 + }, + { + "epoch": 0.29, + "learning_rate": 1.8082898739678403e-05, + "loss": 0.3789, + "step": 3529 + }, + { + "epoch": 0.29, + "learning_rate": 1.8082355497609737e-05, + "loss": 0.4755, + "step": 3530 + }, + { + "epoch": 0.29, + "learning_rate": 1.808181225554107e-05, + "loss": 0.5142, + "step": 3531 + }, + { + "epoch": 0.29, + "learning_rate": 1.8081269013472406e-05, + "loss": 0.3971, + "step": 3532 + }, + { + "epoch": 0.29, + "learning_rate": 1.808072577140374e-05, + "loss": 0.2099, + "step": 3533 + }, + { + "epoch": 0.29, + "learning_rate": 1.8080182529335074e-05, + "loss": 0.328, + "step": 3534 + }, + { + "epoch": 0.29, + "learning_rate": 1.807963928726641e-05, + "loss": 0.6717, + "step": 3535 + }, + { + "epoch": 0.29, + "learning_rate": 1.8079096045197743e-05, + "loss": 0.6124, + "step": 3536 + }, + { + "epoch": 0.29, + "learning_rate": 1.8078552803129077e-05, + "loss": 0.3655, + "step": 3537 + }, + { + "epoch": 0.29, + "learning_rate": 1.807800956106041e-05, + "loss": 0.7195, + "step": 3538 + }, + { + "epoch": 0.29, + "learning_rate": 1.8077466318991742e-05, + "loss": 0.5318, + "step": 3539 + }, + { + "epoch": 0.29, + "learning_rate": 1.807692307692308e-05, + "loss": 0.5608, + "step": 3540 + }, + { + "epoch": 0.29, + "learning_rate": 1.807637983485441e-05, + "loss": 0.2784, + "step": 3541 + }, + { + "epoch": 0.29, + "learning_rate": 1.8075836592785748e-05, + "loss": 0.4084, + "step": 3542 + }, + { + "epoch": 0.29, + "learning_rate": 1.807529335071708e-05, + "loss": 0.416, + "step": 3543 + }, + { + "epoch": 0.29, + "learning_rate": 1.8074750108648416e-05, + "loss": 0.4879, + "step": 3544 + }, + { + "epoch": 0.29, + "learning_rate": 1.8074206866579747e-05, + "loss": 0.5913, + "step": 3545 + }, + { + "epoch": 0.29, + "learning_rate": 1.8073663624511085e-05, + "loss": 0.7239, + "step": 3546 + }, + { + "epoch": 0.29, + "learning_rate": 1.8073120382442416e-05, + "loss": 0.3055, + "step": 3547 + }, + { + "epoch": 0.29, + "learning_rate": 1.8072577140373753e-05, + "loss": 0.4016, + "step": 3548 + }, + { + "epoch": 0.29, + "learning_rate": 1.8072033898305084e-05, + "loss": 0.6738, + "step": 3549 + }, + { + "epoch": 0.29, + "learning_rate": 1.8071490656236422e-05, + "loss": 0.2997, + "step": 3550 + }, + { + "epoch": 0.29, + "learning_rate": 1.8070947414167753e-05, + "loss": 0.5029, + "step": 3551 + }, + { + "epoch": 0.29, + "learning_rate": 1.807040417209909e-05, + "loss": 0.5266, + "step": 3552 + }, + { + "epoch": 0.29, + "learning_rate": 1.8069860930030425e-05, + "loss": 0.4803, + "step": 3553 + }, + { + "epoch": 0.29, + "learning_rate": 1.806931768796176e-05, + "loss": 0.8447, + "step": 3554 + }, + { + "epoch": 0.29, + "learning_rate": 1.8068774445893093e-05, + "loss": 0.5434, + "step": 3555 + }, + { + "epoch": 0.29, + "learning_rate": 1.8068231203824427e-05, + "loss": 0.4026, + "step": 3556 + }, + { + "epoch": 0.29, + "learning_rate": 1.806768796175576e-05, + "loss": 0.5143, + "step": 3557 + }, + { + "epoch": 0.29, + "learning_rate": 1.8067144719687092e-05, + "loss": 0.5066, + "step": 3558 + }, + { + "epoch": 0.29, + "learning_rate": 1.806660147761843e-05, + "loss": 0.7823, + "step": 3559 + }, + { + "epoch": 0.29, + "learning_rate": 1.806605823554976e-05, + "loss": 0.4599, + "step": 3560 + }, + { + "epoch": 0.29, + "learning_rate": 1.80655149934811e-05, + "loss": 0.6275, + "step": 3561 + }, + { + "epoch": 0.29, + "learning_rate": 1.806497175141243e-05, + "loss": 0.4567, + "step": 3562 + }, + { + "epoch": 0.29, + "learning_rate": 1.8064428509343767e-05, + "loss": 0.5522, + "step": 3563 + }, + { + "epoch": 0.29, + "learning_rate": 1.8063885267275098e-05, + "loss": 0.823, + "step": 3564 + }, + { + "epoch": 0.29, + "learning_rate": 1.8063342025206435e-05, + "loss": 0.7679, + "step": 3565 + }, + { + "epoch": 0.29, + "learning_rate": 1.8062798783137766e-05, + "loss": 0.3999, + "step": 3566 + }, + { + "epoch": 0.29, + "learning_rate": 1.8062255541069104e-05, + "loss": 0.4924, + "step": 3567 + }, + { + "epoch": 0.29, + "learning_rate": 1.8061712299000435e-05, + "loss": 0.5054, + "step": 3568 + }, + { + "epoch": 0.29, + "learning_rate": 1.8061169056931772e-05, + "loss": 0.9253, + "step": 3569 + }, + { + "epoch": 0.29, + "learning_rate": 1.8060625814863103e-05, + "loss": 0.5103, + "step": 3570 + }, + { + "epoch": 0.29, + "learning_rate": 1.806008257279444e-05, + "loss": 0.5126, + "step": 3571 + }, + { + "epoch": 0.29, + "learning_rate": 1.805953933072577e-05, + "loss": 0.5827, + "step": 3572 + }, + { + "epoch": 0.29, + "learning_rate": 1.805899608865711e-05, + "loss": 0.4011, + "step": 3573 + }, + { + "epoch": 0.29, + "learning_rate": 1.805845284658844e-05, + "loss": 0.5389, + "step": 3574 + }, + { + "epoch": 0.29, + "learning_rate": 1.8057909604519778e-05, + "loss": 0.691, + "step": 3575 + }, + { + "epoch": 0.29, + "learning_rate": 1.805736636245111e-05, + "loss": 0.8362, + "step": 3576 + }, + { + "epoch": 0.29, + "learning_rate": 1.8056823120382443e-05, + "loss": 0.4675, + "step": 3577 + }, + { + "epoch": 0.29, + "learning_rate": 1.8056279878313777e-05, + "loss": 0.5239, + "step": 3578 + }, + { + "epoch": 0.29, + "learning_rate": 1.805573663624511e-05, + "loss": 0.4499, + "step": 3579 + }, + { + "epoch": 0.29, + "learning_rate": 1.8055193394176445e-05, + "loss": 0.7236, + "step": 3580 + }, + { + "epoch": 0.29, + "learning_rate": 1.805465015210778e-05, + "loss": 0.482, + "step": 3581 + }, + { + "epoch": 0.29, + "learning_rate": 1.8054106910039114e-05, + "loss": 0.5386, + "step": 3582 + }, + { + "epoch": 0.29, + "learning_rate": 1.8053563667970448e-05, + "loss": 0.6016, + "step": 3583 + }, + { + "epoch": 0.29, + "learning_rate": 1.8053020425901782e-05, + "loss": 0.4907, + "step": 3584 + }, + { + "epoch": 0.29, + "learning_rate": 1.8052477183833116e-05, + "loss": 0.3156, + "step": 3585 + }, + { + "epoch": 0.29, + "learning_rate": 1.805193394176445e-05, + "loss": 0.6306, + "step": 3586 + }, + { + "epoch": 0.29, + "learning_rate": 1.8051390699695785e-05, + "loss": 0.4584, + "step": 3587 + }, + { + "epoch": 0.29, + "learning_rate": 1.805084745762712e-05, + "loss": 0.2971, + "step": 3588 + }, + { + "epoch": 0.29, + "learning_rate": 1.8050304215558453e-05, + "loss": 0.4495, + "step": 3589 + }, + { + "epoch": 0.29, + "learning_rate": 1.804976097348979e-05, + "loss": 0.4496, + "step": 3590 + }, + { + "epoch": 0.29, + "learning_rate": 1.8049217731421122e-05, + "loss": 0.601, + "step": 3591 + }, + { + "epoch": 0.29, + "learning_rate": 1.804867448935246e-05, + "loss": 0.5242, + "step": 3592 + }, + { + "epoch": 0.29, + "learning_rate": 1.804813124728379e-05, + "loss": 0.4067, + "step": 3593 + }, + { + "epoch": 0.29, + "learning_rate": 1.8047588005215128e-05, + "loss": 0.6613, + "step": 3594 + }, + { + "epoch": 0.29, + "learning_rate": 1.804704476314646e-05, + "loss": 0.3777, + "step": 3595 + }, + { + "epoch": 0.29, + "learning_rate": 1.8046501521077793e-05, + "loss": 0.8822, + "step": 3596 + }, + { + "epoch": 0.29, + "learning_rate": 1.8045958279009127e-05, + "loss": 0.5627, + "step": 3597 + }, + { + "epoch": 0.29, + "learning_rate": 1.804541503694046e-05, + "loss": 0.5746, + "step": 3598 + }, + { + "epoch": 0.29, + "learning_rate": 1.8044871794871796e-05, + "loss": 0.3398, + "step": 3599 + }, + { + "epoch": 0.29, + "learning_rate": 1.804432855280313e-05, + "loss": 0.3598, + "step": 3600 + }, + { + "epoch": 0.29, + "learning_rate": 1.8043785310734464e-05, + "loss": 0.3653, + "step": 3601 + }, + { + "epoch": 0.29, + "learning_rate": 1.80432420686658e-05, + "loss": 0.746, + "step": 3602 + }, + { + "epoch": 0.29, + "learning_rate": 1.8042698826597133e-05, + "loss": 0.5196, + "step": 3603 + }, + { + "epoch": 0.29, + "learning_rate": 1.8042155584528467e-05, + "loss": 0.3979, + "step": 3604 + }, + { + "epoch": 0.29, + "learning_rate": 1.80416123424598e-05, + "loss": 0.3809, + "step": 3605 + }, + { + "epoch": 0.29, + "learning_rate": 1.8041069100391135e-05, + "loss": 0.5571, + "step": 3606 + }, + { + "epoch": 0.29, + "learning_rate": 1.804052585832247e-05, + "loss": 0.6797, + "step": 3607 + }, + { + "epoch": 0.29, + "learning_rate": 1.8039982616253804e-05, + "loss": 0.5404, + "step": 3608 + }, + { + "epoch": 0.29, + "learning_rate": 1.8039439374185138e-05, + "loss": 0.5212, + "step": 3609 + }, + { + "epoch": 0.29, + "learning_rate": 1.8038896132116472e-05, + "loss": 0.4823, + "step": 3610 + }, + { + "epoch": 0.29, + "learning_rate": 1.8038352890047806e-05, + "loss": 0.6561, + "step": 3611 + }, + { + "epoch": 0.29, + "learning_rate": 1.803780964797914e-05, + "loss": 0.5865, + "step": 3612 + }, + { + "epoch": 0.29, + "learning_rate": 1.8037266405910475e-05, + "loss": 0.5688, + "step": 3613 + }, + { + "epoch": 0.29, + "learning_rate": 1.803672316384181e-05, + "loss": 0.4812, + "step": 3614 + }, + { + "epoch": 0.29, + "learning_rate": 1.8036179921773143e-05, + "loss": 0.4012, + "step": 3615 + }, + { + "epoch": 0.29, + "learning_rate": 1.8035636679704478e-05, + "loss": 0.3098, + "step": 3616 + }, + { + "epoch": 0.29, + "learning_rate": 1.8035093437635812e-05, + "loss": 0.4129, + "step": 3617 + }, + { + "epoch": 0.29, + "learning_rate": 1.8034550195567146e-05, + "loss": 0.5452, + "step": 3618 + }, + { + "epoch": 0.29, + "learning_rate": 1.803400695349848e-05, + "loss": 0.4647, + "step": 3619 + }, + { + "epoch": 0.29, + "learning_rate": 1.8033463711429815e-05, + "loss": 0.2872, + "step": 3620 + }, + { + "epoch": 0.3, + "learning_rate": 1.803292046936115e-05, + "loss": 0.6244, + "step": 3621 + }, + { + "epoch": 0.3, + "learning_rate": 1.8032377227292483e-05, + "loss": 0.5969, + "step": 3622 + }, + { + "epoch": 0.3, + "learning_rate": 1.8031833985223817e-05, + "loss": 0.7314, + "step": 3623 + }, + { + "epoch": 0.3, + "learning_rate": 1.803129074315515e-05, + "loss": 0.6854, + "step": 3624 + }, + { + "epoch": 0.3, + "learning_rate": 1.8030747501086486e-05, + "loss": 0.6827, + "step": 3625 + }, + { + "epoch": 0.3, + "learning_rate": 1.803020425901782e-05, + "loss": 0.6519, + "step": 3626 + }, + { + "epoch": 0.3, + "learning_rate": 1.8029661016949154e-05, + "loss": 0.3798, + "step": 3627 + }, + { + "epoch": 0.3, + "learning_rate": 1.802911777488049e-05, + "loss": 0.4957, + "step": 3628 + }, + { + "epoch": 0.3, + "learning_rate": 1.8028574532811823e-05, + "loss": 0.725, + "step": 3629 + }, + { + "epoch": 0.3, + "learning_rate": 1.8028031290743157e-05, + "loss": 0.5631, + "step": 3630 + }, + { + "epoch": 0.3, + "learning_rate": 1.802748804867449e-05, + "loss": 0.437, + "step": 3631 + }, + { + "epoch": 0.3, + "learning_rate": 1.8026944806605825e-05, + "loss": 0.4937, + "step": 3632 + }, + { + "epoch": 0.3, + "learning_rate": 1.802640156453716e-05, + "loss": 0.4642, + "step": 3633 + }, + { + "epoch": 0.3, + "learning_rate": 1.8025858322468494e-05, + "loss": 0.533, + "step": 3634 + }, + { + "epoch": 0.3, + "learning_rate": 1.8025315080399828e-05, + "loss": 0.5447, + "step": 3635 + }, + { + "epoch": 0.3, + "learning_rate": 1.8024771838331162e-05, + "loss": 0.651, + "step": 3636 + }, + { + "epoch": 0.3, + "learning_rate": 1.8024228596262496e-05, + "loss": 0.3617, + "step": 3637 + }, + { + "epoch": 0.3, + "learning_rate": 1.802368535419383e-05, + "loss": 0.3827, + "step": 3638 + }, + { + "epoch": 0.3, + "learning_rate": 1.8023142112125165e-05, + "loss": 0.4328, + "step": 3639 + }, + { + "epoch": 0.3, + "learning_rate": 1.80225988700565e-05, + "loss": 0.551, + "step": 3640 + }, + { + "epoch": 0.3, + "learning_rate": 1.8022055627987833e-05, + "loss": 0.5458, + "step": 3641 + }, + { + "epoch": 0.3, + "learning_rate": 1.8021512385919168e-05, + "loss": 0.4288, + "step": 3642 + }, + { + "epoch": 0.3, + "learning_rate": 1.8020969143850502e-05, + "loss": 0.4325, + "step": 3643 + }, + { + "epoch": 0.3, + "learning_rate": 1.8020425901781836e-05, + "loss": 0.6527, + "step": 3644 + }, + { + "epoch": 0.3, + "learning_rate": 1.801988265971317e-05, + "loss": 0.6403, + "step": 3645 + }, + { + "epoch": 0.3, + "learning_rate": 1.8019339417644505e-05, + "loss": 0.6135, + "step": 3646 + }, + { + "epoch": 0.3, + "learning_rate": 1.801879617557584e-05, + "loss": 0.4632, + "step": 3647 + }, + { + "epoch": 0.3, + "learning_rate": 1.8018252933507173e-05, + "loss": 0.3599, + "step": 3648 + }, + { + "epoch": 0.3, + "learning_rate": 1.8017709691438507e-05, + "loss": 0.5192, + "step": 3649 + }, + { + "epoch": 0.3, + "learning_rate": 1.801716644936984e-05, + "loss": 0.7048, + "step": 3650 + }, + { + "epoch": 0.3, + "learning_rate": 1.8016623207301176e-05, + "loss": 0.4636, + "step": 3651 + }, + { + "epoch": 0.3, + "learning_rate": 1.801607996523251e-05, + "loss": 0.524, + "step": 3652 + }, + { + "epoch": 0.3, + "learning_rate": 1.801553672316384e-05, + "loss": 0.306, + "step": 3653 + }, + { + "epoch": 0.3, + "learning_rate": 1.801499348109518e-05, + "loss": 0.5202, + "step": 3654 + }, + { + "epoch": 0.3, + "learning_rate": 1.801445023902651e-05, + "loss": 0.43, + "step": 3655 + }, + { + "epoch": 0.3, + "learning_rate": 1.8013906996957847e-05, + "loss": 0.2709, + "step": 3656 + }, + { + "epoch": 0.3, + "learning_rate": 1.8013363754889178e-05, + "loss": 0.6581, + "step": 3657 + }, + { + "epoch": 0.3, + "learning_rate": 1.8012820512820515e-05, + "loss": 0.3692, + "step": 3658 + }, + { + "epoch": 0.3, + "learning_rate": 1.8012277270751846e-05, + "loss": 0.5974, + "step": 3659 + }, + { + "epoch": 0.3, + "learning_rate": 1.8011734028683184e-05, + "loss": 0.5163, + "step": 3660 + }, + { + "epoch": 0.3, + "learning_rate": 1.8011190786614518e-05, + "loss": 0.4632, + "step": 3661 + }, + { + "epoch": 0.3, + "learning_rate": 1.8010647544545852e-05, + "loss": 0.6375, + "step": 3662 + }, + { + "epoch": 0.3, + "learning_rate": 1.8010104302477186e-05, + "loss": 0.5682, + "step": 3663 + }, + { + "epoch": 0.3, + "learning_rate": 1.800956106040852e-05, + "loss": 0.263, + "step": 3664 + }, + { + "epoch": 0.3, + "learning_rate": 1.8009017818339855e-05, + "loss": 0.7175, + "step": 3665 + }, + { + "epoch": 0.3, + "learning_rate": 1.800847457627119e-05, + "loss": 0.5646, + "step": 3666 + }, + { + "epoch": 0.3, + "learning_rate": 1.8007931334202523e-05, + "loss": 0.6626, + "step": 3667 + }, + { + "epoch": 0.3, + "learning_rate": 1.8007388092133858e-05, + "loss": 0.4304, + "step": 3668 + }, + { + "epoch": 0.3, + "learning_rate": 1.8006844850065192e-05, + "loss": 0.5992, + "step": 3669 + }, + { + "epoch": 0.3, + "learning_rate": 1.8006301607996526e-05, + "loss": 0.4794, + "step": 3670 + }, + { + "epoch": 0.3, + "learning_rate": 1.800575836592786e-05, + "loss": 0.6161, + "step": 3671 + }, + { + "epoch": 0.3, + "learning_rate": 1.800521512385919e-05, + "loss": 0.5448, + "step": 3672 + }, + { + "epoch": 0.3, + "learning_rate": 1.800467188179053e-05, + "loss": 0.4874, + "step": 3673 + }, + { + "epoch": 0.3, + "learning_rate": 1.800412863972186e-05, + "loss": 0.3856, + "step": 3674 + }, + { + "epoch": 0.3, + "learning_rate": 1.8003585397653197e-05, + "loss": 0.2969, + "step": 3675 + }, + { + "epoch": 0.3, + "learning_rate": 1.8003042155584528e-05, + "loss": 0.6395, + "step": 3676 + }, + { + "epoch": 0.3, + "learning_rate": 1.8002498913515866e-05, + "loss": 0.4336, + "step": 3677 + }, + { + "epoch": 0.3, + "learning_rate": 1.8001955671447197e-05, + "loss": 0.544, + "step": 3678 + }, + { + "epoch": 0.3, + "learning_rate": 1.8001412429378534e-05, + "loss": 0.5421, + "step": 3679 + }, + { + "epoch": 0.3, + "learning_rate": 1.8000869187309865e-05, + "loss": 0.6383, + "step": 3680 + }, + { + "epoch": 0.3, + "learning_rate": 1.8000325945241203e-05, + "loss": 0.6923, + "step": 3681 + }, + { + "epoch": 0.3, + "learning_rate": 1.7999782703172533e-05, + "loss": 0.5546, + "step": 3682 + }, + { + "epoch": 0.3, + "learning_rate": 1.799923946110387e-05, + "loss": 0.3692, + "step": 3683 + }, + { + "epoch": 0.3, + "learning_rate": 1.7998696219035202e-05, + "loss": 0.5695, + "step": 3684 + }, + { + "epoch": 0.3, + "learning_rate": 1.799815297696654e-05, + "loss": 0.5819, + "step": 3685 + }, + { + "epoch": 0.3, + "learning_rate": 1.799760973489787e-05, + "loss": 0.4299, + "step": 3686 + }, + { + "epoch": 0.3, + "learning_rate": 1.7997066492829208e-05, + "loss": 0.3263, + "step": 3687 + }, + { + "epoch": 0.3, + "learning_rate": 1.799652325076054e-05, + "loss": 0.4037, + "step": 3688 + }, + { + "epoch": 0.3, + "learning_rate": 1.7995980008691876e-05, + "loss": 0.7236, + "step": 3689 + }, + { + "epoch": 0.3, + "learning_rate": 1.7995436766623207e-05, + "loss": 0.5366, + "step": 3690 + }, + { + "epoch": 0.3, + "learning_rate": 1.799489352455454e-05, + "loss": 0.2934, + "step": 3691 + }, + { + "epoch": 0.3, + "learning_rate": 1.7994350282485876e-05, + "loss": 0.5372, + "step": 3692 + }, + { + "epoch": 0.3, + "learning_rate": 1.799380704041721e-05, + "loss": 0.5837, + "step": 3693 + }, + { + "epoch": 0.3, + "learning_rate": 1.7993263798348544e-05, + "loss": 0.4393, + "step": 3694 + }, + { + "epoch": 0.3, + "learning_rate": 1.799272055627988e-05, + "loss": 0.6043, + "step": 3695 + }, + { + "epoch": 0.3, + "learning_rate": 1.7992177314211213e-05, + "loss": 0.3971, + "step": 3696 + }, + { + "epoch": 0.3, + "learning_rate": 1.7991634072142547e-05, + "loss": 0.7438, + "step": 3697 + }, + { + "epoch": 0.3, + "learning_rate": 1.7991090830073885e-05, + "loss": 0.3898, + "step": 3698 + }, + { + "epoch": 0.3, + "learning_rate": 1.7990547588005215e-05, + "loss": 0.6546, + "step": 3699 + }, + { + "epoch": 0.3, + "learning_rate": 1.7990004345936553e-05, + "loss": 0.5415, + "step": 3700 + }, + { + "epoch": 0.3, + "learning_rate": 1.7989461103867884e-05, + "loss": 0.7291, + "step": 3701 + }, + { + "epoch": 0.3, + "learning_rate": 1.798891786179922e-05, + "loss": 0.7044, + "step": 3702 + }, + { + "epoch": 0.3, + "learning_rate": 1.7988374619730552e-05, + "loss": 0.5966, + "step": 3703 + }, + { + "epoch": 0.3, + "learning_rate": 1.798783137766189e-05, + "loss": 0.4958, + "step": 3704 + }, + { + "epoch": 0.3, + "learning_rate": 1.798728813559322e-05, + "loss": 0.4084, + "step": 3705 + }, + { + "epoch": 0.3, + "learning_rate": 1.798674489352456e-05, + "loss": 0.4257, + "step": 3706 + }, + { + "epoch": 0.3, + "learning_rate": 1.798620165145589e-05, + "loss": 0.2888, + "step": 3707 + }, + { + "epoch": 0.3, + "learning_rate": 1.7985658409387227e-05, + "loss": 0.488, + "step": 3708 + }, + { + "epoch": 0.3, + "learning_rate": 1.7985115167318558e-05, + "loss": 0.5646, + "step": 3709 + }, + { + "epoch": 0.3, + "learning_rate": 1.7984571925249892e-05, + "loss": 0.5148, + "step": 3710 + }, + { + "epoch": 0.3, + "learning_rate": 1.7984028683181226e-05, + "loss": 0.453, + "step": 3711 + }, + { + "epoch": 0.3, + "learning_rate": 1.798348544111256e-05, + "loss": 0.7319, + "step": 3712 + }, + { + "epoch": 0.3, + "learning_rate": 1.7982942199043895e-05, + "loss": 0.5937, + "step": 3713 + }, + { + "epoch": 0.3, + "learning_rate": 1.798239895697523e-05, + "loss": 0.4693, + "step": 3714 + }, + { + "epoch": 0.3, + "learning_rate": 1.7981855714906563e-05, + "loss": 0.6747, + "step": 3715 + }, + { + "epoch": 0.3, + "learning_rate": 1.7981312472837897e-05, + "loss": 0.5395, + "step": 3716 + }, + { + "epoch": 0.3, + "learning_rate": 1.798076923076923e-05, + "loss": 0.4731, + "step": 3717 + }, + { + "epoch": 0.3, + "learning_rate": 1.7980225988700566e-05, + "loss": 0.6873, + "step": 3718 + }, + { + "epoch": 0.3, + "learning_rate": 1.79796827466319e-05, + "loss": 0.685, + "step": 3719 + }, + { + "epoch": 0.3, + "learning_rate": 1.7979139504563234e-05, + "loss": 0.3233, + "step": 3720 + }, + { + "epoch": 0.3, + "learning_rate": 1.797859626249457e-05, + "loss": 0.3267, + "step": 3721 + }, + { + "epoch": 0.3, + "learning_rate": 1.7978053020425903e-05, + "loss": 0.5992, + "step": 3722 + }, + { + "epoch": 0.3, + "learning_rate": 1.7977509778357237e-05, + "loss": 0.6026, + "step": 3723 + }, + { + "epoch": 0.3, + "learning_rate": 1.797696653628857e-05, + "loss": 0.712, + "step": 3724 + }, + { + "epoch": 0.3, + "learning_rate": 1.7976423294219905e-05, + "loss": 0.4467, + "step": 3725 + }, + { + "epoch": 0.3, + "learning_rate": 1.797588005215124e-05, + "loss": 0.5015, + "step": 3726 + }, + { + "epoch": 0.3, + "learning_rate": 1.7975336810082574e-05, + "loss": 0.454, + "step": 3727 + }, + { + "epoch": 0.3, + "learning_rate": 1.7974793568013908e-05, + "loss": 0.5816, + "step": 3728 + }, + { + "epoch": 0.3, + "learning_rate": 1.7974250325945242e-05, + "loss": 0.5111, + "step": 3729 + }, + { + "epoch": 0.3, + "learning_rate": 1.7973707083876577e-05, + "loss": 0.361, + "step": 3730 + }, + { + "epoch": 0.3, + "learning_rate": 1.797316384180791e-05, + "loss": 0.4799, + "step": 3731 + }, + { + "epoch": 0.3, + "learning_rate": 1.7972620599739245e-05, + "loss": 0.4298, + "step": 3732 + }, + { + "epoch": 0.3, + "learning_rate": 1.797207735767058e-05, + "loss": 0.6727, + "step": 3733 + }, + { + "epoch": 0.3, + "learning_rate": 1.7971534115601913e-05, + "loss": 0.3718, + "step": 3734 + }, + { + "epoch": 0.3, + "learning_rate": 1.7970990873533248e-05, + "loss": 0.3941, + "step": 3735 + }, + { + "epoch": 0.3, + "learning_rate": 1.7970447631464582e-05, + "loss": 0.4713, + "step": 3736 + }, + { + "epoch": 0.3, + "learning_rate": 1.7969904389395916e-05, + "loss": 0.6025, + "step": 3737 + }, + { + "epoch": 0.3, + "learning_rate": 1.796936114732725e-05, + "loss": 0.9216, + "step": 3738 + }, + { + "epoch": 0.3, + "learning_rate": 1.7968817905258585e-05, + "loss": 0.3385, + "step": 3739 + }, + { + "epoch": 0.3, + "learning_rate": 1.796827466318992e-05, + "loss": 0.2385, + "step": 3740 + }, + { + "epoch": 0.3, + "learning_rate": 1.7967731421121253e-05, + "loss": 0.4724, + "step": 3741 + }, + { + "epoch": 0.3, + "learning_rate": 1.7967188179052587e-05, + "loss": 0.3566, + "step": 3742 + }, + { + "epoch": 0.31, + "learning_rate": 1.796664493698392e-05, + "loss": 0.5362, + "step": 3743 + }, + { + "epoch": 0.31, + "learning_rate": 1.7966101694915256e-05, + "loss": 0.7321, + "step": 3744 + }, + { + "epoch": 0.31, + "learning_rate": 1.796555845284659e-05, + "loss": 0.4979, + "step": 3745 + }, + { + "epoch": 0.31, + "learning_rate": 1.7965015210777924e-05, + "loss": 0.427, + "step": 3746 + }, + { + "epoch": 0.31, + "learning_rate": 1.796447196870926e-05, + "loss": 0.4302, + "step": 3747 + }, + { + "epoch": 0.31, + "learning_rate": 1.7963928726640593e-05, + "loss": 0.4179, + "step": 3748 + }, + { + "epoch": 0.31, + "learning_rate": 1.7963385484571927e-05, + "loss": 0.4806, + "step": 3749 + }, + { + "epoch": 0.31, + "learning_rate": 1.796284224250326e-05, + "loss": 0.4404, + "step": 3750 + }, + { + "epoch": 0.31, + "eval_accuracy": 0.8072338257768721, + "eval_loss": 0.4938150644302368, + "eval_runtime": 22.2343, + "eval_samples_per_second": 441.435, + "eval_steps_per_second": 3.463, + "step": 3750 + }, + { + "epoch": 0.31, + "learning_rate": 1.7962299000434595e-05, + "loss": 0.6475, + "step": 3751 + }, + { + "epoch": 0.31, + "learning_rate": 1.796175575836593e-05, + "loss": 0.5464, + "step": 3752 + }, + { + "epoch": 0.31, + "learning_rate": 1.7961212516297264e-05, + "loss": 0.5323, + "step": 3753 + }, + { + "epoch": 0.31, + "learning_rate": 1.7960669274228598e-05, + "loss": 0.4239, + "step": 3754 + }, + { + "epoch": 0.31, + "learning_rate": 1.7960126032159932e-05, + "loss": 0.6122, + "step": 3755 + }, + { + "epoch": 0.31, + "learning_rate": 1.7959582790091267e-05, + "loss": 0.5161, + "step": 3756 + }, + { + "epoch": 0.31, + "learning_rate": 1.79590395480226e-05, + "loss": 0.5457, + "step": 3757 + }, + { + "epoch": 0.31, + "learning_rate": 1.7958496305953935e-05, + "loss": 0.6439, + "step": 3758 + }, + { + "epoch": 0.31, + "learning_rate": 1.795795306388527e-05, + "loss": 0.382, + "step": 3759 + }, + { + "epoch": 0.31, + "learning_rate": 1.7957409821816603e-05, + "loss": 0.6122, + "step": 3760 + }, + { + "epoch": 0.31, + "learning_rate": 1.7956866579747938e-05, + "loss": 0.7424, + "step": 3761 + }, + { + "epoch": 0.31, + "learning_rate": 1.7956323337679272e-05, + "loss": 0.7721, + "step": 3762 + }, + { + "epoch": 0.31, + "learning_rate": 1.7955780095610606e-05, + "loss": 0.4001, + "step": 3763 + }, + { + "epoch": 0.31, + "learning_rate": 1.795523685354194e-05, + "loss": 0.5875, + "step": 3764 + }, + { + "epoch": 0.31, + "learning_rate": 1.7954693611473275e-05, + "loss": 0.4468, + "step": 3765 + }, + { + "epoch": 0.31, + "learning_rate": 1.795415036940461e-05, + "loss": 0.3798, + "step": 3766 + }, + { + "epoch": 0.31, + "learning_rate": 1.795360712733594e-05, + "loss": 0.4602, + "step": 3767 + }, + { + "epoch": 0.31, + "learning_rate": 1.7953063885267277e-05, + "loss": 0.5713, + "step": 3768 + }, + { + "epoch": 0.31, + "learning_rate": 1.795252064319861e-05, + "loss": 0.6057, + "step": 3769 + }, + { + "epoch": 0.31, + "learning_rate": 1.7951977401129946e-05, + "loss": 0.6949, + "step": 3770 + }, + { + "epoch": 0.31, + "learning_rate": 1.795143415906128e-05, + "loss": 0.4029, + "step": 3771 + }, + { + "epoch": 0.31, + "learning_rate": 1.7950890916992614e-05, + "loss": 0.4376, + "step": 3772 + }, + { + "epoch": 0.31, + "learning_rate": 1.795034767492395e-05, + "loss": 0.5646, + "step": 3773 + }, + { + "epoch": 0.31, + "learning_rate": 1.7949804432855283e-05, + "loss": 0.3168, + "step": 3774 + }, + { + "epoch": 0.31, + "learning_rate": 1.7949261190786617e-05, + "loss": 0.7139, + "step": 3775 + }, + { + "epoch": 0.31, + "learning_rate": 1.794871794871795e-05, + "loss": 0.4405, + "step": 3776 + }, + { + "epoch": 0.31, + "learning_rate": 1.7948174706649285e-05, + "loss": 0.5042, + "step": 3777 + }, + { + "epoch": 0.31, + "learning_rate": 1.794763146458062e-05, + "loss": 0.5167, + "step": 3778 + }, + { + "epoch": 0.31, + "learning_rate": 1.7947088222511954e-05, + "loss": 0.4619, + "step": 3779 + }, + { + "epoch": 0.31, + "learning_rate": 1.7946544980443288e-05, + "loss": 0.49, + "step": 3780 + }, + { + "epoch": 0.31, + "learning_rate": 1.7946001738374622e-05, + "loss": 0.4231, + "step": 3781 + }, + { + "epoch": 0.31, + "learning_rate": 1.7945458496305957e-05, + "loss": 0.4385, + "step": 3782 + }, + { + "epoch": 0.31, + "learning_rate": 1.794491525423729e-05, + "loss": 0.3138, + "step": 3783 + }, + { + "epoch": 0.31, + "learning_rate": 1.7944372012168625e-05, + "loss": 0.7074, + "step": 3784 + }, + { + "epoch": 0.31, + "learning_rate": 1.794382877009996e-05, + "loss": 0.6816, + "step": 3785 + }, + { + "epoch": 0.31, + "learning_rate": 1.794328552803129e-05, + "loss": 0.6185, + "step": 3786 + }, + { + "epoch": 0.31, + "learning_rate": 1.7942742285962628e-05, + "loss": 0.3597, + "step": 3787 + }, + { + "epoch": 0.31, + "learning_rate": 1.794219904389396e-05, + "loss": 0.509, + "step": 3788 + }, + { + "epoch": 0.31, + "learning_rate": 1.7941655801825296e-05, + "loss": 0.4701, + "step": 3789 + }, + { + "epoch": 0.31, + "learning_rate": 1.7941112559756627e-05, + "loss": 0.807, + "step": 3790 + }, + { + "epoch": 0.31, + "learning_rate": 1.7940569317687965e-05, + "loss": 0.5579, + "step": 3791 + }, + { + "epoch": 0.31, + "learning_rate": 1.7940026075619295e-05, + "loss": 0.4476, + "step": 3792 + }, + { + "epoch": 0.31, + "learning_rate": 1.7939482833550633e-05, + "loss": 0.6631, + "step": 3793 + }, + { + "epoch": 0.31, + "learning_rate": 1.7938939591481964e-05, + "loss": 0.4353, + "step": 3794 + }, + { + "epoch": 0.31, + "learning_rate": 1.79383963494133e-05, + "loss": 0.5609, + "step": 3795 + }, + { + "epoch": 0.31, + "learning_rate": 1.7937853107344632e-05, + "loss": 0.8445, + "step": 3796 + }, + { + "epoch": 0.31, + "learning_rate": 1.793730986527597e-05, + "loss": 0.5577, + "step": 3797 + }, + { + "epoch": 0.31, + "learning_rate": 1.79367666232073e-05, + "loss": 0.4773, + "step": 3798 + }, + { + "epoch": 0.31, + "learning_rate": 1.793622338113864e-05, + "loss": 0.4452, + "step": 3799 + }, + { + "epoch": 0.31, + "learning_rate": 1.793568013906997e-05, + "loss": 0.464, + "step": 3800 + }, + { + "epoch": 0.31, + "learning_rate": 1.7935136897001307e-05, + "loss": 0.5821, + "step": 3801 + }, + { + "epoch": 0.31, + "learning_rate": 1.7934593654932638e-05, + "loss": 0.536, + "step": 3802 + }, + { + "epoch": 0.31, + "learning_rate": 1.7934050412863975e-05, + "loss": 0.3374, + "step": 3803 + }, + { + "epoch": 0.31, + "learning_rate": 1.7933507170795306e-05, + "loss": 0.531, + "step": 3804 + }, + { + "epoch": 0.31, + "learning_rate": 1.793296392872664e-05, + "loss": 0.6928, + "step": 3805 + }, + { + "epoch": 0.31, + "learning_rate": 1.7932420686657978e-05, + "loss": 0.3818, + "step": 3806 + }, + { + "epoch": 0.31, + "learning_rate": 1.793187744458931e-05, + "loss": 0.3832, + "step": 3807 + }, + { + "epoch": 0.31, + "learning_rate": 1.7931334202520647e-05, + "loss": 0.5346, + "step": 3808 + }, + { + "epoch": 0.31, + "learning_rate": 1.7930790960451977e-05, + "loss": 0.7198, + "step": 3809 + }, + { + "epoch": 0.31, + "learning_rate": 1.7930247718383315e-05, + "loss": 0.3389, + "step": 3810 + }, + { + "epoch": 0.31, + "learning_rate": 1.7929704476314646e-05, + "loss": 0.4174, + "step": 3811 + }, + { + "epoch": 0.31, + "learning_rate": 1.7929161234245983e-05, + "loss": 0.509, + "step": 3812 + }, + { + "epoch": 0.31, + "learning_rate": 1.7928617992177314e-05, + "loss": 0.395, + "step": 3813 + }, + { + "epoch": 0.31, + "learning_rate": 1.7928074750108652e-05, + "loss": 0.4725, + "step": 3814 + }, + { + "epoch": 0.31, + "learning_rate": 1.7927531508039983e-05, + "loss": 0.3216, + "step": 3815 + }, + { + "epoch": 0.31, + "learning_rate": 1.792698826597132e-05, + "loss": 0.5563, + "step": 3816 + }, + { + "epoch": 0.31, + "learning_rate": 1.792644502390265e-05, + "loss": 0.5015, + "step": 3817 + }, + { + "epoch": 0.31, + "learning_rate": 1.792590178183399e-05, + "loss": 0.4622, + "step": 3818 + }, + { + "epoch": 0.31, + "learning_rate": 1.792535853976532e-05, + "loss": 0.3352, + "step": 3819 + }, + { + "epoch": 0.31, + "learning_rate": 1.7924815297696657e-05, + "loss": 0.4575, + "step": 3820 + }, + { + "epoch": 0.31, + "learning_rate": 1.7924272055627988e-05, + "loss": 0.5917, + "step": 3821 + }, + { + "epoch": 0.31, + "learning_rate": 1.7923728813559326e-05, + "loss": 0.2581, + "step": 3822 + }, + { + "epoch": 0.31, + "learning_rate": 1.7923185571490657e-05, + "loss": 0.6434, + "step": 3823 + }, + { + "epoch": 0.31, + "learning_rate": 1.792264232942199e-05, + "loss": 0.369, + "step": 3824 + }, + { + "epoch": 0.31, + "learning_rate": 1.7922099087353325e-05, + "loss": 0.6634, + "step": 3825 + }, + { + "epoch": 0.31, + "learning_rate": 1.792155584528466e-05, + "loss": 0.4741, + "step": 3826 + }, + { + "epoch": 0.31, + "learning_rate": 1.7921012603215994e-05, + "loss": 0.4558, + "step": 3827 + }, + { + "epoch": 0.31, + "learning_rate": 1.7920469361147328e-05, + "loss": 0.4212, + "step": 3828 + }, + { + "epoch": 0.31, + "learning_rate": 1.7919926119078662e-05, + "loss": 0.3865, + "step": 3829 + }, + { + "epoch": 0.31, + "learning_rate": 1.7919382877009996e-05, + "loss": 0.5624, + "step": 3830 + }, + { + "epoch": 0.31, + "learning_rate": 1.791883963494133e-05, + "loss": 0.6067, + "step": 3831 + }, + { + "epoch": 0.31, + "learning_rate": 1.7918296392872665e-05, + "loss": 0.3676, + "step": 3832 + }, + { + "epoch": 0.31, + "learning_rate": 1.7917753150804e-05, + "loss": 0.5364, + "step": 3833 + }, + { + "epoch": 0.31, + "learning_rate": 1.7917209908735333e-05, + "loss": 0.5355, + "step": 3834 + }, + { + "epoch": 0.31, + "learning_rate": 1.7916666666666667e-05, + "loss": 0.5665, + "step": 3835 + }, + { + "epoch": 0.31, + "learning_rate": 1.7916123424598e-05, + "loss": 0.642, + "step": 3836 + }, + { + "epoch": 0.31, + "learning_rate": 1.7915580182529336e-05, + "loss": 0.5747, + "step": 3837 + }, + { + "epoch": 0.31, + "learning_rate": 1.791503694046067e-05, + "loss": 0.6233, + "step": 3838 + }, + { + "epoch": 0.31, + "learning_rate": 1.7914493698392004e-05, + "loss": 0.3744, + "step": 3839 + }, + { + "epoch": 0.31, + "learning_rate": 1.791395045632334e-05, + "loss": 0.4707, + "step": 3840 + }, + { + "epoch": 0.31, + "learning_rate": 1.7913407214254676e-05, + "loss": 0.5044, + "step": 3841 + }, + { + "epoch": 0.31, + "learning_rate": 1.7912863972186007e-05, + "loss": 0.6258, + "step": 3842 + }, + { + "epoch": 0.31, + "learning_rate": 1.791232073011734e-05, + "loss": 0.8646, + "step": 3843 + }, + { + "epoch": 0.31, + "learning_rate": 1.7911777488048675e-05, + "loss": 0.5434, + "step": 3844 + }, + { + "epoch": 0.31, + "learning_rate": 1.791123424598001e-05, + "loss": 0.3766, + "step": 3845 + }, + { + "epoch": 0.31, + "learning_rate": 1.7910691003911344e-05, + "loss": 0.3792, + "step": 3846 + }, + { + "epoch": 0.31, + "learning_rate": 1.7910147761842678e-05, + "loss": 0.6583, + "step": 3847 + }, + { + "epoch": 0.31, + "learning_rate": 1.7909604519774012e-05, + "loss": 0.6357, + "step": 3848 + }, + { + "epoch": 0.31, + "learning_rate": 1.7909061277705347e-05, + "loss": 0.5101, + "step": 3849 + }, + { + "epoch": 0.31, + "learning_rate": 1.790851803563668e-05, + "loss": 0.4724, + "step": 3850 + }, + { + "epoch": 0.31, + "learning_rate": 1.7907974793568015e-05, + "loss": 0.5068, + "step": 3851 + }, + { + "epoch": 0.31, + "learning_rate": 1.790743155149935e-05, + "loss": 0.5508, + "step": 3852 + }, + { + "epoch": 0.31, + "learning_rate": 1.7906888309430684e-05, + "loss": 0.4791, + "step": 3853 + }, + { + "epoch": 0.31, + "learning_rate": 1.7906345067362018e-05, + "loss": 0.8354, + "step": 3854 + }, + { + "epoch": 0.31, + "learning_rate": 1.7905801825293352e-05, + "loss": 0.366, + "step": 3855 + }, + { + "epoch": 0.31, + "learning_rate": 1.7905258583224686e-05, + "loss": 0.3776, + "step": 3856 + }, + { + "epoch": 0.31, + "learning_rate": 1.790471534115602e-05, + "loss": 0.6483, + "step": 3857 + }, + { + "epoch": 0.31, + "learning_rate": 1.7904172099087355e-05, + "loss": 0.717, + "step": 3858 + }, + { + "epoch": 0.31, + "learning_rate": 1.790362885701869e-05, + "loss": 0.6036, + "step": 3859 + }, + { + "epoch": 0.31, + "learning_rate": 1.7903085614950023e-05, + "loss": 0.6303, + "step": 3860 + }, + { + "epoch": 0.31, + "learning_rate": 1.7902542372881357e-05, + "loss": 0.3405, + "step": 3861 + }, + { + "epoch": 0.31, + "learning_rate": 1.790199913081269e-05, + "loss": 0.5899, + "step": 3862 + }, + { + "epoch": 0.31, + "learning_rate": 1.7901455888744026e-05, + "loss": 0.39, + "step": 3863 + }, + { + "epoch": 0.31, + "learning_rate": 1.790091264667536e-05, + "loss": 0.3912, + "step": 3864 + }, + { + "epoch": 0.31, + "learning_rate": 1.7900369404606694e-05, + "loss": 0.517, + "step": 3865 + }, + { + "epoch": 0.32, + "learning_rate": 1.789982616253803e-05, + "loss": 0.5129, + "step": 3866 + }, + { + "epoch": 0.32, + "learning_rate": 1.7899282920469363e-05, + "loss": 0.464, + "step": 3867 + }, + { + "epoch": 0.32, + "learning_rate": 1.7898739678400697e-05, + "loss": 0.5164, + "step": 3868 + }, + { + "epoch": 0.32, + "learning_rate": 1.789819643633203e-05, + "loss": 0.789, + "step": 3869 + }, + { + "epoch": 0.32, + "learning_rate": 1.7897653194263365e-05, + "loss": 0.5706, + "step": 3870 + }, + { + "epoch": 0.32, + "learning_rate": 1.78971099521947e-05, + "loss": 0.6492, + "step": 3871 + }, + { + "epoch": 0.32, + "learning_rate": 1.7896566710126034e-05, + "loss": 0.5889, + "step": 3872 + }, + { + "epoch": 0.32, + "learning_rate": 1.7896023468057368e-05, + "loss": 0.3872, + "step": 3873 + }, + { + "epoch": 0.32, + "learning_rate": 1.7895480225988702e-05, + "loss": 0.5284, + "step": 3874 + }, + { + "epoch": 0.32, + "learning_rate": 1.7894936983920037e-05, + "loss": 0.3352, + "step": 3875 + }, + { + "epoch": 0.32, + "learning_rate": 1.789439374185137e-05, + "loss": 0.4136, + "step": 3876 + }, + { + "epoch": 0.32, + "learning_rate": 1.7893850499782705e-05, + "loss": 0.4974, + "step": 3877 + }, + { + "epoch": 0.32, + "learning_rate": 1.789330725771404e-05, + "loss": 0.613, + "step": 3878 + }, + { + "epoch": 0.32, + "learning_rate": 1.7892764015645373e-05, + "loss": 0.3119, + "step": 3879 + }, + { + "epoch": 0.32, + "learning_rate": 1.7892220773576708e-05, + "loss": 0.3764, + "step": 3880 + }, + { + "epoch": 0.32, + "learning_rate": 1.7891677531508042e-05, + "loss": 0.5222, + "step": 3881 + }, + { + "epoch": 0.32, + "learning_rate": 1.7891134289439376e-05, + "loss": 0.3175, + "step": 3882 + }, + { + "epoch": 0.32, + "learning_rate": 1.789059104737071e-05, + "loss": 0.3865, + "step": 3883 + }, + { + "epoch": 0.32, + "learning_rate": 1.7890047805302045e-05, + "loss": 0.4799, + "step": 3884 + }, + { + "epoch": 0.32, + "learning_rate": 1.788950456323338e-05, + "loss": 0.5301, + "step": 3885 + }, + { + "epoch": 0.32, + "learning_rate": 1.7888961321164713e-05, + "loss": 0.3433, + "step": 3886 + }, + { + "epoch": 0.32, + "learning_rate": 1.7888418079096047e-05, + "loss": 0.4411, + "step": 3887 + }, + { + "epoch": 0.32, + "learning_rate": 1.788787483702738e-05, + "loss": 0.4288, + "step": 3888 + }, + { + "epoch": 0.32, + "learning_rate": 1.7887331594958716e-05, + "loss": 0.7534, + "step": 3889 + }, + { + "epoch": 0.32, + "learning_rate": 1.788678835289005e-05, + "loss": 0.4919, + "step": 3890 + }, + { + "epoch": 0.32, + "learning_rate": 1.7886245110821384e-05, + "loss": 0.462, + "step": 3891 + }, + { + "epoch": 0.32, + "learning_rate": 1.788570186875272e-05, + "loss": 0.3224, + "step": 3892 + }, + { + "epoch": 0.32, + "learning_rate": 1.7885158626684053e-05, + "loss": 0.67, + "step": 3893 + }, + { + "epoch": 0.32, + "learning_rate": 1.7884615384615387e-05, + "loss": 0.6084, + "step": 3894 + }, + { + "epoch": 0.32, + "learning_rate": 1.788407214254672e-05, + "loss": 0.4205, + "step": 3895 + }, + { + "epoch": 0.32, + "learning_rate": 1.7883528900478055e-05, + "loss": 0.7044, + "step": 3896 + }, + { + "epoch": 0.32, + "learning_rate": 1.788298565840939e-05, + "loss": 0.7777, + "step": 3897 + }, + { + "epoch": 0.32, + "learning_rate": 1.7882442416340724e-05, + "loss": 0.4829, + "step": 3898 + }, + { + "epoch": 0.32, + "learning_rate": 1.7881899174272058e-05, + "loss": 0.4338, + "step": 3899 + }, + { + "epoch": 0.32, + "learning_rate": 1.788135593220339e-05, + "loss": 0.8597, + "step": 3900 + }, + { + "epoch": 0.32, + "learning_rate": 1.7880812690134727e-05, + "loss": 0.4052, + "step": 3901 + }, + { + "epoch": 0.32, + "learning_rate": 1.7880269448066057e-05, + "loss": 0.5825, + "step": 3902 + }, + { + "epoch": 0.32, + "learning_rate": 1.7879726205997395e-05, + "loss": 0.4655, + "step": 3903 + }, + { + "epoch": 0.32, + "learning_rate": 1.7879182963928726e-05, + "loss": 0.4824, + "step": 3904 + }, + { + "epoch": 0.32, + "learning_rate": 1.7878639721860063e-05, + "loss": 0.6283, + "step": 3905 + }, + { + "epoch": 0.32, + "learning_rate": 1.7878096479791394e-05, + "loss": 0.5352, + "step": 3906 + }, + { + "epoch": 0.32, + "learning_rate": 1.7877553237722732e-05, + "loss": 0.5656, + "step": 3907 + }, + { + "epoch": 0.32, + "learning_rate": 1.7877009995654063e-05, + "loss": 0.6399, + "step": 3908 + }, + { + "epoch": 0.32, + "learning_rate": 1.78764667535854e-05, + "loss": 0.4393, + "step": 3909 + }, + { + "epoch": 0.32, + "learning_rate": 1.787592351151673e-05, + "loss": 0.542, + "step": 3910 + }, + { + "epoch": 0.32, + "learning_rate": 1.787538026944807e-05, + "loss": 0.4519, + "step": 3911 + }, + { + "epoch": 0.32, + "learning_rate": 1.78748370273794e-05, + "loss": 0.5236, + "step": 3912 + }, + { + "epoch": 0.32, + "learning_rate": 1.7874293785310737e-05, + "loss": 0.681, + "step": 3913 + }, + { + "epoch": 0.32, + "learning_rate": 1.787375054324207e-05, + "loss": 0.5733, + "step": 3914 + }, + { + "epoch": 0.32, + "learning_rate": 1.7873207301173406e-05, + "loss": 0.3811, + "step": 3915 + }, + { + "epoch": 0.32, + "learning_rate": 1.787266405910474e-05, + "loss": 0.3354, + "step": 3916 + }, + { + "epoch": 0.32, + "learning_rate": 1.7872120817036074e-05, + "loss": 0.4311, + "step": 3917 + }, + { + "epoch": 0.32, + "learning_rate": 1.787157757496741e-05, + "loss": 0.3085, + "step": 3918 + }, + { + "epoch": 0.32, + "learning_rate": 1.787103433289874e-05, + "loss": 0.4614, + "step": 3919 + }, + { + "epoch": 0.32, + "learning_rate": 1.7870491090830077e-05, + "loss": 0.5635, + "step": 3920 + }, + { + "epoch": 0.32, + "learning_rate": 1.7869947848761408e-05, + "loss": 0.3436, + "step": 3921 + }, + { + "epoch": 0.32, + "learning_rate": 1.7869404606692745e-05, + "loss": 0.7294, + "step": 3922 + }, + { + "epoch": 0.32, + "learning_rate": 1.7868861364624076e-05, + "loss": 0.4595, + "step": 3923 + }, + { + "epoch": 0.32, + "learning_rate": 1.7868318122555414e-05, + "loss": 0.5879, + "step": 3924 + }, + { + "epoch": 0.32, + "learning_rate": 1.7867774880486745e-05, + "loss": 0.5286, + "step": 3925 + }, + { + "epoch": 0.32, + "learning_rate": 1.7867231638418082e-05, + "loss": 0.397, + "step": 3926 + }, + { + "epoch": 0.32, + "learning_rate": 1.7866688396349413e-05, + "loss": 0.6006, + "step": 3927 + }, + { + "epoch": 0.32, + "learning_rate": 1.786614515428075e-05, + "loss": 0.6068, + "step": 3928 + }, + { + "epoch": 0.32, + "learning_rate": 1.786560191221208e-05, + "loss": 0.411, + "step": 3929 + }, + { + "epoch": 0.32, + "learning_rate": 1.786505867014342e-05, + "loss": 0.4317, + "step": 3930 + }, + { + "epoch": 0.32, + "learning_rate": 1.786451542807475e-05, + "loss": 0.4347, + "step": 3931 + }, + { + "epoch": 0.32, + "learning_rate": 1.7863972186006088e-05, + "loss": 0.5603, + "step": 3932 + }, + { + "epoch": 0.32, + "learning_rate": 1.786342894393742e-05, + "loss": 0.4514, + "step": 3933 + }, + { + "epoch": 0.32, + "learning_rate": 1.7862885701868756e-05, + "loss": 0.5151, + "step": 3934 + }, + { + "epoch": 0.32, + "learning_rate": 1.7862342459800087e-05, + "loss": 0.5803, + "step": 3935 + }, + { + "epoch": 0.32, + "learning_rate": 1.7861799217731425e-05, + "loss": 0.4903, + "step": 3936 + }, + { + "epoch": 0.32, + "learning_rate": 1.7861255975662755e-05, + "loss": 0.3571, + "step": 3937 + }, + { + "epoch": 0.32, + "learning_rate": 1.786071273359409e-05, + "loss": 0.5432, + "step": 3938 + }, + { + "epoch": 0.32, + "learning_rate": 1.7860169491525424e-05, + "loss": 0.7168, + "step": 3939 + }, + { + "epoch": 0.32, + "learning_rate": 1.7859626249456758e-05, + "loss": 0.6785, + "step": 3940 + }, + { + "epoch": 0.32, + "learning_rate": 1.7859083007388092e-05, + "loss": 0.1738, + "step": 3941 + }, + { + "epoch": 0.32, + "learning_rate": 1.7858539765319427e-05, + "loss": 0.4167, + "step": 3942 + }, + { + "epoch": 0.32, + "learning_rate": 1.785799652325076e-05, + "loss": 0.8224, + "step": 3943 + }, + { + "epoch": 0.32, + "learning_rate": 1.7857453281182095e-05, + "loss": 0.6608, + "step": 3944 + }, + { + "epoch": 0.32, + "learning_rate": 1.785691003911343e-05, + "loss": 0.3301, + "step": 3945 + }, + { + "epoch": 0.32, + "learning_rate": 1.7856366797044764e-05, + "loss": 0.597, + "step": 3946 + }, + { + "epoch": 0.32, + "learning_rate": 1.7855823554976098e-05, + "loss": 0.3474, + "step": 3947 + }, + { + "epoch": 0.32, + "learning_rate": 1.7855280312907432e-05, + "loss": 0.4279, + "step": 3948 + }, + { + "epoch": 0.32, + "learning_rate": 1.785473707083877e-05, + "loss": 0.7043, + "step": 3949 + }, + { + "epoch": 0.32, + "learning_rate": 1.78541938287701e-05, + "loss": 0.5928, + "step": 3950 + }, + { + "epoch": 0.32, + "learning_rate": 1.7853650586701438e-05, + "loss": 0.3209, + "step": 3951 + }, + { + "epoch": 0.32, + "learning_rate": 1.785310734463277e-05, + "loss": 0.5429, + "step": 3952 + }, + { + "epoch": 0.32, + "learning_rate": 1.7852564102564107e-05, + "loss": 0.5398, + "step": 3953 + }, + { + "epoch": 0.32, + "learning_rate": 1.7852020860495437e-05, + "loss": 0.4569, + "step": 3954 + }, + { + "epoch": 0.32, + "learning_rate": 1.7851477618426775e-05, + "loss": 0.4732, + "step": 3955 + }, + { + "epoch": 0.32, + "learning_rate": 1.7850934376358106e-05, + "loss": 0.3701, + "step": 3956 + }, + { + "epoch": 0.32, + "learning_rate": 1.785039113428944e-05, + "loss": 0.5096, + "step": 3957 + }, + { + "epoch": 0.32, + "learning_rate": 1.7849847892220774e-05, + "loss": 0.5014, + "step": 3958 + }, + { + "epoch": 0.32, + "learning_rate": 1.784930465015211e-05, + "loss": 0.3713, + "step": 3959 + }, + { + "epoch": 0.32, + "learning_rate": 1.7848761408083443e-05, + "loss": 0.3743, + "step": 3960 + }, + { + "epoch": 0.32, + "learning_rate": 1.7848218166014777e-05, + "loss": 0.6626, + "step": 3961 + }, + { + "epoch": 0.32, + "learning_rate": 1.784767492394611e-05, + "loss": 0.5929, + "step": 3962 + }, + { + "epoch": 0.32, + "learning_rate": 1.7847131681877445e-05, + "loss": 0.5136, + "step": 3963 + }, + { + "epoch": 0.32, + "learning_rate": 1.784658843980878e-05, + "loss": 0.5022, + "step": 3964 + }, + { + "epoch": 0.32, + "learning_rate": 1.7846045197740114e-05, + "loss": 0.5942, + "step": 3965 + }, + { + "epoch": 0.32, + "learning_rate": 1.7845501955671448e-05, + "loss": 0.6573, + "step": 3966 + }, + { + "epoch": 0.32, + "learning_rate": 1.7844958713602782e-05, + "loss": 0.5841, + "step": 3967 + }, + { + "epoch": 0.32, + "learning_rate": 1.7844415471534117e-05, + "loss": 0.4981, + "step": 3968 + }, + { + "epoch": 0.32, + "learning_rate": 1.784387222946545e-05, + "loss": 0.5475, + "step": 3969 + }, + { + "epoch": 0.32, + "learning_rate": 1.7843328987396785e-05, + "loss": 0.6843, + "step": 3970 + }, + { + "epoch": 0.32, + "learning_rate": 1.784278574532812e-05, + "loss": 0.3739, + "step": 3971 + }, + { + "epoch": 0.32, + "learning_rate": 1.7842242503259454e-05, + "loss": 0.3663, + "step": 3972 + }, + { + "epoch": 0.32, + "learning_rate": 1.7841699261190788e-05, + "loss": 0.6741, + "step": 3973 + }, + { + "epoch": 0.32, + "learning_rate": 1.7841156019122122e-05, + "loss": 0.5444, + "step": 3974 + }, + { + "epoch": 0.32, + "learning_rate": 1.7840612777053456e-05, + "loss": 0.4453, + "step": 3975 + }, + { + "epoch": 0.32, + "learning_rate": 1.784006953498479e-05, + "loss": 0.4256, + "step": 3976 + }, + { + "epoch": 0.32, + "learning_rate": 1.7839526292916125e-05, + "loss": 0.3477, + "step": 3977 + }, + { + "epoch": 0.32, + "learning_rate": 1.783898305084746e-05, + "loss": 0.5012, + "step": 3978 + }, + { + "epoch": 0.32, + "learning_rate": 1.7838439808778793e-05, + "loss": 0.555, + "step": 3979 + }, + { + "epoch": 0.32, + "learning_rate": 1.7837896566710127e-05, + "loss": 0.5376, + "step": 3980 + }, + { + "epoch": 0.32, + "learning_rate": 1.783735332464146e-05, + "loss": 0.4853, + "step": 3981 + }, + { + "epoch": 0.32, + "learning_rate": 1.7836810082572796e-05, + "loss": 0.5846, + "step": 3982 + }, + { + "epoch": 0.32, + "learning_rate": 1.783626684050413e-05, + "loss": 0.6966, + "step": 3983 + }, + { + "epoch": 0.32, + "learning_rate": 1.7835723598435464e-05, + "loss": 0.4667, + "step": 3984 + }, + { + "epoch": 0.32, + "learning_rate": 1.78351803563668e-05, + "loss": 0.4909, + "step": 3985 + }, + { + "epoch": 0.32, + "learning_rate": 1.7834637114298133e-05, + "loss": 0.2287, + "step": 3986 + }, + { + "epoch": 0.32, + "learning_rate": 1.7834093872229467e-05, + "loss": 0.4195, + "step": 3987 + }, + { + "epoch": 0.32, + "learning_rate": 1.78335506301608e-05, + "loss": 0.5309, + "step": 3988 + }, + { + "epoch": 0.33, + "learning_rate": 1.7833007388092135e-05, + "loss": 0.4799, + "step": 3989 + }, + { + "epoch": 0.33, + "learning_rate": 1.783246414602347e-05, + "loss": 0.2895, + "step": 3990 + }, + { + "epoch": 0.33, + "learning_rate": 1.7831920903954804e-05, + "loss": 0.5533, + "step": 3991 + }, + { + "epoch": 0.33, + "learning_rate": 1.7831377661886138e-05, + "loss": 0.5353, + "step": 3992 + }, + { + "epoch": 0.33, + "learning_rate": 1.7830834419817472e-05, + "loss": 0.6804, + "step": 3993 + }, + { + "epoch": 0.33, + "learning_rate": 1.7830291177748807e-05, + "loss": 0.5869, + "step": 3994 + }, + { + "epoch": 0.33, + "learning_rate": 1.782974793568014e-05, + "loss": 0.475, + "step": 3995 + }, + { + "epoch": 0.33, + "learning_rate": 1.7829204693611475e-05, + "loss": 0.495, + "step": 3996 + }, + { + "epoch": 0.33, + "learning_rate": 1.782866145154281e-05, + "loss": 0.3636, + "step": 3997 + }, + { + "epoch": 0.33, + "learning_rate": 1.7828118209474144e-05, + "loss": 0.4146, + "step": 3998 + }, + { + "epoch": 0.33, + "learning_rate": 1.7827574967405478e-05, + "loss": 0.4967, + "step": 3999 + }, + { + "epoch": 0.33, + "learning_rate": 1.7827031725336812e-05, + "loss": 0.5992, + "step": 4000 + }, + { + "epoch": 0.33, + "eval_accuracy": 0.81365257259297, + "eval_loss": 0.4785742163658142, + "eval_runtime": 22.3212, + "eval_samples_per_second": 439.717, + "eval_steps_per_second": 3.45, + "step": 4000 + }, + { + "epoch": 0.33, + "learning_rate": 1.7826488483268146e-05, + "loss": 0.2662, + "step": 4001 + }, + { + "epoch": 0.33, + "learning_rate": 1.782594524119948e-05, + "loss": 0.4388, + "step": 4002 + }, + { + "epoch": 0.33, + "learning_rate": 1.7825401999130815e-05, + "loss": 0.3, + "step": 4003 + }, + { + "epoch": 0.33, + "learning_rate": 1.782485875706215e-05, + "loss": 0.4695, + "step": 4004 + }, + { + "epoch": 0.33, + "learning_rate": 1.7824315514993483e-05, + "loss": 0.4689, + "step": 4005 + }, + { + "epoch": 0.33, + "learning_rate": 1.7823772272924817e-05, + "loss": 0.4399, + "step": 4006 + }, + { + "epoch": 0.33, + "learning_rate": 1.782322903085615e-05, + "loss": 0.3682, + "step": 4007 + }, + { + "epoch": 0.33, + "learning_rate": 1.7822685788787486e-05, + "loss": 0.4885, + "step": 4008 + }, + { + "epoch": 0.33, + "learning_rate": 1.782214254671882e-05, + "loss": 0.4322, + "step": 4009 + }, + { + "epoch": 0.33, + "learning_rate": 1.7821599304650154e-05, + "loss": 0.2914, + "step": 4010 + }, + { + "epoch": 0.33, + "learning_rate": 1.782105606258149e-05, + "loss": 0.3833, + "step": 4011 + }, + { + "epoch": 0.33, + "learning_rate": 1.7820512820512823e-05, + "loss": 0.556, + "step": 4012 + }, + { + "epoch": 0.33, + "learning_rate": 1.7819969578444157e-05, + "loss": 0.673, + "step": 4013 + }, + { + "epoch": 0.33, + "learning_rate": 1.7819426336375488e-05, + "loss": 0.5599, + "step": 4014 + }, + { + "epoch": 0.33, + "learning_rate": 1.7818883094306825e-05, + "loss": 0.4419, + "step": 4015 + }, + { + "epoch": 0.33, + "learning_rate": 1.7818339852238156e-05, + "loss": 0.5431, + "step": 4016 + }, + { + "epoch": 0.33, + "learning_rate": 1.7817796610169494e-05, + "loss": 0.3669, + "step": 4017 + }, + { + "epoch": 0.33, + "learning_rate": 1.7817253368100825e-05, + "loss": 0.2944, + "step": 4018 + }, + { + "epoch": 0.33, + "learning_rate": 1.7816710126032162e-05, + "loss": 0.6446, + "step": 4019 + }, + { + "epoch": 0.33, + "learning_rate": 1.7816166883963493e-05, + "loss": 0.5161, + "step": 4020 + }, + { + "epoch": 0.33, + "learning_rate": 1.781562364189483e-05, + "loss": 0.5906, + "step": 4021 + }, + { + "epoch": 0.33, + "learning_rate": 1.7815080399826165e-05, + "loss": 0.5901, + "step": 4022 + }, + { + "epoch": 0.33, + "learning_rate": 1.78145371577575e-05, + "loss": 0.2928, + "step": 4023 + }, + { + "epoch": 0.33, + "learning_rate": 1.7813993915688834e-05, + "loss": 0.6064, + "step": 4024 + }, + { + "epoch": 0.33, + "learning_rate": 1.7813450673620168e-05, + "loss": 0.7145, + "step": 4025 + }, + { + "epoch": 0.33, + "learning_rate": 1.7812907431551502e-05, + "loss": 0.5903, + "step": 4026 + }, + { + "epoch": 0.33, + "learning_rate": 1.7812364189482836e-05, + "loss": 0.5164, + "step": 4027 + }, + { + "epoch": 0.33, + "learning_rate": 1.781182094741417e-05, + "loss": 0.7166, + "step": 4028 + }, + { + "epoch": 0.33, + "learning_rate": 1.7811277705345505e-05, + "loss": 0.5709, + "step": 4029 + }, + { + "epoch": 0.33, + "learning_rate": 1.781073446327684e-05, + "loss": 0.4496, + "step": 4030 + }, + { + "epoch": 0.33, + "learning_rate": 1.7810191221208173e-05, + "loss": 0.7655, + "step": 4031 + }, + { + "epoch": 0.33, + "learning_rate": 1.7809647979139507e-05, + "loss": 0.615, + "step": 4032 + }, + { + "epoch": 0.33, + "learning_rate": 1.7809104737070838e-05, + "loss": 0.3376, + "step": 4033 + }, + { + "epoch": 0.33, + "learning_rate": 1.7808561495002176e-05, + "loss": 0.4632, + "step": 4034 + }, + { + "epoch": 0.33, + "learning_rate": 1.7808018252933507e-05, + "loss": 0.6507, + "step": 4035 + }, + { + "epoch": 0.33, + "learning_rate": 1.7807475010864844e-05, + "loss": 0.4085, + "step": 4036 + }, + { + "epoch": 0.33, + "learning_rate": 1.7806931768796175e-05, + "loss": 0.5821, + "step": 4037 + }, + { + "epoch": 0.33, + "learning_rate": 1.7806388526727513e-05, + "loss": 0.4246, + "step": 4038 + }, + { + "epoch": 0.33, + "learning_rate": 1.7805845284658844e-05, + "loss": 0.4903, + "step": 4039 + }, + { + "epoch": 0.33, + "learning_rate": 1.780530204259018e-05, + "loss": 0.4922, + "step": 4040 + }, + { + "epoch": 0.33, + "learning_rate": 1.7804758800521512e-05, + "loss": 0.6603, + "step": 4041 + }, + { + "epoch": 0.33, + "learning_rate": 1.780421555845285e-05, + "loss": 0.2982, + "step": 4042 + }, + { + "epoch": 0.33, + "learning_rate": 1.780367231638418e-05, + "loss": 0.6644, + "step": 4043 + }, + { + "epoch": 0.33, + "learning_rate": 1.7803129074315518e-05, + "loss": 0.737, + "step": 4044 + }, + { + "epoch": 0.33, + "learning_rate": 1.780258583224685e-05, + "loss": 0.3891, + "step": 4045 + }, + { + "epoch": 0.33, + "learning_rate": 1.7802042590178187e-05, + "loss": 0.5458, + "step": 4046 + }, + { + "epoch": 0.33, + "learning_rate": 1.7801499348109517e-05, + "loss": 0.4075, + "step": 4047 + }, + { + "epoch": 0.33, + "learning_rate": 1.7800956106040855e-05, + "loss": 0.3739, + "step": 4048 + }, + { + "epoch": 0.33, + "learning_rate": 1.7800412863972186e-05, + "loss": 0.5304, + "step": 4049 + }, + { + "epoch": 0.33, + "learning_rate": 1.7799869621903524e-05, + "loss": 0.54, + "step": 4050 + }, + { + "epoch": 0.33, + "learning_rate": 1.7799326379834854e-05, + "loss": 0.5709, + "step": 4051 + }, + { + "epoch": 0.33, + "learning_rate": 1.779878313776619e-05, + "loss": 0.5588, + "step": 4052 + }, + { + "epoch": 0.33, + "learning_rate": 1.7798239895697523e-05, + "loss": 0.5415, + "step": 4053 + }, + { + "epoch": 0.33, + "learning_rate": 1.7797696653628857e-05, + "loss": 0.472, + "step": 4054 + }, + { + "epoch": 0.33, + "learning_rate": 1.779715341156019e-05, + "loss": 0.6741, + "step": 4055 + }, + { + "epoch": 0.33, + "learning_rate": 1.7796610169491526e-05, + "loss": 0.5637, + "step": 4056 + }, + { + "epoch": 0.33, + "learning_rate": 1.7796066927422863e-05, + "loss": 0.5358, + "step": 4057 + }, + { + "epoch": 0.33, + "learning_rate": 1.7795523685354194e-05, + "loss": 0.2859, + "step": 4058 + }, + { + "epoch": 0.33, + "learning_rate": 1.779498044328553e-05, + "loss": 0.387, + "step": 4059 + }, + { + "epoch": 0.33, + "learning_rate": 1.7794437201216862e-05, + "loss": 0.5289, + "step": 4060 + }, + { + "epoch": 0.33, + "learning_rate": 1.77938939591482e-05, + "loss": 0.6218, + "step": 4061 + }, + { + "epoch": 0.33, + "learning_rate": 1.779335071707953e-05, + "loss": 0.7267, + "step": 4062 + }, + { + "epoch": 0.33, + "learning_rate": 1.779280747501087e-05, + "loss": 0.6462, + "step": 4063 + }, + { + "epoch": 0.33, + "learning_rate": 1.77922642329422e-05, + "loss": 0.5147, + "step": 4064 + }, + { + "epoch": 0.33, + "learning_rate": 1.7791720990873537e-05, + "loss": 0.4238, + "step": 4065 + }, + { + "epoch": 0.33, + "learning_rate": 1.7791177748804868e-05, + "loss": 0.5386, + "step": 4066 + }, + { + "epoch": 0.33, + "learning_rate": 1.7790634506736205e-05, + "loss": 0.4128, + "step": 4067 + }, + { + "epoch": 0.33, + "learning_rate": 1.7790091264667536e-05, + "loss": 0.5198, + "step": 4068 + }, + { + "epoch": 0.33, + "learning_rate": 1.7789548022598874e-05, + "loss": 0.613, + "step": 4069 + }, + { + "epoch": 0.33, + "learning_rate": 1.7789004780530205e-05, + "loss": 0.6249, + "step": 4070 + }, + { + "epoch": 0.33, + "learning_rate": 1.778846153846154e-05, + "loss": 0.3836, + "step": 4071 + }, + { + "epoch": 0.33, + "learning_rate": 1.7787918296392873e-05, + "loss": 0.3971, + "step": 4072 + }, + { + "epoch": 0.33, + "learning_rate": 1.7787375054324207e-05, + "loss": 0.5234, + "step": 4073 + }, + { + "epoch": 0.33, + "learning_rate": 1.778683181225554e-05, + "loss": 0.5275, + "step": 4074 + }, + { + "epoch": 0.33, + "learning_rate": 1.7786288570186876e-05, + "loss": 0.3703, + "step": 4075 + }, + { + "epoch": 0.33, + "learning_rate": 1.778574532811821e-05, + "loss": 0.4106, + "step": 4076 + }, + { + "epoch": 0.33, + "learning_rate": 1.7785202086049544e-05, + "loss": 0.85, + "step": 4077 + }, + { + "epoch": 0.33, + "learning_rate": 1.778465884398088e-05, + "loss": 0.6255, + "step": 4078 + }, + { + "epoch": 0.33, + "learning_rate": 1.7784115601912213e-05, + "loss": 0.5173, + "step": 4079 + }, + { + "epoch": 0.33, + "learning_rate": 1.7783572359843547e-05, + "loss": 0.5258, + "step": 4080 + }, + { + "epoch": 0.33, + "learning_rate": 1.778302911777488e-05, + "loss": 0.5566, + "step": 4081 + }, + { + "epoch": 0.33, + "learning_rate": 1.7782485875706216e-05, + "loss": 0.5963, + "step": 4082 + }, + { + "epoch": 0.33, + "learning_rate": 1.778194263363755e-05, + "loss": 0.3445, + "step": 4083 + }, + { + "epoch": 0.33, + "learning_rate": 1.7781399391568884e-05, + "loss": 0.4993, + "step": 4084 + }, + { + "epoch": 0.33, + "learning_rate": 1.7780856149500218e-05, + "loss": 0.5938, + "step": 4085 + }, + { + "epoch": 0.33, + "learning_rate": 1.7780312907431552e-05, + "loss": 0.5167, + "step": 4086 + }, + { + "epoch": 0.33, + "learning_rate": 1.7779769665362887e-05, + "loss": 0.369, + "step": 4087 + }, + { + "epoch": 0.33, + "learning_rate": 1.777922642329422e-05, + "loss": 0.5851, + "step": 4088 + }, + { + "epoch": 0.33, + "learning_rate": 1.7778683181225555e-05, + "loss": 0.584, + "step": 4089 + }, + { + "epoch": 0.33, + "learning_rate": 1.777813993915689e-05, + "loss": 0.2763, + "step": 4090 + }, + { + "epoch": 0.33, + "learning_rate": 1.7777596697088224e-05, + "loss": 0.6003, + "step": 4091 + }, + { + "epoch": 0.33, + "learning_rate": 1.7777053455019558e-05, + "loss": 0.4688, + "step": 4092 + }, + { + "epoch": 0.33, + "learning_rate": 1.7776510212950892e-05, + "loss": 0.5054, + "step": 4093 + }, + { + "epoch": 0.33, + "learning_rate": 1.7775966970882226e-05, + "loss": 0.4571, + "step": 4094 + }, + { + "epoch": 0.33, + "learning_rate": 1.777542372881356e-05, + "loss": 0.7921, + "step": 4095 + }, + { + "epoch": 0.33, + "learning_rate": 1.7774880486744895e-05, + "loss": 0.3635, + "step": 4096 + }, + { + "epoch": 0.33, + "learning_rate": 1.777433724467623e-05, + "loss": 0.5112, + "step": 4097 + }, + { + "epoch": 0.33, + "learning_rate": 1.7773794002607563e-05, + "loss": 0.2863, + "step": 4098 + }, + { + "epoch": 0.33, + "learning_rate": 1.7773250760538897e-05, + "loss": 0.5993, + "step": 4099 + }, + { + "epoch": 0.33, + "learning_rate": 1.777270751847023e-05, + "loss": 0.8041, + "step": 4100 + }, + { + "epoch": 0.33, + "learning_rate": 1.7772164276401566e-05, + "loss": 0.619, + "step": 4101 + }, + { + "epoch": 0.33, + "learning_rate": 1.77716210343329e-05, + "loss": 0.2548, + "step": 4102 + }, + { + "epoch": 0.33, + "learning_rate": 1.7771077792264234e-05, + "loss": 0.5478, + "step": 4103 + }, + { + "epoch": 0.33, + "learning_rate": 1.777053455019557e-05, + "loss": 0.5783, + "step": 4104 + }, + { + "epoch": 0.33, + "learning_rate": 1.7769991308126903e-05, + "loss": 0.394, + "step": 4105 + }, + { + "epoch": 0.33, + "learning_rate": 1.7769448066058237e-05, + "loss": 0.6283, + "step": 4106 + }, + { + "epoch": 0.33, + "learning_rate": 1.776890482398957e-05, + "loss": 0.6318, + "step": 4107 + }, + { + "epoch": 0.33, + "learning_rate": 1.7768361581920906e-05, + "loss": 0.5189, + "step": 4108 + }, + { + "epoch": 0.33, + "learning_rate": 1.776781833985224e-05, + "loss": 0.4432, + "step": 4109 + }, + { + "epoch": 0.33, + "learning_rate": 1.7767275097783574e-05, + "loss": 0.3891, + "step": 4110 + }, + { + "epoch": 0.33, + "learning_rate": 1.7766731855714908e-05, + "loss": 0.7137, + "step": 4111 + }, + { + "epoch": 0.34, + "learning_rate": 1.7766188613646242e-05, + "loss": 0.4406, + "step": 4112 + }, + { + "epoch": 0.34, + "learning_rate": 1.7765645371577577e-05, + "loss": 0.4276, + "step": 4113 + }, + { + "epoch": 0.34, + "learning_rate": 1.776510212950891e-05, + "loss": 0.2268, + "step": 4114 + }, + { + "epoch": 0.34, + "learning_rate": 1.7764558887440245e-05, + "loss": 0.4657, + "step": 4115 + }, + { + "epoch": 0.34, + "learning_rate": 1.776401564537158e-05, + "loss": 0.5385, + "step": 4116 + }, + { + "epoch": 0.34, + "learning_rate": 1.7763472403302914e-05, + "loss": 0.7901, + "step": 4117 + }, + { + "epoch": 0.34, + "learning_rate": 1.7762929161234248e-05, + "loss": 0.3823, + "step": 4118 + }, + { + "epoch": 0.34, + "learning_rate": 1.7762385919165582e-05, + "loss": 0.5444, + "step": 4119 + }, + { + "epoch": 0.34, + "learning_rate": 1.7761842677096916e-05, + "loss": 0.4919, + "step": 4120 + }, + { + "epoch": 0.34, + "learning_rate": 1.776129943502825e-05, + "loss": 0.7505, + "step": 4121 + }, + { + "epoch": 0.34, + "learning_rate": 1.7760756192959585e-05, + "loss": 0.5295, + "step": 4122 + }, + { + "epoch": 0.34, + "learning_rate": 1.776021295089092e-05, + "loss": 0.4269, + "step": 4123 + }, + { + "epoch": 0.34, + "learning_rate": 1.7759669708822253e-05, + "loss": 0.4628, + "step": 4124 + }, + { + "epoch": 0.34, + "learning_rate": 1.7759126466753587e-05, + "loss": 0.5244, + "step": 4125 + }, + { + "epoch": 0.34, + "learning_rate": 1.775858322468492e-05, + "loss": 0.3202, + "step": 4126 + }, + { + "epoch": 0.34, + "learning_rate": 1.7758039982616256e-05, + "loss": 0.5708, + "step": 4127 + }, + { + "epoch": 0.34, + "learning_rate": 1.7757496740547587e-05, + "loss": 0.531, + "step": 4128 + }, + { + "epoch": 0.34, + "learning_rate": 1.7756953498478924e-05, + "loss": 0.7325, + "step": 4129 + }, + { + "epoch": 0.34, + "learning_rate": 1.775641025641026e-05, + "loss": 0.6545, + "step": 4130 + }, + { + "epoch": 0.34, + "learning_rate": 1.7755867014341593e-05, + "loss": 0.3601, + "step": 4131 + }, + { + "epoch": 0.34, + "learning_rate": 1.7755323772272927e-05, + "loss": 0.5506, + "step": 4132 + }, + { + "epoch": 0.34, + "learning_rate": 1.775478053020426e-05, + "loss": 0.6517, + "step": 4133 + }, + { + "epoch": 0.34, + "learning_rate": 1.7754237288135596e-05, + "loss": 0.4392, + "step": 4134 + }, + { + "epoch": 0.34, + "learning_rate": 1.775369404606693e-05, + "loss": 0.5617, + "step": 4135 + }, + { + "epoch": 0.34, + "learning_rate": 1.7753150803998264e-05, + "loss": 0.4802, + "step": 4136 + }, + { + "epoch": 0.34, + "learning_rate": 1.7752607561929598e-05, + "loss": 0.5658, + "step": 4137 + }, + { + "epoch": 0.34, + "learning_rate": 1.7752064319860932e-05, + "loss": 0.3852, + "step": 4138 + }, + { + "epoch": 0.34, + "learning_rate": 1.7751521077792267e-05, + "loss": 0.63, + "step": 4139 + }, + { + "epoch": 0.34, + "learning_rate": 1.77509778357236e-05, + "loss": 0.338, + "step": 4140 + }, + { + "epoch": 0.34, + "learning_rate": 1.7750434593654935e-05, + "loss": 0.5013, + "step": 4141 + }, + { + "epoch": 0.34, + "learning_rate": 1.774989135158627e-05, + "loss": 0.4497, + "step": 4142 + }, + { + "epoch": 0.34, + "learning_rate": 1.7749348109517604e-05, + "loss": 0.3686, + "step": 4143 + }, + { + "epoch": 0.34, + "learning_rate": 1.7748804867448938e-05, + "loss": 0.6438, + "step": 4144 + }, + { + "epoch": 0.34, + "learning_rate": 1.7748261625380272e-05, + "loss": 0.4166, + "step": 4145 + }, + { + "epoch": 0.34, + "learning_rate": 1.7747718383311606e-05, + "loss": 0.7347, + "step": 4146 + }, + { + "epoch": 0.34, + "learning_rate": 1.7747175141242937e-05, + "loss": 0.6395, + "step": 4147 + }, + { + "epoch": 0.34, + "learning_rate": 1.7746631899174275e-05, + "loss": 0.3858, + "step": 4148 + }, + { + "epoch": 0.34, + "learning_rate": 1.7746088657105606e-05, + "loss": 0.4879, + "step": 4149 + }, + { + "epoch": 0.34, + "learning_rate": 1.7745545415036943e-05, + "loss": 0.5923, + "step": 4150 + }, + { + "epoch": 0.34, + "learning_rate": 1.7745002172968274e-05, + "loss": 0.7848, + "step": 4151 + }, + { + "epoch": 0.34, + "learning_rate": 1.774445893089961e-05, + "loss": 0.3431, + "step": 4152 + }, + { + "epoch": 0.34, + "learning_rate": 1.7743915688830943e-05, + "loss": 0.3546, + "step": 4153 + }, + { + "epoch": 0.34, + "learning_rate": 1.774337244676228e-05, + "loss": 0.5786, + "step": 4154 + }, + { + "epoch": 0.34, + "learning_rate": 1.774282920469361e-05, + "loss": 0.3923, + "step": 4155 + }, + { + "epoch": 0.34, + "learning_rate": 1.774228596262495e-05, + "loss": 0.7648, + "step": 4156 + }, + { + "epoch": 0.34, + "learning_rate": 1.774174272055628e-05, + "loss": 0.4068, + "step": 4157 + }, + { + "epoch": 0.34, + "learning_rate": 1.7741199478487617e-05, + "loss": 0.5347, + "step": 4158 + }, + { + "epoch": 0.34, + "learning_rate": 1.7740656236418948e-05, + "loss": 0.2865, + "step": 4159 + }, + { + "epoch": 0.34, + "learning_rate": 1.7740112994350286e-05, + "loss": 0.675, + "step": 4160 + }, + { + "epoch": 0.34, + "learning_rate": 1.7739569752281616e-05, + "loss": 0.5925, + "step": 4161 + }, + { + "epoch": 0.34, + "learning_rate": 1.7739026510212954e-05, + "loss": 0.5232, + "step": 4162 + }, + { + "epoch": 0.34, + "learning_rate": 1.7738483268144285e-05, + "loss": 0.3373, + "step": 4163 + }, + { + "epoch": 0.34, + "learning_rate": 1.7737940026075622e-05, + "loss": 0.794, + "step": 4164 + }, + { + "epoch": 0.34, + "learning_rate": 1.7737396784006957e-05, + "loss": 0.3701, + "step": 4165 + }, + { + "epoch": 0.34, + "learning_rate": 1.7736853541938288e-05, + "loss": 0.268, + "step": 4166 + }, + { + "epoch": 0.34, + "learning_rate": 1.7736310299869625e-05, + "loss": 0.8179, + "step": 4167 + }, + { + "epoch": 0.34, + "learning_rate": 1.7735767057800956e-05, + "loss": 0.4693, + "step": 4168 + }, + { + "epoch": 0.34, + "learning_rate": 1.7735223815732294e-05, + "loss": 0.3702, + "step": 4169 + }, + { + "epoch": 0.34, + "learning_rate": 1.7734680573663624e-05, + "loss": 0.4101, + "step": 4170 + }, + { + "epoch": 0.34, + "learning_rate": 1.7734137331594962e-05, + "loss": 0.4611, + "step": 4171 + }, + { + "epoch": 0.34, + "learning_rate": 1.7733594089526293e-05, + "loss": 0.421, + "step": 4172 + }, + { + "epoch": 0.34, + "learning_rate": 1.773305084745763e-05, + "loss": 0.3939, + "step": 4173 + }, + { + "epoch": 0.34, + "learning_rate": 1.773250760538896e-05, + "loss": 0.222, + "step": 4174 + }, + { + "epoch": 0.34, + "learning_rate": 1.77319643633203e-05, + "loss": 0.4645, + "step": 4175 + }, + { + "epoch": 0.34, + "learning_rate": 1.773142112125163e-05, + "loss": 0.3916, + "step": 4176 + }, + { + "epoch": 0.34, + "learning_rate": 1.7730877879182967e-05, + "loss": 0.5754, + "step": 4177 + }, + { + "epoch": 0.34, + "learning_rate": 1.7730334637114298e-05, + "loss": 0.4231, + "step": 4178 + }, + { + "epoch": 0.34, + "learning_rate": 1.7729791395045636e-05, + "loss": 0.5713, + "step": 4179 + }, + { + "epoch": 0.34, + "learning_rate": 1.7729248152976967e-05, + "loss": 0.6978, + "step": 4180 + }, + { + "epoch": 0.34, + "learning_rate": 1.7728704910908304e-05, + "loss": 0.4977, + "step": 4181 + }, + { + "epoch": 0.34, + "learning_rate": 1.7728161668839635e-05, + "loss": 0.5184, + "step": 4182 + }, + { + "epoch": 0.34, + "learning_rate": 1.7727618426770973e-05, + "loss": 0.5916, + "step": 4183 + }, + { + "epoch": 0.34, + "learning_rate": 1.7727075184702304e-05, + "loss": 0.3296, + "step": 4184 + }, + { + "epoch": 0.34, + "learning_rate": 1.7726531942633638e-05, + "loss": 0.6037, + "step": 4185 + }, + { + "epoch": 0.34, + "learning_rate": 1.7725988700564972e-05, + "loss": 0.432, + "step": 4186 + }, + { + "epoch": 0.34, + "learning_rate": 1.7725445458496306e-05, + "loss": 0.3018, + "step": 4187 + }, + { + "epoch": 0.34, + "learning_rate": 1.772490221642764e-05, + "loss": 0.6592, + "step": 4188 + }, + { + "epoch": 0.34, + "learning_rate": 1.7724358974358975e-05, + "loss": 0.7003, + "step": 4189 + }, + { + "epoch": 0.34, + "learning_rate": 1.772381573229031e-05, + "loss": 0.4914, + "step": 4190 + }, + { + "epoch": 0.34, + "learning_rate": 1.7723272490221643e-05, + "loss": 0.4561, + "step": 4191 + }, + { + "epoch": 0.34, + "learning_rate": 1.7722729248152977e-05, + "loss": 0.6772, + "step": 4192 + }, + { + "epoch": 0.34, + "learning_rate": 1.7722186006084312e-05, + "loss": 0.6167, + "step": 4193 + }, + { + "epoch": 0.34, + "learning_rate": 1.7721642764015646e-05, + "loss": 0.7473, + "step": 4194 + }, + { + "epoch": 0.34, + "learning_rate": 1.772109952194698e-05, + "loss": 0.6158, + "step": 4195 + }, + { + "epoch": 0.34, + "learning_rate": 1.7720556279878314e-05, + "loss": 0.3933, + "step": 4196 + }, + { + "epoch": 0.34, + "learning_rate": 1.772001303780965e-05, + "loss": 0.4724, + "step": 4197 + }, + { + "epoch": 0.34, + "learning_rate": 1.7719469795740983e-05, + "loss": 0.4396, + "step": 4198 + }, + { + "epoch": 0.34, + "learning_rate": 1.7718926553672317e-05, + "loss": 0.58, + "step": 4199 + }, + { + "epoch": 0.34, + "learning_rate": 1.771838331160365e-05, + "loss": 0.5113, + "step": 4200 + }, + { + "epoch": 0.34, + "learning_rate": 1.7717840069534986e-05, + "loss": 0.3656, + "step": 4201 + }, + { + "epoch": 0.34, + "learning_rate": 1.7717296827466323e-05, + "loss": 0.3613, + "step": 4202 + }, + { + "epoch": 0.34, + "learning_rate": 1.7716753585397654e-05, + "loss": 0.4368, + "step": 4203 + }, + { + "epoch": 0.34, + "learning_rate": 1.7716210343328988e-05, + "loss": 0.4543, + "step": 4204 + }, + { + "epoch": 0.34, + "learning_rate": 1.7715667101260322e-05, + "loss": 0.4514, + "step": 4205 + }, + { + "epoch": 0.34, + "learning_rate": 1.7715123859191657e-05, + "loss": 0.4052, + "step": 4206 + }, + { + "epoch": 0.34, + "learning_rate": 1.771458061712299e-05, + "loss": 0.5385, + "step": 4207 + }, + { + "epoch": 0.34, + "learning_rate": 1.7714037375054325e-05, + "loss": 0.4719, + "step": 4208 + }, + { + "epoch": 0.34, + "learning_rate": 1.771349413298566e-05, + "loss": 0.5187, + "step": 4209 + }, + { + "epoch": 0.34, + "learning_rate": 1.7712950890916994e-05, + "loss": 0.5539, + "step": 4210 + }, + { + "epoch": 0.34, + "learning_rate": 1.7712407648848328e-05, + "loss": 0.4501, + "step": 4211 + }, + { + "epoch": 0.34, + "learning_rate": 1.7711864406779662e-05, + "loss": 0.3796, + "step": 4212 + }, + { + "epoch": 0.34, + "learning_rate": 1.7711321164710996e-05, + "loss": 0.5564, + "step": 4213 + }, + { + "epoch": 0.34, + "learning_rate": 1.771077792264233e-05, + "loss": 0.3225, + "step": 4214 + }, + { + "epoch": 0.34, + "learning_rate": 1.7710234680573665e-05, + "loss": 0.5002, + "step": 4215 + }, + { + "epoch": 0.34, + "learning_rate": 1.7709691438505e-05, + "loss": 0.4965, + "step": 4216 + }, + { + "epoch": 0.34, + "learning_rate": 1.7709148196436333e-05, + "loss": 0.5198, + "step": 4217 + }, + { + "epoch": 0.34, + "learning_rate": 1.7708604954367667e-05, + "loss": 0.423, + "step": 4218 + }, + { + "epoch": 0.34, + "learning_rate": 1.7708061712299002e-05, + "loss": 0.6831, + "step": 4219 + }, + { + "epoch": 0.34, + "learning_rate": 1.7707518470230336e-05, + "loss": 0.5143, + "step": 4220 + }, + { + "epoch": 0.34, + "learning_rate": 1.770697522816167e-05, + "loss": 0.6728, + "step": 4221 + }, + { + "epoch": 0.34, + "learning_rate": 1.7706431986093004e-05, + "loss": 0.4446, + "step": 4222 + }, + { + "epoch": 0.34, + "learning_rate": 1.770588874402434e-05, + "loss": 0.3667, + "step": 4223 + }, + { + "epoch": 0.34, + "learning_rate": 1.7705345501955673e-05, + "loss": 0.4848, + "step": 4224 + }, + { + "epoch": 0.34, + "learning_rate": 1.7704802259887007e-05, + "loss": 0.4187, + "step": 4225 + }, + { + "epoch": 0.34, + "learning_rate": 1.770425901781834e-05, + "loss": 0.8272, + "step": 4226 + }, + { + "epoch": 0.34, + "learning_rate": 1.7703715775749676e-05, + "loss": 0.6151, + "step": 4227 + }, + { + "epoch": 0.34, + "learning_rate": 1.770317253368101e-05, + "loss": 0.3953, + "step": 4228 + }, + { + "epoch": 0.34, + "learning_rate": 1.7702629291612344e-05, + "loss": 0.6986, + "step": 4229 + }, + { + "epoch": 0.34, + "learning_rate": 1.7702086049543678e-05, + "loss": 0.4913, + "step": 4230 + }, + { + "epoch": 0.34, + "learning_rate": 1.7701542807475012e-05, + "loss": 0.5155, + "step": 4231 + }, + { + "epoch": 0.34, + "learning_rate": 1.7700999565406347e-05, + "loss": 0.5995, + "step": 4232 + }, + { + "epoch": 0.34, + "learning_rate": 1.770045632333768e-05, + "loss": 0.3186, + "step": 4233 + }, + { + "epoch": 0.35, + "learning_rate": 1.7699913081269015e-05, + "loss": 0.74, + "step": 4234 + }, + { + "epoch": 0.35, + "learning_rate": 1.769936983920035e-05, + "loss": 0.4741, + "step": 4235 + }, + { + "epoch": 0.35, + "learning_rate": 1.7698826597131684e-05, + "loss": 0.646, + "step": 4236 + }, + { + "epoch": 0.35, + "learning_rate": 1.7698283355063018e-05, + "loss": 0.5757, + "step": 4237 + }, + { + "epoch": 0.35, + "learning_rate": 1.7697740112994352e-05, + "loss": 0.5431, + "step": 4238 + }, + { + "epoch": 0.35, + "learning_rate": 1.7697196870925686e-05, + "loss": 0.499, + "step": 4239 + }, + { + "epoch": 0.35, + "learning_rate": 1.769665362885702e-05, + "loss": 0.4981, + "step": 4240 + }, + { + "epoch": 0.35, + "learning_rate": 1.7696110386788355e-05, + "loss": 0.4682, + "step": 4241 + }, + { + "epoch": 0.35, + "learning_rate": 1.769556714471969e-05, + "loss": 0.7284, + "step": 4242 + }, + { + "epoch": 0.35, + "learning_rate": 1.7695023902651023e-05, + "loss": 0.3942, + "step": 4243 + }, + { + "epoch": 0.35, + "learning_rate": 1.7694480660582357e-05, + "loss": 0.7162, + "step": 4244 + }, + { + "epoch": 0.35, + "learning_rate": 1.7693937418513692e-05, + "loss": 0.4742, + "step": 4245 + }, + { + "epoch": 0.35, + "learning_rate": 1.7693394176445026e-05, + "loss": 0.4855, + "step": 4246 + }, + { + "epoch": 0.35, + "learning_rate": 1.769285093437636e-05, + "loss": 0.6236, + "step": 4247 + }, + { + "epoch": 0.35, + "learning_rate": 1.7692307692307694e-05, + "loss": 0.4904, + "step": 4248 + }, + { + "epoch": 0.35, + "learning_rate": 1.769176445023903e-05, + "loss": 0.714, + "step": 4249 + }, + { + "epoch": 0.35, + "learning_rate": 1.7691221208170363e-05, + "loss": 0.4032, + "step": 4250 + }, + { + "epoch": 0.35, + "eval_accuracy": 0.8154865002547121, + "eval_loss": 0.4664754867553711, + "eval_runtime": 22.276, + "eval_samples_per_second": 440.609, + "eval_steps_per_second": 3.457, + "step": 4250 + }, + { + "epoch": 0.35, + "learning_rate": 1.7690677966101697e-05, + "loss": 0.3246, + "step": 4251 + }, + { + "epoch": 0.35, + "learning_rate": 1.769013472403303e-05, + "loss": 0.6552, + "step": 4252 + }, + { + "epoch": 0.35, + "learning_rate": 1.7689591481964366e-05, + "loss": 0.3591, + "step": 4253 + }, + { + "epoch": 0.35, + "learning_rate": 1.76890482398957e-05, + "loss": 0.5636, + "step": 4254 + }, + { + "epoch": 0.35, + "learning_rate": 1.7688504997827034e-05, + "loss": 0.6245, + "step": 4255 + }, + { + "epoch": 0.35, + "learning_rate": 1.7687961755758368e-05, + "loss": 0.5166, + "step": 4256 + }, + { + "epoch": 0.35, + "learning_rate": 1.7687418513689702e-05, + "loss": 0.6245, + "step": 4257 + }, + { + "epoch": 0.35, + "learning_rate": 1.7686875271621037e-05, + "loss": 0.6144, + "step": 4258 + }, + { + "epoch": 0.35, + "learning_rate": 1.768633202955237e-05, + "loss": 0.4149, + "step": 4259 + }, + { + "epoch": 0.35, + "learning_rate": 1.7685788787483705e-05, + "loss": 0.4591, + "step": 4260 + }, + { + "epoch": 0.35, + "learning_rate": 1.7685245545415036e-05, + "loss": 0.5946, + "step": 4261 + }, + { + "epoch": 0.35, + "learning_rate": 1.7684702303346374e-05, + "loss": 0.3874, + "step": 4262 + }, + { + "epoch": 0.35, + "learning_rate": 1.7684159061277704e-05, + "loss": 0.5838, + "step": 4263 + }, + { + "epoch": 0.35, + "learning_rate": 1.7683615819209042e-05, + "loss": 0.4037, + "step": 4264 + }, + { + "epoch": 0.35, + "learning_rate": 1.7683072577140373e-05, + "loss": 0.4004, + "step": 4265 + }, + { + "epoch": 0.35, + "learning_rate": 1.768252933507171e-05, + "loss": 0.4267, + "step": 4266 + }, + { + "epoch": 0.35, + "learning_rate": 1.768198609300304e-05, + "loss": 0.437, + "step": 4267 + }, + { + "epoch": 0.35, + "learning_rate": 1.768144285093438e-05, + "loss": 0.5878, + "step": 4268 + }, + { + "epoch": 0.35, + "learning_rate": 1.768089960886571e-05, + "loss": 0.7544, + "step": 4269 + }, + { + "epoch": 0.35, + "learning_rate": 1.7680356366797047e-05, + "loss": 0.426, + "step": 4270 + }, + { + "epoch": 0.35, + "learning_rate": 1.767981312472838e-05, + "loss": 0.5678, + "step": 4271 + }, + { + "epoch": 0.35, + "learning_rate": 1.7679269882659716e-05, + "loss": 0.4633, + "step": 4272 + }, + { + "epoch": 0.35, + "learning_rate": 1.767872664059105e-05, + "loss": 0.5255, + "step": 4273 + }, + { + "epoch": 0.35, + "learning_rate": 1.7678183398522384e-05, + "loss": 0.3475, + "step": 4274 + }, + { + "epoch": 0.35, + "learning_rate": 1.767764015645372e-05, + "loss": 0.6262, + "step": 4275 + }, + { + "epoch": 0.35, + "learning_rate": 1.7677096914385053e-05, + "loss": 0.4262, + "step": 4276 + }, + { + "epoch": 0.35, + "learning_rate": 1.7676553672316387e-05, + "loss": 0.4253, + "step": 4277 + }, + { + "epoch": 0.35, + "learning_rate": 1.767601043024772e-05, + "loss": 0.6005, + "step": 4278 + }, + { + "epoch": 0.35, + "learning_rate": 1.7675467188179056e-05, + "loss": 0.4661, + "step": 4279 + }, + { + "epoch": 0.35, + "learning_rate": 1.7674923946110386e-05, + "loss": 0.392, + "step": 4280 + }, + { + "epoch": 0.35, + "learning_rate": 1.7674380704041724e-05, + "loss": 0.5083, + "step": 4281 + }, + { + "epoch": 0.35, + "learning_rate": 1.7673837461973055e-05, + "loss": 0.24, + "step": 4282 + }, + { + "epoch": 0.35, + "learning_rate": 1.7673294219904392e-05, + "loss": 0.9429, + "step": 4283 + }, + { + "epoch": 0.35, + "learning_rate": 1.7672750977835723e-05, + "loss": 0.3051, + "step": 4284 + }, + { + "epoch": 0.35, + "learning_rate": 1.767220773576706e-05, + "loss": 0.4081, + "step": 4285 + }, + { + "epoch": 0.35, + "learning_rate": 1.7671664493698392e-05, + "loss": 0.6263, + "step": 4286 + }, + { + "epoch": 0.35, + "learning_rate": 1.767112125162973e-05, + "loss": 0.5237, + "step": 4287 + }, + { + "epoch": 0.35, + "learning_rate": 1.767057800956106e-05, + "loss": 0.4932, + "step": 4288 + }, + { + "epoch": 0.35, + "learning_rate": 1.7670034767492398e-05, + "loss": 0.576, + "step": 4289 + }, + { + "epoch": 0.35, + "learning_rate": 1.766949152542373e-05, + "loss": 0.5433, + "step": 4290 + }, + { + "epoch": 0.35, + "learning_rate": 1.7668948283355066e-05, + "loss": 0.5956, + "step": 4291 + }, + { + "epoch": 0.35, + "learning_rate": 1.7668405041286397e-05, + "loss": 0.3879, + "step": 4292 + }, + { + "epoch": 0.35, + "learning_rate": 1.7667861799217735e-05, + "loss": 0.4298, + "step": 4293 + }, + { + "epoch": 0.35, + "learning_rate": 1.7667318557149066e-05, + "loss": 0.4997, + "step": 4294 + }, + { + "epoch": 0.35, + "learning_rate": 1.7666775315080403e-05, + "loss": 0.5544, + "step": 4295 + }, + { + "epoch": 0.35, + "learning_rate": 1.7666232073011734e-05, + "loss": 0.4161, + "step": 4296 + }, + { + "epoch": 0.35, + "learning_rate": 1.7665688830943072e-05, + "loss": 0.3633, + "step": 4297 + }, + { + "epoch": 0.35, + "learning_rate": 1.7665145588874403e-05, + "loss": 0.6467, + "step": 4298 + }, + { + "epoch": 0.35, + "learning_rate": 1.7664602346805737e-05, + "loss": 0.505, + "step": 4299 + }, + { + "epoch": 0.35, + "learning_rate": 1.766405910473707e-05, + "loss": 0.4607, + "step": 4300 + }, + { + "epoch": 0.35, + "learning_rate": 1.7663515862668405e-05, + "loss": 0.3398, + "step": 4301 + }, + { + "epoch": 0.35, + "learning_rate": 1.766297262059974e-05, + "loss": 0.3519, + "step": 4302 + }, + { + "epoch": 0.35, + "learning_rate": 1.7662429378531074e-05, + "loss": 0.3051, + "step": 4303 + }, + { + "epoch": 0.35, + "learning_rate": 1.7661886136462408e-05, + "loss": 0.4071, + "step": 4304 + }, + { + "epoch": 0.35, + "learning_rate": 1.7661342894393742e-05, + "loss": 0.504, + "step": 4305 + }, + { + "epoch": 0.35, + "learning_rate": 1.7660799652325076e-05, + "loss": 0.2806, + "step": 4306 + }, + { + "epoch": 0.35, + "learning_rate": 1.766025641025641e-05, + "loss": 0.528, + "step": 4307 + }, + { + "epoch": 0.35, + "learning_rate": 1.7659713168187745e-05, + "loss": 0.3138, + "step": 4308 + }, + { + "epoch": 0.35, + "learning_rate": 1.765916992611908e-05, + "loss": 0.5374, + "step": 4309 + }, + { + "epoch": 0.35, + "learning_rate": 1.7658626684050417e-05, + "loss": 0.4566, + "step": 4310 + }, + { + "epoch": 0.35, + "learning_rate": 1.7658083441981748e-05, + "loss": 0.5154, + "step": 4311 + }, + { + "epoch": 0.35, + "learning_rate": 1.7657540199913085e-05, + "loss": 0.4854, + "step": 4312 + }, + { + "epoch": 0.35, + "learning_rate": 1.7656996957844416e-05, + "loss": 0.671, + "step": 4313 + }, + { + "epoch": 0.35, + "learning_rate": 1.7656453715775754e-05, + "loss": 0.3867, + "step": 4314 + }, + { + "epoch": 0.35, + "learning_rate": 1.7655910473707084e-05, + "loss": 0.3726, + "step": 4315 + }, + { + "epoch": 0.35, + "learning_rate": 1.7655367231638422e-05, + "loss": 0.7369, + "step": 4316 + }, + { + "epoch": 0.35, + "learning_rate": 1.7654823989569753e-05, + "loss": 0.6345, + "step": 4317 + }, + { + "epoch": 0.35, + "learning_rate": 1.7654280747501087e-05, + "loss": 0.5162, + "step": 4318 + }, + { + "epoch": 0.35, + "learning_rate": 1.765373750543242e-05, + "loss": 0.6354, + "step": 4319 + }, + { + "epoch": 0.35, + "learning_rate": 1.7653194263363756e-05, + "loss": 0.4883, + "step": 4320 + }, + { + "epoch": 0.35, + "learning_rate": 1.765265102129509e-05, + "loss": 0.3615, + "step": 4321 + }, + { + "epoch": 0.35, + "learning_rate": 1.7652107779226424e-05, + "loss": 0.6782, + "step": 4322 + }, + { + "epoch": 0.35, + "learning_rate": 1.765156453715776e-05, + "loss": 0.3213, + "step": 4323 + }, + { + "epoch": 0.35, + "learning_rate": 1.7651021295089093e-05, + "loss": 0.6745, + "step": 4324 + }, + { + "epoch": 0.35, + "learning_rate": 1.7650478053020427e-05, + "loss": 0.2999, + "step": 4325 + }, + { + "epoch": 0.35, + "learning_rate": 1.764993481095176e-05, + "loss": 0.157, + "step": 4326 + }, + { + "epoch": 0.35, + "learning_rate": 1.7649391568883095e-05, + "loss": 0.3921, + "step": 4327 + }, + { + "epoch": 0.35, + "learning_rate": 1.764884832681443e-05, + "loss": 0.3057, + "step": 4328 + }, + { + "epoch": 0.35, + "learning_rate": 1.7648305084745764e-05, + "loss": 0.7526, + "step": 4329 + }, + { + "epoch": 0.35, + "learning_rate": 1.7647761842677098e-05, + "loss": 0.3994, + "step": 4330 + }, + { + "epoch": 0.35, + "learning_rate": 1.7647218600608432e-05, + "loss": 0.5343, + "step": 4331 + }, + { + "epoch": 0.35, + "learning_rate": 1.7646675358539766e-05, + "loss": 0.6253, + "step": 4332 + }, + { + "epoch": 0.35, + "learning_rate": 1.76461321164711e-05, + "loss": 0.6404, + "step": 4333 + }, + { + "epoch": 0.35, + "learning_rate": 1.7645588874402435e-05, + "loss": 0.489, + "step": 4334 + }, + { + "epoch": 0.35, + "learning_rate": 1.764504563233377e-05, + "loss": 0.3801, + "step": 4335 + }, + { + "epoch": 0.35, + "learning_rate": 1.7644502390265103e-05, + "loss": 0.5289, + "step": 4336 + }, + { + "epoch": 0.35, + "learning_rate": 1.7643959148196438e-05, + "loss": 0.6552, + "step": 4337 + }, + { + "epoch": 0.35, + "learning_rate": 1.7643415906127772e-05, + "loss": 0.5997, + "step": 4338 + }, + { + "epoch": 0.35, + "learning_rate": 1.7642872664059106e-05, + "loss": 0.4165, + "step": 4339 + }, + { + "epoch": 0.35, + "learning_rate": 1.764232942199044e-05, + "loss": 0.4466, + "step": 4340 + }, + { + "epoch": 0.35, + "learning_rate": 1.7641786179921774e-05, + "loss": 0.4627, + "step": 4341 + }, + { + "epoch": 0.35, + "learning_rate": 1.764124293785311e-05, + "loss": 0.7109, + "step": 4342 + }, + { + "epoch": 0.35, + "learning_rate": 1.7640699695784443e-05, + "loss": 0.3792, + "step": 4343 + }, + { + "epoch": 0.35, + "learning_rate": 1.7640156453715777e-05, + "loss": 0.3939, + "step": 4344 + }, + { + "epoch": 0.35, + "learning_rate": 1.763961321164711e-05, + "loss": 0.5283, + "step": 4345 + }, + { + "epoch": 0.35, + "learning_rate": 1.7639069969578446e-05, + "loss": 0.3277, + "step": 4346 + }, + { + "epoch": 0.35, + "learning_rate": 1.763852672750978e-05, + "loss": 0.4428, + "step": 4347 + }, + { + "epoch": 0.35, + "learning_rate": 1.7637983485441114e-05, + "loss": 0.5552, + "step": 4348 + }, + { + "epoch": 0.35, + "learning_rate": 1.7637440243372448e-05, + "loss": 0.2797, + "step": 4349 + }, + { + "epoch": 0.35, + "learning_rate": 1.7636897001303783e-05, + "loss": 0.5355, + "step": 4350 + }, + { + "epoch": 0.35, + "learning_rate": 1.7636353759235117e-05, + "loss": 0.383, + "step": 4351 + }, + { + "epoch": 0.35, + "learning_rate": 1.763581051716645e-05, + "loss": 0.8322, + "step": 4352 + }, + { + "epoch": 0.35, + "learning_rate": 1.7635267275097785e-05, + "loss": 0.3722, + "step": 4353 + }, + { + "epoch": 0.35, + "learning_rate": 1.763472403302912e-05, + "loss": 0.3637, + "step": 4354 + }, + { + "epoch": 0.35, + "learning_rate": 1.7634180790960454e-05, + "loss": 0.3994, + "step": 4355 + }, + { + "epoch": 0.35, + "learning_rate": 1.7633637548891788e-05, + "loss": 0.5356, + "step": 4356 + }, + { + "epoch": 0.36, + "learning_rate": 1.7633094306823122e-05, + "loss": 0.4439, + "step": 4357 + }, + { + "epoch": 0.36, + "learning_rate": 1.7632551064754456e-05, + "loss": 0.6798, + "step": 4358 + }, + { + "epoch": 0.36, + "learning_rate": 1.763200782268579e-05, + "loss": 0.8139, + "step": 4359 + }, + { + "epoch": 0.36, + "learning_rate": 1.7631464580617125e-05, + "loss": 0.3857, + "step": 4360 + }, + { + "epoch": 0.36, + "learning_rate": 1.763092133854846e-05, + "loss": 0.5056, + "step": 4361 + }, + { + "epoch": 0.36, + "learning_rate": 1.7630378096479793e-05, + "loss": 0.4662, + "step": 4362 + }, + { + "epoch": 0.36, + "learning_rate": 1.7629834854411128e-05, + "loss": 0.5913, + "step": 4363 + }, + { + "epoch": 0.36, + "learning_rate": 1.7629291612342462e-05, + "loss": 0.3042, + "step": 4364 + }, + { + "epoch": 0.36, + "learning_rate": 1.7628748370273796e-05, + "loss": 0.7088, + "step": 4365 + }, + { + "epoch": 0.36, + "learning_rate": 1.762820512820513e-05, + "loss": 0.4093, + "step": 4366 + }, + { + "epoch": 0.36, + "learning_rate": 1.7627661886136464e-05, + "loss": 0.5135, + "step": 4367 + }, + { + "epoch": 0.36, + "learning_rate": 1.76271186440678e-05, + "loss": 0.2455, + "step": 4368 + }, + { + "epoch": 0.36, + "learning_rate": 1.7626575401999133e-05, + "loss": 0.7183, + "step": 4369 + }, + { + "epoch": 0.36, + "learning_rate": 1.7626032159930467e-05, + "loss": 0.6207, + "step": 4370 + }, + { + "epoch": 0.36, + "learning_rate": 1.76254889178618e-05, + "loss": 0.7788, + "step": 4371 + }, + { + "epoch": 0.36, + "learning_rate": 1.7624945675793136e-05, + "loss": 0.5646, + "step": 4372 + }, + { + "epoch": 0.36, + "learning_rate": 1.762440243372447e-05, + "loss": 0.3401, + "step": 4373 + }, + { + "epoch": 0.36, + "learning_rate": 1.7623859191655804e-05, + "loss": 0.5605, + "step": 4374 + }, + { + "epoch": 0.36, + "learning_rate": 1.7623315949587135e-05, + "loss": 0.5222, + "step": 4375 + }, + { + "epoch": 0.36, + "learning_rate": 1.7622772707518473e-05, + "loss": 0.3206, + "step": 4376 + }, + { + "epoch": 0.36, + "learning_rate": 1.7622229465449803e-05, + "loss": 0.5244, + "step": 4377 + }, + { + "epoch": 0.36, + "learning_rate": 1.762168622338114e-05, + "loss": 0.5257, + "step": 4378 + }, + { + "epoch": 0.36, + "learning_rate": 1.7621142981312472e-05, + "loss": 0.4667, + "step": 4379 + }, + { + "epoch": 0.36, + "learning_rate": 1.762059973924381e-05, + "loss": 0.2521, + "step": 4380 + }, + { + "epoch": 0.36, + "learning_rate": 1.7620056497175144e-05, + "loss": 0.3033, + "step": 4381 + }, + { + "epoch": 0.36, + "learning_rate": 1.7619513255106478e-05, + "loss": 0.6226, + "step": 4382 + }, + { + "epoch": 0.36, + "learning_rate": 1.7618970013037812e-05, + "loss": 0.3684, + "step": 4383 + }, + { + "epoch": 0.36, + "learning_rate": 1.7618426770969146e-05, + "loss": 0.459, + "step": 4384 + }, + { + "epoch": 0.36, + "learning_rate": 1.761788352890048e-05, + "loss": 0.6209, + "step": 4385 + }, + { + "epoch": 0.36, + "learning_rate": 1.7617340286831815e-05, + "loss": 0.4887, + "step": 4386 + }, + { + "epoch": 0.36, + "learning_rate": 1.761679704476315e-05, + "loss": 0.3792, + "step": 4387 + }, + { + "epoch": 0.36, + "learning_rate": 1.7616253802694483e-05, + "loss": 0.2639, + "step": 4388 + }, + { + "epoch": 0.36, + "learning_rate": 1.7615710560625818e-05, + "loss": 0.7126, + "step": 4389 + }, + { + "epoch": 0.36, + "learning_rate": 1.7615167318557152e-05, + "loss": 0.6886, + "step": 4390 + }, + { + "epoch": 0.36, + "learning_rate": 1.7614624076488486e-05, + "loss": 0.4437, + "step": 4391 + }, + { + "epoch": 0.36, + "learning_rate": 1.761408083441982e-05, + "loss": 0.7552, + "step": 4392 + }, + { + "epoch": 0.36, + "learning_rate": 1.7613537592351154e-05, + "loss": 0.5427, + "step": 4393 + }, + { + "epoch": 0.36, + "learning_rate": 1.7612994350282485e-05, + "loss": 0.4355, + "step": 4394 + }, + { + "epoch": 0.36, + "learning_rate": 1.7612451108213823e-05, + "loss": 0.3733, + "step": 4395 + }, + { + "epoch": 0.36, + "learning_rate": 1.7611907866145154e-05, + "loss": 0.7262, + "step": 4396 + }, + { + "epoch": 0.36, + "learning_rate": 1.761136462407649e-05, + "loss": 0.5784, + "step": 4397 + }, + { + "epoch": 0.36, + "learning_rate": 1.7610821382007822e-05, + "loss": 0.2061, + "step": 4398 + }, + { + "epoch": 0.36, + "learning_rate": 1.761027813993916e-05, + "loss": 0.4958, + "step": 4399 + }, + { + "epoch": 0.36, + "learning_rate": 1.760973489787049e-05, + "loss": 0.5083, + "step": 4400 + }, + { + "epoch": 0.36, + "learning_rate": 1.7609191655801828e-05, + "loss": 0.5548, + "step": 4401 + }, + { + "epoch": 0.36, + "learning_rate": 1.760864841373316e-05, + "loss": 0.2574, + "step": 4402 + }, + { + "epoch": 0.36, + "learning_rate": 1.7608105171664497e-05, + "loss": 0.6402, + "step": 4403 + }, + { + "epoch": 0.36, + "learning_rate": 1.7607561929595828e-05, + "loss": 0.7168, + "step": 4404 + }, + { + "epoch": 0.36, + "learning_rate": 1.7607018687527165e-05, + "loss": 0.6546, + "step": 4405 + }, + { + "epoch": 0.36, + "learning_rate": 1.7606475445458496e-05, + "loss": 0.6084, + "step": 4406 + }, + { + "epoch": 0.36, + "learning_rate": 1.7605932203389834e-05, + "loss": 0.4615, + "step": 4407 + }, + { + "epoch": 0.36, + "learning_rate": 1.7605388961321165e-05, + "loss": 0.6585, + "step": 4408 + }, + { + "epoch": 0.36, + "learning_rate": 1.7604845719252502e-05, + "loss": 0.5225, + "step": 4409 + }, + { + "epoch": 0.36, + "learning_rate": 1.7604302477183833e-05, + "loss": 0.7317, + "step": 4410 + }, + { + "epoch": 0.36, + "learning_rate": 1.760375923511517e-05, + "loss": 0.665, + "step": 4411 + }, + { + "epoch": 0.36, + "learning_rate": 1.76032159930465e-05, + "loss": 0.5472, + "step": 4412 + }, + { + "epoch": 0.36, + "learning_rate": 1.7602672750977836e-05, + "loss": 0.4985, + "step": 4413 + }, + { + "epoch": 0.36, + "learning_rate": 1.760212950890917e-05, + "loss": 0.4419, + "step": 4414 + }, + { + "epoch": 0.36, + "learning_rate": 1.7601586266840504e-05, + "loss": 0.4309, + "step": 4415 + }, + { + "epoch": 0.36, + "learning_rate": 1.760104302477184e-05, + "loss": 0.5449, + "step": 4416 + }, + { + "epoch": 0.36, + "learning_rate": 1.7600499782703173e-05, + "loss": 0.4407, + "step": 4417 + }, + { + "epoch": 0.36, + "learning_rate": 1.759995654063451e-05, + "loss": 0.4912, + "step": 4418 + }, + { + "epoch": 0.36, + "learning_rate": 1.759941329856584e-05, + "loss": 0.4433, + "step": 4419 + }, + { + "epoch": 0.36, + "learning_rate": 1.759887005649718e-05, + "loss": 0.6426, + "step": 4420 + }, + { + "epoch": 0.36, + "learning_rate": 1.759832681442851e-05, + "loss": 0.7279, + "step": 4421 + }, + { + "epoch": 0.36, + "learning_rate": 1.7597783572359847e-05, + "loss": 0.458, + "step": 4422 + }, + { + "epoch": 0.36, + "learning_rate": 1.7597240330291178e-05, + "loss": 0.4683, + "step": 4423 + }, + { + "epoch": 0.36, + "learning_rate": 1.7596697088222516e-05, + "loss": 0.5051, + "step": 4424 + }, + { + "epoch": 0.36, + "learning_rate": 1.7596153846153846e-05, + "loss": 0.456, + "step": 4425 + }, + { + "epoch": 0.36, + "learning_rate": 1.7595610604085184e-05, + "loss": 0.47, + "step": 4426 + }, + { + "epoch": 0.36, + "learning_rate": 1.7595067362016515e-05, + "loss": 0.6168, + "step": 4427 + }, + { + "epoch": 0.36, + "learning_rate": 1.7594524119947853e-05, + "loss": 0.3716, + "step": 4428 + }, + { + "epoch": 0.36, + "learning_rate": 1.7593980877879183e-05, + "loss": 0.5548, + "step": 4429 + }, + { + "epoch": 0.36, + "learning_rate": 1.759343763581052e-05, + "loss": 0.5198, + "step": 4430 + }, + { + "epoch": 0.36, + "learning_rate": 1.7592894393741852e-05, + "loss": 0.3804, + "step": 4431 + }, + { + "epoch": 0.36, + "learning_rate": 1.7592351151673186e-05, + "loss": 0.4203, + "step": 4432 + }, + { + "epoch": 0.36, + "learning_rate": 1.759180790960452e-05, + "loss": 0.8285, + "step": 4433 + }, + { + "epoch": 0.36, + "learning_rate": 1.7591264667535855e-05, + "loss": 0.3618, + "step": 4434 + }, + { + "epoch": 0.36, + "learning_rate": 1.759072142546719e-05, + "loss": 0.5135, + "step": 4435 + }, + { + "epoch": 0.36, + "learning_rate": 1.7590178183398523e-05, + "loss": 0.5322, + "step": 4436 + }, + { + "epoch": 0.36, + "learning_rate": 1.7589634941329857e-05, + "loss": 0.5718, + "step": 4437 + }, + { + "epoch": 0.36, + "learning_rate": 1.758909169926119e-05, + "loss": 0.3031, + "step": 4438 + }, + { + "epoch": 0.36, + "learning_rate": 1.7588548457192526e-05, + "loss": 0.4506, + "step": 4439 + }, + { + "epoch": 0.36, + "learning_rate": 1.758800521512386e-05, + "loss": 0.3835, + "step": 4440 + }, + { + "epoch": 0.36, + "learning_rate": 1.7587461973055194e-05, + "loss": 0.537, + "step": 4441 + }, + { + "epoch": 0.36, + "learning_rate": 1.758691873098653e-05, + "loss": 0.2446, + "step": 4442 + }, + { + "epoch": 0.36, + "learning_rate": 1.7586375488917863e-05, + "loss": 0.3422, + "step": 4443 + }, + { + "epoch": 0.36, + "learning_rate": 1.7585832246849197e-05, + "loss": 0.5988, + "step": 4444 + }, + { + "epoch": 0.36, + "learning_rate": 1.758528900478053e-05, + "loss": 0.5094, + "step": 4445 + }, + { + "epoch": 0.36, + "learning_rate": 1.7584745762711865e-05, + "loss": 0.383, + "step": 4446 + }, + { + "epoch": 0.36, + "learning_rate": 1.75842025206432e-05, + "loss": 0.6859, + "step": 4447 + }, + { + "epoch": 0.36, + "learning_rate": 1.7583659278574534e-05, + "loss": 0.4054, + "step": 4448 + }, + { + "epoch": 0.36, + "learning_rate": 1.7583116036505868e-05, + "loss": 0.5394, + "step": 4449 + }, + { + "epoch": 0.36, + "learning_rate": 1.7582572794437202e-05, + "loss": 0.5386, + "step": 4450 + }, + { + "epoch": 0.36, + "learning_rate": 1.7582029552368536e-05, + "loss": 0.4158, + "step": 4451 + }, + { + "epoch": 0.36, + "learning_rate": 1.758148631029987e-05, + "loss": 0.6063, + "step": 4452 + }, + { + "epoch": 0.36, + "learning_rate": 1.7580943068231205e-05, + "loss": 0.2578, + "step": 4453 + }, + { + "epoch": 0.36, + "learning_rate": 1.758039982616254e-05, + "loss": 0.4463, + "step": 4454 + }, + { + "epoch": 0.36, + "learning_rate": 1.7579856584093873e-05, + "loss": 0.2651, + "step": 4455 + }, + { + "epoch": 0.36, + "learning_rate": 1.7579313342025208e-05, + "loss": 0.4184, + "step": 4456 + }, + { + "epoch": 0.36, + "learning_rate": 1.7578770099956542e-05, + "loss": 0.5262, + "step": 4457 + }, + { + "epoch": 0.36, + "learning_rate": 1.7578226857887876e-05, + "loss": 0.3215, + "step": 4458 + }, + { + "epoch": 0.36, + "learning_rate": 1.757768361581921e-05, + "loss": 0.5558, + "step": 4459 + }, + { + "epoch": 0.36, + "learning_rate": 1.7577140373750545e-05, + "loss": 0.4913, + "step": 4460 + }, + { + "epoch": 0.36, + "learning_rate": 1.757659713168188e-05, + "loss": 0.5478, + "step": 4461 + }, + { + "epoch": 0.36, + "learning_rate": 1.7576053889613213e-05, + "loss": 0.444, + "step": 4462 + }, + { + "epoch": 0.36, + "learning_rate": 1.7575510647544547e-05, + "loss": 0.346, + "step": 4463 + }, + { + "epoch": 0.36, + "learning_rate": 1.757496740547588e-05, + "loss": 0.4042, + "step": 4464 + }, + { + "epoch": 0.36, + "learning_rate": 1.7574424163407216e-05, + "loss": 0.4799, + "step": 4465 + }, + { + "epoch": 0.36, + "learning_rate": 1.757388092133855e-05, + "loss": 0.642, + "step": 4466 + }, + { + "epoch": 0.36, + "learning_rate": 1.7573337679269884e-05, + "loss": 0.8181, + "step": 4467 + }, + { + "epoch": 0.36, + "learning_rate": 1.757279443720122e-05, + "loss": 0.65, + "step": 4468 + }, + { + "epoch": 0.36, + "learning_rate": 1.7572251195132553e-05, + "loss": 0.6624, + "step": 4469 + }, + { + "epoch": 0.36, + "learning_rate": 1.7571707953063887e-05, + "loss": 0.4644, + "step": 4470 + }, + { + "epoch": 0.36, + "learning_rate": 1.757116471099522e-05, + "loss": 0.3533, + "step": 4471 + }, + { + "epoch": 0.36, + "learning_rate": 1.7570621468926555e-05, + "loss": 0.5339, + "step": 4472 + }, + { + "epoch": 0.36, + "learning_rate": 1.757007822685789e-05, + "loss": 0.427, + "step": 4473 + }, + { + "epoch": 0.36, + "learning_rate": 1.7569534984789224e-05, + "loss": 0.4149, + "step": 4474 + }, + { + "epoch": 0.36, + "learning_rate": 1.7568991742720558e-05, + "loss": 0.3106, + "step": 4475 + }, + { + "epoch": 0.36, + "learning_rate": 1.7568448500651892e-05, + "loss": 0.445, + "step": 4476 + }, + { + "epoch": 0.36, + "learning_rate": 1.7567905258583226e-05, + "loss": 0.4656, + "step": 4477 + }, + { + "epoch": 0.36, + "learning_rate": 1.756736201651456e-05, + "loss": 0.3842, + "step": 4478 + }, + { + "epoch": 0.36, + "learning_rate": 1.7566818774445895e-05, + "loss": 0.4693, + "step": 4479 + }, + { + "epoch": 0.37, + "learning_rate": 1.756627553237723e-05, + "loss": 0.5553, + "step": 4480 + }, + { + "epoch": 0.37, + "learning_rate": 1.7565732290308563e-05, + "loss": 0.5732, + "step": 4481 + }, + { + "epoch": 0.37, + "learning_rate": 1.7565189048239898e-05, + "loss": 0.5523, + "step": 4482 + }, + { + "epoch": 0.37, + "learning_rate": 1.7564645806171232e-05, + "loss": 0.4276, + "step": 4483 + }, + { + "epoch": 0.37, + "learning_rate": 1.7564102564102566e-05, + "loss": 0.6953, + "step": 4484 + }, + { + "epoch": 0.37, + "learning_rate": 1.75635593220339e-05, + "loss": 0.5458, + "step": 4485 + }, + { + "epoch": 0.37, + "learning_rate": 1.7563016079965234e-05, + "loss": 0.3488, + "step": 4486 + }, + { + "epoch": 0.37, + "learning_rate": 1.756247283789657e-05, + "loss": 0.7452, + "step": 4487 + }, + { + "epoch": 0.37, + "learning_rate": 1.7561929595827903e-05, + "loss": 0.5095, + "step": 4488 + }, + { + "epoch": 0.37, + "learning_rate": 1.7561386353759237e-05, + "loss": 0.5514, + "step": 4489 + }, + { + "epoch": 0.37, + "learning_rate": 1.756084311169057e-05, + "loss": 0.4038, + "step": 4490 + }, + { + "epoch": 0.37, + "learning_rate": 1.7560299869621906e-05, + "loss": 0.4465, + "step": 4491 + }, + { + "epoch": 0.37, + "learning_rate": 1.755975662755324e-05, + "loss": 0.4389, + "step": 4492 + }, + { + "epoch": 0.37, + "learning_rate": 1.7559213385484574e-05, + "loss": 0.5241, + "step": 4493 + }, + { + "epoch": 0.37, + "learning_rate": 1.755867014341591e-05, + "loss": 0.5341, + "step": 4494 + }, + { + "epoch": 0.37, + "learning_rate": 1.7558126901347243e-05, + "loss": 0.6654, + "step": 4495 + }, + { + "epoch": 0.37, + "learning_rate": 1.7557583659278577e-05, + "loss": 0.4762, + "step": 4496 + }, + { + "epoch": 0.37, + "learning_rate": 1.755704041720991e-05, + "loss": 0.2845, + "step": 4497 + }, + { + "epoch": 0.37, + "learning_rate": 1.7556497175141245e-05, + "loss": 0.4491, + "step": 4498 + }, + { + "epoch": 0.37, + "learning_rate": 1.755595393307258e-05, + "loss": 0.3833, + "step": 4499 + }, + { + "epoch": 0.37, + "learning_rate": 1.7555410691003914e-05, + "loss": 0.4585, + "step": 4500 + }, + { + "epoch": 0.37, + "eval_accuracy": 0.8114111054508405, + "eval_loss": 0.4917827546596527, + "eval_runtime": 22.32, + "eval_samples_per_second": 439.74, + "eval_steps_per_second": 3.45, + "step": 4500 + }, + { + "epoch": 0.37, + "learning_rate": 1.7554867448935248e-05, + "loss": 0.6065, + "step": 4501 + }, + { + "epoch": 0.37, + "learning_rate": 1.7554324206866582e-05, + "loss": 0.5398, + "step": 4502 + }, + { + "epoch": 0.37, + "learning_rate": 1.7553780964797916e-05, + "loss": 0.7966, + "step": 4503 + }, + { + "epoch": 0.37, + "learning_rate": 1.755323772272925e-05, + "loss": 0.4349, + "step": 4504 + }, + { + "epoch": 0.37, + "learning_rate": 1.7552694480660585e-05, + "loss": 0.313, + "step": 4505 + }, + { + "epoch": 0.37, + "learning_rate": 1.755215123859192e-05, + "loss": 0.5403, + "step": 4506 + }, + { + "epoch": 0.37, + "learning_rate": 1.7551607996523253e-05, + "loss": 0.718, + "step": 4507 + }, + { + "epoch": 0.37, + "learning_rate": 1.7551064754454584e-05, + "loss": 0.6389, + "step": 4508 + }, + { + "epoch": 0.37, + "learning_rate": 1.7550521512385922e-05, + "loss": 0.6499, + "step": 4509 + }, + { + "epoch": 0.37, + "learning_rate": 1.7549978270317253e-05, + "loss": 0.4819, + "step": 4510 + }, + { + "epoch": 0.37, + "learning_rate": 1.754943502824859e-05, + "loss": 0.5044, + "step": 4511 + }, + { + "epoch": 0.37, + "learning_rate": 1.754889178617992e-05, + "loss": 0.3044, + "step": 4512 + }, + { + "epoch": 0.37, + "learning_rate": 1.754834854411126e-05, + "loss": 0.4886, + "step": 4513 + }, + { + "epoch": 0.37, + "learning_rate": 1.754780530204259e-05, + "loss": 0.4425, + "step": 4514 + }, + { + "epoch": 0.37, + "learning_rate": 1.7547262059973927e-05, + "loss": 0.6672, + "step": 4515 + }, + { + "epoch": 0.37, + "learning_rate": 1.7546718817905258e-05, + "loss": 0.7054, + "step": 4516 + }, + { + "epoch": 0.37, + "learning_rate": 1.7546175575836596e-05, + "loss": 0.7176, + "step": 4517 + }, + { + "epoch": 0.37, + "learning_rate": 1.7545632333767926e-05, + "loss": 0.6102, + "step": 4518 + }, + { + "epoch": 0.37, + "learning_rate": 1.7545089091699264e-05, + "loss": 0.6088, + "step": 4519 + }, + { + "epoch": 0.37, + "learning_rate": 1.7544545849630595e-05, + "loss": 0.5522, + "step": 4520 + }, + { + "epoch": 0.37, + "learning_rate": 1.7544002607561933e-05, + "loss": 0.6372, + "step": 4521 + }, + { + "epoch": 0.37, + "learning_rate": 1.7543459365493263e-05, + "loss": 0.4419, + "step": 4522 + }, + { + "epoch": 0.37, + "learning_rate": 1.75429161234246e-05, + "loss": 0.523, + "step": 4523 + }, + { + "epoch": 0.37, + "learning_rate": 1.7542372881355932e-05, + "loss": 0.4037, + "step": 4524 + }, + { + "epoch": 0.37, + "learning_rate": 1.754182963928727e-05, + "loss": 0.5622, + "step": 4525 + }, + { + "epoch": 0.37, + "learning_rate": 1.7541286397218604e-05, + "loss": 0.4789, + "step": 4526 + }, + { + "epoch": 0.37, + "learning_rate": 1.7540743155149935e-05, + "loss": 0.4539, + "step": 4527 + }, + { + "epoch": 0.37, + "learning_rate": 1.7540199913081272e-05, + "loss": 0.6695, + "step": 4528 + }, + { + "epoch": 0.37, + "learning_rate": 1.7539656671012603e-05, + "loss": 0.4468, + "step": 4529 + }, + { + "epoch": 0.37, + "learning_rate": 1.753911342894394e-05, + "loss": 0.371, + "step": 4530 + }, + { + "epoch": 0.37, + "learning_rate": 1.753857018687527e-05, + "loss": 0.4493, + "step": 4531 + }, + { + "epoch": 0.37, + "learning_rate": 1.753802694480661e-05, + "loss": 0.3913, + "step": 4532 + }, + { + "epoch": 0.37, + "learning_rate": 1.753748370273794e-05, + "loss": 0.4197, + "step": 4533 + }, + { + "epoch": 0.37, + "learning_rate": 1.7536940460669278e-05, + "loss": 0.4528, + "step": 4534 + }, + { + "epoch": 0.37, + "learning_rate": 1.753639721860061e-05, + "loss": 0.6215, + "step": 4535 + }, + { + "epoch": 0.37, + "learning_rate": 1.7535853976531946e-05, + "loss": 0.4357, + "step": 4536 + }, + { + "epoch": 0.37, + "learning_rate": 1.7535310734463277e-05, + "loss": 0.6918, + "step": 4537 + }, + { + "epoch": 0.37, + "learning_rate": 1.7534767492394614e-05, + "loss": 0.5455, + "step": 4538 + }, + { + "epoch": 0.37, + "learning_rate": 1.7534224250325945e-05, + "loss": 0.5946, + "step": 4539 + }, + { + "epoch": 0.37, + "learning_rate": 1.7533681008257283e-05, + "loss": 0.4276, + "step": 4540 + }, + { + "epoch": 0.37, + "learning_rate": 1.7533137766188614e-05, + "loss": 0.5261, + "step": 4541 + }, + { + "epoch": 0.37, + "learning_rate": 1.753259452411995e-05, + "loss": 0.4917, + "step": 4542 + }, + { + "epoch": 0.37, + "learning_rate": 1.7532051282051282e-05, + "loss": 0.2802, + "step": 4543 + }, + { + "epoch": 0.37, + "learning_rate": 1.753150803998262e-05, + "loss": 0.4423, + "step": 4544 + }, + { + "epoch": 0.37, + "learning_rate": 1.753096479791395e-05, + "loss": 0.7018, + "step": 4545 + }, + { + "epoch": 0.37, + "learning_rate": 1.7530421555845285e-05, + "loss": 0.3631, + "step": 4546 + }, + { + "epoch": 0.37, + "learning_rate": 1.752987831377662e-05, + "loss": 0.7033, + "step": 4547 + }, + { + "epoch": 0.37, + "learning_rate": 1.7529335071707953e-05, + "loss": 0.41, + "step": 4548 + }, + { + "epoch": 0.37, + "learning_rate": 1.7528791829639288e-05, + "loss": 0.7637, + "step": 4549 + }, + { + "epoch": 0.37, + "learning_rate": 1.7528248587570622e-05, + "loss": 1.0242, + "step": 4550 + }, + { + "epoch": 0.37, + "learning_rate": 1.7527705345501956e-05, + "loss": 0.5289, + "step": 4551 + }, + { + "epoch": 0.37, + "learning_rate": 1.752716210343329e-05, + "loss": 0.3217, + "step": 4552 + }, + { + "epoch": 0.37, + "learning_rate": 1.7526618861364625e-05, + "loss": 0.518, + "step": 4553 + }, + { + "epoch": 0.37, + "learning_rate": 1.752607561929596e-05, + "loss": 0.6538, + "step": 4554 + }, + { + "epoch": 0.37, + "learning_rate": 1.7525532377227293e-05, + "loss": 0.4073, + "step": 4555 + }, + { + "epoch": 0.37, + "learning_rate": 1.7524989135158627e-05, + "loss": 0.5851, + "step": 4556 + }, + { + "epoch": 0.37, + "learning_rate": 1.752444589308996e-05, + "loss": 0.8309, + "step": 4557 + }, + { + "epoch": 0.37, + "learning_rate": 1.7523902651021296e-05, + "loss": 0.5153, + "step": 4558 + }, + { + "epoch": 0.37, + "learning_rate": 1.752335940895263e-05, + "loss": 0.7646, + "step": 4559 + }, + { + "epoch": 0.37, + "learning_rate": 1.7522816166883964e-05, + "loss": 0.6153, + "step": 4560 + }, + { + "epoch": 0.37, + "learning_rate": 1.75222729248153e-05, + "loss": 0.5982, + "step": 4561 + }, + { + "epoch": 0.37, + "learning_rate": 1.7521729682746633e-05, + "loss": 0.3948, + "step": 4562 + }, + { + "epoch": 0.37, + "learning_rate": 1.752118644067797e-05, + "loss": 0.5172, + "step": 4563 + }, + { + "epoch": 0.37, + "learning_rate": 1.75206431986093e-05, + "loss": 0.5171, + "step": 4564 + }, + { + "epoch": 0.37, + "learning_rate": 1.7520099956540635e-05, + "loss": 0.6367, + "step": 4565 + }, + { + "epoch": 0.37, + "learning_rate": 1.751955671447197e-05, + "loss": 0.5018, + "step": 4566 + }, + { + "epoch": 0.37, + "learning_rate": 1.7519013472403304e-05, + "loss": 0.4807, + "step": 4567 + }, + { + "epoch": 0.37, + "learning_rate": 1.7518470230334638e-05, + "loss": 0.5142, + "step": 4568 + }, + { + "epoch": 0.37, + "learning_rate": 1.7517926988265972e-05, + "loss": 0.3459, + "step": 4569 + }, + { + "epoch": 0.37, + "learning_rate": 1.7517383746197306e-05, + "loss": 0.514, + "step": 4570 + }, + { + "epoch": 0.37, + "learning_rate": 1.751684050412864e-05, + "loss": 0.1939, + "step": 4571 + }, + { + "epoch": 0.37, + "learning_rate": 1.7516297262059975e-05, + "loss": 0.215, + "step": 4572 + }, + { + "epoch": 0.37, + "learning_rate": 1.751575401999131e-05, + "loss": 0.6022, + "step": 4573 + }, + { + "epoch": 0.37, + "learning_rate": 1.7515210777922643e-05, + "loss": 0.5456, + "step": 4574 + }, + { + "epoch": 0.37, + "learning_rate": 1.7514667535853978e-05, + "loss": 0.6722, + "step": 4575 + }, + { + "epoch": 0.37, + "learning_rate": 1.7514124293785312e-05, + "loss": 0.4952, + "step": 4576 + }, + { + "epoch": 0.37, + "learning_rate": 1.7513581051716646e-05, + "loss": 0.5147, + "step": 4577 + }, + { + "epoch": 0.37, + "learning_rate": 1.751303780964798e-05, + "loss": 0.4211, + "step": 4578 + }, + { + "epoch": 0.37, + "learning_rate": 1.7512494567579315e-05, + "loss": 0.704, + "step": 4579 + }, + { + "epoch": 0.37, + "learning_rate": 1.751195132551065e-05, + "loss": 0.8561, + "step": 4580 + }, + { + "epoch": 0.37, + "learning_rate": 1.7511408083441983e-05, + "loss": 0.6742, + "step": 4581 + }, + { + "epoch": 0.37, + "learning_rate": 1.7510864841373317e-05, + "loss": 0.6043, + "step": 4582 + }, + { + "epoch": 0.37, + "learning_rate": 1.751032159930465e-05, + "loss": 0.4199, + "step": 4583 + }, + { + "epoch": 0.37, + "learning_rate": 1.7509778357235986e-05, + "loss": 0.5721, + "step": 4584 + }, + { + "epoch": 0.37, + "learning_rate": 1.750923511516732e-05, + "loss": 0.4753, + "step": 4585 + }, + { + "epoch": 0.37, + "learning_rate": 1.7508691873098654e-05, + "loss": 0.4062, + "step": 4586 + }, + { + "epoch": 0.37, + "learning_rate": 1.750814863102999e-05, + "loss": 0.4829, + "step": 4587 + }, + { + "epoch": 0.37, + "learning_rate": 1.7507605388961323e-05, + "loss": 0.4067, + "step": 4588 + }, + { + "epoch": 0.37, + "learning_rate": 1.7507062146892657e-05, + "loss": 0.4207, + "step": 4589 + }, + { + "epoch": 0.37, + "learning_rate": 1.750651890482399e-05, + "loss": 0.6418, + "step": 4590 + }, + { + "epoch": 0.37, + "learning_rate": 1.7505975662755325e-05, + "loss": 0.775, + "step": 4591 + }, + { + "epoch": 0.37, + "learning_rate": 1.750543242068666e-05, + "loss": 0.4857, + "step": 4592 + }, + { + "epoch": 0.37, + "learning_rate": 1.7504889178617994e-05, + "loss": 0.5033, + "step": 4593 + }, + { + "epoch": 0.37, + "learning_rate": 1.7504345936549328e-05, + "loss": 0.7141, + "step": 4594 + }, + { + "epoch": 0.37, + "learning_rate": 1.7503802694480662e-05, + "loss": 0.3063, + "step": 4595 + }, + { + "epoch": 0.37, + "learning_rate": 1.7503259452411996e-05, + "loss": 0.5114, + "step": 4596 + }, + { + "epoch": 0.37, + "learning_rate": 1.750271621034333e-05, + "loss": 0.5506, + "step": 4597 + }, + { + "epoch": 0.37, + "learning_rate": 1.7502172968274665e-05, + "loss": 0.388, + "step": 4598 + }, + { + "epoch": 0.37, + "learning_rate": 1.7501629726206e-05, + "loss": 0.6732, + "step": 4599 + }, + { + "epoch": 0.37, + "learning_rate": 1.7501086484137333e-05, + "loss": 0.5118, + "step": 4600 + }, + { + "epoch": 0.37, + "learning_rate": 1.7500543242068668e-05, + "loss": 0.4519, + "step": 4601 + }, + { + "epoch": 0.38, + "learning_rate": 1.7500000000000002e-05, + "loss": 0.4064, + "step": 4602 + }, + { + "epoch": 0.38, + "learning_rate": 1.7499456757931336e-05, + "loss": 0.5206, + "step": 4603 + }, + { + "epoch": 0.38, + "learning_rate": 1.749891351586267e-05, + "loss": 0.4093, + "step": 4604 + }, + { + "epoch": 0.38, + "learning_rate": 1.7498370273794005e-05, + "loss": 0.6337, + "step": 4605 + }, + { + "epoch": 0.38, + "learning_rate": 1.749782703172534e-05, + "loss": 0.4965, + "step": 4606 + }, + { + "epoch": 0.38, + "learning_rate": 1.7497283789656673e-05, + "loss": 0.5009, + "step": 4607 + }, + { + "epoch": 0.38, + "learning_rate": 1.7496740547588007e-05, + "loss": 0.6141, + "step": 4608 + }, + { + "epoch": 0.38, + "learning_rate": 1.749619730551934e-05, + "loss": 0.7812, + "step": 4609 + }, + { + "epoch": 0.38, + "learning_rate": 1.7495654063450676e-05, + "loss": 0.4571, + "step": 4610 + }, + { + "epoch": 0.38, + "learning_rate": 1.749511082138201e-05, + "loss": 0.5666, + "step": 4611 + }, + { + "epoch": 0.38, + "learning_rate": 1.7494567579313344e-05, + "loss": 0.4488, + "step": 4612 + }, + { + "epoch": 0.38, + "learning_rate": 1.749402433724468e-05, + "loss": 0.3844, + "step": 4613 + }, + { + "epoch": 0.38, + "learning_rate": 1.7493481095176013e-05, + "loss": 0.294, + "step": 4614 + }, + { + "epoch": 0.38, + "learning_rate": 1.7492937853107347e-05, + "loss": 0.6097, + "step": 4615 + }, + { + "epoch": 0.38, + "learning_rate": 1.749239461103868e-05, + "loss": 0.4654, + "step": 4616 + }, + { + "epoch": 0.38, + "learning_rate": 1.7491851368970015e-05, + "loss": 0.3142, + "step": 4617 + }, + { + "epoch": 0.38, + "learning_rate": 1.749130812690135e-05, + "loss": 0.3152, + "step": 4618 + }, + { + "epoch": 0.38, + "learning_rate": 1.7490764884832684e-05, + "loss": 0.4785, + "step": 4619 + }, + { + "epoch": 0.38, + "learning_rate": 1.7490221642764018e-05, + "loss": 0.3004, + "step": 4620 + }, + { + "epoch": 0.38, + "learning_rate": 1.7489678400695352e-05, + "loss": 0.6998, + "step": 4621 + }, + { + "epoch": 0.38, + "learning_rate": 1.7489135158626683e-05, + "loss": 0.4327, + "step": 4622 + }, + { + "epoch": 0.38, + "learning_rate": 1.748859191655802e-05, + "loss": 0.3379, + "step": 4623 + }, + { + "epoch": 0.38, + "learning_rate": 1.748804867448935e-05, + "loss": 0.3846, + "step": 4624 + }, + { + "epoch": 0.38, + "learning_rate": 1.748750543242069e-05, + "loss": 0.7781, + "step": 4625 + }, + { + "epoch": 0.38, + "learning_rate": 1.748696219035202e-05, + "loss": 0.3925, + "step": 4626 + }, + { + "epoch": 0.38, + "learning_rate": 1.7486418948283358e-05, + "loss": 0.3374, + "step": 4627 + }, + { + "epoch": 0.38, + "learning_rate": 1.748587570621469e-05, + "loss": 0.4107, + "step": 4628 + }, + { + "epoch": 0.38, + "learning_rate": 1.7485332464146026e-05, + "loss": 0.473, + "step": 4629 + }, + { + "epoch": 0.38, + "learning_rate": 1.7484789222077357e-05, + "loss": 0.3727, + "step": 4630 + }, + { + "epoch": 0.38, + "learning_rate": 1.7484245980008695e-05, + "loss": 0.61, + "step": 4631 + }, + { + "epoch": 0.38, + "learning_rate": 1.7483702737940025e-05, + "loss": 0.2679, + "step": 4632 + }, + { + "epoch": 0.38, + "learning_rate": 1.7483159495871363e-05, + "loss": 0.352, + "step": 4633 + }, + { + "epoch": 0.38, + "learning_rate": 1.7482616253802697e-05, + "loss": 0.4315, + "step": 4634 + }, + { + "epoch": 0.38, + "learning_rate": 1.748207301173403e-05, + "loss": 0.6569, + "step": 4635 + }, + { + "epoch": 0.38, + "learning_rate": 1.7481529769665366e-05, + "loss": 0.8655, + "step": 4636 + }, + { + "epoch": 0.38, + "learning_rate": 1.74809865275967e-05, + "loss": 0.2009, + "step": 4637 + }, + { + "epoch": 0.38, + "learning_rate": 1.7480443285528034e-05, + "loss": 0.5755, + "step": 4638 + }, + { + "epoch": 0.38, + "learning_rate": 1.747990004345937e-05, + "loss": 0.333, + "step": 4639 + }, + { + "epoch": 0.38, + "learning_rate": 1.7479356801390703e-05, + "loss": 0.6107, + "step": 4640 + }, + { + "epoch": 0.38, + "learning_rate": 1.7478813559322033e-05, + "loss": 0.4659, + "step": 4641 + }, + { + "epoch": 0.38, + "learning_rate": 1.747827031725337e-05, + "loss": 0.4214, + "step": 4642 + }, + { + "epoch": 0.38, + "learning_rate": 1.7477727075184702e-05, + "loss": 0.6398, + "step": 4643 + }, + { + "epoch": 0.38, + "learning_rate": 1.747718383311604e-05, + "loss": 0.3623, + "step": 4644 + }, + { + "epoch": 0.38, + "learning_rate": 1.747664059104737e-05, + "loss": 0.5514, + "step": 4645 + }, + { + "epoch": 0.38, + "learning_rate": 1.7476097348978708e-05, + "loss": 0.4509, + "step": 4646 + }, + { + "epoch": 0.38, + "learning_rate": 1.747555410691004e-05, + "loss": 0.3883, + "step": 4647 + }, + { + "epoch": 0.38, + "learning_rate": 1.7475010864841376e-05, + "loss": 0.4287, + "step": 4648 + }, + { + "epoch": 0.38, + "learning_rate": 1.7474467622772707e-05, + "loss": 0.3649, + "step": 4649 + }, + { + "epoch": 0.38, + "learning_rate": 1.7473924380704045e-05, + "loss": 0.8414, + "step": 4650 + }, + { + "epoch": 0.38, + "learning_rate": 1.7473381138635376e-05, + "loss": 0.6594, + "step": 4651 + }, + { + "epoch": 0.38, + "learning_rate": 1.7472837896566713e-05, + "loss": 0.4933, + "step": 4652 + }, + { + "epoch": 0.38, + "learning_rate": 1.7472294654498044e-05, + "loss": 0.6702, + "step": 4653 + }, + { + "epoch": 0.38, + "learning_rate": 1.7471751412429382e-05, + "loss": 0.385, + "step": 4654 + }, + { + "epoch": 0.38, + "learning_rate": 1.7471208170360713e-05, + "loss": 0.5479, + "step": 4655 + }, + { + "epoch": 0.38, + "learning_rate": 1.747066492829205e-05, + "loss": 0.4918, + "step": 4656 + }, + { + "epoch": 0.38, + "learning_rate": 1.747012168622338e-05, + "loss": 0.3626, + "step": 4657 + }, + { + "epoch": 0.38, + "learning_rate": 1.746957844415472e-05, + "loss": 0.186, + "step": 4658 + }, + { + "epoch": 0.38, + "learning_rate": 1.746903520208605e-05, + "loss": 0.2877, + "step": 4659 + }, + { + "epoch": 0.38, + "learning_rate": 1.7468491960017384e-05, + "loss": 0.539, + "step": 4660 + }, + { + "epoch": 0.38, + "learning_rate": 1.7467948717948718e-05, + "loss": 0.4926, + "step": 4661 + }, + { + "epoch": 0.38, + "learning_rate": 1.7467405475880052e-05, + "loss": 0.7173, + "step": 4662 + }, + { + "epoch": 0.38, + "learning_rate": 1.7466862233811387e-05, + "loss": 0.5165, + "step": 4663 + }, + { + "epoch": 0.38, + "learning_rate": 1.746631899174272e-05, + "loss": 0.5626, + "step": 4664 + }, + { + "epoch": 0.38, + "learning_rate": 1.7465775749674055e-05, + "loss": 0.3621, + "step": 4665 + }, + { + "epoch": 0.38, + "learning_rate": 1.746523250760539e-05, + "loss": 0.3824, + "step": 4666 + }, + { + "epoch": 0.38, + "learning_rate": 1.7464689265536723e-05, + "loss": 0.4313, + "step": 4667 + }, + { + "epoch": 0.38, + "learning_rate": 1.7464146023468058e-05, + "loss": 0.4766, + "step": 4668 + }, + { + "epoch": 0.38, + "learning_rate": 1.7463602781399392e-05, + "loss": 0.4255, + "step": 4669 + }, + { + "epoch": 0.38, + "learning_rate": 1.7463059539330726e-05, + "loss": 0.5597, + "step": 4670 + }, + { + "epoch": 0.38, + "learning_rate": 1.7462516297262064e-05, + "loss": 0.7968, + "step": 4671 + }, + { + "epoch": 0.38, + "learning_rate": 1.7461973055193395e-05, + "loss": 0.6332, + "step": 4672 + }, + { + "epoch": 0.38, + "learning_rate": 1.7461429813124732e-05, + "loss": 0.5574, + "step": 4673 + }, + { + "epoch": 0.38, + "learning_rate": 1.7460886571056063e-05, + "loss": 0.2949, + "step": 4674 + }, + { + "epoch": 0.38, + "learning_rate": 1.74603433289874e-05, + "loss": 0.6148, + "step": 4675 + }, + { + "epoch": 0.38, + "learning_rate": 1.745980008691873e-05, + "loss": 0.6727, + "step": 4676 + }, + { + "epoch": 0.38, + "learning_rate": 1.745925684485007e-05, + "loss": 0.4922, + "step": 4677 + }, + { + "epoch": 0.38, + "learning_rate": 1.74587136027814e-05, + "loss": 0.5145, + "step": 4678 + }, + { + "epoch": 0.38, + "learning_rate": 1.7458170360712734e-05, + "loss": 0.4007, + "step": 4679 + }, + { + "epoch": 0.38, + "learning_rate": 1.745762711864407e-05, + "loss": 0.4902, + "step": 4680 + }, + { + "epoch": 0.38, + "learning_rate": 1.7457083876575403e-05, + "loss": 0.4593, + "step": 4681 + }, + { + "epoch": 0.38, + "learning_rate": 1.7456540634506737e-05, + "loss": 0.6854, + "step": 4682 + }, + { + "epoch": 0.38, + "learning_rate": 1.745599739243807e-05, + "loss": 0.3942, + "step": 4683 + }, + { + "epoch": 0.38, + "learning_rate": 1.7455454150369405e-05, + "loss": 0.3027, + "step": 4684 + }, + { + "epoch": 0.38, + "learning_rate": 1.745491090830074e-05, + "loss": 0.4353, + "step": 4685 + }, + { + "epoch": 0.38, + "learning_rate": 1.7454367666232074e-05, + "loss": 0.2193, + "step": 4686 + }, + { + "epoch": 0.38, + "learning_rate": 1.7453824424163408e-05, + "loss": 0.3382, + "step": 4687 + }, + { + "epoch": 0.38, + "learning_rate": 1.7453281182094742e-05, + "loss": 0.5709, + "step": 4688 + }, + { + "epoch": 0.38, + "learning_rate": 1.7452737940026077e-05, + "loss": 0.6585, + "step": 4689 + }, + { + "epoch": 0.38, + "learning_rate": 1.745219469795741e-05, + "loss": 0.6885, + "step": 4690 + }, + { + "epoch": 0.38, + "learning_rate": 1.7451651455888745e-05, + "loss": 0.4715, + "step": 4691 + }, + { + "epoch": 0.38, + "learning_rate": 1.745110821382008e-05, + "loss": 0.492, + "step": 4692 + }, + { + "epoch": 0.38, + "learning_rate": 1.7450564971751413e-05, + "loss": 0.5318, + "step": 4693 + }, + { + "epoch": 0.38, + "learning_rate": 1.7450021729682748e-05, + "loss": 0.512, + "step": 4694 + }, + { + "epoch": 0.38, + "learning_rate": 1.7449478487614082e-05, + "loss": 0.4385, + "step": 4695 + }, + { + "epoch": 0.38, + "learning_rate": 1.7448935245545416e-05, + "loss": 0.4096, + "step": 4696 + }, + { + "epoch": 0.38, + "learning_rate": 1.744839200347675e-05, + "loss": 0.7703, + "step": 4697 + }, + { + "epoch": 0.38, + "learning_rate": 1.7447848761408085e-05, + "loss": 0.5157, + "step": 4698 + }, + { + "epoch": 0.38, + "learning_rate": 1.744730551933942e-05, + "loss": 0.57, + "step": 4699 + }, + { + "epoch": 0.38, + "learning_rate": 1.7446762277270753e-05, + "loss": 0.3946, + "step": 4700 + }, + { + "epoch": 0.38, + "learning_rate": 1.7446219035202087e-05, + "loss": 0.2716, + "step": 4701 + }, + { + "epoch": 0.38, + "learning_rate": 1.744567579313342e-05, + "loss": 0.2976, + "step": 4702 + }, + { + "epoch": 0.38, + "learning_rate": 1.7445132551064756e-05, + "loss": 0.6361, + "step": 4703 + }, + { + "epoch": 0.38, + "learning_rate": 1.744458930899609e-05, + "loss": 0.4808, + "step": 4704 + }, + { + "epoch": 0.38, + "learning_rate": 1.7444046066927424e-05, + "loss": 0.3257, + "step": 4705 + }, + { + "epoch": 0.38, + "learning_rate": 1.744350282485876e-05, + "loss": 0.4208, + "step": 4706 + }, + { + "epoch": 0.38, + "learning_rate": 1.7442959582790093e-05, + "loss": 0.821, + "step": 4707 + }, + { + "epoch": 0.38, + "learning_rate": 1.7442416340721427e-05, + "loss": 0.3171, + "step": 4708 + }, + { + "epoch": 0.38, + "learning_rate": 1.744187309865276e-05, + "loss": 0.6965, + "step": 4709 + }, + { + "epoch": 0.38, + "learning_rate": 1.7441329856584095e-05, + "loss": 0.4731, + "step": 4710 + }, + { + "epoch": 0.38, + "learning_rate": 1.744078661451543e-05, + "loss": 0.4834, + "step": 4711 + }, + { + "epoch": 0.38, + "learning_rate": 1.7440243372446764e-05, + "loss": 0.5784, + "step": 4712 + }, + { + "epoch": 0.38, + "learning_rate": 1.7439700130378098e-05, + "loss": 0.6395, + "step": 4713 + }, + { + "epoch": 0.38, + "learning_rate": 1.7439156888309432e-05, + "loss": 0.5973, + "step": 4714 + }, + { + "epoch": 0.38, + "learning_rate": 1.7438613646240767e-05, + "loss": 0.2728, + "step": 4715 + }, + { + "epoch": 0.38, + "learning_rate": 1.74380704041721e-05, + "loss": 0.6501, + "step": 4716 + }, + { + "epoch": 0.38, + "learning_rate": 1.7437527162103435e-05, + "loss": 0.5227, + "step": 4717 + }, + { + "epoch": 0.38, + "learning_rate": 1.743698392003477e-05, + "loss": 0.5824, + "step": 4718 + }, + { + "epoch": 0.38, + "learning_rate": 1.7436440677966103e-05, + "loss": 0.5621, + "step": 4719 + }, + { + "epoch": 0.38, + "learning_rate": 1.7435897435897438e-05, + "loss": 0.4858, + "step": 4720 + }, + { + "epoch": 0.38, + "learning_rate": 1.7435354193828772e-05, + "loss": 0.4184, + "step": 4721 + }, + { + "epoch": 0.38, + "learning_rate": 1.7434810951760106e-05, + "loss": 0.5498, + "step": 4722 + }, + { + "epoch": 0.38, + "learning_rate": 1.743426770969144e-05, + "loss": 0.4776, + "step": 4723 + }, + { + "epoch": 0.38, + "learning_rate": 1.7433724467622775e-05, + "loss": 0.5603, + "step": 4724 + }, + { + "epoch": 0.39, + "learning_rate": 1.743318122555411e-05, + "loss": 0.5145, + "step": 4725 + }, + { + "epoch": 0.39, + "learning_rate": 1.7432637983485443e-05, + "loss": 0.2976, + "step": 4726 + }, + { + "epoch": 0.39, + "learning_rate": 1.7432094741416777e-05, + "loss": 0.5521, + "step": 4727 + }, + { + "epoch": 0.39, + "learning_rate": 1.743155149934811e-05, + "loss": 0.5333, + "step": 4728 + }, + { + "epoch": 0.39, + "learning_rate": 1.7431008257279446e-05, + "loss": 0.3856, + "step": 4729 + }, + { + "epoch": 0.39, + "learning_rate": 1.743046501521078e-05, + "loss": 0.439, + "step": 4730 + }, + { + "epoch": 0.39, + "learning_rate": 1.7429921773142114e-05, + "loss": 0.7544, + "step": 4731 + }, + { + "epoch": 0.39, + "learning_rate": 1.742937853107345e-05, + "loss": 0.324, + "step": 4732 + }, + { + "epoch": 0.39, + "learning_rate": 1.7428835289004783e-05, + "loss": 0.6803, + "step": 4733 + }, + { + "epoch": 0.39, + "learning_rate": 1.7428292046936117e-05, + "loss": 0.2742, + "step": 4734 + }, + { + "epoch": 0.39, + "learning_rate": 1.742774880486745e-05, + "loss": 0.554, + "step": 4735 + }, + { + "epoch": 0.39, + "learning_rate": 1.7427205562798782e-05, + "loss": 0.4948, + "step": 4736 + }, + { + "epoch": 0.39, + "learning_rate": 1.742666232073012e-05, + "loss": 0.703, + "step": 4737 + }, + { + "epoch": 0.39, + "learning_rate": 1.742611907866145e-05, + "loss": 0.5225, + "step": 4738 + }, + { + "epoch": 0.39, + "learning_rate": 1.7425575836592788e-05, + "loss": 0.496, + "step": 4739 + }, + { + "epoch": 0.39, + "learning_rate": 1.742503259452412e-05, + "loss": 0.3906, + "step": 4740 + }, + { + "epoch": 0.39, + "learning_rate": 1.7424489352455457e-05, + "loss": 0.3996, + "step": 4741 + }, + { + "epoch": 0.39, + "learning_rate": 1.742394611038679e-05, + "loss": 0.3928, + "step": 4742 + }, + { + "epoch": 0.39, + "learning_rate": 1.7423402868318125e-05, + "loss": 0.2501, + "step": 4743 + }, + { + "epoch": 0.39, + "learning_rate": 1.742285962624946e-05, + "loss": 0.4459, + "step": 4744 + }, + { + "epoch": 0.39, + "learning_rate": 1.7422316384180793e-05, + "loss": 0.6752, + "step": 4745 + }, + { + "epoch": 0.39, + "learning_rate": 1.7421773142112128e-05, + "loss": 0.5127, + "step": 4746 + }, + { + "epoch": 0.39, + "learning_rate": 1.7421229900043462e-05, + "loss": 0.6099, + "step": 4747 + }, + { + "epoch": 0.39, + "learning_rate": 1.7420686657974796e-05, + "loss": 0.5027, + "step": 4748 + }, + { + "epoch": 0.39, + "learning_rate": 1.742014341590613e-05, + "loss": 0.6347, + "step": 4749 + }, + { + "epoch": 0.39, + "learning_rate": 1.7419600173837465e-05, + "loss": 0.4153, + "step": 4750 + }, + { + "epoch": 0.39, + "eval_accuracy": 0.8178298522669384, + "eval_loss": 0.46711739897727966, + "eval_runtime": 22.3078, + "eval_samples_per_second": 439.98, + "eval_steps_per_second": 3.452, + "step": 4750 + }, + { + "epoch": 0.39, + "learning_rate": 1.74190569317688e-05, + "loss": 0.4761, + "step": 4751 + }, + { + "epoch": 0.39, + "learning_rate": 1.7418513689700133e-05, + "loss": 0.5422, + "step": 4752 + }, + { + "epoch": 0.39, + "learning_rate": 1.7417970447631467e-05, + "loss": 0.5512, + "step": 4753 + }, + { + "epoch": 0.39, + "learning_rate": 1.74174272055628e-05, + "loss": 0.5558, + "step": 4754 + }, + { + "epoch": 0.39, + "learning_rate": 1.7416883963494132e-05, + "loss": 0.3996, + "step": 4755 + }, + { + "epoch": 0.39, + "learning_rate": 1.741634072142547e-05, + "loss": 0.4318, + "step": 4756 + }, + { + "epoch": 0.39, + "learning_rate": 1.74157974793568e-05, + "loss": 0.2806, + "step": 4757 + }, + { + "epoch": 0.39, + "learning_rate": 1.741525423728814e-05, + "loss": 0.6508, + "step": 4758 + }, + { + "epoch": 0.39, + "learning_rate": 1.741471099521947e-05, + "loss": 0.6366, + "step": 4759 + }, + { + "epoch": 0.39, + "learning_rate": 1.7414167753150807e-05, + "loss": 0.3133, + "step": 4760 + }, + { + "epoch": 0.39, + "learning_rate": 1.7413624511082138e-05, + "loss": 0.7398, + "step": 4761 + }, + { + "epoch": 0.39, + "learning_rate": 1.7413081269013475e-05, + "loss": 0.5361, + "step": 4762 + }, + { + "epoch": 0.39, + "learning_rate": 1.7412538026944806e-05, + "loss": 0.3627, + "step": 4763 + }, + { + "epoch": 0.39, + "learning_rate": 1.7411994784876144e-05, + "loss": 0.5419, + "step": 4764 + }, + { + "epoch": 0.39, + "learning_rate": 1.7411451542807475e-05, + "loss": 0.2847, + "step": 4765 + }, + { + "epoch": 0.39, + "learning_rate": 1.7410908300738812e-05, + "loss": 0.3556, + "step": 4766 + }, + { + "epoch": 0.39, + "learning_rate": 1.7410365058670143e-05, + "loss": 0.6004, + "step": 4767 + }, + { + "epoch": 0.39, + "learning_rate": 1.740982181660148e-05, + "loss": 0.5642, + "step": 4768 + }, + { + "epoch": 0.39, + "learning_rate": 1.740927857453281e-05, + "loss": 0.4526, + "step": 4769 + }, + { + "epoch": 0.39, + "learning_rate": 1.740873533246415e-05, + "loss": 0.5408, + "step": 4770 + }, + { + "epoch": 0.39, + "learning_rate": 1.740819209039548e-05, + "loss": 0.6863, + "step": 4771 + }, + { + "epoch": 0.39, + "learning_rate": 1.7407648848326818e-05, + "loss": 0.458, + "step": 4772 + }, + { + "epoch": 0.39, + "learning_rate": 1.740710560625815e-05, + "loss": 0.5, + "step": 4773 + }, + { + "epoch": 0.39, + "learning_rate": 1.7406562364189483e-05, + "loss": 0.3848, + "step": 4774 + }, + { + "epoch": 0.39, + "learning_rate": 1.7406019122120817e-05, + "loss": 0.4563, + "step": 4775 + }, + { + "epoch": 0.39, + "learning_rate": 1.740547588005215e-05, + "loss": 0.5437, + "step": 4776 + }, + { + "epoch": 0.39, + "learning_rate": 1.7404932637983485e-05, + "loss": 0.8005, + "step": 4777 + }, + { + "epoch": 0.39, + "learning_rate": 1.740438939591482e-05, + "loss": 0.3304, + "step": 4778 + }, + { + "epoch": 0.39, + "learning_rate": 1.7403846153846157e-05, + "loss": 0.5527, + "step": 4779 + }, + { + "epoch": 0.39, + "learning_rate": 1.7403302911777488e-05, + "loss": 0.3133, + "step": 4780 + }, + { + "epoch": 0.39, + "learning_rate": 1.7402759669708826e-05, + "loss": 0.5642, + "step": 4781 + }, + { + "epoch": 0.39, + "learning_rate": 1.7402216427640157e-05, + "loss": 0.661, + "step": 4782 + }, + { + "epoch": 0.39, + "learning_rate": 1.7401673185571494e-05, + "loss": 0.4815, + "step": 4783 + }, + { + "epoch": 0.39, + "learning_rate": 1.7401129943502825e-05, + "loss": 0.3347, + "step": 4784 + }, + { + "epoch": 0.39, + "learning_rate": 1.7400586701434163e-05, + "loss": 0.3607, + "step": 4785 + }, + { + "epoch": 0.39, + "learning_rate": 1.7400043459365493e-05, + "loss": 0.8068, + "step": 4786 + }, + { + "epoch": 0.39, + "learning_rate": 1.739950021729683e-05, + "loss": 0.3075, + "step": 4787 + }, + { + "epoch": 0.39, + "learning_rate": 1.7398956975228162e-05, + "loss": 0.6384, + "step": 4788 + }, + { + "epoch": 0.39, + "learning_rate": 1.73984137331595e-05, + "loss": 0.8213, + "step": 4789 + }, + { + "epoch": 0.39, + "learning_rate": 1.739787049109083e-05, + "loss": 0.4571, + "step": 4790 + }, + { + "epoch": 0.39, + "learning_rate": 1.7397327249022168e-05, + "loss": 0.6611, + "step": 4791 + }, + { + "epoch": 0.39, + "learning_rate": 1.73967840069535e-05, + "loss": 0.7008, + "step": 4792 + }, + { + "epoch": 0.39, + "learning_rate": 1.7396240764884833e-05, + "loss": 0.298, + "step": 4793 + }, + { + "epoch": 0.39, + "learning_rate": 1.7395697522816167e-05, + "loss": 0.3666, + "step": 4794 + }, + { + "epoch": 0.39, + "learning_rate": 1.73951542807475e-05, + "loss": 0.6146, + "step": 4795 + }, + { + "epoch": 0.39, + "learning_rate": 1.7394611038678836e-05, + "loss": 0.826, + "step": 4796 + }, + { + "epoch": 0.39, + "learning_rate": 1.739406779661017e-05, + "loss": 0.4742, + "step": 4797 + }, + { + "epoch": 0.39, + "learning_rate": 1.7393524554541504e-05, + "loss": 0.2932, + "step": 4798 + }, + { + "epoch": 0.39, + "learning_rate": 1.739298131247284e-05, + "loss": 0.5572, + "step": 4799 + }, + { + "epoch": 0.39, + "learning_rate": 1.7392438070404173e-05, + "loss": 0.5059, + "step": 4800 + }, + { + "epoch": 0.39, + "learning_rate": 1.7391894828335507e-05, + "loss": 0.6183, + "step": 4801 + }, + { + "epoch": 0.39, + "learning_rate": 1.739135158626684e-05, + "loss": 0.6111, + "step": 4802 + }, + { + "epoch": 0.39, + "learning_rate": 1.7390808344198175e-05, + "loss": 0.5056, + "step": 4803 + }, + { + "epoch": 0.39, + "learning_rate": 1.739026510212951e-05, + "loss": 0.6655, + "step": 4804 + }, + { + "epoch": 0.39, + "learning_rate": 1.7389721860060844e-05, + "loss": 0.424, + "step": 4805 + }, + { + "epoch": 0.39, + "learning_rate": 1.7389178617992178e-05, + "loss": 0.8241, + "step": 4806 + }, + { + "epoch": 0.39, + "learning_rate": 1.7388635375923512e-05, + "loss": 0.3274, + "step": 4807 + }, + { + "epoch": 0.39, + "learning_rate": 1.7388092133854847e-05, + "loss": 0.4186, + "step": 4808 + }, + { + "epoch": 0.39, + "learning_rate": 1.738754889178618e-05, + "loss": 0.3934, + "step": 4809 + }, + { + "epoch": 0.39, + "learning_rate": 1.7387005649717515e-05, + "loss": 0.4515, + "step": 4810 + }, + { + "epoch": 0.39, + "learning_rate": 1.738646240764885e-05, + "loss": 0.9062, + "step": 4811 + }, + { + "epoch": 0.39, + "learning_rate": 1.7385919165580183e-05, + "loss": 0.2496, + "step": 4812 + }, + { + "epoch": 0.39, + "learning_rate": 1.7385375923511518e-05, + "loss": 0.5007, + "step": 4813 + }, + { + "epoch": 0.39, + "learning_rate": 1.7384832681442852e-05, + "loss": 0.5163, + "step": 4814 + }, + { + "epoch": 0.39, + "learning_rate": 1.7384289439374186e-05, + "loss": 0.7323, + "step": 4815 + }, + { + "epoch": 0.39, + "learning_rate": 1.738374619730552e-05, + "loss": 0.4053, + "step": 4816 + }, + { + "epoch": 0.39, + "learning_rate": 1.7383202955236855e-05, + "loss": 0.3935, + "step": 4817 + }, + { + "epoch": 0.39, + "learning_rate": 1.738265971316819e-05, + "loss": 0.3336, + "step": 4818 + }, + { + "epoch": 0.39, + "learning_rate": 1.7382116471099523e-05, + "loss": 0.5402, + "step": 4819 + }, + { + "epoch": 0.39, + "learning_rate": 1.7381573229030857e-05, + "loss": 0.502, + "step": 4820 + }, + { + "epoch": 0.39, + "learning_rate": 1.738102998696219e-05, + "loss": 0.5349, + "step": 4821 + }, + { + "epoch": 0.39, + "learning_rate": 1.7380486744893526e-05, + "loss": 0.4899, + "step": 4822 + }, + { + "epoch": 0.39, + "learning_rate": 1.737994350282486e-05, + "loss": 0.3644, + "step": 4823 + }, + { + "epoch": 0.39, + "learning_rate": 1.7379400260756194e-05, + "loss": 0.4343, + "step": 4824 + }, + { + "epoch": 0.39, + "learning_rate": 1.737885701868753e-05, + "loss": 0.3939, + "step": 4825 + }, + { + "epoch": 0.39, + "learning_rate": 1.7378313776618863e-05, + "loss": 0.3899, + "step": 4826 + }, + { + "epoch": 0.39, + "learning_rate": 1.7377770534550197e-05, + "loss": 0.4036, + "step": 4827 + }, + { + "epoch": 0.39, + "learning_rate": 1.737722729248153e-05, + "loss": 0.6664, + "step": 4828 + }, + { + "epoch": 0.39, + "learning_rate": 1.7376684050412865e-05, + "loss": 0.588, + "step": 4829 + }, + { + "epoch": 0.39, + "learning_rate": 1.73761408083442e-05, + "loss": 0.2027, + "step": 4830 + }, + { + "epoch": 0.39, + "learning_rate": 1.7375597566275534e-05, + "loss": 0.6456, + "step": 4831 + }, + { + "epoch": 0.39, + "learning_rate": 1.7375054324206868e-05, + "loss": 0.601, + "step": 4832 + }, + { + "epoch": 0.39, + "learning_rate": 1.7374511082138202e-05, + "loss": 0.4691, + "step": 4833 + }, + { + "epoch": 0.39, + "learning_rate": 1.7373967840069537e-05, + "loss": 0.4025, + "step": 4834 + }, + { + "epoch": 0.39, + "learning_rate": 1.737342459800087e-05, + "loss": 0.3973, + "step": 4835 + }, + { + "epoch": 0.39, + "learning_rate": 1.7372881355932205e-05, + "loss": 1.0615, + "step": 4836 + }, + { + "epoch": 0.39, + "learning_rate": 1.737233811386354e-05, + "loss": 0.8751, + "step": 4837 + }, + { + "epoch": 0.39, + "learning_rate": 1.7371794871794873e-05, + "loss": 0.6297, + "step": 4838 + }, + { + "epoch": 0.39, + "learning_rate": 1.7371251629726208e-05, + "loss": 0.3154, + "step": 4839 + }, + { + "epoch": 0.39, + "learning_rate": 1.7370708387657542e-05, + "loss": 0.33, + "step": 4840 + }, + { + "epoch": 0.39, + "learning_rate": 1.7370165145588876e-05, + "loss": 0.4948, + "step": 4841 + }, + { + "epoch": 0.39, + "learning_rate": 1.736962190352021e-05, + "loss": 0.6083, + "step": 4842 + }, + { + "epoch": 0.39, + "learning_rate": 1.7369078661451545e-05, + "loss": 0.5555, + "step": 4843 + }, + { + "epoch": 0.39, + "learning_rate": 1.736853541938288e-05, + "loss": 0.6236, + "step": 4844 + }, + { + "epoch": 0.39, + "learning_rate": 1.7367992177314213e-05, + "loss": 0.4662, + "step": 4845 + }, + { + "epoch": 0.39, + "learning_rate": 1.7367448935245547e-05, + "loss": 0.7047, + "step": 4846 + }, + { + "epoch": 0.39, + "learning_rate": 1.736690569317688e-05, + "loss": 0.6412, + "step": 4847 + }, + { + "epoch": 0.4, + "learning_rate": 1.7366362451108216e-05, + "loss": 0.6044, + "step": 4848 + }, + { + "epoch": 0.4, + "learning_rate": 1.736581920903955e-05, + "loss": 0.485, + "step": 4849 + }, + { + "epoch": 0.4, + "learning_rate": 1.7365275966970884e-05, + "loss": 0.2962, + "step": 4850 + }, + { + "epoch": 0.4, + "learning_rate": 1.736473272490222e-05, + "loss": 0.6926, + "step": 4851 + }, + { + "epoch": 0.4, + "learning_rate": 1.7364189482833553e-05, + "loss": 0.8118, + "step": 4852 + }, + { + "epoch": 0.4, + "learning_rate": 1.7363646240764887e-05, + "loss": 0.661, + "step": 4853 + }, + { + "epoch": 0.4, + "learning_rate": 1.736310299869622e-05, + "loss": 0.5547, + "step": 4854 + }, + { + "epoch": 0.4, + "learning_rate": 1.7362559756627555e-05, + "loss": 0.5854, + "step": 4855 + }, + { + "epoch": 0.4, + "learning_rate": 1.736201651455889e-05, + "loss": 0.3922, + "step": 4856 + }, + { + "epoch": 0.4, + "learning_rate": 1.7361473272490224e-05, + "loss": 0.3891, + "step": 4857 + }, + { + "epoch": 0.4, + "learning_rate": 1.7360930030421558e-05, + "loss": 0.3973, + "step": 4858 + }, + { + "epoch": 0.4, + "learning_rate": 1.7360386788352892e-05, + "loss": 0.548, + "step": 4859 + }, + { + "epoch": 0.4, + "learning_rate": 1.7359843546284227e-05, + "loss": 0.4666, + "step": 4860 + }, + { + "epoch": 0.4, + "learning_rate": 1.735930030421556e-05, + "loss": 0.3621, + "step": 4861 + }, + { + "epoch": 0.4, + "learning_rate": 1.7358757062146895e-05, + "loss": 0.6558, + "step": 4862 + }, + { + "epoch": 0.4, + "learning_rate": 1.735821382007823e-05, + "loss": 0.3937, + "step": 4863 + }, + { + "epoch": 0.4, + "learning_rate": 1.7357670578009563e-05, + "loss": 0.4741, + "step": 4864 + }, + { + "epoch": 0.4, + "learning_rate": 1.7357127335940898e-05, + "loss": 0.4351, + "step": 4865 + }, + { + "epoch": 0.4, + "learning_rate": 1.7356584093872232e-05, + "loss": 0.4446, + "step": 4866 + }, + { + "epoch": 0.4, + "learning_rate": 1.7356040851803566e-05, + "loss": 0.4176, + "step": 4867 + }, + { + "epoch": 0.4, + "learning_rate": 1.73554976097349e-05, + "loss": 0.37, + "step": 4868 + }, + { + "epoch": 0.4, + "learning_rate": 1.735495436766623e-05, + "loss": 0.3514, + "step": 4869 + }, + { + "epoch": 0.4, + "learning_rate": 1.735441112559757e-05, + "loss": 0.4463, + "step": 4870 + }, + { + "epoch": 0.4, + "learning_rate": 1.73538678835289e-05, + "loss": 0.5302, + "step": 4871 + }, + { + "epoch": 0.4, + "learning_rate": 1.7353324641460237e-05, + "loss": 0.3887, + "step": 4872 + }, + { + "epoch": 0.4, + "learning_rate": 1.7352781399391568e-05, + "loss": 0.5002, + "step": 4873 + }, + { + "epoch": 0.4, + "learning_rate": 1.7352238157322906e-05, + "loss": 0.3271, + "step": 4874 + }, + { + "epoch": 0.4, + "learning_rate": 1.7351694915254237e-05, + "loss": 0.3712, + "step": 4875 + }, + { + "epoch": 0.4, + "learning_rate": 1.7351151673185574e-05, + "loss": 0.7824, + "step": 4876 + }, + { + "epoch": 0.4, + "learning_rate": 1.7350608431116905e-05, + "loss": 0.3949, + "step": 4877 + }, + { + "epoch": 0.4, + "learning_rate": 1.7350065189048243e-05, + "loss": 0.7289, + "step": 4878 + }, + { + "epoch": 0.4, + "learning_rate": 1.7349521946979574e-05, + "loss": 0.5805, + "step": 4879 + }, + { + "epoch": 0.4, + "learning_rate": 1.734897870491091e-05, + "loss": 0.3719, + "step": 4880 + }, + { + "epoch": 0.4, + "learning_rate": 1.7348435462842242e-05, + "loss": 0.4383, + "step": 4881 + }, + { + "epoch": 0.4, + "learning_rate": 1.734789222077358e-05, + "loss": 0.8553, + "step": 4882 + }, + { + "epoch": 0.4, + "learning_rate": 1.734734897870491e-05, + "loss": 0.3918, + "step": 4883 + }, + { + "epoch": 0.4, + "learning_rate": 1.7346805736636248e-05, + "loss": 0.7327, + "step": 4884 + }, + { + "epoch": 0.4, + "learning_rate": 1.734626249456758e-05, + "loss": 0.3795, + "step": 4885 + }, + { + "epoch": 0.4, + "learning_rate": 1.7345719252498917e-05, + "loss": 0.639, + "step": 4886 + }, + { + "epoch": 0.4, + "learning_rate": 1.734517601043025e-05, + "loss": 0.3632, + "step": 4887 + }, + { + "epoch": 0.4, + "learning_rate": 1.734463276836158e-05, + "loss": 0.3506, + "step": 4888 + }, + { + "epoch": 0.4, + "learning_rate": 1.734408952629292e-05, + "loss": 0.3289, + "step": 4889 + }, + { + "epoch": 0.4, + "learning_rate": 1.734354628422425e-05, + "loss": 0.5481, + "step": 4890 + }, + { + "epoch": 0.4, + "learning_rate": 1.7343003042155588e-05, + "loss": 0.5575, + "step": 4891 + }, + { + "epoch": 0.4, + "learning_rate": 1.734245980008692e-05, + "loss": 0.5181, + "step": 4892 + }, + { + "epoch": 0.4, + "learning_rate": 1.7341916558018256e-05, + "loss": 0.3151, + "step": 4893 + }, + { + "epoch": 0.4, + "learning_rate": 1.7341373315949587e-05, + "loss": 0.4203, + "step": 4894 + }, + { + "epoch": 0.4, + "learning_rate": 1.7340830073880925e-05, + "loss": 0.6552, + "step": 4895 + }, + { + "epoch": 0.4, + "learning_rate": 1.7340286831812255e-05, + "loss": 0.4035, + "step": 4896 + }, + { + "epoch": 0.4, + "learning_rate": 1.7339743589743593e-05, + "loss": 0.4442, + "step": 4897 + }, + { + "epoch": 0.4, + "learning_rate": 1.7339200347674924e-05, + "loss": 0.3353, + "step": 4898 + }, + { + "epoch": 0.4, + "learning_rate": 1.733865710560626e-05, + "loss": 0.3893, + "step": 4899 + }, + { + "epoch": 0.4, + "learning_rate": 1.7338113863537592e-05, + "loss": 0.4762, + "step": 4900 + }, + { + "epoch": 0.4, + "learning_rate": 1.733757062146893e-05, + "loss": 0.5024, + "step": 4901 + }, + { + "epoch": 0.4, + "learning_rate": 1.733702737940026e-05, + "loss": 0.7337, + "step": 4902 + }, + { + "epoch": 0.4, + "learning_rate": 1.73364841373316e-05, + "loss": 0.2468, + "step": 4903 + }, + { + "epoch": 0.4, + "learning_rate": 1.733594089526293e-05, + "loss": 0.406, + "step": 4904 + }, + { + "epoch": 0.4, + "learning_rate": 1.7335397653194267e-05, + "loss": 0.404, + "step": 4905 + }, + { + "epoch": 0.4, + "learning_rate": 1.7334854411125598e-05, + "loss": 0.3429, + "step": 4906 + }, + { + "epoch": 0.4, + "learning_rate": 1.7334311169056932e-05, + "loss": 0.6176, + "step": 4907 + }, + { + "epoch": 0.4, + "learning_rate": 1.7333767926988266e-05, + "loss": 0.5294, + "step": 4908 + }, + { + "epoch": 0.4, + "learning_rate": 1.73332246849196e-05, + "loss": 0.6857, + "step": 4909 + }, + { + "epoch": 0.4, + "learning_rate": 1.7332681442850935e-05, + "loss": 0.4282, + "step": 4910 + }, + { + "epoch": 0.4, + "learning_rate": 1.733213820078227e-05, + "loss": 0.8774, + "step": 4911 + }, + { + "epoch": 0.4, + "learning_rate": 1.7331594958713603e-05, + "loss": 0.539, + "step": 4912 + }, + { + "epoch": 0.4, + "learning_rate": 1.7331051716644937e-05, + "loss": 0.6348, + "step": 4913 + }, + { + "epoch": 0.4, + "learning_rate": 1.733050847457627e-05, + "loss": 0.2463, + "step": 4914 + }, + { + "epoch": 0.4, + "learning_rate": 1.7329965232507606e-05, + "loss": 0.6362, + "step": 4915 + }, + { + "epoch": 0.4, + "learning_rate": 1.732942199043894e-05, + "loss": 0.4102, + "step": 4916 + }, + { + "epoch": 0.4, + "learning_rate": 1.7328878748370274e-05, + "loss": 0.5965, + "step": 4917 + }, + { + "epoch": 0.4, + "learning_rate": 1.732833550630161e-05, + "loss": 0.4677, + "step": 4918 + }, + { + "epoch": 0.4, + "learning_rate": 1.7327792264232943e-05, + "loss": 0.499, + "step": 4919 + }, + { + "epoch": 0.4, + "learning_rate": 1.7327249022164277e-05, + "loss": 0.5192, + "step": 4920 + }, + { + "epoch": 0.4, + "learning_rate": 1.732670578009561e-05, + "loss": 0.5066, + "step": 4921 + }, + { + "epoch": 0.4, + "learning_rate": 1.7326162538026945e-05, + "loss": 0.3586, + "step": 4922 + }, + { + "epoch": 0.4, + "learning_rate": 1.732561929595828e-05, + "loss": 0.5736, + "step": 4923 + }, + { + "epoch": 0.4, + "learning_rate": 1.7325076053889617e-05, + "loss": 0.4737, + "step": 4924 + }, + { + "epoch": 0.4, + "learning_rate": 1.7324532811820948e-05, + "loss": 0.5106, + "step": 4925 + }, + { + "epoch": 0.4, + "learning_rate": 1.7323989569752282e-05, + "loss": 0.5011, + "step": 4926 + }, + { + "epoch": 0.4, + "learning_rate": 1.7323446327683617e-05, + "loss": 0.8676, + "step": 4927 + }, + { + "epoch": 0.4, + "learning_rate": 1.732290308561495e-05, + "loss": 0.5196, + "step": 4928 + }, + { + "epoch": 0.4, + "learning_rate": 1.7322359843546285e-05, + "loss": 0.3745, + "step": 4929 + }, + { + "epoch": 0.4, + "learning_rate": 1.732181660147762e-05, + "loss": 0.3713, + "step": 4930 + }, + { + "epoch": 0.4, + "learning_rate": 1.7321273359408954e-05, + "loss": 0.5822, + "step": 4931 + }, + { + "epoch": 0.4, + "learning_rate": 1.7320730117340288e-05, + "loss": 0.5639, + "step": 4932 + }, + { + "epoch": 0.4, + "learning_rate": 1.7320186875271622e-05, + "loss": 0.5678, + "step": 4933 + }, + { + "epoch": 0.4, + "learning_rate": 1.7319643633202956e-05, + "loss": 0.5477, + "step": 4934 + }, + { + "epoch": 0.4, + "learning_rate": 1.731910039113429e-05, + "loss": 0.4119, + "step": 4935 + }, + { + "epoch": 0.4, + "learning_rate": 1.7318557149065625e-05, + "loss": 0.4648, + "step": 4936 + }, + { + "epoch": 0.4, + "learning_rate": 1.731801390699696e-05, + "loss": 0.4475, + "step": 4937 + }, + { + "epoch": 0.4, + "learning_rate": 1.7317470664928293e-05, + "loss": 0.4737, + "step": 4938 + }, + { + "epoch": 0.4, + "learning_rate": 1.7316927422859627e-05, + "loss": 0.358, + "step": 4939 + }, + { + "epoch": 0.4, + "learning_rate": 1.731638418079096e-05, + "loss": 0.5535, + "step": 4940 + }, + { + "epoch": 0.4, + "learning_rate": 1.7315840938722296e-05, + "loss": 0.385, + "step": 4941 + }, + { + "epoch": 0.4, + "learning_rate": 1.731529769665363e-05, + "loss": 0.2441, + "step": 4942 + }, + { + "epoch": 0.4, + "learning_rate": 1.7314754454584964e-05, + "loss": 0.2697, + "step": 4943 + }, + { + "epoch": 0.4, + "learning_rate": 1.73142112125163e-05, + "loss": 0.6628, + "step": 4944 + }, + { + "epoch": 0.4, + "learning_rate": 1.7313667970447633e-05, + "loss": 0.5678, + "step": 4945 + }, + { + "epoch": 0.4, + "learning_rate": 1.7313124728378967e-05, + "loss": 0.4919, + "step": 4946 + }, + { + "epoch": 0.4, + "learning_rate": 1.73125814863103e-05, + "loss": 0.5409, + "step": 4947 + }, + { + "epoch": 0.4, + "learning_rate": 1.7312038244241635e-05, + "loss": 0.4522, + "step": 4948 + }, + { + "epoch": 0.4, + "learning_rate": 1.731149500217297e-05, + "loss": 0.2964, + "step": 4949 + }, + { + "epoch": 0.4, + "learning_rate": 1.7310951760104304e-05, + "loss": 0.4311, + "step": 4950 + }, + { + "epoch": 0.4, + "learning_rate": 1.7310408518035638e-05, + "loss": 0.4789, + "step": 4951 + }, + { + "epoch": 0.4, + "learning_rate": 1.7309865275966972e-05, + "loss": 0.7687, + "step": 4952 + }, + { + "epoch": 0.4, + "learning_rate": 1.7309322033898307e-05, + "loss": 0.2474, + "step": 4953 + }, + { + "epoch": 0.4, + "learning_rate": 1.730877879182964e-05, + "loss": 0.482, + "step": 4954 + }, + { + "epoch": 0.4, + "learning_rate": 1.7308235549760975e-05, + "loss": 0.3169, + "step": 4955 + }, + { + "epoch": 0.4, + "learning_rate": 1.730769230769231e-05, + "loss": 0.3356, + "step": 4956 + }, + { + "epoch": 0.4, + "learning_rate": 1.7307149065623644e-05, + "loss": 0.2698, + "step": 4957 + }, + { + "epoch": 0.4, + "learning_rate": 1.7306605823554978e-05, + "loss": 0.643, + "step": 4958 + }, + { + "epoch": 0.4, + "learning_rate": 1.7306062581486312e-05, + "loss": 0.6192, + "step": 4959 + }, + { + "epoch": 0.4, + "learning_rate": 1.7305519339417646e-05, + "loss": 0.4858, + "step": 4960 + }, + { + "epoch": 0.4, + "learning_rate": 1.730497609734898e-05, + "loss": 0.5205, + "step": 4961 + }, + { + "epoch": 0.4, + "learning_rate": 1.7304432855280315e-05, + "loss": 0.4746, + "step": 4962 + }, + { + "epoch": 0.4, + "learning_rate": 1.730388961321165e-05, + "loss": 0.2236, + "step": 4963 + }, + { + "epoch": 0.4, + "learning_rate": 1.7303346371142983e-05, + "loss": 0.6845, + "step": 4964 + }, + { + "epoch": 0.4, + "learning_rate": 1.7302803129074317e-05, + "loss": 0.4505, + "step": 4965 + }, + { + "epoch": 0.4, + "learning_rate": 1.730225988700565e-05, + "loss": 0.5012, + "step": 4966 + }, + { + "epoch": 0.4, + "learning_rate": 1.7301716644936986e-05, + "loss": 0.7957, + "step": 4967 + }, + { + "epoch": 0.4, + "learning_rate": 1.730117340286832e-05, + "loss": 0.348, + "step": 4968 + }, + { + "epoch": 0.4, + "learning_rate": 1.7300630160799654e-05, + "loss": 0.3082, + "step": 4969 + }, + { + "epoch": 0.4, + "learning_rate": 1.730008691873099e-05, + "loss": 0.4777, + "step": 4970 + }, + { + "epoch": 0.41, + "learning_rate": 1.7299543676662323e-05, + "loss": 0.454, + "step": 4971 + }, + { + "epoch": 0.41, + "learning_rate": 1.7299000434593657e-05, + "loss": 0.42, + "step": 4972 + }, + { + "epoch": 0.41, + "learning_rate": 1.729845719252499e-05, + "loss": 0.481, + "step": 4973 + }, + { + "epoch": 0.41, + "learning_rate": 1.7297913950456325e-05, + "loss": 0.5056, + "step": 4974 + }, + { + "epoch": 0.41, + "learning_rate": 1.729737070838766e-05, + "loss": 0.5973, + "step": 4975 + }, + { + "epoch": 0.41, + "learning_rate": 1.7296827466318994e-05, + "loss": 0.9205, + "step": 4976 + }, + { + "epoch": 0.41, + "learning_rate": 1.7296284224250328e-05, + "loss": 0.6305, + "step": 4977 + }, + { + "epoch": 0.41, + "learning_rate": 1.7295740982181662e-05, + "loss": 0.4436, + "step": 4978 + }, + { + "epoch": 0.41, + "learning_rate": 1.7295197740112997e-05, + "loss": 0.569, + "step": 4979 + }, + { + "epoch": 0.41, + "learning_rate": 1.729465449804433e-05, + "loss": 0.5627, + "step": 4980 + }, + { + "epoch": 0.41, + "learning_rate": 1.7294111255975665e-05, + "loss": 0.4065, + "step": 4981 + }, + { + "epoch": 0.41, + "learning_rate": 1.7293568013907e-05, + "loss": 0.5883, + "step": 4982 + }, + { + "epoch": 0.41, + "learning_rate": 1.729302477183833e-05, + "loss": 0.5311, + "step": 4983 + }, + { + "epoch": 0.41, + "learning_rate": 1.7292481529769668e-05, + "loss": 0.3181, + "step": 4984 + }, + { + "epoch": 0.41, + "learning_rate": 1.7291938287701e-05, + "loss": 0.7114, + "step": 4985 + }, + { + "epoch": 0.41, + "learning_rate": 1.7291395045632336e-05, + "loss": 0.3781, + "step": 4986 + }, + { + "epoch": 0.41, + "learning_rate": 1.7290851803563667e-05, + "loss": 0.7865, + "step": 4987 + }, + { + "epoch": 0.41, + "learning_rate": 1.7290308561495005e-05, + "loss": 0.6551, + "step": 4988 + }, + { + "epoch": 0.41, + "learning_rate": 1.7289765319426336e-05, + "loss": 0.5066, + "step": 4989 + }, + { + "epoch": 0.41, + "learning_rate": 1.7289222077357673e-05, + "loss": 0.4324, + "step": 4990 + }, + { + "epoch": 0.41, + "learning_rate": 1.7288678835289004e-05, + "loss": 0.5093, + "step": 4991 + }, + { + "epoch": 0.41, + "learning_rate": 1.728813559322034e-05, + "loss": 0.541, + "step": 4992 + }, + { + "epoch": 0.41, + "learning_rate": 1.7287592351151672e-05, + "loss": 0.661, + "step": 4993 + }, + { + "epoch": 0.41, + "learning_rate": 1.728704910908301e-05, + "loss": 0.4791, + "step": 4994 + }, + { + "epoch": 0.41, + "learning_rate": 1.7286505867014344e-05, + "loss": 0.6137, + "step": 4995 + }, + { + "epoch": 0.41, + "learning_rate": 1.728596262494568e-05, + "loss": 0.4231, + "step": 4996 + }, + { + "epoch": 0.41, + "learning_rate": 1.7285419382877013e-05, + "loss": 0.4487, + "step": 4997 + }, + { + "epoch": 0.41, + "learning_rate": 1.7284876140808347e-05, + "loss": 0.7967, + "step": 4998 + }, + { + "epoch": 0.41, + "learning_rate": 1.728433289873968e-05, + "loss": 0.5, + "step": 4999 + }, + { + "epoch": 0.41, + "learning_rate": 1.7283789656671015e-05, + "loss": 0.4317, + "step": 5000 + }, + { + "epoch": 0.41, + "eval_accuracy": 0.8189505858380031, + "eval_loss": 0.4609137773513794, + "eval_runtime": 22.2693, + "eval_samples_per_second": 440.742, + "eval_steps_per_second": 3.458, + "step": 5000 + }, + { + "epoch": 0.41, + "learning_rate": 1.728324641460235e-05, + "loss": 0.728, + "step": 5001 + }, + { + "epoch": 0.41, + "learning_rate": 1.728270317253368e-05, + "loss": 0.5332, + "step": 5002 + }, + { + "epoch": 0.41, + "learning_rate": 1.7282159930465018e-05, + "loss": 0.5343, + "step": 5003 + }, + { + "epoch": 0.41, + "learning_rate": 1.728161668839635e-05, + "loss": 0.3436, + "step": 5004 + }, + { + "epoch": 0.41, + "learning_rate": 1.7281073446327687e-05, + "loss": 0.5907, + "step": 5005 + }, + { + "epoch": 0.41, + "learning_rate": 1.7280530204259017e-05, + "loss": 0.3312, + "step": 5006 + }, + { + "epoch": 0.41, + "learning_rate": 1.7279986962190355e-05, + "loss": 0.3432, + "step": 5007 + }, + { + "epoch": 0.41, + "learning_rate": 1.7279443720121686e-05, + "loss": 0.3783, + "step": 5008 + }, + { + "epoch": 0.41, + "learning_rate": 1.7278900478053024e-05, + "loss": 0.5317, + "step": 5009 + }, + { + "epoch": 0.41, + "learning_rate": 1.7278357235984354e-05, + "loss": 0.4691, + "step": 5010 + }, + { + "epoch": 0.41, + "learning_rate": 1.7277813993915692e-05, + "loss": 0.5504, + "step": 5011 + }, + { + "epoch": 0.41, + "learning_rate": 1.7277270751847023e-05, + "loss": 0.5958, + "step": 5012 + }, + { + "epoch": 0.41, + "learning_rate": 1.727672750977836e-05, + "loss": 0.7647, + "step": 5013 + }, + { + "epoch": 0.41, + "learning_rate": 1.727618426770969e-05, + "loss": 0.4516, + "step": 5014 + }, + { + "epoch": 0.41, + "learning_rate": 1.727564102564103e-05, + "loss": 0.9014, + "step": 5015 + }, + { + "epoch": 0.41, + "learning_rate": 1.727509778357236e-05, + "loss": 0.3244, + "step": 5016 + }, + { + "epoch": 0.41, + "learning_rate": 1.7274554541503697e-05, + "loss": 0.378, + "step": 5017 + }, + { + "epoch": 0.41, + "learning_rate": 1.7274011299435028e-05, + "loss": 0.4458, + "step": 5018 + }, + { + "epoch": 0.41, + "learning_rate": 1.7273468057366366e-05, + "loss": 0.6588, + "step": 5019 + }, + { + "epoch": 0.41, + "learning_rate": 1.7272924815297697e-05, + "loss": 0.3225, + "step": 5020 + }, + { + "epoch": 0.41, + "learning_rate": 1.727238157322903e-05, + "loss": 0.5059, + "step": 5021 + }, + { + "epoch": 0.41, + "learning_rate": 1.7271838331160365e-05, + "loss": 0.5398, + "step": 5022 + }, + { + "epoch": 0.41, + "learning_rate": 1.72712950890917e-05, + "loss": 0.3154, + "step": 5023 + }, + { + "epoch": 0.41, + "learning_rate": 1.7270751847023034e-05, + "loss": 0.6023, + "step": 5024 + }, + { + "epoch": 0.41, + "learning_rate": 1.7270208604954368e-05, + "loss": 0.7306, + "step": 5025 + }, + { + "epoch": 0.41, + "learning_rate": 1.7269665362885702e-05, + "loss": 0.5056, + "step": 5026 + }, + { + "epoch": 0.41, + "learning_rate": 1.7269122120817036e-05, + "loss": 0.485, + "step": 5027 + }, + { + "epoch": 0.41, + "learning_rate": 1.726857887874837e-05, + "loss": 0.4755, + "step": 5028 + }, + { + "epoch": 0.41, + "learning_rate": 1.7268035636679705e-05, + "loss": 0.315, + "step": 5029 + }, + { + "epoch": 0.41, + "learning_rate": 1.726749239461104e-05, + "loss": 0.5537, + "step": 5030 + }, + { + "epoch": 0.41, + "learning_rate": 1.7266949152542373e-05, + "loss": 0.5787, + "step": 5031 + }, + { + "epoch": 0.41, + "learning_rate": 1.726640591047371e-05, + "loss": 0.3186, + "step": 5032 + }, + { + "epoch": 0.41, + "learning_rate": 1.726586266840504e-05, + "loss": 0.6288, + "step": 5033 + }, + { + "epoch": 0.41, + "learning_rate": 1.726531942633638e-05, + "loss": 0.409, + "step": 5034 + }, + { + "epoch": 0.41, + "learning_rate": 1.726477618426771e-05, + "loss": 0.5044, + "step": 5035 + }, + { + "epoch": 0.41, + "learning_rate": 1.7264232942199048e-05, + "loss": 0.534, + "step": 5036 + }, + { + "epoch": 0.41, + "learning_rate": 1.726368970013038e-05, + "loss": 0.4662, + "step": 5037 + }, + { + "epoch": 0.41, + "learning_rate": 1.7263146458061716e-05, + "loss": 0.4474, + "step": 5038 + }, + { + "epoch": 0.41, + "learning_rate": 1.7262603215993047e-05, + "loss": 0.3685, + "step": 5039 + }, + { + "epoch": 0.41, + "learning_rate": 1.726205997392438e-05, + "loss": 0.3865, + "step": 5040 + }, + { + "epoch": 0.41, + "learning_rate": 1.7261516731855716e-05, + "loss": 0.5606, + "step": 5041 + }, + { + "epoch": 0.41, + "learning_rate": 1.726097348978705e-05, + "loss": 0.5256, + "step": 5042 + }, + { + "epoch": 0.41, + "learning_rate": 1.7260430247718384e-05, + "loss": 0.3332, + "step": 5043 + }, + { + "epoch": 0.41, + "learning_rate": 1.7259887005649718e-05, + "loss": 0.5874, + "step": 5044 + }, + { + "epoch": 0.41, + "learning_rate": 1.7259343763581052e-05, + "loss": 0.3855, + "step": 5045 + }, + { + "epoch": 0.41, + "learning_rate": 1.7258800521512387e-05, + "loss": 0.6894, + "step": 5046 + }, + { + "epoch": 0.41, + "learning_rate": 1.725825727944372e-05, + "loss": 0.5425, + "step": 5047 + }, + { + "epoch": 0.41, + "learning_rate": 1.7257714037375055e-05, + "loss": 0.5632, + "step": 5048 + }, + { + "epoch": 0.41, + "learning_rate": 1.725717079530639e-05, + "loss": 0.5409, + "step": 5049 + }, + { + "epoch": 0.41, + "learning_rate": 1.7256627553237724e-05, + "loss": 0.5614, + "step": 5050 + }, + { + "epoch": 0.41, + "learning_rate": 1.7256084311169058e-05, + "loss": 0.4532, + "step": 5051 + }, + { + "epoch": 0.41, + "learning_rate": 1.7255541069100392e-05, + "loss": 0.3895, + "step": 5052 + }, + { + "epoch": 0.41, + "learning_rate": 1.7254997827031726e-05, + "loss": 0.5147, + "step": 5053 + }, + { + "epoch": 0.41, + "learning_rate": 1.725445458496306e-05, + "loss": 0.4237, + "step": 5054 + }, + { + "epoch": 0.41, + "learning_rate": 1.7253911342894395e-05, + "loss": 0.4491, + "step": 5055 + }, + { + "epoch": 0.41, + "learning_rate": 1.725336810082573e-05, + "loss": 0.5009, + "step": 5056 + }, + { + "epoch": 0.41, + "learning_rate": 1.7252824858757063e-05, + "loss": 0.5565, + "step": 5057 + }, + { + "epoch": 0.41, + "learning_rate": 1.7252281616688397e-05, + "loss": 0.6456, + "step": 5058 + }, + { + "epoch": 0.41, + "learning_rate": 1.725173837461973e-05, + "loss": 0.5816, + "step": 5059 + }, + { + "epoch": 0.41, + "learning_rate": 1.7251195132551066e-05, + "loss": 0.4714, + "step": 5060 + }, + { + "epoch": 0.41, + "learning_rate": 1.72506518904824e-05, + "loss": 0.7943, + "step": 5061 + }, + { + "epoch": 0.41, + "learning_rate": 1.7250108648413734e-05, + "loss": 0.6436, + "step": 5062 + }, + { + "epoch": 0.41, + "learning_rate": 1.724956540634507e-05, + "loss": 0.4635, + "step": 5063 + }, + { + "epoch": 0.41, + "learning_rate": 1.7249022164276403e-05, + "loss": 0.4626, + "step": 5064 + }, + { + "epoch": 0.41, + "learning_rate": 1.7248478922207737e-05, + "loss": 0.4151, + "step": 5065 + }, + { + "epoch": 0.41, + "learning_rate": 1.724793568013907e-05, + "loss": 0.1882, + "step": 5066 + }, + { + "epoch": 0.41, + "learning_rate": 1.7247392438070406e-05, + "loss": 0.5433, + "step": 5067 + }, + { + "epoch": 0.41, + "learning_rate": 1.724684919600174e-05, + "loss": 0.5717, + "step": 5068 + }, + { + "epoch": 0.41, + "learning_rate": 1.7246305953933074e-05, + "loss": 0.8297, + "step": 5069 + }, + { + "epoch": 0.41, + "learning_rate": 1.7245762711864408e-05, + "loss": 0.4437, + "step": 5070 + }, + { + "epoch": 0.41, + "learning_rate": 1.7245219469795742e-05, + "loss": 0.3669, + "step": 5071 + }, + { + "epoch": 0.41, + "learning_rate": 1.7244676227727077e-05, + "loss": 0.4642, + "step": 5072 + }, + { + "epoch": 0.41, + "learning_rate": 1.724413298565841e-05, + "loss": 0.3425, + "step": 5073 + }, + { + "epoch": 0.41, + "learning_rate": 1.7243589743589745e-05, + "loss": 0.3374, + "step": 5074 + }, + { + "epoch": 0.41, + "learning_rate": 1.724304650152108e-05, + "loss": 0.6395, + "step": 5075 + }, + { + "epoch": 0.41, + "learning_rate": 1.7242503259452414e-05, + "loss": 0.37, + "step": 5076 + }, + { + "epoch": 0.41, + "learning_rate": 1.7241960017383748e-05, + "loss": 0.4339, + "step": 5077 + }, + { + "epoch": 0.41, + "learning_rate": 1.7241416775315082e-05, + "loss": 0.6255, + "step": 5078 + }, + { + "epoch": 0.41, + "learning_rate": 1.7240873533246416e-05, + "loss": 0.4384, + "step": 5079 + }, + { + "epoch": 0.41, + "learning_rate": 1.724033029117775e-05, + "loss": 0.4079, + "step": 5080 + }, + { + "epoch": 0.41, + "learning_rate": 1.7239787049109085e-05, + "loss": 0.5421, + "step": 5081 + }, + { + "epoch": 0.41, + "learning_rate": 1.723924380704042e-05, + "loss": 0.497, + "step": 5082 + }, + { + "epoch": 0.41, + "learning_rate": 1.7238700564971753e-05, + "loss": 0.6668, + "step": 5083 + }, + { + "epoch": 0.41, + "learning_rate": 1.7238157322903087e-05, + "loss": 0.4912, + "step": 5084 + }, + { + "epoch": 0.41, + "learning_rate": 1.723761408083442e-05, + "loss": 0.5375, + "step": 5085 + }, + { + "epoch": 0.41, + "learning_rate": 1.7237070838765756e-05, + "loss": 0.296, + "step": 5086 + }, + { + "epoch": 0.41, + "learning_rate": 1.723652759669709e-05, + "loss": 0.3738, + "step": 5087 + }, + { + "epoch": 0.41, + "learning_rate": 1.7235984354628424e-05, + "loss": 0.6143, + "step": 5088 + }, + { + "epoch": 0.41, + "learning_rate": 1.723544111255976e-05, + "loss": 0.4194, + "step": 5089 + }, + { + "epoch": 0.41, + "learning_rate": 1.7234897870491093e-05, + "loss": 0.3082, + "step": 5090 + }, + { + "epoch": 0.41, + "learning_rate": 1.7234354628422427e-05, + "loss": 0.4528, + "step": 5091 + }, + { + "epoch": 0.41, + "learning_rate": 1.723381138635376e-05, + "loss": 0.5508, + "step": 5092 + }, + { + "epoch": 0.42, + "learning_rate": 1.7233268144285096e-05, + "loss": 0.2235, + "step": 5093 + }, + { + "epoch": 0.42, + "learning_rate": 1.723272490221643e-05, + "loss": 0.1609, + "step": 5094 + }, + { + "epoch": 0.42, + "learning_rate": 1.7232181660147764e-05, + "loss": 0.5107, + "step": 5095 + }, + { + "epoch": 0.42, + "learning_rate": 1.7231638418079098e-05, + "loss": 0.5296, + "step": 5096 + }, + { + "epoch": 0.42, + "learning_rate": 1.723109517601043e-05, + "loss": 0.691, + "step": 5097 + }, + { + "epoch": 0.42, + "learning_rate": 1.7230551933941767e-05, + "loss": 0.6884, + "step": 5098 + }, + { + "epoch": 0.42, + "learning_rate": 1.7230008691873097e-05, + "loss": 0.4528, + "step": 5099 + }, + { + "epoch": 0.42, + "learning_rate": 1.7229465449804435e-05, + "loss": 0.6393, + "step": 5100 + }, + { + "epoch": 0.42, + "learning_rate": 1.7228922207735766e-05, + "loss": 0.8345, + "step": 5101 + }, + { + "epoch": 0.42, + "learning_rate": 1.7228378965667104e-05, + "loss": 0.485, + "step": 5102 + }, + { + "epoch": 0.42, + "learning_rate": 1.7227835723598438e-05, + "loss": 0.5616, + "step": 5103 + }, + { + "epoch": 0.42, + "learning_rate": 1.7227292481529772e-05, + "loss": 0.5228, + "step": 5104 + }, + { + "epoch": 0.42, + "learning_rate": 1.7226749239461106e-05, + "loss": 0.5331, + "step": 5105 + }, + { + "epoch": 0.42, + "learning_rate": 1.722620599739244e-05, + "loss": 0.6872, + "step": 5106 + }, + { + "epoch": 0.42, + "learning_rate": 1.7225662755323775e-05, + "loss": 0.3865, + "step": 5107 + }, + { + "epoch": 0.42, + "learning_rate": 1.722511951325511e-05, + "loss": 0.6991, + "step": 5108 + }, + { + "epoch": 0.42, + "learning_rate": 1.7224576271186443e-05, + "loss": 0.6052, + "step": 5109 + }, + { + "epoch": 0.42, + "learning_rate": 1.7224033029117777e-05, + "loss": 0.5516, + "step": 5110 + }, + { + "epoch": 0.42, + "learning_rate": 1.722348978704911e-05, + "loss": 0.5489, + "step": 5111 + }, + { + "epoch": 0.42, + "learning_rate": 1.7222946544980446e-05, + "loss": 0.5471, + "step": 5112 + }, + { + "epoch": 0.42, + "learning_rate": 1.722240330291178e-05, + "loss": 0.6239, + "step": 5113 + }, + { + "epoch": 0.42, + "learning_rate": 1.7221860060843114e-05, + "loss": 0.3001, + "step": 5114 + }, + { + "epoch": 0.42, + "learning_rate": 1.722131681877445e-05, + "loss": 0.4483, + "step": 5115 + }, + { + "epoch": 0.42, + "learning_rate": 1.722077357670578e-05, + "loss": 0.4763, + "step": 5116 + }, + { + "epoch": 0.42, + "learning_rate": 1.7220230334637117e-05, + "loss": 0.5729, + "step": 5117 + }, + { + "epoch": 0.42, + "learning_rate": 1.7219687092568448e-05, + "loss": 0.4093, + "step": 5118 + }, + { + "epoch": 0.42, + "learning_rate": 1.7219143850499785e-05, + "loss": 0.5223, + "step": 5119 + }, + { + "epoch": 0.42, + "learning_rate": 1.7218600608431116e-05, + "loss": 0.4374, + "step": 5120 + }, + { + "epoch": 0.42, + "learning_rate": 1.7218057366362454e-05, + "loss": 0.4156, + "step": 5121 + }, + { + "epoch": 0.42, + "learning_rate": 1.7217514124293785e-05, + "loss": 0.6351, + "step": 5122 + }, + { + "epoch": 0.42, + "learning_rate": 1.7216970882225122e-05, + "loss": 0.6512, + "step": 5123 + }, + { + "epoch": 0.42, + "learning_rate": 1.7216427640156453e-05, + "loss": 0.5701, + "step": 5124 + }, + { + "epoch": 0.42, + "learning_rate": 1.721588439808779e-05, + "loss": 0.3449, + "step": 5125 + }, + { + "epoch": 0.42, + "learning_rate": 1.7215341156019122e-05, + "loss": 0.4723, + "step": 5126 + }, + { + "epoch": 0.42, + "learning_rate": 1.721479791395046e-05, + "loss": 0.5095, + "step": 5127 + }, + { + "epoch": 0.42, + "learning_rate": 1.721425467188179e-05, + "loss": 0.5442, + "step": 5128 + }, + { + "epoch": 0.42, + "learning_rate": 1.7213711429813128e-05, + "loss": 0.4053, + "step": 5129 + }, + { + "epoch": 0.42, + "learning_rate": 1.721316818774446e-05, + "loss": 0.2114, + "step": 5130 + }, + { + "epoch": 0.42, + "learning_rate": 1.7212624945675796e-05, + "loss": 0.5199, + "step": 5131 + }, + { + "epoch": 0.42, + "learning_rate": 1.7212081703607127e-05, + "loss": 0.607, + "step": 5132 + }, + { + "epoch": 0.42, + "learning_rate": 1.7211538461538465e-05, + "loss": 0.3699, + "step": 5133 + }, + { + "epoch": 0.42, + "learning_rate": 1.7210995219469796e-05, + "loss": 0.4978, + "step": 5134 + }, + { + "epoch": 0.42, + "learning_rate": 1.721045197740113e-05, + "loss": 0.4165, + "step": 5135 + }, + { + "epoch": 0.42, + "learning_rate": 1.7209908735332464e-05, + "loss": 0.5953, + "step": 5136 + }, + { + "epoch": 0.42, + "learning_rate": 1.7209365493263798e-05, + "loss": 0.5285, + "step": 5137 + }, + { + "epoch": 0.42, + "learning_rate": 1.7208822251195132e-05, + "loss": 0.505, + "step": 5138 + }, + { + "epoch": 0.42, + "learning_rate": 1.7208279009126467e-05, + "loss": 0.6727, + "step": 5139 + }, + { + "epoch": 0.42, + "learning_rate": 1.7207735767057804e-05, + "loss": 0.4363, + "step": 5140 + }, + { + "epoch": 0.42, + "learning_rate": 1.7207192524989135e-05, + "loss": 0.6924, + "step": 5141 + }, + { + "epoch": 0.42, + "learning_rate": 1.7206649282920473e-05, + "loss": 0.4342, + "step": 5142 + }, + { + "epoch": 0.42, + "learning_rate": 1.7206106040851804e-05, + "loss": 0.4834, + "step": 5143 + }, + { + "epoch": 0.42, + "learning_rate": 1.720556279878314e-05, + "loss": 0.4906, + "step": 5144 + }, + { + "epoch": 0.42, + "learning_rate": 1.7205019556714472e-05, + "loss": 0.5555, + "step": 5145 + }, + { + "epoch": 0.42, + "learning_rate": 1.720447631464581e-05, + "loss": 0.4479, + "step": 5146 + }, + { + "epoch": 0.42, + "learning_rate": 1.720393307257714e-05, + "loss": 0.5601, + "step": 5147 + }, + { + "epoch": 0.42, + "learning_rate": 1.7203389830508478e-05, + "loss": 0.4207, + "step": 5148 + }, + { + "epoch": 0.42, + "learning_rate": 1.720284658843981e-05, + "loss": 0.5729, + "step": 5149 + }, + { + "epoch": 0.42, + "learning_rate": 1.7202303346371147e-05, + "loss": 0.2797, + "step": 5150 + }, + { + "epoch": 0.42, + "learning_rate": 1.7201760104302477e-05, + "loss": 0.5586, + "step": 5151 + }, + { + "epoch": 0.42, + "learning_rate": 1.7201216862233815e-05, + "loss": 0.6027, + "step": 5152 + }, + { + "epoch": 0.42, + "learning_rate": 1.7200673620165146e-05, + "loss": 0.258, + "step": 5153 + }, + { + "epoch": 0.42, + "learning_rate": 1.720013037809648e-05, + "loss": 0.5052, + "step": 5154 + }, + { + "epoch": 0.42, + "learning_rate": 1.7199587136027814e-05, + "loss": 0.4396, + "step": 5155 + }, + { + "epoch": 0.42, + "learning_rate": 1.719904389395915e-05, + "loss": 0.373, + "step": 5156 + }, + { + "epoch": 0.42, + "learning_rate": 1.7198500651890483e-05, + "loss": 0.6939, + "step": 5157 + }, + { + "epoch": 0.42, + "learning_rate": 1.7197957409821817e-05, + "loss": 0.4863, + "step": 5158 + }, + { + "epoch": 0.42, + "learning_rate": 1.719741416775315e-05, + "loss": 0.2191, + "step": 5159 + }, + { + "epoch": 0.42, + "learning_rate": 1.7196870925684486e-05, + "loss": 0.6669, + "step": 5160 + }, + { + "epoch": 0.42, + "learning_rate": 1.719632768361582e-05, + "loss": 0.7348, + "step": 5161 + }, + { + "epoch": 0.42, + "learning_rate": 1.7195784441547154e-05, + "loss": 0.4255, + "step": 5162 + }, + { + "epoch": 0.42, + "learning_rate": 1.7195241199478488e-05, + "loss": 0.3596, + "step": 5163 + }, + { + "epoch": 0.42, + "learning_rate": 1.7194697957409822e-05, + "loss": 0.6394, + "step": 5164 + }, + { + "epoch": 0.42, + "learning_rate": 1.7194154715341157e-05, + "loss": 0.6206, + "step": 5165 + }, + { + "epoch": 0.42, + "learning_rate": 1.719361147327249e-05, + "loss": 0.3187, + "step": 5166 + }, + { + "epoch": 0.42, + "learning_rate": 1.7193068231203825e-05, + "loss": 0.3725, + "step": 5167 + }, + { + "epoch": 0.42, + "learning_rate": 1.719252498913516e-05, + "loss": 0.6559, + "step": 5168 + }, + { + "epoch": 0.42, + "learning_rate": 1.7191981747066494e-05, + "loss": 0.5426, + "step": 5169 + }, + { + "epoch": 0.42, + "learning_rate": 1.7191438504997828e-05, + "loss": 0.4594, + "step": 5170 + }, + { + "epoch": 0.42, + "learning_rate": 1.7190895262929162e-05, + "loss": 0.4837, + "step": 5171 + }, + { + "epoch": 0.42, + "learning_rate": 1.7190352020860496e-05, + "loss": 0.5106, + "step": 5172 + }, + { + "epoch": 0.42, + "learning_rate": 1.718980877879183e-05, + "loss": 0.452, + "step": 5173 + }, + { + "epoch": 0.42, + "learning_rate": 1.7189265536723165e-05, + "loss": 0.5345, + "step": 5174 + }, + { + "epoch": 0.42, + "learning_rate": 1.71887222946545e-05, + "loss": 0.4766, + "step": 5175 + }, + { + "epoch": 0.42, + "learning_rate": 1.7188179052585833e-05, + "loss": 0.6148, + "step": 5176 + }, + { + "epoch": 0.42, + "learning_rate": 1.7187635810517167e-05, + "loss": 0.6393, + "step": 5177 + }, + { + "epoch": 0.42, + "learning_rate": 1.7187092568448502e-05, + "loss": 0.5769, + "step": 5178 + }, + { + "epoch": 0.42, + "learning_rate": 1.7186549326379836e-05, + "loss": 0.5956, + "step": 5179 + }, + { + "epoch": 0.42, + "learning_rate": 1.718600608431117e-05, + "loss": 0.5368, + "step": 5180 + }, + { + "epoch": 0.42, + "learning_rate": 1.7185462842242504e-05, + "loss": 0.3229, + "step": 5181 + }, + { + "epoch": 0.42, + "learning_rate": 1.718491960017384e-05, + "loss": 0.5149, + "step": 5182 + }, + { + "epoch": 0.42, + "learning_rate": 1.7184376358105173e-05, + "loss": 0.4684, + "step": 5183 + }, + { + "epoch": 0.42, + "learning_rate": 1.7183833116036507e-05, + "loss": 0.2964, + "step": 5184 + }, + { + "epoch": 0.42, + "learning_rate": 1.718328987396784e-05, + "loss": 0.389, + "step": 5185 + }, + { + "epoch": 0.42, + "learning_rate": 1.7182746631899176e-05, + "loss": 0.7563, + "step": 5186 + }, + { + "epoch": 0.42, + "learning_rate": 1.718220338983051e-05, + "loss": 0.3746, + "step": 5187 + }, + { + "epoch": 0.42, + "learning_rate": 1.7181660147761844e-05, + "loss": 0.6457, + "step": 5188 + }, + { + "epoch": 0.42, + "learning_rate": 1.7181116905693178e-05, + "loss": 0.4856, + "step": 5189 + }, + { + "epoch": 0.42, + "learning_rate": 1.7180573663624512e-05, + "loss": 0.5772, + "step": 5190 + }, + { + "epoch": 0.42, + "learning_rate": 1.7180030421555847e-05, + "loss": 0.3831, + "step": 5191 + }, + { + "epoch": 0.42, + "learning_rate": 1.717948717948718e-05, + "loss": 0.4873, + "step": 5192 + }, + { + "epoch": 0.42, + "learning_rate": 1.7178943937418515e-05, + "loss": 0.6959, + "step": 5193 + }, + { + "epoch": 0.42, + "learning_rate": 1.717840069534985e-05, + "loss": 0.4282, + "step": 5194 + }, + { + "epoch": 0.42, + "learning_rate": 1.7177857453281184e-05, + "loss": 0.6495, + "step": 5195 + }, + { + "epoch": 0.42, + "learning_rate": 1.7177314211212518e-05, + "loss": 0.5607, + "step": 5196 + }, + { + "epoch": 0.42, + "learning_rate": 1.7176770969143852e-05, + "loss": 0.426, + "step": 5197 + }, + { + "epoch": 0.42, + "learning_rate": 1.7176227727075186e-05, + "loss": 0.4958, + "step": 5198 + }, + { + "epoch": 0.42, + "learning_rate": 1.717568448500652e-05, + "loss": 0.461, + "step": 5199 + }, + { + "epoch": 0.42, + "learning_rate": 1.7175141242937855e-05, + "loss": 0.4567, + "step": 5200 + }, + { + "epoch": 0.42, + "learning_rate": 1.717459800086919e-05, + "loss": 0.3446, + "step": 5201 + }, + { + "epoch": 0.42, + "learning_rate": 1.7174054758800523e-05, + "loss": 0.4857, + "step": 5202 + }, + { + "epoch": 0.42, + "learning_rate": 1.7173511516731857e-05, + "loss": 0.5033, + "step": 5203 + }, + { + "epoch": 0.42, + "learning_rate": 1.7172968274663192e-05, + "loss": 0.5375, + "step": 5204 + }, + { + "epoch": 0.42, + "learning_rate": 1.7172425032594526e-05, + "loss": 0.6688, + "step": 5205 + }, + { + "epoch": 0.42, + "learning_rate": 1.717188179052586e-05, + "loss": 0.384, + "step": 5206 + }, + { + "epoch": 0.42, + "learning_rate": 1.7171338548457194e-05, + "loss": 0.2575, + "step": 5207 + }, + { + "epoch": 0.42, + "learning_rate": 1.717079530638853e-05, + "loss": 0.4866, + "step": 5208 + }, + { + "epoch": 0.42, + "learning_rate": 1.7170252064319863e-05, + "loss": 0.6746, + "step": 5209 + }, + { + "epoch": 0.42, + "learning_rate": 1.7169708822251197e-05, + "loss": 0.5069, + "step": 5210 + }, + { + "epoch": 0.42, + "learning_rate": 1.716916558018253e-05, + "loss": 0.4823, + "step": 5211 + }, + { + "epoch": 0.42, + "learning_rate": 1.7168622338113866e-05, + "loss": 0.6446, + "step": 5212 + }, + { + "epoch": 0.42, + "learning_rate": 1.71680790960452e-05, + "loss": 0.4906, + "step": 5213 + }, + { + "epoch": 0.42, + "learning_rate": 1.7167535853976534e-05, + "loss": 0.6863, + "step": 5214 + }, + { + "epoch": 0.42, + "learning_rate": 1.7166992611907868e-05, + "loss": 0.4342, + "step": 5215 + }, + { + "epoch": 0.43, + "learning_rate": 1.7166449369839202e-05, + "loss": 0.7398, + "step": 5216 + }, + { + "epoch": 0.43, + "learning_rate": 1.7165906127770537e-05, + "loss": 0.8777, + "step": 5217 + }, + { + "epoch": 0.43, + "learning_rate": 1.716536288570187e-05, + "loss": 0.5296, + "step": 5218 + }, + { + "epoch": 0.43, + "learning_rate": 1.7164819643633205e-05, + "loss": 0.309, + "step": 5219 + }, + { + "epoch": 0.43, + "learning_rate": 1.716427640156454e-05, + "loss": 0.5595, + "step": 5220 + }, + { + "epoch": 0.43, + "learning_rate": 1.7163733159495874e-05, + "loss": 0.7317, + "step": 5221 + }, + { + "epoch": 0.43, + "learning_rate": 1.7163189917427208e-05, + "loss": 0.5285, + "step": 5222 + }, + { + "epoch": 0.43, + "learning_rate": 1.7162646675358542e-05, + "loss": 0.6084, + "step": 5223 + }, + { + "epoch": 0.43, + "learning_rate": 1.7162103433289876e-05, + "loss": 0.6066, + "step": 5224 + }, + { + "epoch": 0.43, + "learning_rate": 1.716156019122121e-05, + "loss": 0.3623, + "step": 5225 + }, + { + "epoch": 0.43, + "learning_rate": 1.7161016949152545e-05, + "loss": 0.4509, + "step": 5226 + }, + { + "epoch": 0.43, + "learning_rate": 1.716047370708388e-05, + "loss": 0.4115, + "step": 5227 + }, + { + "epoch": 0.43, + "learning_rate": 1.7159930465015213e-05, + "loss": 0.3418, + "step": 5228 + }, + { + "epoch": 0.43, + "learning_rate": 1.7159387222946547e-05, + "loss": 0.331, + "step": 5229 + }, + { + "epoch": 0.43, + "learning_rate": 1.715884398087788e-05, + "loss": 0.4078, + "step": 5230 + }, + { + "epoch": 0.43, + "learning_rate": 1.7158300738809216e-05, + "loss": 0.748, + "step": 5231 + }, + { + "epoch": 0.43, + "learning_rate": 1.7157757496740547e-05, + "loss": 0.5784, + "step": 5232 + }, + { + "epoch": 0.43, + "learning_rate": 1.7157214254671884e-05, + "loss": 0.5348, + "step": 5233 + }, + { + "epoch": 0.43, + "learning_rate": 1.7156671012603215e-05, + "loss": 0.4783, + "step": 5234 + }, + { + "epoch": 0.43, + "learning_rate": 1.7156127770534553e-05, + "loss": 0.5233, + "step": 5235 + }, + { + "epoch": 0.43, + "learning_rate": 1.7155584528465884e-05, + "loss": 0.3176, + "step": 5236 + }, + { + "epoch": 0.43, + "learning_rate": 1.715504128639722e-05, + "loss": 0.4248, + "step": 5237 + }, + { + "epoch": 0.43, + "learning_rate": 1.7154498044328552e-05, + "loss": 0.3647, + "step": 5238 + }, + { + "epoch": 0.43, + "learning_rate": 1.715395480225989e-05, + "loss": 0.5541, + "step": 5239 + }, + { + "epoch": 0.43, + "learning_rate": 1.715341156019122e-05, + "loss": 0.3325, + "step": 5240 + }, + { + "epoch": 0.43, + "learning_rate": 1.7152868318122558e-05, + "loss": 0.4542, + "step": 5241 + }, + { + "epoch": 0.43, + "learning_rate": 1.715232507605389e-05, + "loss": 0.4787, + "step": 5242 + }, + { + "epoch": 0.43, + "learning_rate": 1.7151781833985227e-05, + "loss": 0.5123, + "step": 5243 + }, + { + "epoch": 0.43, + "learning_rate": 1.7151238591916558e-05, + "loss": 0.4593, + "step": 5244 + }, + { + "epoch": 0.43, + "learning_rate": 1.7150695349847895e-05, + "loss": 0.7322, + "step": 5245 + }, + { + "epoch": 0.43, + "learning_rate": 1.7150152107779226e-05, + "loss": 0.511, + "step": 5246 + }, + { + "epoch": 0.43, + "learning_rate": 1.7149608865710564e-05, + "loss": 0.5307, + "step": 5247 + }, + { + "epoch": 0.43, + "learning_rate": 1.7149065623641898e-05, + "loss": 0.7587, + "step": 5248 + }, + { + "epoch": 0.43, + "learning_rate": 1.714852238157323e-05, + "loss": 0.5865, + "step": 5249 + }, + { + "epoch": 0.43, + "learning_rate": 1.7147979139504566e-05, + "loss": 0.7769, + "step": 5250 + }, + { + "epoch": 0.43, + "eval_accuracy": 0.8203769740193582, + "eval_loss": 0.4577733874320984, + "eval_runtime": 22.3054, + "eval_samples_per_second": 440.027, + "eval_steps_per_second": 3.452, + "step": 5250 + }, + { + "epoch": 0.43, + "learning_rate": 1.7147435897435897e-05, + "loss": 0.467, + "step": 5251 + }, + { + "epoch": 0.43, + "learning_rate": 1.7146892655367235e-05, + "loss": 0.6163, + "step": 5252 + }, + { + "epoch": 0.43, + "learning_rate": 1.7146349413298566e-05, + "loss": 0.6336, + "step": 5253 + }, + { + "epoch": 0.43, + "learning_rate": 1.7145806171229903e-05, + "loss": 0.4167, + "step": 5254 + }, + { + "epoch": 0.43, + "learning_rate": 1.7145262929161234e-05, + "loss": 0.4575, + "step": 5255 + }, + { + "epoch": 0.43, + "learning_rate": 1.714471968709257e-05, + "loss": 0.5365, + "step": 5256 + }, + { + "epoch": 0.43, + "learning_rate": 1.7144176445023903e-05, + "loss": 0.4102, + "step": 5257 + }, + { + "epoch": 0.43, + "learning_rate": 1.714363320295524e-05, + "loss": 0.3987, + "step": 5258 + }, + { + "epoch": 0.43, + "learning_rate": 1.714308996088657e-05, + "loss": 0.6397, + "step": 5259 + }, + { + "epoch": 0.43, + "learning_rate": 1.714254671881791e-05, + "loss": 0.4909, + "step": 5260 + }, + { + "epoch": 0.43, + "learning_rate": 1.714200347674924e-05, + "loss": 0.5579, + "step": 5261 + }, + { + "epoch": 0.43, + "learning_rate": 1.7141460234680577e-05, + "loss": 0.6159, + "step": 5262 + }, + { + "epoch": 0.43, + "learning_rate": 1.7140916992611908e-05, + "loss": 0.546, + "step": 5263 + }, + { + "epoch": 0.43, + "learning_rate": 1.7140373750543246e-05, + "loss": 0.4559, + "step": 5264 + }, + { + "epoch": 0.43, + "learning_rate": 1.7139830508474576e-05, + "loss": 0.4953, + "step": 5265 + }, + { + "epoch": 0.43, + "learning_rate": 1.7139287266405914e-05, + "loss": 0.3308, + "step": 5266 + }, + { + "epoch": 0.43, + "learning_rate": 1.7138744024337245e-05, + "loss": 0.4881, + "step": 5267 + }, + { + "epoch": 0.43, + "learning_rate": 1.713820078226858e-05, + "loss": 0.2996, + "step": 5268 + }, + { + "epoch": 0.43, + "learning_rate": 1.7137657540199913e-05, + "loss": 0.2996, + "step": 5269 + }, + { + "epoch": 0.43, + "learning_rate": 1.7137114298131248e-05, + "loss": 0.3061, + "step": 5270 + }, + { + "epoch": 0.43, + "learning_rate": 1.7136571056062582e-05, + "loss": 0.4332, + "step": 5271 + }, + { + "epoch": 0.43, + "learning_rate": 1.7136027813993916e-05, + "loss": 0.3323, + "step": 5272 + }, + { + "epoch": 0.43, + "learning_rate": 1.713548457192525e-05, + "loss": 0.5088, + "step": 5273 + }, + { + "epoch": 0.43, + "learning_rate": 1.7134941329856584e-05, + "loss": 0.1732, + "step": 5274 + }, + { + "epoch": 0.43, + "learning_rate": 1.713439808778792e-05, + "loss": 0.3259, + "step": 5275 + }, + { + "epoch": 0.43, + "learning_rate": 1.7133854845719253e-05, + "loss": 0.6584, + "step": 5276 + }, + { + "epoch": 0.43, + "learning_rate": 1.7133311603650587e-05, + "loss": 0.5411, + "step": 5277 + }, + { + "epoch": 0.43, + "learning_rate": 1.713276836158192e-05, + "loss": 0.3925, + "step": 5278 + }, + { + "epoch": 0.43, + "learning_rate": 1.7132225119513256e-05, + "loss": 0.2373, + "step": 5279 + }, + { + "epoch": 0.43, + "learning_rate": 1.713168187744459e-05, + "loss": 0.7062, + "step": 5280 + }, + { + "epoch": 0.43, + "learning_rate": 1.7131138635375924e-05, + "loss": 0.4697, + "step": 5281 + }, + { + "epoch": 0.43, + "learning_rate": 1.7130595393307258e-05, + "loss": 0.6795, + "step": 5282 + }, + { + "epoch": 0.43, + "learning_rate": 1.7130052151238593e-05, + "loss": 0.2836, + "step": 5283 + }, + { + "epoch": 0.43, + "learning_rate": 1.7129508909169927e-05, + "loss": 0.1624, + "step": 5284 + }, + { + "epoch": 0.43, + "learning_rate": 1.7128965667101264e-05, + "loss": 0.769, + "step": 5285 + }, + { + "epoch": 0.43, + "learning_rate": 1.7128422425032595e-05, + "loss": 0.3283, + "step": 5286 + }, + { + "epoch": 0.43, + "learning_rate": 1.712787918296393e-05, + "loss": 0.5164, + "step": 5287 + }, + { + "epoch": 0.43, + "learning_rate": 1.7127335940895264e-05, + "loss": 0.4565, + "step": 5288 + }, + { + "epoch": 0.43, + "learning_rate": 1.7126792698826598e-05, + "loss": 0.4395, + "step": 5289 + }, + { + "epoch": 0.43, + "learning_rate": 1.7126249456757932e-05, + "loss": 0.4763, + "step": 5290 + }, + { + "epoch": 0.43, + "learning_rate": 1.7125706214689266e-05, + "loss": 0.5825, + "step": 5291 + }, + { + "epoch": 0.43, + "learning_rate": 1.71251629726206e-05, + "loss": 0.6187, + "step": 5292 + }, + { + "epoch": 0.43, + "learning_rate": 1.7124619730551935e-05, + "loss": 0.2997, + "step": 5293 + }, + { + "epoch": 0.43, + "learning_rate": 1.712407648848327e-05, + "loss": 0.4219, + "step": 5294 + }, + { + "epoch": 0.43, + "learning_rate": 1.7123533246414603e-05, + "loss": 0.5018, + "step": 5295 + }, + { + "epoch": 0.43, + "learning_rate": 1.7122990004345938e-05, + "loss": 0.5697, + "step": 5296 + }, + { + "epoch": 0.43, + "learning_rate": 1.7122446762277272e-05, + "loss": 0.4936, + "step": 5297 + }, + { + "epoch": 0.43, + "learning_rate": 1.7121903520208606e-05, + "loss": 0.6992, + "step": 5298 + }, + { + "epoch": 0.43, + "learning_rate": 1.712136027813994e-05, + "loss": 0.5233, + "step": 5299 + }, + { + "epoch": 0.43, + "learning_rate": 1.7120817036071274e-05, + "loss": 0.4, + "step": 5300 + }, + { + "epoch": 0.43, + "learning_rate": 1.712027379400261e-05, + "loss": 0.4805, + "step": 5301 + }, + { + "epoch": 0.43, + "learning_rate": 1.7119730551933943e-05, + "loss": 0.593, + "step": 5302 + }, + { + "epoch": 0.43, + "learning_rate": 1.7119187309865277e-05, + "loss": 0.6889, + "step": 5303 + }, + { + "epoch": 0.43, + "learning_rate": 1.711864406779661e-05, + "loss": 0.8731, + "step": 5304 + }, + { + "epoch": 0.43, + "learning_rate": 1.7118100825727946e-05, + "loss": 0.723, + "step": 5305 + }, + { + "epoch": 0.43, + "learning_rate": 1.711755758365928e-05, + "loss": 0.8288, + "step": 5306 + }, + { + "epoch": 0.43, + "learning_rate": 1.7117014341590614e-05, + "loss": 0.318, + "step": 5307 + }, + { + "epoch": 0.43, + "learning_rate": 1.7116471099521948e-05, + "loss": 0.6619, + "step": 5308 + }, + { + "epoch": 0.43, + "learning_rate": 1.7115927857453283e-05, + "loss": 0.5851, + "step": 5309 + }, + { + "epoch": 0.43, + "learning_rate": 1.7115384615384617e-05, + "loss": 0.4919, + "step": 5310 + }, + { + "epoch": 0.43, + "learning_rate": 1.711484137331595e-05, + "loss": 0.2827, + "step": 5311 + }, + { + "epoch": 0.43, + "learning_rate": 1.7114298131247285e-05, + "loss": 0.3332, + "step": 5312 + }, + { + "epoch": 0.43, + "learning_rate": 1.711375488917862e-05, + "loss": 0.6067, + "step": 5313 + }, + { + "epoch": 0.43, + "learning_rate": 1.7113211647109954e-05, + "loss": 0.3857, + "step": 5314 + }, + { + "epoch": 0.43, + "learning_rate": 1.7112668405041288e-05, + "loss": 0.3764, + "step": 5315 + }, + { + "epoch": 0.43, + "learning_rate": 1.7112125162972622e-05, + "loss": 0.3578, + "step": 5316 + }, + { + "epoch": 0.43, + "learning_rate": 1.7111581920903956e-05, + "loss": 0.4182, + "step": 5317 + }, + { + "epoch": 0.43, + "learning_rate": 1.711103867883529e-05, + "loss": 0.486, + "step": 5318 + }, + { + "epoch": 0.43, + "learning_rate": 1.7110495436766625e-05, + "loss": 0.4512, + "step": 5319 + }, + { + "epoch": 0.43, + "learning_rate": 1.710995219469796e-05, + "loss": 0.3796, + "step": 5320 + }, + { + "epoch": 0.43, + "learning_rate": 1.7109408952629293e-05, + "loss": 0.4105, + "step": 5321 + }, + { + "epoch": 0.43, + "learning_rate": 1.7108865710560628e-05, + "loss": 0.5611, + "step": 5322 + }, + { + "epoch": 0.43, + "learning_rate": 1.7108322468491962e-05, + "loss": 0.3499, + "step": 5323 + }, + { + "epoch": 0.43, + "learning_rate": 1.7107779226423296e-05, + "loss": 0.3745, + "step": 5324 + }, + { + "epoch": 0.43, + "learning_rate": 1.710723598435463e-05, + "loss": 0.4617, + "step": 5325 + }, + { + "epoch": 0.43, + "learning_rate": 1.7106692742285964e-05, + "loss": 0.5325, + "step": 5326 + }, + { + "epoch": 0.43, + "learning_rate": 1.71061495002173e-05, + "loss": 0.4884, + "step": 5327 + }, + { + "epoch": 0.43, + "learning_rate": 1.7105606258148633e-05, + "loss": 0.5673, + "step": 5328 + }, + { + "epoch": 0.43, + "learning_rate": 1.7105063016079967e-05, + "loss": 0.3633, + "step": 5329 + }, + { + "epoch": 0.43, + "learning_rate": 1.71045197740113e-05, + "loss": 0.6073, + "step": 5330 + }, + { + "epoch": 0.43, + "learning_rate": 1.7103976531942636e-05, + "loss": 0.2629, + "step": 5331 + }, + { + "epoch": 0.43, + "learning_rate": 1.710343328987397e-05, + "loss": 0.4477, + "step": 5332 + }, + { + "epoch": 0.43, + "learning_rate": 1.7102890047805304e-05, + "loss": 0.5579, + "step": 5333 + }, + { + "epoch": 0.43, + "learning_rate": 1.7102346805736638e-05, + "loss": 0.5534, + "step": 5334 + }, + { + "epoch": 0.43, + "learning_rate": 1.7101803563667973e-05, + "loss": 0.6531, + "step": 5335 + }, + { + "epoch": 0.43, + "learning_rate": 1.7101260321599307e-05, + "loss": 0.4645, + "step": 5336 + }, + { + "epoch": 0.43, + "learning_rate": 1.710071707953064e-05, + "loss": 0.5551, + "step": 5337 + }, + { + "epoch": 0.43, + "learning_rate": 1.7100173837461975e-05, + "loss": 0.388, + "step": 5338 + }, + { + "epoch": 0.44, + "learning_rate": 1.709963059539331e-05, + "loss": 0.5332, + "step": 5339 + }, + { + "epoch": 0.44, + "learning_rate": 1.7099087353324644e-05, + "loss": 0.4657, + "step": 5340 + }, + { + "epoch": 0.44, + "learning_rate": 1.7098544111255978e-05, + "loss": 0.5164, + "step": 5341 + }, + { + "epoch": 0.44, + "learning_rate": 1.7098000869187312e-05, + "loss": 0.4595, + "step": 5342 + }, + { + "epoch": 0.44, + "learning_rate": 1.7097457627118646e-05, + "loss": 0.5485, + "step": 5343 + }, + { + "epoch": 0.44, + "learning_rate": 1.7096914385049977e-05, + "loss": 0.5121, + "step": 5344 + }, + { + "epoch": 0.44, + "learning_rate": 1.7096371142981315e-05, + "loss": 0.6476, + "step": 5345 + }, + { + "epoch": 0.44, + "learning_rate": 1.7095827900912646e-05, + "loss": 0.3491, + "step": 5346 + }, + { + "epoch": 0.44, + "learning_rate": 1.7095284658843983e-05, + "loss": 0.3804, + "step": 5347 + }, + { + "epoch": 0.44, + "learning_rate": 1.7094741416775314e-05, + "loss": 0.5209, + "step": 5348 + }, + { + "epoch": 0.44, + "learning_rate": 1.7094198174706652e-05, + "loss": 0.441, + "step": 5349 + }, + { + "epoch": 0.44, + "learning_rate": 1.7093654932637983e-05, + "loss": 0.349, + "step": 5350 + }, + { + "epoch": 0.44, + "learning_rate": 1.709311169056932e-05, + "loss": 0.3963, + "step": 5351 + }, + { + "epoch": 0.44, + "learning_rate": 1.709256844850065e-05, + "loss": 0.7588, + "step": 5352 + }, + { + "epoch": 0.44, + "learning_rate": 1.709202520643199e-05, + "loss": 0.2498, + "step": 5353 + }, + { + "epoch": 0.44, + "learning_rate": 1.709148196436332e-05, + "loss": 0.3273, + "step": 5354 + }, + { + "epoch": 0.44, + "learning_rate": 1.7090938722294657e-05, + "loss": 0.4763, + "step": 5355 + }, + { + "epoch": 0.44, + "learning_rate": 1.709039548022599e-05, + "loss": 0.6917, + "step": 5356 + }, + { + "epoch": 0.44, + "learning_rate": 1.7089852238157326e-05, + "loss": 0.412, + "step": 5357 + }, + { + "epoch": 0.44, + "learning_rate": 1.708930899608866e-05, + "loss": 0.3637, + "step": 5358 + }, + { + "epoch": 0.44, + "learning_rate": 1.7088765754019994e-05, + "loss": 0.4146, + "step": 5359 + }, + { + "epoch": 0.44, + "learning_rate": 1.7088222511951328e-05, + "loss": 0.4883, + "step": 5360 + }, + { + "epoch": 0.44, + "learning_rate": 1.7087679269882663e-05, + "loss": 0.3149, + "step": 5361 + }, + { + "epoch": 0.44, + "learning_rate": 1.7087136027813997e-05, + "loss": 0.6017, + "step": 5362 + }, + { + "epoch": 0.44, + "learning_rate": 1.7086592785745328e-05, + "loss": 0.8622, + "step": 5363 + }, + { + "epoch": 0.44, + "learning_rate": 1.7086049543676665e-05, + "loss": 0.4914, + "step": 5364 + }, + { + "epoch": 0.44, + "learning_rate": 1.7085506301607996e-05, + "loss": 0.3551, + "step": 5365 + }, + { + "epoch": 0.44, + "learning_rate": 1.7084963059539334e-05, + "loss": 0.4616, + "step": 5366 + }, + { + "epoch": 0.44, + "learning_rate": 1.7084419817470665e-05, + "loss": 0.5799, + "step": 5367 + }, + { + "epoch": 0.44, + "learning_rate": 1.7083876575402002e-05, + "loss": 0.5143, + "step": 5368 + }, + { + "epoch": 0.44, + "learning_rate": 1.7083333333333333e-05, + "loss": 0.6265, + "step": 5369 + }, + { + "epoch": 0.44, + "learning_rate": 1.708279009126467e-05, + "loss": 0.6267, + "step": 5370 + }, + { + "epoch": 0.44, + "learning_rate": 1.7082246849196e-05, + "loss": 0.4631, + "step": 5371 + }, + { + "epoch": 0.44, + "learning_rate": 1.708170360712734e-05, + "loss": 0.5373, + "step": 5372 + }, + { + "epoch": 0.44, + "learning_rate": 1.708116036505867e-05, + "loss": 0.4482, + "step": 5373 + }, + { + "epoch": 0.44, + "learning_rate": 1.7080617122990008e-05, + "loss": 0.5164, + "step": 5374 + }, + { + "epoch": 0.44, + "learning_rate": 1.708007388092134e-05, + "loss": 0.5309, + "step": 5375 + }, + { + "epoch": 0.44, + "learning_rate": 1.7079530638852676e-05, + "loss": 0.4192, + "step": 5376 + }, + { + "epoch": 0.44, + "learning_rate": 1.7078987396784007e-05, + "loss": 0.6124, + "step": 5377 + }, + { + "epoch": 0.44, + "learning_rate": 1.7078444154715344e-05, + "loss": 0.4873, + "step": 5378 + }, + { + "epoch": 0.44, + "learning_rate": 1.7077900912646675e-05, + "loss": 0.5545, + "step": 5379 + }, + { + "epoch": 0.44, + "learning_rate": 1.7077357670578013e-05, + "loss": 0.5454, + "step": 5380 + }, + { + "epoch": 0.44, + "learning_rate": 1.7076814428509344e-05, + "loss": 0.413, + "step": 5381 + }, + { + "epoch": 0.44, + "learning_rate": 1.7076271186440678e-05, + "loss": 0.6103, + "step": 5382 + }, + { + "epoch": 0.44, + "learning_rate": 1.7075727944372012e-05, + "loss": 0.4701, + "step": 5383 + }, + { + "epoch": 0.44, + "learning_rate": 1.7075184702303346e-05, + "loss": 0.4419, + "step": 5384 + }, + { + "epoch": 0.44, + "learning_rate": 1.707464146023468e-05, + "loss": 0.4692, + "step": 5385 + }, + { + "epoch": 0.44, + "learning_rate": 1.7074098218166015e-05, + "loss": 0.5178, + "step": 5386 + }, + { + "epoch": 0.44, + "learning_rate": 1.707355497609735e-05, + "loss": 0.6196, + "step": 5387 + }, + { + "epoch": 0.44, + "learning_rate": 1.7073011734028683e-05, + "loss": 0.5531, + "step": 5388 + }, + { + "epoch": 0.44, + "learning_rate": 1.7072468491960018e-05, + "loss": 0.5152, + "step": 5389 + }, + { + "epoch": 0.44, + "learning_rate": 1.7071925249891352e-05, + "loss": 0.2704, + "step": 5390 + }, + { + "epoch": 0.44, + "learning_rate": 1.7071382007822686e-05, + "loss": 0.4491, + "step": 5391 + }, + { + "epoch": 0.44, + "learning_rate": 1.707083876575402e-05, + "loss": 0.6721, + "step": 5392 + }, + { + "epoch": 0.44, + "learning_rate": 1.7070295523685358e-05, + "loss": 0.4436, + "step": 5393 + }, + { + "epoch": 0.44, + "learning_rate": 1.706975228161669e-05, + "loss": 0.4576, + "step": 5394 + }, + { + "epoch": 0.44, + "learning_rate": 1.7069209039548026e-05, + "loss": 0.3078, + "step": 5395 + }, + { + "epoch": 0.44, + "learning_rate": 1.7068665797479357e-05, + "loss": 0.5159, + "step": 5396 + }, + { + "epoch": 0.44, + "learning_rate": 1.7068122555410695e-05, + "loss": 0.2635, + "step": 5397 + }, + { + "epoch": 0.44, + "learning_rate": 1.7067579313342026e-05, + "loss": 0.6282, + "step": 5398 + }, + { + "epoch": 0.44, + "learning_rate": 1.7067036071273363e-05, + "loss": 0.4071, + "step": 5399 + }, + { + "epoch": 0.44, + "learning_rate": 1.7066492829204694e-05, + "loss": 0.3447, + "step": 5400 + }, + { + "epoch": 0.44, + "learning_rate": 1.706594958713603e-05, + "loss": 0.4124, + "step": 5401 + }, + { + "epoch": 0.44, + "learning_rate": 1.7065406345067363e-05, + "loss": 0.6135, + "step": 5402 + }, + { + "epoch": 0.44, + "learning_rate": 1.7064863102998697e-05, + "loss": 0.3235, + "step": 5403 + }, + { + "epoch": 0.44, + "learning_rate": 1.706431986093003e-05, + "loss": 0.485, + "step": 5404 + }, + { + "epoch": 0.44, + "learning_rate": 1.7063776618861365e-05, + "loss": 0.294, + "step": 5405 + }, + { + "epoch": 0.44, + "learning_rate": 1.70632333767927e-05, + "loss": 0.3682, + "step": 5406 + }, + { + "epoch": 0.44, + "learning_rate": 1.7062690134724034e-05, + "loss": 0.3558, + "step": 5407 + }, + { + "epoch": 0.44, + "learning_rate": 1.7062146892655368e-05, + "loss": 0.5918, + "step": 5408 + }, + { + "epoch": 0.44, + "learning_rate": 1.7061603650586702e-05, + "loss": 0.574, + "step": 5409 + }, + { + "epoch": 0.44, + "learning_rate": 1.7061060408518036e-05, + "loss": 0.2925, + "step": 5410 + }, + { + "epoch": 0.44, + "learning_rate": 1.706051716644937e-05, + "loss": 0.7509, + "step": 5411 + }, + { + "epoch": 0.44, + "learning_rate": 1.7059973924380705e-05, + "loss": 0.477, + "step": 5412 + }, + { + "epoch": 0.44, + "learning_rate": 1.705943068231204e-05, + "loss": 0.844, + "step": 5413 + }, + { + "epoch": 0.44, + "learning_rate": 1.7058887440243373e-05, + "loss": 0.4025, + "step": 5414 + }, + { + "epoch": 0.44, + "learning_rate": 1.7058344198174708e-05, + "loss": 0.3604, + "step": 5415 + }, + { + "epoch": 0.44, + "learning_rate": 1.7057800956106042e-05, + "loss": 0.3847, + "step": 5416 + }, + { + "epoch": 0.44, + "learning_rate": 1.7057257714037376e-05, + "loss": 0.6723, + "step": 5417 + }, + { + "epoch": 0.44, + "learning_rate": 1.705671447196871e-05, + "loss": 0.6467, + "step": 5418 + }, + { + "epoch": 0.44, + "learning_rate": 1.7056171229900044e-05, + "loss": 0.6761, + "step": 5419 + }, + { + "epoch": 0.44, + "learning_rate": 1.705562798783138e-05, + "loss": 0.3656, + "step": 5420 + }, + { + "epoch": 0.44, + "learning_rate": 1.7055084745762713e-05, + "loss": 0.4852, + "step": 5421 + }, + { + "epoch": 0.44, + "learning_rate": 1.7054541503694047e-05, + "loss": 0.8389, + "step": 5422 + }, + { + "epoch": 0.44, + "learning_rate": 1.705399826162538e-05, + "loss": 0.6929, + "step": 5423 + }, + { + "epoch": 0.44, + "learning_rate": 1.7053455019556716e-05, + "loss": 0.4106, + "step": 5424 + }, + { + "epoch": 0.44, + "learning_rate": 1.705291177748805e-05, + "loss": 0.4973, + "step": 5425 + }, + { + "epoch": 0.44, + "learning_rate": 1.7052368535419384e-05, + "loss": 0.6996, + "step": 5426 + }, + { + "epoch": 0.44, + "learning_rate": 1.705182529335072e-05, + "loss": 0.6555, + "step": 5427 + }, + { + "epoch": 0.44, + "learning_rate": 1.7051282051282053e-05, + "loss": 0.4387, + "step": 5428 + }, + { + "epoch": 0.44, + "learning_rate": 1.7050738809213387e-05, + "loss": 0.3585, + "step": 5429 + }, + { + "epoch": 0.44, + "learning_rate": 1.705019556714472e-05, + "loss": 0.5754, + "step": 5430 + }, + { + "epoch": 0.44, + "learning_rate": 1.7049652325076055e-05, + "loss": 0.449, + "step": 5431 + }, + { + "epoch": 0.44, + "learning_rate": 1.704910908300739e-05, + "loss": 0.5511, + "step": 5432 + }, + { + "epoch": 0.44, + "learning_rate": 1.7048565840938724e-05, + "loss": 0.6913, + "step": 5433 + }, + { + "epoch": 0.44, + "learning_rate": 1.7048022598870058e-05, + "loss": 0.5004, + "step": 5434 + }, + { + "epoch": 0.44, + "learning_rate": 1.7047479356801392e-05, + "loss": 0.507, + "step": 5435 + }, + { + "epoch": 0.44, + "learning_rate": 1.7046936114732726e-05, + "loss": 0.6792, + "step": 5436 + }, + { + "epoch": 0.44, + "learning_rate": 1.704639287266406e-05, + "loss": 0.4027, + "step": 5437 + }, + { + "epoch": 0.44, + "learning_rate": 1.7045849630595395e-05, + "loss": 0.4698, + "step": 5438 + }, + { + "epoch": 0.44, + "learning_rate": 1.704530638852673e-05, + "loss": 0.3774, + "step": 5439 + }, + { + "epoch": 0.44, + "learning_rate": 1.7044763146458063e-05, + "loss": 0.8564, + "step": 5440 + }, + { + "epoch": 0.44, + "learning_rate": 1.7044219904389398e-05, + "loss": 0.8143, + "step": 5441 + }, + { + "epoch": 0.44, + "learning_rate": 1.7043676662320732e-05, + "loss": 0.424, + "step": 5442 + }, + { + "epoch": 0.44, + "learning_rate": 1.7043133420252066e-05, + "loss": 0.493, + "step": 5443 + }, + { + "epoch": 0.44, + "learning_rate": 1.70425901781834e-05, + "loss": 0.6302, + "step": 5444 + }, + { + "epoch": 0.44, + "learning_rate": 1.7042046936114734e-05, + "loss": 0.3831, + "step": 5445 + }, + { + "epoch": 0.44, + "learning_rate": 1.704150369404607e-05, + "loss": 0.6481, + "step": 5446 + }, + { + "epoch": 0.44, + "learning_rate": 1.7040960451977403e-05, + "loss": 0.2594, + "step": 5447 + }, + { + "epoch": 0.44, + "learning_rate": 1.7040417209908737e-05, + "loss": 0.5388, + "step": 5448 + }, + { + "epoch": 0.44, + "learning_rate": 1.703987396784007e-05, + "loss": 0.6704, + "step": 5449 + }, + { + "epoch": 0.44, + "learning_rate": 1.7039330725771406e-05, + "loss": 0.5871, + "step": 5450 + }, + { + "epoch": 0.44, + "learning_rate": 1.703878748370274e-05, + "loss": 0.4379, + "step": 5451 + }, + { + "epoch": 0.44, + "learning_rate": 1.7038244241634074e-05, + "loss": 0.3176, + "step": 5452 + }, + { + "epoch": 0.44, + "learning_rate": 1.703770099956541e-05, + "loss": 0.5176, + "step": 5453 + }, + { + "epoch": 0.44, + "learning_rate": 1.7037157757496743e-05, + "loss": 0.3758, + "step": 5454 + }, + { + "epoch": 0.44, + "learning_rate": 1.7036614515428077e-05, + "loss": 0.3828, + "step": 5455 + }, + { + "epoch": 0.44, + "learning_rate": 1.703607127335941e-05, + "loss": 0.3615, + "step": 5456 + }, + { + "epoch": 0.44, + "learning_rate": 1.7035528031290745e-05, + "loss": 0.4828, + "step": 5457 + }, + { + "epoch": 0.44, + "learning_rate": 1.7034984789222076e-05, + "loss": 0.5424, + "step": 5458 + }, + { + "epoch": 0.44, + "learning_rate": 1.7034441547153414e-05, + "loss": 0.6503, + "step": 5459 + }, + { + "epoch": 0.44, + "learning_rate": 1.7033898305084745e-05, + "loss": 0.5163, + "step": 5460 + }, + { + "epoch": 0.44, + "learning_rate": 1.7033355063016082e-05, + "loss": 0.4724, + "step": 5461 + }, + { + "epoch": 0.45, + "learning_rate": 1.7032811820947413e-05, + "loss": 0.4589, + "step": 5462 + }, + { + "epoch": 0.45, + "learning_rate": 1.703226857887875e-05, + "loss": 0.3438, + "step": 5463 + }, + { + "epoch": 0.45, + "learning_rate": 1.7031725336810085e-05, + "loss": 0.3199, + "step": 5464 + }, + { + "epoch": 0.45, + "learning_rate": 1.703118209474142e-05, + "loss": 0.46, + "step": 5465 + }, + { + "epoch": 0.45, + "learning_rate": 1.7030638852672753e-05, + "loss": 0.6473, + "step": 5466 + }, + { + "epoch": 0.45, + "learning_rate": 1.7030095610604088e-05, + "loss": 0.3694, + "step": 5467 + }, + { + "epoch": 0.45, + "learning_rate": 1.7029552368535422e-05, + "loss": 0.4768, + "step": 5468 + }, + { + "epoch": 0.45, + "learning_rate": 1.7029009126466756e-05, + "loss": 0.7211, + "step": 5469 + }, + { + "epoch": 0.45, + "learning_rate": 1.702846588439809e-05, + "loss": 0.3698, + "step": 5470 + }, + { + "epoch": 0.45, + "learning_rate": 1.7027922642329424e-05, + "loss": 0.2846, + "step": 5471 + }, + { + "epoch": 0.45, + "learning_rate": 1.702737940026076e-05, + "loss": 0.4573, + "step": 5472 + }, + { + "epoch": 0.45, + "learning_rate": 1.7026836158192093e-05, + "loss": 0.5359, + "step": 5473 + }, + { + "epoch": 0.45, + "learning_rate": 1.7026292916123427e-05, + "loss": 0.545, + "step": 5474 + }, + { + "epoch": 0.45, + "learning_rate": 1.702574967405476e-05, + "loss": 0.4886, + "step": 5475 + }, + { + "epoch": 0.45, + "learning_rate": 1.7025206431986096e-05, + "loss": 0.6357, + "step": 5476 + }, + { + "epoch": 0.45, + "learning_rate": 1.7024663189917426e-05, + "loss": 0.3107, + "step": 5477 + }, + { + "epoch": 0.45, + "learning_rate": 1.7024119947848764e-05, + "loss": 0.4423, + "step": 5478 + }, + { + "epoch": 0.45, + "learning_rate": 1.7023576705780095e-05, + "loss": 0.5691, + "step": 5479 + }, + { + "epoch": 0.45, + "learning_rate": 1.7023033463711433e-05, + "loss": 0.6797, + "step": 5480 + }, + { + "epoch": 0.45, + "learning_rate": 1.7022490221642763e-05, + "loss": 0.3793, + "step": 5481 + }, + { + "epoch": 0.45, + "learning_rate": 1.70219469795741e-05, + "loss": 0.4918, + "step": 5482 + }, + { + "epoch": 0.45, + "learning_rate": 1.7021403737505432e-05, + "loss": 0.708, + "step": 5483 + }, + { + "epoch": 0.45, + "learning_rate": 1.702086049543677e-05, + "loss": 0.5577, + "step": 5484 + }, + { + "epoch": 0.45, + "learning_rate": 1.70203172533681e-05, + "loss": 0.7787, + "step": 5485 + }, + { + "epoch": 0.45, + "learning_rate": 1.7019774011299438e-05, + "loss": 0.4991, + "step": 5486 + }, + { + "epoch": 0.45, + "learning_rate": 1.701923076923077e-05, + "loss": 0.7068, + "step": 5487 + }, + { + "epoch": 0.45, + "learning_rate": 1.7018687527162106e-05, + "loss": 0.6118, + "step": 5488 + }, + { + "epoch": 0.45, + "learning_rate": 1.7018144285093437e-05, + "loss": 0.5161, + "step": 5489 + }, + { + "epoch": 0.45, + "learning_rate": 1.7017601043024775e-05, + "loss": 0.4601, + "step": 5490 + }, + { + "epoch": 0.45, + "learning_rate": 1.7017057800956106e-05, + "loss": 0.7713, + "step": 5491 + }, + { + "epoch": 0.45, + "learning_rate": 1.7016514558887443e-05, + "loss": 0.7059, + "step": 5492 + }, + { + "epoch": 0.45, + "learning_rate": 1.7015971316818774e-05, + "loss": 0.5514, + "step": 5493 + }, + { + "epoch": 0.45, + "learning_rate": 1.7015428074750112e-05, + "loss": 0.4017, + "step": 5494 + }, + { + "epoch": 0.45, + "learning_rate": 1.7014884832681443e-05, + "loss": 0.564, + "step": 5495 + }, + { + "epoch": 0.45, + "learning_rate": 1.7014341590612777e-05, + "loss": 0.3792, + "step": 5496 + }, + { + "epoch": 0.45, + "learning_rate": 1.701379834854411e-05, + "loss": 0.5567, + "step": 5497 + }, + { + "epoch": 0.45, + "learning_rate": 1.7013255106475445e-05, + "loss": 0.515, + "step": 5498 + }, + { + "epoch": 0.45, + "learning_rate": 1.701271186440678e-05, + "loss": 0.3533, + "step": 5499 + }, + { + "epoch": 0.45, + "learning_rate": 1.7012168622338114e-05, + "loss": 0.6654, + "step": 5500 + }, + { + "epoch": 0.45, + "eval_accuracy": 0.811207335710647, + "eval_loss": 0.4741332232952118, + "eval_runtime": 22.2816, + "eval_samples_per_second": 440.497, + "eval_steps_per_second": 3.456, + "step": 5500 + }, + { + "epoch": 0.45, + "learning_rate": 1.701162538026945e-05, + "loss": 0.5366, + "step": 5501 + }, + { + "epoch": 0.45, + "learning_rate": 1.7011082138200782e-05, + "loss": 0.5228, + "step": 5502 + }, + { + "epoch": 0.45, + "learning_rate": 1.701053889613212e-05, + "loss": 0.3579, + "step": 5503 + }, + { + "epoch": 0.45, + "learning_rate": 1.700999565406345e-05, + "loss": 0.4038, + "step": 5504 + }, + { + "epoch": 0.45, + "learning_rate": 1.700945241199479e-05, + "loss": 0.4888, + "step": 5505 + }, + { + "epoch": 0.45, + "learning_rate": 1.700890916992612e-05, + "loss": 0.5375, + "step": 5506 + }, + { + "epoch": 0.45, + "learning_rate": 1.7008365927857457e-05, + "loss": 0.4884, + "step": 5507 + }, + { + "epoch": 0.45, + "learning_rate": 1.7007822685788788e-05, + "loss": 0.4359, + "step": 5508 + }, + { + "epoch": 0.45, + "learning_rate": 1.7007279443720125e-05, + "loss": 0.5115, + "step": 5509 + }, + { + "epoch": 0.45, + "learning_rate": 1.7006736201651456e-05, + "loss": 0.7528, + "step": 5510 + }, + { + "epoch": 0.45, + "learning_rate": 1.7006192959582794e-05, + "loss": 0.5997, + "step": 5511 + }, + { + "epoch": 0.45, + "learning_rate": 1.7005649717514125e-05, + "loss": 0.6773, + "step": 5512 + }, + { + "epoch": 0.45, + "learning_rate": 1.7005106475445462e-05, + "loss": 0.4774, + "step": 5513 + }, + { + "epoch": 0.45, + "learning_rate": 1.7004563233376793e-05, + "loss": 0.4964, + "step": 5514 + }, + { + "epoch": 0.45, + "learning_rate": 1.7004019991308127e-05, + "loss": 0.5781, + "step": 5515 + }, + { + "epoch": 0.45, + "learning_rate": 1.700347674923946e-05, + "loss": 0.5035, + "step": 5516 + }, + { + "epoch": 0.45, + "learning_rate": 1.7002933507170796e-05, + "loss": 0.5286, + "step": 5517 + }, + { + "epoch": 0.45, + "learning_rate": 1.700239026510213e-05, + "loss": 0.3863, + "step": 5518 + }, + { + "epoch": 0.45, + "learning_rate": 1.7001847023033464e-05, + "loss": 0.4066, + "step": 5519 + }, + { + "epoch": 0.45, + "learning_rate": 1.70013037809648e-05, + "loss": 0.4581, + "step": 5520 + }, + { + "epoch": 0.45, + "learning_rate": 1.7000760538896133e-05, + "loss": 0.305, + "step": 5521 + }, + { + "epoch": 0.45, + "learning_rate": 1.7000217296827467e-05, + "loss": 0.3462, + "step": 5522 + }, + { + "epoch": 0.45, + "learning_rate": 1.69996740547588e-05, + "loss": 0.3775, + "step": 5523 + }, + { + "epoch": 0.45, + "learning_rate": 1.6999130812690135e-05, + "loss": 0.7196, + "step": 5524 + }, + { + "epoch": 0.45, + "learning_rate": 1.699858757062147e-05, + "loss": 0.2042, + "step": 5525 + }, + { + "epoch": 0.45, + "learning_rate": 1.6998044328552804e-05, + "loss": 0.5961, + "step": 5526 + }, + { + "epoch": 0.45, + "learning_rate": 1.6997501086484138e-05, + "loss": 0.6887, + "step": 5527 + }, + { + "epoch": 0.45, + "learning_rate": 1.6996957844415472e-05, + "loss": 0.4101, + "step": 5528 + }, + { + "epoch": 0.45, + "learning_rate": 1.6996414602346806e-05, + "loss": 0.3628, + "step": 5529 + }, + { + "epoch": 0.45, + "learning_rate": 1.699587136027814e-05, + "loss": 0.6411, + "step": 5530 + }, + { + "epoch": 0.45, + "learning_rate": 1.6995328118209475e-05, + "loss": 0.345, + "step": 5531 + }, + { + "epoch": 0.45, + "learning_rate": 1.699478487614081e-05, + "loss": 0.2901, + "step": 5532 + }, + { + "epoch": 0.45, + "learning_rate": 1.6994241634072143e-05, + "loss": 0.283, + "step": 5533 + }, + { + "epoch": 0.45, + "learning_rate": 1.6993698392003478e-05, + "loss": 0.6141, + "step": 5534 + }, + { + "epoch": 0.45, + "learning_rate": 1.6993155149934812e-05, + "loss": 0.5939, + "step": 5535 + }, + { + "epoch": 0.45, + "learning_rate": 1.6992611907866146e-05, + "loss": 0.7776, + "step": 5536 + }, + { + "epoch": 0.45, + "learning_rate": 1.699206866579748e-05, + "loss": 0.5653, + "step": 5537 + }, + { + "epoch": 0.45, + "learning_rate": 1.6991525423728815e-05, + "loss": 0.4658, + "step": 5538 + }, + { + "epoch": 0.45, + "learning_rate": 1.699098218166015e-05, + "loss": 0.4083, + "step": 5539 + }, + { + "epoch": 0.45, + "learning_rate": 1.6990438939591483e-05, + "loss": 0.4793, + "step": 5540 + }, + { + "epoch": 0.45, + "learning_rate": 1.6989895697522817e-05, + "loss": 0.2993, + "step": 5541 + }, + { + "epoch": 0.45, + "learning_rate": 1.698935245545415e-05, + "loss": 0.5641, + "step": 5542 + }, + { + "epoch": 0.45, + "learning_rate": 1.6988809213385486e-05, + "loss": 0.4158, + "step": 5543 + }, + { + "epoch": 0.45, + "learning_rate": 1.698826597131682e-05, + "loss": 0.6727, + "step": 5544 + }, + { + "epoch": 0.45, + "learning_rate": 1.6987722729248154e-05, + "loss": 0.4715, + "step": 5545 + }, + { + "epoch": 0.45, + "learning_rate": 1.698717948717949e-05, + "loss": 0.3674, + "step": 5546 + }, + { + "epoch": 0.45, + "learning_rate": 1.6986636245110823e-05, + "loss": 0.5658, + "step": 5547 + }, + { + "epoch": 0.45, + "learning_rate": 1.6986093003042157e-05, + "loss": 0.663, + "step": 5548 + }, + { + "epoch": 0.45, + "learning_rate": 1.698554976097349e-05, + "loss": 0.495, + "step": 5549 + }, + { + "epoch": 0.45, + "learning_rate": 1.6985006518904825e-05, + "loss": 0.3952, + "step": 5550 + }, + { + "epoch": 0.45, + "learning_rate": 1.698446327683616e-05, + "loss": 0.6896, + "step": 5551 + }, + { + "epoch": 0.45, + "learning_rate": 1.6983920034767494e-05, + "loss": 0.8652, + "step": 5552 + }, + { + "epoch": 0.45, + "learning_rate": 1.6983376792698828e-05, + "loss": 0.5308, + "step": 5553 + }, + { + "epoch": 0.45, + "learning_rate": 1.6982833550630162e-05, + "loss": 0.6432, + "step": 5554 + }, + { + "epoch": 0.45, + "learning_rate": 1.6982290308561496e-05, + "loss": 0.5415, + "step": 5555 + }, + { + "epoch": 0.45, + "learning_rate": 1.698174706649283e-05, + "loss": 0.3955, + "step": 5556 + }, + { + "epoch": 0.45, + "learning_rate": 1.6981203824424165e-05, + "loss": 0.313, + "step": 5557 + }, + { + "epoch": 0.45, + "learning_rate": 1.69806605823555e-05, + "loss": 0.5303, + "step": 5558 + }, + { + "epoch": 0.45, + "learning_rate": 1.6980117340286833e-05, + "loss": 0.5194, + "step": 5559 + }, + { + "epoch": 0.45, + "learning_rate": 1.6979574098218168e-05, + "loss": 0.5797, + "step": 5560 + }, + { + "epoch": 0.45, + "learning_rate": 1.6979030856149502e-05, + "loss": 0.5283, + "step": 5561 + }, + { + "epoch": 0.45, + "learning_rate": 1.6978487614080836e-05, + "loss": 0.4933, + "step": 5562 + }, + { + "epoch": 0.45, + "learning_rate": 1.697794437201217e-05, + "loss": 0.2391, + "step": 5563 + }, + { + "epoch": 0.45, + "learning_rate": 1.6977401129943505e-05, + "loss": 0.3323, + "step": 5564 + }, + { + "epoch": 0.45, + "learning_rate": 1.697685788787484e-05, + "loss": 0.6445, + "step": 5565 + }, + { + "epoch": 0.45, + "learning_rate": 1.6976314645806173e-05, + "loss": 0.5459, + "step": 5566 + }, + { + "epoch": 0.45, + "learning_rate": 1.6975771403737507e-05, + "loss": 0.278, + "step": 5567 + }, + { + "epoch": 0.45, + "learning_rate": 1.697522816166884e-05, + "loss": 0.5623, + "step": 5568 + }, + { + "epoch": 0.45, + "learning_rate": 1.6974684919600176e-05, + "loss": 0.4577, + "step": 5569 + }, + { + "epoch": 0.45, + "learning_rate": 1.697414167753151e-05, + "loss": 0.4052, + "step": 5570 + }, + { + "epoch": 0.45, + "learning_rate": 1.6973598435462844e-05, + "loss": 0.4359, + "step": 5571 + }, + { + "epoch": 0.45, + "learning_rate": 1.697305519339418e-05, + "loss": 0.6572, + "step": 5572 + }, + { + "epoch": 0.45, + "learning_rate": 1.6972511951325513e-05, + "loss": 0.2529, + "step": 5573 + }, + { + "epoch": 0.45, + "learning_rate": 1.6971968709256847e-05, + "loss": 0.4589, + "step": 5574 + }, + { + "epoch": 0.45, + "learning_rate": 1.697142546718818e-05, + "loss": 0.4035, + "step": 5575 + }, + { + "epoch": 0.45, + "learning_rate": 1.6970882225119515e-05, + "loss": 0.5412, + "step": 5576 + }, + { + "epoch": 0.45, + "learning_rate": 1.697033898305085e-05, + "loss": 0.2176, + "step": 5577 + }, + { + "epoch": 0.45, + "learning_rate": 1.6969795740982184e-05, + "loss": 0.4546, + "step": 5578 + }, + { + "epoch": 0.45, + "learning_rate": 1.6969252498913518e-05, + "loss": 0.3019, + "step": 5579 + }, + { + "epoch": 0.45, + "learning_rate": 1.6968709256844852e-05, + "loss": 0.5527, + "step": 5580 + }, + { + "epoch": 0.45, + "learning_rate": 1.6968166014776186e-05, + "loss": 0.5554, + "step": 5581 + }, + { + "epoch": 0.45, + "learning_rate": 1.696762277270752e-05, + "loss": 0.6801, + "step": 5582 + }, + { + "epoch": 0.45, + "learning_rate": 1.6967079530638855e-05, + "loss": 0.5163, + "step": 5583 + }, + { + "epoch": 0.46, + "learning_rate": 1.696653628857019e-05, + "loss": 0.5713, + "step": 5584 + }, + { + "epoch": 0.46, + "learning_rate": 1.6965993046501523e-05, + "loss": 0.5384, + "step": 5585 + }, + { + "epoch": 0.46, + "learning_rate": 1.6965449804432858e-05, + "loss": 0.3141, + "step": 5586 + }, + { + "epoch": 0.46, + "learning_rate": 1.6964906562364192e-05, + "loss": 0.2563, + "step": 5587 + }, + { + "epoch": 0.46, + "learning_rate": 1.6964363320295526e-05, + "loss": 0.4491, + "step": 5588 + }, + { + "epoch": 0.46, + "learning_rate": 1.696382007822686e-05, + "loss": 0.4964, + "step": 5589 + }, + { + "epoch": 0.46, + "learning_rate": 1.6963276836158195e-05, + "loss": 0.5701, + "step": 5590 + }, + { + "epoch": 0.46, + "learning_rate": 1.6962733594089525e-05, + "loss": 0.6275, + "step": 5591 + }, + { + "epoch": 0.46, + "learning_rate": 1.6962190352020863e-05, + "loss": 0.455, + "step": 5592 + }, + { + "epoch": 0.46, + "learning_rate": 1.6961647109952194e-05, + "loss": 0.4797, + "step": 5593 + }, + { + "epoch": 0.46, + "learning_rate": 1.696110386788353e-05, + "loss": 0.6684, + "step": 5594 + }, + { + "epoch": 0.46, + "learning_rate": 1.6960560625814862e-05, + "loss": 0.616, + "step": 5595 + }, + { + "epoch": 0.46, + "learning_rate": 1.69600173837462e-05, + "loss": 0.814, + "step": 5596 + }, + { + "epoch": 0.46, + "learning_rate": 1.695947414167753e-05, + "loss": 0.5915, + "step": 5597 + }, + { + "epoch": 0.46, + "learning_rate": 1.695893089960887e-05, + "loss": 0.3269, + "step": 5598 + }, + { + "epoch": 0.46, + "learning_rate": 1.69583876575402e-05, + "loss": 0.3875, + "step": 5599 + }, + { + "epoch": 0.46, + "learning_rate": 1.6957844415471537e-05, + "loss": 0.6852, + "step": 5600 + }, + { + "epoch": 0.46, + "learning_rate": 1.6957301173402868e-05, + "loss": 0.517, + "step": 5601 + }, + { + "epoch": 0.46, + "learning_rate": 1.6956757931334205e-05, + "loss": 0.4601, + "step": 5602 + }, + { + "epoch": 0.46, + "learning_rate": 1.6956214689265536e-05, + "loss": 0.6975, + "step": 5603 + }, + { + "epoch": 0.46, + "learning_rate": 1.6955671447196874e-05, + "loss": 0.4045, + "step": 5604 + }, + { + "epoch": 0.46, + "learning_rate": 1.6955128205128205e-05, + "loss": 0.6417, + "step": 5605 + }, + { + "epoch": 0.46, + "learning_rate": 1.6954584963059542e-05, + "loss": 0.5238, + "step": 5606 + }, + { + "epoch": 0.46, + "learning_rate": 1.6954041720990873e-05, + "loss": 0.4461, + "step": 5607 + }, + { + "epoch": 0.46, + "learning_rate": 1.695349847892221e-05, + "loss": 0.461, + "step": 5608 + }, + { + "epoch": 0.46, + "learning_rate": 1.6952955236853545e-05, + "loss": 0.4421, + "step": 5609 + }, + { + "epoch": 0.46, + "learning_rate": 1.6952411994784876e-05, + "loss": 0.4058, + "step": 5610 + }, + { + "epoch": 0.46, + "learning_rate": 1.6951868752716213e-05, + "loss": 0.5468, + "step": 5611 + }, + { + "epoch": 0.46, + "learning_rate": 1.6951325510647544e-05, + "loss": 0.5242, + "step": 5612 + }, + { + "epoch": 0.46, + "learning_rate": 1.6950782268578882e-05, + "loss": 0.4499, + "step": 5613 + }, + { + "epoch": 0.46, + "learning_rate": 1.6950239026510213e-05, + "loss": 0.4046, + "step": 5614 + }, + { + "epoch": 0.46, + "learning_rate": 1.694969578444155e-05, + "loss": 0.6735, + "step": 5615 + }, + { + "epoch": 0.46, + "learning_rate": 1.694915254237288e-05, + "loss": 0.3456, + "step": 5616 + }, + { + "epoch": 0.46, + "learning_rate": 1.694860930030422e-05, + "loss": 0.3697, + "step": 5617 + }, + { + "epoch": 0.46, + "learning_rate": 1.694806605823555e-05, + "loss": 0.4857, + "step": 5618 + }, + { + "epoch": 0.46, + "learning_rate": 1.6947522816166887e-05, + "loss": 0.4286, + "step": 5619 + }, + { + "epoch": 0.46, + "learning_rate": 1.6946979574098218e-05, + "loss": 0.5006, + "step": 5620 + }, + { + "epoch": 0.46, + "learning_rate": 1.6946436332029556e-05, + "loss": 0.6576, + "step": 5621 + }, + { + "epoch": 0.46, + "learning_rate": 1.6945893089960887e-05, + "loss": 0.3018, + "step": 5622 + }, + { + "epoch": 0.46, + "learning_rate": 1.6945349847892224e-05, + "loss": 0.5035, + "step": 5623 + }, + { + "epoch": 0.46, + "learning_rate": 1.6944806605823555e-05, + "loss": 0.5259, + "step": 5624 + }, + { + "epoch": 0.46, + "learning_rate": 1.6944263363754893e-05, + "loss": 0.6026, + "step": 5625 + }, + { + "epoch": 0.46, + "learning_rate": 1.6943720121686223e-05, + "loss": 0.5772, + "step": 5626 + }, + { + "epoch": 0.46, + "learning_rate": 1.694317687961756e-05, + "loss": 0.4672, + "step": 5627 + }, + { + "epoch": 0.46, + "learning_rate": 1.6942633637548892e-05, + "loss": 0.5101, + "step": 5628 + }, + { + "epoch": 0.46, + "learning_rate": 1.6942090395480226e-05, + "loss": 0.2721, + "step": 5629 + }, + { + "epoch": 0.46, + "learning_rate": 1.694154715341156e-05, + "loss": 0.4398, + "step": 5630 + }, + { + "epoch": 0.46, + "learning_rate": 1.6941003911342895e-05, + "loss": 0.4293, + "step": 5631 + }, + { + "epoch": 0.46, + "learning_rate": 1.694046066927423e-05, + "loss": 0.3446, + "step": 5632 + }, + { + "epoch": 0.46, + "learning_rate": 1.6939917427205563e-05, + "loss": 0.6221, + "step": 5633 + }, + { + "epoch": 0.46, + "learning_rate": 1.6939374185136897e-05, + "loss": 0.4112, + "step": 5634 + }, + { + "epoch": 0.46, + "learning_rate": 1.693883094306823e-05, + "loss": 0.507, + "step": 5635 + }, + { + "epoch": 0.46, + "learning_rate": 1.6938287700999566e-05, + "loss": 0.2669, + "step": 5636 + }, + { + "epoch": 0.46, + "learning_rate": 1.69377444589309e-05, + "loss": 0.4783, + "step": 5637 + }, + { + "epoch": 0.46, + "learning_rate": 1.6937201216862234e-05, + "loss": 0.5155, + "step": 5638 + }, + { + "epoch": 0.46, + "learning_rate": 1.693665797479357e-05, + "loss": 0.4909, + "step": 5639 + }, + { + "epoch": 0.46, + "learning_rate": 1.6936114732724903e-05, + "loss": 0.3856, + "step": 5640 + }, + { + "epoch": 0.46, + "learning_rate": 1.6935571490656237e-05, + "loss": 0.4376, + "step": 5641 + }, + { + "epoch": 0.46, + "learning_rate": 1.693502824858757e-05, + "loss": 0.7514, + "step": 5642 + }, + { + "epoch": 0.46, + "learning_rate": 1.6934485006518905e-05, + "loss": 0.39, + "step": 5643 + }, + { + "epoch": 0.46, + "learning_rate": 1.6933941764450243e-05, + "loss": 0.4054, + "step": 5644 + }, + { + "epoch": 0.46, + "learning_rate": 1.6933398522381574e-05, + "loss": 0.3803, + "step": 5645 + }, + { + "epoch": 0.46, + "learning_rate": 1.693285528031291e-05, + "loss": 0.5258, + "step": 5646 + }, + { + "epoch": 0.46, + "learning_rate": 1.6932312038244242e-05, + "loss": 0.467, + "step": 5647 + }, + { + "epoch": 0.46, + "learning_rate": 1.6931768796175577e-05, + "loss": 0.3973, + "step": 5648 + }, + { + "epoch": 0.46, + "learning_rate": 1.693122555410691e-05, + "loss": 0.4599, + "step": 5649 + }, + { + "epoch": 0.46, + "learning_rate": 1.6930682312038245e-05, + "loss": 0.5145, + "step": 5650 + }, + { + "epoch": 0.46, + "learning_rate": 1.693013906996958e-05, + "loss": 0.5936, + "step": 5651 + }, + { + "epoch": 0.46, + "learning_rate": 1.6929595827900913e-05, + "loss": 0.4004, + "step": 5652 + }, + { + "epoch": 0.46, + "learning_rate": 1.6929052585832248e-05, + "loss": 0.2985, + "step": 5653 + }, + { + "epoch": 0.46, + "learning_rate": 1.6928509343763582e-05, + "loss": 0.4869, + "step": 5654 + }, + { + "epoch": 0.46, + "learning_rate": 1.6927966101694916e-05, + "loss": 0.4271, + "step": 5655 + }, + { + "epoch": 0.46, + "learning_rate": 1.692742285962625e-05, + "loss": 0.3827, + "step": 5656 + }, + { + "epoch": 0.46, + "learning_rate": 1.6926879617557585e-05, + "loss": 0.6159, + "step": 5657 + }, + { + "epoch": 0.46, + "learning_rate": 1.692633637548892e-05, + "loss": 0.6122, + "step": 5658 + }, + { + "epoch": 0.46, + "learning_rate": 1.6925793133420253e-05, + "loss": 0.2657, + "step": 5659 + }, + { + "epoch": 0.46, + "learning_rate": 1.6925249891351587e-05, + "loss": 0.2633, + "step": 5660 + }, + { + "epoch": 0.46, + "learning_rate": 1.692470664928292e-05, + "loss": 0.6755, + "step": 5661 + }, + { + "epoch": 0.46, + "learning_rate": 1.6924163407214256e-05, + "loss": 0.6252, + "step": 5662 + }, + { + "epoch": 0.46, + "learning_rate": 1.692362016514559e-05, + "loss": 0.4002, + "step": 5663 + }, + { + "epoch": 0.46, + "learning_rate": 1.6923076923076924e-05, + "loss": 0.4089, + "step": 5664 + }, + { + "epoch": 0.46, + "learning_rate": 1.692253368100826e-05, + "loss": 0.4313, + "step": 5665 + }, + { + "epoch": 0.46, + "learning_rate": 1.6921990438939593e-05, + "loss": 0.5437, + "step": 5666 + }, + { + "epoch": 0.46, + "learning_rate": 1.6921447196870927e-05, + "loss": 0.4569, + "step": 5667 + }, + { + "epoch": 0.46, + "learning_rate": 1.692090395480226e-05, + "loss": 0.436, + "step": 5668 + }, + { + "epoch": 0.46, + "learning_rate": 1.6920360712733595e-05, + "loss": 0.5115, + "step": 5669 + }, + { + "epoch": 0.46, + "learning_rate": 1.691981747066493e-05, + "loss": 0.5373, + "step": 5670 + }, + { + "epoch": 0.46, + "learning_rate": 1.6919274228596264e-05, + "loss": 0.6543, + "step": 5671 + }, + { + "epoch": 0.46, + "learning_rate": 1.6918730986527598e-05, + "loss": 0.6694, + "step": 5672 + }, + { + "epoch": 0.46, + "learning_rate": 1.6918187744458932e-05, + "loss": 0.4324, + "step": 5673 + }, + { + "epoch": 0.46, + "learning_rate": 1.6917644502390267e-05, + "loss": 0.8127, + "step": 5674 + }, + { + "epoch": 0.46, + "learning_rate": 1.69171012603216e-05, + "loss": 0.4711, + "step": 5675 + }, + { + "epoch": 0.46, + "learning_rate": 1.6916558018252935e-05, + "loss": 0.6618, + "step": 5676 + }, + { + "epoch": 0.46, + "learning_rate": 1.691601477618427e-05, + "loss": 0.7015, + "step": 5677 + }, + { + "epoch": 0.46, + "learning_rate": 1.6915471534115603e-05, + "loss": 0.565, + "step": 5678 + }, + { + "epoch": 0.46, + "learning_rate": 1.6914928292046938e-05, + "loss": 0.4811, + "step": 5679 + }, + { + "epoch": 0.46, + "learning_rate": 1.6914385049978272e-05, + "loss": 0.5452, + "step": 5680 + }, + { + "epoch": 0.46, + "learning_rate": 1.6913841807909606e-05, + "loss": 0.5372, + "step": 5681 + }, + { + "epoch": 0.46, + "learning_rate": 1.691329856584094e-05, + "loss": 0.4267, + "step": 5682 + }, + { + "epoch": 0.46, + "learning_rate": 1.6912755323772275e-05, + "loss": 0.4862, + "step": 5683 + }, + { + "epoch": 0.46, + "learning_rate": 1.691221208170361e-05, + "loss": 0.4806, + "step": 5684 + }, + { + "epoch": 0.46, + "learning_rate": 1.6911668839634943e-05, + "loss": 0.4656, + "step": 5685 + }, + { + "epoch": 0.46, + "learning_rate": 1.6911125597566277e-05, + "loss": 0.4699, + "step": 5686 + }, + { + "epoch": 0.46, + "learning_rate": 1.691058235549761e-05, + "loss": 0.7049, + "step": 5687 + }, + { + "epoch": 0.46, + "learning_rate": 1.6910039113428946e-05, + "loss": 0.3769, + "step": 5688 + }, + { + "epoch": 0.46, + "learning_rate": 1.690949587136028e-05, + "loss": 0.3576, + "step": 5689 + }, + { + "epoch": 0.46, + "learning_rate": 1.6908952629291614e-05, + "loss": 0.6484, + "step": 5690 + }, + { + "epoch": 0.46, + "learning_rate": 1.690840938722295e-05, + "loss": 0.5094, + "step": 5691 + }, + { + "epoch": 0.46, + "learning_rate": 1.6907866145154283e-05, + "loss": 0.3317, + "step": 5692 + }, + { + "epoch": 0.46, + "learning_rate": 1.6907322903085617e-05, + "loss": 0.5865, + "step": 5693 + }, + { + "epoch": 0.46, + "learning_rate": 1.690677966101695e-05, + "loss": 0.5306, + "step": 5694 + }, + { + "epoch": 0.46, + "learning_rate": 1.6906236418948285e-05, + "loss": 0.3435, + "step": 5695 + }, + { + "epoch": 0.46, + "learning_rate": 1.690569317687962e-05, + "loss": 0.4035, + "step": 5696 + }, + { + "epoch": 0.46, + "learning_rate": 1.6905149934810954e-05, + "loss": 0.6289, + "step": 5697 + }, + { + "epoch": 0.46, + "learning_rate": 1.6904606692742288e-05, + "loss": 0.5513, + "step": 5698 + }, + { + "epoch": 0.46, + "learning_rate": 1.6904063450673622e-05, + "loss": 0.2872, + "step": 5699 + }, + { + "epoch": 0.46, + "learning_rate": 1.6903520208604957e-05, + "loss": 0.4044, + "step": 5700 + }, + { + "epoch": 0.46, + "learning_rate": 1.690297696653629e-05, + "loss": 0.7735, + "step": 5701 + }, + { + "epoch": 0.46, + "learning_rate": 1.6902433724467625e-05, + "loss": 0.5673, + "step": 5702 + }, + { + "epoch": 0.46, + "learning_rate": 1.690189048239896e-05, + "loss": 0.5054, + "step": 5703 + }, + { + "epoch": 0.46, + "learning_rate": 1.6901347240330293e-05, + "loss": 0.6095, + "step": 5704 + }, + { + "epoch": 0.46, + "learning_rate": 1.6900803998261624e-05, + "loss": 0.3852, + "step": 5705 + }, + { + "epoch": 0.46, + "learning_rate": 1.6900260756192962e-05, + "loss": 0.2966, + "step": 5706 + }, + { + "epoch": 0.47, + "learning_rate": 1.6899717514124293e-05, + "loss": 0.5054, + "step": 5707 + }, + { + "epoch": 0.47, + "learning_rate": 1.689917427205563e-05, + "loss": 0.473, + "step": 5708 + }, + { + "epoch": 0.47, + "learning_rate": 1.689863102998696e-05, + "loss": 0.3178, + "step": 5709 + }, + { + "epoch": 0.47, + "learning_rate": 1.68980877879183e-05, + "loss": 0.3507, + "step": 5710 + }, + { + "epoch": 0.47, + "learning_rate": 1.689754454584963e-05, + "loss": 0.4433, + "step": 5711 + }, + { + "epoch": 0.47, + "learning_rate": 1.6897001303780967e-05, + "loss": 0.6256, + "step": 5712 + }, + { + "epoch": 0.47, + "learning_rate": 1.6896458061712298e-05, + "loss": 0.3688, + "step": 5713 + }, + { + "epoch": 0.47, + "learning_rate": 1.6895914819643636e-05, + "loss": 0.4719, + "step": 5714 + }, + { + "epoch": 0.47, + "learning_rate": 1.6895371577574967e-05, + "loss": 0.3585, + "step": 5715 + }, + { + "epoch": 0.47, + "learning_rate": 1.6894828335506304e-05, + "loss": 0.389, + "step": 5716 + }, + { + "epoch": 0.47, + "learning_rate": 1.689428509343764e-05, + "loss": 0.5122, + "step": 5717 + }, + { + "epoch": 0.47, + "learning_rate": 1.6893741851368973e-05, + "loss": 0.3887, + "step": 5718 + }, + { + "epoch": 0.47, + "learning_rate": 1.6893198609300307e-05, + "loss": 0.5717, + "step": 5719 + }, + { + "epoch": 0.47, + "learning_rate": 1.689265536723164e-05, + "loss": 0.6654, + "step": 5720 + }, + { + "epoch": 0.47, + "learning_rate": 1.6892112125162975e-05, + "loss": 0.5746, + "step": 5721 + }, + { + "epoch": 0.47, + "learning_rate": 1.689156888309431e-05, + "loss": 0.485, + "step": 5722 + }, + { + "epoch": 0.47, + "learning_rate": 1.6891025641025644e-05, + "loss": 0.4465, + "step": 5723 + }, + { + "epoch": 0.47, + "learning_rate": 1.6890482398956975e-05, + "loss": 0.3997, + "step": 5724 + }, + { + "epoch": 0.47, + "learning_rate": 1.6889939156888312e-05, + "loss": 0.4008, + "step": 5725 + }, + { + "epoch": 0.47, + "learning_rate": 1.6889395914819643e-05, + "loss": 0.4382, + "step": 5726 + }, + { + "epoch": 0.47, + "learning_rate": 1.688885267275098e-05, + "loss": 0.5456, + "step": 5727 + }, + { + "epoch": 0.47, + "learning_rate": 1.688830943068231e-05, + "loss": 0.7264, + "step": 5728 + }, + { + "epoch": 0.47, + "learning_rate": 1.688776618861365e-05, + "loss": 0.4485, + "step": 5729 + }, + { + "epoch": 0.47, + "learning_rate": 1.688722294654498e-05, + "loss": 0.2954, + "step": 5730 + }, + { + "epoch": 0.47, + "learning_rate": 1.6886679704476318e-05, + "loss": 0.513, + "step": 5731 + }, + { + "epoch": 0.47, + "learning_rate": 1.688613646240765e-05, + "loss": 0.6457, + "step": 5732 + }, + { + "epoch": 0.47, + "learning_rate": 1.6885593220338986e-05, + "loss": 0.4182, + "step": 5733 + }, + { + "epoch": 0.47, + "learning_rate": 1.6885049978270317e-05, + "loss": 0.3635, + "step": 5734 + }, + { + "epoch": 0.47, + "learning_rate": 1.6884506736201655e-05, + "loss": 0.6411, + "step": 5735 + }, + { + "epoch": 0.47, + "learning_rate": 1.6883963494132985e-05, + "loss": 0.4274, + "step": 5736 + }, + { + "epoch": 0.47, + "learning_rate": 1.6883420252064323e-05, + "loss": 0.375, + "step": 5737 + }, + { + "epoch": 0.47, + "learning_rate": 1.6882877009995654e-05, + "loss": 0.5796, + "step": 5738 + }, + { + "epoch": 0.47, + "learning_rate": 1.688233376792699e-05, + "loss": 0.7142, + "step": 5739 + }, + { + "epoch": 0.47, + "learning_rate": 1.6881790525858322e-05, + "loss": 0.3861, + "step": 5740 + }, + { + "epoch": 0.47, + "learning_rate": 1.688124728378966e-05, + "loss": 0.4625, + "step": 5741 + }, + { + "epoch": 0.47, + "learning_rate": 1.688070404172099e-05, + "loss": 0.74, + "step": 5742 + }, + { + "epoch": 0.47, + "learning_rate": 1.6880160799652325e-05, + "loss": 0.3111, + "step": 5743 + }, + { + "epoch": 0.47, + "learning_rate": 1.687961755758366e-05, + "loss": 0.3666, + "step": 5744 + }, + { + "epoch": 0.47, + "learning_rate": 1.6879074315514993e-05, + "loss": 0.3735, + "step": 5745 + }, + { + "epoch": 0.47, + "learning_rate": 1.6878531073446328e-05, + "loss": 0.5731, + "step": 5746 + }, + { + "epoch": 0.47, + "learning_rate": 1.6877987831377662e-05, + "loss": 0.4273, + "step": 5747 + }, + { + "epoch": 0.47, + "learning_rate": 1.6877444589308996e-05, + "loss": 0.4611, + "step": 5748 + }, + { + "epoch": 0.47, + "learning_rate": 1.687690134724033e-05, + "loss": 0.3357, + "step": 5749 + }, + { + "epoch": 0.47, + "learning_rate": 1.6876358105171665e-05, + "loss": 0.5021, + "step": 5750 + }, + { + "epoch": 0.47, + "eval_accuracy": 0.8160978094752929, + "eval_loss": 0.46806398034095764, + "eval_runtime": 22.3747, + "eval_samples_per_second": 438.664, + "eval_steps_per_second": 3.441, + "step": 5750 + }, + { + "epoch": 0.47, + "learning_rate": 1.6875814863103e-05, + "loss": 0.3537, + "step": 5751 + }, + { + "epoch": 0.47, + "learning_rate": 1.6875271621034336e-05, + "loss": 0.4684, + "step": 5752 + }, + { + "epoch": 0.47, + "learning_rate": 1.6874728378965667e-05, + "loss": 0.3172, + "step": 5753 + }, + { + "epoch": 0.47, + "learning_rate": 1.6874185136897005e-05, + "loss": 0.365, + "step": 5754 + }, + { + "epoch": 0.47, + "learning_rate": 1.6873641894828336e-05, + "loss": 0.3822, + "step": 5755 + }, + { + "epoch": 0.47, + "learning_rate": 1.6873098652759673e-05, + "loss": 0.5129, + "step": 5756 + }, + { + "epoch": 0.47, + "learning_rate": 1.6872555410691004e-05, + "loss": 0.8921, + "step": 5757 + }, + { + "epoch": 0.47, + "learning_rate": 1.6872012168622342e-05, + "loss": 0.4491, + "step": 5758 + }, + { + "epoch": 0.47, + "learning_rate": 1.6871468926553673e-05, + "loss": 0.5952, + "step": 5759 + }, + { + "epoch": 0.47, + "learning_rate": 1.687092568448501e-05, + "loss": 0.5174, + "step": 5760 + }, + { + "epoch": 0.47, + "learning_rate": 1.687038244241634e-05, + "loss": 0.4874, + "step": 5761 + }, + { + "epoch": 0.47, + "learning_rate": 1.686983920034768e-05, + "loss": 0.4994, + "step": 5762 + }, + { + "epoch": 0.47, + "learning_rate": 1.686929595827901e-05, + "loss": 0.6186, + "step": 5763 + }, + { + "epoch": 0.47, + "learning_rate": 1.6868752716210344e-05, + "loss": 0.5583, + "step": 5764 + }, + { + "epoch": 0.47, + "learning_rate": 1.6868209474141678e-05, + "loss": 0.4344, + "step": 5765 + }, + { + "epoch": 0.47, + "learning_rate": 1.6867666232073012e-05, + "loss": 0.4368, + "step": 5766 + }, + { + "epoch": 0.47, + "learning_rate": 1.6867122990004347e-05, + "loss": 0.4713, + "step": 5767 + }, + { + "epoch": 0.47, + "learning_rate": 1.686657974793568e-05, + "loss": 0.3894, + "step": 5768 + }, + { + "epoch": 0.47, + "learning_rate": 1.6866036505867015e-05, + "loss": 0.4058, + "step": 5769 + }, + { + "epoch": 0.47, + "learning_rate": 1.686549326379835e-05, + "loss": 0.5849, + "step": 5770 + }, + { + "epoch": 0.47, + "learning_rate": 1.6864950021729683e-05, + "loss": 0.4476, + "step": 5771 + }, + { + "epoch": 0.47, + "learning_rate": 1.6864406779661018e-05, + "loss": 0.6502, + "step": 5772 + }, + { + "epoch": 0.47, + "learning_rate": 1.6863863537592352e-05, + "loss": 0.3778, + "step": 5773 + }, + { + "epoch": 0.47, + "learning_rate": 1.6863320295523686e-05, + "loss": 0.3882, + "step": 5774 + }, + { + "epoch": 0.47, + "learning_rate": 1.686277705345502e-05, + "loss": 0.3664, + "step": 5775 + }, + { + "epoch": 0.47, + "learning_rate": 1.6862233811386355e-05, + "loss": 0.5396, + "step": 5776 + }, + { + "epoch": 0.47, + "learning_rate": 1.686169056931769e-05, + "loss": 0.5521, + "step": 5777 + }, + { + "epoch": 0.47, + "learning_rate": 1.6861147327249023e-05, + "loss": 0.5726, + "step": 5778 + }, + { + "epoch": 0.47, + "learning_rate": 1.6860604085180357e-05, + "loss": 0.5045, + "step": 5779 + }, + { + "epoch": 0.47, + "learning_rate": 1.686006084311169e-05, + "loss": 0.4758, + "step": 5780 + }, + { + "epoch": 0.47, + "learning_rate": 1.6859517601043026e-05, + "loss": 0.3791, + "step": 5781 + }, + { + "epoch": 0.47, + "learning_rate": 1.685897435897436e-05, + "loss": 0.3513, + "step": 5782 + }, + { + "epoch": 0.47, + "learning_rate": 1.6858431116905694e-05, + "loss": 0.4641, + "step": 5783 + }, + { + "epoch": 0.47, + "learning_rate": 1.685788787483703e-05, + "loss": 0.2956, + "step": 5784 + }, + { + "epoch": 0.47, + "learning_rate": 1.6857344632768363e-05, + "loss": 0.4492, + "step": 5785 + }, + { + "epoch": 0.47, + "learning_rate": 1.6856801390699697e-05, + "loss": 0.5248, + "step": 5786 + }, + { + "epoch": 0.47, + "learning_rate": 1.685625814863103e-05, + "loss": 0.521, + "step": 5787 + }, + { + "epoch": 0.47, + "learning_rate": 1.6855714906562365e-05, + "loss": 0.3363, + "step": 5788 + }, + { + "epoch": 0.47, + "learning_rate": 1.68551716644937e-05, + "loss": 0.4478, + "step": 5789 + }, + { + "epoch": 0.47, + "learning_rate": 1.6854628422425034e-05, + "loss": 0.4229, + "step": 5790 + }, + { + "epoch": 0.47, + "learning_rate": 1.6854085180356368e-05, + "loss": 0.5571, + "step": 5791 + }, + { + "epoch": 0.47, + "learning_rate": 1.6853541938287702e-05, + "loss": 0.4221, + "step": 5792 + }, + { + "epoch": 0.47, + "learning_rate": 1.6852998696219037e-05, + "loss": 0.4068, + "step": 5793 + }, + { + "epoch": 0.47, + "learning_rate": 1.685245545415037e-05, + "loss": 0.5598, + "step": 5794 + }, + { + "epoch": 0.47, + "learning_rate": 1.6851912212081705e-05, + "loss": 0.5523, + "step": 5795 + }, + { + "epoch": 0.47, + "learning_rate": 1.685136897001304e-05, + "loss": 0.6396, + "step": 5796 + }, + { + "epoch": 0.47, + "learning_rate": 1.6850825727944373e-05, + "loss": 0.3788, + "step": 5797 + }, + { + "epoch": 0.47, + "learning_rate": 1.6850282485875708e-05, + "loss": 0.4781, + "step": 5798 + }, + { + "epoch": 0.47, + "learning_rate": 1.6849739243807042e-05, + "loss": 0.5264, + "step": 5799 + }, + { + "epoch": 0.47, + "learning_rate": 1.6849196001738376e-05, + "loss": 0.3179, + "step": 5800 + }, + { + "epoch": 0.47, + "learning_rate": 1.684865275966971e-05, + "loss": 0.4725, + "step": 5801 + }, + { + "epoch": 0.47, + "learning_rate": 1.6848109517601045e-05, + "loss": 0.743, + "step": 5802 + }, + { + "epoch": 0.47, + "learning_rate": 1.684756627553238e-05, + "loss": 0.4582, + "step": 5803 + }, + { + "epoch": 0.47, + "learning_rate": 1.6847023033463713e-05, + "loss": 0.7571, + "step": 5804 + }, + { + "epoch": 0.47, + "learning_rate": 1.6846479791395047e-05, + "loss": 0.4895, + "step": 5805 + }, + { + "epoch": 0.47, + "learning_rate": 1.684593654932638e-05, + "loss": 0.9108, + "step": 5806 + }, + { + "epoch": 0.47, + "learning_rate": 1.6845393307257716e-05, + "loss": 0.5342, + "step": 5807 + }, + { + "epoch": 0.47, + "learning_rate": 1.684485006518905e-05, + "loss": 0.3745, + "step": 5808 + }, + { + "epoch": 0.47, + "learning_rate": 1.6844306823120384e-05, + "loss": 0.4793, + "step": 5809 + }, + { + "epoch": 0.47, + "learning_rate": 1.684376358105172e-05, + "loss": 0.5977, + "step": 5810 + }, + { + "epoch": 0.47, + "learning_rate": 1.6843220338983053e-05, + "loss": 0.374, + "step": 5811 + }, + { + "epoch": 0.47, + "learning_rate": 1.6842677096914387e-05, + "loss": 0.5444, + "step": 5812 + }, + { + "epoch": 0.47, + "learning_rate": 1.684213385484572e-05, + "loss": 0.5151, + "step": 5813 + }, + { + "epoch": 0.47, + "learning_rate": 1.6841590612777055e-05, + "loss": 0.4106, + "step": 5814 + }, + { + "epoch": 0.47, + "learning_rate": 1.684104737070839e-05, + "loss": 0.4493, + "step": 5815 + }, + { + "epoch": 0.47, + "learning_rate": 1.6840504128639724e-05, + "loss": 0.3664, + "step": 5816 + }, + { + "epoch": 0.47, + "learning_rate": 1.6839960886571058e-05, + "loss": 0.7576, + "step": 5817 + }, + { + "epoch": 0.47, + "learning_rate": 1.6839417644502392e-05, + "loss": 0.3203, + "step": 5818 + }, + { + "epoch": 0.47, + "learning_rate": 1.6838874402433727e-05, + "loss": 0.621, + "step": 5819 + }, + { + "epoch": 0.47, + "learning_rate": 1.683833116036506e-05, + "loss": 0.6079, + "step": 5820 + }, + { + "epoch": 0.47, + "learning_rate": 1.683778791829639e-05, + "loss": 0.6086, + "step": 5821 + }, + { + "epoch": 0.47, + "learning_rate": 1.683724467622773e-05, + "loss": 0.4214, + "step": 5822 + }, + { + "epoch": 0.47, + "learning_rate": 1.683670143415906e-05, + "loss": 0.35, + "step": 5823 + }, + { + "epoch": 0.47, + "learning_rate": 1.6836158192090398e-05, + "loss": 0.7902, + "step": 5824 + }, + { + "epoch": 0.47, + "learning_rate": 1.6835614950021732e-05, + "loss": 0.5735, + "step": 5825 + }, + { + "epoch": 0.47, + "learning_rate": 1.6835071707953066e-05, + "loss": 0.4414, + "step": 5826 + }, + { + "epoch": 0.47, + "learning_rate": 1.68345284658844e-05, + "loss": 0.4651, + "step": 5827 + }, + { + "epoch": 0.47, + "learning_rate": 1.6833985223815735e-05, + "loss": 0.4233, + "step": 5828 + }, + { + "epoch": 0.47, + "learning_rate": 1.683344198174707e-05, + "loss": 0.638, + "step": 5829 + }, + { + "epoch": 0.48, + "learning_rate": 1.6832898739678403e-05, + "loss": 0.3053, + "step": 5830 + }, + { + "epoch": 0.48, + "learning_rate": 1.6832355497609737e-05, + "loss": 0.7054, + "step": 5831 + }, + { + "epoch": 0.48, + "learning_rate": 1.683181225554107e-05, + "loss": 0.6905, + "step": 5832 + }, + { + "epoch": 0.48, + "learning_rate": 1.6831269013472406e-05, + "loss": 0.5679, + "step": 5833 + }, + { + "epoch": 0.48, + "learning_rate": 1.683072577140374e-05, + "loss": 0.4355, + "step": 5834 + }, + { + "epoch": 0.48, + "learning_rate": 1.6830182529335074e-05, + "loss": 0.374, + "step": 5835 + }, + { + "epoch": 0.48, + "learning_rate": 1.682963928726641e-05, + "loss": 0.511, + "step": 5836 + }, + { + "epoch": 0.48, + "learning_rate": 1.6829096045197743e-05, + "loss": 0.6456, + "step": 5837 + }, + { + "epoch": 0.48, + "learning_rate": 1.6828552803129077e-05, + "loss": 0.3806, + "step": 5838 + }, + { + "epoch": 0.48, + "learning_rate": 1.682800956106041e-05, + "loss": 0.7206, + "step": 5839 + }, + { + "epoch": 0.48, + "learning_rate": 1.6827466318991742e-05, + "loss": 0.568, + "step": 5840 + }, + { + "epoch": 0.48, + "learning_rate": 1.682692307692308e-05, + "loss": 0.353, + "step": 5841 + }, + { + "epoch": 0.48, + "learning_rate": 1.682637983485441e-05, + "loss": 0.4976, + "step": 5842 + }, + { + "epoch": 0.48, + "learning_rate": 1.6825836592785748e-05, + "loss": 0.4291, + "step": 5843 + }, + { + "epoch": 0.48, + "learning_rate": 1.682529335071708e-05, + "loss": 0.4615, + "step": 5844 + }, + { + "epoch": 0.48, + "learning_rate": 1.6824750108648417e-05, + "loss": 0.3377, + "step": 5845 + }, + { + "epoch": 0.48, + "learning_rate": 1.6824206866579747e-05, + "loss": 0.4007, + "step": 5846 + }, + { + "epoch": 0.48, + "learning_rate": 1.6823663624511085e-05, + "loss": 0.4297, + "step": 5847 + }, + { + "epoch": 0.48, + "learning_rate": 1.6823120382442416e-05, + "loss": 0.4142, + "step": 5848 + }, + { + "epoch": 0.48, + "learning_rate": 1.6822577140373753e-05, + "loss": 0.4194, + "step": 5849 + }, + { + "epoch": 0.48, + "learning_rate": 1.6822033898305084e-05, + "loss": 0.5266, + "step": 5850 + }, + { + "epoch": 0.48, + "learning_rate": 1.6821490656236422e-05, + "loss": 0.3017, + "step": 5851 + }, + { + "epoch": 0.48, + "learning_rate": 1.6820947414167753e-05, + "loss": 0.5176, + "step": 5852 + }, + { + "epoch": 0.48, + "learning_rate": 1.682040417209909e-05, + "loss": 0.8132, + "step": 5853 + }, + { + "epoch": 0.48, + "learning_rate": 1.681986093003042e-05, + "loss": 0.5805, + "step": 5854 + }, + { + "epoch": 0.48, + "learning_rate": 1.681931768796176e-05, + "loss": 0.5701, + "step": 5855 + }, + { + "epoch": 0.48, + "learning_rate": 1.681877444589309e-05, + "loss": 0.3792, + "step": 5856 + }, + { + "epoch": 0.48, + "learning_rate": 1.6818231203824427e-05, + "loss": 0.3601, + "step": 5857 + }, + { + "epoch": 0.48, + "learning_rate": 1.6817687961755758e-05, + "loss": 0.4056, + "step": 5858 + }, + { + "epoch": 0.48, + "learning_rate": 1.6817144719687092e-05, + "loss": 0.5621, + "step": 5859 + }, + { + "epoch": 0.48, + "learning_rate": 1.681660147761843e-05, + "loss": 0.388, + "step": 5860 + }, + { + "epoch": 0.48, + "learning_rate": 1.681605823554976e-05, + "loss": 0.2367, + "step": 5861 + }, + { + "epoch": 0.48, + "learning_rate": 1.68155149934811e-05, + "loss": 0.3573, + "step": 5862 + }, + { + "epoch": 0.48, + "learning_rate": 1.681497175141243e-05, + "loss": 0.6211, + "step": 5863 + }, + { + "epoch": 0.48, + "learning_rate": 1.6814428509343767e-05, + "loss": 0.4179, + "step": 5864 + }, + { + "epoch": 0.48, + "learning_rate": 1.6813885267275098e-05, + "loss": 0.3525, + "step": 5865 + }, + { + "epoch": 0.48, + "learning_rate": 1.6813342025206435e-05, + "loss": 0.3102, + "step": 5866 + }, + { + "epoch": 0.48, + "learning_rate": 1.6812798783137766e-05, + "loss": 0.5648, + "step": 5867 + }, + { + "epoch": 0.48, + "learning_rate": 1.6812255541069104e-05, + "loss": 0.5221, + "step": 5868 + }, + { + "epoch": 0.48, + "learning_rate": 1.6811712299000435e-05, + "loss": 0.6794, + "step": 5869 + }, + { + "epoch": 0.48, + "learning_rate": 1.6811169056931772e-05, + "loss": 0.3331, + "step": 5870 + }, + { + "epoch": 0.48, + "learning_rate": 1.6810625814863103e-05, + "loss": 0.5406, + "step": 5871 + }, + { + "epoch": 0.48, + "learning_rate": 1.681008257279444e-05, + "loss": 0.4105, + "step": 5872 + }, + { + "epoch": 0.48, + "learning_rate": 1.680953933072577e-05, + "loss": 0.2762, + "step": 5873 + }, + { + "epoch": 0.48, + "learning_rate": 1.680899608865711e-05, + "loss": 0.5377, + "step": 5874 + }, + { + "epoch": 0.48, + "learning_rate": 1.680845284658844e-05, + "loss": 0.2675, + "step": 5875 + }, + { + "epoch": 0.48, + "learning_rate": 1.6807909604519778e-05, + "loss": 0.471, + "step": 5876 + }, + { + "epoch": 0.48, + "learning_rate": 1.680736636245111e-05, + "loss": 0.5558, + "step": 5877 + }, + { + "epoch": 0.48, + "learning_rate": 1.6806823120382443e-05, + "loss": 0.5626, + "step": 5878 + }, + { + "epoch": 0.48, + "learning_rate": 1.6806279878313777e-05, + "loss": 0.4579, + "step": 5879 + }, + { + "epoch": 0.48, + "learning_rate": 1.680573663624511e-05, + "loss": 0.6567, + "step": 5880 + }, + { + "epoch": 0.48, + "learning_rate": 1.6805193394176445e-05, + "loss": 0.6948, + "step": 5881 + }, + { + "epoch": 0.48, + "learning_rate": 1.680465015210778e-05, + "loss": 0.364, + "step": 5882 + }, + { + "epoch": 0.48, + "learning_rate": 1.6804106910039114e-05, + "loss": 0.6553, + "step": 5883 + }, + { + "epoch": 0.48, + "learning_rate": 1.6803563667970448e-05, + "loss": 0.3338, + "step": 5884 + }, + { + "epoch": 0.48, + "learning_rate": 1.6803020425901782e-05, + "loss": 0.5173, + "step": 5885 + }, + { + "epoch": 0.48, + "learning_rate": 1.6802477183833117e-05, + "loss": 0.6662, + "step": 5886 + }, + { + "epoch": 0.48, + "learning_rate": 1.680193394176445e-05, + "loss": 0.4049, + "step": 5887 + }, + { + "epoch": 0.48, + "learning_rate": 1.6801390699695785e-05, + "loss": 0.5716, + "step": 5888 + }, + { + "epoch": 0.48, + "learning_rate": 1.680084745762712e-05, + "loss": 0.6501, + "step": 5889 + }, + { + "epoch": 0.48, + "learning_rate": 1.6800304215558454e-05, + "loss": 0.4331, + "step": 5890 + }, + { + "epoch": 0.48, + "learning_rate": 1.6799760973489788e-05, + "loss": 0.3002, + "step": 5891 + }, + { + "epoch": 0.48, + "learning_rate": 1.6799217731421122e-05, + "loss": 0.3991, + "step": 5892 + }, + { + "epoch": 0.48, + "learning_rate": 1.6798674489352456e-05, + "loss": 0.5417, + "step": 5893 + }, + { + "epoch": 0.48, + "learning_rate": 1.679813124728379e-05, + "loss": 0.5558, + "step": 5894 + }, + { + "epoch": 0.48, + "learning_rate": 1.6797588005215125e-05, + "loss": 0.4605, + "step": 5895 + }, + { + "epoch": 0.48, + "learning_rate": 1.679704476314646e-05, + "loss": 0.5653, + "step": 5896 + }, + { + "epoch": 0.48, + "learning_rate": 1.6796501521077793e-05, + "loss": 0.2814, + "step": 5897 + }, + { + "epoch": 0.48, + "learning_rate": 1.6795958279009127e-05, + "loss": 0.4422, + "step": 5898 + }, + { + "epoch": 0.48, + "learning_rate": 1.679541503694046e-05, + "loss": 0.5117, + "step": 5899 + }, + { + "epoch": 0.48, + "learning_rate": 1.6794871794871796e-05, + "loss": 0.4863, + "step": 5900 + }, + { + "epoch": 0.48, + "learning_rate": 1.679432855280313e-05, + "loss": 0.6914, + "step": 5901 + }, + { + "epoch": 0.48, + "learning_rate": 1.6793785310734464e-05, + "loss": 0.5114, + "step": 5902 + }, + { + "epoch": 0.48, + "learning_rate": 1.67932420686658e-05, + "loss": 0.5423, + "step": 5903 + }, + { + "epoch": 0.48, + "learning_rate": 1.6792698826597133e-05, + "loss": 0.3834, + "step": 5904 + }, + { + "epoch": 0.48, + "learning_rate": 1.6792155584528467e-05, + "loss": 0.3512, + "step": 5905 + }, + { + "epoch": 0.48, + "learning_rate": 1.67916123424598e-05, + "loss": 0.3208, + "step": 5906 + }, + { + "epoch": 0.48, + "learning_rate": 1.6791069100391135e-05, + "loss": 0.1714, + "step": 5907 + }, + { + "epoch": 0.48, + "learning_rate": 1.679052585832247e-05, + "loss": 0.3654, + "step": 5908 + }, + { + "epoch": 0.48, + "learning_rate": 1.6789982616253804e-05, + "loss": 0.6188, + "step": 5909 + }, + { + "epoch": 0.48, + "learning_rate": 1.6789439374185138e-05, + "loss": 0.3769, + "step": 5910 + }, + { + "epoch": 0.48, + "learning_rate": 1.6788896132116472e-05, + "loss": 0.395, + "step": 5911 + }, + { + "epoch": 0.48, + "learning_rate": 1.6788352890047807e-05, + "loss": 0.5261, + "step": 5912 + }, + { + "epoch": 0.48, + "learning_rate": 1.678780964797914e-05, + "loss": 0.4442, + "step": 5913 + }, + { + "epoch": 0.48, + "learning_rate": 1.6787266405910475e-05, + "loss": 0.4974, + "step": 5914 + }, + { + "epoch": 0.48, + "learning_rate": 1.678672316384181e-05, + "loss": 0.7381, + "step": 5915 + }, + { + "epoch": 0.48, + "learning_rate": 1.6786179921773144e-05, + "loss": 0.5557, + "step": 5916 + }, + { + "epoch": 0.48, + "learning_rate": 1.6785636679704478e-05, + "loss": 0.19, + "step": 5917 + }, + { + "epoch": 0.48, + "learning_rate": 1.6785093437635812e-05, + "loss": 0.7142, + "step": 5918 + }, + { + "epoch": 0.48, + "learning_rate": 1.6784550195567146e-05, + "loss": 0.2688, + "step": 5919 + }, + { + "epoch": 0.48, + "learning_rate": 1.678400695349848e-05, + "loss": 0.6771, + "step": 5920 + }, + { + "epoch": 0.48, + "learning_rate": 1.6783463711429815e-05, + "loss": 0.6482, + "step": 5921 + }, + { + "epoch": 0.48, + "learning_rate": 1.678292046936115e-05, + "loss": 0.5036, + "step": 5922 + }, + { + "epoch": 0.48, + "learning_rate": 1.6782377227292483e-05, + "loss": 0.5867, + "step": 5923 + }, + { + "epoch": 0.48, + "learning_rate": 1.6781833985223817e-05, + "loss": 0.679, + "step": 5924 + }, + { + "epoch": 0.48, + "learning_rate": 1.678129074315515e-05, + "loss": 0.3056, + "step": 5925 + }, + { + "epoch": 0.48, + "learning_rate": 1.6780747501086486e-05, + "loss": 0.5805, + "step": 5926 + }, + { + "epoch": 0.48, + "learning_rate": 1.678020425901782e-05, + "loss": 0.4378, + "step": 5927 + }, + { + "epoch": 0.48, + "learning_rate": 1.6779661016949154e-05, + "loss": 0.4465, + "step": 5928 + }, + { + "epoch": 0.48, + "learning_rate": 1.677911777488049e-05, + "loss": 0.7014, + "step": 5929 + }, + { + "epoch": 0.48, + "learning_rate": 1.6778574532811823e-05, + "loss": 0.6656, + "step": 5930 + }, + { + "epoch": 0.48, + "learning_rate": 1.6778031290743157e-05, + "loss": 0.812, + "step": 5931 + }, + { + "epoch": 0.48, + "learning_rate": 1.677748804867449e-05, + "loss": 0.2431, + "step": 5932 + }, + { + "epoch": 0.48, + "learning_rate": 1.6776944806605825e-05, + "loss": 0.4068, + "step": 5933 + }, + { + "epoch": 0.48, + "learning_rate": 1.677640156453716e-05, + "loss": 0.4329, + "step": 5934 + }, + { + "epoch": 0.48, + "learning_rate": 1.6775858322468494e-05, + "loss": 0.3838, + "step": 5935 + }, + { + "epoch": 0.48, + "learning_rate": 1.6775315080399828e-05, + "loss": 0.6434, + "step": 5936 + }, + { + "epoch": 0.48, + "learning_rate": 1.6774771838331162e-05, + "loss": 0.4735, + "step": 5937 + }, + { + "epoch": 0.48, + "learning_rate": 1.6774228596262497e-05, + "loss": 0.6698, + "step": 5938 + }, + { + "epoch": 0.48, + "learning_rate": 1.677368535419383e-05, + "loss": 0.4271, + "step": 5939 + }, + { + "epoch": 0.48, + "learning_rate": 1.6773142112125165e-05, + "loss": 0.7036, + "step": 5940 + }, + { + "epoch": 0.48, + "learning_rate": 1.67725988700565e-05, + "loss": 0.4143, + "step": 5941 + }, + { + "epoch": 0.48, + "learning_rate": 1.6772055627987834e-05, + "loss": 0.4454, + "step": 5942 + }, + { + "epoch": 0.48, + "learning_rate": 1.6771512385919168e-05, + "loss": 0.481, + "step": 5943 + }, + { + "epoch": 0.48, + "learning_rate": 1.6770969143850502e-05, + "loss": 0.411, + "step": 5944 + }, + { + "epoch": 0.48, + "learning_rate": 1.6770425901781836e-05, + "loss": 0.5548, + "step": 5945 + }, + { + "epoch": 0.48, + "learning_rate": 1.676988265971317e-05, + "loss": 0.5942, + "step": 5946 + }, + { + "epoch": 0.48, + "learning_rate": 1.6769339417644505e-05, + "loss": 0.4081, + "step": 5947 + }, + { + "epoch": 0.48, + "learning_rate": 1.676879617557584e-05, + "loss": 0.3464, + "step": 5948 + }, + { + "epoch": 0.48, + "learning_rate": 1.6768252933507173e-05, + "loss": 0.3919, + "step": 5949 + }, + { + "epoch": 0.48, + "learning_rate": 1.6767709691438507e-05, + "loss": 0.5217, + "step": 5950 + }, + { + "epoch": 0.48, + "learning_rate": 1.676716644936984e-05, + "loss": 0.2928, + "step": 5951 + }, + { + "epoch": 0.49, + "learning_rate": 1.6766623207301176e-05, + "loss": 0.3686, + "step": 5952 + }, + { + "epoch": 0.49, + "learning_rate": 1.676607996523251e-05, + "loss": 0.5904, + "step": 5953 + }, + { + "epoch": 0.49, + "learning_rate": 1.676553672316384e-05, + "loss": 0.5545, + "step": 5954 + }, + { + "epoch": 0.49, + "learning_rate": 1.676499348109518e-05, + "loss": 0.5234, + "step": 5955 + }, + { + "epoch": 0.49, + "learning_rate": 1.676445023902651e-05, + "loss": 0.6192, + "step": 5956 + }, + { + "epoch": 0.49, + "learning_rate": 1.6763906996957847e-05, + "loss": 0.4047, + "step": 5957 + }, + { + "epoch": 0.49, + "learning_rate": 1.6763363754889178e-05, + "loss": 0.4489, + "step": 5958 + }, + { + "epoch": 0.49, + "learning_rate": 1.6762820512820515e-05, + "loss": 0.5938, + "step": 5959 + }, + { + "epoch": 0.49, + "learning_rate": 1.6762277270751846e-05, + "loss": 0.4305, + "step": 5960 + }, + { + "epoch": 0.49, + "learning_rate": 1.6761734028683184e-05, + "loss": 0.5303, + "step": 5961 + }, + { + "epoch": 0.49, + "learning_rate": 1.6761190786614515e-05, + "loss": 0.3809, + "step": 5962 + }, + { + "epoch": 0.49, + "learning_rate": 1.6760647544545852e-05, + "loss": 0.6777, + "step": 5963 + }, + { + "epoch": 0.49, + "learning_rate": 1.6760104302477183e-05, + "loss": 0.5959, + "step": 5964 + }, + { + "epoch": 0.49, + "learning_rate": 1.675956106040852e-05, + "loss": 0.255, + "step": 5965 + }, + { + "epoch": 0.49, + "learning_rate": 1.675901781833985e-05, + "loss": 0.433, + "step": 5966 + }, + { + "epoch": 0.49, + "learning_rate": 1.675847457627119e-05, + "loss": 0.4722, + "step": 5967 + }, + { + "epoch": 0.49, + "learning_rate": 1.6757931334202524e-05, + "loss": 0.4691, + "step": 5968 + }, + { + "epoch": 0.49, + "learning_rate": 1.6757388092133858e-05, + "loss": 0.5013, + "step": 5969 + }, + { + "epoch": 0.49, + "learning_rate": 1.6756844850065192e-05, + "loss": 0.3295, + "step": 5970 + }, + { + "epoch": 0.49, + "learning_rate": 1.6756301607996526e-05, + "loss": 0.5184, + "step": 5971 + }, + { + "epoch": 0.49, + "learning_rate": 1.675575836592786e-05, + "loss": 0.3326, + "step": 5972 + }, + { + "epoch": 0.49, + "learning_rate": 1.675521512385919e-05, + "loss": 0.329, + "step": 5973 + }, + { + "epoch": 0.49, + "learning_rate": 1.675467188179053e-05, + "loss": 0.679, + "step": 5974 + }, + { + "epoch": 0.49, + "learning_rate": 1.675412863972186e-05, + "loss": 0.3744, + "step": 5975 + }, + { + "epoch": 0.49, + "learning_rate": 1.6753585397653197e-05, + "loss": 0.474, + "step": 5976 + }, + { + "epoch": 0.49, + "learning_rate": 1.6753042155584528e-05, + "loss": 0.425, + "step": 5977 + }, + { + "epoch": 0.49, + "learning_rate": 1.6752498913515866e-05, + "loss": 0.5097, + "step": 5978 + }, + { + "epoch": 0.49, + "learning_rate": 1.6751955671447197e-05, + "loss": 0.4966, + "step": 5979 + }, + { + "epoch": 0.49, + "learning_rate": 1.6751412429378534e-05, + "loss": 0.4329, + "step": 5980 + }, + { + "epoch": 0.49, + "learning_rate": 1.6750869187309865e-05, + "loss": 0.5627, + "step": 5981 + }, + { + "epoch": 0.49, + "learning_rate": 1.6750325945241203e-05, + "loss": 0.4473, + "step": 5982 + }, + { + "epoch": 0.49, + "learning_rate": 1.6749782703172534e-05, + "loss": 0.6685, + "step": 5983 + }, + { + "epoch": 0.49, + "learning_rate": 1.674923946110387e-05, + "loss": 0.6365, + "step": 5984 + }, + { + "epoch": 0.49, + "learning_rate": 1.6748696219035202e-05, + "loss": 0.4572, + "step": 5985 + }, + { + "epoch": 0.49, + "learning_rate": 1.674815297696654e-05, + "loss": 0.3895, + "step": 5986 + }, + { + "epoch": 0.49, + "learning_rate": 1.674760973489787e-05, + "loss": 0.3432, + "step": 5987 + }, + { + "epoch": 0.49, + "learning_rate": 1.6747066492829208e-05, + "loss": 0.5314, + "step": 5988 + }, + { + "epoch": 0.49, + "learning_rate": 1.674652325076054e-05, + "loss": 0.3892, + "step": 5989 + }, + { + "epoch": 0.49, + "learning_rate": 1.6745980008691877e-05, + "loss": 0.5451, + "step": 5990 + }, + { + "epoch": 0.49, + "learning_rate": 1.6745436766623207e-05, + "loss": 0.4614, + "step": 5991 + }, + { + "epoch": 0.49, + "learning_rate": 1.674489352455454e-05, + "loss": 0.5138, + "step": 5992 + }, + { + "epoch": 0.49, + "learning_rate": 1.6744350282485876e-05, + "loss": 0.3267, + "step": 5993 + }, + { + "epoch": 0.49, + "learning_rate": 1.674380704041721e-05, + "loss": 0.5822, + "step": 5994 + }, + { + "epoch": 0.49, + "learning_rate": 1.6743263798348544e-05, + "loss": 0.4086, + "step": 5995 + }, + { + "epoch": 0.49, + "learning_rate": 1.674272055627988e-05, + "loss": 0.5499, + "step": 5996 + }, + { + "epoch": 0.49, + "learning_rate": 1.6742177314211213e-05, + "loss": 0.667, + "step": 5997 + }, + { + "epoch": 0.49, + "learning_rate": 1.6741634072142547e-05, + "loss": 0.4288, + "step": 5998 + }, + { + "epoch": 0.49, + "learning_rate": 1.674109083007388e-05, + "loss": 0.3753, + "step": 5999 + }, + { + "epoch": 0.49, + "learning_rate": 1.6740547588005215e-05, + "loss": 0.6367, + "step": 6000 + }, + { + "epoch": 0.49, + "eval_accuracy": 0.8169128884360672, + "eval_loss": 0.46820515394210815, + "eval_runtime": 22.302, + "eval_samples_per_second": 440.094, + "eval_steps_per_second": 3.453, + "step": 6000 + }, + { + "epoch": 0.49, + "learning_rate": 1.674000434593655e-05, + "loss": 0.658, + "step": 6001 + }, + { + "epoch": 0.49, + "learning_rate": 1.6739461103867884e-05, + "loss": 0.507, + "step": 6002 + }, + { + "epoch": 0.49, + "learning_rate": 1.6738917861799218e-05, + "loss": 0.5647, + "step": 6003 + }, + { + "epoch": 0.49, + "learning_rate": 1.6738374619730552e-05, + "loss": 0.4118, + "step": 6004 + }, + { + "epoch": 0.49, + "learning_rate": 1.673783137766189e-05, + "loss": 0.5084, + "step": 6005 + }, + { + "epoch": 0.49, + "learning_rate": 1.673728813559322e-05, + "loss": 0.6149, + "step": 6006 + }, + { + "epoch": 0.49, + "learning_rate": 1.673674489352456e-05, + "loss": 0.4179, + "step": 6007 + }, + { + "epoch": 0.49, + "learning_rate": 1.673620165145589e-05, + "loss": 0.5265, + "step": 6008 + }, + { + "epoch": 0.49, + "learning_rate": 1.6735658409387227e-05, + "loss": 0.5221, + "step": 6009 + }, + { + "epoch": 0.49, + "learning_rate": 1.6735115167318558e-05, + "loss": 0.4319, + "step": 6010 + }, + { + "epoch": 0.49, + "learning_rate": 1.6734571925249892e-05, + "loss": 0.4757, + "step": 6011 + }, + { + "epoch": 0.49, + "learning_rate": 1.6734028683181226e-05, + "loss": 0.3713, + "step": 6012 + }, + { + "epoch": 0.49, + "learning_rate": 1.673348544111256e-05, + "loss": 0.5085, + "step": 6013 + }, + { + "epoch": 0.49, + "learning_rate": 1.6732942199043895e-05, + "loss": 0.3023, + "step": 6014 + }, + { + "epoch": 0.49, + "learning_rate": 1.673239895697523e-05, + "loss": 0.3032, + "step": 6015 + }, + { + "epoch": 0.49, + "learning_rate": 1.6731855714906563e-05, + "loss": 0.487, + "step": 6016 + }, + { + "epoch": 0.49, + "learning_rate": 1.6731312472837897e-05, + "loss": 0.3826, + "step": 6017 + }, + { + "epoch": 0.49, + "learning_rate": 1.673076923076923e-05, + "loss": 0.4982, + "step": 6018 + }, + { + "epoch": 0.49, + "learning_rate": 1.6730225988700566e-05, + "loss": 0.6234, + "step": 6019 + }, + { + "epoch": 0.49, + "learning_rate": 1.67296827466319e-05, + "loss": 0.4381, + "step": 6020 + }, + { + "epoch": 0.49, + "learning_rate": 1.6729139504563234e-05, + "loss": 0.4152, + "step": 6021 + }, + { + "epoch": 0.49, + "learning_rate": 1.672859626249457e-05, + "loss": 0.3413, + "step": 6022 + }, + { + "epoch": 0.49, + "learning_rate": 1.6728053020425903e-05, + "loss": 0.2502, + "step": 6023 + }, + { + "epoch": 0.49, + "learning_rate": 1.6727509778357237e-05, + "loss": 0.3731, + "step": 6024 + }, + { + "epoch": 0.49, + "learning_rate": 1.672696653628857e-05, + "loss": 0.2677, + "step": 6025 + }, + { + "epoch": 0.49, + "learning_rate": 1.6726423294219905e-05, + "loss": 0.3775, + "step": 6026 + }, + { + "epoch": 0.49, + "learning_rate": 1.672588005215124e-05, + "loss": 0.5931, + "step": 6027 + }, + { + "epoch": 0.49, + "learning_rate": 1.6725336810082574e-05, + "loss": 0.2435, + "step": 6028 + }, + { + "epoch": 0.49, + "learning_rate": 1.6724793568013908e-05, + "loss": 0.342, + "step": 6029 + }, + { + "epoch": 0.49, + "learning_rate": 1.6724250325945242e-05, + "loss": 0.4185, + "step": 6030 + }, + { + "epoch": 0.49, + "learning_rate": 1.6723707083876577e-05, + "loss": 0.5021, + "step": 6031 + }, + { + "epoch": 0.49, + "learning_rate": 1.672316384180791e-05, + "loss": 0.4905, + "step": 6032 + }, + { + "epoch": 0.49, + "learning_rate": 1.6722620599739245e-05, + "loss": 0.4992, + "step": 6033 + }, + { + "epoch": 0.49, + "learning_rate": 1.672207735767058e-05, + "loss": 0.5702, + "step": 6034 + }, + { + "epoch": 0.49, + "learning_rate": 1.6721534115601914e-05, + "loss": 0.6748, + "step": 6035 + }, + { + "epoch": 0.49, + "learning_rate": 1.6720990873533248e-05, + "loss": 0.63, + "step": 6036 + }, + { + "epoch": 0.49, + "learning_rate": 1.6720447631464582e-05, + "loss": 0.6041, + "step": 6037 + }, + { + "epoch": 0.49, + "learning_rate": 1.6719904389395916e-05, + "loss": 0.6251, + "step": 6038 + }, + { + "epoch": 0.49, + "learning_rate": 1.671936114732725e-05, + "loss": 0.3253, + "step": 6039 + }, + { + "epoch": 0.49, + "learning_rate": 1.6718817905258585e-05, + "loss": 0.5292, + "step": 6040 + }, + { + "epoch": 0.49, + "learning_rate": 1.671827466318992e-05, + "loss": 0.6032, + "step": 6041 + }, + { + "epoch": 0.49, + "learning_rate": 1.6717731421121253e-05, + "loss": 0.6155, + "step": 6042 + }, + { + "epoch": 0.49, + "learning_rate": 1.6717188179052587e-05, + "loss": 0.2814, + "step": 6043 + }, + { + "epoch": 0.49, + "learning_rate": 1.671664493698392e-05, + "loss": 0.3663, + "step": 6044 + }, + { + "epoch": 0.49, + "learning_rate": 1.6716101694915256e-05, + "loss": 0.6347, + "step": 6045 + }, + { + "epoch": 0.49, + "learning_rate": 1.671555845284659e-05, + "loss": 0.5935, + "step": 6046 + }, + { + "epoch": 0.49, + "learning_rate": 1.6715015210777924e-05, + "loss": 0.4061, + "step": 6047 + }, + { + "epoch": 0.49, + "learning_rate": 1.671447196870926e-05, + "loss": 0.2733, + "step": 6048 + }, + { + "epoch": 0.49, + "learning_rate": 1.6713928726640593e-05, + "loss": 0.3294, + "step": 6049 + }, + { + "epoch": 0.49, + "learning_rate": 1.6713385484571927e-05, + "loss": 0.5606, + "step": 6050 + }, + { + "epoch": 0.49, + "learning_rate": 1.671284224250326e-05, + "loss": 0.4954, + "step": 6051 + }, + { + "epoch": 0.49, + "learning_rate": 1.6712299000434595e-05, + "loss": 0.3775, + "step": 6052 + }, + { + "epoch": 0.49, + "learning_rate": 1.671175575836593e-05, + "loss": 0.3374, + "step": 6053 + }, + { + "epoch": 0.49, + "learning_rate": 1.6711212516297264e-05, + "loss": 0.4412, + "step": 6054 + }, + { + "epoch": 0.49, + "learning_rate": 1.6710669274228598e-05, + "loss": 0.5477, + "step": 6055 + }, + { + "epoch": 0.49, + "learning_rate": 1.6710126032159932e-05, + "loss": 0.4395, + "step": 6056 + }, + { + "epoch": 0.49, + "learning_rate": 1.6709582790091267e-05, + "loss": 0.5238, + "step": 6057 + }, + { + "epoch": 0.49, + "learning_rate": 1.67090395480226e-05, + "loss": 0.4057, + "step": 6058 + }, + { + "epoch": 0.49, + "learning_rate": 1.6708496305953935e-05, + "loss": 0.4053, + "step": 6059 + }, + { + "epoch": 0.49, + "learning_rate": 1.670795306388527e-05, + "loss": 0.1887, + "step": 6060 + }, + { + "epoch": 0.49, + "learning_rate": 1.6707409821816604e-05, + "loss": 0.2918, + "step": 6061 + }, + { + "epoch": 0.49, + "learning_rate": 1.6706866579747938e-05, + "loss": 0.3746, + "step": 6062 + }, + { + "epoch": 0.49, + "learning_rate": 1.6706323337679272e-05, + "loss": 0.3946, + "step": 6063 + }, + { + "epoch": 0.49, + "learning_rate": 1.6705780095610606e-05, + "loss": 0.4644, + "step": 6064 + }, + { + "epoch": 0.49, + "learning_rate": 1.670523685354194e-05, + "loss": 0.2828, + "step": 6065 + }, + { + "epoch": 0.49, + "learning_rate": 1.6704693611473275e-05, + "loss": 0.3421, + "step": 6066 + }, + { + "epoch": 0.49, + "learning_rate": 1.670415036940461e-05, + "loss": 0.4859, + "step": 6067 + }, + { + "epoch": 0.49, + "learning_rate": 1.670360712733594e-05, + "loss": 0.3012, + "step": 6068 + }, + { + "epoch": 0.49, + "learning_rate": 1.6703063885267277e-05, + "loss": 0.4188, + "step": 6069 + }, + { + "epoch": 0.49, + "learning_rate": 1.6702520643198608e-05, + "loss": 0.5759, + "step": 6070 + }, + { + "epoch": 0.49, + "learning_rate": 1.6701977401129946e-05, + "loss": 0.3026, + "step": 6071 + }, + { + "epoch": 0.49, + "learning_rate": 1.6701434159061277e-05, + "loss": 0.5617, + "step": 6072 + }, + { + "epoch": 0.49, + "learning_rate": 1.6700890916992614e-05, + "loss": 0.219, + "step": 6073 + }, + { + "epoch": 0.49, + "learning_rate": 1.6700347674923945e-05, + "loss": 0.5004, + "step": 6074 + }, + { + "epoch": 0.5, + "learning_rate": 1.6699804432855283e-05, + "loss": 0.4582, + "step": 6075 + }, + { + "epoch": 0.5, + "learning_rate": 1.6699261190786617e-05, + "loss": 0.4992, + "step": 6076 + }, + { + "epoch": 0.5, + "learning_rate": 1.669871794871795e-05, + "loss": 0.369, + "step": 6077 + }, + { + "epoch": 0.5, + "learning_rate": 1.6698174706649285e-05, + "loss": 0.1853, + "step": 6078 + }, + { + "epoch": 0.5, + "learning_rate": 1.669763146458062e-05, + "loss": 0.7175, + "step": 6079 + }, + { + "epoch": 0.5, + "learning_rate": 1.6697088222511954e-05, + "loss": 0.3928, + "step": 6080 + }, + { + "epoch": 0.5, + "learning_rate": 1.6696544980443288e-05, + "loss": 0.5458, + "step": 6081 + }, + { + "epoch": 0.5, + "learning_rate": 1.6696001738374622e-05, + "loss": 0.4332, + "step": 6082 + }, + { + "epoch": 0.5, + "learning_rate": 1.6695458496305957e-05, + "loss": 0.4468, + "step": 6083 + }, + { + "epoch": 0.5, + "learning_rate": 1.669491525423729e-05, + "loss": 0.357, + "step": 6084 + }, + { + "epoch": 0.5, + "learning_rate": 1.6694372012168625e-05, + "loss": 0.3712, + "step": 6085 + }, + { + "epoch": 0.5, + "learning_rate": 1.669382877009996e-05, + "loss": 0.5294, + "step": 6086 + }, + { + "epoch": 0.5, + "learning_rate": 1.669328552803129e-05, + "loss": 0.5015, + "step": 6087 + }, + { + "epoch": 0.5, + "learning_rate": 1.6692742285962628e-05, + "loss": 0.6818, + "step": 6088 + }, + { + "epoch": 0.5, + "learning_rate": 1.669219904389396e-05, + "loss": 0.271, + "step": 6089 + }, + { + "epoch": 0.5, + "learning_rate": 1.6691655801825296e-05, + "loss": 0.3936, + "step": 6090 + }, + { + "epoch": 0.5, + "learning_rate": 1.6691112559756627e-05, + "loss": 0.6774, + "step": 6091 + }, + { + "epoch": 0.5, + "learning_rate": 1.6690569317687965e-05, + "loss": 0.3755, + "step": 6092 + }, + { + "epoch": 0.5, + "learning_rate": 1.6690026075619296e-05, + "loss": 0.2966, + "step": 6093 + }, + { + "epoch": 0.5, + "learning_rate": 1.6689482833550633e-05, + "loss": 0.3826, + "step": 6094 + }, + { + "epoch": 0.5, + "learning_rate": 1.6688939591481964e-05, + "loss": 0.2486, + "step": 6095 + }, + { + "epoch": 0.5, + "learning_rate": 1.66883963494133e-05, + "loss": 0.3886, + "step": 6096 + }, + { + "epoch": 0.5, + "learning_rate": 1.6687853107344632e-05, + "loss": 0.2075, + "step": 6097 + }, + { + "epoch": 0.5, + "learning_rate": 1.668730986527597e-05, + "loss": 0.2834, + "step": 6098 + }, + { + "epoch": 0.5, + "learning_rate": 1.66867666232073e-05, + "loss": 0.4407, + "step": 6099 + }, + { + "epoch": 0.5, + "learning_rate": 1.668622338113864e-05, + "loss": 0.755, + "step": 6100 + }, + { + "epoch": 0.5, + "learning_rate": 1.668568013906997e-05, + "loss": 0.6876, + "step": 6101 + }, + { + "epoch": 0.5, + "learning_rate": 1.6685136897001307e-05, + "loss": 0.3946, + "step": 6102 + }, + { + "epoch": 0.5, + "learning_rate": 1.6684593654932638e-05, + "loss": 0.5997, + "step": 6103 + }, + { + "epoch": 0.5, + "learning_rate": 1.6684050412863975e-05, + "loss": 0.466, + "step": 6104 + }, + { + "epoch": 0.5, + "learning_rate": 1.6683507170795306e-05, + "loss": 0.5299, + "step": 6105 + }, + { + "epoch": 0.5, + "learning_rate": 1.668296392872664e-05, + "loss": 0.4073, + "step": 6106 + }, + { + "epoch": 0.5, + "learning_rate": 1.6682420686657975e-05, + "loss": 0.7445, + "step": 6107 + }, + { + "epoch": 0.5, + "learning_rate": 1.668187744458931e-05, + "loss": 0.5031, + "step": 6108 + }, + { + "epoch": 0.5, + "learning_rate": 1.6681334202520643e-05, + "loss": 0.6113, + "step": 6109 + }, + { + "epoch": 0.5, + "learning_rate": 1.6680790960451977e-05, + "loss": 0.8089, + "step": 6110 + }, + { + "epoch": 0.5, + "learning_rate": 1.6680247718383312e-05, + "loss": 0.3394, + "step": 6111 + }, + { + "epoch": 0.5, + "learning_rate": 1.6679704476314646e-05, + "loss": 0.7149, + "step": 6112 + }, + { + "epoch": 0.5, + "learning_rate": 1.6679161234245984e-05, + "loss": 0.3345, + "step": 6113 + }, + { + "epoch": 0.5, + "learning_rate": 1.6678617992177314e-05, + "loss": 0.4099, + "step": 6114 + }, + { + "epoch": 0.5, + "learning_rate": 1.6678074750108652e-05, + "loss": 0.4061, + "step": 6115 + }, + { + "epoch": 0.5, + "learning_rate": 1.6677531508039983e-05, + "loss": 0.593, + "step": 6116 + }, + { + "epoch": 0.5, + "learning_rate": 1.667698826597132e-05, + "loss": 0.6611, + "step": 6117 + }, + { + "epoch": 0.5, + "learning_rate": 1.667644502390265e-05, + "loss": 0.3355, + "step": 6118 + }, + { + "epoch": 0.5, + "learning_rate": 1.667590178183399e-05, + "loss": 0.3454, + "step": 6119 + }, + { + "epoch": 0.5, + "learning_rate": 1.667535853976532e-05, + "loss": 0.3283, + "step": 6120 + }, + { + "epoch": 0.5, + "learning_rate": 1.6674815297696657e-05, + "loss": 0.4628, + "step": 6121 + }, + { + "epoch": 0.5, + "learning_rate": 1.6674272055627988e-05, + "loss": 0.5825, + "step": 6122 + }, + { + "epoch": 0.5, + "learning_rate": 1.6673728813559326e-05, + "loss": 0.7841, + "step": 6123 + }, + { + "epoch": 0.5, + "learning_rate": 1.6673185571490657e-05, + "loss": 0.3388, + "step": 6124 + }, + { + "epoch": 0.5, + "learning_rate": 1.667264232942199e-05, + "loss": 0.4319, + "step": 6125 + }, + { + "epoch": 0.5, + "learning_rate": 1.6672099087353325e-05, + "loss": 0.9046, + "step": 6126 + }, + { + "epoch": 0.5, + "learning_rate": 1.667155584528466e-05, + "loss": 0.572, + "step": 6127 + }, + { + "epoch": 0.5, + "learning_rate": 1.6671012603215994e-05, + "loss": 0.6734, + "step": 6128 + }, + { + "epoch": 0.5, + "learning_rate": 1.6670469361147328e-05, + "loss": 0.2717, + "step": 6129 + }, + { + "epoch": 0.5, + "learning_rate": 1.6669926119078662e-05, + "loss": 0.286, + "step": 6130 + }, + { + "epoch": 0.5, + "learning_rate": 1.6669382877009996e-05, + "loss": 0.3546, + "step": 6131 + }, + { + "epoch": 0.5, + "learning_rate": 1.666883963494133e-05, + "loss": 0.5084, + "step": 6132 + }, + { + "epoch": 0.5, + "learning_rate": 1.6668296392872665e-05, + "loss": 0.7547, + "step": 6133 + }, + { + "epoch": 0.5, + "learning_rate": 1.6667753150804e-05, + "loss": 0.4264, + "step": 6134 + }, + { + "epoch": 0.5, + "learning_rate": 1.6667209908735333e-05, + "loss": 0.2371, + "step": 6135 + }, + { + "epoch": 0.5, + "learning_rate": 1.6666666666666667e-05, + "loss": 0.5472, + "step": 6136 + }, + { + "epoch": 0.5, + "learning_rate": 1.6666123424598002e-05, + "loss": 0.6278, + "step": 6137 + }, + { + "epoch": 0.5, + "learning_rate": 1.6665580182529336e-05, + "loss": 0.5137, + "step": 6138 + }, + { + "epoch": 0.5, + "learning_rate": 1.666503694046067e-05, + "loss": 0.5855, + "step": 6139 + }, + { + "epoch": 0.5, + "learning_rate": 1.6664493698392004e-05, + "loss": 0.5285, + "step": 6140 + }, + { + "epoch": 0.5, + "learning_rate": 1.666395045632334e-05, + "loss": 0.5002, + "step": 6141 + }, + { + "epoch": 0.5, + "learning_rate": 1.6663407214254673e-05, + "loss": 0.5619, + "step": 6142 + }, + { + "epoch": 0.5, + "learning_rate": 1.6662863972186007e-05, + "loss": 0.8786, + "step": 6143 + }, + { + "epoch": 0.5, + "learning_rate": 1.666232073011734e-05, + "loss": 0.3342, + "step": 6144 + }, + { + "epoch": 0.5, + "learning_rate": 1.6661777488048676e-05, + "loss": 0.3221, + "step": 6145 + }, + { + "epoch": 0.5, + "learning_rate": 1.666123424598001e-05, + "loss": 0.5464, + "step": 6146 + }, + { + "epoch": 0.5, + "learning_rate": 1.6660691003911344e-05, + "loss": 0.3801, + "step": 6147 + }, + { + "epoch": 0.5, + "learning_rate": 1.6660147761842678e-05, + "loss": 0.3992, + "step": 6148 + }, + { + "epoch": 0.5, + "learning_rate": 1.6659604519774012e-05, + "loss": 0.3945, + "step": 6149 + }, + { + "epoch": 0.5, + "learning_rate": 1.6659061277705347e-05, + "loss": 0.4969, + "step": 6150 + }, + { + "epoch": 0.5, + "learning_rate": 1.665851803563668e-05, + "loss": 0.6512, + "step": 6151 + }, + { + "epoch": 0.5, + "learning_rate": 1.6657974793568015e-05, + "loss": 0.552, + "step": 6152 + }, + { + "epoch": 0.5, + "learning_rate": 1.665743155149935e-05, + "loss": 0.6055, + "step": 6153 + }, + { + "epoch": 0.5, + "learning_rate": 1.6656888309430684e-05, + "loss": 0.4611, + "step": 6154 + }, + { + "epoch": 0.5, + "learning_rate": 1.6656345067362018e-05, + "loss": 0.4437, + "step": 6155 + }, + { + "epoch": 0.5, + "learning_rate": 1.6655801825293352e-05, + "loss": 0.3837, + "step": 6156 + }, + { + "epoch": 0.5, + "learning_rate": 1.6655258583224686e-05, + "loss": 0.5972, + "step": 6157 + }, + { + "epoch": 0.5, + "learning_rate": 1.665471534115602e-05, + "loss": 0.5938, + "step": 6158 + }, + { + "epoch": 0.5, + "learning_rate": 1.6654172099087355e-05, + "loss": 0.3678, + "step": 6159 + }, + { + "epoch": 0.5, + "learning_rate": 1.665362885701869e-05, + "loss": 0.7374, + "step": 6160 + }, + { + "epoch": 0.5, + "learning_rate": 1.6653085614950023e-05, + "loss": 0.3045, + "step": 6161 + }, + { + "epoch": 0.5, + "learning_rate": 1.6652542372881357e-05, + "loss": 0.8669, + "step": 6162 + }, + { + "epoch": 0.5, + "learning_rate": 1.665199913081269e-05, + "loss": 0.4433, + "step": 6163 + }, + { + "epoch": 0.5, + "learning_rate": 1.6651455888744026e-05, + "loss": 0.5426, + "step": 6164 + }, + { + "epoch": 0.5, + "learning_rate": 1.665091264667536e-05, + "loss": 0.4298, + "step": 6165 + }, + { + "epoch": 0.5, + "learning_rate": 1.6650369404606694e-05, + "loss": 0.3986, + "step": 6166 + }, + { + "epoch": 0.5, + "learning_rate": 1.664982616253803e-05, + "loss": 0.5626, + "step": 6167 + }, + { + "epoch": 0.5, + "learning_rate": 1.6649282920469363e-05, + "loss": 0.2948, + "step": 6168 + }, + { + "epoch": 0.5, + "learning_rate": 1.6648739678400697e-05, + "loss": 0.7492, + "step": 6169 + }, + { + "epoch": 0.5, + "learning_rate": 1.664819643633203e-05, + "loss": 0.3513, + "step": 6170 + }, + { + "epoch": 0.5, + "learning_rate": 1.6647653194263366e-05, + "loss": 0.6256, + "step": 6171 + }, + { + "epoch": 0.5, + "learning_rate": 1.66471099521947e-05, + "loss": 0.5502, + "step": 6172 + }, + { + "epoch": 0.5, + "learning_rate": 1.6646566710126034e-05, + "loss": 0.4455, + "step": 6173 + }, + { + "epoch": 0.5, + "learning_rate": 1.6646023468057368e-05, + "loss": 0.5396, + "step": 6174 + }, + { + "epoch": 0.5, + "learning_rate": 1.6645480225988702e-05, + "loss": 0.6799, + "step": 6175 + }, + { + "epoch": 0.5, + "learning_rate": 1.6644936983920037e-05, + "loss": 0.5847, + "step": 6176 + }, + { + "epoch": 0.5, + "learning_rate": 1.664439374185137e-05, + "loss": 0.6452, + "step": 6177 + }, + { + "epoch": 0.5, + "learning_rate": 1.6643850499782705e-05, + "loss": 0.8499, + "step": 6178 + }, + { + "epoch": 0.5, + "learning_rate": 1.664330725771404e-05, + "loss": 0.4152, + "step": 6179 + }, + { + "epoch": 0.5, + "learning_rate": 1.6642764015645374e-05, + "loss": 0.3899, + "step": 6180 + }, + { + "epoch": 0.5, + "learning_rate": 1.6642220773576708e-05, + "loss": 0.4152, + "step": 6181 + }, + { + "epoch": 0.5, + "learning_rate": 1.664167753150804e-05, + "loss": 0.371, + "step": 6182 + }, + { + "epoch": 0.5, + "learning_rate": 1.6641134289439376e-05, + "loss": 0.293, + "step": 6183 + }, + { + "epoch": 0.5, + "learning_rate": 1.664059104737071e-05, + "loss": 0.4855, + "step": 6184 + }, + { + "epoch": 0.5, + "learning_rate": 1.6640047805302045e-05, + "loss": 0.3677, + "step": 6185 + }, + { + "epoch": 0.5, + "learning_rate": 1.663950456323338e-05, + "loss": 0.3838, + "step": 6186 + }, + { + "epoch": 0.5, + "learning_rate": 1.6638961321164713e-05, + "loss": 0.3015, + "step": 6187 + }, + { + "epoch": 0.5, + "learning_rate": 1.6638418079096047e-05, + "loss": 0.7043, + "step": 6188 + }, + { + "epoch": 0.5, + "learning_rate": 1.663787483702738e-05, + "loss": 0.4752, + "step": 6189 + }, + { + "epoch": 0.5, + "learning_rate": 1.6637331594958716e-05, + "loss": 0.6514, + "step": 6190 + }, + { + "epoch": 0.5, + "learning_rate": 1.663678835289005e-05, + "loss": 0.4137, + "step": 6191 + }, + { + "epoch": 0.5, + "learning_rate": 1.6636245110821384e-05, + "loss": 0.3269, + "step": 6192 + }, + { + "epoch": 0.5, + "learning_rate": 1.663570186875272e-05, + "loss": 0.5941, + "step": 6193 + }, + { + "epoch": 0.5, + "learning_rate": 1.6635158626684053e-05, + "loss": 0.7374, + "step": 6194 + }, + { + "epoch": 0.5, + "learning_rate": 1.6634615384615387e-05, + "loss": 0.3251, + "step": 6195 + }, + { + "epoch": 0.5, + "learning_rate": 1.663407214254672e-05, + "loss": 0.4987, + "step": 6196 + }, + { + "epoch": 0.5, + "learning_rate": 1.6633528900478056e-05, + "loss": 0.4362, + "step": 6197 + }, + { + "epoch": 0.51, + "learning_rate": 1.663298565840939e-05, + "loss": 0.7889, + "step": 6198 + }, + { + "epoch": 0.51, + "learning_rate": 1.6632442416340724e-05, + "loss": 0.4664, + "step": 6199 + }, + { + "epoch": 0.51, + "learning_rate": 1.6631899174272058e-05, + "loss": 0.2168, + "step": 6200 + }, + { + "epoch": 0.51, + "learning_rate": 1.663135593220339e-05, + "loss": 0.5332, + "step": 6201 + }, + { + "epoch": 0.51, + "learning_rate": 1.6630812690134727e-05, + "loss": 0.5302, + "step": 6202 + }, + { + "epoch": 0.51, + "learning_rate": 1.6630269448066058e-05, + "loss": 0.4828, + "step": 6203 + }, + { + "epoch": 0.51, + "learning_rate": 1.6629726205997395e-05, + "loss": 0.3878, + "step": 6204 + }, + { + "epoch": 0.51, + "learning_rate": 1.6629182963928726e-05, + "loss": 0.2829, + "step": 6205 + }, + { + "epoch": 0.51, + "learning_rate": 1.6628639721860064e-05, + "loss": 0.7603, + "step": 6206 + }, + { + "epoch": 0.51, + "learning_rate": 1.6628096479791394e-05, + "loss": 0.3929, + "step": 6207 + }, + { + "epoch": 0.51, + "learning_rate": 1.6627553237722732e-05, + "loss": 0.798, + "step": 6208 + }, + { + "epoch": 0.51, + "learning_rate": 1.6627009995654063e-05, + "loss": 0.3093, + "step": 6209 + }, + { + "epoch": 0.51, + "learning_rate": 1.66264667535854e-05, + "loss": 0.2685, + "step": 6210 + }, + { + "epoch": 0.51, + "learning_rate": 1.662592351151673e-05, + "loss": 0.3317, + "step": 6211 + }, + { + "epoch": 0.51, + "learning_rate": 1.662538026944807e-05, + "loss": 0.2499, + "step": 6212 + }, + { + "epoch": 0.51, + "learning_rate": 1.66248370273794e-05, + "loss": 0.408, + "step": 6213 + }, + { + "epoch": 0.51, + "learning_rate": 1.6624293785310737e-05, + "loss": 0.3948, + "step": 6214 + }, + { + "epoch": 0.51, + "learning_rate": 1.6623750543242068e-05, + "loss": 0.3469, + "step": 6215 + }, + { + "epoch": 0.51, + "learning_rate": 1.6623207301173406e-05, + "loss": 0.4129, + "step": 6216 + }, + { + "epoch": 0.51, + "learning_rate": 1.6622664059104737e-05, + "loss": 0.553, + "step": 6217 + }, + { + "epoch": 0.51, + "learning_rate": 1.6622120817036074e-05, + "loss": 0.4169, + "step": 6218 + }, + { + "epoch": 0.51, + "learning_rate": 1.6621577574967405e-05, + "loss": 0.7519, + "step": 6219 + }, + { + "epoch": 0.51, + "learning_rate": 1.662103433289874e-05, + "loss": 0.6327, + "step": 6220 + }, + { + "epoch": 0.51, + "learning_rate": 1.6620491090830077e-05, + "loss": 0.3579, + "step": 6221 + }, + { + "epoch": 0.51, + "learning_rate": 1.6619947848761408e-05, + "loss": 0.4906, + "step": 6222 + }, + { + "epoch": 0.51, + "learning_rate": 1.6619404606692746e-05, + "loss": 0.6382, + "step": 6223 + }, + { + "epoch": 0.51, + "learning_rate": 1.6618861364624076e-05, + "loss": 0.4614, + "step": 6224 + }, + { + "epoch": 0.51, + "learning_rate": 1.6618318122555414e-05, + "loss": 0.5565, + "step": 6225 + }, + { + "epoch": 0.51, + "learning_rate": 1.6617774880486745e-05, + "loss": 0.6203, + "step": 6226 + }, + { + "epoch": 0.51, + "learning_rate": 1.6617231638418082e-05, + "loss": 0.6204, + "step": 6227 + }, + { + "epoch": 0.51, + "learning_rate": 1.6616688396349413e-05, + "loss": 0.4628, + "step": 6228 + }, + { + "epoch": 0.51, + "learning_rate": 1.661614515428075e-05, + "loss": 0.5085, + "step": 6229 + }, + { + "epoch": 0.51, + "learning_rate": 1.6615601912212082e-05, + "loss": 0.7239, + "step": 6230 + }, + { + "epoch": 0.51, + "learning_rate": 1.661505867014342e-05, + "loss": 0.7859, + "step": 6231 + }, + { + "epoch": 0.51, + "learning_rate": 1.661451542807475e-05, + "loss": 0.4902, + "step": 6232 + }, + { + "epoch": 0.51, + "learning_rate": 1.6613972186006088e-05, + "loss": 0.4733, + "step": 6233 + }, + { + "epoch": 0.51, + "learning_rate": 1.661342894393742e-05, + "loss": 0.5491, + "step": 6234 + }, + { + "epoch": 0.51, + "learning_rate": 1.6612885701868756e-05, + "loss": 0.549, + "step": 6235 + }, + { + "epoch": 0.51, + "learning_rate": 1.6612342459800087e-05, + "loss": 0.3703, + "step": 6236 + }, + { + "epoch": 0.51, + "learning_rate": 1.6611799217731425e-05, + "loss": 0.4219, + "step": 6237 + }, + { + "epoch": 0.51, + "learning_rate": 1.6611255975662756e-05, + "loss": 0.4977, + "step": 6238 + }, + { + "epoch": 0.51, + "learning_rate": 1.661071273359409e-05, + "loss": 0.2795, + "step": 6239 + }, + { + "epoch": 0.51, + "learning_rate": 1.6610169491525424e-05, + "loss": 0.5809, + "step": 6240 + }, + { + "epoch": 0.51, + "learning_rate": 1.6609626249456758e-05, + "loss": 0.3419, + "step": 6241 + }, + { + "epoch": 0.51, + "learning_rate": 1.6609083007388093e-05, + "loss": 0.3756, + "step": 6242 + }, + { + "epoch": 0.51, + "learning_rate": 1.6608539765319427e-05, + "loss": 0.5928, + "step": 6243 + }, + { + "epoch": 0.51, + "learning_rate": 1.660799652325076e-05, + "loss": 0.4974, + "step": 6244 + }, + { + "epoch": 0.51, + "learning_rate": 1.6607453281182095e-05, + "loss": 0.587, + "step": 6245 + }, + { + "epoch": 0.51, + "learning_rate": 1.660691003911343e-05, + "loss": 0.4339, + "step": 6246 + }, + { + "epoch": 0.51, + "learning_rate": 1.6606366797044764e-05, + "loss": 0.217, + "step": 6247 + }, + { + "epoch": 0.51, + "learning_rate": 1.6605823554976098e-05, + "loss": 0.4214, + "step": 6248 + }, + { + "epoch": 0.51, + "learning_rate": 1.6605280312907432e-05, + "loss": 0.3532, + "step": 6249 + }, + { + "epoch": 0.51, + "learning_rate": 1.6604737070838766e-05, + "loss": 0.498, + "step": 6250 + }, + { + "epoch": 0.51, + "eval_accuracy": 0.8222109016811003, + "eval_loss": 0.45893293619155884, + "eval_runtime": 22.2395, + "eval_samples_per_second": 441.332, + "eval_steps_per_second": 3.462, + "step": 6250 + }, + { + "epoch": 0.51, + "learning_rate": 1.66041938287701e-05, + "loss": 0.669, + "step": 6251 + }, + { + "epoch": 0.51, + "learning_rate": 1.6603650586701435e-05, + "loss": 0.6008, + "step": 6252 + }, + { + "epoch": 0.51, + "learning_rate": 1.660310734463277e-05, + "loss": 0.6407, + "step": 6253 + }, + { + "epoch": 0.51, + "learning_rate": 1.6602564102564103e-05, + "loss": 0.5669, + "step": 6254 + }, + { + "epoch": 0.51, + "learning_rate": 1.6602020860495438e-05, + "loss": 0.3817, + "step": 6255 + }, + { + "epoch": 0.51, + "learning_rate": 1.6601477618426772e-05, + "loss": 0.4763, + "step": 6256 + }, + { + "epoch": 0.51, + "learning_rate": 1.6600934376358106e-05, + "loss": 0.7299, + "step": 6257 + }, + { + "epoch": 0.51, + "learning_rate": 1.660039113428944e-05, + "loss": 0.396, + "step": 6258 + }, + { + "epoch": 0.51, + "learning_rate": 1.6599847892220774e-05, + "loss": 0.5459, + "step": 6259 + }, + { + "epoch": 0.51, + "learning_rate": 1.659930465015211e-05, + "loss": 0.3476, + "step": 6260 + }, + { + "epoch": 0.51, + "learning_rate": 1.6598761408083443e-05, + "loss": 0.4629, + "step": 6261 + }, + { + "epoch": 0.51, + "learning_rate": 1.6598218166014777e-05, + "loss": 0.4888, + "step": 6262 + }, + { + "epoch": 0.51, + "learning_rate": 1.659767492394611e-05, + "loss": 0.5444, + "step": 6263 + }, + { + "epoch": 0.51, + "learning_rate": 1.6597131681877446e-05, + "loss": 0.3823, + "step": 6264 + }, + { + "epoch": 0.51, + "learning_rate": 1.659658843980878e-05, + "loss": 0.7064, + "step": 6265 + }, + { + "epoch": 0.51, + "learning_rate": 1.6596045197740114e-05, + "loss": 0.5877, + "step": 6266 + }, + { + "epoch": 0.51, + "learning_rate": 1.6595501955671448e-05, + "loss": 0.3926, + "step": 6267 + }, + { + "epoch": 0.51, + "learning_rate": 1.6594958713602783e-05, + "loss": 0.4899, + "step": 6268 + }, + { + "epoch": 0.51, + "learning_rate": 1.6594415471534117e-05, + "loss": 0.5738, + "step": 6269 + }, + { + "epoch": 0.51, + "learning_rate": 1.659387222946545e-05, + "loss": 0.5411, + "step": 6270 + }, + { + "epoch": 0.51, + "learning_rate": 1.6593328987396785e-05, + "loss": 0.2762, + "step": 6271 + }, + { + "epoch": 0.51, + "learning_rate": 1.659278574532812e-05, + "loss": 0.5726, + "step": 6272 + }, + { + "epoch": 0.51, + "learning_rate": 1.6592242503259454e-05, + "loss": 0.4014, + "step": 6273 + }, + { + "epoch": 0.51, + "learning_rate": 1.6591699261190788e-05, + "loss": 0.7609, + "step": 6274 + }, + { + "epoch": 0.51, + "learning_rate": 1.6591156019122122e-05, + "loss": 0.4254, + "step": 6275 + }, + { + "epoch": 0.51, + "learning_rate": 1.6590612777053456e-05, + "loss": 0.5267, + "step": 6276 + }, + { + "epoch": 0.51, + "learning_rate": 1.659006953498479e-05, + "loss": 0.4684, + "step": 6277 + }, + { + "epoch": 0.51, + "learning_rate": 1.6589526292916125e-05, + "loss": 0.555, + "step": 6278 + }, + { + "epoch": 0.51, + "learning_rate": 1.658898305084746e-05, + "loss": 0.6252, + "step": 6279 + }, + { + "epoch": 0.51, + "learning_rate": 1.6588439808778793e-05, + "loss": 0.3901, + "step": 6280 + }, + { + "epoch": 0.51, + "learning_rate": 1.6587896566710128e-05, + "loss": 0.6176, + "step": 6281 + }, + { + "epoch": 0.51, + "learning_rate": 1.6587353324641462e-05, + "loss": 0.2762, + "step": 6282 + }, + { + "epoch": 0.51, + "learning_rate": 1.6586810082572796e-05, + "loss": 0.3646, + "step": 6283 + }, + { + "epoch": 0.51, + "learning_rate": 1.658626684050413e-05, + "loss": 0.4692, + "step": 6284 + }, + { + "epoch": 0.51, + "learning_rate": 1.6585723598435464e-05, + "loss": 0.5412, + "step": 6285 + }, + { + "epoch": 0.51, + "learning_rate": 1.65851803563668e-05, + "loss": 0.59, + "step": 6286 + }, + { + "epoch": 0.51, + "learning_rate": 1.6584637114298133e-05, + "loss": 0.6063, + "step": 6287 + }, + { + "epoch": 0.51, + "learning_rate": 1.6584093872229467e-05, + "loss": 0.36, + "step": 6288 + }, + { + "epoch": 0.51, + "learning_rate": 1.65835506301608e-05, + "loss": 0.4038, + "step": 6289 + }, + { + "epoch": 0.51, + "learning_rate": 1.6583007388092136e-05, + "loss": 0.7129, + "step": 6290 + }, + { + "epoch": 0.51, + "learning_rate": 1.658246414602347e-05, + "loss": 0.4463, + "step": 6291 + }, + { + "epoch": 0.51, + "learning_rate": 1.6581920903954804e-05, + "loss": 0.3123, + "step": 6292 + }, + { + "epoch": 0.51, + "learning_rate": 1.6581377661886138e-05, + "loss": 0.533, + "step": 6293 + }, + { + "epoch": 0.51, + "learning_rate": 1.6580834419817473e-05, + "loss": 0.6372, + "step": 6294 + }, + { + "epoch": 0.51, + "learning_rate": 1.6580291177748807e-05, + "loss": 0.4544, + "step": 6295 + }, + { + "epoch": 0.51, + "learning_rate": 1.657974793568014e-05, + "loss": 0.4288, + "step": 6296 + }, + { + "epoch": 0.51, + "learning_rate": 1.6579204693611475e-05, + "loss": 0.3876, + "step": 6297 + }, + { + "epoch": 0.51, + "learning_rate": 1.657866145154281e-05, + "loss": 0.5089, + "step": 6298 + }, + { + "epoch": 0.51, + "learning_rate": 1.6578118209474144e-05, + "loss": 0.4819, + "step": 6299 + }, + { + "epoch": 0.51, + "learning_rate": 1.6577574967405478e-05, + "loss": 0.5413, + "step": 6300 + }, + { + "epoch": 0.51, + "learning_rate": 1.6577031725336812e-05, + "loss": 0.5259, + "step": 6301 + }, + { + "epoch": 0.51, + "learning_rate": 1.6576488483268146e-05, + "loss": 0.7402, + "step": 6302 + }, + { + "epoch": 0.51, + "learning_rate": 1.657594524119948e-05, + "loss": 0.4863, + "step": 6303 + }, + { + "epoch": 0.51, + "learning_rate": 1.6575401999130815e-05, + "loss": 0.5232, + "step": 6304 + }, + { + "epoch": 0.51, + "learning_rate": 1.657485875706215e-05, + "loss": 0.8032, + "step": 6305 + }, + { + "epoch": 0.51, + "learning_rate": 1.6574315514993483e-05, + "loss": 0.425, + "step": 6306 + }, + { + "epoch": 0.51, + "learning_rate": 1.6573772272924818e-05, + "loss": 0.6643, + "step": 6307 + }, + { + "epoch": 0.51, + "learning_rate": 1.6573229030856152e-05, + "loss": 0.2462, + "step": 6308 + }, + { + "epoch": 0.51, + "learning_rate": 1.6572685788787486e-05, + "loss": 0.5319, + "step": 6309 + }, + { + "epoch": 0.51, + "learning_rate": 1.657214254671882e-05, + "loss": 0.7228, + "step": 6310 + }, + { + "epoch": 0.51, + "learning_rate": 1.6571599304650154e-05, + "loss": 0.7694, + "step": 6311 + }, + { + "epoch": 0.51, + "learning_rate": 1.657105606258149e-05, + "loss": 0.6839, + "step": 6312 + }, + { + "epoch": 0.51, + "learning_rate": 1.6570512820512823e-05, + "loss": 0.84, + "step": 6313 + }, + { + "epoch": 0.51, + "learning_rate": 1.6569969578444157e-05, + "loss": 0.4627, + "step": 6314 + }, + { + "epoch": 0.51, + "learning_rate": 1.6569426336375488e-05, + "loss": 0.4857, + "step": 6315 + }, + { + "epoch": 0.51, + "learning_rate": 1.6568883094306826e-05, + "loss": 0.3833, + "step": 6316 + }, + { + "epoch": 0.51, + "learning_rate": 1.6568339852238156e-05, + "loss": 0.619, + "step": 6317 + }, + { + "epoch": 0.51, + "learning_rate": 1.6567796610169494e-05, + "loss": 0.3563, + "step": 6318 + }, + { + "epoch": 0.51, + "learning_rate": 1.6567253368100825e-05, + "loss": 0.5642, + "step": 6319 + }, + { + "epoch": 0.51, + "learning_rate": 1.6566710126032162e-05, + "loss": 0.4889, + "step": 6320 + }, + { + "epoch": 0.52, + "learning_rate": 1.6566166883963493e-05, + "loss": 0.5382, + "step": 6321 + }, + { + "epoch": 0.52, + "learning_rate": 1.656562364189483e-05, + "loss": 0.5551, + "step": 6322 + }, + { + "epoch": 0.52, + "learning_rate": 1.6565080399826162e-05, + "loss": 0.5238, + "step": 6323 + }, + { + "epoch": 0.52, + "learning_rate": 1.65645371577575e-05, + "loss": 0.5871, + "step": 6324 + }, + { + "epoch": 0.52, + "learning_rate": 1.656399391568883e-05, + "loss": 0.4748, + "step": 6325 + }, + { + "epoch": 0.52, + "learning_rate": 1.6563450673620168e-05, + "loss": 0.3553, + "step": 6326 + }, + { + "epoch": 0.52, + "learning_rate": 1.65629074315515e-05, + "loss": 0.5363, + "step": 6327 + }, + { + "epoch": 0.52, + "learning_rate": 1.6562364189482836e-05, + "loss": 0.6669, + "step": 6328 + }, + { + "epoch": 0.52, + "learning_rate": 1.656182094741417e-05, + "loss": 0.6108, + "step": 6329 + }, + { + "epoch": 0.52, + "learning_rate": 1.6561277705345505e-05, + "loss": 0.3063, + "step": 6330 + }, + { + "epoch": 0.52, + "learning_rate": 1.656073446327684e-05, + "loss": 0.4626, + "step": 6331 + }, + { + "epoch": 0.52, + "learning_rate": 1.6560191221208173e-05, + "loss": 0.7054, + "step": 6332 + }, + { + "epoch": 0.52, + "learning_rate": 1.6559647979139507e-05, + "loss": 0.4046, + "step": 6333 + }, + { + "epoch": 0.52, + "learning_rate": 1.655910473707084e-05, + "loss": 0.381, + "step": 6334 + }, + { + "epoch": 0.52, + "learning_rate": 1.6558561495002176e-05, + "loss": 0.3085, + "step": 6335 + }, + { + "epoch": 0.52, + "learning_rate": 1.6558018252933507e-05, + "loss": 0.531, + "step": 6336 + }, + { + "epoch": 0.52, + "learning_rate": 1.6557475010864844e-05, + "loss": 0.552, + "step": 6337 + }, + { + "epoch": 0.52, + "learning_rate": 1.6556931768796175e-05, + "loss": 0.5067, + "step": 6338 + }, + { + "epoch": 0.52, + "learning_rate": 1.6556388526727513e-05, + "loss": 0.6719, + "step": 6339 + }, + { + "epoch": 0.52, + "learning_rate": 1.6555845284658844e-05, + "loss": 0.3693, + "step": 6340 + }, + { + "epoch": 0.52, + "learning_rate": 1.655530204259018e-05, + "loss": 0.4609, + "step": 6341 + }, + { + "epoch": 0.52, + "learning_rate": 1.6554758800521512e-05, + "loss": 0.5038, + "step": 6342 + }, + { + "epoch": 0.52, + "learning_rate": 1.655421555845285e-05, + "loss": 0.6183, + "step": 6343 + }, + { + "epoch": 0.52, + "learning_rate": 1.655367231638418e-05, + "loss": 0.502, + "step": 6344 + }, + { + "epoch": 0.52, + "learning_rate": 1.6553129074315518e-05, + "loss": 0.673, + "step": 6345 + }, + { + "epoch": 0.52, + "learning_rate": 1.655258583224685e-05, + "loss": 0.4779, + "step": 6346 + }, + { + "epoch": 0.52, + "learning_rate": 1.6552042590178187e-05, + "loss": 0.5574, + "step": 6347 + }, + { + "epoch": 0.52, + "learning_rate": 1.6551499348109518e-05, + "loss": 0.3083, + "step": 6348 + }, + { + "epoch": 0.52, + "learning_rate": 1.6550956106040855e-05, + "loss": 0.5487, + "step": 6349 + }, + { + "epoch": 0.52, + "learning_rate": 1.6550412863972186e-05, + "loss": 0.4956, + "step": 6350 + }, + { + "epoch": 0.52, + "learning_rate": 1.6549869621903524e-05, + "loss": 0.4028, + "step": 6351 + }, + { + "epoch": 0.52, + "learning_rate": 1.6549326379834854e-05, + "loss": 0.2851, + "step": 6352 + }, + { + "epoch": 0.52, + "learning_rate": 1.654878313776619e-05, + "loss": 0.4031, + "step": 6353 + }, + { + "epoch": 0.52, + "learning_rate": 1.6548239895697523e-05, + "loss": 0.6359, + "step": 6354 + }, + { + "epoch": 0.52, + "learning_rate": 1.6547696653628857e-05, + "loss": 0.3682, + "step": 6355 + }, + { + "epoch": 0.52, + "learning_rate": 1.654715341156019e-05, + "loss": 0.3483, + "step": 6356 + }, + { + "epoch": 0.52, + "learning_rate": 1.6546610169491526e-05, + "loss": 0.5643, + "step": 6357 + }, + { + "epoch": 0.52, + "learning_rate": 1.654606692742286e-05, + "loss": 0.4335, + "step": 6358 + }, + { + "epoch": 0.52, + "learning_rate": 1.6545523685354194e-05, + "loss": 0.4236, + "step": 6359 + }, + { + "epoch": 0.52, + "learning_rate": 1.654498044328553e-05, + "loss": 0.5931, + "step": 6360 + }, + { + "epoch": 0.52, + "learning_rate": 1.6544437201216863e-05, + "loss": 0.4827, + "step": 6361 + }, + { + "epoch": 0.52, + "learning_rate": 1.6543893959148197e-05, + "loss": 0.6546, + "step": 6362 + }, + { + "epoch": 0.52, + "learning_rate": 1.654335071707953e-05, + "loss": 0.5049, + "step": 6363 + }, + { + "epoch": 0.52, + "learning_rate": 1.6542807475010865e-05, + "loss": 0.5388, + "step": 6364 + }, + { + "epoch": 0.52, + "learning_rate": 1.65422642329422e-05, + "loss": 0.4022, + "step": 6365 + }, + { + "epoch": 0.52, + "learning_rate": 1.6541720990873537e-05, + "loss": 0.54, + "step": 6366 + }, + { + "epoch": 0.52, + "learning_rate": 1.6541177748804868e-05, + "loss": 0.5393, + "step": 6367 + }, + { + "epoch": 0.52, + "learning_rate": 1.6540634506736206e-05, + "loss": 0.5204, + "step": 6368 + }, + { + "epoch": 0.52, + "learning_rate": 1.6540091264667536e-05, + "loss": 0.4063, + "step": 6369 + }, + { + "epoch": 0.52, + "learning_rate": 1.6539548022598874e-05, + "loss": 0.4596, + "step": 6370 + }, + { + "epoch": 0.52, + "learning_rate": 1.6539004780530205e-05, + "loss": 0.3054, + "step": 6371 + }, + { + "epoch": 0.52, + "learning_rate": 1.653846153846154e-05, + "loss": 0.5801, + "step": 6372 + }, + { + "epoch": 0.52, + "learning_rate": 1.6537918296392873e-05, + "loss": 0.2733, + "step": 6373 + }, + { + "epoch": 0.52, + "learning_rate": 1.6537375054324208e-05, + "loss": 0.5543, + "step": 6374 + }, + { + "epoch": 0.52, + "learning_rate": 1.6536831812255542e-05, + "loss": 0.7243, + "step": 6375 + }, + { + "epoch": 0.52, + "learning_rate": 1.6536288570186876e-05, + "loss": 0.5535, + "step": 6376 + }, + { + "epoch": 0.52, + "learning_rate": 1.653574532811821e-05, + "loss": 0.3789, + "step": 6377 + }, + { + "epoch": 0.52, + "learning_rate": 1.6535202086049544e-05, + "loss": 0.6152, + "step": 6378 + }, + { + "epoch": 0.52, + "learning_rate": 1.653465884398088e-05, + "loss": 0.589, + "step": 6379 + }, + { + "epoch": 0.52, + "learning_rate": 1.6534115601912213e-05, + "loss": 0.6771, + "step": 6380 + }, + { + "epoch": 0.52, + "learning_rate": 1.6533572359843547e-05, + "loss": 0.6163, + "step": 6381 + }, + { + "epoch": 0.52, + "learning_rate": 1.653302911777488e-05, + "loss": 0.335, + "step": 6382 + }, + { + "epoch": 0.52, + "learning_rate": 1.6532485875706216e-05, + "loss": 0.3869, + "step": 6383 + }, + { + "epoch": 0.52, + "learning_rate": 1.653194263363755e-05, + "loss": 0.6281, + "step": 6384 + }, + { + "epoch": 0.52, + "learning_rate": 1.6531399391568884e-05, + "loss": 0.4878, + "step": 6385 + }, + { + "epoch": 0.52, + "learning_rate": 1.653085614950022e-05, + "loss": 0.4421, + "step": 6386 + }, + { + "epoch": 0.52, + "learning_rate": 1.6530312907431553e-05, + "loss": 0.3015, + "step": 6387 + }, + { + "epoch": 0.52, + "learning_rate": 1.6529769665362887e-05, + "loss": 0.7517, + "step": 6388 + }, + { + "epoch": 0.52, + "learning_rate": 1.652922642329422e-05, + "loss": 0.4759, + "step": 6389 + }, + { + "epoch": 0.52, + "learning_rate": 1.6528683181225555e-05, + "loss": 0.3962, + "step": 6390 + }, + { + "epoch": 0.52, + "learning_rate": 1.652813993915689e-05, + "loss": 0.3566, + "step": 6391 + }, + { + "epoch": 0.52, + "learning_rate": 1.6527596697088224e-05, + "loss": 0.421, + "step": 6392 + }, + { + "epoch": 0.52, + "learning_rate": 1.6527053455019558e-05, + "loss": 0.5989, + "step": 6393 + }, + { + "epoch": 0.52, + "learning_rate": 1.6526510212950892e-05, + "loss": 0.6493, + "step": 6394 + }, + { + "epoch": 0.52, + "learning_rate": 1.6525966970882226e-05, + "loss": 0.6817, + "step": 6395 + }, + { + "epoch": 0.52, + "learning_rate": 1.652542372881356e-05, + "loss": 0.4252, + "step": 6396 + }, + { + "epoch": 0.52, + "learning_rate": 1.6524880486744895e-05, + "loss": 0.3988, + "step": 6397 + }, + { + "epoch": 0.52, + "learning_rate": 1.652433724467623e-05, + "loss": 0.8545, + "step": 6398 + }, + { + "epoch": 0.52, + "learning_rate": 1.6523794002607563e-05, + "loss": 0.5278, + "step": 6399 + }, + { + "epoch": 0.52, + "learning_rate": 1.6523250760538898e-05, + "loss": 0.2814, + "step": 6400 + }, + { + "epoch": 0.52, + "learning_rate": 1.6522707518470232e-05, + "loss": 0.7198, + "step": 6401 + }, + { + "epoch": 0.52, + "learning_rate": 1.6522164276401566e-05, + "loss": 0.3001, + "step": 6402 + }, + { + "epoch": 0.52, + "learning_rate": 1.65216210343329e-05, + "loss": 0.5366, + "step": 6403 + }, + { + "epoch": 0.52, + "learning_rate": 1.6521077792264234e-05, + "loss": 0.5766, + "step": 6404 + }, + { + "epoch": 0.52, + "learning_rate": 1.652053455019557e-05, + "loss": 0.4387, + "step": 6405 + }, + { + "epoch": 0.52, + "learning_rate": 1.6519991308126903e-05, + "loss": 0.5915, + "step": 6406 + }, + { + "epoch": 0.52, + "learning_rate": 1.6519448066058237e-05, + "loss": 0.2516, + "step": 6407 + }, + { + "epoch": 0.52, + "learning_rate": 1.651890482398957e-05, + "loss": 0.4817, + "step": 6408 + }, + { + "epoch": 0.52, + "learning_rate": 1.6518361581920906e-05, + "loss": 0.478, + "step": 6409 + }, + { + "epoch": 0.52, + "learning_rate": 1.651781833985224e-05, + "loss": 0.2958, + "step": 6410 + }, + { + "epoch": 0.52, + "learning_rate": 1.6517275097783574e-05, + "loss": 0.3252, + "step": 6411 + }, + { + "epoch": 0.52, + "learning_rate": 1.651673185571491e-05, + "loss": 0.5612, + "step": 6412 + }, + { + "epoch": 0.52, + "learning_rate": 1.6516188613646243e-05, + "loss": 0.3776, + "step": 6413 + }, + { + "epoch": 0.52, + "learning_rate": 1.6515645371577577e-05, + "loss": 0.8196, + "step": 6414 + }, + { + "epoch": 0.52, + "learning_rate": 1.651510212950891e-05, + "loss": 0.2988, + "step": 6415 + }, + { + "epoch": 0.52, + "learning_rate": 1.6514558887440245e-05, + "loss": 0.4306, + "step": 6416 + }, + { + "epoch": 0.52, + "learning_rate": 1.651401564537158e-05, + "loss": 0.6409, + "step": 6417 + }, + { + "epoch": 0.52, + "learning_rate": 1.6513472403302914e-05, + "loss": 0.3027, + "step": 6418 + }, + { + "epoch": 0.52, + "learning_rate": 1.6512929161234248e-05, + "loss": 0.6098, + "step": 6419 + }, + { + "epoch": 0.52, + "learning_rate": 1.6512385919165582e-05, + "loss": 0.3901, + "step": 6420 + }, + { + "epoch": 0.52, + "learning_rate": 1.6511842677096916e-05, + "loss": 0.4556, + "step": 6421 + }, + { + "epoch": 0.52, + "learning_rate": 1.651129943502825e-05, + "loss": 0.4243, + "step": 6422 + }, + { + "epoch": 0.52, + "learning_rate": 1.6510756192959585e-05, + "loss": 0.6556, + "step": 6423 + }, + { + "epoch": 0.52, + "learning_rate": 1.651021295089092e-05, + "loss": 0.4703, + "step": 6424 + }, + { + "epoch": 0.52, + "learning_rate": 1.6509669708822253e-05, + "loss": 0.4726, + "step": 6425 + }, + { + "epoch": 0.52, + "learning_rate": 1.6509126466753588e-05, + "loss": 0.6894, + "step": 6426 + }, + { + "epoch": 0.52, + "learning_rate": 1.6508583224684922e-05, + "loss": 0.586, + "step": 6427 + }, + { + "epoch": 0.52, + "learning_rate": 1.6508039982616256e-05, + "loss": 0.4544, + "step": 6428 + }, + { + "epoch": 0.52, + "learning_rate": 1.6507496740547587e-05, + "loss": 0.5801, + "step": 6429 + }, + { + "epoch": 0.52, + "learning_rate": 1.6506953498478924e-05, + "loss": 0.4425, + "step": 6430 + }, + { + "epoch": 0.52, + "learning_rate": 1.6506410256410255e-05, + "loss": 0.3053, + "step": 6431 + }, + { + "epoch": 0.52, + "learning_rate": 1.6505867014341593e-05, + "loss": 0.6106, + "step": 6432 + }, + { + "epoch": 0.52, + "learning_rate": 1.6505323772272924e-05, + "loss": 0.4624, + "step": 6433 + }, + { + "epoch": 0.52, + "learning_rate": 1.650478053020426e-05, + "loss": 0.4656, + "step": 6434 + }, + { + "epoch": 0.52, + "learning_rate": 1.6504237288135592e-05, + "loss": 0.437, + "step": 6435 + }, + { + "epoch": 0.52, + "learning_rate": 1.650369404606693e-05, + "loss": 0.4624, + "step": 6436 + }, + { + "epoch": 0.52, + "learning_rate": 1.6503150803998264e-05, + "loss": 0.4336, + "step": 6437 + }, + { + "epoch": 0.52, + "learning_rate": 1.65026075619296e-05, + "loss": 0.3486, + "step": 6438 + }, + { + "epoch": 0.52, + "learning_rate": 1.6502064319860933e-05, + "loss": 0.3322, + "step": 6439 + }, + { + "epoch": 0.52, + "learning_rate": 1.6501521077792267e-05, + "loss": 0.489, + "step": 6440 + }, + { + "epoch": 0.52, + "learning_rate": 1.65009778357236e-05, + "loss": 0.7213, + "step": 6441 + }, + { + "epoch": 0.52, + "learning_rate": 1.6500434593654935e-05, + "loss": 0.4054, + "step": 6442 + }, + { + "epoch": 0.53, + "learning_rate": 1.649989135158627e-05, + "loss": 0.4216, + "step": 6443 + }, + { + "epoch": 0.53, + "learning_rate": 1.6499348109517604e-05, + "loss": 0.3758, + "step": 6444 + }, + { + "epoch": 0.53, + "learning_rate": 1.6498804867448938e-05, + "loss": 0.8237, + "step": 6445 + }, + { + "epoch": 0.53, + "learning_rate": 1.6498261625380272e-05, + "loss": 0.5472, + "step": 6446 + }, + { + "epoch": 0.53, + "learning_rate": 1.6497718383311606e-05, + "loss": 0.5752, + "step": 6447 + }, + { + "epoch": 0.53, + "learning_rate": 1.6497175141242937e-05, + "loss": 0.6348, + "step": 6448 + }, + { + "epoch": 0.53, + "learning_rate": 1.6496631899174275e-05, + "loss": 0.4451, + "step": 6449 + }, + { + "epoch": 0.53, + "learning_rate": 1.6496088657105606e-05, + "loss": 0.456, + "step": 6450 + }, + { + "epoch": 0.53, + "learning_rate": 1.6495545415036943e-05, + "loss": 0.4164, + "step": 6451 + }, + { + "epoch": 0.53, + "learning_rate": 1.6495002172968274e-05, + "loss": 0.5407, + "step": 6452 + }, + { + "epoch": 0.53, + "learning_rate": 1.6494458930899612e-05, + "loss": 0.4428, + "step": 6453 + }, + { + "epoch": 0.53, + "learning_rate": 1.6493915688830943e-05, + "loss": 0.6133, + "step": 6454 + }, + { + "epoch": 0.53, + "learning_rate": 1.649337244676228e-05, + "loss": 0.5479, + "step": 6455 + }, + { + "epoch": 0.53, + "learning_rate": 1.649282920469361e-05, + "loss": 0.5318, + "step": 6456 + }, + { + "epoch": 0.53, + "learning_rate": 1.649228596262495e-05, + "loss": 0.4739, + "step": 6457 + }, + { + "epoch": 0.53, + "learning_rate": 1.649174272055628e-05, + "loss": 0.4007, + "step": 6458 + }, + { + "epoch": 0.53, + "learning_rate": 1.6491199478487617e-05, + "loss": 0.4862, + "step": 6459 + }, + { + "epoch": 0.53, + "learning_rate": 1.6490656236418948e-05, + "loss": 0.4765, + "step": 6460 + }, + { + "epoch": 0.53, + "learning_rate": 1.6490112994350286e-05, + "loss": 0.758, + "step": 6461 + }, + { + "epoch": 0.53, + "learning_rate": 1.6489569752281616e-05, + "loss": 0.7857, + "step": 6462 + }, + { + "epoch": 0.53, + "learning_rate": 1.6489026510212954e-05, + "loss": 0.5198, + "step": 6463 + }, + { + "epoch": 0.53, + "learning_rate": 1.6488483268144285e-05, + "loss": 0.6094, + "step": 6464 + }, + { + "epoch": 0.53, + "learning_rate": 1.6487940026075623e-05, + "loss": 0.3727, + "step": 6465 + }, + { + "epoch": 0.53, + "learning_rate": 1.6487396784006953e-05, + "loss": 0.6635, + "step": 6466 + }, + { + "epoch": 0.53, + "learning_rate": 1.6486853541938288e-05, + "loss": 0.6801, + "step": 6467 + }, + { + "epoch": 0.53, + "learning_rate": 1.6486310299869622e-05, + "loss": 0.5615, + "step": 6468 + }, + { + "epoch": 0.53, + "learning_rate": 1.6485767057800956e-05, + "loss": 0.6666, + "step": 6469 + }, + { + "epoch": 0.53, + "learning_rate": 1.648522381573229e-05, + "loss": 0.5228, + "step": 6470 + }, + { + "epoch": 0.53, + "learning_rate": 1.6484680573663625e-05, + "loss": 0.5537, + "step": 6471 + }, + { + "epoch": 0.53, + "learning_rate": 1.648413733159496e-05, + "loss": 0.4972, + "step": 6472 + }, + { + "epoch": 0.53, + "learning_rate": 1.6483594089526293e-05, + "loss": 0.2709, + "step": 6473 + }, + { + "epoch": 0.53, + "learning_rate": 1.648305084745763e-05, + "loss": 0.5778, + "step": 6474 + }, + { + "epoch": 0.53, + "learning_rate": 1.648250760538896e-05, + "loss": 0.5756, + "step": 6475 + }, + { + "epoch": 0.53, + "learning_rate": 1.64819643633203e-05, + "loss": 0.5383, + "step": 6476 + }, + { + "epoch": 0.53, + "learning_rate": 1.648142112125163e-05, + "loss": 0.3823, + "step": 6477 + }, + { + "epoch": 0.53, + "learning_rate": 1.6480877879182968e-05, + "loss": 0.5175, + "step": 6478 + }, + { + "epoch": 0.53, + "learning_rate": 1.64803346371143e-05, + "loss": 0.4209, + "step": 6479 + }, + { + "epoch": 0.53, + "learning_rate": 1.6479791395045636e-05, + "loss": 0.3548, + "step": 6480 + }, + { + "epoch": 0.53, + "learning_rate": 1.6479248152976967e-05, + "loss": 0.495, + "step": 6481 + }, + { + "epoch": 0.53, + "learning_rate": 1.6478704910908304e-05, + "loss": 0.363, + "step": 6482 + }, + { + "epoch": 0.53, + "learning_rate": 1.6478161668839635e-05, + "loss": 0.5837, + "step": 6483 + }, + { + "epoch": 0.53, + "learning_rate": 1.6477618426770973e-05, + "loss": 0.3392, + "step": 6484 + }, + { + "epoch": 0.53, + "learning_rate": 1.6477075184702304e-05, + "loss": 0.7248, + "step": 6485 + }, + { + "epoch": 0.53, + "learning_rate": 1.6476531942633638e-05, + "loss": 0.6012, + "step": 6486 + }, + { + "epoch": 0.53, + "learning_rate": 1.6475988700564972e-05, + "loss": 0.6961, + "step": 6487 + }, + { + "epoch": 0.53, + "learning_rate": 1.6475445458496306e-05, + "loss": 0.5555, + "step": 6488 + }, + { + "epoch": 0.53, + "learning_rate": 1.647490221642764e-05, + "loss": 0.452, + "step": 6489 + }, + { + "epoch": 0.53, + "learning_rate": 1.6474358974358975e-05, + "loss": 0.3566, + "step": 6490 + }, + { + "epoch": 0.53, + "learning_rate": 1.647381573229031e-05, + "loss": 0.3807, + "step": 6491 + }, + { + "epoch": 0.53, + "learning_rate": 1.6473272490221643e-05, + "loss": 0.5454, + "step": 6492 + }, + { + "epoch": 0.53, + "learning_rate": 1.6472729248152978e-05, + "loss": 0.4776, + "step": 6493 + }, + { + "epoch": 0.53, + "learning_rate": 1.6472186006084312e-05, + "loss": 0.6482, + "step": 6494 + }, + { + "epoch": 0.53, + "learning_rate": 1.6471642764015646e-05, + "loss": 0.4849, + "step": 6495 + }, + { + "epoch": 0.53, + "learning_rate": 1.647109952194698e-05, + "loss": 0.2194, + "step": 6496 + }, + { + "epoch": 0.53, + "learning_rate": 1.6470556279878315e-05, + "loss": 0.3676, + "step": 6497 + }, + { + "epoch": 0.53, + "learning_rate": 1.647001303780965e-05, + "loss": 0.5847, + "step": 6498 + }, + { + "epoch": 0.53, + "learning_rate": 1.6469469795740983e-05, + "loss": 0.6012, + "step": 6499 + }, + { + "epoch": 0.53, + "learning_rate": 1.6468926553672317e-05, + "loss": 0.7069, + "step": 6500 + }, + { + "epoch": 0.53, + "eval_accuracy": 0.823331635252165, + "eval_loss": 0.45604264736175537, + "eval_runtime": 22.2635, + "eval_samples_per_second": 440.856, + "eval_steps_per_second": 3.459, + "step": 6500 + }, + { + "epoch": 0.53, + "learning_rate": 1.646838331160365e-05, + "loss": 0.5394, + "step": 6501 + }, + { + "epoch": 0.53, + "learning_rate": 1.6467840069534986e-05, + "loss": 0.4621, + "step": 6502 + }, + { + "epoch": 0.53, + "learning_rate": 1.646729682746632e-05, + "loss": 0.6731, + "step": 6503 + }, + { + "epoch": 0.53, + "learning_rate": 1.6466753585397654e-05, + "loss": 0.3947, + "step": 6504 + }, + { + "epoch": 0.53, + "learning_rate": 1.646621034332899e-05, + "loss": 0.6263, + "step": 6505 + }, + { + "epoch": 0.53, + "learning_rate": 1.6465667101260323e-05, + "loss": 0.762, + "step": 6506 + }, + { + "epoch": 0.53, + "learning_rate": 1.6465123859191657e-05, + "loss": 0.4615, + "step": 6507 + }, + { + "epoch": 0.53, + "learning_rate": 1.646458061712299e-05, + "loss": 0.5556, + "step": 6508 + }, + { + "epoch": 0.53, + "learning_rate": 1.6464037375054325e-05, + "loss": 0.4109, + "step": 6509 + }, + { + "epoch": 0.53, + "learning_rate": 1.646349413298566e-05, + "loss": 0.5094, + "step": 6510 + }, + { + "epoch": 0.53, + "learning_rate": 1.6462950890916994e-05, + "loss": 0.4574, + "step": 6511 + }, + { + "epoch": 0.53, + "learning_rate": 1.6462407648848328e-05, + "loss": 0.5365, + "step": 6512 + }, + { + "epoch": 0.53, + "learning_rate": 1.6461864406779662e-05, + "loss": 0.4636, + "step": 6513 + }, + { + "epoch": 0.53, + "learning_rate": 1.6461321164710996e-05, + "loss": 0.7197, + "step": 6514 + }, + { + "epoch": 0.53, + "learning_rate": 1.646077792264233e-05, + "loss": 0.4008, + "step": 6515 + }, + { + "epoch": 0.53, + "learning_rate": 1.6460234680573665e-05, + "loss": 0.3909, + "step": 6516 + }, + { + "epoch": 0.53, + "learning_rate": 1.6459691438505e-05, + "loss": 0.2719, + "step": 6517 + }, + { + "epoch": 0.53, + "learning_rate": 1.6459148196436333e-05, + "loss": 0.5151, + "step": 6518 + }, + { + "epoch": 0.53, + "learning_rate": 1.6458604954367668e-05, + "loss": 0.5836, + "step": 6519 + }, + { + "epoch": 0.53, + "learning_rate": 1.6458061712299002e-05, + "loss": 0.3265, + "step": 6520 + }, + { + "epoch": 0.53, + "learning_rate": 1.6457518470230336e-05, + "loss": 0.5564, + "step": 6521 + }, + { + "epoch": 0.53, + "learning_rate": 1.645697522816167e-05, + "loss": 0.4423, + "step": 6522 + }, + { + "epoch": 0.53, + "learning_rate": 1.6456431986093005e-05, + "loss": 0.3203, + "step": 6523 + }, + { + "epoch": 0.53, + "learning_rate": 1.645588874402434e-05, + "loss": 0.6083, + "step": 6524 + }, + { + "epoch": 0.53, + "learning_rate": 1.6455345501955673e-05, + "loss": 0.3301, + "step": 6525 + }, + { + "epoch": 0.53, + "learning_rate": 1.6454802259887007e-05, + "loss": 0.4877, + "step": 6526 + }, + { + "epoch": 0.53, + "learning_rate": 1.645425901781834e-05, + "loss": 0.4829, + "step": 6527 + }, + { + "epoch": 0.53, + "learning_rate": 1.6453715775749676e-05, + "loss": 0.4717, + "step": 6528 + }, + { + "epoch": 0.53, + "learning_rate": 1.645317253368101e-05, + "loss": 0.2373, + "step": 6529 + }, + { + "epoch": 0.53, + "learning_rate": 1.6452629291612344e-05, + "loss": 0.4275, + "step": 6530 + }, + { + "epoch": 0.53, + "learning_rate": 1.645208604954368e-05, + "loss": 0.4754, + "step": 6531 + }, + { + "epoch": 0.53, + "learning_rate": 1.6451542807475013e-05, + "loss": 0.3961, + "step": 6532 + }, + { + "epoch": 0.53, + "learning_rate": 1.6450999565406347e-05, + "loss": 0.5416, + "step": 6533 + }, + { + "epoch": 0.53, + "learning_rate": 1.645045632333768e-05, + "loss": 0.5469, + "step": 6534 + }, + { + "epoch": 0.53, + "learning_rate": 1.6449913081269015e-05, + "loss": 0.8925, + "step": 6535 + }, + { + "epoch": 0.53, + "learning_rate": 1.644936983920035e-05, + "loss": 0.5686, + "step": 6536 + }, + { + "epoch": 0.53, + "learning_rate": 1.6448826597131684e-05, + "loss": 0.2974, + "step": 6537 + }, + { + "epoch": 0.53, + "learning_rate": 1.6448283355063018e-05, + "loss": 0.6115, + "step": 6538 + }, + { + "epoch": 0.53, + "learning_rate": 1.6447740112994352e-05, + "loss": 0.4921, + "step": 6539 + }, + { + "epoch": 0.53, + "learning_rate": 1.6447196870925686e-05, + "loss": 0.8034, + "step": 6540 + }, + { + "epoch": 0.53, + "learning_rate": 1.644665362885702e-05, + "loss": 0.3466, + "step": 6541 + }, + { + "epoch": 0.53, + "learning_rate": 1.6446110386788355e-05, + "loss": 0.4808, + "step": 6542 + }, + { + "epoch": 0.53, + "learning_rate": 1.6445567144719686e-05, + "loss": 0.6364, + "step": 6543 + }, + { + "epoch": 0.53, + "learning_rate": 1.6445023902651023e-05, + "loss": 0.5369, + "step": 6544 + }, + { + "epoch": 0.53, + "learning_rate": 1.6444480660582358e-05, + "loss": 0.5211, + "step": 6545 + }, + { + "epoch": 0.53, + "learning_rate": 1.6443937418513692e-05, + "loss": 0.5147, + "step": 6546 + }, + { + "epoch": 0.53, + "learning_rate": 1.6443394176445026e-05, + "loss": 0.3096, + "step": 6547 + }, + { + "epoch": 0.53, + "learning_rate": 1.644285093437636e-05, + "loss": 0.4695, + "step": 6548 + }, + { + "epoch": 0.53, + "learning_rate": 1.6442307692307695e-05, + "loss": 0.3936, + "step": 6549 + }, + { + "epoch": 0.53, + "learning_rate": 1.644176445023903e-05, + "loss": 0.4995, + "step": 6550 + }, + { + "epoch": 0.53, + "learning_rate": 1.6441221208170363e-05, + "loss": 0.5685, + "step": 6551 + }, + { + "epoch": 0.53, + "learning_rate": 1.6440677966101697e-05, + "loss": 0.398, + "step": 6552 + }, + { + "epoch": 0.53, + "learning_rate": 1.644013472403303e-05, + "loss": 0.5958, + "step": 6553 + }, + { + "epoch": 0.53, + "learning_rate": 1.6439591481964366e-05, + "loss": 0.5986, + "step": 6554 + }, + { + "epoch": 0.53, + "learning_rate": 1.64390482398957e-05, + "loss": 0.4595, + "step": 6555 + }, + { + "epoch": 0.53, + "learning_rate": 1.6438504997827034e-05, + "loss": 0.3388, + "step": 6556 + }, + { + "epoch": 0.53, + "learning_rate": 1.643796175575837e-05, + "loss": 0.5325, + "step": 6557 + }, + { + "epoch": 0.53, + "learning_rate": 1.6437418513689703e-05, + "loss": 0.5385, + "step": 6558 + }, + { + "epoch": 0.53, + "learning_rate": 1.6436875271621037e-05, + "loss": 0.4523, + "step": 6559 + }, + { + "epoch": 0.53, + "learning_rate": 1.643633202955237e-05, + "loss": 0.4623, + "step": 6560 + }, + { + "epoch": 0.53, + "learning_rate": 1.6435788787483705e-05, + "loss": 0.3889, + "step": 6561 + }, + { + "epoch": 0.53, + "learning_rate": 1.6435245545415036e-05, + "loss": 0.66, + "step": 6562 + }, + { + "epoch": 0.53, + "learning_rate": 1.6434702303346374e-05, + "loss": 0.6544, + "step": 6563 + }, + { + "epoch": 0.53, + "learning_rate": 1.6434159061277705e-05, + "loss": 0.3014, + "step": 6564 + }, + { + "epoch": 0.53, + "learning_rate": 1.6433615819209042e-05, + "loss": 0.6976, + "step": 6565 + }, + { + "epoch": 0.54, + "learning_rate": 1.6433072577140373e-05, + "loss": 0.3317, + "step": 6566 + }, + { + "epoch": 0.54, + "learning_rate": 1.643252933507171e-05, + "loss": 0.5141, + "step": 6567 + }, + { + "epoch": 0.54, + "learning_rate": 1.643198609300304e-05, + "loss": 0.3349, + "step": 6568 + }, + { + "epoch": 0.54, + "learning_rate": 1.643144285093438e-05, + "loss": 0.5303, + "step": 6569 + }, + { + "epoch": 0.54, + "learning_rate": 1.643089960886571e-05, + "loss": 0.3038, + "step": 6570 + }, + { + "epoch": 0.54, + "learning_rate": 1.6430356366797048e-05, + "loss": 0.3977, + "step": 6571 + }, + { + "epoch": 0.54, + "learning_rate": 1.642981312472838e-05, + "loss": 0.262, + "step": 6572 + }, + { + "epoch": 0.54, + "learning_rate": 1.6429269882659716e-05, + "loss": 0.6782, + "step": 6573 + }, + { + "epoch": 0.54, + "learning_rate": 1.6428726640591047e-05, + "loss": 0.3322, + "step": 6574 + }, + { + "epoch": 0.54, + "learning_rate": 1.6428183398522385e-05, + "loss": 0.781, + "step": 6575 + }, + { + "epoch": 0.54, + "learning_rate": 1.6427640156453715e-05, + "loss": 0.8504, + "step": 6576 + }, + { + "epoch": 0.54, + "learning_rate": 1.6427096914385053e-05, + "loss": 0.5997, + "step": 6577 + }, + { + "epoch": 0.54, + "learning_rate": 1.6426553672316384e-05, + "loss": 0.4706, + "step": 6578 + }, + { + "epoch": 0.54, + "learning_rate": 1.642601043024772e-05, + "loss": 0.4557, + "step": 6579 + }, + { + "epoch": 0.54, + "learning_rate": 1.6425467188179052e-05, + "loss": 0.2465, + "step": 6580 + }, + { + "epoch": 0.54, + "learning_rate": 1.6424923946110387e-05, + "loss": 0.579, + "step": 6581 + }, + { + "epoch": 0.54, + "learning_rate": 1.6424380704041724e-05, + "loss": 0.3522, + "step": 6582 + }, + { + "epoch": 0.54, + "learning_rate": 1.6423837461973055e-05, + "loss": 0.5399, + "step": 6583 + }, + { + "epoch": 0.54, + "learning_rate": 1.6423294219904393e-05, + "loss": 0.4703, + "step": 6584 + }, + { + "epoch": 0.54, + "learning_rate": 1.6422750977835723e-05, + "loss": 0.4709, + "step": 6585 + }, + { + "epoch": 0.54, + "learning_rate": 1.642220773576706e-05, + "loss": 0.4637, + "step": 6586 + }, + { + "epoch": 0.54, + "learning_rate": 1.6421664493698392e-05, + "loss": 0.3182, + "step": 6587 + }, + { + "epoch": 0.54, + "learning_rate": 1.642112125162973e-05, + "loss": 0.499, + "step": 6588 + }, + { + "epoch": 0.54, + "learning_rate": 1.642057800956106e-05, + "loss": 0.6986, + "step": 6589 + }, + { + "epoch": 0.54, + "learning_rate": 1.6420034767492398e-05, + "loss": 0.5179, + "step": 6590 + }, + { + "epoch": 0.54, + "learning_rate": 1.641949152542373e-05, + "loss": 0.2779, + "step": 6591 + }, + { + "epoch": 0.54, + "learning_rate": 1.6418948283355066e-05, + "loss": 0.4284, + "step": 6592 + }, + { + "epoch": 0.54, + "learning_rate": 1.6418405041286397e-05, + "loss": 0.514, + "step": 6593 + }, + { + "epoch": 0.54, + "learning_rate": 1.6417861799217735e-05, + "loss": 0.3863, + "step": 6594 + }, + { + "epoch": 0.54, + "learning_rate": 1.6417318557149066e-05, + "loss": 0.4738, + "step": 6595 + }, + { + "epoch": 0.54, + "learning_rate": 1.6416775315080403e-05, + "loss": 0.2411, + "step": 6596 + }, + { + "epoch": 0.54, + "learning_rate": 1.6416232073011734e-05, + "loss": 0.4823, + "step": 6597 + }, + { + "epoch": 0.54, + "learning_rate": 1.6415688830943072e-05, + "loss": 0.4648, + "step": 6598 + }, + { + "epoch": 0.54, + "learning_rate": 1.6415145588874403e-05, + "loss": 0.5389, + "step": 6599 + }, + { + "epoch": 0.54, + "learning_rate": 1.6414602346805737e-05, + "loss": 0.6346, + "step": 6600 + }, + { + "epoch": 0.54, + "learning_rate": 1.641405910473707e-05, + "loss": 0.3202, + "step": 6601 + }, + { + "epoch": 0.54, + "learning_rate": 1.6413515862668405e-05, + "loss": 0.5404, + "step": 6602 + }, + { + "epoch": 0.54, + "learning_rate": 1.641297262059974e-05, + "loss": 0.5965, + "step": 6603 + }, + { + "epoch": 0.54, + "learning_rate": 1.6412429378531074e-05, + "loss": 0.423, + "step": 6604 + }, + { + "epoch": 0.54, + "learning_rate": 1.6411886136462408e-05, + "loss": 0.4265, + "step": 6605 + }, + { + "epoch": 0.54, + "learning_rate": 1.6411342894393742e-05, + "loss": 0.6199, + "step": 6606 + }, + { + "epoch": 0.54, + "learning_rate": 1.6410799652325076e-05, + "loss": 0.593, + "step": 6607 + }, + { + "epoch": 0.54, + "learning_rate": 1.641025641025641e-05, + "loss": 0.3712, + "step": 6608 + }, + { + "epoch": 0.54, + "learning_rate": 1.6409713168187745e-05, + "loss": 0.5507, + "step": 6609 + }, + { + "epoch": 0.54, + "learning_rate": 1.640916992611908e-05, + "loss": 0.3528, + "step": 6610 + }, + { + "epoch": 0.54, + "learning_rate": 1.6408626684050413e-05, + "loss": 0.4994, + "step": 6611 + }, + { + "epoch": 0.54, + "learning_rate": 1.6408083441981748e-05, + "loss": 0.7465, + "step": 6612 + }, + { + "epoch": 0.54, + "learning_rate": 1.6407540199913082e-05, + "loss": 0.3823, + "step": 6613 + }, + { + "epoch": 0.54, + "learning_rate": 1.6406996957844416e-05, + "loss": 0.4152, + "step": 6614 + }, + { + "epoch": 0.54, + "learning_rate": 1.640645371577575e-05, + "loss": 0.6348, + "step": 6615 + }, + { + "epoch": 0.54, + "learning_rate": 1.6405910473707085e-05, + "loss": 0.371, + "step": 6616 + }, + { + "epoch": 0.54, + "learning_rate": 1.640536723163842e-05, + "loss": 0.2581, + "step": 6617 + }, + { + "epoch": 0.54, + "learning_rate": 1.6404823989569753e-05, + "loss": 0.4252, + "step": 6618 + }, + { + "epoch": 0.54, + "learning_rate": 1.6404280747501087e-05, + "loss": 0.8312, + "step": 6619 + }, + { + "epoch": 0.54, + "learning_rate": 1.640373750543242e-05, + "loss": 0.5393, + "step": 6620 + }, + { + "epoch": 0.54, + "learning_rate": 1.6403194263363756e-05, + "loss": 0.5622, + "step": 6621 + }, + { + "epoch": 0.54, + "learning_rate": 1.640265102129509e-05, + "loss": 0.3941, + "step": 6622 + }, + { + "epoch": 0.54, + "learning_rate": 1.6402107779226424e-05, + "loss": 0.3035, + "step": 6623 + }, + { + "epoch": 0.54, + "learning_rate": 1.640156453715776e-05, + "loss": 0.8185, + "step": 6624 + }, + { + "epoch": 0.54, + "learning_rate": 1.6401021295089093e-05, + "loss": 0.4752, + "step": 6625 + }, + { + "epoch": 0.54, + "learning_rate": 1.6400478053020427e-05, + "loss": 0.3104, + "step": 6626 + }, + { + "epoch": 0.54, + "learning_rate": 1.639993481095176e-05, + "loss": 0.8873, + "step": 6627 + }, + { + "epoch": 0.54, + "learning_rate": 1.6399391568883095e-05, + "loss": 0.6146, + "step": 6628 + }, + { + "epoch": 0.54, + "learning_rate": 1.639884832681443e-05, + "loss": 0.6891, + "step": 6629 + }, + { + "epoch": 0.54, + "learning_rate": 1.6398305084745764e-05, + "loss": 0.8897, + "step": 6630 + }, + { + "epoch": 0.54, + "learning_rate": 1.6397761842677098e-05, + "loss": 0.4901, + "step": 6631 + }, + { + "epoch": 0.54, + "learning_rate": 1.6397218600608432e-05, + "loss": 0.437, + "step": 6632 + }, + { + "epoch": 0.54, + "learning_rate": 1.6396675358539766e-05, + "loss": 0.7261, + "step": 6633 + }, + { + "epoch": 0.54, + "learning_rate": 1.63961321164711e-05, + "loss": 0.6881, + "step": 6634 + }, + { + "epoch": 0.54, + "learning_rate": 1.6395588874402435e-05, + "loss": 0.5489, + "step": 6635 + }, + { + "epoch": 0.54, + "learning_rate": 1.639504563233377e-05, + "loss": 0.485, + "step": 6636 + }, + { + "epoch": 0.54, + "learning_rate": 1.6394502390265103e-05, + "loss": 0.462, + "step": 6637 + }, + { + "epoch": 0.54, + "learning_rate": 1.6393959148196438e-05, + "loss": 0.4345, + "step": 6638 + }, + { + "epoch": 0.54, + "learning_rate": 1.6393415906127772e-05, + "loss": 0.6736, + "step": 6639 + }, + { + "epoch": 0.54, + "learning_rate": 1.6392872664059106e-05, + "loss": 0.5757, + "step": 6640 + }, + { + "epoch": 0.54, + "learning_rate": 1.639232942199044e-05, + "loss": 0.3398, + "step": 6641 + }, + { + "epoch": 0.54, + "learning_rate": 1.6391786179921775e-05, + "loss": 0.581, + "step": 6642 + }, + { + "epoch": 0.54, + "learning_rate": 1.639124293785311e-05, + "loss": 0.6927, + "step": 6643 + }, + { + "epoch": 0.54, + "learning_rate": 1.6390699695784443e-05, + "loss": 0.6235, + "step": 6644 + }, + { + "epoch": 0.54, + "learning_rate": 1.6390156453715777e-05, + "loss": 0.6384, + "step": 6645 + }, + { + "epoch": 0.54, + "learning_rate": 1.638961321164711e-05, + "loss": 0.5227, + "step": 6646 + }, + { + "epoch": 0.54, + "learning_rate": 1.6389069969578446e-05, + "loss": 0.4612, + "step": 6647 + }, + { + "epoch": 0.54, + "learning_rate": 1.638852672750978e-05, + "loss": 0.3571, + "step": 6648 + }, + { + "epoch": 0.54, + "learning_rate": 1.6387983485441114e-05, + "loss": 0.4302, + "step": 6649 + }, + { + "epoch": 0.54, + "learning_rate": 1.638744024337245e-05, + "loss": 0.4607, + "step": 6650 + }, + { + "epoch": 0.54, + "learning_rate": 1.6386897001303783e-05, + "loss": 0.3827, + "step": 6651 + }, + { + "epoch": 0.54, + "learning_rate": 1.6386353759235117e-05, + "loss": 0.4927, + "step": 6652 + }, + { + "epoch": 0.54, + "learning_rate": 1.638581051716645e-05, + "loss": 0.5263, + "step": 6653 + }, + { + "epoch": 0.54, + "learning_rate": 1.6385267275097785e-05, + "loss": 0.5787, + "step": 6654 + }, + { + "epoch": 0.54, + "learning_rate": 1.638472403302912e-05, + "loss": 0.3406, + "step": 6655 + }, + { + "epoch": 0.54, + "learning_rate": 1.6384180790960454e-05, + "loss": 0.5197, + "step": 6656 + }, + { + "epoch": 0.54, + "learning_rate": 1.6383637548891788e-05, + "loss": 0.3781, + "step": 6657 + }, + { + "epoch": 0.54, + "learning_rate": 1.6383094306823122e-05, + "loss": 0.5791, + "step": 6658 + }, + { + "epoch": 0.54, + "learning_rate": 1.6382551064754456e-05, + "loss": 0.4981, + "step": 6659 + }, + { + "epoch": 0.54, + "learning_rate": 1.638200782268579e-05, + "loss": 0.3858, + "step": 6660 + }, + { + "epoch": 0.54, + "learning_rate": 1.6381464580617125e-05, + "loss": 0.5998, + "step": 6661 + }, + { + "epoch": 0.54, + "learning_rate": 1.638092133854846e-05, + "loss": 0.3527, + "step": 6662 + }, + { + "epoch": 0.54, + "learning_rate": 1.6380378096479793e-05, + "loss": 0.4126, + "step": 6663 + }, + { + "epoch": 0.54, + "learning_rate": 1.6379834854411128e-05, + "loss": 0.692, + "step": 6664 + }, + { + "epoch": 0.54, + "learning_rate": 1.6379291612342462e-05, + "loss": 0.362, + "step": 6665 + }, + { + "epoch": 0.54, + "learning_rate": 1.6378748370273796e-05, + "loss": 0.6288, + "step": 6666 + }, + { + "epoch": 0.54, + "learning_rate": 1.637820512820513e-05, + "loss": 0.275, + "step": 6667 + }, + { + "epoch": 0.54, + "learning_rate": 1.6377661886136465e-05, + "loss": 0.6398, + "step": 6668 + }, + { + "epoch": 0.54, + "learning_rate": 1.63771186440678e-05, + "loss": 0.4861, + "step": 6669 + }, + { + "epoch": 0.54, + "learning_rate": 1.6376575401999133e-05, + "loss": 0.5937, + "step": 6670 + }, + { + "epoch": 0.54, + "learning_rate": 1.6376032159930467e-05, + "loss": 0.4379, + "step": 6671 + }, + { + "epoch": 0.54, + "learning_rate": 1.63754889178618e-05, + "loss": 0.5361, + "step": 6672 + }, + { + "epoch": 0.54, + "learning_rate": 1.6374945675793136e-05, + "loss": 0.4871, + "step": 6673 + }, + { + "epoch": 0.54, + "learning_rate": 1.637440243372447e-05, + "loss": 0.3638, + "step": 6674 + }, + { + "epoch": 0.54, + "learning_rate": 1.6373859191655804e-05, + "loss": 0.5444, + "step": 6675 + }, + { + "epoch": 0.54, + "learning_rate": 1.6373315949587135e-05, + "loss": 0.5204, + "step": 6676 + }, + { + "epoch": 0.54, + "learning_rate": 1.6372772707518473e-05, + "loss": 0.4136, + "step": 6677 + }, + { + "epoch": 0.54, + "learning_rate": 1.6372229465449803e-05, + "loss": 0.4388, + "step": 6678 + }, + { + "epoch": 0.54, + "learning_rate": 1.637168622338114e-05, + "loss": 0.1938, + "step": 6679 + }, + { + "epoch": 0.54, + "learning_rate": 1.6371142981312472e-05, + "loss": 0.3423, + "step": 6680 + }, + { + "epoch": 0.54, + "learning_rate": 1.637059973924381e-05, + "loss": 0.5601, + "step": 6681 + }, + { + "epoch": 0.54, + "learning_rate": 1.637005649717514e-05, + "loss": 0.5774, + "step": 6682 + }, + { + "epoch": 0.54, + "learning_rate": 1.6369513255106478e-05, + "loss": 0.2765, + "step": 6683 + }, + { + "epoch": 0.54, + "learning_rate": 1.636897001303781e-05, + "loss": 0.4477, + "step": 6684 + }, + { + "epoch": 0.54, + "learning_rate": 1.6368426770969146e-05, + "loss": 0.534, + "step": 6685 + }, + { + "epoch": 0.54, + "learning_rate": 1.6367883528900477e-05, + "loss": 0.5444, + "step": 6686 + }, + { + "epoch": 0.54, + "learning_rate": 1.6367340286831815e-05, + "loss": 0.4484, + "step": 6687 + }, + { + "epoch": 0.54, + "learning_rate": 1.6366797044763146e-05, + "loss": 0.4976, + "step": 6688 + }, + { + "epoch": 0.55, + "learning_rate": 1.6366253802694483e-05, + "loss": 0.2355, + "step": 6689 + }, + { + "epoch": 0.55, + "learning_rate": 1.6365710560625818e-05, + "loss": 0.3173, + "step": 6690 + }, + { + "epoch": 0.55, + "learning_rate": 1.6365167318557152e-05, + "loss": 0.6473, + "step": 6691 + }, + { + "epoch": 0.55, + "learning_rate": 1.6364624076488486e-05, + "loss": 0.3894, + "step": 6692 + }, + { + "epoch": 0.55, + "learning_rate": 1.636408083441982e-05, + "loss": 0.5891, + "step": 6693 + }, + { + "epoch": 0.55, + "learning_rate": 1.6363537592351155e-05, + "loss": 0.5812, + "step": 6694 + }, + { + "epoch": 0.55, + "learning_rate": 1.6362994350282485e-05, + "loss": 0.4146, + "step": 6695 + }, + { + "epoch": 0.55, + "learning_rate": 1.6362451108213823e-05, + "loss": 0.4276, + "step": 6696 + }, + { + "epoch": 0.55, + "learning_rate": 1.6361907866145154e-05, + "loss": 0.5648, + "step": 6697 + }, + { + "epoch": 0.55, + "learning_rate": 1.636136462407649e-05, + "loss": 0.4295, + "step": 6698 + }, + { + "epoch": 0.55, + "learning_rate": 1.6360821382007822e-05, + "loss": 0.2157, + "step": 6699 + }, + { + "epoch": 0.55, + "learning_rate": 1.636027813993916e-05, + "loss": 0.305, + "step": 6700 + }, + { + "epoch": 0.55, + "learning_rate": 1.635973489787049e-05, + "loss": 0.3097, + "step": 6701 + }, + { + "epoch": 0.55, + "learning_rate": 1.635919165580183e-05, + "loss": 0.4276, + "step": 6702 + }, + { + "epoch": 0.55, + "learning_rate": 1.635864841373316e-05, + "loss": 0.3018, + "step": 6703 + }, + { + "epoch": 0.55, + "learning_rate": 1.6358105171664497e-05, + "loss": 0.2493, + "step": 6704 + }, + { + "epoch": 0.55, + "learning_rate": 1.6357561929595828e-05, + "loss": 0.6061, + "step": 6705 + }, + { + "epoch": 0.55, + "learning_rate": 1.6357018687527165e-05, + "loss": 0.3726, + "step": 6706 + }, + { + "epoch": 0.55, + "learning_rate": 1.6356475445458496e-05, + "loss": 0.3529, + "step": 6707 + }, + { + "epoch": 0.55, + "learning_rate": 1.6355932203389834e-05, + "loss": 0.4344, + "step": 6708 + }, + { + "epoch": 0.55, + "learning_rate": 1.6355388961321165e-05, + "loss": 0.3542, + "step": 6709 + }, + { + "epoch": 0.55, + "learning_rate": 1.6354845719252502e-05, + "loss": 0.4353, + "step": 6710 + }, + { + "epoch": 0.55, + "learning_rate": 1.6354302477183833e-05, + "loss": 0.4775, + "step": 6711 + }, + { + "epoch": 0.55, + "learning_rate": 1.635375923511517e-05, + "loss": 0.343, + "step": 6712 + }, + { + "epoch": 0.55, + "learning_rate": 1.63532159930465e-05, + "loss": 0.3943, + "step": 6713 + }, + { + "epoch": 0.55, + "learning_rate": 1.6352672750977836e-05, + "loss": 0.313, + "step": 6714 + }, + { + "epoch": 0.55, + "learning_rate": 1.635212950890917e-05, + "loss": 0.2139, + "step": 6715 + }, + { + "epoch": 0.55, + "learning_rate": 1.6351586266840504e-05, + "loss": 0.6574, + "step": 6716 + }, + { + "epoch": 0.55, + "learning_rate": 1.635104302477184e-05, + "loss": 0.4716, + "step": 6717 + }, + { + "epoch": 0.55, + "learning_rate": 1.6350499782703173e-05, + "loss": 0.5505, + "step": 6718 + }, + { + "epoch": 0.55, + "learning_rate": 1.6349956540634507e-05, + "loss": 0.7614, + "step": 6719 + }, + { + "epoch": 0.55, + "learning_rate": 1.634941329856584e-05, + "loss": 0.4001, + "step": 6720 + }, + { + "epoch": 0.55, + "learning_rate": 1.6348870056497175e-05, + "loss": 0.411, + "step": 6721 + }, + { + "epoch": 0.55, + "learning_rate": 1.634832681442851e-05, + "loss": 0.724, + "step": 6722 + }, + { + "epoch": 0.55, + "learning_rate": 1.6347783572359844e-05, + "loss": 0.6036, + "step": 6723 + }, + { + "epoch": 0.55, + "learning_rate": 1.6347240330291178e-05, + "loss": 0.3153, + "step": 6724 + }, + { + "epoch": 0.55, + "learning_rate": 1.6346697088222512e-05, + "loss": 0.5123, + "step": 6725 + }, + { + "epoch": 0.55, + "learning_rate": 1.6346153846153847e-05, + "loss": 0.4111, + "step": 6726 + }, + { + "epoch": 0.55, + "learning_rate": 1.6345610604085184e-05, + "loss": 0.5389, + "step": 6727 + }, + { + "epoch": 0.55, + "learning_rate": 1.6345067362016515e-05, + "loss": 0.6097, + "step": 6728 + }, + { + "epoch": 0.55, + "learning_rate": 1.6344524119947853e-05, + "loss": 0.2714, + "step": 6729 + }, + { + "epoch": 0.55, + "learning_rate": 1.6343980877879183e-05, + "loss": 0.1837, + "step": 6730 + }, + { + "epoch": 0.55, + "learning_rate": 1.634343763581052e-05, + "loss": 0.379, + "step": 6731 + }, + { + "epoch": 0.55, + "learning_rate": 1.6342894393741852e-05, + "loss": 0.5669, + "step": 6732 + }, + { + "epoch": 0.55, + "learning_rate": 1.6342351151673186e-05, + "loss": 0.4392, + "step": 6733 + }, + { + "epoch": 0.55, + "learning_rate": 1.634180790960452e-05, + "loss": 0.5029, + "step": 6734 + }, + { + "epoch": 0.55, + "learning_rate": 1.6341264667535855e-05, + "loss": 0.4456, + "step": 6735 + }, + { + "epoch": 0.55, + "learning_rate": 1.634072142546719e-05, + "loss": 0.3857, + "step": 6736 + }, + { + "epoch": 0.55, + "learning_rate": 1.6340178183398523e-05, + "loss": 0.394, + "step": 6737 + }, + { + "epoch": 0.55, + "learning_rate": 1.6339634941329857e-05, + "loss": 0.7799, + "step": 6738 + }, + { + "epoch": 0.55, + "learning_rate": 1.633909169926119e-05, + "loss": 0.5511, + "step": 6739 + }, + { + "epoch": 0.55, + "learning_rate": 1.6338548457192526e-05, + "loss": 0.2398, + "step": 6740 + }, + { + "epoch": 0.55, + "learning_rate": 1.633800521512386e-05, + "loss": 0.4331, + "step": 6741 + }, + { + "epoch": 0.55, + "learning_rate": 1.6337461973055194e-05, + "loss": 0.7785, + "step": 6742 + }, + { + "epoch": 0.55, + "learning_rate": 1.633691873098653e-05, + "loss": 0.4206, + "step": 6743 + }, + { + "epoch": 0.55, + "learning_rate": 1.6336375488917863e-05, + "loss": 0.5193, + "step": 6744 + }, + { + "epoch": 0.55, + "learning_rate": 1.6335832246849197e-05, + "loss": 0.4259, + "step": 6745 + }, + { + "epoch": 0.55, + "learning_rate": 1.633528900478053e-05, + "loss": 0.4431, + "step": 6746 + }, + { + "epoch": 0.55, + "learning_rate": 1.6334745762711865e-05, + "loss": 0.421, + "step": 6747 + }, + { + "epoch": 0.55, + "learning_rate": 1.63342025206432e-05, + "loss": 0.2246, + "step": 6748 + }, + { + "epoch": 0.55, + "learning_rate": 1.6333659278574534e-05, + "loss": 0.4409, + "step": 6749 + }, + { + "epoch": 0.55, + "learning_rate": 1.6333116036505868e-05, + "loss": 0.2978, + "step": 6750 + }, + { + "epoch": 0.55, + "eval_accuracy": 0.8117167600611309, + "eval_loss": 0.4870717227458954, + "eval_runtime": 22.2669, + "eval_samples_per_second": 440.789, + "eval_steps_per_second": 3.458, + "step": 6750 + }, + { + "epoch": 0.55, + "learning_rate": 1.6332572794437202e-05, + "loss": 0.8169, + "step": 6751 + }, + { + "epoch": 0.55, + "learning_rate": 1.6332029552368537e-05, + "loss": 0.4573, + "step": 6752 + }, + { + "epoch": 0.55, + "learning_rate": 1.633148631029987e-05, + "loss": 0.6071, + "step": 6753 + }, + { + "epoch": 0.55, + "learning_rate": 1.6330943068231205e-05, + "loss": 0.5774, + "step": 6754 + }, + { + "epoch": 0.55, + "learning_rate": 1.633039982616254e-05, + "loss": 0.4999, + "step": 6755 + }, + { + "epoch": 0.55, + "learning_rate": 1.6329856584093873e-05, + "loss": 0.3722, + "step": 6756 + }, + { + "epoch": 0.55, + "learning_rate": 1.6329313342025208e-05, + "loss": 0.5796, + "step": 6757 + }, + { + "epoch": 0.55, + "learning_rate": 1.6328770099956542e-05, + "loss": 0.3815, + "step": 6758 + }, + { + "epoch": 0.55, + "learning_rate": 1.6328226857887876e-05, + "loss": 0.5363, + "step": 6759 + }, + { + "epoch": 0.55, + "learning_rate": 1.632768361581921e-05, + "loss": 0.6462, + "step": 6760 + }, + { + "epoch": 0.55, + "learning_rate": 1.6327140373750545e-05, + "loss": 0.5159, + "step": 6761 + }, + { + "epoch": 0.55, + "learning_rate": 1.632659713168188e-05, + "loss": 0.6085, + "step": 6762 + }, + { + "epoch": 0.55, + "learning_rate": 1.6326053889613213e-05, + "loss": 0.4099, + "step": 6763 + }, + { + "epoch": 0.55, + "learning_rate": 1.6325510647544547e-05, + "loss": 0.448, + "step": 6764 + }, + { + "epoch": 0.55, + "learning_rate": 1.632496740547588e-05, + "loss": 0.4847, + "step": 6765 + }, + { + "epoch": 0.55, + "learning_rate": 1.6324424163407216e-05, + "loss": 0.251, + "step": 6766 + }, + { + "epoch": 0.55, + "learning_rate": 1.632388092133855e-05, + "loss": 0.4681, + "step": 6767 + }, + { + "epoch": 0.55, + "learning_rate": 1.6323337679269884e-05, + "loss": 0.555, + "step": 6768 + }, + { + "epoch": 0.55, + "learning_rate": 1.632279443720122e-05, + "loss": 0.4555, + "step": 6769 + }, + { + "epoch": 0.55, + "learning_rate": 1.6322251195132553e-05, + "loss": 0.3175, + "step": 6770 + }, + { + "epoch": 0.55, + "learning_rate": 1.6321707953063887e-05, + "loss": 0.6677, + "step": 6771 + }, + { + "epoch": 0.55, + "learning_rate": 1.632116471099522e-05, + "loss": 0.6981, + "step": 6772 + }, + { + "epoch": 0.55, + "learning_rate": 1.6320621468926555e-05, + "loss": 0.408, + "step": 6773 + }, + { + "epoch": 0.55, + "learning_rate": 1.632007822685789e-05, + "loss": 0.4467, + "step": 6774 + }, + { + "epoch": 0.55, + "learning_rate": 1.6319534984789224e-05, + "loss": 0.688, + "step": 6775 + }, + { + "epoch": 0.55, + "learning_rate": 1.6318991742720558e-05, + "loss": 0.4619, + "step": 6776 + }, + { + "epoch": 0.55, + "learning_rate": 1.6318448500651892e-05, + "loss": 0.4082, + "step": 6777 + }, + { + "epoch": 0.55, + "learning_rate": 1.6317905258583227e-05, + "loss": 0.4988, + "step": 6778 + }, + { + "epoch": 0.55, + "learning_rate": 1.631736201651456e-05, + "loss": 0.605, + "step": 6779 + }, + { + "epoch": 0.55, + "learning_rate": 1.6316818774445895e-05, + "loss": 0.5177, + "step": 6780 + }, + { + "epoch": 0.55, + "learning_rate": 1.631627553237723e-05, + "loss": 0.4672, + "step": 6781 + }, + { + "epoch": 0.55, + "learning_rate": 1.6315732290308563e-05, + "loss": 0.4672, + "step": 6782 + }, + { + "epoch": 0.55, + "learning_rate": 1.6315189048239898e-05, + "loss": 0.4524, + "step": 6783 + }, + { + "epoch": 0.55, + "learning_rate": 1.6314645806171232e-05, + "loss": 0.6708, + "step": 6784 + }, + { + "epoch": 0.55, + "learning_rate": 1.6314102564102566e-05, + "loss": 0.3079, + "step": 6785 + }, + { + "epoch": 0.55, + "learning_rate": 1.63135593220339e-05, + "loss": 0.5815, + "step": 6786 + }, + { + "epoch": 0.55, + "learning_rate": 1.6313016079965235e-05, + "loss": 0.4467, + "step": 6787 + }, + { + "epoch": 0.55, + "learning_rate": 1.631247283789657e-05, + "loss": 0.7695, + "step": 6788 + }, + { + "epoch": 0.55, + "learning_rate": 1.6311929595827903e-05, + "loss": 0.4001, + "step": 6789 + }, + { + "epoch": 0.55, + "learning_rate": 1.6311386353759234e-05, + "loss": 0.283, + "step": 6790 + }, + { + "epoch": 0.55, + "learning_rate": 1.631084311169057e-05, + "loss": 0.4987, + "step": 6791 + }, + { + "epoch": 0.55, + "learning_rate": 1.6310299869621902e-05, + "loss": 0.3856, + "step": 6792 + }, + { + "epoch": 0.55, + "learning_rate": 1.630975662755324e-05, + "loss": 0.7238, + "step": 6793 + }, + { + "epoch": 0.55, + "learning_rate": 1.630921338548457e-05, + "loss": 0.7471, + "step": 6794 + }, + { + "epoch": 0.55, + "learning_rate": 1.630867014341591e-05, + "loss": 0.4395, + "step": 6795 + }, + { + "epoch": 0.55, + "learning_rate": 1.630812690134724e-05, + "loss": 0.6607, + "step": 6796 + }, + { + "epoch": 0.55, + "learning_rate": 1.6307583659278577e-05, + "loss": 0.5175, + "step": 6797 + }, + { + "epoch": 0.55, + "learning_rate": 1.630704041720991e-05, + "loss": 0.4688, + "step": 6798 + }, + { + "epoch": 0.55, + "learning_rate": 1.6306497175141245e-05, + "loss": 0.5199, + "step": 6799 + }, + { + "epoch": 0.55, + "learning_rate": 1.630595393307258e-05, + "loss": 0.3412, + "step": 6800 + }, + { + "epoch": 0.55, + "learning_rate": 1.6305410691003914e-05, + "loss": 0.3898, + "step": 6801 + }, + { + "epoch": 0.55, + "learning_rate": 1.6304867448935248e-05, + "loss": 0.2545, + "step": 6802 + }, + { + "epoch": 0.55, + "learning_rate": 1.6304324206866582e-05, + "loss": 0.4162, + "step": 6803 + }, + { + "epoch": 0.55, + "learning_rate": 1.6303780964797917e-05, + "loss": 0.4869, + "step": 6804 + }, + { + "epoch": 0.55, + "learning_rate": 1.630323772272925e-05, + "loss": 0.468, + "step": 6805 + }, + { + "epoch": 0.55, + "learning_rate": 1.6302694480660585e-05, + "loss": 0.4725, + "step": 6806 + }, + { + "epoch": 0.55, + "learning_rate": 1.630215123859192e-05, + "loss": 0.2318, + "step": 6807 + }, + { + "epoch": 0.55, + "learning_rate": 1.6301607996523253e-05, + "loss": 0.6076, + "step": 6808 + }, + { + "epoch": 0.55, + "learning_rate": 1.6301064754454584e-05, + "loss": 0.4663, + "step": 6809 + }, + { + "epoch": 0.55, + "learning_rate": 1.6300521512385922e-05, + "loss": 0.4002, + "step": 6810 + }, + { + "epoch": 0.56, + "learning_rate": 1.6299978270317253e-05, + "loss": 0.392, + "step": 6811 + }, + { + "epoch": 0.56, + "learning_rate": 1.629943502824859e-05, + "loss": 0.443, + "step": 6812 + }, + { + "epoch": 0.56, + "learning_rate": 1.629889178617992e-05, + "loss": 0.3174, + "step": 6813 + }, + { + "epoch": 0.56, + "learning_rate": 1.629834854411126e-05, + "loss": 0.5225, + "step": 6814 + }, + { + "epoch": 0.56, + "learning_rate": 1.629780530204259e-05, + "loss": 0.6749, + "step": 6815 + }, + { + "epoch": 0.56, + "learning_rate": 1.6297262059973927e-05, + "loss": 0.4871, + "step": 6816 + }, + { + "epoch": 0.56, + "learning_rate": 1.6296718817905258e-05, + "loss": 0.4581, + "step": 6817 + }, + { + "epoch": 0.56, + "learning_rate": 1.6296175575836596e-05, + "loss": 0.8332, + "step": 6818 + }, + { + "epoch": 0.56, + "learning_rate": 1.6295632333767927e-05, + "loss": 0.4526, + "step": 6819 + }, + { + "epoch": 0.56, + "learning_rate": 1.6295089091699264e-05, + "loss": 0.444, + "step": 6820 + }, + { + "epoch": 0.56, + "learning_rate": 1.6294545849630595e-05, + "loss": 0.4784, + "step": 6821 + }, + { + "epoch": 0.56, + "learning_rate": 1.6294002607561933e-05, + "loss": 0.5013, + "step": 6822 + }, + { + "epoch": 0.56, + "learning_rate": 1.6293459365493264e-05, + "loss": 0.5146, + "step": 6823 + }, + { + "epoch": 0.56, + "learning_rate": 1.62929161234246e-05, + "loss": 0.2205, + "step": 6824 + }, + { + "epoch": 0.56, + "learning_rate": 1.6292372881355932e-05, + "loss": 0.3463, + "step": 6825 + }, + { + "epoch": 0.56, + "learning_rate": 1.629182963928727e-05, + "loss": 0.306, + "step": 6826 + }, + { + "epoch": 0.56, + "learning_rate": 1.62912863972186e-05, + "loss": 0.3921, + "step": 6827 + }, + { + "epoch": 0.56, + "learning_rate": 1.6290743155149935e-05, + "loss": 0.5351, + "step": 6828 + }, + { + "epoch": 0.56, + "learning_rate": 1.629019991308127e-05, + "loss": 0.3758, + "step": 6829 + }, + { + "epoch": 0.56, + "learning_rate": 1.6289656671012603e-05, + "loss": 0.4848, + "step": 6830 + }, + { + "epoch": 0.56, + "learning_rate": 1.6289113428943937e-05, + "loss": 0.3706, + "step": 6831 + }, + { + "epoch": 0.56, + "learning_rate": 1.628857018687527e-05, + "loss": 0.6684, + "step": 6832 + }, + { + "epoch": 0.56, + "learning_rate": 1.6288026944806606e-05, + "loss": 0.5567, + "step": 6833 + }, + { + "epoch": 0.56, + "learning_rate": 1.628748370273794e-05, + "loss": 0.5056, + "step": 6834 + }, + { + "epoch": 0.56, + "learning_rate": 1.6286940460669278e-05, + "loss": 0.3624, + "step": 6835 + }, + { + "epoch": 0.56, + "learning_rate": 1.628639721860061e-05, + "loss": 0.5283, + "step": 6836 + }, + { + "epoch": 0.56, + "learning_rate": 1.6285853976531946e-05, + "loss": 0.6187, + "step": 6837 + }, + { + "epoch": 0.56, + "learning_rate": 1.6285310734463277e-05, + "loss": 0.6722, + "step": 6838 + }, + { + "epoch": 0.56, + "learning_rate": 1.6284767492394615e-05, + "loss": 0.5703, + "step": 6839 + }, + { + "epoch": 0.56, + "learning_rate": 1.6284224250325945e-05, + "loss": 0.3716, + "step": 6840 + }, + { + "epoch": 0.56, + "learning_rate": 1.6283681008257283e-05, + "loss": 0.6127, + "step": 6841 + }, + { + "epoch": 0.56, + "learning_rate": 1.6283137766188614e-05, + "loss": 0.5202, + "step": 6842 + }, + { + "epoch": 0.56, + "learning_rate": 1.628259452411995e-05, + "loss": 0.5996, + "step": 6843 + }, + { + "epoch": 0.56, + "learning_rate": 1.6282051282051282e-05, + "loss": 0.5266, + "step": 6844 + }, + { + "epoch": 0.56, + "learning_rate": 1.628150803998262e-05, + "loss": 0.4128, + "step": 6845 + }, + { + "epoch": 0.56, + "learning_rate": 1.628096479791395e-05, + "loss": 0.4225, + "step": 6846 + }, + { + "epoch": 0.56, + "learning_rate": 1.6280421555845285e-05, + "loss": 0.5885, + "step": 6847 + }, + { + "epoch": 0.56, + "learning_rate": 1.627987831377662e-05, + "loss": 0.4121, + "step": 6848 + }, + { + "epoch": 0.56, + "learning_rate": 1.6279335071707954e-05, + "loss": 0.5767, + "step": 6849 + }, + { + "epoch": 0.56, + "learning_rate": 1.6278791829639288e-05, + "loss": 0.5392, + "step": 6850 + }, + { + "epoch": 0.56, + "learning_rate": 1.6278248587570622e-05, + "loss": 0.4333, + "step": 6851 + }, + { + "epoch": 0.56, + "learning_rate": 1.6277705345501956e-05, + "loss": 0.2489, + "step": 6852 + }, + { + "epoch": 0.56, + "learning_rate": 1.627716210343329e-05, + "loss": 0.4474, + "step": 6853 + }, + { + "epoch": 0.56, + "learning_rate": 1.6276618861364625e-05, + "loss": 0.4223, + "step": 6854 + }, + { + "epoch": 0.56, + "learning_rate": 1.627607561929596e-05, + "loss": 0.4476, + "step": 6855 + }, + { + "epoch": 0.56, + "learning_rate": 1.6275532377227293e-05, + "loss": 0.4318, + "step": 6856 + }, + { + "epoch": 0.56, + "learning_rate": 1.6274989135158627e-05, + "loss": 0.3486, + "step": 6857 + }, + { + "epoch": 0.56, + "learning_rate": 1.627444589308996e-05, + "loss": 0.2096, + "step": 6858 + }, + { + "epoch": 0.56, + "learning_rate": 1.6273902651021296e-05, + "loss": 0.5394, + "step": 6859 + }, + { + "epoch": 0.56, + "learning_rate": 1.627335940895263e-05, + "loss": 0.6798, + "step": 6860 + }, + { + "epoch": 0.56, + "learning_rate": 1.6272816166883964e-05, + "loss": 0.5458, + "step": 6861 + }, + { + "epoch": 0.56, + "learning_rate": 1.62722729248153e-05, + "loss": 0.492, + "step": 6862 + }, + { + "epoch": 0.56, + "learning_rate": 1.6271729682746633e-05, + "loss": 0.5874, + "step": 6863 + }, + { + "epoch": 0.56, + "learning_rate": 1.6271186440677967e-05, + "loss": 0.2847, + "step": 6864 + }, + { + "epoch": 0.56, + "learning_rate": 1.62706431986093e-05, + "loss": 0.4106, + "step": 6865 + }, + { + "epoch": 0.56, + "learning_rate": 1.6270099956540635e-05, + "loss": 0.406, + "step": 6866 + }, + { + "epoch": 0.56, + "learning_rate": 1.626955671447197e-05, + "loss": 0.5434, + "step": 6867 + }, + { + "epoch": 0.56, + "learning_rate": 1.6269013472403304e-05, + "loss": 0.5974, + "step": 6868 + }, + { + "epoch": 0.56, + "learning_rate": 1.6268470230334638e-05, + "loss": 0.2843, + "step": 6869 + }, + { + "epoch": 0.56, + "learning_rate": 1.6267926988265972e-05, + "loss": 0.2749, + "step": 6870 + }, + { + "epoch": 0.56, + "learning_rate": 1.6267383746197307e-05, + "loss": 0.6029, + "step": 6871 + }, + { + "epoch": 0.56, + "learning_rate": 1.626684050412864e-05, + "loss": 0.6619, + "step": 6872 + }, + { + "epoch": 0.56, + "learning_rate": 1.6266297262059975e-05, + "loss": 0.3278, + "step": 6873 + }, + { + "epoch": 0.56, + "learning_rate": 1.626575401999131e-05, + "loss": 0.5988, + "step": 6874 + }, + { + "epoch": 0.56, + "learning_rate": 1.6265210777922644e-05, + "loss": 0.8694, + "step": 6875 + }, + { + "epoch": 0.56, + "learning_rate": 1.6264667535853978e-05, + "loss": 0.3393, + "step": 6876 + }, + { + "epoch": 0.56, + "learning_rate": 1.6264124293785312e-05, + "loss": 0.2933, + "step": 6877 + }, + { + "epoch": 0.56, + "learning_rate": 1.6263581051716646e-05, + "loss": 0.586, + "step": 6878 + }, + { + "epoch": 0.56, + "learning_rate": 1.626303780964798e-05, + "loss": 0.4364, + "step": 6879 + }, + { + "epoch": 0.56, + "learning_rate": 1.6262494567579315e-05, + "loss": 0.3457, + "step": 6880 + }, + { + "epoch": 0.56, + "learning_rate": 1.626195132551065e-05, + "loss": 0.5838, + "step": 6881 + }, + { + "epoch": 0.56, + "learning_rate": 1.6261408083441983e-05, + "loss": 0.4761, + "step": 6882 + }, + { + "epoch": 0.56, + "learning_rate": 1.6260864841373317e-05, + "loss": 0.4067, + "step": 6883 + }, + { + "epoch": 0.56, + "learning_rate": 1.626032159930465e-05, + "loss": 0.6227, + "step": 6884 + }, + { + "epoch": 0.56, + "learning_rate": 1.6259778357235986e-05, + "loss": 0.3674, + "step": 6885 + }, + { + "epoch": 0.56, + "learning_rate": 1.625923511516732e-05, + "loss": 0.6069, + "step": 6886 + }, + { + "epoch": 0.56, + "learning_rate": 1.6258691873098654e-05, + "loss": 0.464, + "step": 6887 + }, + { + "epoch": 0.56, + "learning_rate": 1.625814863102999e-05, + "loss": 0.4465, + "step": 6888 + }, + { + "epoch": 0.56, + "learning_rate": 1.6257605388961323e-05, + "loss": 0.3916, + "step": 6889 + }, + { + "epoch": 0.56, + "learning_rate": 1.6257062146892657e-05, + "loss": 0.6582, + "step": 6890 + }, + { + "epoch": 0.56, + "learning_rate": 1.625651890482399e-05, + "loss": 0.2384, + "step": 6891 + }, + { + "epoch": 0.56, + "learning_rate": 1.6255975662755325e-05, + "loss": 0.8641, + "step": 6892 + }, + { + "epoch": 0.56, + "learning_rate": 1.625543242068666e-05, + "loss": 0.4761, + "step": 6893 + }, + { + "epoch": 0.56, + "learning_rate": 1.6254889178617994e-05, + "loss": 0.3877, + "step": 6894 + }, + { + "epoch": 0.56, + "learning_rate": 1.6254345936549328e-05, + "loss": 0.2453, + "step": 6895 + }, + { + "epoch": 0.56, + "learning_rate": 1.6253802694480662e-05, + "loss": 0.5912, + "step": 6896 + }, + { + "epoch": 0.56, + "learning_rate": 1.6253259452411997e-05, + "loss": 0.5208, + "step": 6897 + }, + { + "epoch": 0.56, + "learning_rate": 1.625271621034333e-05, + "loss": 0.5273, + "step": 6898 + }, + { + "epoch": 0.56, + "learning_rate": 1.6252172968274665e-05, + "loss": 0.3781, + "step": 6899 + }, + { + "epoch": 0.56, + "learning_rate": 1.6251629726206e-05, + "loss": 0.4074, + "step": 6900 + }, + { + "epoch": 0.56, + "learning_rate": 1.6251086484137334e-05, + "loss": 0.4104, + "step": 6901 + }, + { + "epoch": 0.56, + "learning_rate": 1.6250543242068668e-05, + "loss": 0.5089, + "step": 6902 + }, + { + "epoch": 0.56, + "learning_rate": 1.6250000000000002e-05, + "loss": 0.4155, + "step": 6903 + }, + { + "epoch": 0.56, + "learning_rate": 1.6249456757931333e-05, + "loss": 0.6118, + "step": 6904 + }, + { + "epoch": 0.56, + "learning_rate": 1.624891351586267e-05, + "loss": 0.4243, + "step": 6905 + }, + { + "epoch": 0.56, + "learning_rate": 1.6248370273794005e-05, + "loss": 0.4469, + "step": 6906 + }, + { + "epoch": 0.56, + "learning_rate": 1.624782703172534e-05, + "loss": 0.4378, + "step": 6907 + }, + { + "epoch": 0.56, + "learning_rate": 1.6247283789656673e-05, + "loss": 0.339, + "step": 6908 + }, + { + "epoch": 0.56, + "learning_rate": 1.6246740547588007e-05, + "loss": 0.5775, + "step": 6909 + }, + { + "epoch": 0.56, + "learning_rate": 1.624619730551934e-05, + "loss": 0.5334, + "step": 6910 + }, + { + "epoch": 0.56, + "learning_rate": 1.6245654063450676e-05, + "loss": 0.2476, + "step": 6911 + }, + { + "epoch": 0.56, + "learning_rate": 1.624511082138201e-05, + "loss": 0.5933, + "step": 6912 + }, + { + "epoch": 0.56, + "learning_rate": 1.6244567579313344e-05, + "loss": 0.2838, + "step": 6913 + }, + { + "epoch": 0.56, + "learning_rate": 1.624402433724468e-05, + "loss": 0.649, + "step": 6914 + }, + { + "epoch": 0.56, + "learning_rate": 1.6243481095176013e-05, + "loss": 0.61, + "step": 6915 + }, + { + "epoch": 0.56, + "learning_rate": 1.6242937853107347e-05, + "loss": 0.8385, + "step": 6916 + }, + { + "epoch": 0.56, + "learning_rate": 1.624239461103868e-05, + "loss": 0.483, + "step": 6917 + }, + { + "epoch": 0.56, + "learning_rate": 1.6241851368970015e-05, + "loss": 0.5003, + "step": 6918 + }, + { + "epoch": 0.56, + "learning_rate": 1.624130812690135e-05, + "loss": 0.3325, + "step": 6919 + }, + { + "epoch": 0.56, + "learning_rate": 1.6240764884832684e-05, + "loss": 0.4112, + "step": 6920 + }, + { + "epoch": 0.56, + "learning_rate": 1.6240221642764018e-05, + "loss": 0.904, + "step": 6921 + }, + { + "epoch": 0.56, + "learning_rate": 1.6239678400695352e-05, + "loss": 0.4635, + "step": 6922 + }, + { + "epoch": 0.56, + "learning_rate": 1.6239135158626683e-05, + "loss": 0.5378, + "step": 6923 + }, + { + "epoch": 0.56, + "learning_rate": 1.623859191655802e-05, + "loss": 0.3676, + "step": 6924 + }, + { + "epoch": 0.56, + "learning_rate": 1.623804867448935e-05, + "loss": 0.3045, + "step": 6925 + }, + { + "epoch": 0.56, + "learning_rate": 1.623750543242069e-05, + "loss": 0.6289, + "step": 6926 + }, + { + "epoch": 0.56, + "learning_rate": 1.623696219035202e-05, + "loss": 0.5774, + "step": 6927 + }, + { + "epoch": 0.56, + "learning_rate": 1.6236418948283358e-05, + "loss": 0.3681, + "step": 6928 + }, + { + "epoch": 0.56, + "learning_rate": 1.623587570621469e-05, + "loss": 0.4285, + "step": 6929 + }, + { + "epoch": 0.56, + "learning_rate": 1.6235332464146026e-05, + "loss": 0.367, + "step": 6930 + }, + { + "epoch": 0.56, + "learning_rate": 1.6234789222077357e-05, + "loss": 0.6526, + "step": 6931 + }, + { + "epoch": 0.56, + "learning_rate": 1.6234245980008695e-05, + "loss": 0.5915, + "step": 6932 + }, + { + "epoch": 0.56, + "learning_rate": 1.6233702737940025e-05, + "loss": 0.2293, + "step": 6933 + }, + { + "epoch": 0.57, + "learning_rate": 1.6233159495871363e-05, + "loss": 0.5922, + "step": 6934 + }, + { + "epoch": 0.57, + "learning_rate": 1.6232616253802694e-05, + "loss": 0.5069, + "step": 6935 + }, + { + "epoch": 0.57, + "learning_rate": 1.623207301173403e-05, + "loss": 0.5417, + "step": 6936 + }, + { + "epoch": 0.57, + "learning_rate": 1.6231529769665362e-05, + "loss": 0.6229, + "step": 6937 + }, + { + "epoch": 0.57, + "learning_rate": 1.62309865275967e-05, + "loss": 0.8178, + "step": 6938 + }, + { + "epoch": 0.57, + "learning_rate": 1.623044328552803e-05, + "loss": 0.5938, + "step": 6939 + }, + { + "epoch": 0.57, + "learning_rate": 1.622990004345937e-05, + "loss": 0.5214, + "step": 6940 + }, + { + "epoch": 0.57, + "learning_rate": 1.62293568013907e-05, + "loss": 0.3986, + "step": 6941 + }, + { + "epoch": 0.57, + "learning_rate": 1.6228813559322034e-05, + "loss": 0.4499, + "step": 6942 + }, + { + "epoch": 0.57, + "learning_rate": 1.622827031725337e-05, + "loss": 0.6869, + "step": 6943 + }, + { + "epoch": 0.57, + "learning_rate": 1.6227727075184702e-05, + "loss": 0.5386, + "step": 6944 + }, + { + "epoch": 0.57, + "learning_rate": 1.622718383311604e-05, + "loss": 0.4391, + "step": 6945 + }, + { + "epoch": 0.57, + "learning_rate": 1.622664059104737e-05, + "loss": 0.5187, + "step": 6946 + }, + { + "epoch": 0.57, + "learning_rate": 1.6226097348978708e-05, + "loss": 0.4653, + "step": 6947 + }, + { + "epoch": 0.57, + "learning_rate": 1.622555410691004e-05, + "loss": 0.3521, + "step": 6948 + }, + { + "epoch": 0.57, + "learning_rate": 1.6225010864841377e-05, + "loss": 0.598, + "step": 6949 + }, + { + "epoch": 0.57, + "learning_rate": 1.6224467622772707e-05, + "loss": 0.4366, + "step": 6950 + }, + { + "epoch": 0.57, + "learning_rate": 1.6223924380704045e-05, + "loss": 0.5103, + "step": 6951 + }, + { + "epoch": 0.57, + "learning_rate": 1.6223381138635376e-05, + "loss": 0.6081, + "step": 6952 + }, + { + "epoch": 0.57, + "learning_rate": 1.6222837896566713e-05, + "loss": 0.3457, + "step": 6953 + }, + { + "epoch": 0.57, + "learning_rate": 1.6222294654498044e-05, + "loss": 0.4714, + "step": 6954 + }, + { + "epoch": 0.57, + "learning_rate": 1.6221751412429382e-05, + "loss": 0.407, + "step": 6955 + }, + { + "epoch": 0.57, + "learning_rate": 1.6221208170360713e-05, + "loss": 0.2712, + "step": 6956 + }, + { + "epoch": 0.57, + "learning_rate": 1.622066492829205e-05, + "loss": 0.4918, + "step": 6957 + }, + { + "epoch": 0.57, + "learning_rate": 1.622012168622338e-05, + "loss": 0.5101, + "step": 6958 + }, + { + "epoch": 0.57, + "learning_rate": 1.621957844415472e-05, + "loss": 0.5175, + "step": 6959 + }, + { + "epoch": 0.57, + "learning_rate": 1.621903520208605e-05, + "loss": 0.4311, + "step": 6960 + }, + { + "epoch": 0.57, + "learning_rate": 1.6218491960017384e-05, + "loss": 0.5184, + "step": 6961 + }, + { + "epoch": 0.57, + "learning_rate": 1.6217948717948718e-05, + "loss": 0.3225, + "step": 6962 + }, + { + "epoch": 0.57, + "learning_rate": 1.6217405475880052e-05, + "loss": 0.3588, + "step": 6963 + }, + { + "epoch": 0.57, + "learning_rate": 1.6216862233811387e-05, + "loss": 0.6182, + "step": 6964 + }, + { + "epoch": 0.57, + "learning_rate": 1.621631899174272e-05, + "loss": 0.5388, + "step": 6965 + }, + { + "epoch": 0.57, + "learning_rate": 1.6215775749674055e-05, + "loss": 0.3655, + "step": 6966 + }, + { + "epoch": 0.57, + "learning_rate": 1.621523250760539e-05, + "loss": 0.4608, + "step": 6967 + }, + { + "epoch": 0.57, + "learning_rate": 1.6214689265536724e-05, + "loss": 0.336, + "step": 6968 + }, + { + "epoch": 0.57, + "learning_rate": 1.6214146023468058e-05, + "loss": 0.1473, + "step": 6969 + }, + { + "epoch": 0.57, + "learning_rate": 1.6213602781399392e-05, + "loss": 0.4771, + "step": 6970 + }, + { + "epoch": 0.57, + "learning_rate": 1.6213059539330726e-05, + "loss": 0.732, + "step": 6971 + }, + { + "epoch": 0.57, + "learning_rate": 1.621251629726206e-05, + "loss": 0.7959, + "step": 6972 + }, + { + "epoch": 0.57, + "learning_rate": 1.6211973055193395e-05, + "loss": 0.4187, + "step": 6973 + }, + { + "epoch": 0.57, + "learning_rate": 1.621142981312473e-05, + "loss": 0.2815, + "step": 6974 + }, + { + "epoch": 0.57, + "learning_rate": 1.6210886571056063e-05, + "loss": 0.5821, + "step": 6975 + }, + { + "epoch": 0.57, + "learning_rate": 1.6210343328987397e-05, + "loss": 0.2866, + "step": 6976 + }, + { + "epoch": 0.57, + "learning_rate": 1.620980008691873e-05, + "loss": 0.4997, + "step": 6977 + }, + { + "epoch": 0.57, + "learning_rate": 1.620925684485007e-05, + "loss": 0.6427, + "step": 6978 + }, + { + "epoch": 0.57, + "learning_rate": 1.62087136027814e-05, + "loss": 0.4722, + "step": 6979 + }, + { + "epoch": 0.57, + "learning_rate": 1.6208170360712734e-05, + "loss": 0.4725, + "step": 6980 + }, + { + "epoch": 0.57, + "learning_rate": 1.620762711864407e-05, + "loss": 0.5889, + "step": 6981 + }, + { + "epoch": 0.57, + "learning_rate": 1.6207083876575403e-05, + "loss": 0.5633, + "step": 6982 + }, + { + "epoch": 0.57, + "learning_rate": 1.6206540634506737e-05, + "loss": 0.3675, + "step": 6983 + }, + { + "epoch": 0.57, + "learning_rate": 1.620599739243807e-05, + "loss": 0.3273, + "step": 6984 + }, + { + "epoch": 0.57, + "learning_rate": 1.6205454150369405e-05, + "loss": 0.4157, + "step": 6985 + }, + { + "epoch": 0.57, + "learning_rate": 1.620491090830074e-05, + "loss": 0.4967, + "step": 6986 + }, + { + "epoch": 0.57, + "learning_rate": 1.6204367666232074e-05, + "loss": 0.3395, + "step": 6987 + }, + { + "epoch": 0.57, + "learning_rate": 1.6203824424163408e-05, + "loss": 0.232, + "step": 6988 + }, + { + "epoch": 0.57, + "learning_rate": 1.6203281182094742e-05, + "loss": 0.5805, + "step": 6989 + }, + { + "epoch": 0.57, + "learning_rate": 1.6202737940026077e-05, + "loss": 0.7193, + "step": 6990 + }, + { + "epoch": 0.57, + "learning_rate": 1.620219469795741e-05, + "loss": 0.4588, + "step": 6991 + }, + { + "epoch": 0.57, + "learning_rate": 1.6201651455888745e-05, + "loss": 0.3535, + "step": 6992 + }, + { + "epoch": 0.57, + "learning_rate": 1.620110821382008e-05, + "loss": 0.4165, + "step": 6993 + }, + { + "epoch": 0.57, + "learning_rate": 1.6200564971751414e-05, + "loss": 0.4675, + "step": 6994 + }, + { + "epoch": 0.57, + "learning_rate": 1.6200021729682748e-05, + "loss": 0.6103, + "step": 6995 + }, + { + "epoch": 0.57, + "learning_rate": 1.6199478487614082e-05, + "loss": 0.478, + "step": 6996 + }, + { + "epoch": 0.57, + "learning_rate": 1.6198935245545416e-05, + "loss": 0.3862, + "step": 6997 + }, + { + "epoch": 0.57, + "learning_rate": 1.619839200347675e-05, + "loss": 0.3531, + "step": 6998 + }, + { + "epoch": 0.57, + "learning_rate": 1.6197848761408085e-05, + "loss": 0.2811, + "step": 6999 + }, + { + "epoch": 0.57, + "learning_rate": 1.619730551933942e-05, + "loss": 0.5928, + "step": 7000 + }, + { + "epoch": 0.57, + "eval_accuracy": 0.8253693326541008, + "eval_loss": 0.4572164714336395, + "eval_runtime": 22.2754, + "eval_samples_per_second": 440.62, + "eval_steps_per_second": 3.457, + "step": 7000 + }, + { + "epoch": 0.57, + "learning_rate": 1.6196762277270753e-05, + "loss": 0.4934, + "step": 7001 + }, + { + "epoch": 0.57, + "learning_rate": 1.6196219035202087e-05, + "loss": 0.6767, + "step": 7002 + }, + { + "epoch": 0.57, + "learning_rate": 1.619567579313342e-05, + "loss": 0.3118, + "step": 7003 + }, + { + "epoch": 0.57, + "learning_rate": 1.6195132551064756e-05, + "loss": 0.4973, + "step": 7004 + }, + { + "epoch": 0.57, + "learning_rate": 1.619458930899609e-05, + "loss": 0.2309, + "step": 7005 + }, + { + "epoch": 0.57, + "learning_rate": 1.6194046066927424e-05, + "loss": 0.3334, + "step": 7006 + }, + { + "epoch": 0.57, + "learning_rate": 1.619350282485876e-05, + "loss": 0.446, + "step": 7007 + }, + { + "epoch": 0.57, + "learning_rate": 1.6192959582790093e-05, + "loss": 0.5664, + "step": 7008 + }, + { + "epoch": 0.57, + "learning_rate": 1.6192416340721427e-05, + "loss": 0.4209, + "step": 7009 + }, + { + "epoch": 0.57, + "learning_rate": 1.619187309865276e-05, + "loss": 0.6195, + "step": 7010 + }, + { + "epoch": 0.57, + "learning_rate": 1.6191329856584095e-05, + "loss": 0.656, + "step": 7011 + }, + { + "epoch": 0.57, + "learning_rate": 1.619078661451543e-05, + "loss": 0.7745, + "step": 7012 + }, + { + "epoch": 0.57, + "learning_rate": 1.6190243372446764e-05, + "loss": 0.701, + "step": 7013 + }, + { + "epoch": 0.57, + "learning_rate": 1.6189700130378098e-05, + "loss": 0.4181, + "step": 7014 + }, + { + "epoch": 0.57, + "learning_rate": 1.6189156888309432e-05, + "loss": 0.3193, + "step": 7015 + }, + { + "epoch": 0.57, + "learning_rate": 1.6188613646240767e-05, + "loss": 0.433, + "step": 7016 + }, + { + "epoch": 0.57, + "learning_rate": 1.61880704041721e-05, + "loss": 0.2458, + "step": 7017 + }, + { + "epoch": 0.57, + "learning_rate": 1.6187527162103435e-05, + "loss": 0.2882, + "step": 7018 + }, + { + "epoch": 0.57, + "learning_rate": 1.618698392003477e-05, + "loss": 0.6695, + "step": 7019 + }, + { + "epoch": 0.57, + "learning_rate": 1.6186440677966104e-05, + "loss": 0.4336, + "step": 7020 + }, + { + "epoch": 0.57, + "learning_rate": 1.6185897435897438e-05, + "loss": 0.5135, + "step": 7021 + }, + { + "epoch": 0.57, + "learning_rate": 1.6185354193828772e-05, + "loss": 0.3042, + "step": 7022 + }, + { + "epoch": 0.57, + "learning_rate": 1.6184810951760106e-05, + "loss": 0.6017, + "step": 7023 + }, + { + "epoch": 0.57, + "learning_rate": 1.618426770969144e-05, + "loss": 0.4018, + "step": 7024 + }, + { + "epoch": 0.57, + "learning_rate": 1.6183724467622775e-05, + "loss": 0.513, + "step": 7025 + }, + { + "epoch": 0.57, + "learning_rate": 1.618318122555411e-05, + "loss": 0.4673, + "step": 7026 + }, + { + "epoch": 0.57, + "learning_rate": 1.6182637983485443e-05, + "loss": 0.2005, + "step": 7027 + }, + { + "epoch": 0.57, + "learning_rate": 1.6182094741416777e-05, + "loss": 0.3061, + "step": 7028 + }, + { + "epoch": 0.57, + "learning_rate": 1.618155149934811e-05, + "loss": 0.67, + "step": 7029 + }, + { + "epoch": 0.57, + "learning_rate": 1.6181008257279446e-05, + "loss": 0.4126, + "step": 7030 + }, + { + "epoch": 0.57, + "learning_rate": 1.618046501521078e-05, + "loss": 0.3232, + "step": 7031 + }, + { + "epoch": 0.57, + "learning_rate": 1.6179921773142114e-05, + "loss": 0.4137, + "step": 7032 + }, + { + "epoch": 0.57, + "learning_rate": 1.617937853107345e-05, + "loss": 0.4178, + "step": 7033 + }, + { + "epoch": 0.57, + "learning_rate": 1.6178835289004783e-05, + "loss": 0.6032, + "step": 7034 + }, + { + "epoch": 0.57, + "learning_rate": 1.6178292046936117e-05, + "loss": 0.4716, + "step": 7035 + }, + { + "epoch": 0.57, + "learning_rate": 1.617774880486745e-05, + "loss": 0.3633, + "step": 7036 + }, + { + "epoch": 0.57, + "learning_rate": 1.6177205562798782e-05, + "loss": 0.5672, + "step": 7037 + }, + { + "epoch": 0.57, + "learning_rate": 1.617666232073012e-05, + "loss": 0.3751, + "step": 7038 + }, + { + "epoch": 0.57, + "learning_rate": 1.617611907866145e-05, + "loss": 0.3267, + "step": 7039 + }, + { + "epoch": 0.57, + "learning_rate": 1.6175575836592788e-05, + "loss": 0.7015, + "step": 7040 + }, + { + "epoch": 0.57, + "learning_rate": 1.617503259452412e-05, + "loss": 0.3405, + "step": 7041 + }, + { + "epoch": 0.57, + "learning_rate": 1.6174489352455457e-05, + "loss": 0.6132, + "step": 7042 + }, + { + "epoch": 0.57, + "learning_rate": 1.6173946110386787e-05, + "loss": 0.2749, + "step": 7043 + }, + { + "epoch": 0.57, + "learning_rate": 1.6173402868318125e-05, + "loss": 0.5129, + "step": 7044 + }, + { + "epoch": 0.57, + "learning_rate": 1.6172859626249456e-05, + "loss": 0.3689, + "step": 7045 + }, + { + "epoch": 0.57, + "learning_rate": 1.6172316384180794e-05, + "loss": 0.4087, + "step": 7046 + }, + { + "epoch": 0.57, + "learning_rate": 1.6171773142112124e-05, + "loss": 0.5025, + "step": 7047 + }, + { + "epoch": 0.57, + "learning_rate": 1.6171229900043462e-05, + "loss": 0.6977, + "step": 7048 + }, + { + "epoch": 0.57, + "learning_rate": 1.6170686657974793e-05, + "loss": 0.4302, + "step": 7049 + }, + { + "epoch": 0.57, + "learning_rate": 1.617014341590613e-05, + "loss": 0.3951, + "step": 7050 + }, + { + "epoch": 0.57, + "learning_rate": 1.6169600173837465e-05, + "loss": 0.373, + "step": 7051 + }, + { + "epoch": 0.57, + "learning_rate": 1.61690569317688e-05, + "loss": 0.4346, + "step": 7052 + }, + { + "epoch": 0.57, + "learning_rate": 1.6168513689700133e-05, + "loss": 0.6044, + "step": 7053 + }, + { + "epoch": 0.57, + "learning_rate": 1.6167970447631467e-05, + "loss": 0.4498, + "step": 7054 + }, + { + "epoch": 0.57, + "learning_rate": 1.61674272055628e-05, + "loss": 0.7239, + "step": 7055 + }, + { + "epoch": 0.57, + "learning_rate": 1.6166883963494132e-05, + "loss": 0.4829, + "step": 7056 + }, + { + "epoch": 0.58, + "learning_rate": 1.616634072142547e-05, + "loss": 0.4347, + "step": 7057 + }, + { + "epoch": 0.58, + "learning_rate": 1.61657974793568e-05, + "loss": 0.3224, + "step": 7058 + }, + { + "epoch": 0.58, + "learning_rate": 1.616525423728814e-05, + "loss": 0.6456, + "step": 7059 + }, + { + "epoch": 0.58, + "learning_rate": 1.616471099521947e-05, + "loss": 0.3314, + "step": 7060 + }, + { + "epoch": 0.58, + "learning_rate": 1.6164167753150807e-05, + "loss": 0.6205, + "step": 7061 + }, + { + "epoch": 0.58, + "learning_rate": 1.6163624511082138e-05, + "loss": 0.4814, + "step": 7062 + }, + { + "epoch": 0.58, + "learning_rate": 1.6163081269013475e-05, + "loss": 0.4098, + "step": 7063 + }, + { + "epoch": 0.58, + "learning_rate": 1.6162538026944806e-05, + "loss": 0.3952, + "step": 7064 + }, + { + "epoch": 0.58, + "learning_rate": 1.6161994784876144e-05, + "loss": 0.5516, + "step": 7065 + }, + { + "epoch": 0.58, + "learning_rate": 1.6161451542807475e-05, + "loss": 0.6641, + "step": 7066 + }, + { + "epoch": 0.58, + "learning_rate": 1.6160908300738812e-05, + "loss": 0.5296, + "step": 7067 + }, + { + "epoch": 0.58, + "learning_rate": 1.6160365058670143e-05, + "loss": 0.6537, + "step": 7068 + }, + { + "epoch": 0.58, + "learning_rate": 1.615982181660148e-05, + "loss": 0.4416, + "step": 7069 + }, + { + "epoch": 0.58, + "learning_rate": 1.615927857453281e-05, + "loss": 0.441, + "step": 7070 + }, + { + "epoch": 0.58, + "learning_rate": 1.615873533246415e-05, + "loss": 0.42, + "step": 7071 + }, + { + "epoch": 0.58, + "learning_rate": 1.615819209039548e-05, + "loss": 0.3553, + "step": 7072 + }, + { + "epoch": 0.58, + "learning_rate": 1.6157648848326818e-05, + "loss": 0.4478, + "step": 7073 + }, + { + "epoch": 0.58, + "learning_rate": 1.615710560625815e-05, + "loss": 0.5246, + "step": 7074 + }, + { + "epoch": 0.58, + "learning_rate": 1.6156562364189483e-05, + "loss": 0.5148, + "step": 7075 + }, + { + "epoch": 0.58, + "learning_rate": 1.6156019122120817e-05, + "loss": 0.5389, + "step": 7076 + }, + { + "epoch": 0.58, + "learning_rate": 1.615547588005215e-05, + "loss": 0.6484, + "step": 7077 + }, + { + "epoch": 0.58, + "learning_rate": 1.6154932637983486e-05, + "loss": 0.3399, + "step": 7078 + }, + { + "epoch": 0.58, + "learning_rate": 1.615438939591482e-05, + "loss": 0.3481, + "step": 7079 + }, + { + "epoch": 0.58, + "learning_rate": 1.6153846153846154e-05, + "loss": 0.4126, + "step": 7080 + }, + { + "epoch": 0.58, + "learning_rate": 1.6153302911777488e-05, + "loss": 0.652, + "step": 7081 + }, + { + "epoch": 0.58, + "learning_rate": 1.6152759669708822e-05, + "loss": 0.3752, + "step": 7082 + }, + { + "epoch": 0.58, + "learning_rate": 1.6152216427640157e-05, + "loss": 0.5095, + "step": 7083 + }, + { + "epoch": 0.58, + "learning_rate": 1.615167318557149e-05, + "loss": 0.5342, + "step": 7084 + }, + { + "epoch": 0.58, + "learning_rate": 1.6151129943502825e-05, + "loss": 0.5883, + "step": 7085 + }, + { + "epoch": 0.58, + "learning_rate": 1.6150586701434163e-05, + "loss": 0.4308, + "step": 7086 + }, + { + "epoch": 0.58, + "learning_rate": 1.6150043459365494e-05, + "loss": 0.3716, + "step": 7087 + }, + { + "epoch": 0.58, + "learning_rate": 1.614950021729683e-05, + "loss": 0.4406, + "step": 7088 + }, + { + "epoch": 0.58, + "learning_rate": 1.6148956975228162e-05, + "loss": 0.2538, + "step": 7089 + }, + { + "epoch": 0.58, + "learning_rate": 1.61484137331595e-05, + "loss": 0.546, + "step": 7090 + }, + { + "epoch": 0.58, + "learning_rate": 1.614787049109083e-05, + "loss": 0.5583, + "step": 7091 + }, + { + "epoch": 0.58, + "learning_rate": 1.6147327249022168e-05, + "loss": 0.213, + "step": 7092 + }, + { + "epoch": 0.58, + "learning_rate": 1.61467840069535e-05, + "loss": 0.7532, + "step": 7093 + }, + { + "epoch": 0.58, + "learning_rate": 1.6146240764884833e-05, + "loss": 0.3587, + "step": 7094 + }, + { + "epoch": 0.58, + "learning_rate": 1.6145697522816167e-05, + "loss": 0.3562, + "step": 7095 + }, + { + "epoch": 0.58, + "learning_rate": 1.61451542807475e-05, + "loss": 0.6102, + "step": 7096 + }, + { + "epoch": 0.58, + "learning_rate": 1.6144611038678836e-05, + "loss": 0.3487, + "step": 7097 + }, + { + "epoch": 0.58, + "learning_rate": 1.614406779661017e-05, + "loss": 0.5347, + "step": 7098 + }, + { + "epoch": 0.58, + "learning_rate": 1.6143524554541504e-05, + "loss": 0.319, + "step": 7099 + }, + { + "epoch": 0.58, + "learning_rate": 1.614298131247284e-05, + "loss": 0.383, + "step": 7100 + }, + { + "epoch": 0.58, + "learning_rate": 1.6142438070404173e-05, + "loss": 0.4053, + "step": 7101 + }, + { + "epoch": 0.58, + "learning_rate": 1.6141894828335507e-05, + "loss": 0.5023, + "step": 7102 + }, + { + "epoch": 0.58, + "learning_rate": 1.614135158626684e-05, + "loss": 0.3003, + "step": 7103 + }, + { + "epoch": 0.58, + "learning_rate": 1.6140808344198176e-05, + "loss": 0.63, + "step": 7104 + }, + { + "epoch": 0.58, + "learning_rate": 1.614026510212951e-05, + "loss": 0.4556, + "step": 7105 + }, + { + "epoch": 0.58, + "learning_rate": 1.6139721860060844e-05, + "loss": 0.4792, + "step": 7106 + }, + { + "epoch": 0.58, + "learning_rate": 1.6139178617992178e-05, + "loss": 0.3877, + "step": 7107 + }, + { + "epoch": 0.58, + "learning_rate": 1.6138635375923512e-05, + "loss": 0.5167, + "step": 7108 + }, + { + "epoch": 0.58, + "learning_rate": 1.6138092133854847e-05, + "loss": 0.3168, + "step": 7109 + }, + { + "epoch": 0.58, + "learning_rate": 1.613754889178618e-05, + "loss": 0.3043, + "step": 7110 + }, + { + "epoch": 0.58, + "learning_rate": 1.6137005649717515e-05, + "loss": 0.6052, + "step": 7111 + }, + { + "epoch": 0.58, + "learning_rate": 1.613646240764885e-05, + "loss": 0.7653, + "step": 7112 + }, + { + "epoch": 0.58, + "learning_rate": 1.6135919165580184e-05, + "loss": 0.2865, + "step": 7113 + }, + { + "epoch": 0.58, + "learning_rate": 1.6135375923511518e-05, + "loss": 0.6087, + "step": 7114 + }, + { + "epoch": 0.58, + "learning_rate": 1.6134832681442852e-05, + "loss": 0.4797, + "step": 7115 + }, + { + "epoch": 0.58, + "learning_rate": 1.6134289439374186e-05, + "loss": 0.4516, + "step": 7116 + }, + { + "epoch": 0.58, + "learning_rate": 1.613374619730552e-05, + "loss": 0.3332, + "step": 7117 + }, + { + "epoch": 0.58, + "learning_rate": 1.6133202955236855e-05, + "loss": 0.5209, + "step": 7118 + }, + { + "epoch": 0.58, + "learning_rate": 1.613265971316819e-05, + "loss": 0.1818, + "step": 7119 + }, + { + "epoch": 0.58, + "learning_rate": 1.6132116471099523e-05, + "loss": 0.5742, + "step": 7120 + }, + { + "epoch": 0.58, + "learning_rate": 1.6131573229030857e-05, + "loss": 0.6092, + "step": 7121 + }, + { + "epoch": 0.58, + "learning_rate": 1.613102998696219e-05, + "loss": 0.482, + "step": 7122 + }, + { + "epoch": 0.58, + "learning_rate": 1.6130486744893526e-05, + "loss": 0.2439, + "step": 7123 + }, + { + "epoch": 0.58, + "learning_rate": 1.612994350282486e-05, + "loss": 0.3852, + "step": 7124 + }, + { + "epoch": 0.58, + "learning_rate": 1.6129400260756194e-05, + "loss": 0.3283, + "step": 7125 + }, + { + "epoch": 0.58, + "learning_rate": 1.612885701868753e-05, + "loss": 0.8272, + "step": 7126 + }, + { + "epoch": 0.58, + "learning_rate": 1.6128313776618863e-05, + "loss": 0.5255, + "step": 7127 + }, + { + "epoch": 0.58, + "learning_rate": 1.6127770534550197e-05, + "loss": 0.2485, + "step": 7128 + }, + { + "epoch": 0.58, + "learning_rate": 1.612722729248153e-05, + "loss": 0.5243, + "step": 7129 + }, + { + "epoch": 0.58, + "learning_rate": 1.6126684050412866e-05, + "loss": 0.3736, + "step": 7130 + }, + { + "epoch": 0.58, + "learning_rate": 1.61261408083442e-05, + "loss": 0.4666, + "step": 7131 + }, + { + "epoch": 0.58, + "learning_rate": 1.6125597566275534e-05, + "loss": 0.5414, + "step": 7132 + }, + { + "epoch": 0.58, + "learning_rate": 1.6125054324206868e-05, + "loss": 0.2979, + "step": 7133 + }, + { + "epoch": 0.58, + "learning_rate": 1.6124511082138202e-05, + "loss": 0.4445, + "step": 7134 + }, + { + "epoch": 0.58, + "learning_rate": 1.6123967840069537e-05, + "loss": 0.2538, + "step": 7135 + }, + { + "epoch": 0.58, + "learning_rate": 1.612342459800087e-05, + "loss": 0.4966, + "step": 7136 + }, + { + "epoch": 0.58, + "learning_rate": 1.6122881355932205e-05, + "loss": 0.8066, + "step": 7137 + }, + { + "epoch": 0.58, + "learning_rate": 1.612233811386354e-05, + "loss": 0.2834, + "step": 7138 + }, + { + "epoch": 0.58, + "learning_rate": 1.6121794871794874e-05, + "loss": 0.4732, + "step": 7139 + }, + { + "epoch": 0.58, + "learning_rate": 1.6121251629726208e-05, + "loss": 0.5615, + "step": 7140 + }, + { + "epoch": 0.58, + "learning_rate": 1.6120708387657542e-05, + "loss": 0.4593, + "step": 7141 + }, + { + "epoch": 0.58, + "learning_rate": 1.6120165145588876e-05, + "loss": 0.5076, + "step": 7142 + }, + { + "epoch": 0.58, + "learning_rate": 1.611962190352021e-05, + "loss": 0.7534, + "step": 7143 + }, + { + "epoch": 0.58, + "learning_rate": 1.6119078661451545e-05, + "loss": 0.534, + "step": 7144 + }, + { + "epoch": 0.58, + "learning_rate": 1.611853541938288e-05, + "loss": 0.333, + "step": 7145 + }, + { + "epoch": 0.58, + "learning_rate": 1.6117992177314213e-05, + "loss": 0.5723, + "step": 7146 + }, + { + "epoch": 0.58, + "learning_rate": 1.6117448935245547e-05, + "loss": 0.3957, + "step": 7147 + }, + { + "epoch": 0.58, + "learning_rate": 1.611690569317688e-05, + "loss": 0.4224, + "step": 7148 + }, + { + "epoch": 0.58, + "learning_rate": 1.6116362451108216e-05, + "loss": 0.378, + "step": 7149 + }, + { + "epoch": 0.58, + "learning_rate": 1.611581920903955e-05, + "loss": 0.5557, + "step": 7150 + }, + { + "epoch": 0.58, + "learning_rate": 1.611527596697088e-05, + "loss": 0.4133, + "step": 7151 + }, + { + "epoch": 0.58, + "learning_rate": 1.611473272490222e-05, + "loss": 0.7663, + "step": 7152 + }, + { + "epoch": 0.58, + "learning_rate": 1.611418948283355e-05, + "loss": 0.384, + "step": 7153 + }, + { + "epoch": 0.58, + "learning_rate": 1.6113646240764887e-05, + "loss": 0.6443, + "step": 7154 + }, + { + "epoch": 0.58, + "learning_rate": 1.6113102998696218e-05, + "loss": 0.4746, + "step": 7155 + }, + { + "epoch": 0.58, + "learning_rate": 1.6112559756627556e-05, + "loss": 0.2911, + "step": 7156 + }, + { + "epoch": 0.58, + "learning_rate": 1.6112016514558886e-05, + "loss": 0.7301, + "step": 7157 + }, + { + "epoch": 0.58, + "learning_rate": 1.6111473272490224e-05, + "loss": 0.525, + "step": 7158 + }, + { + "epoch": 0.58, + "learning_rate": 1.6110930030421558e-05, + "loss": 0.6149, + "step": 7159 + }, + { + "epoch": 0.58, + "learning_rate": 1.6110386788352892e-05, + "loss": 0.4172, + "step": 7160 + }, + { + "epoch": 0.58, + "learning_rate": 1.6109843546284227e-05, + "loss": 0.5575, + "step": 7161 + }, + { + "epoch": 0.58, + "learning_rate": 1.610930030421556e-05, + "loss": 0.5338, + "step": 7162 + }, + { + "epoch": 0.58, + "learning_rate": 1.6108757062146895e-05, + "loss": 0.2416, + "step": 7163 + }, + { + "epoch": 0.58, + "learning_rate": 1.610821382007823e-05, + "loss": 0.3299, + "step": 7164 + }, + { + "epoch": 0.58, + "learning_rate": 1.6107670578009564e-05, + "loss": 0.3378, + "step": 7165 + }, + { + "epoch": 0.58, + "learning_rate": 1.6107127335940898e-05, + "loss": 0.4896, + "step": 7166 + }, + { + "epoch": 0.58, + "learning_rate": 1.6106584093872232e-05, + "loss": 0.4007, + "step": 7167 + }, + { + "epoch": 0.58, + "learning_rate": 1.6106040851803566e-05, + "loss": 0.3451, + "step": 7168 + }, + { + "epoch": 0.58, + "learning_rate": 1.61054976097349e-05, + "loss": 0.5645, + "step": 7169 + }, + { + "epoch": 0.58, + "learning_rate": 1.610495436766623e-05, + "loss": 0.476, + "step": 7170 + }, + { + "epoch": 0.58, + "learning_rate": 1.610441112559757e-05, + "loss": 0.3596, + "step": 7171 + }, + { + "epoch": 0.58, + "learning_rate": 1.61038678835289e-05, + "loss": 0.6932, + "step": 7172 + }, + { + "epoch": 0.58, + "learning_rate": 1.6103324641460237e-05, + "loss": 0.6736, + "step": 7173 + }, + { + "epoch": 0.58, + "learning_rate": 1.6102781399391568e-05, + "loss": 0.5001, + "step": 7174 + }, + { + "epoch": 0.58, + "learning_rate": 1.6102238157322906e-05, + "loss": 0.4511, + "step": 7175 + }, + { + "epoch": 0.58, + "learning_rate": 1.6101694915254237e-05, + "loss": 0.2578, + "step": 7176 + }, + { + "epoch": 0.58, + "learning_rate": 1.6101151673185574e-05, + "loss": 0.8787, + "step": 7177 + }, + { + "epoch": 0.58, + "learning_rate": 1.6100608431116905e-05, + "loss": 0.4252, + "step": 7178 + }, + { + "epoch": 0.58, + "learning_rate": 1.6100065189048243e-05, + "loss": 0.6714, + "step": 7179 + }, + { + "epoch": 0.59, + "learning_rate": 1.6099521946979574e-05, + "loss": 0.2102, + "step": 7180 + }, + { + "epoch": 0.59, + "learning_rate": 1.609897870491091e-05, + "loss": 0.3523, + "step": 7181 + }, + { + "epoch": 0.59, + "learning_rate": 1.6098435462842242e-05, + "loss": 0.5845, + "step": 7182 + }, + { + "epoch": 0.59, + "learning_rate": 1.609789222077358e-05, + "loss": 0.366, + "step": 7183 + }, + { + "epoch": 0.59, + "learning_rate": 1.609734897870491e-05, + "loss": 0.4935, + "step": 7184 + }, + { + "epoch": 0.59, + "learning_rate": 1.6096805736636248e-05, + "loss": 0.4688, + "step": 7185 + }, + { + "epoch": 0.59, + "learning_rate": 1.609626249456758e-05, + "loss": 0.6215, + "step": 7186 + }, + { + "epoch": 0.59, + "learning_rate": 1.6095719252498917e-05, + "loss": 0.4877, + "step": 7187 + }, + { + "epoch": 0.59, + "learning_rate": 1.6095176010430248e-05, + "loss": 0.5444, + "step": 7188 + }, + { + "epoch": 0.59, + "learning_rate": 1.6094632768361582e-05, + "loss": 0.3468, + "step": 7189 + }, + { + "epoch": 0.59, + "learning_rate": 1.6094089526292916e-05, + "loss": 0.459, + "step": 7190 + }, + { + "epoch": 0.59, + "learning_rate": 1.609354628422425e-05, + "loss": 0.4098, + "step": 7191 + }, + { + "epoch": 0.59, + "learning_rate": 1.6093003042155584e-05, + "loss": 0.4455, + "step": 7192 + }, + { + "epoch": 0.59, + "learning_rate": 1.609245980008692e-05, + "loss": 0.8238, + "step": 7193 + }, + { + "epoch": 0.59, + "learning_rate": 1.6091916558018256e-05, + "loss": 0.2064, + "step": 7194 + }, + { + "epoch": 0.59, + "learning_rate": 1.6091373315949587e-05, + "loss": 0.4508, + "step": 7195 + }, + { + "epoch": 0.59, + "learning_rate": 1.6090830073880925e-05, + "loss": 0.5247, + "step": 7196 + }, + { + "epoch": 0.59, + "learning_rate": 1.6090286831812256e-05, + "loss": 0.4564, + "step": 7197 + }, + { + "epoch": 0.59, + "learning_rate": 1.6089743589743593e-05, + "loss": 0.2942, + "step": 7198 + }, + { + "epoch": 0.59, + "learning_rate": 1.6089200347674924e-05, + "loss": 0.3536, + "step": 7199 + }, + { + "epoch": 0.59, + "learning_rate": 1.608865710560626e-05, + "loss": 0.614, + "step": 7200 + }, + { + "epoch": 0.59, + "learning_rate": 1.6088113863537593e-05, + "loss": 0.3355, + "step": 7201 + }, + { + "epoch": 0.59, + "learning_rate": 1.608757062146893e-05, + "loss": 0.6175, + "step": 7202 + }, + { + "epoch": 0.59, + "learning_rate": 1.608702737940026e-05, + "loss": 0.3713, + "step": 7203 + }, + { + "epoch": 0.59, + "learning_rate": 1.60864841373316e-05, + "loss": 0.3764, + "step": 7204 + }, + { + "epoch": 0.59, + "learning_rate": 1.608594089526293e-05, + "loss": 0.2834, + "step": 7205 + }, + { + "epoch": 0.59, + "learning_rate": 1.6085397653194267e-05, + "loss": 0.4084, + "step": 7206 + }, + { + "epoch": 0.59, + "learning_rate": 1.6084854411125598e-05, + "loss": 0.6003, + "step": 7207 + }, + { + "epoch": 0.59, + "learning_rate": 1.6084311169056932e-05, + "loss": 0.5717, + "step": 7208 + }, + { + "epoch": 0.59, + "learning_rate": 1.6083767926988266e-05, + "loss": 0.3996, + "step": 7209 + }, + { + "epoch": 0.59, + "learning_rate": 1.60832246849196e-05, + "loss": 0.6562, + "step": 7210 + }, + { + "epoch": 0.59, + "learning_rate": 1.6082681442850935e-05, + "loss": 0.5287, + "step": 7211 + }, + { + "epoch": 0.59, + "learning_rate": 1.608213820078227e-05, + "loss": 0.645, + "step": 7212 + }, + { + "epoch": 0.59, + "learning_rate": 1.6081594958713603e-05, + "loss": 0.4809, + "step": 7213 + }, + { + "epoch": 0.59, + "learning_rate": 1.6081051716644937e-05, + "loss": 0.5527, + "step": 7214 + }, + { + "epoch": 0.59, + "learning_rate": 1.6080508474576272e-05, + "loss": 0.4477, + "step": 7215 + }, + { + "epoch": 0.59, + "learning_rate": 1.6079965232507606e-05, + "loss": 0.3187, + "step": 7216 + }, + { + "epoch": 0.59, + "learning_rate": 1.607942199043894e-05, + "loss": 0.8637, + "step": 7217 + }, + { + "epoch": 0.59, + "learning_rate": 1.6078878748370274e-05, + "loss": 0.6793, + "step": 7218 + }, + { + "epoch": 0.59, + "learning_rate": 1.607833550630161e-05, + "loss": 0.4942, + "step": 7219 + }, + { + "epoch": 0.59, + "learning_rate": 1.6077792264232943e-05, + "loss": 0.3843, + "step": 7220 + }, + { + "epoch": 0.59, + "learning_rate": 1.6077249022164277e-05, + "loss": 0.5024, + "step": 7221 + }, + { + "epoch": 0.59, + "learning_rate": 1.607670578009561e-05, + "loss": 0.616, + "step": 7222 + }, + { + "epoch": 0.59, + "learning_rate": 1.6076162538026946e-05, + "loss": 0.2538, + "step": 7223 + }, + { + "epoch": 0.59, + "learning_rate": 1.607561929595828e-05, + "loss": 0.4636, + "step": 7224 + }, + { + "epoch": 0.59, + "learning_rate": 1.6075076053889614e-05, + "loss": 0.3421, + "step": 7225 + }, + { + "epoch": 0.59, + "learning_rate": 1.6074532811820948e-05, + "loss": 0.4533, + "step": 7226 + }, + { + "epoch": 0.59, + "learning_rate": 1.6073989569752282e-05, + "loss": 0.6686, + "step": 7227 + }, + { + "epoch": 0.59, + "learning_rate": 1.6073446327683617e-05, + "loss": 0.5946, + "step": 7228 + }, + { + "epoch": 0.59, + "learning_rate": 1.607290308561495e-05, + "loss": 0.3052, + "step": 7229 + }, + { + "epoch": 0.59, + "learning_rate": 1.6072359843546285e-05, + "loss": 0.2666, + "step": 7230 + }, + { + "epoch": 0.59, + "learning_rate": 1.607181660147762e-05, + "loss": 0.5166, + "step": 7231 + }, + { + "epoch": 0.59, + "learning_rate": 1.6071273359408954e-05, + "loss": 0.33, + "step": 7232 + }, + { + "epoch": 0.59, + "learning_rate": 1.6070730117340288e-05, + "loss": 0.4944, + "step": 7233 + }, + { + "epoch": 0.59, + "learning_rate": 1.6070186875271622e-05, + "loss": 0.5488, + "step": 7234 + }, + { + "epoch": 0.59, + "learning_rate": 1.6069643633202956e-05, + "loss": 0.3466, + "step": 7235 + }, + { + "epoch": 0.59, + "learning_rate": 1.606910039113429e-05, + "loss": 0.5614, + "step": 7236 + }, + { + "epoch": 0.59, + "learning_rate": 1.6068557149065625e-05, + "loss": 0.5108, + "step": 7237 + }, + { + "epoch": 0.59, + "learning_rate": 1.606801390699696e-05, + "loss": 0.7763, + "step": 7238 + }, + { + "epoch": 0.59, + "learning_rate": 1.6067470664928293e-05, + "loss": 0.1588, + "step": 7239 + }, + { + "epoch": 0.59, + "learning_rate": 1.6066927422859627e-05, + "loss": 0.3732, + "step": 7240 + }, + { + "epoch": 0.59, + "learning_rate": 1.6066384180790962e-05, + "loss": 0.6176, + "step": 7241 + }, + { + "epoch": 0.59, + "learning_rate": 1.6065840938722296e-05, + "loss": 0.4604, + "step": 7242 + }, + { + "epoch": 0.59, + "learning_rate": 1.606529769665363e-05, + "loss": 0.3554, + "step": 7243 + }, + { + "epoch": 0.59, + "learning_rate": 1.6064754454584964e-05, + "loss": 0.6219, + "step": 7244 + }, + { + "epoch": 0.59, + "learning_rate": 1.60642112125163e-05, + "loss": 0.6425, + "step": 7245 + }, + { + "epoch": 0.59, + "learning_rate": 1.6063667970447633e-05, + "loss": 0.4538, + "step": 7246 + }, + { + "epoch": 0.59, + "learning_rate": 1.6063124728378967e-05, + "loss": 0.3779, + "step": 7247 + }, + { + "epoch": 0.59, + "learning_rate": 1.60625814863103e-05, + "loss": 0.4251, + "step": 7248 + }, + { + "epoch": 0.59, + "learning_rate": 1.6062038244241636e-05, + "loss": 0.8943, + "step": 7249 + }, + { + "epoch": 0.59, + "learning_rate": 1.606149500217297e-05, + "loss": 0.466, + "step": 7250 + }, + { + "epoch": 0.59, + "eval_accuracy": 0.8261844116148752, + "eval_loss": 0.4475253224372864, + "eval_runtime": 22.3131, + "eval_samples_per_second": 439.877, + "eval_steps_per_second": 3.451, + "step": 7250 + }, + { + "epoch": 0.59, + "learning_rate": 1.6060951760104304e-05, + "loss": 0.5599, + "step": 7251 + }, + { + "epoch": 0.59, + "learning_rate": 1.6060408518035638e-05, + "loss": 0.8033, + "step": 7252 + }, + { + "epoch": 0.59, + "learning_rate": 1.6059865275966972e-05, + "loss": 0.517, + "step": 7253 + }, + { + "epoch": 0.59, + "learning_rate": 1.6059322033898307e-05, + "loss": 0.3389, + "step": 7254 + }, + { + "epoch": 0.59, + "learning_rate": 1.605877879182964e-05, + "loss": 0.4296, + "step": 7255 + }, + { + "epoch": 0.59, + "learning_rate": 1.6058235549760975e-05, + "loss": 0.2852, + "step": 7256 + }, + { + "epoch": 0.59, + "learning_rate": 1.605769230769231e-05, + "loss": 0.3813, + "step": 7257 + }, + { + "epoch": 0.59, + "learning_rate": 1.6057149065623644e-05, + "loss": 0.3651, + "step": 7258 + }, + { + "epoch": 0.59, + "learning_rate": 1.6056605823554978e-05, + "loss": 0.5406, + "step": 7259 + }, + { + "epoch": 0.59, + "learning_rate": 1.6056062581486312e-05, + "loss": 0.3312, + "step": 7260 + }, + { + "epoch": 0.59, + "learning_rate": 1.6055519339417646e-05, + "loss": 0.2467, + "step": 7261 + }, + { + "epoch": 0.59, + "learning_rate": 1.605497609734898e-05, + "loss": 0.573, + "step": 7262 + }, + { + "epoch": 0.59, + "learning_rate": 1.6054432855280315e-05, + "loss": 0.64, + "step": 7263 + }, + { + "epoch": 0.59, + "learning_rate": 1.605388961321165e-05, + "loss": 0.523, + "step": 7264 + }, + { + "epoch": 0.59, + "learning_rate": 1.605334637114298e-05, + "loss": 0.2789, + "step": 7265 + }, + { + "epoch": 0.59, + "learning_rate": 1.6052803129074317e-05, + "loss": 0.5106, + "step": 7266 + }, + { + "epoch": 0.59, + "learning_rate": 1.6052259887005652e-05, + "loss": 0.6181, + "step": 7267 + }, + { + "epoch": 0.59, + "learning_rate": 1.6051716644936986e-05, + "loss": 0.2794, + "step": 7268 + }, + { + "epoch": 0.59, + "learning_rate": 1.605117340286832e-05, + "loss": 0.5568, + "step": 7269 + }, + { + "epoch": 0.59, + "learning_rate": 1.6050630160799654e-05, + "loss": 0.6859, + "step": 7270 + }, + { + "epoch": 0.59, + "learning_rate": 1.605008691873099e-05, + "loss": 0.5502, + "step": 7271 + }, + { + "epoch": 0.59, + "learning_rate": 1.6049543676662323e-05, + "loss": 0.2813, + "step": 7272 + }, + { + "epoch": 0.59, + "learning_rate": 1.6049000434593657e-05, + "loss": 0.4638, + "step": 7273 + }, + { + "epoch": 0.59, + "learning_rate": 1.604845719252499e-05, + "loss": 0.6227, + "step": 7274 + }, + { + "epoch": 0.59, + "learning_rate": 1.6047913950456326e-05, + "loss": 0.6391, + "step": 7275 + }, + { + "epoch": 0.59, + "learning_rate": 1.604737070838766e-05, + "loss": 0.3508, + "step": 7276 + }, + { + "epoch": 0.59, + "learning_rate": 1.6046827466318994e-05, + "loss": 0.57, + "step": 7277 + }, + { + "epoch": 0.59, + "learning_rate": 1.6046284224250328e-05, + "loss": 0.3017, + "step": 7278 + }, + { + "epoch": 0.59, + "learning_rate": 1.6045740982181662e-05, + "loss": 0.6135, + "step": 7279 + }, + { + "epoch": 0.59, + "learning_rate": 1.6045197740112997e-05, + "loss": 0.3583, + "step": 7280 + }, + { + "epoch": 0.59, + "learning_rate": 1.604465449804433e-05, + "loss": 0.7886, + "step": 7281 + }, + { + "epoch": 0.59, + "learning_rate": 1.6044111255975665e-05, + "loss": 0.5126, + "step": 7282 + }, + { + "epoch": 0.59, + "learning_rate": 1.6043568013907e-05, + "loss": 0.221, + "step": 7283 + }, + { + "epoch": 0.59, + "learning_rate": 1.604302477183833e-05, + "loss": 0.5987, + "step": 7284 + }, + { + "epoch": 0.59, + "learning_rate": 1.6042481529769668e-05, + "loss": 0.4005, + "step": 7285 + }, + { + "epoch": 0.59, + "learning_rate": 1.6041938287701e-05, + "loss": 0.4198, + "step": 7286 + }, + { + "epoch": 0.59, + "learning_rate": 1.6041395045632336e-05, + "loss": 0.6191, + "step": 7287 + }, + { + "epoch": 0.59, + "learning_rate": 1.6040851803563667e-05, + "loss": 0.595, + "step": 7288 + }, + { + "epoch": 0.59, + "learning_rate": 1.6040308561495005e-05, + "loss": 0.6103, + "step": 7289 + }, + { + "epoch": 0.59, + "learning_rate": 1.6039765319426336e-05, + "loss": 0.3678, + "step": 7290 + }, + { + "epoch": 0.59, + "learning_rate": 1.6039222077357673e-05, + "loss": 0.4826, + "step": 7291 + }, + { + "epoch": 0.59, + "learning_rate": 1.6038678835289004e-05, + "loss": 0.2264, + "step": 7292 + }, + { + "epoch": 0.59, + "learning_rate": 1.6038135593220342e-05, + "loss": 0.2893, + "step": 7293 + }, + { + "epoch": 0.59, + "learning_rate": 1.6037592351151673e-05, + "loss": 0.4946, + "step": 7294 + }, + { + "epoch": 0.59, + "learning_rate": 1.603704910908301e-05, + "loss": 0.3452, + "step": 7295 + }, + { + "epoch": 0.59, + "learning_rate": 1.603650586701434e-05, + "loss": 0.4257, + "step": 7296 + }, + { + "epoch": 0.59, + "learning_rate": 1.603596262494568e-05, + "loss": 0.543, + "step": 7297 + }, + { + "epoch": 0.59, + "learning_rate": 1.603541938287701e-05, + "loss": 0.6763, + "step": 7298 + }, + { + "epoch": 0.59, + "learning_rate": 1.6034876140808347e-05, + "loss": 0.3876, + "step": 7299 + }, + { + "epoch": 0.59, + "learning_rate": 1.6034332898739678e-05, + "loss": 0.6038, + "step": 7300 + }, + { + "epoch": 0.59, + "learning_rate": 1.6033789656671016e-05, + "loss": 0.4552, + "step": 7301 + }, + { + "epoch": 0.6, + "learning_rate": 1.603324641460235e-05, + "loss": 0.5518, + "step": 7302 + }, + { + "epoch": 0.6, + "learning_rate": 1.603270317253368e-05, + "loss": 0.3535, + "step": 7303 + }, + { + "epoch": 0.6, + "learning_rate": 1.6032159930465018e-05, + "loss": 0.3392, + "step": 7304 + }, + { + "epoch": 0.6, + "learning_rate": 1.603161668839635e-05, + "loss": 0.3363, + "step": 7305 + }, + { + "epoch": 0.6, + "learning_rate": 1.6031073446327687e-05, + "loss": 0.4835, + "step": 7306 + }, + { + "epoch": 0.6, + "learning_rate": 1.6030530204259018e-05, + "loss": 0.3519, + "step": 7307 + }, + { + "epoch": 0.6, + "learning_rate": 1.6029986962190355e-05, + "loss": 0.4807, + "step": 7308 + }, + { + "epoch": 0.6, + "learning_rate": 1.6029443720121686e-05, + "loss": 0.5964, + "step": 7309 + }, + { + "epoch": 0.6, + "learning_rate": 1.6028900478053024e-05, + "loss": 0.3402, + "step": 7310 + }, + { + "epoch": 0.6, + "learning_rate": 1.6028357235984354e-05, + "loss": 0.419, + "step": 7311 + }, + { + "epoch": 0.6, + "learning_rate": 1.6027813993915692e-05, + "loss": 0.5051, + "step": 7312 + }, + { + "epoch": 0.6, + "learning_rate": 1.6027270751847023e-05, + "loss": 0.3524, + "step": 7313 + }, + { + "epoch": 0.6, + "learning_rate": 1.602672750977836e-05, + "loss": 0.4639, + "step": 7314 + }, + { + "epoch": 0.6, + "learning_rate": 1.602618426770969e-05, + "loss": 0.4887, + "step": 7315 + }, + { + "epoch": 0.6, + "learning_rate": 1.602564102564103e-05, + "loss": 0.5771, + "step": 7316 + }, + { + "epoch": 0.6, + "learning_rate": 1.602509778357236e-05, + "loss": 0.3872, + "step": 7317 + }, + { + "epoch": 0.6, + "learning_rate": 1.6024554541503697e-05, + "loss": 0.5224, + "step": 7318 + }, + { + "epoch": 0.6, + "learning_rate": 1.602401129943503e-05, + "loss": 0.9513, + "step": 7319 + }, + { + "epoch": 0.6, + "learning_rate": 1.6023468057366366e-05, + "loss": 0.4068, + "step": 7320 + }, + { + "epoch": 0.6, + "learning_rate": 1.6022924815297697e-05, + "loss": 0.5412, + "step": 7321 + }, + { + "epoch": 0.6, + "learning_rate": 1.602238157322903e-05, + "loss": 0.5694, + "step": 7322 + }, + { + "epoch": 0.6, + "learning_rate": 1.6021838331160365e-05, + "loss": 0.5369, + "step": 7323 + }, + { + "epoch": 0.6, + "learning_rate": 1.60212950890917e-05, + "loss": 0.3389, + "step": 7324 + }, + { + "epoch": 0.6, + "learning_rate": 1.6020751847023034e-05, + "loss": 0.5624, + "step": 7325 + }, + { + "epoch": 0.6, + "learning_rate": 1.6020208604954368e-05, + "loss": 0.3133, + "step": 7326 + }, + { + "epoch": 0.6, + "learning_rate": 1.6019665362885702e-05, + "loss": 0.5654, + "step": 7327 + }, + { + "epoch": 0.6, + "learning_rate": 1.6019122120817036e-05, + "loss": 0.5577, + "step": 7328 + }, + { + "epoch": 0.6, + "learning_rate": 1.601857887874837e-05, + "loss": 0.276, + "step": 7329 + }, + { + "epoch": 0.6, + "learning_rate": 1.6018035636679705e-05, + "loss": 0.2663, + "step": 7330 + }, + { + "epoch": 0.6, + "learning_rate": 1.601749239461104e-05, + "loss": 0.5945, + "step": 7331 + }, + { + "epoch": 0.6, + "learning_rate": 1.6016949152542373e-05, + "loss": 0.5823, + "step": 7332 + }, + { + "epoch": 0.6, + "learning_rate": 1.6016405910473708e-05, + "loss": 0.4927, + "step": 7333 + }, + { + "epoch": 0.6, + "learning_rate": 1.6015862668405042e-05, + "loss": 0.3199, + "step": 7334 + }, + { + "epoch": 0.6, + "learning_rate": 1.6015319426336376e-05, + "loss": 0.4568, + "step": 7335 + }, + { + "epoch": 0.6, + "learning_rate": 1.601477618426771e-05, + "loss": 0.5657, + "step": 7336 + }, + { + "epoch": 0.6, + "learning_rate": 1.6014232942199044e-05, + "loss": 0.464, + "step": 7337 + }, + { + "epoch": 0.6, + "learning_rate": 1.601368970013038e-05, + "loss": 0.7449, + "step": 7338 + }, + { + "epoch": 0.6, + "learning_rate": 1.6013146458061716e-05, + "loss": 0.341, + "step": 7339 + }, + { + "epoch": 0.6, + "learning_rate": 1.6012603215993047e-05, + "loss": 0.5824, + "step": 7340 + }, + { + "epoch": 0.6, + "learning_rate": 1.601205997392438e-05, + "loss": 0.691, + "step": 7341 + }, + { + "epoch": 0.6, + "learning_rate": 1.6011516731855716e-05, + "loss": 0.303, + "step": 7342 + }, + { + "epoch": 0.6, + "learning_rate": 1.601097348978705e-05, + "loss": 0.5796, + "step": 7343 + }, + { + "epoch": 0.6, + "learning_rate": 1.6010430247718384e-05, + "loss": 0.5591, + "step": 7344 + }, + { + "epoch": 0.6, + "learning_rate": 1.600988700564972e-05, + "loss": 0.4788, + "step": 7345 + }, + { + "epoch": 0.6, + "learning_rate": 1.6009343763581053e-05, + "loss": 0.5434, + "step": 7346 + }, + { + "epoch": 0.6, + "learning_rate": 1.6008800521512387e-05, + "loss": 0.3792, + "step": 7347 + }, + { + "epoch": 0.6, + "learning_rate": 1.600825727944372e-05, + "loss": 0.5851, + "step": 7348 + }, + { + "epoch": 0.6, + "learning_rate": 1.6007714037375055e-05, + "loss": 0.4483, + "step": 7349 + }, + { + "epoch": 0.6, + "learning_rate": 1.600717079530639e-05, + "loss": 0.5799, + "step": 7350 + }, + { + "epoch": 0.6, + "learning_rate": 1.6006627553237724e-05, + "loss": 0.2985, + "step": 7351 + }, + { + "epoch": 0.6, + "learning_rate": 1.6006084311169058e-05, + "loss": 0.2776, + "step": 7352 + }, + { + "epoch": 0.6, + "learning_rate": 1.6005541069100392e-05, + "loss": 0.2434, + "step": 7353 + }, + { + "epoch": 0.6, + "learning_rate": 1.6004997827031726e-05, + "loss": 0.6343, + "step": 7354 + }, + { + "epoch": 0.6, + "learning_rate": 1.600445458496306e-05, + "loss": 0.2547, + "step": 7355 + }, + { + "epoch": 0.6, + "learning_rate": 1.6003911342894395e-05, + "loss": 0.5216, + "step": 7356 + }, + { + "epoch": 0.6, + "learning_rate": 1.600336810082573e-05, + "loss": 0.309, + "step": 7357 + }, + { + "epoch": 0.6, + "learning_rate": 1.6002824858757063e-05, + "loss": 0.5576, + "step": 7358 + }, + { + "epoch": 0.6, + "learning_rate": 1.6002281616688398e-05, + "loss": 0.3339, + "step": 7359 + }, + { + "epoch": 0.6, + "learning_rate": 1.6001738374619732e-05, + "loss": 0.4405, + "step": 7360 + }, + { + "epoch": 0.6, + "learning_rate": 1.6001195132551066e-05, + "loss": 0.364, + "step": 7361 + }, + { + "epoch": 0.6, + "learning_rate": 1.60006518904824e-05, + "loss": 0.3114, + "step": 7362 + }, + { + "epoch": 0.6, + "learning_rate": 1.6000108648413734e-05, + "loss": 0.3863, + "step": 7363 + }, + { + "epoch": 0.6, + "learning_rate": 1.599956540634507e-05, + "loss": 0.6542, + "step": 7364 + }, + { + "epoch": 0.6, + "learning_rate": 1.5999022164276403e-05, + "loss": 0.5359, + "step": 7365 + }, + { + "epoch": 0.6, + "learning_rate": 1.5998478922207737e-05, + "loss": 0.3522, + "step": 7366 + }, + { + "epoch": 0.6, + "learning_rate": 1.599793568013907e-05, + "loss": 0.3368, + "step": 7367 + }, + { + "epoch": 0.6, + "learning_rate": 1.5997392438070406e-05, + "loss": 0.3181, + "step": 7368 + }, + { + "epoch": 0.6, + "learning_rate": 1.599684919600174e-05, + "loss": 0.3601, + "step": 7369 + }, + { + "epoch": 0.6, + "learning_rate": 1.5996305953933074e-05, + "loss": 0.6733, + "step": 7370 + }, + { + "epoch": 0.6, + "learning_rate": 1.599576271186441e-05, + "loss": 0.6067, + "step": 7371 + }, + { + "epoch": 0.6, + "learning_rate": 1.5995219469795743e-05, + "loss": 0.3602, + "step": 7372 + }, + { + "epoch": 0.6, + "learning_rate": 1.5994676227727077e-05, + "loss": 0.3026, + "step": 7373 + }, + { + "epoch": 0.6, + "learning_rate": 1.599413298565841e-05, + "loss": 0.6442, + "step": 7374 + }, + { + "epoch": 0.6, + "learning_rate": 1.5993589743589745e-05, + "loss": 0.5571, + "step": 7375 + }, + { + "epoch": 0.6, + "learning_rate": 1.599304650152108e-05, + "loss": 0.4426, + "step": 7376 + }, + { + "epoch": 0.6, + "learning_rate": 1.5992503259452414e-05, + "loss": 0.4435, + "step": 7377 + }, + { + "epoch": 0.6, + "learning_rate": 1.5991960017383748e-05, + "loss": 0.8357, + "step": 7378 + }, + { + "epoch": 0.6, + "learning_rate": 1.5991416775315082e-05, + "loss": 0.7711, + "step": 7379 + }, + { + "epoch": 0.6, + "learning_rate": 1.5990873533246416e-05, + "loss": 0.2776, + "step": 7380 + }, + { + "epoch": 0.6, + "learning_rate": 1.599033029117775e-05, + "loss": 0.3094, + "step": 7381 + }, + { + "epoch": 0.6, + "learning_rate": 1.5989787049109085e-05, + "loss": 0.3921, + "step": 7382 + }, + { + "epoch": 0.6, + "learning_rate": 1.598924380704042e-05, + "loss": 0.3911, + "step": 7383 + }, + { + "epoch": 0.6, + "learning_rate": 1.5988700564971753e-05, + "loss": 0.7821, + "step": 7384 + }, + { + "epoch": 0.6, + "learning_rate": 1.5988157322903088e-05, + "loss": 0.7911, + "step": 7385 + }, + { + "epoch": 0.6, + "learning_rate": 1.5987614080834422e-05, + "loss": 0.7598, + "step": 7386 + }, + { + "epoch": 0.6, + "learning_rate": 1.5987070838765756e-05, + "loss": 0.3293, + "step": 7387 + }, + { + "epoch": 0.6, + "learning_rate": 1.598652759669709e-05, + "loss": 0.4858, + "step": 7388 + }, + { + "epoch": 0.6, + "learning_rate": 1.5985984354628424e-05, + "loss": 0.5912, + "step": 7389 + }, + { + "epoch": 0.6, + "learning_rate": 1.598544111255976e-05, + "loss": 0.5367, + "step": 7390 + }, + { + "epoch": 0.6, + "learning_rate": 1.5984897870491093e-05, + "loss": 0.5336, + "step": 7391 + }, + { + "epoch": 0.6, + "learning_rate": 1.5984354628422427e-05, + "loss": 0.4777, + "step": 7392 + }, + { + "epoch": 0.6, + "learning_rate": 1.598381138635376e-05, + "loss": 0.4926, + "step": 7393 + }, + { + "epoch": 0.6, + "learning_rate": 1.5983268144285096e-05, + "loss": 0.6026, + "step": 7394 + }, + { + "epoch": 0.6, + "learning_rate": 1.598272490221643e-05, + "loss": 0.3202, + "step": 7395 + }, + { + "epoch": 0.6, + "learning_rate": 1.5982181660147764e-05, + "loss": 0.3889, + "step": 7396 + }, + { + "epoch": 0.6, + "learning_rate": 1.5981638418079098e-05, + "loss": 0.5003, + "step": 7397 + }, + { + "epoch": 0.6, + "learning_rate": 1.598109517601043e-05, + "loss": 0.4387, + "step": 7398 + }, + { + "epoch": 0.6, + "learning_rate": 1.5980551933941767e-05, + "loss": 0.3527, + "step": 7399 + }, + { + "epoch": 0.6, + "learning_rate": 1.5980008691873098e-05, + "loss": 0.412, + "step": 7400 + }, + { + "epoch": 0.6, + "learning_rate": 1.5979465449804435e-05, + "loss": 0.5661, + "step": 7401 + }, + { + "epoch": 0.6, + "learning_rate": 1.5978922207735766e-05, + "loss": 0.2544, + "step": 7402 + }, + { + "epoch": 0.6, + "learning_rate": 1.5978378965667104e-05, + "loss": 0.3222, + "step": 7403 + }, + { + "epoch": 0.6, + "learning_rate": 1.5977835723598435e-05, + "loss": 0.4635, + "step": 7404 + }, + { + "epoch": 0.6, + "learning_rate": 1.5977292481529772e-05, + "loss": 0.4613, + "step": 7405 + }, + { + "epoch": 0.6, + "learning_rate": 1.5976749239461103e-05, + "loss": 0.6789, + "step": 7406 + }, + { + "epoch": 0.6, + "learning_rate": 1.597620599739244e-05, + "loss": 0.5774, + "step": 7407 + }, + { + "epoch": 0.6, + "learning_rate": 1.597566275532377e-05, + "loss": 0.5155, + "step": 7408 + }, + { + "epoch": 0.6, + "learning_rate": 1.597511951325511e-05, + "loss": 0.6719, + "step": 7409 + }, + { + "epoch": 0.6, + "learning_rate": 1.5974576271186443e-05, + "loss": 0.6537, + "step": 7410 + }, + { + "epoch": 0.6, + "learning_rate": 1.5974033029117778e-05, + "loss": 0.4838, + "step": 7411 + }, + { + "epoch": 0.6, + "learning_rate": 1.5973489787049112e-05, + "loss": 0.4342, + "step": 7412 + }, + { + "epoch": 0.6, + "learning_rate": 1.5972946544980446e-05, + "loss": 0.3335, + "step": 7413 + }, + { + "epoch": 0.6, + "learning_rate": 1.597240330291178e-05, + "loss": 0.4312, + "step": 7414 + }, + { + "epoch": 0.6, + "learning_rate": 1.5971860060843114e-05, + "loss": 0.3944, + "step": 7415 + }, + { + "epoch": 0.6, + "learning_rate": 1.597131681877445e-05, + "loss": 0.5146, + "step": 7416 + }, + { + "epoch": 0.6, + "learning_rate": 1.597077357670578e-05, + "loss": 0.4251, + "step": 7417 + }, + { + "epoch": 0.6, + "learning_rate": 1.5970230334637117e-05, + "loss": 0.5597, + "step": 7418 + }, + { + "epoch": 0.6, + "learning_rate": 1.5969687092568448e-05, + "loss": 0.338, + "step": 7419 + }, + { + "epoch": 0.6, + "learning_rate": 1.5969143850499786e-05, + "loss": 0.5531, + "step": 7420 + }, + { + "epoch": 0.6, + "learning_rate": 1.5968600608431116e-05, + "loss": 0.5496, + "step": 7421 + }, + { + "epoch": 0.6, + "learning_rate": 1.5968057366362454e-05, + "loss": 0.3928, + "step": 7422 + }, + { + "epoch": 0.6, + "learning_rate": 1.5967514124293785e-05, + "loss": 0.6197, + "step": 7423 + }, + { + "epoch": 0.6, + "learning_rate": 1.5966970882225123e-05, + "loss": 0.5082, + "step": 7424 + }, + { + "epoch": 0.61, + "learning_rate": 1.5966427640156453e-05, + "loss": 0.5512, + "step": 7425 + }, + { + "epoch": 0.61, + "learning_rate": 1.596588439808779e-05, + "loss": 0.3969, + "step": 7426 + }, + { + "epoch": 0.61, + "learning_rate": 1.5965341156019122e-05, + "loss": 0.5331, + "step": 7427 + }, + { + "epoch": 0.61, + "learning_rate": 1.596479791395046e-05, + "loss": 0.4021, + "step": 7428 + }, + { + "epoch": 0.61, + "learning_rate": 1.596425467188179e-05, + "loss": 0.5855, + "step": 7429 + }, + { + "epoch": 0.61, + "learning_rate": 1.5963711429813128e-05, + "loss": 0.3933, + "step": 7430 + }, + { + "epoch": 0.61, + "learning_rate": 1.596316818774446e-05, + "loss": 0.4958, + "step": 7431 + }, + { + "epoch": 0.61, + "learning_rate": 1.5962624945675796e-05, + "loss": 0.5889, + "step": 7432 + }, + { + "epoch": 0.61, + "learning_rate": 1.5962081703607127e-05, + "loss": 0.4869, + "step": 7433 + }, + { + "epoch": 0.61, + "learning_rate": 1.5961538461538465e-05, + "loss": 0.6337, + "step": 7434 + }, + { + "epoch": 0.61, + "learning_rate": 1.5960995219469796e-05, + "loss": 0.4417, + "step": 7435 + }, + { + "epoch": 0.61, + "learning_rate": 1.596045197740113e-05, + "loss": 0.6687, + "step": 7436 + }, + { + "epoch": 0.61, + "learning_rate": 1.5959908735332464e-05, + "loss": 0.5628, + "step": 7437 + }, + { + "epoch": 0.61, + "learning_rate": 1.59593654932638e-05, + "loss": 0.3504, + "step": 7438 + }, + { + "epoch": 0.61, + "learning_rate": 1.5958822251195133e-05, + "loss": 0.2763, + "step": 7439 + }, + { + "epoch": 0.61, + "learning_rate": 1.5958279009126467e-05, + "loss": 0.6942, + "step": 7440 + }, + { + "epoch": 0.61, + "learning_rate": 1.59577357670578e-05, + "loss": 0.4666, + "step": 7441 + }, + { + "epoch": 0.61, + "learning_rate": 1.5957192524989135e-05, + "loss": 0.5048, + "step": 7442 + }, + { + "epoch": 0.61, + "learning_rate": 1.595664928292047e-05, + "loss": 0.5498, + "step": 7443 + }, + { + "epoch": 0.61, + "learning_rate": 1.5956106040851804e-05, + "loss": 0.3668, + "step": 7444 + }, + { + "epoch": 0.61, + "learning_rate": 1.5955562798783138e-05, + "loss": 0.5767, + "step": 7445 + }, + { + "epoch": 0.61, + "learning_rate": 1.5955019556714472e-05, + "loss": 0.4852, + "step": 7446 + }, + { + "epoch": 0.61, + "learning_rate": 1.595447631464581e-05, + "loss": 0.5435, + "step": 7447 + }, + { + "epoch": 0.61, + "learning_rate": 1.595393307257714e-05, + "loss": 0.4013, + "step": 7448 + }, + { + "epoch": 0.61, + "learning_rate": 1.5953389830508478e-05, + "loss": 0.4383, + "step": 7449 + }, + { + "epoch": 0.61, + "learning_rate": 1.595284658843981e-05, + "loss": 0.4875, + "step": 7450 + }, + { + "epoch": 0.61, + "learning_rate": 1.5952303346371147e-05, + "loss": 0.3953, + "step": 7451 + }, + { + "epoch": 0.61, + "learning_rate": 1.5951760104302478e-05, + "loss": 0.2872, + "step": 7452 + }, + { + "epoch": 0.61, + "learning_rate": 1.5951216862233815e-05, + "loss": 0.491, + "step": 7453 + }, + { + "epoch": 0.61, + "learning_rate": 1.5950673620165146e-05, + "loss": 0.3973, + "step": 7454 + }, + { + "epoch": 0.61, + "learning_rate": 1.595013037809648e-05, + "loss": 0.5469, + "step": 7455 + }, + { + "epoch": 0.61, + "learning_rate": 1.5949587136027815e-05, + "loss": 0.3335, + "step": 7456 + }, + { + "epoch": 0.61, + "learning_rate": 1.594904389395915e-05, + "loss": 0.5946, + "step": 7457 + }, + { + "epoch": 0.61, + "learning_rate": 1.5948500651890483e-05, + "loss": 0.3789, + "step": 7458 + }, + { + "epoch": 0.61, + "learning_rate": 1.5947957409821817e-05, + "loss": 0.5626, + "step": 7459 + }, + { + "epoch": 0.61, + "learning_rate": 1.594741416775315e-05, + "loss": 0.6862, + "step": 7460 + }, + { + "epoch": 0.61, + "learning_rate": 1.5946870925684486e-05, + "loss": 0.4858, + "step": 7461 + }, + { + "epoch": 0.61, + "learning_rate": 1.594632768361582e-05, + "loss": 0.7017, + "step": 7462 + }, + { + "epoch": 0.61, + "learning_rate": 1.5945784441547154e-05, + "loss": 0.6691, + "step": 7463 + }, + { + "epoch": 0.61, + "learning_rate": 1.594524119947849e-05, + "loss": 0.4491, + "step": 7464 + }, + { + "epoch": 0.61, + "learning_rate": 1.5944697957409823e-05, + "loss": 0.5767, + "step": 7465 + }, + { + "epoch": 0.61, + "learning_rate": 1.5944154715341157e-05, + "loss": 0.3153, + "step": 7466 + }, + { + "epoch": 0.61, + "learning_rate": 1.594361147327249e-05, + "loss": 0.4832, + "step": 7467 + }, + { + "epoch": 0.61, + "learning_rate": 1.5943068231203825e-05, + "loss": 0.4845, + "step": 7468 + }, + { + "epoch": 0.61, + "learning_rate": 1.594252498913516e-05, + "loss": 0.3971, + "step": 7469 + }, + { + "epoch": 0.61, + "learning_rate": 1.5941981747066494e-05, + "loss": 0.5711, + "step": 7470 + }, + { + "epoch": 0.61, + "learning_rate": 1.5941438504997828e-05, + "loss": 0.3114, + "step": 7471 + }, + { + "epoch": 0.61, + "learning_rate": 1.5940895262929162e-05, + "loss": 0.6414, + "step": 7472 + }, + { + "epoch": 0.61, + "learning_rate": 1.5940352020860496e-05, + "loss": 0.5171, + "step": 7473 + }, + { + "epoch": 0.61, + "learning_rate": 1.593980877879183e-05, + "loss": 0.6711, + "step": 7474 + }, + { + "epoch": 0.61, + "learning_rate": 1.5939265536723165e-05, + "loss": 0.7463, + "step": 7475 + }, + { + "epoch": 0.61, + "learning_rate": 1.59387222946545e-05, + "loss": 0.5512, + "step": 7476 + }, + { + "epoch": 0.61, + "learning_rate": 1.5938179052585833e-05, + "loss": 0.3112, + "step": 7477 + }, + { + "epoch": 0.61, + "learning_rate": 1.5937635810517168e-05, + "loss": 0.402, + "step": 7478 + }, + { + "epoch": 0.61, + "learning_rate": 1.5937092568448502e-05, + "loss": 0.793, + "step": 7479 + }, + { + "epoch": 0.61, + "learning_rate": 1.5936549326379836e-05, + "loss": 0.5026, + "step": 7480 + }, + { + "epoch": 0.61, + "learning_rate": 1.593600608431117e-05, + "loss": 0.5066, + "step": 7481 + }, + { + "epoch": 0.61, + "learning_rate": 1.5935462842242505e-05, + "loss": 0.5235, + "step": 7482 + }, + { + "epoch": 0.61, + "learning_rate": 1.593491960017384e-05, + "loss": 0.4231, + "step": 7483 + }, + { + "epoch": 0.61, + "learning_rate": 1.5934376358105173e-05, + "loss": 0.6251, + "step": 7484 + }, + { + "epoch": 0.61, + "learning_rate": 1.5933833116036507e-05, + "loss": 0.5617, + "step": 7485 + }, + { + "epoch": 0.61, + "learning_rate": 1.593328987396784e-05, + "loss": 0.5033, + "step": 7486 + }, + { + "epoch": 0.61, + "learning_rate": 1.5932746631899176e-05, + "loss": 0.36, + "step": 7487 + }, + { + "epoch": 0.61, + "learning_rate": 1.593220338983051e-05, + "loss": 0.5368, + "step": 7488 + }, + { + "epoch": 0.61, + "learning_rate": 1.5931660147761844e-05, + "loss": 0.4493, + "step": 7489 + }, + { + "epoch": 0.61, + "learning_rate": 1.593111690569318e-05, + "loss": 0.4201, + "step": 7490 + }, + { + "epoch": 0.61, + "learning_rate": 1.5930573663624513e-05, + "loss": 0.5519, + "step": 7491 + }, + { + "epoch": 0.61, + "learning_rate": 1.5930030421555847e-05, + "loss": 0.5701, + "step": 7492 + }, + { + "epoch": 0.61, + "learning_rate": 1.592948717948718e-05, + "loss": 0.5432, + "step": 7493 + }, + { + "epoch": 0.61, + "learning_rate": 1.5928943937418515e-05, + "loss": 0.5073, + "step": 7494 + }, + { + "epoch": 0.61, + "learning_rate": 1.592840069534985e-05, + "loss": 0.3844, + "step": 7495 + }, + { + "epoch": 0.61, + "learning_rate": 1.5927857453281184e-05, + "loss": 0.5118, + "step": 7496 + }, + { + "epoch": 0.61, + "learning_rate": 1.5927314211212518e-05, + "loss": 0.4117, + "step": 7497 + }, + { + "epoch": 0.61, + "learning_rate": 1.5926770969143852e-05, + "loss": 0.5957, + "step": 7498 + }, + { + "epoch": 0.61, + "learning_rate": 1.5926227727075186e-05, + "loss": 0.6088, + "step": 7499 + }, + { + "epoch": 0.61, + "learning_rate": 1.592568448500652e-05, + "loss": 0.4398, + "step": 7500 + }, + { + "epoch": 0.61, + "eval_accuracy": 0.8223127865511971, + "eval_loss": 0.45114800333976746, + "eval_runtime": 22.2272, + "eval_samples_per_second": 441.576, + "eval_steps_per_second": 3.464, + "step": 7500 + }, + { + "epoch": 0.61, + "learning_rate": 1.5925141242937855e-05, + "loss": 0.8206, + "step": 7501 + }, + { + "epoch": 0.61, + "learning_rate": 1.592459800086919e-05, + "loss": 0.4602, + "step": 7502 + }, + { + "epoch": 0.61, + "learning_rate": 1.5924054758800523e-05, + "loss": 0.6486, + "step": 7503 + }, + { + "epoch": 0.61, + "learning_rate": 1.5923511516731858e-05, + "loss": 0.5541, + "step": 7504 + }, + { + "epoch": 0.61, + "learning_rate": 1.5922968274663192e-05, + "loss": 0.7186, + "step": 7505 + }, + { + "epoch": 0.61, + "learning_rate": 1.5922425032594526e-05, + "loss": 0.3129, + "step": 7506 + }, + { + "epoch": 0.61, + "learning_rate": 1.592188179052586e-05, + "loss": 0.605, + "step": 7507 + }, + { + "epoch": 0.61, + "learning_rate": 1.5921338548457195e-05, + "loss": 0.4714, + "step": 7508 + }, + { + "epoch": 0.61, + "learning_rate": 1.592079530638853e-05, + "loss": 0.5304, + "step": 7509 + }, + { + "epoch": 0.61, + "learning_rate": 1.5920252064319863e-05, + "loss": 0.3058, + "step": 7510 + }, + { + "epoch": 0.61, + "learning_rate": 1.5919708822251197e-05, + "loss": 0.3939, + "step": 7511 + }, + { + "epoch": 0.61, + "learning_rate": 1.5919165580182528e-05, + "loss": 0.3627, + "step": 7512 + }, + { + "epoch": 0.61, + "learning_rate": 1.5918622338113866e-05, + "loss": 0.4612, + "step": 7513 + }, + { + "epoch": 0.61, + "learning_rate": 1.5918079096045196e-05, + "loss": 0.7546, + "step": 7514 + }, + { + "epoch": 0.61, + "learning_rate": 1.5917535853976534e-05, + "loss": 0.5042, + "step": 7515 + }, + { + "epoch": 0.61, + "learning_rate": 1.5916992611907865e-05, + "loss": 0.4186, + "step": 7516 + }, + { + "epoch": 0.61, + "learning_rate": 1.5916449369839203e-05, + "loss": 0.7987, + "step": 7517 + }, + { + "epoch": 0.61, + "learning_rate": 1.5915906127770537e-05, + "loss": 0.3908, + "step": 7518 + }, + { + "epoch": 0.61, + "learning_rate": 1.591536288570187e-05, + "loss": 0.3291, + "step": 7519 + }, + { + "epoch": 0.61, + "learning_rate": 1.5914819643633205e-05, + "loss": 0.8042, + "step": 7520 + }, + { + "epoch": 0.61, + "learning_rate": 1.591427640156454e-05, + "loss": 0.4158, + "step": 7521 + }, + { + "epoch": 0.61, + "learning_rate": 1.5913733159495874e-05, + "loss": 0.5951, + "step": 7522 + }, + { + "epoch": 0.61, + "learning_rate": 1.5913189917427208e-05, + "loss": 0.7629, + "step": 7523 + }, + { + "epoch": 0.61, + "learning_rate": 1.5912646675358542e-05, + "loss": 0.3477, + "step": 7524 + }, + { + "epoch": 0.61, + "learning_rate": 1.5912103433289876e-05, + "loss": 0.3613, + "step": 7525 + }, + { + "epoch": 0.61, + "learning_rate": 1.591156019122121e-05, + "loss": 0.6527, + "step": 7526 + }, + { + "epoch": 0.61, + "learning_rate": 1.5911016949152545e-05, + "loss": 0.4034, + "step": 7527 + }, + { + "epoch": 0.61, + "learning_rate": 1.591047370708388e-05, + "loss": 0.422, + "step": 7528 + }, + { + "epoch": 0.61, + "learning_rate": 1.5909930465015213e-05, + "loss": 0.4106, + "step": 7529 + }, + { + "epoch": 0.61, + "learning_rate": 1.5909387222946548e-05, + "loss": 0.3237, + "step": 7530 + }, + { + "epoch": 0.61, + "learning_rate": 1.590884398087788e-05, + "loss": 0.6711, + "step": 7531 + }, + { + "epoch": 0.61, + "learning_rate": 1.5908300738809216e-05, + "loss": 0.261, + "step": 7532 + }, + { + "epoch": 0.61, + "learning_rate": 1.5907757496740547e-05, + "loss": 0.5789, + "step": 7533 + }, + { + "epoch": 0.61, + "learning_rate": 1.5907214254671884e-05, + "loss": 0.6086, + "step": 7534 + }, + { + "epoch": 0.61, + "learning_rate": 1.5906671012603215e-05, + "loss": 0.4419, + "step": 7535 + }, + { + "epoch": 0.61, + "learning_rate": 1.5906127770534553e-05, + "loss": 0.6432, + "step": 7536 + }, + { + "epoch": 0.61, + "learning_rate": 1.5905584528465884e-05, + "loss": 0.3814, + "step": 7537 + }, + { + "epoch": 0.61, + "learning_rate": 1.590504128639722e-05, + "loss": 0.2284, + "step": 7538 + }, + { + "epoch": 0.61, + "learning_rate": 1.5904498044328552e-05, + "loss": 0.2114, + "step": 7539 + }, + { + "epoch": 0.61, + "learning_rate": 1.590395480225989e-05, + "loss": 0.3171, + "step": 7540 + }, + { + "epoch": 0.61, + "learning_rate": 1.590341156019122e-05, + "loss": 0.2897, + "step": 7541 + }, + { + "epoch": 0.61, + "learning_rate": 1.590286831812256e-05, + "loss": 0.469, + "step": 7542 + }, + { + "epoch": 0.61, + "learning_rate": 1.590232507605389e-05, + "loss": 0.5865, + "step": 7543 + }, + { + "epoch": 0.61, + "learning_rate": 1.5901781833985227e-05, + "loss": 0.3548, + "step": 7544 + }, + { + "epoch": 0.61, + "learning_rate": 1.5901238591916558e-05, + "loss": 0.6989, + "step": 7545 + }, + { + "epoch": 0.61, + "learning_rate": 1.5900695349847895e-05, + "loss": 0.3976, + "step": 7546 + }, + { + "epoch": 0.61, + "learning_rate": 1.5900152107779226e-05, + "loss": 0.341, + "step": 7547 + }, + { + "epoch": 0.62, + "learning_rate": 1.5899608865710564e-05, + "loss": 0.4112, + "step": 7548 + }, + { + "epoch": 0.62, + "learning_rate": 1.5899065623641895e-05, + "loss": 0.4459, + "step": 7549 + }, + { + "epoch": 0.62, + "learning_rate": 1.589852238157323e-05, + "loss": 0.5124, + "step": 7550 + }, + { + "epoch": 0.62, + "learning_rate": 1.5897979139504563e-05, + "loss": 0.4297, + "step": 7551 + }, + { + "epoch": 0.62, + "learning_rate": 1.5897435897435897e-05, + "loss": 0.6411, + "step": 7552 + }, + { + "epoch": 0.62, + "learning_rate": 1.589689265536723e-05, + "loss": 0.4137, + "step": 7553 + }, + { + "epoch": 0.62, + "learning_rate": 1.5896349413298566e-05, + "loss": 0.4788, + "step": 7554 + }, + { + "epoch": 0.62, + "learning_rate": 1.5895806171229903e-05, + "loss": 0.4549, + "step": 7555 + }, + { + "epoch": 0.62, + "learning_rate": 1.5895262929161234e-05, + "loss": 0.4609, + "step": 7556 + }, + { + "epoch": 0.62, + "learning_rate": 1.5894719687092572e-05, + "loss": 0.5592, + "step": 7557 + }, + { + "epoch": 0.62, + "learning_rate": 1.5894176445023903e-05, + "loss": 0.2992, + "step": 7558 + }, + { + "epoch": 0.62, + "learning_rate": 1.589363320295524e-05, + "loss": 0.3459, + "step": 7559 + }, + { + "epoch": 0.62, + "learning_rate": 1.589308996088657e-05, + "loss": 0.2841, + "step": 7560 + }, + { + "epoch": 0.62, + "learning_rate": 1.589254671881791e-05, + "loss": 0.398, + "step": 7561 + }, + { + "epoch": 0.62, + "learning_rate": 1.589200347674924e-05, + "loss": 0.5857, + "step": 7562 + }, + { + "epoch": 0.62, + "learning_rate": 1.5891460234680577e-05, + "loss": 0.5501, + "step": 7563 + }, + { + "epoch": 0.62, + "learning_rate": 1.5890916992611908e-05, + "loss": 0.6199, + "step": 7564 + }, + { + "epoch": 0.62, + "learning_rate": 1.5890373750543246e-05, + "loss": 0.8134, + "step": 7565 + }, + { + "epoch": 0.62, + "learning_rate": 1.5889830508474576e-05, + "loss": 0.5252, + "step": 7566 + }, + { + "epoch": 0.62, + "learning_rate": 1.5889287266405914e-05, + "loss": 0.3834, + "step": 7567 + }, + { + "epoch": 0.62, + "learning_rate": 1.5888744024337245e-05, + "loss": 0.3993, + "step": 7568 + }, + { + "epoch": 0.62, + "learning_rate": 1.588820078226858e-05, + "loss": 0.6399, + "step": 7569 + }, + { + "epoch": 0.62, + "learning_rate": 1.5887657540199913e-05, + "loss": 0.4662, + "step": 7570 + }, + { + "epoch": 0.62, + "learning_rate": 1.5887114298131248e-05, + "loss": 0.462, + "step": 7571 + }, + { + "epoch": 0.62, + "learning_rate": 1.5886571056062582e-05, + "loss": 0.5091, + "step": 7572 + }, + { + "epoch": 0.62, + "learning_rate": 1.5886027813993916e-05, + "loss": 0.3407, + "step": 7573 + }, + { + "epoch": 0.62, + "learning_rate": 1.588548457192525e-05, + "loss": 0.3702, + "step": 7574 + }, + { + "epoch": 0.62, + "learning_rate": 1.5884941329856585e-05, + "loss": 0.6032, + "step": 7575 + }, + { + "epoch": 0.62, + "learning_rate": 1.588439808778792e-05, + "loss": 0.4439, + "step": 7576 + }, + { + "epoch": 0.62, + "learning_rate": 1.5883854845719253e-05, + "loss": 0.5307, + "step": 7577 + }, + { + "epoch": 0.62, + "learning_rate": 1.5883311603650587e-05, + "loss": 0.278, + "step": 7578 + }, + { + "epoch": 0.62, + "learning_rate": 1.588276836158192e-05, + "loss": 0.4567, + "step": 7579 + }, + { + "epoch": 0.62, + "learning_rate": 1.5882225119513256e-05, + "loss": 0.4825, + "step": 7580 + }, + { + "epoch": 0.62, + "learning_rate": 1.588168187744459e-05, + "loss": 0.4724, + "step": 7581 + }, + { + "epoch": 0.62, + "learning_rate": 1.5881138635375924e-05, + "loss": 0.2828, + "step": 7582 + }, + { + "epoch": 0.62, + "learning_rate": 1.588059539330726e-05, + "loss": 0.2715, + "step": 7583 + }, + { + "epoch": 0.62, + "learning_rate": 1.5880052151238593e-05, + "loss": 0.534, + "step": 7584 + }, + { + "epoch": 0.62, + "learning_rate": 1.5879508909169927e-05, + "loss": 0.3561, + "step": 7585 + }, + { + "epoch": 0.62, + "learning_rate": 1.587896566710126e-05, + "loss": 0.3971, + "step": 7586 + }, + { + "epoch": 0.62, + "learning_rate": 1.5878422425032595e-05, + "loss": 0.4074, + "step": 7587 + }, + { + "epoch": 0.62, + "learning_rate": 1.587787918296393e-05, + "loss": 0.3298, + "step": 7588 + }, + { + "epoch": 0.62, + "learning_rate": 1.5877335940895264e-05, + "loss": 0.3326, + "step": 7589 + }, + { + "epoch": 0.62, + "learning_rate": 1.5876792698826598e-05, + "loss": 0.3826, + "step": 7590 + }, + { + "epoch": 0.62, + "learning_rate": 1.5876249456757932e-05, + "loss": 0.4226, + "step": 7591 + }, + { + "epoch": 0.62, + "learning_rate": 1.5875706214689266e-05, + "loss": 0.6418, + "step": 7592 + }, + { + "epoch": 0.62, + "learning_rate": 1.58751629726206e-05, + "loss": 0.4894, + "step": 7593 + }, + { + "epoch": 0.62, + "learning_rate": 1.5874619730551935e-05, + "loss": 0.2104, + "step": 7594 + }, + { + "epoch": 0.62, + "learning_rate": 1.587407648848327e-05, + "loss": 0.4108, + "step": 7595 + }, + { + "epoch": 0.62, + "learning_rate": 1.5873533246414603e-05, + "loss": 0.3983, + "step": 7596 + }, + { + "epoch": 0.62, + "learning_rate": 1.5872990004345938e-05, + "loss": 0.3322, + "step": 7597 + }, + { + "epoch": 0.62, + "learning_rate": 1.5872446762277272e-05, + "loss": 0.5293, + "step": 7598 + }, + { + "epoch": 0.62, + "learning_rate": 1.5871903520208606e-05, + "loss": 0.4203, + "step": 7599 + }, + { + "epoch": 0.62, + "learning_rate": 1.587136027813994e-05, + "loss": 0.5549, + "step": 7600 + }, + { + "epoch": 0.62, + "learning_rate": 1.5870817036071275e-05, + "loss": 0.879, + "step": 7601 + }, + { + "epoch": 0.62, + "learning_rate": 1.587027379400261e-05, + "loss": 0.4952, + "step": 7602 + }, + { + "epoch": 0.62, + "learning_rate": 1.5869730551933943e-05, + "loss": 0.4562, + "step": 7603 + }, + { + "epoch": 0.62, + "learning_rate": 1.5869187309865277e-05, + "loss": 0.5621, + "step": 7604 + }, + { + "epoch": 0.62, + "learning_rate": 1.586864406779661e-05, + "loss": 0.283, + "step": 7605 + }, + { + "epoch": 0.62, + "learning_rate": 1.5868100825727946e-05, + "loss": 0.287, + "step": 7606 + }, + { + "epoch": 0.62, + "learning_rate": 1.586755758365928e-05, + "loss": 0.426, + "step": 7607 + }, + { + "epoch": 0.62, + "learning_rate": 1.5867014341590614e-05, + "loss": 0.487, + "step": 7608 + }, + { + "epoch": 0.62, + "learning_rate": 1.586647109952195e-05, + "loss": 0.3908, + "step": 7609 + }, + { + "epoch": 0.62, + "learning_rate": 1.5865927857453283e-05, + "loss": 0.6298, + "step": 7610 + }, + { + "epoch": 0.62, + "learning_rate": 1.5865384615384617e-05, + "loss": 0.6928, + "step": 7611 + }, + { + "epoch": 0.62, + "learning_rate": 1.586484137331595e-05, + "loss": 0.2605, + "step": 7612 + }, + { + "epoch": 0.62, + "learning_rate": 1.5864298131247285e-05, + "loss": 0.603, + "step": 7613 + }, + { + "epoch": 0.62, + "learning_rate": 1.586375488917862e-05, + "loss": 0.4727, + "step": 7614 + }, + { + "epoch": 0.62, + "learning_rate": 1.5863211647109954e-05, + "loss": 0.3858, + "step": 7615 + }, + { + "epoch": 0.62, + "learning_rate": 1.5862668405041288e-05, + "loss": 0.641, + "step": 7616 + }, + { + "epoch": 0.62, + "learning_rate": 1.5862125162972622e-05, + "loss": 0.2661, + "step": 7617 + }, + { + "epoch": 0.62, + "learning_rate": 1.5861581920903956e-05, + "loss": 0.5267, + "step": 7618 + }, + { + "epoch": 0.62, + "learning_rate": 1.586103867883529e-05, + "loss": 0.5751, + "step": 7619 + }, + { + "epoch": 0.62, + "learning_rate": 1.5860495436766625e-05, + "loss": 0.6323, + "step": 7620 + }, + { + "epoch": 0.62, + "learning_rate": 1.585995219469796e-05, + "loss": 0.3384, + "step": 7621 + }, + { + "epoch": 0.62, + "learning_rate": 1.5859408952629293e-05, + "loss": 0.2995, + "step": 7622 + }, + { + "epoch": 0.62, + "learning_rate": 1.5858865710560628e-05, + "loss": 0.4576, + "step": 7623 + }, + { + "epoch": 0.62, + "learning_rate": 1.5858322468491962e-05, + "loss": 0.3115, + "step": 7624 + }, + { + "epoch": 0.62, + "learning_rate": 1.5857779226423296e-05, + "loss": 0.5792, + "step": 7625 + }, + { + "epoch": 0.62, + "learning_rate": 1.585723598435463e-05, + "loss": 0.6002, + "step": 7626 + }, + { + "epoch": 0.62, + "learning_rate": 1.5856692742285965e-05, + "loss": 0.2855, + "step": 7627 + }, + { + "epoch": 0.62, + "learning_rate": 1.58561495002173e-05, + "loss": 0.2936, + "step": 7628 + }, + { + "epoch": 0.62, + "learning_rate": 1.5855606258148633e-05, + "loss": 0.3912, + "step": 7629 + }, + { + "epoch": 0.62, + "learning_rate": 1.5855063016079967e-05, + "loss": 0.6477, + "step": 7630 + }, + { + "epoch": 0.62, + "learning_rate": 1.58545197740113e-05, + "loss": 0.367, + "step": 7631 + }, + { + "epoch": 0.62, + "learning_rate": 1.5853976531942636e-05, + "loss": 0.469, + "step": 7632 + }, + { + "epoch": 0.62, + "learning_rate": 1.585343328987397e-05, + "loss": 0.4358, + "step": 7633 + }, + { + "epoch": 0.62, + "learning_rate": 1.5852890047805304e-05, + "loss": 0.4709, + "step": 7634 + }, + { + "epoch": 0.62, + "learning_rate": 1.585234680573664e-05, + "loss": 0.4915, + "step": 7635 + }, + { + "epoch": 0.62, + "learning_rate": 1.5851803563667973e-05, + "loss": 0.3488, + "step": 7636 + }, + { + "epoch": 0.62, + "learning_rate": 1.5851260321599307e-05, + "loss": 0.4142, + "step": 7637 + }, + { + "epoch": 0.62, + "learning_rate": 1.585071707953064e-05, + "loss": 0.3003, + "step": 7638 + }, + { + "epoch": 0.62, + "learning_rate": 1.5850173837461975e-05, + "loss": 0.3848, + "step": 7639 + }, + { + "epoch": 0.62, + "learning_rate": 1.584963059539331e-05, + "loss": 0.5714, + "step": 7640 + }, + { + "epoch": 0.62, + "learning_rate": 1.5849087353324644e-05, + "loss": 0.4451, + "step": 7641 + }, + { + "epoch": 0.62, + "learning_rate": 1.5848544111255978e-05, + "loss": 0.4333, + "step": 7642 + }, + { + "epoch": 0.62, + "learning_rate": 1.5848000869187312e-05, + "loss": 0.3655, + "step": 7643 + }, + { + "epoch": 0.62, + "learning_rate": 1.5847457627118646e-05, + "loss": 0.4397, + "step": 7644 + }, + { + "epoch": 0.62, + "learning_rate": 1.5846914385049977e-05, + "loss": 0.7092, + "step": 7645 + }, + { + "epoch": 0.62, + "learning_rate": 1.5846371142981315e-05, + "loss": 0.2977, + "step": 7646 + }, + { + "epoch": 0.62, + "learning_rate": 1.5845827900912646e-05, + "loss": 0.603, + "step": 7647 + }, + { + "epoch": 0.62, + "learning_rate": 1.5845284658843983e-05, + "loss": 0.3826, + "step": 7648 + }, + { + "epoch": 0.62, + "learning_rate": 1.5844741416775314e-05, + "loss": 0.4456, + "step": 7649 + }, + { + "epoch": 0.62, + "learning_rate": 1.5844198174706652e-05, + "loss": 0.4077, + "step": 7650 + }, + { + "epoch": 0.62, + "learning_rate": 1.5843654932637983e-05, + "loss": 0.5854, + "step": 7651 + }, + { + "epoch": 0.62, + "learning_rate": 1.584311169056932e-05, + "loss": 0.5301, + "step": 7652 + }, + { + "epoch": 0.62, + "learning_rate": 1.584256844850065e-05, + "loss": 0.5354, + "step": 7653 + }, + { + "epoch": 0.62, + "learning_rate": 1.584202520643199e-05, + "loss": 0.5045, + "step": 7654 + }, + { + "epoch": 0.62, + "learning_rate": 1.584148196436332e-05, + "loss": 0.4734, + "step": 7655 + }, + { + "epoch": 0.62, + "learning_rate": 1.5840938722294657e-05, + "loss": 0.4839, + "step": 7656 + }, + { + "epoch": 0.62, + "learning_rate": 1.5840395480225988e-05, + "loss": 0.5109, + "step": 7657 + }, + { + "epoch": 0.62, + "learning_rate": 1.5839852238157326e-05, + "loss": 0.4715, + "step": 7658 + }, + { + "epoch": 0.62, + "learning_rate": 1.5839308996088657e-05, + "loss": 0.3208, + "step": 7659 + }, + { + "epoch": 0.62, + "learning_rate": 1.5838765754019994e-05, + "loss": 0.2764, + "step": 7660 + }, + { + "epoch": 0.62, + "learning_rate": 1.5838222511951325e-05, + "loss": 0.5809, + "step": 7661 + }, + { + "epoch": 0.62, + "learning_rate": 1.5837679269882663e-05, + "loss": 0.5686, + "step": 7662 + }, + { + "epoch": 0.62, + "learning_rate": 1.5837136027813997e-05, + "loss": 0.6603, + "step": 7663 + }, + { + "epoch": 0.62, + "learning_rate": 1.5836592785745328e-05, + "loss": 0.719, + "step": 7664 + }, + { + "epoch": 0.62, + "learning_rate": 1.5836049543676665e-05, + "loss": 0.3833, + "step": 7665 + }, + { + "epoch": 0.62, + "learning_rate": 1.5835506301607996e-05, + "loss": 0.5501, + "step": 7666 + }, + { + "epoch": 0.62, + "learning_rate": 1.5834963059539334e-05, + "loss": 0.5636, + "step": 7667 + }, + { + "epoch": 0.62, + "learning_rate": 1.5834419817470665e-05, + "loss": 0.5971, + "step": 7668 + }, + { + "epoch": 0.62, + "learning_rate": 1.5833876575402002e-05, + "loss": 0.5283, + "step": 7669 + }, + { + "epoch": 0.62, + "learning_rate": 1.5833333333333333e-05, + "loss": 0.4927, + "step": 7670 + }, + { + "epoch": 0.63, + "learning_rate": 1.583279009126467e-05, + "loss": 0.4482, + "step": 7671 + }, + { + "epoch": 0.63, + "learning_rate": 1.5832246849196e-05, + "loss": 0.4063, + "step": 7672 + }, + { + "epoch": 0.63, + "learning_rate": 1.583170360712734e-05, + "loss": 0.3143, + "step": 7673 + }, + { + "epoch": 0.63, + "learning_rate": 1.583116036505867e-05, + "loss": 0.3989, + "step": 7674 + }, + { + "epoch": 0.63, + "learning_rate": 1.5830617122990008e-05, + "loss": 0.3299, + "step": 7675 + }, + { + "epoch": 0.63, + "learning_rate": 1.583007388092134e-05, + "loss": 0.2939, + "step": 7676 + }, + { + "epoch": 0.63, + "learning_rate": 1.5829530638852676e-05, + "loss": 0.4259, + "step": 7677 + }, + { + "epoch": 0.63, + "learning_rate": 1.5828987396784007e-05, + "loss": 0.3737, + "step": 7678 + }, + { + "epoch": 0.63, + "learning_rate": 1.5828444154715345e-05, + "loss": 0.7002, + "step": 7679 + }, + { + "epoch": 0.63, + "learning_rate": 1.5827900912646675e-05, + "loss": 0.5548, + "step": 7680 + }, + { + "epoch": 0.63, + "learning_rate": 1.5827357670578013e-05, + "loss": 0.4956, + "step": 7681 + }, + { + "epoch": 0.63, + "learning_rate": 1.5826814428509344e-05, + "loss": 0.7434, + "step": 7682 + }, + { + "epoch": 0.63, + "learning_rate": 1.5826271186440678e-05, + "loss": 0.309, + "step": 7683 + }, + { + "epoch": 0.63, + "learning_rate": 1.5825727944372012e-05, + "loss": 0.3399, + "step": 7684 + }, + { + "epoch": 0.63, + "learning_rate": 1.5825184702303347e-05, + "loss": 0.2988, + "step": 7685 + }, + { + "epoch": 0.63, + "learning_rate": 1.582464146023468e-05, + "loss": 0.4222, + "step": 7686 + }, + { + "epoch": 0.63, + "learning_rate": 1.5824098218166015e-05, + "loss": 0.4703, + "step": 7687 + }, + { + "epoch": 0.63, + "learning_rate": 1.582355497609735e-05, + "loss": 0.6195, + "step": 7688 + }, + { + "epoch": 0.63, + "learning_rate": 1.5823011734028683e-05, + "loss": 0.4216, + "step": 7689 + }, + { + "epoch": 0.63, + "learning_rate": 1.5822468491960018e-05, + "loss": 0.3865, + "step": 7690 + }, + { + "epoch": 0.63, + "learning_rate": 1.5821925249891352e-05, + "loss": 0.6163, + "step": 7691 + }, + { + "epoch": 0.63, + "learning_rate": 1.5821382007822686e-05, + "loss": 0.6542, + "step": 7692 + }, + { + "epoch": 0.63, + "learning_rate": 1.582083876575402e-05, + "loss": 0.3739, + "step": 7693 + }, + { + "epoch": 0.63, + "learning_rate": 1.5820295523685355e-05, + "loss": 0.2646, + "step": 7694 + }, + { + "epoch": 0.63, + "learning_rate": 1.581975228161669e-05, + "loss": 0.5187, + "step": 7695 + }, + { + "epoch": 0.63, + "learning_rate": 1.5819209039548023e-05, + "loss": 0.4096, + "step": 7696 + }, + { + "epoch": 0.63, + "learning_rate": 1.5818665797479357e-05, + "loss": 0.4441, + "step": 7697 + }, + { + "epoch": 0.63, + "learning_rate": 1.581812255541069e-05, + "loss": 0.3123, + "step": 7698 + }, + { + "epoch": 0.63, + "learning_rate": 1.5817579313342026e-05, + "loss": 0.3374, + "step": 7699 + }, + { + "epoch": 0.63, + "learning_rate": 1.5817036071273363e-05, + "loss": 0.3704, + "step": 7700 + }, + { + "epoch": 0.63, + "learning_rate": 1.5816492829204694e-05, + "loss": 1.1083, + "step": 7701 + }, + { + "epoch": 0.63, + "learning_rate": 1.581594958713603e-05, + "loss": 0.5686, + "step": 7702 + }, + { + "epoch": 0.63, + "learning_rate": 1.5815406345067363e-05, + "loss": 0.6813, + "step": 7703 + }, + { + "epoch": 0.63, + "learning_rate": 1.5814863102998697e-05, + "loss": 0.574, + "step": 7704 + }, + { + "epoch": 0.63, + "learning_rate": 1.581431986093003e-05, + "loss": 0.669, + "step": 7705 + }, + { + "epoch": 0.63, + "learning_rate": 1.5813776618861365e-05, + "loss": 0.3353, + "step": 7706 + }, + { + "epoch": 0.63, + "learning_rate": 1.58132333767927e-05, + "loss": 0.9196, + "step": 7707 + }, + { + "epoch": 0.63, + "learning_rate": 1.5812690134724034e-05, + "loss": 0.6896, + "step": 7708 + }, + { + "epoch": 0.63, + "learning_rate": 1.5812146892655368e-05, + "loss": 0.6506, + "step": 7709 + }, + { + "epoch": 0.63, + "learning_rate": 1.5811603650586702e-05, + "loss": 0.5449, + "step": 7710 + }, + { + "epoch": 0.63, + "learning_rate": 1.5811060408518037e-05, + "loss": 0.6181, + "step": 7711 + }, + { + "epoch": 0.63, + "learning_rate": 1.581051716644937e-05, + "loss": 0.238, + "step": 7712 + }, + { + "epoch": 0.63, + "learning_rate": 1.5809973924380705e-05, + "loss": 0.4671, + "step": 7713 + }, + { + "epoch": 0.63, + "learning_rate": 1.580943068231204e-05, + "loss": 0.4405, + "step": 7714 + }, + { + "epoch": 0.63, + "learning_rate": 1.5808887440243373e-05, + "loss": 0.2969, + "step": 7715 + }, + { + "epoch": 0.63, + "learning_rate": 1.5808344198174708e-05, + "loss": 0.7185, + "step": 7716 + }, + { + "epoch": 0.63, + "learning_rate": 1.5807800956106042e-05, + "loss": 0.2339, + "step": 7717 + }, + { + "epoch": 0.63, + "learning_rate": 1.5807257714037376e-05, + "loss": 0.8113, + "step": 7718 + }, + { + "epoch": 0.63, + "learning_rate": 1.580671447196871e-05, + "loss": 0.4224, + "step": 7719 + }, + { + "epoch": 0.63, + "learning_rate": 1.5806171229900045e-05, + "loss": 0.4839, + "step": 7720 + }, + { + "epoch": 0.63, + "learning_rate": 1.580562798783138e-05, + "loss": 0.4753, + "step": 7721 + }, + { + "epoch": 0.63, + "learning_rate": 1.5805084745762713e-05, + "loss": 0.6386, + "step": 7722 + }, + { + "epoch": 0.63, + "learning_rate": 1.5804541503694047e-05, + "loss": 0.3196, + "step": 7723 + }, + { + "epoch": 0.63, + "learning_rate": 1.580399826162538e-05, + "loss": 0.589, + "step": 7724 + }, + { + "epoch": 0.63, + "learning_rate": 1.5803455019556716e-05, + "loss": 0.4798, + "step": 7725 + }, + { + "epoch": 0.63, + "learning_rate": 1.580291177748805e-05, + "loss": 0.2169, + "step": 7726 + }, + { + "epoch": 0.63, + "learning_rate": 1.5802368535419384e-05, + "loss": 0.2965, + "step": 7727 + }, + { + "epoch": 0.63, + "learning_rate": 1.580182529335072e-05, + "loss": 0.4074, + "step": 7728 + }, + { + "epoch": 0.63, + "learning_rate": 1.5801282051282053e-05, + "loss": 0.4596, + "step": 7729 + }, + { + "epoch": 0.63, + "learning_rate": 1.5800738809213387e-05, + "loss": 0.5812, + "step": 7730 + }, + { + "epoch": 0.63, + "learning_rate": 1.580019556714472e-05, + "loss": 0.4314, + "step": 7731 + }, + { + "epoch": 0.63, + "learning_rate": 1.5799652325076055e-05, + "loss": 0.4541, + "step": 7732 + }, + { + "epoch": 0.63, + "learning_rate": 1.579910908300739e-05, + "loss": 0.4441, + "step": 7733 + }, + { + "epoch": 0.63, + "learning_rate": 1.5798565840938724e-05, + "loss": 0.494, + "step": 7734 + }, + { + "epoch": 0.63, + "learning_rate": 1.5798022598870058e-05, + "loss": 0.5426, + "step": 7735 + }, + { + "epoch": 0.63, + "learning_rate": 1.5797479356801392e-05, + "loss": 0.6683, + "step": 7736 + }, + { + "epoch": 0.63, + "learning_rate": 1.5796936114732727e-05, + "loss": 0.2416, + "step": 7737 + }, + { + "epoch": 0.63, + "learning_rate": 1.579639287266406e-05, + "loss": 0.385, + "step": 7738 + }, + { + "epoch": 0.63, + "learning_rate": 1.5795849630595395e-05, + "loss": 0.4913, + "step": 7739 + }, + { + "epoch": 0.63, + "learning_rate": 1.579530638852673e-05, + "loss": 0.5434, + "step": 7740 + }, + { + "epoch": 0.63, + "learning_rate": 1.5794763146458063e-05, + "loss": 0.5989, + "step": 7741 + }, + { + "epoch": 0.63, + "learning_rate": 1.5794219904389398e-05, + "loss": 0.7462, + "step": 7742 + }, + { + "epoch": 0.63, + "learning_rate": 1.5793676662320732e-05, + "loss": 0.4773, + "step": 7743 + }, + { + "epoch": 0.63, + "learning_rate": 1.5793133420252066e-05, + "loss": 0.4737, + "step": 7744 + }, + { + "epoch": 0.63, + "learning_rate": 1.57925901781834e-05, + "loss": 0.5441, + "step": 7745 + }, + { + "epoch": 0.63, + "learning_rate": 1.5792046936114735e-05, + "loss": 0.2265, + "step": 7746 + }, + { + "epoch": 0.63, + "learning_rate": 1.579150369404607e-05, + "loss": 0.3304, + "step": 7747 + }, + { + "epoch": 0.63, + "learning_rate": 1.5790960451977403e-05, + "loss": 0.4613, + "step": 7748 + }, + { + "epoch": 0.63, + "learning_rate": 1.5790417209908737e-05, + "loss": 0.2172, + "step": 7749 + }, + { + "epoch": 0.63, + "learning_rate": 1.578987396784007e-05, + "loss": 0.4976, + "step": 7750 + }, + { + "epoch": 0.63, + "eval_accuracy": 0.8279164544065206, + "eval_loss": 0.44188955426216125, + "eval_runtime": 22.3456, + "eval_samples_per_second": 439.237, + "eval_steps_per_second": 3.446, + "step": 7750 + }, + { + "epoch": 0.63, + "learning_rate": 1.5789330725771406e-05, + "loss": 0.5306, + "step": 7751 + }, + { + "epoch": 0.63, + "learning_rate": 1.578878748370274e-05, + "loss": 0.5816, + "step": 7752 + }, + { + "epoch": 0.63, + "learning_rate": 1.5788244241634074e-05, + "loss": 0.4134, + "step": 7753 + }, + { + "epoch": 0.63, + "learning_rate": 1.578770099956541e-05, + "loss": 0.3909, + "step": 7754 + }, + { + "epoch": 0.63, + "learning_rate": 1.5787157757496743e-05, + "loss": 0.899, + "step": 7755 + }, + { + "epoch": 0.63, + "learning_rate": 1.5786614515428077e-05, + "loss": 0.2933, + "step": 7756 + }, + { + "epoch": 0.63, + "learning_rate": 1.578607127335941e-05, + "loss": 0.6011, + "step": 7757 + }, + { + "epoch": 0.63, + "learning_rate": 1.5785528031290745e-05, + "loss": 0.6142, + "step": 7758 + }, + { + "epoch": 0.63, + "learning_rate": 1.5784984789222076e-05, + "loss": 0.5865, + "step": 7759 + }, + { + "epoch": 0.63, + "learning_rate": 1.5784441547153414e-05, + "loss": 0.3566, + "step": 7760 + }, + { + "epoch": 0.63, + "learning_rate": 1.5783898305084745e-05, + "loss": 0.4341, + "step": 7761 + }, + { + "epoch": 0.63, + "learning_rate": 1.5783355063016082e-05, + "loss": 0.5501, + "step": 7762 + }, + { + "epoch": 0.63, + "learning_rate": 1.5782811820947413e-05, + "loss": 0.3754, + "step": 7763 + }, + { + "epoch": 0.63, + "learning_rate": 1.578226857887875e-05, + "loss": 0.4116, + "step": 7764 + }, + { + "epoch": 0.63, + "learning_rate": 1.578172533681008e-05, + "loss": 0.4235, + "step": 7765 + }, + { + "epoch": 0.63, + "learning_rate": 1.578118209474142e-05, + "loss": 0.3156, + "step": 7766 + }, + { + "epoch": 0.63, + "learning_rate": 1.578063885267275e-05, + "loss": 0.3965, + "step": 7767 + }, + { + "epoch": 0.63, + "learning_rate": 1.5780095610604088e-05, + "loss": 0.5018, + "step": 7768 + }, + { + "epoch": 0.63, + "learning_rate": 1.577955236853542e-05, + "loss": 0.3979, + "step": 7769 + }, + { + "epoch": 0.63, + "learning_rate": 1.5779009126466756e-05, + "loss": 0.5813, + "step": 7770 + }, + { + "epoch": 0.63, + "learning_rate": 1.577846588439809e-05, + "loss": 0.2534, + "step": 7771 + }, + { + "epoch": 0.63, + "learning_rate": 1.5777922642329425e-05, + "loss": 0.457, + "step": 7772 + }, + { + "epoch": 0.63, + "learning_rate": 1.577737940026076e-05, + "loss": 0.4652, + "step": 7773 + }, + { + "epoch": 0.63, + "learning_rate": 1.5776836158192093e-05, + "loss": 0.3447, + "step": 7774 + }, + { + "epoch": 0.63, + "learning_rate": 1.5776292916123427e-05, + "loss": 0.5121, + "step": 7775 + }, + { + "epoch": 0.63, + "learning_rate": 1.577574967405476e-05, + "loss": 0.4342, + "step": 7776 + }, + { + "epoch": 0.63, + "learning_rate": 1.5775206431986096e-05, + "loss": 0.6453, + "step": 7777 + }, + { + "epoch": 0.63, + "learning_rate": 1.5774663189917427e-05, + "loss": 0.5062, + "step": 7778 + }, + { + "epoch": 0.63, + "learning_rate": 1.5774119947848764e-05, + "loss": 0.307, + "step": 7779 + }, + { + "epoch": 0.63, + "learning_rate": 1.5773576705780095e-05, + "loss": 0.5016, + "step": 7780 + }, + { + "epoch": 0.63, + "learning_rate": 1.5773033463711433e-05, + "loss": 0.3999, + "step": 7781 + }, + { + "epoch": 0.63, + "learning_rate": 1.5772490221642764e-05, + "loss": 0.4705, + "step": 7782 + }, + { + "epoch": 0.63, + "learning_rate": 1.57719469795741e-05, + "loss": 0.5186, + "step": 7783 + }, + { + "epoch": 0.63, + "learning_rate": 1.5771403737505432e-05, + "loss": 0.2178, + "step": 7784 + }, + { + "epoch": 0.63, + "learning_rate": 1.577086049543677e-05, + "loss": 0.3369, + "step": 7785 + }, + { + "epoch": 0.63, + "learning_rate": 1.57703172533681e-05, + "loss": 0.5598, + "step": 7786 + }, + { + "epoch": 0.63, + "learning_rate": 1.5769774011299438e-05, + "loss": 0.5515, + "step": 7787 + }, + { + "epoch": 0.63, + "learning_rate": 1.576923076923077e-05, + "loss": 0.3311, + "step": 7788 + }, + { + "epoch": 0.63, + "learning_rate": 1.5768687527162107e-05, + "loss": 0.1968, + "step": 7789 + }, + { + "epoch": 0.63, + "learning_rate": 1.5768144285093437e-05, + "loss": 0.6855, + "step": 7790 + }, + { + "epoch": 0.63, + "learning_rate": 1.5767601043024775e-05, + "loss": 0.3379, + "step": 7791 + }, + { + "epoch": 0.63, + "learning_rate": 1.5767057800956106e-05, + "loss": 0.4945, + "step": 7792 + }, + { + "epoch": 0.64, + "learning_rate": 1.5766514558887443e-05, + "loss": 0.4555, + "step": 7793 + }, + { + "epoch": 0.64, + "learning_rate": 1.5765971316818774e-05, + "loss": 0.6663, + "step": 7794 + }, + { + "epoch": 0.64, + "learning_rate": 1.5765428074750112e-05, + "loss": 0.3239, + "step": 7795 + }, + { + "epoch": 0.64, + "learning_rate": 1.5764884832681443e-05, + "loss": 0.5833, + "step": 7796 + }, + { + "epoch": 0.64, + "learning_rate": 1.5764341590612777e-05, + "loss": 0.4877, + "step": 7797 + }, + { + "epoch": 0.64, + "learning_rate": 1.576379834854411e-05, + "loss": 0.6909, + "step": 7798 + }, + { + "epoch": 0.64, + "learning_rate": 1.5763255106475445e-05, + "loss": 0.2425, + "step": 7799 + }, + { + "epoch": 0.64, + "learning_rate": 1.576271186440678e-05, + "loss": 0.451, + "step": 7800 + }, + { + "epoch": 0.64, + "learning_rate": 1.5762168622338114e-05, + "loss": 0.3004, + "step": 7801 + }, + { + "epoch": 0.64, + "learning_rate": 1.5761625380269448e-05, + "loss": 0.6445, + "step": 7802 + }, + { + "epoch": 0.64, + "learning_rate": 1.5761082138200782e-05, + "loss": 0.4602, + "step": 7803 + }, + { + "epoch": 0.64, + "learning_rate": 1.5760538896132117e-05, + "loss": 0.4667, + "step": 7804 + }, + { + "epoch": 0.64, + "learning_rate": 1.575999565406345e-05, + "loss": 0.3737, + "step": 7805 + }, + { + "epoch": 0.64, + "learning_rate": 1.5759452411994785e-05, + "loss": 0.5806, + "step": 7806 + }, + { + "epoch": 0.64, + "learning_rate": 1.575890916992612e-05, + "loss": 0.573, + "step": 7807 + }, + { + "epoch": 0.64, + "learning_rate": 1.5758365927857457e-05, + "loss": 0.6086, + "step": 7808 + }, + { + "epoch": 0.64, + "learning_rate": 1.5757822685788788e-05, + "loss": 0.6503, + "step": 7809 + }, + { + "epoch": 0.64, + "learning_rate": 1.5757279443720125e-05, + "loss": 0.6297, + "step": 7810 + }, + { + "epoch": 0.64, + "learning_rate": 1.5756736201651456e-05, + "loss": 0.3199, + "step": 7811 + }, + { + "epoch": 0.64, + "learning_rate": 1.5756192959582794e-05, + "loss": 0.5684, + "step": 7812 + }, + { + "epoch": 0.64, + "learning_rate": 1.5755649717514125e-05, + "loss": 0.3143, + "step": 7813 + }, + { + "epoch": 0.64, + "learning_rate": 1.5755106475445462e-05, + "loss": 0.4413, + "step": 7814 + }, + { + "epoch": 0.64, + "learning_rate": 1.5754563233376793e-05, + "loss": 0.5671, + "step": 7815 + }, + { + "epoch": 0.64, + "learning_rate": 1.5754019991308127e-05, + "loss": 0.5683, + "step": 7816 + }, + { + "epoch": 0.64, + "learning_rate": 1.575347674923946e-05, + "loss": 0.3766, + "step": 7817 + }, + { + "epoch": 0.64, + "learning_rate": 1.5752933507170796e-05, + "loss": 0.3604, + "step": 7818 + }, + { + "epoch": 0.64, + "learning_rate": 1.575239026510213e-05, + "loss": 0.588, + "step": 7819 + }, + { + "epoch": 0.64, + "learning_rate": 1.5751847023033464e-05, + "loss": 0.398, + "step": 7820 + }, + { + "epoch": 0.64, + "learning_rate": 1.57513037809648e-05, + "loss": 0.3491, + "step": 7821 + }, + { + "epoch": 0.64, + "learning_rate": 1.5750760538896133e-05, + "loss": 0.5864, + "step": 7822 + }, + { + "epoch": 0.64, + "learning_rate": 1.5750217296827467e-05, + "loss": 0.326, + "step": 7823 + }, + { + "epoch": 0.64, + "learning_rate": 1.57496740547588e-05, + "loss": 0.4198, + "step": 7824 + }, + { + "epoch": 0.64, + "learning_rate": 1.5749130812690135e-05, + "loss": 0.6523, + "step": 7825 + }, + { + "epoch": 0.64, + "learning_rate": 1.574858757062147e-05, + "loss": 0.5711, + "step": 7826 + }, + { + "epoch": 0.64, + "learning_rate": 1.5748044328552804e-05, + "loss": 0.6177, + "step": 7827 + }, + { + "epoch": 0.64, + "learning_rate": 1.5747501086484138e-05, + "loss": 0.4579, + "step": 7828 + }, + { + "epoch": 0.64, + "learning_rate": 1.5746957844415472e-05, + "loss": 0.4743, + "step": 7829 + }, + { + "epoch": 0.64, + "learning_rate": 1.5746414602346807e-05, + "loss": 0.5371, + "step": 7830 + }, + { + "epoch": 0.64, + "learning_rate": 1.574587136027814e-05, + "loss": 0.5526, + "step": 7831 + }, + { + "epoch": 0.64, + "learning_rate": 1.5745328118209475e-05, + "loss": 0.2807, + "step": 7832 + }, + { + "epoch": 0.64, + "learning_rate": 1.574478487614081e-05, + "loss": 0.5007, + "step": 7833 + }, + { + "epoch": 0.64, + "learning_rate": 1.5744241634072143e-05, + "loss": 0.2413, + "step": 7834 + }, + { + "epoch": 0.64, + "learning_rate": 1.5743698392003478e-05, + "loss": 0.2995, + "step": 7835 + }, + { + "epoch": 0.64, + "learning_rate": 1.5743155149934812e-05, + "loss": 0.3665, + "step": 7836 + }, + { + "epoch": 0.64, + "learning_rate": 1.5742611907866146e-05, + "loss": 0.4239, + "step": 7837 + }, + { + "epoch": 0.64, + "learning_rate": 1.574206866579748e-05, + "loss": 0.5567, + "step": 7838 + }, + { + "epoch": 0.64, + "learning_rate": 1.5741525423728815e-05, + "loss": 0.4881, + "step": 7839 + }, + { + "epoch": 0.64, + "learning_rate": 1.574098218166015e-05, + "loss": 0.501, + "step": 7840 + }, + { + "epoch": 0.64, + "learning_rate": 1.5740438939591483e-05, + "loss": 0.4345, + "step": 7841 + }, + { + "epoch": 0.64, + "learning_rate": 1.5739895697522817e-05, + "loss": 0.3678, + "step": 7842 + }, + { + "epoch": 0.64, + "learning_rate": 1.573935245545415e-05, + "loss": 0.7257, + "step": 7843 + }, + { + "epoch": 0.64, + "learning_rate": 1.5738809213385486e-05, + "loss": 0.6214, + "step": 7844 + }, + { + "epoch": 0.64, + "learning_rate": 1.573826597131682e-05, + "loss": 0.329, + "step": 7845 + }, + { + "epoch": 0.64, + "learning_rate": 1.5737722729248154e-05, + "loss": 0.8474, + "step": 7846 + }, + { + "epoch": 0.64, + "learning_rate": 1.573717948717949e-05, + "loss": 0.5844, + "step": 7847 + }, + { + "epoch": 0.64, + "learning_rate": 1.5736636245110823e-05, + "loss": 0.7479, + "step": 7848 + }, + { + "epoch": 0.64, + "learning_rate": 1.5736093003042157e-05, + "loss": 0.585, + "step": 7849 + }, + { + "epoch": 0.64, + "learning_rate": 1.573554976097349e-05, + "loss": 0.7203, + "step": 7850 + }, + { + "epoch": 0.64, + "learning_rate": 1.5735006518904825e-05, + "loss": 0.5507, + "step": 7851 + }, + { + "epoch": 0.64, + "learning_rate": 1.573446327683616e-05, + "loss": 0.3785, + "step": 7852 + }, + { + "epoch": 0.64, + "learning_rate": 1.5733920034767494e-05, + "loss": 0.2959, + "step": 7853 + }, + { + "epoch": 0.64, + "learning_rate": 1.5733376792698828e-05, + "loss": 0.5251, + "step": 7854 + }, + { + "epoch": 0.64, + "learning_rate": 1.5732833550630162e-05, + "loss": 0.4412, + "step": 7855 + }, + { + "epoch": 0.64, + "learning_rate": 1.5732290308561497e-05, + "loss": 0.4587, + "step": 7856 + }, + { + "epoch": 0.64, + "learning_rate": 1.573174706649283e-05, + "loss": 0.5653, + "step": 7857 + }, + { + "epoch": 0.64, + "learning_rate": 1.5731203824424165e-05, + "loss": 0.4382, + "step": 7858 + }, + { + "epoch": 0.64, + "learning_rate": 1.57306605823555e-05, + "loss": 0.5475, + "step": 7859 + }, + { + "epoch": 0.64, + "learning_rate": 1.5730117340286833e-05, + "loss": 0.6931, + "step": 7860 + }, + { + "epoch": 0.64, + "learning_rate": 1.5729574098218168e-05, + "loss": 0.4012, + "step": 7861 + }, + { + "epoch": 0.64, + "learning_rate": 1.5729030856149502e-05, + "loss": 0.3855, + "step": 7862 + }, + { + "epoch": 0.64, + "learning_rate": 1.5728487614080836e-05, + "loss": 0.5044, + "step": 7863 + }, + { + "epoch": 0.64, + "learning_rate": 1.572794437201217e-05, + "loss": 0.6184, + "step": 7864 + }, + { + "epoch": 0.64, + "learning_rate": 1.5727401129943505e-05, + "loss": 0.5166, + "step": 7865 + }, + { + "epoch": 0.64, + "learning_rate": 1.572685788787484e-05, + "loss": 0.3289, + "step": 7866 + }, + { + "epoch": 0.64, + "learning_rate": 1.5726314645806173e-05, + "loss": 0.3982, + "step": 7867 + }, + { + "epoch": 0.64, + "learning_rate": 1.5725771403737507e-05, + "loss": 0.825, + "step": 7868 + }, + { + "epoch": 0.64, + "learning_rate": 1.572522816166884e-05, + "loss": 0.3578, + "step": 7869 + }, + { + "epoch": 0.64, + "learning_rate": 1.5724684919600176e-05, + "loss": 0.3701, + "step": 7870 + }, + { + "epoch": 0.64, + "learning_rate": 1.572414167753151e-05, + "loss": 0.6673, + "step": 7871 + }, + { + "epoch": 0.64, + "learning_rate": 1.5723598435462844e-05, + "loss": 0.5042, + "step": 7872 + }, + { + "epoch": 0.64, + "learning_rate": 1.5723055193394175e-05, + "loss": 0.4949, + "step": 7873 + }, + { + "epoch": 0.64, + "learning_rate": 1.5722511951325513e-05, + "loss": 0.5428, + "step": 7874 + }, + { + "epoch": 0.64, + "learning_rate": 1.5721968709256844e-05, + "loss": 0.4631, + "step": 7875 + }, + { + "epoch": 0.64, + "learning_rate": 1.572142546718818e-05, + "loss": 0.5492, + "step": 7876 + }, + { + "epoch": 0.64, + "learning_rate": 1.5720882225119512e-05, + "loss": 0.5543, + "step": 7877 + }, + { + "epoch": 0.64, + "learning_rate": 1.572033898305085e-05, + "loss": 0.5319, + "step": 7878 + }, + { + "epoch": 0.64, + "learning_rate": 1.5719795740982184e-05, + "loss": 0.3485, + "step": 7879 + }, + { + "epoch": 0.64, + "learning_rate": 1.5719252498913518e-05, + "loss": 0.467, + "step": 7880 + }, + { + "epoch": 0.64, + "learning_rate": 1.5718709256844852e-05, + "loss": 0.3245, + "step": 7881 + }, + { + "epoch": 0.64, + "learning_rate": 1.5718166014776187e-05, + "loss": 0.4085, + "step": 7882 + }, + { + "epoch": 0.64, + "learning_rate": 1.571762277270752e-05, + "loss": 0.5152, + "step": 7883 + }, + { + "epoch": 0.64, + "learning_rate": 1.5717079530638855e-05, + "loss": 0.5129, + "step": 7884 + }, + { + "epoch": 0.64, + "learning_rate": 1.571653628857019e-05, + "loss": 0.3695, + "step": 7885 + }, + { + "epoch": 0.64, + "learning_rate": 1.5715993046501523e-05, + "loss": 0.5259, + "step": 7886 + }, + { + "epoch": 0.64, + "learning_rate": 1.5715449804432858e-05, + "loss": 0.413, + "step": 7887 + }, + { + "epoch": 0.64, + "learning_rate": 1.5714906562364192e-05, + "loss": 0.4837, + "step": 7888 + }, + { + "epoch": 0.64, + "learning_rate": 1.5714363320295526e-05, + "loss": 0.3977, + "step": 7889 + }, + { + "epoch": 0.64, + "learning_rate": 1.571382007822686e-05, + "loss": 0.5067, + "step": 7890 + }, + { + "epoch": 0.64, + "learning_rate": 1.5713276836158195e-05, + "loss": 0.4145, + "step": 7891 + }, + { + "epoch": 0.64, + "learning_rate": 1.5712733594089525e-05, + "loss": 0.3907, + "step": 7892 + }, + { + "epoch": 0.64, + "learning_rate": 1.5712190352020863e-05, + "loss": 0.468, + "step": 7893 + }, + { + "epoch": 0.64, + "learning_rate": 1.5711647109952194e-05, + "loss": 0.6169, + "step": 7894 + }, + { + "epoch": 0.64, + "learning_rate": 1.571110386788353e-05, + "loss": 0.3939, + "step": 7895 + }, + { + "epoch": 0.64, + "learning_rate": 1.5710560625814862e-05, + "loss": 0.166, + "step": 7896 + }, + { + "epoch": 0.64, + "learning_rate": 1.57100173837462e-05, + "loss": 0.3652, + "step": 7897 + }, + { + "epoch": 0.64, + "learning_rate": 1.570947414167753e-05, + "loss": 0.2291, + "step": 7898 + }, + { + "epoch": 0.64, + "learning_rate": 1.570893089960887e-05, + "loss": 0.6206, + "step": 7899 + }, + { + "epoch": 0.64, + "learning_rate": 1.57083876575402e-05, + "loss": 0.3827, + "step": 7900 + }, + { + "epoch": 0.64, + "learning_rate": 1.5707844415471537e-05, + "loss": 0.4362, + "step": 7901 + }, + { + "epoch": 0.64, + "learning_rate": 1.5707301173402868e-05, + "loss": 0.5636, + "step": 7902 + }, + { + "epoch": 0.64, + "learning_rate": 1.5706757931334205e-05, + "loss": 0.4862, + "step": 7903 + }, + { + "epoch": 0.64, + "learning_rate": 1.5706214689265536e-05, + "loss": 0.383, + "step": 7904 + }, + { + "epoch": 0.64, + "learning_rate": 1.5705671447196874e-05, + "loss": 0.5507, + "step": 7905 + }, + { + "epoch": 0.64, + "learning_rate": 1.5705128205128205e-05, + "loss": 0.5314, + "step": 7906 + }, + { + "epoch": 0.64, + "learning_rate": 1.5704584963059542e-05, + "loss": 0.2927, + "step": 7907 + }, + { + "epoch": 0.64, + "learning_rate": 1.5704041720990873e-05, + "loss": 0.5336, + "step": 7908 + }, + { + "epoch": 0.64, + "learning_rate": 1.570349847892221e-05, + "loss": 0.5845, + "step": 7909 + }, + { + "epoch": 0.64, + "learning_rate": 1.570295523685354e-05, + "loss": 0.2811, + "step": 7910 + }, + { + "epoch": 0.64, + "learning_rate": 1.5702411994784876e-05, + "loss": 0.6838, + "step": 7911 + }, + { + "epoch": 0.64, + "learning_rate": 1.570186875271621e-05, + "loss": 0.5023, + "step": 7912 + }, + { + "epoch": 0.64, + "learning_rate": 1.5701325510647544e-05, + "loss": 0.4013, + "step": 7913 + }, + { + "epoch": 0.64, + "learning_rate": 1.570078226857888e-05, + "loss": 0.3418, + "step": 7914 + }, + { + "epoch": 0.64, + "learning_rate": 1.5700239026510213e-05, + "loss": 0.6673, + "step": 7915 + }, + { + "epoch": 0.65, + "learning_rate": 1.569969578444155e-05, + "loss": 0.2272, + "step": 7916 + }, + { + "epoch": 0.65, + "learning_rate": 1.569915254237288e-05, + "loss": 0.3956, + "step": 7917 + }, + { + "epoch": 0.65, + "learning_rate": 1.569860930030422e-05, + "loss": 0.5171, + "step": 7918 + }, + { + "epoch": 0.65, + "learning_rate": 1.569806605823555e-05, + "loss": 0.3783, + "step": 7919 + }, + { + "epoch": 0.65, + "learning_rate": 1.5697522816166887e-05, + "loss": 0.2273, + "step": 7920 + }, + { + "epoch": 0.65, + "learning_rate": 1.5696979574098218e-05, + "loss": 0.4791, + "step": 7921 + }, + { + "epoch": 0.65, + "learning_rate": 1.5696436332029556e-05, + "loss": 0.385, + "step": 7922 + }, + { + "epoch": 0.65, + "learning_rate": 1.5695893089960887e-05, + "loss": 0.4486, + "step": 7923 + }, + { + "epoch": 0.65, + "learning_rate": 1.5695349847892224e-05, + "loss": 0.3755, + "step": 7924 + }, + { + "epoch": 0.65, + "learning_rate": 1.5694806605823555e-05, + "loss": 0.4163, + "step": 7925 + }, + { + "epoch": 0.65, + "learning_rate": 1.5694263363754893e-05, + "loss": 0.5259, + "step": 7926 + }, + { + "epoch": 0.65, + "learning_rate": 1.5693720121686224e-05, + "loss": 0.4637, + "step": 7927 + }, + { + "epoch": 0.65, + "learning_rate": 1.569317687961756e-05, + "loss": 0.6282, + "step": 7928 + }, + { + "epoch": 0.65, + "learning_rate": 1.5692633637548892e-05, + "loss": 0.616, + "step": 7929 + }, + { + "epoch": 0.65, + "learning_rate": 1.5692090395480226e-05, + "loss": 0.4082, + "step": 7930 + }, + { + "epoch": 0.65, + "learning_rate": 1.569154715341156e-05, + "loss": 0.5311, + "step": 7931 + }, + { + "epoch": 0.65, + "learning_rate": 1.5691003911342895e-05, + "loss": 0.4474, + "step": 7932 + }, + { + "epoch": 0.65, + "learning_rate": 1.569046066927423e-05, + "loss": 0.3175, + "step": 7933 + }, + { + "epoch": 0.65, + "learning_rate": 1.5689917427205563e-05, + "loss": 0.4018, + "step": 7934 + }, + { + "epoch": 0.65, + "learning_rate": 1.5689374185136897e-05, + "loss": 0.2754, + "step": 7935 + }, + { + "epoch": 0.65, + "learning_rate": 1.568883094306823e-05, + "loss": 0.423, + "step": 7936 + }, + { + "epoch": 0.65, + "learning_rate": 1.5688287700999566e-05, + "loss": 0.7064, + "step": 7937 + }, + { + "epoch": 0.65, + "learning_rate": 1.56877444589309e-05, + "loss": 0.4231, + "step": 7938 + }, + { + "epoch": 0.65, + "learning_rate": 1.5687201216862234e-05, + "loss": 0.4908, + "step": 7939 + }, + { + "epoch": 0.65, + "learning_rate": 1.568665797479357e-05, + "loss": 0.3206, + "step": 7940 + }, + { + "epoch": 0.65, + "learning_rate": 1.5686114732724903e-05, + "loss": 0.6324, + "step": 7941 + }, + { + "epoch": 0.65, + "learning_rate": 1.5685571490656237e-05, + "loss": 0.3684, + "step": 7942 + }, + { + "epoch": 0.65, + "learning_rate": 1.568502824858757e-05, + "loss": 0.3692, + "step": 7943 + }, + { + "epoch": 0.65, + "learning_rate": 1.5684485006518905e-05, + "loss": 0.2432, + "step": 7944 + }, + { + "epoch": 0.65, + "learning_rate": 1.568394176445024e-05, + "loss": 0.4115, + "step": 7945 + }, + { + "epoch": 0.65, + "learning_rate": 1.5683398522381574e-05, + "loss": 0.5287, + "step": 7946 + }, + { + "epoch": 0.65, + "learning_rate": 1.5682855280312908e-05, + "loss": 0.6684, + "step": 7947 + }, + { + "epoch": 0.65, + "learning_rate": 1.5682312038244242e-05, + "loss": 0.6268, + "step": 7948 + }, + { + "epoch": 0.65, + "learning_rate": 1.5681768796175577e-05, + "loss": 0.2379, + "step": 7949 + }, + { + "epoch": 0.65, + "learning_rate": 1.568122555410691e-05, + "loss": 0.3651, + "step": 7950 + }, + { + "epoch": 0.65, + "learning_rate": 1.5680682312038245e-05, + "loss": 0.6518, + "step": 7951 + }, + { + "epoch": 0.65, + "learning_rate": 1.568013906996958e-05, + "loss": 0.4639, + "step": 7952 + }, + { + "epoch": 0.65, + "learning_rate": 1.5679595827900914e-05, + "loss": 0.4911, + "step": 7953 + }, + { + "epoch": 0.65, + "learning_rate": 1.5679052585832248e-05, + "loss": 0.262, + "step": 7954 + }, + { + "epoch": 0.65, + "learning_rate": 1.5678509343763582e-05, + "loss": 0.6441, + "step": 7955 + }, + { + "epoch": 0.65, + "learning_rate": 1.5677966101694916e-05, + "loss": 0.7069, + "step": 7956 + }, + { + "epoch": 0.65, + "learning_rate": 1.567742285962625e-05, + "loss": 0.587, + "step": 7957 + }, + { + "epoch": 0.65, + "learning_rate": 1.5676879617557585e-05, + "loss": 0.5997, + "step": 7958 + }, + { + "epoch": 0.65, + "learning_rate": 1.567633637548892e-05, + "loss": 0.2681, + "step": 7959 + }, + { + "epoch": 0.65, + "learning_rate": 1.5675793133420253e-05, + "loss": 0.7219, + "step": 7960 + }, + { + "epoch": 0.65, + "learning_rate": 1.5675249891351587e-05, + "loss": 0.5215, + "step": 7961 + }, + { + "epoch": 0.65, + "learning_rate": 1.567470664928292e-05, + "loss": 0.6181, + "step": 7962 + }, + { + "epoch": 0.65, + "learning_rate": 1.5674163407214256e-05, + "loss": 0.485, + "step": 7963 + }, + { + "epoch": 0.65, + "learning_rate": 1.567362016514559e-05, + "loss": 0.441, + "step": 7964 + }, + { + "epoch": 0.65, + "learning_rate": 1.5673076923076924e-05, + "loss": 0.3804, + "step": 7965 + }, + { + "epoch": 0.65, + "learning_rate": 1.567253368100826e-05, + "loss": 0.3351, + "step": 7966 + }, + { + "epoch": 0.65, + "learning_rate": 1.5671990438939593e-05, + "loss": 0.4113, + "step": 7967 + }, + { + "epoch": 0.65, + "learning_rate": 1.5671447196870927e-05, + "loss": 0.4114, + "step": 7968 + }, + { + "epoch": 0.65, + "learning_rate": 1.567090395480226e-05, + "loss": 0.1424, + "step": 7969 + }, + { + "epoch": 0.65, + "learning_rate": 1.5670360712733595e-05, + "loss": 0.2918, + "step": 7970 + }, + { + "epoch": 0.65, + "learning_rate": 1.566981747066493e-05, + "loss": 0.6351, + "step": 7971 + }, + { + "epoch": 0.65, + "learning_rate": 1.5669274228596264e-05, + "loss": 0.6939, + "step": 7972 + }, + { + "epoch": 0.65, + "learning_rate": 1.5668730986527598e-05, + "loss": 0.3297, + "step": 7973 + }, + { + "epoch": 0.65, + "learning_rate": 1.5668187744458932e-05, + "loss": 0.5335, + "step": 7974 + }, + { + "epoch": 0.65, + "learning_rate": 1.5667644502390267e-05, + "loss": 0.6904, + "step": 7975 + }, + { + "epoch": 0.65, + "learning_rate": 1.56671012603216e-05, + "loss": 0.3112, + "step": 7976 + }, + { + "epoch": 0.65, + "learning_rate": 1.5666558018252935e-05, + "loss": 0.5653, + "step": 7977 + }, + { + "epoch": 0.65, + "learning_rate": 1.566601477618427e-05, + "loss": 0.6341, + "step": 7978 + }, + { + "epoch": 0.65, + "learning_rate": 1.5665471534115604e-05, + "loss": 0.9413, + "step": 7979 + }, + { + "epoch": 0.65, + "learning_rate": 1.5664928292046938e-05, + "loss": 0.266, + "step": 7980 + }, + { + "epoch": 0.65, + "learning_rate": 1.5664385049978272e-05, + "loss": 0.3989, + "step": 7981 + }, + { + "epoch": 0.65, + "learning_rate": 1.5663841807909606e-05, + "loss": 0.344, + "step": 7982 + }, + { + "epoch": 0.65, + "learning_rate": 1.566329856584094e-05, + "loss": 0.6609, + "step": 7983 + }, + { + "epoch": 0.65, + "learning_rate": 1.5662755323772275e-05, + "loss": 0.4538, + "step": 7984 + }, + { + "epoch": 0.65, + "learning_rate": 1.566221208170361e-05, + "loss": 0.6388, + "step": 7985 + }, + { + "epoch": 0.65, + "learning_rate": 1.5661668839634943e-05, + "loss": 0.489, + "step": 7986 + }, + { + "epoch": 0.65, + "learning_rate": 1.5661125597566277e-05, + "loss": 0.4505, + "step": 7987 + }, + { + "epoch": 0.65, + "learning_rate": 1.566058235549761e-05, + "loss": 0.6249, + "step": 7988 + }, + { + "epoch": 0.65, + "learning_rate": 1.5660039113428946e-05, + "loss": 0.382, + "step": 7989 + }, + { + "epoch": 0.65, + "learning_rate": 1.565949587136028e-05, + "loss": 0.5026, + "step": 7990 + }, + { + "epoch": 0.65, + "learning_rate": 1.5658952629291614e-05, + "loss": 0.4595, + "step": 7991 + }, + { + "epoch": 0.65, + "learning_rate": 1.565840938722295e-05, + "loss": 0.5675, + "step": 7992 + }, + { + "epoch": 0.65, + "learning_rate": 1.5657866145154283e-05, + "loss": 0.5116, + "step": 7993 + }, + { + "epoch": 0.65, + "learning_rate": 1.5657322903085617e-05, + "loss": 0.7347, + "step": 7994 + }, + { + "epoch": 0.65, + "learning_rate": 1.565677966101695e-05, + "loss": 0.3081, + "step": 7995 + }, + { + "epoch": 0.65, + "learning_rate": 1.5656236418948285e-05, + "loss": 0.3425, + "step": 7996 + }, + { + "epoch": 0.65, + "learning_rate": 1.565569317687962e-05, + "loss": 0.4564, + "step": 7997 + }, + { + "epoch": 0.65, + "learning_rate": 1.5655149934810954e-05, + "loss": 0.4014, + "step": 7998 + }, + { + "epoch": 0.65, + "learning_rate": 1.5654606692742288e-05, + "loss": 0.4138, + "step": 7999 + }, + { + "epoch": 0.65, + "learning_rate": 1.5654063450673622e-05, + "loss": 0.5938, + "step": 8000 + }, + { + "epoch": 0.65, + "eval_accuracy": 0.8272032603158431, + "eval_loss": 0.44935375452041626, + "eval_runtime": 22.1658, + "eval_samples_per_second": 442.8, + "eval_steps_per_second": 3.474, + "step": 8000 + }, + { + "epoch": 0.65, + "learning_rate": 1.5653520208604957e-05, + "loss": 0.4753, + "step": 8001 + }, + { + "epoch": 0.65, + "learning_rate": 1.565297696653629e-05, + "loss": 0.3095, + "step": 8002 + }, + { + "epoch": 0.65, + "learning_rate": 1.5652433724467625e-05, + "loss": 0.3046, + "step": 8003 + }, + { + "epoch": 0.65, + "learning_rate": 1.565189048239896e-05, + "loss": 0.5147, + "step": 8004 + }, + { + "epoch": 0.65, + "learning_rate": 1.5651347240330294e-05, + "loss": 0.4994, + "step": 8005 + }, + { + "epoch": 0.65, + "learning_rate": 1.5650803998261624e-05, + "loss": 0.6287, + "step": 8006 + }, + { + "epoch": 0.65, + "learning_rate": 1.5650260756192962e-05, + "loss": 0.5855, + "step": 8007 + }, + { + "epoch": 0.65, + "learning_rate": 1.5649717514124293e-05, + "loss": 0.503, + "step": 8008 + }, + { + "epoch": 0.65, + "learning_rate": 1.564917427205563e-05, + "loss": 0.67, + "step": 8009 + }, + { + "epoch": 0.65, + "learning_rate": 1.564863102998696e-05, + "loss": 0.3503, + "step": 8010 + }, + { + "epoch": 0.65, + "learning_rate": 1.56480877879183e-05, + "loss": 0.4002, + "step": 8011 + }, + { + "epoch": 0.65, + "learning_rate": 1.564754454584963e-05, + "loss": 0.435, + "step": 8012 + }, + { + "epoch": 0.65, + "learning_rate": 1.5647001303780967e-05, + "loss": 0.3989, + "step": 8013 + }, + { + "epoch": 0.65, + "learning_rate": 1.5646458061712298e-05, + "loss": 0.4631, + "step": 8014 + }, + { + "epoch": 0.65, + "learning_rate": 1.5645914819643636e-05, + "loss": 0.3629, + "step": 8015 + }, + { + "epoch": 0.65, + "learning_rate": 1.5645371577574967e-05, + "loss": 0.4752, + "step": 8016 + }, + { + "epoch": 0.65, + "learning_rate": 1.5644828335506304e-05, + "loss": 0.3627, + "step": 8017 + }, + { + "epoch": 0.65, + "learning_rate": 1.5644285093437635e-05, + "loss": 0.3903, + "step": 8018 + }, + { + "epoch": 0.65, + "learning_rate": 1.5643741851368973e-05, + "loss": 0.3924, + "step": 8019 + }, + { + "epoch": 0.65, + "learning_rate": 1.5643198609300304e-05, + "loss": 0.4299, + "step": 8020 + }, + { + "epoch": 0.65, + "learning_rate": 1.564265536723164e-05, + "loss": 0.521, + "step": 8021 + }, + { + "epoch": 0.65, + "learning_rate": 1.5642112125162972e-05, + "loss": 0.6083, + "step": 8022 + }, + { + "epoch": 0.65, + "learning_rate": 1.564156888309431e-05, + "loss": 0.3263, + "step": 8023 + }, + { + "epoch": 0.65, + "learning_rate": 1.5641025641025644e-05, + "loss": 0.2253, + "step": 8024 + }, + { + "epoch": 0.65, + "learning_rate": 1.5640482398956975e-05, + "loss": 0.2385, + "step": 8025 + }, + { + "epoch": 0.65, + "learning_rate": 1.5639939156888312e-05, + "loss": 0.5451, + "step": 8026 + }, + { + "epoch": 0.65, + "learning_rate": 1.5639395914819643e-05, + "loss": 0.359, + "step": 8027 + }, + { + "epoch": 0.65, + "learning_rate": 1.563885267275098e-05, + "loss": 0.4353, + "step": 8028 + }, + { + "epoch": 0.65, + "learning_rate": 1.563830943068231e-05, + "loss": 0.5641, + "step": 8029 + }, + { + "epoch": 0.65, + "learning_rate": 1.563776618861365e-05, + "loss": 0.4158, + "step": 8030 + }, + { + "epoch": 0.65, + "learning_rate": 1.563722294654498e-05, + "loss": 0.4033, + "step": 8031 + }, + { + "epoch": 0.65, + "learning_rate": 1.5636679704476318e-05, + "loss": 0.7394, + "step": 8032 + }, + { + "epoch": 0.65, + "learning_rate": 1.563613646240765e-05, + "loss": 0.4502, + "step": 8033 + }, + { + "epoch": 0.65, + "learning_rate": 1.5635593220338986e-05, + "loss": 0.5166, + "step": 8034 + }, + { + "epoch": 0.65, + "learning_rate": 1.5635049978270317e-05, + "loss": 0.3282, + "step": 8035 + }, + { + "epoch": 0.65, + "learning_rate": 1.5634506736201655e-05, + "loss": 0.5974, + "step": 8036 + }, + { + "epoch": 0.65, + "learning_rate": 1.5633963494132986e-05, + "loss": 0.4488, + "step": 8037 + }, + { + "epoch": 0.65, + "learning_rate": 1.5633420252064323e-05, + "loss": 0.5776, + "step": 8038 + }, + { + "epoch": 0.66, + "learning_rate": 1.5632877009995654e-05, + "loss": 0.4568, + "step": 8039 + }, + { + "epoch": 0.66, + "learning_rate": 1.563233376792699e-05, + "loss": 0.4878, + "step": 8040 + }, + { + "epoch": 0.66, + "learning_rate": 1.5631790525858322e-05, + "loss": 0.7517, + "step": 8041 + }, + { + "epoch": 0.66, + "learning_rate": 1.563124728378966e-05, + "loss": 0.3527, + "step": 8042 + }, + { + "epoch": 0.66, + "learning_rate": 1.563070404172099e-05, + "loss": 0.4654, + "step": 8043 + }, + { + "epoch": 0.66, + "learning_rate": 1.5630160799652325e-05, + "loss": 0.4325, + "step": 8044 + }, + { + "epoch": 0.66, + "learning_rate": 1.562961755758366e-05, + "loss": 0.3842, + "step": 8045 + }, + { + "epoch": 0.66, + "learning_rate": 1.5629074315514994e-05, + "loss": 0.3908, + "step": 8046 + }, + { + "epoch": 0.66, + "learning_rate": 1.5628531073446328e-05, + "loss": 0.3983, + "step": 8047 + }, + { + "epoch": 0.66, + "learning_rate": 1.5627987831377662e-05, + "loss": 0.5631, + "step": 8048 + }, + { + "epoch": 0.66, + "learning_rate": 1.5627444589308996e-05, + "loss": 0.3722, + "step": 8049 + }, + { + "epoch": 0.66, + "learning_rate": 1.562690134724033e-05, + "loss": 0.5076, + "step": 8050 + }, + { + "epoch": 0.66, + "learning_rate": 1.5626358105171665e-05, + "loss": 0.3753, + "step": 8051 + }, + { + "epoch": 0.66, + "learning_rate": 1.5625814863103e-05, + "loss": 0.285, + "step": 8052 + }, + { + "epoch": 0.66, + "learning_rate": 1.5625271621034333e-05, + "loss": 0.5588, + "step": 8053 + }, + { + "epoch": 0.66, + "learning_rate": 1.5624728378965667e-05, + "loss": 0.3778, + "step": 8054 + }, + { + "epoch": 0.66, + "learning_rate": 1.5624185136897e-05, + "loss": 0.5926, + "step": 8055 + }, + { + "epoch": 0.66, + "learning_rate": 1.5623641894828336e-05, + "loss": 0.2609, + "step": 8056 + }, + { + "epoch": 0.66, + "learning_rate": 1.562309865275967e-05, + "loss": 0.8032, + "step": 8057 + }, + { + "epoch": 0.66, + "learning_rate": 1.5622555410691004e-05, + "loss": 0.2566, + "step": 8058 + }, + { + "epoch": 0.66, + "learning_rate": 1.562201216862234e-05, + "loss": 0.4308, + "step": 8059 + }, + { + "epoch": 0.66, + "learning_rate": 1.5621468926553673e-05, + "loss": 0.5523, + "step": 8060 + }, + { + "epoch": 0.66, + "learning_rate": 1.562092568448501e-05, + "loss": 0.2297, + "step": 8061 + }, + { + "epoch": 0.66, + "learning_rate": 1.562038244241634e-05, + "loss": 0.3673, + "step": 8062 + }, + { + "epoch": 0.66, + "learning_rate": 1.561983920034768e-05, + "loss": 0.3938, + "step": 8063 + }, + { + "epoch": 0.66, + "learning_rate": 1.561929595827901e-05, + "loss": 0.6759, + "step": 8064 + }, + { + "epoch": 0.66, + "learning_rate": 1.5618752716210344e-05, + "loss": 0.3819, + "step": 8065 + }, + { + "epoch": 0.66, + "learning_rate": 1.5618209474141678e-05, + "loss": 0.3574, + "step": 8066 + }, + { + "epoch": 0.66, + "learning_rate": 1.5617666232073012e-05, + "loss": 0.4102, + "step": 8067 + }, + { + "epoch": 0.66, + "learning_rate": 1.5617122990004347e-05, + "loss": 0.5374, + "step": 8068 + }, + { + "epoch": 0.66, + "learning_rate": 1.561657974793568e-05, + "loss": 0.5311, + "step": 8069 + }, + { + "epoch": 0.66, + "learning_rate": 1.5616036505867015e-05, + "loss": 0.4625, + "step": 8070 + }, + { + "epoch": 0.66, + "learning_rate": 1.561549326379835e-05, + "loss": 0.5249, + "step": 8071 + }, + { + "epoch": 0.66, + "learning_rate": 1.5614950021729684e-05, + "loss": 0.7537, + "step": 8072 + }, + { + "epoch": 0.66, + "learning_rate": 1.5614406779661018e-05, + "loss": 0.4456, + "step": 8073 + }, + { + "epoch": 0.66, + "learning_rate": 1.5613863537592352e-05, + "loss": 0.3494, + "step": 8074 + }, + { + "epoch": 0.66, + "learning_rate": 1.5613320295523686e-05, + "loss": 0.6223, + "step": 8075 + }, + { + "epoch": 0.66, + "learning_rate": 1.561277705345502e-05, + "loss": 0.4257, + "step": 8076 + }, + { + "epoch": 0.66, + "learning_rate": 1.5612233811386355e-05, + "loss": 0.3628, + "step": 8077 + }, + { + "epoch": 0.66, + "learning_rate": 1.561169056931769e-05, + "loss": 0.7922, + "step": 8078 + }, + { + "epoch": 0.66, + "learning_rate": 1.5611147327249023e-05, + "loss": 0.5956, + "step": 8079 + }, + { + "epoch": 0.66, + "learning_rate": 1.5610604085180357e-05, + "loss": 0.5139, + "step": 8080 + }, + { + "epoch": 0.66, + "learning_rate": 1.561006084311169e-05, + "loss": 0.3384, + "step": 8081 + }, + { + "epoch": 0.66, + "learning_rate": 1.5609517601043026e-05, + "loss": 0.4777, + "step": 8082 + }, + { + "epoch": 0.66, + "learning_rate": 1.560897435897436e-05, + "loss": 0.5376, + "step": 8083 + }, + { + "epoch": 0.66, + "learning_rate": 1.5608431116905694e-05, + "loss": 0.4627, + "step": 8084 + }, + { + "epoch": 0.66, + "learning_rate": 1.560788787483703e-05, + "loss": 0.5119, + "step": 8085 + }, + { + "epoch": 0.66, + "learning_rate": 1.5607344632768363e-05, + "loss": 0.764, + "step": 8086 + }, + { + "epoch": 0.66, + "learning_rate": 1.5606801390699697e-05, + "loss": 0.798, + "step": 8087 + }, + { + "epoch": 0.66, + "learning_rate": 1.560625814863103e-05, + "loss": 0.4552, + "step": 8088 + }, + { + "epoch": 0.66, + "learning_rate": 1.5605714906562366e-05, + "loss": 0.6016, + "step": 8089 + }, + { + "epoch": 0.66, + "learning_rate": 1.56051716644937e-05, + "loss": 0.3682, + "step": 8090 + }, + { + "epoch": 0.66, + "learning_rate": 1.5604628422425034e-05, + "loss": 0.7646, + "step": 8091 + }, + { + "epoch": 0.66, + "learning_rate": 1.5604085180356368e-05, + "loss": 0.3229, + "step": 8092 + }, + { + "epoch": 0.66, + "learning_rate": 1.5603541938287702e-05, + "loss": 0.5982, + "step": 8093 + }, + { + "epoch": 0.66, + "learning_rate": 1.5602998696219037e-05, + "loss": 0.4042, + "step": 8094 + }, + { + "epoch": 0.66, + "learning_rate": 1.560245545415037e-05, + "loss": 0.5836, + "step": 8095 + }, + { + "epoch": 0.66, + "learning_rate": 1.5601912212081705e-05, + "loss": 0.5337, + "step": 8096 + }, + { + "epoch": 0.66, + "learning_rate": 1.560136897001304e-05, + "loss": 0.3905, + "step": 8097 + }, + { + "epoch": 0.66, + "learning_rate": 1.5600825727944374e-05, + "loss": 0.5296, + "step": 8098 + }, + { + "epoch": 0.66, + "learning_rate": 1.5600282485875708e-05, + "loss": 0.3326, + "step": 8099 + }, + { + "epoch": 0.66, + "learning_rate": 1.5599739243807042e-05, + "loss": 0.7542, + "step": 8100 + }, + { + "epoch": 0.66, + "learning_rate": 1.5599196001738376e-05, + "loss": 0.4167, + "step": 8101 + }, + { + "epoch": 0.66, + "learning_rate": 1.559865275966971e-05, + "loss": 0.3953, + "step": 8102 + }, + { + "epoch": 0.66, + "learning_rate": 1.5598109517601045e-05, + "loss": 0.6299, + "step": 8103 + }, + { + "epoch": 0.66, + "learning_rate": 1.559756627553238e-05, + "loss": 0.4919, + "step": 8104 + }, + { + "epoch": 0.66, + "learning_rate": 1.5597023033463713e-05, + "loss": 0.3628, + "step": 8105 + }, + { + "epoch": 0.66, + "learning_rate": 1.5596479791395047e-05, + "loss": 0.4797, + "step": 8106 + }, + { + "epoch": 0.66, + "learning_rate": 1.559593654932638e-05, + "loss": 0.4882, + "step": 8107 + }, + { + "epoch": 0.66, + "learning_rate": 1.5595393307257716e-05, + "loss": 0.52, + "step": 8108 + }, + { + "epoch": 0.66, + "learning_rate": 1.559485006518905e-05, + "loss": 0.4452, + "step": 8109 + }, + { + "epoch": 0.66, + "learning_rate": 1.5594306823120384e-05, + "loss": 0.3415, + "step": 8110 + }, + { + "epoch": 0.66, + "learning_rate": 1.559376358105172e-05, + "loss": 0.4882, + "step": 8111 + }, + { + "epoch": 0.66, + "learning_rate": 1.5593220338983053e-05, + "loss": 0.6238, + "step": 8112 + }, + { + "epoch": 0.66, + "learning_rate": 1.5592677096914387e-05, + "loss": 0.3927, + "step": 8113 + }, + { + "epoch": 0.66, + "learning_rate": 1.559213385484572e-05, + "loss": 0.3986, + "step": 8114 + }, + { + "epoch": 0.66, + "learning_rate": 1.5591590612777056e-05, + "loss": 0.3393, + "step": 8115 + }, + { + "epoch": 0.66, + "learning_rate": 1.559104737070839e-05, + "loss": 0.5374, + "step": 8116 + }, + { + "epoch": 0.66, + "learning_rate": 1.5590504128639724e-05, + "loss": 0.5139, + "step": 8117 + }, + { + "epoch": 0.66, + "learning_rate": 1.5589960886571058e-05, + "loss": 0.4965, + "step": 8118 + }, + { + "epoch": 0.66, + "learning_rate": 1.5589417644502392e-05, + "loss": 0.5075, + "step": 8119 + }, + { + "epoch": 0.66, + "learning_rate": 1.5588874402433727e-05, + "loss": 0.3989, + "step": 8120 + }, + { + "epoch": 0.66, + "learning_rate": 1.558833116036506e-05, + "loss": 0.2697, + "step": 8121 + }, + { + "epoch": 0.66, + "learning_rate": 1.5587787918296392e-05, + "loss": 0.389, + "step": 8122 + }, + { + "epoch": 0.66, + "learning_rate": 1.558724467622773e-05, + "loss": 0.4532, + "step": 8123 + }, + { + "epoch": 0.66, + "learning_rate": 1.558670143415906e-05, + "loss": 0.3453, + "step": 8124 + }, + { + "epoch": 0.66, + "learning_rate": 1.5586158192090398e-05, + "loss": 0.6129, + "step": 8125 + }, + { + "epoch": 0.66, + "learning_rate": 1.558561495002173e-05, + "loss": 0.6152, + "step": 8126 + }, + { + "epoch": 0.66, + "learning_rate": 1.5585071707953066e-05, + "loss": 0.3749, + "step": 8127 + }, + { + "epoch": 0.66, + "learning_rate": 1.5584528465884397e-05, + "loss": 0.4702, + "step": 8128 + }, + { + "epoch": 0.66, + "learning_rate": 1.5583985223815735e-05, + "loss": 0.4652, + "step": 8129 + }, + { + "epoch": 0.66, + "learning_rate": 1.5583441981747066e-05, + "loss": 0.3811, + "step": 8130 + }, + { + "epoch": 0.66, + "learning_rate": 1.5582898739678403e-05, + "loss": 0.3266, + "step": 8131 + }, + { + "epoch": 0.66, + "learning_rate": 1.5582355497609737e-05, + "loss": 0.5629, + "step": 8132 + }, + { + "epoch": 0.66, + "learning_rate": 1.558181225554107e-05, + "loss": 0.4592, + "step": 8133 + }, + { + "epoch": 0.66, + "learning_rate": 1.5581269013472406e-05, + "loss": 0.6977, + "step": 8134 + }, + { + "epoch": 0.66, + "learning_rate": 1.558072577140374e-05, + "loss": 0.4777, + "step": 8135 + }, + { + "epoch": 0.66, + "learning_rate": 1.5580182529335074e-05, + "loss": 0.4054, + "step": 8136 + }, + { + "epoch": 0.66, + "learning_rate": 1.557963928726641e-05, + "loss": 0.4839, + "step": 8137 + }, + { + "epoch": 0.66, + "learning_rate": 1.5579096045197743e-05, + "loss": 0.6496, + "step": 8138 + }, + { + "epoch": 0.66, + "learning_rate": 1.5578552803129077e-05, + "loss": 0.5546, + "step": 8139 + }, + { + "epoch": 0.66, + "learning_rate": 1.557800956106041e-05, + "loss": 0.3229, + "step": 8140 + }, + { + "epoch": 0.66, + "learning_rate": 1.5577466318991742e-05, + "loss": 0.4086, + "step": 8141 + }, + { + "epoch": 0.66, + "learning_rate": 1.557692307692308e-05, + "loss": 0.7671, + "step": 8142 + }, + { + "epoch": 0.66, + "learning_rate": 1.557637983485441e-05, + "loss": 0.8395, + "step": 8143 + }, + { + "epoch": 0.66, + "learning_rate": 1.5575836592785748e-05, + "loss": 0.2751, + "step": 8144 + }, + { + "epoch": 0.66, + "learning_rate": 1.557529335071708e-05, + "loss": 0.7151, + "step": 8145 + }, + { + "epoch": 0.66, + "learning_rate": 1.5574750108648417e-05, + "loss": 0.4777, + "step": 8146 + }, + { + "epoch": 0.66, + "learning_rate": 1.5574206866579747e-05, + "loss": 0.4355, + "step": 8147 + }, + { + "epoch": 0.66, + "learning_rate": 1.5573663624511085e-05, + "loss": 0.8805, + "step": 8148 + }, + { + "epoch": 0.66, + "learning_rate": 1.5573120382442416e-05, + "loss": 0.6655, + "step": 8149 + }, + { + "epoch": 0.66, + "learning_rate": 1.5572577140373754e-05, + "loss": 0.2569, + "step": 8150 + }, + { + "epoch": 0.66, + "learning_rate": 1.5572033898305084e-05, + "loss": 0.6589, + "step": 8151 + }, + { + "epoch": 0.66, + "learning_rate": 1.5571490656236422e-05, + "loss": 0.2823, + "step": 8152 + }, + { + "epoch": 0.66, + "learning_rate": 1.5570947414167753e-05, + "loss": 0.6351, + "step": 8153 + }, + { + "epoch": 0.66, + "learning_rate": 1.557040417209909e-05, + "loss": 0.533, + "step": 8154 + }, + { + "epoch": 0.66, + "learning_rate": 1.556986093003042e-05, + "loss": 0.7997, + "step": 8155 + }, + { + "epoch": 0.66, + "learning_rate": 1.556931768796176e-05, + "loss": 0.4919, + "step": 8156 + }, + { + "epoch": 0.66, + "learning_rate": 1.556877444589309e-05, + "loss": 0.4933, + "step": 8157 + }, + { + "epoch": 0.66, + "learning_rate": 1.5568231203824427e-05, + "loss": 0.4635, + "step": 8158 + }, + { + "epoch": 0.66, + "learning_rate": 1.5567687961755758e-05, + "loss": 0.5462, + "step": 8159 + }, + { + "epoch": 0.66, + "learning_rate": 1.5567144719687092e-05, + "loss": 0.4233, + "step": 8160 + }, + { + "epoch": 0.67, + "learning_rate": 1.5566601477618427e-05, + "loss": 0.3783, + "step": 8161 + }, + { + "epoch": 0.67, + "learning_rate": 1.556605823554976e-05, + "loss": 0.4157, + "step": 8162 + }, + { + "epoch": 0.67, + "learning_rate": 1.5565514993481095e-05, + "loss": 0.2531, + "step": 8163 + }, + { + "epoch": 0.67, + "learning_rate": 1.556497175141243e-05, + "loss": 0.5667, + "step": 8164 + }, + { + "epoch": 0.67, + "learning_rate": 1.5564428509343764e-05, + "loss": 0.5532, + "step": 8165 + }, + { + "epoch": 0.67, + "learning_rate": 1.5563885267275098e-05, + "loss": 0.8476, + "step": 8166 + }, + { + "epoch": 0.67, + "learning_rate": 1.5563342025206432e-05, + "loss": 0.2906, + "step": 8167 + }, + { + "epoch": 0.67, + "learning_rate": 1.5562798783137766e-05, + "loss": 0.5388, + "step": 8168 + }, + { + "epoch": 0.67, + "learning_rate": 1.5562255541069104e-05, + "loss": 0.6284, + "step": 8169 + }, + { + "epoch": 0.67, + "learning_rate": 1.5561712299000435e-05, + "loss": 0.6996, + "step": 8170 + }, + { + "epoch": 0.67, + "learning_rate": 1.5561169056931772e-05, + "loss": 0.6287, + "step": 8171 + }, + { + "epoch": 0.67, + "learning_rate": 1.5560625814863103e-05, + "loss": 0.4693, + "step": 8172 + }, + { + "epoch": 0.67, + "learning_rate": 1.556008257279444e-05, + "loss": 0.3282, + "step": 8173 + }, + { + "epoch": 0.67, + "learning_rate": 1.5559539330725772e-05, + "loss": 0.4151, + "step": 8174 + }, + { + "epoch": 0.67, + "learning_rate": 1.555899608865711e-05, + "loss": 0.7185, + "step": 8175 + }, + { + "epoch": 0.67, + "learning_rate": 1.555845284658844e-05, + "loss": 0.2864, + "step": 8176 + }, + { + "epoch": 0.67, + "learning_rate": 1.5557909604519778e-05, + "loss": 0.3373, + "step": 8177 + }, + { + "epoch": 0.67, + "learning_rate": 1.555736636245111e-05, + "loss": 0.476, + "step": 8178 + }, + { + "epoch": 0.67, + "learning_rate": 1.5556823120382443e-05, + "loss": 0.3199, + "step": 8179 + }, + { + "epoch": 0.67, + "learning_rate": 1.5556279878313777e-05, + "loss": 0.4781, + "step": 8180 + }, + { + "epoch": 0.67, + "learning_rate": 1.555573663624511e-05, + "loss": 0.7441, + "step": 8181 + }, + { + "epoch": 0.67, + "learning_rate": 1.5555193394176446e-05, + "loss": 0.4248, + "step": 8182 + }, + { + "epoch": 0.67, + "learning_rate": 1.555465015210778e-05, + "loss": 0.4931, + "step": 8183 + }, + { + "epoch": 0.67, + "learning_rate": 1.5554106910039114e-05, + "loss": 0.2675, + "step": 8184 + }, + { + "epoch": 0.67, + "learning_rate": 1.5553563667970448e-05, + "loss": 0.7531, + "step": 8185 + }, + { + "epoch": 0.67, + "learning_rate": 1.5553020425901782e-05, + "loss": 0.4802, + "step": 8186 + }, + { + "epoch": 0.67, + "learning_rate": 1.5552477183833117e-05, + "loss": 0.5155, + "step": 8187 + }, + { + "epoch": 0.67, + "learning_rate": 1.555193394176445e-05, + "loss": 0.5669, + "step": 8188 + }, + { + "epoch": 0.67, + "learning_rate": 1.5551390699695785e-05, + "loss": 0.1811, + "step": 8189 + }, + { + "epoch": 0.67, + "learning_rate": 1.555084745762712e-05, + "loss": 0.2556, + "step": 8190 + }, + { + "epoch": 0.67, + "learning_rate": 1.5550304215558454e-05, + "loss": 0.5363, + "step": 8191 + }, + { + "epoch": 0.67, + "learning_rate": 1.5549760973489788e-05, + "loss": 0.3707, + "step": 8192 + }, + { + "epoch": 0.67, + "learning_rate": 1.5549217731421122e-05, + "loss": 0.5251, + "step": 8193 + }, + { + "epoch": 0.67, + "learning_rate": 1.5548674489352456e-05, + "loss": 0.5517, + "step": 8194 + }, + { + "epoch": 0.67, + "learning_rate": 1.554813124728379e-05, + "loss": 0.3294, + "step": 8195 + }, + { + "epoch": 0.67, + "learning_rate": 1.5547588005215125e-05, + "loss": 0.4824, + "step": 8196 + }, + { + "epoch": 0.67, + "learning_rate": 1.554704476314646e-05, + "loss": 0.4967, + "step": 8197 + }, + { + "epoch": 0.67, + "learning_rate": 1.5546501521077793e-05, + "loss": 0.6529, + "step": 8198 + }, + { + "epoch": 0.67, + "learning_rate": 1.5545958279009127e-05, + "loss": 0.2329, + "step": 8199 + }, + { + "epoch": 0.67, + "learning_rate": 1.5545415036940462e-05, + "loss": 0.5846, + "step": 8200 + }, + { + "epoch": 0.67, + "learning_rate": 1.5544871794871796e-05, + "loss": 0.3548, + "step": 8201 + }, + { + "epoch": 0.67, + "learning_rate": 1.554432855280313e-05, + "loss": 0.4776, + "step": 8202 + }, + { + "epoch": 0.67, + "learning_rate": 1.5543785310734464e-05, + "loss": 0.5938, + "step": 8203 + }, + { + "epoch": 0.67, + "learning_rate": 1.55432420686658e-05, + "loss": 0.5029, + "step": 8204 + }, + { + "epoch": 0.67, + "learning_rate": 1.5542698826597133e-05, + "loss": 0.2446, + "step": 8205 + }, + { + "epoch": 0.67, + "learning_rate": 1.5542155584528467e-05, + "loss": 0.6077, + "step": 8206 + }, + { + "epoch": 0.67, + "learning_rate": 1.55416123424598e-05, + "loss": 0.4509, + "step": 8207 + }, + { + "epoch": 0.67, + "learning_rate": 1.5541069100391136e-05, + "loss": 0.596, + "step": 8208 + }, + { + "epoch": 0.67, + "learning_rate": 1.554052585832247e-05, + "loss": 0.3361, + "step": 8209 + }, + { + "epoch": 0.67, + "learning_rate": 1.5539982616253804e-05, + "loss": 0.4404, + "step": 8210 + }, + { + "epoch": 0.67, + "learning_rate": 1.5539439374185138e-05, + "loss": 0.276, + "step": 8211 + }, + { + "epoch": 0.67, + "learning_rate": 1.5538896132116472e-05, + "loss": 0.4581, + "step": 8212 + }, + { + "epoch": 0.67, + "learning_rate": 1.5538352890047807e-05, + "loss": 0.381, + "step": 8213 + }, + { + "epoch": 0.67, + "learning_rate": 1.553780964797914e-05, + "loss": 0.5351, + "step": 8214 + }, + { + "epoch": 0.67, + "learning_rate": 1.5537266405910475e-05, + "loss": 0.4828, + "step": 8215 + }, + { + "epoch": 0.67, + "learning_rate": 1.553672316384181e-05, + "loss": 0.3895, + "step": 8216 + }, + { + "epoch": 0.67, + "learning_rate": 1.5536179921773144e-05, + "loss": 0.5181, + "step": 8217 + }, + { + "epoch": 0.67, + "learning_rate": 1.5535636679704478e-05, + "loss": 0.4445, + "step": 8218 + }, + { + "epoch": 0.67, + "learning_rate": 1.5535093437635812e-05, + "loss": 0.57, + "step": 8219 + }, + { + "epoch": 0.67, + "learning_rate": 1.5534550195567146e-05, + "loss": 0.6851, + "step": 8220 + }, + { + "epoch": 0.67, + "learning_rate": 1.553400695349848e-05, + "loss": 0.276, + "step": 8221 + }, + { + "epoch": 0.67, + "learning_rate": 1.5533463711429815e-05, + "loss": 0.4057, + "step": 8222 + }, + { + "epoch": 0.67, + "learning_rate": 1.553292046936115e-05, + "loss": 0.5304, + "step": 8223 + }, + { + "epoch": 0.67, + "learning_rate": 1.5532377227292483e-05, + "loss": 0.3186, + "step": 8224 + }, + { + "epoch": 0.67, + "learning_rate": 1.5531833985223817e-05, + "loss": 0.5426, + "step": 8225 + }, + { + "epoch": 0.67, + "learning_rate": 1.5531290743155152e-05, + "loss": 0.5604, + "step": 8226 + }, + { + "epoch": 0.67, + "learning_rate": 1.5530747501086486e-05, + "loss": 0.5606, + "step": 8227 + }, + { + "epoch": 0.67, + "learning_rate": 1.553020425901782e-05, + "loss": 0.3461, + "step": 8228 + }, + { + "epoch": 0.67, + "learning_rate": 1.5529661016949154e-05, + "loss": 0.4242, + "step": 8229 + }, + { + "epoch": 0.67, + "learning_rate": 1.552911777488049e-05, + "loss": 0.4055, + "step": 8230 + }, + { + "epoch": 0.67, + "learning_rate": 1.5528574532811823e-05, + "loss": 0.5465, + "step": 8231 + }, + { + "epoch": 0.67, + "learning_rate": 1.5528031290743157e-05, + "loss": 0.5997, + "step": 8232 + }, + { + "epoch": 0.67, + "learning_rate": 1.552748804867449e-05, + "loss": 0.5709, + "step": 8233 + }, + { + "epoch": 0.67, + "learning_rate": 1.5526944806605826e-05, + "loss": 0.4532, + "step": 8234 + }, + { + "epoch": 0.67, + "learning_rate": 1.552640156453716e-05, + "loss": 0.3233, + "step": 8235 + }, + { + "epoch": 0.67, + "learning_rate": 1.552585832246849e-05, + "loss": 0.3725, + "step": 8236 + }, + { + "epoch": 0.67, + "learning_rate": 1.5525315080399828e-05, + "loss": 0.5174, + "step": 8237 + }, + { + "epoch": 0.67, + "learning_rate": 1.552477183833116e-05, + "loss": 0.3915, + "step": 8238 + }, + { + "epoch": 0.67, + "learning_rate": 1.5524228596262497e-05, + "loss": 0.6382, + "step": 8239 + }, + { + "epoch": 0.67, + "learning_rate": 1.552368535419383e-05, + "loss": 0.5871, + "step": 8240 + }, + { + "epoch": 0.67, + "learning_rate": 1.5523142112125165e-05, + "loss": 0.4571, + "step": 8241 + }, + { + "epoch": 0.67, + "learning_rate": 1.55225988700565e-05, + "loss": 0.3872, + "step": 8242 + }, + { + "epoch": 0.67, + "learning_rate": 1.5522055627987834e-05, + "loss": 0.3117, + "step": 8243 + }, + { + "epoch": 0.67, + "learning_rate": 1.5521512385919168e-05, + "loss": 0.6262, + "step": 8244 + }, + { + "epoch": 0.67, + "learning_rate": 1.5520969143850502e-05, + "loss": 0.6402, + "step": 8245 + }, + { + "epoch": 0.67, + "learning_rate": 1.5520425901781836e-05, + "loss": 0.4388, + "step": 8246 + }, + { + "epoch": 0.67, + "learning_rate": 1.551988265971317e-05, + "loss": 0.6323, + "step": 8247 + }, + { + "epoch": 0.67, + "learning_rate": 1.5519339417644505e-05, + "loss": 0.5595, + "step": 8248 + }, + { + "epoch": 0.67, + "learning_rate": 1.551879617557584e-05, + "loss": 0.3812, + "step": 8249 + }, + { + "epoch": 0.67, + "learning_rate": 1.5518252933507173e-05, + "loss": 0.4065, + "step": 8250 + }, + { + "epoch": 0.67, + "eval_accuracy": 0.8281202241467143, + "eval_loss": 0.446122407913208, + "eval_runtime": 22.3137, + "eval_samples_per_second": 439.864, + "eval_steps_per_second": 3.451, + "step": 8250 + }, + { + "epoch": 0.67, + "learning_rate": 1.5517709691438507e-05, + "loss": 0.6851, + "step": 8251 + }, + { + "epoch": 0.67, + "learning_rate": 1.5517166449369842e-05, + "loss": 0.4282, + "step": 8252 + }, + { + "epoch": 0.67, + "learning_rate": 1.5516623207301176e-05, + "loss": 0.4743, + "step": 8253 + }, + { + "epoch": 0.67, + "learning_rate": 1.551607996523251e-05, + "loss": 0.4492, + "step": 8254 + }, + { + "epoch": 0.67, + "learning_rate": 1.551553672316384e-05, + "loss": 0.3369, + "step": 8255 + }, + { + "epoch": 0.67, + "learning_rate": 1.551499348109518e-05, + "loss": 0.3701, + "step": 8256 + }, + { + "epoch": 0.67, + "learning_rate": 1.551445023902651e-05, + "loss": 0.3924, + "step": 8257 + }, + { + "epoch": 0.67, + "learning_rate": 1.5513906996957847e-05, + "loss": 0.32, + "step": 8258 + }, + { + "epoch": 0.67, + "learning_rate": 1.5513363754889178e-05, + "loss": 0.8046, + "step": 8259 + }, + { + "epoch": 0.67, + "learning_rate": 1.5512820512820516e-05, + "loss": 0.6925, + "step": 8260 + }, + { + "epoch": 0.67, + "learning_rate": 1.5512277270751846e-05, + "loss": 0.6196, + "step": 8261 + }, + { + "epoch": 0.67, + "learning_rate": 1.5511734028683184e-05, + "loss": 0.3608, + "step": 8262 + }, + { + "epoch": 0.67, + "learning_rate": 1.5511190786614515e-05, + "loss": 0.7006, + "step": 8263 + }, + { + "epoch": 0.67, + "learning_rate": 1.5510647544545852e-05, + "loss": 0.555, + "step": 8264 + }, + { + "epoch": 0.67, + "learning_rate": 1.5510104302477183e-05, + "loss": 0.3429, + "step": 8265 + }, + { + "epoch": 0.67, + "learning_rate": 1.550956106040852e-05, + "loss": 0.4739, + "step": 8266 + }, + { + "epoch": 0.67, + "learning_rate": 1.5509017818339852e-05, + "loss": 0.3733, + "step": 8267 + }, + { + "epoch": 0.67, + "learning_rate": 1.550847457627119e-05, + "loss": 0.4584, + "step": 8268 + }, + { + "epoch": 0.67, + "learning_rate": 1.550793133420252e-05, + "loss": 0.6001, + "step": 8269 + }, + { + "epoch": 0.67, + "learning_rate": 1.5507388092133858e-05, + "loss": 0.7057, + "step": 8270 + }, + { + "epoch": 0.67, + "learning_rate": 1.550684485006519e-05, + "loss": 0.4673, + "step": 8271 + }, + { + "epoch": 0.67, + "learning_rate": 1.5506301607996526e-05, + "loss": 0.3761, + "step": 8272 + }, + { + "epoch": 0.67, + "learning_rate": 1.5505758365927857e-05, + "loss": 0.6248, + "step": 8273 + }, + { + "epoch": 0.67, + "learning_rate": 1.550521512385919e-05, + "loss": 0.663, + "step": 8274 + }, + { + "epoch": 0.67, + "learning_rate": 1.5504671881790526e-05, + "loss": 0.4621, + "step": 8275 + }, + { + "epoch": 0.67, + "learning_rate": 1.550412863972186e-05, + "loss": 0.5753, + "step": 8276 + }, + { + "epoch": 0.67, + "learning_rate": 1.5503585397653197e-05, + "loss": 0.4748, + "step": 8277 + }, + { + "epoch": 0.67, + "learning_rate": 1.550304215558453e-05, + "loss": 0.3704, + "step": 8278 + }, + { + "epoch": 0.67, + "learning_rate": 1.5502498913515866e-05, + "loss": 0.4879, + "step": 8279 + }, + { + "epoch": 0.67, + "learning_rate": 1.5501955671447197e-05, + "loss": 0.4213, + "step": 8280 + }, + { + "epoch": 0.67, + "learning_rate": 1.5501412429378534e-05, + "loss": 0.4803, + "step": 8281 + }, + { + "epoch": 0.67, + "learning_rate": 1.5500869187309865e-05, + "loss": 0.3253, + "step": 8282 + }, + { + "epoch": 0.67, + "learning_rate": 1.5500325945241203e-05, + "loss": 0.5191, + "step": 8283 + }, + { + "epoch": 0.68, + "learning_rate": 1.5499782703172534e-05, + "loss": 0.5207, + "step": 8284 + }, + { + "epoch": 0.68, + "learning_rate": 1.549923946110387e-05, + "loss": 0.3439, + "step": 8285 + }, + { + "epoch": 0.68, + "learning_rate": 1.5498696219035202e-05, + "loss": 0.5302, + "step": 8286 + }, + { + "epoch": 0.68, + "learning_rate": 1.549815297696654e-05, + "loss": 0.8781, + "step": 8287 + }, + { + "epoch": 0.68, + "learning_rate": 1.549760973489787e-05, + "loss": 0.4584, + "step": 8288 + }, + { + "epoch": 0.68, + "learning_rate": 1.5497066492829208e-05, + "loss": 0.6967, + "step": 8289 + }, + { + "epoch": 0.68, + "learning_rate": 1.549652325076054e-05, + "loss": 0.4629, + "step": 8290 + }, + { + "epoch": 0.68, + "learning_rate": 1.5495980008691877e-05, + "loss": 0.4003, + "step": 8291 + }, + { + "epoch": 0.68, + "learning_rate": 1.5495436766623208e-05, + "loss": 0.4937, + "step": 8292 + }, + { + "epoch": 0.68, + "learning_rate": 1.5494893524554542e-05, + "loss": 0.5296, + "step": 8293 + }, + { + "epoch": 0.68, + "learning_rate": 1.5494350282485876e-05, + "loss": 0.4892, + "step": 8294 + }, + { + "epoch": 0.68, + "learning_rate": 1.549380704041721e-05, + "loss": 0.346, + "step": 8295 + }, + { + "epoch": 0.68, + "learning_rate": 1.5493263798348544e-05, + "loss": 0.472, + "step": 8296 + }, + { + "epoch": 0.68, + "learning_rate": 1.549272055627988e-05, + "loss": 0.435, + "step": 8297 + }, + { + "epoch": 0.68, + "learning_rate": 1.5492177314211213e-05, + "loss": 0.3634, + "step": 8298 + }, + { + "epoch": 0.68, + "learning_rate": 1.5491634072142547e-05, + "loss": 0.2786, + "step": 8299 + }, + { + "epoch": 0.68, + "learning_rate": 1.549109083007388e-05, + "loss": 0.3423, + "step": 8300 + }, + { + "epoch": 0.68, + "learning_rate": 1.5490547588005216e-05, + "loss": 0.6182, + "step": 8301 + }, + { + "epoch": 0.68, + "learning_rate": 1.549000434593655e-05, + "loss": 0.3784, + "step": 8302 + }, + { + "epoch": 0.68, + "learning_rate": 1.5489461103867884e-05, + "loss": 0.3861, + "step": 8303 + }, + { + "epoch": 0.68, + "learning_rate": 1.5488917861799218e-05, + "loss": 0.5712, + "step": 8304 + }, + { + "epoch": 0.68, + "learning_rate": 1.5488374619730553e-05, + "loss": 0.4329, + "step": 8305 + }, + { + "epoch": 0.68, + "learning_rate": 1.5487831377661887e-05, + "loss": 0.4128, + "step": 8306 + }, + { + "epoch": 0.68, + "learning_rate": 1.548728813559322e-05, + "loss": 0.7111, + "step": 8307 + }, + { + "epoch": 0.68, + "learning_rate": 1.5486744893524555e-05, + "loss": 0.5392, + "step": 8308 + }, + { + "epoch": 0.68, + "learning_rate": 1.548620165145589e-05, + "loss": 0.672, + "step": 8309 + }, + { + "epoch": 0.68, + "learning_rate": 1.5485658409387224e-05, + "loss": 0.4183, + "step": 8310 + }, + { + "epoch": 0.68, + "learning_rate": 1.5485115167318558e-05, + "loss": 0.5757, + "step": 8311 + }, + { + "epoch": 0.68, + "learning_rate": 1.5484571925249892e-05, + "loss": 0.3706, + "step": 8312 + }, + { + "epoch": 0.68, + "learning_rate": 1.5484028683181226e-05, + "loss": 0.5214, + "step": 8313 + }, + { + "epoch": 0.68, + "learning_rate": 1.548348544111256e-05, + "loss": 0.3033, + "step": 8314 + }, + { + "epoch": 0.68, + "learning_rate": 1.5482942199043895e-05, + "loss": 0.472, + "step": 8315 + }, + { + "epoch": 0.68, + "learning_rate": 1.548239895697523e-05, + "loss": 0.2509, + "step": 8316 + }, + { + "epoch": 0.68, + "learning_rate": 1.5481855714906563e-05, + "loss": 0.5987, + "step": 8317 + }, + { + "epoch": 0.68, + "learning_rate": 1.5481312472837898e-05, + "loss": 0.2539, + "step": 8318 + }, + { + "epoch": 0.68, + "learning_rate": 1.5480769230769232e-05, + "loss": 0.4609, + "step": 8319 + }, + { + "epoch": 0.68, + "learning_rate": 1.5480225988700566e-05, + "loss": 0.3639, + "step": 8320 + }, + { + "epoch": 0.68, + "learning_rate": 1.54796827466319e-05, + "loss": 0.4027, + "step": 8321 + }, + { + "epoch": 0.68, + "learning_rate": 1.5479139504563234e-05, + "loss": 0.4854, + "step": 8322 + }, + { + "epoch": 0.68, + "learning_rate": 1.547859626249457e-05, + "loss": 0.3956, + "step": 8323 + }, + { + "epoch": 0.68, + "learning_rate": 1.5478053020425903e-05, + "loss": 0.4712, + "step": 8324 + }, + { + "epoch": 0.68, + "learning_rate": 1.5477509778357237e-05, + "loss": 0.5242, + "step": 8325 + }, + { + "epoch": 0.68, + "learning_rate": 1.547696653628857e-05, + "loss": 0.6543, + "step": 8326 + }, + { + "epoch": 0.68, + "learning_rate": 1.5476423294219906e-05, + "loss": 0.5963, + "step": 8327 + }, + { + "epoch": 0.68, + "learning_rate": 1.547588005215124e-05, + "loss": 0.3646, + "step": 8328 + }, + { + "epoch": 0.68, + "learning_rate": 1.5475336810082574e-05, + "loss": 0.4757, + "step": 8329 + }, + { + "epoch": 0.68, + "learning_rate": 1.5474793568013908e-05, + "loss": 0.4287, + "step": 8330 + }, + { + "epoch": 0.68, + "learning_rate": 1.5474250325945243e-05, + "loss": 0.5158, + "step": 8331 + }, + { + "epoch": 0.68, + "learning_rate": 1.5473707083876577e-05, + "loss": 0.3059, + "step": 8332 + }, + { + "epoch": 0.68, + "learning_rate": 1.547316384180791e-05, + "loss": 0.4209, + "step": 8333 + }, + { + "epoch": 0.68, + "learning_rate": 1.5472620599739245e-05, + "loss": 0.4565, + "step": 8334 + }, + { + "epoch": 0.68, + "learning_rate": 1.547207735767058e-05, + "loss": 0.3139, + "step": 8335 + }, + { + "epoch": 0.68, + "learning_rate": 1.5471534115601914e-05, + "loss": 0.3289, + "step": 8336 + }, + { + "epoch": 0.68, + "learning_rate": 1.5470990873533248e-05, + "loss": 0.3903, + "step": 8337 + }, + { + "epoch": 0.68, + "learning_rate": 1.5470447631464582e-05, + "loss": 0.416, + "step": 8338 + }, + { + "epoch": 0.68, + "learning_rate": 1.5469904389395916e-05, + "loss": 0.598, + "step": 8339 + }, + { + "epoch": 0.68, + "learning_rate": 1.546936114732725e-05, + "loss": 0.5726, + "step": 8340 + }, + { + "epoch": 0.68, + "learning_rate": 1.5468817905258585e-05, + "loss": 0.4413, + "step": 8341 + }, + { + "epoch": 0.68, + "learning_rate": 1.546827466318992e-05, + "loss": 0.4171, + "step": 8342 + }, + { + "epoch": 0.68, + "learning_rate": 1.5467731421121253e-05, + "loss": 0.5448, + "step": 8343 + }, + { + "epoch": 0.68, + "learning_rate": 1.5467188179052588e-05, + "loss": 0.497, + "step": 8344 + }, + { + "epoch": 0.68, + "learning_rate": 1.5466644936983922e-05, + "loss": 0.4489, + "step": 8345 + }, + { + "epoch": 0.68, + "learning_rate": 1.5466101694915256e-05, + "loss": 0.4384, + "step": 8346 + }, + { + "epoch": 0.68, + "learning_rate": 1.546555845284659e-05, + "loss": 0.5056, + "step": 8347 + }, + { + "epoch": 0.68, + "learning_rate": 1.5465015210777924e-05, + "loss": 0.388, + "step": 8348 + }, + { + "epoch": 0.68, + "learning_rate": 1.546447196870926e-05, + "loss": 0.3763, + "step": 8349 + }, + { + "epoch": 0.68, + "learning_rate": 1.5463928726640593e-05, + "loss": 0.3855, + "step": 8350 + }, + { + "epoch": 0.68, + "learning_rate": 1.5463385484571927e-05, + "loss": 0.5154, + "step": 8351 + }, + { + "epoch": 0.68, + "learning_rate": 1.546284224250326e-05, + "loss": 0.6886, + "step": 8352 + }, + { + "epoch": 0.68, + "learning_rate": 1.5462299000434596e-05, + "loss": 0.6214, + "step": 8353 + }, + { + "epoch": 0.68, + "learning_rate": 1.546175575836593e-05, + "loss": 0.3864, + "step": 8354 + }, + { + "epoch": 0.68, + "learning_rate": 1.5461212516297264e-05, + "loss": 0.4981, + "step": 8355 + }, + { + "epoch": 0.68, + "learning_rate": 1.5460669274228598e-05, + "loss": 0.3767, + "step": 8356 + }, + { + "epoch": 0.68, + "learning_rate": 1.5460126032159933e-05, + "loss": 0.598, + "step": 8357 + }, + { + "epoch": 0.68, + "learning_rate": 1.5459582790091267e-05, + "loss": 0.2223, + "step": 8358 + }, + { + "epoch": 0.68, + "learning_rate": 1.54590395480226e-05, + "loss": 0.4732, + "step": 8359 + }, + { + "epoch": 0.68, + "learning_rate": 1.5458496305953935e-05, + "loss": 0.4207, + "step": 8360 + }, + { + "epoch": 0.68, + "learning_rate": 1.545795306388527e-05, + "loss": 0.3466, + "step": 8361 + }, + { + "epoch": 0.68, + "learning_rate": 1.5457409821816604e-05, + "loss": 0.592, + "step": 8362 + }, + { + "epoch": 0.68, + "learning_rate": 1.5456866579747938e-05, + "loss": 0.3893, + "step": 8363 + }, + { + "epoch": 0.68, + "learning_rate": 1.5456323337679272e-05, + "loss": 0.4063, + "step": 8364 + }, + { + "epoch": 0.68, + "learning_rate": 1.5455780095610606e-05, + "loss": 0.5443, + "step": 8365 + }, + { + "epoch": 0.68, + "learning_rate": 1.545523685354194e-05, + "loss": 0.2493, + "step": 8366 + }, + { + "epoch": 0.68, + "learning_rate": 1.5454693611473275e-05, + "loss": 0.4156, + "step": 8367 + }, + { + "epoch": 0.68, + "learning_rate": 1.545415036940461e-05, + "loss": 0.4426, + "step": 8368 + }, + { + "epoch": 0.68, + "learning_rate": 1.545360712733594e-05, + "loss": 0.6009, + "step": 8369 + }, + { + "epoch": 0.68, + "learning_rate": 1.5453063885267278e-05, + "loss": 0.4241, + "step": 8370 + }, + { + "epoch": 0.68, + "learning_rate": 1.545252064319861e-05, + "loss": 0.6607, + "step": 8371 + }, + { + "epoch": 0.68, + "learning_rate": 1.5451977401129946e-05, + "loss": 0.4646, + "step": 8372 + }, + { + "epoch": 0.68, + "learning_rate": 1.5451434159061277e-05, + "loss": 0.5511, + "step": 8373 + }, + { + "epoch": 0.68, + "learning_rate": 1.5450890916992614e-05, + "loss": 0.4753, + "step": 8374 + }, + { + "epoch": 0.68, + "learning_rate": 1.5450347674923945e-05, + "loss": 0.3942, + "step": 8375 + }, + { + "epoch": 0.68, + "learning_rate": 1.5449804432855283e-05, + "loss": 0.228, + "step": 8376 + }, + { + "epoch": 0.68, + "learning_rate": 1.5449261190786614e-05, + "loss": 0.443, + "step": 8377 + }, + { + "epoch": 0.68, + "learning_rate": 1.544871794871795e-05, + "loss": 0.2899, + "step": 8378 + }, + { + "epoch": 0.68, + "learning_rate": 1.5448174706649282e-05, + "loss": 0.5861, + "step": 8379 + }, + { + "epoch": 0.68, + "learning_rate": 1.544763146458062e-05, + "loss": 0.3707, + "step": 8380 + }, + { + "epoch": 0.68, + "learning_rate": 1.544708822251195e-05, + "loss": 0.3937, + "step": 8381 + }, + { + "epoch": 0.68, + "learning_rate": 1.5446544980443288e-05, + "loss": 0.4288, + "step": 8382 + }, + { + "epoch": 0.68, + "learning_rate": 1.544600173837462e-05, + "loss": 0.4911, + "step": 8383 + }, + { + "epoch": 0.68, + "learning_rate": 1.5445458496305957e-05, + "loss": 0.3605, + "step": 8384 + }, + { + "epoch": 0.68, + "learning_rate": 1.544491525423729e-05, + "loss": 0.406, + "step": 8385 + }, + { + "epoch": 0.68, + "learning_rate": 1.5444372012168625e-05, + "loss": 0.5585, + "step": 8386 + }, + { + "epoch": 0.68, + "learning_rate": 1.544382877009996e-05, + "loss": 0.3234, + "step": 8387 + }, + { + "epoch": 0.68, + "learning_rate": 1.544328552803129e-05, + "loss": 0.4768, + "step": 8388 + }, + { + "epoch": 0.68, + "learning_rate": 1.5442742285962628e-05, + "loss": 0.4184, + "step": 8389 + }, + { + "epoch": 0.68, + "learning_rate": 1.544219904389396e-05, + "loss": 0.4232, + "step": 8390 + }, + { + "epoch": 0.68, + "learning_rate": 1.5441655801825296e-05, + "loss": 0.3643, + "step": 8391 + }, + { + "epoch": 0.68, + "learning_rate": 1.5441112559756627e-05, + "loss": 0.448, + "step": 8392 + }, + { + "epoch": 0.68, + "learning_rate": 1.5440569317687965e-05, + "loss": 0.5362, + "step": 8393 + }, + { + "epoch": 0.68, + "learning_rate": 1.5440026075619296e-05, + "loss": 0.4966, + "step": 8394 + }, + { + "epoch": 0.68, + "learning_rate": 1.5439482833550633e-05, + "loss": 0.2254, + "step": 8395 + }, + { + "epoch": 0.68, + "learning_rate": 1.5438939591481964e-05, + "loss": 0.4233, + "step": 8396 + }, + { + "epoch": 0.68, + "learning_rate": 1.5438396349413302e-05, + "loss": 0.3574, + "step": 8397 + }, + { + "epoch": 0.68, + "learning_rate": 1.5437853107344633e-05, + "loss": 0.5964, + "step": 8398 + }, + { + "epoch": 0.68, + "learning_rate": 1.543730986527597e-05, + "loss": 0.35, + "step": 8399 + }, + { + "epoch": 0.68, + "learning_rate": 1.54367666232073e-05, + "loss": 0.6276, + "step": 8400 + }, + { + "epoch": 0.68, + "learning_rate": 1.543622338113864e-05, + "loss": 0.4209, + "step": 8401 + }, + { + "epoch": 0.68, + "learning_rate": 1.543568013906997e-05, + "loss": 0.371, + "step": 8402 + }, + { + "epoch": 0.68, + "learning_rate": 1.5435136897001307e-05, + "loss": 0.5566, + "step": 8403 + }, + { + "epoch": 0.68, + "learning_rate": 1.5434593654932638e-05, + "loss": 0.4725, + "step": 8404 + }, + { + "epoch": 0.68, + "learning_rate": 1.5434050412863976e-05, + "loss": 0.4351, + "step": 8405 + }, + { + "epoch": 0.68, + "learning_rate": 1.5433507170795306e-05, + "loss": 0.4375, + "step": 8406 + }, + { + "epoch": 0.69, + "learning_rate": 1.543296392872664e-05, + "loss": 0.6034, + "step": 8407 + }, + { + "epoch": 0.69, + "learning_rate": 1.5432420686657975e-05, + "loss": 0.3795, + "step": 8408 + }, + { + "epoch": 0.69, + "learning_rate": 1.543187744458931e-05, + "loss": 0.4009, + "step": 8409 + }, + { + "epoch": 0.69, + "learning_rate": 1.5431334202520643e-05, + "loss": 0.4653, + "step": 8410 + }, + { + "epoch": 0.69, + "learning_rate": 1.5430790960451978e-05, + "loss": 0.5209, + "step": 8411 + }, + { + "epoch": 0.69, + "learning_rate": 1.5430247718383312e-05, + "loss": 0.6099, + "step": 8412 + }, + { + "epoch": 0.69, + "learning_rate": 1.5429704476314646e-05, + "loss": 0.2969, + "step": 8413 + }, + { + "epoch": 0.69, + "learning_rate": 1.542916123424598e-05, + "loss": 0.6961, + "step": 8414 + }, + { + "epoch": 0.69, + "learning_rate": 1.5428617992177315e-05, + "loss": 0.458, + "step": 8415 + }, + { + "epoch": 0.69, + "learning_rate": 1.542807475010865e-05, + "loss": 0.322, + "step": 8416 + }, + { + "epoch": 0.69, + "learning_rate": 1.5427531508039983e-05, + "loss": 0.5476, + "step": 8417 + }, + { + "epoch": 0.69, + "learning_rate": 1.5426988265971317e-05, + "loss": 0.4343, + "step": 8418 + }, + { + "epoch": 0.69, + "learning_rate": 1.542644502390265e-05, + "loss": 0.4109, + "step": 8419 + }, + { + "epoch": 0.69, + "learning_rate": 1.5425901781833986e-05, + "loss": 0.3727, + "step": 8420 + }, + { + "epoch": 0.69, + "learning_rate": 1.542535853976532e-05, + "loss": 0.6385, + "step": 8421 + }, + { + "epoch": 0.69, + "learning_rate": 1.5424815297696658e-05, + "loss": 0.5718, + "step": 8422 + }, + { + "epoch": 0.69, + "learning_rate": 1.542427205562799e-05, + "loss": 0.3886, + "step": 8423 + }, + { + "epoch": 0.69, + "learning_rate": 1.5423728813559326e-05, + "loss": 0.3634, + "step": 8424 + }, + { + "epoch": 0.69, + "learning_rate": 1.5423185571490657e-05, + "loss": 0.4145, + "step": 8425 + }, + { + "epoch": 0.69, + "learning_rate": 1.542264232942199e-05, + "loss": 0.3621, + "step": 8426 + }, + { + "epoch": 0.69, + "learning_rate": 1.5422099087353325e-05, + "loss": 0.2434, + "step": 8427 + }, + { + "epoch": 0.69, + "learning_rate": 1.542155584528466e-05, + "loss": 0.5698, + "step": 8428 + }, + { + "epoch": 0.69, + "learning_rate": 1.5421012603215994e-05, + "loss": 0.5995, + "step": 8429 + }, + { + "epoch": 0.69, + "learning_rate": 1.5420469361147328e-05, + "loss": 0.4886, + "step": 8430 + }, + { + "epoch": 0.69, + "learning_rate": 1.5419926119078662e-05, + "loss": 0.4985, + "step": 8431 + }, + { + "epoch": 0.69, + "learning_rate": 1.5419382877009996e-05, + "loss": 0.4169, + "step": 8432 + }, + { + "epoch": 0.69, + "learning_rate": 1.541883963494133e-05, + "loss": 0.4843, + "step": 8433 + }, + { + "epoch": 0.69, + "learning_rate": 1.5418296392872665e-05, + "loss": 0.5309, + "step": 8434 + }, + { + "epoch": 0.69, + "learning_rate": 1.5417753150804e-05, + "loss": 0.4168, + "step": 8435 + }, + { + "epoch": 0.69, + "learning_rate": 1.5417209908735333e-05, + "loss": 0.3503, + "step": 8436 + }, + { + "epoch": 0.69, + "learning_rate": 1.5416666666666668e-05, + "loss": 0.425, + "step": 8437 + }, + { + "epoch": 0.69, + "learning_rate": 1.5416123424598002e-05, + "loss": 0.4958, + "step": 8438 + }, + { + "epoch": 0.69, + "learning_rate": 1.5415580182529336e-05, + "loss": 0.5348, + "step": 8439 + }, + { + "epoch": 0.69, + "learning_rate": 1.541503694046067e-05, + "loss": 0.2988, + "step": 8440 + }, + { + "epoch": 0.69, + "learning_rate": 1.5414493698392004e-05, + "loss": 0.5118, + "step": 8441 + }, + { + "epoch": 0.69, + "learning_rate": 1.541395045632334e-05, + "loss": 0.3342, + "step": 8442 + }, + { + "epoch": 0.69, + "learning_rate": 1.5413407214254673e-05, + "loss": 0.4702, + "step": 8443 + }, + { + "epoch": 0.69, + "learning_rate": 1.5412863972186007e-05, + "loss": 0.5633, + "step": 8444 + }, + { + "epoch": 0.69, + "learning_rate": 1.541232073011734e-05, + "loss": 0.4463, + "step": 8445 + }, + { + "epoch": 0.69, + "learning_rate": 1.5411777488048676e-05, + "loss": 0.5055, + "step": 8446 + }, + { + "epoch": 0.69, + "learning_rate": 1.541123424598001e-05, + "loss": 0.4249, + "step": 8447 + }, + { + "epoch": 0.69, + "learning_rate": 1.5410691003911344e-05, + "loss": 0.3807, + "step": 8448 + }, + { + "epoch": 0.69, + "learning_rate": 1.541014776184268e-05, + "loss": 0.4759, + "step": 8449 + }, + { + "epoch": 0.69, + "learning_rate": 1.5409604519774013e-05, + "loss": 0.4414, + "step": 8450 + }, + { + "epoch": 0.69, + "learning_rate": 1.5409061277705347e-05, + "loss": 0.3802, + "step": 8451 + }, + { + "epoch": 0.69, + "learning_rate": 1.540851803563668e-05, + "loss": 0.2685, + "step": 8452 + }, + { + "epoch": 0.69, + "learning_rate": 1.5407974793568015e-05, + "loss": 0.4099, + "step": 8453 + }, + { + "epoch": 0.69, + "learning_rate": 1.540743155149935e-05, + "loss": 0.4236, + "step": 8454 + }, + { + "epoch": 0.69, + "learning_rate": 1.5406888309430684e-05, + "loss": 0.4246, + "step": 8455 + }, + { + "epoch": 0.69, + "learning_rate": 1.5406345067362018e-05, + "loss": 0.5178, + "step": 8456 + }, + { + "epoch": 0.69, + "learning_rate": 1.5405801825293352e-05, + "loss": 0.1944, + "step": 8457 + }, + { + "epoch": 0.69, + "learning_rate": 1.5405258583224686e-05, + "loss": 0.3249, + "step": 8458 + }, + { + "epoch": 0.69, + "learning_rate": 1.540471534115602e-05, + "loss": 0.6293, + "step": 8459 + }, + { + "epoch": 0.69, + "learning_rate": 1.5404172099087355e-05, + "loss": 0.737, + "step": 8460 + }, + { + "epoch": 0.69, + "learning_rate": 1.540362885701869e-05, + "loss": 0.467, + "step": 8461 + }, + { + "epoch": 0.69, + "learning_rate": 1.5403085614950023e-05, + "loss": 0.435, + "step": 8462 + }, + { + "epoch": 0.69, + "learning_rate": 1.5402542372881358e-05, + "loss": 0.7222, + "step": 8463 + }, + { + "epoch": 0.69, + "learning_rate": 1.5401999130812692e-05, + "loss": 0.2353, + "step": 8464 + }, + { + "epoch": 0.69, + "learning_rate": 1.5401455888744026e-05, + "loss": 0.4792, + "step": 8465 + }, + { + "epoch": 0.69, + "learning_rate": 1.540091264667536e-05, + "loss": 0.5695, + "step": 8466 + }, + { + "epoch": 0.69, + "learning_rate": 1.5400369404606694e-05, + "loss": 0.536, + "step": 8467 + }, + { + "epoch": 0.69, + "learning_rate": 1.539982616253803e-05, + "loss": 0.3765, + "step": 8468 + }, + { + "epoch": 0.69, + "learning_rate": 1.5399282920469363e-05, + "loss": 0.2527, + "step": 8469 + }, + { + "epoch": 0.69, + "learning_rate": 1.5398739678400697e-05, + "loss": 0.2642, + "step": 8470 + }, + { + "epoch": 0.69, + "learning_rate": 1.539819643633203e-05, + "loss": 0.3448, + "step": 8471 + }, + { + "epoch": 0.69, + "learning_rate": 1.5397653194263366e-05, + "loss": 0.6314, + "step": 8472 + }, + { + "epoch": 0.69, + "learning_rate": 1.53971099521947e-05, + "loss": 0.3209, + "step": 8473 + }, + { + "epoch": 0.69, + "learning_rate": 1.5396566710126034e-05, + "loss": 0.2452, + "step": 8474 + }, + { + "epoch": 0.69, + "learning_rate": 1.539602346805737e-05, + "loss": 0.3826, + "step": 8475 + }, + { + "epoch": 0.69, + "learning_rate": 1.5395480225988703e-05, + "loss": 0.4009, + "step": 8476 + }, + { + "epoch": 0.69, + "learning_rate": 1.5394936983920037e-05, + "loss": 0.3501, + "step": 8477 + }, + { + "epoch": 0.69, + "learning_rate": 1.539439374185137e-05, + "loss": 0.6608, + "step": 8478 + }, + { + "epoch": 0.69, + "learning_rate": 1.5393850499782705e-05, + "loss": 0.2513, + "step": 8479 + }, + { + "epoch": 0.69, + "learning_rate": 1.539330725771404e-05, + "loss": 0.4399, + "step": 8480 + }, + { + "epoch": 0.69, + "learning_rate": 1.5392764015645374e-05, + "loss": 0.3403, + "step": 8481 + }, + { + "epoch": 0.69, + "learning_rate": 1.5392220773576708e-05, + "loss": 0.5954, + "step": 8482 + }, + { + "epoch": 0.69, + "learning_rate": 1.539167753150804e-05, + "loss": 0.2714, + "step": 8483 + }, + { + "epoch": 0.69, + "learning_rate": 1.5391134289439376e-05, + "loss": 0.4871, + "step": 8484 + }, + { + "epoch": 0.69, + "learning_rate": 1.5390591047370707e-05, + "loss": 0.5085, + "step": 8485 + }, + { + "epoch": 0.69, + "learning_rate": 1.5390047805302045e-05, + "loss": 0.3394, + "step": 8486 + }, + { + "epoch": 0.69, + "learning_rate": 1.5389504563233376e-05, + "loss": 0.5988, + "step": 8487 + }, + { + "epoch": 0.69, + "learning_rate": 1.5388961321164713e-05, + "loss": 0.3503, + "step": 8488 + }, + { + "epoch": 0.69, + "learning_rate": 1.5388418079096044e-05, + "loss": 0.4842, + "step": 8489 + }, + { + "epoch": 0.69, + "learning_rate": 1.5387874837027382e-05, + "loss": 0.307, + "step": 8490 + }, + { + "epoch": 0.69, + "learning_rate": 1.5387331594958713e-05, + "loss": 0.5788, + "step": 8491 + }, + { + "epoch": 0.69, + "learning_rate": 1.538678835289005e-05, + "loss": 0.3299, + "step": 8492 + }, + { + "epoch": 0.69, + "learning_rate": 1.5386245110821384e-05, + "loss": 0.3895, + "step": 8493 + }, + { + "epoch": 0.69, + "learning_rate": 1.538570186875272e-05, + "loss": 0.4284, + "step": 8494 + }, + { + "epoch": 0.69, + "learning_rate": 1.5385158626684053e-05, + "loss": 0.6253, + "step": 8495 + }, + { + "epoch": 0.69, + "learning_rate": 1.5384615384615387e-05, + "loss": 0.547, + "step": 8496 + }, + { + "epoch": 0.69, + "learning_rate": 1.538407214254672e-05, + "loss": 0.32, + "step": 8497 + }, + { + "epoch": 0.69, + "learning_rate": 1.5383528900478056e-05, + "loss": 0.3993, + "step": 8498 + }, + { + "epoch": 0.69, + "learning_rate": 1.538298565840939e-05, + "loss": 0.3315, + "step": 8499 + }, + { + "epoch": 0.69, + "learning_rate": 1.5382442416340724e-05, + "loss": 0.3787, + "step": 8500 + }, + { + "epoch": 0.69, + "eval_accuracy": 0.8260825267447784, + "eval_loss": 0.4526952803134918, + "eval_runtime": 22.358, + "eval_samples_per_second": 438.993, + "eval_steps_per_second": 3.444, + "step": 8500 + }, + { + "epoch": 0.69, + "learning_rate": 1.538189917427206e-05, + "loss": 0.5072, + "step": 8501 + }, + { + "epoch": 0.69, + "learning_rate": 1.538135593220339e-05, + "loss": 0.4649, + "step": 8502 + }, + { + "epoch": 0.69, + "learning_rate": 1.5380812690134727e-05, + "loss": 0.7378, + "step": 8503 + }, + { + "epoch": 0.69, + "learning_rate": 1.5380269448066058e-05, + "loss": 0.5075, + "step": 8504 + }, + { + "epoch": 0.69, + "learning_rate": 1.5379726205997395e-05, + "loss": 0.3224, + "step": 8505 + }, + { + "epoch": 0.69, + "learning_rate": 1.5379182963928726e-05, + "loss": 0.3454, + "step": 8506 + }, + { + "epoch": 0.69, + "learning_rate": 1.5378639721860064e-05, + "loss": 0.5811, + "step": 8507 + }, + { + "epoch": 0.69, + "learning_rate": 1.5378096479791395e-05, + "loss": 0.3977, + "step": 8508 + }, + { + "epoch": 0.69, + "learning_rate": 1.5377553237722732e-05, + "loss": 0.4532, + "step": 8509 + }, + { + "epoch": 0.69, + "learning_rate": 1.5377009995654063e-05, + "loss": 0.3327, + "step": 8510 + }, + { + "epoch": 0.69, + "learning_rate": 1.53764667535854e-05, + "loss": 0.4185, + "step": 8511 + }, + { + "epoch": 0.69, + "learning_rate": 1.537592351151673e-05, + "loss": 0.4153, + "step": 8512 + }, + { + "epoch": 0.69, + "learning_rate": 1.537538026944807e-05, + "loss": 0.5806, + "step": 8513 + }, + { + "epoch": 0.69, + "learning_rate": 1.53748370273794e-05, + "loss": 0.4591, + "step": 8514 + }, + { + "epoch": 0.69, + "learning_rate": 1.5374293785310738e-05, + "loss": 0.3606, + "step": 8515 + }, + { + "epoch": 0.69, + "learning_rate": 1.537375054324207e-05, + "loss": 0.4064, + "step": 8516 + }, + { + "epoch": 0.69, + "learning_rate": 1.5373207301173406e-05, + "loss": 0.6419, + "step": 8517 + }, + { + "epoch": 0.69, + "learning_rate": 1.5372664059104737e-05, + "loss": 0.7663, + "step": 8518 + }, + { + "epoch": 0.69, + "learning_rate": 1.5372120817036074e-05, + "loss": 0.3871, + "step": 8519 + }, + { + "epoch": 0.69, + "learning_rate": 1.5371577574967405e-05, + "loss": 0.4114, + "step": 8520 + }, + { + "epoch": 0.69, + "learning_rate": 1.537103433289874e-05, + "loss": 0.3395, + "step": 8521 + }, + { + "epoch": 0.69, + "learning_rate": 1.5370491090830074e-05, + "loss": 0.3309, + "step": 8522 + }, + { + "epoch": 0.69, + "learning_rate": 1.5369947848761408e-05, + "loss": 0.5123, + "step": 8523 + }, + { + "epoch": 0.69, + "learning_rate": 1.5369404606692742e-05, + "loss": 0.5434, + "step": 8524 + }, + { + "epoch": 0.69, + "learning_rate": 1.5368861364624076e-05, + "loss": 0.7156, + "step": 8525 + }, + { + "epoch": 0.69, + "learning_rate": 1.536831812255541e-05, + "loss": 0.5519, + "step": 8526 + }, + { + "epoch": 0.69, + "learning_rate": 1.5367774880486745e-05, + "loss": 0.3165, + "step": 8527 + }, + { + "epoch": 0.69, + "learning_rate": 1.536723163841808e-05, + "loss": 0.3588, + "step": 8528 + }, + { + "epoch": 0.69, + "learning_rate": 1.5366688396349413e-05, + "loss": 0.5442, + "step": 8529 + }, + { + "epoch": 0.7, + "learning_rate": 1.536614515428075e-05, + "loss": 0.3248, + "step": 8530 + }, + { + "epoch": 0.7, + "learning_rate": 1.5365601912212082e-05, + "loss": 0.5233, + "step": 8531 + }, + { + "epoch": 0.7, + "learning_rate": 1.536505867014342e-05, + "loss": 0.5265, + "step": 8532 + }, + { + "epoch": 0.7, + "learning_rate": 1.536451542807475e-05, + "loss": 0.667, + "step": 8533 + }, + { + "epoch": 0.7, + "learning_rate": 1.5363972186006088e-05, + "loss": 0.4071, + "step": 8534 + }, + { + "epoch": 0.7, + "learning_rate": 1.536342894393742e-05, + "loss": 0.5784, + "step": 8535 + }, + { + "epoch": 0.7, + "learning_rate": 1.5362885701868756e-05, + "loss": 0.7136, + "step": 8536 + }, + { + "epoch": 0.7, + "learning_rate": 1.5362342459800087e-05, + "loss": 0.7615, + "step": 8537 + }, + { + "epoch": 0.7, + "learning_rate": 1.5361799217731425e-05, + "loss": 0.4971, + "step": 8538 + }, + { + "epoch": 0.7, + "learning_rate": 1.5361255975662756e-05, + "loss": 0.3222, + "step": 8539 + }, + { + "epoch": 0.7, + "learning_rate": 1.536071273359409e-05, + "loss": 0.2975, + "step": 8540 + }, + { + "epoch": 0.7, + "learning_rate": 1.5360169491525424e-05, + "loss": 0.5269, + "step": 8541 + }, + { + "epoch": 0.7, + "learning_rate": 1.535962624945676e-05, + "loss": 0.4791, + "step": 8542 + }, + { + "epoch": 0.7, + "learning_rate": 1.5359083007388093e-05, + "loss": 0.3844, + "step": 8543 + }, + { + "epoch": 0.7, + "learning_rate": 1.5358539765319427e-05, + "loss": 0.3635, + "step": 8544 + }, + { + "epoch": 0.7, + "learning_rate": 1.535799652325076e-05, + "loss": 0.3649, + "step": 8545 + }, + { + "epoch": 0.7, + "learning_rate": 1.5357453281182095e-05, + "loss": 0.5908, + "step": 8546 + }, + { + "epoch": 0.7, + "learning_rate": 1.535691003911343e-05, + "loss": 0.4331, + "step": 8547 + }, + { + "epoch": 0.7, + "learning_rate": 1.5356366797044764e-05, + "loss": 0.7061, + "step": 8548 + }, + { + "epoch": 0.7, + "learning_rate": 1.5355823554976098e-05, + "loss": 0.6468, + "step": 8549 + }, + { + "epoch": 0.7, + "learning_rate": 1.5355280312907432e-05, + "loss": 0.4096, + "step": 8550 + }, + { + "epoch": 0.7, + "learning_rate": 1.5354737070838766e-05, + "loss": 0.4749, + "step": 8551 + }, + { + "epoch": 0.7, + "learning_rate": 1.53541938287701e-05, + "loss": 0.4358, + "step": 8552 + }, + { + "epoch": 0.7, + "learning_rate": 1.5353650586701435e-05, + "loss": 0.4958, + "step": 8553 + }, + { + "epoch": 0.7, + "learning_rate": 1.535310734463277e-05, + "loss": 0.6423, + "step": 8554 + }, + { + "epoch": 0.7, + "learning_rate": 1.5352564102564103e-05, + "loss": 0.3683, + "step": 8555 + }, + { + "epoch": 0.7, + "learning_rate": 1.5352020860495438e-05, + "loss": 0.4426, + "step": 8556 + }, + { + "epoch": 0.7, + "learning_rate": 1.5351477618426772e-05, + "loss": 0.6831, + "step": 8557 + }, + { + "epoch": 0.7, + "learning_rate": 1.5350934376358106e-05, + "loss": 0.3537, + "step": 8558 + }, + { + "epoch": 0.7, + "learning_rate": 1.535039113428944e-05, + "loss": 0.4868, + "step": 8559 + }, + { + "epoch": 0.7, + "learning_rate": 1.5349847892220775e-05, + "loss": 0.477, + "step": 8560 + }, + { + "epoch": 0.7, + "learning_rate": 1.534930465015211e-05, + "loss": 0.2602, + "step": 8561 + }, + { + "epoch": 0.7, + "learning_rate": 1.5348761408083443e-05, + "loss": 0.5069, + "step": 8562 + }, + { + "epoch": 0.7, + "learning_rate": 1.5348218166014777e-05, + "loss": 0.5041, + "step": 8563 + }, + { + "epoch": 0.7, + "learning_rate": 1.534767492394611e-05, + "loss": 0.4311, + "step": 8564 + }, + { + "epoch": 0.7, + "learning_rate": 1.5347131681877446e-05, + "loss": 0.6644, + "step": 8565 + }, + { + "epoch": 0.7, + "learning_rate": 1.534658843980878e-05, + "loss": 0.4349, + "step": 8566 + }, + { + "epoch": 0.7, + "learning_rate": 1.5346045197740114e-05, + "loss": 0.6266, + "step": 8567 + }, + { + "epoch": 0.7, + "learning_rate": 1.534550195567145e-05, + "loss": 0.499, + "step": 8568 + }, + { + "epoch": 0.7, + "learning_rate": 1.5344958713602783e-05, + "loss": 0.4216, + "step": 8569 + }, + { + "epoch": 0.7, + "learning_rate": 1.5344415471534117e-05, + "loss": 0.3416, + "step": 8570 + }, + { + "epoch": 0.7, + "learning_rate": 1.534387222946545e-05, + "loss": 0.2984, + "step": 8571 + }, + { + "epoch": 0.7, + "learning_rate": 1.5343328987396785e-05, + "loss": 0.3813, + "step": 8572 + }, + { + "epoch": 0.7, + "learning_rate": 1.534278574532812e-05, + "loss": 0.3851, + "step": 8573 + }, + { + "epoch": 0.7, + "learning_rate": 1.5342242503259454e-05, + "loss": 0.5444, + "step": 8574 + }, + { + "epoch": 0.7, + "learning_rate": 1.5341699261190788e-05, + "loss": 0.6765, + "step": 8575 + }, + { + "epoch": 0.7, + "learning_rate": 1.5341156019122122e-05, + "loss": 0.5025, + "step": 8576 + }, + { + "epoch": 0.7, + "learning_rate": 1.5340612777053456e-05, + "loss": 0.6545, + "step": 8577 + }, + { + "epoch": 0.7, + "learning_rate": 1.534006953498479e-05, + "loss": 0.3621, + "step": 8578 + }, + { + "epoch": 0.7, + "learning_rate": 1.5339526292916125e-05, + "loss": 0.4311, + "step": 8579 + }, + { + "epoch": 0.7, + "learning_rate": 1.533898305084746e-05, + "loss": 0.4918, + "step": 8580 + }, + { + "epoch": 0.7, + "learning_rate": 1.5338439808778793e-05, + "loss": 0.5744, + "step": 8581 + }, + { + "epoch": 0.7, + "learning_rate": 1.5337896566710128e-05, + "loss": 0.4935, + "step": 8582 + }, + { + "epoch": 0.7, + "learning_rate": 1.5337353324641462e-05, + "loss": 0.6394, + "step": 8583 + }, + { + "epoch": 0.7, + "learning_rate": 1.5336810082572796e-05, + "loss": 0.5849, + "step": 8584 + }, + { + "epoch": 0.7, + "learning_rate": 1.533626684050413e-05, + "loss": 0.4032, + "step": 8585 + }, + { + "epoch": 0.7, + "learning_rate": 1.5335723598435465e-05, + "loss": 0.4531, + "step": 8586 + }, + { + "epoch": 0.7, + "learning_rate": 1.53351803563668e-05, + "loss": 0.2235, + "step": 8587 + }, + { + "epoch": 0.7, + "learning_rate": 1.5334637114298133e-05, + "loss": 0.7856, + "step": 8588 + }, + { + "epoch": 0.7, + "learning_rate": 1.5334093872229467e-05, + "loss": 0.5333, + "step": 8589 + }, + { + "epoch": 0.7, + "learning_rate": 1.53335506301608e-05, + "loss": 0.6204, + "step": 8590 + }, + { + "epoch": 0.7, + "learning_rate": 1.5333007388092136e-05, + "loss": 0.4209, + "step": 8591 + }, + { + "epoch": 0.7, + "learning_rate": 1.533246414602347e-05, + "loss": 0.6515, + "step": 8592 + }, + { + "epoch": 0.7, + "learning_rate": 1.5331920903954804e-05, + "loss": 0.4337, + "step": 8593 + }, + { + "epoch": 0.7, + "learning_rate": 1.533137766188614e-05, + "loss": 0.736, + "step": 8594 + }, + { + "epoch": 0.7, + "learning_rate": 1.5330834419817473e-05, + "loss": 0.4707, + "step": 8595 + }, + { + "epoch": 0.7, + "learning_rate": 1.5330291177748807e-05, + "loss": 0.6272, + "step": 8596 + }, + { + "epoch": 0.7, + "learning_rate": 1.5329747935680138e-05, + "loss": 0.4683, + "step": 8597 + }, + { + "epoch": 0.7, + "learning_rate": 1.5329204693611475e-05, + "loss": 0.6133, + "step": 8598 + }, + { + "epoch": 0.7, + "learning_rate": 1.5328661451542806e-05, + "loss": 0.3683, + "step": 8599 + }, + { + "epoch": 0.7, + "learning_rate": 1.5328118209474144e-05, + "loss": 0.6436, + "step": 8600 + }, + { + "epoch": 0.7, + "learning_rate": 1.5327574967405478e-05, + "loss": 0.4114, + "step": 8601 + }, + { + "epoch": 0.7, + "learning_rate": 1.5327031725336812e-05, + "loss": 0.4632, + "step": 8602 + }, + { + "epoch": 0.7, + "learning_rate": 1.5326488483268146e-05, + "loss": 0.2729, + "step": 8603 + }, + { + "epoch": 0.7, + "learning_rate": 1.532594524119948e-05, + "loss": 0.2904, + "step": 8604 + }, + { + "epoch": 0.7, + "learning_rate": 1.5325401999130815e-05, + "loss": 0.4435, + "step": 8605 + }, + { + "epoch": 0.7, + "learning_rate": 1.532485875706215e-05, + "loss": 0.3784, + "step": 8606 + }, + { + "epoch": 0.7, + "learning_rate": 1.5324315514993483e-05, + "loss": 0.3809, + "step": 8607 + }, + { + "epoch": 0.7, + "learning_rate": 1.5323772272924818e-05, + "loss": 0.6585, + "step": 8608 + }, + { + "epoch": 0.7, + "learning_rate": 1.5323229030856152e-05, + "loss": 0.1448, + "step": 8609 + }, + { + "epoch": 0.7, + "learning_rate": 1.5322685788787486e-05, + "loss": 0.653, + "step": 8610 + }, + { + "epoch": 0.7, + "learning_rate": 1.532214254671882e-05, + "loss": 0.2834, + "step": 8611 + }, + { + "epoch": 0.7, + "learning_rate": 1.5321599304650155e-05, + "loss": 0.5041, + "step": 8612 + }, + { + "epoch": 0.7, + "learning_rate": 1.532105606258149e-05, + "loss": 0.5198, + "step": 8613 + }, + { + "epoch": 0.7, + "learning_rate": 1.5320512820512823e-05, + "loss": 0.319, + "step": 8614 + }, + { + "epoch": 0.7, + "learning_rate": 1.5319969578444157e-05, + "loss": 0.4322, + "step": 8615 + }, + { + "epoch": 0.7, + "learning_rate": 1.5319426336375488e-05, + "loss": 0.5596, + "step": 8616 + }, + { + "epoch": 0.7, + "learning_rate": 1.5318883094306826e-05, + "loss": 0.4884, + "step": 8617 + }, + { + "epoch": 0.7, + "learning_rate": 1.5318339852238157e-05, + "loss": 0.443, + "step": 8618 + }, + { + "epoch": 0.7, + "learning_rate": 1.5317796610169494e-05, + "loss": 0.4323, + "step": 8619 + }, + { + "epoch": 0.7, + "learning_rate": 1.5317253368100825e-05, + "loss": 0.5331, + "step": 8620 + }, + { + "epoch": 0.7, + "learning_rate": 1.5316710126032163e-05, + "loss": 0.4944, + "step": 8621 + }, + { + "epoch": 0.7, + "learning_rate": 1.5316166883963493e-05, + "loss": 0.2566, + "step": 8622 + }, + { + "epoch": 0.7, + "learning_rate": 1.531562364189483e-05, + "loss": 0.4939, + "step": 8623 + }, + { + "epoch": 0.7, + "learning_rate": 1.5315080399826162e-05, + "loss": 0.4285, + "step": 8624 + }, + { + "epoch": 0.7, + "learning_rate": 1.53145371577575e-05, + "loss": 0.2934, + "step": 8625 + }, + { + "epoch": 0.7, + "learning_rate": 1.531399391568883e-05, + "loss": 0.381, + "step": 8626 + }, + { + "epoch": 0.7, + "learning_rate": 1.5313450673620168e-05, + "loss": 0.603, + "step": 8627 + }, + { + "epoch": 0.7, + "learning_rate": 1.53129074315515e-05, + "loss": 0.4951, + "step": 8628 + }, + { + "epoch": 0.7, + "learning_rate": 1.5312364189482836e-05, + "loss": 0.4952, + "step": 8629 + }, + { + "epoch": 0.7, + "learning_rate": 1.5311820947414167e-05, + "loss": 0.6772, + "step": 8630 + }, + { + "epoch": 0.7, + "learning_rate": 1.5311277705345505e-05, + "loss": 0.4597, + "step": 8631 + }, + { + "epoch": 0.7, + "learning_rate": 1.5310734463276836e-05, + "loss": 0.3941, + "step": 8632 + }, + { + "epoch": 0.7, + "learning_rate": 1.5310191221208173e-05, + "loss": 0.3044, + "step": 8633 + }, + { + "epoch": 0.7, + "learning_rate": 1.5309647979139504e-05, + "loss": 0.3203, + "step": 8634 + }, + { + "epoch": 0.7, + "learning_rate": 1.530910473707084e-05, + "loss": 0.324, + "step": 8635 + }, + { + "epoch": 0.7, + "learning_rate": 1.5308561495002173e-05, + "loss": 0.4562, + "step": 8636 + }, + { + "epoch": 0.7, + "learning_rate": 1.5308018252933507e-05, + "loss": 0.1737, + "step": 8637 + }, + { + "epoch": 0.7, + "learning_rate": 1.5307475010864845e-05, + "loss": 0.3759, + "step": 8638 + }, + { + "epoch": 0.7, + "learning_rate": 1.5306931768796175e-05, + "loss": 0.4961, + "step": 8639 + }, + { + "epoch": 0.7, + "learning_rate": 1.5306388526727513e-05, + "loss": 0.6152, + "step": 8640 + }, + { + "epoch": 0.7, + "learning_rate": 1.5305845284658844e-05, + "loss": 0.572, + "step": 8641 + }, + { + "epoch": 0.7, + "learning_rate": 1.530530204259018e-05, + "loss": 0.9019, + "step": 8642 + }, + { + "epoch": 0.7, + "learning_rate": 1.5304758800521512e-05, + "loss": 0.4095, + "step": 8643 + }, + { + "epoch": 0.7, + "learning_rate": 1.530421555845285e-05, + "loss": 0.8238, + "step": 8644 + }, + { + "epoch": 0.7, + "learning_rate": 1.530367231638418e-05, + "loss": 0.6964, + "step": 8645 + }, + { + "epoch": 0.7, + "learning_rate": 1.530312907431552e-05, + "loss": 0.5979, + "step": 8646 + }, + { + "epoch": 0.7, + "learning_rate": 1.530258583224685e-05, + "loss": 0.5145, + "step": 8647 + }, + { + "epoch": 0.7, + "learning_rate": 1.5302042590178187e-05, + "loss": 0.5574, + "step": 8648 + }, + { + "epoch": 0.7, + "learning_rate": 1.5301499348109518e-05, + "loss": 0.3384, + "step": 8649 + }, + { + "epoch": 0.7, + "learning_rate": 1.5300956106040855e-05, + "loss": 0.5125, + "step": 8650 + }, + { + "epoch": 0.7, + "learning_rate": 1.5300412863972186e-05, + "loss": 0.4101, + "step": 8651 + }, + { + "epoch": 0.71, + "learning_rate": 1.5299869621903524e-05, + "loss": 0.5548, + "step": 8652 + }, + { + "epoch": 0.71, + "learning_rate": 1.5299326379834855e-05, + "loss": 0.4903, + "step": 8653 + }, + { + "epoch": 0.71, + "learning_rate": 1.529878313776619e-05, + "loss": 0.7906, + "step": 8654 + }, + { + "epoch": 0.71, + "learning_rate": 1.5298239895697523e-05, + "loss": 0.316, + "step": 8655 + }, + { + "epoch": 0.71, + "learning_rate": 1.5297696653628857e-05, + "loss": 0.6354, + "step": 8656 + }, + { + "epoch": 0.71, + "learning_rate": 1.529715341156019e-05, + "loss": 0.4491, + "step": 8657 + }, + { + "epoch": 0.71, + "learning_rate": 1.5296610169491526e-05, + "loss": 0.6281, + "step": 8658 + }, + { + "epoch": 0.71, + "learning_rate": 1.529606692742286e-05, + "loss": 0.5294, + "step": 8659 + }, + { + "epoch": 0.71, + "learning_rate": 1.5295523685354194e-05, + "loss": 0.204, + "step": 8660 + }, + { + "epoch": 0.71, + "learning_rate": 1.529498044328553e-05, + "loss": 0.2272, + "step": 8661 + }, + { + "epoch": 0.71, + "learning_rate": 1.5294437201216863e-05, + "loss": 0.3866, + "step": 8662 + }, + { + "epoch": 0.71, + "learning_rate": 1.5293893959148197e-05, + "loss": 0.3954, + "step": 8663 + }, + { + "epoch": 0.71, + "learning_rate": 1.529335071707953e-05, + "loss": 0.3695, + "step": 8664 + }, + { + "epoch": 0.71, + "learning_rate": 1.5292807475010865e-05, + "loss": 0.2398, + "step": 8665 + }, + { + "epoch": 0.71, + "learning_rate": 1.52922642329422e-05, + "loss": 0.3871, + "step": 8666 + }, + { + "epoch": 0.71, + "learning_rate": 1.5291720990873534e-05, + "loss": 0.4208, + "step": 8667 + }, + { + "epoch": 0.71, + "learning_rate": 1.5291177748804868e-05, + "loss": 0.5103, + "step": 8668 + }, + { + "epoch": 0.71, + "learning_rate": 1.5290634506736202e-05, + "loss": 0.4272, + "step": 8669 + }, + { + "epoch": 0.71, + "learning_rate": 1.5290091264667537e-05, + "loss": 0.2509, + "step": 8670 + }, + { + "epoch": 0.71, + "learning_rate": 1.528954802259887e-05, + "loss": 0.5973, + "step": 8671 + }, + { + "epoch": 0.71, + "learning_rate": 1.5289004780530205e-05, + "loss": 0.4969, + "step": 8672 + }, + { + "epoch": 0.71, + "learning_rate": 1.528846153846154e-05, + "loss": 0.2835, + "step": 8673 + }, + { + "epoch": 0.71, + "learning_rate": 1.5287918296392873e-05, + "loss": 0.3392, + "step": 8674 + }, + { + "epoch": 0.71, + "learning_rate": 1.5287375054324208e-05, + "loss": 0.5571, + "step": 8675 + }, + { + "epoch": 0.71, + "learning_rate": 1.5286831812255542e-05, + "loss": 0.4041, + "step": 8676 + }, + { + "epoch": 0.71, + "learning_rate": 1.5286288570186876e-05, + "loss": 0.6858, + "step": 8677 + }, + { + "epoch": 0.71, + "learning_rate": 1.528574532811821e-05, + "loss": 0.8132, + "step": 8678 + }, + { + "epoch": 0.71, + "learning_rate": 1.5285202086049545e-05, + "loss": 0.5176, + "step": 8679 + }, + { + "epoch": 0.71, + "learning_rate": 1.528465884398088e-05, + "loss": 0.5819, + "step": 8680 + }, + { + "epoch": 0.71, + "learning_rate": 1.5284115601912213e-05, + "loss": 0.6507, + "step": 8681 + }, + { + "epoch": 0.71, + "learning_rate": 1.5283572359843547e-05, + "loss": 0.4428, + "step": 8682 + }, + { + "epoch": 0.71, + "learning_rate": 1.528302911777488e-05, + "loss": 0.3215, + "step": 8683 + }, + { + "epoch": 0.71, + "learning_rate": 1.5282485875706216e-05, + "loss": 0.2178, + "step": 8684 + }, + { + "epoch": 0.71, + "learning_rate": 1.528194263363755e-05, + "loss": 0.5315, + "step": 8685 + }, + { + "epoch": 0.71, + "learning_rate": 1.5281399391568884e-05, + "loss": 0.5648, + "step": 8686 + }, + { + "epoch": 0.71, + "learning_rate": 1.528085614950022e-05, + "loss": 0.6588, + "step": 8687 + }, + { + "epoch": 0.71, + "learning_rate": 1.5280312907431553e-05, + "loss": 0.5471, + "step": 8688 + }, + { + "epoch": 0.71, + "learning_rate": 1.5279769665362887e-05, + "loss": 0.463, + "step": 8689 + }, + { + "epoch": 0.71, + "learning_rate": 1.527922642329422e-05, + "loss": 0.5168, + "step": 8690 + }, + { + "epoch": 0.71, + "learning_rate": 1.5278683181225555e-05, + "loss": 0.3306, + "step": 8691 + }, + { + "epoch": 0.71, + "learning_rate": 1.527813993915689e-05, + "loss": 0.3568, + "step": 8692 + }, + { + "epoch": 0.71, + "learning_rate": 1.5277596697088224e-05, + "loss": 0.5686, + "step": 8693 + }, + { + "epoch": 0.71, + "learning_rate": 1.5277053455019558e-05, + "loss": 0.6362, + "step": 8694 + }, + { + "epoch": 0.71, + "learning_rate": 1.5276510212950892e-05, + "loss": 0.3347, + "step": 8695 + }, + { + "epoch": 0.71, + "learning_rate": 1.5275966970882227e-05, + "loss": 0.3317, + "step": 8696 + }, + { + "epoch": 0.71, + "learning_rate": 1.527542372881356e-05, + "loss": 0.3857, + "step": 8697 + }, + { + "epoch": 0.71, + "learning_rate": 1.5274880486744895e-05, + "loss": 0.4401, + "step": 8698 + }, + { + "epoch": 0.71, + "learning_rate": 1.527433724467623e-05, + "loss": 0.5755, + "step": 8699 + }, + { + "epoch": 0.71, + "learning_rate": 1.5273794002607563e-05, + "loss": 0.4721, + "step": 8700 + }, + { + "epoch": 0.71, + "learning_rate": 1.5273250760538898e-05, + "loss": 0.5178, + "step": 8701 + }, + { + "epoch": 0.71, + "learning_rate": 1.5272707518470232e-05, + "loss": 0.3754, + "step": 8702 + }, + { + "epoch": 0.71, + "learning_rate": 1.5272164276401566e-05, + "loss": 0.4929, + "step": 8703 + }, + { + "epoch": 0.71, + "learning_rate": 1.52716210343329e-05, + "loss": 0.5769, + "step": 8704 + }, + { + "epoch": 0.71, + "learning_rate": 1.5271077792264235e-05, + "loss": 0.383, + "step": 8705 + }, + { + "epoch": 0.71, + "learning_rate": 1.527053455019557e-05, + "loss": 0.5128, + "step": 8706 + }, + { + "epoch": 0.71, + "learning_rate": 1.5269991308126903e-05, + "loss": 0.3486, + "step": 8707 + }, + { + "epoch": 0.71, + "learning_rate": 1.5269448066058237e-05, + "loss": 0.4508, + "step": 8708 + }, + { + "epoch": 0.71, + "learning_rate": 1.526890482398957e-05, + "loss": 0.5261, + "step": 8709 + }, + { + "epoch": 0.71, + "learning_rate": 1.5268361581920906e-05, + "loss": 0.5569, + "step": 8710 + }, + { + "epoch": 0.71, + "learning_rate": 1.526781833985224e-05, + "loss": 0.3749, + "step": 8711 + }, + { + "epoch": 0.71, + "learning_rate": 1.5267275097783574e-05, + "loss": 0.4425, + "step": 8712 + }, + { + "epoch": 0.71, + "learning_rate": 1.526673185571491e-05, + "loss": 0.3981, + "step": 8713 + }, + { + "epoch": 0.71, + "learning_rate": 1.5266188613646243e-05, + "loss": 0.5437, + "step": 8714 + }, + { + "epoch": 0.71, + "learning_rate": 1.5265645371577577e-05, + "loss": 0.3331, + "step": 8715 + }, + { + "epoch": 0.71, + "learning_rate": 1.526510212950891e-05, + "loss": 0.384, + "step": 8716 + }, + { + "epoch": 0.71, + "learning_rate": 1.5264558887440245e-05, + "loss": 0.6146, + "step": 8717 + }, + { + "epoch": 0.71, + "learning_rate": 1.526401564537158e-05, + "loss": 0.5362, + "step": 8718 + }, + { + "epoch": 0.71, + "learning_rate": 1.5263472403302914e-05, + "loss": 0.3374, + "step": 8719 + }, + { + "epoch": 0.71, + "learning_rate": 1.5262929161234248e-05, + "loss": 0.2788, + "step": 8720 + }, + { + "epoch": 0.71, + "learning_rate": 1.5262385919165582e-05, + "loss": 0.4987, + "step": 8721 + }, + { + "epoch": 0.71, + "learning_rate": 1.5261842677096917e-05, + "loss": 0.4972, + "step": 8722 + }, + { + "epoch": 0.71, + "learning_rate": 1.526129943502825e-05, + "loss": 0.4499, + "step": 8723 + }, + { + "epoch": 0.71, + "learning_rate": 1.5260756192959585e-05, + "loss": 0.4836, + "step": 8724 + }, + { + "epoch": 0.71, + "learning_rate": 1.526021295089092e-05, + "loss": 0.3679, + "step": 8725 + }, + { + "epoch": 0.71, + "learning_rate": 1.5259669708822253e-05, + "loss": 0.4825, + "step": 8726 + }, + { + "epoch": 0.71, + "learning_rate": 1.5259126466753588e-05, + "loss": 0.511, + "step": 8727 + }, + { + "epoch": 0.71, + "learning_rate": 1.5258583224684922e-05, + "loss": 0.4846, + "step": 8728 + }, + { + "epoch": 0.71, + "learning_rate": 1.5258039982616254e-05, + "loss": 0.4904, + "step": 8729 + }, + { + "epoch": 0.71, + "learning_rate": 1.5257496740547589e-05, + "loss": 0.6008, + "step": 8730 + }, + { + "epoch": 0.71, + "learning_rate": 1.5256953498478923e-05, + "loss": 0.6401, + "step": 8731 + }, + { + "epoch": 0.71, + "learning_rate": 1.5256410256410257e-05, + "loss": 0.5716, + "step": 8732 + }, + { + "epoch": 0.71, + "learning_rate": 1.5255867014341591e-05, + "loss": 0.2838, + "step": 8733 + }, + { + "epoch": 0.71, + "learning_rate": 1.5255323772272926e-05, + "loss": 0.3348, + "step": 8734 + }, + { + "epoch": 0.71, + "learning_rate": 1.525478053020426e-05, + "loss": 0.6946, + "step": 8735 + }, + { + "epoch": 0.71, + "learning_rate": 1.5254237288135594e-05, + "loss": 0.5781, + "step": 8736 + }, + { + "epoch": 0.71, + "learning_rate": 1.525369404606693e-05, + "loss": 0.4067, + "step": 8737 + }, + { + "epoch": 0.71, + "learning_rate": 1.5253150803998262e-05, + "loss": 0.4989, + "step": 8738 + }, + { + "epoch": 0.71, + "learning_rate": 1.5252607561929598e-05, + "loss": 0.5834, + "step": 8739 + }, + { + "epoch": 0.71, + "learning_rate": 1.5252064319860931e-05, + "loss": 0.6009, + "step": 8740 + }, + { + "epoch": 0.71, + "learning_rate": 1.5251521077792267e-05, + "loss": 0.5684, + "step": 8741 + }, + { + "epoch": 0.71, + "learning_rate": 1.52509778357236e-05, + "loss": 0.5857, + "step": 8742 + }, + { + "epoch": 0.71, + "learning_rate": 1.5250434593654935e-05, + "loss": 0.4012, + "step": 8743 + }, + { + "epoch": 0.71, + "learning_rate": 1.5249891351586268e-05, + "loss": 0.4329, + "step": 8744 + }, + { + "epoch": 0.71, + "learning_rate": 1.5249348109517604e-05, + "loss": 0.7616, + "step": 8745 + }, + { + "epoch": 0.71, + "learning_rate": 1.5248804867448936e-05, + "loss": 0.1934, + "step": 8746 + }, + { + "epoch": 0.71, + "learning_rate": 1.5248261625380272e-05, + "loss": 0.5416, + "step": 8747 + }, + { + "epoch": 0.71, + "learning_rate": 1.5247718383311605e-05, + "loss": 0.4444, + "step": 8748 + }, + { + "epoch": 0.71, + "learning_rate": 1.5247175141242937e-05, + "loss": 0.4747, + "step": 8749 + }, + { + "epoch": 0.71, + "learning_rate": 1.5246631899174273e-05, + "loss": 0.5906, + "step": 8750 + }, + { + "epoch": 0.71, + "eval_accuracy": 0.8332144676515537, + "eval_loss": 0.4383261799812317, + "eval_runtime": 22.2549, + "eval_samples_per_second": 441.026, + "eval_steps_per_second": 3.46, + "step": 8750 + }, + { + "epoch": 0.71, + "learning_rate": 1.5246088657105606e-05, + "loss": 0.8071, + "step": 8751 + }, + { + "epoch": 0.71, + "learning_rate": 1.5245545415036942e-05, + "loss": 0.4971, + "step": 8752 + }, + { + "epoch": 0.71, + "learning_rate": 1.5245002172968276e-05, + "loss": 0.4798, + "step": 8753 + }, + { + "epoch": 0.71, + "learning_rate": 1.524445893089961e-05, + "loss": 0.3483, + "step": 8754 + }, + { + "epoch": 0.71, + "learning_rate": 1.5243915688830944e-05, + "loss": 0.4608, + "step": 8755 + }, + { + "epoch": 0.71, + "learning_rate": 1.5243372446762279e-05, + "loss": 0.5507, + "step": 8756 + }, + { + "epoch": 0.71, + "learning_rate": 1.5242829204693613e-05, + "loss": 0.2692, + "step": 8757 + }, + { + "epoch": 0.71, + "learning_rate": 1.5242285962624947e-05, + "loss": 0.4097, + "step": 8758 + }, + { + "epoch": 0.71, + "learning_rate": 1.5241742720556281e-05, + "loss": 0.3421, + "step": 8759 + }, + { + "epoch": 0.71, + "learning_rate": 1.5241199478487616e-05, + "loss": 0.6088, + "step": 8760 + }, + { + "epoch": 0.71, + "learning_rate": 1.524065623641895e-05, + "loss": 0.2811, + "step": 8761 + }, + { + "epoch": 0.71, + "learning_rate": 1.5240112994350284e-05, + "loss": 0.3918, + "step": 8762 + }, + { + "epoch": 0.71, + "learning_rate": 1.5239569752281618e-05, + "loss": 0.6666, + "step": 8763 + }, + { + "epoch": 0.71, + "learning_rate": 1.5239026510212952e-05, + "loss": 0.4795, + "step": 8764 + }, + { + "epoch": 0.71, + "learning_rate": 1.5238483268144287e-05, + "loss": 0.3632, + "step": 8765 + }, + { + "epoch": 0.71, + "learning_rate": 1.5237940026075621e-05, + "loss": 0.5088, + "step": 8766 + }, + { + "epoch": 0.71, + "learning_rate": 1.5237396784006955e-05, + "loss": 0.4067, + "step": 8767 + }, + { + "epoch": 0.71, + "learning_rate": 1.5236853541938288e-05, + "loss": 0.4689, + "step": 8768 + }, + { + "epoch": 0.71, + "learning_rate": 1.5236310299869624e-05, + "loss": 0.2361, + "step": 8769 + }, + { + "epoch": 0.71, + "learning_rate": 1.5235767057800956e-05, + "loss": 0.4168, + "step": 8770 + }, + { + "epoch": 0.71, + "learning_rate": 1.5235223815732292e-05, + "loss": 0.6116, + "step": 8771 + }, + { + "epoch": 0.71, + "learning_rate": 1.5234680573663625e-05, + "loss": 0.5129, + "step": 8772 + }, + { + "epoch": 0.71, + "learning_rate": 1.523413733159496e-05, + "loss": 0.3406, + "step": 8773 + }, + { + "epoch": 0.71, + "learning_rate": 1.5233594089526293e-05, + "loss": 0.4728, + "step": 8774 + }, + { + "epoch": 0.72, + "learning_rate": 1.5233050847457629e-05, + "loss": 0.422, + "step": 8775 + }, + { + "epoch": 0.72, + "learning_rate": 1.5232507605388962e-05, + "loss": 0.5915, + "step": 8776 + }, + { + "epoch": 0.72, + "learning_rate": 1.5231964363320297e-05, + "loss": 0.4259, + "step": 8777 + }, + { + "epoch": 0.72, + "learning_rate": 1.523142112125163e-05, + "loss": 0.3997, + "step": 8778 + }, + { + "epoch": 0.72, + "learning_rate": 1.5230877879182966e-05, + "loss": 0.2847, + "step": 8779 + }, + { + "epoch": 0.72, + "learning_rate": 1.5230334637114298e-05, + "loss": 0.6045, + "step": 8780 + }, + { + "epoch": 0.72, + "learning_rate": 1.5229791395045634e-05, + "loss": 0.5392, + "step": 8781 + }, + { + "epoch": 0.72, + "learning_rate": 1.5229248152976967e-05, + "loss": 0.3202, + "step": 8782 + }, + { + "epoch": 0.72, + "learning_rate": 1.5228704910908303e-05, + "loss": 0.509, + "step": 8783 + }, + { + "epoch": 0.72, + "learning_rate": 1.5228161668839635e-05, + "loss": 0.387, + "step": 8784 + }, + { + "epoch": 0.72, + "learning_rate": 1.5227618426770971e-05, + "loss": 0.4722, + "step": 8785 + }, + { + "epoch": 0.72, + "learning_rate": 1.5227075184702304e-05, + "loss": 0.4941, + "step": 8786 + }, + { + "epoch": 0.72, + "learning_rate": 1.5226531942633638e-05, + "loss": 0.4767, + "step": 8787 + }, + { + "epoch": 0.72, + "learning_rate": 1.5225988700564972e-05, + "loss": 0.3529, + "step": 8788 + }, + { + "epoch": 0.72, + "learning_rate": 1.5225445458496307e-05, + "loss": 0.7529, + "step": 8789 + }, + { + "epoch": 0.72, + "learning_rate": 1.5224902216427642e-05, + "loss": 0.363, + "step": 8790 + }, + { + "epoch": 0.72, + "learning_rate": 1.5224358974358975e-05, + "loss": 0.6726, + "step": 8791 + }, + { + "epoch": 0.72, + "learning_rate": 1.5223815732290311e-05, + "loss": 0.5177, + "step": 8792 + }, + { + "epoch": 0.72, + "learning_rate": 1.5223272490221643e-05, + "loss": 0.5311, + "step": 8793 + }, + { + "epoch": 0.72, + "learning_rate": 1.522272924815298e-05, + "loss": 0.4528, + "step": 8794 + }, + { + "epoch": 0.72, + "learning_rate": 1.5222186006084312e-05, + "loss": 0.2783, + "step": 8795 + }, + { + "epoch": 0.72, + "learning_rate": 1.5221642764015648e-05, + "loss": 0.3159, + "step": 8796 + }, + { + "epoch": 0.72, + "learning_rate": 1.522109952194698e-05, + "loss": 0.5966, + "step": 8797 + }, + { + "epoch": 0.72, + "learning_rate": 1.5220556279878316e-05, + "loss": 0.4219, + "step": 8798 + }, + { + "epoch": 0.72, + "learning_rate": 1.5220013037809649e-05, + "loss": 0.4945, + "step": 8799 + }, + { + "epoch": 0.72, + "learning_rate": 1.5219469795740985e-05, + "loss": 0.3618, + "step": 8800 + }, + { + "epoch": 0.72, + "learning_rate": 1.5218926553672317e-05, + "loss": 0.776, + "step": 8801 + }, + { + "epoch": 0.72, + "learning_rate": 1.5218383311603653e-05, + "loss": 0.1751, + "step": 8802 + }, + { + "epoch": 0.72, + "learning_rate": 1.5217840069534986e-05, + "loss": 0.4104, + "step": 8803 + }, + { + "epoch": 0.72, + "learning_rate": 1.5217296827466322e-05, + "loss": 0.4571, + "step": 8804 + }, + { + "epoch": 0.72, + "learning_rate": 1.5216753585397654e-05, + "loss": 0.5062, + "step": 8805 + }, + { + "epoch": 0.72, + "learning_rate": 1.5216210343328987e-05, + "loss": 0.5128, + "step": 8806 + }, + { + "epoch": 0.72, + "learning_rate": 1.5215667101260323e-05, + "loss": 0.3618, + "step": 8807 + }, + { + "epoch": 0.72, + "learning_rate": 1.5215123859191657e-05, + "loss": 0.4126, + "step": 8808 + }, + { + "epoch": 0.72, + "learning_rate": 1.5214580617122991e-05, + "loss": 0.5585, + "step": 8809 + }, + { + "epoch": 0.72, + "learning_rate": 1.5214037375054325e-05, + "loss": 0.4604, + "step": 8810 + }, + { + "epoch": 0.72, + "learning_rate": 1.521349413298566e-05, + "loss": 0.4219, + "step": 8811 + }, + { + "epoch": 0.72, + "learning_rate": 1.5212950890916994e-05, + "loss": 0.3113, + "step": 8812 + }, + { + "epoch": 0.72, + "learning_rate": 1.5212407648848328e-05, + "loss": 0.4522, + "step": 8813 + }, + { + "epoch": 0.72, + "learning_rate": 1.5211864406779662e-05, + "loss": 0.2918, + "step": 8814 + }, + { + "epoch": 0.72, + "learning_rate": 1.5211321164710997e-05, + "loss": 0.6921, + "step": 8815 + }, + { + "epoch": 0.72, + "learning_rate": 1.521077792264233e-05, + "loss": 0.3207, + "step": 8816 + }, + { + "epoch": 0.72, + "learning_rate": 1.5210234680573665e-05, + "loss": 0.2979, + "step": 8817 + }, + { + "epoch": 0.72, + "learning_rate": 1.5209691438505e-05, + "loss": 0.5775, + "step": 8818 + }, + { + "epoch": 0.72, + "learning_rate": 1.5209148196436333e-05, + "loss": 0.6181, + "step": 8819 + }, + { + "epoch": 0.72, + "learning_rate": 1.5208604954367668e-05, + "loss": 0.5031, + "step": 8820 + }, + { + "epoch": 0.72, + "learning_rate": 1.5208061712299002e-05, + "loss": 0.2549, + "step": 8821 + }, + { + "epoch": 0.72, + "learning_rate": 1.5207518470230336e-05, + "loss": 0.3244, + "step": 8822 + }, + { + "epoch": 0.72, + "learning_rate": 1.520697522816167e-05, + "loss": 0.1632, + "step": 8823 + }, + { + "epoch": 0.72, + "learning_rate": 1.5206431986093005e-05, + "loss": 0.5372, + "step": 8824 + }, + { + "epoch": 0.72, + "learning_rate": 1.5205888744024337e-05, + "loss": 0.6069, + "step": 8825 + }, + { + "epoch": 0.72, + "learning_rate": 1.5205345501955673e-05, + "loss": 0.3382, + "step": 8826 + }, + { + "epoch": 0.72, + "learning_rate": 1.5204802259887006e-05, + "loss": 0.5092, + "step": 8827 + }, + { + "epoch": 0.72, + "learning_rate": 1.5204259017818342e-05, + "loss": 0.4901, + "step": 8828 + }, + { + "epoch": 0.72, + "learning_rate": 1.5203715775749674e-05, + "loss": 0.9576, + "step": 8829 + }, + { + "epoch": 0.72, + "learning_rate": 1.520317253368101e-05, + "loss": 0.6992, + "step": 8830 + }, + { + "epoch": 0.72, + "learning_rate": 1.5202629291612343e-05, + "loss": 0.4515, + "step": 8831 + }, + { + "epoch": 0.72, + "learning_rate": 1.5202086049543678e-05, + "loss": 0.7595, + "step": 8832 + }, + { + "epoch": 0.72, + "learning_rate": 1.5201542807475011e-05, + "loss": 0.5071, + "step": 8833 + }, + { + "epoch": 0.72, + "learning_rate": 1.5200999565406347e-05, + "loss": 0.5197, + "step": 8834 + }, + { + "epoch": 0.72, + "learning_rate": 1.520045632333768e-05, + "loss": 0.5427, + "step": 8835 + }, + { + "epoch": 0.72, + "learning_rate": 1.5199913081269015e-05, + "loss": 0.372, + "step": 8836 + }, + { + "epoch": 0.72, + "learning_rate": 1.5199369839200348e-05, + "loss": 0.3777, + "step": 8837 + }, + { + "epoch": 0.72, + "learning_rate": 1.5198826597131684e-05, + "loss": 0.187, + "step": 8838 + }, + { + "epoch": 0.72, + "learning_rate": 1.5198283355063016e-05, + "loss": 0.3911, + "step": 8839 + }, + { + "epoch": 0.72, + "learning_rate": 1.5197740112994352e-05, + "loss": 0.3269, + "step": 8840 + }, + { + "epoch": 0.72, + "learning_rate": 1.5197196870925685e-05, + "loss": 0.2633, + "step": 8841 + }, + { + "epoch": 0.72, + "learning_rate": 1.519665362885702e-05, + "loss": 0.2844, + "step": 8842 + }, + { + "epoch": 0.72, + "learning_rate": 1.5196110386788353e-05, + "loss": 0.6396, + "step": 8843 + }, + { + "epoch": 0.72, + "learning_rate": 1.5195567144719688e-05, + "loss": 0.347, + "step": 8844 + }, + { + "epoch": 0.72, + "learning_rate": 1.5195023902651023e-05, + "loss": 0.745, + "step": 8845 + }, + { + "epoch": 0.72, + "learning_rate": 1.5194480660582356e-05, + "loss": 0.3291, + "step": 8846 + }, + { + "epoch": 0.72, + "learning_rate": 1.5193937418513692e-05, + "loss": 0.7388, + "step": 8847 + }, + { + "epoch": 0.72, + "learning_rate": 1.5193394176445024e-05, + "loss": 0.8637, + "step": 8848 + }, + { + "epoch": 0.72, + "learning_rate": 1.519285093437636e-05, + "loss": 0.351, + "step": 8849 + }, + { + "epoch": 0.72, + "learning_rate": 1.5192307692307693e-05, + "loss": 0.5468, + "step": 8850 + }, + { + "epoch": 0.72, + "learning_rate": 1.5191764450239029e-05, + "loss": 0.6431, + "step": 8851 + }, + { + "epoch": 0.72, + "learning_rate": 1.5191221208170361e-05, + "loss": 0.3816, + "step": 8852 + }, + { + "epoch": 0.72, + "learning_rate": 1.5190677966101697e-05, + "loss": 0.3715, + "step": 8853 + }, + { + "epoch": 0.72, + "learning_rate": 1.519013472403303e-05, + "loss": 0.4546, + "step": 8854 + }, + { + "epoch": 0.72, + "learning_rate": 1.5189591481964366e-05, + "loss": 0.4546, + "step": 8855 + }, + { + "epoch": 0.72, + "learning_rate": 1.5189048239895698e-05, + "loss": 0.3841, + "step": 8856 + }, + { + "epoch": 0.72, + "learning_rate": 1.5188504997827034e-05, + "loss": 0.6488, + "step": 8857 + }, + { + "epoch": 0.72, + "learning_rate": 1.5187961755758367e-05, + "loss": 0.6088, + "step": 8858 + }, + { + "epoch": 0.72, + "learning_rate": 1.5187418513689703e-05, + "loss": 0.4971, + "step": 8859 + }, + { + "epoch": 0.72, + "learning_rate": 1.5186875271621035e-05, + "loss": 0.4313, + "step": 8860 + }, + { + "epoch": 0.72, + "learning_rate": 1.5186332029552371e-05, + "loss": 0.3403, + "step": 8861 + }, + { + "epoch": 0.72, + "learning_rate": 1.5185788787483704e-05, + "loss": 0.2919, + "step": 8862 + }, + { + "epoch": 0.72, + "learning_rate": 1.5185245545415038e-05, + "loss": 0.2703, + "step": 8863 + }, + { + "epoch": 0.72, + "learning_rate": 1.5184702303346372e-05, + "loss": 0.3616, + "step": 8864 + }, + { + "epoch": 0.72, + "learning_rate": 1.5184159061277706e-05, + "loss": 0.3859, + "step": 8865 + }, + { + "epoch": 0.72, + "learning_rate": 1.518361581920904e-05, + "loss": 0.5563, + "step": 8866 + }, + { + "epoch": 0.72, + "learning_rate": 1.5183072577140375e-05, + "loss": 0.5448, + "step": 8867 + }, + { + "epoch": 0.72, + "learning_rate": 1.5182529335071709e-05, + "loss": 0.3951, + "step": 8868 + }, + { + "epoch": 0.72, + "learning_rate": 1.5181986093003043e-05, + "loss": 0.4885, + "step": 8869 + }, + { + "epoch": 0.72, + "learning_rate": 1.5181442850934378e-05, + "loss": 0.3053, + "step": 8870 + }, + { + "epoch": 0.72, + "learning_rate": 1.5180899608865712e-05, + "loss": 0.5398, + "step": 8871 + }, + { + "epoch": 0.72, + "learning_rate": 1.5180356366797046e-05, + "loss": 0.3505, + "step": 8872 + }, + { + "epoch": 0.72, + "learning_rate": 1.517981312472838e-05, + "loss": 0.3464, + "step": 8873 + }, + { + "epoch": 0.72, + "learning_rate": 1.5179269882659714e-05, + "loss": 0.4613, + "step": 8874 + }, + { + "epoch": 0.72, + "learning_rate": 1.5178726640591049e-05, + "loss": 0.3556, + "step": 8875 + }, + { + "epoch": 0.72, + "learning_rate": 1.5178183398522383e-05, + "loss": 0.2269, + "step": 8876 + }, + { + "epoch": 0.72, + "learning_rate": 1.5177640156453717e-05, + "loss": 0.602, + "step": 8877 + }, + { + "epoch": 0.72, + "learning_rate": 1.5177096914385051e-05, + "loss": 0.252, + "step": 8878 + }, + { + "epoch": 0.72, + "learning_rate": 1.5176553672316386e-05, + "loss": 0.7029, + "step": 8879 + }, + { + "epoch": 0.72, + "learning_rate": 1.517601043024772e-05, + "loss": 0.5399, + "step": 8880 + }, + { + "epoch": 0.72, + "learning_rate": 1.5175467188179054e-05, + "loss": 0.4314, + "step": 8881 + }, + { + "epoch": 0.72, + "learning_rate": 1.5174923946110387e-05, + "loss": 0.5359, + "step": 8882 + }, + { + "epoch": 0.72, + "learning_rate": 1.5174380704041723e-05, + "loss": 0.3438, + "step": 8883 + }, + { + "epoch": 0.72, + "learning_rate": 1.5173837461973055e-05, + "loss": 0.5217, + "step": 8884 + }, + { + "epoch": 0.72, + "learning_rate": 1.5173294219904391e-05, + "loss": 0.5426, + "step": 8885 + }, + { + "epoch": 0.72, + "learning_rate": 1.5172750977835724e-05, + "loss": 0.4588, + "step": 8886 + }, + { + "epoch": 0.72, + "learning_rate": 1.517220773576706e-05, + "loss": 0.6195, + "step": 8887 + }, + { + "epoch": 0.72, + "learning_rate": 1.5171664493698392e-05, + "loss": 0.6975, + "step": 8888 + }, + { + "epoch": 0.72, + "learning_rate": 1.5171121251629728e-05, + "loss": 0.3041, + "step": 8889 + }, + { + "epoch": 0.72, + "learning_rate": 1.517057800956106e-05, + "loss": 0.4546, + "step": 8890 + }, + { + "epoch": 0.72, + "learning_rate": 1.5170034767492396e-05, + "loss": 0.4102, + "step": 8891 + }, + { + "epoch": 0.72, + "learning_rate": 1.5169491525423729e-05, + "loss": 0.427, + "step": 8892 + }, + { + "epoch": 0.72, + "learning_rate": 1.5168948283355065e-05, + "loss": 0.5516, + "step": 8893 + }, + { + "epoch": 0.72, + "learning_rate": 1.5168405041286397e-05, + "loss": 0.5497, + "step": 8894 + }, + { + "epoch": 0.72, + "learning_rate": 1.5167861799217733e-05, + "loss": 0.4799, + "step": 8895 + }, + { + "epoch": 0.72, + "learning_rate": 1.5167318557149066e-05, + "loss": 0.6134, + "step": 8896 + }, + { + "epoch": 0.72, + "learning_rate": 1.5166775315080402e-05, + "loss": 0.2876, + "step": 8897 + }, + { + "epoch": 0.73, + "learning_rate": 1.5166232073011736e-05, + "loss": 0.1857, + "step": 8898 + }, + { + "epoch": 0.73, + "learning_rate": 1.516568883094307e-05, + "loss": 0.3118, + "step": 8899 + }, + { + "epoch": 0.73, + "learning_rate": 1.5165145588874404e-05, + "loss": 0.4605, + "step": 8900 + }, + { + "epoch": 0.73, + "learning_rate": 1.5164602346805737e-05, + "loss": 0.4588, + "step": 8901 + }, + { + "epoch": 0.73, + "learning_rate": 1.5164059104737073e-05, + "loss": 0.4946, + "step": 8902 + }, + { + "epoch": 0.73, + "learning_rate": 1.5163515862668405e-05, + "loss": 0.5085, + "step": 8903 + }, + { + "epoch": 0.73, + "learning_rate": 1.5162972620599741e-05, + "loss": 0.6555, + "step": 8904 + }, + { + "epoch": 0.73, + "learning_rate": 1.5162429378531074e-05, + "loss": 0.6267, + "step": 8905 + }, + { + "epoch": 0.73, + "learning_rate": 1.516188613646241e-05, + "loss": 0.576, + "step": 8906 + }, + { + "epoch": 0.73, + "learning_rate": 1.5161342894393742e-05, + "loss": 0.3808, + "step": 8907 + }, + { + "epoch": 0.73, + "learning_rate": 1.5160799652325078e-05, + "loss": 0.5174, + "step": 8908 + }, + { + "epoch": 0.73, + "learning_rate": 1.516025641025641e-05, + "loss": 0.2423, + "step": 8909 + }, + { + "epoch": 0.73, + "learning_rate": 1.5159713168187747e-05, + "loss": 0.5139, + "step": 8910 + }, + { + "epoch": 0.73, + "learning_rate": 1.515916992611908e-05, + "loss": 0.3014, + "step": 8911 + }, + { + "epoch": 0.73, + "learning_rate": 1.5158626684050415e-05, + "loss": 0.5311, + "step": 8912 + }, + { + "epoch": 0.73, + "learning_rate": 1.5158083441981748e-05, + "loss": 0.3739, + "step": 8913 + }, + { + "epoch": 0.73, + "learning_rate": 1.5157540199913084e-05, + "loss": 0.5997, + "step": 8914 + }, + { + "epoch": 0.73, + "learning_rate": 1.5156996957844416e-05, + "loss": 0.3767, + "step": 8915 + }, + { + "epoch": 0.73, + "learning_rate": 1.5156453715775752e-05, + "loss": 0.574, + "step": 8916 + }, + { + "epoch": 0.73, + "learning_rate": 1.5155910473707085e-05, + "loss": 0.5899, + "step": 8917 + }, + { + "epoch": 0.73, + "learning_rate": 1.515536723163842e-05, + "loss": 0.3358, + "step": 8918 + }, + { + "epoch": 0.73, + "learning_rate": 1.5154823989569753e-05, + "loss": 0.2724, + "step": 8919 + }, + { + "epoch": 0.73, + "learning_rate": 1.5154280747501087e-05, + "loss": 0.59, + "step": 8920 + }, + { + "epoch": 0.73, + "learning_rate": 1.5153737505432422e-05, + "loss": 0.3069, + "step": 8921 + }, + { + "epoch": 0.73, + "learning_rate": 1.5153194263363756e-05, + "loss": 0.2794, + "step": 8922 + }, + { + "epoch": 0.73, + "learning_rate": 1.515265102129509e-05, + "loss": 0.3949, + "step": 8923 + }, + { + "epoch": 0.73, + "learning_rate": 1.5152107779226424e-05, + "loss": 0.5063, + "step": 8924 + }, + { + "epoch": 0.73, + "learning_rate": 1.5151564537157759e-05, + "loss": 0.4915, + "step": 8925 + }, + { + "epoch": 0.73, + "learning_rate": 1.5151021295089093e-05, + "loss": 0.7689, + "step": 8926 + }, + { + "epoch": 0.73, + "learning_rate": 1.5150478053020427e-05, + "loss": 0.4214, + "step": 8927 + }, + { + "epoch": 0.73, + "learning_rate": 1.5149934810951761e-05, + "loss": 0.3572, + "step": 8928 + }, + { + "epoch": 0.73, + "learning_rate": 1.5149391568883095e-05, + "loss": 0.5847, + "step": 8929 + }, + { + "epoch": 0.73, + "learning_rate": 1.514884832681443e-05, + "loss": 0.333, + "step": 8930 + }, + { + "epoch": 0.73, + "learning_rate": 1.5148305084745764e-05, + "loss": 0.4398, + "step": 8931 + }, + { + "epoch": 0.73, + "learning_rate": 1.5147761842677098e-05, + "loss": 0.67, + "step": 8932 + }, + { + "epoch": 0.73, + "learning_rate": 1.5147218600608432e-05, + "loss": 0.4109, + "step": 8933 + }, + { + "epoch": 0.73, + "learning_rate": 1.5146675358539767e-05, + "loss": 0.3201, + "step": 8934 + }, + { + "epoch": 0.73, + "learning_rate": 1.5146132116471103e-05, + "loss": 0.4364, + "step": 8935 + }, + { + "epoch": 0.73, + "learning_rate": 1.5145588874402435e-05, + "loss": 0.3274, + "step": 8936 + }, + { + "epoch": 0.73, + "learning_rate": 1.5145045632333771e-05, + "loss": 0.236, + "step": 8937 + }, + { + "epoch": 0.73, + "learning_rate": 1.5144502390265104e-05, + "loss": 0.5349, + "step": 8938 + }, + { + "epoch": 0.73, + "learning_rate": 1.5143959148196436e-05, + "loss": 0.4929, + "step": 8939 + }, + { + "epoch": 0.73, + "learning_rate": 1.5143415906127772e-05, + "loss": 0.2465, + "step": 8940 + }, + { + "epoch": 0.73, + "learning_rate": 1.5142872664059105e-05, + "loss": 0.7511, + "step": 8941 + }, + { + "epoch": 0.73, + "learning_rate": 1.514232942199044e-05, + "loss": 0.5477, + "step": 8942 + }, + { + "epoch": 0.73, + "learning_rate": 1.5141786179921773e-05, + "loss": 0.3141, + "step": 8943 + }, + { + "epoch": 0.73, + "learning_rate": 1.5141242937853109e-05, + "loss": 0.5623, + "step": 8944 + }, + { + "epoch": 0.73, + "learning_rate": 1.5140699695784441e-05, + "loss": 0.2945, + "step": 8945 + }, + { + "epoch": 0.73, + "learning_rate": 1.5140156453715777e-05, + "loss": 0.6016, + "step": 8946 + }, + { + "epoch": 0.73, + "learning_rate": 1.513961321164711e-05, + "loss": 0.3994, + "step": 8947 + }, + { + "epoch": 0.73, + "learning_rate": 1.5139069969578446e-05, + "loss": 0.428, + "step": 8948 + }, + { + "epoch": 0.73, + "learning_rate": 1.5138526727509778e-05, + "loss": 0.5492, + "step": 8949 + }, + { + "epoch": 0.73, + "learning_rate": 1.5137983485441114e-05, + "loss": 0.5951, + "step": 8950 + }, + { + "epoch": 0.73, + "learning_rate": 1.5137440243372447e-05, + "loss": 0.7731, + "step": 8951 + }, + { + "epoch": 0.73, + "learning_rate": 1.5136897001303783e-05, + "loss": 0.448, + "step": 8952 + }, + { + "epoch": 0.73, + "learning_rate": 1.5136353759235117e-05, + "loss": 0.3093, + "step": 8953 + }, + { + "epoch": 0.73, + "learning_rate": 1.5135810517166451e-05, + "loss": 0.3927, + "step": 8954 + }, + { + "epoch": 0.73, + "learning_rate": 1.5135267275097785e-05, + "loss": 0.4234, + "step": 8955 + }, + { + "epoch": 0.73, + "learning_rate": 1.513472403302912e-05, + "loss": 0.384, + "step": 8956 + }, + { + "epoch": 0.73, + "learning_rate": 1.5134180790960454e-05, + "loss": 0.3933, + "step": 8957 + }, + { + "epoch": 0.73, + "learning_rate": 1.5133637548891786e-05, + "loss": 0.4601, + "step": 8958 + }, + { + "epoch": 0.73, + "learning_rate": 1.5133094306823122e-05, + "loss": 0.5225, + "step": 8959 + }, + { + "epoch": 0.73, + "learning_rate": 1.5132551064754455e-05, + "loss": 0.5051, + "step": 8960 + }, + { + "epoch": 0.73, + "learning_rate": 1.513200782268579e-05, + "loss": 0.5373, + "step": 8961 + }, + { + "epoch": 0.73, + "learning_rate": 1.5131464580617123e-05, + "loss": 0.4682, + "step": 8962 + }, + { + "epoch": 0.73, + "learning_rate": 1.513092133854846e-05, + "loss": 0.3838, + "step": 8963 + }, + { + "epoch": 0.73, + "learning_rate": 1.5130378096479792e-05, + "loss": 0.4215, + "step": 8964 + }, + { + "epoch": 0.73, + "learning_rate": 1.5129834854411128e-05, + "loss": 0.377, + "step": 8965 + }, + { + "epoch": 0.73, + "learning_rate": 1.512929161234246e-05, + "loss": 0.3713, + "step": 8966 + }, + { + "epoch": 0.73, + "learning_rate": 1.5128748370273796e-05, + "loss": 0.3711, + "step": 8967 + }, + { + "epoch": 0.73, + "learning_rate": 1.5128205128205129e-05, + "loss": 0.4654, + "step": 8968 + }, + { + "epoch": 0.73, + "learning_rate": 1.5127661886136465e-05, + "loss": 0.3702, + "step": 8969 + }, + { + "epoch": 0.73, + "learning_rate": 1.5127118644067797e-05, + "loss": 0.3, + "step": 8970 + }, + { + "epoch": 0.73, + "learning_rate": 1.5126575401999133e-05, + "loss": 0.5792, + "step": 8971 + }, + { + "epoch": 0.73, + "learning_rate": 1.5126032159930466e-05, + "loss": 0.38, + "step": 8972 + }, + { + "epoch": 0.73, + "learning_rate": 1.5125488917861802e-05, + "loss": 0.4052, + "step": 8973 + }, + { + "epoch": 0.73, + "learning_rate": 1.5124945675793134e-05, + "loss": 0.3763, + "step": 8974 + }, + { + "epoch": 0.73, + "learning_rate": 1.512440243372447e-05, + "loss": 0.5033, + "step": 8975 + }, + { + "epoch": 0.73, + "learning_rate": 1.5123859191655803e-05, + "loss": 0.4417, + "step": 8976 + }, + { + "epoch": 0.73, + "learning_rate": 1.5123315949587137e-05, + "loss": 0.4088, + "step": 8977 + }, + { + "epoch": 0.73, + "learning_rate": 1.5122772707518471e-05, + "loss": 0.1496, + "step": 8978 + }, + { + "epoch": 0.73, + "learning_rate": 1.5122229465449805e-05, + "loss": 0.4099, + "step": 8979 + }, + { + "epoch": 0.73, + "learning_rate": 1.512168622338114e-05, + "loss": 0.5085, + "step": 8980 + }, + { + "epoch": 0.73, + "learning_rate": 1.5121142981312474e-05, + "loss": 0.5087, + "step": 8981 + }, + { + "epoch": 0.73, + "learning_rate": 1.5120599739243808e-05, + "loss": 0.5922, + "step": 8982 + }, + { + "epoch": 0.73, + "learning_rate": 1.5120056497175142e-05, + "loss": 0.3243, + "step": 8983 + }, + { + "epoch": 0.73, + "learning_rate": 1.5119513255106476e-05, + "loss": 0.2559, + "step": 8984 + }, + { + "epoch": 0.73, + "learning_rate": 1.511897001303781e-05, + "loss": 0.5048, + "step": 8985 + }, + { + "epoch": 0.73, + "learning_rate": 1.5118426770969145e-05, + "loss": 0.3851, + "step": 8986 + }, + { + "epoch": 0.73, + "learning_rate": 1.5117883528900479e-05, + "loss": 0.3278, + "step": 8987 + }, + { + "epoch": 0.73, + "learning_rate": 1.5117340286831813e-05, + "loss": 0.2811, + "step": 8988 + }, + { + "epoch": 0.73, + "learning_rate": 1.5116797044763148e-05, + "loss": 0.3737, + "step": 8989 + }, + { + "epoch": 0.73, + "learning_rate": 1.5116253802694484e-05, + "loss": 0.3915, + "step": 8990 + }, + { + "epoch": 0.73, + "learning_rate": 1.5115710560625816e-05, + "loss": 0.5493, + "step": 8991 + }, + { + "epoch": 0.73, + "learning_rate": 1.5115167318557152e-05, + "loss": 0.5434, + "step": 8992 + }, + { + "epoch": 0.73, + "learning_rate": 1.5114624076488485e-05, + "loss": 0.5316, + "step": 8993 + }, + { + "epoch": 0.73, + "learning_rate": 1.511408083441982e-05, + "loss": 0.5093, + "step": 8994 + }, + { + "epoch": 0.73, + "learning_rate": 1.5113537592351153e-05, + "loss": 0.4288, + "step": 8995 + }, + { + "epoch": 0.73, + "learning_rate": 1.5112994350282486e-05, + "loss": 0.242, + "step": 8996 + }, + { + "epoch": 0.73, + "learning_rate": 1.5112451108213821e-05, + "loss": 0.5388, + "step": 8997 + }, + { + "epoch": 0.73, + "learning_rate": 1.5111907866145154e-05, + "loss": 0.2338, + "step": 8998 + }, + { + "epoch": 0.73, + "learning_rate": 1.511136462407649e-05, + "loss": 0.3955, + "step": 8999 + }, + { + "epoch": 0.73, + "learning_rate": 1.5110821382007822e-05, + "loss": 0.5588, + "step": 9000 + }, + { + "epoch": 0.73, + "eval_accuracy": 0.8293428425878757, + "eval_loss": 0.4501349627971649, + "eval_runtime": 22.3271, + "eval_samples_per_second": 439.601, + "eval_steps_per_second": 3.449, + "step": 9000 + }, + { + "epoch": 0.73, + "learning_rate": 1.5110278139939158e-05, + "loss": 0.2747, + "step": 9001 + }, + { + "epoch": 0.73, + "learning_rate": 1.5109734897870491e-05, + "loss": 0.5685, + "step": 9002 + }, + { + "epoch": 0.73, + "learning_rate": 1.5109191655801827e-05, + "loss": 0.7048, + "step": 9003 + }, + { + "epoch": 0.73, + "learning_rate": 1.510864841373316e-05, + "loss": 0.5426, + "step": 9004 + }, + { + "epoch": 0.73, + "learning_rate": 1.5108105171664495e-05, + "loss": 0.4651, + "step": 9005 + }, + { + "epoch": 0.73, + "learning_rate": 1.510756192959583e-05, + "loss": 0.5835, + "step": 9006 + }, + { + "epoch": 0.73, + "learning_rate": 1.5107018687527164e-05, + "loss": 0.3569, + "step": 9007 + }, + { + "epoch": 0.73, + "learning_rate": 1.5106475445458498e-05, + "loss": 0.6057, + "step": 9008 + }, + { + "epoch": 0.73, + "learning_rate": 1.5105932203389832e-05, + "loss": 0.2903, + "step": 9009 + }, + { + "epoch": 0.73, + "learning_rate": 1.5105388961321166e-05, + "loss": 0.3072, + "step": 9010 + }, + { + "epoch": 0.73, + "learning_rate": 1.51048457192525e-05, + "loss": 0.6094, + "step": 9011 + }, + { + "epoch": 0.73, + "learning_rate": 1.5104302477183835e-05, + "loss": 0.531, + "step": 9012 + }, + { + "epoch": 0.73, + "learning_rate": 1.5103759235115169e-05, + "loss": 0.2275, + "step": 9013 + }, + { + "epoch": 0.73, + "learning_rate": 1.5103215993046503e-05, + "loss": 0.406, + "step": 9014 + }, + { + "epoch": 0.73, + "learning_rate": 1.5102672750977836e-05, + "loss": 0.4088, + "step": 9015 + }, + { + "epoch": 0.73, + "learning_rate": 1.5102129508909172e-05, + "loss": 0.777, + "step": 9016 + }, + { + "epoch": 0.73, + "learning_rate": 1.5101586266840504e-05, + "loss": 0.4664, + "step": 9017 + }, + { + "epoch": 0.73, + "learning_rate": 1.510104302477184e-05, + "loss": 0.183, + "step": 9018 + }, + { + "epoch": 0.73, + "learning_rate": 1.5100499782703173e-05, + "loss": 0.3695, + "step": 9019 + }, + { + "epoch": 0.74, + "learning_rate": 1.5099956540634509e-05, + "loss": 0.5333, + "step": 9020 + }, + { + "epoch": 0.74, + "learning_rate": 1.5099413298565841e-05, + "loss": 0.5456, + "step": 9021 + }, + { + "epoch": 0.74, + "learning_rate": 1.5098870056497177e-05, + "loss": 0.459, + "step": 9022 + }, + { + "epoch": 0.74, + "learning_rate": 1.509832681442851e-05, + "loss": 0.4587, + "step": 9023 + }, + { + "epoch": 0.74, + "learning_rate": 1.5097783572359846e-05, + "loss": 0.2957, + "step": 9024 + }, + { + "epoch": 0.74, + "learning_rate": 1.5097240330291178e-05, + "loss": 0.3818, + "step": 9025 + }, + { + "epoch": 0.74, + "learning_rate": 1.5096697088222514e-05, + "loss": 0.2735, + "step": 9026 + }, + { + "epoch": 0.74, + "learning_rate": 1.5096153846153847e-05, + "loss": 0.2512, + "step": 9027 + }, + { + "epoch": 0.74, + "learning_rate": 1.5095610604085183e-05, + "loss": 0.1709, + "step": 9028 + }, + { + "epoch": 0.74, + "learning_rate": 1.5095067362016515e-05, + "loss": 0.7322, + "step": 9029 + }, + { + "epoch": 0.74, + "learning_rate": 1.5094524119947851e-05, + "loss": 0.4076, + "step": 9030 + }, + { + "epoch": 0.74, + "learning_rate": 1.5093980877879184e-05, + "loss": 0.288, + "step": 9031 + }, + { + "epoch": 0.74, + "learning_rate": 1.509343763581052e-05, + "loss": 0.4142, + "step": 9032 + }, + { + "epoch": 0.74, + "learning_rate": 1.5092894393741852e-05, + "loss": 0.6107, + "step": 9033 + }, + { + "epoch": 0.74, + "learning_rate": 1.5092351151673186e-05, + "loss": 0.5653, + "step": 9034 + }, + { + "epoch": 0.74, + "learning_rate": 1.509180790960452e-05, + "loss": 0.6562, + "step": 9035 + }, + { + "epoch": 0.74, + "learning_rate": 1.5091264667535855e-05, + "loss": 0.4637, + "step": 9036 + }, + { + "epoch": 0.74, + "learning_rate": 1.5090721425467189e-05, + "loss": 0.4463, + "step": 9037 + }, + { + "epoch": 0.74, + "learning_rate": 1.5090178183398523e-05, + "loss": 0.2952, + "step": 9038 + }, + { + "epoch": 0.74, + "learning_rate": 1.5089634941329857e-05, + "loss": 0.5075, + "step": 9039 + }, + { + "epoch": 0.74, + "learning_rate": 1.5089091699261192e-05, + "loss": 0.5253, + "step": 9040 + }, + { + "epoch": 0.74, + "learning_rate": 1.5088548457192526e-05, + "loss": 0.2424, + "step": 9041 + }, + { + "epoch": 0.74, + "learning_rate": 1.508800521512386e-05, + "loss": 0.4914, + "step": 9042 + }, + { + "epoch": 0.74, + "learning_rate": 1.5087461973055196e-05, + "loss": 0.3819, + "step": 9043 + }, + { + "epoch": 0.74, + "learning_rate": 1.5086918730986529e-05, + "loss": 0.2714, + "step": 9044 + }, + { + "epoch": 0.74, + "learning_rate": 1.5086375488917864e-05, + "loss": 0.3383, + "step": 9045 + }, + { + "epoch": 0.74, + "learning_rate": 1.5085832246849197e-05, + "loss": 0.5329, + "step": 9046 + }, + { + "epoch": 0.74, + "learning_rate": 1.5085289004780533e-05, + "loss": 0.4825, + "step": 9047 + }, + { + "epoch": 0.74, + "learning_rate": 1.5084745762711865e-05, + "loss": 0.3816, + "step": 9048 + }, + { + "epoch": 0.74, + "learning_rate": 1.5084202520643201e-05, + "loss": 0.5507, + "step": 9049 + }, + { + "epoch": 0.74, + "learning_rate": 1.5083659278574534e-05, + "loss": 0.3172, + "step": 9050 + }, + { + "epoch": 0.74, + "learning_rate": 1.508311603650587e-05, + "loss": 0.9634, + "step": 9051 + }, + { + "epoch": 0.74, + "learning_rate": 1.5082572794437202e-05, + "loss": 0.6094, + "step": 9052 + }, + { + "epoch": 0.74, + "learning_rate": 1.5082029552368535e-05, + "loss": 0.5746, + "step": 9053 + }, + { + "epoch": 0.74, + "learning_rate": 1.5081486310299871e-05, + "loss": 0.5094, + "step": 9054 + }, + { + "epoch": 0.74, + "learning_rate": 1.5080943068231203e-05, + "loss": 0.4498, + "step": 9055 + }, + { + "epoch": 0.74, + "learning_rate": 1.508039982616254e-05, + "loss": 0.52, + "step": 9056 + }, + { + "epoch": 0.74, + "learning_rate": 1.5079856584093872e-05, + "loss": 0.5934, + "step": 9057 + }, + { + "epoch": 0.74, + "learning_rate": 1.5079313342025208e-05, + "loss": 0.4573, + "step": 9058 + }, + { + "epoch": 0.74, + "learning_rate": 1.507877009995654e-05, + "loss": 0.3215, + "step": 9059 + }, + { + "epoch": 0.74, + "learning_rate": 1.5078226857887876e-05, + "loss": 0.4013, + "step": 9060 + }, + { + "epoch": 0.74, + "learning_rate": 1.507768361581921e-05, + "loss": 0.6352, + "step": 9061 + }, + { + "epoch": 0.74, + "learning_rate": 1.5077140373750545e-05, + "loss": 0.7384, + "step": 9062 + }, + { + "epoch": 0.74, + "learning_rate": 1.5076597131681879e-05, + "loss": 0.4732, + "step": 9063 + }, + { + "epoch": 0.74, + "learning_rate": 1.5076053889613213e-05, + "loss": 0.5781, + "step": 9064 + }, + { + "epoch": 0.74, + "learning_rate": 1.5075510647544547e-05, + "loss": 0.593, + "step": 9065 + }, + { + "epoch": 0.74, + "learning_rate": 1.5074967405475882e-05, + "loss": 0.3991, + "step": 9066 + }, + { + "epoch": 0.74, + "learning_rate": 1.5074424163407216e-05, + "loss": 0.4483, + "step": 9067 + }, + { + "epoch": 0.74, + "learning_rate": 1.507388092133855e-05, + "loss": 0.4032, + "step": 9068 + }, + { + "epoch": 0.74, + "learning_rate": 1.5073337679269884e-05, + "loss": 0.6178, + "step": 9069 + }, + { + "epoch": 0.74, + "learning_rate": 1.5072794437201219e-05, + "loss": 0.333, + "step": 9070 + }, + { + "epoch": 0.74, + "learning_rate": 1.5072251195132553e-05, + "loss": 0.2946, + "step": 9071 + }, + { + "epoch": 0.74, + "learning_rate": 1.5071707953063885e-05, + "loss": 0.6255, + "step": 9072 + }, + { + "epoch": 0.74, + "learning_rate": 1.5071164710995221e-05, + "loss": 0.4974, + "step": 9073 + }, + { + "epoch": 0.74, + "learning_rate": 1.5070621468926554e-05, + "loss": 0.4774, + "step": 9074 + }, + { + "epoch": 0.74, + "learning_rate": 1.507007822685789e-05, + "loss": 0.3394, + "step": 9075 + }, + { + "epoch": 0.74, + "learning_rate": 1.5069534984789222e-05, + "loss": 0.3702, + "step": 9076 + }, + { + "epoch": 0.74, + "learning_rate": 1.5068991742720558e-05, + "loss": 0.5713, + "step": 9077 + }, + { + "epoch": 0.74, + "learning_rate": 1.506844850065189e-05, + "loss": 0.4429, + "step": 9078 + }, + { + "epoch": 0.74, + "learning_rate": 1.5067905258583227e-05, + "loss": 0.4791, + "step": 9079 + }, + { + "epoch": 0.74, + "learning_rate": 1.506736201651456e-05, + "loss": 0.6527, + "step": 9080 + }, + { + "epoch": 0.74, + "learning_rate": 1.5066818774445895e-05, + "loss": 0.5177, + "step": 9081 + }, + { + "epoch": 0.74, + "learning_rate": 1.5066275532377228e-05, + "loss": 0.2024, + "step": 9082 + }, + { + "epoch": 0.74, + "learning_rate": 1.5065732290308564e-05, + "loss": 0.3987, + "step": 9083 + }, + { + "epoch": 0.74, + "learning_rate": 1.5065189048239896e-05, + "loss": 0.4802, + "step": 9084 + }, + { + "epoch": 0.74, + "learning_rate": 1.5064645806171232e-05, + "loss": 0.6189, + "step": 9085 + }, + { + "epoch": 0.74, + "learning_rate": 1.5064102564102565e-05, + "loss": 0.4154, + "step": 9086 + }, + { + "epoch": 0.74, + "learning_rate": 1.50635593220339e-05, + "loss": 0.3503, + "step": 9087 + }, + { + "epoch": 0.74, + "learning_rate": 1.5063016079965233e-05, + "loss": 0.5424, + "step": 9088 + }, + { + "epoch": 0.74, + "learning_rate": 1.5062472837896569e-05, + "loss": 0.5369, + "step": 9089 + }, + { + "epoch": 0.74, + "learning_rate": 1.5061929595827901e-05, + "loss": 0.3377, + "step": 9090 + }, + { + "epoch": 0.74, + "learning_rate": 1.5061386353759236e-05, + "loss": 0.5999, + "step": 9091 + }, + { + "epoch": 0.74, + "learning_rate": 1.506084311169057e-05, + "loss": 0.2128, + "step": 9092 + }, + { + "epoch": 0.74, + "learning_rate": 1.5060299869621904e-05, + "loss": 0.5865, + "step": 9093 + }, + { + "epoch": 0.74, + "learning_rate": 1.5059756627553238e-05, + "loss": 0.4625, + "step": 9094 + }, + { + "epoch": 0.74, + "learning_rate": 1.5059213385484573e-05, + "loss": 0.2598, + "step": 9095 + }, + { + "epoch": 0.74, + "learning_rate": 1.5058670143415907e-05, + "loss": 0.4224, + "step": 9096 + }, + { + "epoch": 0.74, + "learning_rate": 1.5058126901347241e-05, + "loss": 0.6717, + "step": 9097 + }, + { + "epoch": 0.74, + "learning_rate": 1.5057583659278577e-05, + "loss": 0.5799, + "step": 9098 + }, + { + "epoch": 0.74, + "learning_rate": 1.505704041720991e-05, + "loss": 0.4519, + "step": 9099 + }, + { + "epoch": 0.74, + "learning_rate": 1.5056497175141245e-05, + "loss": 0.6583, + "step": 9100 + }, + { + "epoch": 0.74, + "learning_rate": 1.5055953933072578e-05, + "loss": 0.3615, + "step": 9101 + }, + { + "epoch": 0.74, + "learning_rate": 1.5055410691003914e-05, + "loss": 0.3199, + "step": 9102 + }, + { + "epoch": 0.74, + "learning_rate": 1.5054867448935246e-05, + "loss": 0.4614, + "step": 9103 + }, + { + "epoch": 0.74, + "learning_rate": 1.5054324206866582e-05, + "loss": 0.4428, + "step": 9104 + }, + { + "epoch": 0.74, + "learning_rate": 1.5053780964797915e-05, + "loss": 0.4351, + "step": 9105 + }, + { + "epoch": 0.74, + "learning_rate": 1.5053237722729251e-05, + "loss": 0.5002, + "step": 9106 + }, + { + "epoch": 0.74, + "learning_rate": 1.5052694480660583e-05, + "loss": 0.5917, + "step": 9107 + }, + { + "epoch": 0.74, + "learning_rate": 1.505215123859192e-05, + "loss": 0.2916, + "step": 9108 + }, + { + "epoch": 0.74, + "learning_rate": 1.5051607996523252e-05, + "loss": 0.1783, + "step": 9109 + }, + { + "epoch": 0.74, + "learning_rate": 1.5051064754454584e-05, + "loss": 0.7312, + "step": 9110 + }, + { + "epoch": 0.74, + "learning_rate": 1.505052151238592e-05, + "loss": 0.086, + "step": 9111 + }, + { + "epoch": 0.74, + "learning_rate": 1.5049978270317253e-05, + "loss": 0.2534, + "step": 9112 + }, + { + "epoch": 0.74, + "learning_rate": 1.5049435028248589e-05, + "loss": 0.4264, + "step": 9113 + }, + { + "epoch": 0.74, + "learning_rate": 1.5048891786179923e-05, + "loss": 0.3147, + "step": 9114 + }, + { + "epoch": 0.74, + "learning_rate": 1.5048348544111257e-05, + "loss": 0.622, + "step": 9115 + }, + { + "epoch": 0.74, + "learning_rate": 1.5047805302042591e-05, + "loss": 0.4057, + "step": 9116 + }, + { + "epoch": 0.74, + "learning_rate": 1.5047262059973926e-05, + "loss": 0.2515, + "step": 9117 + }, + { + "epoch": 0.74, + "learning_rate": 1.504671881790526e-05, + "loss": 0.4091, + "step": 9118 + }, + { + "epoch": 0.74, + "learning_rate": 1.5046175575836594e-05, + "loss": 0.7547, + "step": 9119 + }, + { + "epoch": 0.74, + "learning_rate": 1.5045632333767928e-05, + "loss": 0.3396, + "step": 9120 + }, + { + "epoch": 0.74, + "learning_rate": 1.5045089091699263e-05, + "loss": 0.5573, + "step": 9121 + }, + { + "epoch": 0.74, + "learning_rate": 1.5044545849630597e-05, + "loss": 0.343, + "step": 9122 + }, + { + "epoch": 0.74, + "learning_rate": 1.5044002607561931e-05, + "loss": 0.2183, + "step": 9123 + }, + { + "epoch": 0.74, + "learning_rate": 1.5043459365493265e-05, + "loss": 0.5021, + "step": 9124 + }, + { + "epoch": 0.74, + "learning_rate": 1.50429161234246e-05, + "loss": 0.4285, + "step": 9125 + }, + { + "epoch": 0.74, + "learning_rate": 1.5042372881355934e-05, + "loss": 0.7357, + "step": 9126 + }, + { + "epoch": 0.74, + "learning_rate": 1.5041829639287268e-05, + "loss": 0.7248, + "step": 9127 + }, + { + "epoch": 0.74, + "learning_rate": 1.5041286397218602e-05, + "loss": 0.6754, + "step": 9128 + }, + { + "epoch": 0.74, + "learning_rate": 1.5040743155149935e-05, + "loss": 0.2702, + "step": 9129 + }, + { + "epoch": 0.74, + "learning_rate": 1.504019991308127e-05, + "loss": 0.2392, + "step": 9130 + }, + { + "epoch": 0.74, + "learning_rate": 1.5039656671012603e-05, + "loss": 0.3252, + "step": 9131 + }, + { + "epoch": 0.74, + "learning_rate": 1.503911342894394e-05, + "loss": 0.528, + "step": 9132 + }, + { + "epoch": 0.74, + "learning_rate": 1.5038570186875272e-05, + "loss": 0.744, + "step": 9133 + }, + { + "epoch": 0.74, + "learning_rate": 1.5038026944806608e-05, + "loss": 0.2883, + "step": 9134 + }, + { + "epoch": 0.74, + "learning_rate": 1.503748370273794e-05, + "loss": 0.4518, + "step": 9135 + }, + { + "epoch": 0.74, + "learning_rate": 1.5036940460669276e-05, + "loss": 0.4939, + "step": 9136 + }, + { + "epoch": 0.74, + "learning_rate": 1.5036397218600609e-05, + "loss": 0.4927, + "step": 9137 + }, + { + "epoch": 0.74, + "learning_rate": 1.5035853976531945e-05, + "loss": 0.4434, + "step": 9138 + }, + { + "epoch": 0.74, + "learning_rate": 1.5035310734463277e-05, + "loss": 0.424, + "step": 9139 + }, + { + "epoch": 0.74, + "learning_rate": 1.5034767492394613e-05, + "loss": 0.4895, + "step": 9140 + }, + { + "epoch": 0.74, + "learning_rate": 1.5034224250325946e-05, + "loss": 0.6171, + "step": 9141 + }, + { + "epoch": 0.74, + "learning_rate": 1.5033681008257281e-05, + "loss": 0.2918, + "step": 9142 + }, + { + "epoch": 0.75, + "learning_rate": 1.5033137766188614e-05, + "loss": 0.3081, + "step": 9143 + }, + { + "epoch": 0.75, + "learning_rate": 1.503259452411995e-05, + "loss": 0.2984, + "step": 9144 + }, + { + "epoch": 0.75, + "learning_rate": 1.5032051282051282e-05, + "loss": 0.6114, + "step": 9145 + }, + { + "epoch": 0.75, + "learning_rate": 1.5031508039982618e-05, + "loss": 0.4661, + "step": 9146 + }, + { + "epoch": 0.75, + "learning_rate": 1.5030964797913951e-05, + "loss": 0.4779, + "step": 9147 + }, + { + "epoch": 0.75, + "learning_rate": 1.5030421555845285e-05, + "loss": 0.7084, + "step": 9148 + }, + { + "epoch": 0.75, + "learning_rate": 1.502987831377662e-05, + "loss": 0.2807, + "step": 9149 + }, + { + "epoch": 0.75, + "learning_rate": 1.5029335071707954e-05, + "loss": 0.2748, + "step": 9150 + }, + { + "epoch": 0.75, + "learning_rate": 1.502879182963929e-05, + "loss": 0.2813, + "step": 9151 + }, + { + "epoch": 0.75, + "learning_rate": 1.5028248587570622e-05, + "loss": 0.2379, + "step": 9152 + }, + { + "epoch": 0.75, + "learning_rate": 1.5027705345501958e-05, + "loss": 0.6432, + "step": 9153 + }, + { + "epoch": 0.75, + "learning_rate": 1.502716210343329e-05, + "loss": 0.3899, + "step": 9154 + }, + { + "epoch": 0.75, + "learning_rate": 1.5026618861364626e-05, + "loss": 0.585, + "step": 9155 + }, + { + "epoch": 0.75, + "learning_rate": 1.5026075619295959e-05, + "loss": 0.6208, + "step": 9156 + }, + { + "epoch": 0.75, + "learning_rate": 1.5025532377227295e-05, + "loss": 0.2586, + "step": 9157 + }, + { + "epoch": 0.75, + "learning_rate": 1.5024989135158627e-05, + "loss": 0.4429, + "step": 9158 + }, + { + "epoch": 0.75, + "learning_rate": 1.5024445893089963e-05, + "loss": 0.373, + "step": 9159 + }, + { + "epoch": 0.75, + "learning_rate": 1.5023902651021296e-05, + "loss": 0.3806, + "step": 9160 + }, + { + "epoch": 0.75, + "learning_rate": 1.5023359408952632e-05, + "loss": 0.315, + "step": 9161 + }, + { + "epoch": 0.75, + "learning_rate": 1.5022816166883964e-05, + "loss": 0.4638, + "step": 9162 + }, + { + "epoch": 0.75, + "learning_rate": 1.50222729248153e-05, + "loss": 0.3619, + "step": 9163 + }, + { + "epoch": 0.75, + "learning_rate": 1.5021729682746633e-05, + "loss": 0.6205, + "step": 9164 + }, + { + "epoch": 0.75, + "learning_rate": 1.5021186440677969e-05, + "loss": 0.4658, + "step": 9165 + }, + { + "epoch": 0.75, + "learning_rate": 1.5020643198609301e-05, + "loss": 0.5205, + "step": 9166 + }, + { + "epoch": 0.75, + "learning_rate": 1.5020099956540634e-05, + "loss": 0.5164, + "step": 9167 + }, + { + "epoch": 0.75, + "learning_rate": 1.501955671447197e-05, + "loss": 0.4644, + "step": 9168 + }, + { + "epoch": 0.75, + "learning_rate": 1.5019013472403304e-05, + "loss": 0.1854, + "step": 9169 + }, + { + "epoch": 0.75, + "learning_rate": 1.5018470230334638e-05, + "loss": 0.5034, + "step": 9170 + }, + { + "epoch": 0.75, + "learning_rate": 1.5017926988265972e-05, + "loss": 0.5787, + "step": 9171 + }, + { + "epoch": 0.75, + "learning_rate": 1.5017383746197307e-05, + "loss": 0.5978, + "step": 9172 + }, + { + "epoch": 0.75, + "learning_rate": 1.5016840504128641e-05, + "loss": 0.6523, + "step": 9173 + }, + { + "epoch": 0.75, + "learning_rate": 1.5016297262059975e-05, + "loss": 0.3548, + "step": 9174 + }, + { + "epoch": 0.75, + "learning_rate": 1.501575401999131e-05, + "loss": 0.3311, + "step": 9175 + }, + { + "epoch": 0.75, + "learning_rate": 1.5015210777922644e-05, + "loss": 0.6249, + "step": 9176 + }, + { + "epoch": 0.75, + "learning_rate": 1.5014667535853978e-05, + "loss": 0.3328, + "step": 9177 + }, + { + "epoch": 0.75, + "learning_rate": 1.5014124293785312e-05, + "loss": 0.7661, + "step": 9178 + }, + { + "epoch": 0.75, + "learning_rate": 1.5013581051716646e-05, + "loss": 0.3828, + "step": 9179 + }, + { + "epoch": 0.75, + "learning_rate": 1.501303780964798e-05, + "loss": 0.4317, + "step": 9180 + }, + { + "epoch": 0.75, + "learning_rate": 1.5012494567579315e-05, + "loss": 0.3968, + "step": 9181 + }, + { + "epoch": 0.75, + "learning_rate": 1.5011951325510649e-05, + "loss": 0.4545, + "step": 9182 + }, + { + "epoch": 0.75, + "learning_rate": 1.5011408083441983e-05, + "loss": 0.3173, + "step": 9183 + }, + { + "epoch": 0.75, + "learning_rate": 1.5010864841373317e-05, + "loss": 0.3864, + "step": 9184 + }, + { + "epoch": 0.75, + "learning_rate": 1.5010321599304652e-05, + "loss": 0.3657, + "step": 9185 + }, + { + "epoch": 0.75, + "learning_rate": 1.5009778357235984e-05, + "loss": 0.2902, + "step": 9186 + }, + { + "epoch": 0.75, + "learning_rate": 1.500923511516732e-05, + "loss": 0.557, + "step": 9187 + }, + { + "epoch": 0.75, + "learning_rate": 1.5008691873098653e-05, + "loss": 0.4568, + "step": 9188 + }, + { + "epoch": 0.75, + "learning_rate": 1.5008148631029989e-05, + "loss": 0.585, + "step": 9189 + }, + { + "epoch": 0.75, + "learning_rate": 1.5007605388961321e-05, + "loss": 0.3913, + "step": 9190 + }, + { + "epoch": 0.75, + "learning_rate": 1.5007062146892657e-05, + "loss": 0.4522, + "step": 9191 + }, + { + "epoch": 0.75, + "learning_rate": 1.500651890482399e-05, + "loss": 0.3791, + "step": 9192 + }, + { + "epoch": 0.75, + "learning_rate": 1.5005975662755326e-05, + "loss": 0.236, + "step": 9193 + }, + { + "epoch": 0.75, + "learning_rate": 1.5005432420686658e-05, + "loss": 0.4419, + "step": 9194 + }, + { + "epoch": 0.75, + "learning_rate": 1.5004889178617994e-05, + "loss": 0.4545, + "step": 9195 + }, + { + "epoch": 0.75, + "learning_rate": 1.5004345936549327e-05, + "loss": 0.3005, + "step": 9196 + }, + { + "epoch": 0.75, + "learning_rate": 1.5003802694480662e-05, + "loss": 0.4056, + "step": 9197 + }, + { + "epoch": 0.75, + "learning_rate": 1.5003259452411995e-05, + "loss": 0.5242, + "step": 9198 + }, + { + "epoch": 0.75, + "learning_rate": 1.5002716210343331e-05, + "loss": 0.3894, + "step": 9199 + }, + { + "epoch": 0.75, + "learning_rate": 1.5002172968274663e-05, + "loss": 0.3503, + "step": 9200 + }, + { + "epoch": 0.75, + "learning_rate": 1.5001629726206e-05, + "loss": 0.468, + "step": 9201 + }, + { + "epoch": 0.75, + "learning_rate": 1.5001086484137332e-05, + "loss": 0.5259, + "step": 9202 + }, + { + "epoch": 0.75, + "learning_rate": 1.5000543242068668e-05, + "loss": 0.271, + "step": 9203 + }, + { + "epoch": 0.75, + "learning_rate": 1.5000000000000002e-05, + "loss": 0.278, + "step": 9204 + }, + { + "epoch": 0.75, + "learning_rate": 1.4999456757931335e-05, + "loss": 0.5528, + "step": 9205 + }, + { + "epoch": 0.75, + "learning_rate": 1.499891351586267e-05, + "loss": 0.4666, + "step": 9206 + }, + { + "epoch": 0.75, + "learning_rate": 1.4998370273794003e-05, + "loss": 0.688, + "step": 9207 + }, + { + "epoch": 0.75, + "learning_rate": 1.4997827031725339e-05, + "loss": 0.4839, + "step": 9208 + }, + { + "epoch": 0.75, + "learning_rate": 1.4997283789656672e-05, + "loss": 0.4918, + "step": 9209 + }, + { + "epoch": 0.75, + "learning_rate": 1.4996740547588007e-05, + "loss": 0.6096, + "step": 9210 + }, + { + "epoch": 0.75, + "learning_rate": 1.499619730551934e-05, + "loss": 0.5865, + "step": 9211 + }, + { + "epoch": 0.75, + "learning_rate": 1.4995654063450676e-05, + "loss": 0.4936, + "step": 9212 + }, + { + "epoch": 0.75, + "learning_rate": 1.4995110821382008e-05, + "loss": 0.3727, + "step": 9213 + }, + { + "epoch": 0.75, + "learning_rate": 1.4994567579313344e-05, + "loss": 0.4739, + "step": 9214 + }, + { + "epoch": 0.75, + "learning_rate": 1.4994024337244677e-05, + "loss": 0.4861, + "step": 9215 + }, + { + "epoch": 0.75, + "learning_rate": 1.4993481095176013e-05, + "loss": 0.4798, + "step": 9216 + }, + { + "epoch": 0.75, + "learning_rate": 1.4992937853107345e-05, + "loss": 0.4432, + "step": 9217 + }, + { + "epoch": 0.75, + "learning_rate": 1.4992394611038681e-05, + "loss": 0.2221, + "step": 9218 + }, + { + "epoch": 0.75, + "learning_rate": 1.4991851368970014e-05, + "loss": 0.4041, + "step": 9219 + }, + { + "epoch": 0.75, + "learning_rate": 1.499130812690135e-05, + "loss": 0.5166, + "step": 9220 + }, + { + "epoch": 0.75, + "learning_rate": 1.4990764884832682e-05, + "loss": 0.544, + "step": 9221 + }, + { + "epoch": 0.75, + "learning_rate": 1.4990221642764018e-05, + "loss": 0.66, + "step": 9222 + }, + { + "epoch": 0.75, + "learning_rate": 1.498967840069535e-05, + "loss": 0.4723, + "step": 9223 + }, + { + "epoch": 0.75, + "learning_rate": 1.4989135158626685e-05, + "loss": 0.5052, + "step": 9224 + }, + { + "epoch": 0.75, + "learning_rate": 1.498859191655802e-05, + "loss": 0.3561, + "step": 9225 + }, + { + "epoch": 0.75, + "learning_rate": 1.4988048674489353e-05, + "loss": 0.3247, + "step": 9226 + }, + { + "epoch": 0.75, + "learning_rate": 1.4987505432420688e-05, + "loss": 0.5252, + "step": 9227 + }, + { + "epoch": 0.75, + "learning_rate": 1.4986962190352022e-05, + "loss": 0.463, + "step": 9228 + }, + { + "epoch": 0.75, + "learning_rate": 1.4986418948283356e-05, + "loss": 0.3195, + "step": 9229 + }, + { + "epoch": 0.75, + "learning_rate": 1.498587570621469e-05, + "loss": 0.3469, + "step": 9230 + }, + { + "epoch": 0.75, + "learning_rate": 1.4985332464146025e-05, + "loss": 0.2803, + "step": 9231 + }, + { + "epoch": 0.75, + "learning_rate": 1.4984789222077359e-05, + "loss": 0.458, + "step": 9232 + }, + { + "epoch": 0.75, + "learning_rate": 1.4984245980008693e-05, + "loss": 0.4657, + "step": 9233 + }, + { + "epoch": 0.75, + "learning_rate": 1.4983702737940027e-05, + "loss": 0.3449, + "step": 9234 + }, + { + "epoch": 0.75, + "learning_rate": 1.4983159495871362e-05, + "loss": 0.2432, + "step": 9235 + }, + { + "epoch": 0.75, + "learning_rate": 1.4982616253802696e-05, + "loss": 0.369, + "step": 9236 + }, + { + "epoch": 0.75, + "learning_rate": 1.498207301173403e-05, + "loss": 0.7453, + "step": 9237 + }, + { + "epoch": 0.75, + "learning_rate": 1.4981529769665364e-05, + "loss": 0.4513, + "step": 9238 + }, + { + "epoch": 0.75, + "learning_rate": 1.4980986527596698e-05, + "loss": 0.4206, + "step": 9239 + }, + { + "epoch": 0.75, + "learning_rate": 1.4980443285528033e-05, + "loss": 0.4624, + "step": 9240 + }, + { + "epoch": 0.75, + "learning_rate": 1.4979900043459369e-05, + "loss": 0.6668, + "step": 9241 + }, + { + "epoch": 0.75, + "learning_rate": 1.4979356801390701e-05, + "loss": 0.6337, + "step": 9242 + }, + { + "epoch": 0.75, + "learning_rate": 1.4978813559322034e-05, + "loss": 0.561, + "step": 9243 + }, + { + "epoch": 0.75, + "learning_rate": 1.497827031725337e-05, + "loss": 0.667, + "step": 9244 + }, + { + "epoch": 0.75, + "learning_rate": 1.4977727075184702e-05, + "loss": 0.4361, + "step": 9245 + }, + { + "epoch": 0.75, + "learning_rate": 1.4977183833116038e-05, + "loss": 0.2441, + "step": 9246 + }, + { + "epoch": 0.75, + "learning_rate": 1.497664059104737e-05, + "loss": 0.383, + "step": 9247 + }, + { + "epoch": 0.75, + "learning_rate": 1.4976097348978707e-05, + "loss": 0.4987, + "step": 9248 + }, + { + "epoch": 0.75, + "learning_rate": 1.4975554106910039e-05, + "loss": 0.4269, + "step": 9249 + }, + { + "epoch": 0.75, + "learning_rate": 1.4975010864841375e-05, + "loss": 0.2626, + "step": 9250 + }, + { + "epoch": 0.75, + "eval_accuracy": 0.8252674477840041, + "eval_loss": 0.46096014976501465, + "eval_runtime": 22.3113, + "eval_samples_per_second": 439.911, + "eval_steps_per_second": 3.451, + "step": 9250 + }, + { + "epoch": 0.75, + "learning_rate": 1.4974467622772708e-05, + "loss": 0.6022, + "step": 9251 + }, + { + "epoch": 0.75, + "learning_rate": 1.4973924380704043e-05, + "loss": 0.5186, + "step": 9252 + }, + { + "epoch": 0.75, + "learning_rate": 1.4973381138635376e-05, + "loss": 0.5327, + "step": 9253 + }, + { + "epoch": 0.75, + "learning_rate": 1.4972837896566712e-05, + "loss": 0.467, + "step": 9254 + }, + { + "epoch": 0.75, + "learning_rate": 1.4972294654498044e-05, + "loss": 0.4611, + "step": 9255 + }, + { + "epoch": 0.75, + "learning_rate": 1.497175141242938e-05, + "loss": 0.3542, + "step": 9256 + }, + { + "epoch": 0.75, + "learning_rate": 1.4971208170360713e-05, + "loss": 0.4209, + "step": 9257 + }, + { + "epoch": 0.75, + "learning_rate": 1.4970664928292049e-05, + "loss": 0.4582, + "step": 9258 + }, + { + "epoch": 0.75, + "learning_rate": 1.4970121686223383e-05, + "loss": 0.4256, + "step": 9259 + }, + { + "epoch": 0.75, + "learning_rate": 1.4969578444154717e-05, + "loss": 0.6099, + "step": 9260 + }, + { + "epoch": 0.75, + "learning_rate": 1.4969035202086052e-05, + "loss": 0.4425, + "step": 9261 + }, + { + "epoch": 0.75, + "learning_rate": 1.4968491960017384e-05, + "loss": 0.3993, + "step": 9262 + }, + { + "epoch": 0.75, + "learning_rate": 1.496794871794872e-05, + "loss": 0.3142, + "step": 9263 + }, + { + "epoch": 0.75, + "learning_rate": 1.4967405475880053e-05, + "loss": 0.6213, + "step": 9264 + }, + { + "epoch": 0.75, + "learning_rate": 1.4966862233811388e-05, + "loss": 0.7401, + "step": 9265 + }, + { + "epoch": 0.76, + "learning_rate": 1.4966318991742721e-05, + "loss": 0.5313, + "step": 9266 + }, + { + "epoch": 0.76, + "learning_rate": 1.4965775749674057e-05, + "loss": 0.6418, + "step": 9267 + }, + { + "epoch": 0.76, + "learning_rate": 1.496523250760539e-05, + "loss": 0.5253, + "step": 9268 + }, + { + "epoch": 0.76, + "learning_rate": 1.4964689265536725e-05, + "loss": 0.7755, + "step": 9269 + }, + { + "epoch": 0.76, + "learning_rate": 1.4964146023468058e-05, + "loss": 0.5567, + "step": 9270 + }, + { + "epoch": 0.76, + "learning_rate": 1.4963602781399394e-05, + "loss": 0.3711, + "step": 9271 + }, + { + "epoch": 0.76, + "learning_rate": 1.4963059539330726e-05, + "loss": 0.313, + "step": 9272 + }, + { + "epoch": 0.76, + "learning_rate": 1.4962516297262062e-05, + "loss": 0.4369, + "step": 9273 + }, + { + "epoch": 0.76, + "learning_rate": 1.4961973055193395e-05, + "loss": 0.3594, + "step": 9274 + }, + { + "epoch": 0.76, + "learning_rate": 1.496142981312473e-05, + "loss": 0.4268, + "step": 9275 + }, + { + "epoch": 0.76, + "learning_rate": 1.4960886571056063e-05, + "loss": 0.3923, + "step": 9276 + }, + { + "epoch": 0.76, + "learning_rate": 1.49603433289874e-05, + "loss": 0.3621, + "step": 9277 + }, + { + "epoch": 0.76, + "learning_rate": 1.4959800086918732e-05, + "loss": 0.7014, + "step": 9278 + }, + { + "epoch": 0.76, + "learning_rate": 1.4959256844850068e-05, + "loss": 0.575, + "step": 9279 + }, + { + "epoch": 0.76, + "learning_rate": 1.49587136027814e-05, + "loss": 0.5198, + "step": 9280 + }, + { + "epoch": 0.76, + "learning_rate": 1.4958170360712734e-05, + "loss": 0.5915, + "step": 9281 + }, + { + "epoch": 0.76, + "learning_rate": 1.4957627118644069e-05, + "loss": 0.4607, + "step": 9282 + }, + { + "epoch": 0.76, + "learning_rate": 1.4957083876575403e-05, + "loss": 0.7846, + "step": 9283 + }, + { + "epoch": 0.76, + "learning_rate": 1.4956540634506737e-05, + "loss": 0.5757, + "step": 9284 + }, + { + "epoch": 0.76, + "learning_rate": 1.4955997392438071e-05, + "loss": 0.3902, + "step": 9285 + }, + { + "epoch": 0.76, + "learning_rate": 1.4955454150369406e-05, + "loss": 0.7025, + "step": 9286 + }, + { + "epoch": 0.76, + "learning_rate": 1.495491090830074e-05, + "loss": 0.383, + "step": 9287 + }, + { + "epoch": 0.76, + "learning_rate": 1.4954367666232074e-05, + "loss": 0.3859, + "step": 9288 + }, + { + "epoch": 0.76, + "learning_rate": 1.4953824424163408e-05, + "loss": 0.3308, + "step": 9289 + }, + { + "epoch": 0.76, + "learning_rate": 1.4953281182094743e-05, + "loss": 0.3392, + "step": 9290 + }, + { + "epoch": 0.76, + "learning_rate": 1.4952737940026077e-05, + "loss": 0.4864, + "step": 9291 + }, + { + "epoch": 0.76, + "learning_rate": 1.4952194697957411e-05, + "loss": 0.4925, + "step": 9292 + }, + { + "epoch": 0.76, + "learning_rate": 1.4951651455888745e-05, + "loss": 0.6115, + "step": 9293 + }, + { + "epoch": 0.76, + "learning_rate": 1.495110821382008e-05, + "loss": 0.2818, + "step": 9294 + }, + { + "epoch": 0.76, + "learning_rate": 1.4950564971751414e-05, + "loss": 0.5053, + "step": 9295 + }, + { + "epoch": 0.76, + "learning_rate": 1.495002172968275e-05, + "loss": 0.5572, + "step": 9296 + }, + { + "epoch": 0.76, + "learning_rate": 1.4949478487614082e-05, + "loss": 0.5266, + "step": 9297 + }, + { + "epoch": 0.76, + "learning_rate": 1.4948935245545418e-05, + "loss": 0.4146, + "step": 9298 + }, + { + "epoch": 0.76, + "learning_rate": 1.494839200347675e-05, + "loss": 0.4359, + "step": 9299 + }, + { + "epoch": 0.76, + "learning_rate": 1.4947848761408083e-05, + "loss": 0.3418, + "step": 9300 + }, + { + "epoch": 0.76, + "learning_rate": 1.4947305519339419e-05, + "loss": 0.3708, + "step": 9301 + }, + { + "epoch": 0.76, + "learning_rate": 1.4946762277270752e-05, + "loss": 0.3309, + "step": 9302 + }, + { + "epoch": 0.76, + "learning_rate": 1.4946219035202088e-05, + "loss": 0.4743, + "step": 9303 + }, + { + "epoch": 0.76, + "learning_rate": 1.494567579313342e-05, + "loss": 0.5473, + "step": 9304 + }, + { + "epoch": 0.76, + "learning_rate": 1.4945132551064756e-05, + "loss": 0.5459, + "step": 9305 + }, + { + "epoch": 0.76, + "learning_rate": 1.4944589308996089e-05, + "loss": 0.4739, + "step": 9306 + }, + { + "epoch": 0.76, + "learning_rate": 1.4944046066927424e-05, + "loss": 0.3807, + "step": 9307 + }, + { + "epoch": 0.76, + "learning_rate": 1.4943502824858757e-05, + "loss": 0.3045, + "step": 9308 + }, + { + "epoch": 0.76, + "learning_rate": 1.4942959582790093e-05, + "loss": 0.6241, + "step": 9309 + }, + { + "epoch": 0.76, + "learning_rate": 1.4942416340721425e-05, + "loss": 0.3161, + "step": 9310 + }, + { + "epoch": 0.76, + "learning_rate": 1.4941873098652761e-05, + "loss": 0.5785, + "step": 9311 + }, + { + "epoch": 0.76, + "learning_rate": 1.4941329856584096e-05, + "loss": 0.4902, + "step": 9312 + }, + { + "epoch": 0.76, + "learning_rate": 1.494078661451543e-05, + "loss": 0.4828, + "step": 9313 + }, + { + "epoch": 0.76, + "learning_rate": 1.4940243372446764e-05, + "loss": 0.4327, + "step": 9314 + }, + { + "epoch": 0.76, + "learning_rate": 1.4939700130378098e-05, + "loss": 0.3828, + "step": 9315 + }, + { + "epoch": 0.76, + "learning_rate": 1.4939156888309433e-05, + "loss": 0.5542, + "step": 9316 + }, + { + "epoch": 0.76, + "learning_rate": 1.4938613646240767e-05, + "loss": 0.609, + "step": 9317 + }, + { + "epoch": 0.76, + "learning_rate": 1.4938070404172101e-05, + "loss": 0.2851, + "step": 9318 + }, + { + "epoch": 0.76, + "learning_rate": 1.4937527162103434e-05, + "loss": 0.5339, + "step": 9319 + }, + { + "epoch": 0.76, + "learning_rate": 1.493698392003477e-05, + "loss": 0.4027, + "step": 9320 + }, + { + "epoch": 0.76, + "learning_rate": 1.4936440677966102e-05, + "loss": 0.6289, + "step": 9321 + }, + { + "epoch": 0.76, + "learning_rate": 1.4935897435897438e-05, + "loss": 0.6462, + "step": 9322 + }, + { + "epoch": 0.76, + "learning_rate": 1.493535419382877e-05, + "loss": 0.4694, + "step": 9323 + }, + { + "epoch": 0.76, + "learning_rate": 1.4934810951760106e-05, + "loss": 0.5427, + "step": 9324 + }, + { + "epoch": 0.76, + "learning_rate": 1.4934267709691439e-05, + "loss": 0.5925, + "step": 9325 + }, + { + "epoch": 0.76, + "learning_rate": 1.4933724467622775e-05, + "loss": 0.4649, + "step": 9326 + }, + { + "epoch": 0.76, + "learning_rate": 1.4933181225554107e-05, + "loss": 0.3724, + "step": 9327 + }, + { + "epoch": 0.76, + "learning_rate": 1.4932637983485443e-05, + "loss": 0.3592, + "step": 9328 + }, + { + "epoch": 0.76, + "learning_rate": 1.4932094741416776e-05, + "loss": 0.3451, + "step": 9329 + }, + { + "epoch": 0.76, + "learning_rate": 1.4931551499348112e-05, + "loss": 0.5173, + "step": 9330 + }, + { + "epoch": 0.76, + "learning_rate": 1.4931008257279444e-05, + "loss": 0.4166, + "step": 9331 + }, + { + "epoch": 0.76, + "learning_rate": 1.493046501521078e-05, + "loss": 0.313, + "step": 9332 + }, + { + "epoch": 0.76, + "learning_rate": 1.4929921773142113e-05, + "loss": 0.4359, + "step": 9333 + }, + { + "epoch": 0.76, + "learning_rate": 1.4929378531073449e-05, + "loss": 0.493, + "step": 9334 + }, + { + "epoch": 0.76, + "learning_rate": 1.4928835289004781e-05, + "loss": 0.3897, + "step": 9335 + }, + { + "epoch": 0.76, + "learning_rate": 1.4928292046936117e-05, + "loss": 0.3656, + "step": 9336 + }, + { + "epoch": 0.76, + "learning_rate": 1.492774880486745e-05, + "loss": 0.3323, + "step": 9337 + }, + { + "epoch": 0.76, + "learning_rate": 1.4927205562798784e-05, + "loss": 0.3518, + "step": 9338 + }, + { + "epoch": 0.76, + "learning_rate": 1.4926662320730118e-05, + "loss": 0.3488, + "step": 9339 + }, + { + "epoch": 0.76, + "learning_rate": 1.4926119078661452e-05, + "loss": 0.3939, + "step": 9340 + }, + { + "epoch": 0.76, + "learning_rate": 1.4925575836592787e-05, + "loss": 0.5008, + "step": 9341 + }, + { + "epoch": 0.76, + "learning_rate": 1.492503259452412e-05, + "loss": 0.4291, + "step": 9342 + }, + { + "epoch": 0.76, + "learning_rate": 1.4924489352455455e-05, + "loss": 0.4566, + "step": 9343 + }, + { + "epoch": 0.76, + "learning_rate": 1.492394611038679e-05, + "loss": 0.7056, + "step": 9344 + }, + { + "epoch": 0.76, + "learning_rate": 1.4923402868318123e-05, + "loss": 0.5178, + "step": 9345 + }, + { + "epoch": 0.76, + "learning_rate": 1.4922859626249458e-05, + "loss": 0.6163, + "step": 9346 + }, + { + "epoch": 0.76, + "learning_rate": 1.4922316384180792e-05, + "loss": 0.3222, + "step": 9347 + }, + { + "epoch": 0.76, + "learning_rate": 1.4921773142112126e-05, + "loss": 0.4738, + "step": 9348 + }, + { + "epoch": 0.76, + "learning_rate": 1.4921229900043462e-05, + "loss": 0.6173, + "step": 9349 + }, + { + "epoch": 0.76, + "learning_rate": 1.4920686657974795e-05, + "loss": 0.4418, + "step": 9350 + }, + { + "epoch": 0.76, + "learning_rate": 1.492014341590613e-05, + "loss": 0.3582, + "step": 9351 + }, + { + "epoch": 0.76, + "learning_rate": 1.4919600173837463e-05, + "loss": 0.2899, + "step": 9352 + }, + { + "epoch": 0.76, + "learning_rate": 1.4919056931768799e-05, + "loss": 0.4923, + "step": 9353 + }, + { + "epoch": 0.76, + "learning_rate": 1.4918513689700132e-05, + "loss": 0.5588, + "step": 9354 + }, + { + "epoch": 0.76, + "learning_rate": 1.4917970447631467e-05, + "loss": 0.3226, + "step": 9355 + }, + { + "epoch": 0.76, + "learning_rate": 1.49174272055628e-05, + "loss": 0.3933, + "step": 9356 + }, + { + "epoch": 0.76, + "learning_rate": 1.4916883963494133e-05, + "loss": 0.2907, + "step": 9357 + }, + { + "epoch": 0.76, + "learning_rate": 1.4916340721425468e-05, + "loss": 0.4743, + "step": 9358 + }, + { + "epoch": 0.76, + "learning_rate": 1.4915797479356801e-05, + "loss": 0.5837, + "step": 9359 + }, + { + "epoch": 0.76, + "learning_rate": 1.4915254237288137e-05, + "loss": 0.4525, + "step": 9360 + }, + { + "epoch": 0.76, + "learning_rate": 1.491471099521947e-05, + "loss": 0.7389, + "step": 9361 + }, + { + "epoch": 0.76, + "learning_rate": 1.4914167753150805e-05, + "loss": 0.6056, + "step": 9362 + }, + { + "epoch": 0.76, + "learning_rate": 1.4913624511082138e-05, + "loss": 0.7168, + "step": 9363 + }, + { + "epoch": 0.76, + "learning_rate": 1.4913081269013474e-05, + "loss": 0.5668, + "step": 9364 + }, + { + "epoch": 0.76, + "learning_rate": 1.4912538026944806e-05, + "loss": 0.526, + "step": 9365 + }, + { + "epoch": 0.76, + "learning_rate": 1.4911994784876142e-05, + "loss": 0.4335, + "step": 9366 + }, + { + "epoch": 0.76, + "learning_rate": 1.4911451542807477e-05, + "loss": 0.494, + "step": 9367 + }, + { + "epoch": 0.76, + "learning_rate": 1.491090830073881e-05, + "loss": 0.4576, + "step": 9368 + }, + { + "epoch": 0.76, + "learning_rate": 1.4910365058670145e-05, + "loss": 0.412, + "step": 9369 + }, + { + "epoch": 0.76, + "learning_rate": 1.490982181660148e-05, + "loss": 0.6136, + "step": 9370 + }, + { + "epoch": 0.76, + "learning_rate": 1.4909278574532813e-05, + "loss": 0.4322, + "step": 9371 + }, + { + "epoch": 0.76, + "learning_rate": 1.4908735332464148e-05, + "loss": 0.3052, + "step": 9372 + }, + { + "epoch": 0.76, + "learning_rate": 1.4908192090395482e-05, + "loss": 0.614, + "step": 9373 + }, + { + "epoch": 0.76, + "learning_rate": 1.4907648848326816e-05, + "loss": 0.3104, + "step": 9374 + }, + { + "epoch": 0.76, + "learning_rate": 1.490710560625815e-05, + "loss": 0.5546, + "step": 9375 + }, + { + "epoch": 0.76, + "learning_rate": 1.4906562364189483e-05, + "loss": 0.7549, + "step": 9376 + }, + { + "epoch": 0.76, + "learning_rate": 1.4906019122120819e-05, + "loss": 0.5296, + "step": 9377 + }, + { + "epoch": 0.76, + "learning_rate": 1.4905475880052151e-05, + "loss": 0.6357, + "step": 9378 + }, + { + "epoch": 0.76, + "learning_rate": 1.4904932637983487e-05, + "loss": 0.292, + "step": 9379 + }, + { + "epoch": 0.76, + "learning_rate": 1.490438939591482e-05, + "loss": 0.5896, + "step": 9380 + }, + { + "epoch": 0.76, + "learning_rate": 1.4903846153846156e-05, + "loss": 0.3813, + "step": 9381 + }, + { + "epoch": 0.76, + "learning_rate": 1.4903302911777488e-05, + "loss": 0.5114, + "step": 9382 + }, + { + "epoch": 0.76, + "learning_rate": 1.4902759669708824e-05, + "loss": 0.403, + "step": 9383 + }, + { + "epoch": 0.76, + "learning_rate": 1.4902216427640157e-05, + "loss": 0.4291, + "step": 9384 + }, + { + "epoch": 0.76, + "learning_rate": 1.4901673185571493e-05, + "loss": 0.6882, + "step": 9385 + }, + { + "epoch": 0.76, + "learning_rate": 1.4901129943502825e-05, + "loss": 0.4854, + "step": 9386 + }, + { + "epoch": 0.76, + "learning_rate": 1.4900586701434161e-05, + "loss": 0.4566, + "step": 9387 + }, + { + "epoch": 0.76, + "learning_rate": 1.4900043459365494e-05, + "loss": 0.4109, + "step": 9388 + }, + { + "epoch": 0.77, + "learning_rate": 1.489950021729683e-05, + "loss": 0.3974, + "step": 9389 + }, + { + "epoch": 0.77, + "learning_rate": 1.4898956975228162e-05, + "loss": 0.627, + "step": 9390 + }, + { + "epoch": 0.77, + "learning_rate": 1.4898413733159498e-05, + "loss": 0.5603, + "step": 9391 + }, + { + "epoch": 0.77, + "learning_rate": 1.489787049109083e-05, + "loss": 0.4926, + "step": 9392 + }, + { + "epoch": 0.77, + "learning_rate": 1.4897327249022167e-05, + "loss": 0.3771, + "step": 9393 + }, + { + "epoch": 0.77, + "learning_rate": 1.4896784006953499e-05, + "loss": 0.333, + "step": 9394 + }, + { + "epoch": 0.77, + "learning_rate": 1.4896240764884833e-05, + "loss": 0.4503, + "step": 9395 + }, + { + "epoch": 0.77, + "learning_rate": 1.4895697522816168e-05, + "loss": 0.5654, + "step": 9396 + }, + { + "epoch": 0.77, + "learning_rate": 1.4895154280747502e-05, + "loss": 0.4251, + "step": 9397 + }, + { + "epoch": 0.77, + "learning_rate": 1.4894611038678836e-05, + "loss": 0.4609, + "step": 9398 + }, + { + "epoch": 0.77, + "learning_rate": 1.489406779661017e-05, + "loss": 0.3444, + "step": 9399 + }, + { + "epoch": 0.77, + "learning_rate": 1.4893524554541504e-05, + "loss": 0.2626, + "step": 9400 + }, + { + "epoch": 0.77, + "learning_rate": 1.4892981312472839e-05, + "loss": 0.5278, + "step": 9401 + }, + { + "epoch": 0.77, + "learning_rate": 1.4892438070404173e-05, + "loss": 0.3742, + "step": 9402 + }, + { + "epoch": 0.77, + "learning_rate": 1.4891894828335507e-05, + "loss": 0.486, + "step": 9403 + }, + { + "epoch": 0.77, + "learning_rate": 1.4891351586266843e-05, + "loss": 0.4423, + "step": 9404 + }, + { + "epoch": 0.77, + "learning_rate": 1.4890808344198176e-05, + "loss": 0.4753, + "step": 9405 + }, + { + "epoch": 0.77, + "learning_rate": 1.4890265102129512e-05, + "loss": 0.601, + "step": 9406 + }, + { + "epoch": 0.77, + "learning_rate": 1.4889721860060844e-05, + "loss": 0.3792, + "step": 9407 + }, + { + "epoch": 0.77, + "learning_rate": 1.488917861799218e-05, + "loss": 0.7093, + "step": 9408 + }, + { + "epoch": 0.77, + "learning_rate": 1.4888635375923513e-05, + "loss": 0.3197, + "step": 9409 + }, + { + "epoch": 0.77, + "learning_rate": 1.4888092133854848e-05, + "loss": 0.4477, + "step": 9410 + }, + { + "epoch": 0.77, + "learning_rate": 1.4887548891786181e-05, + "loss": 0.7185, + "step": 9411 + }, + { + "epoch": 0.77, + "learning_rate": 1.4887005649717517e-05, + "loss": 0.6801, + "step": 9412 + }, + { + "epoch": 0.77, + "learning_rate": 1.488646240764885e-05, + "loss": 0.365, + "step": 9413 + }, + { + "epoch": 0.77, + "learning_rate": 1.4885919165580182e-05, + "loss": 0.4147, + "step": 9414 + }, + { + "epoch": 0.77, + "learning_rate": 1.4885375923511518e-05, + "loss": 0.6034, + "step": 9415 + }, + { + "epoch": 0.77, + "learning_rate": 1.488483268144285e-05, + "loss": 0.4816, + "step": 9416 + }, + { + "epoch": 0.77, + "learning_rate": 1.4884289439374186e-05, + "loss": 0.4046, + "step": 9417 + }, + { + "epoch": 0.77, + "learning_rate": 1.4883746197305519e-05, + "loss": 0.5892, + "step": 9418 + }, + { + "epoch": 0.77, + "learning_rate": 1.4883202955236855e-05, + "loss": 0.5678, + "step": 9419 + }, + { + "epoch": 0.77, + "learning_rate": 1.4882659713168189e-05, + "loss": 0.4645, + "step": 9420 + }, + { + "epoch": 0.77, + "learning_rate": 1.4882116471099523e-05, + "loss": 0.3732, + "step": 9421 + }, + { + "epoch": 0.77, + "learning_rate": 1.4881573229030858e-05, + "loss": 0.5887, + "step": 9422 + }, + { + "epoch": 0.77, + "learning_rate": 1.4881029986962192e-05, + "loss": 0.3478, + "step": 9423 + }, + { + "epoch": 0.77, + "learning_rate": 1.4880486744893526e-05, + "loss": 0.5927, + "step": 9424 + }, + { + "epoch": 0.77, + "learning_rate": 1.487994350282486e-05, + "loss": 0.428, + "step": 9425 + }, + { + "epoch": 0.77, + "learning_rate": 1.4879400260756194e-05, + "loss": 0.4781, + "step": 9426 + }, + { + "epoch": 0.77, + "learning_rate": 1.4878857018687529e-05, + "loss": 0.5148, + "step": 9427 + }, + { + "epoch": 0.77, + "learning_rate": 1.4878313776618863e-05, + "loss": 0.4874, + "step": 9428 + }, + { + "epoch": 0.77, + "learning_rate": 1.4877770534550197e-05, + "loss": 0.319, + "step": 9429 + }, + { + "epoch": 0.77, + "learning_rate": 1.4877227292481531e-05, + "loss": 0.3166, + "step": 9430 + }, + { + "epoch": 0.77, + "learning_rate": 1.4876684050412866e-05, + "loss": 0.3199, + "step": 9431 + }, + { + "epoch": 0.77, + "learning_rate": 1.48761408083442e-05, + "loss": 0.5516, + "step": 9432 + }, + { + "epoch": 0.77, + "learning_rate": 1.4875597566275532e-05, + "loss": 0.361, + "step": 9433 + }, + { + "epoch": 0.77, + "learning_rate": 1.4875054324206868e-05, + "loss": 0.2249, + "step": 9434 + }, + { + "epoch": 0.77, + "learning_rate": 1.4874511082138201e-05, + "loss": 0.3368, + "step": 9435 + }, + { + "epoch": 0.77, + "learning_rate": 1.4873967840069537e-05, + "loss": 0.3484, + "step": 9436 + }, + { + "epoch": 0.77, + "learning_rate": 1.487342459800087e-05, + "loss": 0.1699, + "step": 9437 + }, + { + "epoch": 0.77, + "learning_rate": 1.4872881355932205e-05, + "loss": 0.4717, + "step": 9438 + }, + { + "epoch": 0.77, + "learning_rate": 1.4872338113863538e-05, + "loss": 0.4142, + "step": 9439 + }, + { + "epoch": 0.77, + "learning_rate": 1.4871794871794874e-05, + "loss": 0.3249, + "step": 9440 + }, + { + "epoch": 0.77, + "learning_rate": 1.4871251629726206e-05, + "loss": 0.263, + "step": 9441 + }, + { + "epoch": 0.77, + "learning_rate": 1.4870708387657542e-05, + "loss": 0.4845, + "step": 9442 + }, + { + "epoch": 0.77, + "learning_rate": 1.4870165145588875e-05, + "loss": 0.5159, + "step": 9443 + }, + { + "epoch": 0.77, + "learning_rate": 1.486962190352021e-05, + "loss": 0.581, + "step": 9444 + }, + { + "epoch": 0.77, + "learning_rate": 1.4869078661451543e-05, + "loss": 0.4543, + "step": 9445 + }, + { + "epoch": 0.77, + "learning_rate": 1.4868535419382879e-05, + "loss": 0.4373, + "step": 9446 + }, + { + "epoch": 0.77, + "learning_rate": 1.4867992177314212e-05, + "loss": 0.6313, + "step": 9447 + }, + { + "epoch": 0.77, + "learning_rate": 1.4867448935245548e-05, + "loss": 0.3905, + "step": 9448 + }, + { + "epoch": 0.77, + "learning_rate": 1.486690569317688e-05, + "loss": 0.5709, + "step": 9449 + }, + { + "epoch": 0.77, + "learning_rate": 1.4866362451108216e-05, + "loss": 0.3792, + "step": 9450 + }, + { + "epoch": 0.77, + "learning_rate": 1.4865819209039549e-05, + "loss": 0.3796, + "step": 9451 + }, + { + "epoch": 0.77, + "learning_rate": 1.4865275966970883e-05, + "loss": 0.5287, + "step": 9452 + }, + { + "epoch": 0.77, + "learning_rate": 1.4864732724902217e-05, + "loss": 0.4616, + "step": 9453 + }, + { + "epoch": 0.77, + "learning_rate": 1.4864189482833551e-05, + "loss": 0.4725, + "step": 9454 + }, + { + "epoch": 0.77, + "learning_rate": 1.4863646240764885e-05, + "loss": 0.3882, + "step": 9455 + }, + { + "epoch": 0.77, + "learning_rate": 1.486310299869622e-05, + "loss": 0.6799, + "step": 9456 + }, + { + "epoch": 0.77, + "learning_rate": 1.4862559756627556e-05, + "loss": 0.5895, + "step": 9457 + }, + { + "epoch": 0.77, + "learning_rate": 1.4862016514558888e-05, + "loss": 0.4985, + "step": 9458 + }, + { + "epoch": 0.77, + "learning_rate": 1.4861473272490224e-05, + "loss": 0.3497, + "step": 9459 + }, + { + "epoch": 0.77, + "learning_rate": 1.4860930030421557e-05, + "loss": 0.6164, + "step": 9460 + }, + { + "epoch": 0.77, + "learning_rate": 1.4860386788352893e-05, + "loss": 0.408, + "step": 9461 + }, + { + "epoch": 0.77, + "learning_rate": 1.4859843546284225e-05, + "loss": 0.4279, + "step": 9462 + }, + { + "epoch": 0.77, + "learning_rate": 1.4859300304215561e-05, + "loss": 0.6678, + "step": 9463 + }, + { + "epoch": 0.77, + "learning_rate": 1.4858757062146894e-05, + "loss": 0.5014, + "step": 9464 + }, + { + "epoch": 0.77, + "learning_rate": 1.485821382007823e-05, + "loss": 0.547, + "step": 9465 + }, + { + "epoch": 0.77, + "learning_rate": 1.4857670578009562e-05, + "loss": 0.3529, + "step": 9466 + }, + { + "epoch": 0.77, + "learning_rate": 1.4857127335940898e-05, + "loss": 0.4357, + "step": 9467 + }, + { + "epoch": 0.77, + "learning_rate": 1.485658409387223e-05, + "loss": 0.3638, + "step": 9468 + }, + { + "epoch": 0.77, + "learning_rate": 1.4856040851803566e-05, + "loss": 0.5176, + "step": 9469 + }, + { + "epoch": 0.77, + "learning_rate": 1.4855497609734899e-05, + "loss": 0.5093, + "step": 9470 + }, + { + "epoch": 0.77, + "learning_rate": 1.4854954367666231e-05, + "loss": 0.4689, + "step": 9471 + }, + { + "epoch": 0.77, + "learning_rate": 1.4854411125597567e-05, + "loss": 0.2211, + "step": 9472 + }, + { + "epoch": 0.77, + "learning_rate": 1.48538678835289e-05, + "loss": 0.3107, + "step": 9473 + }, + { + "epoch": 0.77, + "learning_rate": 1.4853324641460236e-05, + "loss": 0.6165, + "step": 9474 + }, + { + "epoch": 0.77, + "learning_rate": 1.485278139939157e-05, + "loss": 0.4342, + "step": 9475 + }, + { + "epoch": 0.77, + "learning_rate": 1.4852238157322904e-05, + "loss": 0.3648, + "step": 9476 + }, + { + "epoch": 0.77, + "learning_rate": 1.4851694915254239e-05, + "loss": 0.2982, + "step": 9477 + }, + { + "epoch": 0.77, + "learning_rate": 1.4851151673185573e-05, + "loss": 0.788, + "step": 9478 + }, + { + "epoch": 0.77, + "learning_rate": 1.4850608431116907e-05, + "loss": 0.3699, + "step": 9479 + }, + { + "epoch": 0.77, + "learning_rate": 1.4850065189048241e-05, + "loss": 0.5583, + "step": 9480 + }, + { + "epoch": 0.77, + "learning_rate": 1.4849521946979575e-05, + "loss": 0.4321, + "step": 9481 + }, + { + "epoch": 0.77, + "learning_rate": 1.484897870491091e-05, + "loss": 0.5302, + "step": 9482 + }, + { + "epoch": 0.77, + "learning_rate": 1.4848435462842244e-05, + "loss": 0.4263, + "step": 9483 + }, + { + "epoch": 0.77, + "learning_rate": 1.4847892220773578e-05, + "loss": 0.5796, + "step": 9484 + }, + { + "epoch": 0.77, + "learning_rate": 1.4847348978704912e-05, + "loss": 0.2465, + "step": 9485 + }, + { + "epoch": 0.77, + "learning_rate": 1.4846805736636247e-05, + "loss": 0.3992, + "step": 9486 + }, + { + "epoch": 0.77, + "learning_rate": 1.4846262494567581e-05, + "loss": 0.3896, + "step": 9487 + }, + { + "epoch": 0.77, + "learning_rate": 1.4845719252498915e-05, + "loss": 0.5043, + "step": 9488 + }, + { + "epoch": 0.77, + "learning_rate": 1.484517601043025e-05, + "loss": 0.3707, + "step": 9489 + }, + { + "epoch": 0.77, + "learning_rate": 1.4844632768361582e-05, + "loss": 0.389, + "step": 9490 + }, + { + "epoch": 0.77, + "learning_rate": 1.4844089526292918e-05, + "loss": 0.3298, + "step": 9491 + }, + { + "epoch": 0.77, + "learning_rate": 1.484354628422425e-05, + "loss": 0.5566, + "step": 9492 + }, + { + "epoch": 0.77, + "learning_rate": 1.4843003042155586e-05, + "loss": 0.3767, + "step": 9493 + }, + { + "epoch": 0.77, + "learning_rate": 1.4842459800086919e-05, + "loss": 0.4491, + "step": 9494 + }, + { + "epoch": 0.77, + "learning_rate": 1.4841916558018255e-05, + "loss": 0.7117, + "step": 9495 + }, + { + "epoch": 0.77, + "learning_rate": 1.4841373315949587e-05, + "loss": 0.4173, + "step": 9496 + }, + { + "epoch": 0.77, + "learning_rate": 1.4840830073880923e-05, + "loss": 0.372, + "step": 9497 + }, + { + "epoch": 0.77, + "learning_rate": 1.4840286831812256e-05, + "loss": 0.8537, + "step": 9498 + }, + { + "epoch": 0.77, + "learning_rate": 1.4839743589743592e-05, + "loss": 0.6988, + "step": 9499 + }, + { + "epoch": 0.77, + "learning_rate": 1.4839200347674924e-05, + "loss": 0.6804, + "step": 9500 + }, + { + "epoch": 0.77, + "eval_accuracy": 0.8295466123280693, + "eval_loss": 0.4423360526561737, + "eval_runtime": 22.2293, + "eval_samples_per_second": 441.535, + "eval_steps_per_second": 3.464, + "step": 9500 + }, + { + "epoch": 0.77, + "learning_rate": 1.483865710560626e-05, + "loss": 0.4193, + "step": 9501 + }, + { + "epoch": 0.77, + "learning_rate": 1.4838113863537593e-05, + "loss": 0.3222, + "step": 9502 + }, + { + "epoch": 0.77, + "learning_rate": 1.4837570621468929e-05, + "loss": 0.3591, + "step": 9503 + }, + { + "epoch": 0.77, + "learning_rate": 1.4837027379400261e-05, + "loss": 0.2975, + "step": 9504 + }, + { + "epoch": 0.77, + "learning_rate": 1.4836484137331597e-05, + "loss": 0.3754, + "step": 9505 + }, + { + "epoch": 0.77, + "learning_rate": 1.483594089526293e-05, + "loss": 0.5123, + "step": 9506 + }, + { + "epoch": 0.77, + "learning_rate": 1.4835397653194265e-05, + "loss": 0.2663, + "step": 9507 + }, + { + "epoch": 0.77, + "learning_rate": 1.4834854411125598e-05, + "loss": 0.286, + "step": 9508 + }, + { + "epoch": 0.77, + "learning_rate": 1.4834311169056932e-05, + "loss": 0.6377, + "step": 9509 + }, + { + "epoch": 0.77, + "learning_rate": 1.4833767926988266e-05, + "loss": 0.2965, + "step": 9510 + }, + { + "epoch": 0.78, + "learning_rate": 1.48332246849196e-05, + "loss": 0.2635, + "step": 9511 + }, + { + "epoch": 0.78, + "learning_rate": 1.4832681442850937e-05, + "loss": 0.5469, + "step": 9512 + }, + { + "epoch": 0.78, + "learning_rate": 1.4832138200782269e-05, + "loss": 0.5055, + "step": 9513 + }, + { + "epoch": 0.78, + "learning_rate": 1.4831594958713605e-05, + "loss": 0.2229, + "step": 9514 + }, + { + "epoch": 0.78, + "learning_rate": 1.4831051716644938e-05, + "loss": 0.3118, + "step": 9515 + }, + { + "epoch": 0.78, + "learning_rate": 1.4830508474576274e-05, + "loss": 0.5559, + "step": 9516 + }, + { + "epoch": 0.78, + "learning_rate": 1.4829965232507606e-05, + "loss": 0.169, + "step": 9517 + }, + { + "epoch": 0.78, + "learning_rate": 1.4829421990438942e-05, + "loss": 0.5135, + "step": 9518 + }, + { + "epoch": 0.78, + "learning_rate": 1.4828878748370275e-05, + "loss": 0.4148, + "step": 9519 + }, + { + "epoch": 0.78, + "learning_rate": 1.482833550630161e-05, + "loss": 0.3613, + "step": 9520 + }, + { + "epoch": 0.78, + "learning_rate": 1.4827792264232943e-05, + "loss": 0.709, + "step": 9521 + }, + { + "epoch": 0.78, + "learning_rate": 1.4827249022164279e-05, + "loss": 0.3931, + "step": 9522 + }, + { + "epoch": 0.78, + "learning_rate": 1.4826705780095611e-05, + "loss": 0.5049, + "step": 9523 + }, + { + "epoch": 0.78, + "learning_rate": 1.4826162538026947e-05, + "loss": 0.6249, + "step": 9524 + }, + { + "epoch": 0.78, + "learning_rate": 1.482561929595828e-05, + "loss": 0.3508, + "step": 9525 + }, + { + "epoch": 0.78, + "learning_rate": 1.4825076053889616e-05, + "loss": 0.3254, + "step": 9526 + }, + { + "epoch": 0.78, + "learning_rate": 1.4824532811820948e-05, + "loss": 0.714, + "step": 9527 + }, + { + "epoch": 0.78, + "learning_rate": 1.4823989569752283e-05, + "loss": 0.3489, + "step": 9528 + }, + { + "epoch": 0.78, + "learning_rate": 1.4823446327683617e-05, + "loss": 0.2927, + "step": 9529 + }, + { + "epoch": 0.78, + "learning_rate": 1.4822903085614951e-05, + "loss": 0.4265, + "step": 9530 + }, + { + "epoch": 0.78, + "learning_rate": 1.4822359843546285e-05, + "loss": 0.249, + "step": 9531 + }, + { + "epoch": 0.78, + "learning_rate": 1.482181660147762e-05, + "loss": 0.4413, + "step": 9532 + }, + { + "epoch": 0.78, + "learning_rate": 1.4821273359408954e-05, + "loss": 0.553, + "step": 9533 + }, + { + "epoch": 0.78, + "learning_rate": 1.4820730117340288e-05, + "loss": 0.4394, + "step": 9534 + }, + { + "epoch": 0.78, + "learning_rate": 1.4820186875271622e-05, + "loss": 0.3024, + "step": 9535 + }, + { + "epoch": 0.78, + "learning_rate": 1.4819643633202956e-05, + "loss": 0.3634, + "step": 9536 + }, + { + "epoch": 0.78, + "learning_rate": 1.481910039113429e-05, + "loss": 0.5913, + "step": 9537 + }, + { + "epoch": 0.78, + "learning_rate": 1.4818557149065625e-05, + "loss": 0.4478, + "step": 9538 + }, + { + "epoch": 0.78, + "learning_rate": 1.4818013906996959e-05, + "loss": 0.8495, + "step": 9539 + }, + { + "epoch": 0.78, + "learning_rate": 1.4817470664928293e-05, + "loss": 0.5297, + "step": 9540 + }, + { + "epoch": 0.78, + "learning_rate": 1.4816927422859628e-05, + "loss": 0.7674, + "step": 9541 + }, + { + "epoch": 0.78, + "learning_rate": 1.4816384180790962e-05, + "loss": 0.4215, + "step": 9542 + }, + { + "epoch": 0.78, + "learning_rate": 1.4815840938722296e-05, + "loss": 0.259, + "step": 9543 + }, + { + "epoch": 0.78, + "learning_rate": 1.481529769665363e-05, + "loss": 0.446, + "step": 9544 + }, + { + "epoch": 0.78, + "learning_rate": 1.4814754454584965e-05, + "loss": 0.513, + "step": 9545 + }, + { + "epoch": 0.78, + "learning_rate": 1.4814211212516299e-05, + "loss": 0.1917, + "step": 9546 + }, + { + "epoch": 0.78, + "learning_rate": 1.4813667970447631e-05, + "loss": 0.4677, + "step": 9547 + }, + { + "epoch": 0.78, + "learning_rate": 1.4813124728378967e-05, + "loss": 0.4781, + "step": 9548 + }, + { + "epoch": 0.78, + "learning_rate": 1.48125814863103e-05, + "loss": 0.3403, + "step": 9549 + }, + { + "epoch": 0.78, + "learning_rate": 1.4812038244241636e-05, + "loss": 0.2792, + "step": 9550 + }, + { + "epoch": 0.78, + "learning_rate": 1.4811495002172968e-05, + "loss": 0.2803, + "step": 9551 + }, + { + "epoch": 0.78, + "learning_rate": 1.4810951760104304e-05, + "loss": 0.4241, + "step": 9552 + }, + { + "epoch": 0.78, + "learning_rate": 1.4810408518035637e-05, + "loss": 0.4244, + "step": 9553 + }, + { + "epoch": 0.78, + "learning_rate": 1.4809865275966973e-05, + "loss": 0.4927, + "step": 9554 + }, + { + "epoch": 0.78, + "learning_rate": 1.4809322033898305e-05, + "loss": 0.633, + "step": 9555 + }, + { + "epoch": 0.78, + "learning_rate": 1.4808778791829641e-05, + "loss": 0.7278, + "step": 9556 + }, + { + "epoch": 0.78, + "learning_rate": 1.4808235549760974e-05, + "loss": 0.5741, + "step": 9557 + }, + { + "epoch": 0.78, + "learning_rate": 1.480769230769231e-05, + "loss": 0.418, + "step": 9558 + }, + { + "epoch": 0.78, + "learning_rate": 1.4807149065623642e-05, + "loss": 0.4885, + "step": 9559 + }, + { + "epoch": 0.78, + "learning_rate": 1.4806605823554978e-05, + "loss": 0.4814, + "step": 9560 + }, + { + "epoch": 0.78, + "learning_rate": 1.480606258148631e-05, + "loss": 0.48, + "step": 9561 + }, + { + "epoch": 0.78, + "learning_rate": 1.4805519339417646e-05, + "loss": 0.5113, + "step": 9562 + }, + { + "epoch": 0.78, + "learning_rate": 1.4804976097348979e-05, + "loss": 0.3366, + "step": 9563 + }, + { + "epoch": 0.78, + "learning_rate": 1.4804432855280315e-05, + "loss": 0.5051, + "step": 9564 + }, + { + "epoch": 0.78, + "learning_rate": 1.4803889613211649e-05, + "loss": 0.607, + "step": 9565 + }, + { + "epoch": 0.78, + "learning_rate": 1.4803346371142982e-05, + "loss": 0.8059, + "step": 9566 + }, + { + "epoch": 0.78, + "learning_rate": 1.4802803129074318e-05, + "loss": 0.3279, + "step": 9567 + }, + { + "epoch": 0.78, + "learning_rate": 1.480225988700565e-05, + "loss": 0.3898, + "step": 9568 + }, + { + "epoch": 0.78, + "learning_rate": 1.4801716644936986e-05, + "loss": 0.4128, + "step": 9569 + }, + { + "epoch": 0.78, + "learning_rate": 1.4801173402868319e-05, + "loss": 0.6155, + "step": 9570 + }, + { + "epoch": 0.78, + "learning_rate": 1.4800630160799655e-05, + "loss": 0.456, + "step": 9571 + }, + { + "epoch": 0.78, + "learning_rate": 1.4800086918730987e-05, + "loss": 0.3456, + "step": 9572 + }, + { + "epoch": 0.78, + "learning_rate": 1.4799543676662323e-05, + "loss": 0.278, + "step": 9573 + }, + { + "epoch": 0.78, + "learning_rate": 1.4799000434593656e-05, + "loss": 0.392, + "step": 9574 + }, + { + "epoch": 0.78, + "learning_rate": 1.4798457192524991e-05, + "loss": 0.351, + "step": 9575 + }, + { + "epoch": 0.78, + "learning_rate": 1.4797913950456324e-05, + "loss": 0.4704, + "step": 9576 + }, + { + "epoch": 0.78, + "learning_rate": 1.479737070838766e-05, + "loss": 0.4015, + "step": 9577 + }, + { + "epoch": 0.78, + "learning_rate": 1.4796827466318992e-05, + "loss": 0.5323, + "step": 9578 + }, + { + "epoch": 0.78, + "learning_rate": 1.4796284224250328e-05, + "loss": 0.5105, + "step": 9579 + }, + { + "epoch": 0.78, + "learning_rate": 1.4795740982181661e-05, + "loss": 0.3773, + "step": 9580 + }, + { + "epoch": 0.78, + "learning_rate": 1.4795197740112997e-05, + "loss": 0.3483, + "step": 9581 + }, + { + "epoch": 0.78, + "learning_rate": 1.479465449804433e-05, + "loss": 0.4516, + "step": 9582 + }, + { + "epoch": 0.78, + "learning_rate": 1.4794111255975665e-05, + "loss": 0.4914, + "step": 9583 + }, + { + "epoch": 0.78, + "learning_rate": 1.4793568013906998e-05, + "loss": 0.4929, + "step": 9584 + }, + { + "epoch": 0.78, + "learning_rate": 1.4793024771838332e-05, + "loss": 0.4188, + "step": 9585 + }, + { + "epoch": 0.78, + "learning_rate": 1.4792481529769666e-05, + "loss": 0.4994, + "step": 9586 + }, + { + "epoch": 0.78, + "learning_rate": 1.4791938287701e-05, + "loss": 0.2757, + "step": 9587 + }, + { + "epoch": 0.78, + "learning_rate": 1.4791395045632335e-05, + "loss": 0.589, + "step": 9588 + }, + { + "epoch": 0.78, + "learning_rate": 1.4790851803563669e-05, + "loss": 0.2481, + "step": 9589 + }, + { + "epoch": 0.78, + "learning_rate": 1.4790308561495003e-05, + "loss": 0.6779, + "step": 9590 + }, + { + "epoch": 0.78, + "learning_rate": 1.4789765319426337e-05, + "loss": 0.5718, + "step": 9591 + }, + { + "epoch": 0.78, + "learning_rate": 1.4789222077357672e-05, + "loss": 0.4305, + "step": 9592 + }, + { + "epoch": 0.78, + "learning_rate": 1.4788678835289006e-05, + "loss": 0.4253, + "step": 9593 + }, + { + "epoch": 0.78, + "learning_rate": 1.478813559322034e-05, + "loss": 0.483, + "step": 9594 + }, + { + "epoch": 0.78, + "learning_rate": 1.4787592351151674e-05, + "loss": 0.5876, + "step": 9595 + }, + { + "epoch": 0.78, + "learning_rate": 1.4787049109083009e-05, + "loss": 0.7682, + "step": 9596 + }, + { + "epoch": 0.78, + "learning_rate": 1.4786505867014343e-05, + "loss": 0.5372, + "step": 9597 + }, + { + "epoch": 0.78, + "learning_rate": 1.4785962624945677e-05, + "loss": 0.3487, + "step": 9598 + }, + { + "epoch": 0.78, + "learning_rate": 1.4785419382877011e-05, + "loss": 0.6355, + "step": 9599 + }, + { + "epoch": 0.78, + "learning_rate": 1.4784876140808346e-05, + "loss": 0.3489, + "step": 9600 + }, + { + "epoch": 0.78, + "learning_rate": 1.478433289873968e-05, + "loss": 0.4144, + "step": 9601 + }, + { + "epoch": 0.78, + "learning_rate": 1.4783789656671016e-05, + "loss": 0.6077, + "step": 9602 + }, + { + "epoch": 0.78, + "learning_rate": 1.4783246414602348e-05, + "loss": 0.6794, + "step": 9603 + }, + { + "epoch": 0.78, + "learning_rate": 1.478270317253368e-05, + "loss": 0.5867, + "step": 9604 + }, + { + "epoch": 0.78, + "learning_rate": 1.4782159930465017e-05, + "loss": 0.5671, + "step": 9605 + }, + { + "epoch": 0.78, + "learning_rate": 1.478161668839635e-05, + "loss": 0.5605, + "step": 9606 + }, + { + "epoch": 0.78, + "learning_rate": 1.4781073446327685e-05, + "loss": 0.5312, + "step": 9607 + }, + { + "epoch": 0.78, + "learning_rate": 1.4780530204259018e-05, + "loss": 0.4554, + "step": 9608 + }, + { + "epoch": 0.78, + "learning_rate": 1.4779986962190354e-05, + "loss": 0.4434, + "step": 9609 + }, + { + "epoch": 0.78, + "learning_rate": 1.4779443720121686e-05, + "loss": 0.4637, + "step": 9610 + }, + { + "epoch": 0.78, + "learning_rate": 1.4778900478053022e-05, + "loss": 0.4767, + "step": 9611 + }, + { + "epoch": 0.78, + "learning_rate": 1.4778357235984355e-05, + "loss": 0.5008, + "step": 9612 + }, + { + "epoch": 0.78, + "learning_rate": 1.477781399391569e-05, + "loss": 0.2579, + "step": 9613 + }, + { + "epoch": 0.78, + "learning_rate": 1.4777270751847023e-05, + "loss": 0.5021, + "step": 9614 + }, + { + "epoch": 0.78, + "learning_rate": 1.4776727509778359e-05, + "loss": 0.3494, + "step": 9615 + }, + { + "epoch": 0.78, + "learning_rate": 1.4776184267709692e-05, + "loss": 0.4558, + "step": 9616 + }, + { + "epoch": 0.78, + "learning_rate": 1.4775641025641027e-05, + "loss": 0.4207, + "step": 9617 + }, + { + "epoch": 0.78, + "learning_rate": 1.477509778357236e-05, + "loss": 0.5635, + "step": 9618 + }, + { + "epoch": 0.78, + "learning_rate": 1.4774554541503696e-05, + "loss": 0.3936, + "step": 9619 + }, + { + "epoch": 0.78, + "learning_rate": 1.477401129943503e-05, + "loss": 0.6568, + "step": 9620 + }, + { + "epoch": 0.78, + "learning_rate": 1.4773468057366364e-05, + "loss": 0.2142, + "step": 9621 + }, + { + "epoch": 0.78, + "learning_rate": 1.4772924815297699e-05, + "loss": 0.455, + "step": 9622 + }, + { + "epoch": 0.78, + "learning_rate": 1.4772381573229031e-05, + "loss": 0.258, + "step": 9623 + }, + { + "epoch": 0.78, + "learning_rate": 1.4771838331160367e-05, + "loss": 0.6108, + "step": 9624 + }, + { + "epoch": 0.78, + "learning_rate": 1.47712950890917e-05, + "loss": 0.8243, + "step": 9625 + }, + { + "epoch": 0.78, + "learning_rate": 1.4770751847023036e-05, + "loss": 0.3635, + "step": 9626 + }, + { + "epoch": 0.78, + "learning_rate": 1.4770208604954368e-05, + "loss": 0.2357, + "step": 9627 + }, + { + "epoch": 0.78, + "learning_rate": 1.4769665362885704e-05, + "loss": 0.4127, + "step": 9628 + }, + { + "epoch": 0.78, + "learning_rate": 1.4769122120817037e-05, + "loss": 0.6944, + "step": 9629 + }, + { + "epoch": 0.78, + "learning_rate": 1.4768578878748372e-05, + "loss": 0.5109, + "step": 9630 + }, + { + "epoch": 0.78, + "learning_rate": 1.4768035636679705e-05, + "loss": 0.2818, + "step": 9631 + }, + { + "epoch": 0.78, + "learning_rate": 1.4767492394611041e-05, + "loss": 0.6803, + "step": 9632 + }, + { + "epoch": 0.78, + "learning_rate": 1.4766949152542373e-05, + "loss": 0.6638, + "step": 9633 + }, + { + "epoch": 0.79, + "learning_rate": 1.476640591047371e-05, + "loss": 0.3034, + "step": 9634 + }, + { + "epoch": 0.79, + "learning_rate": 1.4765862668405042e-05, + "loss": 0.388, + "step": 9635 + }, + { + "epoch": 0.79, + "learning_rate": 1.4765319426336378e-05, + "loss": 0.5008, + "step": 9636 + }, + { + "epoch": 0.79, + "learning_rate": 1.476477618426771e-05, + "loss": 0.3819, + "step": 9637 + }, + { + "epoch": 0.79, + "learning_rate": 1.4764232942199046e-05, + "loss": 0.3444, + "step": 9638 + }, + { + "epoch": 0.79, + "learning_rate": 1.4763689700130379e-05, + "loss": 0.3185, + "step": 9639 + }, + { + "epoch": 0.79, + "learning_rate": 1.4763146458061715e-05, + "loss": 0.5813, + "step": 9640 + }, + { + "epoch": 0.79, + "learning_rate": 1.4762603215993047e-05, + "loss": 0.4245, + "step": 9641 + }, + { + "epoch": 0.79, + "learning_rate": 1.4762059973924382e-05, + "loss": 0.4788, + "step": 9642 + }, + { + "epoch": 0.79, + "learning_rate": 1.4761516731855716e-05, + "loss": 0.3645, + "step": 9643 + }, + { + "epoch": 0.79, + "learning_rate": 1.476097348978705e-05, + "loss": 0.4255, + "step": 9644 + }, + { + "epoch": 0.79, + "learning_rate": 1.4760430247718384e-05, + "loss": 0.3918, + "step": 9645 + }, + { + "epoch": 0.79, + "learning_rate": 1.4759887005649718e-05, + "loss": 0.3603, + "step": 9646 + }, + { + "epoch": 0.79, + "learning_rate": 1.4759343763581053e-05, + "loss": 0.2096, + "step": 9647 + }, + { + "epoch": 0.79, + "learning_rate": 1.4758800521512387e-05, + "loss": 0.7154, + "step": 9648 + }, + { + "epoch": 0.79, + "learning_rate": 1.4758257279443721e-05, + "loss": 0.7554, + "step": 9649 + }, + { + "epoch": 0.79, + "learning_rate": 1.4757714037375055e-05, + "loss": 0.4245, + "step": 9650 + }, + { + "epoch": 0.79, + "learning_rate": 1.475717079530639e-05, + "loss": 0.3139, + "step": 9651 + }, + { + "epoch": 0.79, + "learning_rate": 1.4756627553237724e-05, + "loss": 0.4697, + "step": 9652 + }, + { + "epoch": 0.79, + "learning_rate": 1.4756084311169058e-05, + "loss": 0.377, + "step": 9653 + }, + { + "epoch": 0.79, + "learning_rate": 1.4755541069100392e-05, + "loss": 0.3957, + "step": 9654 + }, + { + "epoch": 0.79, + "learning_rate": 1.4754997827031726e-05, + "loss": 0.5173, + "step": 9655 + }, + { + "epoch": 0.79, + "learning_rate": 1.475445458496306e-05, + "loss": 0.4211, + "step": 9656 + }, + { + "epoch": 0.79, + "learning_rate": 1.4753911342894397e-05, + "loss": 0.3401, + "step": 9657 + }, + { + "epoch": 0.79, + "learning_rate": 1.475336810082573e-05, + "loss": 0.603, + "step": 9658 + }, + { + "epoch": 0.79, + "learning_rate": 1.4752824858757065e-05, + "loss": 0.3435, + "step": 9659 + }, + { + "epoch": 0.79, + "learning_rate": 1.4752281616688398e-05, + "loss": 0.2156, + "step": 9660 + }, + { + "epoch": 0.79, + "learning_rate": 1.475173837461973e-05, + "loss": 0.6032, + "step": 9661 + }, + { + "epoch": 0.79, + "learning_rate": 1.4751195132551066e-05, + "loss": 0.2324, + "step": 9662 + }, + { + "epoch": 0.79, + "learning_rate": 1.4750651890482399e-05, + "loss": 0.3678, + "step": 9663 + }, + { + "epoch": 0.79, + "learning_rate": 1.4750108648413735e-05, + "loss": 0.2638, + "step": 9664 + }, + { + "epoch": 0.79, + "learning_rate": 1.4749565406345067e-05, + "loss": 0.5619, + "step": 9665 + }, + { + "epoch": 0.79, + "learning_rate": 1.4749022164276403e-05, + "loss": 0.1763, + "step": 9666 + }, + { + "epoch": 0.79, + "learning_rate": 1.4748478922207736e-05, + "loss": 0.7596, + "step": 9667 + }, + { + "epoch": 0.79, + "learning_rate": 1.4747935680139071e-05, + "loss": 0.4705, + "step": 9668 + }, + { + "epoch": 0.79, + "learning_rate": 1.4747392438070404e-05, + "loss": 0.4813, + "step": 9669 + }, + { + "epoch": 0.79, + "learning_rate": 1.474684919600174e-05, + "loss": 0.3137, + "step": 9670 + }, + { + "epoch": 0.79, + "learning_rate": 1.4746305953933072e-05, + "loss": 0.5256, + "step": 9671 + }, + { + "epoch": 0.79, + "learning_rate": 1.4745762711864408e-05, + "loss": 0.5355, + "step": 9672 + }, + { + "epoch": 0.79, + "learning_rate": 1.4745219469795743e-05, + "loss": 0.5814, + "step": 9673 + }, + { + "epoch": 0.79, + "learning_rate": 1.4744676227727077e-05, + "loss": 0.5073, + "step": 9674 + }, + { + "epoch": 0.79, + "learning_rate": 1.4744132985658411e-05, + "loss": 0.6557, + "step": 9675 + }, + { + "epoch": 0.79, + "learning_rate": 1.4743589743589745e-05, + "loss": 0.6045, + "step": 9676 + }, + { + "epoch": 0.79, + "learning_rate": 1.474304650152108e-05, + "loss": 0.5148, + "step": 9677 + }, + { + "epoch": 0.79, + "learning_rate": 1.4742503259452414e-05, + "loss": 0.479, + "step": 9678 + }, + { + "epoch": 0.79, + "learning_rate": 1.4741960017383748e-05, + "loss": 0.2852, + "step": 9679 + }, + { + "epoch": 0.79, + "learning_rate": 1.474141677531508e-05, + "loss": 0.724, + "step": 9680 + }, + { + "epoch": 0.79, + "learning_rate": 1.4740873533246416e-05, + "loss": 0.3372, + "step": 9681 + }, + { + "epoch": 0.79, + "learning_rate": 1.4740330291177749e-05, + "loss": 0.3984, + "step": 9682 + }, + { + "epoch": 0.79, + "learning_rate": 1.4739787049109085e-05, + "loss": 0.2854, + "step": 9683 + }, + { + "epoch": 0.79, + "learning_rate": 1.4739243807040417e-05, + "loss": 0.3195, + "step": 9684 + }, + { + "epoch": 0.79, + "learning_rate": 1.4738700564971753e-05, + "loss": 0.5126, + "step": 9685 + }, + { + "epoch": 0.79, + "learning_rate": 1.4738157322903086e-05, + "loss": 0.3954, + "step": 9686 + }, + { + "epoch": 0.79, + "learning_rate": 1.4737614080834422e-05, + "loss": 0.441, + "step": 9687 + }, + { + "epoch": 0.79, + "learning_rate": 1.4737070838765754e-05, + "loss": 0.4526, + "step": 9688 + }, + { + "epoch": 0.79, + "learning_rate": 1.473652759669709e-05, + "loss": 0.46, + "step": 9689 + }, + { + "epoch": 0.79, + "learning_rate": 1.4735984354628423e-05, + "loss": 0.194, + "step": 9690 + }, + { + "epoch": 0.79, + "learning_rate": 1.4735441112559759e-05, + "loss": 0.6026, + "step": 9691 + }, + { + "epoch": 0.79, + "learning_rate": 1.4734897870491091e-05, + "loss": 0.365, + "step": 9692 + }, + { + "epoch": 0.79, + "learning_rate": 1.4734354628422427e-05, + "loss": 0.5206, + "step": 9693 + }, + { + "epoch": 0.79, + "learning_rate": 1.473381138635376e-05, + "loss": 0.316, + "step": 9694 + }, + { + "epoch": 0.79, + "learning_rate": 1.4733268144285096e-05, + "loss": 0.3684, + "step": 9695 + }, + { + "epoch": 0.79, + "learning_rate": 1.4732724902216428e-05, + "loss": 0.4351, + "step": 9696 + }, + { + "epoch": 0.79, + "learning_rate": 1.4732181660147764e-05, + "loss": 0.4597, + "step": 9697 + }, + { + "epoch": 0.79, + "learning_rate": 1.4731638418079097e-05, + "loss": 0.725, + "step": 9698 + }, + { + "epoch": 0.79, + "learning_rate": 1.4731095176010431e-05, + "loss": 0.5156, + "step": 9699 + }, + { + "epoch": 0.79, + "learning_rate": 1.4730551933941765e-05, + "loss": 0.4007, + "step": 9700 + }, + { + "epoch": 0.79, + "learning_rate": 1.47300086918731e-05, + "loss": 0.4053, + "step": 9701 + }, + { + "epoch": 0.79, + "learning_rate": 1.4729465449804434e-05, + "loss": 0.32, + "step": 9702 + }, + { + "epoch": 0.79, + "learning_rate": 1.4728922207735768e-05, + "loss": 0.5381, + "step": 9703 + }, + { + "epoch": 0.79, + "learning_rate": 1.4728378965667102e-05, + "loss": 0.3754, + "step": 9704 + }, + { + "epoch": 0.79, + "learning_rate": 1.4727835723598436e-05, + "loss": 0.3004, + "step": 9705 + }, + { + "epoch": 0.79, + "learning_rate": 1.472729248152977e-05, + "loss": 0.3084, + "step": 9706 + }, + { + "epoch": 0.79, + "learning_rate": 1.4726749239461105e-05, + "loss": 0.4423, + "step": 9707 + }, + { + "epoch": 0.79, + "learning_rate": 1.4726205997392439e-05, + "loss": 0.359, + "step": 9708 + }, + { + "epoch": 0.79, + "learning_rate": 1.4725662755323773e-05, + "loss": 0.1819, + "step": 9709 + }, + { + "epoch": 0.79, + "learning_rate": 1.472511951325511e-05, + "loss": 0.5982, + "step": 9710 + }, + { + "epoch": 0.79, + "learning_rate": 1.4724576271186442e-05, + "loss": 0.4393, + "step": 9711 + }, + { + "epoch": 0.79, + "learning_rate": 1.4724033029117778e-05, + "loss": 0.4582, + "step": 9712 + }, + { + "epoch": 0.79, + "learning_rate": 1.472348978704911e-05, + "loss": 0.3772, + "step": 9713 + }, + { + "epoch": 0.79, + "learning_rate": 1.4722946544980446e-05, + "loss": 0.3504, + "step": 9714 + }, + { + "epoch": 0.79, + "learning_rate": 1.4722403302911779e-05, + "loss": 0.4482, + "step": 9715 + }, + { + "epoch": 0.79, + "learning_rate": 1.4721860060843115e-05, + "loss": 0.726, + "step": 9716 + }, + { + "epoch": 0.79, + "learning_rate": 1.4721316818774447e-05, + "loss": 0.4846, + "step": 9717 + }, + { + "epoch": 0.79, + "learning_rate": 1.472077357670578e-05, + "loss": 0.6007, + "step": 9718 + }, + { + "epoch": 0.79, + "learning_rate": 1.4720230334637116e-05, + "loss": 0.6423, + "step": 9719 + }, + { + "epoch": 0.79, + "learning_rate": 1.4719687092568448e-05, + "loss": 0.5223, + "step": 9720 + }, + { + "epoch": 0.79, + "learning_rate": 1.4719143850499784e-05, + "loss": 0.6939, + "step": 9721 + }, + { + "epoch": 0.79, + "learning_rate": 1.4718600608431117e-05, + "loss": 0.5877, + "step": 9722 + }, + { + "epoch": 0.79, + "learning_rate": 1.4718057366362452e-05, + "loss": 0.6346, + "step": 9723 + }, + { + "epoch": 0.79, + "learning_rate": 1.4717514124293785e-05, + "loss": 0.5978, + "step": 9724 + }, + { + "epoch": 0.79, + "learning_rate": 1.4716970882225121e-05, + "loss": 0.7404, + "step": 9725 + }, + { + "epoch": 0.79, + "learning_rate": 1.4716427640156453e-05, + "loss": 0.4689, + "step": 9726 + }, + { + "epoch": 0.79, + "learning_rate": 1.471588439808779e-05, + "loss": 0.6743, + "step": 9727 + }, + { + "epoch": 0.79, + "learning_rate": 1.4715341156019124e-05, + "loss": 0.3522, + "step": 9728 + }, + { + "epoch": 0.79, + "learning_rate": 1.4714797913950458e-05, + "loss": 0.4972, + "step": 9729 + }, + { + "epoch": 0.79, + "learning_rate": 1.4714254671881792e-05, + "loss": 0.5636, + "step": 9730 + }, + { + "epoch": 0.79, + "learning_rate": 1.4713711429813126e-05, + "loss": 0.3456, + "step": 9731 + }, + { + "epoch": 0.79, + "learning_rate": 1.471316818774446e-05, + "loss": 0.4604, + "step": 9732 + }, + { + "epoch": 0.79, + "learning_rate": 1.4712624945675795e-05, + "loss": 0.4747, + "step": 9733 + }, + { + "epoch": 0.79, + "learning_rate": 1.4712081703607129e-05, + "loss": 0.3672, + "step": 9734 + }, + { + "epoch": 0.79, + "learning_rate": 1.4711538461538463e-05, + "loss": 0.7591, + "step": 9735 + }, + { + "epoch": 0.79, + "learning_rate": 1.4710995219469797e-05, + "loss": 0.3254, + "step": 9736 + }, + { + "epoch": 0.79, + "learning_rate": 1.471045197740113e-05, + "loss": 0.5847, + "step": 9737 + }, + { + "epoch": 0.79, + "learning_rate": 1.4709908735332466e-05, + "loss": 0.3363, + "step": 9738 + }, + { + "epoch": 0.79, + "learning_rate": 1.4709365493263798e-05, + "loss": 0.2345, + "step": 9739 + }, + { + "epoch": 0.79, + "learning_rate": 1.4708822251195134e-05, + "loss": 0.4417, + "step": 9740 + }, + { + "epoch": 0.79, + "learning_rate": 1.4708279009126467e-05, + "loss": 0.2965, + "step": 9741 + }, + { + "epoch": 0.79, + "learning_rate": 1.4707735767057803e-05, + "loss": 0.4614, + "step": 9742 + }, + { + "epoch": 0.79, + "learning_rate": 1.4707192524989135e-05, + "loss": 0.364, + "step": 9743 + }, + { + "epoch": 0.79, + "learning_rate": 1.4706649282920471e-05, + "loss": 0.5096, + "step": 9744 + }, + { + "epoch": 0.79, + "learning_rate": 1.4706106040851804e-05, + "loss": 0.3838, + "step": 9745 + }, + { + "epoch": 0.79, + "learning_rate": 1.470556279878314e-05, + "loss": 0.4267, + "step": 9746 + }, + { + "epoch": 0.79, + "learning_rate": 1.4705019556714472e-05, + "loss": 0.2578, + "step": 9747 + }, + { + "epoch": 0.79, + "learning_rate": 1.4704476314645808e-05, + "loss": 0.4294, + "step": 9748 + }, + { + "epoch": 0.79, + "learning_rate": 1.470393307257714e-05, + "loss": 0.3898, + "step": 9749 + }, + { + "epoch": 0.79, + "learning_rate": 1.4703389830508477e-05, + "loss": 0.3141, + "step": 9750 + }, + { + "epoch": 0.79, + "eval_accuracy": 0.832603158430973, + "eval_loss": 0.4343816041946411, + "eval_runtime": 22.331, + "eval_samples_per_second": 439.524, + "eval_steps_per_second": 3.448, + "step": 9750 + }, + { + "epoch": 0.79, + "learning_rate": 1.470284658843981e-05, + "loss": 0.3276, + "step": 9751 + }, + { + "epoch": 0.79, + "learning_rate": 1.4702303346371145e-05, + "loss": 0.2122, + "step": 9752 + }, + { + "epoch": 0.79, + "learning_rate": 1.4701760104302478e-05, + "loss": 0.6603, + "step": 9753 + }, + { + "epoch": 0.79, + "learning_rate": 1.4701216862233814e-05, + "loss": 0.6107, + "step": 9754 + }, + { + "epoch": 0.79, + "learning_rate": 1.4700673620165146e-05, + "loss": 0.5341, + "step": 9755 + }, + { + "epoch": 0.79, + "learning_rate": 1.470013037809648e-05, + "loss": 0.4373, + "step": 9756 + }, + { + "epoch": 0.8, + "learning_rate": 1.4699587136027815e-05, + "loss": 0.3894, + "step": 9757 + }, + { + "epoch": 0.8, + "learning_rate": 1.4699043893959149e-05, + "loss": 0.7074, + "step": 9758 + }, + { + "epoch": 0.8, + "learning_rate": 1.4698500651890483e-05, + "loss": 0.3074, + "step": 9759 + }, + { + "epoch": 0.8, + "learning_rate": 1.4697957409821817e-05, + "loss": 0.8312, + "step": 9760 + }, + { + "epoch": 0.8, + "learning_rate": 1.4697414167753152e-05, + "loss": 0.3811, + "step": 9761 + }, + { + "epoch": 0.8, + "learning_rate": 1.4696870925684486e-05, + "loss": 0.5649, + "step": 9762 + }, + { + "epoch": 0.8, + "learning_rate": 1.469632768361582e-05, + "loss": 0.3944, + "step": 9763 + }, + { + "epoch": 0.8, + "learning_rate": 1.4695784441547154e-05, + "loss": 0.4831, + "step": 9764 + }, + { + "epoch": 0.8, + "learning_rate": 1.469524119947849e-05, + "loss": 0.4844, + "step": 9765 + }, + { + "epoch": 0.8, + "learning_rate": 1.4694697957409823e-05, + "loss": 0.3117, + "step": 9766 + }, + { + "epoch": 0.8, + "learning_rate": 1.4694154715341159e-05, + "loss": 0.3809, + "step": 9767 + }, + { + "epoch": 0.8, + "learning_rate": 1.4693611473272491e-05, + "loss": 0.3502, + "step": 9768 + }, + { + "epoch": 0.8, + "learning_rate": 1.4693068231203827e-05, + "loss": 0.4151, + "step": 9769 + }, + { + "epoch": 0.8, + "learning_rate": 1.469252498913516e-05, + "loss": 0.4103, + "step": 9770 + }, + { + "epoch": 0.8, + "learning_rate": 1.4691981747066496e-05, + "loss": 0.2032, + "step": 9771 + }, + { + "epoch": 0.8, + "learning_rate": 1.4691438504997828e-05, + "loss": 0.3002, + "step": 9772 + }, + { + "epoch": 0.8, + "learning_rate": 1.4690895262929164e-05, + "loss": 0.4311, + "step": 9773 + }, + { + "epoch": 0.8, + "learning_rate": 1.4690352020860497e-05, + "loss": 0.6626, + "step": 9774 + }, + { + "epoch": 0.8, + "learning_rate": 1.4689808778791829e-05, + "loss": 0.7179, + "step": 9775 + }, + { + "epoch": 0.8, + "learning_rate": 1.4689265536723165e-05, + "loss": 0.4976, + "step": 9776 + }, + { + "epoch": 0.8, + "learning_rate": 1.4688722294654498e-05, + "loss": 0.2751, + "step": 9777 + }, + { + "epoch": 0.8, + "learning_rate": 1.4688179052585833e-05, + "loss": 0.281, + "step": 9778 + }, + { + "epoch": 0.8, + "learning_rate": 1.4687635810517166e-05, + "loss": 0.4059, + "step": 9779 + }, + { + "epoch": 0.8, + "learning_rate": 1.4687092568448502e-05, + "loss": 0.4276, + "step": 9780 + }, + { + "epoch": 0.8, + "learning_rate": 1.4686549326379836e-05, + "loss": 0.4248, + "step": 9781 + }, + { + "epoch": 0.8, + "learning_rate": 1.468600608431117e-05, + "loss": 0.8768, + "step": 9782 + }, + { + "epoch": 0.8, + "learning_rate": 1.4685462842242505e-05, + "loss": 0.5759, + "step": 9783 + }, + { + "epoch": 0.8, + "learning_rate": 1.4684919600173839e-05, + "loss": 0.6008, + "step": 9784 + }, + { + "epoch": 0.8, + "learning_rate": 1.4684376358105173e-05, + "loss": 0.4532, + "step": 9785 + }, + { + "epoch": 0.8, + "learning_rate": 1.4683833116036507e-05, + "loss": 0.3201, + "step": 9786 + }, + { + "epoch": 0.8, + "learning_rate": 1.4683289873967842e-05, + "loss": 0.7036, + "step": 9787 + }, + { + "epoch": 0.8, + "learning_rate": 1.4682746631899176e-05, + "loss": 0.5378, + "step": 9788 + }, + { + "epoch": 0.8, + "learning_rate": 1.468220338983051e-05, + "loss": 0.597, + "step": 9789 + }, + { + "epoch": 0.8, + "learning_rate": 1.4681660147761844e-05, + "loss": 0.3404, + "step": 9790 + }, + { + "epoch": 0.8, + "learning_rate": 1.4681116905693178e-05, + "loss": 0.4343, + "step": 9791 + }, + { + "epoch": 0.8, + "learning_rate": 1.4680573663624513e-05, + "loss": 0.4365, + "step": 9792 + }, + { + "epoch": 0.8, + "learning_rate": 1.4680030421555847e-05, + "loss": 0.3882, + "step": 9793 + }, + { + "epoch": 0.8, + "learning_rate": 1.467948717948718e-05, + "loss": 0.6618, + "step": 9794 + }, + { + "epoch": 0.8, + "learning_rate": 1.4678943937418515e-05, + "loss": 0.5029, + "step": 9795 + }, + { + "epoch": 0.8, + "learning_rate": 1.4678400695349848e-05, + "loss": 0.4543, + "step": 9796 + }, + { + "epoch": 0.8, + "learning_rate": 1.4677857453281184e-05, + "loss": 0.2204, + "step": 9797 + }, + { + "epoch": 0.8, + "learning_rate": 1.4677314211212516e-05, + "loss": 0.4656, + "step": 9798 + }, + { + "epoch": 0.8, + "learning_rate": 1.4676770969143852e-05, + "loss": 0.3386, + "step": 9799 + }, + { + "epoch": 0.8, + "learning_rate": 1.4676227727075185e-05, + "loss": 0.4934, + "step": 9800 + }, + { + "epoch": 0.8, + "learning_rate": 1.467568448500652e-05, + "loss": 0.7145, + "step": 9801 + }, + { + "epoch": 0.8, + "learning_rate": 1.4675141242937853e-05, + "loss": 0.3202, + "step": 9802 + }, + { + "epoch": 0.8, + "learning_rate": 1.467459800086919e-05, + "loss": 0.7264, + "step": 9803 + }, + { + "epoch": 0.8, + "learning_rate": 1.4674054758800522e-05, + "loss": 0.4568, + "step": 9804 + }, + { + "epoch": 0.8, + "learning_rate": 1.4673511516731858e-05, + "loss": 0.3585, + "step": 9805 + }, + { + "epoch": 0.8, + "learning_rate": 1.467296827466319e-05, + "loss": 0.3443, + "step": 9806 + }, + { + "epoch": 0.8, + "learning_rate": 1.4672425032594526e-05, + "loss": 0.3816, + "step": 9807 + }, + { + "epoch": 0.8, + "learning_rate": 1.4671881790525859e-05, + "loss": 0.5171, + "step": 9808 + }, + { + "epoch": 0.8, + "learning_rate": 1.4671338548457195e-05, + "loss": 0.4788, + "step": 9809 + }, + { + "epoch": 0.8, + "learning_rate": 1.4670795306388527e-05, + "loss": 0.3763, + "step": 9810 + }, + { + "epoch": 0.8, + "learning_rate": 1.4670252064319863e-05, + "loss": 0.3321, + "step": 9811 + }, + { + "epoch": 0.8, + "learning_rate": 1.4669708822251196e-05, + "loss": 0.4753, + "step": 9812 + }, + { + "epoch": 0.8, + "learning_rate": 1.466916558018253e-05, + "loss": 0.4908, + "step": 9813 + }, + { + "epoch": 0.8, + "learning_rate": 1.4668622338113864e-05, + "loss": 0.2915, + "step": 9814 + }, + { + "epoch": 0.8, + "learning_rate": 1.4668079096045198e-05, + "loss": 0.5189, + "step": 9815 + }, + { + "epoch": 0.8, + "learning_rate": 1.4667535853976533e-05, + "loss": 0.5686, + "step": 9816 + }, + { + "epoch": 0.8, + "learning_rate": 1.4666992611907867e-05, + "loss": 0.3725, + "step": 9817 + }, + { + "epoch": 0.8, + "learning_rate": 1.4666449369839203e-05, + "loss": 0.3079, + "step": 9818 + }, + { + "epoch": 0.8, + "learning_rate": 1.4665906127770535e-05, + "loss": 0.2937, + "step": 9819 + }, + { + "epoch": 0.8, + "learning_rate": 1.4665362885701871e-05, + "loss": 0.5034, + "step": 9820 + }, + { + "epoch": 0.8, + "learning_rate": 1.4664819643633204e-05, + "loss": 0.1798, + "step": 9821 + }, + { + "epoch": 0.8, + "learning_rate": 1.466427640156454e-05, + "loss": 0.6146, + "step": 9822 + }, + { + "epoch": 0.8, + "learning_rate": 1.4663733159495872e-05, + "loss": 0.3995, + "step": 9823 + }, + { + "epoch": 0.8, + "learning_rate": 1.4663189917427208e-05, + "loss": 0.5727, + "step": 9824 + }, + { + "epoch": 0.8, + "learning_rate": 1.466264667535854e-05, + "loss": 0.3278, + "step": 9825 + }, + { + "epoch": 0.8, + "learning_rate": 1.4662103433289877e-05, + "loss": 0.5046, + "step": 9826 + }, + { + "epoch": 0.8, + "learning_rate": 1.4661560191221209e-05, + "loss": 0.3213, + "step": 9827 + }, + { + "epoch": 0.8, + "learning_rate": 1.4661016949152545e-05, + "loss": 0.4349, + "step": 9828 + }, + { + "epoch": 0.8, + "learning_rate": 1.4660473707083878e-05, + "loss": 0.264, + "step": 9829 + }, + { + "epoch": 0.8, + "learning_rate": 1.4659930465015213e-05, + "loss": 0.4489, + "step": 9830 + }, + { + "epoch": 0.8, + "learning_rate": 1.4659387222946546e-05, + "loss": 0.4126, + "step": 9831 + }, + { + "epoch": 0.8, + "learning_rate": 1.4658843980877879e-05, + "loss": 0.3125, + "step": 9832 + }, + { + "epoch": 0.8, + "learning_rate": 1.4658300738809214e-05, + "loss": 0.4333, + "step": 9833 + }, + { + "epoch": 0.8, + "learning_rate": 1.4657757496740547e-05, + "loss": 0.6956, + "step": 9834 + }, + { + "epoch": 0.8, + "learning_rate": 1.4657214254671883e-05, + "loss": 0.2486, + "step": 9835 + }, + { + "epoch": 0.8, + "learning_rate": 1.4656671012603217e-05, + "loss": 0.4725, + "step": 9836 + }, + { + "epoch": 0.8, + "learning_rate": 1.4656127770534551e-05, + "loss": 0.2683, + "step": 9837 + }, + { + "epoch": 0.8, + "learning_rate": 1.4655584528465886e-05, + "loss": 0.3624, + "step": 9838 + }, + { + "epoch": 0.8, + "learning_rate": 1.465504128639722e-05, + "loss": 0.3275, + "step": 9839 + }, + { + "epoch": 0.8, + "learning_rate": 1.4654498044328554e-05, + "loss": 0.4812, + "step": 9840 + }, + { + "epoch": 0.8, + "learning_rate": 1.4653954802259888e-05, + "loss": 0.5008, + "step": 9841 + }, + { + "epoch": 0.8, + "learning_rate": 1.4653411560191223e-05, + "loss": 0.4458, + "step": 9842 + }, + { + "epoch": 0.8, + "learning_rate": 1.4652868318122557e-05, + "loss": 0.5146, + "step": 9843 + }, + { + "epoch": 0.8, + "learning_rate": 1.4652325076053891e-05, + "loss": 0.3336, + "step": 9844 + }, + { + "epoch": 0.8, + "learning_rate": 1.4651781833985225e-05, + "loss": 0.4412, + "step": 9845 + }, + { + "epoch": 0.8, + "learning_rate": 1.465123859191656e-05, + "loss": 0.4948, + "step": 9846 + }, + { + "epoch": 0.8, + "learning_rate": 1.4650695349847894e-05, + "loss": 0.8088, + "step": 9847 + }, + { + "epoch": 0.8, + "learning_rate": 1.4650152107779228e-05, + "loss": 0.4071, + "step": 9848 + }, + { + "epoch": 0.8, + "learning_rate": 1.4649608865710562e-05, + "loss": 0.4816, + "step": 9849 + }, + { + "epoch": 0.8, + "learning_rate": 1.4649065623641896e-05, + "loss": 0.2972, + "step": 9850 + }, + { + "epoch": 0.8, + "learning_rate": 1.4648522381573229e-05, + "loss": 0.457, + "step": 9851 + }, + { + "epoch": 0.8, + "learning_rate": 1.4647979139504565e-05, + "loss": 0.2938, + "step": 9852 + }, + { + "epoch": 0.8, + "learning_rate": 1.4647435897435897e-05, + "loss": 0.3013, + "step": 9853 + }, + { + "epoch": 0.8, + "learning_rate": 1.4646892655367233e-05, + "loss": 0.4478, + "step": 9854 + }, + { + "epoch": 0.8, + "learning_rate": 1.4646349413298566e-05, + "loss": 0.2892, + "step": 9855 + }, + { + "epoch": 0.8, + "learning_rate": 1.4645806171229902e-05, + "loss": 0.6297, + "step": 9856 + }, + { + "epoch": 0.8, + "learning_rate": 1.4645262929161234e-05, + "loss": 0.6825, + "step": 9857 + }, + { + "epoch": 0.8, + "learning_rate": 1.464471968709257e-05, + "loss": 0.4211, + "step": 9858 + }, + { + "epoch": 0.8, + "learning_rate": 1.4644176445023903e-05, + "loss": 0.7453, + "step": 9859 + }, + { + "epoch": 0.8, + "learning_rate": 1.4643633202955239e-05, + "loss": 0.4483, + "step": 9860 + }, + { + "epoch": 0.8, + "learning_rate": 1.4643089960886571e-05, + "loss": 0.4782, + "step": 9861 + }, + { + "epoch": 0.8, + "learning_rate": 1.4642546718817907e-05, + "loss": 0.4377, + "step": 9862 + }, + { + "epoch": 0.8, + "learning_rate": 1.464200347674924e-05, + "loss": 0.436, + "step": 9863 + }, + { + "epoch": 0.8, + "learning_rate": 1.4641460234680576e-05, + "loss": 0.3052, + "step": 9864 + }, + { + "epoch": 0.8, + "learning_rate": 1.4640916992611908e-05, + "loss": 0.4794, + "step": 9865 + }, + { + "epoch": 0.8, + "learning_rate": 1.4640373750543244e-05, + "loss": 0.2253, + "step": 9866 + }, + { + "epoch": 0.8, + "learning_rate": 1.4639830508474577e-05, + "loss": 0.4794, + "step": 9867 + }, + { + "epoch": 0.8, + "learning_rate": 1.4639287266405913e-05, + "loss": 0.6242, + "step": 9868 + }, + { + "epoch": 0.8, + "learning_rate": 1.4638744024337245e-05, + "loss": 0.3061, + "step": 9869 + }, + { + "epoch": 0.8, + "learning_rate": 1.463820078226858e-05, + "loss": 0.3201, + "step": 9870 + }, + { + "epoch": 0.8, + "learning_rate": 1.4637657540199914e-05, + "loss": 0.4413, + "step": 9871 + }, + { + "epoch": 0.8, + "learning_rate": 1.4637114298131248e-05, + "loss": 0.663, + "step": 9872 + }, + { + "epoch": 0.8, + "learning_rate": 1.4636571056062584e-05, + "loss": 0.5017, + "step": 9873 + }, + { + "epoch": 0.8, + "learning_rate": 1.4636027813993916e-05, + "loss": 0.4313, + "step": 9874 + }, + { + "epoch": 0.8, + "learning_rate": 1.4635484571925252e-05, + "loss": 0.4275, + "step": 9875 + }, + { + "epoch": 0.8, + "learning_rate": 1.4634941329856585e-05, + "loss": 0.5309, + "step": 9876 + }, + { + "epoch": 0.8, + "learning_rate": 1.463439808778792e-05, + "loss": 0.4822, + "step": 9877 + }, + { + "epoch": 0.8, + "learning_rate": 1.4633854845719253e-05, + "loss": 0.5368, + "step": 9878 + }, + { + "epoch": 0.81, + "learning_rate": 1.4633311603650589e-05, + "loss": 0.375, + "step": 9879 + }, + { + "epoch": 0.81, + "learning_rate": 1.4632768361581922e-05, + "loss": 0.3553, + "step": 9880 + }, + { + "epoch": 0.81, + "learning_rate": 1.4632225119513258e-05, + "loss": 0.6399, + "step": 9881 + }, + { + "epoch": 0.81, + "learning_rate": 1.463168187744459e-05, + "loss": 0.4363, + "step": 9882 + }, + { + "epoch": 0.81, + "learning_rate": 1.4631138635375926e-05, + "loss": 0.4036, + "step": 9883 + }, + { + "epoch": 0.81, + "learning_rate": 1.4630595393307259e-05, + "loss": 0.444, + "step": 9884 + }, + { + "epoch": 0.81, + "learning_rate": 1.4630052151238594e-05, + "loss": 0.4449, + "step": 9885 + }, + { + "epoch": 0.81, + "learning_rate": 1.4629508909169927e-05, + "loss": 0.4732, + "step": 9886 + }, + { + "epoch": 0.81, + "learning_rate": 1.4628965667101263e-05, + "loss": 0.4652, + "step": 9887 + }, + { + "epoch": 0.81, + "learning_rate": 1.4628422425032595e-05, + "loss": 0.5129, + "step": 9888 + }, + { + "epoch": 0.81, + "learning_rate": 1.462787918296393e-05, + "loss": 0.2667, + "step": 9889 + }, + { + "epoch": 0.81, + "learning_rate": 1.4627335940895264e-05, + "loss": 0.3434, + "step": 9890 + }, + { + "epoch": 0.81, + "learning_rate": 1.4626792698826598e-05, + "loss": 0.3853, + "step": 9891 + }, + { + "epoch": 0.81, + "learning_rate": 1.4626249456757932e-05, + "loss": 0.2008, + "step": 9892 + }, + { + "epoch": 0.81, + "learning_rate": 1.4625706214689267e-05, + "loss": 0.7114, + "step": 9893 + }, + { + "epoch": 0.81, + "learning_rate": 1.46251629726206e-05, + "loss": 0.6059, + "step": 9894 + }, + { + "epoch": 0.81, + "learning_rate": 1.4624619730551935e-05, + "loss": 0.3789, + "step": 9895 + }, + { + "epoch": 0.81, + "learning_rate": 1.462407648848327e-05, + "loss": 0.2857, + "step": 9896 + }, + { + "epoch": 0.81, + "learning_rate": 1.4623533246414604e-05, + "loss": 0.429, + "step": 9897 + }, + { + "epoch": 0.81, + "learning_rate": 1.4622990004345938e-05, + "loss": 0.4902, + "step": 9898 + }, + { + "epoch": 0.81, + "learning_rate": 1.4622446762277272e-05, + "loss": 0.5444, + "step": 9899 + }, + { + "epoch": 0.81, + "learning_rate": 1.4621903520208606e-05, + "loss": 0.4315, + "step": 9900 + }, + { + "epoch": 0.81, + "learning_rate": 1.462136027813994e-05, + "loss": 0.7503, + "step": 9901 + }, + { + "epoch": 0.81, + "learning_rate": 1.4620817036071275e-05, + "loss": 0.5032, + "step": 9902 + }, + { + "epoch": 0.81, + "learning_rate": 1.4620273794002609e-05, + "loss": 0.5787, + "step": 9903 + }, + { + "epoch": 0.81, + "learning_rate": 1.4619730551933943e-05, + "loss": 0.5498, + "step": 9904 + }, + { + "epoch": 0.81, + "learning_rate": 1.4619187309865277e-05, + "loss": 0.4494, + "step": 9905 + }, + { + "epoch": 0.81, + "learning_rate": 1.4618644067796612e-05, + "loss": 0.4667, + "step": 9906 + }, + { + "epoch": 0.81, + "learning_rate": 1.4618100825727946e-05, + "loss": 0.3867, + "step": 9907 + }, + { + "epoch": 0.81, + "learning_rate": 1.4617557583659278e-05, + "loss": 0.2327, + "step": 9908 + }, + { + "epoch": 0.81, + "learning_rate": 1.4617014341590614e-05, + "loss": 0.3085, + "step": 9909 + }, + { + "epoch": 0.81, + "learning_rate": 1.4616471099521947e-05, + "loss": 0.4965, + "step": 9910 + }, + { + "epoch": 0.81, + "learning_rate": 1.4615927857453283e-05, + "loss": 0.2699, + "step": 9911 + }, + { + "epoch": 0.81, + "learning_rate": 1.4615384615384615e-05, + "loss": 0.4742, + "step": 9912 + }, + { + "epoch": 0.81, + "learning_rate": 1.4614841373315951e-05, + "loss": 0.716, + "step": 9913 + }, + { + "epoch": 0.81, + "learning_rate": 1.4614298131247284e-05, + "loss": 0.2588, + "step": 9914 + }, + { + "epoch": 0.81, + "learning_rate": 1.461375488917862e-05, + "loss": 0.4917, + "step": 9915 + }, + { + "epoch": 0.81, + "learning_rate": 1.4613211647109952e-05, + "loss": 0.5568, + "step": 9916 + }, + { + "epoch": 0.81, + "learning_rate": 1.4612668405041288e-05, + "loss": 0.606, + "step": 9917 + }, + { + "epoch": 0.81, + "learning_rate": 1.461212516297262e-05, + "loss": 0.3986, + "step": 9918 + }, + { + "epoch": 0.81, + "learning_rate": 1.4611581920903957e-05, + "loss": 0.2894, + "step": 9919 + }, + { + "epoch": 0.81, + "learning_rate": 1.4611038678835289e-05, + "loss": 0.513, + "step": 9920 + }, + { + "epoch": 0.81, + "learning_rate": 1.4610495436766625e-05, + "loss": 0.4925, + "step": 9921 + }, + { + "epoch": 0.81, + "learning_rate": 1.4609952194697958e-05, + "loss": 0.2731, + "step": 9922 + }, + { + "epoch": 0.81, + "learning_rate": 1.4609408952629294e-05, + "loss": 0.4982, + "step": 9923 + }, + { + "epoch": 0.81, + "learning_rate": 1.4608865710560626e-05, + "loss": 0.4277, + "step": 9924 + }, + { + "epoch": 0.81, + "learning_rate": 1.4608322468491962e-05, + "loss": 0.4663, + "step": 9925 + }, + { + "epoch": 0.81, + "learning_rate": 1.4607779226423296e-05, + "loss": 0.3571, + "step": 9926 + }, + { + "epoch": 0.81, + "learning_rate": 1.4607235984354629e-05, + "loss": 0.4657, + "step": 9927 + }, + { + "epoch": 0.81, + "learning_rate": 1.4606692742285965e-05, + "loss": 0.5279, + "step": 9928 + }, + { + "epoch": 0.81, + "learning_rate": 1.4606149500217297e-05, + "loss": 0.5219, + "step": 9929 + }, + { + "epoch": 0.81, + "learning_rate": 1.4605606258148633e-05, + "loss": 0.7081, + "step": 9930 + }, + { + "epoch": 0.81, + "learning_rate": 1.4605063016079966e-05, + "loss": 0.2414, + "step": 9931 + }, + { + "epoch": 0.81, + "learning_rate": 1.4604519774011302e-05, + "loss": 0.4771, + "step": 9932 + }, + { + "epoch": 0.81, + "learning_rate": 1.4603976531942634e-05, + "loss": 0.4252, + "step": 9933 + }, + { + "epoch": 0.81, + "learning_rate": 1.460343328987397e-05, + "loss": 0.6095, + "step": 9934 + }, + { + "epoch": 0.81, + "learning_rate": 1.4602890047805303e-05, + "loss": 0.4442, + "step": 9935 + }, + { + "epoch": 0.81, + "learning_rate": 1.4602346805736639e-05, + "loss": 0.4874, + "step": 9936 + }, + { + "epoch": 0.81, + "learning_rate": 1.4601803563667971e-05, + "loss": 0.2608, + "step": 9937 + }, + { + "epoch": 0.81, + "learning_rate": 1.4601260321599307e-05, + "loss": 0.5129, + "step": 9938 + }, + { + "epoch": 0.81, + "learning_rate": 1.460071707953064e-05, + "loss": 0.3976, + "step": 9939 + }, + { + "epoch": 0.81, + "learning_rate": 1.4600173837461975e-05, + "loss": 0.4237, + "step": 9940 + }, + { + "epoch": 0.81, + "learning_rate": 1.4599630595393308e-05, + "loss": 0.4849, + "step": 9941 + }, + { + "epoch": 0.81, + "learning_rate": 1.4599087353324644e-05, + "loss": 0.4548, + "step": 9942 + }, + { + "epoch": 0.81, + "learning_rate": 1.4598544111255976e-05, + "loss": 0.1655, + "step": 9943 + }, + { + "epoch": 0.81, + "learning_rate": 1.4598000869187312e-05, + "loss": 0.4186, + "step": 9944 + }, + { + "epoch": 0.81, + "learning_rate": 1.4597457627118645e-05, + "loss": 0.3614, + "step": 9945 + }, + { + "epoch": 0.81, + "learning_rate": 1.4596914385049979e-05, + "loss": 0.5321, + "step": 9946 + }, + { + "epoch": 0.81, + "learning_rate": 1.4596371142981313e-05, + "loss": 0.4711, + "step": 9947 + }, + { + "epoch": 0.81, + "learning_rate": 1.4595827900912648e-05, + "loss": 0.4233, + "step": 9948 + }, + { + "epoch": 0.81, + "learning_rate": 1.4595284658843982e-05, + "loss": 0.3231, + "step": 9949 + }, + { + "epoch": 0.81, + "learning_rate": 1.4594741416775316e-05, + "loss": 0.6202, + "step": 9950 + }, + { + "epoch": 0.81, + "learning_rate": 1.459419817470665e-05, + "loss": 0.2992, + "step": 9951 + }, + { + "epoch": 0.81, + "learning_rate": 1.4593654932637984e-05, + "loss": 0.335, + "step": 9952 + }, + { + "epoch": 0.81, + "learning_rate": 1.4593111690569319e-05, + "loss": 0.6099, + "step": 9953 + }, + { + "epoch": 0.81, + "learning_rate": 1.4592568448500653e-05, + "loss": 0.3416, + "step": 9954 + }, + { + "epoch": 0.81, + "learning_rate": 1.4592025206431987e-05, + "loss": 0.5932, + "step": 9955 + }, + { + "epoch": 0.81, + "learning_rate": 1.4591481964363321e-05, + "loss": 0.4582, + "step": 9956 + }, + { + "epoch": 0.81, + "learning_rate": 1.4590938722294656e-05, + "loss": 0.4809, + "step": 9957 + }, + { + "epoch": 0.81, + "learning_rate": 1.459039548022599e-05, + "loss": 0.5982, + "step": 9958 + }, + { + "epoch": 0.81, + "learning_rate": 1.4589852238157324e-05, + "loss": 0.2226, + "step": 9959 + }, + { + "epoch": 0.81, + "learning_rate": 1.4589308996088658e-05, + "loss": 0.6026, + "step": 9960 + }, + { + "epoch": 0.81, + "learning_rate": 1.4588765754019993e-05, + "loss": 0.3569, + "step": 9961 + }, + { + "epoch": 0.81, + "learning_rate": 1.4588222511951327e-05, + "loss": 0.6719, + "step": 9962 + }, + { + "epoch": 0.81, + "learning_rate": 1.4587679269882663e-05, + "loss": 0.3423, + "step": 9963 + }, + { + "epoch": 0.81, + "learning_rate": 1.4587136027813995e-05, + "loss": 0.2183, + "step": 9964 + }, + { + "epoch": 0.81, + "learning_rate": 1.4586592785745328e-05, + "loss": 0.4329, + "step": 9965 + }, + { + "epoch": 0.81, + "learning_rate": 1.4586049543676664e-05, + "loss": 0.3384, + "step": 9966 + }, + { + "epoch": 0.81, + "learning_rate": 1.4585506301607996e-05, + "loss": 0.3994, + "step": 9967 + }, + { + "epoch": 0.81, + "learning_rate": 1.4584963059539332e-05, + "loss": 0.377, + "step": 9968 + }, + { + "epoch": 0.81, + "learning_rate": 1.4584419817470665e-05, + "loss": 0.7576, + "step": 9969 + }, + { + "epoch": 0.81, + "learning_rate": 1.4583876575402e-05, + "loss": 0.5938, + "step": 9970 + }, + { + "epoch": 0.81, + "learning_rate": 1.4583333333333333e-05, + "loss": 0.5142, + "step": 9971 + }, + { + "epoch": 0.81, + "learning_rate": 1.4582790091264669e-05, + "loss": 0.4764, + "step": 9972 + }, + { + "epoch": 0.81, + "learning_rate": 1.4582246849196002e-05, + "loss": 0.2983, + "step": 9973 + }, + { + "epoch": 0.81, + "learning_rate": 1.4581703607127338e-05, + "loss": 0.4764, + "step": 9974 + }, + { + "epoch": 0.81, + "learning_rate": 1.458116036505867e-05, + "loss": 0.4576, + "step": 9975 + }, + { + "epoch": 0.81, + "learning_rate": 1.4580617122990006e-05, + "loss": 0.5642, + "step": 9976 + }, + { + "epoch": 0.81, + "learning_rate": 1.4580073880921339e-05, + "loss": 0.5839, + "step": 9977 + }, + { + "epoch": 0.81, + "learning_rate": 1.4579530638852674e-05, + "loss": 0.5006, + "step": 9978 + }, + { + "epoch": 0.81, + "learning_rate": 1.4578987396784007e-05, + "loss": 0.2917, + "step": 9979 + }, + { + "epoch": 0.81, + "learning_rate": 1.4578444154715343e-05, + "loss": 0.5576, + "step": 9980 + }, + { + "epoch": 0.81, + "learning_rate": 1.4577900912646677e-05, + "loss": 0.325, + "step": 9981 + }, + { + "epoch": 0.81, + "learning_rate": 1.4577357670578011e-05, + "loss": 0.3583, + "step": 9982 + }, + { + "epoch": 0.81, + "learning_rate": 1.4576814428509346e-05, + "loss": 0.6378, + "step": 9983 + }, + { + "epoch": 0.81, + "learning_rate": 1.4576271186440678e-05, + "loss": 0.4063, + "step": 9984 + }, + { + "epoch": 0.81, + "learning_rate": 1.4575727944372014e-05, + "loss": 0.875, + "step": 9985 + }, + { + "epoch": 0.81, + "learning_rate": 1.4575184702303347e-05, + "loss": 0.5806, + "step": 9986 + }, + { + "epoch": 0.81, + "learning_rate": 1.4574641460234683e-05, + "loss": 0.4185, + "step": 9987 + }, + { + "epoch": 0.81, + "learning_rate": 1.4574098218166015e-05, + "loss": 0.515, + "step": 9988 + }, + { + "epoch": 0.81, + "learning_rate": 1.4573554976097351e-05, + "loss": 0.5034, + "step": 9989 + }, + { + "epoch": 0.81, + "learning_rate": 1.4573011734028684e-05, + "loss": 0.2893, + "step": 9990 + }, + { + "epoch": 0.81, + "learning_rate": 1.457246849196002e-05, + "loss": 0.5553, + "step": 9991 + }, + { + "epoch": 0.81, + "learning_rate": 1.4571925249891352e-05, + "loss": 0.3393, + "step": 9992 + }, + { + "epoch": 0.81, + "learning_rate": 1.4571382007822688e-05, + "loss": 0.2909, + "step": 9993 + }, + { + "epoch": 0.81, + "learning_rate": 1.457083876575402e-05, + "loss": 0.4887, + "step": 9994 + }, + { + "epoch": 0.81, + "learning_rate": 1.4570295523685356e-05, + "loss": 0.334, + "step": 9995 + }, + { + "epoch": 0.81, + "learning_rate": 1.4569752281616689e-05, + "loss": 0.3597, + "step": 9996 + }, + { + "epoch": 0.81, + "learning_rate": 1.4569209039548025e-05, + "loss": 0.4079, + "step": 9997 + }, + { + "epoch": 0.81, + "learning_rate": 1.4568665797479357e-05, + "loss": 0.2833, + "step": 9998 + }, + { + "epoch": 0.81, + "learning_rate": 1.4568122555410693e-05, + "loss": 0.3093, + "step": 9999 + }, + { + "epoch": 0.81, + "learning_rate": 1.4567579313342026e-05, + "loss": 0.3835, + "step": 10000 + }, + { + "epoch": 0.81, + "eval_accuracy": 0.8352521650534895, + "eval_loss": 0.4367486536502838, + "eval_runtime": 22.3225, + "eval_samples_per_second": 439.691, + "eval_steps_per_second": 3.449, + "step": 10000 + }, + { + "epoch": 0.81, + "learning_rate": 1.4567036071273362e-05, + "loss": 0.2891, + "step": 10001 + }, + { + "epoch": 0.82, + "learning_rate": 1.4566492829204694e-05, + "loss": 0.4229, + "step": 10002 + }, + { + "epoch": 0.82, + "learning_rate": 1.4565949587136029e-05, + "loss": 0.2228, + "step": 10003 + }, + { + "epoch": 0.82, + "learning_rate": 1.4565406345067363e-05, + "loss": 0.3069, + "step": 10004 + }, + { + "epoch": 0.82, + "learning_rate": 1.4564863102998697e-05, + "loss": 0.4128, + "step": 10005 + }, + { + "epoch": 0.82, + "learning_rate": 1.4564319860930031e-05, + "loss": 0.4199, + "step": 10006 + }, + { + "epoch": 0.82, + "learning_rate": 1.4563776618861365e-05, + "loss": 0.2693, + "step": 10007 + }, + { + "epoch": 0.82, + "learning_rate": 1.45632333767927e-05, + "loss": 0.4917, + "step": 10008 + }, + { + "epoch": 0.82, + "learning_rate": 1.4562690134724034e-05, + "loss": 0.3607, + "step": 10009 + }, + { + "epoch": 0.82, + "learning_rate": 1.4562146892655368e-05, + "loss": 0.3953, + "step": 10010 + }, + { + "epoch": 0.82, + "learning_rate": 1.4561603650586702e-05, + "loss": 0.243, + "step": 10011 + }, + { + "epoch": 0.82, + "learning_rate": 1.4561060408518037e-05, + "loss": 0.2703, + "step": 10012 + }, + { + "epoch": 0.82, + "learning_rate": 1.4560517166449371e-05, + "loss": 0.6436, + "step": 10013 + }, + { + "epoch": 0.82, + "learning_rate": 1.4559973924380705e-05, + "loss": 0.3813, + "step": 10014 + }, + { + "epoch": 0.82, + "learning_rate": 1.455943068231204e-05, + "loss": 0.852, + "step": 10015 + }, + { + "epoch": 0.82, + "learning_rate": 1.4558887440243375e-05, + "loss": 0.1918, + "step": 10016 + }, + { + "epoch": 0.82, + "learning_rate": 1.4558344198174708e-05, + "loss": 0.3839, + "step": 10017 + }, + { + "epoch": 0.82, + "learning_rate": 1.4557800956106044e-05, + "loss": 0.1196, + "step": 10018 + }, + { + "epoch": 0.82, + "learning_rate": 1.4557257714037376e-05, + "loss": 0.7465, + "step": 10019 + }, + { + "epoch": 0.82, + "learning_rate": 1.4556714471968712e-05, + "loss": 0.2081, + "step": 10020 + }, + { + "epoch": 0.82, + "learning_rate": 1.4556171229900045e-05, + "loss": 0.4383, + "step": 10021 + }, + { + "epoch": 0.82, + "learning_rate": 1.4555627987831377e-05, + "loss": 0.5697, + "step": 10022 + }, + { + "epoch": 0.82, + "learning_rate": 1.4555084745762713e-05, + "loss": 0.4005, + "step": 10023 + }, + { + "epoch": 0.82, + "learning_rate": 1.4554541503694046e-05, + "loss": 0.27, + "step": 10024 + }, + { + "epoch": 0.82, + "learning_rate": 1.4553998261625382e-05, + "loss": 0.5531, + "step": 10025 + }, + { + "epoch": 0.82, + "learning_rate": 1.4553455019556714e-05, + "loss": 0.7955, + "step": 10026 + }, + { + "epoch": 0.82, + "learning_rate": 1.455291177748805e-05, + "loss": 0.5623, + "step": 10027 + }, + { + "epoch": 0.82, + "learning_rate": 1.4552368535419383e-05, + "loss": 0.4848, + "step": 10028 + }, + { + "epoch": 0.82, + "learning_rate": 1.4551825293350719e-05, + "loss": 0.6841, + "step": 10029 + }, + { + "epoch": 0.82, + "learning_rate": 1.4551282051282051e-05, + "loss": 0.3172, + "step": 10030 + }, + { + "epoch": 0.82, + "learning_rate": 1.4550738809213387e-05, + "loss": 0.3497, + "step": 10031 + }, + { + "epoch": 0.82, + "learning_rate": 1.455019556714472e-05, + "loss": 0.2527, + "step": 10032 + }, + { + "epoch": 0.82, + "learning_rate": 1.4549652325076055e-05, + "loss": 0.5191, + "step": 10033 + }, + { + "epoch": 0.82, + "learning_rate": 1.454910908300739e-05, + "loss": 0.3974, + "step": 10034 + }, + { + "epoch": 0.82, + "learning_rate": 1.4548565840938724e-05, + "loss": 0.2071, + "step": 10035 + }, + { + "epoch": 0.82, + "learning_rate": 1.4548022598870058e-05, + "loss": 0.5451, + "step": 10036 + }, + { + "epoch": 0.82, + "learning_rate": 1.4547479356801392e-05, + "loss": 0.3874, + "step": 10037 + }, + { + "epoch": 0.82, + "learning_rate": 1.4546936114732727e-05, + "loss": 0.3511, + "step": 10038 + }, + { + "epoch": 0.82, + "learning_rate": 1.4546392872664061e-05, + "loss": 0.3515, + "step": 10039 + }, + { + "epoch": 0.82, + "learning_rate": 1.4545849630595395e-05, + "loss": 0.2569, + "step": 10040 + }, + { + "epoch": 0.82, + "learning_rate": 1.4545306388526728e-05, + "loss": 0.3678, + "step": 10041 + }, + { + "epoch": 0.82, + "learning_rate": 1.4544763146458064e-05, + "loss": 0.5067, + "step": 10042 + }, + { + "epoch": 0.82, + "learning_rate": 1.4544219904389396e-05, + "loss": 0.3656, + "step": 10043 + }, + { + "epoch": 0.82, + "learning_rate": 1.4543676662320732e-05, + "loss": 0.445, + "step": 10044 + }, + { + "epoch": 0.82, + "learning_rate": 1.4543133420252065e-05, + "loss": 0.3342, + "step": 10045 + }, + { + "epoch": 0.82, + "learning_rate": 1.45425901781834e-05, + "loss": 0.3543, + "step": 10046 + }, + { + "epoch": 0.82, + "learning_rate": 1.4542046936114733e-05, + "loss": 0.3362, + "step": 10047 + }, + { + "epoch": 0.82, + "learning_rate": 1.4541503694046069e-05, + "loss": 0.5212, + "step": 10048 + }, + { + "epoch": 0.82, + "learning_rate": 1.4540960451977401e-05, + "loss": 0.6216, + "step": 10049 + }, + { + "epoch": 0.82, + "learning_rate": 1.4540417209908737e-05, + "loss": 0.5005, + "step": 10050 + }, + { + "epoch": 0.82, + "learning_rate": 1.453987396784007e-05, + "loss": 0.3023, + "step": 10051 + }, + { + "epoch": 0.82, + "learning_rate": 1.4539330725771406e-05, + "loss": 0.4872, + "step": 10052 + }, + { + "epoch": 0.82, + "learning_rate": 1.4538787483702738e-05, + "loss": 0.6053, + "step": 10053 + }, + { + "epoch": 0.82, + "learning_rate": 1.4538244241634074e-05, + "loss": 0.7924, + "step": 10054 + }, + { + "epoch": 0.82, + "learning_rate": 1.4537700999565407e-05, + "loss": 0.9394, + "step": 10055 + }, + { + "epoch": 0.82, + "learning_rate": 1.4537157757496743e-05, + "loss": 0.1937, + "step": 10056 + }, + { + "epoch": 0.82, + "learning_rate": 1.4536614515428075e-05, + "loss": 0.4932, + "step": 10057 + }, + { + "epoch": 0.82, + "learning_rate": 1.4536071273359411e-05, + "loss": 0.6884, + "step": 10058 + }, + { + "epoch": 0.82, + "learning_rate": 1.4535528031290744e-05, + "loss": 0.4731, + "step": 10059 + }, + { + "epoch": 0.82, + "learning_rate": 1.4534984789222078e-05, + "loss": 0.5145, + "step": 10060 + }, + { + "epoch": 0.82, + "learning_rate": 1.4534441547153412e-05, + "loss": 0.2079, + "step": 10061 + }, + { + "epoch": 0.82, + "learning_rate": 1.4533898305084746e-05, + "loss": 0.3393, + "step": 10062 + }, + { + "epoch": 0.82, + "learning_rate": 1.453335506301608e-05, + "loss": 0.6188, + "step": 10063 + }, + { + "epoch": 0.82, + "learning_rate": 1.4532811820947415e-05, + "loss": 0.8567, + "step": 10064 + }, + { + "epoch": 0.82, + "learning_rate": 1.453226857887875e-05, + "loss": 0.5194, + "step": 10065 + }, + { + "epoch": 0.82, + "learning_rate": 1.4531725336810083e-05, + "loss": 0.5312, + "step": 10066 + }, + { + "epoch": 0.82, + "learning_rate": 1.4531182094741418e-05, + "loss": 0.4568, + "step": 10067 + }, + { + "epoch": 0.82, + "learning_rate": 1.4530638852672752e-05, + "loss": 0.6827, + "step": 10068 + }, + { + "epoch": 0.82, + "learning_rate": 1.4530095610604086e-05, + "loss": 0.437, + "step": 10069 + }, + { + "epoch": 0.82, + "learning_rate": 1.452955236853542e-05, + "loss": 0.4062, + "step": 10070 + }, + { + "epoch": 0.82, + "learning_rate": 1.4529009126466756e-05, + "loss": 0.3061, + "step": 10071 + }, + { + "epoch": 0.82, + "learning_rate": 1.4528465884398089e-05, + "loss": 0.4236, + "step": 10072 + }, + { + "epoch": 0.82, + "learning_rate": 1.4527922642329425e-05, + "loss": 0.4839, + "step": 10073 + }, + { + "epoch": 0.82, + "learning_rate": 1.4527379400260757e-05, + "loss": 0.3627, + "step": 10074 + }, + { + "epoch": 0.82, + "learning_rate": 1.4526836158192093e-05, + "loss": 0.6834, + "step": 10075 + }, + { + "epoch": 0.82, + "learning_rate": 1.4526292916123426e-05, + "loss": 0.3525, + "step": 10076 + }, + { + "epoch": 0.82, + "learning_rate": 1.4525749674054762e-05, + "loss": 0.533, + "step": 10077 + }, + { + "epoch": 0.82, + "learning_rate": 1.4525206431986094e-05, + "loss": 0.3479, + "step": 10078 + }, + { + "epoch": 0.82, + "learning_rate": 1.4524663189917427e-05, + "loss": 0.2566, + "step": 10079 + }, + { + "epoch": 0.82, + "learning_rate": 1.4524119947848763e-05, + "loss": 0.408, + "step": 10080 + }, + { + "epoch": 0.82, + "learning_rate": 1.4523576705780095e-05, + "loss": 0.5459, + "step": 10081 + }, + { + "epoch": 0.82, + "learning_rate": 1.4523033463711431e-05, + "loss": 0.5074, + "step": 10082 + }, + { + "epoch": 0.82, + "learning_rate": 1.4522490221642764e-05, + "loss": 0.4957, + "step": 10083 + }, + { + "epoch": 0.82, + "learning_rate": 1.45219469795741e-05, + "loss": 0.5885, + "step": 10084 + }, + { + "epoch": 0.82, + "learning_rate": 1.4521403737505432e-05, + "loss": 0.5738, + "step": 10085 + }, + { + "epoch": 0.82, + "learning_rate": 1.4520860495436768e-05, + "loss": 0.4943, + "step": 10086 + }, + { + "epoch": 0.82, + "learning_rate": 1.45203172533681e-05, + "loss": 0.4755, + "step": 10087 + }, + { + "epoch": 0.82, + "learning_rate": 1.4519774011299436e-05, + "loss": 0.3455, + "step": 10088 + }, + { + "epoch": 0.82, + "learning_rate": 1.451923076923077e-05, + "loss": 0.5472, + "step": 10089 + }, + { + "epoch": 0.82, + "learning_rate": 1.4518687527162105e-05, + "loss": 0.4316, + "step": 10090 + }, + { + "epoch": 0.82, + "learning_rate": 1.451814428509344e-05, + "loss": 0.5489, + "step": 10091 + }, + { + "epoch": 0.82, + "learning_rate": 1.4517601043024773e-05, + "loss": 0.2974, + "step": 10092 + }, + { + "epoch": 0.82, + "learning_rate": 1.4517057800956108e-05, + "loss": 0.3673, + "step": 10093 + }, + { + "epoch": 0.82, + "learning_rate": 1.4516514558887442e-05, + "loss": 0.5808, + "step": 10094 + }, + { + "epoch": 0.82, + "learning_rate": 1.4515971316818776e-05, + "loss": 0.3931, + "step": 10095 + }, + { + "epoch": 0.82, + "learning_rate": 1.451542807475011e-05, + "loss": 0.2403, + "step": 10096 + }, + { + "epoch": 0.82, + "learning_rate": 1.4514884832681445e-05, + "loss": 0.4902, + "step": 10097 + }, + { + "epoch": 0.82, + "learning_rate": 1.4514341590612777e-05, + "loss": 0.5291, + "step": 10098 + }, + { + "epoch": 0.82, + "learning_rate": 1.4513798348544113e-05, + "loss": 0.2816, + "step": 10099 + }, + { + "epoch": 0.82, + "learning_rate": 1.4513255106475446e-05, + "loss": 0.5405, + "step": 10100 + }, + { + "epoch": 0.82, + "learning_rate": 1.4512711864406781e-05, + "loss": 0.241, + "step": 10101 + }, + { + "epoch": 0.82, + "learning_rate": 1.4512168622338114e-05, + "loss": 0.4681, + "step": 10102 + }, + { + "epoch": 0.82, + "learning_rate": 1.451162538026945e-05, + "loss": 0.3457, + "step": 10103 + }, + { + "epoch": 0.82, + "learning_rate": 1.4511082138200782e-05, + "loss": 0.43, + "step": 10104 + }, + { + "epoch": 0.82, + "learning_rate": 1.4510538896132118e-05, + "loss": 0.741, + "step": 10105 + }, + { + "epoch": 0.82, + "learning_rate": 1.4509995654063451e-05, + "loss": 0.5197, + "step": 10106 + }, + { + "epoch": 0.82, + "learning_rate": 1.4509452411994787e-05, + "loss": 0.5057, + "step": 10107 + }, + { + "epoch": 0.82, + "learning_rate": 1.450890916992612e-05, + "loss": 0.6061, + "step": 10108 + }, + { + "epoch": 0.82, + "learning_rate": 1.4508365927857455e-05, + "loss": 0.4379, + "step": 10109 + }, + { + "epoch": 0.82, + "learning_rate": 1.4507822685788788e-05, + "loss": 0.3768, + "step": 10110 + }, + { + "epoch": 0.82, + "learning_rate": 1.4507279443720124e-05, + "loss": 0.5415, + "step": 10111 + }, + { + "epoch": 0.82, + "learning_rate": 1.4506736201651456e-05, + "loss": 0.5972, + "step": 10112 + }, + { + "epoch": 0.82, + "learning_rate": 1.4506192959582792e-05, + "loss": 0.7077, + "step": 10113 + }, + { + "epoch": 0.82, + "learning_rate": 1.4505649717514125e-05, + "loss": 0.6691, + "step": 10114 + }, + { + "epoch": 0.82, + "learning_rate": 1.450510647544546e-05, + "loss": 0.4651, + "step": 10115 + }, + { + "epoch": 0.82, + "learning_rate": 1.4504563233376793e-05, + "loss": 0.5718, + "step": 10116 + }, + { + "epoch": 0.82, + "learning_rate": 1.4504019991308127e-05, + "loss": 0.6049, + "step": 10117 + }, + { + "epoch": 0.82, + "learning_rate": 1.4503476749239462e-05, + "loss": 0.4258, + "step": 10118 + }, + { + "epoch": 0.82, + "learning_rate": 1.4502933507170796e-05, + "loss": 0.491, + "step": 10119 + }, + { + "epoch": 0.82, + "learning_rate": 1.450239026510213e-05, + "loss": 0.581, + "step": 10120 + }, + { + "epoch": 0.82, + "learning_rate": 1.4501847023033464e-05, + "loss": 0.5515, + "step": 10121 + }, + { + "epoch": 0.82, + "learning_rate": 1.4501303780964799e-05, + "loss": 0.4192, + "step": 10122 + }, + { + "epoch": 0.82, + "learning_rate": 1.4500760538896133e-05, + "loss": 0.3949, + "step": 10123 + }, + { + "epoch": 0.82, + "learning_rate": 1.4500217296827469e-05, + "loss": 0.6821, + "step": 10124 + }, + { + "epoch": 0.83, + "learning_rate": 1.4499674054758801e-05, + "loss": 0.4652, + "step": 10125 + }, + { + "epoch": 0.83, + "learning_rate": 1.4499130812690137e-05, + "loss": 0.4425, + "step": 10126 + }, + { + "epoch": 0.83, + "learning_rate": 1.449858757062147e-05, + "loss": 0.5318, + "step": 10127 + }, + { + "epoch": 0.83, + "learning_rate": 1.4498044328552806e-05, + "loss": 0.4011, + "step": 10128 + }, + { + "epoch": 0.83, + "learning_rate": 1.4497501086484138e-05, + "loss": 0.4773, + "step": 10129 + }, + { + "epoch": 0.83, + "learning_rate": 1.4496957844415474e-05, + "loss": 0.4561, + "step": 10130 + }, + { + "epoch": 0.83, + "learning_rate": 1.4496414602346807e-05, + "loss": 0.6281, + "step": 10131 + }, + { + "epoch": 0.83, + "learning_rate": 1.4495871360278143e-05, + "loss": 0.299, + "step": 10132 + }, + { + "epoch": 0.83, + "learning_rate": 1.4495328118209475e-05, + "loss": 0.6453, + "step": 10133 + }, + { + "epoch": 0.83, + "learning_rate": 1.4494784876140811e-05, + "loss": 0.5513, + "step": 10134 + }, + { + "epoch": 0.83, + "learning_rate": 1.4494241634072144e-05, + "loss": 0.5828, + "step": 10135 + }, + { + "epoch": 0.83, + "learning_rate": 1.4493698392003476e-05, + "loss": 0.3513, + "step": 10136 + }, + { + "epoch": 0.83, + "learning_rate": 1.4493155149934812e-05, + "loss": 0.7378, + "step": 10137 + }, + { + "epoch": 0.83, + "learning_rate": 1.4492611907866145e-05, + "loss": 0.4671, + "step": 10138 + }, + { + "epoch": 0.83, + "learning_rate": 1.449206866579748e-05, + "loss": 0.6512, + "step": 10139 + }, + { + "epoch": 0.83, + "learning_rate": 1.4491525423728813e-05, + "loss": 0.2992, + "step": 10140 + }, + { + "epoch": 0.83, + "learning_rate": 1.4490982181660149e-05, + "loss": 0.4168, + "step": 10141 + }, + { + "epoch": 0.83, + "learning_rate": 1.4490438939591483e-05, + "loss": 0.5432, + "step": 10142 + }, + { + "epoch": 0.83, + "learning_rate": 1.4489895697522817e-05, + "loss": 0.7111, + "step": 10143 + }, + { + "epoch": 0.83, + "learning_rate": 1.4489352455454152e-05, + "loss": 0.45, + "step": 10144 + }, + { + "epoch": 0.83, + "learning_rate": 1.4488809213385486e-05, + "loss": 0.566, + "step": 10145 + }, + { + "epoch": 0.83, + "learning_rate": 1.448826597131682e-05, + "loss": 0.4527, + "step": 10146 + }, + { + "epoch": 0.83, + "learning_rate": 1.4487722729248154e-05, + "loss": 0.5283, + "step": 10147 + }, + { + "epoch": 0.83, + "learning_rate": 1.4487179487179489e-05, + "loss": 0.5767, + "step": 10148 + }, + { + "epoch": 0.83, + "learning_rate": 1.4486636245110823e-05, + "loss": 0.3039, + "step": 10149 + }, + { + "epoch": 0.83, + "learning_rate": 1.4486093003042157e-05, + "loss": 0.337, + "step": 10150 + }, + { + "epoch": 0.83, + "learning_rate": 1.4485549760973491e-05, + "loss": 0.3584, + "step": 10151 + }, + { + "epoch": 0.83, + "learning_rate": 1.4485006518904826e-05, + "loss": 0.4771, + "step": 10152 + }, + { + "epoch": 0.83, + "learning_rate": 1.448446327683616e-05, + "loss": 0.3362, + "step": 10153 + }, + { + "epoch": 0.83, + "learning_rate": 1.4483920034767494e-05, + "loss": 0.5749, + "step": 10154 + }, + { + "epoch": 0.83, + "learning_rate": 1.4483376792698827e-05, + "loss": 0.3303, + "step": 10155 + }, + { + "epoch": 0.83, + "learning_rate": 1.4482833550630162e-05, + "loss": 0.6427, + "step": 10156 + }, + { + "epoch": 0.83, + "learning_rate": 1.4482290308561495e-05, + "loss": 0.352, + "step": 10157 + }, + { + "epoch": 0.83, + "learning_rate": 1.4481747066492831e-05, + "loss": 0.3822, + "step": 10158 + }, + { + "epoch": 0.83, + "learning_rate": 1.4481203824424163e-05, + "loss": 0.449, + "step": 10159 + }, + { + "epoch": 0.83, + "learning_rate": 1.44806605823555e-05, + "loss": 0.589, + "step": 10160 + }, + { + "epoch": 0.83, + "learning_rate": 1.4480117340286832e-05, + "loss": 0.4322, + "step": 10161 + }, + { + "epoch": 0.83, + "learning_rate": 1.4479574098218168e-05, + "loss": 0.4396, + "step": 10162 + }, + { + "epoch": 0.83, + "learning_rate": 1.44790308561495e-05, + "loss": 0.2744, + "step": 10163 + }, + { + "epoch": 0.83, + "learning_rate": 1.4478487614080836e-05, + "loss": 0.4935, + "step": 10164 + }, + { + "epoch": 0.83, + "learning_rate": 1.4477944372012169e-05, + "loss": 0.3962, + "step": 10165 + }, + { + "epoch": 0.83, + "learning_rate": 1.4477401129943505e-05, + "loss": 0.4597, + "step": 10166 + }, + { + "epoch": 0.83, + "learning_rate": 1.4476857887874837e-05, + "loss": 0.2711, + "step": 10167 + }, + { + "epoch": 0.83, + "learning_rate": 1.4476314645806173e-05, + "loss": 0.3791, + "step": 10168 + }, + { + "epoch": 0.83, + "learning_rate": 1.4475771403737506e-05, + "loss": 0.5308, + "step": 10169 + }, + { + "epoch": 0.83, + "learning_rate": 1.4475228161668842e-05, + "loss": 0.4973, + "step": 10170 + }, + { + "epoch": 0.83, + "learning_rate": 1.4474684919600174e-05, + "loss": 0.3956, + "step": 10171 + }, + { + "epoch": 0.83, + "learning_rate": 1.447414167753151e-05, + "loss": 0.3306, + "step": 10172 + }, + { + "epoch": 0.83, + "learning_rate": 1.4473598435462843e-05, + "loss": 0.3139, + "step": 10173 + }, + { + "epoch": 0.83, + "learning_rate": 1.4473055193394177e-05, + "loss": 0.5212, + "step": 10174 + }, + { + "epoch": 0.83, + "learning_rate": 1.4472511951325511e-05, + "loss": 0.5829, + "step": 10175 + }, + { + "epoch": 0.83, + "learning_rate": 1.4471968709256845e-05, + "loss": 0.3852, + "step": 10176 + }, + { + "epoch": 0.83, + "learning_rate": 1.447142546718818e-05, + "loss": 0.7806, + "step": 10177 + }, + { + "epoch": 0.83, + "learning_rate": 1.4470882225119514e-05, + "loss": 0.2917, + "step": 10178 + }, + { + "epoch": 0.83, + "learning_rate": 1.447033898305085e-05, + "loss": 0.488, + "step": 10179 + }, + { + "epoch": 0.83, + "learning_rate": 1.4469795740982182e-05, + "loss": 0.8993, + "step": 10180 + }, + { + "epoch": 0.83, + "learning_rate": 1.4469252498913518e-05, + "loss": 0.325, + "step": 10181 + }, + { + "epoch": 0.83, + "learning_rate": 1.446870925684485e-05, + "loss": 0.3199, + "step": 10182 + }, + { + "epoch": 0.83, + "learning_rate": 1.4468166014776187e-05, + "loss": 0.5102, + "step": 10183 + }, + { + "epoch": 0.83, + "learning_rate": 1.446762277270752e-05, + "loss": 0.4215, + "step": 10184 + }, + { + "epoch": 0.83, + "learning_rate": 1.4467079530638855e-05, + "loss": 0.3525, + "step": 10185 + }, + { + "epoch": 0.83, + "learning_rate": 1.4466536288570188e-05, + "loss": 0.3989, + "step": 10186 + }, + { + "epoch": 0.83, + "learning_rate": 1.4465993046501524e-05, + "loss": 0.3935, + "step": 10187 + }, + { + "epoch": 0.83, + "learning_rate": 1.4465449804432856e-05, + "loss": 0.4185, + "step": 10188 + }, + { + "epoch": 0.83, + "learning_rate": 1.4464906562364192e-05, + "loss": 0.2366, + "step": 10189 + }, + { + "epoch": 0.83, + "learning_rate": 1.4464363320295525e-05, + "loss": 0.5668, + "step": 10190 + }, + { + "epoch": 0.83, + "learning_rate": 1.446382007822686e-05, + "loss": 0.4984, + "step": 10191 + }, + { + "epoch": 0.83, + "learning_rate": 1.4463276836158193e-05, + "loss": 0.4987, + "step": 10192 + }, + { + "epoch": 0.83, + "learning_rate": 1.4462733594089526e-05, + "loss": 0.7345, + "step": 10193 + }, + { + "epoch": 0.83, + "learning_rate": 1.4462190352020862e-05, + "loss": 0.6224, + "step": 10194 + }, + { + "epoch": 0.83, + "learning_rate": 1.4461647109952194e-05, + "loss": 0.445, + "step": 10195 + }, + { + "epoch": 0.83, + "learning_rate": 1.446110386788353e-05, + "loss": 0.5975, + "step": 10196 + }, + { + "epoch": 0.83, + "learning_rate": 1.4460560625814864e-05, + "loss": 0.4928, + "step": 10197 + }, + { + "epoch": 0.83, + "learning_rate": 1.4460017383746198e-05, + "loss": 0.5167, + "step": 10198 + }, + { + "epoch": 0.83, + "learning_rate": 1.4459474141677533e-05, + "loss": 0.3379, + "step": 10199 + }, + { + "epoch": 0.83, + "learning_rate": 1.4458930899608867e-05, + "loss": 0.1653, + "step": 10200 + }, + { + "epoch": 0.83, + "learning_rate": 1.4458387657540201e-05, + "loss": 0.4774, + "step": 10201 + }, + { + "epoch": 0.83, + "learning_rate": 1.4457844415471535e-05, + "loss": 0.5333, + "step": 10202 + }, + { + "epoch": 0.83, + "learning_rate": 1.445730117340287e-05, + "loss": 0.3699, + "step": 10203 + }, + { + "epoch": 0.83, + "learning_rate": 1.4456757931334204e-05, + "loss": 0.2754, + "step": 10204 + }, + { + "epoch": 0.83, + "learning_rate": 1.4456214689265538e-05, + "loss": 0.1689, + "step": 10205 + }, + { + "epoch": 0.83, + "learning_rate": 1.4455671447196872e-05, + "loss": 0.3587, + "step": 10206 + }, + { + "epoch": 0.83, + "learning_rate": 1.4455128205128207e-05, + "loss": 0.4739, + "step": 10207 + }, + { + "epoch": 0.83, + "learning_rate": 1.445458496305954e-05, + "loss": 0.4549, + "step": 10208 + }, + { + "epoch": 0.83, + "learning_rate": 1.4454041720990875e-05, + "loss": 0.6989, + "step": 10209 + }, + { + "epoch": 0.83, + "learning_rate": 1.445349847892221e-05, + "loss": 0.2163, + "step": 10210 + }, + { + "epoch": 0.83, + "learning_rate": 1.4452955236853543e-05, + "loss": 0.178, + "step": 10211 + }, + { + "epoch": 0.83, + "learning_rate": 1.4452411994784876e-05, + "loss": 0.6023, + "step": 10212 + }, + { + "epoch": 0.83, + "learning_rate": 1.4451868752716212e-05, + "loss": 0.6685, + "step": 10213 + }, + { + "epoch": 0.83, + "learning_rate": 1.4451325510647544e-05, + "loss": 0.3961, + "step": 10214 + }, + { + "epoch": 0.83, + "learning_rate": 1.445078226857888e-05, + "loss": 0.4867, + "step": 10215 + }, + { + "epoch": 0.83, + "learning_rate": 1.4450239026510213e-05, + "loss": 0.2951, + "step": 10216 + }, + { + "epoch": 0.83, + "learning_rate": 1.4449695784441549e-05, + "loss": 0.4807, + "step": 10217 + }, + { + "epoch": 0.83, + "learning_rate": 1.4449152542372881e-05, + "loss": 0.5006, + "step": 10218 + }, + { + "epoch": 0.83, + "learning_rate": 1.4448609300304217e-05, + "loss": 0.7231, + "step": 10219 + }, + { + "epoch": 0.83, + "learning_rate": 1.444806605823555e-05, + "loss": 0.554, + "step": 10220 + }, + { + "epoch": 0.83, + "learning_rate": 1.4447522816166886e-05, + "loss": 0.5203, + "step": 10221 + }, + { + "epoch": 0.83, + "learning_rate": 1.4446979574098218e-05, + "loss": 0.3889, + "step": 10222 + }, + { + "epoch": 0.83, + "learning_rate": 1.4446436332029554e-05, + "loss": 0.3949, + "step": 10223 + }, + { + "epoch": 0.83, + "learning_rate": 1.4445893089960887e-05, + "loss": 0.3086, + "step": 10224 + }, + { + "epoch": 0.83, + "learning_rate": 1.4445349847892223e-05, + "loss": 0.4055, + "step": 10225 + }, + { + "epoch": 0.83, + "learning_rate": 1.4444806605823555e-05, + "loss": 0.5393, + "step": 10226 + }, + { + "epoch": 0.83, + "learning_rate": 1.4444263363754891e-05, + "loss": 0.5082, + "step": 10227 + }, + { + "epoch": 0.83, + "learning_rate": 1.4443720121686224e-05, + "loss": 0.4595, + "step": 10228 + }, + { + "epoch": 0.83, + "learning_rate": 1.444317687961756e-05, + "loss": 0.6741, + "step": 10229 + }, + { + "epoch": 0.83, + "learning_rate": 1.4442633637548892e-05, + "loss": 0.3888, + "step": 10230 + }, + { + "epoch": 0.83, + "learning_rate": 1.4442090395480226e-05, + "loss": 0.5504, + "step": 10231 + }, + { + "epoch": 0.83, + "learning_rate": 1.4441547153411562e-05, + "loss": 0.4081, + "step": 10232 + }, + { + "epoch": 0.83, + "learning_rate": 1.4441003911342895e-05, + "loss": 0.5512, + "step": 10233 + }, + { + "epoch": 0.83, + "learning_rate": 1.444046066927423e-05, + "loss": 0.5338, + "step": 10234 + }, + { + "epoch": 0.83, + "learning_rate": 1.4439917427205563e-05, + "loss": 0.3738, + "step": 10235 + }, + { + "epoch": 0.83, + "learning_rate": 1.44393741851369e-05, + "loss": 0.342, + "step": 10236 + }, + { + "epoch": 0.83, + "learning_rate": 1.4438830943068232e-05, + "loss": 0.4469, + "step": 10237 + }, + { + "epoch": 0.83, + "learning_rate": 1.4438287700999568e-05, + "loss": 0.7756, + "step": 10238 + }, + { + "epoch": 0.83, + "learning_rate": 1.44377444589309e-05, + "loss": 0.416, + "step": 10239 + }, + { + "epoch": 0.83, + "learning_rate": 1.4437201216862236e-05, + "loss": 0.617, + "step": 10240 + }, + { + "epoch": 0.83, + "learning_rate": 1.4436657974793569e-05, + "loss": 0.6291, + "step": 10241 + }, + { + "epoch": 0.83, + "learning_rate": 1.4436114732724905e-05, + "loss": 0.2272, + "step": 10242 + }, + { + "epoch": 0.83, + "learning_rate": 1.4435571490656237e-05, + "loss": 0.3668, + "step": 10243 + }, + { + "epoch": 0.83, + "learning_rate": 1.4435028248587573e-05, + "loss": 0.6554, + "step": 10244 + }, + { + "epoch": 0.83, + "learning_rate": 1.4434485006518906e-05, + "loss": 0.2283, + "step": 10245 + }, + { + "epoch": 0.83, + "learning_rate": 1.4433941764450242e-05, + "loss": 0.3162, + "step": 10246 + }, + { + "epoch": 0.83, + "learning_rate": 1.4433398522381574e-05, + "loss": 0.4618, + "step": 10247 + }, + { + "epoch": 0.84, + "learning_rate": 1.443285528031291e-05, + "loss": 0.4943, + "step": 10248 + }, + { + "epoch": 0.84, + "learning_rate": 1.4432312038244243e-05, + "loss": 0.3583, + "step": 10249 + }, + { + "epoch": 0.84, + "learning_rate": 1.4431768796175577e-05, + "loss": 0.299, + "step": 10250 + }, + { + "epoch": 0.84, + "eval_accuracy": 0.8321956189505858, + "eval_loss": 0.4297224283218384, + "eval_runtime": 22.3271, + "eval_samples_per_second": 439.601, + "eval_steps_per_second": 3.449, + "step": 10250 + }, + { + "epoch": 0.84, + "learning_rate": 1.4431225554106911e-05, + "loss": 0.5661, + "step": 10251 + }, + { + "epoch": 0.84, + "learning_rate": 1.4430682312038245e-05, + "loss": 0.4831, + "step": 10252 + }, + { + "epoch": 0.84, + "learning_rate": 1.443013906996958e-05, + "loss": 0.3548, + "step": 10253 + }, + { + "epoch": 0.84, + "learning_rate": 1.4429595827900914e-05, + "loss": 0.4585, + "step": 10254 + }, + { + "epoch": 0.84, + "learning_rate": 1.4429052585832248e-05, + "loss": 0.4438, + "step": 10255 + }, + { + "epoch": 0.84, + "learning_rate": 1.4428509343763582e-05, + "loss": 0.4917, + "step": 10256 + }, + { + "epoch": 0.84, + "learning_rate": 1.4427966101694916e-05, + "loss": 0.4237, + "step": 10257 + }, + { + "epoch": 0.84, + "learning_rate": 1.442742285962625e-05, + "loss": 0.2502, + "step": 10258 + }, + { + "epoch": 0.84, + "learning_rate": 1.4426879617557585e-05, + "loss": 0.3427, + "step": 10259 + }, + { + "epoch": 0.84, + "learning_rate": 1.4426336375488919e-05, + "loss": 0.4449, + "step": 10260 + }, + { + "epoch": 0.84, + "learning_rate": 1.4425793133420253e-05, + "loss": 0.2882, + "step": 10261 + }, + { + "epoch": 0.84, + "learning_rate": 1.4425249891351587e-05, + "loss": 0.5896, + "step": 10262 + }, + { + "epoch": 0.84, + "learning_rate": 1.4424706649282922e-05, + "loss": 0.3545, + "step": 10263 + }, + { + "epoch": 0.84, + "learning_rate": 1.4424163407214256e-05, + "loss": 0.3468, + "step": 10264 + }, + { + "epoch": 0.84, + "learning_rate": 1.442362016514559e-05, + "loss": 0.398, + "step": 10265 + }, + { + "epoch": 0.84, + "learning_rate": 1.4423076923076924e-05, + "loss": 0.4102, + "step": 10266 + }, + { + "epoch": 0.84, + "learning_rate": 1.4422533681008259e-05, + "loss": 0.3677, + "step": 10267 + }, + { + "epoch": 0.84, + "learning_rate": 1.4421990438939593e-05, + "loss": 0.4813, + "step": 10268 + }, + { + "epoch": 0.84, + "learning_rate": 1.4421447196870925e-05, + "loss": 0.3078, + "step": 10269 + }, + { + "epoch": 0.84, + "learning_rate": 1.4420903954802261e-05, + "loss": 0.5498, + "step": 10270 + }, + { + "epoch": 0.84, + "learning_rate": 1.4420360712733594e-05, + "loss": 0.3711, + "step": 10271 + }, + { + "epoch": 0.84, + "learning_rate": 1.441981747066493e-05, + "loss": 0.4142, + "step": 10272 + }, + { + "epoch": 0.84, + "learning_rate": 1.4419274228596262e-05, + "loss": 0.4782, + "step": 10273 + }, + { + "epoch": 0.84, + "learning_rate": 1.4418730986527598e-05, + "loss": 0.4971, + "step": 10274 + }, + { + "epoch": 0.84, + "learning_rate": 1.441818774445893e-05, + "loss": 0.3915, + "step": 10275 + }, + { + "epoch": 0.84, + "learning_rate": 1.4417644502390267e-05, + "loss": 0.3909, + "step": 10276 + }, + { + "epoch": 0.84, + "learning_rate": 1.44171012603216e-05, + "loss": 0.4882, + "step": 10277 + }, + { + "epoch": 0.84, + "learning_rate": 1.4416558018252935e-05, + "loss": 0.3618, + "step": 10278 + }, + { + "epoch": 0.84, + "learning_rate": 1.4416014776184268e-05, + "loss": 0.3068, + "step": 10279 + }, + { + "epoch": 0.84, + "learning_rate": 1.4415471534115604e-05, + "loss": 0.5276, + "step": 10280 + }, + { + "epoch": 0.84, + "learning_rate": 1.4414928292046936e-05, + "loss": 0.6985, + "step": 10281 + }, + { + "epoch": 0.84, + "learning_rate": 1.4414385049978272e-05, + "loss": 0.4767, + "step": 10282 + }, + { + "epoch": 0.84, + "learning_rate": 1.4413841807909605e-05, + "loss": 0.4265, + "step": 10283 + }, + { + "epoch": 0.84, + "learning_rate": 1.441329856584094e-05, + "loss": 0.4522, + "step": 10284 + }, + { + "epoch": 0.84, + "learning_rate": 1.4412755323772273e-05, + "loss": 0.4642, + "step": 10285 + }, + { + "epoch": 0.84, + "learning_rate": 1.4412212081703609e-05, + "loss": 0.4517, + "step": 10286 + }, + { + "epoch": 0.84, + "learning_rate": 1.4411668839634943e-05, + "loss": 0.5211, + "step": 10287 + }, + { + "epoch": 0.84, + "learning_rate": 1.4411125597566276e-05, + "loss": 0.4008, + "step": 10288 + }, + { + "epoch": 0.84, + "learning_rate": 1.4410582355497612e-05, + "loss": 0.4032, + "step": 10289 + }, + { + "epoch": 0.84, + "learning_rate": 1.4410039113428944e-05, + "loss": 0.3331, + "step": 10290 + }, + { + "epoch": 0.84, + "learning_rate": 1.440949587136028e-05, + "loss": 0.4186, + "step": 10291 + }, + { + "epoch": 0.84, + "learning_rate": 1.4408952629291613e-05, + "loss": 0.4012, + "step": 10292 + }, + { + "epoch": 0.84, + "learning_rate": 1.4408409387222949e-05, + "loss": 0.4257, + "step": 10293 + }, + { + "epoch": 0.84, + "learning_rate": 1.4407866145154281e-05, + "loss": 0.6228, + "step": 10294 + }, + { + "epoch": 0.84, + "learning_rate": 1.4407322903085617e-05, + "loss": 0.5463, + "step": 10295 + }, + { + "epoch": 0.84, + "learning_rate": 1.440677966101695e-05, + "loss": 0.3953, + "step": 10296 + }, + { + "epoch": 0.84, + "learning_rate": 1.4406236418948286e-05, + "loss": 0.3587, + "step": 10297 + }, + { + "epoch": 0.84, + "learning_rate": 1.4405693176879618e-05, + "loss": 0.2906, + "step": 10298 + }, + { + "epoch": 0.84, + "learning_rate": 1.4405149934810954e-05, + "loss": 0.2954, + "step": 10299 + }, + { + "epoch": 0.84, + "learning_rate": 1.4404606692742287e-05, + "loss": 0.7004, + "step": 10300 + }, + { + "epoch": 0.84, + "learning_rate": 1.4404063450673622e-05, + "loss": 0.4008, + "step": 10301 + }, + { + "epoch": 0.84, + "learning_rate": 1.4403520208604955e-05, + "loss": 0.609, + "step": 10302 + }, + { + "epoch": 0.84, + "learning_rate": 1.4402976966536291e-05, + "loss": 0.3795, + "step": 10303 + }, + { + "epoch": 0.84, + "learning_rate": 1.4402433724467623e-05, + "loss": 0.3138, + "step": 10304 + }, + { + "epoch": 0.84, + "learning_rate": 1.440189048239896e-05, + "loss": 0.4668, + "step": 10305 + }, + { + "epoch": 0.84, + "learning_rate": 1.4401347240330292e-05, + "loss": 0.2555, + "step": 10306 + }, + { + "epoch": 0.84, + "learning_rate": 1.4400803998261626e-05, + "loss": 0.4562, + "step": 10307 + }, + { + "epoch": 0.84, + "learning_rate": 1.440026075619296e-05, + "loss": 0.2755, + "step": 10308 + }, + { + "epoch": 0.84, + "learning_rate": 1.4399717514124295e-05, + "loss": 0.652, + "step": 10309 + }, + { + "epoch": 0.84, + "learning_rate": 1.4399174272055629e-05, + "loss": 0.3593, + "step": 10310 + }, + { + "epoch": 0.84, + "learning_rate": 1.4398631029986963e-05, + "loss": 0.3091, + "step": 10311 + }, + { + "epoch": 0.84, + "learning_rate": 1.4398087787918297e-05, + "loss": 0.4184, + "step": 10312 + }, + { + "epoch": 0.84, + "learning_rate": 1.4397544545849632e-05, + "loss": 0.495, + "step": 10313 + }, + { + "epoch": 0.84, + "learning_rate": 1.4397001303780966e-05, + "loss": 0.2582, + "step": 10314 + }, + { + "epoch": 0.84, + "learning_rate": 1.43964580617123e-05, + "loss": 0.4102, + "step": 10315 + }, + { + "epoch": 0.84, + "learning_rate": 1.4395914819643634e-05, + "loss": 0.422, + "step": 10316 + }, + { + "epoch": 0.84, + "learning_rate": 1.4395371577574968e-05, + "loss": 0.3344, + "step": 10317 + }, + { + "epoch": 0.84, + "learning_rate": 1.4394828335506303e-05, + "loss": 0.5178, + "step": 10318 + }, + { + "epoch": 0.84, + "learning_rate": 1.4394285093437637e-05, + "loss": 0.534, + "step": 10319 + }, + { + "epoch": 0.84, + "learning_rate": 1.4393741851368971e-05, + "loss": 0.4668, + "step": 10320 + }, + { + "epoch": 0.84, + "learning_rate": 1.4393198609300305e-05, + "loss": 0.4037, + "step": 10321 + }, + { + "epoch": 0.84, + "learning_rate": 1.439265536723164e-05, + "loss": 0.6128, + "step": 10322 + }, + { + "epoch": 0.84, + "learning_rate": 1.4392112125162974e-05, + "loss": 0.3683, + "step": 10323 + }, + { + "epoch": 0.84, + "learning_rate": 1.439156888309431e-05, + "loss": 0.7254, + "step": 10324 + }, + { + "epoch": 0.84, + "learning_rate": 1.4391025641025642e-05, + "loss": 0.3287, + "step": 10325 + }, + { + "epoch": 0.84, + "learning_rate": 1.4390482398956975e-05, + "loss": 0.3754, + "step": 10326 + }, + { + "epoch": 0.84, + "learning_rate": 1.438993915688831e-05, + "loss": 0.5917, + "step": 10327 + }, + { + "epoch": 0.84, + "learning_rate": 1.4389395914819643e-05, + "loss": 0.3058, + "step": 10328 + }, + { + "epoch": 0.84, + "learning_rate": 1.438885267275098e-05, + "loss": 0.263, + "step": 10329 + }, + { + "epoch": 0.84, + "learning_rate": 1.4388309430682312e-05, + "loss": 0.3852, + "step": 10330 + }, + { + "epoch": 0.84, + "learning_rate": 1.4387766188613648e-05, + "loss": 0.5781, + "step": 10331 + }, + { + "epoch": 0.84, + "learning_rate": 1.438722294654498e-05, + "loss": 0.5205, + "step": 10332 + }, + { + "epoch": 0.84, + "learning_rate": 1.4386679704476316e-05, + "loss": 0.5786, + "step": 10333 + }, + { + "epoch": 0.84, + "learning_rate": 1.4386136462407649e-05, + "loss": 0.3901, + "step": 10334 + }, + { + "epoch": 0.84, + "learning_rate": 1.4385593220338985e-05, + "loss": 0.2393, + "step": 10335 + }, + { + "epoch": 0.84, + "learning_rate": 1.4385049978270317e-05, + "loss": 0.5954, + "step": 10336 + }, + { + "epoch": 0.84, + "learning_rate": 1.4384506736201653e-05, + "loss": 0.4423, + "step": 10337 + }, + { + "epoch": 0.84, + "learning_rate": 1.4383963494132986e-05, + "loss": 0.6784, + "step": 10338 + }, + { + "epoch": 0.84, + "learning_rate": 1.4383420252064322e-05, + "loss": 0.4052, + "step": 10339 + }, + { + "epoch": 0.84, + "learning_rate": 1.4382877009995656e-05, + "loss": 0.4803, + "step": 10340 + }, + { + "epoch": 0.84, + "learning_rate": 1.438233376792699e-05, + "loss": 0.7707, + "step": 10341 + }, + { + "epoch": 0.84, + "learning_rate": 1.4381790525858324e-05, + "loss": 0.5389, + "step": 10342 + }, + { + "epoch": 0.84, + "learning_rate": 1.4381247283789658e-05, + "loss": 0.5859, + "step": 10343 + }, + { + "epoch": 0.84, + "learning_rate": 1.4380704041720993e-05, + "loss": 0.6342, + "step": 10344 + }, + { + "epoch": 0.84, + "learning_rate": 1.4380160799652325e-05, + "loss": 0.2489, + "step": 10345 + }, + { + "epoch": 0.84, + "learning_rate": 1.4379617557583661e-05, + "loss": 0.5481, + "step": 10346 + }, + { + "epoch": 0.84, + "learning_rate": 1.4379074315514994e-05, + "loss": 0.4548, + "step": 10347 + }, + { + "epoch": 0.84, + "learning_rate": 1.437853107344633e-05, + "loss": 0.5389, + "step": 10348 + }, + { + "epoch": 0.84, + "learning_rate": 1.4377987831377662e-05, + "loss": 0.418, + "step": 10349 + }, + { + "epoch": 0.84, + "learning_rate": 1.4377444589308998e-05, + "loss": 0.169, + "step": 10350 + }, + { + "epoch": 0.84, + "learning_rate": 1.437690134724033e-05, + "loss": 0.4774, + "step": 10351 + }, + { + "epoch": 0.84, + "learning_rate": 1.4376358105171667e-05, + "loss": 0.4228, + "step": 10352 + }, + { + "epoch": 0.84, + "learning_rate": 1.4375814863102999e-05, + "loss": 0.4013, + "step": 10353 + }, + { + "epoch": 0.84, + "learning_rate": 1.4375271621034335e-05, + "loss": 0.4625, + "step": 10354 + }, + { + "epoch": 0.84, + "learning_rate": 1.4374728378965668e-05, + "loss": 0.7316, + "step": 10355 + }, + { + "epoch": 0.84, + "learning_rate": 1.4374185136897003e-05, + "loss": 0.6989, + "step": 10356 + }, + { + "epoch": 0.84, + "learning_rate": 1.4373641894828336e-05, + "loss": 0.667, + "step": 10357 + }, + { + "epoch": 0.84, + "learning_rate": 1.4373098652759672e-05, + "loss": 0.527, + "step": 10358 + }, + { + "epoch": 0.84, + "learning_rate": 1.4372555410691004e-05, + "loss": 0.3924, + "step": 10359 + }, + { + "epoch": 0.84, + "learning_rate": 1.437201216862234e-05, + "loss": 0.4617, + "step": 10360 + }, + { + "epoch": 0.84, + "learning_rate": 1.4371468926553673e-05, + "loss": 0.4458, + "step": 10361 + }, + { + "epoch": 0.84, + "learning_rate": 1.4370925684485009e-05, + "loss": 0.3744, + "step": 10362 + }, + { + "epoch": 0.84, + "learning_rate": 1.4370382442416341e-05, + "loss": 0.3734, + "step": 10363 + }, + { + "epoch": 0.84, + "learning_rate": 1.4369839200347677e-05, + "loss": 0.3535, + "step": 10364 + }, + { + "epoch": 0.84, + "learning_rate": 1.436929595827901e-05, + "loss": 0.4629, + "step": 10365 + }, + { + "epoch": 0.84, + "learning_rate": 1.4368752716210344e-05, + "loss": 0.4377, + "step": 10366 + }, + { + "epoch": 0.84, + "learning_rate": 1.4368209474141678e-05, + "loss": 0.4473, + "step": 10367 + }, + { + "epoch": 0.84, + "learning_rate": 1.4367666232073013e-05, + "loss": 0.4291, + "step": 10368 + }, + { + "epoch": 0.84, + "learning_rate": 1.4367122990004347e-05, + "loss": 0.6594, + "step": 10369 + }, + { + "epoch": 0.85, + "learning_rate": 1.4366579747935681e-05, + "loss": 0.4512, + "step": 10370 + }, + { + "epoch": 0.85, + "learning_rate": 1.4366036505867015e-05, + "loss": 0.4607, + "step": 10371 + }, + { + "epoch": 0.85, + "learning_rate": 1.436549326379835e-05, + "loss": 0.5363, + "step": 10372 + }, + { + "epoch": 0.85, + "learning_rate": 1.4364950021729684e-05, + "loss": 0.3711, + "step": 10373 + }, + { + "epoch": 0.85, + "learning_rate": 1.4364406779661018e-05, + "loss": 0.8005, + "step": 10374 + }, + { + "epoch": 0.85, + "learning_rate": 1.4363863537592352e-05, + "loss": 0.4058, + "step": 10375 + }, + { + "epoch": 0.85, + "learning_rate": 1.4363320295523686e-05, + "loss": 0.544, + "step": 10376 + }, + { + "epoch": 0.85, + "learning_rate": 1.4362777053455022e-05, + "loss": 0.4923, + "step": 10377 + }, + { + "epoch": 0.85, + "learning_rate": 1.4362233811386355e-05, + "loss": 0.5435, + "step": 10378 + }, + { + "epoch": 0.85, + "learning_rate": 1.436169056931769e-05, + "loss": 0.4573, + "step": 10379 + }, + { + "epoch": 0.85, + "learning_rate": 1.4361147327249023e-05, + "loss": 0.321, + "step": 10380 + }, + { + "epoch": 0.85, + "learning_rate": 1.436060408518036e-05, + "loss": 0.4631, + "step": 10381 + }, + { + "epoch": 0.85, + "learning_rate": 1.4360060843111692e-05, + "loss": 0.4444, + "step": 10382 + }, + { + "epoch": 0.85, + "learning_rate": 1.4359517601043028e-05, + "loss": 0.2713, + "step": 10383 + }, + { + "epoch": 0.85, + "learning_rate": 1.435897435897436e-05, + "loss": 0.5188, + "step": 10384 + }, + { + "epoch": 0.85, + "learning_rate": 1.4358431116905693e-05, + "loss": 0.516, + "step": 10385 + }, + { + "epoch": 0.85, + "learning_rate": 1.4357887874837029e-05, + "loss": 0.5265, + "step": 10386 + }, + { + "epoch": 0.85, + "learning_rate": 1.4357344632768361e-05, + "loss": 0.5759, + "step": 10387 + }, + { + "epoch": 0.85, + "learning_rate": 1.4356801390699697e-05, + "loss": 0.3765, + "step": 10388 + }, + { + "epoch": 0.85, + "learning_rate": 1.435625814863103e-05, + "loss": 0.6545, + "step": 10389 + }, + { + "epoch": 0.85, + "learning_rate": 1.4355714906562366e-05, + "loss": 0.3008, + "step": 10390 + }, + { + "epoch": 0.85, + "learning_rate": 1.4355171664493698e-05, + "loss": 0.3543, + "step": 10391 + }, + { + "epoch": 0.85, + "learning_rate": 1.4354628422425034e-05, + "loss": 0.3264, + "step": 10392 + }, + { + "epoch": 0.85, + "learning_rate": 1.4354085180356367e-05, + "loss": 0.4966, + "step": 10393 + }, + { + "epoch": 0.85, + "learning_rate": 1.4353541938287703e-05, + "loss": 0.4983, + "step": 10394 + }, + { + "epoch": 0.85, + "learning_rate": 1.4352998696219037e-05, + "loss": 0.5104, + "step": 10395 + }, + { + "epoch": 0.85, + "learning_rate": 1.4352455454150371e-05, + "loss": 0.6484, + "step": 10396 + }, + { + "epoch": 0.85, + "learning_rate": 1.4351912212081705e-05, + "loss": 0.643, + "step": 10397 + }, + { + "epoch": 0.85, + "learning_rate": 1.435136897001304e-05, + "loss": 0.5489, + "step": 10398 + }, + { + "epoch": 0.85, + "learning_rate": 1.4350825727944374e-05, + "loss": 0.2532, + "step": 10399 + }, + { + "epoch": 0.85, + "learning_rate": 1.4350282485875708e-05, + "loss": 0.4173, + "step": 10400 + }, + { + "epoch": 0.85, + "learning_rate": 1.4349739243807042e-05, + "loss": 0.5571, + "step": 10401 + }, + { + "epoch": 0.85, + "learning_rate": 1.4349196001738376e-05, + "loss": 0.249, + "step": 10402 + }, + { + "epoch": 0.85, + "learning_rate": 1.434865275966971e-05, + "loss": 0.3793, + "step": 10403 + }, + { + "epoch": 0.85, + "learning_rate": 1.4348109517601043e-05, + "loss": 0.5908, + "step": 10404 + }, + { + "epoch": 0.85, + "learning_rate": 1.4347566275532379e-05, + "loss": 0.6118, + "step": 10405 + }, + { + "epoch": 0.85, + "learning_rate": 1.4347023033463712e-05, + "loss": 0.5727, + "step": 10406 + }, + { + "epoch": 0.85, + "learning_rate": 1.4346479791395048e-05, + "loss": 0.646, + "step": 10407 + }, + { + "epoch": 0.85, + "learning_rate": 1.434593654932638e-05, + "loss": 0.4075, + "step": 10408 + }, + { + "epoch": 0.85, + "learning_rate": 1.4345393307257716e-05, + "loss": 0.3369, + "step": 10409 + }, + { + "epoch": 0.85, + "learning_rate": 1.4344850065189049e-05, + "loss": 0.2998, + "step": 10410 + }, + { + "epoch": 0.85, + "learning_rate": 1.4344306823120384e-05, + "loss": 0.4452, + "step": 10411 + }, + { + "epoch": 0.85, + "learning_rate": 1.4343763581051717e-05, + "loss": 0.4659, + "step": 10412 + }, + { + "epoch": 0.85, + "learning_rate": 1.4343220338983053e-05, + "loss": 0.3904, + "step": 10413 + }, + { + "epoch": 0.85, + "learning_rate": 1.4342677096914385e-05, + "loss": 0.403, + "step": 10414 + }, + { + "epoch": 0.85, + "learning_rate": 1.4342133854845721e-05, + "loss": 0.5127, + "step": 10415 + }, + { + "epoch": 0.85, + "learning_rate": 1.4341590612777054e-05, + "loss": 0.7528, + "step": 10416 + }, + { + "epoch": 0.85, + "learning_rate": 1.434104737070839e-05, + "loss": 0.3663, + "step": 10417 + }, + { + "epoch": 0.85, + "learning_rate": 1.4340504128639722e-05, + "loss": 0.4886, + "step": 10418 + }, + { + "epoch": 0.85, + "learning_rate": 1.4339960886571058e-05, + "loss": 0.4917, + "step": 10419 + }, + { + "epoch": 0.85, + "learning_rate": 1.433941764450239e-05, + "loss": 0.3687, + "step": 10420 + }, + { + "epoch": 0.85, + "learning_rate": 1.4338874402433727e-05, + "loss": 0.6115, + "step": 10421 + }, + { + "epoch": 0.85, + "learning_rate": 1.433833116036506e-05, + "loss": 0.354, + "step": 10422 + }, + { + "epoch": 0.85, + "learning_rate": 1.4337787918296394e-05, + "loss": 0.4199, + "step": 10423 + }, + { + "epoch": 0.85, + "learning_rate": 1.4337244676227728e-05, + "loss": 0.6369, + "step": 10424 + }, + { + "epoch": 0.85, + "learning_rate": 1.4336701434159062e-05, + "loss": 0.3443, + "step": 10425 + }, + { + "epoch": 0.85, + "learning_rate": 1.4336158192090396e-05, + "loss": 0.584, + "step": 10426 + }, + { + "epoch": 0.85, + "learning_rate": 1.433561495002173e-05, + "loss": 0.5222, + "step": 10427 + }, + { + "epoch": 0.85, + "learning_rate": 1.4335071707953065e-05, + "loss": 0.4877, + "step": 10428 + }, + { + "epoch": 0.85, + "learning_rate": 1.4334528465884399e-05, + "loss": 0.4932, + "step": 10429 + }, + { + "epoch": 0.85, + "learning_rate": 1.4333985223815733e-05, + "loss": 0.4265, + "step": 10430 + }, + { + "epoch": 0.85, + "learning_rate": 1.4333441981747067e-05, + "loss": 0.3755, + "step": 10431 + }, + { + "epoch": 0.85, + "learning_rate": 1.4332898739678403e-05, + "loss": 0.3525, + "step": 10432 + }, + { + "epoch": 0.85, + "learning_rate": 1.4332355497609736e-05, + "loss": 0.4414, + "step": 10433 + }, + { + "epoch": 0.85, + "learning_rate": 1.4331812255541072e-05, + "loss": 0.3587, + "step": 10434 + }, + { + "epoch": 0.85, + "learning_rate": 1.4331269013472404e-05, + "loss": 0.2444, + "step": 10435 + }, + { + "epoch": 0.85, + "learning_rate": 1.433072577140374e-05, + "loss": 0.666, + "step": 10436 + }, + { + "epoch": 0.85, + "learning_rate": 1.4330182529335073e-05, + "loss": 0.4636, + "step": 10437 + }, + { + "epoch": 0.85, + "learning_rate": 1.4329639287266409e-05, + "loss": 0.5382, + "step": 10438 + }, + { + "epoch": 0.85, + "learning_rate": 1.4329096045197741e-05, + "loss": 0.4234, + "step": 10439 + }, + { + "epoch": 0.85, + "learning_rate": 1.4328552803129077e-05, + "loss": 0.5109, + "step": 10440 + }, + { + "epoch": 0.85, + "learning_rate": 1.432800956106041e-05, + "loss": 0.3874, + "step": 10441 + }, + { + "epoch": 0.85, + "learning_rate": 1.4327466318991742e-05, + "loss": 0.4439, + "step": 10442 + }, + { + "epoch": 0.85, + "learning_rate": 1.4326923076923078e-05, + "loss": 0.6128, + "step": 10443 + }, + { + "epoch": 0.85, + "learning_rate": 1.432637983485441e-05, + "loss": 0.3607, + "step": 10444 + }, + { + "epoch": 0.85, + "learning_rate": 1.4325836592785747e-05, + "loss": 0.448, + "step": 10445 + }, + { + "epoch": 0.85, + "learning_rate": 1.4325293350717079e-05, + "loss": 0.4048, + "step": 10446 + }, + { + "epoch": 0.85, + "learning_rate": 1.4324750108648415e-05, + "loss": 0.3078, + "step": 10447 + }, + { + "epoch": 0.85, + "learning_rate": 1.432420686657975e-05, + "loss": 0.7025, + "step": 10448 + }, + { + "epoch": 0.85, + "learning_rate": 1.4323663624511084e-05, + "loss": 0.6048, + "step": 10449 + }, + { + "epoch": 0.85, + "learning_rate": 1.4323120382442418e-05, + "loss": 0.3379, + "step": 10450 + }, + { + "epoch": 0.85, + "learning_rate": 1.4322577140373752e-05, + "loss": 0.3833, + "step": 10451 + }, + { + "epoch": 0.85, + "learning_rate": 1.4322033898305086e-05, + "loss": 0.2605, + "step": 10452 + }, + { + "epoch": 0.85, + "learning_rate": 1.432149065623642e-05, + "loss": 0.3401, + "step": 10453 + }, + { + "epoch": 0.85, + "learning_rate": 1.4320947414167755e-05, + "loss": 0.371, + "step": 10454 + }, + { + "epoch": 0.85, + "learning_rate": 1.4320404172099089e-05, + "loss": 0.5853, + "step": 10455 + }, + { + "epoch": 0.85, + "learning_rate": 1.4319860930030423e-05, + "loss": 0.4366, + "step": 10456 + }, + { + "epoch": 0.85, + "learning_rate": 1.4319317687961757e-05, + "loss": 0.3592, + "step": 10457 + }, + { + "epoch": 0.85, + "learning_rate": 1.4318774445893092e-05, + "loss": 0.6, + "step": 10458 + }, + { + "epoch": 0.85, + "learning_rate": 1.4318231203824426e-05, + "loss": 0.5135, + "step": 10459 + }, + { + "epoch": 0.85, + "learning_rate": 1.431768796175576e-05, + "loss": 0.5403, + "step": 10460 + }, + { + "epoch": 0.85, + "learning_rate": 1.4317144719687093e-05, + "loss": 0.2813, + "step": 10461 + }, + { + "epoch": 0.85, + "learning_rate": 1.4316601477618429e-05, + "loss": 0.4163, + "step": 10462 + }, + { + "epoch": 0.85, + "learning_rate": 1.4316058235549761e-05, + "loss": 0.3531, + "step": 10463 + }, + { + "epoch": 0.85, + "learning_rate": 1.4315514993481097e-05, + "loss": 0.6235, + "step": 10464 + }, + { + "epoch": 0.85, + "learning_rate": 1.431497175141243e-05, + "loss": 0.5905, + "step": 10465 + }, + { + "epoch": 0.85, + "learning_rate": 1.4314428509343765e-05, + "loss": 0.3448, + "step": 10466 + }, + { + "epoch": 0.85, + "learning_rate": 1.4313885267275098e-05, + "loss": 0.43, + "step": 10467 + }, + { + "epoch": 0.85, + "learning_rate": 1.4313342025206434e-05, + "loss": 0.3216, + "step": 10468 + }, + { + "epoch": 0.85, + "learning_rate": 1.4312798783137766e-05, + "loss": 0.5451, + "step": 10469 + }, + { + "epoch": 0.85, + "learning_rate": 1.4312255541069102e-05, + "loss": 0.2703, + "step": 10470 + }, + { + "epoch": 0.85, + "learning_rate": 1.4311712299000435e-05, + "loss": 0.5083, + "step": 10471 + }, + { + "epoch": 0.85, + "learning_rate": 1.431116905693177e-05, + "loss": 0.2996, + "step": 10472 + }, + { + "epoch": 0.85, + "learning_rate": 1.4310625814863103e-05, + "loss": 0.492, + "step": 10473 + }, + { + "epoch": 0.85, + "learning_rate": 1.431008257279444e-05, + "loss": 0.6166, + "step": 10474 + }, + { + "epoch": 0.85, + "learning_rate": 1.4309539330725772e-05, + "loss": 0.4138, + "step": 10475 + }, + { + "epoch": 0.85, + "learning_rate": 1.4308996088657108e-05, + "loss": 0.4322, + "step": 10476 + }, + { + "epoch": 0.85, + "learning_rate": 1.430845284658844e-05, + "loss": 0.4534, + "step": 10477 + }, + { + "epoch": 0.85, + "learning_rate": 1.4307909604519776e-05, + "loss": 0.5644, + "step": 10478 + }, + { + "epoch": 0.85, + "learning_rate": 1.4307366362451109e-05, + "loss": 0.7345, + "step": 10479 + }, + { + "epoch": 0.85, + "learning_rate": 1.4306823120382443e-05, + "loss": 0.4822, + "step": 10480 + }, + { + "epoch": 0.85, + "learning_rate": 1.4306279878313777e-05, + "loss": 0.4706, + "step": 10481 + }, + { + "epoch": 0.85, + "learning_rate": 1.4305736636245111e-05, + "loss": 0.5314, + "step": 10482 + }, + { + "epoch": 0.85, + "learning_rate": 1.4305193394176446e-05, + "loss": 0.3874, + "step": 10483 + }, + { + "epoch": 0.85, + "learning_rate": 1.430465015210778e-05, + "loss": 0.1646, + "step": 10484 + }, + { + "epoch": 0.85, + "learning_rate": 1.4304106910039116e-05, + "loss": 0.29, + "step": 10485 + }, + { + "epoch": 0.85, + "learning_rate": 1.4303563667970448e-05, + "loss": 0.4424, + "step": 10486 + }, + { + "epoch": 0.85, + "learning_rate": 1.4303020425901784e-05, + "loss": 0.556, + "step": 10487 + }, + { + "epoch": 0.85, + "learning_rate": 1.4302477183833117e-05, + "loss": 0.2841, + "step": 10488 + }, + { + "epoch": 0.85, + "learning_rate": 1.4301933941764453e-05, + "loss": 0.5848, + "step": 10489 + }, + { + "epoch": 0.85, + "learning_rate": 1.4301390699695785e-05, + "loss": 0.2744, + "step": 10490 + }, + { + "epoch": 0.85, + "learning_rate": 1.4300847457627121e-05, + "loss": 0.6826, + "step": 10491 + }, + { + "epoch": 0.85, + "learning_rate": 1.4300304215558454e-05, + "loss": 0.3936, + "step": 10492 + }, + { + "epoch": 0.86, + "learning_rate": 1.429976097348979e-05, + "loss": 0.4685, + "step": 10493 + }, + { + "epoch": 0.86, + "learning_rate": 1.4299217731421122e-05, + "loss": 0.4524, + "step": 10494 + }, + { + "epoch": 0.86, + "learning_rate": 1.4298674489352458e-05, + "loss": 0.3256, + "step": 10495 + }, + { + "epoch": 0.86, + "learning_rate": 1.429813124728379e-05, + "loss": 0.3914, + "step": 10496 + }, + { + "epoch": 0.86, + "learning_rate": 1.4297588005215127e-05, + "loss": 0.7393, + "step": 10497 + }, + { + "epoch": 0.86, + "learning_rate": 1.4297044763146459e-05, + "loss": 0.7616, + "step": 10498 + }, + { + "epoch": 0.86, + "learning_rate": 1.4296501521077792e-05, + "loss": 0.2784, + "step": 10499 + }, + { + "epoch": 0.86, + "learning_rate": 1.4295958279009128e-05, + "loss": 0.4433, + "step": 10500 + }, + { + "epoch": 0.86, + "eval_accuracy": 0.8328069281711665, + "eval_loss": 0.42812132835388184, + "eval_runtime": 22.2247, + "eval_samples_per_second": 441.626, + "eval_steps_per_second": 3.465, + "step": 10500 + }, + { + "epoch": 0.86, + "learning_rate": 1.429541503694046e-05, + "loss": 0.3596, + "step": 10501 + }, + { + "epoch": 0.86, + "learning_rate": 1.4294871794871796e-05, + "loss": 0.288, + "step": 10502 + }, + { + "epoch": 0.86, + "learning_rate": 1.429432855280313e-05, + "loss": 0.4106, + "step": 10503 + }, + { + "epoch": 0.86, + "learning_rate": 1.4293785310734465e-05, + "loss": 0.2783, + "step": 10504 + }, + { + "epoch": 0.86, + "learning_rate": 1.4293242068665799e-05, + "loss": 0.2312, + "step": 10505 + }, + { + "epoch": 0.86, + "learning_rate": 1.4292698826597133e-05, + "loss": 0.464, + "step": 10506 + }, + { + "epoch": 0.86, + "learning_rate": 1.4292155584528467e-05, + "loss": 0.4008, + "step": 10507 + }, + { + "epoch": 0.86, + "learning_rate": 1.4291612342459801e-05, + "loss": 0.5593, + "step": 10508 + }, + { + "epoch": 0.86, + "learning_rate": 1.4291069100391136e-05, + "loss": 0.4735, + "step": 10509 + }, + { + "epoch": 0.86, + "learning_rate": 1.429052585832247e-05, + "loss": 0.3396, + "step": 10510 + }, + { + "epoch": 0.86, + "learning_rate": 1.4289982616253804e-05, + "loss": 0.497, + "step": 10511 + }, + { + "epoch": 0.86, + "learning_rate": 1.4289439374185138e-05, + "loss": 0.5519, + "step": 10512 + }, + { + "epoch": 0.86, + "learning_rate": 1.4288896132116473e-05, + "loss": 0.2823, + "step": 10513 + }, + { + "epoch": 0.86, + "learning_rate": 1.4288352890047807e-05, + "loss": 0.8983, + "step": 10514 + }, + { + "epoch": 0.86, + "learning_rate": 1.4287809647979141e-05, + "loss": 0.5439, + "step": 10515 + }, + { + "epoch": 0.86, + "learning_rate": 1.4287266405910475e-05, + "loss": 0.5742, + "step": 10516 + }, + { + "epoch": 0.86, + "learning_rate": 1.428672316384181e-05, + "loss": 0.6168, + "step": 10517 + }, + { + "epoch": 0.86, + "learning_rate": 1.4286179921773142e-05, + "loss": 0.3328, + "step": 10518 + }, + { + "epoch": 0.86, + "learning_rate": 1.4285636679704478e-05, + "loss": 0.3625, + "step": 10519 + }, + { + "epoch": 0.86, + "learning_rate": 1.428509343763581e-05, + "loss": 0.5844, + "step": 10520 + }, + { + "epoch": 0.86, + "learning_rate": 1.4284550195567146e-05, + "loss": 0.2767, + "step": 10521 + }, + { + "epoch": 0.86, + "learning_rate": 1.4284006953498479e-05, + "loss": 0.4942, + "step": 10522 + }, + { + "epoch": 0.86, + "learning_rate": 1.4283463711429815e-05, + "loss": 0.5731, + "step": 10523 + }, + { + "epoch": 0.86, + "learning_rate": 1.4282920469361147e-05, + "loss": 0.8771, + "step": 10524 + }, + { + "epoch": 0.86, + "learning_rate": 1.4282377227292483e-05, + "loss": 0.4036, + "step": 10525 + }, + { + "epoch": 0.86, + "learning_rate": 1.4281833985223816e-05, + "loss": 0.3997, + "step": 10526 + }, + { + "epoch": 0.86, + "learning_rate": 1.4281290743155152e-05, + "loss": 0.6684, + "step": 10527 + }, + { + "epoch": 0.86, + "learning_rate": 1.4280747501086484e-05, + "loss": 0.4517, + "step": 10528 + }, + { + "epoch": 0.86, + "learning_rate": 1.428020425901782e-05, + "loss": 0.6191, + "step": 10529 + }, + { + "epoch": 0.86, + "learning_rate": 1.4279661016949153e-05, + "loss": 0.788, + "step": 10530 + }, + { + "epoch": 0.86, + "learning_rate": 1.4279117774880489e-05, + "loss": 0.4357, + "step": 10531 + }, + { + "epoch": 0.86, + "learning_rate": 1.4278574532811821e-05, + "loss": 0.3536, + "step": 10532 + }, + { + "epoch": 0.86, + "learning_rate": 1.4278031290743157e-05, + "loss": 0.3499, + "step": 10533 + }, + { + "epoch": 0.86, + "learning_rate": 1.427748804867449e-05, + "loss": 0.4913, + "step": 10534 + }, + { + "epoch": 0.86, + "learning_rate": 1.4276944806605826e-05, + "loss": 0.3855, + "step": 10535 + }, + { + "epoch": 0.86, + "learning_rate": 1.4276401564537158e-05, + "loss": 0.7153, + "step": 10536 + }, + { + "epoch": 0.86, + "learning_rate": 1.4275858322468492e-05, + "loss": 0.4407, + "step": 10537 + }, + { + "epoch": 0.86, + "learning_rate": 1.4275315080399827e-05, + "loss": 0.3623, + "step": 10538 + }, + { + "epoch": 0.86, + "learning_rate": 1.4274771838331161e-05, + "loss": 0.3628, + "step": 10539 + }, + { + "epoch": 0.86, + "learning_rate": 1.4274228596262497e-05, + "loss": 0.3711, + "step": 10540 + }, + { + "epoch": 0.86, + "learning_rate": 1.427368535419383e-05, + "loss": 0.2798, + "step": 10541 + }, + { + "epoch": 0.86, + "learning_rate": 1.4273142112125165e-05, + "loss": 0.595, + "step": 10542 + }, + { + "epoch": 0.86, + "learning_rate": 1.4272598870056498e-05, + "loss": 0.7395, + "step": 10543 + }, + { + "epoch": 0.86, + "learning_rate": 1.4272055627987834e-05, + "loss": 0.5036, + "step": 10544 + }, + { + "epoch": 0.86, + "learning_rate": 1.4271512385919166e-05, + "loss": 0.7241, + "step": 10545 + }, + { + "epoch": 0.86, + "learning_rate": 1.4270969143850502e-05, + "loss": 0.4999, + "step": 10546 + }, + { + "epoch": 0.86, + "learning_rate": 1.4270425901781835e-05, + "loss": 0.4856, + "step": 10547 + }, + { + "epoch": 0.86, + "learning_rate": 1.426988265971317e-05, + "loss": 0.6704, + "step": 10548 + }, + { + "epoch": 0.86, + "learning_rate": 1.4269339417644503e-05, + "loss": 0.4293, + "step": 10549 + }, + { + "epoch": 0.86, + "learning_rate": 1.4268796175575839e-05, + "loss": 0.6225, + "step": 10550 + }, + { + "epoch": 0.86, + "learning_rate": 1.4268252933507172e-05, + "loss": 0.7524, + "step": 10551 + }, + { + "epoch": 0.86, + "learning_rate": 1.4267709691438508e-05, + "loss": 0.1462, + "step": 10552 + }, + { + "epoch": 0.86, + "learning_rate": 1.426716644936984e-05, + "loss": 0.4547, + "step": 10553 + }, + { + "epoch": 0.86, + "learning_rate": 1.4266623207301176e-05, + "loss": 0.4994, + "step": 10554 + }, + { + "epoch": 0.86, + "learning_rate": 1.4266079965232509e-05, + "loss": 0.3839, + "step": 10555 + }, + { + "epoch": 0.86, + "learning_rate": 1.4265536723163843e-05, + "loss": 0.2927, + "step": 10556 + }, + { + "epoch": 0.86, + "learning_rate": 1.4264993481095177e-05, + "loss": 0.3352, + "step": 10557 + }, + { + "epoch": 0.86, + "learning_rate": 1.4264450239026511e-05, + "loss": 0.478, + "step": 10558 + }, + { + "epoch": 0.86, + "learning_rate": 1.4263906996957845e-05, + "loss": 0.2135, + "step": 10559 + }, + { + "epoch": 0.86, + "learning_rate": 1.426336375488918e-05, + "loss": 0.2387, + "step": 10560 + }, + { + "epoch": 0.86, + "learning_rate": 1.4262820512820514e-05, + "loss": 0.4564, + "step": 10561 + }, + { + "epoch": 0.86, + "learning_rate": 1.4262277270751848e-05, + "loss": 0.588, + "step": 10562 + }, + { + "epoch": 0.86, + "learning_rate": 1.4261734028683182e-05, + "loss": 0.5659, + "step": 10563 + }, + { + "epoch": 0.86, + "learning_rate": 1.4261190786614517e-05, + "loss": 0.3902, + "step": 10564 + }, + { + "epoch": 0.86, + "learning_rate": 1.4260647544545851e-05, + "loss": 0.4396, + "step": 10565 + }, + { + "epoch": 0.86, + "learning_rate": 1.4260104302477185e-05, + "loss": 0.3966, + "step": 10566 + }, + { + "epoch": 0.86, + "learning_rate": 1.425956106040852e-05, + "loss": 0.508, + "step": 10567 + }, + { + "epoch": 0.86, + "learning_rate": 1.4259017818339854e-05, + "loss": 0.4986, + "step": 10568 + }, + { + "epoch": 0.86, + "learning_rate": 1.4258474576271188e-05, + "loss": 0.4711, + "step": 10569 + }, + { + "epoch": 0.86, + "learning_rate": 1.4257931334202522e-05, + "loss": 0.5098, + "step": 10570 + }, + { + "epoch": 0.86, + "learning_rate": 1.4257388092133856e-05, + "loss": 0.3947, + "step": 10571 + }, + { + "epoch": 0.86, + "learning_rate": 1.425684485006519e-05, + "loss": 0.6716, + "step": 10572 + }, + { + "epoch": 0.86, + "learning_rate": 1.4256301607996525e-05, + "loss": 0.4187, + "step": 10573 + }, + { + "epoch": 0.86, + "learning_rate": 1.4255758365927859e-05, + "loss": 0.7948, + "step": 10574 + }, + { + "epoch": 0.86, + "learning_rate": 1.4255215123859191e-05, + "loss": 0.3834, + "step": 10575 + }, + { + "epoch": 0.86, + "learning_rate": 1.4254671881790527e-05, + "loss": 0.7729, + "step": 10576 + }, + { + "epoch": 0.86, + "learning_rate": 1.425412863972186e-05, + "loss": 0.7115, + "step": 10577 + }, + { + "epoch": 0.86, + "learning_rate": 1.4253585397653196e-05, + "loss": 0.4394, + "step": 10578 + }, + { + "epoch": 0.86, + "learning_rate": 1.4253042155584528e-05, + "loss": 0.6375, + "step": 10579 + }, + { + "epoch": 0.86, + "learning_rate": 1.4252498913515864e-05, + "loss": 0.5127, + "step": 10580 + }, + { + "epoch": 0.86, + "learning_rate": 1.4251955671447197e-05, + "loss": 0.6255, + "step": 10581 + }, + { + "epoch": 0.86, + "learning_rate": 1.4251412429378533e-05, + "loss": 0.45, + "step": 10582 + }, + { + "epoch": 0.86, + "learning_rate": 1.4250869187309865e-05, + "loss": 0.393, + "step": 10583 + }, + { + "epoch": 0.86, + "learning_rate": 1.4250325945241201e-05, + "loss": 0.5513, + "step": 10584 + }, + { + "epoch": 0.86, + "learning_rate": 1.4249782703172534e-05, + "loss": 0.4339, + "step": 10585 + }, + { + "epoch": 0.86, + "learning_rate": 1.424923946110387e-05, + "loss": 0.6225, + "step": 10586 + }, + { + "epoch": 0.86, + "learning_rate": 1.4248696219035202e-05, + "loss": 0.3236, + "step": 10587 + }, + { + "epoch": 0.86, + "learning_rate": 1.4248152976966538e-05, + "loss": 0.206, + "step": 10588 + }, + { + "epoch": 0.86, + "learning_rate": 1.424760973489787e-05, + "loss": 0.526, + "step": 10589 + }, + { + "epoch": 0.86, + "learning_rate": 1.4247066492829207e-05, + "loss": 0.4837, + "step": 10590 + }, + { + "epoch": 0.86, + "learning_rate": 1.424652325076054e-05, + "loss": 0.364, + "step": 10591 + }, + { + "epoch": 0.86, + "learning_rate": 1.4245980008691875e-05, + "loss": 0.1879, + "step": 10592 + }, + { + "epoch": 0.86, + "learning_rate": 1.424543676662321e-05, + "loss": 0.2716, + "step": 10593 + }, + { + "epoch": 0.86, + "learning_rate": 1.4244893524554542e-05, + "loss": 0.5296, + "step": 10594 + }, + { + "epoch": 0.86, + "learning_rate": 1.4244350282485878e-05, + "loss": 0.5135, + "step": 10595 + }, + { + "epoch": 0.86, + "learning_rate": 1.424380704041721e-05, + "loss": 0.5063, + "step": 10596 + }, + { + "epoch": 0.86, + "learning_rate": 1.4243263798348546e-05, + "loss": 0.6129, + "step": 10597 + }, + { + "epoch": 0.86, + "learning_rate": 1.4242720556279879e-05, + "loss": 0.6917, + "step": 10598 + }, + { + "epoch": 0.86, + "learning_rate": 1.4242177314211215e-05, + "loss": 0.5472, + "step": 10599 + }, + { + "epoch": 0.86, + "learning_rate": 1.4241634072142547e-05, + "loss": 0.4451, + "step": 10600 + }, + { + "epoch": 0.86, + "learning_rate": 1.4241090830073883e-05, + "loss": 0.3323, + "step": 10601 + }, + { + "epoch": 0.86, + "learning_rate": 1.4240547588005216e-05, + "loss": 0.4243, + "step": 10602 + }, + { + "epoch": 0.86, + "learning_rate": 1.4240004345936552e-05, + "loss": 0.6264, + "step": 10603 + }, + { + "epoch": 0.86, + "learning_rate": 1.4239461103867884e-05, + "loss": 0.2779, + "step": 10604 + }, + { + "epoch": 0.86, + "learning_rate": 1.423891786179922e-05, + "loss": 0.3622, + "step": 10605 + }, + { + "epoch": 0.86, + "learning_rate": 1.4238374619730553e-05, + "loss": 0.3941, + "step": 10606 + }, + { + "epoch": 0.86, + "learning_rate": 1.4237831377661889e-05, + "loss": 0.3167, + "step": 10607 + }, + { + "epoch": 0.86, + "learning_rate": 1.4237288135593221e-05, + "loss": 0.3301, + "step": 10608 + }, + { + "epoch": 0.86, + "learning_rate": 1.4236744893524557e-05, + "loss": 0.4024, + "step": 10609 + }, + { + "epoch": 0.86, + "learning_rate": 1.423620165145589e-05, + "loss": 0.38, + "step": 10610 + }, + { + "epoch": 0.86, + "learning_rate": 1.4235658409387225e-05, + "loss": 0.3553, + "step": 10611 + }, + { + "epoch": 0.86, + "learning_rate": 1.4235115167318558e-05, + "loss": 0.4949, + "step": 10612 + }, + { + "epoch": 0.86, + "learning_rate": 1.4234571925249892e-05, + "loss": 0.2704, + "step": 10613 + }, + { + "epoch": 0.86, + "learning_rate": 1.4234028683181226e-05, + "loss": 0.4533, + "step": 10614 + }, + { + "epoch": 0.86, + "learning_rate": 1.423348544111256e-05, + "loss": 0.4113, + "step": 10615 + }, + { + "epoch": 0.87, + "learning_rate": 1.4232942199043895e-05, + "loss": 0.2215, + "step": 10616 + }, + { + "epoch": 0.87, + "learning_rate": 1.423239895697523e-05, + "loss": 0.2918, + "step": 10617 + }, + { + "epoch": 0.87, + "learning_rate": 1.4231855714906563e-05, + "loss": 0.6228, + "step": 10618 + }, + { + "epoch": 0.87, + "learning_rate": 1.4231312472837898e-05, + "loss": 0.3517, + "step": 10619 + }, + { + "epoch": 0.87, + "learning_rate": 1.4230769230769232e-05, + "loss": 0.5529, + "step": 10620 + }, + { + "epoch": 0.87, + "learning_rate": 1.4230225988700566e-05, + "loss": 0.3063, + "step": 10621 + }, + { + "epoch": 0.87, + "learning_rate": 1.42296827466319e-05, + "loss": 0.4409, + "step": 10622 + }, + { + "epoch": 0.87, + "learning_rate": 1.4229139504563235e-05, + "loss": 0.6639, + "step": 10623 + }, + { + "epoch": 0.87, + "learning_rate": 1.4228596262494569e-05, + "loss": 0.4242, + "step": 10624 + }, + { + "epoch": 0.87, + "learning_rate": 1.4228053020425903e-05, + "loss": 0.3141, + "step": 10625 + }, + { + "epoch": 0.87, + "learning_rate": 1.4227509778357237e-05, + "loss": 0.3559, + "step": 10626 + }, + { + "epoch": 0.87, + "learning_rate": 1.4226966536288571e-05, + "loss": 0.3151, + "step": 10627 + }, + { + "epoch": 0.87, + "learning_rate": 1.4226423294219906e-05, + "loss": 0.4036, + "step": 10628 + }, + { + "epoch": 0.87, + "learning_rate": 1.422588005215124e-05, + "loss": 0.318, + "step": 10629 + }, + { + "epoch": 0.87, + "learning_rate": 1.4225336810082576e-05, + "loss": 0.2964, + "step": 10630 + }, + { + "epoch": 0.87, + "learning_rate": 1.4224793568013908e-05, + "loss": 0.5441, + "step": 10631 + }, + { + "epoch": 0.87, + "learning_rate": 1.4224250325945241e-05, + "loss": 0.463, + "step": 10632 + }, + { + "epoch": 0.87, + "learning_rate": 1.4223707083876577e-05, + "loss": 0.5933, + "step": 10633 + }, + { + "epoch": 0.87, + "learning_rate": 1.422316384180791e-05, + "loss": 0.3638, + "step": 10634 + }, + { + "epoch": 0.87, + "learning_rate": 1.4222620599739245e-05, + "loss": 0.6724, + "step": 10635 + }, + { + "epoch": 0.87, + "learning_rate": 1.4222077357670578e-05, + "loss": 0.5071, + "step": 10636 + }, + { + "epoch": 0.87, + "learning_rate": 1.4221534115601914e-05, + "loss": 0.3291, + "step": 10637 + }, + { + "epoch": 0.87, + "learning_rate": 1.4220990873533246e-05, + "loss": 0.3984, + "step": 10638 + }, + { + "epoch": 0.87, + "learning_rate": 1.4220447631464582e-05, + "loss": 0.3745, + "step": 10639 + }, + { + "epoch": 0.87, + "learning_rate": 1.4219904389395915e-05, + "loss": 0.6596, + "step": 10640 + }, + { + "epoch": 0.87, + "learning_rate": 1.421936114732725e-05, + "loss": 0.4397, + "step": 10641 + }, + { + "epoch": 0.87, + "learning_rate": 1.4218817905258583e-05, + "loss": 0.4527, + "step": 10642 + }, + { + "epoch": 0.87, + "learning_rate": 1.421827466318992e-05, + "loss": 0.2657, + "step": 10643 + }, + { + "epoch": 0.87, + "learning_rate": 1.4217731421121252e-05, + "loss": 0.5659, + "step": 10644 + }, + { + "epoch": 0.87, + "learning_rate": 1.4217188179052588e-05, + "loss": 0.273, + "step": 10645 + }, + { + "epoch": 0.87, + "learning_rate": 1.421664493698392e-05, + "loss": 0.5832, + "step": 10646 + }, + { + "epoch": 0.87, + "learning_rate": 1.4216101694915256e-05, + "loss": 0.3523, + "step": 10647 + }, + { + "epoch": 0.87, + "learning_rate": 1.421555845284659e-05, + "loss": 0.5733, + "step": 10648 + }, + { + "epoch": 0.87, + "learning_rate": 1.4215015210777925e-05, + "loss": 0.6436, + "step": 10649 + }, + { + "epoch": 0.87, + "learning_rate": 1.4214471968709259e-05, + "loss": 0.7461, + "step": 10650 + }, + { + "epoch": 0.87, + "learning_rate": 1.4213928726640591e-05, + "loss": 0.357, + "step": 10651 + }, + { + "epoch": 0.87, + "learning_rate": 1.4213385484571927e-05, + "loss": 0.5751, + "step": 10652 + }, + { + "epoch": 0.87, + "learning_rate": 1.421284224250326e-05, + "loss": 0.4688, + "step": 10653 + }, + { + "epoch": 0.87, + "learning_rate": 1.4212299000434596e-05, + "loss": 0.6312, + "step": 10654 + }, + { + "epoch": 0.87, + "learning_rate": 1.4211755758365928e-05, + "loss": 0.3889, + "step": 10655 + }, + { + "epoch": 0.87, + "learning_rate": 1.4211212516297264e-05, + "loss": 0.6336, + "step": 10656 + }, + { + "epoch": 0.87, + "learning_rate": 1.4210669274228597e-05, + "loss": 0.4588, + "step": 10657 + }, + { + "epoch": 0.87, + "learning_rate": 1.4210126032159933e-05, + "loss": 0.2822, + "step": 10658 + }, + { + "epoch": 0.87, + "learning_rate": 1.4209582790091265e-05, + "loss": 0.3825, + "step": 10659 + }, + { + "epoch": 0.87, + "learning_rate": 1.4209039548022601e-05, + "loss": 0.5542, + "step": 10660 + }, + { + "epoch": 0.87, + "learning_rate": 1.4208496305953934e-05, + "loss": 0.4129, + "step": 10661 + }, + { + "epoch": 0.87, + "learning_rate": 1.420795306388527e-05, + "loss": 0.51, + "step": 10662 + }, + { + "epoch": 0.87, + "learning_rate": 1.4207409821816602e-05, + "loss": 0.5563, + "step": 10663 + }, + { + "epoch": 0.87, + "learning_rate": 1.4206866579747938e-05, + "loss": 0.3566, + "step": 10664 + }, + { + "epoch": 0.87, + "learning_rate": 1.420632333767927e-05, + "loss": 0.641, + "step": 10665 + }, + { + "epoch": 0.87, + "learning_rate": 1.4205780095610606e-05, + "loss": 0.5768, + "step": 10666 + }, + { + "epoch": 0.87, + "learning_rate": 1.4205236853541939e-05, + "loss": 0.4158, + "step": 10667 + }, + { + "epoch": 0.87, + "learning_rate": 1.4204693611473275e-05, + "loss": 0.3318, + "step": 10668 + }, + { + "epoch": 0.87, + "learning_rate": 1.4204150369404607e-05, + "loss": 0.4042, + "step": 10669 + }, + { + "epoch": 0.87, + "learning_rate": 1.4203607127335942e-05, + "loss": 0.3874, + "step": 10670 + }, + { + "epoch": 0.87, + "learning_rate": 1.4203063885267276e-05, + "loss": 0.3298, + "step": 10671 + }, + { + "epoch": 0.87, + "learning_rate": 1.420252064319861e-05, + "loss": 0.477, + "step": 10672 + }, + { + "epoch": 0.87, + "learning_rate": 1.4201977401129944e-05, + "loss": 0.6685, + "step": 10673 + }, + { + "epoch": 0.87, + "learning_rate": 1.4201434159061279e-05, + "loss": 0.3705, + "step": 10674 + }, + { + "epoch": 0.87, + "learning_rate": 1.4200890916992613e-05, + "loss": 0.5657, + "step": 10675 + }, + { + "epoch": 0.87, + "learning_rate": 1.4200347674923947e-05, + "loss": 0.1622, + "step": 10676 + }, + { + "epoch": 0.87, + "learning_rate": 1.4199804432855281e-05, + "loss": 0.6258, + "step": 10677 + }, + { + "epoch": 0.87, + "learning_rate": 1.4199261190786616e-05, + "loss": 0.6044, + "step": 10678 + }, + { + "epoch": 0.87, + "learning_rate": 1.419871794871795e-05, + "loss": 0.1971, + "step": 10679 + }, + { + "epoch": 0.87, + "learning_rate": 1.4198174706649284e-05, + "loss": 0.4267, + "step": 10680 + }, + { + "epoch": 0.87, + "learning_rate": 1.4197631464580618e-05, + "loss": 0.4834, + "step": 10681 + }, + { + "epoch": 0.87, + "learning_rate": 1.4197088222511952e-05, + "loss": 0.6165, + "step": 10682 + }, + { + "epoch": 0.87, + "learning_rate": 1.4196544980443288e-05, + "loss": 0.5048, + "step": 10683 + }, + { + "epoch": 0.87, + "learning_rate": 1.4196001738374621e-05, + "loss": 0.9776, + "step": 10684 + }, + { + "epoch": 0.87, + "learning_rate": 1.4195458496305957e-05, + "loss": 0.3345, + "step": 10685 + }, + { + "epoch": 0.87, + "learning_rate": 1.419491525423729e-05, + "loss": 0.6124, + "step": 10686 + }, + { + "epoch": 0.87, + "learning_rate": 1.4194372012168625e-05, + "loss": 0.5914, + "step": 10687 + }, + { + "epoch": 0.87, + "learning_rate": 1.4193828770099958e-05, + "loss": 0.3629, + "step": 10688 + }, + { + "epoch": 0.87, + "learning_rate": 1.419328552803129e-05, + "loss": 0.3836, + "step": 10689 + }, + { + "epoch": 0.87, + "learning_rate": 1.4192742285962626e-05, + "loss": 0.1841, + "step": 10690 + }, + { + "epoch": 0.87, + "learning_rate": 1.4192199043893959e-05, + "loss": 0.4958, + "step": 10691 + }, + { + "epoch": 0.87, + "learning_rate": 1.4191655801825295e-05, + "loss": 0.394, + "step": 10692 + }, + { + "epoch": 0.87, + "learning_rate": 1.4191112559756627e-05, + "loss": 0.3646, + "step": 10693 + }, + { + "epoch": 0.87, + "learning_rate": 1.4190569317687963e-05, + "loss": 0.4077, + "step": 10694 + }, + { + "epoch": 0.87, + "learning_rate": 1.4190026075619296e-05, + "loss": 0.5273, + "step": 10695 + }, + { + "epoch": 0.87, + "learning_rate": 1.4189482833550632e-05, + "loss": 0.4417, + "step": 10696 + }, + { + "epoch": 0.87, + "learning_rate": 1.4188939591481964e-05, + "loss": 0.5953, + "step": 10697 + }, + { + "epoch": 0.87, + "learning_rate": 1.41883963494133e-05, + "loss": 0.3646, + "step": 10698 + }, + { + "epoch": 0.87, + "learning_rate": 1.4187853107344633e-05, + "loss": 0.6784, + "step": 10699 + }, + { + "epoch": 0.87, + "learning_rate": 1.4187309865275969e-05, + "loss": 0.4209, + "step": 10700 + }, + { + "epoch": 0.87, + "learning_rate": 1.4186766623207303e-05, + "loss": 0.5515, + "step": 10701 + }, + { + "epoch": 0.87, + "learning_rate": 1.4186223381138637e-05, + "loss": 0.3531, + "step": 10702 + }, + { + "epoch": 0.87, + "learning_rate": 1.4185680139069971e-05, + "loss": 0.2442, + "step": 10703 + }, + { + "epoch": 0.87, + "learning_rate": 1.4185136897001306e-05, + "loss": 0.4201, + "step": 10704 + }, + { + "epoch": 0.87, + "learning_rate": 1.418459365493264e-05, + "loss": 0.4299, + "step": 10705 + }, + { + "epoch": 0.87, + "learning_rate": 1.4184050412863974e-05, + "loss": 0.4294, + "step": 10706 + }, + { + "epoch": 0.87, + "learning_rate": 1.4183507170795308e-05, + "loss": 0.123, + "step": 10707 + }, + { + "epoch": 0.87, + "learning_rate": 1.418296392872664e-05, + "loss": 0.2944, + "step": 10708 + }, + { + "epoch": 0.87, + "learning_rate": 1.4182420686657977e-05, + "loss": 0.3723, + "step": 10709 + }, + { + "epoch": 0.87, + "learning_rate": 1.418187744458931e-05, + "loss": 0.5462, + "step": 10710 + }, + { + "epoch": 0.87, + "learning_rate": 1.4181334202520645e-05, + "loss": 0.4237, + "step": 10711 + }, + { + "epoch": 0.87, + "learning_rate": 1.4180790960451978e-05, + "loss": 0.3653, + "step": 10712 + }, + { + "epoch": 0.87, + "learning_rate": 1.4180247718383314e-05, + "loss": 0.4736, + "step": 10713 + }, + { + "epoch": 0.87, + "learning_rate": 1.4179704476314646e-05, + "loss": 0.4132, + "step": 10714 + }, + { + "epoch": 0.87, + "learning_rate": 1.4179161234245982e-05, + "loss": 0.4171, + "step": 10715 + }, + { + "epoch": 0.87, + "learning_rate": 1.4178617992177315e-05, + "loss": 0.3702, + "step": 10716 + }, + { + "epoch": 0.87, + "learning_rate": 1.417807475010865e-05, + "loss": 0.3712, + "step": 10717 + }, + { + "epoch": 0.87, + "learning_rate": 1.4177531508039983e-05, + "loss": 0.4135, + "step": 10718 + }, + { + "epoch": 0.87, + "learning_rate": 1.4176988265971319e-05, + "loss": 0.4077, + "step": 10719 + }, + { + "epoch": 0.87, + "learning_rate": 1.4176445023902652e-05, + "loss": 0.2496, + "step": 10720 + }, + { + "epoch": 0.87, + "learning_rate": 1.4175901781833987e-05, + "loss": 0.2761, + "step": 10721 + }, + { + "epoch": 0.87, + "learning_rate": 1.417535853976532e-05, + "loss": 0.4025, + "step": 10722 + }, + { + "epoch": 0.87, + "learning_rate": 1.4174815297696656e-05, + "loss": 0.5484, + "step": 10723 + }, + { + "epoch": 0.87, + "learning_rate": 1.4174272055627988e-05, + "loss": 0.2106, + "step": 10724 + }, + { + "epoch": 0.87, + "learning_rate": 1.4173728813559324e-05, + "loss": 0.5289, + "step": 10725 + }, + { + "epoch": 0.87, + "learning_rate": 1.4173185571490657e-05, + "loss": 0.4237, + "step": 10726 + }, + { + "epoch": 0.87, + "learning_rate": 1.4172642329421991e-05, + "loss": 0.3053, + "step": 10727 + }, + { + "epoch": 0.87, + "learning_rate": 1.4172099087353325e-05, + "loss": 0.3345, + "step": 10728 + }, + { + "epoch": 0.87, + "learning_rate": 1.417155584528466e-05, + "loss": 0.4116, + "step": 10729 + }, + { + "epoch": 0.87, + "learning_rate": 1.4171012603215994e-05, + "loss": 0.5097, + "step": 10730 + }, + { + "epoch": 0.87, + "learning_rate": 1.4170469361147328e-05, + "loss": 0.4391, + "step": 10731 + }, + { + "epoch": 0.87, + "learning_rate": 1.4169926119078662e-05, + "loss": 0.1783, + "step": 10732 + }, + { + "epoch": 0.87, + "learning_rate": 1.4169382877009997e-05, + "loss": 0.3098, + "step": 10733 + }, + { + "epoch": 0.87, + "learning_rate": 1.416883963494133e-05, + "loss": 0.2785, + "step": 10734 + }, + { + "epoch": 0.87, + "learning_rate": 1.4168296392872665e-05, + "loss": 0.4068, + "step": 10735 + }, + { + "epoch": 0.87, + "learning_rate": 1.4167753150804e-05, + "loss": 0.4653, + "step": 10736 + }, + { + "epoch": 0.87, + "learning_rate": 1.4167209908735333e-05, + "loss": 0.6141, + "step": 10737 + }, + { + "epoch": 0.88, + "learning_rate": 1.416666666666667e-05, + "loss": 0.2172, + "step": 10738 + }, + { + "epoch": 0.88, + "learning_rate": 1.4166123424598002e-05, + "loss": 0.3711, + "step": 10739 + }, + { + "epoch": 0.88, + "learning_rate": 1.4165580182529338e-05, + "loss": 0.4906, + "step": 10740 + }, + { + "epoch": 0.88, + "learning_rate": 1.416503694046067e-05, + "loss": 0.4571, + "step": 10741 + }, + { + "epoch": 0.88, + "learning_rate": 1.4164493698392006e-05, + "loss": 0.2721, + "step": 10742 + }, + { + "epoch": 0.88, + "learning_rate": 1.4163950456323339e-05, + "loss": 0.5887, + "step": 10743 + }, + { + "epoch": 0.88, + "learning_rate": 1.4163407214254675e-05, + "loss": 0.339, + "step": 10744 + }, + { + "epoch": 0.88, + "learning_rate": 1.4162863972186007e-05, + "loss": 0.4462, + "step": 10745 + }, + { + "epoch": 0.88, + "learning_rate": 1.416232073011734e-05, + "loss": 0.4625, + "step": 10746 + }, + { + "epoch": 0.88, + "learning_rate": 1.4161777488048676e-05, + "loss": 0.5172, + "step": 10747 + }, + { + "epoch": 0.88, + "learning_rate": 1.4161234245980008e-05, + "loss": 0.4926, + "step": 10748 + }, + { + "epoch": 0.88, + "learning_rate": 1.4160691003911344e-05, + "loss": 0.7182, + "step": 10749 + }, + { + "epoch": 0.88, + "learning_rate": 1.4160147761842677e-05, + "loss": 0.6901, + "step": 10750 + }, + { + "epoch": 0.88, + "eval_accuracy": 0.8323993886907795, + "eval_loss": 0.44680699706077576, + "eval_runtime": 22.324, + "eval_samples_per_second": 439.661, + "eval_steps_per_second": 3.449, + "step": 10750 + }, + { + "epoch": 0.88, + "learning_rate": 1.4159604519774013e-05, + "loss": 0.6135, + "step": 10751 + }, + { + "epoch": 0.88, + "learning_rate": 1.4159061277705345e-05, + "loss": 0.3244, + "step": 10752 + }, + { + "epoch": 0.88, + "learning_rate": 1.4158518035636681e-05, + "loss": 0.6821, + "step": 10753 + }, + { + "epoch": 0.88, + "learning_rate": 1.4157974793568014e-05, + "loss": 0.4128, + "step": 10754 + }, + { + "epoch": 0.88, + "learning_rate": 1.415743155149935e-05, + "loss": 0.4026, + "step": 10755 + }, + { + "epoch": 0.88, + "learning_rate": 1.4156888309430684e-05, + "loss": 0.4069, + "step": 10756 + }, + { + "epoch": 0.88, + "learning_rate": 1.4156345067362018e-05, + "loss": 0.368, + "step": 10757 + }, + { + "epoch": 0.88, + "learning_rate": 1.4155801825293352e-05, + "loss": 0.6386, + "step": 10758 + }, + { + "epoch": 0.88, + "learning_rate": 1.4155258583224687e-05, + "loss": 0.7472, + "step": 10759 + }, + { + "epoch": 0.88, + "learning_rate": 1.415471534115602e-05, + "loss": 0.4684, + "step": 10760 + }, + { + "epoch": 0.88, + "learning_rate": 1.4154172099087355e-05, + "loss": 0.4209, + "step": 10761 + }, + { + "epoch": 0.88, + "learning_rate": 1.415362885701869e-05, + "loss": 0.6659, + "step": 10762 + }, + { + "epoch": 0.88, + "learning_rate": 1.4153085614950023e-05, + "loss": 0.3711, + "step": 10763 + }, + { + "epoch": 0.88, + "learning_rate": 1.4152542372881358e-05, + "loss": 0.2891, + "step": 10764 + }, + { + "epoch": 0.88, + "learning_rate": 1.415199913081269e-05, + "loss": 0.3697, + "step": 10765 + }, + { + "epoch": 0.88, + "learning_rate": 1.4151455888744026e-05, + "loss": 0.3414, + "step": 10766 + }, + { + "epoch": 0.88, + "learning_rate": 1.4150912646675359e-05, + "loss": 0.5278, + "step": 10767 + }, + { + "epoch": 0.88, + "learning_rate": 1.4150369404606695e-05, + "loss": 0.4256, + "step": 10768 + }, + { + "epoch": 0.88, + "learning_rate": 1.4149826162538027e-05, + "loss": 0.5322, + "step": 10769 + }, + { + "epoch": 0.88, + "learning_rate": 1.4149282920469363e-05, + "loss": 0.3028, + "step": 10770 + }, + { + "epoch": 0.88, + "learning_rate": 1.4148739678400696e-05, + "loss": 0.3948, + "step": 10771 + }, + { + "epoch": 0.88, + "learning_rate": 1.4148196436332032e-05, + "loss": 0.2601, + "step": 10772 + }, + { + "epoch": 0.88, + "learning_rate": 1.4147653194263364e-05, + "loss": 0.4562, + "step": 10773 + }, + { + "epoch": 0.88, + "learning_rate": 1.41471099521947e-05, + "loss": 0.3872, + "step": 10774 + }, + { + "epoch": 0.88, + "learning_rate": 1.4146566710126033e-05, + "loss": 0.4708, + "step": 10775 + }, + { + "epoch": 0.88, + "learning_rate": 1.4146023468057368e-05, + "loss": 0.6056, + "step": 10776 + }, + { + "epoch": 0.88, + "learning_rate": 1.4145480225988701e-05, + "loss": 0.4176, + "step": 10777 + }, + { + "epoch": 0.88, + "learning_rate": 1.4144936983920037e-05, + "loss": 0.3464, + "step": 10778 + }, + { + "epoch": 0.88, + "learning_rate": 1.414439374185137e-05, + "loss": 0.3431, + "step": 10779 + }, + { + "epoch": 0.88, + "learning_rate": 1.4143850499782705e-05, + "loss": 0.5878, + "step": 10780 + }, + { + "epoch": 0.88, + "learning_rate": 1.4143307257714038e-05, + "loss": 0.4653, + "step": 10781 + }, + { + "epoch": 0.88, + "learning_rate": 1.4142764015645374e-05, + "loss": 0.4555, + "step": 10782 + }, + { + "epoch": 0.88, + "learning_rate": 1.4142220773576706e-05, + "loss": 0.3358, + "step": 10783 + }, + { + "epoch": 0.88, + "learning_rate": 1.414167753150804e-05, + "loss": 0.3281, + "step": 10784 + }, + { + "epoch": 0.88, + "learning_rate": 1.4141134289439375e-05, + "loss": 0.3847, + "step": 10785 + }, + { + "epoch": 0.88, + "learning_rate": 1.4140591047370709e-05, + "loss": 0.367, + "step": 10786 + }, + { + "epoch": 0.88, + "learning_rate": 1.4140047805302043e-05, + "loss": 0.5227, + "step": 10787 + }, + { + "epoch": 0.88, + "learning_rate": 1.4139504563233378e-05, + "loss": 0.414, + "step": 10788 + }, + { + "epoch": 0.88, + "learning_rate": 1.4138961321164712e-05, + "loss": 0.2317, + "step": 10789 + }, + { + "epoch": 0.88, + "learning_rate": 1.4138418079096046e-05, + "loss": 0.3649, + "step": 10790 + }, + { + "epoch": 0.88, + "learning_rate": 1.4137874837027382e-05, + "loss": 0.4321, + "step": 10791 + }, + { + "epoch": 0.88, + "learning_rate": 1.4137331594958714e-05, + "loss": 0.356, + "step": 10792 + }, + { + "epoch": 0.88, + "learning_rate": 1.413678835289005e-05, + "loss": 0.7004, + "step": 10793 + }, + { + "epoch": 0.88, + "learning_rate": 1.4136245110821383e-05, + "loss": 0.3219, + "step": 10794 + }, + { + "epoch": 0.88, + "learning_rate": 1.4135701868752719e-05, + "loss": 0.418, + "step": 10795 + }, + { + "epoch": 0.88, + "learning_rate": 1.4135158626684051e-05, + "loss": 0.4093, + "step": 10796 + }, + { + "epoch": 0.88, + "learning_rate": 1.4134615384615387e-05, + "loss": 0.4864, + "step": 10797 + }, + { + "epoch": 0.88, + "learning_rate": 1.413407214254672e-05, + "loss": 0.3868, + "step": 10798 + }, + { + "epoch": 0.88, + "learning_rate": 1.4133528900478056e-05, + "loss": 0.23, + "step": 10799 + }, + { + "epoch": 0.88, + "learning_rate": 1.4132985658409388e-05, + "loss": 0.4252, + "step": 10800 + }, + { + "epoch": 0.88, + "learning_rate": 1.4132442416340724e-05, + "loss": 0.6949, + "step": 10801 + }, + { + "epoch": 0.88, + "learning_rate": 1.4131899174272057e-05, + "loss": 0.2081, + "step": 10802 + }, + { + "epoch": 0.88, + "learning_rate": 1.413135593220339e-05, + "loss": 0.3356, + "step": 10803 + }, + { + "epoch": 0.88, + "learning_rate": 1.4130812690134725e-05, + "loss": 0.4188, + "step": 10804 + }, + { + "epoch": 0.88, + "learning_rate": 1.4130269448066058e-05, + "loss": 0.3264, + "step": 10805 + }, + { + "epoch": 0.88, + "learning_rate": 1.4129726205997394e-05, + "loss": 0.3917, + "step": 10806 + }, + { + "epoch": 0.88, + "learning_rate": 1.4129182963928726e-05, + "loss": 0.5864, + "step": 10807 + }, + { + "epoch": 0.88, + "learning_rate": 1.4128639721860062e-05, + "loss": 0.5501, + "step": 10808 + }, + { + "epoch": 0.88, + "learning_rate": 1.4128096479791396e-05, + "loss": 0.6517, + "step": 10809 + }, + { + "epoch": 0.88, + "learning_rate": 1.412755323772273e-05, + "loss": 0.4395, + "step": 10810 + }, + { + "epoch": 0.88, + "learning_rate": 1.4127009995654065e-05, + "loss": 0.3576, + "step": 10811 + }, + { + "epoch": 0.88, + "learning_rate": 1.4126466753585399e-05, + "loss": 0.4008, + "step": 10812 + }, + { + "epoch": 0.88, + "learning_rate": 1.4125923511516733e-05, + "loss": 0.4907, + "step": 10813 + }, + { + "epoch": 0.88, + "learning_rate": 1.4125380269448068e-05, + "loss": 0.3281, + "step": 10814 + }, + { + "epoch": 0.88, + "learning_rate": 1.4124837027379402e-05, + "loss": 0.5606, + "step": 10815 + }, + { + "epoch": 0.88, + "learning_rate": 1.4124293785310736e-05, + "loss": 0.3928, + "step": 10816 + }, + { + "epoch": 0.88, + "learning_rate": 1.412375054324207e-05, + "loss": 0.6333, + "step": 10817 + }, + { + "epoch": 0.88, + "learning_rate": 1.4123207301173404e-05, + "loss": 0.3729, + "step": 10818 + }, + { + "epoch": 0.88, + "learning_rate": 1.4122664059104739e-05, + "loss": 0.5031, + "step": 10819 + }, + { + "epoch": 0.88, + "learning_rate": 1.4122120817036073e-05, + "loss": 0.5152, + "step": 10820 + }, + { + "epoch": 0.88, + "learning_rate": 1.4121577574967407e-05, + "loss": 0.4245, + "step": 10821 + }, + { + "epoch": 0.88, + "learning_rate": 1.412103433289874e-05, + "loss": 0.7627, + "step": 10822 + }, + { + "epoch": 0.88, + "learning_rate": 1.4120491090830076e-05, + "loss": 0.3979, + "step": 10823 + }, + { + "epoch": 0.88, + "learning_rate": 1.4119947848761408e-05, + "loss": 0.3953, + "step": 10824 + }, + { + "epoch": 0.88, + "learning_rate": 1.4119404606692744e-05, + "loss": 0.4774, + "step": 10825 + }, + { + "epoch": 0.88, + "learning_rate": 1.4118861364624077e-05, + "loss": 0.4433, + "step": 10826 + }, + { + "epoch": 0.88, + "learning_rate": 1.4118318122555413e-05, + "loss": 0.4105, + "step": 10827 + }, + { + "epoch": 0.88, + "learning_rate": 1.4117774880486745e-05, + "loss": 0.4618, + "step": 10828 + }, + { + "epoch": 0.88, + "learning_rate": 1.4117231638418081e-05, + "loss": 0.3965, + "step": 10829 + }, + { + "epoch": 0.88, + "learning_rate": 1.4116688396349414e-05, + "loss": 0.4299, + "step": 10830 + }, + { + "epoch": 0.88, + "learning_rate": 1.411614515428075e-05, + "loss": 0.4255, + "step": 10831 + }, + { + "epoch": 0.88, + "learning_rate": 1.4115601912212082e-05, + "loss": 0.3181, + "step": 10832 + }, + { + "epoch": 0.88, + "learning_rate": 1.4115058670143418e-05, + "loss": 0.4965, + "step": 10833 + }, + { + "epoch": 0.88, + "learning_rate": 1.411451542807475e-05, + "loss": 0.44, + "step": 10834 + }, + { + "epoch": 0.88, + "learning_rate": 1.4113972186006086e-05, + "loss": 0.674, + "step": 10835 + }, + { + "epoch": 0.88, + "learning_rate": 1.4113428943937419e-05, + "loss": 0.6445, + "step": 10836 + }, + { + "epoch": 0.88, + "learning_rate": 1.4112885701868755e-05, + "loss": 0.4309, + "step": 10837 + }, + { + "epoch": 0.88, + "learning_rate": 1.4112342459800087e-05, + "loss": 0.5695, + "step": 10838 + }, + { + "epoch": 0.88, + "learning_rate": 1.4111799217731423e-05, + "loss": 0.3635, + "step": 10839 + }, + { + "epoch": 0.88, + "learning_rate": 1.4111255975662756e-05, + "loss": 0.3505, + "step": 10840 + }, + { + "epoch": 0.88, + "learning_rate": 1.411071273359409e-05, + "loss": 0.4346, + "step": 10841 + }, + { + "epoch": 0.88, + "learning_rate": 1.4110169491525424e-05, + "loss": 0.292, + "step": 10842 + }, + { + "epoch": 0.88, + "learning_rate": 1.4109626249456759e-05, + "loss": 0.3314, + "step": 10843 + }, + { + "epoch": 0.88, + "learning_rate": 1.4109083007388093e-05, + "loss": 0.4212, + "step": 10844 + }, + { + "epoch": 0.88, + "learning_rate": 1.4108539765319427e-05, + "loss": 0.6958, + "step": 10845 + }, + { + "epoch": 0.88, + "learning_rate": 1.4107996523250763e-05, + "loss": 0.4469, + "step": 10846 + }, + { + "epoch": 0.88, + "learning_rate": 1.4107453281182095e-05, + "loss": 0.4383, + "step": 10847 + }, + { + "epoch": 0.88, + "learning_rate": 1.4106910039113431e-05, + "loss": 0.3193, + "step": 10848 + }, + { + "epoch": 0.88, + "learning_rate": 1.4106366797044764e-05, + "loss": 0.4048, + "step": 10849 + }, + { + "epoch": 0.88, + "learning_rate": 1.41058235549761e-05, + "loss": 0.3955, + "step": 10850 + }, + { + "epoch": 0.88, + "learning_rate": 1.4105280312907432e-05, + "loss": 0.2658, + "step": 10851 + }, + { + "epoch": 0.88, + "learning_rate": 1.4104737070838768e-05, + "loss": 0.3935, + "step": 10852 + }, + { + "epoch": 0.88, + "learning_rate": 1.41041938287701e-05, + "loss": 0.4403, + "step": 10853 + }, + { + "epoch": 0.88, + "learning_rate": 1.4103650586701437e-05, + "loss": 0.4084, + "step": 10854 + }, + { + "epoch": 0.88, + "learning_rate": 1.410310734463277e-05, + "loss": 0.406, + "step": 10855 + }, + { + "epoch": 0.88, + "learning_rate": 1.4102564102564105e-05, + "loss": 0.373, + "step": 10856 + }, + { + "epoch": 0.88, + "learning_rate": 1.4102020860495438e-05, + "loss": 0.3743, + "step": 10857 + }, + { + "epoch": 0.88, + "learning_rate": 1.4101477618426774e-05, + "loss": 0.5659, + "step": 10858 + }, + { + "epoch": 0.88, + "learning_rate": 1.4100934376358106e-05, + "loss": 0.3343, + "step": 10859 + }, + { + "epoch": 0.88, + "learning_rate": 1.4100391134289439e-05, + "loss": 0.4218, + "step": 10860 + }, + { + "epoch": 0.89, + "learning_rate": 1.4099847892220775e-05, + "loss": 0.5055, + "step": 10861 + }, + { + "epoch": 0.89, + "learning_rate": 1.4099304650152107e-05, + "loss": 0.5754, + "step": 10862 + }, + { + "epoch": 0.89, + "learning_rate": 1.4098761408083443e-05, + "loss": 0.8872, + "step": 10863 + }, + { + "epoch": 0.89, + "learning_rate": 1.4098218166014777e-05, + "loss": 0.5685, + "step": 10864 + }, + { + "epoch": 0.89, + "learning_rate": 1.4097674923946112e-05, + "loss": 0.3128, + "step": 10865 + }, + { + "epoch": 0.89, + "learning_rate": 1.4097131681877446e-05, + "loss": 0.5797, + "step": 10866 + }, + { + "epoch": 0.89, + "learning_rate": 1.409658843980878e-05, + "loss": 0.7088, + "step": 10867 + }, + { + "epoch": 0.89, + "learning_rate": 1.4096045197740114e-05, + "loss": 0.4309, + "step": 10868 + }, + { + "epoch": 0.89, + "learning_rate": 1.4095501955671448e-05, + "loss": 0.3972, + "step": 10869 + }, + { + "epoch": 0.89, + "learning_rate": 1.4094958713602783e-05, + "loss": 0.4014, + "step": 10870 + }, + { + "epoch": 0.89, + "learning_rate": 1.4094415471534117e-05, + "loss": 0.5954, + "step": 10871 + }, + { + "epoch": 0.89, + "learning_rate": 1.4093872229465451e-05, + "loss": 0.4959, + "step": 10872 + }, + { + "epoch": 0.89, + "learning_rate": 1.4093328987396785e-05, + "loss": 0.3859, + "step": 10873 + }, + { + "epoch": 0.89, + "learning_rate": 1.409278574532812e-05, + "loss": 0.3317, + "step": 10874 + }, + { + "epoch": 0.89, + "learning_rate": 1.4092242503259454e-05, + "loss": 0.643, + "step": 10875 + }, + { + "epoch": 0.89, + "learning_rate": 1.4091699261190788e-05, + "loss": 0.5424, + "step": 10876 + }, + { + "epoch": 0.89, + "learning_rate": 1.4091156019122122e-05, + "loss": 0.7043, + "step": 10877 + }, + { + "epoch": 0.89, + "learning_rate": 1.4090612777053457e-05, + "loss": 0.4068, + "step": 10878 + }, + { + "epoch": 0.89, + "learning_rate": 1.4090069534984789e-05, + "loss": 0.6969, + "step": 10879 + }, + { + "epoch": 0.89, + "learning_rate": 1.4089526292916125e-05, + "loss": 0.3745, + "step": 10880 + }, + { + "epoch": 0.89, + "learning_rate": 1.4088983050847458e-05, + "loss": 0.405, + "step": 10881 + }, + { + "epoch": 0.89, + "learning_rate": 1.4088439808778793e-05, + "loss": 0.5453, + "step": 10882 + }, + { + "epoch": 0.89, + "learning_rate": 1.4087896566710126e-05, + "loss": 0.4705, + "step": 10883 + }, + { + "epoch": 0.89, + "learning_rate": 1.4087353324641462e-05, + "loss": 0.7704, + "step": 10884 + }, + { + "epoch": 0.89, + "learning_rate": 1.4086810082572794e-05, + "loss": 0.8142, + "step": 10885 + }, + { + "epoch": 0.89, + "learning_rate": 1.408626684050413e-05, + "loss": 0.5653, + "step": 10886 + }, + { + "epoch": 0.89, + "learning_rate": 1.4085723598435463e-05, + "loss": 0.4411, + "step": 10887 + }, + { + "epoch": 0.89, + "learning_rate": 1.4085180356366799e-05, + "loss": 0.3449, + "step": 10888 + }, + { + "epoch": 0.89, + "learning_rate": 1.4084637114298131e-05, + "loss": 0.4962, + "step": 10889 + }, + { + "epoch": 0.89, + "learning_rate": 1.4084093872229467e-05, + "loss": 0.5483, + "step": 10890 + }, + { + "epoch": 0.89, + "learning_rate": 1.40835506301608e-05, + "loss": 0.3397, + "step": 10891 + }, + { + "epoch": 0.89, + "learning_rate": 1.4083007388092136e-05, + "loss": 0.4596, + "step": 10892 + }, + { + "epoch": 0.89, + "learning_rate": 1.4082464146023468e-05, + "loss": 0.3025, + "step": 10893 + }, + { + "epoch": 0.89, + "learning_rate": 1.4081920903954804e-05, + "loss": 0.5247, + "step": 10894 + }, + { + "epoch": 0.89, + "learning_rate": 1.4081377661886137e-05, + "loss": 0.7021, + "step": 10895 + }, + { + "epoch": 0.89, + "learning_rate": 1.4080834419817473e-05, + "loss": 0.4344, + "step": 10896 + }, + { + "epoch": 0.89, + "learning_rate": 1.4080291177748805e-05, + "loss": 0.5392, + "step": 10897 + }, + { + "epoch": 0.89, + "learning_rate": 1.407974793568014e-05, + "loss": 0.436, + "step": 10898 + }, + { + "epoch": 0.89, + "learning_rate": 1.4079204693611475e-05, + "loss": 0.5469, + "step": 10899 + }, + { + "epoch": 0.89, + "learning_rate": 1.4078661451542808e-05, + "loss": 0.6248, + "step": 10900 + }, + { + "epoch": 0.89, + "learning_rate": 1.4078118209474144e-05, + "loss": 0.3749, + "step": 10901 + }, + { + "epoch": 0.89, + "learning_rate": 1.4077574967405476e-05, + "loss": 0.2478, + "step": 10902 + }, + { + "epoch": 0.89, + "learning_rate": 1.4077031725336812e-05, + "loss": 0.4748, + "step": 10903 + }, + { + "epoch": 0.89, + "learning_rate": 1.4076488483268145e-05, + "loss": 0.3357, + "step": 10904 + }, + { + "epoch": 0.89, + "learning_rate": 1.407594524119948e-05, + "loss": 0.5829, + "step": 10905 + }, + { + "epoch": 0.89, + "learning_rate": 1.4075401999130813e-05, + "loss": 0.6221, + "step": 10906 + }, + { + "epoch": 0.89, + "learning_rate": 1.407485875706215e-05, + "loss": 0.3473, + "step": 10907 + }, + { + "epoch": 0.89, + "learning_rate": 1.4074315514993482e-05, + "loss": 0.4338, + "step": 10908 + }, + { + "epoch": 0.89, + "learning_rate": 1.4073772272924818e-05, + "loss": 0.4023, + "step": 10909 + }, + { + "epoch": 0.89, + "learning_rate": 1.407322903085615e-05, + "loss": 0.2913, + "step": 10910 + }, + { + "epoch": 0.89, + "learning_rate": 1.4072685788787486e-05, + "loss": 0.6052, + "step": 10911 + }, + { + "epoch": 0.89, + "learning_rate": 1.4072142546718819e-05, + "loss": 0.3994, + "step": 10912 + }, + { + "epoch": 0.89, + "learning_rate": 1.4071599304650155e-05, + "loss": 0.4271, + "step": 10913 + }, + { + "epoch": 0.89, + "learning_rate": 1.4071056062581487e-05, + "loss": 0.2834, + "step": 10914 + }, + { + "epoch": 0.89, + "learning_rate": 1.4070512820512823e-05, + "loss": 0.7314, + "step": 10915 + }, + { + "epoch": 0.89, + "learning_rate": 1.4069969578444156e-05, + "loss": 0.2741, + "step": 10916 + }, + { + "epoch": 0.89, + "learning_rate": 1.406942633637549e-05, + "loss": 0.5316, + "step": 10917 + }, + { + "epoch": 0.89, + "learning_rate": 1.4068883094306824e-05, + "loss": 0.2905, + "step": 10918 + }, + { + "epoch": 0.89, + "learning_rate": 1.4068339852238158e-05, + "loss": 0.6001, + "step": 10919 + }, + { + "epoch": 0.89, + "learning_rate": 1.4067796610169493e-05, + "loss": 0.3047, + "step": 10920 + }, + { + "epoch": 0.89, + "learning_rate": 1.4067253368100827e-05, + "loss": 0.4799, + "step": 10921 + }, + { + "epoch": 0.89, + "learning_rate": 1.4066710126032161e-05, + "loss": 0.5524, + "step": 10922 + }, + { + "epoch": 0.89, + "learning_rate": 1.4066166883963495e-05, + "loss": 0.3087, + "step": 10923 + }, + { + "epoch": 0.89, + "learning_rate": 1.406562364189483e-05, + "loss": 0.5635, + "step": 10924 + }, + { + "epoch": 0.89, + "learning_rate": 1.4065080399826164e-05, + "loss": 0.5956, + "step": 10925 + }, + { + "epoch": 0.89, + "learning_rate": 1.4064537157757498e-05, + "loss": 0.2764, + "step": 10926 + }, + { + "epoch": 0.89, + "learning_rate": 1.4063993915688832e-05, + "loss": 0.3441, + "step": 10927 + }, + { + "epoch": 0.89, + "learning_rate": 1.4063450673620166e-05, + "loss": 0.2554, + "step": 10928 + }, + { + "epoch": 0.89, + "learning_rate": 1.40629074315515e-05, + "loss": 0.4778, + "step": 10929 + }, + { + "epoch": 0.89, + "learning_rate": 1.4062364189482835e-05, + "loss": 0.4305, + "step": 10930 + }, + { + "epoch": 0.89, + "learning_rate": 1.4061820947414169e-05, + "loss": 0.4745, + "step": 10931 + }, + { + "epoch": 0.89, + "learning_rate": 1.4061277705345503e-05, + "loss": 0.4611, + "step": 10932 + }, + { + "epoch": 0.89, + "learning_rate": 1.4060734463276838e-05, + "loss": 0.4335, + "step": 10933 + }, + { + "epoch": 0.89, + "learning_rate": 1.4060191221208172e-05, + "loss": 0.1963, + "step": 10934 + }, + { + "epoch": 0.89, + "learning_rate": 1.4059647979139506e-05, + "loss": 0.3819, + "step": 10935 + }, + { + "epoch": 0.89, + "learning_rate": 1.4059104737070839e-05, + "loss": 0.3046, + "step": 10936 + }, + { + "epoch": 0.89, + "learning_rate": 1.4058561495002174e-05, + "loss": 0.5376, + "step": 10937 + }, + { + "epoch": 0.89, + "learning_rate": 1.4058018252933507e-05, + "loss": 0.4499, + "step": 10938 + }, + { + "epoch": 0.89, + "learning_rate": 1.4057475010864843e-05, + "loss": 0.5306, + "step": 10939 + }, + { + "epoch": 0.89, + "learning_rate": 1.4056931768796175e-05, + "loss": 0.8033, + "step": 10940 + }, + { + "epoch": 0.89, + "learning_rate": 1.4056388526727511e-05, + "loss": 0.5153, + "step": 10941 + }, + { + "epoch": 0.89, + "learning_rate": 1.4055845284658844e-05, + "loss": 0.5181, + "step": 10942 + }, + { + "epoch": 0.89, + "learning_rate": 1.405530204259018e-05, + "loss": 0.6603, + "step": 10943 + }, + { + "epoch": 0.89, + "learning_rate": 1.4054758800521512e-05, + "loss": 0.3488, + "step": 10944 + }, + { + "epoch": 0.89, + "learning_rate": 1.4054215558452848e-05, + "loss": 0.1905, + "step": 10945 + }, + { + "epoch": 0.89, + "learning_rate": 1.4053672316384181e-05, + "loss": 0.5154, + "step": 10946 + }, + { + "epoch": 0.89, + "learning_rate": 1.4053129074315517e-05, + "loss": 0.6186, + "step": 10947 + }, + { + "epoch": 0.89, + "learning_rate": 1.405258583224685e-05, + "loss": 0.3709, + "step": 10948 + }, + { + "epoch": 0.89, + "learning_rate": 1.4052042590178185e-05, + "loss": 0.4491, + "step": 10949 + }, + { + "epoch": 0.89, + "learning_rate": 1.4051499348109518e-05, + "loss": 0.4633, + "step": 10950 + }, + { + "epoch": 0.89, + "learning_rate": 1.4050956106040854e-05, + "loss": 0.3409, + "step": 10951 + }, + { + "epoch": 0.89, + "learning_rate": 1.4050412863972186e-05, + "loss": 0.6167, + "step": 10952 + }, + { + "epoch": 0.89, + "learning_rate": 1.4049869621903522e-05, + "loss": 0.3045, + "step": 10953 + }, + { + "epoch": 0.89, + "learning_rate": 1.4049326379834856e-05, + "loss": 0.4693, + "step": 10954 + }, + { + "epoch": 0.89, + "learning_rate": 1.4048783137766189e-05, + "loss": 0.563, + "step": 10955 + }, + { + "epoch": 0.89, + "learning_rate": 1.4048239895697525e-05, + "loss": 0.5868, + "step": 10956 + }, + { + "epoch": 0.89, + "learning_rate": 1.4047696653628857e-05, + "loss": 0.4299, + "step": 10957 + }, + { + "epoch": 0.89, + "learning_rate": 1.4047153411560193e-05, + "loss": 0.235, + "step": 10958 + }, + { + "epoch": 0.89, + "learning_rate": 1.4046610169491526e-05, + "loss": 0.3496, + "step": 10959 + }, + { + "epoch": 0.89, + "learning_rate": 1.4046066927422862e-05, + "loss": 0.3343, + "step": 10960 + }, + { + "epoch": 0.89, + "learning_rate": 1.4045523685354194e-05, + "loss": 0.6584, + "step": 10961 + }, + { + "epoch": 0.89, + "learning_rate": 1.404498044328553e-05, + "loss": 0.4713, + "step": 10962 + }, + { + "epoch": 0.89, + "learning_rate": 1.4044437201216863e-05, + "loss": 0.708, + "step": 10963 + }, + { + "epoch": 0.89, + "learning_rate": 1.4043893959148199e-05, + "loss": 0.5357, + "step": 10964 + }, + { + "epoch": 0.89, + "learning_rate": 1.4043350717079531e-05, + "loss": 0.2462, + "step": 10965 + }, + { + "epoch": 0.89, + "learning_rate": 1.4042807475010867e-05, + "loss": 0.3714, + "step": 10966 + }, + { + "epoch": 0.89, + "learning_rate": 1.40422642329422e-05, + "loss": 0.4258, + "step": 10967 + }, + { + "epoch": 0.89, + "learning_rate": 1.4041720990873536e-05, + "loss": 0.4947, + "step": 10968 + }, + { + "epoch": 0.89, + "learning_rate": 1.4041177748804868e-05, + "loss": 0.52, + "step": 10969 + }, + { + "epoch": 0.89, + "learning_rate": 1.4040634506736204e-05, + "loss": 0.3106, + "step": 10970 + }, + { + "epoch": 0.89, + "learning_rate": 1.4040091264667537e-05, + "loss": 0.5113, + "step": 10971 + }, + { + "epoch": 0.89, + "learning_rate": 1.4039548022598873e-05, + "loss": 0.6446, + "step": 10972 + }, + { + "epoch": 0.89, + "learning_rate": 1.4039004780530205e-05, + "loss": 0.5138, + "step": 10973 + }, + { + "epoch": 0.89, + "learning_rate": 1.403846153846154e-05, + "loss": 0.3132, + "step": 10974 + }, + { + "epoch": 0.89, + "learning_rate": 1.4037918296392874e-05, + "loss": 0.5382, + "step": 10975 + }, + { + "epoch": 0.89, + "learning_rate": 1.4037375054324208e-05, + "loss": 0.585, + "step": 10976 + }, + { + "epoch": 0.89, + "learning_rate": 1.4036831812255542e-05, + "loss": 0.4038, + "step": 10977 + }, + { + "epoch": 0.89, + "learning_rate": 1.4036288570186876e-05, + "loss": 0.4329, + "step": 10978 + }, + { + "epoch": 0.89, + "learning_rate": 1.403574532811821e-05, + "loss": 0.3361, + "step": 10979 + }, + { + "epoch": 0.89, + "learning_rate": 1.4035202086049545e-05, + "loss": 0.8853, + "step": 10980 + }, + { + "epoch": 0.89, + "learning_rate": 1.4034658843980879e-05, + "loss": 0.3238, + "step": 10981 + }, + { + "epoch": 0.89, + "learning_rate": 1.4034115601912213e-05, + "loss": 0.2898, + "step": 10982 + }, + { + "epoch": 0.89, + "learning_rate": 1.4033572359843547e-05, + "loss": 0.4491, + "step": 10983 + }, + { + "epoch": 0.9, + "learning_rate": 1.4033029117774882e-05, + "loss": 0.4387, + "step": 10984 + }, + { + "epoch": 0.9, + "learning_rate": 1.4032485875706216e-05, + "loss": 0.4636, + "step": 10985 + }, + { + "epoch": 0.9, + "learning_rate": 1.403194263363755e-05, + "loss": 0.6755, + "step": 10986 + }, + { + "epoch": 0.9, + "learning_rate": 1.4031399391568884e-05, + "loss": 0.4453, + "step": 10987 + }, + { + "epoch": 0.9, + "learning_rate": 1.4030856149500219e-05, + "loss": 0.4645, + "step": 10988 + }, + { + "epoch": 0.9, + "learning_rate": 1.4030312907431553e-05, + "loss": 0.351, + "step": 10989 + }, + { + "epoch": 0.9, + "learning_rate": 1.4029769665362887e-05, + "loss": 0.7522, + "step": 10990 + }, + { + "epoch": 0.9, + "learning_rate": 1.4029226423294223e-05, + "loss": 0.7657, + "step": 10991 + }, + { + "epoch": 0.9, + "learning_rate": 1.4028683181225555e-05, + "loss": 0.3215, + "step": 10992 + }, + { + "epoch": 0.9, + "learning_rate": 1.4028139939156888e-05, + "loss": 0.4978, + "step": 10993 + }, + { + "epoch": 0.9, + "learning_rate": 1.4027596697088224e-05, + "loss": 0.2783, + "step": 10994 + }, + { + "epoch": 0.9, + "learning_rate": 1.4027053455019556e-05, + "loss": 0.4206, + "step": 10995 + }, + { + "epoch": 0.9, + "learning_rate": 1.4026510212950892e-05, + "loss": 0.377, + "step": 10996 + }, + { + "epoch": 0.9, + "learning_rate": 1.4025966970882225e-05, + "loss": 0.3212, + "step": 10997 + }, + { + "epoch": 0.9, + "learning_rate": 1.4025423728813561e-05, + "loss": 0.4748, + "step": 10998 + }, + { + "epoch": 0.9, + "learning_rate": 1.4024880486744893e-05, + "loss": 0.6656, + "step": 10999 + }, + { + "epoch": 0.9, + "learning_rate": 1.402433724467623e-05, + "loss": 0.5026, + "step": 11000 + }, + { + "epoch": 0.9, + "eval_accuracy": 0.8353540499235863, + "eval_loss": 0.42644956707954407, + "eval_runtime": 22.2807, + "eval_samples_per_second": 440.516, + "eval_steps_per_second": 3.456, + "step": 11000 + }, + { + "epoch": 0.9, + "learning_rate": 1.4023794002607562e-05, + "loss": 0.3439, + "step": 11001 + }, + { + "epoch": 0.9, + "learning_rate": 1.4023250760538898e-05, + "loss": 0.5254, + "step": 11002 + }, + { + "epoch": 0.9, + "learning_rate": 1.402270751847023e-05, + "loss": 0.4171, + "step": 11003 + }, + { + "epoch": 0.9, + "learning_rate": 1.4022164276401566e-05, + "loss": 0.2931, + "step": 11004 + }, + { + "epoch": 0.9, + "learning_rate": 1.4021621034332899e-05, + "loss": 0.272, + "step": 11005 + }, + { + "epoch": 0.9, + "learning_rate": 1.4021077792264235e-05, + "loss": 0.3564, + "step": 11006 + }, + { + "epoch": 0.9, + "learning_rate": 1.4020534550195569e-05, + "loss": 0.4358, + "step": 11007 + }, + { + "epoch": 0.9, + "learning_rate": 1.4019991308126903e-05, + "loss": 0.2644, + "step": 11008 + }, + { + "epoch": 0.9, + "learning_rate": 1.4019448066058237e-05, + "loss": 0.4108, + "step": 11009 + }, + { + "epoch": 0.9, + "learning_rate": 1.4018904823989572e-05, + "loss": 0.5348, + "step": 11010 + }, + { + "epoch": 0.9, + "learning_rate": 1.4018361581920906e-05, + "loss": 0.6126, + "step": 11011 + }, + { + "epoch": 0.9, + "learning_rate": 1.4017818339852238e-05, + "loss": 0.2953, + "step": 11012 + }, + { + "epoch": 0.9, + "learning_rate": 1.4017275097783574e-05, + "loss": 0.1699, + "step": 11013 + }, + { + "epoch": 0.9, + "learning_rate": 1.4016731855714907e-05, + "loss": 0.3469, + "step": 11014 + }, + { + "epoch": 0.9, + "learning_rate": 1.4016188613646243e-05, + "loss": 0.6247, + "step": 11015 + }, + { + "epoch": 0.9, + "learning_rate": 1.4015645371577575e-05, + "loss": 0.286, + "step": 11016 + }, + { + "epoch": 0.9, + "learning_rate": 1.4015102129508911e-05, + "loss": 0.264, + "step": 11017 + }, + { + "epoch": 0.9, + "learning_rate": 1.4014558887440244e-05, + "loss": 0.7508, + "step": 11018 + }, + { + "epoch": 0.9, + "learning_rate": 1.401401564537158e-05, + "loss": 0.4546, + "step": 11019 + }, + { + "epoch": 0.9, + "learning_rate": 1.4013472403302912e-05, + "loss": 0.3366, + "step": 11020 + }, + { + "epoch": 0.9, + "learning_rate": 1.4012929161234248e-05, + "loss": 0.6259, + "step": 11021 + }, + { + "epoch": 0.9, + "learning_rate": 1.401238591916558e-05, + "loss": 0.4738, + "step": 11022 + }, + { + "epoch": 0.9, + "learning_rate": 1.4011842677096917e-05, + "loss": 0.4065, + "step": 11023 + }, + { + "epoch": 0.9, + "learning_rate": 1.4011299435028249e-05, + "loss": 0.4898, + "step": 11024 + }, + { + "epoch": 0.9, + "learning_rate": 1.4010756192959585e-05, + "loss": 0.4431, + "step": 11025 + }, + { + "epoch": 0.9, + "learning_rate": 1.4010212950890918e-05, + "loss": 0.5287, + "step": 11026 + }, + { + "epoch": 0.9, + "learning_rate": 1.4009669708822254e-05, + "loss": 0.6687, + "step": 11027 + }, + { + "epoch": 0.9, + "learning_rate": 1.4009126466753586e-05, + "loss": 0.5497, + "step": 11028 + }, + { + "epoch": 0.9, + "learning_rate": 1.4008583224684922e-05, + "loss": 0.3274, + "step": 11029 + }, + { + "epoch": 0.9, + "learning_rate": 1.4008039982616255e-05, + "loss": 0.4259, + "step": 11030 + }, + { + "epoch": 0.9, + "learning_rate": 1.4007496740547589e-05, + "loss": 0.3997, + "step": 11031 + }, + { + "epoch": 0.9, + "learning_rate": 1.4006953498478923e-05, + "loss": 0.1398, + "step": 11032 + }, + { + "epoch": 0.9, + "learning_rate": 1.4006410256410257e-05, + "loss": 0.385, + "step": 11033 + }, + { + "epoch": 0.9, + "learning_rate": 1.4005867014341591e-05, + "loss": 0.6787, + "step": 11034 + }, + { + "epoch": 0.9, + "learning_rate": 1.4005323772272926e-05, + "loss": 0.4869, + "step": 11035 + }, + { + "epoch": 0.9, + "learning_rate": 1.400478053020426e-05, + "loss": 0.3208, + "step": 11036 + }, + { + "epoch": 0.9, + "learning_rate": 1.4004237288135594e-05, + "loss": 0.7039, + "step": 11037 + }, + { + "epoch": 0.9, + "learning_rate": 1.4003694046066928e-05, + "loss": 0.4602, + "step": 11038 + }, + { + "epoch": 0.9, + "learning_rate": 1.4003150803998263e-05, + "loss": 0.7473, + "step": 11039 + }, + { + "epoch": 0.9, + "learning_rate": 1.4002607561929597e-05, + "loss": 0.4878, + "step": 11040 + }, + { + "epoch": 0.9, + "learning_rate": 1.4002064319860931e-05, + "loss": 0.4107, + "step": 11041 + }, + { + "epoch": 0.9, + "learning_rate": 1.4001521077792265e-05, + "loss": 0.4609, + "step": 11042 + }, + { + "epoch": 0.9, + "learning_rate": 1.40009778357236e-05, + "loss": 0.2018, + "step": 11043 + }, + { + "epoch": 0.9, + "learning_rate": 1.4000434593654935e-05, + "loss": 0.4993, + "step": 11044 + }, + { + "epoch": 0.9, + "learning_rate": 1.3999891351586268e-05, + "loss": 0.6437, + "step": 11045 + }, + { + "epoch": 0.9, + "learning_rate": 1.3999348109517604e-05, + "loss": 0.3346, + "step": 11046 + }, + { + "epoch": 0.9, + "learning_rate": 1.3998804867448936e-05, + "loss": 0.3376, + "step": 11047 + }, + { + "epoch": 0.9, + "learning_rate": 1.3998261625380272e-05, + "loss": 0.4171, + "step": 11048 + }, + { + "epoch": 0.9, + "learning_rate": 1.3997718383311605e-05, + "loss": 0.285, + "step": 11049 + }, + { + "epoch": 0.9, + "learning_rate": 1.3997175141242937e-05, + "loss": 0.4586, + "step": 11050 + }, + { + "epoch": 0.9, + "learning_rate": 1.3996631899174273e-05, + "loss": 0.3728, + "step": 11051 + }, + { + "epoch": 0.9, + "learning_rate": 1.3996088657105606e-05, + "loss": 0.4188, + "step": 11052 + }, + { + "epoch": 0.9, + "learning_rate": 1.3995545415036942e-05, + "loss": 0.1914, + "step": 11053 + }, + { + "epoch": 0.9, + "learning_rate": 1.3995002172968274e-05, + "loss": 0.6198, + "step": 11054 + }, + { + "epoch": 0.9, + "learning_rate": 1.399445893089961e-05, + "loss": 0.3255, + "step": 11055 + }, + { + "epoch": 0.9, + "learning_rate": 1.3993915688830943e-05, + "loss": 0.2389, + "step": 11056 + }, + { + "epoch": 0.9, + "learning_rate": 1.3993372446762279e-05, + "loss": 0.5625, + "step": 11057 + }, + { + "epoch": 0.9, + "learning_rate": 1.3992829204693611e-05, + "loss": 0.5981, + "step": 11058 + }, + { + "epoch": 0.9, + "learning_rate": 1.3992285962624947e-05, + "loss": 0.5196, + "step": 11059 + }, + { + "epoch": 0.9, + "learning_rate": 1.399174272055628e-05, + "loss": 0.5392, + "step": 11060 + }, + { + "epoch": 0.9, + "learning_rate": 1.3991199478487616e-05, + "loss": 0.3866, + "step": 11061 + }, + { + "epoch": 0.9, + "learning_rate": 1.399065623641895e-05, + "loss": 0.3822, + "step": 11062 + }, + { + "epoch": 0.9, + "learning_rate": 1.3990112994350284e-05, + "loss": 0.6467, + "step": 11063 + }, + { + "epoch": 0.9, + "learning_rate": 1.3989569752281618e-05, + "loss": 0.4393, + "step": 11064 + }, + { + "epoch": 0.9, + "learning_rate": 1.3989026510212953e-05, + "loss": 0.2741, + "step": 11065 + }, + { + "epoch": 0.9, + "learning_rate": 1.3988483268144287e-05, + "loss": 0.3825, + "step": 11066 + }, + { + "epoch": 0.9, + "learning_rate": 1.3987940026075621e-05, + "loss": 0.4173, + "step": 11067 + }, + { + "epoch": 0.9, + "learning_rate": 1.3987396784006955e-05, + "loss": 0.3903, + "step": 11068 + }, + { + "epoch": 0.9, + "learning_rate": 1.3986853541938288e-05, + "loss": 0.371, + "step": 11069 + }, + { + "epoch": 0.9, + "learning_rate": 1.3986310299869624e-05, + "loss": 0.6088, + "step": 11070 + }, + { + "epoch": 0.9, + "learning_rate": 1.3985767057800956e-05, + "loss": 0.5199, + "step": 11071 + }, + { + "epoch": 0.9, + "learning_rate": 1.3985223815732292e-05, + "loss": 0.3459, + "step": 11072 + }, + { + "epoch": 0.9, + "learning_rate": 1.3984680573663625e-05, + "loss": 0.4761, + "step": 11073 + }, + { + "epoch": 0.9, + "learning_rate": 1.398413733159496e-05, + "loss": 0.4865, + "step": 11074 + }, + { + "epoch": 0.9, + "learning_rate": 1.3983594089526293e-05, + "loss": 0.5948, + "step": 11075 + }, + { + "epoch": 0.9, + "learning_rate": 1.3983050847457629e-05, + "loss": 0.4398, + "step": 11076 + }, + { + "epoch": 0.9, + "learning_rate": 1.3982507605388962e-05, + "loss": 0.4419, + "step": 11077 + }, + { + "epoch": 0.9, + "learning_rate": 1.3981964363320298e-05, + "loss": 0.3639, + "step": 11078 + }, + { + "epoch": 0.9, + "learning_rate": 1.398142112125163e-05, + "loss": 0.4893, + "step": 11079 + }, + { + "epoch": 0.9, + "learning_rate": 1.3980877879182966e-05, + "loss": 0.5844, + "step": 11080 + }, + { + "epoch": 0.9, + "learning_rate": 1.3980334637114299e-05, + "loss": 0.2884, + "step": 11081 + }, + { + "epoch": 0.9, + "learning_rate": 1.3979791395045635e-05, + "loss": 0.3372, + "step": 11082 + }, + { + "epoch": 0.9, + "learning_rate": 1.3979248152976967e-05, + "loss": 0.3698, + "step": 11083 + }, + { + "epoch": 0.9, + "learning_rate": 1.3978704910908303e-05, + "loss": 0.2834, + "step": 11084 + }, + { + "epoch": 0.9, + "learning_rate": 1.3978161668839636e-05, + "loss": 0.5543, + "step": 11085 + }, + { + "epoch": 0.9, + "learning_rate": 1.3977618426770971e-05, + "loss": 0.3787, + "step": 11086 + }, + { + "epoch": 0.9, + "learning_rate": 1.3977075184702304e-05, + "loss": 0.2467, + "step": 11087 + }, + { + "epoch": 0.9, + "learning_rate": 1.3976531942633638e-05, + "loss": 0.3385, + "step": 11088 + }, + { + "epoch": 0.9, + "learning_rate": 1.3975988700564972e-05, + "loss": 0.3902, + "step": 11089 + }, + { + "epoch": 0.9, + "learning_rate": 1.3975445458496307e-05, + "loss": 0.7172, + "step": 11090 + }, + { + "epoch": 0.9, + "learning_rate": 1.3974902216427641e-05, + "loss": 0.4961, + "step": 11091 + }, + { + "epoch": 0.9, + "learning_rate": 1.3974358974358975e-05, + "loss": 0.398, + "step": 11092 + }, + { + "epoch": 0.9, + "learning_rate": 1.397381573229031e-05, + "loss": 0.5453, + "step": 11093 + }, + { + "epoch": 0.9, + "learning_rate": 1.3973272490221644e-05, + "loss": 0.4096, + "step": 11094 + }, + { + "epoch": 0.9, + "learning_rate": 1.3972729248152978e-05, + "loss": 0.4828, + "step": 11095 + }, + { + "epoch": 0.9, + "learning_rate": 1.3972186006084312e-05, + "loss": 0.6078, + "step": 11096 + }, + { + "epoch": 0.9, + "learning_rate": 1.3971642764015646e-05, + "loss": 0.5621, + "step": 11097 + }, + { + "epoch": 0.9, + "learning_rate": 1.397109952194698e-05, + "loss": 0.8701, + "step": 11098 + }, + { + "epoch": 0.9, + "learning_rate": 1.3970556279878316e-05, + "loss": 0.4102, + "step": 11099 + }, + { + "epoch": 0.9, + "learning_rate": 1.3970013037809649e-05, + "loss": 0.3789, + "step": 11100 + }, + { + "epoch": 0.9, + "learning_rate": 1.3969469795740985e-05, + "loss": 0.3828, + "step": 11101 + }, + { + "epoch": 0.9, + "learning_rate": 1.3968926553672317e-05, + "loss": 0.3302, + "step": 11102 + }, + { + "epoch": 0.9, + "learning_rate": 1.3968383311603653e-05, + "loss": 0.4459, + "step": 11103 + }, + { + "epoch": 0.9, + "learning_rate": 1.3967840069534986e-05, + "loss": 0.2073, + "step": 11104 + }, + { + "epoch": 0.9, + "learning_rate": 1.3967296827466322e-05, + "loss": 0.4112, + "step": 11105 + }, + { + "epoch": 0.9, + "learning_rate": 1.3966753585397654e-05, + "loss": 0.3156, + "step": 11106 + }, + { + "epoch": 0.91, + "learning_rate": 1.3966210343328987e-05, + "loss": 0.4315, + "step": 11107 + }, + { + "epoch": 0.91, + "learning_rate": 1.3965667101260323e-05, + "loss": 0.6971, + "step": 11108 + }, + { + "epoch": 0.91, + "learning_rate": 1.3965123859191655e-05, + "loss": 0.5295, + "step": 11109 + }, + { + "epoch": 0.91, + "learning_rate": 1.3964580617122991e-05, + "loss": 0.3664, + "step": 11110 + }, + { + "epoch": 0.91, + "learning_rate": 1.3964037375054324e-05, + "loss": 0.3686, + "step": 11111 + }, + { + "epoch": 0.91, + "learning_rate": 1.396349413298566e-05, + "loss": 0.4487, + "step": 11112 + }, + { + "epoch": 0.91, + "learning_rate": 1.3962950890916992e-05, + "loss": 0.4079, + "step": 11113 + }, + { + "epoch": 0.91, + "learning_rate": 1.3962407648848328e-05, + "loss": 0.6018, + "step": 11114 + }, + { + "epoch": 0.91, + "learning_rate": 1.3961864406779662e-05, + "loss": 0.5294, + "step": 11115 + }, + { + "epoch": 0.91, + "learning_rate": 1.3961321164710997e-05, + "loss": 0.3918, + "step": 11116 + }, + { + "epoch": 0.91, + "learning_rate": 1.3960777922642331e-05, + "loss": 0.6402, + "step": 11117 + }, + { + "epoch": 0.91, + "learning_rate": 1.3960234680573665e-05, + "loss": 0.3087, + "step": 11118 + }, + { + "epoch": 0.91, + "learning_rate": 1.3959691438505e-05, + "loss": 0.3606, + "step": 11119 + }, + { + "epoch": 0.91, + "learning_rate": 1.3959148196436334e-05, + "loss": 0.4251, + "step": 11120 + }, + { + "epoch": 0.91, + "learning_rate": 1.3958604954367668e-05, + "loss": 0.4773, + "step": 11121 + }, + { + "epoch": 0.91, + "learning_rate": 1.3958061712299002e-05, + "loss": 0.5078, + "step": 11122 + }, + { + "epoch": 0.91, + "learning_rate": 1.3957518470230336e-05, + "loss": 0.5625, + "step": 11123 + }, + { + "epoch": 0.91, + "learning_rate": 1.395697522816167e-05, + "loss": 0.4461, + "step": 11124 + }, + { + "epoch": 0.91, + "learning_rate": 1.3956431986093005e-05, + "loss": 0.5213, + "step": 11125 + }, + { + "epoch": 0.91, + "learning_rate": 1.3955888744024337e-05, + "loss": 0.4272, + "step": 11126 + }, + { + "epoch": 0.91, + "learning_rate": 1.3955345501955673e-05, + "loss": 0.3757, + "step": 11127 + }, + { + "epoch": 0.91, + "learning_rate": 1.3954802259887006e-05, + "loss": 0.3801, + "step": 11128 + }, + { + "epoch": 0.91, + "learning_rate": 1.3954259017818342e-05, + "loss": 0.5114, + "step": 11129 + }, + { + "epoch": 0.91, + "learning_rate": 1.3953715775749674e-05, + "loss": 0.3661, + "step": 11130 + }, + { + "epoch": 0.91, + "learning_rate": 1.395317253368101e-05, + "loss": 0.7656, + "step": 11131 + }, + { + "epoch": 0.91, + "learning_rate": 1.3952629291612343e-05, + "loss": 0.3136, + "step": 11132 + }, + { + "epoch": 0.91, + "learning_rate": 1.3952086049543679e-05, + "loss": 0.2998, + "step": 11133 + }, + { + "epoch": 0.91, + "learning_rate": 1.3951542807475011e-05, + "loss": 0.4709, + "step": 11134 + }, + { + "epoch": 0.91, + "learning_rate": 1.3950999565406347e-05, + "loss": 0.3906, + "step": 11135 + }, + { + "epoch": 0.91, + "learning_rate": 1.395045632333768e-05, + "loss": 0.318, + "step": 11136 + }, + { + "epoch": 0.91, + "learning_rate": 1.3949913081269016e-05, + "loss": 0.411, + "step": 11137 + }, + { + "epoch": 0.91, + "learning_rate": 1.3949369839200348e-05, + "loss": 0.6076, + "step": 11138 + }, + { + "epoch": 0.91, + "learning_rate": 1.3948826597131684e-05, + "loss": 0.4718, + "step": 11139 + }, + { + "epoch": 0.91, + "learning_rate": 1.3948283355063017e-05, + "loss": 0.4102, + "step": 11140 + }, + { + "epoch": 0.91, + "learning_rate": 1.3947740112994352e-05, + "loss": 0.4178, + "step": 11141 + }, + { + "epoch": 0.91, + "learning_rate": 1.3947196870925685e-05, + "loss": 0.4527, + "step": 11142 + }, + { + "epoch": 0.91, + "learning_rate": 1.3946653628857021e-05, + "loss": 0.5006, + "step": 11143 + }, + { + "epoch": 0.91, + "learning_rate": 1.3946110386788353e-05, + "loss": 0.475, + "step": 11144 + }, + { + "epoch": 0.91, + "learning_rate": 1.3945567144719688e-05, + "loss": 0.2649, + "step": 11145 + }, + { + "epoch": 0.91, + "learning_rate": 1.3945023902651022e-05, + "loss": 0.4188, + "step": 11146 + }, + { + "epoch": 0.91, + "learning_rate": 1.3944480660582356e-05, + "loss": 0.3617, + "step": 11147 + }, + { + "epoch": 0.91, + "learning_rate": 1.394393741851369e-05, + "loss": 0.4953, + "step": 11148 + }, + { + "epoch": 0.91, + "learning_rate": 1.3943394176445025e-05, + "loss": 0.5086, + "step": 11149 + }, + { + "epoch": 0.91, + "learning_rate": 1.3942850934376359e-05, + "loss": 0.5073, + "step": 11150 + }, + { + "epoch": 0.91, + "learning_rate": 1.3942307692307693e-05, + "loss": 0.2647, + "step": 11151 + }, + { + "epoch": 0.91, + "learning_rate": 1.3941764450239029e-05, + "loss": 0.6159, + "step": 11152 + }, + { + "epoch": 0.91, + "learning_rate": 1.3941221208170362e-05, + "loss": 0.2932, + "step": 11153 + }, + { + "epoch": 0.91, + "learning_rate": 1.3940677966101697e-05, + "loss": 0.4729, + "step": 11154 + }, + { + "epoch": 0.91, + "learning_rate": 1.394013472403303e-05, + "loss": 0.4717, + "step": 11155 + }, + { + "epoch": 0.91, + "learning_rate": 1.3939591481964366e-05, + "loss": 0.5651, + "step": 11156 + }, + { + "epoch": 0.91, + "learning_rate": 1.3939048239895698e-05, + "loss": 0.3691, + "step": 11157 + }, + { + "epoch": 0.91, + "learning_rate": 1.3938504997827034e-05, + "loss": 0.2992, + "step": 11158 + }, + { + "epoch": 0.91, + "learning_rate": 1.3937961755758367e-05, + "loss": 0.663, + "step": 11159 + }, + { + "epoch": 0.91, + "learning_rate": 1.3937418513689703e-05, + "loss": 0.3973, + "step": 11160 + }, + { + "epoch": 0.91, + "learning_rate": 1.3936875271621035e-05, + "loss": 0.1726, + "step": 11161 + }, + { + "epoch": 0.91, + "learning_rate": 1.3936332029552371e-05, + "loss": 0.2579, + "step": 11162 + }, + { + "epoch": 0.91, + "learning_rate": 1.3935788787483704e-05, + "loss": 0.6018, + "step": 11163 + }, + { + "epoch": 0.91, + "learning_rate": 1.3935245545415036e-05, + "loss": 0.2839, + "step": 11164 + }, + { + "epoch": 0.91, + "learning_rate": 1.3934702303346372e-05, + "loss": 0.4876, + "step": 11165 + }, + { + "epoch": 0.91, + "learning_rate": 1.3934159061277705e-05, + "loss": 0.605, + "step": 11166 + }, + { + "epoch": 0.91, + "learning_rate": 1.393361581920904e-05, + "loss": 0.4523, + "step": 11167 + }, + { + "epoch": 0.91, + "learning_rate": 1.3933072577140373e-05, + "loss": 0.5761, + "step": 11168 + }, + { + "epoch": 0.91, + "learning_rate": 1.393252933507171e-05, + "loss": 0.5855, + "step": 11169 + }, + { + "epoch": 0.91, + "learning_rate": 1.3931986093003043e-05, + "loss": 0.4882, + "step": 11170 + }, + { + "epoch": 0.91, + "learning_rate": 1.3931442850934378e-05, + "loss": 0.2219, + "step": 11171 + }, + { + "epoch": 0.91, + "learning_rate": 1.3930899608865712e-05, + "loss": 0.395, + "step": 11172 + }, + { + "epoch": 0.91, + "learning_rate": 1.3930356366797046e-05, + "loss": 0.3205, + "step": 11173 + }, + { + "epoch": 0.91, + "learning_rate": 1.392981312472838e-05, + "loss": 0.6419, + "step": 11174 + }, + { + "epoch": 0.91, + "learning_rate": 1.3929269882659715e-05, + "loss": 0.3388, + "step": 11175 + }, + { + "epoch": 0.91, + "learning_rate": 1.3928726640591049e-05, + "loss": 0.5281, + "step": 11176 + }, + { + "epoch": 0.91, + "learning_rate": 1.3928183398522383e-05, + "loss": 0.2376, + "step": 11177 + }, + { + "epoch": 0.91, + "learning_rate": 1.3927640156453717e-05, + "loss": 0.3768, + "step": 11178 + }, + { + "epoch": 0.91, + "learning_rate": 1.3927096914385051e-05, + "loss": 0.4483, + "step": 11179 + }, + { + "epoch": 0.91, + "learning_rate": 1.3926553672316386e-05, + "loss": 0.4989, + "step": 11180 + }, + { + "epoch": 0.91, + "learning_rate": 1.392601043024772e-05, + "loss": 0.4355, + "step": 11181 + }, + { + "epoch": 0.91, + "learning_rate": 1.3925467188179054e-05, + "loss": 0.2851, + "step": 11182 + }, + { + "epoch": 0.91, + "learning_rate": 1.3924923946110387e-05, + "loss": 0.1887, + "step": 11183 + }, + { + "epoch": 0.91, + "learning_rate": 1.3924380704041723e-05, + "loss": 0.3328, + "step": 11184 + }, + { + "epoch": 0.91, + "learning_rate": 1.3923837461973055e-05, + "loss": 0.335, + "step": 11185 + }, + { + "epoch": 0.91, + "learning_rate": 1.3923294219904391e-05, + "loss": 0.555, + "step": 11186 + }, + { + "epoch": 0.91, + "learning_rate": 1.3922750977835724e-05, + "loss": 0.1782, + "step": 11187 + }, + { + "epoch": 0.91, + "learning_rate": 1.392220773576706e-05, + "loss": 0.6365, + "step": 11188 + }, + { + "epoch": 0.91, + "learning_rate": 1.3921664493698392e-05, + "loss": 0.5784, + "step": 11189 + }, + { + "epoch": 0.91, + "learning_rate": 1.3921121251629728e-05, + "loss": 0.4956, + "step": 11190 + }, + { + "epoch": 0.91, + "learning_rate": 1.392057800956106e-05, + "loss": 0.373, + "step": 11191 + }, + { + "epoch": 0.91, + "learning_rate": 1.3920034767492396e-05, + "loss": 0.4384, + "step": 11192 + }, + { + "epoch": 0.91, + "learning_rate": 1.3919491525423729e-05, + "loss": 0.4016, + "step": 11193 + }, + { + "epoch": 0.91, + "learning_rate": 1.3918948283355065e-05, + "loss": 0.4601, + "step": 11194 + }, + { + "epoch": 0.91, + "learning_rate": 1.3918405041286397e-05, + "loss": 0.4674, + "step": 11195 + }, + { + "epoch": 0.91, + "learning_rate": 1.3917861799217733e-05, + "loss": 0.73, + "step": 11196 + }, + { + "epoch": 0.91, + "learning_rate": 1.3917318557149066e-05, + "loss": 0.3297, + "step": 11197 + }, + { + "epoch": 0.91, + "learning_rate": 1.3916775315080402e-05, + "loss": 0.5181, + "step": 11198 + }, + { + "epoch": 0.91, + "learning_rate": 1.3916232073011734e-05, + "loss": 0.3347, + "step": 11199 + }, + { + "epoch": 0.91, + "learning_rate": 1.391568883094307e-05, + "loss": 0.2839, + "step": 11200 + }, + { + "epoch": 0.91, + "learning_rate": 1.3915145588874403e-05, + "loss": 0.4832, + "step": 11201 + }, + { + "epoch": 0.91, + "learning_rate": 1.3914602346805737e-05, + "loss": 0.6353, + "step": 11202 + }, + { + "epoch": 0.91, + "learning_rate": 1.3914059104737071e-05, + "loss": 0.6013, + "step": 11203 + }, + { + "epoch": 0.91, + "learning_rate": 1.3913515862668406e-05, + "loss": 0.27, + "step": 11204 + }, + { + "epoch": 0.91, + "learning_rate": 1.391297262059974e-05, + "loss": 0.3854, + "step": 11205 + }, + { + "epoch": 0.91, + "learning_rate": 1.3912429378531074e-05, + "loss": 0.1951, + "step": 11206 + }, + { + "epoch": 0.91, + "learning_rate": 1.391188613646241e-05, + "loss": 0.2967, + "step": 11207 + }, + { + "epoch": 0.91, + "learning_rate": 1.3911342894393742e-05, + "loss": 0.4615, + "step": 11208 + }, + { + "epoch": 0.91, + "learning_rate": 1.3910799652325078e-05, + "loss": 0.342, + "step": 11209 + }, + { + "epoch": 0.91, + "learning_rate": 1.3910256410256411e-05, + "loss": 0.3032, + "step": 11210 + }, + { + "epoch": 0.91, + "learning_rate": 1.3909713168187747e-05, + "loss": 0.787, + "step": 11211 + }, + { + "epoch": 0.91, + "learning_rate": 1.390916992611908e-05, + "loss": 0.3697, + "step": 11212 + }, + { + "epoch": 0.91, + "learning_rate": 1.3908626684050415e-05, + "loss": 0.5616, + "step": 11213 + }, + { + "epoch": 0.91, + "learning_rate": 1.3908083441981748e-05, + "loss": 0.4676, + "step": 11214 + }, + { + "epoch": 0.91, + "learning_rate": 1.3907540199913084e-05, + "loss": 0.3674, + "step": 11215 + }, + { + "epoch": 0.91, + "learning_rate": 1.3906996957844416e-05, + "loss": 0.3646, + "step": 11216 + }, + { + "epoch": 0.91, + "learning_rate": 1.3906453715775752e-05, + "loss": 0.4959, + "step": 11217 + }, + { + "epoch": 0.91, + "learning_rate": 1.3905910473707085e-05, + "loss": 0.5824, + "step": 11218 + }, + { + "epoch": 0.91, + "learning_rate": 1.390536723163842e-05, + "loss": 0.4457, + "step": 11219 + }, + { + "epoch": 0.91, + "learning_rate": 1.3904823989569753e-05, + "loss": 0.3214, + "step": 11220 + }, + { + "epoch": 0.91, + "learning_rate": 1.3904280747501086e-05, + "loss": 0.4099, + "step": 11221 + }, + { + "epoch": 0.91, + "learning_rate": 1.3903737505432422e-05, + "loss": 0.7166, + "step": 11222 + }, + { + "epoch": 0.91, + "learning_rate": 1.3903194263363756e-05, + "loss": 0.3433, + "step": 11223 + }, + { + "epoch": 0.91, + "learning_rate": 1.390265102129509e-05, + "loss": 0.2323, + "step": 11224 + }, + { + "epoch": 0.91, + "learning_rate": 1.3902107779226424e-05, + "loss": 0.4767, + "step": 11225 + }, + { + "epoch": 0.91, + "learning_rate": 1.3901564537157759e-05, + "loss": 0.3062, + "step": 11226 + }, + { + "epoch": 0.91, + "learning_rate": 1.3901021295089093e-05, + "loss": 0.43, + "step": 11227 + }, + { + "epoch": 0.91, + "learning_rate": 1.3900478053020427e-05, + "loss": 0.4159, + "step": 11228 + }, + { + "epoch": 0.92, + "learning_rate": 1.3899934810951761e-05, + "loss": 0.6013, + "step": 11229 + }, + { + "epoch": 0.92, + "learning_rate": 1.3899391568883096e-05, + "loss": 0.7945, + "step": 11230 + }, + { + "epoch": 0.92, + "learning_rate": 1.389884832681443e-05, + "loss": 0.2908, + "step": 11231 + }, + { + "epoch": 0.92, + "learning_rate": 1.3898305084745764e-05, + "loss": 0.566, + "step": 11232 + }, + { + "epoch": 0.92, + "learning_rate": 1.3897761842677098e-05, + "loss": 0.4906, + "step": 11233 + }, + { + "epoch": 0.92, + "learning_rate": 1.3897218600608432e-05, + "loss": 0.2086, + "step": 11234 + }, + { + "epoch": 0.92, + "learning_rate": 1.3896675358539767e-05, + "loss": 0.4752, + "step": 11235 + }, + { + "epoch": 0.92, + "learning_rate": 1.3896132116471101e-05, + "loss": 0.8725, + "step": 11236 + }, + { + "epoch": 0.92, + "learning_rate": 1.3895588874402435e-05, + "loss": 0.4481, + "step": 11237 + }, + { + "epoch": 0.92, + "learning_rate": 1.389504563233377e-05, + "loss": 0.366, + "step": 11238 + }, + { + "epoch": 0.92, + "learning_rate": 1.3894502390265104e-05, + "loss": 0.672, + "step": 11239 + }, + { + "epoch": 0.92, + "learning_rate": 1.3893959148196436e-05, + "loss": 0.4874, + "step": 11240 + }, + { + "epoch": 0.92, + "learning_rate": 1.3893415906127772e-05, + "loss": 0.5952, + "step": 11241 + }, + { + "epoch": 0.92, + "learning_rate": 1.3892872664059105e-05, + "loss": 0.5081, + "step": 11242 + }, + { + "epoch": 0.92, + "learning_rate": 1.389232942199044e-05, + "loss": 0.5175, + "step": 11243 + }, + { + "epoch": 0.92, + "learning_rate": 1.3891786179921773e-05, + "loss": 0.7988, + "step": 11244 + }, + { + "epoch": 0.92, + "learning_rate": 1.3891242937853109e-05, + "loss": 0.4647, + "step": 11245 + }, + { + "epoch": 0.92, + "learning_rate": 1.3890699695784442e-05, + "loss": 0.5309, + "step": 11246 + }, + { + "epoch": 0.92, + "learning_rate": 1.3890156453715777e-05, + "loss": 0.4744, + "step": 11247 + }, + { + "epoch": 0.92, + "learning_rate": 1.388961321164711e-05, + "loss": 0.3009, + "step": 11248 + }, + { + "epoch": 0.92, + "learning_rate": 1.3889069969578446e-05, + "loss": 0.384, + "step": 11249 + }, + { + "epoch": 0.92, + "learning_rate": 1.3888526727509778e-05, + "loss": 0.5898, + "step": 11250 + }, + { + "epoch": 0.92, + "eval_accuracy": 0.8357615894039735, + "eval_loss": 0.42911040782928467, + "eval_runtime": 22.3014, + "eval_samples_per_second": 440.108, + "eval_steps_per_second": 3.453, + "step": 11250 + }, + { + "epoch": 0.92, + "learning_rate": 1.3887983485441114e-05, + "loss": 0.2088, + "step": 11251 + }, + { + "epoch": 0.92, + "learning_rate": 1.3887440243372447e-05, + "loss": 0.7464, + "step": 11252 + }, + { + "epoch": 0.92, + "learning_rate": 1.3886897001303783e-05, + "loss": 0.3697, + "step": 11253 + }, + { + "epoch": 0.92, + "learning_rate": 1.3886353759235115e-05, + "loss": 0.3356, + "step": 11254 + }, + { + "epoch": 0.92, + "learning_rate": 1.3885810517166451e-05, + "loss": 0.5528, + "step": 11255 + }, + { + "epoch": 0.92, + "learning_rate": 1.3885267275097784e-05, + "loss": 0.5375, + "step": 11256 + }, + { + "epoch": 0.92, + "learning_rate": 1.388472403302912e-05, + "loss": 0.3919, + "step": 11257 + }, + { + "epoch": 0.92, + "learning_rate": 1.3884180790960452e-05, + "loss": 0.3476, + "step": 11258 + }, + { + "epoch": 0.92, + "learning_rate": 1.3883637548891787e-05, + "loss": 0.3615, + "step": 11259 + }, + { + "epoch": 0.92, + "learning_rate": 1.3883094306823122e-05, + "loss": 0.3595, + "step": 11260 + }, + { + "epoch": 0.92, + "learning_rate": 1.3882551064754455e-05, + "loss": 0.7536, + "step": 11261 + }, + { + "epoch": 0.92, + "learning_rate": 1.3882007822685791e-05, + "loss": 0.719, + "step": 11262 + }, + { + "epoch": 0.92, + "learning_rate": 1.3881464580617123e-05, + "loss": 0.4919, + "step": 11263 + }, + { + "epoch": 0.92, + "learning_rate": 1.388092133854846e-05, + "loss": 0.7138, + "step": 11264 + }, + { + "epoch": 0.92, + "learning_rate": 1.3880378096479792e-05, + "loss": 0.5757, + "step": 11265 + }, + { + "epoch": 0.92, + "learning_rate": 1.3879834854411128e-05, + "loss": 0.4991, + "step": 11266 + }, + { + "epoch": 0.92, + "learning_rate": 1.387929161234246e-05, + "loss": 0.5442, + "step": 11267 + }, + { + "epoch": 0.92, + "learning_rate": 1.3878748370273796e-05, + "loss": 0.4268, + "step": 11268 + }, + { + "epoch": 0.92, + "learning_rate": 1.3878205128205129e-05, + "loss": 0.408, + "step": 11269 + }, + { + "epoch": 0.92, + "learning_rate": 1.3877661886136465e-05, + "loss": 0.6985, + "step": 11270 + }, + { + "epoch": 0.92, + "learning_rate": 1.3877118644067797e-05, + "loss": 0.5505, + "step": 11271 + }, + { + "epoch": 0.92, + "learning_rate": 1.3876575401999133e-05, + "loss": 0.6115, + "step": 11272 + }, + { + "epoch": 0.92, + "learning_rate": 1.3876032159930466e-05, + "loss": 0.4134, + "step": 11273 + }, + { + "epoch": 0.92, + "learning_rate": 1.3875488917861802e-05, + "loss": 0.2613, + "step": 11274 + }, + { + "epoch": 0.92, + "learning_rate": 1.3874945675793134e-05, + "loss": 0.3824, + "step": 11275 + }, + { + "epoch": 0.92, + "learning_rate": 1.387440243372447e-05, + "loss": 0.3959, + "step": 11276 + }, + { + "epoch": 0.92, + "learning_rate": 1.3873859191655803e-05, + "loss": 0.3985, + "step": 11277 + }, + { + "epoch": 0.92, + "learning_rate": 1.3873315949587137e-05, + "loss": 0.3681, + "step": 11278 + }, + { + "epoch": 0.92, + "learning_rate": 1.3872772707518471e-05, + "loss": 0.4206, + "step": 11279 + }, + { + "epoch": 0.92, + "learning_rate": 1.3872229465449805e-05, + "loss": 0.4875, + "step": 11280 + }, + { + "epoch": 0.92, + "learning_rate": 1.387168622338114e-05, + "loss": 0.2978, + "step": 11281 + }, + { + "epoch": 0.92, + "learning_rate": 1.3871142981312474e-05, + "loss": 0.2676, + "step": 11282 + }, + { + "epoch": 0.92, + "learning_rate": 1.3870599739243808e-05, + "loss": 0.4128, + "step": 11283 + }, + { + "epoch": 0.92, + "learning_rate": 1.3870056497175142e-05, + "loss": 0.6449, + "step": 11284 + }, + { + "epoch": 0.92, + "learning_rate": 1.3869513255106477e-05, + "loss": 0.5529, + "step": 11285 + }, + { + "epoch": 0.92, + "learning_rate": 1.386897001303781e-05, + "loss": 0.4086, + "step": 11286 + }, + { + "epoch": 0.92, + "learning_rate": 1.3868426770969145e-05, + "loss": 0.2804, + "step": 11287 + }, + { + "epoch": 0.92, + "learning_rate": 1.386788352890048e-05, + "loss": 0.5123, + "step": 11288 + }, + { + "epoch": 0.92, + "learning_rate": 1.3867340286831813e-05, + "loss": 0.4455, + "step": 11289 + }, + { + "epoch": 0.92, + "learning_rate": 1.3866797044763148e-05, + "loss": 0.3613, + "step": 11290 + }, + { + "epoch": 0.92, + "learning_rate": 1.3866253802694482e-05, + "loss": 0.2888, + "step": 11291 + }, + { + "epoch": 0.92, + "learning_rate": 1.3865710560625816e-05, + "loss": 0.7016, + "step": 11292 + }, + { + "epoch": 0.92, + "learning_rate": 1.386516731855715e-05, + "loss": 0.4967, + "step": 11293 + }, + { + "epoch": 0.92, + "learning_rate": 1.3864624076488485e-05, + "loss": 0.3712, + "step": 11294 + }, + { + "epoch": 0.92, + "learning_rate": 1.3864080834419819e-05, + "loss": 0.4519, + "step": 11295 + }, + { + "epoch": 0.92, + "learning_rate": 1.3863537592351153e-05, + "loss": 0.3213, + "step": 11296 + }, + { + "epoch": 0.92, + "learning_rate": 1.3862994350282486e-05, + "loss": 0.4762, + "step": 11297 + }, + { + "epoch": 0.92, + "learning_rate": 1.3862451108213822e-05, + "loss": 0.2765, + "step": 11298 + }, + { + "epoch": 0.92, + "learning_rate": 1.3861907866145154e-05, + "loss": 0.5697, + "step": 11299 + }, + { + "epoch": 0.92, + "learning_rate": 1.386136462407649e-05, + "loss": 0.5202, + "step": 11300 + }, + { + "epoch": 0.92, + "learning_rate": 1.3860821382007823e-05, + "loss": 0.5437, + "step": 11301 + }, + { + "epoch": 0.92, + "learning_rate": 1.3860278139939158e-05, + "loss": 0.3592, + "step": 11302 + }, + { + "epoch": 0.92, + "learning_rate": 1.3859734897870491e-05, + "loss": 0.5557, + "step": 11303 + }, + { + "epoch": 0.92, + "learning_rate": 1.3859191655801827e-05, + "loss": 0.4611, + "step": 11304 + }, + { + "epoch": 0.92, + "learning_rate": 1.385864841373316e-05, + "loss": 0.4507, + "step": 11305 + }, + { + "epoch": 0.92, + "learning_rate": 1.3858105171664495e-05, + "loss": 0.4383, + "step": 11306 + }, + { + "epoch": 0.92, + "learning_rate": 1.3857561929595828e-05, + "loss": 0.5921, + "step": 11307 + }, + { + "epoch": 0.92, + "learning_rate": 1.3857018687527164e-05, + "loss": 0.5086, + "step": 11308 + }, + { + "epoch": 0.92, + "learning_rate": 1.3856475445458496e-05, + "loss": 0.4675, + "step": 11309 + }, + { + "epoch": 0.92, + "learning_rate": 1.3855932203389832e-05, + "loss": 0.398, + "step": 11310 + }, + { + "epoch": 0.92, + "learning_rate": 1.3855388961321165e-05, + "loss": 0.367, + "step": 11311 + }, + { + "epoch": 0.92, + "learning_rate": 1.38548457192525e-05, + "loss": 0.514, + "step": 11312 + }, + { + "epoch": 0.92, + "learning_rate": 1.3854302477183833e-05, + "loss": 0.6592, + "step": 11313 + }, + { + "epoch": 0.92, + "learning_rate": 1.385375923511517e-05, + "loss": 0.7026, + "step": 11314 + }, + { + "epoch": 0.92, + "learning_rate": 1.3853215993046503e-05, + "loss": 0.6648, + "step": 11315 + }, + { + "epoch": 0.92, + "learning_rate": 1.3852672750977836e-05, + "loss": 0.3922, + "step": 11316 + }, + { + "epoch": 0.92, + "learning_rate": 1.3852129508909172e-05, + "loss": 0.1863, + "step": 11317 + }, + { + "epoch": 0.92, + "learning_rate": 1.3851586266840504e-05, + "loss": 0.4162, + "step": 11318 + }, + { + "epoch": 0.92, + "learning_rate": 1.385104302477184e-05, + "loss": 0.3811, + "step": 11319 + }, + { + "epoch": 0.92, + "learning_rate": 1.3850499782703173e-05, + "loss": 0.3161, + "step": 11320 + }, + { + "epoch": 0.92, + "learning_rate": 1.3849956540634509e-05, + "loss": 0.5266, + "step": 11321 + }, + { + "epoch": 0.92, + "learning_rate": 1.3849413298565841e-05, + "loss": 0.5458, + "step": 11322 + }, + { + "epoch": 0.92, + "learning_rate": 1.3848870056497177e-05, + "loss": 0.6309, + "step": 11323 + }, + { + "epoch": 0.92, + "learning_rate": 1.384832681442851e-05, + "loss": 0.3879, + "step": 11324 + }, + { + "epoch": 0.92, + "learning_rate": 1.3847783572359846e-05, + "loss": 0.3894, + "step": 11325 + }, + { + "epoch": 0.92, + "learning_rate": 1.3847240330291178e-05, + "loss": 0.2631, + "step": 11326 + }, + { + "epoch": 0.92, + "learning_rate": 1.3846697088222514e-05, + "loss": 0.6065, + "step": 11327 + }, + { + "epoch": 0.92, + "learning_rate": 1.3846153846153847e-05, + "loss": 0.6545, + "step": 11328 + }, + { + "epoch": 0.92, + "learning_rate": 1.3845610604085183e-05, + "loss": 0.6754, + "step": 11329 + }, + { + "epoch": 0.92, + "learning_rate": 1.3845067362016515e-05, + "loss": 0.4773, + "step": 11330 + }, + { + "epoch": 0.92, + "learning_rate": 1.3844524119947851e-05, + "loss": 0.2755, + "step": 11331 + }, + { + "epoch": 0.92, + "learning_rate": 1.3843980877879184e-05, + "loss": 0.2921, + "step": 11332 + }, + { + "epoch": 0.92, + "learning_rate": 1.384343763581052e-05, + "loss": 0.5396, + "step": 11333 + }, + { + "epoch": 0.92, + "learning_rate": 1.3842894393741852e-05, + "loss": 0.234, + "step": 11334 + }, + { + "epoch": 0.92, + "learning_rate": 1.3842351151673186e-05, + "loss": 0.72, + "step": 11335 + }, + { + "epoch": 0.92, + "learning_rate": 1.384180790960452e-05, + "loss": 0.4066, + "step": 11336 + }, + { + "epoch": 0.92, + "learning_rate": 1.3841264667535855e-05, + "loss": 0.6494, + "step": 11337 + }, + { + "epoch": 0.92, + "learning_rate": 1.3840721425467189e-05, + "loss": 0.663, + "step": 11338 + }, + { + "epoch": 0.92, + "learning_rate": 1.3840178183398523e-05, + "loss": 0.4286, + "step": 11339 + }, + { + "epoch": 0.92, + "learning_rate": 1.3839634941329858e-05, + "loss": 0.3851, + "step": 11340 + }, + { + "epoch": 0.92, + "learning_rate": 1.3839091699261192e-05, + "loss": 0.5913, + "step": 11341 + }, + { + "epoch": 0.92, + "learning_rate": 1.3838548457192526e-05, + "loss": 0.3915, + "step": 11342 + }, + { + "epoch": 0.92, + "learning_rate": 1.383800521512386e-05, + "loss": 0.514, + "step": 11343 + }, + { + "epoch": 0.92, + "learning_rate": 1.3837461973055194e-05, + "loss": 0.311, + "step": 11344 + }, + { + "epoch": 0.92, + "learning_rate": 1.3836918730986529e-05, + "loss": 0.3305, + "step": 11345 + }, + { + "epoch": 0.92, + "learning_rate": 1.3836375488917863e-05, + "loss": 0.3904, + "step": 11346 + }, + { + "epoch": 0.92, + "learning_rate": 1.3835832246849197e-05, + "loss": 0.5726, + "step": 11347 + }, + { + "epoch": 0.92, + "learning_rate": 1.3835289004780531e-05, + "loss": 0.3781, + "step": 11348 + }, + { + "epoch": 0.92, + "learning_rate": 1.3834745762711866e-05, + "loss": 0.4057, + "step": 11349 + }, + { + "epoch": 0.92, + "learning_rate": 1.38342025206432e-05, + "loss": 0.2214, + "step": 11350 + }, + { + "epoch": 0.92, + "learning_rate": 1.3833659278574534e-05, + "loss": 0.4353, + "step": 11351 + }, + { + "epoch": 0.93, + "learning_rate": 1.383311603650587e-05, + "loss": 0.4876, + "step": 11352 + }, + { + "epoch": 0.93, + "learning_rate": 1.3832572794437203e-05, + "loss": 0.4346, + "step": 11353 + }, + { + "epoch": 0.93, + "learning_rate": 1.3832029552368535e-05, + "loss": 0.3155, + "step": 11354 + }, + { + "epoch": 0.93, + "learning_rate": 1.3831486310299871e-05, + "loss": 0.6427, + "step": 11355 + }, + { + "epoch": 0.93, + "learning_rate": 1.3830943068231204e-05, + "loss": 0.4037, + "step": 11356 + }, + { + "epoch": 0.93, + "learning_rate": 1.383039982616254e-05, + "loss": 0.5763, + "step": 11357 + }, + { + "epoch": 0.93, + "learning_rate": 1.3829856584093872e-05, + "loss": 0.2584, + "step": 11358 + }, + { + "epoch": 0.93, + "learning_rate": 1.3829313342025208e-05, + "loss": 0.3607, + "step": 11359 + }, + { + "epoch": 0.93, + "learning_rate": 1.382877009995654e-05, + "loss": 0.3452, + "step": 11360 + }, + { + "epoch": 0.93, + "learning_rate": 1.3828226857887876e-05, + "loss": 0.6611, + "step": 11361 + }, + { + "epoch": 0.93, + "learning_rate": 1.3827683615819209e-05, + "loss": 0.2657, + "step": 11362 + }, + { + "epoch": 0.93, + "learning_rate": 1.3827140373750545e-05, + "loss": 0.2681, + "step": 11363 + }, + { + "epoch": 0.93, + "learning_rate": 1.3826597131681877e-05, + "loss": 0.5213, + "step": 11364 + }, + { + "epoch": 0.93, + "learning_rate": 1.3826053889613213e-05, + "loss": 0.5168, + "step": 11365 + }, + { + "epoch": 0.93, + "learning_rate": 1.3825510647544546e-05, + "loss": 0.4421, + "step": 11366 + }, + { + "epoch": 0.93, + "learning_rate": 1.3824967405475882e-05, + "loss": 0.5908, + "step": 11367 + }, + { + "epoch": 0.93, + "learning_rate": 1.3824424163407216e-05, + "loss": 0.6402, + "step": 11368 + }, + { + "epoch": 0.93, + "learning_rate": 1.382388092133855e-05, + "loss": 0.2063, + "step": 11369 + }, + { + "epoch": 0.93, + "learning_rate": 1.3823337679269884e-05, + "loss": 0.4674, + "step": 11370 + }, + { + "epoch": 0.93, + "learning_rate": 1.3822794437201219e-05, + "loss": 0.4084, + "step": 11371 + }, + { + "epoch": 0.93, + "learning_rate": 1.3822251195132553e-05, + "loss": 0.2488, + "step": 11372 + }, + { + "epoch": 0.93, + "learning_rate": 1.3821707953063885e-05, + "loss": 0.2659, + "step": 11373 + }, + { + "epoch": 0.93, + "learning_rate": 1.3821164710995221e-05, + "loss": 0.635, + "step": 11374 + }, + { + "epoch": 0.93, + "learning_rate": 1.3820621468926554e-05, + "loss": 0.2906, + "step": 11375 + }, + { + "epoch": 0.93, + "learning_rate": 1.382007822685789e-05, + "loss": 0.4346, + "step": 11376 + }, + { + "epoch": 0.93, + "learning_rate": 1.3819534984789222e-05, + "loss": 0.4871, + "step": 11377 + }, + { + "epoch": 0.93, + "learning_rate": 1.3818991742720558e-05, + "loss": 0.4549, + "step": 11378 + }, + { + "epoch": 0.93, + "learning_rate": 1.381844850065189e-05, + "loss": 0.3844, + "step": 11379 + }, + { + "epoch": 0.93, + "learning_rate": 1.3817905258583227e-05, + "loss": 0.7057, + "step": 11380 + }, + { + "epoch": 0.93, + "learning_rate": 1.381736201651456e-05, + "loss": 0.3674, + "step": 11381 + }, + { + "epoch": 0.93, + "learning_rate": 1.3816818774445895e-05, + "loss": 0.538, + "step": 11382 + }, + { + "epoch": 0.93, + "learning_rate": 1.3816275532377228e-05, + "loss": 0.5392, + "step": 11383 + }, + { + "epoch": 0.93, + "learning_rate": 1.3815732290308564e-05, + "loss": 0.4052, + "step": 11384 + }, + { + "epoch": 0.93, + "learning_rate": 1.3815189048239896e-05, + "loss": 0.4923, + "step": 11385 + }, + { + "epoch": 0.93, + "learning_rate": 1.3814645806171232e-05, + "loss": 0.5176, + "step": 11386 + }, + { + "epoch": 0.93, + "learning_rate": 1.3814102564102565e-05, + "loss": 0.5327, + "step": 11387 + }, + { + "epoch": 0.93, + "learning_rate": 1.38135593220339e-05, + "loss": 0.6432, + "step": 11388 + }, + { + "epoch": 0.93, + "learning_rate": 1.3813016079965233e-05, + "loss": 0.2673, + "step": 11389 + }, + { + "epoch": 0.93, + "learning_rate": 1.3812472837896569e-05, + "loss": 0.285, + "step": 11390 + }, + { + "epoch": 0.93, + "learning_rate": 1.3811929595827902e-05, + "loss": 0.4501, + "step": 11391 + }, + { + "epoch": 0.93, + "learning_rate": 1.3811386353759236e-05, + "loss": 0.7448, + "step": 11392 + }, + { + "epoch": 0.93, + "learning_rate": 1.381084311169057e-05, + "loss": 0.3637, + "step": 11393 + }, + { + "epoch": 0.93, + "learning_rate": 1.3810299869621904e-05, + "loss": 0.3226, + "step": 11394 + }, + { + "epoch": 0.93, + "learning_rate": 1.3809756627553239e-05, + "loss": 0.6525, + "step": 11395 + }, + { + "epoch": 0.93, + "learning_rate": 1.3809213385484573e-05, + "loss": 0.3937, + "step": 11396 + }, + { + "epoch": 0.93, + "learning_rate": 1.3808670143415907e-05, + "loss": 0.1872, + "step": 11397 + }, + { + "epoch": 0.93, + "learning_rate": 1.3808126901347241e-05, + "loss": 0.4861, + "step": 11398 + }, + { + "epoch": 0.93, + "learning_rate": 1.3807583659278575e-05, + "loss": 0.5118, + "step": 11399 + }, + { + "epoch": 0.93, + "learning_rate": 1.380704041720991e-05, + "loss": 0.5143, + "step": 11400 + }, + { + "epoch": 0.93, + "learning_rate": 1.3806497175141244e-05, + "loss": 0.5108, + "step": 11401 + }, + { + "epoch": 0.93, + "learning_rate": 1.3805953933072578e-05, + "loss": 0.2892, + "step": 11402 + }, + { + "epoch": 0.93, + "learning_rate": 1.3805410691003912e-05, + "loss": 0.5162, + "step": 11403 + }, + { + "epoch": 0.93, + "learning_rate": 1.3804867448935247e-05, + "loss": 0.5349, + "step": 11404 + }, + { + "epoch": 0.93, + "learning_rate": 1.3804324206866583e-05, + "loss": 0.3734, + "step": 11405 + }, + { + "epoch": 0.93, + "learning_rate": 1.3803780964797915e-05, + "loss": 0.3554, + "step": 11406 + }, + { + "epoch": 0.93, + "learning_rate": 1.3803237722729251e-05, + "loss": 0.3525, + "step": 11407 + }, + { + "epoch": 0.93, + "learning_rate": 1.3802694480660584e-05, + "loss": 0.5585, + "step": 11408 + }, + { + "epoch": 0.93, + "learning_rate": 1.380215123859192e-05, + "loss": 0.4602, + "step": 11409 + }, + { + "epoch": 0.93, + "learning_rate": 1.3801607996523252e-05, + "loss": 0.7272, + "step": 11410 + }, + { + "epoch": 0.93, + "learning_rate": 1.3801064754454585e-05, + "loss": 0.6744, + "step": 11411 + }, + { + "epoch": 0.93, + "learning_rate": 1.380052151238592e-05, + "loss": 0.4629, + "step": 11412 + }, + { + "epoch": 0.93, + "learning_rate": 1.3799978270317253e-05, + "loss": 0.2953, + "step": 11413 + }, + { + "epoch": 0.93, + "learning_rate": 1.3799435028248589e-05, + "loss": 0.3098, + "step": 11414 + }, + { + "epoch": 0.93, + "learning_rate": 1.3798891786179921e-05, + "loss": 0.3026, + "step": 11415 + }, + { + "epoch": 0.93, + "learning_rate": 1.3798348544111257e-05, + "loss": 0.3649, + "step": 11416 + }, + { + "epoch": 0.93, + "learning_rate": 1.379780530204259e-05, + "loss": 0.4529, + "step": 11417 + }, + { + "epoch": 0.93, + "learning_rate": 1.3797262059973926e-05, + "loss": 0.354, + "step": 11418 + }, + { + "epoch": 0.93, + "learning_rate": 1.3796718817905258e-05, + "loss": 0.3791, + "step": 11419 + }, + { + "epoch": 0.93, + "learning_rate": 1.3796175575836594e-05, + "loss": 0.4422, + "step": 11420 + }, + { + "epoch": 0.93, + "learning_rate": 1.3795632333767927e-05, + "loss": 0.2996, + "step": 11421 + }, + { + "epoch": 0.93, + "learning_rate": 1.3795089091699263e-05, + "loss": 0.4047, + "step": 11422 + }, + { + "epoch": 0.93, + "learning_rate": 1.3794545849630597e-05, + "loss": 0.3195, + "step": 11423 + }, + { + "epoch": 0.93, + "learning_rate": 1.3794002607561931e-05, + "loss": 0.3913, + "step": 11424 + }, + { + "epoch": 0.93, + "learning_rate": 1.3793459365493265e-05, + "loss": 0.9563, + "step": 11425 + }, + { + "epoch": 0.93, + "learning_rate": 1.37929161234246e-05, + "loss": 0.4012, + "step": 11426 + }, + { + "epoch": 0.93, + "learning_rate": 1.3792372881355934e-05, + "loss": 0.4396, + "step": 11427 + }, + { + "epoch": 0.93, + "learning_rate": 1.3791829639287268e-05, + "loss": 0.3925, + "step": 11428 + }, + { + "epoch": 0.93, + "learning_rate": 1.3791286397218602e-05, + "loss": 0.2713, + "step": 11429 + }, + { + "epoch": 0.93, + "learning_rate": 1.3790743155149935e-05, + "loss": 0.4471, + "step": 11430 + }, + { + "epoch": 0.93, + "learning_rate": 1.379019991308127e-05, + "loss": 0.2652, + "step": 11431 + }, + { + "epoch": 0.93, + "learning_rate": 1.3789656671012603e-05, + "loss": 0.4384, + "step": 11432 + }, + { + "epoch": 0.93, + "learning_rate": 1.378911342894394e-05, + "loss": 0.4318, + "step": 11433 + }, + { + "epoch": 0.93, + "learning_rate": 1.3788570186875272e-05, + "loss": 0.3824, + "step": 11434 + }, + { + "epoch": 0.93, + "learning_rate": 1.3788026944806608e-05, + "loss": 0.6548, + "step": 11435 + }, + { + "epoch": 0.93, + "learning_rate": 1.378748370273794e-05, + "loss": 0.2354, + "step": 11436 + }, + { + "epoch": 0.93, + "learning_rate": 1.3786940460669276e-05, + "loss": 0.3785, + "step": 11437 + }, + { + "epoch": 0.93, + "learning_rate": 1.3786397218600609e-05, + "loss": 0.3502, + "step": 11438 + }, + { + "epoch": 0.93, + "learning_rate": 1.3785853976531945e-05, + "loss": 0.3961, + "step": 11439 + }, + { + "epoch": 0.93, + "learning_rate": 1.3785310734463277e-05, + "loss": 0.6533, + "step": 11440 + }, + { + "epoch": 0.93, + "learning_rate": 1.3784767492394613e-05, + "loss": 0.5647, + "step": 11441 + }, + { + "epoch": 0.93, + "learning_rate": 1.3784224250325946e-05, + "loss": 0.4126, + "step": 11442 + }, + { + "epoch": 0.93, + "learning_rate": 1.3783681008257282e-05, + "loss": 0.3777, + "step": 11443 + }, + { + "epoch": 0.93, + "learning_rate": 1.3783137766188614e-05, + "loss": 0.5733, + "step": 11444 + }, + { + "epoch": 0.93, + "learning_rate": 1.378259452411995e-05, + "loss": 0.2831, + "step": 11445 + }, + { + "epoch": 0.93, + "learning_rate": 1.3782051282051283e-05, + "loss": 0.5896, + "step": 11446 + }, + { + "epoch": 0.93, + "learning_rate": 1.3781508039982619e-05, + "loss": 0.4234, + "step": 11447 + }, + { + "epoch": 0.93, + "learning_rate": 1.3780964797913951e-05, + "loss": 0.4129, + "step": 11448 + }, + { + "epoch": 0.93, + "learning_rate": 1.3780421555845285e-05, + "loss": 0.359, + "step": 11449 + }, + { + "epoch": 0.93, + "learning_rate": 1.377987831377662e-05, + "loss": 0.3537, + "step": 11450 + }, + { + "epoch": 0.93, + "learning_rate": 1.3779335071707954e-05, + "loss": 0.3531, + "step": 11451 + }, + { + "epoch": 0.93, + "learning_rate": 1.3778791829639288e-05, + "loss": 0.4213, + "step": 11452 + }, + { + "epoch": 0.93, + "learning_rate": 1.3778248587570622e-05, + "loss": 0.484, + "step": 11453 + }, + { + "epoch": 0.93, + "learning_rate": 1.3777705345501956e-05, + "loss": 0.6317, + "step": 11454 + }, + { + "epoch": 0.93, + "learning_rate": 1.377716210343329e-05, + "loss": 0.359, + "step": 11455 + }, + { + "epoch": 0.93, + "learning_rate": 1.3776618861364625e-05, + "loss": 0.4852, + "step": 11456 + }, + { + "epoch": 0.93, + "learning_rate": 1.3776075619295959e-05, + "loss": 0.4942, + "step": 11457 + }, + { + "epoch": 0.93, + "learning_rate": 1.3775532377227295e-05, + "loss": 0.2809, + "step": 11458 + }, + { + "epoch": 0.93, + "learning_rate": 1.3774989135158628e-05, + "loss": 0.3938, + "step": 11459 + }, + { + "epoch": 0.93, + "learning_rate": 1.3774445893089964e-05, + "loss": 0.5885, + "step": 11460 + }, + { + "epoch": 0.93, + "learning_rate": 1.3773902651021296e-05, + "loss": 0.4652, + "step": 11461 + }, + { + "epoch": 0.93, + "learning_rate": 1.3773359408952632e-05, + "loss": 0.3846, + "step": 11462 + }, + { + "epoch": 0.93, + "learning_rate": 1.3772816166883965e-05, + "loss": 0.3576, + "step": 11463 + }, + { + "epoch": 0.93, + "learning_rate": 1.37722729248153e-05, + "loss": 0.5302, + "step": 11464 + }, + { + "epoch": 0.93, + "learning_rate": 1.3771729682746633e-05, + "loss": 0.4526, + "step": 11465 + }, + { + "epoch": 0.93, + "learning_rate": 1.3771186440677969e-05, + "loss": 0.2384, + "step": 11466 + }, + { + "epoch": 0.93, + "learning_rate": 1.3770643198609301e-05, + "loss": 0.3239, + "step": 11467 + }, + { + "epoch": 0.93, + "learning_rate": 1.3770099956540634e-05, + "loss": 0.4435, + "step": 11468 + }, + { + "epoch": 0.93, + "learning_rate": 1.376955671447197e-05, + "loss": 0.5886, + "step": 11469 + }, + { + "epoch": 0.93, + "learning_rate": 1.3769013472403302e-05, + "loss": 0.3208, + "step": 11470 + }, + { + "epoch": 0.93, + "learning_rate": 1.3768470230334638e-05, + "loss": 0.5462, + "step": 11471 + }, + { + "epoch": 0.93, + "learning_rate": 1.3767926988265971e-05, + "loss": 0.3013, + "step": 11472 + }, + { + "epoch": 0.93, + "learning_rate": 1.3767383746197307e-05, + "loss": 0.7061, + "step": 11473 + }, + { + "epoch": 0.93, + "learning_rate": 1.376684050412864e-05, + "loss": 0.5306, + "step": 11474 + }, + { + "epoch": 0.94, + "learning_rate": 1.3766297262059975e-05, + "loss": 0.5372, + "step": 11475 + }, + { + "epoch": 0.94, + "learning_rate": 1.376575401999131e-05, + "loss": 0.2782, + "step": 11476 + }, + { + "epoch": 0.94, + "learning_rate": 1.3765210777922644e-05, + "loss": 0.8135, + "step": 11477 + }, + { + "epoch": 0.94, + "learning_rate": 1.3764667535853978e-05, + "loss": 0.3781, + "step": 11478 + }, + { + "epoch": 0.94, + "learning_rate": 1.3764124293785312e-05, + "loss": 0.4229, + "step": 11479 + }, + { + "epoch": 0.94, + "learning_rate": 1.3763581051716646e-05, + "loss": 0.5052, + "step": 11480 + }, + { + "epoch": 0.94, + "learning_rate": 1.376303780964798e-05, + "loss": 0.5055, + "step": 11481 + }, + { + "epoch": 0.94, + "learning_rate": 1.3762494567579315e-05, + "loss": 0.646, + "step": 11482 + }, + { + "epoch": 0.94, + "learning_rate": 1.3761951325510649e-05, + "loss": 0.3671, + "step": 11483 + }, + { + "epoch": 0.94, + "learning_rate": 1.3761408083441983e-05, + "loss": 0.5531, + "step": 11484 + }, + { + "epoch": 0.94, + "learning_rate": 1.3760864841373318e-05, + "loss": 0.4217, + "step": 11485 + }, + { + "epoch": 0.94, + "learning_rate": 1.3760321599304652e-05, + "loss": 0.2881, + "step": 11486 + }, + { + "epoch": 0.94, + "learning_rate": 1.3759778357235984e-05, + "loss": 0.8167, + "step": 11487 + }, + { + "epoch": 0.94, + "learning_rate": 1.375923511516732e-05, + "loss": 0.3531, + "step": 11488 + }, + { + "epoch": 0.94, + "learning_rate": 1.3758691873098653e-05, + "loss": 0.4174, + "step": 11489 + }, + { + "epoch": 0.94, + "learning_rate": 1.3758148631029989e-05, + "loss": 0.556, + "step": 11490 + }, + { + "epoch": 0.94, + "learning_rate": 1.3757605388961321e-05, + "loss": 0.3846, + "step": 11491 + }, + { + "epoch": 0.94, + "learning_rate": 1.3757062146892657e-05, + "loss": 0.4102, + "step": 11492 + }, + { + "epoch": 0.94, + "learning_rate": 1.375651890482399e-05, + "loss": 0.3749, + "step": 11493 + }, + { + "epoch": 0.94, + "learning_rate": 1.3755975662755326e-05, + "loss": 0.4995, + "step": 11494 + }, + { + "epoch": 0.94, + "learning_rate": 1.3755432420686658e-05, + "loss": 0.4577, + "step": 11495 + }, + { + "epoch": 0.94, + "learning_rate": 1.3754889178617994e-05, + "loss": 0.4796, + "step": 11496 + }, + { + "epoch": 0.94, + "learning_rate": 1.3754345936549327e-05, + "loss": 0.549, + "step": 11497 + }, + { + "epoch": 0.94, + "learning_rate": 1.3753802694480663e-05, + "loss": 0.6521, + "step": 11498 + }, + { + "epoch": 0.94, + "learning_rate": 1.3753259452411995e-05, + "loss": 0.5029, + "step": 11499 + }, + { + "epoch": 0.94, + "learning_rate": 1.3752716210343331e-05, + "loss": 0.4048, + "step": 11500 + }, + { + "epoch": 0.94, + "eval_accuracy": 0.8397350993377484, + "eval_loss": 0.42294514179229736, + "eval_runtime": 22.3019, + "eval_samples_per_second": 440.098, + "eval_steps_per_second": 3.453, + "step": 11500 + }, + { + "epoch": 0.94, + "learning_rate": 1.3752172968274664e-05, + "loss": 0.5536, + "step": 11501 + }, + { + "epoch": 0.94, + "learning_rate": 1.3751629726206e-05, + "loss": 0.5375, + "step": 11502 + }, + { + "epoch": 0.94, + "learning_rate": 1.3751086484137332e-05, + "loss": 0.6734, + "step": 11503 + }, + { + "epoch": 0.94, + "learning_rate": 1.3750543242068668e-05, + "loss": 0.3163, + "step": 11504 + }, + { + "epoch": 0.94, + "learning_rate": 1.375e-05, + "loss": 0.3503, + "step": 11505 + }, + { + "epoch": 0.94, + "learning_rate": 1.3749456757931335e-05, + "loss": 0.4121, + "step": 11506 + }, + { + "epoch": 0.94, + "learning_rate": 1.3748913515862669e-05, + "loss": 0.5766, + "step": 11507 + }, + { + "epoch": 0.94, + "learning_rate": 1.3748370273794003e-05, + "loss": 0.6164, + "step": 11508 + }, + { + "epoch": 0.94, + "learning_rate": 1.3747827031725337e-05, + "loss": 0.3676, + "step": 11509 + }, + { + "epoch": 0.94, + "learning_rate": 1.3747283789656672e-05, + "loss": 0.4392, + "step": 11510 + }, + { + "epoch": 0.94, + "learning_rate": 1.3746740547588006e-05, + "loss": 0.3747, + "step": 11511 + }, + { + "epoch": 0.94, + "learning_rate": 1.374619730551934e-05, + "loss": 0.4379, + "step": 11512 + }, + { + "epoch": 0.94, + "learning_rate": 1.3745654063450676e-05, + "loss": 0.5524, + "step": 11513 + }, + { + "epoch": 0.94, + "learning_rate": 1.3745110821382009e-05, + "loss": 0.3119, + "step": 11514 + }, + { + "epoch": 0.94, + "learning_rate": 1.3744567579313344e-05, + "loss": 0.3208, + "step": 11515 + }, + { + "epoch": 0.94, + "learning_rate": 1.3744024337244677e-05, + "loss": 0.5164, + "step": 11516 + }, + { + "epoch": 0.94, + "learning_rate": 1.3743481095176013e-05, + "loss": 0.7163, + "step": 11517 + }, + { + "epoch": 0.94, + "learning_rate": 1.3742937853107345e-05, + "loss": 0.5715, + "step": 11518 + }, + { + "epoch": 0.94, + "learning_rate": 1.3742394611038681e-05, + "loss": 0.5055, + "step": 11519 + }, + { + "epoch": 0.94, + "learning_rate": 1.3741851368970014e-05, + "loss": 0.3842, + "step": 11520 + }, + { + "epoch": 0.94, + "learning_rate": 1.374130812690135e-05, + "loss": 0.6645, + "step": 11521 + }, + { + "epoch": 0.94, + "learning_rate": 1.3740764884832682e-05, + "loss": 0.2993, + "step": 11522 + }, + { + "epoch": 0.94, + "learning_rate": 1.3740221642764018e-05, + "loss": 0.6495, + "step": 11523 + }, + { + "epoch": 0.94, + "learning_rate": 1.3739678400695351e-05, + "loss": 0.615, + "step": 11524 + }, + { + "epoch": 0.94, + "learning_rate": 1.3739135158626683e-05, + "loss": 0.3728, + "step": 11525 + }, + { + "epoch": 0.94, + "learning_rate": 1.373859191655802e-05, + "loss": 0.3062, + "step": 11526 + }, + { + "epoch": 0.94, + "learning_rate": 1.3738048674489352e-05, + "loss": 0.5896, + "step": 11527 + }, + { + "epoch": 0.94, + "learning_rate": 1.3737505432420688e-05, + "loss": 0.539, + "step": 11528 + }, + { + "epoch": 0.94, + "learning_rate": 1.373696219035202e-05, + "loss": 0.4944, + "step": 11529 + }, + { + "epoch": 0.94, + "learning_rate": 1.3736418948283356e-05, + "loss": 0.3704, + "step": 11530 + }, + { + "epoch": 0.94, + "learning_rate": 1.373587570621469e-05, + "loss": 0.3764, + "step": 11531 + }, + { + "epoch": 0.94, + "learning_rate": 1.3735332464146025e-05, + "loss": 0.5078, + "step": 11532 + }, + { + "epoch": 0.94, + "learning_rate": 1.3734789222077359e-05, + "loss": 0.3664, + "step": 11533 + }, + { + "epoch": 0.94, + "learning_rate": 1.3734245980008693e-05, + "loss": 0.4823, + "step": 11534 + }, + { + "epoch": 0.94, + "learning_rate": 1.3733702737940027e-05, + "loss": 0.3433, + "step": 11535 + }, + { + "epoch": 0.94, + "learning_rate": 1.3733159495871362e-05, + "loss": 0.396, + "step": 11536 + }, + { + "epoch": 0.94, + "learning_rate": 1.3732616253802696e-05, + "loss": 0.4844, + "step": 11537 + }, + { + "epoch": 0.94, + "learning_rate": 1.373207301173403e-05, + "loss": 0.4661, + "step": 11538 + }, + { + "epoch": 0.94, + "learning_rate": 1.3731529769665364e-05, + "loss": 0.5607, + "step": 11539 + }, + { + "epoch": 0.94, + "learning_rate": 1.3730986527596699e-05, + "loss": 0.4116, + "step": 11540 + }, + { + "epoch": 0.94, + "learning_rate": 1.3730443285528033e-05, + "loss": 0.2599, + "step": 11541 + }, + { + "epoch": 0.94, + "learning_rate": 1.3729900043459367e-05, + "loss": 0.3043, + "step": 11542 + }, + { + "epoch": 0.94, + "learning_rate": 1.3729356801390701e-05, + "loss": 0.3333, + "step": 11543 + }, + { + "epoch": 0.94, + "learning_rate": 1.3728813559322034e-05, + "loss": 0.3374, + "step": 11544 + }, + { + "epoch": 0.94, + "learning_rate": 1.372827031725337e-05, + "loss": 0.4465, + "step": 11545 + }, + { + "epoch": 0.94, + "learning_rate": 1.3727727075184702e-05, + "loss": 0.3523, + "step": 11546 + }, + { + "epoch": 0.94, + "learning_rate": 1.3727183833116038e-05, + "loss": 0.4436, + "step": 11547 + }, + { + "epoch": 0.94, + "learning_rate": 1.372664059104737e-05, + "loss": 0.3496, + "step": 11548 + }, + { + "epoch": 0.94, + "learning_rate": 1.3726097348978707e-05, + "loss": 0.4977, + "step": 11549 + }, + { + "epoch": 0.94, + "learning_rate": 1.372555410691004e-05, + "loss": 0.3037, + "step": 11550 + }, + { + "epoch": 0.94, + "learning_rate": 1.3725010864841375e-05, + "loss": 0.5286, + "step": 11551 + }, + { + "epoch": 0.94, + "learning_rate": 1.3724467622772708e-05, + "loss": 0.5948, + "step": 11552 + }, + { + "epoch": 0.94, + "learning_rate": 1.3723924380704044e-05, + "loss": 0.4155, + "step": 11553 + }, + { + "epoch": 0.94, + "learning_rate": 1.3723381138635376e-05, + "loss": 0.6487, + "step": 11554 + }, + { + "epoch": 0.94, + "learning_rate": 1.3722837896566712e-05, + "loss": 0.5118, + "step": 11555 + }, + { + "epoch": 0.94, + "learning_rate": 1.3722294654498045e-05, + "loss": 0.7432, + "step": 11556 + }, + { + "epoch": 0.94, + "learning_rate": 1.372175141242938e-05, + "loss": 0.3914, + "step": 11557 + }, + { + "epoch": 0.94, + "learning_rate": 1.3721208170360713e-05, + "loss": 0.7532, + "step": 11558 + }, + { + "epoch": 0.94, + "learning_rate": 1.3720664928292049e-05, + "loss": 0.4626, + "step": 11559 + }, + { + "epoch": 0.94, + "learning_rate": 1.3720121686223381e-05, + "loss": 0.4522, + "step": 11560 + }, + { + "epoch": 0.94, + "learning_rate": 1.3719578444154717e-05, + "loss": 0.506, + "step": 11561 + }, + { + "epoch": 0.94, + "learning_rate": 1.371903520208605e-05, + "loss": 0.2605, + "step": 11562 + }, + { + "epoch": 0.94, + "learning_rate": 1.3718491960017384e-05, + "loss": 0.496, + "step": 11563 + }, + { + "epoch": 0.94, + "learning_rate": 1.3717948717948718e-05, + "loss": 0.4126, + "step": 11564 + }, + { + "epoch": 0.94, + "learning_rate": 1.3717405475880053e-05, + "loss": 0.2783, + "step": 11565 + }, + { + "epoch": 0.94, + "learning_rate": 1.3716862233811389e-05, + "loss": 0.4057, + "step": 11566 + }, + { + "epoch": 0.94, + "learning_rate": 1.3716318991742721e-05, + "loss": 0.5451, + "step": 11567 + }, + { + "epoch": 0.94, + "learning_rate": 1.3715775749674057e-05, + "loss": 0.5643, + "step": 11568 + }, + { + "epoch": 0.94, + "learning_rate": 1.371523250760539e-05, + "loss": 0.2122, + "step": 11569 + }, + { + "epoch": 0.94, + "learning_rate": 1.3714689265536725e-05, + "loss": 0.5777, + "step": 11570 + }, + { + "epoch": 0.94, + "learning_rate": 1.3714146023468058e-05, + "loss": 0.3926, + "step": 11571 + }, + { + "epoch": 0.94, + "learning_rate": 1.3713602781399394e-05, + "loss": 0.4441, + "step": 11572 + }, + { + "epoch": 0.94, + "learning_rate": 1.3713059539330726e-05, + "loss": 0.7379, + "step": 11573 + }, + { + "epoch": 0.94, + "learning_rate": 1.3712516297262062e-05, + "loss": 0.528, + "step": 11574 + }, + { + "epoch": 0.94, + "learning_rate": 1.3711973055193395e-05, + "loss": 0.5003, + "step": 11575 + }, + { + "epoch": 0.94, + "learning_rate": 1.3711429813124731e-05, + "loss": 0.6602, + "step": 11576 + }, + { + "epoch": 0.94, + "learning_rate": 1.3710886571056063e-05, + "loss": 0.5872, + "step": 11577 + }, + { + "epoch": 0.94, + "learning_rate": 1.37103433289874e-05, + "loss": 0.5092, + "step": 11578 + }, + { + "epoch": 0.94, + "learning_rate": 1.3709800086918732e-05, + "loss": 0.232, + "step": 11579 + }, + { + "epoch": 0.94, + "learning_rate": 1.3709256844850068e-05, + "loss": 0.3393, + "step": 11580 + }, + { + "epoch": 0.94, + "learning_rate": 1.37087136027814e-05, + "loss": 0.3651, + "step": 11581 + }, + { + "epoch": 0.94, + "learning_rate": 1.3708170360712733e-05, + "loss": 0.6187, + "step": 11582 + }, + { + "epoch": 0.94, + "learning_rate": 1.3707627118644069e-05, + "loss": 0.3672, + "step": 11583 + }, + { + "epoch": 0.94, + "learning_rate": 1.3707083876575403e-05, + "loss": 0.6424, + "step": 11584 + }, + { + "epoch": 0.94, + "learning_rate": 1.3706540634506737e-05, + "loss": 0.511, + "step": 11585 + }, + { + "epoch": 0.94, + "learning_rate": 1.3705997392438071e-05, + "loss": 0.4389, + "step": 11586 + }, + { + "epoch": 0.94, + "learning_rate": 1.3705454150369406e-05, + "loss": 0.4053, + "step": 11587 + }, + { + "epoch": 0.94, + "learning_rate": 1.370491090830074e-05, + "loss": 0.4267, + "step": 11588 + }, + { + "epoch": 0.94, + "learning_rate": 1.3704367666232074e-05, + "loss": 0.8021, + "step": 11589 + }, + { + "epoch": 0.94, + "learning_rate": 1.3703824424163408e-05, + "loss": 0.4224, + "step": 11590 + }, + { + "epoch": 0.94, + "learning_rate": 1.3703281182094743e-05, + "loss": 0.4249, + "step": 11591 + }, + { + "epoch": 0.94, + "learning_rate": 1.3702737940026077e-05, + "loss": 0.3757, + "step": 11592 + }, + { + "epoch": 0.94, + "learning_rate": 1.3702194697957411e-05, + "loss": 0.6542, + "step": 11593 + }, + { + "epoch": 0.94, + "learning_rate": 1.3701651455888745e-05, + "loss": 0.3847, + "step": 11594 + }, + { + "epoch": 0.94, + "learning_rate": 1.370110821382008e-05, + "loss": 0.2857, + "step": 11595 + }, + { + "epoch": 0.94, + "learning_rate": 1.3700564971751414e-05, + "loss": 0.5668, + "step": 11596 + }, + { + "epoch": 0.94, + "learning_rate": 1.3700021729682748e-05, + "loss": 0.3232, + "step": 11597 + }, + { + "epoch": 0.95, + "learning_rate": 1.3699478487614082e-05, + "loss": 0.3296, + "step": 11598 + }, + { + "epoch": 0.95, + "learning_rate": 1.3698935245545416e-05, + "loss": 0.3565, + "step": 11599 + }, + { + "epoch": 0.95, + "learning_rate": 1.369839200347675e-05, + "loss": 0.3521, + "step": 11600 + }, + { + "epoch": 0.95, + "learning_rate": 1.3697848761408083e-05, + "loss": 0.3638, + "step": 11601 + }, + { + "epoch": 0.95, + "learning_rate": 1.369730551933942e-05, + "loss": 0.6887, + "step": 11602 + }, + { + "epoch": 0.95, + "learning_rate": 1.3696762277270752e-05, + "loss": 0.5436, + "step": 11603 + }, + { + "epoch": 0.95, + "learning_rate": 1.3696219035202088e-05, + "loss": 0.4922, + "step": 11604 + }, + { + "epoch": 0.95, + "learning_rate": 1.369567579313342e-05, + "loss": 0.5451, + "step": 11605 + }, + { + "epoch": 0.95, + "learning_rate": 1.3695132551064756e-05, + "loss": 0.3957, + "step": 11606 + }, + { + "epoch": 0.95, + "learning_rate": 1.3694589308996089e-05, + "loss": 0.552, + "step": 11607 + }, + { + "epoch": 0.95, + "learning_rate": 1.3694046066927425e-05, + "loss": 0.4147, + "step": 11608 + }, + { + "epoch": 0.95, + "learning_rate": 1.3693502824858757e-05, + "loss": 0.4111, + "step": 11609 + }, + { + "epoch": 0.95, + "learning_rate": 1.3692959582790093e-05, + "loss": 0.3447, + "step": 11610 + }, + { + "epoch": 0.95, + "learning_rate": 1.3692416340721426e-05, + "loss": 0.6238, + "step": 11611 + }, + { + "epoch": 0.95, + "learning_rate": 1.3691873098652761e-05, + "loss": 0.2489, + "step": 11612 + }, + { + "epoch": 0.95, + "learning_rate": 1.3691329856584094e-05, + "loss": 0.6247, + "step": 11613 + }, + { + "epoch": 0.95, + "learning_rate": 1.369078661451543e-05, + "loss": 0.251, + "step": 11614 + }, + { + "epoch": 0.95, + "learning_rate": 1.3690243372446762e-05, + "loss": 0.2491, + "step": 11615 + }, + { + "epoch": 0.95, + "learning_rate": 1.3689700130378098e-05, + "loss": 0.4082, + "step": 11616 + }, + { + "epoch": 0.95, + "learning_rate": 1.3689156888309431e-05, + "loss": 0.1567, + "step": 11617 + }, + { + "epoch": 0.95, + "learning_rate": 1.3688613646240767e-05, + "loss": 0.4093, + "step": 11618 + }, + { + "epoch": 0.95, + "learning_rate": 1.36880704041721e-05, + "loss": 0.2709, + "step": 11619 + }, + { + "epoch": 0.95, + "learning_rate": 1.3687527162103434e-05, + "loss": 0.4104, + "step": 11620 + }, + { + "epoch": 0.95, + "learning_rate": 1.368698392003477e-05, + "loss": 0.4523, + "step": 11621 + }, + { + "epoch": 0.95, + "learning_rate": 1.3686440677966102e-05, + "loss": 0.3309, + "step": 11622 + }, + { + "epoch": 0.95, + "learning_rate": 1.3685897435897438e-05, + "loss": 0.3597, + "step": 11623 + }, + { + "epoch": 0.95, + "learning_rate": 1.368535419382877e-05, + "loss": 0.5091, + "step": 11624 + }, + { + "epoch": 0.95, + "learning_rate": 1.3684810951760106e-05, + "loss": 0.8039, + "step": 11625 + }, + { + "epoch": 0.95, + "learning_rate": 1.3684267709691439e-05, + "loss": 0.7052, + "step": 11626 + }, + { + "epoch": 0.95, + "learning_rate": 1.3683724467622775e-05, + "loss": 0.5037, + "step": 11627 + }, + { + "epoch": 0.95, + "learning_rate": 1.3683181225554107e-05, + "loss": 0.5758, + "step": 11628 + }, + { + "epoch": 0.95, + "learning_rate": 1.3682637983485443e-05, + "loss": 0.3776, + "step": 11629 + }, + { + "epoch": 0.95, + "learning_rate": 1.3682094741416776e-05, + "loss": 0.4273, + "step": 11630 + }, + { + "epoch": 0.95, + "learning_rate": 1.3681551499348112e-05, + "loss": 0.4228, + "step": 11631 + }, + { + "epoch": 0.95, + "learning_rate": 1.3681008257279444e-05, + "loss": 0.4072, + "step": 11632 + }, + { + "epoch": 0.95, + "learning_rate": 1.368046501521078e-05, + "loss": 0.188, + "step": 11633 + }, + { + "epoch": 0.95, + "learning_rate": 1.3679921773142113e-05, + "loss": 0.3633, + "step": 11634 + }, + { + "epoch": 0.95, + "learning_rate": 1.3679378531073449e-05, + "loss": 0.7456, + "step": 11635 + }, + { + "epoch": 0.95, + "learning_rate": 1.3678835289004781e-05, + "loss": 0.3041, + "step": 11636 + }, + { + "epoch": 0.95, + "learning_rate": 1.3678292046936117e-05, + "loss": 0.2335, + "step": 11637 + }, + { + "epoch": 0.95, + "learning_rate": 1.367774880486745e-05, + "loss": 0.4583, + "step": 11638 + }, + { + "epoch": 0.95, + "learning_rate": 1.3677205562798784e-05, + "loss": 0.3047, + "step": 11639 + }, + { + "epoch": 0.95, + "learning_rate": 1.3676662320730118e-05, + "loss": 0.5155, + "step": 11640 + }, + { + "epoch": 0.95, + "learning_rate": 1.3676119078661452e-05, + "loss": 0.2544, + "step": 11641 + }, + { + "epoch": 0.95, + "learning_rate": 1.3675575836592787e-05, + "loss": 0.4677, + "step": 11642 + }, + { + "epoch": 0.95, + "learning_rate": 1.3675032594524121e-05, + "loss": 0.4521, + "step": 11643 + }, + { + "epoch": 0.95, + "learning_rate": 1.3674489352455455e-05, + "loss": 0.2121, + "step": 11644 + }, + { + "epoch": 0.95, + "learning_rate": 1.367394611038679e-05, + "loss": 0.4791, + "step": 11645 + }, + { + "epoch": 0.95, + "learning_rate": 1.3673402868318124e-05, + "loss": 0.3636, + "step": 11646 + }, + { + "epoch": 0.95, + "learning_rate": 1.3672859626249458e-05, + "loss": 0.5876, + "step": 11647 + }, + { + "epoch": 0.95, + "learning_rate": 1.3672316384180792e-05, + "loss": 0.2736, + "step": 11648 + }, + { + "epoch": 0.95, + "learning_rate": 1.3671773142112126e-05, + "loss": 0.5608, + "step": 11649 + }, + { + "epoch": 0.95, + "learning_rate": 1.367122990004346e-05, + "loss": 0.2833, + "step": 11650 + }, + { + "epoch": 0.95, + "learning_rate": 1.3670686657974795e-05, + "loss": 0.4147, + "step": 11651 + }, + { + "epoch": 0.95, + "learning_rate": 1.3670143415906129e-05, + "loss": 0.3421, + "step": 11652 + }, + { + "epoch": 0.95, + "learning_rate": 1.3669600173837463e-05, + "loss": 0.2857, + "step": 11653 + }, + { + "epoch": 0.95, + "learning_rate": 1.3669056931768797e-05, + "loss": 0.438, + "step": 11654 + }, + { + "epoch": 0.95, + "learning_rate": 1.3668513689700132e-05, + "loss": 0.447, + "step": 11655 + }, + { + "epoch": 0.95, + "learning_rate": 1.3667970447631466e-05, + "loss": 0.2368, + "step": 11656 + }, + { + "epoch": 0.95, + "learning_rate": 1.36674272055628e-05, + "loss": 0.3452, + "step": 11657 + }, + { + "epoch": 0.95, + "learning_rate": 1.3666883963494133e-05, + "loss": 0.5904, + "step": 11658 + }, + { + "epoch": 0.95, + "learning_rate": 1.3666340721425469e-05, + "loss": 0.5093, + "step": 11659 + }, + { + "epoch": 0.95, + "learning_rate": 1.3665797479356801e-05, + "loss": 0.3321, + "step": 11660 + }, + { + "epoch": 0.95, + "learning_rate": 1.3665254237288137e-05, + "loss": 0.393, + "step": 11661 + }, + { + "epoch": 0.95, + "learning_rate": 1.366471099521947e-05, + "loss": 0.3964, + "step": 11662 + }, + { + "epoch": 0.95, + "learning_rate": 1.3664167753150806e-05, + "loss": 0.5254, + "step": 11663 + }, + { + "epoch": 0.95, + "learning_rate": 1.3663624511082138e-05, + "loss": 0.5934, + "step": 11664 + }, + { + "epoch": 0.95, + "learning_rate": 1.3663081269013474e-05, + "loss": 0.4979, + "step": 11665 + }, + { + "epoch": 0.95, + "learning_rate": 1.3662538026944807e-05, + "loss": 0.2203, + "step": 11666 + }, + { + "epoch": 0.95, + "learning_rate": 1.3661994784876142e-05, + "loss": 0.4237, + "step": 11667 + }, + { + "epoch": 0.95, + "learning_rate": 1.3661451542807475e-05, + "loss": 0.1263, + "step": 11668 + }, + { + "epoch": 0.95, + "learning_rate": 1.3660908300738811e-05, + "loss": 0.2645, + "step": 11669 + }, + { + "epoch": 0.95, + "learning_rate": 1.3660365058670143e-05, + "loss": 0.2196, + "step": 11670 + }, + { + "epoch": 0.95, + "learning_rate": 1.365982181660148e-05, + "loss": 0.6125, + "step": 11671 + }, + { + "epoch": 0.95, + "learning_rate": 1.3659278574532812e-05, + "loss": 0.4472, + "step": 11672 + }, + { + "epoch": 0.95, + "learning_rate": 1.3658735332464148e-05, + "loss": 0.8267, + "step": 11673 + }, + { + "epoch": 0.95, + "learning_rate": 1.3658192090395482e-05, + "loss": 0.3734, + "step": 11674 + }, + { + "epoch": 0.95, + "learning_rate": 1.3657648848326816e-05, + "loss": 0.319, + "step": 11675 + }, + { + "epoch": 0.95, + "learning_rate": 1.365710560625815e-05, + "loss": 0.2252, + "step": 11676 + }, + { + "epoch": 0.95, + "learning_rate": 1.3656562364189483e-05, + "loss": 0.3423, + "step": 11677 + }, + { + "epoch": 0.95, + "learning_rate": 1.3656019122120819e-05, + "loss": 0.6721, + "step": 11678 + }, + { + "epoch": 0.95, + "learning_rate": 1.3655475880052152e-05, + "loss": 0.3163, + "step": 11679 + }, + { + "epoch": 0.95, + "learning_rate": 1.3654932637983487e-05, + "loss": 0.6368, + "step": 11680 + }, + { + "epoch": 0.95, + "learning_rate": 1.365438939591482e-05, + "loss": 0.4462, + "step": 11681 + }, + { + "epoch": 0.95, + "learning_rate": 1.3653846153846156e-05, + "loss": 0.3738, + "step": 11682 + }, + { + "epoch": 0.95, + "learning_rate": 1.3653302911777488e-05, + "loss": 0.3496, + "step": 11683 + }, + { + "epoch": 0.95, + "learning_rate": 1.3652759669708824e-05, + "loss": 0.5005, + "step": 11684 + }, + { + "epoch": 0.95, + "learning_rate": 1.3652216427640157e-05, + "loss": 0.7521, + "step": 11685 + }, + { + "epoch": 0.95, + "learning_rate": 1.3651673185571493e-05, + "loss": 0.1451, + "step": 11686 + }, + { + "epoch": 0.95, + "learning_rate": 1.3651129943502825e-05, + "loss": 0.4536, + "step": 11687 + }, + { + "epoch": 0.95, + "learning_rate": 1.3650586701434161e-05, + "loss": 0.2753, + "step": 11688 + }, + { + "epoch": 0.95, + "learning_rate": 1.3650043459365494e-05, + "loss": 0.3306, + "step": 11689 + }, + { + "epoch": 0.95, + "learning_rate": 1.364950021729683e-05, + "loss": 0.5528, + "step": 11690 + }, + { + "epoch": 0.95, + "learning_rate": 1.3648956975228162e-05, + "loss": 0.1735, + "step": 11691 + }, + { + "epoch": 0.95, + "learning_rate": 1.3648413733159498e-05, + "loss": 0.1422, + "step": 11692 + }, + { + "epoch": 0.95, + "learning_rate": 1.364787049109083e-05, + "loss": 0.4995, + "step": 11693 + }, + { + "epoch": 0.95, + "learning_rate": 1.3647327249022167e-05, + "loss": 0.2373, + "step": 11694 + }, + { + "epoch": 0.95, + "learning_rate": 1.36467840069535e-05, + "loss": 0.6612, + "step": 11695 + }, + { + "epoch": 0.95, + "learning_rate": 1.3646240764884833e-05, + "loss": 0.4631, + "step": 11696 + }, + { + "epoch": 0.95, + "learning_rate": 1.3645697522816168e-05, + "loss": 0.7069, + "step": 11697 + }, + { + "epoch": 0.95, + "learning_rate": 1.3645154280747502e-05, + "loss": 0.2562, + "step": 11698 + }, + { + "epoch": 0.95, + "learning_rate": 1.3644611038678836e-05, + "loss": 0.4666, + "step": 11699 + }, + { + "epoch": 0.95, + "learning_rate": 1.364406779661017e-05, + "loss": 0.2658, + "step": 11700 + }, + { + "epoch": 0.95, + "learning_rate": 1.3643524554541505e-05, + "loss": 0.5811, + "step": 11701 + }, + { + "epoch": 0.95, + "learning_rate": 1.3642981312472839e-05, + "loss": 0.8113, + "step": 11702 + }, + { + "epoch": 0.95, + "learning_rate": 1.3642438070404173e-05, + "loss": 0.2749, + "step": 11703 + }, + { + "epoch": 0.95, + "learning_rate": 1.3641894828335507e-05, + "loss": 0.8841, + "step": 11704 + }, + { + "epoch": 0.95, + "learning_rate": 1.3641351586266842e-05, + "loss": 0.3258, + "step": 11705 + }, + { + "epoch": 0.95, + "learning_rate": 1.3640808344198176e-05, + "loss": 0.4788, + "step": 11706 + }, + { + "epoch": 0.95, + "learning_rate": 1.364026510212951e-05, + "loss": 0.5649, + "step": 11707 + }, + { + "epoch": 0.95, + "learning_rate": 1.3639721860060844e-05, + "loss": 0.2775, + "step": 11708 + }, + { + "epoch": 0.95, + "learning_rate": 1.3639178617992178e-05, + "loss": 0.4382, + "step": 11709 + }, + { + "epoch": 0.95, + "learning_rate": 1.3638635375923513e-05, + "loss": 0.6596, + "step": 11710 + }, + { + "epoch": 0.95, + "learning_rate": 1.3638092133854849e-05, + "loss": 0.6199, + "step": 11711 + }, + { + "epoch": 0.95, + "learning_rate": 1.3637548891786181e-05, + "loss": 0.3597, + "step": 11712 + }, + { + "epoch": 0.95, + "learning_rate": 1.3637005649717517e-05, + "loss": 0.2744, + "step": 11713 + }, + { + "epoch": 0.95, + "learning_rate": 1.363646240764885e-05, + "loss": 0.4168, + "step": 11714 + }, + { + "epoch": 0.95, + "learning_rate": 1.3635919165580182e-05, + "loss": 0.6097, + "step": 11715 + }, + { + "epoch": 0.95, + "learning_rate": 1.3635375923511518e-05, + "loss": 0.4397, + "step": 11716 + }, + { + "epoch": 0.95, + "learning_rate": 1.363483268144285e-05, + "loss": 0.5084, + "step": 11717 + }, + { + "epoch": 0.95, + "learning_rate": 1.3634289439374187e-05, + "loss": 0.7103, + "step": 11718 + }, + { + "epoch": 0.95, + "learning_rate": 1.3633746197305519e-05, + "loss": 0.2626, + "step": 11719 + }, + { + "epoch": 0.96, + "learning_rate": 1.3633202955236855e-05, + "loss": 0.3143, + "step": 11720 + }, + { + "epoch": 0.96, + "learning_rate": 1.3632659713168188e-05, + "loss": 0.4902, + "step": 11721 + }, + { + "epoch": 0.96, + "learning_rate": 1.3632116471099523e-05, + "loss": 0.4839, + "step": 11722 + }, + { + "epoch": 0.96, + "learning_rate": 1.3631573229030856e-05, + "loss": 0.615, + "step": 11723 + }, + { + "epoch": 0.96, + "learning_rate": 1.3631029986962192e-05, + "loss": 0.5899, + "step": 11724 + }, + { + "epoch": 0.96, + "learning_rate": 1.3630486744893524e-05, + "loss": 0.4701, + "step": 11725 + }, + { + "epoch": 0.96, + "learning_rate": 1.362994350282486e-05, + "loss": 0.3674, + "step": 11726 + }, + { + "epoch": 0.96, + "learning_rate": 1.3629400260756193e-05, + "loss": 0.4255, + "step": 11727 + }, + { + "epoch": 0.96, + "learning_rate": 1.3628857018687529e-05, + "loss": 0.4025, + "step": 11728 + }, + { + "epoch": 0.96, + "learning_rate": 1.3628313776618863e-05, + "loss": 0.6461, + "step": 11729 + }, + { + "epoch": 0.96, + "learning_rate": 1.3627770534550197e-05, + "loss": 0.47, + "step": 11730 + }, + { + "epoch": 0.96, + "learning_rate": 1.3627227292481532e-05, + "loss": 0.4007, + "step": 11731 + }, + { + "epoch": 0.96, + "learning_rate": 1.3626684050412866e-05, + "loss": 0.3814, + "step": 11732 + }, + { + "epoch": 0.96, + "learning_rate": 1.36261408083442e-05, + "loss": 0.2553, + "step": 11733 + }, + { + "epoch": 0.96, + "learning_rate": 1.3625597566275533e-05, + "loss": 0.5469, + "step": 11734 + }, + { + "epoch": 0.96, + "learning_rate": 1.3625054324206868e-05, + "loss": 0.1159, + "step": 11735 + }, + { + "epoch": 0.96, + "learning_rate": 1.3624511082138201e-05, + "loss": 0.2418, + "step": 11736 + }, + { + "epoch": 0.96, + "learning_rate": 1.3623967840069537e-05, + "loss": 0.5629, + "step": 11737 + }, + { + "epoch": 0.96, + "learning_rate": 1.362342459800087e-05, + "loss": 0.3714, + "step": 11738 + }, + { + "epoch": 0.96, + "learning_rate": 1.3622881355932205e-05, + "loss": 0.7561, + "step": 11739 + }, + { + "epoch": 0.96, + "learning_rate": 1.3622338113863538e-05, + "loss": 0.6144, + "step": 11740 + }, + { + "epoch": 0.96, + "learning_rate": 1.3621794871794874e-05, + "loss": 0.3591, + "step": 11741 + }, + { + "epoch": 0.96, + "learning_rate": 1.3621251629726206e-05, + "loss": 0.6859, + "step": 11742 + }, + { + "epoch": 0.96, + "learning_rate": 1.3620708387657542e-05, + "loss": 0.2425, + "step": 11743 + }, + { + "epoch": 0.96, + "learning_rate": 1.3620165145588875e-05, + "loss": 0.3358, + "step": 11744 + }, + { + "epoch": 0.96, + "learning_rate": 1.361962190352021e-05, + "loss": 0.3849, + "step": 11745 + }, + { + "epoch": 0.96, + "learning_rate": 1.3619078661451543e-05, + "loss": 0.3571, + "step": 11746 + }, + { + "epoch": 0.96, + "learning_rate": 1.361853541938288e-05, + "loss": 0.2767, + "step": 11747 + }, + { + "epoch": 0.96, + "learning_rate": 1.3617992177314212e-05, + "loss": 0.5095, + "step": 11748 + }, + { + "epoch": 0.96, + "learning_rate": 1.3617448935245548e-05, + "loss": 0.601, + "step": 11749 + }, + { + "epoch": 0.96, + "learning_rate": 1.361690569317688e-05, + "loss": 0.4721, + "step": 11750 + }, + { + "epoch": 0.96, + "eval_accuracy": 0.8381049414161997, + "eval_loss": 0.42285284399986267, + "eval_runtime": 22.4258, + "eval_samples_per_second": 437.666, + "eval_steps_per_second": 3.434, + "step": 11750 + }, + { + "epoch": 0.96, + "learning_rate": 1.3616362451108216e-05, + "loss": 0.3401, + "step": 11751 + }, + { + "epoch": 0.96, + "learning_rate": 1.3615819209039549e-05, + "loss": 0.4101, + "step": 11752 + }, + { + "epoch": 0.96, + "learning_rate": 1.3615275966970883e-05, + "loss": 0.412, + "step": 11753 + }, + { + "epoch": 0.96, + "learning_rate": 1.3614732724902217e-05, + "loss": 0.2956, + "step": 11754 + }, + { + "epoch": 0.96, + "learning_rate": 1.3614189482833551e-05, + "loss": 0.6628, + "step": 11755 + }, + { + "epoch": 0.96, + "learning_rate": 1.3613646240764886e-05, + "loss": 0.8476, + "step": 11756 + }, + { + "epoch": 0.96, + "learning_rate": 1.361310299869622e-05, + "loss": 0.4782, + "step": 11757 + }, + { + "epoch": 0.96, + "learning_rate": 1.3612559756627554e-05, + "loss": 0.6367, + "step": 11758 + }, + { + "epoch": 0.96, + "learning_rate": 1.3612016514558888e-05, + "loss": 0.6232, + "step": 11759 + }, + { + "epoch": 0.96, + "learning_rate": 1.3611473272490223e-05, + "loss": 0.4606, + "step": 11760 + }, + { + "epoch": 0.96, + "learning_rate": 1.3610930030421557e-05, + "loss": 0.5204, + "step": 11761 + }, + { + "epoch": 0.96, + "learning_rate": 1.3610386788352891e-05, + "loss": 0.2943, + "step": 11762 + }, + { + "epoch": 0.96, + "learning_rate": 1.3609843546284225e-05, + "loss": 0.3913, + "step": 11763 + }, + { + "epoch": 0.96, + "learning_rate": 1.360930030421556e-05, + "loss": 0.4968, + "step": 11764 + }, + { + "epoch": 0.96, + "learning_rate": 1.3608757062146894e-05, + "loss": 0.4429, + "step": 11765 + }, + { + "epoch": 0.96, + "learning_rate": 1.360821382007823e-05, + "loss": 0.4441, + "step": 11766 + }, + { + "epoch": 0.96, + "learning_rate": 1.3607670578009562e-05, + "loss": 0.4122, + "step": 11767 + }, + { + "epoch": 0.96, + "learning_rate": 1.3607127335940898e-05, + "loss": 0.4776, + "step": 11768 + }, + { + "epoch": 0.96, + "learning_rate": 1.360658409387223e-05, + "loss": 0.2712, + "step": 11769 + }, + { + "epoch": 0.96, + "learning_rate": 1.3606040851803567e-05, + "loss": 0.499, + "step": 11770 + }, + { + "epoch": 0.96, + "learning_rate": 1.3605497609734899e-05, + "loss": 0.4167, + "step": 11771 + }, + { + "epoch": 0.96, + "learning_rate": 1.3604954367666232e-05, + "loss": 0.6982, + "step": 11772 + }, + { + "epoch": 0.96, + "learning_rate": 1.3604411125597567e-05, + "loss": 0.4238, + "step": 11773 + }, + { + "epoch": 0.96, + "learning_rate": 1.36038678835289e-05, + "loss": 0.417, + "step": 11774 + }, + { + "epoch": 0.96, + "learning_rate": 1.3603324641460236e-05, + "loss": 0.3064, + "step": 11775 + }, + { + "epoch": 0.96, + "learning_rate": 1.3602781399391568e-05, + "loss": 0.3276, + "step": 11776 + }, + { + "epoch": 0.96, + "learning_rate": 1.3602238157322904e-05, + "loss": 0.4498, + "step": 11777 + }, + { + "epoch": 0.96, + "learning_rate": 1.3601694915254237e-05, + "loss": 0.4608, + "step": 11778 + }, + { + "epoch": 0.96, + "learning_rate": 1.3601151673185573e-05, + "loss": 0.4947, + "step": 11779 + }, + { + "epoch": 0.96, + "learning_rate": 1.3600608431116905e-05, + "loss": 0.3733, + "step": 11780 + }, + { + "epoch": 0.96, + "learning_rate": 1.3600065189048241e-05, + "loss": 0.4485, + "step": 11781 + }, + { + "epoch": 0.96, + "learning_rate": 1.3599521946979576e-05, + "loss": 0.5839, + "step": 11782 + }, + { + "epoch": 0.96, + "learning_rate": 1.359897870491091e-05, + "loss": 0.3514, + "step": 11783 + }, + { + "epoch": 0.96, + "learning_rate": 1.3598435462842244e-05, + "loss": 0.4446, + "step": 11784 + }, + { + "epoch": 0.96, + "learning_rate": 1.3597892220773578e-05, + "loss": 0.4301, + "step": 11785 + }, + { + "epoch": 0.96, + "learning_rate": 1.3597348978704912e-05, + "loss": 0.4107, + "step": 11786 + }, + { + "epoch": 0.96, + "learning_rate": 1.3596805736636247e-05, + "loss": 0.6414, + "step": 11787 + }, + { + "epoch": 0.96, + "learning_rate": 1.3596262494567581e-05, + "loss": 0.4384, + "step": 11788 + }, + { + "epoch": 0.96, + "learning_rate": 1.3595719252498915e-05, + "loss": 0.5431, + "step": 11789 + }, + { + "epoch": 0.96, + "learning_rate": 1.359517601043025e-05, + "loss": 0.7048, + "step": 11790 + }, + { + "epoch": 0.96, + "learning_rate": 1.3594632768361582e-05, + "loss": 0.4521, + "step": 11791 + }, + { + "epoch": 0.96, + "learning_rate": 1.3594089526292918e-05, + "loss": 0.4767, + "step": 11792 + }, + { + "epoch": 0.96, + "learning_rate": 1.359354628422425e-05, + "loss": 0.5522, + "step": 11793 + }, + { + "epoch": 0.96, + "learning_rate": 1.3593003042155586e-05, + "loss": 0.3934, + "step": 11794 + }, + { + "epoch": 0.96, + "learning_rate": 1.3592459800086919e-05, + "loss": 0.3554, + "step": 11795 + }, + { + "epoch": 0.96, + "learning_rate": 1.3591916558018255e-05, + "loss": 0.3248, + "step": 11796 + }, + { + "epoch": 0.96, + "learning_rate": 1.3591373315949587e-05, + "loss": 0.4203, + "step": 11797 + }, + { + "epoch": 0.96, + "learning_rate": 1.3590830073880923e-05, + "loss": 0.5665, + "step": 11798 + }, + { + "epoch": 0.96, + "learning_rate": 1.3590286831812256e-05, + "loss": 0.4361, + "step": 11799 + }, + { + "epoch": 0.96, + "learning_rate": 1.3589743589743592e-05, + "loss": 0.4823, + "step": 11800 + }, + { + "epoch": 0.96, + "learning_rate": 1.3589200347674924e-05, + "loss": 0.4443, + "step": 11801 + }, + { + "epoch": 0.96, + "learning_rate": 1.358865710560626e-05, + "loss": 0.3427, + "step": 11802 + }, + { + "epoch": 0.96, + "learning_rate": 1.3588113863537593e-05, + "loss": 0.57, + "step": 11803 + }, + { + "epoch": 0.96, + "learning_rate": 1.3587570621468929e-05, + "loss": 0.4157, + "step": 11804 + }, + { + "epoch": 0.96, + "learning_rate": 1.3587027379400261e-05, + "loss": 0.5215, + "step": 11805 + }, + { + "epoch": 0.96, + "learning_rate": 1.3586484137331597e-05, + "loss": 0.4297, + "step": 11806 + }, + { + "epoch": 0.96, + "learning_rate": 1.358594089526293e-05, + "loss": 0.4563, + "step": 11807 + }, + { + "epoch": 0.96, + "learning_rate": 1.3585397653194266e-05, + "loss": 0.4602, + "step": 11808 + }, + { + "epoch": 0.96, + "learning_rate": 1.3584854411125598e-05, + "loss": 0.5538, + "step": 11809 + }, + { + "epoch": 0.96, + "learning_rate": 1.3584311169056932e-05, + "loss": 0.3151, + "step": 11810 + }, + { + "epoch": 0.96, + "learning_rate": 1.3583767926988267e-05, + "loss": 0.4474, + "step": 11811 + }, + { + "epoch": 0.96, + "learning_rate": 1.35832246849196e-05, + "loss": 0.5632, + "step": 11812 + }, + { + "epoch": 0.96, + "learning_rate": 1.3582681442850935e-05, + "loss": 0.3947, + "step": 11813 + }, + { + "epoch": 0.96, + "learning_rate": 1.358213820078227e-05, + "loss": 0.4739, + "step": 11814 + }, + { + "epoch": 0.96, + "learning_rate": 1.3581594958713603e-05, + "loss": 0.4186, + "step": 11815 + }, + { + "epoch": 0.96, + "learning_rate": 1.3581051716644938e-05, + "loss": 0.4105, + "step": 11816 + }, + { + "epoch": 0.96, + "learning_rate": 1.3580508474576272e-05, + "loss": 0.5245, + "step": 11817 + }, + { + "epoch": 0.96, + "learning_rate": 1.3579965232507606e-05, + "loss": 0.7585, + "step": 11818 + }, + { + "epoch": 0.96, + "learning_rate": 1.3579421990438942e-05, + "loss": 0.5448, + "step": 11819 + }, + { + "epoch": 0.96, + "learning_rate": 1.3578878748370275e-05, + "loss": 0.3607, + "step": 11820 + }, + { + "epoch": 0.96, + "learning_rate": 1.357833550630161e-05, + "loss": 0.6974, + "step": 11821 + }, + { + "epoch": 0.96, + "learning_rate": 1.3577792264232943e-05, + "loss": 0.2911, + "step": 11822 + }, + { + "epoch": 0.96, + "learning_rate": 1.3577249022164279e-05, + "loss": 0.4577, + "step": 11823 + }, + { + "epoch": 0.96, + "learning_rate": 1.3576705780095612e-05, + "loss": 0.3732, + "step": 11824 + }, + { + "epoch": 0.96, + "learning_rate": 1.3576162538026947e-05, + "loss": 0.3724, + "step": 11825 + }, + { + "epoch": 0.96, + "learning_rate": 1.357561929595828e-05, + "loss": 0.328, + "step": 11826 + }, + { + "epoch": 0.96, + "learning_rate": 1.3575076053889616e-05, + "loss": 0.489, + "step": 11827 + }, + { + "epoch": 0.96, + "learning_rate": 1.3574532811820948e-05, + "loss": 0.6004, + "step": 11828 + }, + { + "epoch": 0.96, + "learning_rate": 1.3573989569752281e-05, + "loss": 0.6391, + "step": 11829 + }, + { + "epoch": 0.96, + "learning_rate": 1.3573446327683617e-05, + "loss": 0.4451, + "step": 11830 + }, + { + "epoch": 0.96, + "learning_rate": 1.357290308561495e-05, + "loss": 0.4784, + "step": 11831 + }, + { + "epoch": 0.96, + "learning_rate": 1.3572359843546285e-05, + "loss": 0.3275, + "step": 11832 + }, + { + "epoch": 0.96, + "learning_rate": 1.3571816601477618e-05, + "loss": 0.4831, + "step": 11833 + }, + { + "epoch": 0.96, + "learning_rate": 1.3571273359408954e-05, + "loss": 0.6412, + "step": 11834 + }, + { + "epoch": 0.96, + "learning_rate": 1.3570730117340286e-05, + "loss": 0.4834, + "step": 11835 + }, + { + "epoch": 0.96, + "learning_rate": 1.3570186875271622e-05, + "loss": 0.3974, + "step": 11836 + }, + { + "epoch": 0.96, + "learning_rate": 1.3569643633202957e-05, + "loss": 0.5086, + "step": 11837 + }, + { + "epoch": 0.96, + "learning_rate": 1.356910039113429e-05, + "loss": 0.2428, + "step": 11838 + }, + { + "epoch": 0.96, + "learning_rate": 1.3568557149065625e-05, + "loss": 0.5446, + "step": 11839 + }, + { + "epoch": 0.96, + "learning_rate": 1.356801390699696e-05, + "loss": 0.2277, + "step": 11840 + }, + { + "epoch": 0.96, + "learning_rate": 1.3567470664928293e-05, + "loss": 0.5333, + "step": 11841 + }, + { + "epoch": 0.96, + "learning_rate": 1.3566927422859628e-05, + "loss": 0.5644, + "step": 11842 + }, + { + "epoch": 0.97, + "learning_rate": 1.3566384180790962e-05, + "loss": 0.5909, + "step": 11843 + }, + { + "epoch": 0.97, + "learning_rate": 1.3565840938722296e-05, + "loss": 0.4823, + "step": 11844 + }, + { + "epoch": 0.97, + "learning_rate": 1.356529769665363e-05, + "loss": 0.3075, + "step": 11845 + }, + { + "epoch": 0.97, + "learning_rate": 1.3564754454584965e-05, + "loss": 0.3775, + "step": 11846 + }, + { + "epoch": 0.97, + "learning_rate": 1.3564211212516299e-05, + "loss": 0.5186, + "step": 11847 + }, + { + "epoch": 0.97, + "learning_rate": 1.3563667970447631e-05, + "loss": 0.3212, + "step": 11848 + }, + { + "epoch": 0.97, + "learning_rate": 1.3563124728378967e-05, + "loss": 0.4391, + "step": 11849 + }, + { + "epoch": 0.97, + "learning_rate": 1.35625814863103e-05, + "loss": 0.4478, + "step": 11850 + }, + { + "epoch": 0.97, + "learning_rate": 1.3562038244241636e-05, + "loss": 0.6428, + "step": 11851 + }, + { + "epoch": 0.97, + "learning_rate": 1.3561495002172968e-05, + "loss": 0.623, + "step": 11852 + }, + { + "epoch": 0.97, + "learning_rate": 1.3560951760104304e-05, + "loss": 0.4415, + "step": 11853 + }, + { + "epoch": 0.97, + "learning_rate": 1.3560408518035637e-05, + "loss": 0.4407, + "step": 11854 + }, + { + "epoch": 0.97, + "learning_rate": 1.3559865275966973e-05, + "loss": 0.4983, + "step": 11855 + }, + { + "epoch": 0.97, + "learning_rate": 1.3559322033898305e-05, + "loss": 0.3989, + "step": 11856 + }, + { + "epoch": 0.97, + "learning_rate": 1.3558778791829641e-05, + "loss": 0.4621, + "step": 11857 + }, + { + "epoch": 0.97, + "learning_rate": 1.3558235549760974e-05, + "loss": 0.3785, + "step": 11858 + }, + { + "epoch": 0.97, + "learning_rate": 1.355769230769231e-05, + "loss": 0.2925, + "step": 11859 + }, + { + "epoch": 0.97, + "learning_rate": 1.3557149065623642e-05, + "loss": 0.7254, + "step": 11860 + }, + { + "epoch": 0.97, + "learning_rate": 1.3556605823554978e-05, + "loss": 0.5225, + "step": 11861 + }, + { + "epoch": 0.97, + "learning_rate": 1.355606258148631e-05, + "loss": 0.5589, + "step": 11862 + }, + { + "epoch": 0.97, + "learning_rate": 1.3555519339417647e-05, + "loss": 0.4651, + "step": 11863 + }, + { + "epoch": 0.97, + "learning_rate": 1.3554976097348979e-05, + "loss": 0.3528, + "step": 11864 + }, + { + "epoch": 0.97, + "learning_rate": 1.3554432855280315e-05, + "loss": 0.3453, + "step": 11865 + }, + { + "epoch": 0.97, + "learning_rate": 1.3553889613211648e-05, + "loss": 0.4358, + "step": 11866 + }, + { + "epoch": 0.97, + "learning_rate": 1.3553346371142982e-05, + "loss": 0.5234, + "step": 11867 + }, + { + "epoch": 0.97, + "learning_rate": 1.3552803129074316e-05, + "loss": 0.4438, + "step": 11868 + }, + { + "epoch": 0.97, + "learning_rate": 1.355225988700565e-05, + "loss": 0.7419, + "step": 11869 + }, + { + "epoch": 0.97, + "learning_rate": 1.3551716644936984e-05, + "loss": 0.4237, + "step": 11870 + }, + { + "epoch": 0.97, + "learning_rate": 1.3551173402868319e-05, + "loss": 0.4113, + "step": 11871 + }, + { + "epoch": 0.97, + "learning_rate": 1.3550630160799653e-05, + "loss": 0.3485, + "step": 11872 + }, + { + "epoch": 0.97, + "learning_rate": 1.3550086918730987e-05, + "loss": 0.5201, + "step": 11873 + }, + { + "epoch": 0.97, + "learning_rate": 1.3549543676662323e-05, + "loss": 0.7642, + "step": 11874 + }, + { + "epoch": 0.97, + "learning_rate": 1.3549000434593656e-05, + "loss": 0.5324, + "step": 11875 + }, + { + "epoch": 0.97, + "learning_rate": 1.3548457192524992e-05, + "loss": 0.4876, + "step": 11876 + }, + { + "epoch": 0.97, + "learning_rate": 1.3547913950456324e-05, + "loss": 0.5544, + "step": 11877 + }, + { + "epoch": 0.97, + "learning_rate": 1.354737070838766e-05, + "loss": 0.6518, + "step": 11878 + }, + { + "epoch": 0.97, + "learning_rate": 1.3546827466318993e-05, + "loss": 0.464, + "step": 11879 + }, + { + "epoch": 0.97, + "learning_rate": 1.3546284224250328e-05, + "loss": 0.5393, + "step": 11880 + }, + { + "epoch": 0.97, + "learning_rate": 1.3545740982181661e-05, + "loss": 0.3678, + "step": 11881 + }, + { + "epoch": 0.97, + "learning_rate": 1.3545197740112997e-05, + "loss": 0.5053, + "step": 11882 + }, + { + "epoch": 0.97, + "learning_rate": 1.354465449804433e-05, + "loss": 0.3632, + "step": 11883 + }, + { + "epoch": 0.97, + "learning_rate": 1.3544111255975665e-05, + "loss": 0.4244, + "step": 11884 + }, + { + "epoch": 0.97, + "learning_rate": 1.3543568013906998e-05, + "loss": 0.5649, + "step": 11885 + }, + { + "epoch": 0.97, + "learning_rate": 1.354302477183833e-05, + "loss": 0.3297, + "step": 11886 + }, + { + "epoch": 0.97, + "learning_rate": 1.3542481529769666e-05, + "loss": 0.1792, + "step": 11887 + }, + { + "epoch": 0.97, + "learning_rate": 1.3541938287700999e-05, + "loss": 0.6212, + "step": 11888 + }, + { + "epoch": 0.97, + "learning_rate": 1.3541395045632335e-05, + "loss": 0.236, + "step": 11889 + }, + { + "epoch": 0.97, + "learning_rate": 1.3540851803563669e-05, + "loss": 0.3745, + "step": 11890 + }, + { + "epoch": 0.97, + "learning_rate": 1.3540308561495003e-05, + "loss": 0.2777, + "step": 11891 + }, + { + "epoch": 0.97, + "learning_rate": 1.3539765319426338e-05, + "loss": 0.3404, + "step": 11892 + }, + { + "epoch": 0.97, + "learning_rate": 1.3539222077357672e-05, + "loss": 0.3784, + "step": 11893 + }, + { + "epoch": 0.97, + "learning_rate": 1.3538678835289006e-05, + "loss": 0.4152, + "step": 11894 + }, + { + "epoch": 0.97, + "learning_rate": 1.353813559322034e-05, + "loss": 0.3637, + "step": 11895 + }, + { + "epoch": 0.97, + "learning_rate": 1.3537592351151674e-05, + "loss": 0.4254, + "step": 11896 + }, + { + "epoch": 0.97, + "learning_rate": 1.3537049109083009e-05, + "loss": 0.3274, + "step": 11897 + }, + { + "epoch": 0.97, + "learning_rate": 1.3536505867014343e-05, + "loss": 0.5205, + "step": 11898 + }, + { + "epoch": 0.97, + "learning_rate": 1.3535962624945677e-05, + "loss": 0.5611, + "step": 11899 + }, + { + "epoch": 0.97, + "learning_rate": 1.3535419382877011e-05, + "loss": 0.5162, + "step": 11900 + }, + { + "epoch": 0.97, + "learning_rate": 1.3534876140808346e-05, + "loss": 0.2744, + "step": 11901 + }, + { + "epoch": 0.97, + "learning_rate": 1.353433289873968e-05, + "loss": 0.3692, + "step": 11902 + }, + { + "epoch": 0.97, + "learning_rate": 1.3533789656671014e-05, + "loss": 0.5178, + "step": 11903 + }, + { + "epoch": 0.97, + "learning_rate": 1.3533246414602348e-05, + "loss": 0.4182, + "step": 11904 + }, + { + "epoch": 0.97, + "learning_rate": 1.3532703172533681e-05, + "loss": 0.7227, + "step": 11905 + }, + { + "epoch": 0.97, + "learning_rate": 1.3532159930465017e-05, + "loss": 0.3487, + "step": 11906 + }, + { + "epoch": 0.97, + "learning_rate": 1.353161668839635e-05, + "loss": 0.2184, + "step": 11907 + }, + { + "epoch": 0.97, + "learning_rate": 1.3531073446327685e-05, + "loss": 0.2529, + "step": 11908 + }, + { + "epoch": 0.97, + "learning_rate": 1.3530530204259018e-05, + "loss": 0.5504, + "step": 11909 + }, + { + "epoch": 0.97, + "learning_rate": 1.3529986962190354e-05, + "loss": 0.3587, + "step": 11910 + }, + { + "epoch": 0.97, + "learning_rate": 1.3529443720121686e-05, + "loss": 0.3124, + "step": 11911 + }, + { + "epoch": 0.97, + "learning_rate": 1.3528900478053022e-05, + "loss": 0.3555, + "step": 11912 + }, + { + "epoch": 0.97, + "learning_rate": 1.3528357235984355e-05, + "loss": 0.3917, + "step": 11913 + }, + { + "epoch": 0.97, + "learning_rate": 1.352781399391569e-05, + "loss": 0.2558, + "step": 11914 + }, + { + "epoch": 0.97, + "learning_rate": 1.3527270751847023e-05, + "loss": 0.4265, + "step": 11915 + }, + { + "epoch": 0.97, + "learning_rate": 1.3526727509778359e-05, + "loss": 0.425, + "step": 11916 + }, + { + "epoch": 0.97, + "learning_rate": 1.3526184267709692e-05, + "loss": 0.6196, + "step": 11917 + }, + { + "epoch": 0.97, + "learning_rate": 1.3525641025641028e-05, + "loss": 0.3682, + "step": 11918 + }, + { + "epoch": 0.97, + "learning_rate": 1.352509778357236e-05, + "loss": 0.1755, + "step": 11919 + }, + { + "epoch": 0.97, + "learning_rate": 1.3524554541503696e-05, + "loss": 0.5116, + "step": 11920 + }, + { + "epoch": 0.97, + "learning_rate": 1.3524011299435029e-05, + "loss": 0.2948, + "step": 11921 + }, + { + "epoch": 0.97, + "learning_rate": 1.3523468057366364e-05, + "loss": 0.3399, + "step": 11922 + }, + { + "epoch": 0.97, + "learning_rate": 1.3522924815297697e-05, + "loss": 0.207, + "step": 11923 + }, + { + "epoch": 0.97, + "learning_rate": 1.3522381573229031e-05, + "loss": 0.6713, + "step": 11924 + }, + { + "epoch": 0.97, + "learning_rate": 1.3521838331160365e-05, + "loss": 0.2636, + "step": 11925 + }, + { + "epoch": 0.97, + "learning_rate": 1.35212950890917e-05, + "loss": 0.5403, + "step": 11926 + }, + { + "epoch": 0.97, + "learning_rate": 1.3520751847023036e-05, + "loss": 0.7713, + "step": 11927 + }, + { + "epoch": 0.97, + "learning_rate": 1.3520208604954368e-05, + "loss": 0.4762, + "step": 11928 + }, + { + "epoch": 0.97, + "learning_rate": 1.3519665362885704e-05, + "loss": 0.7445, + "step": 11929 + }, + { + "epoch": 0.97, + "learning_rate": 1.3519122120817037e-05, + "loss": 0.532, + "step": 11930 + }, + { + "epoch": 0.97, + "learning_rate": 1.3518578878748373e-05, + "loss": 0.522, + "step": 11931 + }, + { + "epoch": 0.97, + "learning_rate": 1.3518035636679705e-05, + "loss": 0.5237, + "step": 11932 + }, + { + "epoch": 0.97, + "learning_rate": 1.3517492394611041e-05, + "loss": 0.6448, + "step": 11933 + }, + { + "epoch": 0.97, + "learning_rate": 1.3516949152542374e-05, + "loss": 0.7543, + "step": 11934 + }, + { + "epoch": 0.97, + "learning_rate": 1.351640591047371e-05, + "loss": 0.4078, + "step": 11935 + }, + { + "epoch": 0.97, + "learning_rate": 1.3515862668405042e-05, + "loss": 0.4995, + "step": 11936 + }, + { + "epoch": 0.97, + "learning_rate": 1.3515319426336378e-05, + "loss": 0.5936, + "step": 11937 + }, + { + "epoch": 0.97, + "learning_rate": 1.351477618426771e-05, + "loss": 0.3877, + "step": 11938 + }, + { + "epoch": 0.97, + "learning_rate": 1.3514232942199046e-05, + "loss": 0.4321, + "step": 11939 + }, + { + "epoch": 0.97, + "learning_rate": 1.3513689700130379e-05, + "loss": 0.4219, + "step": 11940 + }, + { + "epoch": 0.97, + "learning_rate": 1.3513146458061715e-05, + "loss": 0.4146, + "step": 11941 + }, + { + "epoch": 0.97, + "learning_rate": 1.3512603215993047e-05, + "loss": 0.3349, + "step": 11942 + }, + { + "epoch": 0.97, + "learning_rate": 1.351205997392438e-05, + "loss": 0.3389, + "step": 11943 + }, + { + "epoch": 0.97, + "learning_rate": 1.3511516731855716e-05, + "loss": 0.2604, + "step": 11944 + }, + { + "epoch": 0.97, + "learning_rate": 1.351097348978705e-05, + "loss": 0.3837, + "step": 11945 + }, + { + "epoch": 0.97, + "learning_rate": 1.3510430247718384e-05, + "loss": 0.4356, + "step": 11946 + }, + { + "epoch": 0.97, + "learning_rate": 1.3509887005649719e-05, + "loss": 0.3331, + "step": 11947 + }, + { + "epoch": 0.97, + "learning_rate": 1.3509343763581053e-05, + "loss": 0.4382, + "step": 11948 + }, + { + "epoch": 0.97, + "learning_rate": 1.3508800521512387e-05, + "loss": 0.5364, + "step": 11949 + }, + { + "epoch": 0.97, + "learning_rate": 1.3508257279443721e-05, + "loss": 0.6541, + "step": 11950 + }, + { + "epoch": 0.97, + "learning_rate": 1.3507714037375055e-05, + "loss": 0.2902, + "step": 11951 + }, + { + "epoch": 0.97, + "learning_rate": 1.350717079530639e-05, + "loss": 0.269, + "step": 11952 + }, + { + "epoch": 0.97, + "learning_rate": 1.3506627553237724e-05, + "loss": 0.4591, + "step": 11953 + }, + { + "epoch": 0.97, + "learning_rate": 1.3506084311169058e-05, + "loss": 0.4717, + "step": 11954 + }, + { + "epoch": 0.97, + "learning_rate": 1.3505541069100392e-05, + "loss": 0.3435, + "step": 11955 + }, + { + "epoch": 0.97, + "learning_rate": 1.3504997827031727e-05, + "loss": 0.4678, + "step": 11956 + }, + { + "epoch": 0.97, + "learning_rate": 1.350445458496306e-05, + "loss": 0.5357, + "step": 11957 + }, + { + "epoch": 0.97, + "learning_rate": 1.3503911342894395e-05, + "loss": 0.4, + "step": 11958 + }, + { + "epoch": 0.97, + "learning_rate": 1.350336810082573e-05, + "loss": 0.4247, + "step": 11959 + }, + { + "epoch": 0.97, + "learning_rate": 1.3502824858757064e-05, + "loss": 0.6641, + "step": 11960 + }, + { + "epoch": 0.97, + "learning_rate": 1.3502281616688398e-05, + "loss": 0.2854, + "step": 11961 + }, + { + "epoch": 0.97, + "learning_rate": 1.350173837461973e-05, + "loss": 0.4409, + "step": 11962 + }, + { + "epoch": 0.97, + "learning_rate": 1.3501195132551066e-05, + "loss": 0.5645, + "step": 11963 + }, + { + "epoch": 0.97, + "learning_rate": 1.3500651890482399e-05, + "loss": 0.488, + "step": 11964 + }, + { + "epoch": 0.97, + "learning_rate": 1.3500108648413735e-05, + "loss": 0.5372, + "step": 11965 + }, + { + "epoch": 0.98, + "learning_rate": 1.3499565406345067e-05, + "loss": 0.5296, + "step": 11966 + }, + { + "epoch": 0.98, + "learning_rate": 1.3499022164276403e-05, + "loss": 0.342, + "step": 11967 + }, + { + "epoch": 0.98, + "learning_rate": 1.3498478922207736e-05, + "loss": 0.3884, + "step": 11968 + }, + { + "epoch": 0.98, + "learning_rate": 1.3497935680139072e-05, + "loss": 0.3521, + "step": 11969 + }, + { + "epoch": 0.98, + "learning_rate": 1.3497392438070404e-05, + "loss": 0.7217, + "step": 11970 + }, + { + "epoch": 0.98, + "learning_rate": 1.349684919600174e-05, + "loss": 0.6765, + "step": 11971 + }, + { + "epoch": 0.98, + "learning_rate": 1.3496305953933073e-05, + "loss": 0.4003, + "step": 11972 + }, + { + "epoch": 0.98, + "learning_rate": 1.3495762711864409e-05, + "loss": 0.4738, + "step": 11973 + }, + { + "epoch": 0.98, + "learning_rate": 1.3495219469795741e-05, + "loss": 0.6339, + "step": 11974 + }, + { + "epoch": 0.98, + "learning_rate": 1.3494676227727077e-05, + "loss": 0.5116, + "step": 11975 + }, + { + "epoch": 0.98, + "learning_rate": 1.349413298565841e-05, + "loss": 0.4446, + "step": 11976 + }, + { + "epoch": 0.98, + "learning_rate": 1.3493589743589745e-05, + "loss": 0.3173, + "step": 11977 + }, + { + "epoch": 0.98, + "learning_rate": 1.3493046501521078e-05, + "loss": 0.4, + "step": 11978 + }, + { + "epoch": 0.98, + "learning_rate": 1.3492503259452414e-05, + "loss": 0.5536, + "step": 11979 + }, + { + "epoch": 0.98, + "learning_rate": 1.3491960017383746e-05, + "loss": 0.4997, + "step": 11980 + }, + { + "epoch": 0.98, + "learning_rate": 1.349141677531508e-05, + "loss": 0.4898, + "step": 11981 + }, + { + "epoch": 0.98, + "learning_rate": 1.3490873533246417e-05, + "loss": 0.3636, + "step": 11982 + }, + { + "epoch": 0.98, + "learning_rate": 1.3490330291177749e-05, + "loss": 0.7541, + "step": 11983 + }, + { + "epoch": 0.98, + "learning_rate": 1.3489787049109085e-05, + "loss": 0.5574, + "step": 11984 + }, + { + "epoch": 0.98, + "learning_rate": 1.3489243807040418e-05, + "loss": 0.6649, + "step": 11985 + }, + { + "epoch": 0.98, + "learning_rate": 1.3488700564971754e-05, + "loss": 0.3872, + "step": 11986 + }, + { + "epoch": 0.98, + "learning_rate": 1.3488157322903086e-05, + "loss": 0.4451, + "step": 11987 + }, + { + "epoch": 0.98, + "learning_rate": 1.3487614080834422e-05, + "loss": 0.4516, + "step": 11988 + }, + { + "epoch": 0.98, + "learning_rate": 1.3487070838765755e-05, + "loss": 0.6, + "step": 11989 + }, + { + "epoch": 0.98, + "learning_rate": 1.348652759669709e-05, + "loss": 0.2698, + "step": 11990 + }, + { + "epoch": 0.98, + "learning_rate": 1.3485984354628423e-05, + "loss": 0.3456, + "step": 11991 + }, + { + "epoch": 0.98, + "learning_rate": 1.3485441112559759e-05, + "loss": 0.4971, + "step": 11992 + }, + { + "epoch": 0.98, + "learning_rate": 1.3484897870491091e-05, + "loss": 0.4407, + "step": 11993 + }, + { + "epoch": 0.98, + "learning_rate": 1.3484354628422427e-05, + "loss": 0.698, + "step": 11994 + }, + { + "epoch": 0.98, + "learning_rate": 1.348381138635376e-05, + "loss": 0.4404, + "step": 11995 + }, + { + "epoch": 0.98, + "learning_rate": 1.3483268144285096e-05, + "loss": 0.3692, + "step": 11996 + }, + { + "epoch": 0.98, + "learning_rate": 1.3482724902216428e-05, + "loss": 0.6479, + "step": 11997 + }, + { + "epoch": 0.98, + "learning_rate": 1.3482181660147764e-05, + "loss": 0.4926, + "step": 11998 + }, + { + "epoch": 0.98, + "learning_rate": 1.3481638418079097e-05, + "loss": 0.5153, + "step": 11999 + }, + { + "epoch": 0.98, + "learning_rate": 1.3481095176010431e-05, + "loss": 0.2796, + "step": 12000 + }, + { + "epoch": 0.98, + "eval_accuracy": 0.8342333163525216, + "eval_loss": 0.42216214537620544, + "eval_runtime": 22.3297, + "eval_samples_per_second": 439.549, + "eval_steps_per_second": 3.448, + "step": 12000 + }, + { + "epoch": 0.98, + "learning_rate": 1.3480551933941765e-05, + "loss": 0.5166, + "step": 12001 + }, + { + "epoch": 0.98, + "learning_rate": 1.34800086918731e-05, + "loss": 0.6927, + "step": 12002 + }, + { + "epoch": 0.98, + "learning_rate": 1.3479465449804434e-05, + "loss": 0.5963, + "step": 12003 + }, + { + "epoch": 0.98, + "learning_rate": 1.3478922207735768e-05, + "loss": 0.6786, + "step": 12004 + }, + { + "epoch": 0.98, + "learning_rate": 1.3478378965667102e-05, + "loss": 0.4698, + "step": 12005 + }, + { + "epoch": 0.98, + "learning_rate": 1.3477835723598436e-05, + "loss": 0.3518, + "step": 12006 + }, + { + "epoch": 0.98, + "learning_rate": 1.347729248152977e-05, + "loss": 0.509, + "step": 12007 + }, + { + "epoch": 0.98, + "learning_rate": 1.3476749239461105e-05, + "loss": 0.5897, + "step": 12008 + }, + { + "epoch": 0.98, + "learning_rate": 1.3476205997392439e-05, + "loss": 0.479, + "step": 12009 + }, + { + "epoch": 0.98, + "learning_rate": 1.3475662755323773e-05, + "loss": 0.2178, + "step": 12010 + }, + { + "epoch": 0.98, + "learning_rate": 1.3475119513255108e-05, + "loss": 0.3485, + "step": 12011 + }, + { + "epoch": 0.98, + "learning_rate": 1.3474576271186442e-05, + "loss": 0.3767, + "step": 12012 + }, + { + "epoch": 0.98, + "learning_rate": 1.3474033029117776e-05, + "loss": 0.374, + "step": 12013 + }, + { + "epoch": 0.98, + "learning_rate": 1.347348978704911e-05, + "loss": 0.5103, + "step": 12014 + }, + { + "epoch": 0.98, + "learning_rate": 1.3472946544980445e-05, + "loss": 0.5315, + "step": 12015 + }, + { + "epoch": 0.98, + "learning_rate": 1.3472403302911779e-05, + "loss": 0.5368, + "step": 12016 + }, + { + "epoch": 0.98, + "learning_rate": 1.3471860060843113e-05, + "loss": 0.4258, + "step": 12017 + }, + { + "epoch": 0.98, + "learning_rate": 1.3471316818774447e-05, + "loss": 0.3317, + "step": 12018 + }, + { + "epoch": 0.98, + "learning_rate": 1.347077357670578e-05, + "loss": 0.3783, + "step": 12019 + }, + { + "epoch": 0.98, + "learning_rate": 1.3470230334637116e-05, + "loss": 0.43, + "step": 12020 + }, + { + "epoch": 0.98, + "learning_rate": 1.3469687092568448e-05, + "loss": 0.6283, + "step": 12021 + }, + { + "epoch": 0.98, + "learning_rate": 1.3469143850499784e-05, + "loss": 0.3149, + "step": 12022 + }, + { + "epoch": 0.98, + "learning_rate": 1.3468600608431117e-05, + "loss": 0.2977, + "step": 12023 + }, + { + "epoch": 0.98, + "learning_rate": 1.3468057366362453e-05, + "loss": 0.5942, + "step": 12024 + }, + { + "epoch": 0.98, + "learning_rate": 1.3467514124293785e-05, + "loss": 0.2698, + "step": 12025 + }, + { + "epoch": 0.98, + "learning_rate": 1.3466970882225121e-05, + "loss": 0.1776, + "step": 12026 + }, + { + "epoch": 0.98, + "learning_rate": 1.3466427640156454e-05, + "loss": 0.4024, + "step": 12027 + }, + { + "epoch": 0.98, + "learning_rate": 1.346588439808779e-05, + "loss": 0.4551, + "step": 12028 + }, + { + "epoch": 0.98, + "learning_rate": 1.3465341156019122e-05, + "loss": 0.2455, + "step": 12029 + }, + { + "epoch": 0.98, + "learning_rate": 1.3464797913950458e-05, + "loss": 0.6367, + "step": 12030 + }, + { + "epoch": 0.98, + "learning_rate": 1.346425467188179e-05, + "loss": 0.4697, + "step": 12031 + }, + { + "epoch": 0.98, + "learning_rate": 1.3463711429813126e-05, + "loss": 0.4788, + "step": 12032 + }, + { + "epoch": 0.98, + "learning_rate": 1.3463168187744459e-05, + "loss": 0.4, + "step": 12033 + }, + { + "epoch": 0.98, + "learning_rate": 1.3462624945675795e-05, + "loss": 0.3549, + "step": 12034 + }, + { + "epoch": 0.98, + "learning_rate": 1.3462081703607129e-05, + "loss": 0.6419, + "step": 12035 + }, + { + "epoch": 0.98, + "learning_rate": 1.3461538461538463e-05, + "loss": 0.3454, + "step": 12036 + }, + { + "epoch": 0.98, + "learning_rate": 1.3460995219469798e-05, + "loss": 0.846, + "step": 12037 + }, + { + "epoch": 0.98, + "learning_rate": 1.346045197740113e-05, + "loss": 0.4074, + "step": 12038 + }, + { + "epoch": 0.98, + "learning_rate": 1.3459908735332466e-05, + "loss": 0.6328, + "step": 12039 + }, + { + "epoch": 0.98, + "learning_rate": 1.3459365493263799e-05, + "loss": 0.3384, + "step": 12040 + }, + { + "epoch": 0.98, + "learning_rate": 1.3458822251195135e-05, + "loss": 0.5305, + "step": 12041 + }, + { + "epoch": 0.98, + "learning_rate": 1.3458279009126467e-05, + "loss": 0.461, + "step": 12042 + }, + { + "epoch": 0.98, + "learning_rate": 1.3457735767057803e-05, + "loss": 0.3181, + "step": 12043 + }, + { + "epoch": 0.98, + "learning_rate": 1.3457192524989136e-05, + "loss": 0.3592, + "step": 12044 + }, + { + "epoch": 0.98, + "learning_rate": 1.3456649282920471e-05, + "loss": 0.2864, + "step": 12045 + }, + { + "epoch": 0.98, + "learning_rate": 1.3456106040851804e-05, + "loss": 0.6195, + "step": 12046 + }, + { + "epoch": 0.98, + "learning_rate": 1.345556279878314e-05, + "loss": 0.3679, + "step": 12047 + }, + { + "epoch": 0.98, + "learning_rate": 1.3455019556714472e-05, + "loss": 0.3283, + "step": 12048 + }, + { + "epoch": 0.98, + "learning_rate": 1.3454476314645808e-05, + "loss": 0.4832, + "step": 12049 + }, + { + "epoch": 0.98, + "learning_rate": 1.3453933072577141e-05, + "loss": 0.8436, + "step": 12050 + }, + { + "epoch": 0.98, + "learning_rate": 1.3453389830508477e-05, + "loss": 0.5926, + "step": 12051 + }, + { + "epoch": 0.98, + "learning_rate": 1.345284658843981e-05, + "loss": 0.4301, + "step": 12052 + }, + { + "epoch": 0.98, + "learning_rate": 1.3452303346371145e-05, + "loss": 0.4136, + "step": 12053 + }, + { + "epoch": 0.98, + "learning_rate": 1.3451760104302478e-05, + "loss": 0.3836, + "step": 12054 + }, + { + "epoch": 0.98, + "learning_rate": 1.3451216862233814e-05, + "loss": 0.3646, + "step": 12055 + }, + { + "epoch": 0.98, + "learning_rate": 1.3450673620165146e-05, + "loss": 0.426, + "step": 12056 + }, + { + "epoch": 0.98, + "learning_rate": 1.345013037809648e-05, + "loss": 0.5729, + "step": 12057 + }, + { + "epoch": 0.98, + "learning_rate": 1.3449587136027815e-05, + "loss": 0.4175, + "step": 12058 + }, + { + "epoch": 0.98, + "learning_rate": 1.3449043893959149e-05, + "loss": 0.3743, + "step": 12059 + }, + { + "epoch": 0.98, + "learning_rate": 1.3448500651890483e-05, + "loss": 0.4625, + "step": 12060 + }, + { + "epoch": 0.98, + "learning_rate": 1.3447957409821817e-05, + "loss": 0.4301, + "step": 12061 + }, + { + "epoch": 0.98, + "learning_rate": 1.3447414167753152e-05, + "loss": 0.3909, + "step": 12062 + }, + { + "epoch": 0.98, + "learning_rate": 1.3446870925684486e-05, + "loss": 0.3382, + "step": 12063 + }, + { + "epoch": 0.98, + "learning_rate": 1.344632768361582e-05, + "loss": 0.648, + "step": 12064 + }, + { + "epoch": 0.98, + "learning_rate": 1.3445784441547154e-05, + "loss": 0.4165, + "step": 12065 + }, + { + "epoch": 0.98, + "learning_rate": 1.3445241199478489e-05, + "loss": 0.3564, + "step": 12066 + }, + { + "epoch": 0.98, + "learning_rate": 1.3444697957409823e-05, + "loss": 0.3436, + "step": 12067 + }, + { + "epoch": 0.98, + "learning_rate": 1.3444154715341157e-05, + "loss": 0.4969, + "step": 12068 + }, + { + "epoch": 0.98, + "learning_rate": 1.3443611473272491e-05, + "loss": 0.3142, + "step": 12069 + }, + { + "epoch": 0.98, + "learning_rate": 1.3443068231203826e-05, + "loss": 0.502, + "step": 12070 + }, + { + "epoch": 0.98, + "learning_rate": 1.344252498913516e-05, + "loss": 0.5287, + "step": 12071 + }, + { + "epoch": 0.98, + "learning_rate": 1.3441981747066496e-05, + "loss": 0.6054, + "step": 12072 + }, + { + "epoch": 0.98, + "learning_rate": 1.3441438504997828e-05, + "loss": 0.359, + "step": 12073 + }, + { + "epoch": 0.98, + "learning_rate": 1.3440895262929164e-05, + "loss": 0.3124, + "step": 12074 + }, + { + "epoch": 0.98, + "learning_rate": 1.3440352020860497e-05, + "loss": 0.4081, + "step": 12075 + }, + { + "epoch": 0.98, + "learning_rate": 1.343980877879183e-05, + "loss": 0.3842, + "step": 12076 + }, + { + "epoch": 0.98, + "learning_rate": 1.3439265536723165e-05, + "loss": 0.3175, + "step": 12077 + }, + { + "epoch": 0.98, + "learning_rate": 1.3438722294654498e-05, + "loss": 0.2668, + "step": 12078 + }, + { + "epoch": 0.98, + "learning_rate": 1.3438179052585834e-05, + "loss": 0.3753, + "step": 12079 + }, + { + "epoch": 0.98, + "learning_rate": 1.3437635810517166e-05, + "loss": 0.4367, + "step": 12080 + }, + { + "epoch": 0.98, + "learning_rate": 1.3437092568448502e-05, + "loss": 0.6751, + "step": 12081 + }, + { + "epoch": 0.98, + "learning_rate": 1.3436549326379835e-05, + "loss": 0.499, + "step": 12082 + }, + { + "epoch": 0.98, + "learning_rate": 1.343600608431117e-05, + "loss": 0.4627, + "step": 12083 + }, + { + "epoch": 0.98, + "learning_rate": 1.3435462842242503e-05, + "loss": 0.6155, + "step": 12084 + }, + { + "epoch": 0.98, + "learning_rate": 1.3434919600173839e-05, + "loss": 0.6971, + "step": 12085 + }, + { + "epoch": 0.98, + "learning_rate": 1.3434376358105171e-05, + "loss": 0.4467, + "step": 12086 + }, + { + "epoch": 0.98, + "learning_rate": 1.3433833116036507e-05, + "loss": 0.4686, + "step": 12087 + }, + { + "epoch": 0.99, + "learning_rate": 1.343328987396784e-05, + "loss": 0.4878, + "step": 12088 + }, + { + "epoch": 0.99, + "learning_rate": 1.3432746631899176e-05, + "loss": 0.7043, + "step": 12089 + }, + { + "epoch": 0.99, + "learning_rate": 1.343220338983051e-05, + "loss": 0.4249, + "step": 12090 + }, + { + "epoch": 0.99, + "learning_rate": 1.3431660147761844e-05, + "loss": 0.2765, + "step": 12091 + }, + { + "epoch": 0.99, + "learning_rate": 1.3431116905693179e-05, + "loss": 0.5216, + "step": 12092 + }, + { + "epoch": 0.99, + "learning_rate": 1.3430573663624513e-05, + "loss": 0.5408, + "step": 12093 + }, + { + "epoch": 0.99, + "learning_rate": 1.3430030421555847e-05, + "loss": 0.183, + "step": 12094 + }, + { + "epoch": 0.99, + "learning_rate": 1.342948717948718e-05, + "loss": 0.4323, + "step": 12095 + }, + { + "epoch": 0.99, + "learning_rate": 1.3428943937418515e-05, + "loss": 0.4547, + "step": 12096 + }, + { + "epoch": 0.99, + "learning_rate": 1.3428400695349848e-05, + "loss": 0.454, + "step": 12097 + }, + { + "epoch": 0.99, + "learning_rate": 1.3427857453281184e-05, + "loss": 0.5601, + "step": 12098 + }, + { + "epoch": 0.99, + "learning_rate": 1.3427314211212516e-05, + "loss": 0.4389, + "step": 12099 + }, + { + "epoch": 0.99, + "learning_rate": 1.3426770969143852e-05, + "loss": 0.5719, + "step": 12100 + }, + { + "epoch": 0.99, + "learning_rate": 1.3426227727075185e-05, + "loss": 0.2935, + "step": 12101 + }, + { + "epoch": 0.99, + "learning_rate": 1.3425684485006521e-05, + "loss": 0.4475, + "step": 12102 + }, + { + "epoch": 0.99, + "learning_rate": 1.3425141242937853e-05, + "loss": 0.6749, + "step": 12103 + }, + { + "epoch": 0.99, + "learning_rate": 1.342459800086919e-05, + "loss": 0.3272, + "step": 12104 + }, + { + "epoch": 0.99, + "learning_rate": 1.3424054758800522e-05, + "loss": 0.3923, + "step": 12105 + }, + { + "epoch": 0.99, + "learning_rate": 1.3423511516731858e-05, + "loss": 0.4409, + "step": 12106 + }, + { + "epoch": 0.99, + "learning_rate": 1.342296827466319e-05, + "loss": 0.4422, + "step": 12107 + }, + { + "epoch": 0.99, + "learning_rate": 1.3422425032594526e-05, + "loss": 0.5061, + "step": 12108 + }, + { + "epoch": 0.99, + "learning_rate": 1.3421881790525859e-05, + "loss": 0.2859, + "step": 12109 + }, + { + "epoch": 0.99, + "learning_rate": 1.3421338548457195e-05, + "loss": 0.611, + "step": 12110 + }, + { + "epoch": 0.99, + "learning_rate": 1.3420795306388527e-05, + "loss": 0.4595, + "step": 12111 + }, + { + "epoch": 0.99, + "learning_rate": 1.3420252064319863e-05, + "loss": 0.4893, + "step": 12112 + }, + { + "epoch": 0.99, + "learning_rate": 1.3419708822251196e-05, + "loss": 0.6139, + "step": 12113 + }, + { + "epoch": 0.99, + "learning_rate": 1.341916558018253e-05, + "loss": 0.648, + "step": 12114 + }, + { + "epoch": 0.99, + "learning_rate": 1.3418622338113864e-05, + "loss": 0.5778, + "step": 12115 + }, + { + "epoch": 0.99, + "learning_rate": 1.3418079096045198e-05, + "loss": 0.322, + "step": 12116 + }, + { + "epoch": 0.99, + "learning_rate": 1.3417535853976533e-05, + "loss": 0.479, + "step": 12117 + }, + { + "epoch": 0.99, + "learning_rate": 1.3416992611907867e-05, + "loss": 0.7562, + "step": 12118 + }, + { + "epoch": 0.99, + "learning_rate": 1.3416449369839201e-05, + "loss": 0.2189, + "step": 12119 + }, + { + "epoch": 0.99, + "learning_rate": 1.3415906127770535e-05, + "loss": 0.3661, + "step": 12120 + }, + { + "epoch": 0.99, + "learning_rate": 1.341536288570187e-05, + "loss": 0.5557, + "step": 12121 + }, + { + "epoch": 0.99, + "learning_rate": 1.3414819643633204e-05, + "loss": 0.5077, + "step": 12122 + }, + { + "epoch": 0.99, + "learning_rate": 1.3414276401564538e-05, + "loss": 0.2751, + "step": 12123 + }, + { + "epoch": 0.99, + "learning_rate": 1.3413733159495872e-05, + "loss": 0.4396, + "step": 12124 + }, + { + "epoch": 0.99, + "learning_rate": 1.3413189917427206e-05, + "loss": 0.2608, + "step": 12125 + }, + { + "epoch": 0.99, + "learning_rate": 1.341264667535854e-05, + "loss": 0.2365, + "step": 12126 + }, + { + "epoch": 0.99, + "learning_rate": 1.3412103433289877e-05, + "loss": 0.3518, + "step": 12127 + }, + { + "epoch": 0.99, + "learning_rate": 1.341156019122121e-05, + "loss": 0.3971, + "step": 12128 + }, + { + "epoch": 0.99, + "learning_rate": 1.3411016949152545e-05, + "loss": 0.284, + "step": 12129 + }, + { + "epoch": 0.99, + "learning_rate": 1.3410473707083878e-05, + "loss": 0.6011, + "step": 12130 + }, + { + "epoch": 0.99, + "learning_rate": 1.3409930465015214e-05, + "loss": 0.5164, + "step": 12131 + }, + { + "epoch": 0.99, + "learning_rate": 1.3409387222946546e-05, + "loss": 0.2355, + "step": 12132 + }, + { + "epoch": 0.99, + "learning_rate": 1.3408843980877879e-05, + "loss": 0.5452, + "step": 12133 + }, + { + "epoch": 0.99, + "learning_rate": 1.3408300738809215e-05, + "loss": 0.2115, + "step": 12134 + }, + { + "epoch": 0.99, + "learning_rate": 1.3407757496740547e-05, + "loss": 0.4606, + "step": 12135 + }, + { + "epoch": 0.99, + "learning_rate": 1.3407214254671883e-05, + "loss": 0.4391, + "step": 12136 + }, + { + "epoch": 0.99, + "learning_rate": 1.3406671012603216e-05, + "loss": 0.3449, + "step": 12137 + }, + { + "epoch": 0.99, + "learning_rate": 1.3406127770534551e-05, + "loss": 0.5606, + "step": 12138 + }, + { + "epoch": 0.99, + "learning_rate": 1.3405584528465884e-05, + "loss": 0.3824, + "step": 12139 + }, + { + "epoch": 0.99, + "learning_rate": 1.340504128639722e-05, + "loss": 0.2856, + "step": 12140 + }, + { + "epoch": 0.99, + "learning_rate": 1.3404498044328552e-05, + "loss": 0.4586, + "step": 12141 + }, + { + "epoch": 0.99, + "learning_rate": 1.3403954802259888e-05, + "loss": 0.2786, + "step": 12142 + }, + { + "epoch": 0.99, + "learning_rate": 1.3403411560191223e-05, + "loss": 0.3421, + "step": 12143 + }, + { + "epoch": 0.99, + "learning_rate": 1.3402868318122557e-05, + "loss": 0.5754, + "step": 12144 + }, + { + "epoch": 0.99, + "learning_rate": 1.3402325076053891e-05, + "loss": 0.3396, + "step": 12145 + }, + { + "epoch": 0.99, + "learning_rate": 1.3401781833985225e-05, + "loss": 0.3495, + "step": 12146 + }, + { + "epoch": 0.99, + "learning_rate": 1.340123859191656e-05, + "loss": 0.106, + "step": 12147 + }, + { + "epoch": 0.99, + "learning_rate": 1.3400695349847894e-05, + "loss": 0.2208, + "step": 12148 + }, + { + "epoch": 0.99, + "learning_rate": 1.3400152107779228e-05, + "loss": 0.2267, + "step": 12149 + }, + { + "epoch": 0.99, + "learning_rate": 1.3399608865710562e-05, + "loss": 0.3983, + "step": 12150 + }, + { + "epoch": 0.99, + "learning_rate": 1.3399065623641896e-05, + "loss": 0.3678, + "step": 12151 + }, + { + "epoch": 0.99, + "learning_rate": 1.3398522381573229e-05, + "loss": 0.4717, + "step": 12152 + }, + { + "epoch": 0.99, + "learning_rate": 1.3397979139504565e-05, + "loss": 0.4041, + "step": 12153 + }, + { + "epoch": 0.99, + "learning_rate": 1.3397435897435897e-05, + "loss": 0.3959, + "step": 12154 + }, + { + "epoch": 0.99, + "learning_rate": 1.3396892655367233e-05, + "loss": 0.8415, + "step": 12155 + }, + { + "epoch": 0.99, + "learning_rate": 1.3396349413298566e-05, + "loss": 0.4196, + "step": 12156 + }, + { + "epoch": 0.99, + "learning_rate": 1.3395806171229902e-05, + "loss": 0.6143, + "step": 12157 + }, + { + "epoch": 0.99, + "learning_rate": 1.3395262929161234e-05, + "loss": 0.3679, + "step": 12158 + }, + { + "epoch": 0.99, + "learning_rate": 1.339471968709257e-05, + "loss": 0.4147, + "step": 12159 + }, + { + "epoch": 0.99, + "learning_rate": 1.3394176445023903e-05, + "loss": 0.5321, + "step": 12160 + }, + { + "epoch": 0.99, + "learning_rate": 1.3393633202955239e-05, + "loss": 0.4182, + "step": 12161 + }, + { + "epoch": 0.99, + "learning_rate": 1.3393089960886571e-05, + "loss": 0.4977, + "step": 12162 + }, + { + "epoch": 0.99, + "learning_rate": 1.3392546718817907e-05, + "loss": 0.6069, + "step": 12163 + }, + { + "epoch": 0.99, + "learning_rate": 1.339200347674924e-05, + "loss": 0.8591, + "step": 12164 + }, + { + "epoch": 0.99, + "learning_rate": 1.3391460234680576e-05, + "loss": 0.4786, + "step": 12165 + }, + { + "epoch": 0.99, + "learning_rate": 1.3390916992611908e-05, + "loss": 0.3757, + "step": 12166 + }, + { + "epoch": 0.99, + "learning_rate": 1.3390373750543244e-05, + "loss": 0.5286, + "step": 12167 + }, + { + "epoch": 0.99, + "learning_rate": 1.3389830508474577e-05, + "loss": 0.4343, + "step": 12168 + }, + { + "epoch": 0.99, + "learning_rate": 1.3389287266405913e-05, + "loss": 0.5544, + "step": 12169 + }, + { + "epoch": 0.99, + "learning_rate": 1.3388744024337245e-05, + "loss": 0.3815, + "step": 12170 + }, + { + "epoch": 0.99, + "learning_rate": 1.338820078226858e-05, + "loss": 0.4498, + "step": 12171 + }, + { + "epoch": 0.99, + "learning_rate": 1.3387657540199914e-05, + "loss": 0.4031, + "step": 12172 + }, + { + "epoch": 0.99, + "learning_rate": 1.3387114298131248e-05, + "loss": 0.4489, + "step": 12173 + }, + { + "epoch": 0.99, + "learning_rate": 1.3386571056062582e-05, + "loss": 0.431, + "step": 12174 + }, + { + "epoch": 0.99, + "learning_rate": 1.3386027813993916e-05, + "loss": 0.4365, + "step": 12175 + }, + { + "epoch": 0.99, + "learning_rate": 1.338548457192525e-05, + "loss": 0.4642, + "step": 12176 + }, + { + "epoch": 0.99, + "learning_rate": 1.3384941329856585e-05, + "loss": 0.3547, + "step": 12177 + }, + { + "epoch": 0.99, + "learning_rate": 1.3384398087787919e-05, + "loss": 0.3908, + "step": 12178 + }, + { + "epoch": 0.99, + "learning_rate": 1.3383854845719253e-05, + "loss": 0.2478, + "step": 12179 + }, + { + "epoch": 0.99, + "learning_rate": 1.338331160365059e-05, + "loss": 0.2785, + "step": 12180 + }, + { + "epoch": 0.99, + "learning_rate": 1.3382768361581922e-05, + "loss": 0.324, + "step": 12181 + }, + { + "epoch": 0.99, + "learning_rate": 1.3382225119513258e-05, + "loss": 0.3217, + "step": 12182 + }, + { + "epoch": 0.99, + "learning_rate": 1.338168187744459e-05, + "loss": 0.3806, + "step": 12183 + }, + { + "epoch": 0.99, + "learning_rate": 1.3381138635375926e-05, + "loss": 0.4269, + "step": 12184 + }, + { + "epoch": 0.99, + "learning_rate": 1.3380595393307259e-05, + "loss": 0.3172, + "step": 12185 + }, + { + "epoch": 0.99, + "learning_rate": 1.3380052151238595e-05, + "loss": 0.2244, + "step": 12186 + }, + { + "epoch": 0.99, + "learning_rate": 1.3379508909169927e-05, + "loss": 0.1228, + "step": 12187 + }, + { + "epoch": 0.99, + "learning_rate": 1.3378965667101263e-05, + "loss": 0.6593, + "step": 12188 + }, + { + "epoch": 0.99, + "learning_rate": 1.3378422425032596e-05, + "loss": 0.5301, + "step": 12189 + }, + { + "epoch": 0.99, + "learning_rate": 1.3377879182963928e-05, + "loss": 0.2026, + "step": 12190 + }, + { + "epoch": 0.99, + "learning_rate": 1.3377335940895264e-05, + "loss": 0.6255, + "step": 12191 + }, + { + "epoch": 0.99, + "learning_rate": 1.3376792698826597e-05, + "loss": 0.6234, + "step": 12192 + }, + { + "epoch": 0.99, + "learning_rate": 1.3376249456757932e-05, + "loss": 0.3548, + "step": 12193 + }, + { + "epoch": 0.99, + "learning_rate": 1.3375706214689265e-05, + "loss": 0.4378, + "step": 12194 + }, + { + "epoch": 0.99, + "learning_rate": 1.3375162972620601e-05, + "loss": 0.3288, + "step": 12195 + }, + { + "epoch": 0.99, + "learning_rate": 1.3374619730551933e-05, + "loss": 0.4916, + "step": 12196 + }, + { + "epoch": 0.99, + "learning_rate": 1.337407648848327e-05, + "loss": 0.6753, + "step": 12197 + }, + { + "epoch": 0.99, + "learning_rate": 1.3373533246414604e-05, + "loss": 0.5535, + "step": 12198 + }, + { + "epoch": 0.99, + "learning_rate": 1.3372990004345938e-05, + "loss": 0.7517, + "step": 12199 + }, + { + "epoch": 0.99, + "learning_rate": 1.3372446762277272e-05, + "loss": 0.3056, + "step": 12200 + }, + { + "epoch": 0.99, + "learning_rate": 1.3371903520208606e-05, + "loss": 0.217, + "step": 12201 + }, + { + "epoch": 0.99, + "learning_rate": 1.337136027813994e-05, + "loss": 0.4091, + "step": 12202 + }, + { + "epoch": 0.99, + "learning_rate": 1.3370817036071275e-05, + "loss": 0.573, + "step": 12203 + }, + { + "epoch": 0.99, + "learning_rate": 1.3370273794002609e-05, + "loss": 0.4218, + "step": 12204 + }, + { + "epoch": 0.99, + "learning_rate": 1.3369730551933943e-05, + "loss": 0.4893, + "step": 12205 + }, + { + "epoch": 0.99, + "learning_rate": 1.3369187309865277e-05, + "loss": 0.5797, + "step": 12206 + }, + { + "epoch": 0.99, + "learning_rate": 1.3368644067796612e-05, + "loss": 0.2709, + "step": 12207 + }, + { + "epoch": 0.99, + "learning_rate": 1.3368100825727946e-05, + "loss": 0.2927, + "step": 12208 + }, + { + "epoch": 0.99, + "learning_rate": 1.3367557583659278e-05, + "loss": 0.4286, + "step": 12209 + }, + { + "epoch": 0.99, + "learning_rate": 1.3367014341590614e-05, + "loss": 0.5446, + "step": 12210 + }, + { + "epoch": 1.0, + "learning_rate": 1.3366471099521947e-05, + "loss": 0.4786, + "step": 12211 + }, + { + "epoch": 1.0, + "learning_rate": 1.3365927857453283e-05, + "loss": 0.3991, + "step": 12212 + }, + { + "epoch": 1.0, + "learning_rate": 1.3365384615384615e-05, + "loss": 0.6275, + "step": 12213 + }, + { + "epoch": 1.0, + "learning_rate": 1.3364841373315951e-05, + "loss": 0.4542, + "step": 12214 + }, + { + "epoch": 1.0, + "learning_rate": 1.3364298131247284e-05, + "loss": 0.3599, + "step": 12215 + }, + { + "epoch": 1.0, + "learning_rate": 1.336375488917862e-05, + "loss": 0.3238, + "step": 12216 + }, + { + "epoch": 1.0, + "learning_rate": 1.3363211647109952e-05, + "loss": 0.5317, + "step": 12217 + }, + { + "epoch": 1.0, + "learning_rate": 1.3362668405041288e-05, + "loss": 0.3901, + "step": 12218 + }, + { + "epoch": 1.0, + "learning_rate": 1.336212516297262e-05, + "loss": 0.3096, + "step": 12219 + }, + { + "epoch": 1.0, + "learning_rate": 1.3361581920903957e-05, + "loss": 0.657, + "step": 12220 + }, + { + "epoch": 1.0, + "learning_rate": 1.336103867883529e-05, + "loss": 0.2136, + "step": 12221 + }, + { + "epoch": 1.0, + "learning_rate": 1.3360495436766625e-05, + "loss": 0.5035, + "step": 12222 + }, + { + "epoch": 1.0, + "learning_rate": 1.3359952194697958e-05, + "loss": 0.348, + "step": 12223 + }, + { + "epoch": 1.0, + "learning_rate": 1.3359408952629294e-05, + "loss": 0.3541, + "step": 12224 + }, + { + "epoch": 1.0, + "learning_rate": 1.3358865710560626e-05, + "loss": 0.7932, + "step": 12225 + }, + { + "epoch": 1.0, + "learning_rate": 1.3358322468491962e-05, + "loss": 0.2377, + "step": 12226 + }, + { + "epoch": 1.0, + "learning_rate": 1.3357779226423295e-05, + "loss": 0.4085, + "step": 12227 + }, + { + "epoch": 1.0, + "learning_rate": 1.3357235984354629e-05, + "loss": 0.5674, + "step": 12228 + }, + { + "epoch": 1.0, + "learning_rate": 1.3356692742285963e-05, + "loss": 0.603, + "step": 12229 + }, + { + "epoch": 1.0, + "learning_rate": 1.3356149500217297e-05, + "loss": 0.4128, + "step": 12230 + }, + { + "epoch": 1.0, + "learning_rate": 1.3355606258148632e-05, + "loss": 0.6438, + "step": 12231 + }, + { + "epoch": 1.0, + "learning_rate": 1.3355063016079966e-05, + "loss": 0.5562, + "step": 12232 + }, + { + "epoch": 1.0, + "learning_rate": 1.33545197740113e-05, + "loss": 0.8588, + "step": 12233 + }, + { + "epoch": 1.0, + "learning_rate": 1.3353976531942634e-05, + "loss": 0.2927, + "step": 12234 + }, + { + "epoch": 1.0, + "learning_rate": 1.335343328987397e-05, + "loss": 0.5887, + "step": 12235 + }, + { + "epoch": 1.0, + "learning_rate": 1.3352890047805303e-05, + "loss": 0.5547, + "step": 12236 + }, + { + "epoch": 1.0, + "learning_rate": 1.3352346805736639e-05, + "loss": 0.595, + "step": 12237 + }, + { + "epoch": 1.0, + "learning_rate": 1.3351803563667971e-05, + "loss": 0.6491, + "step": 12238 + }, + { + "epoch": 1.0, + "learning_rate": 1.3351260321599307e-05, + "loss": 0.4876, + "step": 12239 + }, + { + "epoch": 1.0, + "learning_rate": 1.335071707953064e-05, + "loss": 0.5238, + "step": 12240 + }, + { + "epoch": 1.0, + "learning_rate": 1.3350173837461976e-05, + "loss": 0.4617, + "step": 12241 + }, + { + "epoch": 1.0, + "learning_rate": 1.3349630595393308e-05, + "loss": 0.2387, + "step": 12242 + }, + { + "epoch": 1.0, + "learning_rate": 1.3349087353324644e-05, + "loss": 0.2778, + "step": 12243 + }, + { + "epoch": 1.0, + "learning_rate": 1.3348544111255977e-05, + "loss": 0.4418, + "step": 12244 + }, + { + "epoch": 1.0, + "learning_rate": 1.3348000869187312e-05, + "loss": 0.4341, + "step": 12245 + }, + { + "epoch": 1.0, + "learning_rate": 1.3347457627118645e-05, + "loss": 0.332, + "step": 12246 + }, + { + "epoch": 1.0, + "learning_rate": 1.3346914385049978e-05, + "loss": 0.2217, + "step": 12247 + }, + { + "epoch": 1.0, + "learning_rate": 1.3346371142981313e-05, + "loss": 0.2765, + "step": 12248 + }, + { + "epoch": 1.0, + "learning_rate": 1.3345827900912646e-05, + "loss": 0.4259, + "step": 12249 + }, + { + "epoch": 1.0, + "learning_rate": 1.3345284658843982e-05, + "loss": 0.2437, + "step": 12250 + }, + { + "epoch": 1.0, + "eval_accuracy": 0.8349465104431992, + "eval_loss": 0.4291660785675049, + "eval_runtime": 22.2159, + "eval_samples_per_second": 441.801, + "eval_steps_per_second": 3.466, + "step": 12250 + }, + { + "epoch": 1.0, + "learning_rate": 1.3344741416775316e-05, + "loss": 0.2723, + "step": 12251 + }, + { + "epoch": 1.0, + "learning_rate": 1.334419817470665e-05, + "loss": 0.6944, + "step": 12252 + }, + { + "epoch": 1.0, + "learning_rate": 1.3343654932637985e-05, + "loss": 0.6386, + "step": 12253 + }, + { + "epoch": 1.0, + "learning_rate": 1.3343111690569319e-05, + "loss": 0.2626, + "step": 12254 + }, + { + "epoch": 1.0, + "learning_rate": 1.3342568448500653e-05, + "loss": 0.4373, + "step": 12255 + }, + { + "epoch": 1.0, + "learning_rate": 1.3342025206431987e-05, + "loss": 0.3225, + "step": 12256 + }, + { + "epoch": 1.0, + "learning_rate": 1.3341481964363322e-05, + "loss": 0.2785, + "step": 12257 + }, + { + "epoch": 1.0, + "learning_rate": 1.3340938722294656e-05, + "loss": 0.3507, + "step": 12258 + }, + { + "epoch": 1.0, + "learning_rate": 1.334039548022599e-05, + "loss": 0.7339, + "step": 12259 + }, + { + "epoch": 1.0, + "learning_rate": 1.3339852238157324e-05, + "loss": 0.3682, + "step": 12260 + }, + { + "epoch": 1.0, + "learning_rate": 1.3339308996088658e-05, + "loss": 0.427, + "step": 12261 + }, + { + "epoch": 1.0, + "learning_rate": 1.3338765754019993e-05, + "loss": 0.5444, + "step": 12262 + }, + { + "epoch": 1.0, + "learning_rate": 1.3338222511951327e-05, + "loss": 0.267, + "step": 12263 + }, + { + "epoch": 1.0, + "learning_rate": 1.3337679269882661e-05, + "loss": 0.6021, + "step": 12264 + }, + { + "epoch": 1.0, + "learning_rate": 1.3337136027813995e-05, + "loss": 0.5358, + "step": 12265 + }, + { + "epoch": 1.0, + "learning_rate": 1.3336592785745328e-05, + "loss": 0.3538, + "step": 12266 + }, + { + "epoch": 1.0, + "learning_rate": 1.3336049543676664e-05, + "loss": 0.4496, + "step": 12267 + }, + { + "epoch": 1.0, + "learning_rate": 1.3335506301607996e-05, + "loss": 0.5492, + "step": 12268 + }, + { + "epoch": 1.0, + "learning_rate": 1.3334963059539332e-05, + "loss": 0.4529, + "step": 12269 + }, + { + "epoch": 1.0, + "learning_rate": 1.3334419817470665e-05, + "loss": 0.5549, + "step": 12270 + }, + { + "epoch": 1.0, + "learning_rate": 1.3333876575402e-05, + "loss": 0.7113, + "step": 12271 + }, + { + "epoch": 1.0, + "learning_rate": 1.3333333333333333e-05, + "loss": 0.6527, + "step": 12272 + }, + { + "epoch": 1.0, + "learning_rate": 1.333279009126467e-05, + "loss": 0.4325, + "step": 12273 + }, + { + "epoch": 1.0, + "learning_rate": 1.3332246849196002e-05, + "loss": 0.3347, + "step": 12274 + }, + { + "epoch": 1.0, + "learning_rate": 1.3331703607127338e-05, + "loss": 0.2309, + "step": 12275 + }, + { + "epoch": 1.0, + "learning_rate": 1.333116036505867e-05, + "loss": 0.2692, + "step": 12276 + }, + { + "epoch": 1.0, + "learning_rate": 1.3330617122990006e-05, + "loss": 0.2405, + "step": 12277 + }, + { + "epoch": 1.0, + "learning_rate": 1.3330073880921339e-05, + "loss": 0.2452, + "step": 12278 + }, + { + "epoch": 1.0, + "learning_rate": 1.3329530638852675e-05, + "loss": 0.4087, + "step": 12279 + }, + { + "epoch": 1.0, + "learning_rate": 1.3328987396784007e-05, + "loss": 0.2691, + "step": 12280 + }, + { + "epoch": 1.0, + "learning_rate": 1.3328444154715343e-05, + "loss": 0.318, + "step": 12281 + }, + { + "epoch": 1.0, + "learning_rate": 1.3327900912646676e-05, + "loss": 0.2559, + "step": 12282 + }, + { + "epoch": 1.0, + "learning_rate": 1.3327357670578012e-05, + "loss": 0.2094, + "step": 12283 + }, + { + "epoch": 1.0, + "learning_rate": 1.3326814428509344e-05, + "loss": 0.4477, + "step": 12284 + }, + { + "epoch": 1.0, + "learning_rate": 1.3326271186440678e-05, + "loss": 0.3684, + "step": 12285 + }, + { + "epoch": 1.0, + "learning_rate": 1.3325727944372013e-05, + "loss": 0.2378, + "step": 12286 + }, + { + "epoch": 1.0, + "learning_rate": 1.3325184702303347e-05, + "loss": 0.3766, + "step": 12287 + }, + { + "epoch": 1.0, + "learning_rate": 1.3324641460234683e-05, + "loss": 0.3162, + "step": 12288 + }, + { + "epoch": 1.0, + "learning_rate": 1.3324098218166015e-05, + "loss": 0.4763, + "step": 12289 + }, + { + "epoch": 1.0, + "learning_rate": 1.3323554976097351e-05, + "loss": 0.3244, + "step": 12290 + }, + { + "epoch": 1.0, + "learning_rate": 1.3323011734028684e-05, + "loss": 0.3491, + "step": 12291 + }, + { + "epoch": 1.0, + "learning_rate": 1.332246849196002e-05, + "loss": 0.3074, + "step": 12292 + }, + { + "epoch": 1.0, + "learning_rate": 1.3321925249891352e-05, + "loss": 0.2758, + "step": 12293 + }, + { + "epoch": 1.0, + "learning_rate": 1.3321382007822688e-05, + "loss": 0.517, + "step": 12294 + }, + { + "epoch": 1.0, + "learning_rate": 1.332083876575402e-05, + "loss": 0.2263, + "step": 12295 + }, + { + "epoch": 1.0, + "learning_rate": 1.3320295523685357e-05, + "loss": 0.1853, + "step": 12296 + }, + { + "epoch": 1.0, + "learning_rate": 1.3319752281616689e-05, + "loss": 0.803, + "step": 12297 + }, + { + "epoch": 1.0, + "learning_rate": 1.3319209039548025e-05, + "loss": 0.1759, + "step": 12298 + }, + { + "epoch": 1.0, + "learning_rate": 1.3318665797479358e-05, + "loss": 0.3563, + "step": 12299 + }, + { + "epoch": 1.0, + "learning_rate": 1.3318122555410693e-05, + "loss": 0.2551, + "step": 12300 + }, + { + "epoch": 1.0, + "learning_rate": 1.3317579313342026e-05, + "loss": 0.4064, + "step": 12301 + }, + { + "epoch": 1.0, + "learning_rate": 1.3317036071273362e-05, + "loss": 0.3512, + "step": 12302 + }, + { + "epoch": 1.0, + "learning_rate": 1.3316492829204694e-05, + "loss": 0.1689, + "step": 12303 + }, + { + "epoch": 1.0, + "learning_rate": 1.3315949587136027e-05, + "loss": 0.2814, + "step": 12304 + }, + { + "epoch": 1.0, + "learning_rate": 1.3315406345067363e-05, + "loss": 0.2895, + "step": 12305 + }, + { + "epoch": 1.0, + "learning_rate": 1.3314863102998697e-05, + "loss": 0.4914, + "step": 12306 + }, + { + "epoch": 1.0, + "learning_rate": 1.3314319860930031e-05, + "loss": 0.3115, + "step": 12307 + }, + { + "epoch": 1.0, + "learning_rate": 1.3313776618861366e-05, + "loss": 0.2116, + "step": 12308 + }, + { + "epoch": 1.0, + "learning_rate": 1.33132333767927e-05, + "loss": 0.3706, + "step": 12309 + }, + { + "epoch": 1.0, + "learning_rate": 1.3312690134724034e-05, + "loss": 0.5631, + "step": 12310 + }, + { + "epoch": 1.0, + "learning_rate": 1.3312146892655368e-05, + "loss": 0.184, + "step": 12311 + }, + { + "epoch": 1.0, + "learning_rate": 1.3311603650586703e-05, + "loss": 0.2731, + "step": 12312 + }, + { + "epoch": 1.0, + "learning_rate": 1.3311060408518037e-05, + "loss": 0.2517, + "step": 12313 + }, + { + "epoch": 1.0, + "learning_rate": 1.3310517166449371e-05, + "loss": 0.3119, + "step": 12314 + }, + { + "epoch": 1.0, + "learning_rate": 1.3309973924380705e-05, + "loss": 0.3181, + "step": 12315 + }, + { + "epoch": 1.0, + "learning_rate": 1.330943068231204e-05, + "loss": 0.3932, + "step": 12316 + }, + { + "epoch": 1.0, + "learning_rate": 1.3308887440243374e-05, + "loss": 0.3446, + "step": 12317 + }, + { + "epoch": 1.0, + "learning_rate": 1.3308344198174708e-05, + "loss": 0.2633, + "step": 12318 + }, + { + "epoch": 1.0, + "learning_rate": 1.3307800956106042e-05, + "loss": 0.401, + "step": 12319 + }, + { + "epoch": 1.0, + "learning_rate": 1.3307257714037376e-05, + "loss": 0.2973, + "step": 12320 + }, + { + "epoch": 1.0, + "learning_rate": 1.330671447196871e-05, + "loss": 0.4691, + "step": 12321 + }, + { + "epoch": 1.0, + "learning_rate": 1.3306171229900045e-05, + "loss": 0.3496, + "step": 12322 + }, + { + "epoch": 1.0, + "learning_rate": 1.3305627987831377e-05, + "loss": 0.4152, + "step": 12323 + }, + { + "epoch": 1.0, + "learning_rate": 1.3305084745762713e-05, + "loss": 0.4059, + "step": 12324 + }, + { + "epoch": 1.0, + "learning_rate": 1.3304541503694046e-05, + "loss": 0.3835, + "step": 12325 + }, + { + "epoch": 1.0, + "learning_rate": 1.3303998261625382e-05, + "loss": 0.347, + "step": 12326 + }, + { + "epoch": 1.0, + "learning_rate": 1.3303455019556714e-05, + "loss": 0.2117, + "step": 12327 + }, + { + "epoch": 1.0, + "learning_rate": 1.330291177748805e-05, + "loss": 0.6159, + "step": 12328 + }, + { + "epoch": 1.0, + "learning_rate": 1.3302368535419383e-05, + "loss": 0.5214, + "step": 12329 + }, + { + "epoch": 1.0, + "learning_rate": 1.3301825293350719e-05, + "loss": 0.4788, + "step": 12330 + }, + { + "epoch": 1.0, + "learning_rate": 1.3301282051282051e-05, + "loss": 0.4863, + "step": 12331 + }, + { + "epoch": 1.0, + "learning_rate": 1.3300738809213387e-05, + "loss": 0.2619, + "step": 12332 + }, + { + "epoch": 1.0, + "learning_rate": 1.330019556714472e-05, + "loss": 0.4129, + "step": 12333 + }, + { + "epoch": 1.01, + "learning_rate": 1.3299652325076056e-05, + "loss": 0.3369, + "step": 12334 + }, + { + "epoch": 1.01, + "learning_rate": 1.3299109083007388e-05, + "loss": 0.5364, + "step": 12335 + }, + { + "epoch": 1.01, + "learning_rate": 1.3298565840938724e-05, + "loss": 0.2349, + "step": 12336 + }, + { + "epoch": 1.01, + "learning_rate": 1.3298022598870057e-05, + "loss": 0.1244, + "step": 12337 + }, + { + "epoch": 1.01, + "learning_rate": 1.3297479356801393e-05, + "loss": 0.4322, + "step": 12338 + }, + { + "epoch": 1.01, + "learning_rate": 1.3296936114732725e-05, + "loss": 0.45, + "step": 12339 + }, + { + "epoch": 1.01, + "learning_rate": 1.3296392872664061e-05, + "loss": 0.3068, + "step": 12340 + }, + { + "epoch": 1.01, + "learning_rate": 1.3295849630595394e-05, + "loss": 0.4705, + "step": 12341 + }, + { + "epoch": 1.01, + "learning_rate": 1.3295306388526728e-05, + "loss": 0.1948, + "step": 12342 + }, + { + "epoch": 1.01, + "learning_rate": 1.3294763146458064e-05, + "loss": 0.2396, + "step": 12343 + }, + { + "epoch": 1.01, + "learning_rate": 1.3294219904389396e-05, + "loss": 0.5034, + "step": 12344 + }, + { + "epoch": 1.01, + "learning_rate": 1.3293676662320732e-05, + "loss": 0.3494, + "step": 12345 + }, + { + "epoch": 1.01, + "learning_rate": 1.3293133420252065e-05, + "loss": 0.3881, + "step": 12346 + }, + { + "epoch": 1.01, + "learning_rate": 1.32925901781834e-05, + "loss": 0.3983, + "step": 12347 + }, + { + "epoch": 1.01, + "learning_rate": 1.3292046936114733e-05, + "loss": 0.2645, + "step": 12348 + }, + { + "epoch": 1.01, + "learning_rate": 1.3291503694046069e-05, + "loss": 0.1781, + "step": 12349 + }, + { + "epoch": 1.01, + "learning_rate": 1.3290960451977402e-05, + "loss": 0.3496, + "step": 12350 + }, + { + "epoch": 1.01, + "learning_rate": 1.3290417209908738e-05, + "loss": 0.2216, + "step": 12351 + }, + { + "epoch": 1.01, + "learning_rate": 1.328987396784007e-05, + "loss": 0.3152, + "step": 12352 + }, + { + "epoch": 1.01, + "learning_rate": 1.3289330725771406e-05, + "loss": 0.2654, + "step": 12353 + }, + { + "epoch": 1.01, + "learning_rate": 1.3288787483702739e-05, + "loss": 0.3913, + "step": 12354 + }, + { + "epoch": 1.01, + "learning_rate": 1.3288244241634074e-05, + "loss": 0.2613, + "step": 12355 + }, + { + "epoch": 1.01, + "learning_rate": 1.3287700999565407e-05, + "loss": 0.4897, + "step": 12356 + }, + { + "epoch": 1.01, + "learning_rate": 1.3287157757496743e-05, + "loss": 0.5054, + "step": 12357 + }, + { + "epoch": 1.01, + "learning_rate": 1.3286614515428075e-05, + "loss": 0.3511, + "step": 12358 + }, + { + "epoch": 1.01, + "learning_rate": 1.3286071273359411e-05, + "loss": 0.1989, + "step": 12359 + }, + { + "epoch": 1.01, + "learning_rate": 1.3285528031290744e-05, + "loss": 0.4983, + "step": 12360 + }, + { + "epoch": 1.01, + "learning_rate": 1.3284984789222078e-05, + "loss": 0.4692, + "step": 12361 + }, + { + "epoch": 1.01, + "learning_rate": 1.3284441547153412e-05, + "loss": 0.3171, + "step": 12362 + }, + { + "epoch": 1.01, + "learning_rate": 1.3283898305084747e-05, + "loss": 0.4258, + "step": 12363 + }, + { + "epoch": 1.01, + "learning_rate": 1.328335506301608e-05, + "loss": 0.2511, + "step": 12364 + }, + { + "epoch": 1.01, + "learning_rate": 1.3282811820947415e-05, + "loss": 0.3128, + "step": 12365 + }, + { + "epoch": 1.01, + "learning_rate": 1.328226857887875e-05, + "loss": 0.5071, + "step": 12366 + }, + { + "epoch": 1.01, + "learning_rate": 1.3281725336810084e-05, + "loss": 0.182, + "step": 12367 + }, + { + "epoch": 1.01, + "learning_rate": 1.3281182094741418e-05, + "loss": 0.4001, + "step": 12368 + }, + { + "epoch": 1.01, + "learning_rate": 1.3280638852672752e-05, + "loss": 0.4334, + "step": 12369 + }, + { + "epoch": 1.01, + "learning_rate": 1.3280095610604086e-05, + "loss": 0.2777, + "step": 12370 + }, + { + "epoch": 1.01, + "learning_rate": 1.327955236853542e-05, + "loss": 0.1959, + "step": 12371 + }, + { + "epoch": 1.01, + "learning_rate": 1.3279009126466755e-05, + "loss": 0.3107, + "step": 12372 + }, + { + "epoch": 1.01, + "learning_rate": 1.3278465884398089e-05, + "loss": 0.2706, + "step": 12373 + }, + { + "epoch": 1.01, + "learning_rate": 1.3277922642329423e-05, + "loss": 0.133, + "step": 12374 + }, + { + "epoch": 1.01, + "learning_rate": 1.3277379400260757e-05, + "loss": 0.4668, + "step": 12375 + }, + { + "epoch": 1.01, + "learning_rate": 1.3276836158192092e-05, + "loss": 0.3527, + "step": 12376 + }, + { + "epoch": 1.01, + "learning_rate": 1.3276292916123426e-05, + "loss": 0.2973, + "step": 12377 + }, + { + "epoch": 1.01, + "learning_rate": 1.3275749674054762e-05, + "loss": 0.3798, + "step": 12378 + }, + { + "epoch": 1.01, + "learning_rate": 1.3275206431986094e-05, + "loss": 0.4234, + "step": 12379 + }, + { + "epoch": 1.01, + "learning_rate": 1.3274663189917427e-05, + "loss": 0.3346, + "step": 12380 + }, + { + "epoch": 1.01, + "learning_rate": 1.3274119947848763e-05, + "loss": 0.2819, + "step": 12381 + }, + { + "epoch": 1.01, + "learning_rate": 1.3273576705780095e-05, + "loss": 0.3609, + "step": 12382 + }, + { + "epoch": 1.01, + "learning_rate": 1.3273033463711431e-05, + "loss": 0.6003, + "step": 12383 + }, + { + "epoch": 1.01, + "learning_rate": 1.3272490221642764e-05, + "loss": 0.2508, + "step": 12384 + }, + { + "epoch": 1.01, + "learning_rate": 1.32719469795741e-05, + "loss": 0.3012, + "step": 12385 + }, + { + "epoch": 1.01, + "learning_rate": 1.3271403737505432e-05, + "loss": 0.2896, + "step": 12386 + }, + { + "epoch": 1.01, + "learning_rate": 1.3270860495436768e-05, + "loss": 0.3901, + "step": 12387 + }, + { + "epoch": 1.01, + "learning_rate": 1.32703172533681e-05, + "loss": 0.2084, + "step": 12388 + }, + { + "epoch": 1.01, + "learning_rate": 1.3269774011299437e-05, + "loss": 0.448, + "step": 12389 + }, + { + "epoch": 1.01, + "learning_rate": 1.3269230769230769e-05, + "loss": 0.5441, + "step": 12390 + }, + { + "epoch": 1.01, + "learning_rate": 1.3268687527162105e-05, + "loss": 0.2845, + "step": 12391 + }, + { + "epoch": 1.01, + "learning_rate": 1.3268144285093438e-05, + "loss": 0.4633, + "step": 12392 + }, + { + "epoch": 1.01, + "learning_rate": 1.3267601043024773e-05, + "loss": 0.3095, + "step": 12393 + }, + { + "epoch": 1.01, + "learning_rate": 1.3267057800956106e-05, + "loss": 0.1881, + "step": 12394 + }, + { + "epoch": 1.01, + "learning_rate": 1.3266514558887442e-05, + "loss": 0.4559, + "step": 12395 + }, + { + "epoch": 1.01, + "learning_rate": 1.3265971316818776e-05, + "loss": 0.3107, + "step": 12396 + }, + { + "epoch": 1.01, + "learning_rate": 1.326542807475011e-05, + "loss": 0.5523, + "step": 12397 + }, + { + "epoch": 1.01, + "learning_rate": 1.3264884832681445e-05, + "loss": 0.193, + "step": 12398 + }, + { + "epoch": 1.01, + "learning_rate": 1.3264341590612777e-05, + "loss": 0.488, + "step": 12399 + }, + { + "epoch": 1.01, + "learning_rate": 1.3263798348544113e-05, + "loss": 0.3152, + "step": 12400 + }, + { + "epoch": 1.01, + "learning_rate": 1.3263255106475446e-05, + "loss": 0.1307, + "step": 12401 + }, + { + "epoch": 1.01, + "learning_rate": 1.3262711864406782e-05, + "loss": 0.3705, + "step": 12402 + }, + { + "epoch": 1.01, + "learning_rate": 1.3262168622338114e-05, + "loss": 0.2666, + "step": 12403 + }, + { + "epoch": 1.01, + "learning_rate": 1.326162538026945e-05, + "loss": 0.4769, + "step": 12404 + }, + { + "epoch": 1.01, + "learning_rate": 1.3261082138200783e-05, + "loss": 0.5036, + "step": 12405 + }, + { + "epoch": 1.01, + "learning_rate": 1.3260538896132118e-05, + "loss": 0.3791, + "step": 12406 + }, + { + "epoch": 1.01, + "learning_rate": 1.3259995654063451e-05, + "loss": 0.2593, + "step": 12407 + }, + { + "epoch": 1.01, + "learning_rate": 1.3259452411994787e-05, + "loss": 0.3027, + "step": 12408 + }, + { + "epoch": 1.01, + "learning_rate": 1.325890916992612e-05, + "loss": 0.629, + "step": 12409 + }, + { + "epoch": 1.01, + "learning_rate": 1.3258365927857455e-05, + "loss": 0.2813, + "step": 12410 + }, + { + "epoch": 1.01, + "learning_rate": 1.3257822685788788e-05, + "loss": 0.4191, + "step": 12411 + }, + { + "epoch": 1.01, + "learning_rate": 1.3257279443720124e-05, + "loss": 0.314, + "step": 12412 + }, + { + "epoch": 1.01, + "learning_rate": 1.3256736201651456e-05, + "loss": 0.1407, + "step": 12413 + }, + { + "epoch": 1.01, + "learning_rate": 1.3256192959582792e-05, + "loss": 0.3547, + "step": 12414 + }, + { + "epoch": 1.01, + "learning_rate": 1.3255649717514125e-05, + "loss": 0.3791, + "step": 12415 + }, + { + "epoch": 1.01, + "learning_rate": 1.325510647544546e-05, + "loss": 0.2159, + "step": 12416 + }, + { + "epoch": 1.01, + "learning_rate": 1.3254563233376793e-05, + "loss": 0.2173, + "step": 12417 + }, + { + "epoch": 1.01, + "learning_rate": 1.3254019991308128e-05, + "loss": 0.3468, + "step": 12418 + }, + { + "epoch": 1.01, + "learning_rate": 1.3253476749239462e-05, + "loss": 0.1561, + "step": 12419 + }, + { + "epoch": 1.01, + "learning_rate": 1.3252933507170796e-05, + "loss": 0.2731, + "step": 12420 + }, + { + "epoch": 1.01, + "learning_rate": 1.325239026510213e-05, + "loss": 0.3821, + "step": 12421 + }, + { + "epoch": 1.01, + "learning_rate": 1.3251847023033464e-05, + "loss": 0.3269, + "step": 12422 + }, + { + "epoch": 1.01, + "learning_rate": 1.3251303780964799e-05, + "loss": 0.1842, + "step": 12423 + }, + { + "epoch": 1.01, + "learning_rate": 1.3250760538896133e-05, + "loss": 0.4975, + "step": 12424 + }, + { + "epoch": 1.01, + "learning_rate": 1.3250217296827467e-05, + "loss": 0.3214, + "step": 12425 + }, + { + "epoch": 1.01, + "learning_rate": 1.3249674054758801e-05, + "loss": 0.3429, + "step": 12426 + }, + { + "epoch": 1.01, + "learning_rate": 1.3249130812690136e-05, + "loss": 0.6343, + "step": 12427 + }, + { + "epoch": 1.01, + "learning_rate": 1.324858757062147e-05, + "loss": 0.2363, + "step": 12428 + }, + { + "epoch": 1.01, + "learning_rate": 1.3248044328552804e-05, + "loss": 0.2034, + "step": 12429 + }, + { + "epoch": 1.01, + "learning_rate": 1.3247501086484138e-05, + "loss": 0.2393, + "step": 12430 + }, + { + "epoch": 1.01, + "learning_rate": 1.3246957844415473e-05, + "loss": 0.223, + "step": 12431 + }, + { + "epoch": 1.01, + "learning_rate": 1.3246414602346807e-05, + "loss": 0.4536, + "step": 12432 + }, + { + "epoch": 1.01, + "learning_rate": 1.3245871360278143e-05, + "loss": 0.3882, + "step": 12433 + }, + { + "epoch": 1.01, + "learning_rate": 1.3245328118209475e-05, + "loss": 0.5767, + "step": 12434 + }, + { + "epoch": 1.01, + "learning_rate": 1.3244784876140811e-05, + "loss": 0.5158, + "step": 12435 + }, + { + "epoch": 1.01, + "learning_rate": 1.3244241634072144e-05, + "loss": 0.5369, + "step": 12436 + }, + { + "epoch": 1.01, + "learning_rate": 1.3243698392003476e-05, + "loss": 0.3419, + "step": 12437 + }, + { + "epoch": 1.01, + "learning_rate": 1.3243155149934812e-05, + "loss": 0.4501, + "step": 12438 + }, + { + "epoch": 1.01, + "learning_rate": 1.3242611907866145e-05, + "loss": 0.2602, + "step": 12439 + }, + { + "epoch": 1.01, + "learning_rate": 1.324206866579748e-05, + "loss": 0.1593, + "step": 12440 + }, + { + "epoch": 1.01, + "learning_rate": 1.3241525423728813e-05, + "loss": 0.4262, + "step": 12441 + }, + { + "epoch": 1.01, + "learning_rate": 1.3240982181660149e-05, + "loss": 0.1444, + "step": 12442 + }, + { + "epoch": 1.01, + "learning_rate": 1.3240438939591482e-05, + "loss": 0.6887, + "step": 12443 + }, + { + "epoch": 1.01, + "learning_rate": 1.3239895697522818e-05, + "loss": 0.4962, + "step": 12444 + }, + { + "epoch": 1.01, + "learning_rate": 1.323935245545415e-05, + "loss": 0.3218, + "step": 12445 + }, + { + "epoch": 1.01, + "learning_rate": 1.3238809213385486e-05, + "loss": 0.2106, + "step": 12446 + }, + { + "epoch": 1.01, + "learning_rate": 1.3238265971316819e-05, + "loss": 0.2556, + "step": 12447 + }, + { + "epoch": 1.01, + "learning_rate": 1.3237722729248154e-05, + "loss": 0.2932, + "step": 12448 + }, + { + "epoch": 1.01, + "learning_rate": 1.3237179487179487e-05, + "loss": 0.228, + "step": 12449 + }, + { + "epoch": 1.01, + "learning_rate": 1.3236636245110823e-05, + "loss": 0.2893, + "step": 12450 + }, + { + "epoch": 1.01, + "learning_rate": 1.3236093003042157e-05, + "loss": 0.283, + "step": 12451 + }, + { + "epoch": 1.01, + "learning_rate": 1.3235549760973491e-05, + "loss": 0.3185, + "step": 12452 + }, + { + "epoch": 1.01, + "learning_rate": 1.3235006518904826e-05, + "loss": 0.1463, + "step": 12453 + }, + { + "epoch": 1.01, + "learning_rate": 1.323446327683616e-05, + "loss": 0.2035, + "step": 12454 + }, + { + "epoch": 1.01, + "learning_rate": 1.3233920034767494e-05, + "loss": 0.3274, + "step": 12455 + }, + { + "epoch": 1.01, + "learning_rate": 1.3233376792698827e-05, + "loss": 0.1377, + "step": 12456 + }, + { + "epoch": 1.02, + "learning_rate": 1.3232833550630163e-05, + "loss": 0.288, + "step": 12457 + }, + { + "epoch": 1.02, + "learning_rate": 1.3232290308561495e-05, + "loss": 0.3062, + "step": 12458 + }, + { + "epoch": 1.02, + "learning_rate": 1.3231747066492831e-05, + "loss": 0.1998, + "step": 12459 + }, + { + "epoch": 1.02, + "learning_rate": 1.3231203824424164e-05, + "loss": 0.3085, + "step": 12460 + }, + { + "epoch": 1.02, + "learning_rate": 1.32306605823555e-05, + "loss": 0.2145, + "step": 12461 + }, + { + "epoch": 1.02, + "learning_rate": 1.3230117340286832e-05, + "loss": 0.4801, + "step": 12462 + }, + { + "epoch": 1.02, + "learning_rate": 1.3229574098218168e-05, + "loss": 0.4557, + "step": 12463 + }, + { + "epoch": 1.02, + "learning_rate": 1.32290308561495e-05, + "loss": 0.2093, + "step": 12464 + }, + { + "epoch": 1.02, + "learning_rate": 1.3228487614080836e-05, + "loss": 0.2341, + "step": 12465 + }, + { + "epoch": 1.02, + "learning_rate": 1.3227944372012169e-05, + "loss": 0.4553, + "step": 12466 + }, + { + "epoch": 1.02, + "learning_rate": 1.3227401129943505e-05, + "loss": 0.594, + "step": 12467 + }, + { + "epoch": 1.02, + "learning_rate": 1.3226857887874837e-05, + "loss": 0.6321, + "step": 12468 + }, + { + "epoch": 1.02, + "learning_rate": 1.3226314645806173e-05, + "loss": 0.2691, + "step": 12469 + }, + { + "epoch": 1.02, + "learning_rate": 1.3225771403737506e-05, + "loss": 0.2703, + "step": 12470 + }, + { + "epoch": 1.02, + "learning_rate": 1.3225228161668842e-05, + "loss": 0.0696, + "step": 12471 + }, + { + "epoch": 1.02, + "learning_rate": 1.3224684919600174e-05, + "loss": 0.2047, + "step": 12472 + }, + { + "epoch": 1.02, + "learning_rate": 1.322414167753151e-05, + "loss": 0.2689, + "step": 12473 + }, + { + "epoch": 1.02, + "learning_rate": 1.3223598435462843e-05, + "loss": 0.2911, + "step": 12474 + }, + { + "epoch": 1.02, + "learning_rate": 1.3223055193394177e-05, + "loss": 0.3599, + "step": 12475 + }, + { + "epoch": 1.02, + "learning_rate": 1.3222511951325511e-05, + "loss": 0.5134, + "step": 12476 + }, + { + "epoch": 1.02, + "learning_rate": 1.3221968709256845e-05, + "loss": 0.4367, + "step": 12477 + }, + { + "epoch": 1.02, + "learning_rate": 1.322142546718818e-05, + "loss": 0.3356, + "step": 12478 + }, + { + "epoch": 1.02, + "learning_rate": 1.3220882225119514e-05, + "loss": 0.3921, + "step": 12479 + }, + { + "epoch": 1.02, + "learning_rate": 1.3220338983050848e-05, + "loss": 0.2546, + "step": 12480 + }, + { + "epoch": 1.02, + "learning_rate": 1.3219795740982182e-05, + "loss": 0.2441, + "step": 12481 + }, + { + "epoch": 1.02, + "learning_rate": 1.3219252498913517e-05, + "loss": 0.574, + "step": 12482 + }, + { + "epoch": 1.02, + "learning_rate": 1.3218709256844851e-05, + "loss": 0.3314, + "step": 12483 + }, + { + "epoch": 1.02, + "learning_rate": 1.3218166014776185e-05, + "loss": 0.5898, + "step": 12484 + }, + { + "epoch": 1.02, + "learning_rate": 1.321762277270752e-05, + "loss": 0.2212, + "step": 12485 + }, + { + "epoch": 1.02, + "learning_rate": 1.3217079530638855e-05, + "loss": 0.2447, + "step": 12486 + }, + { + "epoch": 1.02, + "learning_rate": 1.3216536288570188e-05, + "loss": 0.1742, + "step": 12487 + }, + { + "epoch": 1.02, + "learning_rate": 1.3215993046501524e-05, + "loss": 0.4477, + "step": 12488 + }, + { + "epoch": 1.02, + "learning_rate": 1.3215449804432856e-05, + "loss": 0.1222, + "step": 12489 + }, + { + "epoch": 1.02, + "learning_rate": 1.3214906562364192e-05, + "loss": 0.4017, + "step": 12490 + }, + { + "epoch": 1.02, + "learning_rate": 1.3214363320295525e-05, + "loss": 0.4843, + "step": 12491 + }, + { + "epoch": 1.02, + "learning_rate": 1.321382007822686e-05, + "loss": 0.2499, + "step": 12492 + }, + { + "epoch": 1.02, + "learning_rate": 1.3213276836158193e-05, + "loss": 0.279, + "step": 12493 + }, + { + "epoch": 1.02, + "learning_rate": 1.3212733594089526e-05, + "loss": 0.6588, + "step": 12494 + }, + { + "epoch": 1.02, + "learning_rate": 1.3212190352020862e-05, + "loss": 0.7588, + "step": 12495 + }, + { + "epoch": 1.02, + "learning_rate": 1.3211647109952194e-05, + "loss": 0.2985, + "step": 12496 + }, + { + "epoch": 1.02, + "learning_rate": 1.321110386788353e-05, + "loss": 0.4055, + "step": 12497 + }, + { + "epoch": 1.02, + "learning_rate": 1.3210560625814863e-05, + "loss": 0.7823, + "step": 12498 + }, + { + "epoch": 1.02, + "learning_rate": 1.3210017383746199e-05, + "loss": 0.2227, + "step": 12499 + }, + { + "epoch": 1.02, + "learning_rate": 1.3209474141677531e-05, + "loss": 0.176, + "step": 12500 + }, + { + "epoch": 1.02, + "eval_accuracy": 0.8332144676515537, + "eval_loss": 0.46492111682891846, + "eval_runtime": 22.2511, + "eval_samples_per_second": 441.101, + "eval_steps_per_second": 3.46, + "step": 12500 + }, + { + "epoch": 1.02, + "learning_rate": 1.3208930899608867e-05, + "loss": 0.4295, + "step": 12501 + }, + { + "epoch": 1.02, + "learning_rate": 1.32083876575402e-05, + "loss": 0.3879, + "step": 12502 + }, + { + "epoch": 1.02, + "learning_rate": 1.3207844415471535e-05, + "loss": 0.3502, + "step": 12503 + }, + { + "epoch": 1.02, + "learning_rate": 1.320730117340287e-05, + "loss": 0.2144, + "step": 12504 + }, + { + "epoch": 1.02, + "learning_rate": 1.3206757931334204e-05, + "loss": 0.4061, + "step": 12505 + }, + { + "epoch": 1.02, + "learning_rate": 1.3206214689265538e-05, + "loss": 0.3492, + "step": 12506 + }, + { + "epoch": 1.02, + "learning_rate": 1.3205671447196872e-05, + "loss": 0.3543, + "step": 12507 + }, + { + "epoch": 1.02, + "learning_rate": 1.3205128205128207e-05, + "loss": 0.4775, + "step": 12508 + }, + { + "epoch": 1.02, + "learning_rate": 1.3204584963059541e-05, + "loss": 0.4963, + "step": 12509 + }, + { + "epoch": 1.02, + "learning_rate": 1.3204041720990875e-05, + "loss": 0.3341, + "step": 12510 + }, + { + "epoch": 1.02, + "learning_rate": 1.320349847892221e-05, + "loss": 0.4173, + "step": 12511 + }, + { + "epoch": 1.02, + "learning_rate": 1.3202955236853544e-05, + "loss": 0.3421, + "step": 12512 + }, + { + "epoch": 1.02, + "learning_rate": 1.3202411994784876e-05, + "loss": 0.5769, + "step": 12513 + }, + { + "epoch": 1.02, + "learning_rate": 1.3201868752716212e-05, + "loss": 0.2582, + "step": 12514 + }, + { + "epoch": 1.02, + "learning_rate": 1.3201325510647545e-05, + "loss": 0.2548, + "step": 12515 + }, + { + "epoch": 1.02, + "learning_rate": 1.320078226857888e-05, + "loss": 0.1965, + "step": 12516 + }, + { + "epoch": 1.02, + "learning_rate": 1.3200239026510213e-05, + "loss": 0.3138, + "step": 12517 + }, + { + "epoch": 1.02, + "learning_rate": 1.3199695784441549e-05, + "loss": 0.3692, + "step": 12518 + }, + { + "epoch": 1.02, + "learning_rate": 1.3199152542372881e-05, + "loss": 0.4801, + "step": 12519 + }, + { + "epoch": 1.02, + "learning_rate": 1.3198609300304217e-05, + "loss": 0.2716, + "step": 12520 + }, + { + "epoch": 1.02, + "learning_rate": 1.319806605823555e-05, + "loss": 0.3058, + "step": 12521 + }, + { + "epoch": 1.02, + "learning_rate": 1.3197522816166886e-05, + "loss": 0.1489, + "step": 12522 + }, + { + "epoch": 1.02, + "learning_rate": 1.3196979574098218e-05, + "loss": 0.218, + "step": 12523 + }, + { + "epoch": 1.02, + "learning_rate": 1.3196436332029554e-05, + "loss": 0.4369, + "step": 12524 + }, + { + "epoch": 1.02, + "learning_rate": 1.3195893089960887e-05, + "loss": 0.4888, + "step": 12525 + }, + { + "epoch": 1.02, + "learning_rate": 1.3195349847892223e-05, + "loss": 0.3206, + "step": 12526 + }, + { + "epoch": 1.02, + "learning_rate": 1.3194806605823555e-05, + "loss": 0.2131, + "step": 12527 + }, + { + "epoch": 1.02, + "learning_rate": 1.3194263363754891e-05, + "loss": 0.1913, + "step": 12528 + }, + { + "epoch": 1.02, + "learning_rate": 1.3193720121686224e-05, + "loss": 0.2293, + "step": 12529 + }, + { + "epoch": 1.02, + "learning_rate": 1.319317687961756e-05, + "loss": 0.6484, + "step": 12530 + }, + { + "epoch": 1.02, + "learning_rate": 1.3192633637548892e-05, + "loss": 0.1992, + "step": 12531 + }, + { + "epoch": 1.02, + "learning_rate": 1.3192090395480226e-05, + "loss": 0.5449, + "step": 12532 + }, + { + "epoch": 1.02, + "learning_rate": 1.319154715341156e-05, + "loss": 0.2044, + "step": 12533 + }, + { + "epoch": 1.02, + "learning_rate": 1.3191003911342895e-05, + "loss": 0.2339, + "step": 12534 + }, + { + "epoch": 1.02, + "learning_rate": 1.3190460669274229e-05, + "loss": 0.3086, + "step": 12535 + }, + { + "epoch": 1.02, + "learning_rate": 1.3189917427205563e-05, + "loss": 0.4489, + "step": 12536 + }, + { + "epoch": 1.02, + "learning_rate": 1.3189374185136898e-05, + "loss": 0.4927, + "step": 12537 + }, + { + "epoch": 1.02, + "learning_rate": 1.3188830943068232e-05, + "loss": 0.3685, + "step": 12538 + }, + { + "epoch": 1.02, + "learning_rate": 1.3188287700999566e-05, + "loss": 0.16, + "step": 12539 + }, + { + "epoch": 1.02, + "learning_rate": 1.31877444589309e-05, + "loss": 0.4505, + "step": 12540 + }, + { + "epoch": 1.02, + "learning_rate": 1.3187201216862236e-05, + "loss": 0.1051, + "step": 12541 + }, + { + "epoch": 1.02, + "learning_rate": 1.3186657974793569e-05, + "loss": 0.3752, + "step": 12542 + }, + { + "epoch": 1.02, + "learning_rate": 1.3186114732724905e-05, + "loss": 0.3997, + "step": 12543 + }, + { + "epoch": 1.02, + "learning_rate": 1.3185571490656237e-05, + "loss": 0.6245, + "step": 12544 + }, + { + "epoch": 1.02, + "learning_rate": 1.3185028248587573e-05, + "loss": 0.2266, + "step": 12545 + }, + { + "epoch": 1.02, + "learning_rate": 1.3184485006518906e-05, + "loss": 0.3259, + "step": 12546 + }, + { + "epoch": 1.02, + "learning_rate": 1.3183941764450242e-05, + "loss": 0.2985, + "step": 12547 + }, + { + "epoch": 1.02, + "learning_rate": 1.3183398522381574e-05, + "loss": 0.6887, + "step": 12548 + }, + { + "epoch": 1.02, + "learning_rate": 1.318285528031291e-05, + "loss": 0.4511, + "step": 12549 + }, + { + "epoch": 1.02, + "learning_rate": 1.3182312038244243e-05, + "loss": 0.434, + "step": 12550 + }, + { + "epoch": 1.02, + "learning_rate": 1.3181768796175575e-05, + "loss": 0.53, + "step": 12551 + }, + { + "epoch": 1.02, + "learning_rate": 1.3181225554106911e-05, + "loss": 0.2614, + "step": 12552 + }, + { + "epoch": 1.02, + "learning_rate": 1.3180682312038244e-05, + "loss": 0.5341, + "step": 12553 + }, + { + "epoch": 1.02, + "learning_rate": 1.318013906996958e-05, + "loss": 0.3182, + "step": 12554 + }, + { + "epoch": 1.02, + "learning_rate": 1.3179595827900912e-05, + "loss": 0.4286, + "step": 12555 + }, + { + "epoch": 1.02, + "learning_rate": 1.3179052585832248e-05, + "loss": 0.3112, + "step": 12556 + }, + { + "epoch": 1.02, + "learning_rate": 1.317850934376358e-05, + "loss": 0.0856, + "step": 12557 + }, + { + "epoch": 1.02, + "learning_rate": 1.3177966101694916e-05, + "loss": 0.2124, + "step": 12558 + }, + { + "epoch": 1.02, + "learning_rate": 1.317742285962625e-05, + "loss": 0.2499, + "step": 12559 + }, + { + "epoch": 1.02, + "learning_rate": 1.3176879617557585e-05, + "loss": 0.5278, + "step": 12560 + }, + { + "epoch": 1.02, + "learning_rate": 1.3176336375488919e-05, + "loss": 0.5085, + "step": 12561 + }, + { + "epoch": 1.02, + "learning_rate": 1.3175793133420253e-05, + "loss": 0.3598, + "step": 12562 + }, + { + "epoch": 1.02, + "learning_rate": 1.3175249891351588e-05, + "loss": 0.313, + "step": 12563 + }, + { + "epoch": 1.02, + "learning_rate": 1.3174706649282922e-05, + "loss": 0.3602, + "step": 12564 + }, + { + "epoch": 1.02, + "learning_rate": 1.3174163407214256e-05, + "loss": 0.4215, + "step": 12565 + }, + { + "epoch": 1.02, + "learning_rate": 1.317362016514559e-05, + "loss": 0.216, + "step": 12566 + }, + { + "epoch": 1.02, + "learning_rate": 1.3173076923076925e-05, + "loss": 0.5527, + "step": 12567 + }, + { + "epoch": 1.02, + "learning_rate": 1.3172533681008259e-05, + "loss": 0.4618, + "step": 12568 + }, + { + "epoch": 1.02, + "learning_rate": 1.3171990438939593e-05, + "loss": 0.4203, + "step": 12569 + }, + { + "epoch": 1.02, + "learning_rate": 1.3171447196870926e-05, + "loss": 0.3351, + "step": 12570 + }, + { + "epoch": 1.02, + "learning_rate": 1.3170903954802261e-05, + "loss": 0.3083, + "step": 12571 + }, + { + "epoch": 1.02, + "learning_rate": 1.3170360712733594e-05, + "loss": 0.5847, + "step": 12572 + }, + { + "epoch": 1.02, + "learning_rate": 1.316981747066493e-05, + "loss": 0.403, + "step": 12573 + }, + { + "epoch": 1.02, + "learning_rate": 1.3169274228596262e-05, + "loss": 0.5313, + "step": 12574 + }, + { + "epoch": 1.02, + "learning_rate": 1.3168730986527598e-05, + "loss": 0.5512, + "step": 12575 + }, + { + "epoch": 1.02, + "learning_rate": 1.3168187744458931e-05, + "loss": 0.3434, + "step": 12576 + }, + { + "epoch": 1.02, + "learning_rate": 1.3167644502390267e-05, + "loss": 0.4781, + "step": 12577 + }, + { + "epoch": 1.02, + "learning_rate": 1.31671012603216e-05, + "loss": 0.4628, + "step": 12578 + }, + { + "epoch": 1.03, + "learning_rate": 1.3166558018252935e-05, + "loss": 0.1949, + "step": 12579 + }, + { + "epoch": 1.03, + "learning_rate": 1.3166014776184268e-05, + "loss": 0.3223, + "step": 12580 + }, + { + "epoch": 1.03, + "learning_rate": 1.3165471534115604e-05, + "loss": 0.3947, + "step": 12581 + }, + { + "epoch": 1.03, + "learning_rate": 1.3164928292046936e-05, + "loss": 0.1059, + "step": 12582 + }, + { + "epoch": 1.03, + "learning_rate": 1.3164385049978272e-05, + "loss": 0.2493, + "step": 12583 + }, + { + "epoch": 1.03, + "learning_rate": 1.3163841807909605e-05, + "loss": 0.268, + "step": 12584 + }, + { + "epoch": 1.03, + "learning_rate": 1.316329856584094e-05, + "loss": 0.3389, + "step": 12585 + }, + { + "epoch": 1.03, + "learning_rate": 1.3162755323772273e-05, + "loss": 0.2999, + "step": 12586 + }, + { + "epoch": 1.03, + "learning_rate": 1.3162212081703609e-05, + "loss": 0.3026, + "step": 12587 + }, + { + "epoch": 1.03, + "learning_rate": 1.3161668839634942e-05, + "loss": 0.2974, + "step": 12588 + }, + { + "epoch": 1.03, + "learning_rate": 1.3161125597566276e-05, + "loss": 0.2943, + "step": 12589 + }, + { + "epoch": 1.03, + "learning_rate": 1.316058235549761e-05, + "loss": 0.1735, + "step": 12590 + }, + { + "epoch": 1.03, + "learning_rate": 1.3160039113428944e-05, + "loss": 0.4238, + "step": 12591 + }, + { + "epoch": 1.03, + "learning_rate": 1.3159495871360279e-05, + "loss": 0.4306, + "step": 12592 + }, + { + "epoch": 1.03, + "learning_rate": 1.3158952629291613e-05, + "loss": 0.2519, + "step": 12593 + }, + { + "epoch": 1.03, + "learning_rate": 1.3158409387222949e-05, + "loss": 0.3202, + "step": 12594 + }, + { + "epoch": 1.03, + "learning_rate": 1.3157866145154281e-05, + "loss": 0.3102, + "step": 12595 + }, + { + "epoch": 1.03, + "learning_rate": 1.3157322903085617e-05, + "loss": 0.5135, + "step": 12596 + }, + { + "epoch": 1.03, + "learning_rate": 1.315677966101695e-05, + "loss": 0.3516, + "step": 12597 + }, + { + "epoch": 1.03, + "learning_rate": 1.3156236418948286e-05, + "loss": 0.3905, + "step": 12598 + }, + { + "epoch": 1.03, + "learning_rate": 1.3155693176879618e-05, + "loss": 0.238, + "step": 12599 + }, + { + "epoch": 1.03, + "learning_rate": 1.3155149934810954e-05, + "loss": 0.4379, + "step": 12600 + }, + { + "epoch": 1.03, + "learning_rate": 1.3154606692742287e-05, + "loss": 0.3331, + "step": 12601 + }, + { + "epoch": 1.03, + "learning_rate": 1.3154063450673623e-05, + "loss": 0.2613, + "step": 12602 + }, + { + "epoch": 1.03, + "learning_rate": 1.3153520208604955e-05, + "loss": 0.2783, + "step": 12603 + }, + { + "epoch": 1.03, + "learning_rate": 1.3152976966536291e-05, + "loss": 0.456, + "step": 12604 + }, + { + "epoch": 1.03, + "learning_rate": 1.3152433724467624e-05, + "loss": 0.458, + "step": 12605 + }, + { + "epoch": 1.03, + "learning_rate": 1.315189048239896e-05, + "loss": 0.2938, + "step": 12606 + }, + { + "epoch": 1.03, + "learning_rate": 1.3151347240330292e-05, + "loss": 0.2737, + "step": 12607 + }, + { + "epoch": 1.03, + "learning_rate": 1.3150803998261625e-05, + "loss": 0.4412, + "step": 12608 + }, + { + "epoch": 1.03, + "learning_rate": 1.315026075619296e-05, + "loss": 0.5637, + "step": 12609 + }, + { + "epoch": 1.03, + "learning_rate": 1.3149717514124293e-05, + "loss": 0.216, + "step": 12610 + }, + { + "epoch": 1.03, + "learning_rate": 1.3149174272055629e-05, + "loss": 0.2411, + "step": 12611 + }, + { + "epoch": 1.03, + "learning_rate": 1.3148631029986963e-05, + "loss": 0.2479, + "step": 12612 + }, + { + "epoch": 1.03, + "learning_rate": 1.3148087787918297e-05, + "loss": 0.3341, + "step": 12613 + }, + { + "epoch": 1.03, + "learning_rate": 1.3147544545849632e-05, + "loss": 0.5014, + "step": 12614 + }, + { + "epoch": 1.03, + "learning_rate": 1.3147001303780966e-05, + "loss": 0.2895, + "step": 12615 + }, + { + "epoch": 1.03, + "learning_rate": 1.31464580617123e-05, + "loss": 0.2916, + "step": 12616 + }, + { + "epoch": 1.03, + "learning_rate": 1.3145914819643634e-05, + "loss": 0.5039, + "step": 12617 + }, + { + "epoch": 1.03, + "learning_rate": 1.3145371577574969e-05, + "loss": 0.4027, + "step": 12618 + }, + { + "epoch": 1.03, + "learning_rate": 1.3144828335506303e-05, + "loss": 0.1458, + "step": 12619 + }, + { + "epoch": 1.03, + "learning_rate": 1.3144285093437637e-05, + "loss": 0.3167, + "step": 12620 + }, + { + "epoch": 1.03, + "learning_rate": 1.3143741851368971e-05, + "loss": 0.34, + "step": 12621 + }, + { + "epoch": 1.03, + "learning_rate": 1.3143198609300306e-05, + "loss": 0.4193, + "step": 12622 + }, + { + "epoch": 1.03, + "learning_rate": 1.314265536723164e-05, + "loss": 0.2628, + "step": 12623 + }, + { + "epoch": 1.03, + "learning_rate": 1.3142112125162974e-05, + "loss": 0.3907, + "step": 12624 + }, + { + "epoch": 1.03, + "learning_rate": 1.3141568883094308e-05, + "loss": 0.1067, + "step": 12625 + }, + { + "epoch": 1.03, + "learning_rate": 1.3141025641025642e-05, + "loss": 0.3019, + "step": 12626 + }, + { + "epoch": 1.03, + "learning_rate": 1.3140482398956975e-05, + "loss": 0.2191, + "step": 12627 + }, + { + "epoch": 1.03, + "learning_rate": 1.3139939156888311e-05, + "loss": 0.3592, + "step": 12628 + }, + { + "epoch": 1.03, + "learning_rate": 1.3139395914819643e-05, + "loss": 0.2082, + "step": 12629 + }, + { + "epoch": 1.03, + "learning_rate": 1.313885267275098e-05, + "loss": 0.3125, + "step": 12630 + }, + { + "epoch": 1.03, + "learning_rate": 1.3138309430682312e-05, + "loss": 0.416, + "step": 12631 + }, + { + "epoch": 1.03, + "learning_rate": 1.3137766188613648e-05, + "loss": 0.3571, + "step": 12632 + }, + { + "epoch": 1.03, + "learning_rate": 1.313722294654498e-05, + "loss": 0.4743, + "step": 12633 + }, + { + "epoch": 1.03, + "learning_rate": 1.3136679704476316e-05, + "loss": 0.3893, + "step": 12634 + }, + { + "epoch": 1.03, + "learning_rate": 1.3136136462407649e-05, + "loss": 0.1876, + "step": 12635 + }, + { + "epoch": 1.03, + "learning_rate": 1.3135593220338985e-05, + "loss": 0.3581, + "step": 12636 + }, + { + "epoch": 1.03, + "learning_rate": 1.3135049978270317e-05, + "loss": 0.1188, + "step": 12637 + }, + { + "epoch": 1.03, + "learning_rate": 1.3134506736201653e-05, + "loss": 0.3185, + "step": 12638 + }, + { + "epoch": 1.03, + "learning_rate": 1.3133963494132986e-05, + "loss": 0.3581, + "step": 12639 + }, + { + "epoch": 1.03, + "learning_rate": 1.3133420252064322e-05, + "loss": 0.3816, + "step": 12640 + }, + { + "epoch": 1.03, + "learning_rate": 1.3132877009995654e-05, + "loss": 0.3246, + "step": 12641 + }, + { + "epoch": 1.03, + "learning_rate": 1.313233376792699e-05, + "loss": 0.3258, + "step": 12642 + }, + { + "epoch": 1.03, + "learning_rate": 1.3131790525858323e-05, + "loss": 0.4072, + "step": 12643 + }, + { + "epoch": 1.03, + "learning_rate": 1.3131247283789659e-05, + "loss": 0.2632, + "step": 12644 + }, + { + "epoch": 1.03, + "learning_rate": 1.3130704041720991e-05, + "loss": 0.3073, + "step": 12645 + }, + { + "epoch": 1.03, + "learning_rate": 1.3130160799652325e-05, + "loss": 0.4295, + "step": 12646 + }, + { + "epoch": 1.03, + "learning_rate": 1.312961755758366e-05, + "loss": 0.5179, + "step": 12647 + }, + { + "epoch": 1.03, + "learning_rate": 1.3129074315514994e-05, + "loss": 0.2088, + "step": 12648 + }, + { + "epoch": 1.03, + "learning_rate": 1.312853107344633e-05, + "loss": 0.1717, + "step": 12649 + }, + { + "epoch": 1.03, + "learning_rate": 1.3127987831377662e-05, + "loss": 0.2969, + "step": 12650 + }, + { + "epoch": 1.03, + "learning_rate": 1.3127444589308998e-05, + "loss": 0.3052, + "step": 12651 + }, + { + "epoch": 1.03, + "learning_rate": 1.312690134724033e-05, + "loss": 0.3349, + "step": 12652 + }, + { + "epoch": 1.03, + "learning_rate": 1.3126358105171667e-05, + "loss": 0.3883, + "step": 12653 + }, + { + "epoch": 1.03, + "learning_rate": 1.3125814863103e-05, + "loss": 0.3805, + "step": 12654 + }, + { + "epoch": 1.03, + "learning_rate": 1.3125271621034335e-05, + "loss": 0.3508, + "step": 12655 + }, + { + "epoch": 1.03, + "learning_rate": 1.3124728378965668e-05, + "loss": 0.4099, + "step": 12656 + }, + { + "epoch": 1.03, + "learning_rate": 1.3124185136897004e-05, + "loss": 0.5061, + "step": 12657 + }, + { + "epoch": 1.03, + "learning_rate": 1.3123641894828336e-05, + "loss": 0.3615, + "step": 12658 + }, + { + "epoch": 1.03, + "learning_rate": 1.3123098652759672e-05, + "loss": 0.3499, + "step": 12659 + }, + { + "epoch": 1.03, + "learning_rate": 1.3122555410691005e-05, + "loss": 0.5375, + "step": 12660 + }, + { + "epoch": 1.03, + "learning_rate": 1.312201216862234e-05, + "loss": 0.1447, + "step": 12661 + }, + { + "epoch": 1.03, + "learning_rate": 1.3121468926553673e-05, + "loss": 0.2681, + "step": 12662 + }, + { + "epoch": 1.03, + "learning_rate": 1.3120925684485009e-05, + "loss": 0.395, + "step": 12663 + }, + { + "epoch": 1.03, + "learning_rate": 1.3120382442416342e-05, + "loss": 0.428, + "step": 12664 + }, + { + "epoch": 1.03, + "learning_rate": 1.3119839200347677e-05, + "loss": 0.3971, + "step": 12665 + }, + { + "epoch": 1.03, + "learning_rate": 1.311929595827901e-05, + "loss": 0.4354, + "step": 12666 + }, + { + "epoch": 1.03, + "learning_rate": 1.3118752716210344e-05, + "loss": 0.3346, + "step": 12667 + }, + { + "epoch": 1.03, + "learning_rate": 1.3118209474141678e-05, + "loss": 0.6931, + "step": 12668 + }, + { + "epoch": 1.03, + "learning_rate": 1.3117666232073013e-05, + "loss": 0.294, + "step": 12669 + }, + { + "epoch": 1.03, + "learning_rate": 1.3117122990004347e-05, + "loss": 0.2437, + "step": 12670 + }, + { + "epoch": 1.03, + "learning_rate": 1.3116579747935681e-05, + "loss": 0.2869, + "step": 12671 + }, + { + "epoch": 1.03, + "learning_rate": 1.3116036505867015e-05, + "loss": 0.3948, + "step": 12672 + }, + { + "epoch": 1.03, + "learning_rate": 1.311549326379835e-05, + "loss": 0.3615, + "step": 12673 + }, + { + "epoch": 1.03, + "learning_rate": 1.3114950021729684e-05, + "loss": 0.4062, + "step": 12674 + }, + { + "epoch": 1.03, + "learning_rate": 1.3114406779661018e-05, + "loss": 0.3928, + "step": 12675 + }, + { + "epoch": 1.03, + "learning_rate": 1.3113863537592352e-05, + "loss": 0.4008, + "step": 12676 + }, + { + "epoch": 1.03, + "learning_rate": 1.3113320295523687e-05, + "loss": 0.1543, + "step": 12677 + }, + { + "epoch": 1.03, + "learning_rate": 1.311277705345502e-05, + "loss": 0.2128, + "step": 12678 + }, + { + "epoch": 1.03, + "learning_rate": 1.3112233811386355e-05, + "loss": 0.3279, + "step": 12679 + }, + { + "epoch": 1.03, + "learning_rate": 1.311169056931769e-05, + "loss": 0.2881, + "step": 12680 + }, + { + "epoch": 1.03, + "learning_rate": 1.3111147327249023e-05, + "loss": 0.3075, + "step": 12681 + }, + { + "epoch": 1.03, + "learning_rate": 1.3110604085180358e-05, + "loss": 0.3149, + "step": 12682 + }, + { + "epoch": 1.03, + "learning_rate": 1.3110060843111692e-05, + "loss": 0.4299, + "step": 12683 + }, + { + "epoch": 1.03, + "learning_rate": 1.3109517601043026e-05, + "loss": 0.3984, + "step": 12684 + }, + { + "epoch": 1.03, + "learning_rate": 1.310897435897436e-05, + "loss": 0.2933, + "step": 12685 + }, + { + "epoch": 1.03, + "learning_rate": 1.3108431116905693e-05, + "loss": 0.6747, + "step": 12686 + }, + { + "epoch": 1.03, + "learning_rate": 1.3107887874837029e-05, + "loss": 0.2534, + "step": 12687 + }, + { + "epoch": 1.03, + "learning_rate": 1.3107344632768361e-05, + "loss": 0.3335, + "step": 12688 + }, + { + "epoch": 1.03, + "learning_rate": 1.3106801390699697e-05, + "loss": 0.4206, + "step": 12689 + }, + { + "epoch": 1.03, + "learning_rate": 1.310625814863103e-05, + "loss": 0.732, + "step": 12690 + }, + { + "epoch": 1.03, + "learning_rate": 1.3105714906562366e-05, + "loss": 0.184, + "step": 12691 + }, + { + "epoch": 1.03, + "learning_rate": 1.3105171664493698e-05, + "loss": 0.4611, + "step": 12692 + }, + { + "epoch": 1.03, + "learning_rate": 1.3104628422425034e-05, + "loss": 0.3171, + "step": 12693 + }, + { + "epoch": 1.03, + "learning_rate": 1.3104085180356367e-05, + "loss": 0.2608, + "step": 12694 + }, + { + "epoch": 1.03, + "learning_rate": 1.3103541938287703e-05, + "loss": 0.2897, + "step": 12695 + }, + { + "epoch": 1.03, + "learning_rate": 1.3102998696219035e-05, + "loss": 0.3402, + "step": 12696 + }, + { + "epoch": 1.03, + "learning_rate": 1.3102455454150371e-05, + "loss": 0.5533, + "step": 12697 + }, + { + "epoch": 1.03, + "learning_rate": 1.3101912212081704e-05, + "loss": 0.2297, + "step": 12698 + }, + { + "epoch": 1.03, + "learning_rate": 1.310136897001304e-05, + "loss": 0.338, + "step": 12699 + }, + { + "epoch": 1.03, + "learning_rate": 1.3100825727944372e-05, + "loss": 0.2793, + "step": 12700 + }, + { + "epoch": 1.03, + "learning_rate": 1.3100282485875708e-05, + "loss": 0.3719, + "step": 12701 + }, + { + "epoch": 1.04, + "learning_rate": 1.3099739243807042e-05, + "loss": 0.4656, + "step": 12702 + }, + { + "epoch": 1.04, + "learning_rate": 1.3099196001738376e-05, + "loss": 0.3861, + "step": 12703 + }, + { + "epoch": 1.04, + "learning_rate": 1.309865275966971e-05, + "loss": 0.5118, + "step": 12704 + }, + { + "epoch": 1.04, + "learning_rate": 1.3098109517601043e-05, + "loss": 0.4594, + "step": 12705 + }, + { + "epoch": 1.04, + "learning_rate": 1.309756627553238e-05, + "loss": 0.3295, + "step": 12706 + }, + { + "epoch": 1.04, + "learning_rate": 1.3097023033463712e-05, + "loss": 0.4678, + "step": 12707 + }, + { + "epoch": 1.04, + "learning_rate": 1.3096479791395048e-05, + "loss": 0.5391, + "step": 12708 + }, + { + "epoch": 1.04, + "learning_rate": 1.309593654932638e-05, + "loss": 0.2841, + "step": 12709 + }, + { + "epoch": 1.04, + "learning_rate": 1.3095393307257716e-05, + "loss": 0.2198, + "step": 12710 + }, + { + "epoch": 1.04, + "learning_rate": 1.3094850065189049e-05, + "loss": 0.3931, + "step": 12711 + }, + { + "epoch": 1.04, + "learning_rate": 1.3094306823120385e-05, + "loss": 0.1817, + "step": 12712 + }, + { + "epoch": 1.04, + "learning_rate": 1.3093763581051717e-05, + "loss": 0.3115, + "step": 12713 + }, + { + "epoch": 1.04, + "learning_rate": 1.3093220338983053e-05, + "loss": 0.2581, + "step": 12714 + }, + { + "epoch": 1.04, + "learning_rate": 1.3092677096914386e-05, + "loss": 0.2007, + "step": 12715 + }, + { + "epoch": 1.04, + "learning_rate": 1.3092133854845721e-05, + "loss": 0.4203, + "step": 12716 + }, + { + "epoch": 1.04, + "learning_rate": 1.3091590612777054e-05, + "loss": 0.5773, + "step": 12717 + }, + { + "epoch": 1.04, + "learning_rate": 1.309104737070839e-05, + "loss": 0.3732, + "step": 12718 + }, + { + "epoch": 1.04, + "learning_rate": 1.3090504128639722e-05, + "loss": 0.4401, + "step": 12719 + }, + { + "epoch": 1.04, + "learning_rate": 1.3089960886571058e-05, + "loss": 0.2081, + "step": 12720 + }, + { + "epoch": 1.04, + "learning_rate": 1.3089417644502391e-05, + "loss": 0.1989, + "step": 12721 + }, + { + "epoch": 1.04, + "learning_rate": 1.3088874402433727e-05, + "loss": 0.2149, + "step": 12722 + }, + { + "epoch": 1.04, + "learning_rate": 1.308833116036506e-05, + "loss": 0.201, + "step": 12723 + }, + { + "epoch": 1.04, + "learning_rate": 1.3087787918296394e-05, + "loss": 0.3113, + "step": 12724 + }, + { + "epoch": 1.04, + "learning_rate": 1.3087244676227728e-05, + "loss": 0.5273, + "step": 12725 + }, + { + "epoch": 1.04, + "learning_rate": 1.3086701434159062e-05, + "loss": 0.3066, + "step": 12726 + }, + { + "epoch": 1.04, + "learning_rate": 1.3086158192090396e-05, + "loss": 0.1847, + "step": 12727 + }, + { + "epoch": 1.04, + "learning_rate": 1.308561495002173e-05, + "loss": 0.3837, + "step": 12728 + }, + { + "epoch": 1.04, + "learning_rate": 1.3085071707953065e-05, + "loss": 0.2515, + "step": 12729 + }, + { + "epoch": 1.04, + "learning_rate": 1.3084528465884399e-05, + "loss": 0.2601, + "step": 12730 + }, + { + "epoch": 1.04, + "learning_rate": 1.3083985223815733e-05, + "loss": 0.2833, + "step": 12731 + }, + { + "epoch": 1.04, + "learning_rate": 1.3083441981747067e-05, + "loss": 0.1244, + "step": 12732 + }, + { + "epoch": 1.04, + "learning_rate": 1.3082898739678402e-05, + "loss": 0.2236, + "step": 12733 + }, + { + "epoch": 1.04, + "learning_rate": 1.3082355497609736e-05, + "loss": 0.1559, + "step": 12734 + }, + { + "epoch": 1.04, + "learning_rate": 1.308181225554107e-05, + "loss": 0.4, + "step": 12735 + }, + { + "epoch": 1.04, + "learning_rate": 1.3081269013472404e-05, + "loss": 0.3356, + "step": 12736 + }, + { + "epoch": 1.04, + "learning_rate": 1.3080725771403739e-05, + "loss": 0.1204, + "step": 12737 + }, + { + "epoch": 1.04, + "learning_rate": 1.3080182529335073e-05, + "loss": 0.3141, + "step": 12738 + }, + { + "epoch": 1.04, + "learning_rate": 1.3079639287266409e-05, + "loss": 0.4089, + "step": 12739 + }, + { + "epoch": 1.04, + "learning_rate": 1.3079096045197741e-05, + "loss": 0.3914, + "step": 12740 + }, + { + "epoch": 1.04, + "learning_rate": 1.3078552803129077e-05, + "loss": 0.2996, + "step": 12741 + }, + { + "epoch": 1.04, + "learning_rate": 1.307800956106041e-05, + "loss": 0.1809, + "step": 12742 + }, + { + "epoch": 1.04, + "learning_rate": 1.3077466318991742e-05, + "loss": 0.1791, + "step": 12743 + }, + { + "epoch": 1.04, + "learning_rate": 1.3076923076923078e-05, + "loss": 0.172, + "step": 12744 + }, + { + "epoch": 1.04, + "learning_rate": 1.307637983485441e-05, + "loss": 0.2434, + "step": 12745 + }, + { + "epoch": 1.04, + "learning_rate": 1.3075836592785747e-05, + "loss": 0.2002, + "step": 12746 + }, + { + "epoch": 1.04, + "learning_rate": 1.307529335071708e-05, + "loss": 0.2695, + "step": 12747 + }, + { + "epoch": 1.04, + "learning_rate": 1.3074750108648415e-05, + "loss": 0.4388, + "step": 12748 + }, + { + "epoch": 1.04, + "learning_rate": 1.3074206866579748e-05, + "loss": 0.582, + "step": 12749 + }, + { + "epoch": 1.04, + "learning_rate": 1.3073663624511084e-05, + "loss": 0.4712, + "step": 12750 + }, + { + "epoch": 1.04, + "eval_accuracy": 0.8398369842078451, + "eval_loss": 0.4504384398460388, + "eval_runtime": 22.3065, + "eval_samples_per_second": 440.006, + "eval_steps_per_second": 3.452, + "step": 12750 + }, + { + "epoch": 1.04, + "learning_rate": 1.3073120382442416e-05, + "loss": 0.3013, + "step": 12751 + }, + { + "epoch": 1.04, + "learning_rate": 1.3072577140373752e-05, + "loss": 0.3949, + "step": 12752 + }, + { + "epoch": 1.04, + "learning_rate": 1.3072033898305085e-05, + "loss": 0.3239, + "step": 12753 + }, + { + "epoch": 1.04, + "learning_rate": 1.307149065623642e-05, + "loss": 0.4218, + "step": 12754 + }, + { + "epoch": 1.04, + "learning_rate": 1.3070947414167753e-05, + "loss": 0.1992, + "step": 12755 + }, + { + "epoch": 1.04, + "learning_rate": 1.3070404172099089e-05, + "loss": 0.5127, + "step": 12756 + }, + { + "epoch": 1.04, + "learning_rate": 1.3069860930030423e-05, + "loss": 0.1801, + "step": 12757 + }, + { + "epoch": 1.04, + "learning_rate": 1.3069317687961757e-05, + "loss": 0.416, + "step": 12758 + }, + { + "epoch": 1.04, + "learning_rate": 1.3068774445893092e-05, + "loss": 0.3243, + "step": 12759 + }, + { + "epoch": 1.04, + "learning_rate": 1.3068231203824426e-05, + "loss": 0.4265, + "step": 12760 + }, + { + "epoch": 1.04, + "learning_rate": 1.306768796175576e-05, + "loss": 0.4672, + "step": 12761 + }, + { + "epoch": 1.04, + "learning_rate": 1.3067144719687093e-05, + "loss": 0.3293, + "step": 12762 + }, + { + "epoch": 1.04, + "learning_rate": 1.3066601477618429e-05, + "loss": 0.4251, + "step": 12763 + }, + { + "epoch": 1.04, + "learning_rate": 1.3066058235549761e-05, + "loss": 0.5035, + "step": 12764 + }, + { + "epoch": 1.04, + "learning_rate": 1.3065514993481097e-05, + "loss": 0.4407, + "step": 12765 + }, + { + "epoch": 1.04, + "learning_rate": 1.306497175141243e-05, + "loss": 0.2946, + "step": 12766 + }, + { + "epoch": 1.04, + "learning_rate": 1.3064428509343766e-05, + "loss": 0.385, + "step": 12767 + }, + { + "epoch": 1.04, + "learning_rate": 1.3063885267275098e-05, + "loss": 0.2899, + "step": 12768 + }, + { + "epoch": 1.04, + "learning_rate": 1.3063342025206434e-05, + "loss": 0.612, + "step": 12769 + }, + { + "epoch": 1.04, + "learning_rate": 1.3062798783137767e-05, + "loss": 0.1868, + "step": 12770 + }, + { + "epoch": 1.04, + "learning_rate": 1.3062255541069102e-05, + "loss": 0.2605, + "step": 12771 + }, + { + "epoch": 1.04, + "learning_rate": 1.3061712299000435e-05, + "loss": 0.2146, + "step": 12772 + }, + { + "epoch": 1.04, + "learning_rate": 1.3061169056931771e-05, + "loss": 0.4331, + "step": 12773 + }, + { + "epoch": 1.04, + "learning_rate": 1.3060625814863103e-05, + "loss": 0.2229, + "step": 12774 + }, + { + "epoch": 1.04, + "learning_rate": 1.306008257279444e-05, + "loss": 0.5147, + "step": 12775 + }, + { + "epoch": 1.04, + "learning_rate": 1.3059539330725772e-05, + "loss": 0.2845, + "step": 12776 + }, + { + "epoch": 1.04, + "learning_rate": 1.3058996088657108e-05, + "loss": 0.3616, + "step": 12777 + }, + { + "epoch": 1.04, + "learning_rate": 1.305845284658844e-05, + "loss": 0.3223, + "step": 12778 + }, + { + "epoch": 1.04, + "learning_rate": 1.3057909604519776e-05, + "loss": 0.2071, + "step": 12779 + }, + { + "epoch": 1.04, + "learning_rate": 1.3057366362451109e-05, + "loss": 0.2985, + "step": 12780 + }, + { + "epoch": 1.04, + "learning_rate": 1.3056823120382443e-05, + "loss": 0.0754, + "step": 12781 + }, + { + "epoch": 1.04, + "learning_rate": 1.3056279878313777e-05, + "loss": 0.2308, + "step": 12782 + }, + { + "epoch": 1.04, + "learning_rate": 1.3055736636245112e-05, + "loss": 0.3002, + "step": 12783 + }, + { + "epoch": 1.04, + "learning_rate": 1.3055193394176446e-05, + "loss": 0.3597, + "step": 12784 + }, + { + "epoch": 1.04, + "learning_rate": 1.305465015210778e-05, + "loss": 0.4908, + "step": 12785 + }, + { + "epoch": 1.04, + "learning_rate": 1.3054106910039114e-05, + "loss": 0.4009, + "step": 12786 + }, + { + "epoch": 1.04, + "learning_rate": 1.3053563667970448e-05, + "loss": 0.2807, + "step": 12787 + }, + { + "epoch": 1.04, + "learning_rate": 1.3053020425901783e-05, + "loss": 0.4982, + "step": 12788 + }, + { + "epoch": 1.04, + "learning_rate": 1.3052477183833117e-05, + "loss": 0.4939, + "step": 12789 + }, + { + "epoch": 1.04, + "learning_rate": 1.3051933941764451e-05, + "loss": 0.358, + "step": 12790 + }, + { + "epoch": 1.04, + "learning_rate": 1.3051390699695785e-05, + "loss": 0.4292, + "step": 12791 + }, + { + "epoch": 1.04, + "learning_rate": 1.305084745762712e-05, + "loss": 0.2866, + "step": 12792 + }, + { + "epoch": 1.04, + "learning_rate": 1.3050304215558454e-05, + "loss": 0.3023, + "step": 12793 + }, + { + "epoch": 1.04, + "learning_rate": 1.304976097348979e-05, + "loss": 0.3127, + "step": 12794 + }, + { + "epoch": 1.04, + "learning_rate": 1.3049217731421122e-05, + "loss": 0.3638, + "step": 12795 + }, + { + "epoch": 1.04, + "learning_rate": 1.3048674489352458e-05, + "loss": 0.3854, + "step": 12796 + }, + { + "epoch": 1.04, + "learning_rate": 1.304813124728379e-05, + "loss": 0.2086, + "step": 12797 + }, + { + "epoch": 1.04, + "learning_rate": 1.3047588005215127e-05, + "loss": 0.2622, + "step": 12798 + }, + { + "epoch": 1.04, + "learning_rate": 1.304704476314646e-05, + "loss": 0.1361, + "step": 12799 + }, + { + "epoch": 1.04, + "learning_rate": 1.3046501521077792e-05, + "loss": 0.3426, + "step": 12800 + }, + { + "epoch": 1.04, + "learning_rate": 1.3045958279009128e-05, + "loss": 0.1865, + "step": 12801 + }, + { + "epoch": 1.04, + "learning_rate": 1.304541503694046e-05, + "loss": 0.2397, + "step": 12802 + }, + { + "epoch": 1.04, + "learning_rate": 1.3044871794871796e-05, + "loss": 0.4052, + "step": 12803 + }, + { + "epoch": 1.04, + "learning_rate": 1.3044328552803129e-05, + "loss": 0.2077, + "step": 12804 + }, + { + "epoch": 1.04, + "learning_rate": 1.3043785310734465e-05, + "loss": 0.2859, + "step": 12805 + }, + { + "epoch": 1.04, + "learning_rate": 1.3043242068665797e-05, + "loss": 0.1117, + "step": 12806 + }, + { + "epoch": 1.04, + "learning_rate": 1.3042698826597133e-05, + "loss": 0.7368, + "step": 12807 + }, + { + "epoch": 1.04, + "learning_rate": 1.3042155584528466e-05, + "loss": 0.3493, + "step": 12808 + }, + { + "epoch": 1.04, + "learning_rate": 1.3041612342459802e-05, + "loss": 0.4474, + "step": 12809 + }, + { + "epoch": 1.04, + "learning_rate": 1.3041069100391136e-05, + "loss": 0.2139, + "step": 12810 + }, + { + "epoch": 1.04, + "learning_rate": 1.304052585832247e-05, + "loss": 0.3588, + "step": 12811 + }, + { + "epoch": 1.04, + "learning_rate": 1.3039982616253804e-05, + "loss": 0.3077, + "step": 12812 + }, + { + "epoch": 1.04, + "learning_rate": 1.3039439374185138e-05, + "loss": 0.3186, + "step": 12813 + }, + { + "epoch": 1.04, + "learning_rate": 1.3038896132116473e-05, + "loss": 0.335, + "step": 12814 + }, + { + "epoch": 1.04, + "learning_rate": 1.3038352890047807e-05, + "loss": 0.3946, + "step": 12815 + }, + { + "epoch": 1.04, + "learning_rate": 1.3037809647979141e-05, + "loss": 0.3489, + "step": 12816 + }, + { + "epoch": 1.04, + "learning_rate": 1.3037266405910475e-05, + "loss": 0.3916, + "step": 12817 + }, + { + "epoch": 1.04, + "learning_rate": 1.303672316384181e-05, + "loss": 0.399, + "step": 12818 + }, + { + "epoch": 1.04, + "learning_rate": 1.3036179921773142e-05, + "loss": 0.21, + "step": 12819 + }, + { + "epoch": 1.04, + "learning_rate": 1.3035636679704478e-05, + "loss": 0.3543, + "step": 12820 + }, + { + "epoch": 1.04, + "learning_rate": 1.303509343763581e-05, + "loss": 0.1604, + "step": 12821 + }, + { + "epoch": 1.04, + "learning_rate": 1.3034550195567147e-05, + "loss": 0.4682, + "step": 12822 + }, + { + "epoch": 1.04, + "learning_rate": 1.3034006953498479e-05, + "loss": 0.1009, + "step": 12823 + }, + { + "epoch": 1.04, + "learning_rate": 1.3033463711429815e-05, + "loss": 0.2442, + "step": 12824 + }, + { + "epoch": 1.05, + "learning_rate": 1.3032920469361148e-05, + "loss": 0.1402, + "step": 12825 + }, + { + "epoch": 1.05, + "learning_rate": 1.3032377227292483e-05, + "loss": 0.5713, + "step": 12826 + }, + { + "epoch": 1.05, + "learning_rate": 1.3031833985223816e-05, + "loss": 0.4749, + "step": 12827 + }, + { + "epoch": 1.05, + "learning_rate": 1.3031290743155152e-05, + "loss": 0.3569, + "step": 12828 + }, + { + "epoch": 1.05, + "learning_rate": 1.3030747501086484e-05, + "loss": 0.3457, + "step": 12829 + }, + { + "epoch": 1.05, + "learning_rate": 1.303020425901782e-05, + "loss": 0.2886, + "step": 12830 + }, + { + "epoch": 1.05, + "learning_rate": 1.3029661016949153e-05, + "loss": 0.4278, + "step": 12831 + }, + { + "epoch": 1.05, + "learning_rate": 1.3029117774880489e-05, + "loss": 0.3881, + "step": 12832 + }, + { + "epoch": 1.05, + "learning_rate": 1.3028574532811821e-05, + "loss": 0.4791, + "step": 12833 + }, + { + "epoch": 1.05, + "learning_rate": 1.3028031290743157e-05, + "loss": 0.2586, + "step": 12834 + }, + { + "epoch": 1.05, + "learning_rate": 1.302748804867449e-05, + "loss": 0.7891, + "step": 12835 + }, + { + "epoch": 1.05, + "learning_rate": 1.3026944806605826e-05, + "loss": 0.3817, + "step": 12836 + }, + { + "epoch": 1.05, + "learning_rate": 1.3026401564537158e-05, + "loss": 0.704, + "step": 12837 + }, + { + "epoch": 1.05, + "learning_rate": 1.3025858322468493e-05, + "loss": 0.1917, + "step": 12838 + }, + { + "epoch": 1.05, + "learning_rate": 1.3025315080399827e-05, + "loss": 0.3148, + "step": 12839 + }, + { + "epoch": 1.05, + "learning_rate": 1.3024771838331161e-05, + "loss": 0.4025, + "step": 12840 + }, + { + "epoch": 1.05, + "learning_rate": 1.3024228596262495e-05, + "loss": 0.3915, + "step": 12841 + }, + { + "epoch": 1.05, + "learning_rate": 1.302368535419383e-05, + "loss": 0.4144, + "step": 12842 + }, + { + "epoch": 1.05, + "learning_rate": 1.3023142112125164e-05, + "loss": 0.2161, + "step": 12843 + }, + { + "epoch": 1.05, + "learning_rate": 1.3022598870056498e-05, + "loss": 0.4053, + "step": 12844 + }, + { + "epoch": 1.05, + "learning_rate": 1.3022055627987832e-05, + "loss": 0.5348, + "step": 12845 + }, + { + "epoch": 1.05, + "learning_rate": 1.3021512385919166e-05, + "loss": 0.3131, + "step": 12846 + }, + { + "epoch": 1.05, + "learning_rate": 1.3020969143850502e-05, + "loss": 0.2163, + "step": 12847 + }, + { + "epoch": 1.05, + "learning_rate": 1.3020425901781835e-05, + "loss": 0.3865, + "step": 12848 + }, + { + "epoch": 1.05, + "learning_rate": 1.301988265971317e-05, + "loss": 0.3939, + "step": 12849 + }, + { + "epoch": 1.05, + "learning_rate": 1.3019339417644503e-05, + "loss": 0.2935, + "step": 12850 + }, + { + "epoch": 1.05, + "learning_rate": 1.301879617557584e-05, + "loss": 0.1651, + "step": 12851 + }, + { + "epoch": 1.05, + "learning_rate": 1.3018252933507172e-05, + "loss": 0.2328, + "step": 12852 + }, + { + "epoch": 1.05, + "learning_rate": 1.3017709691438508e-05, + "loss": 0.1671, + "step": 12853 + }, + { + "epoch": 1.05, + "learning_rate": 1.301716644936984e-05, + "loss": 0.2437, + "step": 12854 + }, + { + "epoch": 1.05, + "learning_rate": 1.3016623207301176e-05, + "loss": 0.3934, + "step": 12855 + }, + { + "epoch": 1.05, + "learning_rate": 1.3016079965232509e-05, + "loss": 0.3487, + "step": 12856 + }, + { + "epoch": 1.05, + "learning_rate": 1.3015536723163841e-05, + "loss": 0.0722, + "step": 12857 + }, + { + "epoch": 1.05, + "learning_rate": 1.3014993481095177e-05, + "loss": 0.303, + "step": 12858 + }, + { + "epoch": 1.05, + "learning_rate": 1.301445023902651e-05, + "loss": 0.3526, + "step": 12859 + }, + { + "epoch": 1.05, + "learning_rate": 1.3013906996957846e-05, + "loss": 0.3474, + "step": 12860 + }, + { + "epoch": 1.05, + "learning_rate": 1.3013363754889178e-05, + "loss": 0.4135, + "step": 12861 + }, + { + "epoch": 1.05, + "learning_rate": 1.3012820512820514e-05, + "loss": 0.511, + "step": 12862 + }, + { + "epoch": 1.05, + "learning_rate": 1.3012277270751847e-05, + "loss": 0.2676, + "step": 12863 + }, + { + "epoch": 1.05, + "learning_rate": 1.3011734028683183e-05, + "loss": 0.4209, + "step": 12864 + }, + { + "epoch": 1.05, + "learning_rate": 1.3011190786614517e-05, + "loss": 0.2595, + "step": 12865 + }, + { + "epoch": 1.05, + "learning_rate": 1.3010647544545851e-05, + "loss": 0.4394, + "step": 12866 + }, + { + "epoch": 1.05, + "learning_rate": 1.3010104302477185e-05, + "loss": 0.2243, + "step": 12867 + }, + { + "epoch": 1.05, + "learning_rate": 1.300956106040852e-05, + "loss": 0.3419, + "step": 12868 + }, + { + "epoch": 1.05, + "learning_rate": 1.3009017818339854e-05, + "loss": 0.3045, + "step": 12869 + }, + { + "epoch": 1.05, + "learning_rate": 1.3008474576271188e-05, + "loss": 0.2589, + "step": 12870 + }, + { + "epoch": 1.05, + "learning_rate": 1.3007931334202522e-05, + "loss": 0.4278, + "step": 12871 + }, + { + "epoch": 1.05, + "learning_rate": 1.3007388092133856e-05, + "loss": 0.3796, + "step": 12872 + }, + { + "epoch": 1.05, + "learning_rate": 1.300684485006519e-05, + "loss": 0.308, + "step": 12873 + }, + { + "epoch": 1.05, + "learning_rate": 1.3006301607996525e-05, + "loss": 0.4766, + "step": 12874 + }, + { + "epoch": 1.05, + "learning_rate": 1.3005758365927859e-05, + "loss": 0.3541, + "step": 12875 + }, + { + "epoch": 1.05, + "learning_rate": 1.3005215123859192e-05, + "loss": 0.3664, + "step": 12876 + }, + { + "epoch": 1.05, + "learning_rate": 1.3004671881790528e-05, + "loss": 0.5918, + "step": 12877 + }, + { + "epoch": 1.05, + "learning_rate": 1.300412863972186e-05, + "loss": 0.3818, + "step": 12878 + }, + { + "epoch": 1.05, + "learning_rate": 1.3003585397653196e-05, + "loss": 0.2841, + "step": 12879 + }, + { + "epoch": 1.05, + "learning_rate": 1.3003042155584529e-05, + "loss": 0.3798, + "step": 12880 + }, + { + "epoch": 1.05, + "learning_rate": 1.3002498913515864e-05, + "loss": 0.2098, + "step": 12881 + }, + { + "epoch": 1.05, + "learning_rate": 1.3001955671447197e-05, + "loss": 0.4801, + "step": 12882 + }, + { + "epoch": 1.05, + "learning_rate": 1.3001412429378533e-05, + "loss": 0.4401, + "step": 12883 + }, + { + "epoch": 1.05, + "learning_rate": 1.3000869187309865e-05, + "loss": 0.4122, + "step": 12884 + }, + { + "epoch": 1.05, + "learning_rate": 1.3000325945241201e-05, + "loss": 0.3423, + "step": 12885 + }, + { + "epoch": 1.05, + "learning_rate": 1.2999782703172534e-05, + "loss": 0.1501, + "step": 12886 + }, + { + "epoch": 1.05, + "learning_rate": 1.299923946110387e-05, + "loss": 0.2802, + "step": 12887 + }, + { + "epoch": 1.05, + "learning_rate": 1.2998696219035202e-05, + "loss": 0.3147, + "step": 12888 + }, + { + "epoch": 1.05, + "learning_rate": 1.2998152976966538e-05, + "loss": 0.4707, + "step": 12889 + }, + { + "epoch": 1.05, + "learning_rate": 1.299760973489787e-05, + "loss": 0.9857, + "step": 12890 + }, + { + "epoch": 1.05, + "learning_rate": 1.2997066492829207e-05, + "loss": 0.1835, + "step": 12891 + }, + { + "epoch": 1.05, + "learning_rate": 1.299652325076054e-05, + "loss": 0.3367, + "step": 12892 + }, + { + "epoch": 1.05, + "learning_rate": 1.2995980008691875e-05, + "loss": 0.4579, + "step": 12893 + }, + { + "epoch": 1.05, + "learning_rate": 1.2995436766623208e-05, + "loss": 0.5956, + "step": 12894 + }, + { + "epoch": 1.05, + "learning_rate": 1.2994893524554542e-05, + "loss": 0.5238, + "step": 12895 + }, + { + "epoch": 1.05, + "learning_rate": 1.2994350282485876e-05, + "loss": 0.1656, + "step": 12896 + }, + { + "epoch": 1.05, + "learning_rate": 1.299380704041721e-05, + "loss": 0.1981, + "step": 12897 + }, + { + "epoch": 1.05, + "learning_rate": 1.2993263798348545e-05, + "loss": 0.3115, + "step": 12898 + }, + { + "epoch": 1.05, + "learning_rate": 1.2992720556279879e-05, + "loss": 0.5163, + "step": 12899 + }, + { + "epoch": 1.05, + "learning_rate": 1.2992177314211213e-05, + "loss": 0.4257, + "step": 12900 + }, + { + "epoch": 1.05, + "learning_rate": 1.2991634072142547e-05, + "loss": 0.1818, + "step": 12901 + }, + { + "epoch": 1.05, + "learning_rate": 1.2991090830073883e-05, + "loss": 0.3097, + "step": 12902 + }, + { + "epoch": 1.05, + "learning_rate": 1.2990547588005216e-05, + "loss": 0.3814, + "step": 12903 + }, + { + "epoch": 1.05, + "learning_rate": 1.2990004345936552e-05, + "loss": 0.2142, + "step": 12904 + }, + { + "epoch": 1.05, + "learning_rate": 1.2989461103867884e-05, + "loss": 0.4757, + "step": 12905 + }, + { + "epoch": 1.05, + "learning_rate": 1.298891786179922e-05, + "loss": 0.6911, + "step": 12906 + }, + { + "epoch": 1.05, + "learning_rate": 1.2988374619730553e-05, + "loss": 0.4984, + "step": 12907 + }, + { + "epoch": 1.05, + "learning_rate": 1.2987831377661889e-05, + "loss": 0.2535, + "step": 12908 + }, + { + "epoch": 1.05, + "learning_rate": 1.2987288135593221e-05, + "loss": 0.5151, + "step": 12909 + }, + { + "epoch": 1.05, + "learning_rate": 1.2986744893524557e-05, + "loss": 0.3223, + "step": 12910 + }, + { + "epoch": 1.05, + "learning_rate": 1.298620165145589e-05, + "loss": 0.2466, + "step": 12911 + }, + { + "epoch": 1.05, + "learning_rate": 1.2985658409387226e-05, + "loss": 0.3001, + "step": 12912 + }, + { + "epoch": 1.05, + "learning_rate": 1.2985115167318558e-05, + "loss": 0.1825, + "step": 12913 + }, + { + "epoch": 1.05, + "learning_rate": 1.298457192524989e-05, + "loss": 0.2977, + "step": 12914 + }, + { + "epoch": 1.05, + "learning_rate": 1.2984028683181227e-05, + "loss": 0.4117, + "step": 12915 + }, + { + "epoch": 1.05, + "learning_rate": 1.2983485441112559e-05, + "loss": 0.2427, + "step": 12916 + }, + { + "epoch": 1.05, + "learning_rate": 1.2982942199043895e-05, + "loss": 0.161, + "step": 12917 + }, + { + "epoch": 1.05, + "learning_rate": 1.298239895697523e-05, + "loss": 0.2859, + "step": 12918 + }, + { + "epoch": 1.05, + "learning_rate": 1.2981855714906564e-05, + "loss": 0.1457, + "step": 12919 + }, + { + "epoch": 1.05, + "learning_rate": 1.2981312472837898e-05, + "loss": 0.3722, + "step": 12920 + }, + { + "epoch": 1.05, + "learning_rate": 1.2980769230769232e-05, + "loss": 0.2739, + "step": 12921 + }, + { + "epoch": 1.05, + "learning_rate": 1.2980225988700566e-05, + "loss": 0.3572, + "step": 12922 + }, + { + "epoch": 1.05, + "learning_rate": 1.29796827466319e-05, + "loss": 0.3953, + "step": 12923 + }, + { + "epoch": 1.05, + "learning_rate": 1.2979139504563235e-05, + "loss": 0.2859, + "step": 12924 + }, + { + "epoch": 1.05, + "learning_rate": 1.2978596262494569e-05, + "loss": 0.4245, + "step": 12925 + }, + { + "epoch": 1.05, + "learning_rate": 1.2978053020425903e-05, + "loss": 0.1978, + "step": 12926 + }, + { + "epoch": 1.05, + "learning_rate": 1.2977509778357237e-05, + "loss": 0.1508, + "step": 12927 + }, + { + "epoch": 1.05, + "learning_rate": 1.2976966536288572e-05, + "loss": 0.3269, + "step": 12928 + }, + { + "epoch": 1.05, + "learning_rate": 1.2976423294219906e-05, + "loss": 0.2994, + "step": 12929 + }, + { + "epoch": 1.05, + "learning_rate": 1.297588005215124e-05, + "loss": 0.2469, + "step": 12930 + }, + { + "epoch": 1.05, + "learning_rate": 1.2975336810082574e-05, + "loss": 0.3215, + "step": 12931 + }, + { + "epoch": 1.05, + "learning_rate": 1.2974793568013909e-05, + "loss": 0.3164, + "step": 12932 + }, + { + "epoch": 1.05, + "learning_rate": 1.2974250325945241e-05, + "loss": 0.6348, + "step": 12933 + }, + { + "epoch": 1.05, + "learning_rate": 1.2973707083876577e-05, + "loss": 0.2899, + "step": 12934 + }, + { + "epoch": 1.05, + "learning_rate": 1.297316384180791e-05, + "loss": 0.599, + "step": 12935 + }, + { + "epoch": 1.05, + "learning_rate": 1.2972620599739245e-05, + "loss": 0.3398, + "step": 12936 + }, + { + "epoch": 1.05, + "learning_rate": 1.2972077357670578e-05, + "loss": 0.6223, + "step": 12937 + }, + { + "epoch": 1.05, + "learning_rate": 1.2971534115601914e-05, + "loss": 0.1826, + "step": 12938 + }, + { + "epoch": 1.05, + "learning_rate": 1.2970990873533246e-05, + "loss": 0.141, + "step": 12939 + }, + { + "epoch": 1.05, + "learning_rate": 1.2970447631464582e-05, + "loss": 0.1923, + "step": 12940 + }, + { + "epoch": 1.05, + "learning_rate": 1.2969904389395915e-05, + "loss": 0.4618, + "step": 12941 + }, + { + "epoch": 1.05, + "learning_rate": 1.296936114732725e-05, + "loss": 0.2071, + "step": 12942 + }, + { + "epoch": 1.05, + "learning_rate": 1.2968817905258583e-05, + "loss": 0.1068, + "step": 12943 + }, + { + "epoch": 1.05, + "learning_rate": 1.296827466318992e-05, + "loss": 0.1934, + "step": 12944 + }, + { + "epoch": 1.05, + "learning_rate": 1.2967731421121252e-05, + "loss": 0.3172, + "step": 12945 + }, + { + "epoch": 1.05, + "learning_rate": 1.2967188179052588e-05, + "loss": 0.2453, + "step": 12946 + }, + { + "epoch": 1.06, + "learning_rate": 1.296664493698392e-05, + "loss": 0.2344, + "step": 12947 + }, + { + "epoch": 1.06, + "learning_rate": 1.2966101694915256e-05, + "loss": 0.3687, + "step": 12948 + }, + { + "epoch": 1.06, + "learning_rate": 1.2965558452846589e-05, + "loss": 0.2164, + "step": 12949 + }, + { + "epoch": 1.06, + "learning_rate": 1.2965015210777925e-05, + "loss": 0.3202, + "step": 12950 + }, + { + "epoch": 1.06, + "learning_rate": 1.2964471968709257e-05, + "loss": 0.2834, + "step": 12951 + }, + { + "epoch": 1.06, + "learning_rate": 1.2963928726640591e-05, + "loss": 0.5639, + "step": 12952 + }, + { + "epoch": 1.06, + "learning_rate": 1.2963385484571926e-05, + "loss": 0.1844, + "step": 12953 + }, + { + "epoch": 1.06, + "learning_rate": 1.296284224250326e-05, + "loss": 0.2941, + "step": 12954 + }, + { + "epoch": 1.06, + "learning_rate": 1.2962299000434596e-05, + "loss": 0.3215, + "step": 12955 + }, + { + "epoch": 1.06, + "learning_rate": 1.2961755758365928e-05, + "loss": 0.2657, + "step": 12956 + }, + { + "epoch": 1.06, + "learning_rate": 1.2961212516297264e-05, + "loss": 0.3603, + "step": 12957 + }, + { + "epoch": 1.06, + "learning_rate": 1.2960669274228597e-05, + "loss": 0.4599, + "step": 12958 + }, + { + "epoch": 1.06, + "learning_rate": 1.2960126032159933e-05, + "loss": 0.2954, + "step": 12959 + }, + { + "epoch": 1.06, + "learning_rate": 1.2959582790091265e-05, + "loss": 0.3936, + "step": 12960 + }, + { + "epoch": 1.06, + "learning_rate": 1.2959039548022601e-05, + "loss": 0.2854, + "step": 12961 + }, + { + "epoch": 1.06, + "learning_rate": 1.2958496305953934e-05, + "loss": 0.212, + "step": 12962 + }, + { + "epoch": 1.06, + "learning_rate": 1.295795306388527e-05, + "loss": 0.3024, + "step": 12963 + }, + { + "epoch": 1.06, + "learning_rate": 1.2957409821816602e-05, + "loss": 0.2481, + "step": 12964 + }, + { + "epoch": 1.06, + "learning_rate": 1.2956866579747938e-05, + "loss": 0.3134, + "step": 12965 + }, + { + "epoch": 1.06, + "learning_rate": 1.295632333767927e-05, + "loss": 0.343, + "step": 12966 + }, + { + "epoch": 1.06, + "learning_rate": 1.2955780095610607e-05, + "loss": 0.3087, + "step": 12967 + }, + { + "epoch": 1.06, + "learning_rate": 1.2955236853541939e-05, + "loss": 0.5071, + "step": 12968 + }, + { + "epoch": 1.06, + "learning_rate": 1.2954693611473275e-05, + "loss": 0.3857, + "step": 12969 + }, + { + "epoch": 1.06, + "learning_rate": 1.2954150369404608e-05, + "loss": 0.267, + "step": 12970 + }, + { + "epoch": 1.06, + "learning_rate": 1.295360712733594e-05, + "loss": 0.2781, + "step": 12971 + }, + { + "epoch": 1.06, + "learning_rate": 1.2953063885267276e-05, + "loss": 0.2782, + "step": 12972 + }, + { + "epoch": 1.06, + "learning_rate": 1.295252064319861e-05, + "loss": 0.2804, + "step": 12973 + }, + { + "epoch": 1.06, + "learning_rate": 1.2951977401129945e-05, + "loss": 0.4236, + "step": 12974 + }, + { + "epoch": 1.06, + "learning_rate": 1.2951434159061279e-05, + "loss": 0.3733, + "step": 12975 + }, + { + "epoch": 1.06, + "learning_rate": 1.2950890916992613e-05, + "loss": 0.3163, + "step": 12976 + }, + { + "epoch": 1.06, + "learning_rate": 1.2950347674923947e-05, + "loss": 0.3431, + "step": 12977 + }, + { + "epoch": 1.06, + "learning_rate": 1.2949804432855281e-05, + "loss": 0.3461, + "step": 12978 + }, + { + "epoch": 1.06, + "learning_rate": 1.2949261190786616e-05, + "loss": 0.3903, + "step": 12979 + }, + { + "epoch": 1.06, + "learning_rate": 1.294871794871795e-05, + "loss": 0.2974, + "step": 12980 + }, + { + "epoch": 1.06, + "learning_rate": 1.2948174706649284e-05, + "loss": 0.45, + "step": 12981 + }, + { + "epoch": 1.06, + "learning_rate": 1.2947631464580618e-05, + "loss": 0.54, + "step": 12982 + }, + { + "epoch": 1.06, + "learning_rate": 1.2947088222511953e-05, + "loss": 0.2086, + "step": 12983 + }, + { + "epoch": 1.06, + "learning_rate": 1.2946544980443287e-05, + "loss": 0.4085, + "step": 12984 + }, + { + "epoch": 1.06, + "learning_rate": 1.2946001738374621e-05, + "loss": 0.1953, + "step": 12985 + }, + { + "epoch": 1.06, + "learning_rate": 1.2945458496305955e-05, + "loss": 0.3372, + "step": 12986 + }, + { + "epoch": 1.06, + "learning_rate": 1.294491525423729e-05, + "loss": 0.5039, + "step": 12987 + }, + { + "epoch": 1.06, + "learning_rate": 1.2944372012168624e-05, + "loss": 0.6227, + "step": 12988 + }, + { + "epoch": 1.06, + "learning_rate": 1.2943828770099958e-05, + "loss": 0.2671, + "step": 12989 + }, + { + "epoch": 1.06, + "learning_rate": 1.294328552803129e-05, + "loss": 0.4382, + "step": 12990 + }, + { + "epoch": 1.06, + "learning_rate": 1.2942742285962626e-05, + "loss": 0.552, + "step": 12991 + }, + { + "epoch": 1.06, + "learning_rate": 1.2942199043893959e-05, + "loss": 0.5729, + "step": 12992 + }, + { + "epoch": 1.06, + "learning_rate": 1.2941655801825295e-05, + "loss": 0.215, + "step": 12993 + }, + { + "epoch": 1.06, + "learning_rate": 1.2941112559756627e-05, + "loss": 0.1613, + "step": 12994 + }, + { + "epoch": 1.06, + "learning_rate": 1.2940569317687963e-05, + "loss": 0.3938, + "step": 12995 + }, + { + "epoch": 1.06, + "learning_rate": 1.2940026075619296e-05, + "loss": 0.2782, + "step": 12996 + }, + { + "epoch": 1.06, + "learning_rate": 1.2939482833550632e-05, + "loss": 0.4549, + "step": 12997 + }, + { + "epoch": 1.06, + "learning_rate": 1.2938939591481964e-05, + "loss": 0.4309, + "step": 12998 + }, + { + "epoch": 1.06, + "learning_rate": 1.29383963494133e-05, + "loss": 0.2945, + "step": 12999 + }, + { + "epoch": 1.06, + "learning_rate": 1.2937853107344633e-05, + "loss": 0.1418, + "step": 13000 + }, + { + "epoch": 1.06, + "eval_accuracy": 0.8299541518084564, + "eval_loss": 0.4563964009284973, + "eval_runtime": 22.3214, + "eval_samples_per_second": 439.712, + "eval_steps_per_second": 3.45, + "step": 13000 + }, + { + "epoch": 1.06, + "learning_rate": 1.2937309865275969e-05, + "loss": 0.2752, + "step": 13001 + }, + { + "epoch": 1.06, + "learning_rate": 1.2936766623207301e-05, + "loss": 0.2246, + "step": 13002 + }, + { + "epoch": 1.06, + "learning_rate": 1.2936223381138637e-05, + "loss": 0.3352, + "step": 13003 + }, + { + "epoch": 1.06, + "learning_rate": 1.293568013906997e-05, + "loss": 0.2912, + "step": 13004 + }, + { + "epoch": 1.06, + "learning_rate": 1.2935136897001306e-05, + "loss": 0.3648, + "step": 13005 + }, + { + "epoch": 1.06, + "learning_rate": 1.2934593654932638e-05, + "loss": 0.1969, + "step": 13006 + }, + { + "epoch": 1.06, + "learning_rate": 1.2934050412863974e-05, + "loss": 0.3469, + "step": 13007 + }, + { + "epoch": 1.06, + "learning_rate": 1.2933507170795307e-05, + "loss": 0.3125, + "step": 13008 + }, + { + "epoch": 1.06, + "learning_rate": 1.2932963928726641e-05, + "loss": 0.1349, + "step": 13009 + }, + { + "epoch": 1.06, + "learning_rate": 1.2932420686657977e-05, + "loss": 0.1175, + "step": 13010 + }, + { + "epoch": 1.06, + "learning_rate": 1.293187744458931e-05, + "loss": 0.2538, + "step": 13011 + }, + { + "epoch": 1.06, + "learning_rate": 1.2931334202520645e-05, + "loss": 0.209, + "step": 13012 + }, + { + "epoch": 1.06, + "learning_rate": 1.2930790960451978e-05, + "loss": 0.4394, + "step": 13013 + }, + { + "epoch": 1.06, + "learning_rate": 1.2930247718383314e-05, + "loss": 0.2259, + "step": 13014 + }, + { + "epoch": 1.06, + "learning_rate": 1.2929704476314646e-05, + "loss": 0.3627, + "step": 13015 + }, + { + "epoch": 1.06, + "learning_rate": 1.2929161234245982e-05, + "loss": 0.3751, + "step": 13016 + }, + { + "epoch": 1.06, + "learning_rate": 1.2928617992177315e-05, + "loss": 0.3422, + "step": 13017 + }, + { + "epoch": 1.06, + "learning_rate": 1.292807475010865e-05, + "loss": 0.2815, + "step": 13018 + }, + { + "epoch": 1.06, + "learning_rate": 1.2927531508039983e-05, + "loss": 0.2664, + "step": 13019 + }, + { + "epoch": 1.06, + "learning_rate": 1.2926988265971319e-05, + "loss": 0.1867, + "step": 13020 + }, + { + "epoch": 1.06, + "learning_rate": 1.2926445023902652e-05, + "loss": 0.539, + "step": 13021 + }, + { + "epoch": 1.06, + "learning_rate": 1.2925901781833988e-05, + "loss": 0.2376, + "step": 13022 + }, + { + "epoch": 1.06, + "learning_rate": 1.292535853976532e-05, + "loss": 0.5067, + "step": 13023 + }, + { + "epoch": 1.06, + "learning_rate": 1.2924815297696656e-05, + "loss": 0.4237, + "step": 13024 + }, + { + "epoch": 1.06, + "learning_rate": 1.2924272055627989e-05, + "loss": 0.3035, + "step": 13025 + }, + { + "epoch": 1.06, + "learning_rate": 1.2923728813559324e-05, + "loss": 0.484, + "step": 13026 + }, + { + "epoch": 1.06, + "learning_rate": 1.2923185571490657e-05, + "loss": 0.4471, + "step": 13027 + }, + { + "epoch": 1.06, + "learning_rate": 1.2922642329421991e-05, + "loss": 0.3298, + "step": 13028 + }, + { + "epoch": 1.06, + "learning_rate": 1.2922099087353325e-05, + "loss": 0.4031, + "step": 13029 + }, + { + "epoch": 1.06, + "learning_rate": 1.292155584528466e-05, + "loss": 0.4222, + "step": 13030 + }, + { + "epoch": 1.06, + "learning_rate": 1.2921012603215994e-05, + "loss": 0.2027, + "step": 13031 + }, + { + "epoch": 1.06, + "learning_rate": 1.2920469361147328e-05, + "loss": 0.3727, + "step": 13032 + }, + { + "epoch": 1.06, + "learning_rate": 1.2919926119078662e-05, + "loss": 0.2767, + "step": 13033 + }, + { + "epoch": 1.06, + "learning_rate": 1.2919382877009997e-05, + "loss": 0.3903, + "step": 13034 + }, + { + "epoch": 1.06, + "learning_rate": 1.2918839634941331e-05, + "loss": 0.3026, + "step": 13035 + }, + { + "epoch": 1.06, + "learning_rate": 1.2918296392872665e-05, + "loss": 0.404, + "step": 13036 + }, + { + "epoch": 1.06, + "learning_rate": 1.2917753150804e-05, + "loss": 0.2301, + "step": 13037 + }, + { + "epoch": 1.06, + "learning_rate": 1.2917209908735334e-05, + "loss": 0.2136, + "step": 13038 + }, + { + "epoch": 1.06, + "learning_rate": 1.2916666666666668e-05, + "loss": 0.2994, + "step": 13039 + }, + { + "epoch": 1.06, + "learning_rate": 1.2916123424598002e-05, + "loss": 0.3761, + "step": 13040 + }, + { + "epoch": 1.06, + "learning_rate": 1.2915580182529336e-05, + "loss": 0.1648, + "step": 13041 + }, + { + "epoch": 1.06, + "learning_rate": 1.291503694046067e-05, + "loss": 0.5153, + "step": 13042 + }, + { + "epoch": 1.06, + "learning_rate": 1.2914493698392005e-05, + "loss": 0.5295, + "step": 13043 + }, + { + "epoch": 1.06, + "learning_rate": 1.2913950456323339e-05, + "loss": 0.5046, + "step": 13044 + }, + { + "epoch": 1.06, + "learning_rate": 1.2913407214254675e-05, + "loss": 0.3956, + "step": 13045 + }, + { + "epoch": 1.06, + "learning_rate": 1.2912863972186007e-05, + "loss": 0.6232, + "step": 13046 + }, + { + "epoch": 1.06, + "learning_rate": 1.291232073011734e-05, + "loss": 0.2672, + "step": 13047 + }, + { + "epoch": 1.06, + "learning_rate": 1.2911777488048676e-05, + "loss": 0.6615, + "step": 13048 + }, + { + "epoch": 1.06, + "learning_rate": 1.2911234245980008e-05, + "loss": 0.4049, + "step": 13049 + }, + { + "epoch": 1.06, + "learning_rate": 1.2910691003911344e-05, + "loss": 0.314, + "step": 13050 + }, + { + "epoch": 1.06, + "learning_rate": 1.2910147761842677e-05, + "loss": 0.4068, + "step": 13051 + }, + { + "epoch": 1.06, + "learning_rate": 1.2909604519774013e-05, + "loss": 0.4752, + "step": 13052 + }, + { + "epoch": 1.06, + "learning_rate": 1.2909061277705345e-05, + "loss": 0.3631, + "step": 13053 + }, + { + "epoch": 1.06, + "learning_rate": 1.2908518035636681e-05, + "loss": 0.27, + "step": 13054 + }, + { + "epoch": 1.06, + "learning_rate": 1.2907974793568014e-05, + "loss": 0.5052, + "step": 13055 + }, + { + "epoch": 1.06, + "learning_rate": 1.290743155149935e-05, + "loss": 0.4596, + "step": 13056 + }, + { + "epoch": 1.06, + "learning_rate": 1.2906888309430682e-05, + "loss": 0.503, + "step": 13057 + }, + { + "epoch": 1.06, + "learning_rate": 1.2906345067362018e-05, + "loss": 0.3185, + "step": 13058 + }, + { + "epoch": 1.06, + "learning_rate": 1.290580182529335e-05, + "loss": 0.3991, + "step": 13059 + }, + { + "epoch": 1.06, + "learning_rate": 1.2905258583224687e-05, + "loss": 0.4548, + "step": 13060 + }, + { + "epoch": 1.06, + "learning_rate": 1.290471534115602e-05, + "loss": 0.1753, + "step": 13061 + }, + { + "epoch": 1.06, + "learning_rate": 1.2904172099087355e-05, + "loss": 0.2602, + "step": 13062 + }, + { + "epoch": 1.06, + "learning_rate": 1.290362885701869e-05, + "loss": 0.5436, + "step": 13063 + }, + { + "epoch": 1.06, + "learning_rate": 1.2903085614950024e-05, + "loss": 0.8587, + "step": 13064 + }, + { + "epoch": 1.06, + "learning_rate": 1.2902542372881358e-05, + "loss": 0.2404, + "step": 13065 + }, + { + "epoch": 1.06, + "learning_rate": 1.290199913081269e-05, + "loss": 0.2634, + "step": 13066 + }, + { + "epoch": 1.06, + "learning_rate": 1.2901455888744026e-05, + "loss": 0.3304, + "step": 13067 + }, + { + "epoch": 1.06, + "learning_rate": 1.2900912646675359e-05, + "loss": 0.4558, + "step": 13068 + }, + { + "epoch": 1.06, + "learning_rate": 1.2900369404606695e-05, + "loss": 0.2886, + "step": 13069 + }, + { + "epoch": 1.07, + "learning_rate": 1.2899826162538027e-05, + "loss": 0.4093, + "step": 13070 + }, + { + "epoch": 1.07, + "learning_rate": 1.2899282920469363e-05, + "loss": 0.3326, + "step": 13071 + }, + { + "epoch": 1.07, + "learning_rate": 1.2898739678400696e-05, + "loss": 0.2939, + "step": 13072 + }, + { + "epoch": 1.07, + "learning_rate": 1.2898196436332032e-05, + "loss": 0.5075, + "step": 13073 + }, + { + "epoch": 1.07, + "learning_rate": 1.2897653194263364e-05, + "loss": 0.3661, + "step": 13074 + }, + { + "epoch": 1.07, + "learning_rate": 1.28971099521947e-05, + "loss": 0.4371, + "step": 13075 + }, + { + "epoch": 1.07, + "learning_rate": 1.2896566710126033e-05, + "loss": 0.3085, + "step": 13076 + }, + { + "epoch": 1.07, + "learning_rate": 1.2896023468057369e-05, + "loss": 0.2686, + "step": 13077 + }, + { + "epoch": 1.07, + "learning_rate": 1.2895480225988701e-05, + "loss": 0.4986, + "step": 13078 + }, + { + "epoch": 1.07, + "learning_rate": 1.2894936983920037e-05, + "loss": 0.271, + "step": 13079 + }, + { + "epoch": 1.07, + "learning_rate": 1.289439374185137e-05, + "loss": 0.258, + "step": 13080 + }, + { + "epoch": 1.07, + "learning_rate": 1.2893850499782705e-05, + "loss": 0.4078, + "step": 13081 + }, + { + "epoch": 1.07, + "learning_rate": 1.2893307257714038e-05, + "loss": 0.3368, + "step": 13082 + }, + { + "epoch": 1.07, + "learning_rate": 1.2892764015645374e-05, + "loss": 0.2382, + "step": 13083 + }, + { + "epoch": 1.07, + "learning_rate": 1.2892220773576706e-05, + "loss": 0.4478, + "step": 13084 + }, + { + "epoch": 1.07, + "learning_rate": 1.289167753150804e-05, + "loss": 0.1368, + "step": 13085 + }, + { + "epoch": 1.07, + "learning_rate": 1.2891134289439375e-05, + "loss": 0.3068, + "step": 13086 + }, + { + "epoch": 1.07, + "learning_rate": 1.289059104737071e-05, + "loss": 0.361, + "step": 13087 + }, + { + "epoch": 1.07, + "learning_rate": 1.2890047805302043e-05, + "loss": 0.2869, + "step": 13088 + }, + { + "epoch": 1.07, + "learning_rate": 1.2889504563233378e-05, + "loss": 0.4654, + "step": 13089 + }, + { + "epoch": 1.07, + "learning_rate": 1.2888961321164712e-05, + "loss": 0.2972, + "step": 13090 + }, + { + "epoch": 1.07, + "learning_rate": 1.2888418079096046e-05, + "loss": 0.2798, + "step": 13091 + }, + { + "epoch": 1.07, + "learning_rate": 1.288787483702738e-05, + "loss": 0.3196, + "step": 13092 + }, + { + "epoch": 1.07, + "learning_rate": 1.2887331594958715e-05, + "loss": 0.2399, + "step": 13093 + }, + { + "epoch": 1.07, + "learning_rate": 1.2886788352890049e-05, + "loss": 0.6773, + "step": 13094 + }, + { + "epoch": 1.07, + "learning_rate": 1.2886245110821383e-05, + "loss": 0.2606, + "step": 13095 + }, + { + "epoch": 1.07, + "learning_rate": 1.2885701868752717e-05, + "loss": 0.1896, + "step": 13096 + }, + { + "epoch": 1.07, + "learning_rate": 1.2885158626684051e-05, + "loss": 0.3933, + "step": 13097 + }, + { + "epoch": 1.07, + "learning_rate": 1.2884615384615386e-05, + "loss": 0.3667, + "step": 13098 + }, + { + "epoch": 1.07, + "learning_rate": 1.288407214254672e-05, + "loss": 0.3293, + "step": 13099 + }, + { + "epoch": 1.07, + "learning_rate": 1.2883528900478056e-05, + "loss": 0.2393, + "step": 13100 + }, + { + "epoch": 1.07, + "learning_rate": 1.2882985658409388e-05, + "loss": 0.354, + "step": 13101 + }, + { + "epoch": 1.07, + "learning_rate": 1.2882442416340724e-05, + "loss": 0.5017, + "step": 13102 + }, + { + "epoch": 1.07, + "learning_rate": 1.2881899174272057e-05, + "loss": 0.4075, + "step": 13103 + }, + { + "epoch": 1.07, + "learning_rate": 1.288135593220339e-05, + "loss": 0.2638, + "step": 13104 + }, + { + "epoch": 1.07, + "learning_rate": 1.2880812690134725e-05, + "loss": 0.2168, + "step": 13105 + }, + { + "epoch": 1.07, + "learning_rate": 1.2880269448066058e-05, + "loss": 0.4472, + "step": 13106 + }, + { + "epoch": 1.07, + "learning_rate": 1.2879726205997394e-05, + "loss": 0.3341, + "step": 13107 + }, + { + "epoch": 1.07, + "learning_rate": 1.2879182963928726e-05, + "loss": 0.1987, + "step": 13108 + }, + { + "epoch": 1.07, + "learning_rate": 1.2878639721860062e-05, + "loss": 0.3132, + "step": 13109 + }, + { + "epoch": 1.07, + "learning_rate": 1.2878096479791395e-05, + "loss": 0.3414, + "step": 13110 + }, + { + "epoch": 1.07, + "learning_rate": 1.287755323772273e-05, + "loss": 0.4365, + "step": 13111 + }, + { + "epoch": 1.07, + "learning_rate": 1.2877009995654063e-05, + "loss": 0.3867, + "step": 13112 + }, + { + "epoch": 1.07, + "learning_rate": 1.28764667535854e-05, + "loss": 0.3909, + "step": 13113 + }, + { + "epoch": 1.07, + "learning_rate": 1.2875923511516732e-05, + "loss": 0.8127, + "step": 13114 + }, + { + "epoch": 1.07, + "learning_rate": 1.2875380269448068e-05, + "loss": 0.4233, + "step": 13115 + }, + { + "epoch": 1.07, + "learning_rate": 1.28748370273794e-05, + "loss": 0.1635, + "step": 13116 + }, + { + "epoch": 1.07, + "learning_rate": 1.2874293785310736e-05, + "loss": 0.2776, + "step": 13117 + }, + { + "epoch": 1.07, + "learning_rate": 1.287375054324207e-05, + "loss": 0.5445, + "step": 13118 + }, + { + "epoch": 1.07, + "learning_rate": 1.2873207301173405e-05, + "loss": 0.4649, + "step": 13119 + }, + { + "epoch": 1.07, + "learning_rate": 1.2872664059104739e-05, + "loss": 0.4781, + "step": 13120 + }, + { + "epoch": 1.07, + "learning_rate": 1.2872120817036073e-05, + "loss": 0.4055, + "step": 13121 + }, + { + "epoch": 1.07, + "learning_rate": 1.2871577574967407e-05, + "loss": 0.5311, + "step": 13122 + }, + { + "epoch": 1.07, + "learning_rate": 1.287103433289874e-05, + "loss": 0.6399, + "step": 13123 + }, + { + "epoch": 1.07, + "learning_rate": 1.2870491090830076e-05, + "loss": 0.2557, + "step": 13124 + }, + { + "epoch": 1.07, + "learning_rate": 1.2869947848761408e-05, + "loss": 0.302, + "step": 13125 + }, + { + "epoch": 1.07, + "learning_rate": 1.2869404606692744e-05, + "loss": 0.2569, + "step": 13126 + }, + { + "epoch": 1.07, + "learning_rate": 1.2868861364624077e-05, + "loss": 0.1098, + "step": 13127 + }, + { + "epoch": 1.07, + "learning_rate": 1.2868318122555413e-05, + "loss": 0.3962, + "step": 13128 + }, + { + "epoch": 1.07, + "learning_rate": 1.2867774880486745e-05, + "loss": 0.4912, + "step": 13129 + }, + { + "epoch": 1.07, + "learning_rate": 1.2867231638418081e-05, + "loss": 0.387, + "step": 13130 + }, + { + "epoch": 1.07, + "learning_rate": 1.2866688396349414e-05, + "loss": 0.1708, + "step": 13131 + }, + { + "epoch": 1.07, + "learning_rate": 1.286614515428075e-05, + "loss": 0.2765, + "step": 13132 + }, + { + "epoch": 1.07, + "learning_rate": 1.2865601912212082e-05, + "loss": 0.1463, + "step": 13133 + }, + { + "epoch": 1.07, + "learning_rate": 1.2865058670143418e-05, + "loss": 0.2714, + "step": 13134 + }, + { + "epoch": 1.07, + "learning_rate": 1.286451542807475e-05, + "loss": 0.2603, + "step": 13135 + }, + { + "epoch": 1.07, + "learning_rate": 1.2863972186006086e-05, + "loss": 0.2601, + "step": 13136 + }, + { + "epoch": 1.07, + "learning_rate": 1.2863428943937419e-05, + "loss": 0.117, + "step": 13137 + }, + { + "epoch": 1.07, + "learning_rate": 1.2862885701868755e-05, + "loss": 0.3089, + "step": 13138 + }, + { + "epoch": 1.07, + "learning_rate": 1.2862342459800087e-05, + "loss": 0.2239, + "step": 13139 + }, + { + "epoch": 1.07, + "learning_rate": 1.2861799217731423e-05, + "loss": 0.2469, + "step": 13140 + }, + { + "epoch": 1.07, + "learning_rate": 1.2861255975662756e-05, + "loss": 0.433, + "step": 13141 + }, + { + "epoch": 1.07, + "learning_rate": 1.286071273359409e-05, + "loss": 0.4447, + "step": 13142 + }, + { + "epoch": 1.07, + "learning_rate": 1.2860169491525424e-05, + "loss": 0.3554, + "step": 13143 + }, + { + "epoch": 1.07, + "learning_rate": 1.2859626249456759e-05, + "loss": 0.421, + "step": 13144 + }, + { + "epoch": 1.07, + "learning_rate": 1.2859083007388093e-05, + "loss": 0.2801, + "step": 13145 + }, + { + "epoch": 1.07, + "learning_rate": 1.2858539765319427e-05, + "loss": 0.5372, + "step": 13146 + }, + { + "epoch": 1.07, + "learning_rate": 1.2857996523250761e-05, + "loss": 0.4484, + "step": 13147 + }, + { + "epoch": 1.07, + "learning_rate": 1.2857453281182096e-05, + "loss": 0.1354, + "step": 13148 + }, + { + "epoch": 1.07, + "learning_rate": 1.285691003911343e-05, + "loss": 0.2853, + "step": 13149 + }, + { + "epoch": 1.07, + "learning_rate": 1.2856366797044764e-05, + "loss": 0.3249, + "step": 13150 + }, + { + "epoch": 1.07, + "learning_rate": 1.2855823554976098e-05, + "loss": 0.2722, + "step": 13151 + }, + { + "epoch": 1.07, + "learning_rate": 1.2855280312907432e-05, + "loss": 0.1869, + "step": 13152 + }, + { + "epoch": 1.07, + "learning_rate": 1.2854737070838768e-05, + "loss": 0.1184, + "step": 13153 + }, + { + "epoch": 1.07, + "learning_rate": 1.2854193828770101e-05, + "loss": 0.2314, + "step": 13154 + }, + { + "epoch": 1.07, + "learning_rate": 1.2853650586701437e-05, + "loss": 0.1827, + "step": 13155 + }, + { + "epoch": 1.07, + "learning_rate": 1.285310734463277e-05, + "loss": 0.3445, + "step": 13156 + }, + { + "epoch": 1.07, + "learning_rate": 1.2852564102564105e-05, + "loss": 0.2913, + "step": 13157 + }, + { + "epoch": 1.07, + "learning_rate": 1.2852020860495438e-05, + "loss": 0.1662, + "step": 13158 + }, + { + "epoch": 1.07, + "learning_rate": 1.2851477618426774e-05, + "loss": 0.3452, + "step": 13159 + }, + { + "epoch": 1.07, + "learning_rate": 1.2850934376358106e-05, + "loss": 0.385, + "step": 13160 + }, + { + "epoch": 1.07, + "learning_rate": 1.2850391134289439e-05, + "loss": 0.1983, + "step": 13161 + }, + { + "epoch": 1.07, + "learning_rate": 1.2849847892220775e-05, + "loss": 0.2472, + "step": 13162 + }, + { + "epoch": 1.07, + "learning_rate": 1.2849304650152107e-05, + "loss": 0.4873, + "step": 13163 + }, + { + "epoch": 1.07, + "learning_rate": 1.2848761408083443e-05, + "loss": 0.3436, + "step": 13164 + }, + { + "epoch": 1.07, + "learning_rate": 1.2848218166014776e-05, + "loss": 0.4285, + "step": 13165 + }, + { + "epoch": 1.07, + "learning_rate": 1.2847674923946112e-05, + "loss": 0.5879, + "step": 13166 + }, + { + "epoch": 1.07, + "learning_rate": 1.2847131681877444e-05, + "loss": 0.3725, + "step": 13167 + }, + { + "epoch": 1.07, + "learning_rate": 1.284658843980878e-05, + "loss": 0.3693, + "step": 13168 + }, + { + "epoch": 1.07, + "learning_rate": 1.2846045197740113e-05, + "loss": 0.2486, + "step": 13169 + }, + { + "epoch": 1.07, + "learning_rate": 1.2845501955671449e-05, + "loss": 0.4761, + "step": 13170 + }, + { + "epoch": 1.07, + "learning_rate": 1.2844958713602783e-05, + "loss": 0.5674, + "step": 13171 + }, + { + "epoch": 1.07, + "learning_rate": 1.2844415471534117e-05, + "loss": 0.2717, + "step": 13172 + }, + { + "epoch": 1.07, + "learning_rate": 1.2843872229465451e-05, + "loss": 0.299, + "step": 13173 + }, + { + "epoch": 1.07, + "learning_rate": 1.2843328987396786e-05, + "loss": 0.2344, + "step": 13174 + }, + { + "epoch": 1.07, + "learning_rate": 1.284278574532812e-05, + "loss": 0.4546, + "step": 13175 + }, + { + "epoch": 1.07, + "learning_rate": 1.2842242503259454e-05, + "loss": 0.1575, + "step": 13176 + }, + { + "epoch": 1.07, + "learning_rate": 1.2841699261190788e-05, + "loss": 0.3891, + "step": 13177 + }, + { + "epoch": 1.07, + "learning_rate": 1.2841156019122122e-05, + "loss": 0.3786, + "step": 13178 + }, + { + "epoch": 1.07, + "learning_rate": 1.2840612777053457e-05, + "loss": 0.2571, + "step": 13179 + }, + { + "epoch": 1.07, + "learning_rate": 1.284006953498479e-05, + "loss": 0.2454, + "step": 13180 + }, + { + "epoch": 1.07, + "learning_rate": 1.2839526292916125e-05, + "loss": 0.3684, + "step": 13181 + }, + { + "epoch": 1.07, + "learning_rate": 1.2838983050847458e-05, + "loss": 0.3401, + "step": 13182 + }, + { + "epoch": 1.07, + "learning_rate": 1.2838439808778794e-05, + "loss": 0.6464, + "step": 13183 + }, + { + "epoch": 1.07, + "learning_rate": 1.2837896566710126e-05, + "loss": 0.2891, + "step": 13184 + }, + { + "epoch": 1.07, + "learning_rate": 1.2837353324641462e-05, + "loss": 0.312, + "step": 13185 + }, + { + "epoch": 1.07, + "learning_rate": 1.2836810082572795e-05, + "loss": 0.3134, + "step": 13186 + }, + { + "epoch": 1.07, + "learning_rate": 1.283626684050413e-05, + "loss": 0.2393, + "step": 13187 + }, + { + "epoch": 1.07, + "learning_rate": 1.2835723598435463e-05, + "loss": 0.1697, + "step": 13188 + }, + { + "epoch": 1.07, + "learning_rate": 1.2835180356366799e-05, + "loss": 0.4593, + "step": 13189 + }, + { + "epoch": 1.07, + "learning_rate": 1.2834637114298132e-05, + "loss": 0.3114, + "step": 13190 + }, + { + "epoch": 1.07, + "learning_rate": 1.2834093872229467e-05, + "loss": 0.3296, + "step": 13191 + }, + { + "epoch": 1.07, + "learning_rate": 1.28335506301608e-05, + "loss": 0.3108, + "step": 13192 + }, + { + "epoch": 1.08, + "learning_rate": 1.2833007388092136e-05, + "loss": 0.3919, + "step": 13193 + }, + { + "epoch": 1.08, + "learning_rate": 1.2832464146023468e-05, + "loss": 0.4687, + "step": 13194 + }, + { + "epoch": 1.08, + "learning_rate": 1.2831920903954804e-05, + "loss": 0.3263, + "step": 13195 + }, + { + "epoch": 1.08, + "learning_rate": 1.2831377661886137e-05, + "loss": 0.363, + "step": 13196 + }, + { + "epoch": 1.08, + "learning_rate": 1.2830834419817473e-05, + "loss": 0.1636, + "step": 13197 + }, + { + "epoch": 1.08, + "learning_rate": 1.2830291177748805e-05, + "loss": 0.1852, + "step": 13198 + }, + { + "epoch": 1.08, + "learning_rate": 1.282974793568014e-05, + "loss": 0.3079, + "step": 13199 + }, + { + "epoch": 1.08, + "learning_rate": 1.2829204693611474e-05, + "loss": 0.3496, + "step": 13200 + }, + { + "epoch": 1.08, + "learning_rate": 1.2828661451542808e-05, + "loss": 0.3656, + "step": 13201 + }, + { + "epoch": 1.08, + "learning_rate": 1.2828118209474142e-05, + "loss": 0.3106, + "step": 13202 + }, + { + "epoch": 1.08, + "learning_rate": 1.2827574967405477e-05, + "loss": 0.2963, + "step": 13203 + }, + { + "epoch": 1.08, + "learning_rate": 1.282703172533681e-05, + "loss": 0.5804, + "step": 13204 + }, + { + "epoch": 1.08, + "learning_rate": 1.2826488483268145e-05, + "loss": 0.3046, + "step": 13205 + }, + { + "epoch": 1.08, + "learning_rate": 1.282594524119948e-05, + "loss": 0.0974, + "step": 13206 + }, + { + "epoch": 1.08, + "learning_rate": 1.2825401999130813e-05, + "loss": 0.2542, + "step": 13207 + }, + { + "epoch": 1.08, + "learning_rate": 1.282485875706215e-05, + "loss": 0.451, + "step": 13208 + }, + { + "epoch": 1.08, + "learning_rate": 1.2824315514993482e-05, + "loss": 0.2983, + "step": 13209 + }, + { + "epoch": 1.08, + "learning_rate": 1.2823772272924818e-05, + "loss": 0.3145, + "step": 13210 + }, + { + "epoch": 1.08, + "learning_rate": 1.282322903085615e-05, + "loss": 0.2704, + "step": 13211 + }, + { + "epoch": 1.08, + "learning_rate": 1.2822685788787486e-05, + "loss": 0.5932, + "step": 13212 + }, + { + "epoch": 1.08, + "learning_rate": 1.2822142546718819e-05, + "loss": 0.2417, + "step": 13213 + }, + { + "epoch": 1.08, + "learning_rate": 1.2821599304650155e-05, + "loss": 0.2536, + "step": 13214 + }, + { + "epoch": 1.08, + "learning_rate": 1.2821056062581487e-05, + "loss": 0.2302, + "step": 13215 + }, + { + "epoch": 1.08, + "learning_rate": 1.2820512820512823e-05, + "loss": 0.2062, + "step": 13216 + }, + { + "epoch": 1.08, + "learning_rate": 1.2819969578444156e-05, + "loss": 0.2315, + "step": 13217 + }, + { + "epoch": 1.08, + "learning_rate": 1.2819426336375488e-05, + "loss": 0.3082, + "step": 13218 + }, + { + "epoch": 1.08, + "learning_rate": 1.2818883094306824e-05, + "loss": 0.1218, + "step": 13219 + }, + { + "epoch": 1.08, + "learning_rate": 1.2818339852238157e-05, + "loss": 0.1795, + "step": 13220 + }, + { + "epoch": 1.08, + "learning_rate": 1.2817796610169493e-05, + "loss": 0.1978, + "step": 13221 + }, + { + "epoch": 1.08, + "learning_rate": 1.2817253368100825e-05, + "loss": 0.1772, + "step": 13222 + }, + { + "epoch": 1.08, + "learning_rate": 1.2816710126032161e-05, + "loss": 0.2857, + "step": 13223 + }, + { + "epoch": 1.08, + "learning_rate": 1.2816166883963494e-05, + "loss": 0.3124, + "step": 13224 + }, + { + "epoch": 1.08, + "learning_rate": 1.281562364189483e-05, + "loss": 0.1964, + "step": 13225 + }, + { + "epoch": 1.08, + "learning_rate": 1.2815080399826164e-05, + "loss": 0.3615, + "step": 13226 + }, + { + "epoch": 1.08, + "learning_rate": 1.2814537157757498e-05, + "loss": 0.8198, + "step": 13227 + }, + { + "epoch": 1.08, + "learning_rate": 1.2813993915688832e-05, + "loss": 0.4079, + "step": 13228 + }, + { + "epoch": 1.08, + "learning_rate": 1.2813450673620167e-05, + "loss": 0.4173, + "step": 13229 + }, + { + "epoch": 1.08, + "learning_rate": 1.28129074315515e-05, + "loss": 0.275, + "step": 13230 + }, + { + "epoch": 1.08, + "learning_rate": 1.2812364189482835e-05, + "loss": 0.3481, + "step": 13231 + }, + { + "epoch": 1.08, + "learning_rate": 1.281182094741417e-05, + "loss": 0.5116, + "step": 13232 + }, + { + "epoch": 1.08, + "learning_rate": 1.2811277705345503e-05, + "loss": 0.2357, + "step": 13233 + }, + { + "epoch": 1.08, + "learning_rate": 1.2810734463276838e-05, + "loss": 0.2736, + "step": 13234 + }, + { + "epoch": 1.08, + "learning_rate": 1.2810191221208172e-05, + "loss": 0.3396, + "step": 13235 + }, + { + "epoch": 1.08, + "learning_rate": 1.2809647979139506e-05, + "loss": 0.0603, + "step": 13236 + }, + { + "epoch": 1.08, + "learning_rate": 1.2809104737070839e-05, + "loss": 0.3967, + "step": 13237 + }, + { + "epoch": 1.08, + "learning_rate": 1.2808561495002175e-05, + "loss": 0.1097, + "step": 13238 + }, + { + "epoch": 1.08, + "learning_rate": 1.2808018252933507e-05, + "loss": 0.2645, + "step": 13239 + }, + { + "epoch": 1.08, + "learning_rate": 1.2807475010864843e-05, + "loss": 0.3917, + "step": 13240 + }, + { + "epoch": 1.08, + "learning_rate": 1.2806931768796176e-05, + "loss": 0.5768, + "step": 13241 + }, + { + "epoch": 1.08, + "learning_rate": 1.2806388526727512e-05, + "loss": 0.132, + "step": 13242 + }, + { + "epoch": 1.08, + "learning_rate": 1.2805845284658844e-05, + "loss": 0.1674, + "step": 13243 + }, + { + "epoch": 1.08, + "learning_rate": 1.280530204259018e-05, + "loss": 0.5749, + "step": 13244 + }, + { + "epoch": 1.08, + "learning_rate": 1.2804758800521513e-05, + "loss": 0.5264, + "step": 13245 + }, + { + "epoch": 1.08, + "learning_rate": 1.2804215558452848e-05, + "loss": 0.3773, + "step": 13246 + }, + { + "epoch": 1.08, + "learning_rate": 1.2803672316384181e-05, + "loss": 0.3407, + "step": 13247 + }, + { + "epoch": 1.08, + "learning_rate": 1.2803129074315517e-05, + "loss": 0.2244, + "step": 13248 + }, + { + "epoch": 1.08, + "learning_rate": 1.280258583224685e-05, + "loss": 0.3861, + "step": 13249 + }, + { + "epoch": 1.08, + "learning_rate": 1.2802042590178185e-05, + "loss": 0.3121, + "step": 13250 + }, + { + "epoch": 1.08, + "eval_accuracy": 0.8256749872643913, + "eval_loss": 0.4861257076263428, + "eval_runtime": 22.3201, + "eval_samples_per_second": 439.739, + "eval_steps_per_second": 3.45, + "step": 13250 + }, + { + "epoch": 1.08, + "learning_rate": 1.2801499348109518e-05, + "loss": 0.2162, + "step": 13251 + }, + { + "epoch": 1.08, + "learning_rate": 1.2800956106040854e-05, + "loss": 0.2402, + "step": 13252 + }, + { + "epoch": 1.08, + "learning_rate": 1.2800412863972186e-05, + "loss": 0.4574, + "step": 13253 + }, + { + "epoch": 1.08, + "learning_rate": 1.2799869621903522e-05, + "loss": 0.163, + "step": 13254 + }, + { + "epoch": 1.08, + "learning_rate": 1.2799326379834855e-05, + "loss": 0.1472, + "step": 13255 + }, + { + "epoch": 1.08, + "learning_rate": 1.2798783137766189e-05, + "loss": 0.3104, + "step": 13256 + }, + { + "epoch": 1.08, + "learning_rate": 1.2798239895697523e-05, + "loss": 0.316, + "step": 13257 + }, + { + "epoch": 1.08, + "learning_rate": 1.2797696653628858e-05, + "loss": 0.3665, + "step": 13258 + }, + { + "epoch": 1.08, + "learning_rate": 1.2797153411560192e-05, + "loss": 0.2851, + "step": 13259 + }, + { + "epoch": 1.08, + "learning_rate": 1.2796610169491526e-05, + "loss": 0.3299, + "step": 13260 + }, + { + "epoch": 1.08, + "learning_rate": 1.2796066927422862e-05, + "loss": 0.3139, + "step": 13261 + }, + { + "epoch": 1.08, + "learning_rate": 1.2795523685354194e-05, + "loss": 0.2808, + "step": 13262 + }, + { + "epoch": 1.08, + "learning_rate": 1.279498044328553e-05, + "loss": 0.14, + "step": 13263 + }, + { + "epoch": 1.08, + "learning_rate": 1.2794437201216863e-05, + "loss": 0.0795, + "step": 13264 + }, + { + "epoch": 1.08, + "learning_rate": 1.2793893959148199e-05, + "loss": 0.1956, + "step": 13265 + }, + { + "epoch": 1.08, + "learning_rate": 1.2793350717079531e-05, + "loss": 0.4829, + "step": 13266 + }, + { + "epoch": 1.08, + "learning_rate": 1.2792807475010867e-05, + "loss": 0.3998, + "step": 13267 + }, + { + "epoch": 1.08, + "learning_rate": 1.27922642329422e-05, + "loss": 0.246, + "step": 13268 + }, + { + "epoch": 1.08, + "learning_rate": 1.2791720990873536e-05, + "loss": 0.3082, + "step": 13269 + }, + { + "epoch": 1.08, + "learning_rate": 1.2791177748804868e-05, + "loss": 0.4625, + "step": 13270 + }, + { + "epoch": 1.08, + "learning_rate": 1.2790634506736204e-05, + "loss": 0.4097, + "step": 13271 + }, + { + "epoch": 1.08, + "learning_rate": 1.2790091264667537e-05, + "loss": 0.2316, + "step": 13272 + }, + { + "epoch": 1.08, + "learning_rate": 1.2789548022598873e-05, + "loss": 0.2046, + "step": 13273 + }, + { + "epoch": 1.08, + "learning_rate": 1.2789004780530205e-05, + "loss": 0.0883, + "step": 13274 + }, + { + "epoch": 1.08, + "learning_rate": 1.2788461538461538e-05, + "loss": 0.5546, + "step": 13275 + }, + { + "epoch": 1.08, + "learning_rate": 1.2787918296392874e-05, + "loss": 0.3776, + "step": 13276 + }, + { + "epoch": 1.08, + "learning_rate": 1.2787375054324206e-05, + "loss": 0.2649, + "step": 13277 + }, + { + "epoch": 1.08, + "learning_rate": 1.2786831812255542e-05, + "loss": 0.2373, + "step": 13278 + }, + { + "epoch": 1.08, + "learning_rate": 1.2786288570186876e-05, + "loss": 0.1256, + "step": 13279 + }, + { + "epoch": 1.08, + "learning_rate": 1.278574532811821e-05, + "loss": 0.3389, + "step": 13280 + }, + { + "epoch": 1.08, + "learning_rate": 1.2785202086049545e-05, + "loss": 0.471, + "step": 13281 + }, + { + "epoch": 1.08, + "learning_rate": 1.2784658843980879e-05, + "loss": 0.1693, + "step": 13282 + }, + { + "epoch": 1.08, + "learning_rate": 1.2784115601912213e-05, + "loss": 0.3661, + "step": 13283 + }, + { + "epoch": 1.08, + "learning_rate": 1.2783572359843548e-05, + "loss": 0.6315, + "step": 13284 + }, + { + "epoch": 1.08, + "learning_rate": 1.2783029117774882e-05, + "loss": 0.2595, + "step": 13285 + }, + { + "epoch": 1.08, + "learning_rate": 1.2782485875706216e-05, + "loss": 0.3828, + "step": 13286 + }, + { + "epoch": 1.08, + "learning_rate": 1.278194263363755e-05, + "loss": 0.3194, + "step": 13287 + }, + { + "epoch": 1.08, + "learning_rate": 1.2781399391568884e-05, + "loss": 0.2531, + "step": 13288 + }, + { + "epoch": 1.08, + "learning_rate": 1.2780856149500219e-05, + "loss": 0.2081, + "step": 13289 + }, + { + "epoch": 1.08, + "learning_rate": 1.2780312907431553e-05, + "loss": 0.2355, + "step": 13290 + }, + { + "epoch": 1.08, + "learning_rate": 1.2779769665362887e-05, + "loss": 0.3601, + "step": 13291 + }, + { + "epoch": 1.08, + "learning_rate": 1.2779226423294221e-05, + "loss": 0.3218, + "step": 13292 + }, + { + "epoch": 1.08, + "learning_rate": 1.2778683181225556e-05, + "loss": 0.1771, + "step": 13293 + }, + { + "epoch": 1.08, + "learning_rate": 1.2778139939156888e-05, + "loss": 0.1627, + "step": 13294 + }, + { + "epoch": 1.08, + "learning_rate": 1.2777596697088224e-05, + "loss": 0.478, + "step": 13295 + }, + { + "epoch": 1.08, + "learning_rate": 1.2777053455019557e-05, + "loss": 0.3709, + "step": 13296 + }, + { + "epoch": 1.08, + "learning_rate": 1.2776510212950892e-05, + "loss": 0.4439, + "step": 13297 + }, + { + "epoch": 1.08, + "learning_rate": 1.2775966970882225e-05, + "loss": 0.224, + "step": 13298 + }, + { + "epoch": 1.08, + "learning_rate": 1.2775423728813561e-05, + "loss": 0.3422, + "step": 13299 + }, + { + "epoch": 1.08, + "learning_rate": 1.2774880486744893e-05, + "loss": 0.294, + "step": 13300 + }, + { + "epoch": 1.08, + "learning_rate": 1.277433724467623e-05, + "loss": 0.3724, + "step": 13301 + }, + { + "epoch": 1.08, + "learning_rate": 1.2773794002607562e-05, + "loss": 0.3588, + "step": 13302 + }, + { + "epoch": 1.08, + "learning_rate": 1.2773250760538898e-05, + "loss": 0.3654, + "step": 13303 + }, + { + "epoch": 1.08, + "learning_rate": 1.277270751847023e-05, + "loss": 0.2688, + "step": 13304 + }, + { + "epoch": 1.08, + "learning_rate": 1.2772164276401566e-05, + "loss": 0.5173, + "step": 13305 + }, + { + "epoch": 1.08, + "learning_rate": 1.2771621034332899e-05, + "loss": 0.3848, + "step": 13306 + }, + { + "epoch": 1.08, + "learning_rate": 1.2771077792264235e-05, + "loss": 0.5221, + "step": 13307 + }, + { + "epoch": 1.08, + "learning_rate": 1.2770534550195567e-05, + "loss": 0.3617, + "step": 13308 + }, + { + "epoch": 1.08, + "learning_rate": 1.2769991308126903e-05, + "loss": 0.3835, + "step": 13309 + }, + { + "epoch": 1.08, + "learning_rate": 1.2769448066058236e-05, + "loss": 0.307, + "step": 13310 + }, + { + "epoch": 1.08, + "learning_rate": 1.2768904823989572e-05, + "loss": 0.1197, + "step": 13311 + }, + { + "epoch": 1.08, + "learning_rate": 1.2768361581920904e-05, + "loss": 0.6375, + "step": 13312 + }, + { + "epoch": 1.08, + "learning_rate": 1.2767818339852238e-05, + "loss": 0.282, + "step": 13313 + }, + { + "epoch": 1.08, + "learning_rate": 1.2767275097783573e-05, + "loss": 0.1505, + "step": 13314 + }, + { + "epoch": 1.08, + "learning_rate": 1.2766731855714907e-05, + "loss": 0.2686, + "step": 13315 + }, + { + "epoch": 1.09, + "learning_rate": 1.2766188613646243e-05, + "loss": 0.2382, + "step": 13316 + }, + { + "epoch": 1.09, + "learning_rate": 1.2765645371577575e-05, + "loss": 0.3672, + "step": 13317 + }, + { + "epoch": 1.09, + "learning_rate": 1.2765102129508911e-05, + "loss": 0.3432, + "step": 13318 + }, + { + "epoch": 1.09, + "learning_rate": 1.2764558887440244e-05, + "loss": 0.1501, + "step": 13319 + }, + { + "epoch": 1.09, + "learning_rate": 1.276401564537158e-05, + "loss": 0.417, + "step": 13320 + }, + { + "epoch": 1.09, + "learning_rate": 1.2763472403302912e-05, + "loss": 0.2647, + "step": 13321 + }, + { + "epoch": 1.09, + "learning_rate": 1.2762929161234248e-05, + "loss": 0.4357, + "step": 13322 + }, + { + "epoch": 1.09, + "learning_rate": 1.276238591916558e-05, + "loss": 0.3044, + "step": 13323 + }, + { + "epoch": 1.09, + "learning_rate": 1.2761842677096917e-05, + "loss": 0.1767, + "step": 13324 + }, + { + "epoch": 1.09, + "learning_rate": 1.276129943502825e-05, + "loss": 0.365, + "step": 13325 + }, + { + "epoch": 1.09, + "learning_rate": 1.2760756192959585e-05, + "loss": 0.3763, + "step": 13326 + }, + { + "epoch": 1.09, + "learning_rate": 1.2760212950890918e-05, + "loss": 0.3881, + "step": 13327 + }, + { + "epoch": 1.09, + "learning_rate": 1.2759669708822254e-05, + "loss": 0.2586, + "step": 13328 + }, + { + "epoch": 1.09, + "learning_rate": 1.2759126466753586e-05, + "loss": 0.2694, + "step": 13329 + }, + { + "epoch": 1.09, + "learning_rate": 1.2758583224684922e-05, + "loss": 0.2247, + "step": 13330 + }, + { + "epoch": 1.09, + "learning_rate": 1.2758039982616255e-05, + "loss": 0.4252, + "step": 13331 + }, + { + "epoch": 1.09, + "learning_rate": 1.2757496740547587e-05, + "loss": 0.4629, + "step": 13332 + }, + { + "epoch": 1.09, + "learning_rate": 1.2756953498478923e-05, + "loss": 0.244, + "step": 13333 + }, + { + "epoch": 1.09, + "learning_rate": 1.2756410256410257e-05, + "loss": 0.4035, + "step": 13334 + }, + { + "epoch": 1.09, + "learning_rate": 1.2755867014341592e-05, + "loss": 0.1894, + "step": 13335 + }, + { + "epoch": 1.09, + "learning_rate": 1.2755323772272926e-05, + "loss": 0.2254, + "step": 13336 + }, + { + "epoch": 1.09, + "learning_rate": 1.275478053020426e-05, + "loss": 0.2563, + "step": 13337 + }, + { + "epoch": 1.09, + "learning_rate": 1.2754237288135594e-05, + "loss": 0.2241, + "step": 13338 + }, + { + "epoch": 1.09, + "learning_rate": 1.2753694046066928e-05, + "loss": 0.1377, + "step": 13339 + }, + { + "epoch": 1.09, + "learning_rate": 1.2753150803998263e-05, + "loss": 0.6731, + "step": 13340 + }, + { + "epoch": 1.09, + "learning_rate": 1.2752607561929597e-05, + "loss": 0.3278, + "step": 13341 + }, + { + "epoch": 1.09, + "learning_rate": 1.2752064319860931e-05, + "loss": 0.2584, + "step": 13342 + }, + { + "epoch": 1.09, + "learning_rate": 1.2751521077792265e-05, + "loss": 0.2774, + "step": 13343 + }, + { + "epoch": 1.09, + "learning_rate": 1.27509778357236e-05, + "loss": 0.4057, + "step": 13344 + }, + { + "epoch": 1.09, + "learning_rate": 1.2750434593654934e-05, + "loss": 0.2422, + "step": 13345 + }, + { + "epoch": 1.09, + "learning_rate": 1.2749891351586268e-05, + "loss": 0.2208, + "step": 13346 + }, + { + "epoch": 1.09, + "learning_rate": 1.2749348109517602e-05, + "loss": 0.1624, + "step": 13347 + }, + { + "epoch": 1.09, + "learning_rate": 1.2748804867448937e-05, + "loss": 0.2209, + "step": 13348 + }, + { + "epoch": 1.09, + "learning_rate": 1.274826162538027e-05, + "loss": 0.4784, + "step": 13349 + }, + { + "epoch": 1.09, + "learning_rate": 1.2747718383311605e-05, + "loss": 0.1924, + "step": 13350 + }, + { + "epoch": 1.09, + "learning_rate": 1.2747175141242938e-05, + "loss": 0.3237, + "step": 13351 + }, + { + "epoch": 1.09, + "learning_rate": 1.2746631899174273e-05, + "loss": 0.6501, + "step": 13352 + }, + { + "epoch": 1.09, + "learning_rate": 1.2746088657105606e-05, + "loss": 0.441, + "step": 13353 + }, + { + "epoch": 1.09, + "learning_rate": 1.2745545415036942e-05, + "loss": 0.3174, + "step": 13354 + }, + { + "epoch": 1.09, + "learning_rate": 1.2745002172968274e-05, + "loss": 0.2087, + "step": 13355 + }, + { + "epoch": 1.09, + "learning_rate": 1.274445893089961e-05, + "loss": 0.1345, + "step": 13356 + }, + { + "epoch": 1.09, + "learning_rate": 1.2743915688830943e-05, + "loss": 0.4878, + "step": 13357 + }, + { + "epoch": 1.09, + "learning_rate": 1.2743372446762279e-05, + "loss": 0.2588, + "step": 13358 + }, + { + "epoch": 1.09, + "learning_rate": 1.2742829204693611e-05, + "loss": 0.2829, + "step": 13359 + }, + { + "epoch": 1.09, + "learning_rate": 1.2742285962624947e-05, + "loss": 0.4033, + "step": 13360 + }, + { + "epoch": 1.09, + "learning_rate": 1.274174272055628e-05, + "loss": 0.4804, + "step": 13361 + }, + { + "epoch": 1.09, + "learning_rate": 1.2741199478487616e-05, + "loss": 0.5244, + "step": 13362 + }, + { + "epoch": 1.09, + "learning_rate": 1.2740656236418948e-05, + "loss": 0.7286, + "step": 13363 + }, + { + "epoch": 1.09, + "learning_rate": 1.2740112994350284e-05, + "loss": 0.438, + "step": 13364 + }, + { + "epoch": 1.09, + "learning_rate": 1.2739569752281617e-05, + "loss": 0.2665, + "step": 13365 + }, + { + "epoch": 1.09, + "learning_rate": 1.2739026510212953e-05, + "loss": 0.188, + "step": 13366 + }, + { + "epoch": 1.09, + "learning_rate": 1.2738483268144285e-05, + "loss": 0.4979, + "step": 13367 + }, + { + "epoch": 1.09, + "learning_rate": 1.2737940026075621e-05, + "loss": 0.4915, + "step": 13368 + }, + { + "epoch": 1.09, + "learning_rate": 1.2737396784006955e-05, + "loss": 0.2726, + "step": 13369 + }, + { + "epoch": 1.09, + "learning_rate": 1.2736853541938288e-05, + "loss": 0.2857, + "step": 13370 + }, + { + "epoch": 1.09, + "learning_rate": 1.2736310299869624e-05, + "loss": 0.1226, + "step": 13371 + }, + { + "epoch": 1.09, + "learning_rate": 1.2735767057800956e-05, + "loss": 0.2791, + "step": 13372 + }, + { + "epoch": 1.09, + "learning_rate": 1.2735223815732292e-05, + "loss": 0.1895, + "step": 13373 + }, + { + "epoch": 1.09, + "learning_rate": 1.2734680573663625e-05, + "loss": 0.3997, + "step": 13374 + }, + { + "epoch": 1.09, + "learning_rate": 1.273413733159496e-05, + "loss": 0.195, + "step": 13375 + }, + { + "epoch": 1.09, + "learning_rate": 1.2733594089526293e-05, + "loss": 0.2212, + "step": 13376 + }, + { + "epoch": 1.09, + "learning_rate": 1.273305084745763e-05, + "loss": 0.3398, + "step": 13377 + }, + { + "epoch": 1.09, + "learning_rate": 1.2732507605388962e-05, + "loss": 0.2381, + "step": 13378 + }, + { + "epoch": 1.09, + "learning_rate": 1.2731964363320298e-05, + "loss": 0.3855, + "step": 13379 + }, + { + "epoch": 1.09, + "learning_rate": 1.273142112125163e-05, + "loss": 0.298, + "step": 13380 + }, + { + "epoch": 1.09, + "learning_rate": 1.2730877879182966e-05, + "loss": 0.2996, + "step": 13381 + }, + { + "epoch": 1.09, + "learning_rate": 1.2730334637114299e-05, + "loss": 0.2185, + "step": 13382 + }, + { + "epoch": 1.09, + "learning_rate": 1.2729791395045635e-05, + "loss": 0.5088, + "step": 13383 + }, + { + "epoch": 1.09, + "learning_rate": 1.2729248152976967e-05, + "loss": 0.3349, + "step": 13384 + }, + { + "epoch": 1.09, + "learning_rate": 1.2728704910908303e-05, + "loss": 0.2769, + "step": 13385 + }, + { + "epoch": 1.09, + "learning_rate": 1.2728161668839636e-05, + "loss": 0.4364, + "step": 13386 + }, + { + "epoch": 1.09, + "learning_rate": 1.2727618426770972e-05, + "loss": 0.203, + "step": 13387 + }, + { + "epoch": 1.09, + "learning_rate": 1.2727075184702304e-05, + "loss": 0.463, + "step": 13388 + }, + { + "epoch": 1.09, + "learning_rate": 1.2726531942633638e-05, + "loss": 0.3971, + "step": 13389 + }, + { + "epoch": 1.09, + "learning_rate": 1.2725988700564973e-05, + "loss": 0.3752, + "step": 13390 + }, + { + "epoch": 1.09, + "learning_rate": 1.2725445458496307e-05, + "loss": 0.2532, + "step": 13391 + }, + { + "epoch": 1.09, + "learning_rate": 1.2724902216427641e-05, + "loss": 0.6724, + "step": 13392 + }, + { + "epoch": 1.09, + "learning_rate": 1.2724358974358975e-05, + "loss": 0.3017, + "step": 13393 + }, + { + "epoch": 1.09, + "learning_rate": 1.272381573229031e-05, + "loss": 0.4713, + "step": 13394 + }, + { + "epoch": 1.09, + "learning_rate": 1.2723272490221644e-05, + "loss": 0.4393, + "step": 13395 + }, + { + "epoch": 1.09, + "learning_rate": 1.2722729248152978e-05, + "loss": 0.2609, + "step": 13396 + }, + { + "epoch": 1.09, + "learning_rate": 1.2722186006084312e-05, + "loss": 0.274, + "step": 13397 + }, + { + "epoch": 1.09, + "learning_rate": 1.2721642764015646e-05, + "loss": 0.368, + "step": 13398 + }, + { + "epoch": 1.09, + "learning_rate": 1.272109952194698e-05, + "loss": 0.1641, + "step": 13399 + }, + { + "epoch": 1.09, + "learning_rate": 1.2720556279878315e-05, + "loss": 0.2121, + "step": 13400 + }, + { + "epoch": 1.09, + "learning_rate": 1.2720013037809649e-05, + "loss": 0.1287, + "step": 13401 + }, + { + "epoch": 1.09, + "learning_rate": 1.2719469795740983e-05, + "loss": 0.3305, + "step": 13402 + }, + { + "epoch": 1.09, + "learning_rate": 1.2718926553672318e-05, + "loss": 0.2654, + "step": 13403 + }, + { + "epoch": 1.09, + "learning_rate": 1.2718383311603652e-05, + "loss": 0.642, + "step": 13404 + }, + { + "epoch": 1.09, + "learning_rate": 1.2717840069534986e-05, + "loss": 0.2748, + "step": 13405 + }, + { + "epoch": 1.09, + "learning_rate": 1.2717296827466322e-05, + "loss": 0.3086, + "step": 13406 + }, + { + "epoch": 1.09, + "learning_rate": 1.2716753585397654e-05, + "loss": 0.3036, + "step": 13407 + }, + { + "epoch": 1.09, + "learning_rate": 1.2716210343328987e-05, + "loss": 0.2465, + "step": 13408 + }, + { + "epoch": 1.09, + "learning_rate": 1.2715667101260323e-05, + "loss": 0.1116, + "step": 13409 + }, + { + "epoch": 1.09, + "learning_rate": 1.2715123859191655e-05, + "loss": 0.3733, + "step": 13410 + }, + { + "epoch": 1.09, + "learning_rate": 1.2714580617122991e-05, + "loss": 0.5109, + "step": 13411 + }, + { + "epoch": 1.09, + "learning_rate": 1.2714037375054324e-05, + "loss": 0.4218, + "step": 13412 + }, + { + "epoch": 1.09, + "learning_rate": 1.271349413298566e-05, + "loss": 0.4946, + "step": 13413 + }, + { + "epoch": 1.09, + "learning_rate": 1.2712950890916992e-05, + "loss": 0.2848, + "step": 13414 + }, + { + "epoch": 1.09, + "learning_rate": 1.2712407648848328e-05, + "loss": 0.2081, + "step": 13415 + }, + { + "epoch": 1.09, + "learning_rate": 1.2711864406779661e-05, + "loss": 0.4927, + "step": 13416 + }, + { + "epoch": 1.09, + "learning_rate": 1.2711321164710997e-05, + "loss": 0.338, + "step": 13417 + }, + { + "epoch": 1.09, + "learning_rate": 1.271077792264233e-05, + "loss": 0.3315, + "step": 13418 + }, + { + "epoch": 1.09, + "learning_rate": 1.2710234680573665e-05, + "loss": 0.4088, + "step": 13419 + }, + { + "epoch": 1.09, + "learning_rate": 1.2709691438504998e-05, + "loss": 0.4809, + "step": 13420 + }, + { + "epoch": 1.09, + "learning_rate": 1.2709148196436334e-05, + "loss": 0.3446, + "step": 13421 + }, + { + "epoch": 1.09, + "learning_rate": 1.2708604954367666e-05, + "loss": 0.2731, + "step": 13422 + }, + { + "epoch": 1.09, + "learning_rate": 1.2708061712299002e-05, + "loss": 0.1926, + "step": 13423 + }, + { + "epoch": 1.09, + "learning_rate": 1.2707518470230336e-05, + "loss": 0.2402, + "step": 13424 + }, + { + "epoch": 1.09, + "learning_rate": 1.270697522816167e-05, + "loss": 0.2711, + "step": 13425 + }, + { + "epoch": 1.09, + "learning_rate": 1.2706431986093005e-05, + "loss": 0.4258, + "step": 13426 + }, + { + "epoch": 1.09, + "learning_rate": 1.2705888744024337e-05, + "loss": 0.525, + "step": 13427 + }, + { + "epoch": 1.09, + "learning_rate": 1.2705345501955673e-05, + "loss": 0.3172, + "step": 13428 + }, + { + "epoch": 1.09, + "learning_rate": 1.2704802259887006e-05, + "loss": 0.4041, + "step": 13429 + }, + { + "epoch": 1.09, + "learning_rate": 1.2704259017818342e-05, + "loss": 0.3315, + "step": 13430 + }, + { + "epoch": 1.09, + "learning_rate": 1.2703715775749674e-05, + "loss": 0.4224, + "step": 13431 + }, + { + "epoch": 1.09, + "learning_rate": 1.270317253368101e-05, + "loss": 0.254, + "step": 13432 + }, + { + "epoch": 1.09, + "learning_rate": 1.2702629291612343e-05, + "loss": 0.1614, + "step": 13433 + }, + { + "epoch": 1.09, + "learning_rate": 1.2702086049543679e-05, + "loss": 0.3097, + "step": 13434 + }, + { + "epoch": 1.09, + "learning_rate": 1.2701542807475011e-05, + "loss": 0.448, + "step": 13435 + }, + { + "epoch": 1.09, + "learning_rate": 1.2700999565406347e-05, + "loss": 0.3823, + "step": 13436 + }, + { + "epoch": 1.09, + "learning_rate": 1.270045632333768e-05, + "loss": 0.2433, + "step": 13437 + }, + { + "epoch": 1.1, + "learning_rate": 1.2699913081269016e-05, + "loss": 0.2787, + "step": 13438 + }, + { + "epoch": 1.1, + "learning_rate": 1.2699369839200348e-05, + "loss": 0.1525, + "step": 13439 + }, + { + "epoch": 1.1, + "learning_rate": 1.2698826597131684e-05, + "loss": 0.3937, + "step": 13440 + }, + { + "epoch": 1.1, + "learning_rate": 1.2698283355063017e-05, + "loss": 0.1854, + "step": 13441 + }, + { + "epoch": 1.1, + "learning_rate": 1.2697740112994353e-05, + "loss": 0.2728, + "step": 13442 + }, + { + "epoch": 1.1, + "learning_rate": 1.2697196870925685e-05, + "loss": 0.2251, + "step": 13443 + }, + { + "epoch": 1.1, + "learning_rate": 1.2696653628857021e-05, + "loss": 0.3241, + "step": 13444 + }, + { + "epoch": 1.1, + "learning_rate": 1.2696110386788354e-05, + "loss": 0.2321, + "step": 13445 + }, + { + "epoch": 1.1, + "learning_rate": 1.2695567144719688e-05, + "loss": 0.5281, + "step": 13446 + }, + { + "epoch": 1.1, + "learning_rate": 1.2695023902651022e-05, + "loss": 0.1968, + "step": 13447 + }, + { + "epoch": 1.1, + "learning_rate": 1.2694480660582356e-05, + "loss": 0.157, + "step": 13448 + }, + { + "epoch": 1.1, + "learning_rate": 1.269393741851369e-05, + "loss": 0.5607, + "step": 13449 + }, + { + "epoch": 1.1, + "learning_rate": 1.2693394176445025e-05, + "loss": 0.1514, + "step": 13450 + }, + { + "epoch": 1.1, + "learning_rate": 1.2692850934376359e-05, + "loss": 0.4251, + "step": 13451 + }, + { + "epoch": 1.1, + "learning_rate": 1.2692307692307693e-05, + "loss": 0.1031, + "step": 13452 + }, + { + "epoch": 1.1, + "learning_rate": 1.2691764450239027e-05, + "loss": 0.7883, + "step": 13453 + }, + { + "epoch": 1.1, + "learning_rate": 1.2691221208170362e-05, + "loss": 0.2818, + "step": 13454 + }, + { + "epoch": 1.1, + "learning_rate": 1.2690677966101696e-05, + "loss": 0.1658, + "step": 13455 + }, + { + "epoch": 1.1, + "learning_rate": 1.269013472403303e-05, + "loss": 0.3253, + "step": 13456 + }, + { + "epoch": 1.1, + "learning_rate": 1.2689591481964364e-05, + "loss": 0.3964, + "step": 13457 + }, + { + "epoch": 1.1, + "learning_rate": 1.2689048239895699e-05, + "loss": 0.306, + "step": 13458 + }, + { + "epoch": 1.1, + "learning_rate": 1.2688504997827033e-05, + "loss": 0.4591, + "step": 13459 + }, + { + "epoch": 1.1, + "learning_rate": 1.2687961755758367e-05, + "loss": 0.4284, + "step": 13460 + }, + { + "epoch": 1.1, + "learning_rate": 1.2687418513689703e-05, + "loss": 0.2091, + "step": 13461 + }, + { + "epoch": 1.1, + "learning_rate": 1.2686875271621035e-05, + "loss": 0.4526, + "step": 13462 + }, + { + "epoch": 1.1, + "learning_rate": 1.2686332029552371e-05, + "loss": 0.1228, + "step": 13463 + }, + { + "epoch": 1.1, + "learning_rate": 1.2685788787483704e-05, + "loss": 0.1462, + "step": 13464 + }, + { + "epoch": 1.1, + "learning_rate": 1.2685245545415036e-05, + "loss": 0.2049, + "step": 13465 + }, + { + "epoch": 1.1, + "learning_rate": 1.2684702303346372e-05, + "loss": 0.273, + "step": 13466 + }, + { + "epoch": 1.1, + "learning_rate": 1.2684159061277705e-05, + "loss": 0.3018, + "step": 13467 + }, + { + "epoch": 1.1, + "learning_rate": 1.268361581920904e-05, + "loss": 0.1935, + "step": 13468 + }, + { + "epoch": 1.1, + "learning_rate": 1.2683072577140373e-05, + "loss": 0.5263, + "step": 13469 + }, + { + "epoch": 1.1, + "learning_rate": 1.268252933507171e-05, + "loss": 0.3306, + "step": 13470 + }, + { + "epoch": 1.1, + "learning_rate": 1.2681986093003042e-05, + "loss": 0.2023, + "step": 13471 + }, + { + "epoch": 1.1, + "learning_rate": 1.2681442850934378e-05, + "loss": 0.3704, + "step": 13472 + }, + { + "epoch": 1.1, + "learning_rate": 1.268089960886571e-05, + "loss": 0.2693, + "step": 13473 + }, + { + "epoch": 1.1, + "learning_rate": 1.2680356366797046e-05, + "loss": 0.2042, + "step": 13474 + }, + { + "epoch": 1.1, + "learning_rate": 1.2679813124728379e-05, + "loss": 0.4089, + "step": 13475 + }, + { + "epoch": 1.1, + "learning_rate": 1.2679269882659715e-05, + "loss": 0.5034, + "step": 13476 + }, + { + "epoch": 1.1, + "learning_rate": 1.2678726640591049e-05, + "loss": 0.4865, + "step": 13477 + }, + { + "epoch": 1.1, + "learning_rate": 1.2678183398522383e-05, + "loss": 0.5926, + "step": 13478 + }, + { + "epoch": 1.1, + "learning_rate": 1.2677640156453717e-05, + "loss": 0.3664, + "step": 13479 + }, + { + "epoch": 1.1, + "learning_rate": 1.2677096914385052e-05, + "loss": 0.2995, + "step": 13480 + }, + { + "epoch": 1.1, + "learning_rate": 1.2676553672316386e-05, + "loss": 0.3497, + "step": 13481 + }, + { + "epoch": 1.1, + "learning_rate": 1.267601043024772e-05, + "loss": 0.2208, + "step": 13482 + }, + { + "epoch": 1.1, + "learning_rate": 1.2675467188179054e-05, + "loss": 0.2278, + "step": 13483 + }, + { + "epoch": 1.1, + "learning_rate": 1.2674923946110387e-05, + "loss": 0.3279, + "step": 13484 + }, + { + "epoch": 1.1, + "learning_rate": 1.2674380704041723e-05, + "loss": 0.191, + "step": 13485 + }, + { + "epoch": 1.1, + "learning_rate": 1.2673837461973055e-05, + "loss": 0.4043, + "step": 13486 + }, + { + "epoch": 1.1, + "learning_rate": 1.2673294219904391e-05, + "loss": 0.246, + "step": 13487 + }, + { + "epoch": 1.1, + "learning_rate": 1.2672750977835724e-05, + "loss": 0.4167, + "step": 13488 + }, + { + "epoch": 1.1, + "learning_rate": 1.267220773576706e-05, + "loss": 0.0979, + "step": 13489 + }, + { + "epoch": 1.1, + "learning_rate": 1.2671664493698392e-05, + "loss": 0.4082, + "step": 13490 + }, + { + "epoch": 1.1, + "learning_rate": 1.2671121251629728e-05, + "loss": 0.4402, + "step": 13491 + }, + { + "epoch": 1.1, + "learning_rate": 1.267057800956106e-05, + "loss": 0.3738, + "step": 13492 + }, + { + "epoch": 1.1, + "learning_rate": 1.2670034767492397e-05, + "loss": 0.3359, + "step": 13493 + }, + { + "epoch": 1.1, + "learning_rate": 1.2669491525423729e-05, + "loss": 0.3468, + "step": 13494 + }, + { + "epoch": 1.1, + "learning_rate": 1.2668948283355065e-05, + "loss": 0.2835, + "step": 13495 + }, + { + "epoch": 1.1, + "learning_rate": 1.2668405041286398e-05, + "loss": 0.0915, + "step": 13496 + }, + { + "epoch": 1.1, + "learning_rate": 1.2667861799217734e-05, + "loss": 0.4853, + "step": 13497 + }, + { + "epoch": 1.1, + "learning_rate": 1.2667318557149066e-05, + "loss": 0.262, + "step": 13498 + }, + { + "epoch": 1.1, + "learning_rate": 1.2666775315080402e-05, + "loss": 0.2832, + "step": 13499 + }, + { + "epoch": 1.1, + "learning_rate": 1.2666232073011735e-05, + "loss": 0.1749, + "step": 13500 + }, + { + "epoch": 1.1, + "eval_accuracy": 0.8315843097300051, + "eval_loss": 0.47806257009506226, + "eval_runtime": 22.3067, + "eval_samples_per_second": 440.002, + "eval_steps_per_second": 3.452, + "step": 13500 + }, + { + "epoch": 1.1, + "learning_rate": 1.266568883094307e-05, + "loss": 0.6157, + "step": 13501 + }, + { + "epoch": 1.1, + "learning_rate": 1.2665145588874403e-05, + "loss": 0.3611, + "step": 13502 + }, + { + "epoch": 1.1, + "learning_rate": 1.2664602346805737e-05, + "loss": 0.3899, + "step": 13503 + }, + { + "epoch": 1.1, + "learning_rate": 1.2664059104737071e-05, + "loss": 0.3768, + "step": 13504 + }, + { + "epoch": 1.1, + "learning_rate": 1.2663515862668406e-05, + "loss": 0.4115, + "step": 13505 + }, + { + "epoch": 1.1, + "learning_rate": 1.266297262059974e-05, + "loss": 0.1413, + "step": 13506 + }, + { + "epoch": 1.1, + "learning_rate": 1.2662429378531074e-05, + "loss": 0.4997, + "step": 13507 + }, + { + "epoch": 1.1, + "learning_rate": 1.2661886136462408e-05, + "loss": 0.2543, + "step": 13508 + }, + { + "epoch": 1.1, + "learning_rate": 1.2661342894393743e-05, + "loss": 0.3662, + "step": 13509 + }, + { + "epoch": 1.1, + "learning_rate": 1.2660799652325077e-05, + "loss": 0.3542, + "step": 13510 + }, + { + "epoch": 1.1, + "learning_rate": 1.2660256410256411e-05, + "loss": 0.4427, + "step": 13511 + }, + { + "epoch": 1.1, + "learning_rate": 1.2659713168187745e-05, + "loss": 0.308, + "step": 13512 + }, + { + "epoch": 1.1, + "learning_rate": 1.265916992611908e-05, + "loss": 0.1642, + "step": 13513 + }, + { + "epoch": 1.1, + "learning_rate": 1.2658626684050415e-05, + "loss": 0.1949, + "step": 13514 + }, + { + "epoch": 1.1, + "learning_rate": 1.2658083441981748e-05, + "loss": 0.4542, + "step": 13515 + }, + { + "epoch": 1.1, + "learning_rate": 1.2657540199913084e-05, + "loss": 0.312, + "step": 13516 + }, + { + "epoch": 1.1, + "learning_rate": 1.2656996957844416e-05, + "loss": 0.1941, + "step": 13517 + }, + { + "epoch": 1.1, + "learning_rate": 1.2656453715775752e-05, + "loss": 0.3583, + "step": 13518 + }, + { + "epoch": 1.1, + "learning_rate": 1.2655910473707085e-05, + "loss": 0.2681, + "step": 13519 + }, + { + "epoch": 1.1, + "learning_rate": 1.265536723163842e-05, + "loss": 0.363, + "step": 13520 + }, + { + "epoch": 1.1, + "learning_rate": 1.2654823989569753e-05, + "loss": 0.4637, + "step": 13521 + }, + { + "epoch": 1.1, + "learning_rate": 1.2654280747501086e-05, + "loss": 0.4691, + "step": 13522 + }, + { + "epoch": 1.1, + "learning_rate": 1.2653737505432422e-05, + "loss": 0.1491, + "step": 13523 + }, + { + "epoch": 1.1, + "learning_rate": 1.2653194263363754e-05, + "loss": 0.3169, + "step": 13524 + }, + { + "epoch": 1.1, + "learning_rate": 1.265265102129509e-05, + "loss": 0.2574, + "step": 13525 + }, + { + "epoch": 1.1, + "learning_rate": 1.2652107779226423e-05, + "loss": 0.6478, + "step": 13526 + }, + { + "epoch": 1.1, + "learning_rate": 1.2651564537157759e-05, + "loss": 0.2295, + "step": 13527 + }, + { + "epoch": 1.1, + "learning_rate": 1.2651021295089091e-05, + "loss": 0.342, + "step": 13528 + }, + { + "epoch": 1.1, + "learning_rate": 1.2650478053020427e-05, + "loss": 0.422, + "step": 13529 + }, + { + "epoch": 1.1, + "learning_rate": 1.264993481095176e-05, + "loss": 0.4121, + "step": 13530 + }, + { + "epoch": 1.1, + "learning_rate": 1.2649391568883096e-05, + "loss": 0.3402, + "step": 13531 + }, + { + "epoch": 1.1, + "learning_rate": 1.264884832681443e-05, + "loss": 0.224, + "step": 13532 + }, + { + "epoch": 1.1, + "learning_rate": 1.2648305084745764e-05, + "loss": 0.3136, + "step": 13533 + }, + { + "epoch": 1.1, + "learning_rate": 1.2647761842677098e-05, + "loss": 0.6702, + "step": 13534 + }, + { + "epoch": 1.1, + "learning_rate": 1.2647218600608433e-05, + "loss": 0.2506, + "step": 13535 + }, + { + "epoch": 1.1, + "learning_rate": 1.2646675358539767e-05, + "loss": 0.3538, + "step": 13536 + }, + { + "epoch": 1.1, + "learning_rate": 1.2646132116471101e-05, + "loss": 0.2761, + "step": 13537 + }, + { + "epoch": 1.1, + "learning_rate": 1.2645588874402435e-05, + "loss": 0.6059, + "step": 13538 + }, + { + "epoch": 1.1, + "learning_rate": 1.264504563233377e-05, + "loss": 0.2283, + "step": 13539 + }, + { + "epoch": 1.1, + "learning_rate": 1.2644502390265104e-05, + "loss": 0.3261, + "step": 13540 + }, + { + "epoch": 1.1, + "learning_rate": 1.2643959148196436e-05, + "loss": 0.1645, + "step": 13541 + }, + { + "epoch": 1.1, + "learning_rate": 1.2643415906127772e-05, + "loss": 0.5031, + "step": 13542 + }, + { + "epoch": 1.1, + "learning_rate": 1.2642872664059105e-05, + "loss": 0.3923, + "step": 13543 + }, + { + "epoch": 1.1, + "learning_rate": 1.264232942199044e-05, + "loss": 0.5634, + "step": 13544 + }, + { + "epoch": 1.1, + "learning_rate": 1.2641786179921773e-05, + "loss": 0.5362, + "step": 13545 + }, + { + "epoch": 1.1, + "learning_rate": 1.2641242937853109e-05, + "loss": 0.199, + "step": 13546 + }, + { + "epoch": 1.1, + "learning_rate": 1.2640699695784442e-05, + "loss": 0.4475, + "step": 13547 + }, + { + "epoch": 1.1, + "learning_rate": 1.2640156453715778e-05, + "loss": 0.2867, + "step": 13548 + }, + { + "epoch": 1.1, + "learning_rate": 1.263961321164711e-05, + "loss": 0.6557, + "step": 13549 + }, + { + "epoch": 1.1, + "learning_rate": 1.2639069969578446e-05, + "loss": 0.2357, + "step": 13550 + }, + { + "epoch": 1.1, + "learning_rate": 1.2638526727509779e-05, + "loss": 0.2283, + "step": 13551 + }, + { + "epoch": 1.1, + "learning_rate": 1.2637983485441115e-05, + "loss": 0.1678, + "step": 13552 + }, + { + "epoch": 1.1, + "learning_rate": 1.2637440243372447e-05, + "loss": 0.2921, + "step": 13553 + }, + { + "epoch": 1.1, + "learning_rate": 1.2636897001303783e-05, + "loss": 0.3372, + "step": 13554 + }, + { + "epoch": 1.1, + "learning_rate": 1.2636353759235116e-05, + "loss": 0.3025, + "step": 13555 + }, + { + "epoch": 1.1, + "learning_rate": 1.2635810517166451e-05, + "loss": 0.3816, + "step": 13556 + }, + { + "epoch": 1.1, + "learning_rate": 1.2635267275097784e-05, + "loss": 0.375, + "step": 13557 + }, + { + "epoch": 1.1, + "learning_rate": 1.263472403302912e-05, + "loss": 0.3052, + "step": 13558 + }, + { + "epoch": 1.1, + "learning_rate": 1.2634180790960452e-05, + "loss": 0.2807, + "step": 13559 + }, + { + "epoch": 1.1, + "learning_rate": 1.2633637548891787e-05, + "loss": 0.1603, + "step": 13560 + }, + { + "epoch": 1.11, + "learning_rate": 1.2633094306823121e-05, + "loss": 0.5119, + "step": 13561 + }, + { + "epoch": 1.11, + "learning_rate": 1.2632551064754455e-05, + "loss": 0.3395, + "step": 13562 + }, + { + "epoch": 1.11, + "learning_rate": 1.263200782268579e-05, + "loss": 0.2699, + "step": 13563 + }, + { + "epoch": 1.11, + "learning_rate": 1.2631464580617124e-05, + "loss": 0.2373, + "step": 13564 + }, + { + "epoch": 1.11, + "learning_rate": 1.2630921338548458e-05, + "loss": 0.359, + "step": 13565 + }, + { + "epoch": 1.11, + "learning_rate": 1.2630378096479792e-05, + "loss": 0.2701, + "step": 13566 + }, + { + "epoch": 1.11, + "learning_rate": 1.2629834854411126e-05, + "loss": 0.1647, + "step": 13567 + }, + { + "epoch": 1.11, + "learning_rate": 1.262929161234246e-05, + "loss": 0.1792, + "step": 13568 + }, + { + "epoch": 1.11, + "learning_rate": 1.2628748370273796e-05, + "loss": 0.305, + "step": 13569 + }, + { + "epoch": 1.11, + "learning_rate": 1.2628205128205129e-05, + "loss": 0.4029, + "step": 13570 + }, + { + "epoch": 1.11, + "learning_rate": 1.2627661886136465e-05, + "loss": 0.2139, + "step": 13571 + }, + { + "epoch": 1.11, + "learning_rate": 1.2627118644067797e-05, + "loss": 0.5348, + "step": 13572 + }, + { + "epoch": 1.11, + "learning_rate": 1.2626575401999133e-05, + "loss": 0.34, + "step": 13573 + }, + { + "epoch": 1.11, + "learning_rate": 1.2626032159930466e-05, + "loss": 0.1066, + "step": 13574 + }, + { + "epoch": 1.11, + "learning_rate": 1.2625488917861802e-05, + "loss": 0.1418, + "step": 13575 + }, + { + "epoch": 1.11, + "learning_rate": 1.2624945675793134e-05, + "loss": 0.3922, + "step": 13576 + }, + { + "epoch": 1.11, + "learning_rate": 1.262440243372447e-05, + "loss": 0.4813, + "step": 13577 + }, + { + "epoch": 1.11, + "learning_rate": 1.2623859191655803e-05, + "loss": 0.088, + "step": 13578 + }, + { + "epoch": 1.11, + "learning_rate": 1.2623315949587135e-05, + "loss": 0.2229, + "step": 13579 + }, + { + "epoch": 1.11, + "learning_rate": 1.2622772707518471e-05, + "loss": 0.2672, + "step": 13580 + }, + { + "epoch": 1.11, + "learning_rate": 1.2622229465449804e-05, + "loss": 0.1525, + "step": 13581 + }, + { + "epoch": 1.11, + "learning_rate": 1.262168622338114e-05, + "loss": 0.4509, + "step": 13582 + }, + { + "epoch": 1.11, + "learning_rate": 1.2621142981312472e-05, + "loss": 0.4454, + "step": 13583 + }, + { + "epoch": 1.11, + "learning_rate": 1.2620599739243808e-05, + "loss": 0.5677, + "step": 13584 + }, + { + "epoch": 1.11, + "learning_rate": 1.2620056497175142e-05, + "loss": 0.4212, + "step": 13585 + }, + { + "epoch": 1.11, + "learning_rate": 1.2619513255106477e-05, + "loss": 0.3954, + "step": 13586 + }, + { + "epoch": 1.11, + "learning_rate": 1.2618970013037811e-05, + "loss": 0.2602, + "step": 13587 + }, + { + "epoch": 1.11, + "learning_rate": 1.2618426770969145e-05, + "loss": 0.3371, + "step": 13588 + }, + { + "epoch": 1.11, + "learning_rate": 1.261788352890048e-05, + "loss": 0.3122, + "step": 13589 + }, + { + "epoch": 1.11, + "learning_rate": 1.2617340286831814e-05, + "loss": 0.5281, + "step": 13590 + }, + { + "epoch": 1.11, + "learning_rate": 1.2616797044763148e-05, + "loss": 0.2562, + "step": 13591 + }, + { + "epoch": 1.11, + "learning_rate": 1.2616253802694482e-05, + "loss": 0.6501, + "step": 13592 + }, + { + "epoch": 1.11, + "learning_rate": 1.2615710560625816e-05, + "loss": 0.2914, + "step": 13593 + }, + { + "epoch": 1.11, + "learning_rate": 1.261516731855715e-05, + "loss": 0.2612, + "step": 13594 + }, + { + "epoch": 1.11, + "learning_rate": 1.2614624076488485e-05, + "loss": 0.292, + "step": 13595 + }, + { + "epoch": 1.11, + "learning_rate": 1.2614080834419819e-05, + "loss": 0.5841, + "step": 13596 + }, + { + "epoch": 1.11, + "learning_rate": 1.2613537592351153e-05, + "loss": 0.3499, + "step": 13597 + }, + { + "epoch": 1.11, + "learning_rate": 1.2612994350282486e-05, + "loss": 0.3068, + "step": 13598 + }, + { + "epoch": 1.11, + "learning_rate": 1.2612451108213822e-05, + "loss": 0.2511, + "step": 13599 + }, + { + "epoch": 1.11, + "learning_rate": 1.2611907866145154e-05, + "loss": 0.5092, + "step": 13600 + }, + { + "epoch": 1.11, + "learning_rate": 1.261136462407649e-05, + "loss": 0.354, + "step": 13601 + }, + { + "epoch": 1.11, + "learning_rate": 1.2610821382007823e-05, + "loss": 0.3398, + "step": 13602 + }, + { + "epoch": 1.11, + "learning_rate": 1.2610278139939159e-05, + "loss": 0.31, + "step": 13603 + }, + { + "epoch": 1.11, + "learning_rate": 1.2609734897870491e-05, + "loss": 0.3611, + "step": 13604 + }, + { + "epoch": 1.11, + "learning_rate": 1.2609191655801827e-05, + "loss": 0.4397, + "step": 13605 + }, + { + "epoch": 1.11, + "learning_rate": 1.260864841373316e-05, + "loss": 0.1722, + "step": 13606 + }, + { + "epoch": 1.11, + "learning_rate": 1.2608105171664495e-05, + "loss": 0.2442, + "step": 13607 + }, + { + "epoch": 1.11, + "learning_rate": 1.2607561929595828e-05, + "loss": 0.2779, + "step": 13608 + }, + { + "epoch": 1.11, + "learning_rate": 1.2607018687527164e-05, + "loss": 0.304, + "step": 13609 + }, + { + "epoch": 1.11, + "learning_rate": 1.2606475445458496e-05, + "loss": 0.4286, + "step": 13610 + }, + { + "epoch": 1.11, + "learning_rate": 1.2605932203389832e-05, + "loss": 0.2648, + "step": 13611 + }, + { + "epoch": 1.11, + "learning_rate": 1.2605388961321165e-05, + "loss": 0.2775, + "step": 13612 + }, + { + "epoch": 1.11, + "learning_rate": 1.2604845719252501e-05, + "loss": 0.6092, + "step": 13613 + }, + { + "epoch": 1.11, + "learning_rate": 1.2604302477183833e-05, + "loss": 0.2849, + "step": 13614 + }, + { + "epoch": 1.11, + "learning_rate": 1.260375923511517e-05, + "loss": 0.4101, + "step": 13615 + }, + { + "epoch": 1.11, + "learning_rate": 1.2603215993046502e-05, + "loss": 0.3091, + "step": 13616 + }, + { + "epoch": 1.11, + "learning_rate": 1.2602672750977836e-05, + "loss": 0.3371, + "step": 13617 + }, + { + "epoch": 1.11, + "learning_rate": 1.260212950890917e-05, + "loss": 0.3554, + "step": 13618 + }, + { + "epoch": 1.11, + "learning_rate": 1.2601586266840505e-05, + "loss": 0.3329, + "step": 13619 + }, + { + "epoch": 1.11, + "learning_rate": 1.2601043024771839e-05, + "loss": 0.252, + "step": 13620 + }, + { + "epoch": 1.11, + "learning_rate": 1.2600499782703173e-05, + "loss": 0.283, + "step": 13621 + }, + { + "epoch": 1.11, + "learning_rate": 1.2599956540634509e-05, + "loss": 0.2262, + "step": 13622 + }, + { + "epoch": 1.11, + "learning_rate": 1.2599413298565841e-05, + "loss": 0.1675, + "step": 13623 + }, + { + "epoch": 1.11, + "learning_rate": 1.2598870056497177e-05, + "loss": 0.3502, + "step": 13624 + }, + { + "epoch": 1.11, + "learning_rate": 1.259832681442851e-05, + "loss": 0.3787, + "step": 13625 + }, + { + "epoch": 1.11, + "learning_rate": 1.2597783572359846e-05, + "loss": 0.2352, + "step": 13626 + }, + { + "epoch": 1.11, + "learning_rate": 1.2597240330291178e-05, + "loss": 0.1648, + "step": 13627 + }, + { + "epoch": 1.11, + "learning_rate": 1.2596697088222514e-05, + "loss": 0.4775, + "step": 13628 + }, + { + "epoch": 1.11, + "learning_rate": 1.2596153846153847e-05, + "loss": 0.2825, + "step": 13629 + }, + { + "epoch": 1.11, + "learning_rate": 1.2595610604085183e-05, + "loss": 0.361, + "step": 13630 + }, + { + "epoch": 1.11, + "learning_rate": 1.2595067362016515e-05, + "loss": 0.3435, + "step": 13631 + }, + { + "epoch": 1.11, + "learning_rate": 1.2594524119947851e-05, + "loss": 0.4291, + "step": 13632 + }, + { + "epoch": 1.11, + "learning_rate": 1.2593980877879184e-05, + "loss": 0.1912, + "step": 13633 + }, + { + "epoch": 1.11, + "learning_rate": 1.259343763581052e-05, + "loss": 0.4101, + "step": 13634 + }, + { + "epoch": 1.11, + "learning_rate": 1.2592894393741852e-05, + "loss": 0.3946, + "step": 13635 + }, + { + "epoch": 1.11, + "learning_rate": 1.2592351151673185e-05, + "loss": 0.3388, + "step": 13636 + }, + { + "epoch": 1.11, + "learning_rate": 1.259180790960452e-05, + "loss": 0.2161, + "step": 13637 + }, + { + "epoch": 1.11, + "learning_rate": 1.2591264667535853e-05, + "loss": 0.3837, + "step": 13638 + }, + { + "epoch": 1.11, + "learning_rate": 1.259072142546719e-05, + "loss": 0.2463, + "step": 13639 + }, + { + "epoch": 1.11, + "learning_rate": 1.2590178183398523e-05, + "loss": 0.1294, + "step": 13640 + }, + { + "epoch": 1.11, + "learning_rate": 1.2589634941329858e-05, + "loss": 0.39, + "step": 13641 + }, + { + "epoch": 1.11, + "learning_rate": 1.2589091699261192e-05, + "loss": 0.1388, + "step": 13642 + }, + { + "epoch": 1.11, + "learning_rate": 1.2588548457192526e-05, + "loss": 0.2533, + "step": 13643 + }, + { + "epoch": 1.11, + "learning_rate": 1.258800521512386e-05, + "loss": 0.3391, + "step": 13644 + }, + { + "epoch": 1.11, + "learning_rate": 1.2587461973055195e-05, + "loss": 0.2133, + "step": 13645 + }, + { + "epoch": 1.11, + "learning_rate": 1.2586918730986529e-05, + "loss": 0.2293, + "step": 13646 + }, + { + "epoch": 1.11, + "learning_rate": 1.2586375488917863e-05, + "loss": 0.4833, + "step": 13647 + }, + { + "epoch": 1.11, + "learning_rate": 1.2585832246849197e-05, + "loss": 0.1796, + "step": 13648 + }, + { + "epoch": 1.11, + "learning_rate": 1.2585289004780531e-05, + "loss": 0.2372, + "step": 13649 + }, + { + "epoch": 1.11, + "learning_rate": 1.2584745762711866e-05, + "loss": 0.1897, + "step": 13650 + }, + { + "epoch": 1.11, + "learning_rate": 1.25842025206432e-05, + "loss": 0.3626, + "step": 13651 + }, + { + "epoch": 1.11, + "learning_rate": 1.2583659278574534e-05, + "loss": 0.3955, + "step": 13652 + }, + { + "epoch": 1.11, + "learning_rate": 1.2583116036505868e-05, + "loss": 0.2206, + "step": 13653 + }, + { + "epoch": 1.11, + "learning_rate": 1.2582572794437203e-05, + "loss": 0.2903, + "step": 13654 + }, + { + "epoch": 1.11, + "learning_rate": 1.2582029552368535e-05, + "loss": 0.3908, + "step": 13655 + }, + { + "epoch": 1.11, + "learning_rate": 1.2581486310299871e-05, + "loss": 0.3403, + "step": 13656 + }, + { + "epoch": 1.11, + "learning_rate": 1.2580943068231204e-05, + "loss": 0.4968, + "step": 13657 + }, + { + "epoch": 1.11, + "learning_rate": 1.258039982616254e-05, + "loss": 0.269, + "step": 13658 + }, + { + "epoch": 1.11, + "learning_rate": 1.2579856584093872e-05, + "loss": 0.4548, + "step": 13659 + }, + { + "epoch": 1.11, + "learning_rate": 1.2579313342025208e-05, + "loss": 0.2215, + "step": 13660 + }, + { + "epoch": 1.11, + "learning_rate": 1.257877009995654e-05, + "loss": 0.3797, + "step": 13661 + }, + { + "epoch": 1.11, + "learning_rate": 1.2578226857887876e-05, + "loss": 0.2653, + "step": 13662 + }, + { + "epoch": 1.11, + "learning_rate": 1.2577683615819209e-05, + "loss": 0.4184, + "step": 13663 + }, + { + "epoch": 1.11, + "learning_rate": 1.2577140373750545e-05, + "loss": 0.3114, + "step": 13664 + }, + { + "epoch": 1.11, + "learning_rate": 1.2576597131681877e-05, + "loss": 0.2037, + "step": 13665 + }, + { + "epoch": 1.11, + "learning_rate": 1.2576053889613213e-05, + "loss": 0.4667, + "step": 13666 + }, + { + "epoch": 1.11, + "learning_rate": 1.2575510647544546e-05, + "loss": 0.2807, + "step": 13667 + }, + { + "epoch": 1.11, + "learning_rate": 1.2574967405475882e-05, + "loss": 0.3235, + "step": 13668 + }, + { + "epoch": 1.11, + "learning_rate": 1.2574424163407214e-05, + "loss": 0.3236, + "step": 13669 + }, + { + "epoch": 1.11, + "learning_rate": 1.257388092133855e-05, + "loss": 0.3418, + "step": 13670 + }, + { + "epoch": 1.11, + "learning_rate": 1.2573337679269883e-05, + "loss": 0.3443, + "step": 13671 + }, + { + "epoch": 1.11, + "learning_rate": 1.2572794437201219e-05, + "loss": 0.6898, + "step": 13672 + }, + { + "epoch": 1.11, + "learning_rate": 1.2572251195132551e-05, + "loss": 0.3677, + "step": 13673 + }, + { + "epoch": 1.11, + "learning_rate": 1.2571707953063886e-05, + "loss": 0.2529, + "step": 13674 + }, + { + "epoch": 1.11, + "learning_rate": 1.257116471099522e-05, + "loss": 0.2307, + "step": 13675 + }, + { + "epoch": 1.11, + "learning_rate": 1.2570621468926554e-05, + "loss": 0.3884, + "step": 13676 + }, + { + "epoch": 1.11, + "learning_rate": 1.257007822685789e-05, + "loss": 0.2794, + "step": 13677 + }, + { + "epoch": 1.11, + "learning_rate": 1.2569534984789222e-05, + "loss": 0.214, + "step": 13678 + }, + { + "epoch": 1.11, + "learning_rate": 1.2568991742720558e-05, + "loss": 0.1344, + "step": 13679 + }, + { + "epoch": 1.11, + "learning_rate": 1.2568448500651891e-05, + "loss": 0.4306, + "step": 13680 + }, + { + "epoch": 1.11, + "learning_rate": 1.2567905258583227e-05, + "loss": 0.2196, + "step": 13681 + }, + { + "epoch": 1.11, + "learning_rate": 1.256736201651456e-05, + "loss": 0.2228, + "step": 13682 + }, + { + "epoch": 1.11, + "learning_rate": 1.2566818774445895e-05, + "loss": 0.3, + "step": 13683 + }, + { + "epoch": 1.12, + "learning_rate": 1.2566275532377228e-05, + "loss": 0.2234, + "step": 13684 + }, + { + "epoch": 1.12, + "learning_rate": 1.2565732290308564e-05, + "loss": 0.4088, + "step": 13685 + }, + { + "epoch": 1.12, + "learning_rate": 1.2565189048239896e-05, + "loss": 0.13, + "step": 13686 + }, + { + "epoch": 1.12, + "learning_rate": 1.2564645806171232e-05, + "loss": 0.5443, + "step": 13687 + }, + { + "epoch": 1.12, + "learning_rate": 1.2564102564102565e-05, + "loss": 0.4027, + "step": 13688 + }, + { + "epoch": 1.12, + "learning_rate": 1.25635593220339e-05, + "loss": 0.4742, + "step": 13689 + }, + { + "epoch": 1.12, + "learning_rate": 1.2563016079965233e-05, + "loss": 0.4547, + "step": 13690 + }, + { + "epoch": 1.12, + "learning_rate": 1.256247283789657e-05, + "loss": 0.1917, + "step": 13691 + }, + { + "epoch": 1.12, + "learning_rate": 1.2561929595827902e-05, + "loss": 0.4033, + "step": 13692 + }, + { + "epoch": 1.12, + "learning_rate": 1.2561386353759236e-05, + "loss": 0.2299, + "step": 13693 + }, + { + "epoch": 1.12, + "learning_rate": 1.256084311169057e-05, + "loss": 0.5266, + "step": 13694 + }, + { + "epoch": 1.12, + "learning_rate": 1.2560299869621904e-05, + "loss": 0.2252, + "step": 13695 + }, + { + "epoch": 1.12, + "learning_rate": 1.2559756627553239e-05, + "loss": 0.3879, + "step": 13696 + }, + { + "epoch": 1.12, + "learning_rate": 1.2559213385484573e-05, + "loss": 0.4197, + "step": 13697 + }, + { + "epoch": 1.12, + "learning_rate": 1.2558670143415907e-05, + "loss": 0.1199, + "step": 13698 + }, + { + "epoch": 1.12, + "learning_rate": 1.2558126901347241e-05, + "loss": 0.4973, + "step": 13699 + }, + { + "epoch": 1.12, + "learning_rate": 1.2557583659278576e-05, + "loss": 0.5327, + "step": 13700 + }, + { + "epoch": 1.12, + "learning_rate": 1.255704041720991e-05, + "loss": 0.188, + "step": 13701 + }, + { + "epoch": 1.12, + "learning_rate": 1.2556497175141244e-05, + "loss": 0.2932, + "step": 13702 + }, + { + "epoch": 1.12, + "learning_rate": 1.2555953933072578e-05, + "loss": 0.1251, + "step": 13703 + }, + { + "epoch": 1.12, + "learning_rate": 1.2555410691003912e-05, + "loss": 0.446, + "step": 13704 + }, + { + "epoch": 1.12, + "learning_rate": 1.2554867448935247e-05, + "loss": 0.1681, + "step": 13705 + }, + { + "epoch": 1.12, + "learning_rate": 1.2554324206866581e-05, + "loss": 0.3207, + "step": 13706 + }, + { + "epoch": 1.12, + "learning_rate": 1.2553780964797915e-05, + "loss": 0.1786, + "step": 13707 + }, + { + "epoch": 1.12, + "learning_rate": 1.255323772272925e-05, + "loss": 0.3876, + "step": 13708 + }, + { + "epoch": 1.12, + "learning_rate": 1.2552694480660584e-05, + "loss": 0.7035, + "step": 13709 + }, + { + "epoch": 1.12, + "learning_rate": 1.2552151238591918e-05, + "loss": 0.2867, + "step": 13710 + }, + { + "epoch": 1.12, + "learning_rate": 1.2551607996523252e-05, + "loss": 0.289, + "step": 13711 + }, + { + "epoch": 1.12, + "learning_rate": 1.2551064754454585e-05, + "loss": 0.2633, + "step": 13712 + }, + { + "epoch": 1.12, + "learning_rate": 1.255052151238592e-05, + "loss": 0.1583, + "step": 13713 + }, + { + "epoch": 1.12, + "learning_rate": 1.2549978270317253e-05, + "loss": 0.3885, + "step": 13714 + }, + { + "epoch": 1.12, + "learning_rate": 1.2549435028248589e-05, + "loss": 0.3096, + "step": 13715 + }, + { + "epoch": 1.12, + "learning_rate": 1.2548891786179922e-05, + "loss": 0.196, + "step": 13716 + }, + { + "epoch": 1.12, + "learning_rate": 1.2548348544111257e-05, + "loss": 0.259, + "step": 13717 + }, + { + "epoch": 1.12, + "learning_rate": 1.254780530204259e-05, + "loss": 0.5343, + "step": 13718 + }, + { + "epoch": 1.12, + "learning_rate": 1.2547262059973926e-05, + "loss": 0.15, + "step": 13719 + }, + { + "epoch": 1.12, + "learning_rate": 1.2546718817905258e-05, + "loss": 0.2744, + "step": 13720 + }, + { + "epoch": 1.12, + "learning_rate": 1.2546175575836594e-05, + "loss": 0.3357, + "step": 13721 + }, + { + "epoch": 1.12, + "learning_rate": 1.2545632333767927e-05, + "loss": 0.2077, + "step": 13722 + }, + { + "epoch": 1.12, + "learning_rate": 1.2545089091699263e-05, + "loss": 0.3891, + "step": 13723 + }, + { + "epoch": 1.12, + "learning_rate": 1.2544545849630595e-05, + "loss": 0.3227, + "step": 13724 + }, + { + "epoch": 1.12, + "learning_rate": 1.2544002607561931e-05, + "loss": 0.1625, + "step": 13725 + }, + { + "epoch": 1.12, + "learning_rate": 1.2543459365493264e-05, + "loss": 0.2125, + "step": 13726 + }, + { + "epoch": 1.12, + "learning_rate": 1.25429161234246e-05, + "loss": 0.4018, + "step": 13727 + }, + { + "epoch": 1.12, + "learning_rate": 1.2542372881355932e-05, + "loss": 0.6287, + "step": 13728 + }, + { + "epoch": 1.12, + "learning_rate": 1.2541829639287268e-05, + "loss": 0.4086, + "step": 13729 + }, + { + "epoch": 1.12, + "learning_rate": 1.2541286397218602e-05, + "loss": 0.337, + "step": 13730 + }, + { + "epoch": 1.12, + "learning_rate": 1.2540743155149935e-05, + "loss": 0.3769, + "step": 13731 + }, + { + "epoch": 1.12, + "learning_rate": 1.2540199913081271e-05, + "loss": 0.3328, + "step": 13732 + }, + { + "epoch": 1.12, + "learning_rate": 1.2539656671012603e-05, + "loss": 0.2559, + "step": 13733 + }, + { + "epoch": 1.12, + "learning_rate": 1.253911342894394e-05, + "loss": 0.317, + "step": 13734 + }, + { + "epoch": 1.12, + "learning_rate": 1.2538570186875272e-05, + "loss": 0.4006, + "step": 13735 + }, + { + "epoch": 1.12, + "learning_rate": 1.2538026944806608e-05, + "loss": 0.4134, + "step": 13736 + }, + { + "epoch": 1.12, + "learning_rate": 1.253748370273794e-05, + "loss": 0.2525, + "step": 13737 + }, + { + "epoch": 1.12, + "learning_rate": 1.2536940460669276e-05, + "loss": 0.4447, + "step": 13738 + }, + { + "epoch": 1.12, + "learning_rate": 1.2536397218600609e-05, + "loss": 0.2529, + "step": 13739 + }, + { + "epoch": 1.12, + "learning_rate": 1.2535853976531945e-05, + "loss": 0.698, + "step": 13740 + }, + { + "epoch": 1.12, + "learning_rate": 1.2535310734463277e-05, + "loss": 0.4477, + "step": 13741 + }, + { + "epoch": 1.12, + "learning_rate": 1.2534767492394613e-05, + "loss": 0.5464, + "step": 13742 + }, + { + "epoch": 1.12, + "learning_rate": 1.2534224250325946e-05, + "loss": 0.45, + "step": 13743 + }, + { + "epoch": 1.12, + "learning_rate": 1.2533681008257282e-05, + "loss": 0.5553, + "step": 13744 + }, + { + "epoch": 1.12, + "learning_rate": 1.2533137766188614e-05, + "loss": 0.5212, + "step": 13745 + }, + { + "epoch": 1.12, + "learning_rate": 1.253259452411995e-05, + "loss": 0.2562, + "step": 13746 + }, + { + "epoch": 1.12, + "learning_rate": 1.2532051282051283e-05, + "loss": 0.2962, + "step": 13747 + }, + { + "epoch": 1.12, + "learning_rate": 1.2531508039982619e-05, + "loss": 0.3474, + "step": 13748 + }, + { + "epoch": 1.12, + "learning_rate": 1.2530964797913951e-05, + "loss": 0.155, + "step": 13749 + }, + { + "epoch": 1.12, + "learning_rate": 1.2530421555845285e-05, + "loss": 0.144, + "step": 13750 + }, + { + "epoch": 1.12, + "eval_accuracy": 0.832093734080489, + "eval_loss": 0.45411574840545654, + "eval_runtime": 22.1986, + "eval_samples_per_second": 442.145, + "eval_steps_per_second": 3.469, + "step": 13750 + }, + { + "epoch": 1.12, + "learning_rate": 1.252987831377662e-05, + "loss": 0.35, + "step": 13751 + }, + { + "epoch": 1.12, + "learning_rate": 1.2529335071707954e-05, + "loss": 0.12, + "step": 13752 + }, + { + "epoch": 1.12, + "learning_rate": 1.2528791829639288e-05, + "loss": 0.3722, + "step": 13753 + }, + { + "epoch": 1.12, + "learning_rate": 1.2528248587570622e-05, + "loss": 0.2475, + "step": 13754 + }, + { + "epoch": 1.12, + "learning_rate": 1.2527705345501957e-05, + "loss": 0.2893, + "step": 13755 + }, + { + "epoch": 1.12, + "learning_rate": 1.252716210343329e-05, + "loss": 0.6394, + "step": 13756 + }, + { + "epoch": 1.12, + "learning_rate": 1.2526618861364625e-05, + "loss": 0.2524, + "step": 13757 + }, + { + "epoch": 1.12, + "learning_rate": 1.252607561929596e-05, + "loss": 0.3291, + "step": 13758 + }, + { + "epoch": 1.12, + "learning_rate": 1.2525532377227293e-05, + "loss": 0.2171, + "step": 13759 + }, + { + "epoch": 1.12, + "learning_rate": 1.2524989135158628e-05, + "loss": 0.5748, + "step": 13760 + }, + { + "epoch": 1.12, + "learning_rate": 1.2524445893089962e-05, + "loss": 0.4398, + "step": 13761 + }, + { + "epoch": 1.12, + "learning_rate": 1.2523902651021296e-05, + "loss": 0.1588, + "step": 13762 + }, + { + "epoch": 1.12, + "learning_rate": 1.252335940895263e-05, + "loss": 0.3788, + "step": 13763 + }, + { + "epoch": 1.12, + "learning_rate": 1.2522816166883965e-05, + "loss": 0.2698, + "step": 13764 + }, + { + "epoch": 1.12, + "learning_rate": 1.2522272924815299e-05, + "loss": 0.5364, + "step": 13765 + }, + { + "epoch": 1.12, + "learning_rate": 1.2521729682746633e-05, + "loss": 0.1791, + "step": 13766 + }, + { + "epoch": 1.12, + "learning_rate": 1.2521186440677969e-05, + "loss": 0.5312, + "step": 13767 + }, + { + "epoch": 1.12, + "learning_rate": 1.2520643198609302e-05, + "loss": 0.215, + "step": 13768 + }, + { + "epoch": 1.12, + "learning_rate": 1.2520099956540634e-05, + "loss": 0.2429, + "step": 13769 + }, + { + "epoch": 1.12, + "learning_rate": 1.251955671447197e-05, + "loss": 0.1983, + "step": 13770 + }, + { + "epoch": 1.12, + "learning_rate": 1.2519013472403303e-05, + "loss": 0.2445, + "step": 13771 + }, + { + "epoch": 1.12, + "learning_rate": 1.2518470230334638e-05, + "loss": 0.3732, + "step": 13772 + }, + { + "epoch": 1.12, + "learning_rate": 1.2517926988265971e-05, + "loss": 0.4383, + "step": 13773 + }, + { + "epoch": 1.12, + "learning_rate": 1.2517383746197307e-05, + "loss": 0.4923, + "step": 13774 + }, + { + "epoch": 1.12, + "learning_rate": 1.251684050412864e-05, + "loss": 0.1966, + "step": 13775 + }, + { + "epoch": 1.12, + "learning_rate": 1.2516297262059975e-05, + "loss": 0.4541, + "step": 13776 + }, + { + "epoch": 1.12, + "learning_rate": 1.2515754019991308e-05, + "loss": 0.7106, + "step": 13777 + }, + { + "epoch": 1.12, + "learning_rate": 1.2515210777922644e-05, + "loss": 0.4138, + "step": 13778 + }, + { + "epoch": 1.12, + "learning_rate": 1.2514667535853976e-05, + "loss": 0.3676, + "step": 13779 + }, + { + "epoch": 1.12, + "learning_rate": 1.2514124293785312e-05, + "loss": 0.2383, + "step": 13780 + }, + { + "epoch": 1.12, + "learning_rate": 1.2513581051716645e-05, + "loss": 0.2537, + "step": 13781 + }, + { + "epoch": 1.12, + "learning_rate": 1.251303780964798e-05, + "loss": 0.237, + "step": 13782 + }, + { + "epoch": 1.12, + "learning_rate": 1.2512494567579313e-05, + "loss": 0.1857, + "step": 13783 + }, + { + "epoch": 1.12, + "learning_rate": 1.251195132551065e-05, + "loss": 0.3492, + "step": 13784 + }, + { + "epoch": 1.12, + "learning_rate": 1.2511408083441983e-05, + "loss": 0.2118, + "step": 13785 + }, + { + "epoch": 1.12, + "learning_rate": 1.2510864841373318e-05, + "loss": 0.4732, + "step": 13786 + }, + { + "epoch": 1.12, + "learning_rate": 1.2510321599304652e-05, + "loss": 0.5488, + "step": 13787 + }, + { + "epoch": 1.12, + "learning_rate": 1.2509778357235984e-05, + "loss": 0.4761, + "step": 13788 + }, + { + "epoch": 1.12, + "learning_rate": 1.250923511516732e-05, + "loss": 0.3768, + "step": 13789 + }, + { + "epoch": 1.12, + "learning_rate": 1.2508691873098653e-05, + "loss": 0.2972, + "step": 13790 + }, + { + "epoch": 1.12, + "learning_rate": 1.2508148631029989e-05, + "loss": 0.447, + "step": 13791 + }, + { + "epoch": 1.12, + "learning_rate": 1.2507605388961321e-05, + "loss": 0.1703, + "step": 13792 + }, + { + "epoch": 1.12, + "learning_rate": 1.2507062146892657e-05, + "loss": 0.5972, + "step": 13793 + }, + { + "epoch": 1.12, + "learning_rate": 1.250651890482399e-05, + "loss": 0.3515, + "step": 13794 + }, + { + "epoch": 1.12, + "learning_rate": 1.2505975662755326e-05, + "loss": 0.2257, + "step": 13795 + }, + { + "epoch": 1.12, + "learning_rate": 1.2505432420686658e-05, + "loss": 0.1726, + "step": 13796 + }, + { + "epoch": 1.12, + "learning_rate": 1.2504889178617994e-05, + "loss": 0.4553, + "step": 13797 + }, + { + "epoch": 1.12, + "learning_rate": 1.2504345936549327e-05, + "loss": 0.2884, + "step": 13798 + }, + { + "epoch": 1.12, + "learning_rate": 1.2503802694480663e-05, + "loss": 0.1551, + "step": 13799 + }, + { + "epoch": 1.12, + "learning_rate": 1.2503259452411995e-05, + "loss": 0.4397, + "step": 13800 + }, + { + "epoch": 1.12, + "learning_rate": 1.2502716210343331e-05, + "loss": 0.1124, + "step": 13801 + }, + { + "epoch": 1.12, + "learning_rate": 1.2502172968274664e-05, + "loss": 0.3492, + "step": 13802 + }, + { + "epoch": 1.12, + "learning_rate": 1.2501629726206e-05, + "loss": 0.3067, + "step": 13803 + }, + { + "epoch": 1.12, + "learning_rate": 1.2501086484137332e-05, + "loss": 0.2815, + "step": 13804 + }, + { + "epoch": 1.12, + "learning_rate": 1.2500543242068668e-05, + "loss": 0.1011, + "step": 13805 + }, + { + "epoch": 1.12, + "learning_rate": 1.25e-05, + "loss": 0.4081, + "step": 13806 + }, + { + "epoch": 1.13, + "learning_rate": 1.2499456757931335e-05, + "loss": 0.2666, + "step": 13807 + }, + { + "epoch": 1.13, + "learning_rate": 1.2498913515862669e-05, + "loss": 0.5672, + "step": 13808 + }, + { + "epoch": 1.13, + "learning_rate": 1.2498370273794003e-05, + "loss": 0.3347, + "step": 13809 + }, + { + "epoch": 1.13, + "learning_rate": 1.2497827031725338e-05, + "loss": 0.6247, + "step": 13810 + }, + { + "epoch": 1.13, + "learning_rate": 1.2497283789656672e-05, + "loss": 0.1504, + "step": 13811 + }, + { + "epoch": 1.13, + "learning_rate": 1.2496740547588006e-05, + "loss": 0.5092, + "step": 13812 + }, + { + "epoch": 1.13, + "learning_rate": 1.249619730551934e-05, + "loss": 0.2139, + "step": 13813 + }, + { + "epoch": 1.13, + "learning_rate": 1.2495654063450674e-05, + "loss": 0.5102, + "step": 13814 + }, + { + "epoch": 1.13, + "learning_rate": 1.2495110821382009e-05, + "loss": 0.16, + "step": 13815 + }, + { + "epoch": 1.13, + "learning_rate": 1.2494567579313343e-05, + "loss": 0.2555, + "step": 13816 + }, + { + "epoch": 1.13, + "learning_rate": 1.2494024337244677e-05, + "loss": 0.6457, + "step": 13817 + }, + { + "epoch": 1.13, + "learning_rate": 1.2493481095176011e-05, + "loss": 0.2175, + "step": 13818 + }, + { + "epoch": 1.13, + "learning_rate": 1.2492937853107346e-05, + "loss": 0.3807, + "step": 13819 + }, + { + "epoch": 1.13, + "learning_rate": 1.2492394611038682e-05, + "loss": 0.8098, + "step": 13820 + }, + { + "epoch": 1.13, + "learning_rate": 1.2491851368970014e-05, + "loss": 0.3966, + "step": 13821 + }, + { + "epoch": 1.13, + "learning_rate": 1.249130812690135e-05, + "loss": 0.2578, + "step": 13822 + }, + { + "epoch": 1.13, + "learning_rate": 1.2490764884832683e-05, + "loss": 0.2435, + "step": 13823 + }, + { + "epoch": 1.13, + "learning_rate": 1.2490221642764018e-05, + "loss": 0.3621, + "step": 13824 + }, + { + "epoch": 1.13, + "learning_rate": 1.2489678400695351e-05, + "loss": 0.6804, + "step": 13825 + }, + { + "epoch": 1.13, + "learning_rate": 1.2489135158626684e-05, + "loss": 0.2586, + "step": 13826 + }, + { + "epoch": 1.13, + "learning_rate": 1.248859191655802e-05, + "loss": 0.3981, + "step": 13827 + }, + { + "epoch": 1.13, + "learning_rate": 1.2488048674489352e-05, + "loss": 0.3845, + "step": 13828 + }, + { + "epoch": 1.13, + "learning_rate": 1.2487505432420688e-05, + "loss": 0.2157, + "step": 13829 + }, + { + "epoch": 1.13, + "learning_rate": 1.248696219035202e-05, + "loss": 0.4777, + "step": 13830 + }, + { + "epoch": 1.13, + "learning_rate": 1.2486418948283356e-05, + "loss": 0.2363, + "step": 13831 + }, + { + "epoch": 1.13, + "learning_rate": 1.2485875706214689e-05, + "loss": 0.2062, + "step": 13832 + }, + { + "epoch": 1.13, + "learning_rate": 1.2485332464146025e-05, + "loss": 0.4387, + "step": 13833 + }, + { + "epoch": 1.13, + "learning_rate": 1.2484789222077357e-05, + "loss": 0.6023, + "step": 13834 + }, + { + "epoch": 1.13, + "learning_rate": 1.2484245980008693e-05, + "loss": 0.1901, + "step": 13835 + }, + { + "epoch": 1.13, + "learning_rate": 1.2483702737940026e-05, + "loss": 0.2272, + "step": 13836 + }, + { + "epoch": 1.13, + "learning_rate": 1.2483159495871362e-05, + "loss": 0.6709, + "step": 13837 + }, + { + "epoch": 1.13, + "learning_rate": 1.2482616253802696e-05, + "loss": 0.2077, + "step": 13838 + }, + { + "epoch": 1.13, + "learning_rate": 1.248207301173403e-05, + "loss": 0.2675, + "step": 13839 + }, + { + "epoch": 1.13, + "learning_rate": 1.2481529769665364e-05, + "loss": 0.1906, + "step": 13840 + }, + { + "epoch": 1.13, + "learning_rate": 1.2480986527596699e-05, + "loss": 0.3314, + "step": 13841 + }, + { + "epoch": 1.13, + "learning_rate": 1.2480443285528033e-05, + "loss": 0.2263, + "step": 13842 + }, + { + "epoch": 1.13, + "learning_rate": 1.2479900043459367e-05, + "loss": 0.3611, + "step": 13843 + }, + { + "epoch": 1.13, + "learning_rate": 1.2479356801390701e-05, + "loss": 0.2945, + "step": 13844 + }, + { + "epoch": 1.13, + "learning_rate": 1.2478813559322034e-05, + "loss": 0.39, + "step": 13845 + }, + { + "epoch": 1.13, + "learning_rate": 1.247827031725337e-05, + "loss": 0.3828, + "step": 13846 + }, + { + "epoch": 1.13, + "learning_rate": 1.2477727075184702e-05, + "loss": 0.3551, + "step": 13847 + }, + { + "epoch": 1.13, + "learning_rate": 1.2477183833116038e-05, + "loss": 0.422, + "step": 13848 + }, + { + "epoch": 1.13, + "learning_rate": 1.247664059104737e-05, + "loss": 0.2441, + "step": 13849 + }, + { + "epoch": 1.13, + "learning_rate": 1.2476097348978707e-05, + "loss": 0.5477, + "step": 13850 + }, + { + "epoch": 1.13, + "learning_rate": 1.247555410691004e-05, + "loss": 0.4787, + "step": 13851 + }, + { + "epoch": 1.13, + "learning_rate": 1.2475010864841375e-05, + "loss": 0.6472, + "step": 13852 + }, + { + "epoch": 1.13, + "learning_rate": 1.2474467622772708e-05, + "loss": 0.4231, + "step": 13853 + }, + { + "epoch": 1.13, + "learning_rate": 1.2473924380704044e-05, + "loss": 0.1559, + "step": 13854 + }, + { + "epoch": 1.13, + "learning_rate": 1.2473381138635376e-05, + "loss": 0.3203, + "step": 13855 + }, + { + "epoch": 1.13, + "learning_rate": 1.2472837896566712e-05, + "loss": 0.1564, + "step": 13856 + }, + { + "epoch": 1.13, + "learning_rate": 1.2472294654498045e-05, + "loss": 0.7401, + "step": 13857 + }, + { + "epoch": 1.13, + "learning_rate": 1.247175141242938e-05, + "loss": 0.4218, + "step": 13858 + }, + { + "epoch": 1.13, + "learning_rate": 1.2471208170360713e-05, + "loss": 0.6546, + "step": 13859 + }, + { + "epoch": 1.13, + "learning_rate": 1.2470664928292049e-05, + "loss": 0.0929, + "step": 13860 + }, + { + "epoch": 1.13, + "learning_rate": 1.2470121686223382e-05, + "loss": 0.3993, + "step": 13861 + }, + { + "epoch": 1.13, + "learning_rate": 1.2469578444154718e-05, + "loss": 0.4263, + "step": 13862 + }, + { + "epoch": 1.13, + "learning_rate": 1.246903520208605e-05, + "loss": 0.2381, + "step": 13863 + }, + { + "epoch": 1.13, + "learning_rate": 1.2468491960017384e-05, + "loss": 0.2501, + "step": 13864 + }, + { + "epoch": 1.13, + "learning_rate": 1.2467948717948719e-05, + "loss": 0.2823, + "step": 13865 + }, + { + "epoch": 1.13, + "learning_rate": 1.2467405475880053e-05, + "loss": 0.2857, + "step": 13866 + }, + { + "epoch": 1.13, + "learning_rate": 1.2466862233811387e-05, + "loss": 0.1803, + "step": 13867 + }, + { + "epoch": 1.13, + "learning_rate": 1.2466318991742721e-05, + "loss": 0.3994, + "step": 13868 + }, + { + "epoch": 1.13, + "learning_rate": 1.2465775749674055e-05, + "loss": 0.2798, + "step": 13869 + }, + { + "epoch": 1.13, + "learning_rate": 1.246523250760539e-05, + "loss": 0.466, + "step": 13870 + }, + { + "epoch": 1.13, + "learning_rate": 1.2464689265536724e-05, + "loss": 0.5571, + "step": 13871 + }, + { + "epoch": 1.13, + "learning_rate": 1.2464146023468058e-05, + "loss": 0.3883, + "step": 13872 + }, + { + "epoch": 1.13, + "learning_rate": 1.2463602781399392e-05, + "loss": 0.3626, + "step": 13873 + }, + { + "epoch": 1.13, + "learning_rate": 1.2463059539330727e-05, + "loss": 0.3085, + "step": 13874 + }, + { + "epoch": 1.13, + "learning_rate": 1.2462516297262063e-05, + "loss": 0.5237, + "step": 13875 + }, + { + "epoch": 1.13, + "learning_rate": 1.2461973055193395e-05, + "loss": 0.515, + "step": 13876 + }, + { + "epoch": 1.13, + "learning_rate": 1.2461429813124731e-05, + "loss": 0.2283, + "step": 13877 + }, + { + "epoch": 1.13, + "learning_rate": 1.2460886571056064e-05, + "loss": 0.157, + "step": 13878 + }, + { + "epoch": 1.13, + "learning_rate": 1.24603433289874e-05, + "loss": 0.2651, + "step": 13879 + }, + { + "epoch": 1.13, + "learning_rate": 1.2459800086918732e-05, + "loss": 0.3236, + "step": 13880 + }, + { + "epoch": 1.13, + "learning_rate": 1.2459256844850068e-05, + "loss": 0.4606, + "step": 13881 + }, + { + "epoch": 1.13, + "learning_rate": 1.24587136027814e-05, + "loss": 0.389, + "step": 13882 + }, + { + "epoch": 1.13, + "learning_rate": 1.2458170360712733e-05, + "loss": 0.3585, + "step": 13883 + }, + { + "epoch": 1.13, + "learning_rate": 1.2457627118644069e-05, + "loss": 0.3998, + "step": 13884 + }, + { + "epoch": 1.13, + "learning_rate": 1.2457083876575401e-05, + "loss": 0.2838, + "step": 13885 + }, + { + "epoch": 1.13, + "learning_rate": 1.2456540634506737e-05, + "loss": 0.1801, + "step": 13886 + }, + { + "epoch": 1.13, + "learning_rate": 1.245599739243807e-05, + "loss": 0.3313, + "step": 13887 + }, + { + "epoch": 1.13, + "learning_rate": 1.2455454150369406e-05, + "loss": 0.146, + "step": 13888 + }, + { + "epoch": 1.13, + "learning_rate": 1.2454910908300738e-05, + "loss": 0.2446, + "step": 13889 + }, + { + "epoch": 1.13, + "learning_rate": 1.2454367666232074e-05, + "loss": 0.5489, + "step": 13890 + }, + { + "epoch": 1.13, + "learning_rate": 1.2453824424163407e-05, + "loss": 0.4279, + "step": 13891 + }, + { + "epoch": 1.13, + "learning_rate": 1.2453281182094743e-05, + "loss": 0.4114, + "step": 13892 + }, + { + "epoch": 1.13, + "learning_rate": 1.2452737940026077e-05, + "loss": 0.1836, + "step": 13893 + }, + { + "epoch": 1.13, + "learning_rate": 1.2452194697957411e-05, + "loss": 0.3147, + "step": 13894 + }, + { + "epoch": 1.13, + "learning_rate": 1.2451651455888745e-05, + "loss": 0.3001, + "step": 13895 + }, + { + "epoch": 1.13, + "learning_rate": 1.245110821382008e-05, + "loss": 0.2003, + "step": 13896 + }, + { + "epoch": 1.13, + "learning_rate": 1.2450564971751414e-05, + "loss": 0.124, + "step": 13897 + }, + { + "epoch": 1.13, + "learning_rate": 1.2450021729682748e-05, + "loss": 0.3319, + "step": 13898 + }, + { + "epoch": 1.13, + "learning_rate": 1.2449478487614082e-05, + "loss": 0.4551, + "step": 13899 + }, + { + "epoch": 1.13, + "learning_rate": 1.2448935245545417e-05, + "loss": 0.5468, + "step": 13900 + }, + { + "epoch": 1.13, + "learning_rate": 1.244839200347675e-05, + "loss": 0.1002, + "step": 13901 + }, + { + "epoch": 1.13, + "learning_rate": 1.2447848761408083e-05, + "loss": 0.2578, + "step": 13902 + }, + { + "epoch": 1.13, + "learning_rate": 1.244730551933942e-05, + "loss": 0.2497, + "step": 13903 + }, + { + "epoch": 1.13, + "learning_rate": 1.2446762277270752e-05, + "loss": 0.5479, + "step": 13904 + }, + { + "epoch": 1.13, + "learning_rate": 1.2446219035202088e-05, + "loss": 0.3757, + "step": 13905 + }, + { + "epoch": 1.13, + "learning_rate": 1.244567579313342e-05, + "loss": 0.3668, + "step": 13906 + }, + { + "epoch": 1.13, + "learning_rate": 1.2445132551064756e-05, + "loss": 0.4612, + "step": 13907 + }, + { + "epoch": 1.13, + "learning_rate": 1.2444589308996089e-05, + "loss": 0.1446, + "step": 13908 + }, + { + "epoch": 1.13, + "learning_rate": 1.2444046066927425e-05, + "loss": 0.1975, + "step": 13909 + }, + { + "epoch": 1.13, + "learning_rate": 1.2443502824858757e-05, + "loss": 0.4829, + "step": 13910 + }, + { + "epoch": 1.13, + "learning_rate": 1.2442959582790093e-05, + "loss": 0.3463, + "step": 13911 + }, + { + "epoch": 1.13, + "learning_rate": 1.2442416340721426e-05, + "loss": 0.2836, + "step": 13912 + }, + { + "epoch": 1.13, + "learning_rate": 1.2441873098652762e-05, + "loss": 0.1035, + "step": 13913 + }, + { + "epoch": 1.13, + "learning_rate": 1.2441329856584094e-05, + "loss": 0.5079, + "step": 13914 + }, + { + "epoch": 1.13, + "learning_rate": 1.244078661451543e-05, + "loss": 0.3221, + "step": 13915 + }, + { + "epoch": 1.13, + "learning_rate": 1.2440243372446763e-05, + "loss": 0.4032, + "step": 13916 + }, + { + "epoch": 1.13, + "learning_rate": 1.2439700130378098e-05, + "loss": 0.3224, + "step": 13917 + }, + { + "epoch": 1.13, + "learning_rate": 1.2439156888309431e-05, + "loss": 0.3156, + "step": 13918 + }, + { + "epoch": 1.13, + "learning_rate": 1.2438613646240767e-05, + "loss": 0.1999, + "step": 13919 + }, + { + "epoch": 1.13, + "learning_rate": 1.24380704041721e-05, + "loss": 0.4746, + "step": 13920 + }, + { + "epoch": 1.13, + "learning_rate": 1.2437527162103434e-05, + "loss": 0.5603, + "step": 13921 + }, + { + "epoch": 1.13, + "learning_rate": 1.2436983920034768e-05, + "loss": 0.356, + "step": 13922 + }, + { + "epoch": 1.13, + "learning_rate": 1.2436440677966102e-05, + "loss": 0.2041, + "step": 13923 + }, + { + "epoch": 1.13, + "learning_rate": 1.2435897435897436e-05, + "loss": 0.2614, + "step": 13924 + }, + { + "epoch": 1.13, + "learning_rate": 1.243535419382877e-05, + "loss": 0.3528, + "step": 13925 + }, + { + "epoch": 1.13, + "learning_rate": 1.2434810951760105e-05, + "loss": 0.3477, + "step": 13926 + }, + { + "epoch": 1.13, + "learning_rate": 1.2434267709691439e-05, + "loss": 0.2033, + "step": 13927 + }, + { + "epoch": 1.13, + "learning_rate": 1.2433724467622775e-05, + "loss": 0.2278, + "step": 13928 + }, + { + "epoch": 1.14, + "learning_rate": 1.2433181225554108e-05, + "loss": 0.374, + "step": 13929 + }, + { + "epoch": 1.14, + "learning_rate": 1.2432637983485443e-05, + "loss": 0.5337, + "step": 13930 + }, + { + "epoch": 1.14, + "learning_rate": 1.2432094741416776e-05, + "loss": 0.3944, + "step": 13931 + }, + { + "epoch": 1.14, + "learning_rate": 1.2431551499348112e-05, + "loss": 0.1922, + "step": 13932 + }, + { + "epoch": 1.14, + "learning_rate": 1.2431008257279444e-05, + "loss": 0.3935, + "step": 13933 + }, + { + "epoch": 1.14, + "learning_rate": 1.243046501521078e-05, + "loss": 0.2892, + "step": 13934 + }, + { + "epoch": 1.14, + "learning_rate": 1.2429921773142113e-05, + "loss": 0.3661, + "step": 13935 + }, + { + "epoch": 1.14, + "learning_rate": 1.2429378531073449e-05, + "loss": 0.3853, + "step": 13936 + }, + { + "epoch": 1.14, + "learning_rate": 1.2428835289004781e-05, + "loss": 0.2193, + "step": 13937 + }, + { + "epoch": 1.14, + "learning_rate": 1.2428292046936117e-05, + "loss": 0.4543, + "step": 13938 + }, + { + "epoch": 1.14, + "learning_rate": 1.242774880486745e-05, + "loss": 0.3751, + "step": 13939 + }, + { + "epoch": 1.14, + "learning_rate": 1.2427205562798782e-05, + "loss": 0.3625, + "step": 13940 + }, + { + "epoch": 1.14, + "learning_rate": 1.2426662320730118e-05, + "loss": 0.2473, + "step": 13941 + }, + { + "epoch": 1.14, + "learning_rate": 1.2426119078661451e-05, + "loss": 0.5447, + "step": 13942 + }, + { + "epoch": 1.14, + "learning_rate": 1.2425575836592787e-05, + "loss": 0.6746, + "step": 13943 + }, + { + "epoch": 1.14, + "learning_rate": 1.242503259452412e-05, + "loss": 0.4084, + "step": 13944 + }, + { + "epoch": 1.14, + "learning_rate": 1.2424489352455455e-05, + "loss": 0.3555, + "step": 13945 + }, + { + "epoch": 1.14, + "learning_rate": 1.242394611038679e-05, + "loss": 0.17, + "step": 13946 + }, + { + "epoch": 1.14, + "learning_rate": 1.2423402868318124e-05, + "loss": 0.1677, + "step": 13947 + }, + { + "epoch": 1.14, + "learning_rate": 1.2422859626249458e-05, + "loss": 0.246, + "step": 13948 + }, + { + "epoch": 1.14, + "learning_rate": 1.2422316384180792e-05, + "loss": 0.3203, + "step": 13949 + }, + { + "epoch": 1.14, + "learning_rate": 1.2421773142112126e-05, + "loss": 0.2523, + "step": 13950 + }, + { + "epoch": 1.14, + "learning_rate": 1.242122990004346e-05, + "loss": 0.4427, + "step": 13951 + }, + { + "epoch": 1.14, + "learning_rate": 1.2420686657974795e-05, + "loss": 0.1762, + "step": 13952 + }, + { + "epoch": 1.14, + "learning_rate": 1.2420143415906129e-05, + "loss": 0.3267, + "step": 13953 + }, + { + "epoch": 1.14, + "learning_rate": 1.2419600173837463e-05, + "loss": 0.3284, + "step": 13954 + }, + { + "epoch": 1.14, + "learning_rate": 1.2419056931768798e-05, + "loss": 0.6033, + "step": 13955 + }, + { + "epoch": 1.14, + "learning_rate": 1.2418513689700132e-05, + "loss": 0.2281, + "step": 13956 + }, + { + "epoch": 1.14, + "learning_rate": 1.2417970447631466e-05, + "loss": 0.2665, + "step": 13957 + }, + { + "epoch": 1.14, + "learning_rate": 1.24174272055628e-05, + "loss": 0.463, + "step": 13958 + }, + { + "epoch": 1.14, + "learning_rate": 1.2416883963494133e-05, + "loss": 0.2697, + "step": 13959 + }, + { + "epoch": 1.14, + "learning_rate": 1.2416340721425469e-05, + "loss": 0.1985, + "step": 13960 + }, + { + "epoch": 1.14, + "learning_rate": 1.2415797479356801e-05, + "loss": 0.2373, + "step": 13961 + }, + { + "epoch": 1.14, + "learning_rate": 1.2415254237288137e-05, + "loss": 0.1878, + "step": 13962 + }, + { + "epoch": 1.14, + "learning_rate": 1.241471099521947e-05, + "loss": 0.7059, + "step": 13963 + }, + { + "epoch": 1.14, + "learning_rate": 1.2414167753150806e-05, + "loss": 0.2776, + "step": 13964 + }, + { + "epoch": 1.14, + "learning_rate": 1.2413624511082138e-05, + "loss": 0.5658, + "step": 13965 + }, + { + "epoch": 1.14, + "learning_rate": 1.2413081269013474e-05, + "loss": 0.4133, + "step": 13966 + }, + { + "epoch": 1.14, + "learning_rate": 1.2412538026944807e-05, + "loss": 0.4204, + "step": 13967 + }, + { + "epoch": 1.14, + "learning_rate": 1.2411994784876143e-05, + "loss": 0.3368, + "step": 13968 + }, + { + "epoch": 1.14, + "learning_rate": 1.2411451542807475e-05, + "loss": 0.1929, + "step": 13969 + }, + { + "epoch": 1.14, + "learning_rate": 1.2410908300738811e-05, + "loss": 0.3868, + "step": 13970 + }, + { + "epoch": 1.14, + "learning_rate": 1.2410365058670144e-05, + "loss": 0.3257, + "step": 13971 + }, + { + "epoch": 1.14, + "learning_rate": 1.240982181660148e-05, + "loss": 0.4659, + "step": 13972 + }, + { + "epoch": 1.14, + "learning_rate": 1.2409278574532812e-05, + "loss": 0.3867, + "step": 13973 + }, + { + "epoch": 1.14, + "learning_rate": 1.2408735332464148e-05, + "loss": 0.1544, + "step": 13974 + }, + { + "epoch": 1.14, + "learning_rate": 1.240819209039548e-05, + "loss": 0.5612, + "step": 13975 + }, + { + "epoch": 1.14, + "learning_rate": 1.2407648848326816e-05, + "loss": 0.3385, + "step": 13976 + }, + { + "epoch": 1.14, + "learning_rate": 1.2407105606258149e-05, + "loss": 0.4364, + "step": 13977 + }, + { + "epoch": 1.14, + "learning_rate": 1.2406562364189483e-05, + "loss": 0.343, + "step": 13978 + }, + { + "epoch": 1.14, + "learning_rate": 1.2406019122120817e-05, + "loss": 0.4056, + "step": 13979 + }, + { + "epoch": 1.14, + "learning_rate": 1.2405475880052152e-05, + "loss": 0.1119, + "step": 13980 + }, + { + "epoch": 1.14, + "learning_rate": 1.2404932637983486e-05, + "loss": 0.5507, + "step": 13981 + }, + { + "epoch": 1.14, + "learning_rate": 1.240438939591482e-05, + "loss": 0.219, + "step": 13982 + }, + { + "epoch": 1.14, + "learning_rate": 1.2403846153846156e-05, + "loss": 0.1782, + "step": 13983 + }, + { + "epoch": 1.14, + "learning_rate": 1.2403302911777489e-05, + "loss": 0.2546, + "step": 13984 + }, + { + "epoch": 1.14, + "learning_rate": 1.2402759669708824e-05, + "loss": 0.2722, + "step": 13985 + }, + { + "epoch": 1.14, + "learning_rate": 1.2402216427640157e-05, + "loss": 0.333, + "step": 13986 + }, + { + "epoch": 1.14, + "learning_rate": 1.2401673185571493e-05, + "loss": 0.423, + "step": 13987 + }, + { + "epoch": 1.14, + "learning_rate": 1.2401129943502825e-05, + "loss": 0.1577, + "step": 13988 + }, + { + "epoch": 1.14, + "learning_rate": 1.2400586701434161e-05, + "loss": 0.3767, + "step": 13989 + }, + { + "epoch": 1.14, + "learning_rate": 1.2400043459365494e-05, + "loss": 0.2338, + "step": 13990 + }, + { + "epoch": 1.14, + "learning_rate": 1.239950021729683e-05, + "loss": 0.5342, + "step": 13991 + }, + { + "epoch": 1.14, + "learning_rate": 1.2398956975228162e-05, + "loss": 0.4265, + "step": 13992 + }, + { + "epoch": 1.14, + "learning_rate": 1.2398413733159498e-05, + "loss": 0.3109, + "step": 13993 + }, + { + "epoch": 1.14, + "learning_rate": 1.2397870491090831e-05, + "loss": 0.1072, + "step": 13994 + }, + { + "epoch": 1.14, + "learning_rate": 1.2397327249022167e-05, + "loss": 0.3873, + "step": 13995 + }, + { + "epoch": 1.14, + "learning_rate": 1.23967840069535e-05, + "loss": 0.6218, + "step": 13996 + }, + { + "epoch": 1.14, + "learning_rate": 1.2396240764884832e-05, + "loss": 0.1726, + "step": 13997 + }, + { + "epoch": 1.14, + "learning_rate": 1.2395697522816168e-05, + "loss": 0.2509, + "step": 13998 + }, + { + "epoch": 1.14, + "learning_rate": 1.23951542807475e-05, + "loss": 0.305, + "step": 13999 + }, + { + "epoch": 1.14, + "learning_rate": 1.2394611038678836e-05, + "loss": 0.4449, + "step": 14000 + }, + { + "epoch": 1.14, + "eval_accuracy": 0.8311767702496179, + "eval_loss": 0.46548789739608765, + "eval_runtime": 22.3557, + "eval_samples_per_second": 439.037, + "eval_steps_per_second": 3.444, + "step": 14000 + }, + { + "epoch": 1.14, + "learning_rate": 1.239406779661017e-05, + "loss": 0.2699, + "step": 14001 + }, + { + "epoch": 1.14, + "learning_rate": 1.2393524554541505e-05, + "loss": 0.1793, + "step": 14002 + }, + { + "epoch": 1.14, + "learning_rate": 1.2392981312472839e-05, + "loss": 0.1656, + "step": 14003 + }, + { + "epoch": 1.14, + "learning_rate": 1.2392438070404173e-05, + "loss": 0.2849, + "step": 14004 + }, + { + "epoch": 1.14, + "learning_rate": 1.2391894828335507e-05, + "loss": 0.4885, + "step": 14005 + }, + { + "epoch": 1.14, + "learning_rate": 1.2391351586266842e-05, + "loss": 0.4747, + "step": 14006 + }, + { + "epoch": 1.14, + "learning_rate": 1.2390808344198176e-05, + "loss": 0.196, + "step": 14007 + }, + { + "epoch": 1.14, + "learning_rate": 1.239026510212951e-05, + "loss": 0.1719, + "step": 14008 + }, + { + "epoch": 1.14, + "learning_rate": 1.2389721860060844e-05, + "loss": 0.236, + "step": 14009 + }, + { + "epoch": 1.14, + "learning_rate": 1.2389178617992179e-05, + "loss": 0.3466, + "step": 14010 + }, + { + "epoch": 1.14, + "learning_rate": 1.2388635375923513e-05, + "loss": 0.2295, + "step": 14011 + }, + { + "epoch": 1.14, + "learning_rate": 1.2388092133854847e-05, + "loss": 0.6283, + "step": 14012 + }, + { + "epoch": 1.14, + "learning_rate": 1.2387548891786181e-05, + "loss": 0.4394, + "step": 14013 + }, + { + "epoch": 1.14, + "learning_rate": 1.2387005649717515e-05, + "loss": 0.2278, + "step": 14014 + }, + { + "epoch": 1.14, + "learning_rate": 1.238646240764885e-05, + "loss": 0.3796, + "step": 14015 + }, + { + "epoch": 1.14, + "learning_rate": 1.2385919165580182e-05, + "loss": 0.4454, + "step": 14016 + }, + { + "epoch": 1.14, + "learning_rate": 1.2385375923511518e-05, + "loss": 0.3533, + "step": 14017 + }, + { + "epoch": 1.14, + "learning_rate": 1.238483268144285e-05, + "loss": 0.5167, + "step": 14018 + }, + { + "epoch": 1.14, + "learning_rate": 1.2384289439374187e-05, + "loss": 0.4289, + "step": 14019 + }, + { + "epoch": 1.14, + "learning_rate": 1.238374619730552e-05, + "loss": 0.4878, + "step": 14020 + }, + { + "epoch": 1.14, + "learning_rate": 1.2383202955236855e-05, + "loss": 0.4058, + "step": 14021 + }, + { + "epoch": 1.14, + "learning_rate": 1.2382659713168188e-05, + "loss": 0.5809, + "step": 14022 + }, + { + "epoch": 1.14, + "learning_rate": 1.2382116471099524e-05, + "loss": 0.4396, + "step": 14023 + }, + { + "epoch": 1.14, + "learning_rate": 1.2381573229030856e-05, + "loss": 0.1352, + "step": 14024 + }, + { + "epoch": 1.14, + "learning_rate": 1.2381029986962192e-05, + "loss": 0.4315, + "step": 14025 + }, + { + "epoch": 1.14, + "learning_rate": 1.2380486744893525e-05, + "loss": 0.2341, + "step": 14026 + }, + { + "epoch": 1.14, + "learning_rate": 1.237994350282486e-05, + "loss": 0.2685, + "step": 14027 + }, + { + "epoch": 1.14, + "learning_rate": 1.2379400260756193e-05, + "loss": 0.3967, + "step": 14028 + }, + { + "epoch": 1.14, + "learning_rate": 1.2378857018687529e-05, + "loss": 0.3266, + "step": 14029 + }, + { + "epoch": 1.14, + "learning_rate": 1.2378313776618861e-05, + "loss": 0.4245, + "step": 14030 + }, + { + "epoch": 1.14, + "learning_rate": 1.2377770534550197e-05, + "loss": 0.1922, + "step": 14031 + }, + { + "epoch": 1.14, + "learning_rate": 1.237722729248153e-05, + "loss": 0.2495, + "step": 14032 + }, + { + "epoch": 1.14, + "learning_rate": 1.2376684050412866e-05, + "loss": 0.3676, + "step": 14033 + }, + { + "epoch": 1.14, + "learning_rate": 1.2376140808344198e-05, + "loss": 0.2954, + "step": 14034 + }, + { + "epoch": 1.14, + "learning_rate": 1.2375597566275533e-05, + "loss": 0.239, + "step": 14035 + }, + { + "epoch": 1.14, + "learning_rate": 1.2375054324206869e-05, + "loss": 0.3175, + "step": 14036 + }, + { + "epoch": 1.14, + "learning_rate": 1.2374511082138201e-05, + "loss": 0.5274, + "step": 14037 + }, + { + "epoch": 1.14, + "learning_rate": 1.2373967840069537e-05, + "loss": 0.2645, + "step": 14038 + }, + { + "epoch": 1.14, + "learning_rate": 1.237342459800087e-05, + "loss": 0.2168, + "step": 14039 + }, + { + "epoch": 1.14, + "learning_rate": 1.2372881355932205e-05, + "loss": 0.4589, + "step": 14040 + }, + { + "epoch": 1.14, + "learning_rate": 1.2372338113863538e-05, + "loss": 0.3378, + "step": 14041 + }, + { + "epoch": 1.14, + "learning_rate": 1.2371794871794874e-05, + "loss": 0.6192, + "step": 14042 + }, + { + "epoch": 1.14, + "learning_rate": 1.2371251629726206e-05, + "loss": 0.2069, + "step": 14043 + }, + { + "epoch": 1.14, + "learning_rate": 1.2370708387657542e-05, + "loss": 0.1557, + "step": 14044 + }, + { + "epoch": 1.14, + "learning_rate": 1.2370165145588875e-05, + "loss": 0.6414, + "step": 14045 + }, + { + "epoch": 1.14, + "learning_rate": 1.2369621903520211e-05, + "loss": 0.3521, + "step": 14046 + }, + { + "epoch": 1.14, + "learning_rate": 1.2369078661451543e-05, + "loss": 0.2059, + "step": 14047 + }, + { + "epoch": 1.14, + "learning_rate": 1.236853541938288e-05, + "loss": 0.1657, + "step": 14048 + }, + { + "epoch": 1.14, + "learning_rate": 1.2367992177314212e-05, + "loss": 0.3379, + "step": 14049 + }, + { + "epoch": 1.14, + "learning_rate": 1.2367448935245548e-05, + "loss": 0.2739, + "step": 14050 + }, + { + "epoch": 1.14, + "learning_rate": 1.236690569317688e-05, + "loss": 0.5807, + "step": 14051 + }, + { + "epoch": 1.15, + "learning_rate": 1.2366362451108216e-05, + "loss": 0.6457, + "step": 14052 + }, + { + "epoch": 1.15, + "learning_rate": 1.2365819209039549e-05, + "loss": 0.3245, + "step": 14053 + }, + { + "epoch": 1.15, + "learning_rate": 1.2365275966970883e-05, + "loss": 0.3796, + "step": 14054 + }, + { + "epoch": 1.15, + "learning_rate": 1.2364732724902217e-05, + "loss": 0.7829, + "step": 14055 + }, + { + "epoch": 1.15, + "learning_rate": 1.2364189482833551e-05, + "loss": 0.5927, + "step": 14056 + }, + { + "epoch": 1.15, + "learning_rate": 1.2363646240764886e-05, + "loss": 0.5859, + "step": 14057 + }, + { + "epoch": 1.15, + "learning_rate": 1.236310299869622e-05, + "loss": 0.3468, + "step": 14058 + }, + { + "epoch": 1.15, + "learning_rate": 1.2362559756627554e-05, + "loss": 0.4225, + "step": 14059 + }, + { + "epoch": 1.15, + "learning_rate": 1.2362016514558888e-05, + "loss": 0.3619, + "step": 14060 + }, + { + "epoch": 1.15, + "learning_rate": 1.2361473272490223e-05, + "loss": 0.5952, + "step": 14061 + }, + { + "epoch": 1.15, + "learning_rate": 1.2360930030421557e-05, + "loss": 0.1689, + "step": 14062 + }, + { + "epoch": 1.15, + "learning_rate": 1.2360386788352891e-05, + "loss": 0.287, + "step": 14063 + }, + { + "epoch": 1.15, + "learning_rate": 1.2359843546284225e-05, + "loss": 0.4962, + "step": 14064 + }, + { + "epoch": 1.15, + "learning_rate": 1.235930030421556e-05, + "loss": 0.4311, + "step": 14065 + }, + { + "epoch": 1.15, + "learning_rate": 1.2358757062146894e-05, + "loss": 0.4622, + "step": 14066 + }, + { + "epoch": 1.15, + "learning_rate": 1.2358213820078228e-05, + "loss": 0.2509, + "step": 14067 + }, + { + "epoch": 1.15, + "learning_rate": 1.2357670578009562e-05, + "loss": 0.1786, + "step": 14068 + }, + { + "epoch": 1.15, + "learning_rate": 1.2357127335940896e-05, + "loss": 0.5067, + "step": 14069 + }, + { + "epoch": 1.15, + "learning_rate": 1.235658409387223e-05, + "loss": 0.469, + "step": 14070 + }, + { + "epoch": 1.15, + "learning_rate": 1.2356040851803565e-05, + "loss": 0.1847, + "step": 14071 + }, + { + "epoch": 1.15, + "learning_rate": 1.2355497609734899e-05, + "loss": 0.3222, + "step": 14072 + }, + { + "epoch": 1.15, + "learning_rate": 1.2354954367666232e-05, + "loss": 0.2925, + "step": 14073 + }, + { + "epoch": 1.15, + "learning_rate": 1.2354411125597568e-05, + "loss": 0.3387, + "step": 14074 + }, + { + "epoch": 1.15, + "learning_rate": 1.23538678835289e-05, + "loss": 0.7644, + "step": 14075 + }, + { + "epoch": 1.15, + "learning_rate": 1.2353324641460236e-05, + "loss": 0.1802, + "step": 14076 + }, + { + "epoch": 1.15, + "learning_rate": 1.2352781399391569e-05, + "loss": 0.4967, + "step": 14077 + }, + { + "epoch": 1.15, + "learning_rate": 1.2352238157322905e-05, + "loss": 0.3885, + "step": 14078 + }, + { + "epoch": 1.15, + "learning_rate": 1.2351694915254237e-05, + "loss": 0.2639, + "step": 14079 + }, + { + "epoch": 1.15, + "learning_rate": 1.2351151673185573e-05, + "loss": 0.5668, + "step": 14080 + }, + { + "epoch": 1.15, + "learning_rate": 1.2350608431116906e-05, + "loss": 0.3538, + "step": 14081 + }, + { + "epoch": 1.15, + "learning_rate": 1.2350065189048241e-05, + "loss": 0.6431, + "step": 14082 + }, + { + "epoch": 1.15, + "learning_rate": 1.2349521946979574e-05, + "loss": 0.3021, + "step": 14083 + }, + { + "epoch": 1.15, + "learning_rate": 1.234897870491091e-05, + "loss": 0.2017, + "step": 14084 + }, + { + "epoch": 1.15, + "learning_rate": 1.2348435462842242e-05, + "loss": 0.4303, + "step": 14085 + }, + { + "epoch": 1.15, + "learning_rate": 1.2347892220773578e-05, + "loss": 0.1892, + "step": 14086 + }, + { + "epoch": 1.15, + "learning_rate": 1.2347348978704911e-05, + "loss": 0.2093, + "step": 14087 + }, + { + "epoch": 1.15, + "learning_rate": 1.2346805736636247e-05, + "loss": 0.3613, + "step": 14088 + }, + { + "epoch": 1.15, + "learning_rate": 1.234626249456758e-05, + "loss": 0.3428, + "step": 14089 + }, + { + "epoch": 1.15, + "learning_rate": 1.2345719252498915e-05, + "loss": 0.477, + "step": 14090 + }, + { + "epoch": 1.15, + "learning_rate": 1.234517601043025e-05, + "loss": 0.2751, + "step": 14091 + }, + { + "epoch": 1.15, + "learning_rate": 1.2344632768361582e-05, + "loss": 0.4622, + "step": 14092 + }, + { + "epoch": 1.15, + "learning_rate": 1.2344089526292918e-05, + "loss": 0.1771, + "step": 14093 + }, + { + "epoch": 1.15, + "learning_rate": 1.234354628422425e-05, + "loss": 0.2195, + "step": 14094 + }, + { + "epoch": 1.15, + "learning_rate": 1.2343003042155586e-05, + "loss": 0.1946, + "step": 14095 + }, + { + "epoch": 1.15, + "learning_rate": 1.2342459800086919e-05, + "loss": 0.3234, + "step": 14096 + }, + { + "epoch": 1.15, + "learning_rate": 1.2341916558018255e-05, + "loss": 0.7479, + "step": 14097 + }, + { + "epoch": 1.15, + "learning_rate": 1.2341373315949587e-05, + "loss": 0.1988, + "step": 14098 + }, + { + "epoch": 1.15, + "learning_rate": 1.2340830073880923e-05, + "loss": 0.2414, + "step": 14099 + }, + { + "epoch": 1.15, + "learning_rate": 1.2340286831812256e-05, + "loss": 0.2892, + "step": 14100 + }, + { + "epoch": 1.15, + "learning_rate": 1.2339743589743592e-05, + "loss": 0.3999, + "step": 14101 + }, + { + "epoch": 1.15, + "learning_rate": 1.2339200347674924e-05, + "loss": 0.1782, + "step": 14102 + }, + { + "epoch": 1.15, + "learning_rate": 1.233865710560626e-05, + "loss": 0.4343, + "step": 14103 + }, + { + "epoch": 1.15, + "learning_rate": 1.2338113863537593e-05, + "loss": 0.261, + "step": 14104 + }, + { + "epoch": 1.15, + "learning_rate": 1.2337570621468929e-05, + "loss": 0.4601, + "step": 14105 + }, + { + "epoch": 1.15, + "learning_rate": 1.2337027379400261e-05, + "loss": 0.2933, + "step": 14106 + }, + { + "epoch": 1.15, + "learning_rate": 1.2336484137331597e-05, + "loss": 0.2593, + "step": 14107 + }, + { + "epoch": 1.15, + "learning_rate": 1.233594089526293e-05, + "loss": 0.4314, + "step": 14108 + }, + { + "epoch": 1.15, + "learning_rate": 1.2335397653194266e-05, + "loss": 0.3159, + "step": 14109 + }, + { + "epoch": 1.15, + "learning_rate": 1.2334854411125598e-05, + "loss": 0.2602, + "step": 14110 + }, + { + "epoch": 1.15, + "learning_rate": 1.2334311169056932e-05, + "loss": 0.607, + "step": 14111 + }, + { + "epoch": 1.15, + "learning_rate": 1.2333767926988267e-05, + "loss": 0.3198, + "step": 14112 + }, + { + "epoch": 1.15, + "learning_rate": 1.2333224684919601e-05, + "loss": 0.2379, + "step": 14113 + }, + { + "epoch": 1.15, + "learning_rate": 1.2332681442850935e-05, + "loss": 0.3158, + "step": 14114 + }, + { + "epoch": 1.15, + "learning_rate": 1.233213820078227e-05, + "loss": 0.5481, + "step": 14115 + }, + { + "epoch": 1.15, + "learning_rate": 1.2331594958713604e-05, + "loss": 0.3149, + "step": 14116 + }, + { + "epoch": 1.15, + "learning_rate": 1.2331051716644938e-05, + "loss": 0.3992, + "step": 14117 + }, + { + "epoch": 1.15, + "learning_rate": 1.2330508474576272e-05, + "loss": 0.3073, + "step": 14118 + }, + { + "epoch": 1.15, + "learning_rate": 1.2329965232507606e-05, + "loss": 0.2157, + "step": 14119 + }, + { + "epoch": 1.15, + "learning_rate": 1.232942199043894e-05, + "loss": 0.3809, + "step": 14120 + }, + { + "epoch": 1.15, + "learning_rate": 1.2328878748370275e-05, + "loss": 0.3055, + "step": 14121 + }, + { + "epoch": 1.15, + "learning_rate": 1.2328335506301609e-05, + "loss": 0.4083, + "step": 14122 + }, + { + "epoch": 1.15, + "learning_rate": 1.2327792264232943e-05, + "loss": 0.2769, + "step": 14123 + }, + { + "epoch": 1.15, + "learning_rate": 1.2327249022164277e-05, + "loss": 0.3442, + "step": 14124 + }, + { + "epoch": 1.15, + "learning_rate": 1.2326705780095612e-05, + "loss": 0.6269, + "step": 14125 + }, + { + "epoch": 1.15, + "learning_rate": 1.2326162538026946e-05, + "loss": 0.6341, + "step": 14126 + }, + { + "epoch": 1.15, + "learning_rate": 1.232561929595828e-05, + "loss": 0.2654, + "step": 14127 + }, + { + "epoch": 1.15, + "learning_rate": 1.2325076053889616e-05, + "loss": 0.5329, + "step": 14128 + }, + { + "epoch": 1.15, + "learning_rate": 1.2324532811820949e-05, + "loss": 0.3177, + "step": 14129 + }, + { + "epoch": 1.15, + "learning_rate": 1.2323989569752281e-05, + "loss": 0.1541, + "step": 14130 + }, + { + "epoch": 1.15, + "learning_rate": 1.2323446327683617e-05, + "loss": 0.2752, + "step": 14131 + }, + { + "epoch": 1.15, + "learning_rate": 1.232290308561495e-05, + "loss": 0.4177, + "step": 14132 + }, + { + "epoch": 1.15, + "learning_rate": 1.2322359843546286e-05, + "loss": 0.1583, + "step": 14133 + }, + { + "epoch": 1.15, + "learning_rate": 1.2321816601477618e-05, + "loss": 0.1941, + "step": 14134 + }, + { + "epoch": 1.15, + "learning_rate": 1.2321273359408954e-05, + "loss": 0.3058, + "step": 14135 + }, + { + "epoch": 1.15, + "learning_rate": 1.2320730117340287e-05, + "loss": 0.2973, + "step": 14136 + }, + { + "epoch": 1.15, + "learning_rate": 1.2320186875271622e-05, + "loss": 0.6349, + "step": 14137 + }, + { + "epoch": 1.15, + "learning_rate": 1.2319643633202955e-05, + "loss": 0.6061, + "step": 14138 + }, + { + "epoch": 1.15, + "learning_rate": 1.2319100391134291e-05, + "loss": 0.2151, + "step": 14139 + }, + { + "epoch": 1.15, + "learning_rate": 1.2318557149065623e-05, + "loss": 0.2664, + "step": 14140 + }, + { + "epoch": 1.15, + "learning_rate": 1.231801390699696e-05, + "loss": 0.3498, + "step": 14141 + }, + { + "epoch": 1.15, + "learning_rate": 1.2317470664928292e-05, + "loss": 0.2496, + "step": 14142 + }, + { + "epoch": 1.15, + "learning_rate": 1.2316927422859628e-05, + "loss": 0.1906, + "step": 14143 + }, + { + "epoch": 1.15, + "learning_rate": 1.2316384180790962e-05, + "loss": 0.155, + "step": 14144 + }, + { + "epoch": 1.15, + "learning_rate": 1.2315840938722296e-05, + "loss": 0.4367, + "step": 14145 + }, + { + "epoch": 1.15, + "learning_rate": 1.231529769665363e-05, + "loss": 0.1707, + "step": 14146 + }, + { + "epoch": 1.15, + "learning_rate": 1.2314754454584965e-05, + "loss": 0.5454, + "step": 14147 + }, + { + "epoch": 1.15, + "learning_rate": 1.2314211212516299e-05, + "loss": 0.2071, + "step": 14148 + }, + { + "epoch": 1.15, + "learning_rate": 1.2313667970447632e-05, + "loss": 0.2516, + "step": 14149 + }, + { + "epoch": 1.15, + "learning_rate": 1.2313124728378967e-05, + "loss": 0.1416, + "step": 14150 + }, + { + "epoch": 1.15, + "learning_rate": 1.23125814863103e-05, + "loss": 0.4051, + "step": 14151 + }, + { + "epoch": 1.15, + "learning_rate": 1.2312038244241636e-05, + "loss": 0.3036, + "step": 14152 + }, + { + "epoch": 1.15, + "learning_rate": 1.2311495002172968e-05, + "loss": 0.2937, + "step": 14153 + }, + { + "epoch": 1.15, + "learning_rate": 1.2310951760104304e-05, + "loss": 0.2404, + "step": 14154 + }, + { + "epoch": 1.15, + "learning_rate": 1.2310408518035637e-05, + "loss": 0.4343, + "step": 14155 + }, + { + "epoch": 1.15, + "learning_rate": 1.2309865275966973e-05, + "loss": 0.6575, + "step": 14156 + }, + { + "epoch": 1.15, + "learning_rate": 1.2309322033898305e-05, + "loss": 0.2413, + "step": 14157 + }, + { + "epoch": 1.15, + "learning_rate": 1.2308778791829641e-05, + "loss": 0.4628, + "step": 14158 + }, + { + "epoch": 1.15, + "learning_rate": 1.2308235549760974e-05, + "loss": 0.543, + "step": 14159 + }, + { + "epoch": 1.15, + "learning_rate": 1.230769230769231e-05, + "loss": 0.1859, + "step": 14160 + }, + { + "epoch": 1.15, + "learning_rate": 1.2307149065623642e-05, + "loss": 0.2411, + "step": 14161 + }, + { + "epoch": 1.15, + "learning_rate": 1.2306605823554978e-05, + "loss": 0.256, + "step": 14162 + }, + { + "epoch": 1.15, + "learning_rate": 1.230606258148631e-05, + "loss": 0.4248, + "step": 14163 + }, + { + "epoch": 1.15, + "learning_rate": 1.2305519339417647e-05, + "loss": 0.3176, + "step": 14164 + }, + { + "epoch": 1.15, + "learning_rate": 1.230497609734898e-05, + "loss": 0.5248, + "step": 14165 + }, + { + "epoch": 1.15, + "learning_rate": 1.2304432855280315e-05, + "loss": 0.3019, + "step": 14166 + }, + { + "epoch": 1.15, + "learning_rate": 1.2303889613211648e-05, + "loss": 0.4449, + "step": 14167 + }, + { + "epoch": 1.15, + "learning_rate": 1.2303346371142982e-05, + "loss": 0.2294, + "step": 14168 + }, + { + "epoch": 1.15, + "learning_rate": 1.2302803129074316e-05, + "loss": 0.3163, + "step": 14169 + }, + { + "epoch": 1.15, + "learning_rate": 1.230225988700565e-05, + "loss": 0.2165, + "step": 14170 + }, + { + "epoch": 1.15, + "learning_rate": 1.2301716644936985e-05, + "loss": 0.2873, + "step": 14171 + }, + { + "epoch": 1.15, + "learning_rate": 1.2301173402868319e-05, + "loss": 0.4518, + "step": 14172 + }, + { + "epoch": 1.15, + "learning_rate": 1.2300630160799653e-05, + "loss": 0.2336, + "step": 14173 + }, + { + "epoch": 1.15, + "learning_rate": 1.2300086918730987e-05, + "loss": 0.2057, + "step": 14174 + }, + { + "epoch": 1.16, + "learning_rate": 1.2299543676662322e-05, + "loss": 0.2809, + "step": 14175 + }, + { + "epoch": 1.16, + "learning_rate": 1.2299000434593656e-05, + "loss": 0.2648, + "step": 14176 + }, + { + "epoch": 1.16, + "learning_rate": 1.229845719252499e-05, + "loss": 0.4369, + "step": 14177 + }, + { + "epoch": 1.16, + "learning_rate": 1.2297913950456324e-05, + "loss": 0.3301, + "step": 14178 + }, + { + "epoch": 1.16, + "learning_rate": 1.2297370708387658e-05, + "loss": 0.3082, + "step": 14179 + }, + { + "epoch": 1.16, + "learning_rate": 1.2296827466318993e-05, + "loss": 0.2744, + "step": 14180 + }, + { + "epoch": 1.16, + "learning_rate": 1.2296284224250329e-05, + "loss": 0.6222, + "step": 14181 + }, + { + "epoch": 1.16, + "learning_rate": 1.2295740982181661e-05, + "loss": 0.2058, + "step": 14182 + }, + { + "epoch": 1.16, + "learning_rate": 1.2295197740112997e-05, + "loss": 0.3442, + "step": 14183 + }, + { + "epoch": 1.16, + "learning_rate": 1.229465449804433e-05, + "loss": 0.1629, + "step": 14184 + }, + { + "epoch": 1.16, + "learning_rate": 1.2294111255975666e-05, + "loss": 0.2167, + "step": 14185 + }, + { + "epoch": 1.16, + "learning_rate": 1.2293568013906998e-05, + "loss": 0.2555, + "step": 14186 + }, + { + "epoch": 1.16, + "learning_rate": 1.229302477183833e-05, + "loss": 0.3762, + "step": 14187 + }, + { + "epoch": 1.16, + "learning_rate": 1.2292481529769667e-05, + "loss": 0.3386, + "step": 14188 + }, + { + "epoch": 1.16, + "learning_rate": 1.2291938287700999e-05, + "loss": 0.3705, + "step": 14189 + }, + { + "epoch": 1.16, + "learning_rate": 1.2291395045632335e-05, + "loss": 0.2841, + "step": 14190 + }, + { + "epoch": 1.16, + "learning_rate": 1.2290851803563668e-05, + "loss": 0.4286, + "step": 14191 + }, + { + "epoch": 1.16, + "learning_rate": 1.2290308561495003e-05, + "loss": 0.2814, + "step": 14192 + }, + { + "epoch": 1.16, + "learning_rate": 1.2289765319426336e-05, + "loss": 0.2919, + "step": 14193 + }, + { + "epoch": 1.16, + "learning_rate": 1.2289222077357672e-05, + "loss": 0.7684, + "step": 14194 + }, + { + "epoch": 1.16, + "learning_rate": 1.2288678835289004e-05, + "loss": 0.4531, + "step": 14195 + }, + { + "epoch": 1.16, + "learning_rate": 1.228813559322034e-05, + "loss": 0.7342, + "step": 14196 + }, + { + "epoch": 1.16, + "learning_rate": 1.2287592351151673e-05, + "loss": 0.2587, + "step": 14197 + }, + { + "epoch": 1.16, + "learning_rate": 1.2287049109083009e-05, + "loss": 0.7797, + "step": 14198 + }, + { + "epoch": 1.16, + "learning_rate": 1.2286505867014343e-05, + "loss": 0.3135, + "step": 14199 + }, + { + "epoch": 1.16, + "learning_rate": 1.2285962624945677e-05, + "loss": 0.1404, + "step": 14200 + }, + { + "epoch": 1.16, + "learning_rate": 1.2285419382877011e-05, + "loss": 0.2584, + "step": 14201 + }, + { + "epoch": 1.16, + "learning_rate": 1.2284876140808346e-05, + "loss": 0.2756, + "step": 14202 + }, + { + "epoch": 1.16, + "learning_rate": 1.228433289873968e-05, + "loss": 0.2841, + "step": 14203 + }, + { + "epoch": 1.16, + "learning_rate": 1.2283789656671014e-05, + "loss": 0.4176, + "step": 14204 + }, + { + "epoch": 1.16, + "learning_rate": 1.2283246414602348e-05, + "loss": 0.2865, + "step": 14205 + }, + { + "epoch": 1.16, + "learning_rate": 1.2282703172533681e-05, + "loss": 0.4381, + "step": 14206 + }, + { + "epoch": 1.16, + "learning_rate": 1.2282159930465017e-05, + "loss": 0.1867, + "step": 14207 + }, + { + "epoch": 1.16, + "learning_rate": 1.228161668839635e-05, + "loss": 0.2851, + "step": 14208 + }, + { + "epoch": 1.16, + "learning_rate": 1.2281073446327685e-05, + "loss": 0.3487, + "step": 14209 + }, + { + "epoch": 1.16, + "learning_rate": 1.2280530204259018e-05, + "loss": 0.5288, + "step": 14210 + }, + { + "epoch": 1.16, + "learning_rate": 1.2279986962190354e-05, + "loss": 0.3405, + "step": 14211 + }, + { + "epoch": 1.16, + "learning_rate": 1.2279443720121686e-05, + "loss": 0.3152, + "step": 14212 + }, + { + "epoch": 1.16, + "learning_rate": 1.2278900478053022e-05, + "loss": 0.2758, + "step": 14213 + }, + { + "epoch": 1.16, + "learning_rate": 1.2278357235984355e-05, + "loss": 0.3452, + "step": 14214 + }, + { + "epoch": 1.16, + "learning_rate": 1.227781399391569e-05, + "loss": 0.3579, + "step": 14215 + }, + { + "epoch": 1.16, + "learning_rate": 1.2277270751847023e-05, + "loss": 0.3651, + "step": 14216 + }, + { + "epoch": 1.16, + "learning_rate": 1.227672750977836e-05, + "loss": 0.4178, + "step": 14217 + }, + { + "epoch": 1.16, + "learning_rate": 1.2276184267709692e-05, + "loss": 0.4661, + "step": 14218 + }, + { + "epoch": 1.16, + "learning_rate": 1.2275641025641028e-05, + "loss": 0.1506, + "step": 14219 + }, + { + "epoch": 1.16, + "learning_rate": 1.227509778357236e-05, + "loss": 0.4702, + "step": 14220 + }, + { + "epoch": 1.16, + "learning_rate": 1.2274554541503696e-05, + "loss": 0.2354, + "step": 14221 + }, + { + "epoch": 1.16, + "learning_rate": 1.2274011299435029e-05, + "loss": 0.5377, + "step": 14222 + }, + { + "epoch": 1.16, + "learning_rate": 1.2273468057366365e-05, + "loss": 0.244, + "step": 14223 + }, + { + "epoch": 1.16, + "learning_rate": 1.2272924815297697e-05, + "loss": 0.2678, + "step": 14224 + }, + { + "epoch": 1.16, + "learning_rate": 1.2272381573229031e-05, + "loss": 0.2813, + "step": 14225 + }, + { + "epoch": 1.16, + "learning_rate": 1.2271838331160366e-05, + "loss": 0.3142, + "step": 14226 + }, + { + "epoch": 1.16, + "learning_rate": 1.22712950890917e-05, + "loss": 0.4122, + "step": 14227 + }, + { + "epoch": 1.16, + "learning_rate": 1.2270751847023034e-05, + "loss": 0.3229, + "step": 14228 + }, + { + "epoch": 1.16, + "learning_rate": 1.2270208604954368e-05, + "loss": 0.426, + "step": 14229 + }, + { + "epoch": 1.16, + "learning_rate": 1.2269665362885702e-05, + "loss": 0.3657, + "step": 14230 + }, + { + "epoch": 1.16, + "learning_rate": 1.2269122120817037e-05, + "loss": 0.7028, + "step": 14231 + }, + { + "epoch": 1.16, + "learning_rate": 1.2268578878748371e-05, + "loss": 0.3171, + "step": 14232 + }, + { + "epoch": 1.16, + "learning_rate": 1.2268035636679705e-05, + "loss": 0.3779, + "step": 14233 + }, + { + "epoch": 1.16, + "learning_rate": 1.226749239461104e-05, + "loss": 0.2002, + "step": 14234 + }, + { + "epoch": 1.16, + "learning_rate": 1.2266949152542374e-05, + "loss": 0.4203, + "step": 14235 + }, + { + "epoch": 1.16, + "learning_rate": 1.226640591047371e-05, + "loss": 0.2771, + "step": 14236 + }, + { + "epoch": 1.16, + "learning_rate": 1.2265862668405042e-05, + "loss": 0.1639, + "step": 14237 + }, + { + "epoch": 1.16, + "learning_rate": 1.2265319426336378e-05, + "loss": 0.2316, + "step": 14238 + }, + { + "epoch": 1.16, + "learning_rate": 1.226477618426771e-05, + "loss": 0.258, + "step": 14239 + }, + { + "epoch": 1.16, + "learning_rate": 1.2264232942199046e-05, + "loss": 0.2563, + "step": 14240 + }, + { + "epoch": 1.16, + "learning_rate": 1.2263689700130379e-05, + "loss": 0.3493, + "step": 14241 + }, + { + "epoch": 1.16, + "learning_rate": 1.2263146458061715e-05, + "loss": 0.482, + "step": 14242 + }, + { + "epoch": 1.16, + "learning_rate": 1.2262603215993047e-05, + "loss": 0.4415, + "step": 14243 + }, + { + "epoch": 1.16, + "learning_rate": 1.226205997392438e-05, + "loss": 0.5313, + "step": 14244 + }, + { + "epoch": 1.16, + "learning_rate": 1.2261516731855716e-05, + "loss": 0.2055, + "step": 14245 + }, + { + "epoch": 1.16, + "learning_rate": 1.2260973489787048e-05, + "loss": 0.1309, + "step": 14246 + }, + { + "epoch": 1.16, + "learning_rate": 1.2260430247718384e-05, + "loss": 0.6184, + "step": 14247 + }, + { + "epoch": 1.16, + "learning_rate": 1.2259887005649717e-05, + "loss": 0.26, + "step": 14248 + }, + { + "epoch": 1.16, + "learning_rate": 1.2259343763581053e-05, + "loss": 0.2933, + "step": 14249 + }, + { + "epoch": 1.16, + "learning_rate": 1.2258800521512385e-05, + "loss": 0.2848, + "step": 14250 + }, + { + "epoch": 1.16, + "eval_accuracy": 0.8356597045338767, + "eval_loss": 0.44301968812942505, + "eval_runtime": 22.3747, + "eval_samples_per_second": 438.665, + "eval_steps_per_second": 3.441, + "step": 14250 + }, + { + "epoch": 1.16, + "learning_rate": 1.2258257279443721e-05, + "loss": 0.3087, + "step": 14251 + }, + { + "epoch": 1.16, + "learning_rate": 1.2257714037375056e-05, + "loss": 0.4654, + "step": 14252 + }, + { + "epoch": 1.16, + "learning_rate": 1.225717079530639e-05, + "loss": 0.512, + "step": 14253 + }, + { + "epoch": 1.16, + "learning_rate": 1.2256627553237724e-05, + "loss": 0.308, + "step": 14254 + }, + { + "epoch": 1.16, + "learning_rate": 1.2256084311169058e-05, + "loss": 0.2757, + "step": 14255 + }, + { + "epoch": 1.16, + "learning_rate": 1.2255541069100392e-05, + "loss": 0.6415, + "step": 14256 + }, + { + "epoch": 1.16, + "learning_rate": 1.2254997827031727e-05, + "loss": 0.4026, + "step": 14257 + }, + { + "epoch": 1.16, + "learning_rate": 1.2254454584963061e-05, + "loss": 0.3519, + "step": 14258 + }, + { + "epoch": 1.16, + "learning_rate": 1.2253911342894395e-05, + "loss": 0.1184, + "step": 14259 + }, + { + "epoch": 1.16, + "learning_rate": 1.225336810082573e-05, + "loss": 0.3558, + "step": 14260 + }, + { + "epoch": 1.16, + "learning_rate": 1.2252824858757064e-05, + "loss": 0.3406, + "step": 14261 + }, + { + "epoch": 1.16, + "learning_rate": 1.2252281616688398e-05, + "loss": 0.239, + "step": 14262 + }, + { + "epoch": 1.16, + "learning_rate": 1.225173837461973e-05, + "loss": 0.3247, + "step": 14263 + }, + { + "epoch": 1.16, + "learning_rate": 1.2251195132551066e-05, + "loss": 0.3901, + "step": 14264 + }, + { + "epoch": 1.16, + "learning_rate": 1.2250651890482399e-05, + "loss": 0.5435, + "step": 14265 + }, + { + "epoch": 1.16, + "learning_rate": 1.2250108648413735e-05, + "loss": 0.2881, + "step": 14266 + }, + { + "epoch": 1.16, + "learning_rate": 1.2249565406345067e-05, + "loss": 0.5678, + "step": 14267 + }, + { + "epoch": 1.16, + "learning_rate": 1.2249022164276403e-05, + "loss": 0.4302, + "step": 14268 + }, + { + "epoch": 1.16, + "learning_rate": 1.2248478922207736e-05, + "loss": 0.1943, + "step": 14269 + }, + { + "epoch": 1.16, + "learning_rate": 1.2247935680139072e-05, + "loss": 0.4288, + "step": 14270 + }, + { + "epoch": 1.16, + "learning_rate": 1.2247392438070404e-05, + "loss": 0.3892, + "step": 14271 + }, + { + "epoch": 1.16, + "learning_rate": 1.224684919600174e-05, + "loss": 0.3748, + "step": 14272 + }, + { + "epoch": 1.16, + "learning_rate": 1.2246305953933073e-05, + "loss": 0.2895, + "step": 14273 + }, + { + "epoch": 1.16, + "learning_rate": 1.2245762711864409e-05, + "loss": 0.2344, + "step": 14274 + }, + { + "epoch": 1.16, + "learning_rate": 1.2245219469795741e-05, + "loss": 0.215, + "step": 14275 + }, + { + "epoch": 1.16, + "learning_rate": 1.2244676227727077e-05, + "loss": 0.2193, + "step": 14276 + }, + { + "epoch": 1.16, + "learning_rate": 1.224413298565841e-05, + "loss": 0.4304, + "step": 14277 + }, + { + "epoch": 1.16, + "learning_rate": 1.2243589743589746e-05, + "loss": 0.4562, + "step": 14278 + }, + { + "epoch": 1.16, + "learning_rate": 1.2243046501521078e-05, + "loss": 0.4916, + "step": 14279 + }, + { + "epoch": 1.16, + "learning_rate": 1.2242503259452414e-05, + "loss": 0.2342, + "step": 14280 + }, + { + "epoch": 1.16, + "learning_rate": 1.2241960017383747e-05, + "loss": 0.2769, + "step": 14281 + }, + { + "epoch": 1.16, + "learning_rate": 1.224141677531508e-05, + "loss": 0.2636, + "step": 14282 + }, + { + "epoch": 1.16, + "learning_rate": 1.2240873533246415e-05, + "loss": 0.2146, + "step": 14283 + }, + { + "epoch": 1.16, + "learning_rate": 1.224033029117775e-05, + "loss": 0.2913, + "step": 14284 + }, + { + "epoch": 1.16, + "learning_rate": 1.2239787049109083e-05, + "loss": 0.5544, + "step": 14285 + }, + { + "epoch": 1.16, + "learning_rate": 1.2239243807040418e-05, + "loss": 0.3633, + "step": 14286 + }, + { + "epoch": 1.16, + "learning_rate": 1.2238700564971752e-05, + "loss": 0.3214, + "step": 14287 + }, + { + "epoch": 1.16, + "learning_rate": 1.2238157322903086e-05, + "loss": 0.1983, + "step": 14288 + }, + { + "epoch": 1.16, + "learning_rate": 1.2237614080834422e-05, + "loss": 0.3733, + "step": 14289 + }, + { + "epoch": 1.16, + "learning_rate": 1.2237070838765755e-05, + "loss": 0.1209, + "step": 14290 + }, + { + "epoch": 1.16, + "learning_rate": 1.223652759669709e-05, + "loss": 0.4283, + "step": 14291 + }, + { + "epoch": 1.16, + "learning_rate": 1.2235984354628423e-05, + "loss": 0.5191, + "step": 14292 + }, + { + "epoch": 1.16, + "learning_rate": 1.2235441112559759e-05, + "loss": 0.2364, + "step": 14293 + }, + { + "epoch": 1.16, + "learning_rate": 1.2234897870491092e-05, + "loss": 0.4197, + "step": 14294 + }, + { + "epoch": 1.16, + "learning_rate": 1.2234354628422427e-05, + "loss": 0.8341, + "step": 14295 + }, + { + "epoch": 1.16, + "learning_rate": 1.223381138635376e-05, + "loss": 0.3593, + "step": 14296 + }, + { + "epoch": 1.17, + "learning_rate": 1.2233268144285096e-05, + "loss": 0.2989, + "step": 14297 + }, + { + "epoch": 1.17, + "learning_rate": 1.2232724902216428e-05, + "loss": 0.1822, + "step": 14298 + }, + { + "epoch": 1.17, + "learning_rate": 1.2232181660147764e-05, + "loss": 0.4375, + "step": 14299 + }, + { + "epoch": 1.17, + "learning_rate": 1.2231638418079097e-05, + "loss": 0.3615, + "step": 14300 + }, + { + "epoch": 1.17, + "learning_rate": 1.223109517601043e-05, + "loss": 0.1713, + "step": 14301 + }, + { + "epoch": 1.17, + "learning_rate": 1.2230551933941765e-05, + "loss": 0.2337, + "step": 14302 + }, + { + "epoch": 1.17, + "learning_rate": 1.2230008691873098e-05, + "loss": 0.3422, + "step": 14303 + }, + { + "epoch": 1.17, + "learning_rate": 1.2229465449804434e-05, + "loss": 0.2676, + "step": 14304 + }, + { + "epoch": 1.17, + "learning_rate": 1.2228922207735766e-05, + "loss": 0.3298, + "step": 14305 + }, + { + "epoch": 1.17, + "learning_rate": 1.2228378965667102e-05, + "loss": 0.2838, + "step": 14306 + }, + { + "epoch": 1.17, + "learning_rate": 1.2227835723598437e-05, + "loss": 0.3155, + "step": 14307 + }, + { + "epoch": 1.17, + "learning_rate": 1.222729248152977e-05, + "loss": 0.4282, + "step": 14308 + }, + { + "epoch": 1.17, + "learning_rate": 1.2226749239461105e-05, + "loss": 0.1541, + "step": 14309 + }, + { + "epoch": 1.17, + "learning_rate": 1.222620599739244e-05, + "loss": 0.3785, + "step": 14310 + }, + { + "epoch": 1.17, + "learning_rate": 1.2225662755323773e-05, + "loss": 0.2508, + "step": 14311 + }, + { + "epoch": 1.17, + "learning_rate": 1.2225119513255108e-05, + "loss": 0.2214, + "step": 14312 + }, + { + "epoch": 1.17, + "learning_rate": 1.2224576271186442e-05, + "loss": 0.2065, + "step": 14313 + }, + { + "epoch": 1.17, + "learning_rate": 1.2224033029117776e-05, + "loss": 0.2163, + "step": 14314 + }, + { + "epoch": 1.17, + "learning_rate": 1.222348978704911e-05, + "loss": 0.3439, + "step": 14315 + }, + { + "epoch": 1.17, + "learning_rate": 1.2222946544980445e-05, + "loss": 0.2528, + "step": 14316 + }, + { + "epoch": 1.17, + "learning_rate": 1.2222403302911779e-05, + "loss": 0.2583, + "step": 14317 + }, + { + "epoch": 1.17, + "learning_rate": 1.2221860060843113e-05, + "loss": 0.4289, + "step": 14318 + }, + { + "epoch": 1.17, + "learning_rate": 1.2221316818774447e-05, + "loss": 0.3498, + "step": 14319 + }, + { + "epoch": 1.17, + "learning_rate": 1.222077357670578e-05, + "loss": 0.2474, + "step": 14320 + }, + { + "epoch": 1.17, + "learning_rate": 1.2220230334637116e-05, + "loss": 0.2306, + "step": 14321 + }, + { + "epoch": 1.17, + "learning_rate": 1.2219687092568448e-05, + "loss": 0.267, + "step": 14322 + }, + { + "epoch": 1.17, + "learning_rate": 1.2219143850499784e-05, + "loss": 0.1473, + "step": 14323 + }, + { + "epoch": 1.17, + "learning_rate": 1.2218600608431117e-05, + "loss": 0.2807, + "step": 14324 + }, + { + "epoch": 1.17, + "learning_rate": 1.2218057366362453e-05, + "loss": 0.3482, + "step": 14325 + }, + { + "epoch": 1.17, + "learning_rate": 1.2217514124293785e-05, + "loss": 0.2519, + "step": 14326 + }, + { + "epoch": 1.17, + "learning_rate": 1.2216970882225121e-05, + "loss": 0.5185, + "step": 14327 + }, + { + "epoch": 1.17, + "learning_rate": 1.2216427640156454e-05, + "loss": 0.3585, + "step": 14328 + }, + { + "epoch": 1.17, + "learning_rate": 1.221588439808779e-05, + "loss": 0.4704, + "step": 14329 + }, + { + "epoch": 1.17, + "learning_rate": 1.2215341156019122e-05, + "loss": 0.1533, + "step": 14330 + }, + { + "epoch": 1.17, + "learning_rate": 1.2214797913950458e-05, + "loss": 0.2841, + "step": 14331 + }, + { + "epoch": 1.17, + "learning_rate": 1.221425467188179e-05, + "loss": 0.5065, + "step": 14332 + }, + { + "epoch": 1.17, + "learning_rate": 1.2213711429813127e-05, + "loss": 0.4718, + "step": 14333 + }, + { + "epoch": 1.17, + "learning_rate": 1.2213168187744459e-05, + "loss": 0.38, + "step": 14334 + }, + { + "epoch": 1.17, + "learning_rate": 1.2212624945675795e-05, + "loss": 0.6042, + "step": 14335 + }, + { + "epoch": 1.17, + "learning_rate": 1.2212081703607128e-05, + "loss": 0.2531, + "step": 14336 + }, + { + "epoch": 1.17, + "learning_rate": 1.2211538461538463e-05, + "loss": 0.2176, + "step": 14337 + }, + { + "epoch": 1.17, + "learning_rate": 1.2210995219469796e-05, + "loss": 0.3866, + "step": 14338 + }, + { + "epoch": 1.17, + "learning_rate": 1.221045197740113e-05, + "loss": 0.2947, + "step": 14339 + }, + { + "epoch": 1.17, + "learning_rate": 1.2209908735332464e-05, + "loss": 0.2231, + "step": 14340 + }, + { + "epoch": 1.17, + "learning_rate": 1.2209365493263799e-05, + "loss": 0.3032, + "step": 14341 + }, + { + "epoch": 1.17, + "learning_rate": 1.2208822251195133e-05, + "loss": 0.4504, + "step": 14342 + }, + { + "epoch": 1.17, + "learning_rate": 1.2208279009126467e-05, + "loss": 0.3234, + "step": 14343 + }, + { + "epoch": 1.17, + "learning_rate": 1.2207735767057803e-05, + "loss": 0.4188, + "step": 14344 + }, + { + "epoch": 1.17, + "learning_rate": 1.2207192524989136e-05, + "loss": 0.3645, + "step": 14345 + }, + { + "epoch": 1.17, + "learning_rate": 1.2206649282920472e-05, + "loss": 0.266, + "step": 14346 + }, + { + "epoch": 1.17, + "learning_rate": 1.2206106040851804e-05, + "loss": 0.2957, + "step": 14347 + }, + { + "epoch": 1.17, + "learning_rate": 1.220556279878314e-05, + "loss": 0.2007, + "step": 14348 + }, + { + "epoch": 1.17, + "learning_rate": 1.2205019556714473e-05, + "loss": 0.3767, + "step": 14349 + }, + { + "epoch": 1.17, + "learning_rate": 1.2204476314645808e-05, + "loss": 0.262, + "step": 14350 + }, + { + "epoch": 1.17, + "learning_rate": 1.2203933072577141e-05, + "loss": 0.4223, + "step": 14351 + }, + { + "epoch": 1.17, + "learning_rate": 1.2203389830508477e-05, + "loss": 0.1841, + "step": 14352 + }, + { + "epoch": 1.17, + "learning_rate": 1.220284658843981e-05, + "loss": 0.3103, + "step": 14353 + }, + { + "epoch": 1.17, + "learning_rate": 1.2202303346371145e-05, + "loss": 0.8159, + "step": 14354 + }, + { + "epoch": 1.17, + "learning_rate": 1.2201760104302478e-05, + "loss": 0.3404, + "step": 14355 + }, + { + "epoch": 1.17, + "learning_rate": 1.2201216862233814e-05, + "loss": 0.386, + "step": 14356 + }, + { + "epoch": 1.17, + "learning_rate": 1.2200673620165146e-05, + "loss": 0.4346, + "step": 14357 + }, + { + "epoch": 1.17, + "learning_rate": 1.2200130378096479e-05, + "loss": 0.3191, + "step": 14358 + }, + { + "epoch": 1.17, + "learning_rate": 1.2199587136027815e-05, + "loss": 0.1722, + "step": 14359 + }, + { + "epoch": 1.17, + "learning_rate": 1.2199043893959149e-05, + "loss": 0.3059, + "step": 14360 + }, + { + "epoch": 1.17, + "learning_rate": 1.2198500651890483e-05, + "loss": 0.4964, + "step": 14361 + }, + { + "epoch": 1.17, + "learning_rate": 1.2197957409821818e-05, + "loss": 0.2971, + "step": 14362 + }, + { + "epoch": 1.17, + "learning_rate": 1.2197414167753152e-05, + "loss": 0.5628, + "step": 14363 + }, + { + "epoch": 1.17, + "learning_rate": 1.2196870925684486e-05, + "loss": 0.2112, + "step": 14364 + }, + { + "epoch": 1.17, + "learning_rate": 1.219632768361582e-05, + "loss": 0.2282, + "step": 14365 + }, + { + "epoch": 1.17, + "learning_rate": 1.2195784441547154e-05, + "loss": 0.2447, + "step": 14366 + }, + { + "epoch": 1.17, + "learning_rate": 1.2195241199478489e-05, + "loss": 0.4441, + "step": 14367 + }, + { + "epoch": 1.17, + "learning_rate": 1.2194697957409823e-05, + "loss": 0.2024, + "step": 14368 + }, + { + "epoch": 1.17, + "learning_rate": 1.2194154715341157e-05, + "loss": 0.3454, + "step": 14369 + }, + { + "epoch": 1.17, + "learning_rate": 1.2193611473272491e-05, + "loss": 0.3276, + "step": 14370 + }, + { + "epoch": 1.17, + "learning_rate": 1.2193068231203826e-05, + "loss": 0.3712, + "step": 14371 + }, + { + "epoch": 1.17, + "learning_rate": 1.219252498913516e-05, + "loss": 0.2629, + "step": 14372 + }, + { + "epoch": 1.17, + "learning_rate": 1.2191981747066494e-05, + "loss": 0.2774, + "step": 14373 + }, + { + "epoch": 1.17, + "learning_rate": 1.2191438504997828e-05, + "loss": 0.3112, + "step": 14374 + }, + { + "epoch": 1.17, + "learning_rate": 1.2190895262929163e-05, + "loss": 0.4016, + "step": 14375 + }, + { + "epoch": 1.17, + "learning_rate": 1.2190352020860497e-05, + "loss": 0.5801, + "step": 14376 + }, + { + "epoch": 1.17, + "learning_rate": 1.218980877879183e-05, + "loss": 0.2486, + "step": 14377 + }, + { + "epoch": 1.17, + "learning_rate": 1.2189265536723165e-05, + "loss": 0.1391, + "step": 14378 + }, + { + "epoch": 1.17, + "learning_rate": 1.2188722294654498e-05, + "loss": 0.2078, + "step": 14379 + }, + { + "epoch": 1.17, + "learning_rate": 1.2188179052585834e-05, + "loss": 0.4827, + "step": 14380 + }, + { + "epoch": 1.17, + "learning_rate": 1.2187635810517166e-05, + "loss": 0.2658, + "step": 14381 + }, + { + "epoch": 1.17, + "learning_rate": 1.2187092568448502e-05, + "loss": 0.451, + "step": 14382 + }, + { + "epoch": 1.17, + "learning_rate": 1.2186549326379835e-05, + "loss": 0.4492, + "step": 14383 + }, + { + "epoch": 1.17, + "learning_rate": 1.218600608431117e-05, + "loss": 0.2583, + "step": 14384 + }, + { + "epoch": 1.17, + "learning_rate": 1.2185462842242503e-05, + "loss": 0.4572, + "step": 14385 + }, + { + "epoch": 1.17, + "learning_rate": 1.2184919600173839e-05, + "loss": 0.2231, + "step": 14386 + }, + { + "epoch": 1.17, + "learning_rate": 1.2184376358105172e-05, + "loss": 0.1838, + "step": 14387 + }, + { + "epoch": 1.17, + "learning_rate": 1.2183833116036508e-05, + "loss": 0.3352, + "step": 14388 + }, + { + "epoch": 1.17, + "learning_rate": 1.218328987396784e-05, + "loss": 0.4331, + "step": 14389 + }, + { + "epoch": 1.17, + "learning_rate": 1.2182746631899176e-05, + "loss": 0.1733, + "step": 14390 + }, + { + "epoch": 1.17, + "learning_rate": 1.2182203389830509e-05, + "loss": 0.3916, + "step": 14391 + }, + { + "epoch": 1.17, + "learning_rate": 1.2181660147761844e-05, + "loss": 0.8286, + "step": 14392 + }, + { + "epoch": 1.17, + "learning_rate": 1.2181116905693177e-05, + "loss": 0.2706, + "step": 14393 + }, + { + "epoch": 1.17, + "learning_rate": 1.2180573663624513e-05, + "loss": 0.6886, + "step": 14394 + }, + { + "epoch": 1.17, + "learning_rate": 1.2180030421555845e-05, + "loss": 0.3564, + "step": 14395 + }, + { + "epoch": 1.17, + "learning_rate": 1.217948717948718e-05, + "loss": 0.2385, + "step": 14396 + }, + { + "epoch": 1.17, + "learning_rate": 1.2178943937418516e-05, + "loss": 0.2688, + "step": 14397 + }, + { + "epoch": 1.17, + "learning_rate": 1.2178400695349848e-05, + "loss": 0.4258, + "step": 14398 + }, + { + "epoch": 1.17, + "learning_rate": 1.2177857453281184e-05, + "loss": 0.314, + "step": 14399 + }, + { + "epoch": 1.17, + "learning_rate": 1.2177314211212517e-05, + "loss": 0.2559, + "step": 14400 + }, + { + "epoch": 1.17, + "learning_rate": 1.2176770969143853e-05, + "loss": 0.3986, + "step": 14401 + }, + { + "epoch": 1.17, + "learning_rate": 1.2176227727075185e-05, + "loss": 0.2119, + "step": 14402 + }, + { + "epoch": 1.17, + "learning_rate": 1.2175684485006521e-05, + "loss": 0.3604, + "step": 14403 + }, + { + "epoch": 1.17, + "learning_rate": 1.2175141242937854e-05, + "loss": 0.2439, + "step": 14404 + }, + { + "epoch": 1.17, + "learning_rate": 1.217459800086919e-05, + "loss": 0.1184, + "step": 14405 + }, + { + "epoch": 1.17, + "learning_rate": 1.2174054758800522e-05, + "loss": 0.2892, + "step": 14406 + }, + { + "epoch": 1.17, + "learning_rate": 1.2173511516731858e-05, + "loss": 0.2821, + "step": 14407 + }, + { + "epoch": 1.17, + "learning_rate": 1.217296827466319e-05, + "loss": 0.2001, + "step": 14408 + }, + { + "epoch": 1.17, + "learning_rate": 1.2172425032594526e-05, + "loss": 0.5256, + "step": 14409 + }, + { + "epoch": 1.17, + "learning_rate": 1.2171881790525859e-05, + "loss": 0.4035, + "step": 14410 + }, + { + "epoch": 1.17, + "learning_rate": 1.2171338548457195e-05, + "loss": 0.1295, + "step": 14411 + }, + { + "epoch": 1.17, + "learning_rate": 1.2170795306388527e-05, + "loss": 0.5028, + "step": 14412 + }, + { + "epoch": 1.17, + "learning_rate": 1.2170252064319863e-05, + "loss": 0.3632, + "step": 14413 + }, + { + "epoch": 1.17, + "learning_rate": 1.2169708822251196e-05, + "loss": 0.4461, + "step": 14414 + }, + { + "epoch": 1.17, + "learning_rate": 1.216916558018253e-05, + "loss": 0.3272, + "step": 14415 + }, + { + "epoch": 1.17, + "learning_rate": 1.2168622338113864e-05, + "loss": 0.4171, + "step": 14416 + }, + { + "epoch": 1.17, + "learning_rate": 1.2168079096045199e-05, + "loss": 0.5368, + "step": 14417 + }, + { + "epoch": 1.17, + "learning_rate": 1.2167535853976533e-05, + "loss": 0.1667, + "step": 14418 + }, + { + "epoch": 1.17, + "learning_rate": 1.2166992611907867e-05, + "loss": 0.4801, + "step": 14419 + }, + { + "epoch": 1.18, + "learning_rate": 1.2166449369839201e-05, + "loss": 0.6074, + "step": 14420 + }, + { + "epoch": 1.18, + "learning_rate": 1.2165906127770535e-05, + "loss": 0.2446, + "step": 14421 + }, + { + "epoch": 1.18, + "learning_rate": 1.216536288570187e-05, + "loss": 0.4349, + "step": 14422 + }, + { + "epoch": 1.18, + "learning_rate": 1.2164819643633204e-05, + "loss": 0.3238, + "step": 14423 + }, + { + "epoch": 1.18, + "learning_rate": 1.2164276401564538e-05, + "loss": 0.1496, + "step": 14424 + }, + { + "epoch": 1.18, + "learning_rate": 1.2163733159495872e-05, + "loss": 0.4666, + "step": 14425 + }, + { + "epoch": 1.18, + "learning_rate": 1.2163189917427207e-05, + "loss": 0.2941, + "step": 14426 + }, + { + "epoch": 1.18, + "learning_rate": 1.216264667535854e-05, + "loss": 0.3431, + "step": 14427 + }, + { + "epoch": 1.18, + "learning_rate": 1.2162103433289875e-05, + "loss": 0.3049, + "step": 14428 + }, + { + "epoch": 1.18, + "learning_rate": 1.216156019122121e-05, + "loss": 0.3924, + "step": 14429 + }, + { + "epoch": 1.18, + "learning_rate": 1.2161016949152544e-05, + "loss": 0.4749, + "step": 14430 + }, + { + "epoch": 1.18, + "learning_rate": 1.2160473707083878e-05, + "loss": 0.3691, + "step": 14431 + }, + { + "epoch": 1.18, + "learning_rate": 1.2159930465015212e-05, + "loss": 0.1252, + "step": 14432 + }, + { + "epoch": 1.18, + "learning_rate": 1.2159387222946546e-05, + "loss": 0.3113, + "step": 14433 + }, + { + "epoch": 1.18, + "learning_rate": 1.2158843980877879e-05, + "loss": 0.483, + "step": 14434 + }, + { + "epoch": 1.18, + "learning_rate": 1.2158300738809215e-05, + "loss": 0.2496, + "step": 14435 + }, + { + "epoch": 1.18, + "learning_rate": 1.2157757496740547e-05, + "loss": 0.0956, + "step": 14436 + }, + { + "epoch": 1.18, + "learning_rate": 1.2157214254671883e-05, + "loss": 0.3334, + "step": 14437 + }, + { + "epoch": 1.18, + "learning_rate": 1.2156671012603216e-05, + "loss": 0.1832, + "step": 14438 + }, + { + "epoch": 1.18, + "learning_rate": 1.2156127770534552e-05, + "loss": 0.3147, + "step": 14439 + }, + { + "epoch": 1.18, + "learning_rate": 1.2155584528465884e-05, + "loss": 0.1185, + "step": 14440 + }, + { + "epoch": 1.18, + "learning_rate": 1.215504128639722e-05, + "loss": 0.4994, + "step": 14441 + }, + { + "epoch": 1.18, + "learning_rate": 1.2154498044328553e-05, + "loss": 0.4036, + "step": 14442 + }, + { + "epoch": 1.18, + "learning_rate": 1.2153954802259889e-05, + "loss": 0.2844, + "step": 14443 + }, + { + "epoch": 1.18, + "learning_rate": 1.2153411560191221e-05, + "loss": 0.439, + "step": 14444 + }, + { + "epoch": 1.18, + "learning_rate": 1.2152868318122557e-05, + "loss": 0.3665, + "step": 14445 + }, + { + "epoch": 1.18, + "learning_rate": 1.215232507605389e-05, + "loss": 0.4358, + "step": 14446 + }, + { + "epoch": 1.18, + "learning_rate": 1.2151781833985225e-05, + "loss": 0.2782, + "step": 14447 + }, + { + "epoch": 1.18, + "learning_rate": 1.2151238591916558e-05, + "loss": 0.3458, + "step": 14448 + }, + { + "epoch": 1.18, + "learning_rate": 1.2150695349847894e-05, + "loss": 0.4014, + "step": 14449 + }, + { + "epoch": 1.18, + "learning_rate": 1.2150152107779226e-05, + "loss": 0.4973, + "step": 14450 + }, + { + "epoch": 1.18, + "learning_rate": 1.2149608865710562e-05, + "loss": 0.2776, + "step": 14451 + }, + { + "epoch": 1.18, + "learning_rate": 1.2149065623641897e-05, + "loss": 0.5617, + "step": 14452 + }, + { + "epoch": 1.18, + "learning_rate": 1.2148522381573229e-05, + "loss": 0.4853, + "step": 14453 + }, + { + "epoch": 1.18, + "learning_rate": 1.2147979139504565e-05, + "loss": 0.2158, + "step": 14454 + }, + { + "epoch": 1.18, + "learning_rate": 1.2147435897435898e-05, + "loss": 0.3953, + "step": 14455 + }, + { + "epoch": 1.18, + "learning_rate": 1.2146892655367234e-05, + "loss": 0.2156, + "step": 14456 + }, + { + "epoch": 1.18, + "learning_rate": 1.2146349413298566e-05, + "loss": 0.3314, + "step": 14457 + }, + { + "epoch": 1.18, + "learning_rate": 1.2145806171229902e-05, + "loss": 0.1462, + "step": 14458 + }, + { + "epoch": 1.18, + "learning_rate": 1.2145262929161235e-05, + "loss": 0.4529, + "step": 14459 + }, + { + "epoch": 1.18, + "learning_rate": 1.214471968709257e-05, + "loss": 0.3231, + "step": 14460 + }, + { + "epoch": 1.18, + "learning_rate": 1.2144176445023903e-05, + "loss": 0.4542, + "step": 14461 + }, + { + "epoch": 1.18, + "learning_rate": 1.2143633202955239e-05, + "loss": 0.5513, + "step": 14462 + }, + { + "epoch": 1.18, + "learning_rate": 1.2143089960886571e-05, + "loss": 0.3345, + "step": 14463 + }, + { + "epoch": 1.18, + "learning_rate": 1.2142546718817907e-05, + "loss": 0.4394, + "step": 14464 + }, + { + "epoch": 1.18, + "learning_rate": 1.214200347674924e-05, + "loss": 0.2299, + "step": 14465 + }, + { + "epoch": 1.18, + "learning_rate": 1.2141460234680576e-05, + "loss": 0.1091, + "step": 14466 + }, + { + "epoch": 1.18, + "learning_rate": 1.2140916992611908e-05, + "loss": 0.5125, + "step": 14467 + }, + { + "epoch": 1.18, + "learning_rate": 1.2140373750543244e-05, + "loss": 0.3287, + "step": 14468 + }, + { + "epoch": 1.18, + "learning_rate": 1.2139830508474577e-05, + "loss": 0.1741, + "step": 14469 + }, + { + "epoch": 1.18, + "learning_rate": 1.2139287266405913e-05, + "loss": 0.29, + "step": 14470 + }, + { + "epoch": 1.18, + "learning_rate": 1.2138744024337245e-05, + "loss": 0.4472, + "step": 14471 + }, + { + "epoch": 1.18, + "learning_rate": 1.213820078226858e-05, + "loss": 0.4861, + "step": 14472 + }, + { + "epoch": 1.18, + "learning_rate": 1.2137657540199914e-05, + "loss": 0.2148, + "step": 14473 + }, + { + "epoch": 1.18, + "learning_rate": 1.2137114298131248e-05, + "loss": 0.1829, + "step": 14474 + }, + { + "epoch": 1.18, + "learning_rate": 1.2136571056062582e-05, + "loss": 0.4502, + "step": 14475 + }, + { + "epoch": 1.18, + "learning_rate": 1.2136027813993916e-05, + "loss": 0.3014, + "step": 14476 + }, + { + "epoch": 1.18, + "learning_rate": 1.213548457192525e-05, + "loss": 0.1966, + "step": 14477 + }, + { + "epoch": 1.18, + "learning_rate": 1.2134941329856585e-05, + "loss": 0.1737, + "step": 14478 + }, + { + "epoch": 1.18, + "learning_rate": 1.2134398087787919e-05, + "loss": 0.1599, + "step": 14479 + }, + { + "epoch": 1.18, + "learning_rate": 1.2133854845719253e-05, + "loss": 0.0911, + "step": 14480 + }, + { + "epoch": 1.18, + "learning_rate": 1.2133311603650588e-05, + "loss": 0.567, + "step": 14481 + }, + { + "epoch": 1.18, + "learning_rate": 1.2132768361581922e-05, + "loss": 0.5285, + "step": 14482 + }, + { + "epoch": 1.18, + "learning_rate": 1.2132225119513256e-05, + "loss": 0.335, + "step": 14483 + }, + { + "epoch": 1.18, + "learning_rate": 1.213168187744459e-05, + "loss": 0.322, + "step": 14484 + }, + { + "epoch": 1.18, + "learning_rate": 1.2131138635375925e-05, + "loss": 0.5456, + "step": 14485 + }, + { + "epoch": 1.18, + "learning_rate": 1.2130595393307259e-05, + "loss": 0.525, + "step": 14486 + }, + { + "epoch": 1.18, + "learning_rate": 1.2130052151238593e-05, + "loss": 0.6372, + "step": 14487 + }, + { + "epoch": 1.18, + "learning_rate": 1.2129508909169927e-05, + "loss": 0.3183, + "step": 14488 + }, + { + "epoch": 1.18, + "learning_rate": 1.2128965667101263e-05, + "loss": 0.2359, + "step": 14489 + }, + { + "epoch": 1.18, + "learning_rate": 1.2128422425032596e-05, + "loss": 0.4356, + "step": 14490 + }, + { + "epoch": 1.18, + "learning_rate": 1.2127879182963928e-05, + "loss": 0.3391, + "step": 14491 + }, + { + "epoch": 1.18, + "learning_rate": 1.2127335940895264e-05, + "loss": 0.676, + "step": 14492 + }, + { + "epoch": 1.18, + "learning_rate": 1.2126792698826597e-05, + "loss": 0.2314, + "step": 14493 + }, + { + "epoch": 1.18, + "learning_rate": 1.2126249456757933e-05, + "loss": 0.2251, + "step": 14494 + }, + { + "epoch": 1.18, + "learning_rate": 1.2125706214689265e-05, + "loss": 0.2403, + "step": 14495 + }, + { + "epoch": 1.18, + "learning_rate": 1.2125162972620601e-05, + "loss": 0.6713, + "step": 14496 + }, + { + "epoch": 1.18, + "learning_rate": 1.2124619730551934e-05, + "loss": 0.5206, + "step": 14497 + }, + { + "epoch": 1.18, + "learning_rate": 1.212407648848327e-05, + "loss": 0.5379, + "step": 14498 + }, + { + "epoch": 1.18, + "learning_rate": 1.2123533246414602e-05, + "loss": 0.334, + "step": 14499 + }, + { + "epoch": 1.18, + "learning_rate": 1.2122990004345938e-05, + "loss": 0.1681, + "step": 14500 + }, + { + "epoch": 1.18, + "eval_accuracy": 0.8386143657666837, + "eval_loss": 0.44602540135383606, + "eval_runtime": 22.3165, + "eval_samples_per_second": 439.81, + "eval_steps_per_second": 3.45, + "step": 14500 + }, + { + "epoch": 1.18, + "learning_rate": 1.212244676227727e-05, + "loss": 0.1647, + "step": 14501 + }, + { + "epoch": 1.18, + "learning_rate": 1.2121903520208606e-05, + "loss": 0.4565, + "step": 14502 + }, + { + "epoch": 1.18, + "learning_rate": 1.2121360278139939e-05, + "loss": 0.3581, + "step": 14503 + }, + { + "epoch": 1.18, + "learning_rate": 1.2120817036071275e-05, + "loss": 0.664, + "step": 14504 + }, + { + "epoch": 1.18, + "learning_rate": 1.2120273794002609e-05, + "loss": 0.2656, + "step": 14505 + }, + { + "epoch": 1.18, + "learning_rate": 1.2119730551933943e-05, + "loss": 0.485, + "step": 14506 + }, + { + "epoch": 1.18, + "learning_rate": 1.2119187309865278e-05, + "loss": 0.3957, + "step": 14507 + }, + { + "epoch": 1.18, + "learning_rate": 1.2118644067796612e-05, + "loss": 0.1911, + "step": 14508 + }, + { + "epoch": 1.18, + "learning_rate": 1.2118100825727946e-05, + "loss": 0.285, + "step": 14509 + }, + { + "epoch": 1.18, + "learning_rate": 1.2117557583659279e-05, + "loss": 0.5586, + "step": 14510 + }, + { + "epoch": 1.18, + "learning_rate": 1.2117014341590614e-05, + "loss": 0.2544, + "step": 14511 + }, + { + "epoch": 1.18, + "learning_rate": 1.2116471099521947e-05, + "loss": 0.3921, + "step": 14512 + }, + { + "epoch": 1.18, + "learning_rate": 1.2115927857453283e-05, + "loss": 0.1761, + "step": 14513 + }, + { + "epoch": 1.18, + "learning_rate": 1.2115384615384615e-05, + "loss": 0.3279, + "step": 14514 + }, + { + "epoch": 1.18, + "learning_rate": 1.2114841373315951e-05, + "loss": 0.3497, + "step": 14515 + }, + { + "epoch": 1.18, + "learning_rate": 1.2114298131247284e-05, + "loss": 0.5221, + "step": 14516 + }, + { + "epoch": 1.18, + "learning_rate": 1.211375488917862e-05, + "loss": 0.263, + "step": 14517 + }, + { + "epoch": 1.18, + "learning_rate": 1.2113211647109952e-05, + "loss": 0.3604, + "step": 14518 + }, + { + "epoch": 1.18, + "learning_rate": 1.2112668405041288e-05, + "loss": 0.4115, + "step": 14519 + }, + { + "epoch": 1.18, + "learning_rate": 1.2112125162972621e-05, + "loss": 0.3647, + "step": 14520 + }, + { + "epoch": 1.18, + "learning_rate": 1.2111581920903957e-05, + "loss": 0.4068, + "step": 14521 + }, + { + "epoch": 1.18, + "learning_rate": 1.211103867883529e-05, + "loss": 0.3166, + "step": 14522 + }, + { + "epoch": 1.18, + "learning_rate": 1.2110495436766625e-05, + "loss": 0.5104, + "step": 14523 + }, + { + "epoch": 1.18, + "learning_rate": 1.2109952194697958e-05, + "loss": 0.257, + "step": 14524 + }, + { + "epoch": 1.18, + "learning_rate": 1.2109408952629294e-05, + "loss": 0.4542, + "step": 14525 + }, + { + "epoch": 1.18, + "learning_rate": 1.2108865710560626e-05, + "loss": 0.3988, + "step": 14526 + }, + { + "epoch": 1.18, + "learning_rate": 1.2108322468491962e-05, + "loss": 0.5255, + "step": 14527 + }, + { + "epoch": 1.18, + "learning_rate": 1.2107779226423295e-05, + "loss": 0.2281, + "step": 14528 + }, + { + "epoch": 1.18, + "learning_rate": 1.2107235984354629e-05, + "loss": 0.2703, + "step": 14529 + }, + { + "epoch": 1.18, + "learning_rate": 1.2106692742285963e-05, + "loss": 0.215, + "step": 14530 + }, + { + "epoch": 1.18, + "learning_rate": 1.2106149500217297e-05, + "loss": 0.3401, + "step": 14531 + }, + { + "epoch": 1.18, + "learning_rate": 1.2105606258148632e-05, + "loss": 0.3676, + "step": 14532 + }, + { + "epoch": 1.18, + "learning_rate": 1.2105063016079966e-05, + "loss": 0.4446, + "step": 14533 + }, + { + "epoch": 1.18, + "learning_rate": 1.21045197740113e-05, + "loss": 0.4081, + "step": 14534 + }, + { + "epoch": 1.18, + "learning_rate": 1.2103976531942634e-05, + "loss": 0.1829, + "step": 14535 + }, + { + "epoch": 1.18, + "learning_rate": 1.2103433289873969e-05, + "loss": 0.2996, + "step": 14536 + }, + { + "epoch": 1.18, + "learning_rate": 1.2102890047805303e-05, + "loss": 0.2788, + "step": 14537 + }, + { + "epoch": 1.18, + "learning_rate": 1.2102346805736637e-05, + "loss": 0.42, + "step": 14538 + }, + { + "epoch": 1.18, + "learning_rate": 1.2101803563667971e-05, + "loss": 0.5702, + "step": 14539 + }, + { + "epoch": 1.18, + "learning_rate": 1.2101260321599305e-05, + "loss": 0.2951, + "step": 14540 + }, + { + "epoch": 1.18, + "learning_rate": 1.210071707953064e-05, + "loss": 0.2425, + "step": 14541 + }, + { + "epoch": 1.18, + "learning_rate": 1.2100173837461976e-05, + "loss": 0.2933, + "step": 14542 + }, + { + "epoch": 1.19, + "learning_rate": 1.2099630595393308e-05, + "loss": 0.0788, + "step": 14543 + }, + { + "epoch": 1.19, + "learning_rate": 1.2099087353324644e-05, + "loss": 0.3469, + "step": 14544 + }, + { + "epoch": 1.19, + "learning_rate": 1.2098544111255977e-05, + "loss": 0.5837, + "step": 14545 + }, + { + "epoch": 1.19, + "learning_rate": 1.2098000869187313e-05, + "loss": 0.422, + "step": 14546 + }, + { + "epoch": 1.19, + "learning_rate": 1.2097457627118645e-05, + "loss": 0.1687, + "step": 14547 + }, + { + "epoch": 1.19, + "learning_rate": 1.2096914385049978e-05, + "loss": 0.3047, + "step": 14548 + }, + { + "epoch": 1.19, + "learning_rate": 1.2096371142981314e-05, + "loss": 0.2495, + "step": 14549 + }, + { + "epoch": 1.19, + "learning_rate": 1.2095827900912646e-05, + "loss": 0.292, + "step": 14550 + }, + { + "epoch": 1.19, + "learning_rate": 1.2095284658843982e-05, + "loss": 0.3841, + "step": 14551 + }, + { + "epoch": 1.19, + "learning_rate": 1.2094741416775315e-05, + "loss": 0.3207, + "step": 14552 + }, + { + "epoch": 1.19, + "learning_rate": 1.209419817470665e-05, + "loss": 0.3534, + "step": 14553 + }, + { + "epoch": 1.19, + "learning_rate": 1.2093654932637983e-05, + "loss": 0.6595, + "step": 14554 + }, + { + "epoch": 1.19, + "learning_rate": 1.2093111690569319e-05, + "loss": 0.2339, + "step": 14555 + }, + { + "epoch": 1.19, + "learning_rate": 1.2092568448500651e-05, + "loss": 0.3404, + "step": 14556 + }, + { + "epoch": 1.19, + "learning_rate": 1.2092025206431987e-05, + "loss": 0.1693, + "step": 14557 + }, + { + "epoch": 1.19, + "learning_rate": 1.209148196436332e-05, + "loss": 0.2023, + "step": 14558 + }, + { + "epoch": 1.19, + "learning_rate": 1.2090938722294656e-05, + "loss": 0.131, + "step": 14559 + }, + { + "epoch": 1.19, + "learning_rate": 1.209039548022599e-05, + "loss": 0.4688, + "step": 14560 + }, + { + "epoch": 1.19, + "learning_rate": 1.2089852238157324e-05, + "loss": 0.3249, + "step": 14561 + }, + { + "epoch": 1.19, + "learning_rate": 1.2089308996088659e-05, + "loss": 0.2609, + "step": 14562 + }, + { + "epoch": 1.19, + "learning_rate": 1.2088765754019993e-05, + "loss": 0.2514, + "step": 14563 + }, + { + "epoch": 1.19, + "learning_rate": 1.2088222511951327e-05, + "loss": 0.4263, + "step": 14564 + }, + { + "epoch": 1.19, + "learning_rate": 1.2087679269882661e-05, + "loss": 0.7467, + "step": 14565 + }, + { + "epoch": 1.19, + "learning_rate": 1.2087136027813995e-05, + "loss": 0.3045, + "step": 14566 + }, + { + "epoch": 1.19, + "learning_rate": 1.2086592785745328e-05, + "loss": 0.1756, + "step": 14567 + }, + { + "epoch": 1.19, + "learning_rate": 1.2086049543676664e-05, + "loss": 0.2777, + "step": 14568 + }, + { + "epoch": 1.19, + "learning_rate": 1.2085506301607996e-05, + "loss": 0.2282, + "step": 14569 + }, + { + "epoch": 1.19, + "learning_rate": 1.2084963059539332e-05, + "loss": 0.437, + "step": 14570 + }, + { + "epoch": 1.19, + "learning_rate": 1.2084419817470665e-05, + "loss": 0.3857, + "step": 14571 + }, + { + "epoch": 1.19, + "learning_rate": 1.2083876575402001e-05, + "loss": 0.2354, + "step": 14572 + }, + { + "epoch": 1.19, + "learning_rate": 1.2083333333333333e-05, + "loss": 0.2671, + "step": 14573 + }, + { + "epoch": 1.19, + "learning_rate": 1.208279009126467e-05, + "loss": 0.3579, + "step": 14574 + }, + { + "epoch": 1.19, + "learning_rate": 1.2082246849196002e-05, + "loss": 0.3957, + "step": 14575 + }, + { + "epoch": 1.19, + "learning_rate": 1.2081703607127338e-05, + "loss": 0.2223, + "step": 14576 + }, + { + "epoch": 1.19, + "learning_rate": 1.208116036505867e-05, + "loss": 0.4394, + "step": 14577 + }, + { + "epoch": 1.19, + "learning_rate": 1.2080617122990006e-05, + "loss": 0.4377, + "step": 14578 + }, + { + "epoch": 1.19, + "learning_rate": 1.2080073880921339e-05, + "loss": 0.186, + "step": 14579 + }, + { + "epoch": 1.19, + "learning_rate": 1.2079530638852675e-05, + "loss": 0.3509, + "step": 14580 + }, + { + "epoch": 1.19, + "learning_rate": 1.2078987396784007e-05, + "loss": 0.6443, + "step": 14581 + }, + { + "epoch": 1.19, + "learning_rate": 1.2078444154715343e-05, + "loss": 0.6521, + "step": 14582 + }, + { + "epoch": 1.19, + "learning_rate": 1.2077900912646676e-05, + "loss": 0.3454, + "step": 14583 + }, + { + "epoch": 1.19, + "learning_rate": 1.2077357670578012e-05, + "loss": 0.1311, + "step": 14584 + }, + { + "epoch": 1.19, + "learning_rate": 1.2076814428509344e-05, + "loss": 0.2841, + "step": 14585 + }, + { + "epoch": 1.19, + "learning_rate": 1.2076271186440678e-05, + "loss": 0.2931, + "step": 14586 + }, + { + "epoch": 1.19, + "learning_rate": 1.2075727944372013e-05, + "loss": 0.2015, + "step": 14587 + }, + { + "epoch": 1.19, + "learning_rate": 1.2075184702303347e-05, + "loss": 0.3545, + "step": 14588 + }, + { + "epoch": 1.19, + "learning_rate": 1.2074641460234681e-05, + "loss": 0.4016, + "step": 14589 + }, + { + "epoch": 1.19, + "learning_rate": 1.2074098218166015e-05, + "loss": 0.2846, + "step": 14590 + }, + { + "epoch": 1.19, + "learning_rate": 1.207355497609735e-05, + "loss": 0.6128, + "step": 14591 + }, + { + "epoch": 1.19, + "learning_rate": 1.2073011734028684e-05, + "loss": 0.2468, + "step": 14592 + }, + { + "epoch": 1.19, + "learning_rate": 1.2072468491960018e-05, + "loss": 0.4907, + "step": 14593 + }, + { + "epoch": 1.19, + "learning_rate": 1.2071925249891352e-05, + "loss": 0.4443, + "step": 14594 + }, + { + "epoch": 1.19, + "learning_rate": 1.2071382007822686e-05, + "loss": 0.4353, + "step": 14595 + }, + { + "epoch": 1.19, + "learning_rate": 1.207083876575402e-05, + "loss": 0.3704, + "step": 14596 + }, + { + "epoch": 1.19, + "learning_rate": 1.2070295523685357e-05, + "loss": 0.4372, + "step": 14597 + }, + { + "epoch": 1.19, + "learning_rate": 1.206975228161669e-05, + "loss": 0.4814, + "step": 14598 + }, + { + "epoch": 1.19, + "learning_rate": 1.2069209039548025e-05, + "loss": 0.2665, + "step": 14599 + }, + { + "epoch": 1.19, + "learning_rate": 1.2068665797479358e-05, + "loss": 0.5337, + "step": 14600 + }, + { + "epoch": 1.19, + "learning_rate": 1.2068122555410694e-05, + "loss": 0.2328, + "step": 14601 + }, + { + "epoch": 1.19, + "learning_rate": 1.2067579313342026e-05, + "loss": 0.3484, + "step": 14602 + }, + { + "epoch": 1.19, + "learning_rate": 1.2067036071273362e-05, + "loss": 0.2819, + "step": 14603 + }, + { + "epoch": 1.19, + "learning_rate": 1.2066492829204695e-05, + "loss": 0.2117, + "step": 14604 + }, + { + "epoch": 1.19, + "learning_rate": 1.2065949587136027e-05, + "loss": 0.194, + "step": 14605 + }, + { + "epoch": 1.19, + "learning_rate": 1.2065406345067363e-05, + "loss": 0.3983, + "step": 14606 + }, + { + "epoch": 1.19, + "learning_rate": 1.2064863102998696e-05, + "loss": 0.3735, + "step": 14607 + }, + { + "epoch": 1.19, + "learning_rate": 1.2064319860930031e-05, + "loss": 0.58, + "step": 14608 + }, + { + "epoch": 1.19, + "learning_rate": 1.2063776618861364e-05, + "loss": 0.5792, + "step": 14609 + }, + { + "epoch": 1.19, + "learning_rate": 1.20632333767927e-05, + "loss": 0.1672, + "step": 14610 + }, + { + "epoch": 1.19, + "learning_rate": 1.2062690134724032e-05, + "loss": 0.2782, + "step": 14611 + }, + { + "epoch": 1.19, + "learning_rate": 1.2062146892655368e-05, + "loss": 0.6, + "step": 14612 + }, + { + "epoch": 1.19, + "learning_rate": 1.2061603650586703e-05, + "loss": 0.3087, + "step": 14613 + }, + { + "epoch": 1.19, + "learning_rate": 1.2061060408518037e-05, + "loss": 0.4778, + "step": 14614 + }, + { + "epoch": 1.19, + "learning_rate": 1.2060517166449371e-05, + "loss": 0.4639, + "step": 14615 + }, + { + "epoch": 1.19, + "learning_rate": 1.2059973924380705e-05, + "loss": 0.2215, + "step": 14616 + }, + { + "epoch": 1.19, + "learning_rate": 1.205943068231204e-05, + "loss": 0.182, + "step": 14617 + }, + { + "epoch": 1.19, + "learning_rate": 1.2058887440243374e-05, + "loss": 0.2343, + "step": 14618 + }, + { + "epoch": 1.19, + "learning_rate": 1.2058344198174708e-05, + "loss": 0.273, + "step": 14619 + }, + { + "epoch": 1.19, + "learning_rate": 1.2057800956106042e-05, + "loss": 0.2349, + "step": 14620 + }, + { + "epoch": 1.19, + "learning_rate": 1.2057257714037376e-05, + "loss": 0.2311, + "step": 14621 + }, + { + "epoch": 1.19, + "learning_rate": 1.205671447196871e-05, + "loss": 0.2898, + "step": 14622 + }, + { + "epoch": 1.19, + "learning_rate": 1.2056171229900045e-05, + "loss": 0.5093, + "step": 14623 + }, + { + "epoch": 1.19, + "learning_rate": 1.2055627987831377e-05, + "loss": 0.2777, + "step": 14624 + }, + { + "epoch": 1.19, + "learning_rate": 1.2055084745762713e-05, + "loss": 0.3858, + "step": 14625 + }, + { + "epoch": 1.19, + "learning_rate": 1.2054541503694046e-05, + "loss": 0.379, + "step": 14626 + }, + { + "epoch": 1.19, + "learning_rate": 1.2053998261625382e-05, + "loss": 0.4278, + "step": 14627 + }, + { + "epoch": 1.19, + "learning_rate": 1.2053455019556714e-05, + "loss": 0.3322, + "step": 14628 + }, + { + "epoch": 1.19, + "learning_rate": 1.205291177748805e-05, + "loss": 0.4036, + "step": 14629 + }, + { + "epoch": 1.19, + "learning_rate": 1.2052368535419383e-05, + "loss": 0.2844, + "step": 14630 + }, + { + "epoch": 1.19, + "learning_rate": 1.2051825293350719e-05, + "loss": 0.1558, + "step": 14631 + }, + { + "epoch": 1.19, + "learning_rate": 1.2051282051282051e-05, + "loss": 0.3779, + "step": 14632 + }, + { + "epoch": 1.19, + "learning_rate": 1.2050738809213387e-05, + "loss": 0.475, + "step": 14633 + }, + { + "epoch": 1.19, + "learning_rate": 1.205019556714472e-05, + "loss": 0.3375, + "step": 14634 + }, + { + "epoch": 1.19, + "learning_rate": 1.2049652325076056e-05, + "loss": 0.3761, + "step": 14635 + }, + { + "epoch": 1.19, + "learning_rate": 1.2049109083007388e-05, + "loss": 0.321, + "step": 14636 + }, + { + "epoch": 1.19, + "learning_rate": 1.2048565840938724e-05, + "loss": 0.4265, + "step": 14637 + }, + { + "epoch": 1.19, + "learning_rate": 1.2048022598870057e-05, + "loss": 0.2644, + "step": 14638 + }, + { + "epoch": 1.19, + "learning_rate": 1.2047479356801393e-05, + "loss": 0.2995, + "step": 14639 + }, + { + "epoch": 1.19, + "learning_rate": 1.2046936114732725e-05, + "loss": 0.2129, + "step": 14640 + }, + { + "epoch": 1.19, + "learning_rate": 1.2046392872664061e-05, + "loss": 0.1105, + "step": 14641 + }, + { + "epoch": 1.19, + "learning_rate": 1.2045849630595394e-05, + "loss": 0.4779, + "step": 14642 + }, + { + "epoch": 1.19, + "learning_rate": 1.2045306388526728e-05, + "loss": 0.257, + "step": 14643 + }, + { + "epoch": 1.19, + "learning_rate": 1.2044763146458062e-05, + "loss": 0.498, + "step": 14644 + }, + { + "epoch": 1.19, + "learning_rate": 1.2044219904389396e-05, + "loss": 0.1141, + "step": 14645 + }, + { + "epoch": 1.19, + "learning_rate": 1.204367666232073e-05, + "loss": 0.2559, + "step": 14646 + }, + { + "epoch": 1.19, + "learning_rate": 1.2043133420252065e-05, + "loss": 0.3054, + "step": 14647 + }, + { + "epoch": 1.19, + "learning_rate": 1.2042590178183399e-05, + "loss": 0.2861, + "step": 14648 + }, + { + "epoch": 1.19, + "learning_rate": 1.2042046936114733e-05, + "loss": 0.1819, + "step": 14649 + }, + { + "epoch": 1.19, + "learning_rate": 1.204150369404607e-05, + "loss": 0.4867, + "step": 14650 + }, + { + "epoch": 1.19, + "learning_rate": 1.2040960451977402e-05, + "loss": 0.2046, + "step": 14651 + }, + { + "epoch": 1.19, + "learning_rate": 1.2040417209908738e-05, + "loss": 0.3861, + "step": 14652 + }, + { + "epoch": 1.19, + "learning_rate": 1.203987396784007e-05, + "loss": 0.2747, + "step": 14653 + }, + { + "epoch": 1.19, + "learning_rate": 1.2039330725771406e-05, + "loss": 0.2696, + "step": 14654 + }, + { + "epoch": 1.19, + "learning_rate": 1.2038787483702739e-05, + "loss": 0.2768, + "step": 14655 + }, + { + "epoch": 1.19, + "learning_rate": 1.2038244241634075e-05, + "loss": 0.3539, + "step": 14656 + }, + { + "epoch": 1.19, + "learning_rate": 1.2037700999565407e-05, + "loss": 0.5332, + "step": 14657 + }, + { + "epoch": 1.19, + "learning_rate": 1.2037157757496743e-05, + "loss": 0.3136, + "step": 14658 + }, + { + "epoch": 1.19, + "learning_rate": 1.2036614515428076e-05, + "loss": 0.1191, + "step": 14659 + }, + { + "epoch": 1.19, + "learning_rate": 1.2036071273359411e-05, + "loss": 0.1942, + "step": 14660 + }, + { + "epoch": 1.19, + "learning_rate": 1.2035528031290744e-05, + "loss": 0.1307, + "step": 14661 + }, + { + "epoch": 1.19, + "learning_rate": 1.2034984789222077e-05, + "loss": 0.1995, + "step": 14662 + }, + { + "epoch": 1.19, + "learning_rate": 1.2034441547153412e-05, + "loss": 0.5327, + "step": 14663 + }, + { + "epoch": 1.19, + "learning_rate": 1.2033898305084745e-05, + "loss": 0.2156, + "step": 14664 + }, + { + "epoch": 1.19, + "learning_rate": 1.2033355063016081e-05, + "loss": 0.2163, + "step": 14665 + }, + { + "epoch": 1.2, + "learning_rate": 1.2032811820947413e-05, + "loss": 0.206, + "step": 14666 + }, + { + "epoch": 1.2, + "learning_rate": 1.203226857887875e-05, + "loss": 0.2479, + "step": 14667 + }, + { + "epoch": 1.2, + "learning_rate": 1.2031725336810084e-05, + "loss": 0.3461, + "step": 14668 + }, + { + "epoch": 1.2, + "learning_rate": 1.2031182094741418e-05, + "loss": 0.3257, + "step": 14669 + }, + { + "epoch": 1.2, + "learning_rate": 1.2030638852672752e-05, + "loss": 0.6139, + "step": 14670 + }, + { + "epoch": 1.2, + "learning_rate": 1.2030095610604086e-05, + "loss": 0.3295, + "step": 14671 + }, + { + "epoch": 1.2, + "learning_rate": 1.202955236853542e-05, + "loss": 0.4994, + "step": 14672 + }, + { + "epoch": 1.2, + "learning_rate": 1.2029009126466755e-05, + "loss": 0.4428, + "step": 14673 + }, + { + "epoch": 1.2, + "learning_rate": 1.2028465884398089e-05, + "loss": 0.1439, + "step": 14674 + }, + { + "epoch": 1.2, + "learning_rate": 1.2027922642329423e-05, + "loss": 0.1875, + "step": 14675 + }, + { + "epoch": 1.2, + "learning_rate": 1.2027379400260757e-05, + "loss": 0.3258, + "step": 14676 + }, + { + "epoch": 1.2, + "learning_rate": 1.2026836158192092e-05, + "loss": 0.4798, + "step": 14677 + }, + { + "epoch": 1.2, + "learning_rate": 1.2026292916123426e-05, + "loss": 0.306, + "step": 14678 + }, + { + "epoch": 1.2, + "learning_rate": 1.202574967405476e-05, + "loss": 0.2217, + "step": 14679 + }, + { + "epoch": 1.2, + "learning_rate": 1.2025206431986094e-05, + "loss": 0.2621, + "step": 14680 + }, + { + "epoch": 1.2, + "learning_rate": 1.2024663189917427e-05, + "loss": 0.5298, + "step": 14681 + }, + { + "epoch": 1.2, + "learning_rate": 1.2024119947848763e-05, + "loss": 0.4833, + "step": 14682 + }, + { + "epoch": 1.2, + "learning_rate": 1.2023576705780095e-05, + "loss": 0.5458, + "step": 14683 + }, + { + "epoch": 1.2, + "learning_rate": 1.2023033463711431e-05, + "loss": 0.271, + "step": 14684 + }, + { + "epoch": 1.2, + "learning_rate": 1.2022490221642764e-05, + "loss": 0.2946, + "step": 14685 + }, + { + "epoch": 1.2, + "learning_rate": 1.20219469795741e-05, + "loss": 0.5273, + "step": 14686 + }, + { + "epoch": 1.2, + "learning_rate": 1.2021403737505432e-05, + "loss": 0.2133, + "step": 14687 + }, + { + "epoch": 1.2, + "learning_rate": 1.2020860495436768e-05, + "loss": 0.271, + "step": 14688 + }, + { + "epoch": 1.2, + "learning_rate": 1.20203172533681e-05, + "loss": 0.2782, + "step": 14689 + }, + { + "epoch": 1.2, + "learning_rate": 1.2019774011299437e-05, + "loss": 0.1636, + "step": 14690 + }, + { + "epoch": 1.2, + "learning_rate": 1.201923076923077e-05, + "loss": 0.1445, + "step": 14691 + }, + { + "epoch": 1.2, + "learning_rate": 1.2018687527162105e-05, + "loss": 0.3316, + "step": 14692 + }, + { + "epoch": 1.2, + "learning_rate": 1.2018144285093438e-05, + "loss": 0.1112, + "step": 14693 + }, + { + "epoch": 1.2, + "learning_rate": 1.2017601043024774e-05, + "loss": 0.4769, + "step": 14694 + }, + { + "epoch": 1.2, + "learning_rate": 1.2017057800956106e-05, + "loss": 0.3613, + "step": 14695 + }, + { + "epoch": 1.2, + "learning_rate": 1.2016514558887442e-05, + "loss": 0.3063, + "step": 14696 + }, + { + "epoch": 1.2, + "learning_rate": 1.2015971316818775e-05, + "loss": 0.6485, + "step": 14697 + }, + { + "epoch": 1.2, + "learning_rate": 1.201542807475011e-05, + "loss": 0.3925, + "step": 14698 + }, + { + "epoch": 1.2, + "learning_rate": 1.2014884832681443e-05, + "loss": 0.5264, + "step": 14699 + }, + { + "epoch": 1.2, + "learning_rate": 1.2014341590612777e-05, + "loss": 0.2026, + "step": 14700 + }, + { + "epoch": 1.2, + "learning_rate": 1.2013798348544112e-05, + "loss": 0.7035, + "step": 14701 + }, + { + "epoch": 1.2, + "learning_rate": 1.2013255106475446e-05, + "loss": 0.3159, + "step": 14702 + }, + { + "epoch": 1.2, + "learning_rate": 1.201271186440678e-05, + "loss": 0.3187, + "step": 14703 + }, + { + "epoch": 1.2, + "learning_rate": 1.2012168622338114e-05, + "loss": 0.3551, + "step": 14704 + }, + { + "epoch": 1.2, + "learning_rate": 1.201162538026945e-05, + "loss": 0.45, + "step": 14705 + }, + { + "epoch": 1.2, + "learning_rate": 1.2011082138200783e-05, + "loss": 0.2087, + "step": 14706 + }, + { + "epoch": 1.2, + "learning_rate": 1.2010538896132119e-05, + "loss": 0.4425, + "step": 14707 + }, + { + "epoch": 1.2, + "learning_rate": 1.2009995654063451e-05, + "loss": 0.6945, + "step": 14708 + }, + { + "epoch": 1.2, + "learning_rate": 1.2009452411994787e-05, + "loss": 0.2382, + "step": 14709 + }, + { + "epoch": 1.2, + "learning_rate": 1.200890916992612e-05, + "loss": 0.3083, + "step": 14710 + }, + { + "epoch": 1.2, + "learning_rate": 1.2008365927857456e-05, + "loss": 0.4393, + "step": 14711 + }, + { + "epoch": 1.2, + "learning_rate": 1.2007822685788788e-05, + "loss": 0.337, + "step": 14712 + }, + { + "epoch": 1.2, + "learning_rate": 1.2007279443720124e-05, + "loss": 0.2812, + "step": 14713 + }, + { + "epoch": 1.2, + "learning_rate": 1.2006736201651457e-05, + "loss": 0.2863, + "step": 14714 + }, + { + "epoch": 1.2, + "learning_rate": 1.2006192959582792e-05, + "loss": 0.1872, + "step": 14715 + }, + { + "epoch": 1.2, + "learning_rate": 1.2005649717514125e-05, + "loss": 0.3385, + "step": 14716 + }, + { + "epoch": 1.2, + "learning_rate": 1.2005106475445461e-05, + "loss": 0.4133, + "step": 14717 + }, + { + "epoch": 1.2, + "learning_rate": 1.2004563233376793e-05, + "loss": 0.217, + "step": 14718 + }, + { + "epoch": 1.2, + "learning_rate": 1.2004019991308126e-05, + "loss": 0.251, + "step": 14719 + }, + { + "epoch": 1.2, + "learning_rate": 1.2003476749239462e-05, + "loss": 0.3991, + "step": 14720 + }, + { + "epoch": 1.2, + "learning_rate": 1.2002933507170796e-05, + "loss": 0.3767, + "step": 14721 + }, + { + "epoch": 1.2, + "learning_rate": 1.200239026510213e-05, + "loss": 0.5356, + "step": 14722 + }, + { + "epoch": 1.2, + "learning_rate": 1.2001847023033465e-05, + "loss": 0.4136, + "step": 14723 + }, + { + "epoch": 1.2, + "learning_rate": 1.2001303780964799e-05, + "loss": 0.29, + "step": 14724 + }, + { + "epoch": 1.2, + "learning_rate": 1.2000760538896133e-05, + "loss": 0.0926, + "step": 14725 + }, + { + "epoch": 1.2, + "learning_rate": 1.2000217296827467e-05, + "loss": 0.2714, + "step": 14726 + }, + { + "epoch": 1.2, + "learning_rate": 1.1999674054758802e-05, + "loss": 0.2423, + "step": 14727 + }, + { + "epoch": 1.2, + "learning_rate": 1.1999130812690136e-05, + "loss": 0.4141, + "step": 14728 + }, + { + "epoch": 1.2, + "learning_rate": 1.199858757062147e-05, + "loss": 0.2006, + "step": 14729 + }, + { + "epoch": 1.2, + "learning_rate": 1.1998044328552804e-05, + "loss": 0.266, + "step": 14730 + }, + { + "epoch": 1.2, + "learning_rate": 1.1997501086484138e-05, + "loss": 0.2496, + "step": 14731 + }, + { + "epoch": 1.2, + "learning_rate": 1.1996957844415473e-05, + "loss": 0.4108, + "step": 14732 + }, + { + "epoch": 1.2, + "learning_rate": 1.1996414602346807e-05, + "loss": 0.2703, + "step": 14733 + }, + { + "epoch": 1.2, + "learning_rate": 1.1995871360278141e-05, + "loss": 0.34, + "step": 14734 + }, + { + "epoch": 1.2, + "learning_rate": 1.1995328118209475e-05, + "loss": 0.4524, + "step": 14735 + }, + { + "epoch": 1.2, + "learning_rate": 1.199478487614081e-05, + "loss": 0.3007, + "step": 14736 + }, + { + "epoch": 1.2, + "learning_rate": 1.1994241634072144e-05, + "loss": 0.3794, + "step": 14737 + }, + { + "epoch": 1.2, + "learning_rate": 1.1993698392003476e-05, + "loss": 0.5049, + "step": 14738 + }, + { + "epoch": 1.2, + "learning_rate": 1.1993155149934812e-05, + "loss": 0.2307, + "step": 14739 + }, + { + "epoch": 1.2, + "learning_rate": 1.1992611907866145e-05, + "loss": 0.2418, + "step": 14740 + }, + { + "epoch": 1.2, + "learning_rate": 1.199206866579748e-05, + "loss": 0.4081, + "step": 14741 + }, + { + "epoch": 1.2, + "learning_rate": 1.1991525423728813e-05, + "loss": 0.2037, + "step": 14742 + }, + { + "epoch": 1.2, + "learning_rate": 1.199098218166015e-05, + "loss": 0.2256, + "step": 14743 + }, + { + "epoch": 1.2, + "learning_rate": 1.1990438939591482e-05, + "loss": 0.4923, + "step": 14744 + }, + { + "epoch": 1.2, + "learning_rate": 1.1989895697522818e-05, + "loss": 0.6759, + "step": 14745 + }, + { + "epoch": 1.2, + "learning_rate": 1.198935245545415e-05, + "loss": 0.4559, + "step": 14746 + }, + { + "epoch": 1.2, + "learning_rate": 1.1988809213385486e-05, + "loss": 0.7116, + "step": 14747 + }, + { + "epoch": 1.2, + "learning_rate": 1.1988265971316819e-05, + "loss": 0.2088, + "step": 14748 + }, + { + "epoch": 1.2, + "learning_rate": 1.1987722729248155e-05, + "loss": 0.2571, + "step": 14749 + }, + { + "epoch": 1.2, + "learning_rate": 1.1987179487179487e-05, + "loss": 0.3565, + "step": 14750 + }, + { + "epoch": 1.2, + "eval_accuracy": 0.8334182373917474, + "eval_loss": 0.4506783187389374, + "eval_runtime": 22.2908, + "eval_samples_per_second": 440.317, + "eval_steps_per_second": 3.454, + "step": 14750 + }, + { + "epoch": 1.2, + "learning_rate": 1.1986636245110823e-05, + "loss": 0.4377, + "step": 14751 + }, + { + "epoch": 1.2, + "learning_rate": 1.1986093003042156e-05, + "loss": 0.551, + "step": 14752 + }, + { + "epoch": 1.2, + "learning_rate": 1.1985549760973492e-05, + "loss": 0.265, + "step": 14753 + }, + { + "epoch": 1.2, + "learning_rate": 1.1985006518904824e-05, + "loss": 0.2626, + "step": 14754 + }, + { + "epoch": 1.2, + "learning_rate": 1.198446327683616e-05, + "loss": 0.3717, + "step": 14755 + }, + { + "epoch": 1.2, + "learning_rate": 1.1983920034767493e-05, + "loss": 0.5109, + "step": 14756 + }, + { + "epoch": 1.2, + "learning_rate": 1.1983376792698827e-05, + "loss": 0.3346, + "step": 14757 + }, + { + "epoch": 1.2, + "learning_rate": 1.1982833550630163e-05, + "loss": 0.3562, + "step": 14758 + }, + { + "epoch": 1.2, + "learning_rate": 1.1982290308561495e-05, + "loss": 0.397, + "step": 14759 + }, + { + "epoch": 1.2, + "learning_rate": 1.1981747066492831e-05, + "loss": 0.2279, + "step": 14760 + }, + { + "epoch": 1.2, + "learning_rate": 1.1981203824424164e-05, + "loss": 0.3507, + "step": 14761 + }, + { + "epoch": 1.2, + "learning_rate": 1.19806605823555e-05, + "loss": 0.4146, + "step": 14762 + }, + { + "epoch": 1.2, + "learning_rate": 1.1980117340286832e-05, + "loss": 0.4093, + "step": 14763 + }, + { + "epoch": 1.2, + "learning_rate": 1.1979574098218168e-05, + "loss": 0.2599, + "step": 14764 + }, + { + "epoch": 1.2, + "learning_rate": 1.19790308561495e-05, + "loss": 0.2573, + "step": 14765 + }, + { + "epoch": 1.2, + "learning_rate": 1.1978487614080837e-05, + "loss": 0.4501, + "step": 14766 + }, + { + "epoch": 1.2, + "learning_rate": 1.1977944372012169e-05, + "loss": 0.4181, + "step": 14767 + }, + { + "epoch": 1.2, + "learning_rate": 1.1977401129943505e-05, + "loss": 0.5482, + "step": 14768 + }, + { + "epoch": 1.2, + "learning_rate": 1.1976857887874838e-05, + "loss": 0.2969, + "step": 14769 + }, + { + "epoch": 1.2, + "learning_rate": 1.1976314645806173e-05, + "loss": 0.4194, + "step": 14770 + }, + { + "epoch": 1.2, + "learning_rate": 1.1975771403737506e-05, + "loss": 0.1498, + "step": 14771 + }, + { + "epoch": 1.2, + "learning_rate": 1.1975228161668842e-05, + "loss": 0.4116, + "step": 14772 + }, + { + "epoch": 1.2, + "learning_rate": 1.1974684919600174e-05, + "loss": 0.0976, + "step": 14773 + }, + { + "epoch": 1.2, + "learning_rate": 1.197414167753151e-05, + "loss": 0.2756, + "step": 14774 + }, + { + "epoch": 1.2, + "learning_rate": 1.1973598435462843e-05, + "loss": 0.4161, + "step": 14775 + }, + { + "epoch": 1.2, + "learning_rate": 1.1973055193394177e-05, + "loss": 0.2956, + "step": 14776 + }, + { + "epoch": 1.2, + "learning_rate": 1.1972511951325511e-05, + "loss": 0.2159, + "step": 14777 + }, + { + "epoch": 1.2, + "learning_rate": 1.1971968709256846e-05, + "loss": 0.4693, + "step": 14778 + }, + { + "epoch": 1.2, + "learning_rate": 1.197142546718818e-05, + "loss": 0.4318, + "step": 14779 + }, + { + "epoch": 1.2, + "learning_rate": 1.1970882225119514e-05, + "loss": 0.2366, + "step": 14780 + }, + { + "epoch": 1.2, + "learning_rate": 1.1970338983050848e-05, + "loss": 0.3571, + "step": 14781 + }, + { + "epoch": 1.2, + "learning_rate": 1.1969795740982183e-05, + "loss": 0.3634, + "step": 14782 + }, + { + "epoch": 1.2, + "learning_rate": 1.1969252498913517e-05, + "loss": 0.2606, + "step": 14783 + }, + { + "epoch": 1.2, + "learning_rate": 1.1968709256844851e-05, + "loss": 0.1871, + "step": 14784 + }, + { + "epoch": 1.2, + "learning_rate": 1.1968166014776185e-05, + "loss": 0.3163, + "step": 14785 + }, + { + "epoch": 1.2, + "learning_rate": 1.196762277270752e-05, + "loss": 0.5271, + "step": 14786 + }, + { + "epoch": 1.2, + "learning_rate": 1.1967079530638854e-05, + "loss": 0.2613, + "step": 14787 + }, + { + "epoch": 1.21, + "learning_rate": 1.1966536288570188e-05, + "loss": 0.2502, + "step": 14788 + }, + { + "epoch": 1.21, + "learning_rate": 1.1965993046501522e-05, + "loss": 0.1626, + "step": 14789 + }, + { + "epoch": 1.21, + "learning_rate": 1.1965449804432856e-05, + "loss": 0.2768, + "step": 14790 + }, + { + "epoch": 1.21, + "learning_rate": 1.196490656236419e-05, + "loss": 0.1619, + "step": 14791 + }, + { + "epoch": 1.21, + "learning_rate": 1.1964363320295525e-05, + "loss": 0.2333, + "step": 14792 + }, + { + "epoch": 1.21, + "learning_rate": 1.1963820078226859e-05, + "loss": 0.4434, + "step": 14793 + }, + { + "epoch": 1.21, + "learning_rate": 1.1963276836158193e-05, + "loss": 0.2407, + "step": 14794 + }, + { + "epoch": 1.21, + "learning_rate": 1.1962733594089526e-05, + "loss": 0.3419, + "step": 14795 + }, + { + "epoch": 1.21, + "learning_rate": 1.1962190352020862e-05, + "loss": 0.424, + "step": 14796 + }, + { + "epoch": 1.21, + "learning_rate": 1.1961647109952194e-05, + "loss": 0.1773, + "step": 14797 + }, + { + "epoch": 1.21, + "learning_rate": 1.196110386788353e-05, + "loss": 0.3904, + "step": 14798 + }, + { + "epoch": 1.21, + "learning_rate": 1.1960560625814863e-05, + "loss": 0.227, + "step": 14799 + }, + { + "epoch": 1.21, + "learning_rate": 1.1960017383746199e-05, + "loss": 0.3834, + "step": 14800 + }, + { + "epoch": 1.21, + "learning_rate": 1.1959474141677531e-05, + "loss": 0.2332, + "step": 14801 + }, + { + "epoch": 1.21, + "learning_rate": 1.1958930899608867e-05, + "loss": 0.3552, + "step": 14802 + }, + { + "epoch": 1.21, + "learning_rate": 1.19583876575402e-05, + "loss": 0.1428, + "step": 14803 + }, + { + "epoch": 1.21, + "learning_rate": 1.1957844415471536e-05, + "loss": 0.3045, + "step": 14804 + }, + { + "epoch": 1.21, + "learning_rate": 1.1957301173402868e-05, + "loss": 0.2376, + "step": 14805 + }, + { + "epoch": 1.21, + "learning_rate": 1.1956757931334204e-05, + "loss": 0.4646, + "step": 14806 + }, + { + "epoch": 1.21, + "learning_rate": 1.1956214689265537e-05, + "loss": 0.154, + "step": 14807 + }, + { + "epoch": 1.21, + "learning_rate": 1.1955671447196873e-05, + "loss": 0.1506, + "step": 14808 + }, + { + "epoch": 1.21, + "learning_rate": 1.1955128205128205e-05, + "loss": 0.2084, + "step": 14809 + }, + { + "epoch": 1.21, + "learning_rate": 1.1954584963059541e-05, + "loss": 0.4421, + "step": 14810 + }, + { + "epoch": 1.21, + "learning_rate": 1.1954041720990873e-05, + "loss": 0.1968, + "step": 14811 + }, + { + "epoch": 1.21, + "learning_rate": 1.195349847892221e-05, + "loss": 0.3593, + "step": 14812 + }, + { + "epoch": 1.21, + "learning_rate": 1.1952955236853544e-05, + "loss": 0.3724, + "step": 14813 + }, + { + "epoch": 1.21, + "learning_rate": 1.1952411994784876e-05, + "loss": 0.2502, + "step": 14814 + }, + { + "epoch": 1.21, + "learning_rate": 1.1951868752716212e-05, + "loss": 0.4267, + "step": 14815 + }, + { + "epoch": 1.21, + "learning_rate": 1.1951325510647545e-05, + "loss": 0.4544, + "step": 14816 + }, + { + "epoch": 1.21, + "learning_rate": 1.195078226857888e-05, + "loss": 0.2771, + "step": 14817 + }, + { + "epoch": 1.21, + "learning_rate": 1.1950239026510213e-05, + "loss": 0.3928, + "step": 14818 + }, + { + "epoch": 1.21, + "learning_rate": 1.1949695784441549e-05, + "loss": 0.1972, + "step": 14819 + }, + { + "epoch": 1.21, + "learning_rate": 1.1949152542372882e-05, + "loss": 0.2234, + "step": 14820 + }, + { + "epoch": 1.21, + "learning_rate": 1.1948609300304217e-05, + "loss": 0.3785, + "step": 14821 + }, + { + "epoch": 1.21, + "learning_rate": 1.194806605823555e-05, + "loss": 0.2727, + "step": 14822 + }, + { + "epoch": 1.21, + "learning_rate": 1.1947522816166886e-05, + "loss": 0.6612, + "step": 14823 + }, + { + "epoch": 1.21, + "learning_rate": 1.1946979574098218e-05, + "loss": 0.2156, + "step": 14824 + }, + { + "epoch": 1.21, + "learning_rate": 1.1946436332029554e-05, + "loss": 0.3135, + "step": 14825 + }, + { + "epoch": 1.21, + "learning_rate": 1.1945893089960887e-05, + "loss": 0.2034, + "step": 14826 + }, + { + "epoch": 1.21, + "learning_rate": 1.1945349847892223e-05, + "loss": 0.3093, + "step": 14827 + }, + { + "epoch": 1.21, + "learning_rate": 1.1944806605823555e-05, + "loss": 0.2801, + "step": 14828 + }, + { + "epoch": 1.21, + "learning_rate": 1.1944263363754891e-05, + "loss": 0.2185, + "step": 14829 + }, + { + "epoch": 1.21, + "learning_rate": 1.1943720121686224e-05, + "loss": 0.1537, + "step": 14830 + }, + { + "epoch": 1.21, + "learning_rate": 1.194317687961756e-05, + "loss": 0.301, + "step": 14831 + }, + { + "epoch": 1.21, + "learning_rate": 1.1942633637548892e-05, + "loss": 0.2214, + "step": 14832 + }, + { + "epoch": 1.21, + "learning_rate": 1.1942090395480227e-05, + "loss": 0.1335, + "step": 14833 + }, + { + "epoch": 1.21, + "learning_rate": 1.194154715341156e-05, + "loss": 0.3333, + "step": 14834 + }, + { + "epoch": 1.21, + "learning_rate": 1.1941003911342895e-05, + "loss": 0.1898, + "step": 14835 + }, + { + "epoch": 1.21, + "learning_rate": 1.194046066927423e-05, + "loss": 0.3434, + "step": 14836 + }, + { + "epoch": 1.21, + "learning_rate": 1.1939917427205563e-05, + "loss": 0.1843, + "step": 14837 + }, + { + "epoch": 1.21, + "learning_rate": 1.1939374185136898e-05, + "loss": 0.3611, + "step": 14838 + }, + { + "epoch": 1.21, + "learning_rate": 1.1938830943068232e-05, + "loss": 0.2755, + "step": 14839 + }, + { + "epoch": 1.21, + "learning_rate": 1.1938287700999566e-05, + "loss": 0.2672, + "step": 14840 + }, + { + "epoch": 1.21, + "learning_rate": 1.19377444589309e-05, + "loss": 0.196, + "step": 14841 + }, + { + "epoch": 1.21, + "learning_rate": 1.1937201216862235e-05, + "loss": 0.4488, + "step": 14842 + }, + { + "epoch": 1.21, + "learning_rate": 1.1936657974793569e-05, + "loss": 0.3646, + "step": 14843 + }, + { + "epoch": 1.21, + "learning_rate": 1.1936114732724903e-05, + "loss": 0.4497, + "step": 14844 + }, + { + "epoch": 1.21, + "learning_rate": 1.1935571490656237e-05, + "loss": 0.4821, + "step": 14845 + }, + { + "epoch": 1.21, + "learning_rate": 1.1935028248587572e-05, + "loss": 0.2827, + "step": 14846 + }, + { + "epoch": 1.21, + "learning_rate": 1.1934485006518906e-05, + "loss": 0.0998, + "step": 14847 + }, + { + "epoch": 1.21, + "learning_rate": 1.1933941764450242e-05, + "loss": 0.6213, + "step": 14848 + }, + { + "epoch": 1.21, + "learning_rate": 1.1933398522381574e-05, + "loss": 0.4422, + "step": 14849 + }, + { + "epoch": 1.21, + "learning_rate": 1.193285528031291e-05, + "loss": 0.244, + "step": 14850 + }, + { + "epoch": 1.21, + "learning_rate": 1.1932312038244243e-05, + "loss": 0.3782, + "step": 14851 + }, + { + "epoch": 1.21, + "learning_rate": 1.1931768796175575e-05, + "loss": 0.6148, + "step": 14852 + }, + { + "epoch": 1.21, + "learning_rate": 1.1931225554106911e-05, + "loss": 0.3748, + "step": 14853 + }, + { + "epoch": 1.21, + "learning_rate": 1.1930682312038244e-05, + "loss": 0.3836, + "step": 14854 + }, + { + "epoch": 1.21, + "learning_rate": 1.193013906996958e-05, + "loss": 0.245, + "step": 14855 + }, + { + "epoch": 1.21, + "learning_rate": 1.1929595827900912e-05, + "loss": 0.3589, + "step": 14856 + }, + { + "epoch": 1.21, + "learning_rate": 1.1929052585832248e-05, + "loss": 0.364, + "step": 14857 + }, + { + "epoch": 1.21, + "learning_rate": 1.192850934376358e-05, + "loss": 0.5142, + "step": 14858 + }, + { + "epoch": 1.21, + "learning_rate": 1.1927966101694917e-05, + "loss": 0.2414, + "step": 14859 + }, + { + "epoch": 1.21, + "learning_rate": 1.1927422859626249e-05, + "loss": 0.6751, + "step": 14860 + }, + { + "epoch": 1.21, + "learning_rate": 1.1926879617557585e-05, + "loss": 0.4956, + "step": 14861 + }, + { + "epoch": 1.21, + "learning_rate": 1.1926336375488918e-05, + "loss": 0.2626, + "step": 14862 + }, + { + "epoch": 1.21, + "learning_rate": 1.1925793133420253e-05, + "loss": 0.3735, + "step": 14863 + }, + { + "epoch": 1.21, + "learning_rate": 1.1925249891351586e-05, + "loss": 0.3904, + "step": 14864 + }, + { + "epoch": 1.21, + "learning_rate": 1.1924706649282922e-05, + "loss": 0.2483, + "step": 14865 + }, + { + "epoch": 1.21, + "learning_rate": 1.1924163407214256e-05, + "loss": 0.2971, + "step": 14866 + }, + { + "epoch": 1.21, + "learning_rate": 1.192362016514559e-05, + "loss": 0.2691, + "step": 14867 + }, + { + "epoch": 1.21, + "learning_rate": 1.1923076923076925e-05, + "loss": 0.4703, + "step": 14868 + }, + { + "epoch": 1.21, + "learning_rate": 1.1922533681008259e-05, + "loss": 0.311, + "step": 14869 + }, + { + "epoch": 1.21, + "learning_rate": 1.1921990438939593e-05, + "loss": 0.2583, + "step": 14870 + }, + { + "epoch": 1.21, + "learning_rate": 1.1921447196870926e-05, + "loss": 0.3716, + "step": 14871 + }, + { + "epoch": 1.21, + "learning_rate": 1.1920903954802262e-05, + "loss": 0.4579, + "step": 14872 + }, + { + "epoch": 1.21, + "learning_rate": 1.1920360712733594e-05, + "loss": 0.2432, + "step": 14873 + }, + { + "epoch": 1.21, + "learning_rate": 1.191981747066493e-05, + "loss": 0.2059, + "step": 14874 + }, + { + "epoch": 1.21, + "learning_rate": 1.1919274228596263e-05, + "loss": 0.4096, + "step": 14875 + }, + { + "epoch": 1.21, + "learning_rate": 1.1918730986527598e-05, + "loss": 0.3717, + "step": 14876 + }, + { + "epoch": 1.21, + "learning_rate": 1.1918187744458931e-05, + "loss": 0.2606, + "step": 14877 + }, + { + "epoch": 1.21, + "learning_rate": 1.1917644502390267e-05, + "loss": 0.6187, + "step": 14878 + }, + { + "epoch": 1.21, + "learning_rate": 1.19171012603216e-05, + "loss": 0.4655, + "step": 14879 + }, + { + "epoch": 1.21, + "learning_rate": 1.1916558018252935e-05, + "loss": 0.2341, + "step": 14880 + }, + { + "epoch": 1.21, + "learning_rate": 1.1916014776184268e-05, + "loss": 0.5852, + "step": 14881 + }, + { + "epoch": 1.21, + "learning_rate": 1.1915471534115604e-05, + "loss": 0.4838, + "step": 14882 + }, + { + "epoch": 1.21, + "learning_rate": 1.1914928292046936e-05, + "loss": 0.3801, + "step": 14883 + }, + { + "epoch": 1.21, + "learning_rate": 1.1914385049978272e-05, + "loss": 0.1897, + "step": 14884 + }, + { + "epoch": 1.21, + "learning_rate": 1.1913841807909605e-05, + "loss": 0.1458, + "step": 14885 + }, + { + "epoch": 1.21, + "learning_rate": 1.191329856584094e-05, + "loss": 0.5451, + "step": 14886 + }, + { + "epoch": 1.21, + "learning_rate": 1.1912755323772273e-05, + "loss": 0.3296, + "step": 14887 + }, + { + "epoch": 1.21, + "learning_rate": 1.191221208170361e-05, + "loss": 0.4241, + "step": 14888 + }, + { + "epoch": 1.21, + "learning_rate": 1.1911668839634942e-05, + "loss": 0.1628, + "step": 14889 + }, + { + "epoch": 1.21, + "learning_rate": 1.1911125597566276e-05, + "loss": 0.3216, + "step": 14890 + }, + { + "epoch": 1.21, + "learning_rate": 1.191058235549761e-05, + "loss": 0.2704, + "step": 14891 + }, + { + "epoch": 1.21, + "learning_rate": 1.1910039113428944e-05, + "loss": 0.1939, + "step": 14892 + }, + { + "epoch": 1.21, + "learning_rate": 1.1909495871360279e-05, + "loss": 0.6213, + "step": 14893 + }, + { + "epoch": 1.21, + "learning_rate": 1.1908952629291613e-05, + "loss": 0.376, + "step": 14894 + }, + { + "epoch": 1.21, + "learning_rate": 1.1908409387222947e-05, + "loss": 0.3112, + "step": 14895 + }, + { + "epoch": 1.21, + "learning_rate": 1.1907866145154281e-05, + "loss": 0.4419, + "step": 14896 + }, + { + "epoch": 1.21, + "learning_rate": 1.1907322903085616e-05, + "loss": 0.5237, + "step": 14897 + }, + { + "epoch": 1.21, + "learning_rate": 1.190677966101695e-05, + "loss": 0.264, + "step": 14898 + }, + { + "epoch": 1.21, + "learning_rate": 1.1906236418948284e-05, + "loss": 0.2853, + "step": 14899 + }, + { + "epoch": 1.21, + "learning_rate": 1.1905693176879618e-05, + "loss": 0.2672, + "step": 14900 + }, + { + "epoch": 1.21, + "learning_rate": 1.1905149934810953e-05, + "loss": 0.4414, + "step": 14901 + }, + { + "epoch": 1.21, + "learning_rate": 1.1904606692742287e-05, + "loss": 0.23, + "step": 14902 + }, + { + "epoch": 1.21, + "learning_rate": 1.1904063450673623e-05, + "loss": 0.3164, + "step": 14903 + }, + { + "epoch": 1.21, + "learning_rate": 1.1903520208604955e-05, + "loss": 0.2751, + "step": 14904 + }, + { + "epoch": 1.21, + "learning_rate": 1.1902976966536291e-05, + "loss": 0.2562, + "step": 14905 + }, + { + "epoch": 1.21, + "learning_rate": 1.1902433724467624e-05, + "loss": 0.5188, + "step": 14906 + }, + { + "epoch": 1.21, + "learning_rate": 1.190189048239896e-05, + "loss": 0.4282, + "step": 14907 + }, + { + "epoch": 1.21, + "learning_rate": 1.1901347240330292e-05, + "loss": 0.3826, + "step": 14908 + }, + { + "epoch": 1.21, + "learning_rate": 1.1900803998261625e-05, + "loss": 0.5083, + "step": 14909 + }, + { + "epoch": 1.21, + "learning_rate": 1.190026075619296e-05, + "loss": 0.2587, + "step": 14910 + }, + { + "epoch": 1.22, + "learning_rate": 1.1899717514124293e-05, + "loss": 0.3236, + "step": 14911 + }, + { + "epoch": 1.22, + "learning_rate": 1.1899174272055629e-05, + "loss": 0.5319, + "step": 14912 + }, + { + "epoch": 1.22, + "learning_rate": 1.1898631029986962e-05, + "loss": 0.2268, + "step": 14913 + }, + { + "epoch": 1.22, + "learning_rate": 1.1898087787918298e-05, + "loss": 0.3806, + "step": 14914 + }, + { + "epoch": 1.22, + "learning_rate": 1.189754454584963e-05, + "loss": 0.4012, + "step": 14915 + }, + { + "epoch": 1.22, + "learning_rate": 1.1897001303780966e-05, + "loss": 0.1977, + "step": 14916 + }, + { + "epoch": 1.22, + "learning_rate": 1.1896458061712299e-05, + "loss": 0.6353, + "step": 14917 + }, + { + "epoch": 1.22, + "learning_rate": 1.1895914819643634e-05, + "loss": 0.3621, + "step": 14918 + }, + { + "epoch": 1.22, + "learning_rate": 1.1895371577574967e-05, + "loss": 0.4102, + "step": 14919 + }, + { + "epoch": 1.22, + "learning_rate": 1.1894828335506303e-05, + "loss": 0.1116, + "step": 14920 + }, + { + "epoch": 1.22, + "learning_rate": 1.1894285093437637e-05, + "loss": 0.3097, + "step": 14921 + }, + { + "epoch": 1.22, + "learning_rate": 1.1893741851368971e-05, + "loss": 0.2319, + "step": 14922 + }, + { + "epoch": 1.22, + "learning_rate": 1.1893198609300306e-05, + "loss": 0.2663, + "step": 14923 + }, + { + "epoch": 1.22, + "learning_rate": 1.189265536723164e-05, + "loss": 0.2437, + "step": 14924 + }, + { + "epoch": 1.22, + "learning_rate": 1.1892112125162974e-05, + "loss": 0.3686, + "step": 14925 + }, + { + "epoch": 1.22, + "learning_rate": 1.1891568883094308e-05, + "loss": 0.4577, + "step": 14926 + }, + { + "epoch": 1.22, + "learning_rate": 1.1891025641025643e-05, + "loss": 0.1501, + "step": 14927 + }, + { + "epoch": 1.22, + "learning_rate": 1.1890482398956975e-05, + "loss": 0.5374, + "step": 14928 + }, + { + "epoch": 1.22, + "learning_rate": 1.1889939156888311e-05, + "loss": 0.2617, + "step": 14929 + }, + { + "epoch": 1.22, + "learning_rate": 1.1889395914819644e-05, + "loss": 0.1098, + "step": 14930 + }, + { + "epoch": 1.22, + "learning_rate": 1.188885267275098e-05, + "loss": 0.1652, + "step": 14931 + }, + { + "epoch": 1.22, + "learning_rate": 1.1888309430682312e-05, + "loss": 0.2892, + "step": 14932 + }, + { + "epoch": 1.22, + "learning_rate": 1.1887766188613648e-05, + "loss": 0.2518, + "step": 14933 + }, + { + "epoch": 1.22, + "learning_rate": 1.188722294654498e-05, + "loss": 0.3985, + "step": 14934 + }, + { + "epoch": 1.22, + "learning_rate": 1.1886679704476316e-05, + "loss": 0.4829, + "step": 14935 + }, + { + "epoch": 1.22, + "learning_rate": 1.1886136462407649e-05, + "loss": 0.2645, + "step": 14936 + }, + { + "epoch": 1.22, + "learning_rate": 1.1885593220338985e-05, + "loss": 0.6353, + "step": 14937 + }, + { + "epoch": 1.22, + "learning_rate": 1.1885049978270317e-05, + "loss": 0.2038, + "step": 14938 + }, + { + "epoch": 1.22, + "learning_rate": 1.1884506736201653e-05, + "loss": 0.2051, + "step": 14939 + }, + { + "epoch": 1.22, + "learning_rate": 1.1883963494132986e-05, + "loss": 0.2478, + "step": 14940 + }, + { + "epoch": 1.22, + "learning_rate": 1.1883420252064322e-05, + "loss": 0.3112, + "step": 14941 + }, + { + "epoch": 1.22, + "learning_rate": 1.1882877009995654e-05, + "loss": 0.2685, + "step": 14942 + }, + { + "epoch": 1.22, + "learning_rate": 1.188233376792699e-05, + "loss": 0.1658, + "step": 14943 + }, + { + "epoch": 1.22, + "learning_rate": 1.1881790525858323e-05, + "loss": 0.2986, + "step": 14944 + }, + { + "epoch": 1.22, + "learning_rate": 1.1881247283789659e-05, + "loss": 0.452, + "step": 14945 + }, + { + "epoch": 1.22, + "learning_rate": 1.1880704041720991e-05, + "loss": 0.2431, + "step": 14946 + }, + { + "epoch": 1.22, + "learning_rate": 1.1880160799652325e-05, + "loss": 0.2695, + "step": 14947 + }, + { + "epoch": 1.22, + "learning_rate": 1.187961755758366e-05, + "loss": 0.2146, + "step": 14948 + }, + { + "epoch": 1.22, + "learning_rate": 1.1879074315514994e-05, + "loss": 0.1791, + "step": 14949 + }, + { + "epoch": 1.22, + "learning_rate": 1.1878531073446328e-05, + "loss": 0.2288, + "step": 14950 + }, + { + "epoch": 1.22, + "learning_rate": 1.1877987831377662e-05, + "loss": 0.3737, + "step": 14951 + }, + { + "epoch": 1.22, + "learning_rate": 1.1877444589308997e-05, + "loss": 0.4949, + "step": 14952 + }, + { + "epoch": 1.22, + "learning_rate": 1.187690134724033e-05, + "loss": 0.3573, + "step": 14953 + }, + { + "epoch": 1.22, + "learning_rate": 1.1876358105171665e-05, + "loss": 0.2929, + "step": 14954 + }, + { + "epoch": 1.22, + "learning_rate": 1.1875814863103e-05, + "loss": 0.249, + "step": 14955 + }, + { + "epoch": 1.22, + "learning_rate": 1.1875271621034335e-05, + "loss": 0.6628, + "step": 14956 + }, + { + "epoch": 1.22, + "learning_rate": 1.1874728378965668e-05, + "loss": 0.277, + "step": 14957 + }, + { + "epoch": 1.22, + "learning_rate": 1.1874185136897004e-05, + "loss": 0.3651, + "step": 14958 + }, + { + "epoch": 1.22, + "learning_rate": 1.1873641894828336e-05, + "loss": 0.4298, + "step": 14959 + }, + { + "epoch": 1.22, + "learning_rate": 1.1873098652759672e-05, + "loss": 0.3348, + "step": 14960 + }, + { + "epoch": 1.22, + "learning_rate": 1.1872555410691005e-05, + "loss": 0.4124, + "step": 14961 + }, + { + "epoch": 1.22, + "learning_rate": 1.187201216862234e-05, + "loss": 0.5234, + "step": 14962 + }, + { + "epoch": 1.22, + "learning_rate": 1.1871468926553673e-05, + "loss": 0.3323, + "step": 14963 + }, + { + "epoch": 1.22, + "learning_rate": 1.1870925684485009e-05, + "loss": 0.5021, + "step": 14964 + }, + { + "epoch": 1.22, + "learning_rate": 1.1870382442416342e-05, + "loss": 0.3118, + "step": 14965 + }, + { + "epoch": 1.22, + "learning_rate": 1.1869839200347678e-05, + "loss": 0.512, + "step": 14966 + }, + { + "epoch": 1.22, + "learning_rate": 1.186929595827901e-05, + "loss": 0.4648, + "step": 14967 + }, + { + "epoch": 1.22, + "learning_rate": 1.1868752716210343e-05, + "loss": 0.412, + "step": 14968 + }, + { + "epoch": 1.22, + "learning_rate": 1.1868209474141679e-05, + "loss": 0.3519, + "step": 14969 + }, + { + "epoch": 1.22, + "learning_rate": 1.1867666232073011e-05, + "loss": 0.1697, + "step": 14970 + }, + { + "epoch": 1.22, + "learning_rate": 1.1867122990004347e-05, + "loss": 0.4077, + "step": 14971 + }, + { + "epoch": 1.22, + "learning_rate": 1.186657974793568e-05, + "loss": 0.2854, + "step": 14972 + }, + { + "epoch": 1.22, + "learning_rate": 1.1866036505867015e-05, + "loss": 0.1058, + "step": 14973 + }, + { + "epoch": 1.22, + "learning_rate": 1.186549326379835e-05, + "loss": 0.5129, + "step": 14974 + }, + { + "epoch": 1.22, + "learning_rate": 1.1864950021729684e-05, + "loss": 0.4968, + "step": 14975 + }, + { + "epoch": 1.22, + "learning_rate": 1.1864406779661018e-05, + "loss": 0.3918, + "step": 14976 + }, + { + "epoch": 1.22, + "learning_rate": 1.1863863537592352e-05, + "loss": 0.2773, + "step": 14977 + }, + { + "epoch": 1.22, + "learning_rate": 1.1863320295523687e-05, + "loss": 0.3018, + "step": 14978 + }, + { + "epoch": 1.22, + "learning_rate": 1.186277705345502e-05, + "loss": 0.4614, + "step": 14979 + }, + { + "epoch": 1.22, + "learning_rate": 1.1862233811386355e-05, + "loss": 0.463, + "step": 14980 + }, + { + "epoch": 1.22, + "learning_rate": 1.186169056931769e-05, + "loss": 0.4174, + "step": 14981 + }, + { + "epoch": 1.22, + "learning_rate": 1.1861147327249024e-05, + "loss": 0.4159, + "step": 14982 + }, + { + "epoch": 1.22, + "learning_rate": 1.1860604085180358e-05, + "loss": 0.3252, + "step": 14983 + }, + { + "epoch": 1.22, + "learning_rate": 1.1860060843111692e-05, + "loss": 0.3506, + "step": 14984 + }, + { + "epoch": 1.22, + "learning_rate": 1.1859517601043026e-05, + "loss": 0.2046, + "step": 14985 + }, + { + "epoch": 1.22, + "learning_rate": 1.185897435897436e-05, + "loss": 0.3048, + "step": 14986 + }, + { + "epoch": 1.22, + "learning_rate": 1.1858431116905693e-05, + "loss": 0.4362, + "step": 14987 + }, + { + "epoch": 1.22, + "learning_rate": 1.1857887874837029e-05, + "loss": 0.2098, + "step": 14988 + }, + { + "epoch": 1.22, + "learning_rate": 1.1857344632768361e-05, + "loss": 0.3733, + "step": 14989 + }, + { + "epoch": 1.22, + "learning_rate": 1.1856801390699697e-05, + "loss": 0.3751, + "step": 14990 + }, + { + "epoch": 1.22, + "learning_rate": 1.185625814863103e-05, + "loss": 0.2598, + "step": 14991 + }, + { + "epoch": 1.22, + "learning_rate": 1.1855714906562366e-05, + "loss": 0.1488, + "step": 14992 + }, + { + "epoch": 1.22, + "learning_rate": 1.1855171664493698e-05, + "loss": 0.4289, + "step": 14993 + }, + { + "epoch": 1.22, + "learning_rate": 1.1854628422425034e-05, + "loss": 0.2569, + "step": 14994 + }, + { + "epoch": 1.22, + "learning_rate": 1.1854085180356367e-05, + "loss": 0.5066, + "step": 14995 + }, + { + "epoch": 1.22, + "learning_rate": 1.1853541938287703e-05, + "loss": 0.3434, + "step": 14996 + }, + { + "epoch": 1.22, + "learning_rate": 1.1852998696219035e-05, + "loss": 0.1826, + "step": 14997 + }, + { + "epoch": 1.22, + "learning_rate": 1.1852455454150371e-05, + "loss": 0.4311, + "step": 14998 + }, + { + "epoch": 1.22, + "learning_rate": 1.1851912212081704e-05, + "loss": 0.5664, + "step": 14999 + }, + { + "epoch": 1.22, + "learning_rate": 1.185136897001304e-05, + "loss": 0.2972, + "step": 15000 + }, + { + "epoch": 1.22, + "eval_accuracy": 0.8365766683647479, + "eval_loss": 0.4474148750305176, + "eval_runtime": 22.3807, + "eval_samples_per_second": 438.547, + "eval_steps_per_second": 3.44, + "step": 15000 + }, + { + "epoch": 1.22, + "learning_rate": 1.1850825727944372e-05, + "loss": 0.4469, + "step": 15001 + }, + { + "epoch": 1.22, + "learning_rate": 1.1850282485875708e-05, + "loss": 0.1768, + "step": 15002 + }, + { + "epoch": 1.22, + "learning_rate": 1.184973924380704e-05, + "loss": 0.5873, + "step": 15003 + }, + { + "epoch": 1.22, + "learning_rate": 1.1849196001738377e-05, + "loss": 0.1958, + "step": 15004 + }, + { + "epoch": 1.22, + "learning_rate": 1.1848652759669709e-05, + "loss": 0.3395, + "step": 15005 + }, + { + "epoch": 1.22, + "learning_rate": 1.1848109517601043e-05, + "loss": 0.3941, + "step": 15006 + }, + { + "epoch": 1.22, + "learning_rate": 1.1847566275532378e-05, + "loss": 0.4487, + "step": 15007 + }, + { + "epoch": 1.22, + "learning_rate": 1.1847023033463712e-05, + "loss": 0.3937, + "step": 15008 + }, + { + "epoch": 1.22, + "learning_rate": 1.1846479791395046e-05, + "loss": 0.7492, + "step": 15009 + }, + { + "epoch": 1.22, + "learning_rate": 1.184593654932638e-05, + "loss": 0.4489, + "step": 15010 + }, + { + "epoch": 1.22, + "learning_rate": 1.1845393307257716e-05, + "loss": 0.4372, + "step": 15011 + }, + { + "epoch": 1.22, + "learning_rate": 1.1844850065189049e-05, + "loss": 0.4316, + "step": 15012 + }, + { + "epoch": 1.22, + "learning_rate": 1.1844306823120385e-05, + "loss": 0.0872, + "step": 15013 + }, + { + "epoch": 1.22, + "learning_rate": 1.1843763581051717e-05, + "loss": 0.2652, + "step": 15014 + }, + { + "epoch": 1.22, + "learning_rate": 1.1843220338983053e-05, + "loss": 0.2285, + "step": 15015 + }, + { + "epoch": 1.22, + "learning_rate": 1.1842677096914386e-05, + "loss": 0.1363, + "step": 15016 + }, + { + "epoch": 1.22, + "learning_rate": 1.1842133854845722e-05, + "loss": 0.4366, + "step": 15017 + }, + { + "epoch": 1.22, + "learning_rate": 1.1841590612777054e-05, + "loss": 0.3214, + "step": 15018 + }, + { + "epoch": 1.22, + "learning_rate": 1.184104737070839e-05, + "loss": 0.4537, + "step": 15019 + }, + { + "epoch": 1.22, + "learning_rate": 1.1840504128639723e-05, + "loss": 0.2575, + "step": 15020 + }, + { + "epoch": 1.22, + "learning_rate": 1.1839960886571059e-05, + "loss": 0.4294, + "step": 15021 + }, + { + "epoch": 1.22, + "learning_rate": 1.1839417644502391e-05, + "loss": 0.1513, + "step": 15022 + }, + { + "epoch": 1.22, + "learning_rate": 1.1838874402433727e-05, + "loss": 0.3498, + "step": 15023 + }, + { + "epoch": 1.22, + "learning_rate": 1.183833116036506e-05, + "loss": 0.1958, + "step": 15024 + }, + { + "epoch": 1.22, + "learning_rate": 1.1837787918296392e-05, + "loss": 0.386, + "step": 15025 + }, + { + "epoch": 1.22, + "learning_rate": 1.1837244676227728e-05, + "loss": 0.4453, + "step": 15026 + }, + { + "epoch": 1.22, + "learning_rate": 1.183670143415906e-05, + "loss": 0.3516, + "step": 15027 + }, + { + "epoch": 1.22, + "learning_rate": 1.1836158192090396e-05, + "loss": 0.3013, + "step": 15028 + }, + { + "epoch": 1.22, + "learning_rate": 1.183561495002173e-05, + "loss": 0.4909, + "step": 15029 + }, + { + "epoch": 1.22, + "learning_rate": 1.1835071707953065e-05, + "loss": 0.5365, + "step": 15030 + }, + { + "epoch": 1.22, + "learning_rate": 1.1834528465884399e-05, + "loss": 0.1479, + "step": 15031 + }, + { + "epoch": 1.22, + "learning_rate": 1.1833985223815733e-05, + "loss": 0.3446, + "step": 15032 + }, + { + "epoch": 1.22, + "learning_rate": 1.1833441981747068e-05, + "loss": 0.2771, + "step": 15033 + }, + { + "epoch": 1.23, + "learning_rate": 1.1832898739678402e-05, + "loss": 0.154, + "step": 15034 + }, + { + "epoch": 1.23, + "learning_rate": 1.1832355497609736e-05, + "loss": 0.1766, + "step": 15035 + }, + { + "epoch": 1.23, + "learning_rate": 1.183181225554107e-05, + "loss": 0.4898, + "step": 15036 + }, + { + "epoch": 1.23, + "learning_rate": 1.1831269013472405e-05, + "loss": 0.4181, + "step": 15037 + }, + { + "epoch": 1.23, + "learning_rate": 1.1830725771403739e-05, + "loss": 0.3198, + "step": 15038 + }, + { + "epoch": 1.23, + "learning_rate": 1.1830182529335073e-05, + "loss": 0.4704, + "step": 15039 + }, + { + "epoch": 1.23, + "learning_rate": 1.1829639287266407e-05, + "loss": 0.3217, + "step": 15040 + }, + { + "epoch": 1.23, + "learning_rate": 1.1829096045197741e-05, + "loss": 0.3942, + "step": 15041 + }, + { + "epoch": 1.23, + "learning_rate": 1.1828552803129076e-05, + "loss": 0.3751, + "step": 15042 + }, + { + "epoch": 1.23, + "learning_rate": 1.182800956106041e-05, + "loss": 0.3753, + "step": 15043 + }, + { + "epoch": 1.23, + "learning_rate": 1.1827466318991742e-05, + "loss": 0.5664, + "step": 15044 + }, + { + "epoch": 1.23, + "learning_rate": 1.1826923076923078e-05, + "loss": 0.3135, + "step": 15045 + }, + { + "epoch": 1.23, + "learning_rate": 1.1826379834854411e-05, + "loss": 0.6824, + "step": 15046 + }, + { + "epoch": 1.23, + "learning_rate": 1.1825836592785747e-05, + "loss": 0.4739, + "step": 15047 + }, + { + "epoch": 1.23, + "learning_rate": 1.182529335071708e-05, + "loss": 0.5578, + "step": 15048 + }, + { + "epoch": 1.23, + "learning_rate": 1.1824750108648415e-05, + "loss": 0.1797, + "step": 15049 + }, + { + "epoch": 1.23, + "learning_rate": 1.1824206866579748e-05, + "loss": 0.3571, + "step": 15050 + }, + { + "epoch": 1.23, + "learning_rate": 1.1823663624511084e-05, + "loss": 0.2751, + "step": 15051 + }, + { + "epoch": 1.23, + "learning_rate": 1.1823120382442416e-05, + "loss": 0.2508, + "step": 15052 + }, + { + "epoch": 1.23, + "learning_rate": 1.1822577140373752e-05, + "loss": 0.3068, + "step": 15053 + }, + { + "epoch": 1.23, + "learning_rate": 1.1822033898305085e-05, + "loss": 0.3719, + "step": 15054 + }, + { + "epoch": 1.23, + "learning_rate": 1.182149065623642e-05, + "loss": 0.1336, + "step": 15055 + }, + { + "epoch": 1.23, + "learning_rate": 1.1820947414167753e-05, + "loss": 0.1579, + "step": 15056 + }, + { + "epoch": 1.23, + "learning_rate": 1.1820404172099089e-05, + "loss": 0.4577, + "step": 15057 + }, + { + "epoch": 1.23, + "learning_rate": 1.1819860930030422e-05, + "loss": 0.1536, + "step": 15058 + }, + { + "epoch": 1.23, + "learning_rate": 1.1819317687961758e-05, + "loss": 0.4371, + "step": 15059 + }, + { + "epoch": 1.23, + "learning_rate": 1.181877444589309e-05, + "loss": 0.6015, + "step": 15060 + }, + { + "epoch": 1.23, + "learning_rate": 1.1818231203824426e-05, + "loss": 0.3543, + "step": 15061 + }, + { + "epoch": 1.23, + "learning_rate": 1.1817687961755759e-05, + "loss": 0.2311, + "step": 15062 + }, + { + "epoch": 1.23, + "learning_rate": 1.1817144719687093e-05, + "loss": 0.2385, + "step": 15063 + }, + { + "epoch": 1.23, + "learning_rate": 1.1816601477618429e-05, + "loss": 0.3878, + "step": 15064 + }, + { + "epoch": 1.23, + "learning_rate": 1.1816058235549761e-05, + "loss": 0.3239, + "step": 15065 + }, + { + "epoch": 1.23, + "learning_rate": 1.1815514993481097e-05, + "loss": 0.3375, + "step": 15066 + }, + { + "epoch": 1.23, + "learning_rate": 1.181497175141243e-05, + "loss": 0.2724, + "step": 15067 + }, + { + "epoch": 1.23, + "learning_rate": 1.1814428509343766e-05, + "loss": 0.3092, + "step": 15068 + }, + { + "epoch": 1.23, + "learning_rate": 1.1813885267275098e-05, + "loss": 0.283, + "step": 15069 + }, + { + "epoch": 1.23, + "learning_rate": 1.1813342025206434e-05, + "loss": 0.1095, + "step": 15070 + }, + { + "epoch": 1.23, + "learning_rate": 1.1812798783137767e-05, + "loss": 0.4591, + "step": 15071 + }, + { + "epoch": 1.23, + "learning_rate": 1.1812255541069103e-05, + "loss": 0.3746, + "step": 15072 + }, + { + "epoch": 1.23, + "learning_rate": 1.1811712299000435e-05, + "loss": 0.2199, + "step": 15073 + }, + { + "epoch": 1.23, + "learning_rate": 1.1811169056931771e-05, + "loss": 0.5958, + "step": 15074 + }, + { + "epoch": 1.23, + "learning_rate": 1.1810625814863104e-05, + "loss": 0.5128, + "step": 15075 + }, + { + "epoch": 1.23, + "learning_rate": 1.181008257279444e-05, + "loss": 0.3773, + "step": 15076 + }, + { + "epoch": 1.23, + "learning_rate": 1.1809539330725772e-05, + "loss": 0.2276, + "step": 15077 + }, + { + "epoch": 1.23, + "learning_rate": 1.1808996088657108e-05, + "loss": 0.5539, + "step": 15078 + }, + { + "epoch": 1.23, + "learning_rate": 1.180845284658844e-05, + "loss": 0.3176, + "step": 15079 + }, + { + "epoch": 1.23, + "learning_rate": 1.1807909604519776e-05, + "loss": 0.46, + "step": 15080 + }, + { + "epoch": 1.23, + "learning_rate": 1.1807366362451109e-05, + "loss": 0.5126, + "step": 15081 + }, + { + "epoch": 1.23, + "learning_rate": 1.1806823120382443e-05, + "loss": 0.4084, + "step": 15082 + }, + { + "epoch": 1.23, + "learning_rate": 1.1806279878313777e-05, + "loss": 0.3934, + "step": 15083 + }, + { + "epoch": 1.23, + "learning_rate": 1.1805736636245112e-05, + "loss": 0.2084, + "step": 15084 + }, + { + "epoch": 1.23, + "learning_rate": 1.1805193394176446e-05, + "loss": 0.3209, + "step": 15085 + }, + { + "epoch": 1.23, + "learning_rate": 1.180465015210778e-05, + "loss": 0.48, + "step": 15086 + }, + { + "epoch": 1.23, + "learning_rate": 1.1804106910039114e-05, + "loss": 0.4414, + "step": 15087 + }, + { + "epoch": 1.23, + "learning_rate": 1.1803563667970449e-05, + "loss": 0.7471, + "step": 15088 + }, + { + "epoch": 1.23, + "learning_rate": 1.1803020425901783e-05, + "loss": 0.2706, + "step": 15089 + }, + { + "epoch": 1.23, + "learning_rate": 1.1802477183833117e-05, + "loss": 0.383, + "step": 15090 + }, + { + "epoch": 1.23, + "learning_rate": 1.1801933941764451e-05, + "loss": 0.2162, + "step": 15091 + }, + { + "epoch": 1.23, + "learning_rate": 1.1801390699695786e-05, + "loss": 0.2708, + "step": 15092 + }, + { + "epoch": 1.23, + "learning_rate": 1.180084745762712e-05, + "loss": 0.1825, + "step": 15093 + }, + { + "epoch": 1.23, + "learning_rate": 1.1800304215558454e-05, + "loss": 0.6242, + "step": 15094 + }, + { + "epoch": 1.23, + "learning_rate": 1.1799760973489788e-05, + "loss": 0.2934, + "step": 15095 + }, + { + "epoch": 1.23, + "learning_rate": 1.1799217731421122e-05, + "loss": 0.4105, + "step": 15096 + }, + { + "epoch": 1.23, + "learning_rate": 1.1798674489352457e-05, + "loss": 0.1645, + "step": 15097 + }, + { + "epoch": 1.23, + "learning_rate": 1.1798131247283791e-05, + "loss": 0.2862, + "step": 15098 + }, + { + "epoch": 1.23, + "learning_rate": 1.1797588005215125e-05, + "loss": 0.4813, + "step": 15099 + }, + { + "epoch": 1.23, + "learning_rate": 1.179704476314646e-05, + "loss": 0.2164, + "step": 15100 + }, + { + "epoch": 1.23, + "learning_rate": 1.1796501521077792e-05, + "loss": 0.4187, + "step": 15101 + }, + { + "epoch": 1.23, + "learning_rate": 1.1795958279009128e-05, + "loss": 0.2493, + "step": 15102 + }, + { + "epoch": 1.23, + "learning_rate": 1.179541503694046e-05, + "loss": 0.2934, + "step": 15103 + }, + { + "epoch": 1.23, + "learning_rate": 1.1794871794871796e-05, + "loss": 0.2129, + "step": 15104 + }, + { + "epoch": 1.23, + "learning_rate": 1.1794328552803129e-05, + "loss": 0.3777, + "step": 15105 + }, + { + "epoch": 1.23, + "learning_rate": 1.1793785310734465e-05, + "loss": 0.5, + "step": 15106 + }, + { + "epoch": 1.23, + "learning_rate": 1.1793242068665797e-05, + "loss": 0.2168, + "step": 15107 + }, + { + "epoch": 1.23, + "learning_rate": 1.1792698826597133e-05, + "loss": 0.2799, + "step": 15108 + }, + { + "epoch": 1.23, + "learning_rate": 1.1792155584528466e-05, + "loss": 0.3535, + "step": 15109 + }, + { + "epoch": 1.23, + "learning_rate": 1.1791612342459802e-05, + "loss": 0.5249, + "step": 15110 + }, + { + "epoch": 1.23, + "learning_rate": 1.1791069100391134e-05, + "loss": 0.2022, + "step": 15111 + }, + { + "epoch": 1.23, + "learning_rate": 1.179052585832247e-05, + "loss": 0.2215, + "step": 15112 + }, + { + "epoch": 1.23, + "learning_rate": 1.1789982616253803e-05, + "loss": 0.458, + "step": 15113 + }, + { + "epoch": 1.23, + "learning_rate": 1.1789439374185139e-05, + "loss": 0.457, + "step": 15114 + }, + { + "epoch": 1.23, + "learning_rate": 1.1788896132116471e-05, + "loss": 0.4328, + "step": 15115 + }, + { + "epoch": 1.23, + "learning_rate": 1.1788352890047807e-05, + "loss": 0.2474, + "step": 15116 + }, + { + "epoch": 1.23, + "learning_rate": 1.178780964797914e-05, + "loss": 0.1812, + "step": 15117 + }, + { + "epoch": 1.23, + "learning_rate": 1.1787266405910475e-05, + "loss": 0.3095, + "step": 15118 + }, + { + "epoch": 1.23, + "learning_rate": 1.178672316384181e-05, + "loss": 0.4241, + "step": 15119 + }, + { + "epoch": 1.23, + "learning_rate": 1.1786179921773142e-05, + "loss": 0.3092, + "step": 15120 + }, + { + "epoch": 1.23, + "learning_rate": 1.1785636679704478e-05, + "loss": 0.4851, + "step": 15121 + }, + { + "epoch": 1.23, + "learning_rate": 1.178509343763581e-05, + "loss": 0.4104, + "step": 15122 + }, + { + "epoch": 1.23, + "learning_rate": 1.1784550195567147e-05, + "loss": 0.2665, + "step": 15123 + }, + { + "epoch": 1.23, + "learning_rate": 1.178400695349848e-05, + "loss": 0.1911, + "step": 15124 + }, + { + "epoch": 1.23, + "learning_rate": 1.1783463711429815e-05, + "loss": 0.115, + "step": 15125 + }, + { + "epoch": 1.23, + "learning_rate": 1.1782920469361148e-05, + "loss": 0.2715, + "step": 15126 + }, + { + "epoch": 1.23, + "learning_rate": 1.1782377227292484e-05, + "loss": 0.2936, + "step": 15127 + }, + { + "epoch": 1.23, + "learning_rate": 1.1781833985223816e-05, + "loss": 0.439, + "step": 15128 + }, + { + "epoch": 1.23, + "learning_rate": 1.1781290743155152e-05, + "loss": 0.2446, + "step": 15129 + }, + { + "epoch": 1.23, + "learning_rate": 1.1780747501086485e-05, + "loss": 0.4628, + "step": 15130 + }, + { + "epoch": 1.23, + "learning_rate": 1.178020425901782e-05, + "loss": 0.1752, + "step": 15131 + }, + { + "epoch": 1.23, + "learning_rate": 1.1779661016949153e-05, + "loss": 0.4548, + "step": 15132 + }, + { + "epoch": 1.23, + "learning_rate": 1.1779117774880489e-05, + "loss": 0.2106, + "step": 15133 + }, + { + "epoch": 1.23, + "learning_rate": 1.1778574532811821e-05, + "loss": 0.5198, + "step": 15134 + }, + { + "epoch": 1.23, + "learning_rate": 1.1778031290743157e-05, + "loss": 0.3697, + "step": 15135 + }, + { + "epoch": 1.23, + "learning_rate": 1.177748804867449e-05, + "loss": 0.085, + "step": 15136 + }, + { + "epoch": 1.23, + "learning_rate": 1.1776944806605826e-05, + "loss": 0.1563, + "step": 15137 + }, + { + "epoch": 1.23, + "learning_rate": 1.1776401564537158e-05, + "loss": 0.2144, + "step": 15138 + }, + { + "epoch": 1.23, + "learning_rate": 1.1775858322468493e-05, + "loss": 0.1649, + "step": 15139 + }, + { + "epoch": 1.23, + "learning_rate": 1.1775315080399827e-05, + "loss": 0.4697, + "step": 15140 + }, + { + "epoch": 1.23, + "learning_rate": 1.1774771838331161e-05, + "loss": 0.3094, + "step": 15141 + }, + { + "epoch": 1.23, + "learning_rate": 1.1774228596262495e-05, + "loss": 0.2535, + "step": 15142 + }, + { + "epoch": 1.23, + "learning_rate": 1.177368535419383e-05, + "loss": 0.1472, + "step": 15143 + }, + { + "epoch": 1.23, + "learning_rate": 1.1773142112125164e-05, + "loss": 0.2757, + "step": 15144 + }, + { + "epoch": 1.23, + "learning_rate": 1.1772598870056498e-05, + "loss": 0.3588, + "step": 15145 + }, + { + "epoch": 1.23, + "learning_rate": 1.1772055627987832e-05, + "loss": 0.4025, + "step": 15146 + }, + { + "epoch": 1.23, + "learning_rate": 1.1771512385919166e-05, + "loss": 0.1647, + "step": 15147 + }, + { + "epoch": 1.23, + "learning_rate": 1.17709691438505e-05, + "loss": 0.418, + "step": 15148 + }, + { + "epoch": 1.23, + "learning_rate": 1.1770425901781835e-05, + "loss": 0.5096, + "step": 15149 + }, + { + "epoch": 1.23, + "learning_rate": 1.176988265971317e-05, + "loss": 0.5122, + "step": 15150 + }, + { + "epoch": 1.23, + "learning_rate": 1.1769339417644503e-05, + "loss": 0.5906, + "step": 15151 + }, + { + "epoch": 1.23, + "learning_rate": 1.1768796175575838e-05, + "loss": 0.2664, + "step": 15152 + }, + { + "epoch": 1.23, + "learning_rate": 1.1768252933507172e-05, + "loss": 0.2738, + "step": 15153 + }, + { + "epoch": 1.23, + "learning_rate": 1.1767709691438506e-05, + "loss": 0.457, + "step": 15154 + }, + { + "epoch": 1.23, + "learning_rate": 1.176716644936984e-05, + "loss": 0.289, + "step": 15155 + }, + { + "epoch": 1.24, + "learning_rate": 1.1766623207301176e-05, + "loss": 0.2994, + "step": 15156 + }, + { + "epoch": 1.24, + "learning_rate": 1.1766079965232509e-05, + "loss": 0.5111, + "step": 15157 + }, + { + "epoch": 1.24, + "learning_rate": 1.1765536723163841e-05, + "loss": 0.2023, + "step": 15158 + }, + { + "epoch": 1.24, + "learning_rate": 1.1764993481095177e-05, + "loss": 0.7165, + "step": 15159 + }, + { + "epoch": 1.24, + "learning_rate": 1.176445023902651e-05, + "loss": 0.448, + "step": 15160 + }, + { + "epoch": 1.24, + "learning_rate": 1.1763906996957846e-05, + "loss": 0.5349, + "step": 15161 + }, + { + "epoch": 1.24, + "learning_rate": 1.1763363754889178e-05, + "loss": 0.3915, + "step": 15162 + }, + { + "epoch": 1.24, + "learning_rate": 1.1762820512820514e-05, + "loss": 0.4839, + "step": 15163 + }, + { + "epoch": 1.24, + "learning_rate": 1.1762277270751847e-05, + "loss": 0.4343, + "step": 15164 + }, + { + "epoch": 1.24, + "learning_rate": 1.1761734028683183e-05, + "loss": 0.3841, + "step": 15165 + }, + { + "epoch": 1.24, + "learning_rate": 1.1761190786614515e-05, + "loss": 0.1119, + "step": 15166 + }, + { + "epoch": 1.24, + "learning_rate": 1.1760647544545851e-05, + "loss": 0.2249, + "step": 15167 + }, + { + "epoch": 1.24, + "learning_rate": 1.1760104302477184e-05, + "loss": 0.2948, + "step": 15168 + }, + { + "epoch": 1.24, + "learning_rate": 1.175956106040852e-05, + "loss": 0.612, + "step": 15169 + }, + { + "epoch": 1.24, + "learning_rate": 1.1759017818339852e-05, + "loss": 0.2706, + "step": 15170 + }, + { + "epoch": 1.24, + "learning_rate": 1.1758474576271188e-05, + "loss": 0.3539, + "step": 15171 + }, + { + "epoch": 1.24, + "learning_rate": 1.1757931334202522e-05, + "loss": 0.5854, + "step": 15172 + }, + { + "epoch": 1.24, + "learning_rate": 1.1757388092133856e-05, + "loss": 0.4464, + "step": 15173 + }, + { + "epoch": 1.24, + "learning_rate": 1.175684485006519e-05, + "loss": 0.2132, + "step": 15174 + }, + { + "epoch": 1.24, + "learning_rate": 1.1756301607996525e-05, + "loss": 0.3108, + "step": 15175 + }, + { + "epoch": 1.24, + "learning_rate": 1.175575836592786e-05, + "loss": 0.3092, + "step": 15176 + }, + { + "epoch": 1.24, + "learning_rate": 1.1755215123859192e-05, + "loss": 0.4045, + "step": 15177 + }, + { + "epoch": 1.24, + "learning_rate": 1.1754671881790528e-05, + "loss": 0.4876, + "step": 15178 + }, + { + "epoch": 1.24, + "learning_rate": 1.175412863972186e-05, + "loss": 0.3463, + "step": 15179 + }, + { + "epoch": 1.24, + "learning_rate": 1.1753585397653196e-05, + "loss": 0.3862, + "step": 15180 + }, + { + "epoch": 1.24, + "learning_rate": 1.1753042155584529e-05, + "loss": 0.2533, + "step": 15181 + }, + { + "epoch": 1.24, + "learning_rate": 1.1752498913515865e-05, + "loss": 0.3869, + "step": 15182 + }, + { + "epoch": 1.24, + "learning_rate": 1.1751955671447197e-05, + "loss": 0.4089, + "step": 15183 + }, + { + "epoch": 1.24, + "learning_rate": 1.1751412429378533e-05, + "loss": 0.5156, + "step": 15184 + }, + { + "epoch": 1.24, + "learning_rate": 1.1750869187309866e-05, + "loss": 0.5011, + "step": 15185 + }, + { + "epoch": 1.24, + "learning_rate": 1.1750325945241201e-05, + "loss": 0.381, + "step": 15186 + }, + { + "epoch": 1.24, + "learning_rate": 1.1749782703172534e-05, + "loss": 0.1628, + "step": 15187 + }, + { + "epoch": 1.24, + "learning_rate": 1.174923946110387e-05, + "loss": 0.2559, + "step": 15188 + }, + { + "epoch": 1.24, + "learning_rate": 1.1748696219035202e-05, + "loss": 0.3579, + "step": 15189 + }, + { + "epoch": 1.24, + "learning_rate": 1.1748152976966538e-05, + "loss": 0.1669, + "step": 15190 + }, + { + "epoch": 1.24, + "learning_rate": 1.1747609734897871e-05, + "loss": 0.2482, + "step": 15191 + }, + { + "epoch": 1.24, + "learning_rate": 1.1747066492829207e-05, + "loss": 0.2104, + "step": 15192 + }, + { + "epoch": 1.24, + "learning_rate": 1.174652325076054e-05, + "loss": 0.2876, + "step": 15193 + }, + { + "epoch": 1.24, + "learning_rate": 1.1745980008691875e-05, + "loss": 0.3374, + "step": 15194 + }, + { + "epoch": 1.24, + "learning_rate": 1.1745436766623208e-05, + "loss": 0.2982, + "step": 15195 + }, + { + "epoch": 1.24, + "learning_rate": 1.1744893524554542e-05, + "loss": 0.2747, + "step": 15196 + }, + { + "epoch": 1.24, + "learning_rate": 1.1744350282485876e-05, + "loss": 0.6022, + "step": 15197 + }, + { + "epoch": 1.24, + "learning_rate": 1.174380704041721e-05, + "loss": 0.2541, + "step": 15198 + }, + { + "epoch": 1.24, + "learning_rate": 1.1743263798348545e-05, + "loss": 0.3093, + "step": 15199 + }, + { + "epoch": 1.24, + "learning_rate": 1.1742720556279879e-05, + "loss": 0.1537, + "step": 15200 + }, + { + "epoch": 1.24, + "learning_rate": 1.1742177314211213e-05, + "loss": 0.4422, + "step": 15201 + }, + { + "epoch": 1.24, + "learning_rate": 1.1741634072142547e-05, + "loss": 0.3105, + "step": 15202 + }, + { + "epoch": 1.24, + "learning_rate": 1.1741090830073882e-05, + "loss": 0.2758, + "step": 15203 + }, + { + "epoch": 1.24, + "learning_rate": 1.1740547588005216e-05, + "loss": 0.4667, + "step": 15204 + }, + { + "epoch": 1.24, + "learning_rate": 1.174000434593655e-05, + "loss": 0.3301, + "step": 15205 + }, + { + "epoch": 1.24, + "learning_rate": 1.1739461103867884e-05, + "loss": 0.3516, + "step": 15206 + }, + { + "epoch": 1.24, + "learning_rate": 1.1738917861799219e-05, + "loss": 0.497, + "step": 15207 + }, + { + "epoch": 1.24, + "learning_rate": 1.1738374619730553e-05, + "loss": 0.3268, + "step": 15208 + }, + { + "epoch": 1.24, + "learning_rate": 1.1737831377661889e-05, + "loss": 0.2532, + "step": 15209 + }, + { + "epoch": 1.24, + "learning_rate": 1.1737288135593221e-05, + "loss": 0.3563, + "step": 15210 + }, + { + "epoch": 1.24, + "learning_rate": 1.1736744893524557e-05, + "loss": 0.4088, + "step": 15211 + }, + { + "epoch": 1.24, + "learning_rate": 1.173620165145589e-05, + "loss": 0.3092, + "step": 15212 + }, + { + "epoch": 1.24, + "learning_rate": 1.1735658409387226e-05, + "loss": 0.2126, + "step": 15213 + }, + { + "epoch": 1.24, + "learning_rate": 1.1735115167318558e-05, + "loss": 0.2357, + "step": 15214 + }, + { + "epoch": 1.24, + "learning_rate": 1.173457192524989e-05, + "loss": 0.3063, + "step": 15215 + }, + { + "epoch": 1.24, + "learning_rate": 1.1734028683181227e-05, + "loss": 0.2043, + "step": 15216 + }, + { + "epoch": 1.24, + "learning_rate": 1.173348544111256e-05, + "loss": 0.2761, + "step": 15217 + }, + { + "epoch": 1.24, + "learning_rate": 1.1732942199043895e-05, + "loss": 0.211, + "step": 15218 + }, + { + "epoch": 1.24, + "learning_rate": 1.1732398956975228e-05, + "loss": 0.3209, + "step": 15219 + }, + { + "epoch": 1.24, + "learning_rate": 1.1731855714906564e-05, + "loss": 0.1846, + "step": 15220 + }, + { + "epoch": 1.24, + "learning_rate": 1.1731312472837896e-05, + "loss": 0.2567, + "step": 15221 + }, + { + "epoch": 1.24, + "learning_rate": 1.1730769230769232e-05, + "loss": 0.4275, + "step": 15222 + }, + { + "epoch": 1.24, + "learning_rate": 1.1730225988700565e-05, + "loss": 0.2218, + "step": 15223 + }, + { + "epoch": 1.24, + "learning_rate": 1.17296827466319e-05, + "loss": 0.3742, + "step": 15224 + }, + { + "epoch": 1.24, + "learning_rate": 1.1729139504563233e-05, + "loss": 0.3355, + "step": 15225 + }, + { + "epoch": 1.24, + "learning_rate": 1.1728596262494569e-05, + "loss": 0.4303, + "step": 15226 + }, + { + "epoch": 1.24, + "learning_rate": 1.1728053020425903e-05, + "loss": 0.4698, + "step": 15227 + }, + { + "epoch": 1.24, + "learning_rate": 1.1727509778357237e-05, + "loss": 0.5348, + "step": 15228 + }, + { + "epoch": 1.24, + "learning_rate": 1.1726966536288572e-05, + "loss": 0.4277, + "step": 15229 + }, + { + "epoch": 1.24, + "learning_rate": 1.1726423294219906e-05, + "loss": 0.3763, + "step": 15230 + }, + { + "epoch": 1.24, + "learning_rate": 1.172588005215124e-05, + "loss": 0.2294, + "step": 15231 + }, + { + "epoch": 1.24, + "learning_rate": 1.1725336810082574e-05, + "loss": 0.2425, + "step": 15232 + }, + { + "epoch": 1.24, + "learning_rate": 1.1724793568013909e-05, + "loss": 0.3495, + "step": 15233 + }, + { + "epoch": 1.24, + "learning_rate": 1.1724250325945241e-05, + "loss": 0.162, + "step": 15234 + }, + { + "epoch": 1.24, + "learning_rate": 1.1723707083876577e-05, + "loss": 0.4946, + "step": 15235 + }, + { + "epoch": 1.24, + "learning_rate": 1.172316384180791e-05, + "loss": 0.3377, + "step": 15236 + }, + { + "epoch": 1.24, + "learning_rate": 1.1722620599739246e-05, + "loss": 0.4653, + "step": 15237 + }, + { + "epoch": 1.24, + "learning_rate": 1.1722077357670578e-05, + "loss": 0.2529, + "step": 15238 + }, + { + "epoch": 1.24, + "learning_rate": 1.1721534115601914e-05, + "loss": 0.433, + "step": 15239 + }, + { + "epoch": 1.24, + "learning_rate": 1.1720990873533247e-05, + "loss": 0.3479, + "step": 15240 + }, + { + "epoch": 1.24, + "learning_rate": 1.1720447631464582e-05, + "loss": 0.354, + "step": 15241 + }, + { + "epoch": 1.24, + "learning_rate": 1.1719904389395915e-05, + "loss": 0.5292, + "step": 15242 + }, + { + "epoch": 1.24, + "learning_rate": 1.1719361147327251e-05, + "loss": 0.2912, + "step": 15243 + }, + { + "epoch": 1.24, + "learning_rate": 1.1718817905258583e-05, + "loss": 0.2474, + "step": 15244 + }, + { + "epoch": 1.24, + "learning_rate": 1.171827466318992e-05, + "loss": 0.2062, + "step": 15245 + }, + { + "epoch": 1.24, + "learning_rate": 1.1717731421121252e-05, + "loss": 0.3034, + "step": 15246 + }, + { + "epoch": 1.24, + "learning_rate": 1.1717188179052588e-05, + "loss": 0.2277, + "step": 15247 + }, + { + "epoch": 1.24, + "learning_rate": 1.171664493698392e-05, + "loss": 0.4213, + "step": 15248 + }, + { + "epoch": 1.24, + "learning_rate": 1.1716101694915256e-05, + "loss": 0.1942, + "step": 15249 + }, + { + "epoch": 1.24, + "learning_rate": 1.1715558452846589e-05, + "loss": 0.2992, + "step": 15250 + }, + { + "epoch": 1.24, + "eval_accuracy": 0.8375955170657158, + "eval_loss": 0.44810378551483154, + "eval_runtime": 22.4321, + "eval_samples_per_second": 437.543, + "eval_steps_per_second": 3.433, + "step": 15250 + }, + { + "epoch": 1.24, + "learning_rate": 1.1715015210777925e-05, + "loss": 0.2123, + "step": 15251 + }, + { + "epoch": 1.24, + "learning_rate": 1.1714471968709257e-05, + "loss": 0.4511, + "step": 15252 + }, + { + "epoch": 1.24, + "learning_rate": 1.1713928726640592e-05, + "loss": 0.4264, + "step": 15253 + }, + { + "epoch": 1.24, + "learning_rate": 1.1713385484571926e-05, + "loss": 0.2155, + "step": 15254 + }, + { + "epoch": 1.24, + "learning_rate": 1.171284224250326e-05, + "loss": 0.2134, + "step": 15255 + }, + { + "epoch": 1.24, + "learning_rate": 1.1712299000434594e-05, + "loss": 0.3409, + "step": 15256 + }, + { + "epoch": 1.24, + "learning_rate": 1.1711755758365928e-05, + "loss": 0.3366, + "step": 15257 + }, + { + "epoch": 1.24, + "learning_rate": 1.1711212516297263e-05, + "loss": 0.2184, + "step": 15258 + }, + { + "epoch": 1.24, + "learning_rate": 1.1710669274228597e-05, + "loss": 0.2373, + "step": 15259 + }, + { + "epoch": 1.24, + "learning_rate": 1.1710126032159931e-05, + "loss": 0.636, + "step": 15260 + }, + { + "epoch": 1.24, + "learning_rate": 1.1709582790091265e-05, + "loss": 0.0617, + "step": 15261 + }, + { + "epoch": 1.24, + "learning_rate": 1.17090395480226e-05, + "loss": 0.2776, + "step": 15262 + }, + { + "epoch": 1.24, + "learning_rate": 1.1708496305953934e-05, + "loss": 0.4302, + "step": 15263 + }, + { + "epoch": 1.24, + "learning_rate": 1.170795306388527e-05, + "loss": 0.4225, + "step": 15264 + }, + { + "epoch": 1.24, + "learning_rate": 1.1707409821816602e-05, + "loss": 0.1651, + "step": 15265 + }, + { + "epoch": 1.24, + "learning_rate": 1.1706866579747938e-05, + "loss": 0.3843, + "step": 15266 + }, + { + "epoch": 1.24, + "learning_rate": 1.170632333767927e-05, + "loss": 0.2168, + "step": 15267 + }, + { + "epoch": 1.24, + "learning_rate": 1.1705780095610607e-05, + "loss": 0.1729, + "step": 15268 + }, + { + "epoch": 1.24, + "learning_rate": 1.170523685354194e-05, + "loss": 0.2529, + "step": 15269 + }, + { + "epoch": 1.24, + "learning_rate": 1.1704693611473275e-05, + "loss": 0.3076, + "step": 15270 + }, + { + "epoch": 1.24, + "learning_rate": 1.1704150369404608e-05, + "loss": 0.5388, + "step": 15271 + }, + { + "epoch": 1.24, + "learning_rate": 1.170360712733594e-05, + "loss": 0.119, + "step": 15272 + }, + { + "epoch": 1.24, + "learning_rate": 1.1703063885267276e-05, + "loss": 0.4673, + "step": 15273 + }, + { + "epoch": 1.24, + "learning_rate": 1.1702520643198609e-05, + "loss": 0.1895, + "step": 15274 + }, + { + "epoch": 1.24, + "learning_rate": 1.1701977401129945e-05, + "loss": 0.2595, + "step": 15275 + }, + { + "epoch": 1.24, + "learning_rate": 1.1701434159061277e-05, + "loss": 0.235, + "step": 15276 + }, + { + "epoch": 1.24, + "learning_rate": 1.1700890916992613e-05, + "loss": 0.1707, + "step": 15277 + }, + { + "epoch": 1.24, + "learning_rate": 1.1700347674923946e-05, + "loss": 0.1468, + "step": 15278 + }, + { + "epoch": 1.25, + "learning_rate": 1.1699804432855282e-05, + "loss": 0.4252, + "step": 15279 + }, + { + "epoch": 1.25, + "learning_rate": 1.1699261190786616e-05, + "loss": 0.2168, + "step": 15280 + }, + { + "epoch": 1.25, + "learning_rate": 1.169871794871795e-05, + "loss": 0.2235, + "step": 15281 + }, + { + "epoch": 1.25, + "learning_rate": 1.1698174706649284e-05, + "loss": 0.4356, + "step": 15282 + }, + { + "epoch": 1.25, + "learning_rate": 1.1697631464580618e-05, + "loss": 0.4343, + "step": 15283 + }, + { + "epoch": 1.25, + "learning_rate": 1.1697088222511953e-05, + "loss": 0.3361, + "step": 15284 + }, + { + "epoch": 1.25, + "learning_rate": 1.1696544980443287e-05, + "loss": 0.4416, + "step": 15285 + }, + { + "epoch": 1.25, + "learning_rate": 1.1696001738374621e-05, + "loss": 0.4156, + "step": 15286 + }, + { + "epoch": 1.25, + "learning_rate": 1.1695458496305955e-05, + "loss": 0.2717, + "step": 15287 + }, + { + "epoch": 1.25, + "learning_rate": 1.169491525423729e-05, + "loss": 0.3227, + "step": 15288 + }, + { + "epoch": 1.25, + "learning_rate": 1.1694372012168624e-05, + "loss": 0.5398, + "step": 15289 + }, + { + "epoch": 1.25, + "learning_rate": 1.1693828770099958e-05, + "loss": 0.4769, + "step": 15290 + }, + { + "epoch": 1.25, + "learning_rate": 1.169328552803129e-05, + "loss": 0.2261, + "step": 15291 + }, + { + "epoch": 1.25, + "learning_rate": 1.1692742285962627e-05, + "loss": 0.2066, + "step": 15292 + }, + { + "epoch": 1.25, + "learning_rate": 1.1692199043893959e-05, + "loss": 0.3403, + "step": 15293 + }, + { + "epoch": 1.25, + "learning_rate": 1.1691655801825295e-05, + "loss": 0.3204, + "step": 15294 + }, + { + "epoch": 1.25, + "learning_rate": 1.1691112559756628e-05, + "loss": 0.3078, + "step": 15295 + }, + { + "epoch": 1.25, + "learning_rate": 1.1690569317687963e-05, + "loss": 0.1854, + "step": 15296 + }, + { + "epoch": 1.25, + "learning_rate": 1.1690026075619296e-05, + "loss": 0.3426, + "step": 15297 + }, + { + "epoch": 1.25, + "learning_rate": 1.1689482833550632e-05, + "loss": 0.2953, + "step": 15298 + }, + { + "epoch": 1.25, + "learning_rate": 1.1688939591481964e-05, + "loss": 0.5077, + "step": 15299 + }, + { + "epoch": 1.25, + "learning_rate": 1.16883963494133e-05, + "loss": 0.3282, + "step": 15300 + }, + { + "epoch": 1.25, + "learning_rate": 1.1687853107344633e-05, + "loss": 0.2581, + "step": 15301 + }, + { + "epoch": 1.25, + "learning_rate": 1.1687309865275969e-05, + "loss": 0.2615, + "step": 15302 + }, + { + "epoch": 1.25, + "learning_rate": 1.1686766623207301e-05, + "loss": 0.6515, + "step": 15303 + }, + { + "epoch": 1.25, + "learning_rate": 1.1686223381138637e-05, + "loss": 0.5777, + "step": 15304 + }, + { + "epoch": 1.25, + "learning_rate": 1.168568013906997e-05, + "loss": 0.3021, + "step": 15305 + }, + { + "epoch": 1.25, + "learning_rate": 1.1685136897001306e-05, + "loss": 0.1498, + "step": 15306 + }, + { + "epoch": 1.25, + "learning_rate": 1.1684593654932638e-05, + "loss": 0.4729, + "step": 15307 + }, + { + "epoch": 1.25, + "learning_rate": 1.1684050412863974e-05, + "loss": 0.3264, + "step": 15308 + }, + { + "epoch": 1.25, + "learning_rate": 1.1683507170795307e-05, + "loss": 0.2711, + "step": 15309 + }, + { + "epoch": 1.25, + "learning_rate": 1.1682963928726641e-05, + "loss": 0.3145, + "step": 15310 + }, + { + "epoch": 1.25, + "learning_rate": 1.1682420686657975e-05, + "loss": 0.391, + "step": 15311 + }, + { + "epoch": 1.25, + "learning_rate": 1.168187744458931e-05, + "loss": 0.2096, + "step": 15312 + }, + { + "epoch": 1.25, + "learning_rate": 1.1681334202520644e-05, + "loss": 0.1616, + "step": 15313 + }, + { + "epoch": 1.25, + "learning_rate": 1.1680790960451978e-05, + "loss": 0.1444, + "step": 15314 + }, + { + "epoch": 1.25, + "learning_rate": 1.1680247718383312e-05, + "loss": 0.1382, + "step": 15315 + }, + { + "epoch": 1.25, + "learning_rate": 1.1679704476314646e-05, + "loss": 0.528, + "step": 15316 + }, + { + "epoch": 1.25, + "learning_rate": 1.1679161234245982e-05, + "loss": 0.2792, + "step": 15317 + }, + { + "epoch": 1.25, + "learning_rate": 1.1678617992177315e-05, + "loss": 0.1755, + "step": 15318 + }, + { + "epoch": 1.25, + "learning_rate": 1.167807475010865e-05, + "loss": 0.51, + "step": 15319 + }, + { + "epoch": 1.25, + "learning_rate": 1.1677531508039983e-05, + "loss": 0.3255, + "step": 15320 + }, + { + "epoch": 1.25, + "learning_rate": 1.167698826597132e-05, + "loss": 0.2962, + "step": 15321 + }, + { + "epoch": 1.25, + "learning_rate": 1.1676445023902652e-05, + "loss": 0.3815, + "step": 15322 + }, + { + "epoch": 1.25, + "learning_rate": 1.1675901781833988e-05, + "loss": 0.4381, + "step": 15323 + }, + { + "epoch": 1.25, + "learning_rate": 1.167535853976532e-05, + "loss": 0.2405, + "step": 15324 + }, + { + "epoch": 1.25, + "learning_rate": 1.1674815297696656e-05, + "loss": 0.3086, + "step": 15325 + }, + { + "epoch": 1.25, + "learning_rate": 1.1674272055627989e-05, + "loss": 0.3893, + "step": 15326 + }, + { + "epoch": 1.25, + "learning_rate": 1.1673728813559325e-05, + "loss": 0.2454, + "step": 15327 + }, + { + "epoch": 1.25, + "learning_rate": 1.1673185571490657e-05, + "loss": 0.144, + "step": 15328 + }, + { + "epoch": 1.25, + "learning_rate": 1.167264232942199e-05, + "loss": 0.2545, + "step": 15329 + }, + { + "epoch": 1.25, + "learning_rate": 1.1672099087353326e-05, + "loss": 0.3878, + "step": 15330 + }, + { + "epoch": 1.25, + "learning_rate": 1.1671555845284658e-05, + "loss": 0.308, + "step": 15331 + }, + { + "epoch": 1.25, + "learning_rate": 1.1671012603215994e-05, + "loss": 0.2511, + "step": 15332 + }, + { + "epoch": 1.25, + "learning_rate": 1.1670469361147327e-05, + "loss": 0.2372, + "step": 15333 + }, + { + "epoch": 1.25, + "learning_rate": 1.1669926119078663e-05, + "loss": 0.1547, + "step": 15334 + }, + { + "epoch": 1.25, + "learning_rate": 1.1669382877009997e-05, + "loss": 0.2785, + "step": 15335 + }, + { + "epoch": 1.25, + "learning_rate": 1.1668839634941331e-05, + "loss": 0.4302, + "step": 15336 + }, + { + "epoch": 1.25, + "learning_rate": 1.1668296392872665e-05, + "loss": 0.2269, + "step": 15337 + }, + { + "epoch": 1.25, + "learning_rate": 1.1667753150804e-05, + "loss": 0.405, + "step": 15338 + }, + { + "epoch": 1.25, + "learning_rate": 1.1667209908735334e-05, + "loss": 0.3469, + "step": 15339 + }, + { + "epoch": 1.25, + "learning_rate": 1.1666666666666668e-05, + "loss": 0.1951, + "step": 15340 + }, + { + "epoch": 1.25, + "learning_rate": 1.1666123424598002e-05, + "loss": 0.3293, + "step": 15341 + }, + { + "epoch": 1.25, + "learning_rate": 1.1665580182529336e-05, + "loss": 0.4025, + "step": 15342 + }, + { + "epoch": 1.25, + "learning_rate": 1.166503694046067e-05, + "loss": 0.3543, + "step": 15343 + }, + { + "epoch": 1.25, + "learning_rate": 1.1664493698392005e-05, + "loss": 0.3102, + "step": 15344 + }, + { + "epoch": 1.25, + "learning_rate": 1.1663950456323339e-05, + "loss": 0.17, + "step": 15345 + }, + { + "epoch": 1.25, + "learning_rate": 1.1663407214254673e-05, + "loss": 0.2491, + "step": 15346 + }, + { + "epoch": 1.25, + "learning_rate": 1.1662863972186008e-05, + "loss": 0.5468, + "step": 15347 + }, + { + "epoch": 1.25, + "learning_rate": 1.166232073011734e-05, + "loss": 0.2846, + "step": 15348 + }, + { + "epoch": 1.25, + "learning_rate": 1.1661777488048676e-05, + "loss": 0.1986, + "step": 15349 + }, + { + "epoch": 1.25, + "learning_rate": 1.1661234245980009e-05, + "loss": 0.1663, + "step": 15350 + }, + { + "epoch": 1.25, + "learning_rate": 1.1660691003911344e-05, + "loss": 0.2551, + "step": 15351 + }, + { + "epoch": 1.25, + "learning_rate": 1.1660147761842677e-05, + "loss": 0.2973, + "step": 15352 + }, + { + "epoch": 1.25, + "learning_rate": 1.1659604519774013e-05, + "loss": 0.4348, + "step": 15353 + }, + { + "epoch": 1.25, + "learning_rate": 1.1659061277705345e-05, + "loss": 0.5384, + "step": 15354 + }, + { + "epoch": 1.25, + "learning_rate": 1.1658518035636681e-05, + "loss": 0.2978, + "step": 15355 + }, + { + "epoch": 1.25, + "learning_rate": 1.1657974793568014e-05, + "loss": 0.2878, + "step": 15356 + }, + { + "epoch": 1.25, + "learning_rate": 1.165743155149935e-05, + "loss": 0.1096, + "step": 15357 + }, + { + "epoch": 1.25, + "learning_rate": 1.1656888309430682e-05, + "loss": 0.256, + "step": 15358 + }, + { + "epoch": 1.25, + "learning_rate": 1.1656345067362018e-05, + "loss": 0.359, + "step": 15359 + }, + { + "epoch": 1.25, + "learning_rate": 1.165580182529335e-05, + "loss": 0.3996, + "step": 15360 + }, + { + "epoch": 1.25, + "learning_rate": 1.1655258583224687e-05, + "loss": 0.2585, + "step": 15361 + }, + { + "epoch": 1.25, + "learning_rate": 1.165471534115602e-05, + "loss": 0.3896, + "step": 15362 + }, + { + "epoch": 1.25, + "learning_rate": 1.1654172099087355e-05, + "loss": 0.342, + "step": 15363 + }, + { + "epoch": 1.25, + "learning_rate": 1.1653628857018688e-05, + "loss": 0.1175, + "step": 15364 + }, + { + "epoch": 1.25, + "learning_rate": 1.1653085614950024e-05, + "loss": 0.3063, + "step": 15365 + }, + { + "epoch": 1.25, + "learning_rate": 1.1652542372881356e-05, + "loss": 0.2421, + "step": 15366 + }, + { + "epoch": 1.25, + "learning_rate": 1.165199913081269e-05, + "loss": 0.3013, + "step": 15367 + }, + { + "epoch": 1.25, + "learning_rate": 1.1651455888744025e-05, + "loss": 0.4423, + "step": 15368 + }, + { + "epoch": 1.25, + "learning_rate": 1.1650912646675359e-05, + "loss": 0.268, + "step": 15369 + }, + { + "epoch": 1.25, + "learning_rate": 1.1650369404606693e-05, + "loss": 0.4472, + "step": 15370 + }, + { + "epoch": 1.25, + "learning_rate": 1.1649826162538027e-05, + "loss": 0.3974, + "step": 15371 + }, + { + "epoch": 1.25, + "learning_rate": 1.1649282920469363e-05, + "loss": 0.2117, + "step": 15372 + }, + { + "epoch": 1.25, + "learning_rate": 1.1648739678400696e-05, + "loss": 0.3, + "step": 15373 + }, + { + "epoch": 1.25, + "learning_rate": 1.1648196436332032e-05, + "loss": 0.2961, + "step": 15374 + }, + { + "epoch": 1.25, + "learning_rate": 1.1647653194263364e-05, + "loss": 0.5239, + "step": 15375 + }, + { + "epoch": 1.25, + "learning_rate": 1.16471099521947e-05, + "loss": 0.2516, + "step": 15376 + }, + { + "epoch": 1.25, + "learning_rate": 1.1646566710126033e-05, + "loss": 0.4094, + "step": 15377 + }, + { + "epoch": 1.25, + "learning_rate": 1.1646023468057369e-05, + "loss": 0.1677, + "step": 15378 + }, + { + "epoch": 1.25, + "learning_rate": 1.1645480225988701e-05, + "loss": 0.2692, + "step": 15379 + }, + { + "epoch": 1.25, + "learning_rate": 1.1644936983920037e-05, + "loss": 0.2468, + "step": 15380 + }, + { + "epoch": 1.25, + "learning_rate": 1.164439374185137e-05, + "loss": 0.3304, + "step": 15381 + }, + { + "epoch": 1.25, + "learning_rate": 1.1643850499782706e-05, + "loss": 0.1542, + "step": 15382 + }, + { + "epoch": 1.25, + "learning_rate": 1.1643307257714038e-05, + "loss": 0.2233, + "step": 15383 + }, + { + "epoch": 1.25, + "learning_rate": 1.1642764015645374e-05, + "loss": 0.1931, + "step": 15384 + }, + { + "epoch": 1.25, + "learning_rate": 1.1642220773576707e-05, + "loss": 0.5379, + "step": 15385 + }, + { + "epoch": 1.25, + "learning_rate": 1.1641677531508039e-05, + "loss": 0.3057, + "step": 15386 + }, + { + "epoch": 1.25, + "learning_rate": 1.1641134289439375e-05, + "loss": 0.3045, + "step": 15387 + }, + { + "epoch": 1.25, + "learning_rate": 1.164059104737071e-05, + "loss": 0.3594, + "step": 15388 + }, + { + "epoch": 1.25, + "learning_rate": 1.1640047805302044e-05, + "loss": 0.2857, + "step": 15389 + }, + { + "epoch": 1.25, + "learning_rate": 1.1639504563233378e-05, + "loss": 0.2623, + "step": 15390 + }, + { + "epoch": 1.25, + "learning_rate": 1.1638961321164712e-05, + "loss": 0.3545, + "step": 15391 + }, + { + "epoch": 1.25, + "learning_rate": 1.1638418079096046e-05, + "loss": 0.6915, + "step": 15392 + }, + { + "epoch": 1.25, + "learning_rate": 1.163787483702738e-05, + "loss": 0.5163, + "step": 15393 + }, + { + "epoch": 1.25, + "learning_rate": 1.1637331594958715e-05, + "loss": 0.577, + "step": 15394 + }, + { + "epoch": 1.25, + "learning_rate": 1.1636788352890049e-05, + "loss": 0.4893, + "step": 15395 + }, + { + "epoch": 1.25, + "learning_rate": 1.1636245110821383e-05, + "loss": 0.3175, + "step": 15396 + }, + { + "epoch": 1.25, + "learning_rate": 1.1635701868752717e-05, + "loss": 0.2602, + "step": 15397 + }, + { + "epoch": 1.25, + "learning_rate": 1.1635158626684052e-05, + "loss": 0.2452, + "step": 15398 + }, + { + "epoch": 1.25, + "learning_rate": 1.1634615384615386e-05, + "loss": 0.4367, + "step": 15399 + }, + { + "epoch": 1.25, + "learning_rate": 1.163407214254672e-05, + "loss": 0.3476, + "step": 15400 + }, + { + "epoch": 1.25, + "learning_rate": 1.1633528900478054e-05, + "loss": 0.3953, + "step": 15401 + }, + { + "epoch": 1.26, + "learning_rate": 1.1632985658409389e-05, + "loss": 0.2666, + "step": 15402 + }, + { + "epoch": 1.26, + "learning_rate": 1.1632442416340723e-05, + "loss": 0.3596, + "step": 15403 + }, + { + "epoch": 1.26, + "learning_rate": 1.1631899174272057e-05, + "loss": 0.2503, + "step": 15404 + }, + { + "epoch": 1.26, + "learning_rate": 1.163135593220339e-05, + "loss": 0.2043, + "step": 15405 + }, + { + "epoch": 1.26, + "learning_rate": 1.1630812690134725e-05, + "loss": 0.4373, + "step": 15406 + }, + { + "epoch": 1.26, + "learning_rate": 1.1630269448066058e-05, + "loss": 0.2717, + "step": 15407 + }, + { + "epoch": 1.26, + "learning_rate": 1.1629726205997394e-05, + "loss": 0.5566, + "step": 15408 + }, + { + "epoch": 1.26, + "learning_rate": 1.1629182963928726e-05, + "loss": 0.4367, + "step": 15409 + }, + { + "epoch": 1.26, + "learning_rate": 1.1628639721860062e-05, + "loss": 0.1622, + "step": 15410 + }, + { + "epoch": 1.26, + "learning_rate": 1.1628096479791395e-05, + "loss": 0.2967, + "step": 15411 + }, + { + "epoch": 1.26, + "learning_rate": 1.162755323772273e-05, + "loss": 0.4111, + "step": 15412 + }, + { + "epoch": 1.26, + "learning_rate": 1.1627009995654063e-05, + "loss": 0.5646, + "step": 15413 + }, + { + "epoch": 1.26, + "learning_rate": 1.16264667535854e-05, + "loss": 0.5083, + "step": 15414 + }, + { + "epoch": 1.26, + "learning_rate": 1.1625923511516732e-05, + "loss": 0.4159, + "step": 15415 + }, + { + "epoch": 1.26, + "learning_rate": 1.1625380269448068e-05, + "loss": 0.1403, + "step": 15416 + }, + { + "epoch": 1.26, + "learning_rate": 1.16248370273794e-05, + "loss": 0.1857, + "step": 15417 + }, + { + "epoch": 1.26, + "learning_rate": 1.1624293785310736e-05, + "loss": 0.2063, + "step": 15418 + }, + { + "epoch": 1.26, + "learning_rate": 1.1623750543242069e-05, + "loss": 0.3491, + "step": 15419 + }, + { + "epoch": 1.26, + "learning_rate": 1.1623207301173405e-05, + "loss": 0.2242, + "step": 15420 + }, + { + "epoch": 1.26, + "learning_rate": 1.1622664059104737e-05, + "loss": 0.5341, + "step": 15421 + }, + { + "epoch": 1.26, + "learning_rate": 1.1622120817036073e-05, + "loss": 0.5011, + "step": 15422 + }, + { + "epoch": 1.26, + "learning_rate": 1.1621577574967406e-05, + "loss": 0.4996, + "step": 15423 + }, + { + "epoch": 1.26, + "learning_rate": 1.162103433289874e-05, + "loss": 0.2675, + "step": 15424 + }, + { + "epoch": 1.26, + "learning_rate": 1.1620491090830076e-05, + "loss": 0.2754, + "step": 15425 + }, + { + "epoch": 1.26, + "learning_rate": 1.1619947848761408e-05, + "loss": 0.3839, + "step": 15426 + }, + { + "epoch": 1.26, + "learning_rate": 1.1619404606692744e-05, + "loss": 0.575, + "step": 15427 + }, + { + "epoch": 1.26, + "learning_rate": 1.1618861364624077e-05, + "loss": 0.3003, + "step": 15428 + }, + { + "epoch": 1.26, + "learning_rate": 1.1618318122555413e-05, + "loss": 0.2108, + "step": 15429 + }, + { + "epoch": 1.26, + "learning_rate": 1.1617774880486745e-05, + "loss": 0.2236, + "step": 15430 + }, + { + "epoch": 1.26, + "learning_rate": 1.1617231638418081e-05, + "loss": 0.302, + "step": 15431 + }, + { + "epoch": 1.26, + "learning_rate": 1.1616688396349414e-05, + "loss": 0.198, + "step": 15432 + }, + { + "epoch": 1.26, + "learning_rate": 1.161614515428075e-05, + "loss": 0.3478, + "step": 15433 + }, + { + "epoch": 1.26, + "learning_rate": 1.1615601912212082e-05, + "loss": 0.6565, + "step": 15434 + }, + { + "epoch": 1.26, + "learning_rate": 1.1615058670143418e-05, + "loss": 0.4399, + "step": 15435 + }, + { + "epoch": 1.26, + "learning_rate": 1.161451542807475e-05, + "loss": 0.4119, + "step": 15436 + }, + { + "epoch": 1.26, + "learning_rate": 1.1613972186006087e-05, + "loss": 0.568, + "step": 15437 + }, + { + "epoch": 1.26, + "learning_rate": 1.1613428943937419e-05, + "loss": 0.4328, + "step": 15438 + }, + { + "epoch": 1.26, + "learning_rate": 1.1612885701868755e-05, + "loss": 0.0953, + "step": 15439 + }, + { + "epoch": 1.26, + "learning_rate": 1.1612342459800088e-05, + "loss": 0.2234, + "step": 15440 + }, + { + "epoch": 1.26, + "learning_rate": 1.1611799217731423e-05, + "loss": 0.368, + "step": 15441 + }, + { + "epoch": 1.26, + "learning_rate": 1.1611255975662756e-05, + "loss": 0.2294, + "step": 15442 + }, + { + "epoch": 1.26, + "learning_rate": 1.161071273359409e-05, + "loss": 0.1505, + "step": 15443 + }, + { + "epoch": 1.26, + "learning_rate": 1.1610169491525424e-05, + "loss": 0.5411, + "step": 15444 + }, + { + "epoch": 1.26, + "learning_rate": 1.1609626249456759e-05, + "loss": 0.1453, + "step": 15445 + }, + { + "epoch": 1.26, + "learning_rate": 1.1609083007388093e-05, + "loss": 0.5126, + "step": 15446 + }, + { + "epoch": 1.26, + "learning_rate": 1.1608539765319427e-05, + "loss": 0.1991, + "step": 15447 + }, + { + "epoch": 1.26, + "learning_rate": 1.1607996523250761e-05, + "loss": 0.6067, + "step": 15448 + }, + { + "epoch": 1.26, + "learning_rate": 1.1607453281182096e-05, + "loss": 0.1826, + "step": 15449 + }, + { + "epoch": 1.26, + "learning_rate": 1.160691003911343e-05, + "loss": 0.4165, + "step": 15450 + }, + { + "epoch": 1.26, + "learning_rate": 1.1606366797044764e-05, + "loss": 0.2807, + "step": 15451 + }, + { + "epoch": 1.26, + "learning_rate": 1.1605823554976098e-05, + "loss": 0.4686, + "step": 15452 + }, + { + "epoch": 1.26, + "learning_rate": 1.1605280312907433e-05, + "loss": 0.2694, + "step": 15453 + }, + { + "epoch": 1.26, + "learning_rate": 1.1604737070838767e-05, + "loss": 0.297, + "step": 15454 + }, + { + "epoch": 1.26, + "learning_rate": 1.1604193828770101e-05, + "loss": 0.3053, + "step": 15455 + }, + { + "epoch": 1.26, + "learning_rate": 1.1603650586701435e-05, + "loss": 0.2989, + "step": 15456 + }, + { + "epoch": 1.26, + "learning_rate": 1.160310734463277e-05, + "loss": 0.1782, + "step": 15457 + }, + { + "epoch": 1.26, + "learning_rate": 1.1602564102564104e-05, + "loss": 0.2178, + "step": 15458 + }, + { + "epoch": 1.26, + "learning_rate": 1.1602020860495438e-05, + "loss": 0.2493, + "step": 15459 + }, + { + "epoch": 1.26, + "learning_rate": 1.1601477618426772e-05, + "loss": 0.3536, + "step": 15460 + }, + { + "epoch": 1.26, + "learning_rate": 1.1600934376358106e-05, + "loss": 0.6406, + "step": 15461 + }, + { + "epoch": 1.26, + "learning_rate": 1.1600391134289439e-05, + "loss": 0.2832, + "step": 15462 + }, + { + "epoch": 1.26, + "learning_rate": 1.1599847892220775e-05, + "loss": 0.1995, + "step": 15463 + }, + { + "epoch": 1.26, + "learning_rate": 1.1599304650152107e-05, + "loss": 0.1647, + "step": 15464 + }, + { + "epoch": 1.26, + "learning_rate": 1.1598761408083443e-05, + "loss": 0.707, + "step": 15465 + }, + { + "epoch": 1.26, + "learning_rate": 1.1598218166014776e-05, + "loss": 0.142, + "step": 15466 + }, + { + "epoch": 1.26, + "learning_rate": 1.1597674923946112e-05, + "loss": 0.4631, + "step": 15467 + }, + { + "epoch": 1.26, + "learning_rate": 1.1597131681877444e-05, + "loss": 0.3781, + "step": 15468 + }, + { + "epoch": 1.26, + "learning_rate": 1.159658843980878e-05, + "loss": 0.3015, + "step": 15469 + }, + { + "epoch": 1.26, + "learning_rate": 1.1596045197740113e-05, + "loss": 0.3451, + "step": 15470 + }, + { + "epoch": 1.26, + "learning_rate": 1.1595501955671449e-05, + "loss": 0.3797, + "step": 15471 + }, + { + "epoch": 1.26, + "learning_rate": 1.1594958713602781e-05, + "loss": 0.1921, + "step": 15472 + }, + { + "epoch": 1.26, + "learning_rate": 1.1594415471534117e-05, + "loss": 0.1729, + "step": 15473 + }, + { + "epoch": 1.26, + "learning_rate": 1.159387222946545e-05, + "loss": 0.3201, + "step": 15474 + }, + { + "epoch": 1.26, + "learning_rate": 1.1593328987396786e-05, + "loss": 0.3028, + "step": 15475 + }, + { + "epoch": 1.26, + "learning_rate": 1.1592785745328118e-05, + "loss": 0.5133, + "step": 15476 + }, + { + "epoch": 1.26, + "learning_rate": 1.1592242503259454e-05, + "loss": 0.3101, + "step": 15477 + }, + { + "epoch": 1.26, + "learning_rate": 1.1591699261190787e-05, + "loss": 0.1871, + "step": 15478 + }, + { + "epoch": 1.26, + "learning_rate": 1.1591156019122123e-05, + "loss": 0.448, + "step": 15479 + }, + { + "epoch": 1.26, + "learning_rate": 1.1590612777053457e-05, + "loss": 0.1825, + "step": 15480 + }, + { + "epoch": 1.26, + "learning_rate": 1.159006953498479e-05, + "loss": 0.4005, + "step": 15481 + }, + { + "epoch": 1.26, + "learning_rate": 1.1589526292916125e-05, + "loss": 0.1293, + "step": 15482 + }, + { + "epoch": 1.26, + "learning_rate": 1.1588983050847458e-05, + "loss": 0.5223, + "step": 15483 + }, + { + "epoch": 1.26, + "learning_rate": 1.1588439808778794e-05, + "loss": 0.1314, + "step": 15484 + }, + { + "epoch": 1.26, + "learning_rate": 1.1587896566710126e-05, + "loss": 0.2805, + "step": 15485 + }, + { + "epoch": 1.26, + "learning_rate": 1.1587353324641462e-05, + "loss": 0.3169, + "step": 15486 + }, + { + "epoch": 1.26, + "learning_rate": 1.1586810082572795e-05, + "loss": 0.2177, + "step": 15487 + }, + { + "epoch": 1.26, + "learning_rate": 1.158626684050413e-05, + "loss": 0.4194, + "step": 15488 + }, + { + "epoch": 1.26, + "learning_rate": 1.1585723598435463e-05, + "loss": 0.2432, + "step": 15489 + }, + { + "epoch": 1.26, + "learning_rate": 1.1585180356366799e-05, + "loss": 0.3416, + "step": 15490 + }, + { + "epoch": 1.26, + "learning_rate": 1.1584637114298132e-05, + "loss": 0.2503, + "step": 15491 + }, + { + "epoch": 1.26, + "learning_rate": 1.1584093872229468e-05, + "loss": 0.2998, + "step": 15492 + }, + { + "epoch": 1.26, + "learning_rate": 1.15835506301608e-05, + "loss": 0.3362, + "step": 15493 + }, + { + "epoch": 1.26, + "learning_rate": 1.1583007388092136e-05, + "loss": 0.2492, + "step": 15494 + }, + { + "epoch": 1.26, + "learning_rate": 1.1582464146023469e-05, + "loss": 0.2183, + "step": 15495 + }, + { + "epoch": 1.26, + "learning_rate": 1.1581920903954804e-05, + "loss": 0.4609, + "step": 15496 + }, + { + "epoch": 1.26, + "learning_rate": 1.1581377661886137e-05, + "loss": 0.2285, + "step": 15497 + }, + { + "epoch": 1.26, + "learning_rate": 1.1580834419817473e-05, + "loss": 0.2527, + "step": 15498 + }, + { + "epoch": 1.26, + "learning_rate": 1.1580291177748805e-05, + "loss": 0.5468, + "step": 15499 + }, + { + "epoch": 1.26, + "learning_rate": 1.157974793568014e-05, + "loss": 0.3175, + "step": 15500 + }, + { + "epoch": 1.26, + "eval_accuracy": 0.8382068262862965, + "eval_loss": 0.44924476742744446, + "eval_runtime": 22.4122, + "eval_samples_per_second": 437.932, + "eval_steps_per_second": 3.436, + "step": 15500 + }, + { + "epoch": 1.26, + "learning_rate": 1.1579204693611474e-05, + "loss": 0.1949, + "step": 15501 + }, + { + "epoch": 1.26, + "learning_rate": 1.1578661451542808e-05, + "loss": 0.2208, + "step": 15502 + }, + { + "epoch": 1.26, + "learning_rate": 1.1578118209474142e-05, + "loss": 0.0828, + "step": 15503 + }, + { + "epoch": 1.26, + "learning_rate": 1.1577574967405477e-05, + "loss": 0.344, + "step": 15504 + }, + { + "epoch": 1.26, + "learning_rate": 1.1577031725336811e-05, + "loss": 0.2149, + "step": 15505 + }, + { + "epoch": 1.26, + "learning_rate": 1.1576488483268145e-05, + "loss": 0.1581, + "step": 15506 + }, + { + "epoch": 1.26, + "learning_rate": 1.157594524119948e-05, + "loss": 0.5843, + "step": 15507 + }, + { + "epoch": 1.26, + "learning_rate": 1.1575401999130814e-05, + "loss": 0.4783, + "step": 15508 + }, + { + "epoch": 1.26, + "learning_rate": 1.1574858757062148e-05, + "loss": 0.3473, + "step": 15509 + }, + { + "epoch": 1.26, + "learning_rate": 1.1574315514993482e-05, + "loss": 0.2718, + "step": 15510 + }, + { + "epoch": 1.26, + "learning_rate": 1.1573772272924816e-05, + "loss": 0.2791, + "step": 15511 + }, + { + "epoch": 1.26, + "learning_rate": 1.157322903085615e-05, + "loss": 0.2053, + "step": 15512 + }, + { + "epoch": 1.26, + "learning_rate": 1.1572685788787485e-05, + "loss": 0.2613, + "step": 15513 + }, + { + "epoch": 1.26, + "learning_rate": 1.1572142546718819e-05, + "loss": 0.514, + "step": 15514 + }, + { + "epoch": 1.26, + "learning_rate": 1.1571599304650155e-05, + "loss": 0.2089, + "step": 15515 + }, + { + "epoch": 1.26, + "learning_rate": 1.1571056062581487e-05, + "loss": 0.5429, + "step": 15516 + }, + { + "epoch": 1.26, + "learning_rate": 1.1570512820512823e-05, + "loss": 0.2638, + "step": 15517 + }, + { + "epoch": 1.26, + "learning_rate": 1.1569969578444156e-05, + "loss": 0.4279, + "step": 15518 + }, + { + "epoch": 1.26, + "learning_rate": 1.1569426336375488e-05, + "loss": 0.3958, + "step": 15519 + }, + { + "epoch": 1.26, + "learning_rate": 1.1568883094306824e-05, + "loss": 0.2898, + "step": 15520 + }, + { + "epoch": 1.26, + "learning_rate": 1.1568339852238157e-05, + "loss": 0.4018, + "step": 15521 + }, + { + "epoch": 1.26, + "learning_rate": 1.1567796610169493e-05, + "loss": 0.2571, + "step": 15522 + }, + { + "epoch": 1.26, + "learning_rate": 1.1567253368100825e-05, + "loss": 0.2268, + "step": 15523 + }, + { + "epoch": 1.26, + "learning_rate": 1.1566710126032161e-05, + "loss": 0.1393, + "step": 15524 + }, + { + "epoch": 1.27, + "learning_rate": 1.1566166883963494e-05, + "loss": 0.2178, + "step": 15525 + }, + { + "epoch": 1.27, + "learning_rate": 1.156562364189483e-05, + "loss": 0.1451, + "step": 15526 + }, + { + "epoch": 1.27, + "learning_rate": 1.1565080399826162e-05, + "loss": 0.1345, + "step": 15527 + }, + { + "epoch": 1.27, + "learning_rate": 1.1564537157757498e-05, + "loss": 0.2482, + "step": 15528 + }, + { + "epoch": 1.27, + "learning_rate": 1.156399391568883e-05, + "loss": 0.3465, + "step": 15529 + }, + { + "epoch": 1.27, + "learning_rate": 1.1563450673620167e-05, + "loss": 0.5381, + "step": 15530 + }, + { + "epoch": 1.27, + "learning_rate": 1.15629074315515e-05, + "loss": 0.2326, + "step": 15531 + }, + { + "epoch": 1.27, + "learning_rate": 1.1562364189482835e-05, + "loss": 0.5889, + "step": 15532 + }, + { + "epoch": 1.27, + "learning_rate": 1.156182094741417e-05, + "loss": 0.3131, + "step": 15533 + }, + { + "epoch": 1.27, + "learning_rate": 1.1561277705345504e-05, + "loss": 0.3258, + "step": 15534 + }, + { + "epoch": 1.27, + "learning_rate": 1.1560734463276838e-05, + "loss": 0.3435, + "step": 15535 + }, + { + "epoch": 1.27, + "learning_rate": 1.1560191221208172e-05, + "loss": 0.2101, + "step": 15536 + }, + { + "epoch": 1.27, + "learning_rate": 1.1559647979139506e-05, + "loss": 0.6881, + "step": 15537 + }, + { + "epoch": 1.27, + "learning_rate": 1.1559104737070839e-05, + "loss": 0.3434, + "step": 15538 + }, + { + "epoch": 1.27, + "learning_rate": 1.1558561495002175e-05, + "loss": 0.2048, + "step": 15539 + }, + { + "epoch": 1.27, + "learning_rate": 1.1558018252933507e-05, + "loss": 0.2189, + "step": 15540 + }, + { + "epoch": 1.27, + "learning_rate": 1.1557475010864843e-05, + "loss": 0.4093, + "step": 15541 + }, + { + "epoch": 1.27, + "learning_rate": 1.1556931768796176e-05, + "loss": 0.3868, + "step": 15542 + }, + { + "epoch": 1.27, + "learning_rate": 1.1556388526727512e-05, + "loss": 0.1189, + "step": 15543 + }, + { + "epoch": 1.27, + "learning_rate": 1.1555845284658844e-05, + "loss": 0.1488, + "step": 15544 + }, + { + "epoch": 1.27, + "learning_rate": 1.155530204259018e-05, + "loss": 0.3707, + "step": 15545 + }, + { + "epoch": 1.27, + "learning_rate": 1.1554758800521513e-05, + "loss": 0.241, + "step": 15546 + }, + { + "epoch": 1.27, + "learning_rate": 1.1554215558452849e-05, + "loss": 0.1194, + "step": 15547 + }, + { + "epoch": 1.27, + "learning_rate": 1.1553672316384181e-05, + "loss": 0.4947, + "step": 15548 + }, + { + "epoch": 1.27, + "learning_rate": 1.1553129074315517e-05, + "loss": 0.2656, + "step": 15549 + }, + { + "epoch": 1.27, + "learning_rate": 1.155258583224685e-05, + "loss": 0.2666, + "step": 15550 + }, + { + "epoch": 1.27, + "learning_rate": 1.1552042590178185e-05, + "loss": 0.4, + "step": 15551 + }, + { + "epoch": 1.27, + "learning_rate": 1.1551499348109518e-05, + "loss": 0.334, + "step": 15552 + }, + { + "epoch": 1.27, + "learning_rate": 1.1550956106040854e-05, + "loss": 0.1182, + "step": 15553 + }, + { + "epoch": 1.27, + "learning_rate": 1.1550412863972186e-05, + "loss": 0.2227, + "step": 15554 + }, + { + "epoch": 1.27, + "learning_rate": 1.1549869621903522e-05, + "loss": 0.274, + "step": 15555 + }, + { + "epoch": 1.27, + "learning_rate": 1.1549326379834855e-05, + "loss": 0.4205, + "step": 15556 + }, + { + "epoch": 1.27, + "learning_rate": 1.154878313776619e-05, + "loss": 0.4023, + "step": 15557 + }, + { + "epoch": 1.27, + "learning_rate": 1.1548239895697523e-05, + "loss": 0.1542, + "step": 15558 + }, + { + "epoch": 1.27, + "learning_rate": 1.1547696653628858e-05, + "loss": 0.3531, + "step": 15559 + }, + { + "epoch": 1.27, + "learning_rate": 1.1547153411560192e-05, + "loss": 0.6694, + "step": 15560 + }, + { + "epoch": 1.27, + "learning_rate": 1.1546610169491526e-05, + "loss": 0.3638, + "step": 15561 + }, + { + "epoch": 1.27, + "learning_rate": 1.154606692742286e-05, + "loss": 0.4824, + "step": 15562 + }, + { + "epoch": 1.27, + "learning_rate": 1.1545523685354195e-05, + "loss": 0.2837, + "step": 15563 + }, + { + "epoch": 1.27, + "learning_rate": 1.1544980443285529e-05, + "loss": 0.2168, + "step": 15564 + }, + { + "epoch": 1.27, + "learning_rate": 1.1544437201216863e-05, + "loss": 0.3185, + "step": 15565 + }, + { + "epoch": 1.27, + "learning_rate": 1.1543893959148197e-05, + "loss": 0.2789, + "step": 15566 + }, + { + "epoch": 1.27, + "learning_rate": 1.1543350717079531e-05, + "loss": 0.2063, + "step": 15567 + }, + { + "epoch": 1.27, + "learning_rate": 1.1542807475010866e-05, + "loss": 0.2333, + "step": 15568 + }, + { + "epoch": 1.27, + "learning_rate": 1.15422642329422e-05, + "loss": 0.2314, + "step": 15569 + }, + { + "epoch": 1.27, + "learning_rate": 1.1541720990873536e-05, + "loss": 0.2551, + "step": 15570 + }, + { + "epoch": 1.27, + "learning_rate": 1.1541177748804868e-05, + "loss": 0.5851, + "step": 15571 + }, + { + "epoch": 1.27, + "learning_rate": 1.1540634506736204e-05, + "loss": 0.1437, + "step": 15572 + }, + { + "epoch": 1.27, + "learning_rate": 1.1540091264667537e-05, + "loss": 0.3284, + "step": 15573 + }, + { + "epoch": 1.27, + "learning_rate": 1.1539548022598873e-05, + "loss": 0.3725, + "step": 15574 + }, + { + "epoch": 1.27, + "learning_rate": 1.1539004780530205e-05, + "loss": 0.2421, + "step": 15575 + }, + { + "epoch": 1.27, + "learning_rate": 1.1538461538461538e-05, + "loss": 0.6868, + "step": 15576 + }, + { + "epoch": 1.27, + "learning_rate": 1.1537918296392874e-05, + "loss": 0.2822, + "step": 15577 + }, + { + "epoch": 1.27, + "learning_rate": 1.1537375054324206e-05, + "loss": 0.3751, + "step": 15578 + }, + { + "epoch": 1.27, + "learning_rate": 1.1536831812255542e-05, + "loss": 0.3582, + "step": 15579 + }, + { + "epoch": 1.27, + "learning_rate": 1.1536288570186875e-05, + "loss": 0.3673, + "step": 15580 + }, + { + "epoch": 1.27, + "learning_rate": 1.153574532811821e-05, + "loss": 0.2521, + "step": 15581 + }, + { + "epoch": 1.27, + "learning_rate": 1.1535202086049543e-05, + "loss": 0.5227, + "step": 15582 + }, + { + "epoch": 1.27, + "learning_rate": 1.1534658843980879e-05, + "loss": 0.4311, + "step": 15583 + }, + { + "epoch": 1.27, + "learning_rate": 1.1534115601912212e-05, + "loss": 0.4303, + "step": 15584 + }, + { + "epoch": 1.27, + "learning_rate": 1.1533572359843548e-05, + "loss": 0.3379, + "step": 15585 + }, + { + "epoch": 1.27, + "learning_rate": 1.153302911777488e-05, + "loss": 0.3227, + "step": 15586 + }, + { + "epoch": 1.27, + "learning_rate": 1.1532485875706216e-05, + "loss": 0.3745, + "step": 15587 + }, + { + "epoch": 1.27, + "learning_rate": 1.153194263363755e-05, + "loss": 0.212, + "step": 15588 + }, + { + "epoch": 1.27, + "learning_rate": 1.1531399391568885e-05, + "loss": 0.3307, + "step": 15589 + }, + { + "epoch": 1.27, + "learning_rate": 1.1530856149500219e-05, + "loss": 0.192, + "step": 15590 + }, + { + "epoch": 1.27, + "learning_rate": 1.1530312907431553e-05, + "loss": 0.4338, + "step": 15591 + }, + { + "epoch": 1.27, + "learning_rate": 1.1529769665362887e-05, + "loss": 0.258, + "step": 15592 + }, + { + "epoch": 1.27, + "learning_rate": 1.1529226423294221e-05, + "loss": 0.1498, + "step": 15593 + }, + { + "epoch": 1.27, + "learning_rate": 1.1528683181225556e-05, + "loss": 0.3253, + "step": 15594 + }, + { + "epoch": 1.27, + "learning_rate": 1.1528139939156888e-05, + "loss": 0.4069, + "step": 15595 + }, + { + "epoch": 1.27, + "learning_rate": 1.1527596697088224e-05, + "loss": 0.3276, + "step": 15596 + }, + { + "epoch": 1.27, + "learning_rate": 1.1527053455019557e-05, + "loss": 0.4013, + "step": 15597 + }, + { + "epoch": 1.27, + "learning_rate": 1.1526510212950893e-05, + "loss": 0.2155, + "step": 15598 + }, + { + "epoch": 1.27, + "learning_rate": 1.1525966970882225e-05, + "loss": 0.4958, + "step": 15599 + }, + { + "epoch": 1.27, + "learning_rate": 1.1525423728813561e-05, + "loss": 0.4453, + "step": 15600 + }, + { + "epoch": 1.27, + "learning_rate": 1.1524880486744894e-05, + "loss": 0.4054, + "step": 15601 + }, + { + "epoch": 1.27, + "learning_rate": 1.152433724467623e-05, + "loss": 0.4079, + "step": 15602 + }, + { + "epoch": 1.27, + "learning_rate": 1.1523794002607562e-05, + "loss": 0.4473, + "step": 15603 + }, + { + "epoch": 1.27, + "learning_rate": 1.1523250760538898e-05, + "loss": 0.431, + "step": 15604 + }, + { + "epoch": 1.27, + "learning_rate": 1.152270751847023e-05, + "loss": 0.2651, + "step": 15605 + }, + { + "epoch": 1.27, + "learning_rate": 1.1522164276401566e-05, + "loss": 0.3337, + "step": 15606 + }, + { + "epoch": 1.27, + "learning_rate": 1.1521621034332899e-05, + "loss": 0.2957, + "step": 15607 + }, + { + "epoch": 1.27, + "learning_rate": 1.1521077792264235e-05, + "loss": 0.4965, + "step": 15608 + }, + { + "epoch": 1.27, + "learning_rate": 1.1520534550195567e-05, + "loss": 0.1029, + "step": 15609 + }, + { + "epoch": 1.27, + "learning_rate": 1.1519991308126903e-05, + "loss": 0.2671, + "step": 15610 + }, + { + "epoch": 1.27, + "learning_rate": 1.1519448066058236e-05, + "loss": 0.2654, + "step": 15611 + }, + { + "epoch": 1.27, + "learning_rate": 1.1518904823989572e-05, + "loss": 0.1447, + "step": 15612 + }, + { + "epoch": 1.27, + "learning_rate": 1.1518361581920904e-05, + "loss": 0.4399, + "step": 15613 + }, + { + "epoch": 1.27, + "learning_rate": 1.1517818339852239e-05, + "loss": 0.2676, + "step": 15614 + }, + { + "epoch": 1.27, + "learning_rate": 1.1517275097783573e-05, + "loss": 0.2807, + "step": 15615 + }, + { + "epoch": 1.27, + "learning_rate": 1.1516731855714907e-05, + "loss": 0.154, + "step": 15616 + }, + { + "epoch": 1.27, + "learning_rate": 1.1516188613646241e-05, + "loss": 0.3921, + "step": 15617 + }, + { + "epoch": 1.27, + "learning_rate": 1.1515645371577576e-05, + "loss": 0.1892, + "step": 15618 + }, + { + "epoch": 1.27, + "learning_rate": 1.151510212950891e-05, + "loss": 0.661, + "step": 15619 + }, + { + "epoch": 1.27, + "learning_rate": 1.1514558887440244e-05, + "loss": 0.504, + "step": 15620 + }, + { + "epoch": 1.27, + "learning_rate": 1.1514015645371578e-05, + "loss": 0.3312, + "step": 15621 + }, + { + "epoch": 1.27, + "learning_rate": 1.1513472403302912e-05, + "loss": 0.1653, + "step": 15622 + }, + { + "epoch": 1.27, + "learning_rate": 1.1512929161234248e-05, + "loss": 0.2264, + "step": 15623 + }, + { + "epoch": 1.27, + "learning_rate": 1.1512385919165581e-05, + "loss": 0.3914, + "step": 15624 + }, + { + "epoch": 1.27, + "learning_rate": 1.1511842677096917e-05, + "loss": 0.1869, + "step": 15625 + }, + { + "epoch": 1.27, + "learning_rate": 1.151129943502825e-05, + "loss": 0.4742, + "step": 15626 + }, + { + "epoch": 1.27, + "learning_rate": 1.1510756192959585e-05, + "loss": 0.4907, + "step": 15627 + }, + { + "epoch": 1.27, + "learning_rate": 1.1510212950890918e-05, + "loss": 0.2651, + "step": 15628 + }, + { + "epoch": 1.27, + "learning_rate": 1.1509669708822254e-05, + "loss": 0.4628, + "step": 15629 + }, + { + "epoch": 1.27, + "learning_rate": 1.1509126466753586e-05, + "loss": 0.3376, + "step": 15630 + }, + { + "epoch": 1.27, + "learning_rate": 1.1508583224684922e-05, + "loss": 0.3503, + "step": 15631 + }, + { + "epoch": 1.27, + "learning_rate": 1.1508039982616255e-05, + "loss": 0.3508, + "step": 15632 + }, + { + "epoch": 1.27, + "learning_rate": 1.1507496740547587e-05, + "loss": 0.3606, + "step": 15633 + }, + { + "epoch": 1.27, + "learning_rate": 1.1506953498478923e-05, + "loss": 0.5909, + "step": 15634 + }, + { + "epoch": 1.27, + "learning_rate": 1.1506410256410256e-05, + "loss": 0.4803, + "step": 15635 + }, + { + "epoch": 1.27, + "learning_rate": 1.1505867014341592e-05, + "loss": 0.3304, + "step": 15636 + }, + { + "epoch": 1.27, + "learning_rate": 1.1505323772272924e-05, + "loss": 0.2228, + "step": 15637 + }, + { + "epoch": 1.27, + "learning_rate": 1.150478053020426e-05, + "loss": 0.4631, + "step": 15638 + }, + { + "epoch": 1.27, + "learning_rate": 1.1504237288135593e-05, + "loss": 0.589, + "step": 15639 + }, + { + "epoch": 1.27, + "learning_rate": 1.1503694046066929e-05, + "loss": 0.2772, + "step": 15640 + }, + { + "epoch": 1.27, + "learning_rate": 1.1503150803998263e-05, + "loss": 0.3303, + "step": 15641 + }, + { + "epoch": 1.27, + "learning_rate": 1.1502607561929597e-05, + "loss": 0.238, + "step": 15642 + }, + { + "epoch": 1.27, + "learning_rate": 1.1502064319860931e-05, + "loss": 0.2602, + "step": 15643 + }, + { + "epoch": 1.27, + "learning_rate": 1.1501521077792266e-05, + "loss": 0.1554, + "step": 15644 + }, + { + "epoch": 1.27, + "learning_rate": 1.15009778357236e-05, + "loss": 0.2788, + "step": 15645 + }, + { + "epoch": 1.27, + "learning_rate": 1.1500434593654934e-05, + "loss": 0.1755, + "step": 15646 + }, + { + "epoch": 1.28, + "learning_rate": 1.1499891351586268e-05, + "loss": 0.1259, + "step": 15647 + }, + { + "epoch": 1.28, + "learning_rate": 1.1499348109517602e-05, + "loss": 0.4326, + "step": 15648 + }, + { + "epoch": 1.28, + "learning_rate": 1.1498804867448937e-05, + "loss": 0.3844, + "step": 15649 + }, + { + "epoch": 1.28, + "learning_rate": 1.1498261625380271e-05, + "loss": 0.2363, + "step": 15650 + }, + { + "epoch": 1.28, + "learning_rate": 1.1497718383311605e-05, + "loss": 0.2774, + "step": 15651 + }, + { + "epoch": 1.28, + "learning_rate": 1.1497175141242938e-05, + "loss": 0.2345, + "step": 15652 + }, + { + "epoch": 1.28, + "learning_rate": 1.1496631899174274e-05, + "loss": 0.4246, + "step": 15653 + }, + { + "epoch": 1.28, + "learning_rate": 1.1496088657105606e-05, + "loss": 0.2694, + "step": 15654 + }, + { + "epoch": 1.28, + "learning_rate": 1.1495545415036942e-05, + "loss": 0.3251, + "step": 15655 + }, + { + "epoch": 1.28, + "learning_rate": 1.1495002172968275e-05, + "loss": 0.435, + "step": 15656 + }, + { + "epoch": 1.28, + "learning_rate": 1.149445893089961e-05, + "loss": 0.4291, + "step": 15657 + }, + { + "epoch": 1.28, + "learning_rate": 1.1493915688830943e-05, + "loss": 0.333, + "step": 15658 + }, + { + "epoch": 1.28, + "learning_rate": 1.1493372446762279e-05, + "loss": 0.4274, + "step": 15659 + }, + { + "epoch": 1.28, + "learning_rate": 1.1492829204693612e-05, + "loss": 0.2843, + "step": 15660 + }, + { + "epoch": 1.28, + "learning_rate": 1.1492285962624947e-05, + "loss": 0.4777, + "step": 15661 + }, + { + "epoch": 1.28, + "learning_rate": 1.149174272055628e-05, + "loss": 0.4331, + "step": 15662 + }, + { + "epoch": 1.28, + "learning_rate": 1.1491199478487616e-05, + "loss": 0.2266, + "step": 15663 + }, + { + "epoch": 1.28, + "learning_rate": 1.1490656236418948e-05, + "loss": 0.5424, + "step": 15664 + }, + { + "epoch": 1.28, + "learning_rate": 1.1490112994350284e-05, + "loss": 0.5096, + "step": 15665 + }, + { + "epoch": 1.28, + "learning_rate": 1.1489569752281617e-05, + "loss": 0.4103, + "step": 15666 + }, + { + "epoch": 1.28, + "learning_rate": 1.1489026510212953e-05, + "loss": 0.1751, + "step": 15667 + }, + { + "epoch": 1.28, + "learning_rate": 1.1488483268144285e-05, + "loss": 0.4289, + "step": 15668 + }, + { + "epoch": 1.28, + "learning_rate": 1.1487940026075621e-05, + "loss": 0.4287, + "step": 15669 + }, + { + "epoch": 1.28, + "learning_rate": 1.1487396784006954e-05, + "loss": 0.5453, + "step": 15670 + }, + { + "epoch": 1.28, + "learning_rate": 1.1486853541938288e-05, + "loss": 0.305, + "step": 15671 + }, + { + "epoch": 1.28, + "learning_rate": 1.1486310299869622e-05, + "loss": 0.3344, + "step": 15672 + }, + { + "epoch": 1.28, + "learning_rate": 1.1485767057800957e-05, + "loss": 0.2143, + "step": 15673 + }, + { + "epoch": 1.28, + "learning_rate": 1.148522381573229e-05, + "loss": 0.4724, + "step": 15674 + }, + { + "epoch": 1.28, + "learning_rate": 1.1484680573663625e-05, + "loss": 0.4803, + "step": 15675 + }, + { + "epoch": 1.28, + "learning_rate": 1.148413733159496e-05, + "loss": 0.1222, + "step": 15676 + }, + { + "epoch": 1.28, + "learning_rate": 1.1483594089526293e-05, + "loss": 0.2584, + "step": 15677 + }, + { + "epoch": 1.28, + "learning_rate": 1.148305084745763e-05, + "loss": 0.1458, + "step": 15678 + }, + { + "epoch": 1.28, + "learning_rate": 1.1482507605388962e-05, + "loss": 0.4867, + "step": 15679 + }, + { + "epoch": 1.28, + "learning_rate": 1.1481964363320298e-05, + "loss": 0.3464, + "step": 15680 + }, + { + "epoch": 1.28, + "learning_rate": 1.148142112125163e-05, + "loss": 0.1234, + "step": 15681 + }, + { + "epoch": 1.28, + "learning_rate": 1.1480877879182966e-05, + "loss": 0.4318, + "step": 15682 + }, + { + "epoch": 1.28, + "learning_rate": 1.1480334637114299e-05, + "loss": 0.4609, + "step": 15683 + }, + { + "epoch": 1.28, + "learning_rate": 1.1479791395045635e-05, + "loss": 0.2982, + "step": 15684 + }, + { + "epoch": 1.28, + "learning_rate": 1.1479248152976967e-05, + "loss": 0.3526, + "step": 15685 + }, + { + "epoch": 1.28, + "learning_rate": 1.1478704910908303e-05, + "loss": 0.2024, + "step": 15686 + }, + { + "epoch": 1.28, + "learning_rate": 1.1478161668839636e-05, + "loss": 0.4376, + "step": 15687 + }, + { + "epoch": 1.28, + "learning_rate": 1.1477618426770972e-05, + "loss": 0.5457, + "step": 15688 + }, + { + "epoch": 1.28, + "learning_rate": 1.1477075184702304e-05, + "loss": 0.3432, + "step": 15689 + }, + { + "epoch": 1.28, + "learning_rate": 1.1476531942633637e-05, + "loss": 0.4272, + "step": 15690 + }, + { + "epoch": 1.28, + "learning_rate": 1.1475988700564973e-05, + "loss": 0.4382, + "step": 15691 + }, + { + "epoch": 1.28, + "learning_rate": 1.1475445458496305e-05, + "loss": 0.3369, + "step": 15692 + }, + { + "epoch": 1.28, + "learning_rate": 1.1474902216427641e-05, + "loss": 0.4764, + "step": 15693 + }, + { + "epoch": 1.28, + "learning_rate": 1.1474358974358974e-05, + "loss": 0.3974, + "step": 15694 + }, + { + "epoch": 1.28, + "learning_rate": 1.147381573229031e-05, + "loss": 0.4202, + "step": 15695 + }, + { + "epoch": 1.28, + "learning_rate": 1.1473272490221644e-05, + "loss": 0.4127, + "step": 15696 + }, + { + "epoch": 1.28, + "learning_rate": 1.1472729248152978e-05, + "loss": 0.2626, + "step": 15697 + }, + { + "epoch": 1.28, + "learning_rate": 1.1472186006084312e-05, + "loss": 0.25, + "step": 15698 + }, + { + "epoch": 1.28, + "learning_rate": 1.1471642764015647e-05, + "loss": 0.3591, + "step": 15699 + }, + { + "epoch": 1.28, + "learning_rate": 1.147109952194698e-05, + "loss": 0.4202, + "step": 15700 + }, + { + "epoch": 1.28, + "learning_rate": 1.1470556279878315e-05, + "loss": 0.5555, + "step": 15701 + }, + { + "epoch": 1.28, + "learning_rate": 1.147001303780965e-05, + "loss": 0.2496, + "step": 15702 + }, + { + "epoch": 1.28, + "learning_rate": 1.1469469795740983e-05, + "loss": 0.2609, + "step": 15703 + }, + { + "epoch": 1.28, + "learning_rate": 1.1468926553672318e-05, + "loss": 0.4156, + "step": 15704 + }, + { + "epoch": 1.28, + "learning_rate": 1.1468383311603652e-05, + "loss": 0.3026, + "step": 15705 + }, + { + "epoch": 1.28, + "learning_rate": 1.1467840069534986e-05, + "loss": 0.4277, + "step": 15706 + }, + { + "epoch": 1.28, + "learning_rate": 1.146729682746632e-05, + "loss": 0.2027, + "step": 15707 + }, + { + "epoch": 1.28, + "learning_rate": 1.1466753585397655e-05, + "loss": 0.3912, + "step": 15708 + }, + { + "epoch": 1.28, + "learning_rate": 1.1466210343328987e-05, + "loss": 0.3511, + "step": 15709 + }, + { + "epoch": 1.28, + "learning_rate": 1.1465667101260323e-05, + "loss": 0.6006, + "step": 15710 + }, + { + "epoch": 1.28, + "learning_rate": 1.1465123859191656e-05, + "loss": 0.299, + "step": 15711 + }, + { + "epoch": 1.28, + "learning_rate": 1.1464580617122992e-05, + "loss": 0.3413, + "step": 15712 + }, + { + "epoch": 1.28, + "learning_rate": 1.1464037375054324e-05, + "loss": 0.2182, + "step": 15713 + }, + { + "epoch": 1.28, + "learning_rate": 1.146349413298566e-05, + "loss": 0.4466, + "step": 15714 + }, + { + "epoch": 1.28, + "learning_rate": 1.1462950890916992e-05, + "loss": 0.3611, + "step": 15715 + }, + { + "epoch": 1.28, + "learning_rate": 1.1462407648848328e-05, + "loss": 0.3252, + "step": 15716 + }, + { + "epoch": 1.28, + "learning_rate": 1.1461864406779661e-05, + "loss": 0.1995, + "step": 15717 + }, + { + "epoch": 1.28, + "learning_rate": 1.1461321164710997e-05, + "loss": 0.2718, + "step": 15718 + }, + { + "epoch": 1.28, + "learning_rate": 1.146077792264233e-05, + "loss": 0.3386, + "step": 15719 + }, + { + "epoch": 1.28, + "learning_rate": 1.1460234680573665e-05, + "loss": 0.3783, + "step": 15720 + }, + { + "epoch": 1.28, + "learning_rate": 1.1459691438504998e-05, + "loss": 0.2091, + "step": 15721 + }, + { + "epoch": 1.28, + "learning_rate": 1.1459148196436334e-05, + "loss": 0.1332, + "step": 15722 + }, + { + "epoch": 1.28, + "learning_rate": 1.1458604954367666e-05, + "loss": 0.519, + "step": 15723 + }, + { + "epoch": 1.28, + "learning_rate": 1.1458061712299002e-05, + "loss": 0.2877, + "step": 15724 + }, + { + "epoch": 1.28, + "learning_rate": 1.1457518470230335e-05, + "loss": 0.2477, + "step": 15725 + }, + { + "epoch": 1.28, + "learning_rate": 1.145697522816167e-05, + "loss": 0.1364, + "step": 15726 + }, + { + "epoch": 1.28, + "learning_rate": 1.1456431986093003e-05, + "loss": 0.2764, + "step": 15727 + }, + { + "epoch": 1.28, + "learning_rate": 1.1455888744024337e-05, + "loss": 0.2447, + "step": 15728 + }, + { + "epoch": 1.28, + "learning_rate": 1.1455345501955672e-05, + "loss": 0.2962, + "step": 15729 + }, + { + "epoch": 1.28, + "learning_rate": 1.1454802259887006e-05, + "loss": 0.4495, + "step": 15730 + }, + { + "epoch": 1.28, + "learning_rate": 1.1454259017818342e-05, + "loss": 0.8762, + "step": 15731 + }, + { + "epoch": 1.28, + "learning_rate": 1.1453715775749674e-05, + "loss": 0.4509, + "step": 15732 + }, + { + "epoch": 1.28, + "learning_rate": 1.145317253368101e-05, + "loss": 0.3595, + "step": 15733 + }, + { + "epoch": 1.28, + "learning_rate": 1.1452629291612343e-05, + "loss": 0.4145, + "step": 15734 + }, + { + "epoch": 1.28, + "learning_rate": 1.1452086049543679e-05, + "loss": 0.2011, + "step": 15735 + }, + { + "epoch": 1.28, + "learning_rate": 1.1451542807475011e-05, + "loss": 0.3938, + "step": 15736 + }, + { + "epoch": 1.28, + "learning_rate": 1.1450999565406347e-05, + "loss": 0.3019, + "step": 15737 + }, + { + "epoch": 1.28, + "learning_rate": 1.145045632333768e-05, + "loss": 0.4769, + "step": 15738 + }, + { + "epoch": 1.28, + "learning_rate": 1.1449913081269016e-05, + "loss": 0.4435, + "step": 15739 + }, + { + "epoch": 1.28, + "learning_rate": 1.1449369839200348e-05, + "loss": 0.2258, + "step": 15740 + }, + { + "epoch": 1.28, + "learning_rate": 1.1448826597131684e-05, + "loss": 0.3753, + "step": 15741 + }, + { + "epoch": 1.28, + "learning_rate": 1.1448283355063017e-05, + "loss": 0.1815, + "step": 15742 + }, + { + "epoch": 1.28, + "learning_rate": 1.1447740112994353e-05, + "loss": 0.3281, + "step": 15743 + }, + { + "epoch": 1.28, + "learning_rate": 1.1447196870925685e-05, + "loss": 0.4709, + "step": 15744 + }, + { + "epoch": 1.28, + "learning_rate": 1.1446653628857021e-05, + "loss": 0.2329, + "step": 15745 + }, + { + "epoch": 1.28, + "learning_rate": 1.1446110386788354e-05, + "loss": 0.5329, + "step": 15746 + }, + { + "epoch": 1.28, + "learning_rate": 1.1445567144719686e-05, + "loss": 0.4221, + "step": 15747 + }, + { + "epoch": 1.28, + "learning_rate": 1.1445023902651022e-05, + "loss": 0.1767, + "step": 15748 + }, + { + "epoch": 1.28, + "learning_rate": 1.1444480660582356e-05, + "loss": 0.6304, + "step": 15749 + }, + { + "epoch": 1.28, + "learning_rate": 1.144393741851369e-05, + "loss": 0.3746, + "step": 15750 + }, + { + "epoch": 1.28, + "eval_accuracy": 0.8372898624554254, + "eval_loss": 0.443958044052124, + "eval_runtime": 22.3215, + "eval_samples_per_second": 439.711, + "eval_steps_per_second": 3.45, + "step": 15750 + }, + { + "epoch": 1.28, + "learning_rate": 1.1443394176445025e-05, + "loss": 0.4728, + "step": 15751 + }, + { + "epoch": 1.28, + "learning_rate": 1.1442850934376359e-05, + "loss": 0.3969, + "step": 15752 + }, + { + "epoch": 1.28, + "learning_rate": 1.1442307692307693e-05, + "loss": 0.3004, + "step": 15753 + }, + { + "epoch": 1.28, + "learning_rate": 1.1441764450239027e-05, + "loss": 0.2921, + "step": 15754 + }, + { + "epoch": 1.28, + "learning_rate": 1.1441221208170362e-05, + "loss": 0.3967, + "step": 15755 + }, + { + "epoch": 1.28, + "learning_rate": 1.1440677966101696e-05, + "loss": 0.3082, + "step": 15756 + }, + { + "epoch": 1.28, + "learning_rate": 1.144013472403303e-05, + "loss": 0.3956, + "step": 15757 + }, + { + "epoch": 1.28, + "learning_rate": 1.1439591481964364e-05, + "loss": 0.3176, + "step": 15758 + }, + { + "epoch": 1.28, + "learning_rate": 1.1439048239895699e-05, + "loss": 0.6183, + "step": 15759 + }, + { + "epoch": 1.28, + "learning_rate": 1.1438504997827033e-05, + "loss": 0.1217, + "step": 15760 + }, + { + "epoch": 1.28, + "learning_rate": 1.1437961755758367e-05, + "loss": 0.5166, + "step": 15761 + }, + { + "epoch": 1.28, + "learning_rate": 1.1437418513689701e-05, + "loss": 0.4395, + "step": 15762 + }, + { + "epoch": 1.28, + "learning_rate": 1.1436875271621036e-05, + "loss": 0.5292, + "step": 15763 + }, + { + "epoch": 1.28, + "learning_rate": 1.143633202955237e-05, + "loss": 0.3187, + "step": 15764 + }, + { + "epoch": 1.28, + "learning_rate": 1.1435788787483704e-05, + "loss": 0.1728, + "step": 15765 + }, + { + "epoch": 1.28, + "learning_rate": 1.1435245545415037e-05, + "loss": 0.3544, + "step": 15766 + }, + { + "epoch": 1.28, + "learning_rate": 1.1434702303346372e-05, + "loss": 0.2826, + "step": 15767 + }, + { + "epoch": 1.28, + "learning_rate": 1.1434159061277705e-05, + "loss": 0.3248, + "step": 15768 + }, + { + "epoch": 1.28, + "learning_rate": 1.1433615819209041e-05, + "loss": 0.194, + "step": 15769 + }, + { + "epoch": 1.29, + "learning_rate": 1.1433072577140373e-05, + "loss": 0.2824, + "step": 15770 + }, + { + "epoch": 1.29, + "learning_rate": 1.143252933507171e-05, + "loss": 0.2528, + "step": 15771 + }, + { + "epoch": 1.29, + "learning_rate": 1.1431986093003042e-05, + "loss": 0.4893, + "step": 15772 + }, + { + "epoch": 1.29, + "learning_rate": 1.1431442850934378e-05, + "loss": 0.2611, + "step": 15773 + }, + { + "epoch": 1.29, + "learning_rate": 1.143089960886571e-05, + "loss": 0.4165, + "step": 15774 + }, + { + "epoch": 1.29, + "learning_rate": 1.1430356366797046e-05, + "loss": 0.3458, + "step": 15775 + }, + { + "epoch": 1.29, + "learning_rate": 1.1429813124728379e-05, + "loss": 0.5735, + "step": 15776 + }, + { + "epoch": 1.29, + "learning_rate": 1.1429269882659715e-05, + "loss": 0.4828, + "step": 15777 + }, + { + "epoch": 1.29, + "learning_rate": 1.1428726640591047e-05, + "loss": 0.4931, + "step": 15778 + }, + { + "epoch": 1.29, + "learning_rate": 1.1428183398522383e-05, + "loss": 0.612, + "step": 15779 + }, + { + "epoch": 1.29, + "learning_rate": 1.1427640156453716e-05, + "loss": 0.3415, + "step": 15780 + }, + { + "epoch": 1.29, + "learning_rate": 1.1427096914385052e-05, + "loss": 0.1849, + "step": 15781 + }, + { + "epoch": 1.29, + "learning_rate": 1.1426553672316384e-05, + "loss": 0.1961, + "step": 15782 + }, + { + "epoch": 1.29, + "learning_rate": 1.142601043024772e-05, + "loss": 0.2734, + "step": 15783 + }, + { + "epoch": 1.29, + "learning_rate": 1.1425467188179053e-05, + "loss": 0.2863, + "step": 15784 + }, + { + "epoch": 1.29, + "learning_rate": 1.1424923946110387e-05, + "loss": 0.3361, + "step": 15785 + }, + { + "epoch": 1.29, + "learning_rate": 1.1424380704041723e-05, + "loss": 0.209, + "step": 15786 + }, + { + "epoch": 1.29, + "learning_rate": 1.1423837461973055e-05, + "loss": 0.2288, + "step": 15787 + }, + { + "epoch": 1.29, + "learning_rate": 1.1423294219904391e-05, + "loss": 0.5659, + "step": 15788 + }, + { + "epoch": 1.29, + "learning_rate": 1.1422750977835724e-05, + "loss": 0.319, + "step": 15789 + }, + { + "epoch": 1.29, + "learning_rate": 1.142220773576706e-05, + "loss": 0.5125, + "step": 15790 + }, + { + "epoch": 1.29, + "learning_rate": 1.1421664493698392e-05, + "loss": 0.4193, + "step": 15791 + }, + { + "epoch": 1.29, + "learning_rate": 1.1421121251629728e-05, + "loss": 0.3733, + "step": 15792 + }, + { + "epoch": 1.29, + "learning_rate": 1.142057800956106e-05, + "loss": 0.288, + "step": 15793 + }, + { + "epoch": 1.29, + "learning_rate": 1.1420034767492397e-05, + "loss": 0.2288, + "step": 15794 + }, + { + "epoch": 1.29, + "learning_rate": 1.141949152542373e-05, + "loss": 0.4403, + "step": 15795 + }, + { + "epoch": 1.29, + "learning_rate": 1.1418948283355065e-05, + "loss": 0.4399, + "step": 15796 + }, + { + "epoch": 1.29, + "learning_rate": 1.1418405041286398e-05, + "loss": 0.3056, + "step": 15797 + }, + { + "epoch": 1.29, + "learning_rate": 1.1417861799217734e-05, + "loss": 0.3576, + "step": 15798 + }, + { + "epoch": 1.29, + "learning_rate": 1.1417318557149066e-05, + "loss": 0.3165, + "step": 15799 + }, + { + "epoch": 1.29, + "learning_rate": 1.1416775315080402e-05, + "loss": 0.2398, + "step": 15800 + }, + { + "epoch": 1.29, + "learning_rate": 1.1416232073011735e-05, + "loss": 0.2314, + "step": 15801 + }, + { + "epoch": 1.29, + "learning_rate": 1.141568883094307e-05, + "loss": 0.4984, + "step": 15802 + }, + { + "epoch": 1.29, + "learning_rate": 1.1415145588874403e-05, + "loss": 0.181, + "step": 15803 + }, + { + "epoch": 1.29, + "learning_rate": 1.1414602346805737e-05, + "loss": 0.3999, + "step": 15804 + }, + { + "epoch": 1.29, + "learning_rate": 1.1414059104737072e-05, + "loss": 0.3557, + "step": 15805 + }, + { + "epoch": 1.29, + "learning_rate": 1.1413515862668406e-05, + "loss": 0.2182, + "step": 15806 + }, + { + "epoch": 1.29, + "learning_rate": 1.141297262059974e-05, + "loss": 0.5096, + "step": 15807 + }, + { + "epoch": 1.29, + "learning_rate": 1.1412429378531074e-05, + "loss": 0.2775, + "step": 15808 + }, + { + "epoch": 1.29, + "learning_rate": 1.1411886136462408e-05, + "loss": 0.3732, + "step": 15809 + }, + { + "epoch": 1.29, + "learning_rate": 1.1411342894393743e-05, + "loss": 0.3761, + "step": 15810 + }, + { + "epoch": 1.29, + "learning_rate": 1.1410799652325077e-05, + "loss": 0.4212, + "step": 15811 + }, + { + "epoch": 1.29, + "learning_rate": 1.1410256410256411e-05, + "loss": 0.6054, + "step": 15812 + }, + { + "epoch": 1.29, + "learning_rate": 1.1409713168187745e-05, + "loss": 0.376, + "step": 15813 + }, + { + "epoch": 1.29, + "learning_rate": 1.140916992611908e-05, + "loss": 0.3234, + "step": 15814 + }, + { + "epoch": 1.29, + "learning_rate": 1.1408626684050414e-05, + "loss": 0.1865, + "step": 15815 + }, + { + "epoch": 1.29, + "learning_rate": 1.1408083441981748e-05, + "loss": 0.3325, + "step": 15816 + }, + { + "epoch": 1.29, + "learning_rate": 1.1407540199913082e-05, + "loss": 0.2354, + "step": 15817 + }, + { + "epoch": 1.29, + "learning_rate": 1.1406996957844417e-05, + "loss": 0.1094, + "step": 15818 + }, + { + "epoch": 1.29, + "learning_rate": 1.140645371577575e-05, + "loss": 0.2522, + "step": 15819 + }, + { + "epoch": 1.29, + "learning_rate": 1.1405910473707085e-05, + "loss": 0.1881, + "step": 15820 + }, + { + "epoch": 1.29, + "learning_rate": 1.140536723163842e-05, + "loss": 0.3329, + "step": 15821 + }, + { + "epoch": 1.29, + "learning_rate": 1.1404823989569753e-05, + "loss": 0.2084, + "step": 15822 + }, + { + "epoch": 1.29, + "learning_rate": 1.1404280747501086e-05, + "loss": 0.221, + "step": 15823 + }, + { + "epoch": 1.29, + "learning_rate": 1.1403737505432422e-05, + "loss": 0.4884, + "step": 15824 + }, + { + "epoch": 1.29, + "learning_rate": 1.1403194263363754e-05, + "loss": 0.287, + "step": 15825 + }, + { + "epoch": 1.29, + "learning_rate": 1.140265102129509e-05, + "loss": 0.2215, + "step": 15826 + }, + { + "epoch": 1.29, + "learning_rate": 1.1402107779226423e-05, + "loss": 0.4188, + "step": 15827 + }, + { + "epoch": 1.29, + "learning_rate": 1.1401564537157759e-05, + "loss": 0.573, + "step": 15828 + }, + { + "epoch": 1.29, + "learning_rate": 1.1401021295089091e-05, + "loss": 0.4629, + "step": 15829 + }, + { + "epoch": 1.29, + "learning_rate": 1.1400478053020427e-05, + "loss": 0.3072, + "step": 15830 + }, + { + "epoch": 1.29, + "learning_rate": 1.139993481095176e-05, + "loss": 0.3176, + "step": 15831 + }, + { + "epoch": 1.29, + "learning_rate": 1.1399391568883096e-05, + "loss": 0.287, + "step": 15832 + }, + { + "epoch": 1.29, + "learning_rate": 1.1398848326814428e-05, + "loss": 0.6285, + "step": 15833 + }, + { + "epoch": 1.29, + "learning_rate": 1.1398305084745764e-05, + "loss": 0.2709, + "step": 15834 + }, + { + "epoch": 1.29, + "learning_rate": 1.1397761842677097e-05, + "loss": 0.3373, + "step": 15835 + }, + { + "epoch": 1.29, + "learning_rate": 1.1397218600608433e-05, + "loss": 0.2234, + "step": 15836 + }, + { + "epoch": 1.29, + "learning_rate": 1.1396675358539765e-05, + "loss": 0.3078, + "step": 15837 + }, + { + "epoch": 1.29, + "learning_rate": 1.1396132116471101e-05, + "loss": 0.3453, + "step": 15838 + }, + { + "epoch": 1.29, + "learning_rate": 1.1395588874402435e-05, + "loss": 0.2124, + "step": 15839 + }, + { + "epoch": 1.29, + "learning_rate": 1.139504563233377e-05, + "loss": 0.254, + "step": 15840 + }, + { + "epoch": 1.29, + "learning_rate": 1.1394502390265104e-05, + "loss": 0.5363, + "step": 15841 + }, + { + "epoch": 1.29, + "learning_rate": 1.1393959148196436e-05, + "loss": 0.5724, + "step": 15842 + }, + { + "epoch": 1.29, + "learning_rate": 1.1393415906127772e-05, + "loss": 0.2978, + "step": 15843 + }, + { + "epoch": 1.29, + "learning_rate": 1.1392872664059105e-05, + "loss": 0.5051, + "step": 15844 + }, + { + "epoch": 1.29, + "learning_rate": 1.139232942199044e-05, + "loss": 0.2976, + "step": 15845 + }, + { + "epoch": 1.29, + "learning_rate": 1.1391786179921773e-05, + "loss": 0.3087, + "step": 15846 + }, + { + "epoch": 1.29, + "learning_rate": 1.139124293785311e-05, + "loss": 0.3593, + "step": 15847 + }, + { + "epoch": 1.29, + "learning_rate": 1.1390699695784442e-05, + "loss": 0.1945, + "step": 15848 + }, + { + "epoch": 1.29, + "learning_rate": 1.1390156453715778e-05, + "loss": 0.4157, + "step": 15849 + }, + { + "epoch": 1.29, + "learning_rate": 1.138961321164711e-05, + "loss": 0.2245, + "step": 15850 + }, + { + "epoch": 1.29, + "learning_rate": 1.1389069969578446e-05, + "loss": 0.4913, + "step": 15851 + }, + { + "epoch": 1.29, + "learning_rate": 1.1388526727509779e-05, + "loss": 0.2712, + "step": 15852 + }, + { + "epoch": 1.29, + "learning_rate": 1.1387983485441115e-05, + "loss": 0.4091, + "step": 15853 + }, + { + "epoch": 1.29, + "learning_rate": 1.1387440243372447e-05, + "loss": 0.299, + "step": 15854 + }, + { + "epoch": 1.29, + "learning_rate": 1.1386897001303783e-05, + "loss": 0.3868, + "step": 15855 + }, + { + "epoch": 1.29, + "learning_rate": 1.1386353759235116e-05, + "loss": 0.2868, + "step": 15856 + }, + { + "epoch": 1.29, + "learning_rate": 1.1385810517166452e-05, + "loss": 0.3021, + "step": 15857 + }, + { + "epoch": 1.29, + "learning_rate": 1.1385267275097784e-05, + "loss": 0.7929, + "step": 15858 + }, + { + "epoch": 1.29, + "learning_rate": 1.138472403302912e-05, + "loss": 0.4835, + "step": 15859 + }, + { + "epoch": 1.29, + "learning_rate": 1.1384180790960453e-05, + "loss": 0.1728, + "step": 15860 + }, + { + "epoch": 1.29, + "learning_rate": 1.1383637548891787e-05, + "loss": 0.5326, + "step": 15861 + }, + { + "epoch": 1.29, + "learning_rate": 1.1383094306823121e-05, + "loss": 0.2715, + "step": 15862 + }, + { + "epoch": 1.29, + "learning_rate": 1.1382551064754455e-05, + "loss": 0.4185, + "step": 15863 + }, + { + "epoch": 1.29, + "learning_rate": 1.138200782268579e-05, + "loss": 0.4262, + "step": 15864 + }, + { + "epoch": 1.29, + "learning_rate": 1.1381464580617124e-05, + "loss": 0.21, + "step": 15865 + }, + { + "epoch": 1.29, + "learning_rate": 1.1380921338548458e-05, + "loss": 0.513, + "step": 15866 + }, + { + "epoch": 1.29, + "learning_rate": 1.1380378096479792e-05, + "loss": 0.5352, + "step": 15867 + }, + { + "epoch": 1.29, + "learning_rate": 1.1379834854411126e-05, + "loss": 0.3406, + "step": 15868 + }, + { + "epoch": 1.29, + "learning_rate": 1.137929161234246e-05, + "loss": 0.3768, + "step": 15869 + }, + { + "epoch": 1.29, + "learning_rate": 1.1378748370273795e-05, + "loss": 0.2532, + "step": 15870 + }, + { + "epoch": 1.29, + "learning_rate": 1.1378205128205129e-05, + "loss": 0.3046, + "step": 15871 + }, + { + "epoch": 1.29, + "learning_rate": 1.1377661886136463e-05, + "loss": 0.198, + "step": 15872 + }, + { + "epoch": 1.29, + "learning_rate": 1.1377118644067798e-05, + "loss": 0.3005, + "step": 15873 + }, + { + "epoch": 1.29, + "learning_rate": 1.1376575401999132e-05, + "loss": 0.3174, + "step": 15874 + }, + { + "epoch": 1.29, + "learning_rate": 1.1376032159930466e-05, + "loss": 0.2896, + "step": 15875 + }, + { + "epoch": 1.29, + "learning_rate": 1.1375488917861802e-05, + "loss": 0.3287, + "step": 15876 + }, + { + "epoch": 1.29, + "learning_rate": 1.1374945675793134e-05, + "loss": 0.1579, + "step": 15877 + }, + { + "epoch": 1.29, + "learning_rate": 1.137440243372447e-05, + "loss": 0.3303, + "step": 15878 + }, + { + "epoch": 1.29, + "learning_rate": 1.1373859191655803e-05, + "loss": 0.2651, + "step": 15879 + }, + { + "epoch": 1.29, + "learning_rate": 1.1373315949587135e-05, + "loss": 0.3108, + "step": 15880 + }, + { + "epoch": 1.29, + "learning_rate": 1.1372772707518471e-05, + "loss": 0.2585, + "step": 15881 + }, + { + "epoch": 1.29, + "learning_rate": 1.1372229465449804e-05, + "loss": 0.2328, + "step": 15882 + }, + { + "epoch": 1.29, + "learning_rate": 1.137168622338114e-05, + "loss": 0.3631, + "step": 15883 + }, + { + "epoch": 1.29, + "learning_rate": 1.1371142981312472e-05, + "loss": 0.5591, + "step": 15884 + }, + { + "epoch": 1.29, + "learning_rate": 1.1370599739243808e-05, + "loss": 0.6295, + "step": 15885 + }, + { + "epoch": 1.29, + "learning_rate": 1.137005649717514e-05, + "loss": 0.1882, + "step": 15886 + }, + { + "epoch": 1.29, + "learning_rate": 1.1369513255106477e-05, + "loss": 0.2704, + "step": 15887 + }, + { + "epoch": 1.29, + "learning_rate": 1.136897001303781e-05, + "loss": 0.2842, + "step": 15888 + }, + { + "epoch": 1.29, + "learning_rate": 1.1368426770969145e-05, + "loss": 0.3547, + "step": 15889 + }, + { + "epoch": 1.29, + "learning_rate": 1.1367883528900478e-05, + "loss": 0.326, + "step": 15890 + }, + { + "epoch": 1.29, + "learning_rate": 1.1367340286831814e-05, + "loss": 0.2425, + "step": 15891 + }, + { + "epoch": 1.29, + "learning_rate": 1.1366797044763146e-05, + "loss": 0.224, + "step": 15892 + }, + { + "epoch": 1.3, + "learning_rate": 1.1366253802694482e-05, + "loss": 0.3571, + "step": 15893 + }, + { + "epoch": 1.3, + "learning_rate": 1.1365710560625816e-05, + "loss": 0.2717, + "step": 15894 + }, + { + "epoch": 1.3, + "learning_rate": 1.136516731855715e-05, + "loss": 0.5669, + "step": 15895 + }, + { + "epoch": 1.3, + "learning_rate": 1.1364624076488485e-05, + "loss": 0.1303, + "step": 15896 + }, + { + "epoch": 1.3, + "learning_rate": 1.1364080834419819e-05, + "loss": 0.2451, + "step": 15897 + }, + { + "epoch": 1.3, + "learning_rate": 1.1363537592351153e-05, + "loss": 0.1114, + "step": 15898 + }, + { + "epoch": 1.3, + "learning_rate": 1.1362994350282486e-05, + "loss": 0.2928, + "step": 15899 + }, + { + "epoch": 1.3, + "learning_rate": 1.1362451108213822e-05, + "loss": 0.4449, + "step": 15900 + }, + { + "epoch": 1.3, + "learning_rate": 1.1361907866145154e-05, + "loss": 0.318, + "step": 15901 + }, + { + "epoch": 1.3, + "learning_rate": 1.136136462407649e-05, + "loss": 0.5243, + "step": 15902 + }, + { + "epoch": 1.3, + "learning_rate": 1.1360821382007823e-05, + "loss": 0.3769, + "step": 15903 + }, + { + "epoch": 1.3, + "learning_rate": 1.1360278139939159e-05, + "loss": 0.2019, + "step": 15904 + }, + { + "epoch": 1.3, + "learning_rate": 1.1359734897870491e-05, + "loss": 0.1611, + "step": 15905 + }, + { + "epoch": 1.3, + "learning_rate": 1.1359191655801827e-05, + "loss": 0.3143, + "step": 15906 + }, + { + "epoch": 1.3, + "learning_rate": 1.135864841373316e-05, + "loss": 0.3399, + "step": 15907 + }, + { + "epoch": 1.3, + "learning_rate": 1.1358105171664496e-05, + "loss": 0.3253, + "step": 15908 + }, + { + "epoch": 1.3, + "learning_rate": 1.1357561929595828e-05, + "loss": 0.3116, + "step": 15909 + }, + { + "epoch": 1.3, + "learning_rate": 1.1357018687527164e-05, + "loss": 0.2663, + "step": 15910 + }, + { + "epoch": 1.3, + "learning_rate": 1.1356475445458497e-05, + "loss": 0.1878, + "step": 15911 + }, + { + "epoch": 1.3, + "learning_rate": 1.1355932203389833e-05, + "loss": 0.2879, + "step": 15912 + }, + { + "epoch": 1.3, + "learning_rate": 1.1355388961321165e-05, + "loss": 0.353, + "step": 15913 + }, + { + "epoch": 1.3, + "learning_rate": 1.1354845719252501e-05, + "loss": 0.5427, + "step": 15914 + }, + { + "epoch": 1.3, + "learning_rate": 1.1354302477183834e-05, + "loss": 0.3429, + "step": 15915 + }, + { + "epoch": 1.3, + "learning_rate": 1.135375923511517e-05, + "loss": 0.2945, + "step": 15916 + }, + { + "epoch": 1.3, + "learning_rate": 1.1353215993046502e-05, + "loss": 0.3643, + "step": 15917 + }, + { + "epoch": 1.3, + "learning_rate": 1.1352672750977836e-05, + "loss": 0.3346, + "step": 15918 + }, + { + "epoch": 1.3, + "learning_rate": 1.135212950890917e-05, + "loss": 0.6374, + "step": 15919 + }, + { + "epoch": 1.3, + "learning_rate": 1.1351586266840505e-05, + "loss": 0.327, + "step": 15920 + }, + { + "epoch": 1.3, + "learning_rate": 1.1351043024771839e-05, + "loss": 0.5155, + "step": 15921 + }, + { + "epoch": 1.3, + "learning_rate": 1.1350499782703173e-05, + "loss": 0.4642, + "step": 15922 + }, + { + "epoch": 1.3, + "learning_rate": 1.1349956540634507e-05, + "loss": 0.1475, + "step": 15923 + }, + { + "epoch": 1.3, + "learning_rate": 1.1349413298565842e-05, + "loss": 0.2612, + "step": 15924 + }, + { + "epoch": 1.3, + "learning_rate": 1.1348870056497176e-05, + "loss": 0.2292, + "step": 15925 + }, + { + "epoch": 1.3, + "learning_rate": 1.134832681442851e-05, + "loss": 0.1844, + "step": 15926 + }, + { + "epoch": 1.3, + "learning_rate": 1.1347783572359844e-05, + "loss": 0.6676, + "step": 15927 + }, + { + "epoch": 1.3, + "learning_rate": 1.1347240330291179e-05, + "loss": 0.2918, + "step": 15928 + }, + { + "epoch": 1.3, + "learning_rate": 1.1346697088222513e-05, + "loss": 0.6009, + "step": 15929 + }, + { + "epoch": 1.3, + "learning_rate": 1.1346153846153847e-05, + "loss": 0.3427, + "step": 15930 + }, + { + "epoch": 1.3, + "learning_rate": 1.1345610604085183e-05, + "loss": 0.4585, + "step": 15931 + }, + { + "epoch": 1.3, + "learning_rate": 1.1345067362016515e-05, + "loss": 0.4335, + "step": 15932 + }, + { + "epoch": 1.3, + "learning_rate": 1.1344524119947851e-05, + "loss": 0.3232, + "step": 15933 + }, + { + "epoch": 1.3, + "learning_rate": 1.1343980877879184e-05, + "loss": 0.3259, + "step": 15934 + }, + { + "epoch": 1.3, + "learning_rate": 1.134343763581052e-05, + "loss": 0.3727, + "step": 15935 + }, + { + "epoch": 1.3, + "learning_rate": 1.1342894393741852e-05, + "loss": 0.1193, + "step": 15936 + }, + { + "epoch": 1.3, + "learning_rate": 1.1342351151673185e-05, + "loss": 0.4455, + "step": 15937 + }, + { + "epoch": 1.3, + "learning_rate": 1.134180790960452e-05, + "loss": 0.4201, + "step": 15938 + }, + { + "epoch": 1.3, + "learning_rate": 1.1341264667535853e-05, + "loss": 0.492, + "step": 15939 + }, + { + "epoch": 1.3, + "learning_rate": 1.134072142546719e-05, + "loss": 0.3269, + "step": 15940 + }, + { + "epoch": 1.3, + "learning_rate": 1.1340178183398522e-05, + "loss": 0.2688, + "step": 15941 + }, + { + "epoch": 1.3, + "learning_rate": 1.1339634941329858e-05, + "loss": 0.3933, + "step": 15942 + }, + { + "epoch": 1.3, + "learning_rate": 1.133909169926119e-05, + "loss": 0.1625, + "step": 15943 + }, + { + "epoch": 1.3, + "learning_rate": 1.1338548457192526e-05, + "loss": 0.3598, + "step": 15944 + }, + { + "epoch": 1.3, + "learning_rate": 1.1338005215123859e-05, + "loss": 0.5492, + "step": 15945 + }, + { + "epoch": 1.3, + "learning_rate": 1.1337461973055195e-05, + "loss": 0.2256, + "step": 15946 + }, + { + "epoch": 1.3, + "learning_rate": 1.1336918730986529e-05, + "loss": 0.2012, + "step": 15947 + }, + { + "epoch": 1.3, + "learning_rate": 1.1336375488917863e-05, + "loss": 0.2815, + "step": 15948 + }, + { + "epoch": 1.3, + "learning_rate": 1.1335832246849197e-05, + "loss": 0.4148, + "step": 15949 + }, + { + "epoch": 1.3, + "learning_rate": 1.1335289004780532e-05, + "loss": 0.2485, + "step": 15950 + }, + { + "epoch": 1.3, + "learning_rate": 1.1334745762711866e-05, + "loss": 0.1706, + "step": 15951 + }, + { + "epoch": 1.3, + "learning_rate": 1.13342025206432e-05, + "loss": 0.2234, + "step": 15952 + }, + { + "epoch": 1.3, + "learning_rate": 1.1333659278574534e-05, + "loss": 0.2143, + "step": 15953 + }, + { + "epoch": 1.3, + "learning_rate": 1.1333116036505869e-05, + "loss": 0.3058, + "step": 15954 + }, + { + "epoch": 1.3, + "learning_rate": 1.1332572794437203e-05, + "loss": 0.4137, + "step": 15955 + }, + { + "epoch": 1.3, + "learning_rate": 1.1332029552368535e-05, + "loss": 0.4921, + "step": 15956 + }, + { + "epoch": 1.3, + "learning_rate": 1.1331486310299871e-05, + "loss": 0.2765, + "step": 15957 + }, + { + "epoch": 1.3, + "learning_rate": 1.1330943068231204e-05, + "loss": 0.3735, + "step": 15958 + }, + { + "epoch": 1.3, + "learning_rate": 1.133039982616254e-05, + "loss": 0.2668, + "step": 15959 + }, + { + "epoch": 1.3, + "learning_rate": 1.1329856584093872e-05, + "loss": 0.2309, + "step": 15960 + }, + { + "epoch": 1.3, + "learning_rate": 1.1329313342025208e-05, + "loss": 0.0991, + "step": 15961 + }, + { + "epoch": 1.3, + "learning_rate": 1.132877009995654e-05, + "loss": 0.4845, + "step": 15962 + }, + { + "epoch": 1.3, + "learning_rate": 1.1328226857887877e-05, + "loss": 0.2552, + "step": 15963 + }, + { + "epoch": 1.3, + "learning_rate": 1.1327683615819209e-05, + "loss": 0.2793, + "step": 15964 + }, + { + "epoch": 1.3, + "learning_rate": 1.1327140373750545e-05, + "loss": 0.3207, + "step": 15965 + }, + { + "epoch": 1.3, + "learning_rate": 1.1326597131681878e-05, + "loss": 0.4996, + "step": 15966 + }, + { + "epoch": 1.3, + "learning_rate": 1.1326053889613214e-05, + "loss": 0.1744, + "step": 15967 + }, + { + "epoch": 1.3, + "learning_rate": 1.1325510647544546e-05, + "loss": 0.3396, + "step": 15968 + }, + { + "epoch": 1.3, + "learning_rate": 1.1324967405475882e-05, + "loss": 0.2521, + "step": 15969 + }, + { + "epoch": 1.3, + "learning_rate": 1.1324424163407215e-05, + "loss": 0.1707, + "step": 15970 + }, + { + "epoch": 1.3, + "learning_rate": 1.132388092133855e-05, + "loss": 0.3056, + "step": 15971 + }, + { + "epoch": 1.3, + "learning_rate": 1.1323337679269883e-05, + "loss": 0.5038, + "step": 15972 + }, + { + "epoch": 1.3, + "learning_rate": 1.1322794437201219e-05, + "loss": 0.2917, + "step": 15973 + }, + { + "epoch": 1.3, + "learning_rate": 1.1322251195132551e-05, + "loss": 0.6214, + "step": 15974 + }, + { + "epoch": 1.3, + "learning_rate": 1.1321707953063886e-05, + "loss": 0.454, + "step": 15975 + }, + { + "epoch": 1.3, + "learning_rate": 1.132116471099522e-05, + "loss": 0.6621, + "step": 15976 + }, + { + "epoch": 1.3, + "learning_rate": 1.1320621468926554e-05, + "loss": 0.1593, + "step": 15977 + }, + { + "epoch": 1.3, + "learning_rate": 1.1320078226857888e-05, + "loss": 0.4963, + "step": 15978 + }, + { + "epoch": 1.3, + "learning_rate": 1.1319534984789223e-05, + "loss": 0.2168, + "step": 15979 + }, + { + "epoch": 1.3, + "learning_rate": 1.1318991742720557e-05, + "loss": 0.1042, + "step": 15980 + }, + { + "epoch": 1.3, + "learning_rate": 1.1318448500651891e-05, + "loss": 0.2254, + "step": 15981 + }, + { + "epoch": 1.3, + "learning_rate": 1.1317905258583225e-05, + "loss": 0.4644, + "step": 15982 + }, + { + "epoch": 1.3, + "learning_rate": 1.131736201651456e-05, + "loss": 0.345, + "step": 15983 + }, + { + "epoch": 1.3, + "learning_rate": 1.1316818774445895e-05, + "loss": 0.3849, + "step": 15984 + }, + { + "epoch": 1.3, + "learning_rate": 1.1316275532377228e-05, + "loss": 0.38, + "step": 15985 + }, + { + "epoch": 1.3, + "learning_rate": 1.1315732290308564e-05, + "loss": 0.373, + "step": 15986 + }, + { + "epoch": 1.3, + "learning_rate": 1.1315189048239896e-05, + "loss": 0.2528, + "step": 15987 + }, + { + "epoch": 1.3, + "learning_rate": 1.1314645806171232e-05, + "loss": 0.3978, + "step": 15988 + }, + { + "epoch": 1.3, + "learning_rate": 1.1314102564102565e-05, + "loss": 0.3788, + "step": 15989 + }, + { + "epoch": 1.3, + "learning_rate": 1.13135593220339e-05, + "loss": 0.2842, + "step": 15990 + }, + { + "epoch": 1.3, + "learning_rate": 1.1313016079965233e-05, + "loss": 0.3794, + "step": 15991 + }, + { + "epoch": 1.3, + "learning_rate": 1.131247283789657e-05, + "loss": 0.3355, + "step": 15992 + }, + { + "epoch": 1.3, + "learning_rate": 1.1311929595827902e-05, + "loss": 0.3497, + "step": 15993 + }, + { + "epoch": 1.3, + "learning_rate": 1.1311386353759234e-05, + "loss": 0.6671, + "step": 15994 + }, + { + "epoch": 1.3, + "learning_rate": 1.131084311169057e-05, + "loss": 0.3746, + "step": 15995 + }, + { + "epoch": 1.3, + "learning_rate": 1.1310299869621903e-05, + "loss": 0.3539, + "step": 15996 + }, + { + "epoch": 1.3, + "learning_rate": 1.1309756627553239e-05, + "loss": 0.4153, + "step": 15997 + }, + { + "epoch": 1.3, + "learning_rate": 1.1309213385484571e-05, + "loss": 0.3031, + "step": 15998 + }, + { + "epoch": 1.3, + "learning_rate": 1.1308670143415907e-05, + "loss": 0.2599, + "step": 15999 + }, + { + "epoch": 1.3, + "learning_rate": 1.130812690134724e-05, + "loss": 0.4102, + "step": 16000 + }, + { + "epoch": 1.3, + "eval_accuracy": 0.8377992868059093, + "eval_loss": 0.4359860420227051, + "eval_runtime": 22.3255, + "eval_samples_per_second": 439.633, + "eval_steps_per_second": 3.449, + "step": 16000 + }, + { + "epoch": 1.3, + "learning_rate": 1.1307583659278576e-05, + "loss": 0.2351, + "step": 16001 + }, + { + "epoch": 1.3, + "learning_rate": 1.130704041720991e-05, + "loss": 0.3292, + "step": 16002 + }, + { + "epoch": 1.3, + "learning_rate": 1.1306497175141244e-05, + "loss": 0.3674, + "step": 16003 + }, + { + "epoch": 1.3, + "learning_rate": 1.1305953933072578e-05, + "loss": 0.2811, + "step": 16004 + }, + { + "epoch": 1.3, + "learning_rate": 1.1305410691003913e-05, + "loss": 0.4005, + "step": 16005 + }, + { + "epoch": 1.3, + "learning_rate": 1.1304867448935247e-05, + "loss": 0.4564, + "step": 16006 + }, + { + "epoch": 1.3, + "learning_rate": 1.1304324206866581e-05, + "loss": 0.1879, + "step": 16007 + }, + { + "epoch": 1.3, + "learning_rate": 1.1303780964797915e-05, + "loss": 0.3112, + "step": 16008 + }, + { + "epoch": 1.3, + "learning_rate": 1.130323772272925e-05, + "loss": 0.5578, + "step": 16009 + }, + { + "epoch": 1.3, + "learning_rate": 1.1302694480660584e-05, + "loss": 0.2473, + "step": 16010 + }, + { + "epoch": 1.3, + "learning_rate": 1.1302151238591918e-05, + "loss": 0.5502, + "step": 16011 + }, + { + "epoch": 1.3, + "learning_rate": 1.1301607996523252e-05, + "loss": 0.725, + "step": 16012 + }, + { + "epoch": 1.3, + "learning_rate": 1.1301064754454585e-05, + "loss": 0.3339, + "step": 16013 + }, + { + "epoch": 1.3, + "learning_rate": 1.130052151238592e-05, + "loss": 0.4914, + "step": 16014 + }, + { + "epoch": 1.31, + "learning_rate": 1.1299978270317253e-05, + "loss": 0.6457, + "step": 16015 + }, + { + "epoch": 1.31, + "learning_rate": 1.1299435028248589e-05, + "loss": 0.4561, + "step": 16016 + }, + { + "epoch": 1.31, + "learning_rate": 1.1298891786179922e-05, + "loss": 0.648, + "step": 16017 + }, + { + "epoch": 1.31, + "learning_rate": 1.1298348544111258e-05, + "loss": 0.3343, + "step": 16018 + }, + { + "epoch": 1.31, + "learning_rate": 1.129780530204259e-05, + "loss": 0.152, + "step": 16019 + }, + { + "epoch": 1.31, + "learning_rate": 1.1297262059973926e-05, + "loss": 0.358, + "step": 16020 + }, + { + "epoch": 1.31, + "learning_rate": 1.1296718817905259e-05, + "loss": 0.2523, + "step": 16021 + }, + { + "epoch": 1.31, + "learning_rate": 1.1296175575836595e-05, + "loss": 0.5367, + "step": 16022 + }, + { + "epoch": 1.31, + "learning_rate": 1.1295632333767927e-05, + "loss": 0.3108, + "step": 16023 + }, + { + "epoch": 1.31, + "learning_rate": 1.1295089091699263e-05, + "loss": 0.5783, + "step": 16024 + }, + { + "epoch": 1.31, + "learning_rate": 1.1294545849630595e-05, + "loss": 0.208, + "step": 16025 + }, + { + "epoch": 1.31, + "learning_rate": 1.1294002607561931e-05, + "loss": 0.454, + "step": 16026 + }, + { + "epoch": 1.31, + "learning_rate": 1.1293459365493264e-05, + "loss": 0.5923, + "step": 16027 + }, + { + "epoch": 1.31, + "learning_rate": 1.12929161234246e-05, + "loss": 0.3749, + "step": 16028 + }, + { + "epoch": 1.31, + "learning_rate": 1.1292372881355932e-05, + "loss": 0.3533, + "step": 16029 + }, + { + "epoch": 1.31, + "learning_rate": 1.1291829639287268e-05, + "loss": 0.3227, + "step": 16030 + }, + { + "epoch": 1.31, + "learning_rate": 1.1291286397218601e-05, + "loss": 0.2808, + "step": 16031 + }, + { + "epoch": 1.31, + "learning_rate": 1.1290743155149935e-05, + "loss": 0.5039, + "step": 16032 + }, + { + "epoch": 1.31, + "learning_rate": 1.129019991308127e-05, + "loss": 0.2912, + "step": 16033 + }, + { + "epoch": 1.31, + "learning_rate": 1.1289656671012604e-05, + "loss": 0.2042, + "step": 16034 + }, + { + "epoch": 1.31, + "learning_rate": 1.1289113428943938e-05, + "loss": 0.4342, + "step": 16035 + }, + { + "epoch": 1.31, + "learning_rate": 1.1288570186875272e-05, + "loss": 0.2665, + "step": 16036 + }, + { + "epoch": 1.31, + "learning_rate": 1.1288026944806606e-05, + "loss": 0.0987, + "step": 16037 + }, + { + "epoch": 1.31, + "learning_rate": 1.128748370273794e-05, + "loss": 0.373, + "step": 16038 + }, + { + "epoch": 1.31, + "learning_rate": 1.1286940460669276e-05, + "loss": 0.3521, + "step": 16039 + }, + { + "epoch": 1.31, + "learning_rate": 1.1286397218600609e-05, + "loss": 0.4183, + "step": 16040 + }, + { + "epoch": 1.31, + "learning_rate": 1.1285853976531945e-05, + "loss": 0.3166, + "step": 16041 + }, + { + "epoch": 1.31, + "learning_rate": 1.1285310734463277e-05, + "loss": 0.3469, + "step": 16042 + }, + { + "epoch": 1.31, + "learning_rate": 1.1284767492394613e-05, + "loss": 0.4105, + "step": 16043 + }, + { + "epoch": 1.31, + "learning_rate": 1.1284224250325946e-05, + "loss": 0.3266, + "step": 16044 + }, + { + "epoch": 1.31, + "learning_rate": 1.1283681008257282e-05, + "loss": 0.4591, + "step": 16045 + }, + { + "epoch": 1.31, + "learning_rate": 1.1283137766188614e-05, + "loss": 0.3485, + "step": 16046 + }, + { + "epoch": 1.31, + "learning_rate": 1.128259452411995e-05, + "loss": 0.4086, + "step": 16047 + }, + { + "epoch": 1.31, + "learning_rate": 1.1282051282051283e-05, + "loss": 0.2305, + "step": 16048 + }, + { + "epoch": 1.31, + "learning_rate": 1.1281508039982619e-05, + "loss": 0.2974, + "step": 16049 + }, + { + "epoch": 1.31, + "learning_rate": 1.1280964797913951e-05, + "loss": 0.3485, + "step": 16050 + }, + { + "epoch": 1.31, + "learning_rate": 1.1280421555845284e-05, + "loss": 0.2121, + "step": 16051 + }, + { + "epoch": 1.31, + "learning_rate": 1.127987831377662e-05, + "loss": 0.2423, + "step": 16052 + }, + { + "epoch": 1.31, + "learning_rate": 1.1279335071707952e-05, + "loss": 0.3923, + "step": 16053 + }, + { + "epoch": 1.31, + "learning_rate": 1.1278791829639288e-05, + "loss": 0.4317, + "step": 16054 + }, + { + "epoch": 1.31, + "learning_rate": 1.1278248587570622e-05, + "loss": 0.2302, + "step": 16055 + }, + { + "epoch": 1.31, + "learning_rate": 1.1277705345501957e-05, + "loss": 0.2919, + "step": 16056 + }, + { + "epoch": 1.31, + "learning_rate": 1.1277162103433291e-05, + "loss": 0.4075, + "step": 16057 + }, + { + "epoch": 1.31, + "learning_rate": 1.1276618861364625e-05, + "loss": 0.3083, + "step": 16058 + }, + { + "epoch": 1.31, + "learning_rate": 1.127607561929596e-05, + "loss": 0.3787, + "step": 16059 + }, + { + "epoch": 1.31, + "learning_rate": 1.1275532377227294e-05, + "loss": 0.4206, + "step": 16060 + }, + { + "epoch": 1.31, + "learning_rate": 1.1274989135158628e-05, + "loss": 0.315, + "step": 16061 + }, + { + "epoch": 1.31, + "learning_rate": 1.1274445893089962e-05, + "loss": 0.1334, + "step": 16062 + }, + { + "epoch": 1.31, + "learning_rate": 1.1273902651021296e-05, + "loss": 0.4658, + "step": 16063 + }, + { + "epoch": 1.31, + "learning_rate": 1.127335940895263e-05, + "loss": 0.3708, + "step": 16064 + }, + { + "epoch": 1.31, + "learning_rate": 1.1272816166883965e-05, + "loss": 0.4469, + "step": 16065 + }, + { + "epoch": 1.31, + "learning_rate": 1.1272272924815299e-05, + "loss": 0.3766, + "step": 16066 + }, + { + "epoch": 1.31, + "learning_rate": 1.1271729682746633e-05, + "loss": 0.343, + "step": 16067 + }, + { + "epoch": 1.31, + "learning_rate": 1.1271186440677967e-05, + "loss": 0.2331, + "step": 16068 + }, + { + "epoch": 1.31, + "learning_rate": 1.1270643198609302e-05, + "loss": 0.1643, + "step": 16069 + }, + { + "epoch": 1.31, + "learning_rate": 1.1270099956540634e-05, + "loss": 0.4183, + "step": 16070 + }, + { + "epoch": 1.31, + "learning_rate": 1.126955671447197e-05, + "loss": 0.5432, + "step": 16071 + }, + { + "epoch": 1.31, + "learning_rate": 1.1269013472403303e-05, + "loss": 0.3472, + "step": 16072 + }, + { + "epoch": 1.31, + "learning_rate": 1.1268470230334639e-05, + "loss": 0.2356, + "step": 16073 + }, + { + "epoch": 1.31, + "learning_rate": 1.1267926988265971e-05, + "loss": 0.2222, + "step": 16074 + }, + { + "epoch": 1.31, + "learning_rate": 1.1267383746197307e-05, + "loss": 0.1082, + "step": 16075 + }, + { + "epoch": 1.31, + "learning_rate": 1.126684050412864e-05, + "loss": 0.3442, + "step": 16076 + }, + { + "epoch": 1.31, + "learning_rate": 1.1266297262059975e-05, + "loss": 0.1884, + "step": 16077 + }, + { + "epoch": 1.31, + "learning_rate": 1.1265754019991308e-05, + "loss": 0.2994, + "step": 16078 + }, + { + "epoch": 1.31, + "learning_rate": 1.1265210777922644e-05, + "loss": 0.2606, + "step": 16079 + }, + { + "epoch": 1.31, + "learning_rate": 1.1264667535853976e-05, + "loss": 0.1236, + "step": 16080 + }, + { + "epoch": 1.31, + "learning_rate": 1.1264124293785312e-05, + "loss": 0.5704, + "step": 16081 + }, + { + "epoch": 1.31, + "learning_rate": 1.1263581051716645e-05, + "loss": 0.5845, + "step": 16082 + }, + { + "epoch": 1.31, + "learning_rate": 1.1263037809647981e-05, + "loss": 0.2595, + "step": 16083 + }, + { + "epoch": 1.31, + "learning_rate": 1.1262494567579313e-05, + "loss": 0.3319, + "step": 16084 + }, + { + "epoch": 1.31, + "learning_rate": 1.126195132551065e-05, + "loss": 0.2521, + "step": 16085 + }, + { + "epoch": 1.31, + "learning_rate": 1.1261408083441982e-05, + "loss": 0.204, + "step": 16086 + }, + { + "epoch": 1.31, + "learning_rate": 1.1260864841373318e-05, + "loss": 0.3579, + "step": 16087 + }, + { + "epoch": 1.31, + "learning_rate": 1.126032159930465e-05, + "loss": 0.1998, + "step": 16088 + }, + { + "epoch": 1.31, + "learning_rate": 1.1259778357235985e-05, + "loss": 0.6568, + "step": 16089 + }, + { + "epoch": 1.31, + "learning_rate": 1.1259235115167319e-05, + "loss": 0.3369, + "step": 16090 + }, + { + "epoch": 1.31, + "learning_rate": 1.1258691873098653e-05, + "loss": 0.2027, + "step": 16091 + }, + { + "epoch": 1.31, + "learning_rate": 1.1258148631029989e-05, + "loss": 0.137, + "step": 16092 + }, + { + "epoch": 1.31, + "learning_rate": 1.1257605388961321e-05, + "loss": 0.4322, + "step": 16093 + }, + { + "epoch": 1.31, + "learning_rate": 1.1257062146892657e-05, + "loss": 0.2054, + "step": 16094 + }, + { + "epoch": 1.31, + "learning_rate": 1.125651890482399e-05, + "loss": 0.3806, + "step": 16095 + }, + { + "epoch": 1.31, + "learning_rate": 1.1255975662755326e-05, + "loss": 0.1429, + "step": 16096 + }, + { + "epoch": 1.31, + "learning_rate": 1.1255432420686658e-05, + "loss": 0.4166, + "step": 16097 + }, + { + "epoch": 1.31, + "learning_rate": 1.1254889178617994e-05, + "loss": 0.3318, + "step": 16098 + }, + { + "epoch": 1.31, + "learning_rate": 1.1254345936549327e-05, + "loss": 0.4737, + "step": 16099 + }, + { + "epoch": 1.31, + "learning_rate": 1.1253802694480663e-05, + "loss": 0.401, + "step": 16100 + }, + { + "epoch": 1.31, + "learning_rate": 1.1253259452411995e-05, + "loss": 0.3968, + "step": 16101 + }, + { + "epoch": 1.31, + "learning_rate": 1.1252716210343331e-05, + "loss": 0.6402, + "step": 16102 + }, + { + "epoch": 1.31, + "learning_rate": 1.1252172968274664e-05, + "loss": 0.2951, + "step": 16103 + }, + { + "epoch": 1.31, + "learning_rate": 1.1251629726206e-05, + "loss": 0.2029, + "step": 16104 + }, + { + "epoch": 1.31, + "learning_rate": 1.1251086484137332e-05, + "loss": 0.4418, + "step": 16105 + }, + { + "epoch": 1.31, + "learning_rate": 1.1250543242068668e-05, + "loss": 0.3849, + "step": 16106 + }, + { + "epoch": 1.31, + "learning_rate": 1.125e-05, + "loss": 0.5348, + "step": 16107 + }, + { + "epoch": 1.31, + "learning_rate": 1.1249456757931333e-05, + "loss": 0.3248, + "step": 16108 + }, + { + "epoch": 1.31, + "learning_rate": 1.124891351586267e-05, + "loss": 0.1323, + "step": 16109 + }, + { + "epoch": 1.31, + "learning_rate": 1.1248370273794003e-05, + "loss": 0.2279, + "step": 16110 + }, + { + "epoch": 1.31, + "learning_rate": 1.1247827031725338e-05, + "loss": 0.3971, + "step": 16111 + }, + { + "epoch": 1.31, + "learning_rate": 1.1247283789656672e-05, + "loss": 0.3655, + "step": 16112 + }, + { + "epoch": 1.31, + "learning_rate": 1.1246740547588006e-05, + "loss": 0.2385, + "step": 16113 + }, + { + "epoch": 1.31, + "learning_rate": 1.124619730551934e-05, + "loss": 0.2667, + "step": 16114 + }, + { + "epoch": 1.31, + "learning_rate": 1.1245654063450675e-05, + "loss": 0.2855, + "step": 16115 + }, + { + "epoch": 1.31, + "learning_rate": 1.1245110821382009e-05, + "loss": 0.234, + "step": 16116 + }, + { + "epoch": 1.31, + "learning_rate": 1.1244567579313343e-05, + "loss": 0.4871, + "step": 16117 + }, + { + "epoch": 1.31, + "learning_rate": 1.1244024337244677e-05, + "loss": 0.3418, + "step": 16118 + }, + { + "epoch": 1.31, + "learning_rate": 1.1243481095176011e-05, + "loss": 0.3426, + "step": 16119 + }, + { + "epoch": 1.31, + "learning_rate": 1.1242937853107346e-05, + "loss": 0.2589, + "step": 16120 + }, + { + "epoch": 1.31, + "learning_rate": 1.124239461103868e-05, + "loss": 0.3077, + "step": 16121 + }, + { + "epoch": 1.31, + "learning_rate": 1.1241851368970014e-05, + "loss": 0.3795, + "step": 16122 + }, + { + "epoch": 1.31, + "learning_rate": 1.1241308126901348e-05, + "loss": 0.3752, + "step": 16123 + }, + { + "epoch": 1.31, + "learning_rate": 1.1240764884832683e-05, + "loss": 0.4496, + "step": 16124 + }, + { + "epoch": 1.31, + "learning_rate": 1.1240221642764017e-05, + "loss": 0.2742, + "step": 16125 + }, + { + "epoch": 1.31, + "learning_rate": 1.1239678400695351e-05, + "loss": 0.233, + "step": 16126 + }, + { + "epoch": 1.31, + "learning_rate": 1.1239135158626684e-05, + "loss": 0.3615, + "step": 16127 + }, + { + "epoch": 1.31, + "learning_rate": 1.123859191655802e-05, + "loss": 0.1625, + "step": 16128 + }, + { + "epoch": 1.31, + "learning_rate": 1.1238048674489352e-05, + "loss": 0.2697, + "step": 16129 + }, + { + "epoch": 1.31, + "learning_rate": 1.1237505432420688e-05, + "loss": 0.2419, + "step": 16130 + }, + { + "epoch": 1.31, + "learning_rate": 1.123696219035202e-05, + "loss": 0.2273, + "step": 16131 + }, + { + "epoch": 1.31, + "learning_rate": 1.1236418948283356e-05, + "loss": 0.3826, + "step": 16132 + }, + { + "epoch": 1.31, + "learning_rate": 1.1235875706214689e-05, + "loss": 0.4274, + "step": 16133 + }, + { + "epoch": 1.31, + "learning_rate": 1.1235332464146025e-05, + "loss": 0.3279, + "step": 16134 + }, + { + "epoch": 1.31, + "learning_rate": 1.1234789222077357e-05, + "loss": 0.2998, + "step": 16135 + }, + { + "epoch": 1.31, + "learning_rate": 1.1234245980008693e-05, + "loss": 0.2422, + "step": 16136 + }, + { + "epoch": 1.31, + "learning_rate": 1.1233702737940026e-05, + "loss": 0.2868, + "step": 16137 + }, + { + "epoch": 1.32, + "learning_rate": 1.1233159495871362e-05, + "loss": 0.2246, + "step": 16138 + }, + { + "epoch": 1.32, + "learning_rate": 1.1232616253802694e-05, + "loss": 0.2939, + "step": 16139 + }, + { + "epoch": 1.32, + "learning_rate": 1.123207301173403e-05, + "loss": 0.1869, + "step": 16140 + }, + { + "epoch": 1.32, + "learning_rate": 1.1231529769665363e-05, + "loss": 0.5449, + "step": 16141 + }, + { + "epoch": 1.32, + "learning_rate": 1.1230986527596699e-05, + "loss": 0.4434, + "step": 16142 + }, + { + "epoch": 1.32, + "learning_rate": 1.1230443285528031e-05, + "loss": 0.4006, + "step": 16143 + }, + { + "epoch": 1.32, + "learning_rate": 1.1229900043459367e-05, + "loss": 0.1438, + "step": 16144 + }, + { + "epoch": 1.32, + "learning_rate": 1.12293568013907e-05, + "loss": 0.4196, + "step": 16145 + }, + { + "epoch": 1.32, + "learning_rate": 1.1228813559322034e-05, + "loss": 0.2853, + "step": 16146 + }, + { + "epoch": 1.32, + "learning_rate": 1.122827031725337e-05, + "loss": 0.3213, + "step": 16147 + }, + { + "epoch": 1.32, + "learning_rate": 1.1227727075184702e-05, + "loss": 0.1784, + "step": 16148 + }, + { + "epoch": 1.32, + "learning_rate": 1.1227183833116038e-05, + "loss": 0.1442, + "step": 16149 + }, + { + "epoch": 1.32, + "learning_rate": 1.1226640591047371e-05, + "loss": 0.2316, + "step": 16150 + }, + { + "epoch": 1.32, + "learning_rate": 1.1226097348978707e-05, + "loss": 0.1588, + "step": 16151 + }, + { + "epoch": 1.32, + "learning_rate": 1.122555410691004e-05, + "loss": 0.4721, + "step": 16152 + }, + { + "epoch": 1.32, + "learning_rate": 1.1225010864841375e-05, + "loss": 0.1397, + "step": 16153 + }, + { + "epoch": 1.32, + "learning_rate": 1.1224467622772708e-05, + "loss": 0.2912, + "step": 16154 + }, + { + "epoch": 1.32, + "learning_rate": 1.1223924380704044e-05, + "loss": 0.255, + "step": 16155 + }, + { + "epoch": 1.32, + "learning_rate": 1.1223381138635376e-05, + "loss": 0.2164, + "step": 16156 + }, + { + "epoch": 1.32, + "learning_rate": 1.1222837896566712e-05, + "loss": 0.5657, + "step": 16157 + }, + { + "epoch": 1.32, + "learning_rate": 1.1222294654498045e-05, + "loss": 0.413, + "step": 16158 + }, + { + "epoch": 1.32, + "learning_rate": 1.122175141242938e-05, + "loss": 0.2624, + "step": 16159 + }, + { + "epoch": 1.32, + "learning_rate": 1.1221208170360713e-05, + "loss": 0.3578, + "step": 16160 + }, + { + "epoch": 1.32, + "learning_rate": 1.122066492829205e-05, + "loss": 0.2436, + "step": 16161 + }, + { + "epoch": 1.32, + "learning_rate": 1.1220121686223382e-05, + "loss": 0.3014, + "step": 16162 + }, + { + "epoch": 1.32, + "learning_rate": 1.1219578444154718e-05, + "loss": 0.2765, + "step": 16163 + }, + { + "epoch": 1.32, + "learning_rate": 1.121903520208605e-05, + "loss": 0.4731, + "step": 16164 + }, + { + "epoch": 1.32, + "learning_rate": 1.1218491960017384e-05, + "loss": 0.4975, + "step": 16165 + }, + { + "epoch": 1.32, + "learning_rate": 1.1217948717948719e-05, + "loss": 0.4103, + "step": 16166 + }, + { + "epoch": 1.32, + "learning_rate": 1.1217405475880053e-05, + "loss": 0.2959, + "step": 16167 + }, + { + "epoch": 1.32, + "learning_rate": 1.1216862233811387e-05, + "loss": 0.5662, + "step": 16168 + }, + { + "epoch": 1.32, + "learning_rate": 1.1216318991742721e-05, + "loss": 0.3509, + "step": 16169 + }, + { + "epoch": 1.32, + "learning_rate": 1.1215775749674056e-05, + "loss": 0.1414, + "step": 16170 + }, + { + "epoch": 1.32, + "learning_rate": 1.121523250760539e-05, + "loss": 0.231, + "step": 16171 + }, + { + "epoch": 1.32, + "learning_rate": 1.1214689265536724e-05, + "loss": 0.2541, + "step": 16172 + }, + { + "epoch": 1.32, + "learning_rate": 1.1214146023468058e-05, + "loss": 0.6632, + "step": 16173 + }, + { + "epoch": 1.32, + "learning_rate": 1.1213602781399392e-05, + "loss": 0.212, + "step": 16174 + }, + { + "epoch": 1.32, + "learning_rate": 1.1213059539330727e-05, + "loss": 0.3434, + "step": 16175 + }, + { + "epoch": 1.32, + "learning_rate": 1.1212516297262061e-05, + "loss": 0.363, + "step": 16176 + }, + { + "epoch": 1.32, + "learning_rate": 1.1211973055193395e-05, + "loss": 0.2223, + "step": 16177 + }, + { + "epoch": 1.32, + "learning_rate": 1.121142981312473e-05, + "loss": 0.2227, + "step": 16178 + }, + { + "epoch": 1.32, + "learning_rate": 1.1210886571056064e-05, + "loss": 0.1395, + "step": 16179 + }, + { + "epoch": 1.32, + "learning_rate": 1.1210343328987398e-05, + "loss": 0.3106, + "step": 16180 + }, + { + "epoch": 1.32, + "learning_rate": 1.1209800086918732e-05, + "loss": 0.4004, + "step": 16181 + }, + { + "epoch": 1.32, + "learning_rate": 1.1209256844850068e-05, + "loss": 0.509, + "step": 16182 + }, + { + "epoch": 1.32, + "learning_rate": 1.12087136027814e-05, + "loss": 0.2281, + "step": 16183 + }, + { + "epoch": 1.32, + "learning_rate": 1.1208170360712733e-05, + "loss": 0.4618, + "step": 16184 + }, + { + "epoch": 1.32, + "learning_rate": 1.1207627118644069e-05, + "loss": 0.4706, + "step": 16185 + }, + { + "epoch": 1.32, + "learning_rate": 1.1207083876575402e-05, + "loss": 0.1332, + "step": 16186 + }, + { + "epoch": 1.32, + "learning_rate": 1.1206540634506737e-05, + "loss": 0.2573, + "step": 16187 + }, + { + "epoch": 1.32, + "learning_rate": 1.120599739243807e-05, + "loss": 0.4021, + "step": 16188 + }, + { + "epoch": 1.32, + "learning_rate": 1.1205454150369406e-05, + "loss": 0.4801, + "step": 16189 + }, + { + "epoch": 1.32, + "learning_rate": 1.1204910908300738e-05, + "loss": 0.3101, + "step": 16190 + }, + { + "epoch": 1.32, + "learning_rate": 1.1204367666232074e-05, + "loss": 0.4718, + "step": 16191 + }, + { + "epoch": 1.32, + "learning_rate": 1.1203824424163407e-05, + "loss": 0.484, + "step": 16192 + }, + { + "epoch": 1.32, + "learning_rate": 1.1203281182094743e-05, + "loss": 0.4152, + "step": 16193 + }, + { + "epoch": 1.32, + "learning_rate": 1.1202737940026075e-05, + "loss": 0.2164, + "step": 16194 + }, + { + "epoch": 1.32, + "learning_rate": 1.1202194697957411e-05, + "loss": 0.3585, + "step": 16195 + }, + { + "epoch": 1.32, + "learning_rate": 1.1201651455888744e-05, + "loss": 0.1721, + "step": 16196 + }, + { + "epoch": 1.32, + "learning_rate": 1.120110821382008e-05, + "loss": 0.4293, + "step": 16197 + }, + { + "epoch": 1.32, + "learning_rate": 1.1200564971751412e-05, + "loss": 0.3821, + "step": 16198 + }, + { + "epoch": 1.32, + "learning_rate": 1.1200021729682748e-05, + "loss": 0.1415, + "step": 16199 + }, + { + "epoch": 1.32, + "learning_rate": 1.1199478487614082e-05, + "loss": 0.6136, + "step": 16200 + }, + { + "epoch": 1.32, + "learning_rate": 1.1198935245545417e-05, + "loss": 0.3506, + "step": 16201 + }, + { + "epoch": 1.32, + "learning_rate": 1.1198392003476751e-05, + "loss": 0.6763, + "step": 16202 + }, + { + "epoch": 1.32, + "learning_rate": 1.1197848761408083e-05, + "loss": 0.3604, + "step": 16203 + }, + { + "epoch": 1.32, + "learning_rate": 1.119730551933942e-05, + "loss": 0.1219, + "step": 16204 + }, + { + "epoch": 1.32, + "learning_rate": 1.1196762277270752e-05, + "loss": 0.1751, + "step": 16205 + }, + { + "epoch": 1.32, + "learning_rate": 1.1196219035202088e-05, + "loss": 0.2244, + "step": 16206 + }, + { + "epoch": 1.32, + "learning_rate": 1.119567579313342e-05, + "loss": 0.2739, + "step": 16207 + }, + { + "epoch": 1.32, + "learning_rate": 1.1195132551064756e-05, + "loss": 0.4486, + "step": 16208 + }, + { + "epoch": 1.32, + "learning_rate": 1.1194589308996089e-05, + "loss": 0.4231, + "step": 16209 + }, + { + "epoch": 1.32, + "learning_rate": 1.1194046066927425e-05, + "loss": 0.4031, + "step": 16210 + }, + { + "epoch": 1.32, + "learning_rate": 1.1193502824858757e-05, + "loss": 0.3335, + "step": 16211 + }, + { + "epoch": 1.32, + "learning_rate": 1.1192959582790093e-05, + "loss": 0.1524, + "step": 16212 + }, + { + "epoch": 1.32, + "learning_rate": 1.1192416340721426e-05, + "loss": 0.2937, + "step": 16213 + }, + { + "epoch": 1.32, + "learning_rate": 1.1191873098652762e-05, + "loss": 0.0683, + "step": 16214 + }, + { + "epoch": 1.32, + "learning_rate": 1.1191329856584094e-05, + "loss": 0.5442, + "step": 16215 + }, + { + "epoch": 1.32, + "learning_rate": 1.119078661451543e-05, + "loss": 0.6154, + "step": 16216 + }, + { + "epoch": 1.32, + "learning_rate": 1.1190243372446763e-05, + "loss": 0.3157, + "step": 16217 + }, + { + "epoch": 1.32, + "learning_rate": 1.1189700130378099e-05, + "loss": 0.3695, + "step": 16218 + }, + { + "epoch": 1.32, + "learning_rate": 1.1189156888309431e-05, + "loss": 0.1512, + "step": 16219 + }, + { + "epoch": 1.32, + "learning_rate": 1.1188613646240767e-05, + "loss": 0.1581, + "step": 16220 + }, + { + "epoch": 1.32, + "learning_rate": 1.11880704041721e-05, + "loss": 0.177, + "step": 16221 + }, + { + "epoch": 1.32, + "learning_rate": 1.1187527162103434e-05, + "loss": 0.4311, + "step": 16222 + }, + { + "epoch": 1.32, + "learning_rate": 1.1186983920034768e-05, + "loss": 0.4493, + "step": 16223 + }, + { + "epoch": 1.32, + "learning_rate": 1.1186440677966102e-05, + "loss": 0.3216, + "step": 16224 + }, + { + "epoch": 1.32, + "learning_rate": 1.1185897435897437e-05, + "loss": 0.3619, + "step": 16225 + }, + { + "epoch": 1.32, + "learning_rate": 1.118535419382877e-05, + "loss": 0.5102, + "step": 16226 + }, + { + "epoch": 1.32, + "learning_rate": 1.1184810951760105e-05, + "loss": 0.2911, + "step": 16227 + }, + { + "epoch": 1.32, + "learning_rate": 1.118426770969144e-05, + "loss": 0.3102, + "step": 16228 + }, + { + "epoch": 1.32, + "learning_rate": 1.1183724467622773e-05, + "loss": 0.1479, + "step": 16229 + }, + { + "epoch": 1.32, + "learning_rate": 1.1183181225554108e-05, + "loss": 0.2396, + "step": 16230 + }, + { + "epoch": 1.32, + "learning_rate": 1.1182637983485442e-05, + "loss": 0.2388, + "step": 16231 + }, + { + "epoch": 1.32, + "learning_rate": 1.1182094741416776e-05, + "loss": 0.251, + "step": 16232 + }, + { + "epoch": 1.32, + "learning_rate": 1.118155149934811e-05, + "loss": 0.3522, + "step": 16233 + }, + { + "epoch": 1.32, + "learning_rate": 1.1181008257279445e-05, + "loss": 0.4382, + "step": 16234 + }, + { + "epoch": 1.32, + "learning_rate": 1.1180465015210779e-05, + "loss": 0.3798, + "step": 16235 + }, + { + "epoch": 1.32, + "learning_rate": 1.1179921773142113e-05, + "loss": 0.3412, + "step": 16236 + }, + { + "epoch": 1.32, + "learning_rate": 1.1179378531073449e-05, + "loss": 0.2158, + "step": 16237 + }, + { + "epoch": 1.32, + "learning_rate": 1.1178835289004782e-05, + "loss": 0.0768, + "step": 16238 + }, + { + "epoch": 1.32, + "learning_rate": 1.1178292046936117e-05, + "loss": 0.2403, + "step": 16239 + }, + { + "epoch": 1.32, + "learning_rate": 1.117774880486745e-05, + "loss": 0.1716, + "step": 16240 + }, + { + "epoch": 1.32, + "learning_rate": 1.1177205562798783e-05, + "loss": 0.6076, + "step": 16241 + }, + { + "epoch": 1.32, + "learning_rate": 1.1176662320730118e-05, + "loss": 0.293, + "step": 16242 + }, + { + "epoch": 1.32, + "learning_rate": 1.1176119078661451e-05, + "loss": 0.3043, + "step": 16243 + }, + { + "epoch": 1.32, + "learning_rate": 1.1175575836592787e-05, + "loss": 0.3258, + "step": 16244 + }, + { + "epoch": 1.32, + "learning_rate": 1.117503259452412e-05, + "loss": 0.3747, + "step": 16245 + }, + { + "epoch": 1.32, + "learning_rate": 1.1174489352455455e-05, + "loss": 0.1962, + "step": 16246 + }, + { + "epoch": 1.32, + "learning_rate": 1.1173946110386788e-05, + "loss": 0.3611, + "step": 16247 + }, + { + "epoch": 1.32, + "learning_rate": 1.1173402868318124e-05, + "loss": 0.5471, + "step": 16248 + }, + { + "epoch": 1.32, + "learning_rate": 1.1172859626249456e-05, + "loss": 0.4914, + "step": 16249 + }, + { + "epoch": 1.32, + "learning_rate": 1.1172316384180792e-05, + "loss": 0.4178, + "step": 16250 + }, + { + "epoch": 1.32, + "eval_accuracy": 0.8356597045338767, + "eval_loss": 0.4477827250957489, + "eval_runtime": 22.3682, + "eval_samples_per_second": 438.793, + "eval_steps_per_second": 3.442, + "step": 16250 + }, + { + "epoch": 1.32, + "learning_rate": 1.1171773142112125e-05, + "loss": 0.5115, + "step": 16251 + }, + { + "epoch": 1.32, + "learning_rate": 1.117122990004346e-05, + "loss": 0.4397, + "step": 16252 + }, + { + "epoch": 1.32, + "learning_rate": 1.1170686657974793e-05, + "loss": 0.1698, + "step": 16253 + }, + { + "epoch": 1.32, + "learning_rate": 1.117014341590613e-05, + "loss": 0.1352, + "step": 16254 + }, + { + "epoch": 1.32, + "learning_rate": 1.1169600173837463e-05, + "loss": 0.138, + "step": 16255 + }, + { + "epoch": 1.32, + "learning_rate": 1.1169056931768798e-05, + "loss": 0.3774, + "step": 16256 + }, + { + "epoch": 1.32, + "learning_rate": 1.1168513689700132e-05, + "loss": 0.2657, + "step": 16257 + }, + { + "epoch": 1.32, + "learning_rate": 1.1167970447631466e-05, + "loss": 0.3737, + "step": 16258 + }, + { + "epoch": 1.32, + "learning_rate": 1.11674272055628e-05, + "loss": 0.4477, + "step": 16259 + }, + { + "epoch": 1.32, + "learning_rate": 1.1166883963494133e-05, + "loss": 0.4051, + "step": 16260 + }, + { + "epoch": 1.33, + "learning_rate": 1.1166340721425469e-05, + "loss": 0.2968, + "step": 16261 + }, + { + "epoch": 1.33, + "learning_rate": 1.1165797479356801e-05, + "loss": 0.3437, + "step": 16262 + }, + { + "epoch": 1.33, + "learning_rate": 1.1165254237288137e-05, + "loss": 0.348, + "step": 16263 + }, + { + "epoch": 1.33, + "learning_rate": 1.116471099521947e-05, + "loss": 0.5474, + "step": 16264 + }, + { + "epoch": 1.33, + "learning_rate": 1.1164167753150806e-05, + "loss": 0.4449, + "step": 16265 + }, + { + "epoch": 1.33, + "learning_rate": 1.1163624511082138e-05, + "loss": 0.363, + "step": 16266 + }, + { + "epoch": 1.33, + "learning_rate": 1.1163081269013474e-05, + "loss": 0.3316, + "step": 16267 + }, + { + "epoch": 1.33, + "learning_rate": 1.1162538026944807e-05, + "loss": 0.3169, + "step": 16268 + }, + { + "epoch": 1.33, + "learning_rate": 1.1161994784876143e-05, + "loss": 0.4789, + "step": 16269 + }, + { + "epoch": 1.33, + "learning_rate": 1.1161451542807475e-05, + "loss": 0.398, + "step": 16270 + }, + { + "epoch": 1.33, + "learning_rate": 1.1160908300738811e-05, + "loss": 0.6278, + "step": 16271 + }, + { + "epoch": 1.33, + "learning_rate": 1.1160365058670144e-05, + "loss": 0.2588, + "step": 16272 + }, + { + "epoch": 1.33, + "learning_rate": 1.115982181660148e-05, + "loss": 0.3486, + "step": 16273 + }, + { + "epoch": 1.33, + "learning_rate": 1.1159278574532812e-05, + "loss": 0.3851, + "step": 16274 + }, + { + "epoch": 1.33, + "learning_rate": 1.1158735332464148e-05, + "loss": 0.1365, + "step": 16275 + }, + { + "epoch": 1.33, + "learning_rate": 1.115819209039548e-05, + "loss": 0.1975, + "step": 16276 + }, + { + "epoch": 1.33, + "learning_rate": 1.1157648848326817e-05, + "loss": 0.2042, + "step": 16277 + }, + { + "epoch": 1.33, + "learning_rate": 1.1157105606258149e-05, + "loss": 0.3424, + "step": 16278 + }, + { + "epoch": 1.33, + "learning_rate": 1.1156562364189483e-05, + "loss": 0.589, + "step": 16279 + }, + { + "epoch": 1.33, + "learning_rate": 1.1156019122120818e-05, + "loss": 0.2702, + "step": 16280 + }, + { + "epoch": 1.33, + "learning_rate": 1.1155475880052152e-05, + "loss": 0.436, + "step": 16281 + }, + { + "epoch": 1.33, + "learning_rate": 1.1154932637983486e-05, + "loss": 0.2564, + "step": 16282 + }, + { + "epoch": 1.33, + "learning_rate": 1.115438939591482e-05, + "loss": 0.3006, + "step": 16283 + }, + { + "epoch": 1.33, + "learning_rate": 1.1153846153846154e-05, + "loss": 0.3613, + "step": 16284 + }, + { + "epoch": 1.33, + "learning_rate": 1.1153302911777489e-05, + "loss": 0.4585, + "step": 16285 + }, + { + "epoch": 1.33, + "learning_rate": 1.1152759669708823e-05, + "loss": 0.5779, + "step": 16286 + }, + { + "epoch": 1.33, + "learning_rate": 1.1152216427640157e-05, + "loss": 0.4322, + "step": 16287 + }, + { + "epoch": 1.33, + "learning_rate": 1.1151673185571491e-05, + "loss": 0.48, + "step": 16288 + }, + { + "epoch": 1.33, + "learning_rate": 1.1151129943502826e-05, + "loss": 0.4429, + "step": 16289 + }, + { + "epoch": 1.33, + "learning_rate": 1.1150586701434162e-05, + "loss": 0.2727, + "step": 16290 + }, + { + "epoch": 1.33, + "learning_rate": 1.1150043459365494e-05, + "loss": 0.3668, + "step": 16291 + }, + { + "epoch": 1.33, + "learning_rate": 1.114950021729683e-05, + "loss": 0.2446, + "step": 16292 + }, + { + "epoch": 1.33, + "learning_rate": 1.1148956975228163e-05, + "loss": 0.3126, + "step": 16293 + }, + { + "epoch": 1.33, + "learning_rate": 1.1148413733159498e-05, + "loss": 0.328, + "step": 16294 + }, + { + "epoch": 1.33, + "learning_rate": 1.1147870491090831e-05, + "loss": 0.3134, + "step": 16295 + }, + { + "epoch": 1.33, + "learning_rate": 1.1147327249022167e-05, + "loss": 0.1969, + "step": 16296 + }, + { + "epoch": 1.33, + "learning_rate": 1.11467840069535e-05, + "loss": 0.3288, + "step": 16297 + }, + { + "epoch": 1.33, + "learning_rate": 1.1146240764884832e-05, + "loss": 0.3529, + "step": 16298 + }, + { + "epoch": 1.33, + "learning_rate": 1.1145697522816168e-05, + "loss": 0.4701, + "step": 16299 + }, + { + "epoch": 1.33, + "learning_rate": 1.11451542807475e-05, + "loss": 0.2502, + "step": 16300 + }, + { + "epoch": 1.33, + "learning_rate": 1.1144611038678836e-05, + "loss": 0.3479, + "step": 16301 + }, + { + "epoch": 1.33, + "learning_rate": 1.1144067796610169e-05, + "loss": 0.225, + "step": 16302 + }, + { + "epoch": 1.33, + "learning_rate": 1.1143524554541505e-05, + "loss": 0.4232, + "step": 16303 + }, + { + "epoch": 1.33, + "learning_rate": 1.1142981312472837e-05, + "loss": 0.4782, + "step": 16304 + }, + { + "epoch": 1.33, + "learning_rate": 1.1142438070404173e-05, + "loss": 0.5059, + "step": 16305 + }, + { + "epoch": 1.33, + "learning_rate": 1.1141894828335506e-05, + "loss": 0.2069, + "step": 16306 + }, + { + "epoch": 1.33, + "learning_rate": 1.1141351586266842e-05, + "loss": 0.1397, + "step": 16307 + }, + { + "epoch": 1.33, + "learning_rate": 1.1140808344198176e-05, + "loss": 0.5661, + "step": 16308 + }, + { + "epoch": 1.33, + "learning_rate": 1.114026510212951e-05, + "loss": 0.2251, + "step": 16309 + }, + { + "epoch": 1.33, + "learning_rate": 1.1139721860060844e-05, + "loss": 0.2649, + "step": 16310 + }, + { + "epoch": 1.33, + "learning_rate": 1.1139178617992179e-05, + "loss": 0.3117, + "step": 16311 + }, + { + "epoch": 1.33, + "learning_rate": 1.1138635375923513e-05, + "loss": 0.3163, + "step": 16312 + }, + { + "epoch": 1.33, + "learning_rate": 1.1138092133854847e-05, + "loss": 0.3231, + "step": 16313 + }, + { + "epoch": 1.33, + "learning_rate": 1.1137548891786181e-05, + "loss": 0.5195, + "step": 16314 + }, + { + "epoch": 1.33, + "learning_rate": 1.1137005649717516e-05, + "loss": 0.2479, + "step": 16315 + }, + { + "epoch": 1.33, + "learning_rate": 1.113646240764885e-05, + "loss": 0.2584, + "step": 16316 + }, + { + "epoch": 1.33, + "learning_rate": 1.1135919165580182e-05, + "loss": 0.2469, + "step": 16317 + }, + { + "epoch": 1.33, + "learning_rate": 1.1135375923511518e-05, + "loss": 0.3864, + "step": 16318 + }, + { + "epoch": 1.33, + "learning_rate": 1.113483268144285e-05, + "loss": 0.394, + "step": 16319 + }, + { + "epoch": 1.33, + "learning_rate": 1.1134289439374187e-05, + "loss": 0.2215, + "step": 16320 + }, + { + "epoch": 1.33, + "learning_rate": 1.113374619730552e-05, + "loss": 0.225, + "step": 16321 + }, + { + "epoch": 1.33, + "learning_rate": 1.1133202955236855e-05, + "loss": 0.7111, + "step": 16322 + }, + { + "epoch": 1.33, + "learning_rate": 1.1132659713168188e-05, + "loss": 0.4148, + "step": 16323 + }, + { + "epoch": 1.33, + "learning_rate": 1.1132116471099524e-05, + "loss": 0.1996, + "step": 16324 + }, + { + "epoch": 1.33, + "learning_rate": 1.1131573229030856e-05, + "loss": 0.2175, + "step": 16325 + }, + { + "epoch": 1.33, + "learning_rate": 1.1131029986962192e-05, + "loss": 0.3281, + "step": 16326 + }, + { + "epoch": 1.33, + "learning_rate": 1.1130486744893525e-05, + "loss": 0.3903, + "step": 16327 + }, + { + "epoch": 1.33, + "learning_rate": 1.112994350282486e-05, + "loss": 0.3661, + "step": 16328 + }, + { + "epoch": 1.33, + "learning_rate": 1.1129400260756193e-05, + "loss": 0.3162, + "step": 16329 + }, + { + "epoch": 1.33, + "learning_rate": 1.1128857018687529e-05, + "loss": 0.1165, + "step": 16330 + }, + { + "epoch": 1.33, + "learning_rate": 1.1128313776618862e-05, + "loss": 0.2601, + "step": 16331 + }, + { + "epoch": 1.33, + "learning_rate": 1.1127770534550197e-05, + "loss": 0.2861, + "step": 16332 + }, + { + "epoch": 1.33, + "learning_rate": 1.112722729248153e-05, + "loss": 0.1919, + "step": 16333 + }, + { + "epoch": 1.33, + "learning_rate": 1.1126684050412866e-05, + "loss": 0.3105, + "step": 16334 + }, + { + "epoch": 1.33, + "learning_rate": 1.1126140808344198e-05, + "loss": 0.422, + "step": 16335 + }, + { + "epoch": 1.33, + "learning_rate": 1.1125597566275533e-05, + "loss": 0.422, + "step": 16336 + }, + { + "epoch": 1.33, + "learning_rate": 1.1125054324206867e-05, + "loss": 0.3771, + "step": 16337 + }, + { + "epoch": 1.33, + "learning_rate": 1.1124511082138201e-05, + "loss": 0.5795, + "step": 16338 + }, + { + "epoch": 1.33, + "learning_rate": 1.1123967840069535e-05, + "loss": 0.7476, + "step": 16339 + }, + { + "epoch": 1.33, + "learning_rate": 1.112342459800087e-05, + "loss": 0.1999, + "step": 16340 + }, + { + "epoch": 1.33, + "learning_rate": 1.1122881355932204e-05, + "loss": 0.5005, + "step": 16341 + }, + { + "epoch": 1.33, + "learning_rate": 1.1122338113863538e-05, + "loss": 0.3689, + "step": 16342 + }, + { + "epoch": 1.33, + "learning_rate": 1.1121794871794872e-05, + "loss": 0.3097, + "step": 16343 + }, + { + "epoch": 1.33, + "learning_rate": 1.1121251629726207e-05, + "loss": 0.5055, + "step": 16344 + }, + { + "epoch": 1.33, + "learning_rate": 1.1120708387657542e-05, + "loss": 0.3955, + "step": 16345 + }, + { + "epoch": 1.33, + "learning_rate": 1.1120165145588875e-05, + "loss": 0.5532, + "step": 16346 + }, + { + "epoch": 1.33, + "learning_rate": 1.1119621903520211e-05, + "loss": 0.4104, + "step": 16347 + }, + { + "epoch": 1.33, + "learning_rate": 1.1119078661451543e-05, + "loss": 0.4818, + "step": 16348 + }, + { + "epoch": 1.33, + "learning_rate": 1.111853541938288e-05, + "loss": 0.3654, + "step": 16349 + }, + { + "epoch": 1.33, + "learning_rate": 1.1117992177314212e-05, + "loss": 0.3545, + "step": 16350 + }, + { + "epoch": 1.33, + "learning_rate": 1.1117448935245548e-05, + "loss": 0.2199, + "step": 16351 + }, + { + "epoch": 1.33, + "learning_rate": 1.111690569317688e-05, + "loss": 0.4393, + "step": 16352 + }, + { + "epoch": 1.33, + "learning_rate": 1.1116362451108216e-05, + "loss": 0.224, + "step": 16353 + }, + { + "epoch": 1.33, + "learning_rate": 1.1115819209039549e-05, + "loss": 0.3553, + "step": 16354 + }, + { + "epoch": 1.33, + "learning_rate": 1.1115275966970881e-05, + "loss": 0.2996, + "step": 16355 + }, + { + "epoch": 1.33, + "learning_rate": 1.1114732724902217e-05, + "loss": 0.3053, + "step": 16356 + }, + { + "epoch": 1.33, + "learning_rate": 1.111418948283355e-05, + "loss": 0.6638, + "step": 16357 + }, + { + "epoch": 1.33, + "learning_rate": 1.1113646240764886e-05, + "loss": 0.3335, + "step": 16358 + }, + { + "epoch": 1.33, + "learning_rate": 1.1113102998696218e-05, + "loss": 0.5085, + "step": 16359 + }, + { + "epoch": 1.33, + "learning_rate": 1.1112559756627554e-05, + "loss": 0.2461, + "step": 16360 + }, + { + "epoch": 1.33, + "learning_rate": 1.1112016514558887e-05, + "loss": 0.4588, + "step": 16361 + }, + { + "epoch": 1.33, + "learning_rate": 1.1111473272490223e-05, + "loss": 0.1347, + "step": 16362 + }, + { + "epoch": 1.33, + "learning_rate": 1.1110930030421557e-05, + "loss": 0.2786, + "step": 16363 + }, + { + "epoch": 1.33, + "learning_rate": 1.1110386788352891e-05, + "loss": 0.3027, + "step": 16364 + }, + { + "epoch": 1.33, + "learning_rate": 1.1109843546284225e-05, + "loss": 0.5679, + "step": 16365 + }, + { + "epoch": 1.33, + "learning_rate": 1.110930030421556e-05, + "loss": 0.3118, + "step": 16366 + }, + { + "epoch": 1.33, + "learning_rate": 1.1108757062146894e-05, + "loss": 0.267, + "step": 16367 + }, + { + "epoch": 1.33, + "learning_rate": 1.1108213820078228e-05, + "loss": 0.5562, + "step": 16368 + }, + { + "epoch": 1.33, + "learning_rate": 1.1107670578009562e-05, + "loss": 0.1451, + "step": 16369 + }, + { + "epoch": 1.33, + "learning_rate": 1.1107127335940897e-05, + "loss": 0.411, + "step": 16370 + }, + { + "epoch": 1.33, + "learning_rate": 1.110658409387223e-05, + "loss": 0.6823, + "step": 16371 + }, + { + "epoch": 1.33, + "learning_rate": 1.1106040851803565e-05, + "loss": 0.3729, + "step": 16372 + }, + { + "epoch": 1.33, + "learning_rate": 1.11054976097349e-05, + "loss": 0.3895, + "step": 16373 + }, + { + "epoch": 1.33, + "learning_rate": 1.1104954367666232e-05, + "loss": 0.4955, + "step": 16374 + }, + { + "epoch": 1.33, + "learning_rate": 1.1104411125597568e-05, + "loss": 0.2536, + "step": 16375 + }, + { + "epoch": 1.33, + "learning_rate": 1.11038678835289e-05, + "loss": 0.3399, + "step": 16376 + }, + { + "epoch": 1.33, + "learning_rate": 1.1103324641460236e-05, + "loss": 0.1451, + "step": 16377 + }, + { + "epoch": 1.33, + "learning_rate": 1.1102781399391569e-05, + "loss": 0.3924, + "step": 16378 + }, + { + "epoch": 1.33, + "learning_rate": 1.1102238157322905e-05, + "loss": 0.328, + "step": 16379 + }, + { + "epoch": 1.33, + "learning_rate": 1.1101694915254237e-05, + "loss": 0.3217, + "step": 16380 + }, + { + "epoch": 1.33, + "learning_rate": 1.1101151673185573e-05, + "loss": 0.1509, + "step": 16381 + }, + { + "epoch": 1.33, + "learning_rate": 1.1100608431116906e-05, + "loss": 0.2268, + "step": 16382 + }, + { + "epoch": 1.33, + "learning_rate": 1.1100065189048242e-05, + "loss": 0.2464, + "step": 16383 + }, + { + "epoch": 1.34, + "learning_rate": 1.1099521946979574e-05, + "loss": 0.3001, + "step": 16384 + }, + { + "epoch": 1.34, + "learning_rate": 1.109897870491091e-05, + "loss": 0.2011, + "step": 16385 + }, + { + "epoch": 1.34, + "learning_rate": 1.1098435462842243e-05, + "loss": 0.3133, + "step": 16386 + }, + { + "epoch": 1.34, + "learning_rate": 1.1097892220773578e-05, + "loss": 0.5823, + "step": 16387 + }, + { + "epoch": 1.34, + "learning_rate": 1.1097348978704911e-05, + "loss": 0.3962, + "step": 16388 + }, + { + "epoch": 1.34, + "learning_rate": 1.1096805736636247e-05, + "loss": 0.1991, + "step": 16389 + }, + { + "epoch": 1.34, + "learning_rate": 1.109626249456758e-05, + "loss": 0.2909, + "step": 16390 + }, + { + "epoch": 1.34, + "learning_rate": 1.1095719252498915e-05, + "loss": 0.2138, + "step": 16391 + }, + { + "epoch": 1.34, + "learning_rate": 1.1095176010430248e-05, + "loss": 0.173, + "step": 16392 + }, + { + "epoch": 1.34, + "learning_rate": 1.1094632768361582e-05, + "loss": 0.1727, + "step": 16393 + }, + { + "epoch": 1.34, + "learning_rate": 1.1094089526292916e-05, + "loss": 0.3283, + "step": 16394 + }, + { + "epoch": 1.34, + "learning_rate": 1.109354628422425e-05, + "loss": 0.2124, + "step": 16395 + }, + { + "epoch": 1.34, + "learning_rate": 1.1093003042155585e-05, + "loss": 0.2563, + "step": 16396 + }, + { + "epoch": 1.34, + "learning_rate": 1.1092459800086919e-05, + "loss": 0.4989, + "step": 16397 + }, + { + "epoch": 1.34, + "learning_rate": 1.1091916558018255e-05, + "loss": 0.4412, + "step": 16398 + }, + { + "epoch": 1.34, + "learning_rate": 1.1091373315949588e-05, + "loss": 0.2666, + "step": 16399 + }, + { + "epoch": 1.34, + "learning_rate": 1.1090830073880923e-05, + "loss": 0.2565, + "step": 16400 + }, + { + "epoch": 1.34, + "learning_rate": 1.1090286831812256e-05, + "loss": 0.3468, + "step": 16401 + }, + { + "epoch": 1.34, + "learning_rate": 1.1089743589743592e-05, + "loss": 0.3969, + "step": 16402 + }, + { + "epoch": 1.34, + "learning_rate": 1.1089200347674924e-05, + "loss": 0.3936, + "step": 16403 + }, + { + "epoch": 1.34, + "learning_rate": 1.108865710560626e-05, + "loss": 0.3272, + "step": 16404 + }, + { + "epoch": 1.34, + "learning_rate": 1.1088113863537593e-05, + "loss": 0.3537, + "step": 16405 + }, + { + "epoch": 1.34, + "learning_rate": 1.1087570621468929e-05, + "loss": 0.3822, + "step": 16406 + }, + { + "epoch": 1.34, + "learning_rate": 1.1087027379400261e-05, + "loss": 0.0804, + "step": 16407 + }, + { + "epoch": 1.34, + "learning_rate": 1.1086484137331597e-05, + "loss": 0.2389, + "step": 16408 + }, + { + "epoch": 1.34, + "learning_rate": 1.108594089526293e-05, + "loss": 0.1902, + "step": 16409 + }, + { + "epoch": 1.34, + "learning_rate": 1.1085397653194266e-05, + "loss": 0.2318, + "step": 16410 + }, + { + "epoch": 1.34, + "learning_rate": 1.1084854411125598e-05, + "loss": 0.2463, + "step": 16411 + }, + { + "epoch": 1.34, + "learning_rate": 1.1084311169056931e-05, + "loss": 0.314, + "step": 16412 + }, + { + "epoch": 1.34, + "learning_rate": 1.1083767926988267e-05, + "loss": 0.5661, + "step": 16413 + }, + { + "epoch": 1.34, + "learning_rate": 1.10832246849196e-05, + "loss": 0.2579, + "step": 16414 + }, + { + "epoch": 1.34, + "learning_rate": 1.1082681442850935e-05, + "loss": 0.4646, + "step": 16415 + }, + { + "epoch": 1.34, + "learning_rate": 1.108213820078227e-05, + "loss": 0.3102, + "step": 16416 + }, + { + "epoch": 1.34, + "learning_rate": 1.1081594958713604e-05, + "loss": 0.481, + "step": 16417 + }, + { + "epoch": 1.34, + "learning_rate": 1.1081051716644938e-05, + "loss": 0.152, + "step": 16418 + }, + { + "epoch": 1.34, + "learning_rate": 1.1080508474576272e-05, + "loss": 0.4471, + "step": 16419 + }, + { + "epoch": 1.34, + "learning_rate": 1.1079965232507606e-05, + "loss": 0.3046, + "step": 16420 + }, + { + "epoch": 1.34, + "learning_rate": 1.107942199043894e-05, + "loss": 0.1799, + "step": 16421 + }, + { + "epoch": 1.34, + "learning_rate": 1.1078878748370275e-05, + "loss": 0.3766, + "step": 16422 + }, + { + "epoch": 1.34, + "learning_rate": 1.1078335506301609e-05, + "loss": 0.1081, + "step": 16423 + }, + { + "epoch": 1.34, + "learning_rate": 1.1077792264232943e-05, + "loss": 0.202, + "step": 16424 + }, + { + "epoch": 1.34, + "learning_rate": 1.1077249022164278e-05, + "loss": 0.3976, + "step": 16425 + }, + { + "epoch": 1.34, + "learning_rate": 1.1076705780095612e-05, + "loss": 0.337, + "step": 16426 + }, + { + "epoch": 1.34, + "learning_rate": 1.1076162538026946e-05, + "loss": 0.4208, + "step": 16427 + }, + { + "epoch": 1.34, + "learning_rate": 1.107561929595828e-05, + "loss": 0.2838, + "step": 16428 + }, + { + "epoch": 1.34, + "learning_rate": 1.1075076053889614e-05, + "loss": 0.506, + "step": 16429 + }, + { + "epoch": 1.34, + "learning_rate": 1.1074532811820949e-05, + "loss": 0.4736, + "step": 16430 + }, + { + "epoch": 1.34, + "learning_rate": 1.1073989569752281e-05, + "loss": 0.2649, + "step": 16431 + }, + { + "epoch": 1.34, + "learning_rate": 1.1073446327683617e-05, + "loss": 0.0914, + "step": 16432 + }, + { + "epoch": 1.34, + "learning_rate": 1.107290308561495e-05, + "loss": 0.1513, + "step": 16433 + }, + { + "epoch": 1.34, + "learning_rate": 1.1072359843546286e-05, + "loss": 0.4519, + "step": 16434 + }, + { + "epoch": 1.34, + "learning_rate": 1.1071816601477618e-05, + "loss": 0.4764, + "step": 16435 + }, + { + "epoch": 1.34, + "learning_rate": 1.1071273359408954e-05, + "loss": 0.3426, + "step": 16436 + }, + { + "epoch": 1.34, + "learning_rate": 1.1070730117340287e-05, + "loss": 0.3275, + "step": 16437 + }, + { + "epoch": 1.34, + "learning_rate": 1.1070186875271623e-05, + "loss": 0.2726, + "step": 16438 + }, + { + "epoch": 1.34, + "learning_rate": 1.1069643633202955e-05, + "loss": 0.3602, + "step": 16439 + }, + { + "epoch": 1.34, + "learning_rate": 1.1069100391134291e-05, + "loss": 0.404, + "step": 16440 + }, + { + "epoch": 1.34, + "learning_rate": 1.1068557149065624e-05, + "loss": 0.4457, + "step": 16441 + }, + { + "epoch": 1.34, + "learning_rate": 1.106801390699696e-05, + "loss": 0.2835, + "step": 16442 + }, + { + "epoch": 1.34, + "learning_rate": 1.1067470664928292e-05, + "loss": 0.262, + "step": 16443 + }, + { + "epoch": 1.34, + "learning_rate": 1.1066927422859628e-05, + "loss": 0.4972, + "step": 16444 + }, + { + "epoch": 1.34, + "learning_rate": 1.106638418079096e-05, + "loss": 0.3644, + "step": 16445 + }, + { + "epoch": 1.34, + "learning_rate": 1.1065840938722296e-05, + "loss": 0.3567, + "step": 16446 + }, + { + "epoch": 1.34, + "learning_rate": 1.1065297696653629e-05, + "loss": 0.2722, + "step": 16447 + }, + { + "epoch": 1.34, + "learning_rate": 1.1064754454584965e-05, + "loss": 0.2235, + "step": 16448 + }, + { + "epoch": 1.34, + "learning_rate": 1.1064211212516297e-05, + "loss": 0.5556, + "step": 16449 + }, + { + "epoch": 1.34, + "learning_rate": 1.1063667970447632e-05, + "loss": 0.3563, + "step": 16450 + }, + { + "epoch": 1.34, + "learning_rate": 1.1063124728378966e-05, + "loss": 0.497, + "step": 16451 + }, + { + "epoch": 1.34, + "learning_rate": 1.10625814863103e-05, + "loss": 0.42, + "step": 16452 + }, + { + "epoch": 1.34, + "learning_rate": 1.1062038244241636e-05, + "loss": 0.4013, + "step": 16453 + }, + { + "epoch": 1.34, + "learning_rate": 1.1061495002172969e-05, + "loss": 0.2644, + "step": 16454 + }, + { + "epoch": 1.34, + "learning_rate": 1.1060951760104304e-05, + "loss": 0.5765, + "step": 16455 + }, + { + "epoch": 1.34, + "learning_rate": 1.1060408518035637e-05, + "loss": 0.2863, + "step": 16456 + }, + { + "epoch": 1.34, + "learning_rate": 1.1059865275966973e-05, + "loss": 0.4727, + "step": 16457 + }, + { + "epoch": 1.34, + "learning_rate": 1.1059322033898305e-05, + "loss": 0.2982, + "step": 16458 + }, + { + "epoch": 1.34, + "learning_rate": 1.1058778791829641e-05, + "loss": 0.188, + "step": 16459 + }, + { + "epoch": 1.34, + "learning_rate": 1.1058235549760974e-05, + "loss": 0.2087, + "step": 16460 + }, + { + "epoch": 1.34, + "learning_rate": 1.105769230769231e-05, + "loss": 0.6129, + "step": 16461 + }, + { + "epoch": 1.34, + "learning_rate": 1.1057149065623642e-05, + "loss": 0.1544, + "step": 16462 + }, + { + "epoch": 1.34, + "learning_rate": 1.1056605823554978e-05, + "loss": 0.5188, + "step": 16463 + }, + { + "epoch": 1.34, + "learning_rate": 1.1056062581486311e-05, + "loss": 0.4071, + "step": 16464 + }, + { + "epoch": 1.34, + "learning_rate": 1.1055519339417647e-05, + "loss": 0.2118, + "step": 16465 + }, + { + "epoch": 1.34, + "learning_rate": 1.105497609734898e-05, + "loss": 0.3163, + "step": 16466 + }, + { + "epoch": 1.34, + "learning_rate": 1.1054432855280315e-05, + "loss": 0.3753, + "step": 16467 + }, + { + "epoch": 1.34, + "learning_rate": 1.1053889613211648e-05, + "loss": 0.2586, + "step": 16468 + }, + { + "epoch": 1.34, + "learning_rate": 1.105334637114298e-05, + "loss": 0.3387, + "step": 16469 + }, + { + "epoch": 1.34, + "learning_rate": 1.1052803129074316e-05, + "loss": 0.4111, + "step": 16470 + }, + { + "epoch": 1.34, + "learning_rate": 1.105225988700565e-05, + "loss": 0.2382, + "step": 16471 + }, + { + "epoch": 1.34, + "learning_rate": 1.1051716644936985e-05, + "loss": 0.2784, + "step": 16472 + }, + { + "epoch": 1.34, + "learning_rate": 1.1051173402868319e-05, + "loss": 0.325, + "step": 16473 + }, + { + "epoch": 1.34, + "learning_rate": 1.1050630160799653e-05, + "loss": 0.2739, + "step": 16474 + }, + { + "epoch": 1.34, + "learning_rate": 1.1050086918730987e-05, + "loss": 0.3485, + "step": 16475 + }, + { + "epoch": 1.34, + "learning_rate": 1.1049543676662322e-05, + "loss": 0.4148, + "step": 16476 + }, + { + "epoch": 1.34, + "learning_rate": 1.1049000434593656e-05, + "loss": 0.5412, + "step": 16477 + }, + { + "epoch": 1.34, + "learning_rate": 1.104845719252499e-05, + "loss": 0.3423, + "step": 16478 + }, + { + "epoch": 1.34, + "learning_rate": 1.1047913950456324e-05, + "loss": 0.2892, + "step": 16479 + }, + { + "epoch": 1.34, + "learning_rate": 1.1047370708387659e-05, + "loss": 0.1813, + "step": 16480 + }, + { + "epoch": 1.34, + "learning_rate": 1.1046827466318993e-05, + "loss": 0.3677, + "step": 16481 + }, + { + "epoch": 1.34, + "learning_rate": 1.1046284224250327e-05, + "loss": 0.3637, + "step": 16482 + }, + { + "epoch": 1.34, + "learning_rate": 1.1045740982181661e-05, + "loss": 0.2945, + "step": 16483 + }, + { + "epoch": 1.34, + "learning_rate": 1.1045197740112995e-05, + "loss": 0.4156, + "step": 16484 + }, + { + "epoch": 1.34, + "learning_rate": 1.104465449804433e-05, + "loss": 0.6596, + "step": 16485 + }, + { + "epoch": 1.34, + "learning_rate": 1.1044111255975664e-05, + "loss": 0.5193, + "step": 16486 + }, + { + "epoch": 1.34, + "learning_rate": 1.1043568013906998e-05, + "loss": 0.4083, + "step": 16487 + }, + { + "epoch": 1.34, + "learning_rate": 1.104302477183833e-05, + "loss": 0.6535, + "step": 16488 + }, + { + "epoch": 1.34, + "learning_rate": 1.1042481529769667e-05, + "loss": 0.3188, + "step": 16489 + }, + { + "epoch": 1.34, + "learning_rate": 1.1041938287700999e-05, + "loss": 0.2385, + "step": 16490 + }, + { + "epoch": 1.34, + "learning_rate": 1.1041395045632335e-05, + "loss": 0.2228, + "step": 16491 + }, + { + "epoch": 1.34, + "learning_rate": 1.1040851803563668e-05, + "loss": 0.3653, + "step": 16492 + }, + { + "epoch": 1.34, + "learning_rate": 1.1040308561495004e-05, + "loss": 0.6221, + "step": 16493 + }, + { + "epoch": 1.34, + "learning_rate": 1.1039765319426336e-05, + "loss": 0.216, + "step": 16494 + }, + { + "epoch": 1.34, + "learning_rate": 1.1039222077357672e-05, + "loss": 0.1808, + "step": 16495 + }, + { + "epoch": 1.34, + "learning_rate": 1.1038678835289005e-05, + "loss": 0.2105, + "step": 16496 + }, + { + "epoch": 1.34, + "learning_rate": 1.103813559322034e-05, + "loss": 0.3787, + "step": 16497 + }, + { + "epoch": 1.34, + "learning_rate": 1.1037592351151673e-05, + "loss": 0.2061, + "step": 16498 + }, + { + "epoch": 1.34, + "learning_rate": 1.1037049109083009e-05, + "loss": 0.1262, + "step": 16499 + }, + { + "epoch": 1.34, + "learning_rate": 1.1036505867014341e-05, + "loss": 0.4839, + "step": 16500 + }, + { + "epoch": 1.34, + "eval_accuracy": 0.8401426388181356, + "eval_loss": 0.4363251030445099, + "eval_runtime": 22.3596, + "eval_samples_per_second": 438.962, + "eval_steps_per_second": 3.444, + "step": 16500 + }, + { + "epoch": 1.34, + "learning_rate": 1.1035962624945677e-05, + "loss": 0.2244, + "step": 16501 + }, + { + "epoch": 1.34, + "learning_rate": 1.103541938287701e-05, + "loss": 0.2166, + "step": 16502 + }, + { + "epoch": 1.34, + "learning_rate": 1.1034876140808346e-05, + "loss": 0.3272, + "step": 16503 + }, + { + "epoch": 1.34, + "learning_rate": 1.1034332898739678e-05, + "loss": 0.3746, + "step": 16504 + }, + { + "epoch": 1.34, + "learning_rate": 1.1033789656671014e-05, + "loss": 0.5159, + "step": 16505 + }, + { + "epoch": 1.35, + "learning_rate": 1.1033246414602349e-05, + "loss": 0.4163, + "step": 16506 + }, + { + "epoch": 1.35, + "learning_rate": 1.1032703172533681e-05, + "loss": 0.4161, + "step": 16507 + }, + { + "epoch": 1.35, + "learning_rate": 1.1032159930465017e-05, + "loss": 0.3953, + "step": 16508 + }, + { + "epoch": 1.35, + "learning_rate": 1.103161668839635e-05, + "loss": 0.3999, + "step": 16509 + }, + { + "epoch": 1.35, + "learning_rate": 1.1031073446327685e-05, + "loss": 0.4098, + "step": 16510 + }, + { + "epoch": 1.35, + "learning_rate": 1.1030530204259018e-05, + "loss": 0.3111, + "step": 16511 + }, + { + "epoch": 1.35, + "learning_rate": 1.1029986962190354e-05, + "loss": 0.4052, + "step": 16512 + }, + { + "epoch": 1.35, + "learning_rate": 1.1029443720121686e-05, + "loss": 0.3048, + "step": 16513 + }, + { + "epoch": 1.35, + "learning_rate": 1.1028900478053022e-05, + "loss": 0.3716, + "step": 16514 + }, + { + "epoch": 1.35, + "learning_rate": 1.1028357235984355e-05, + "loss": 0.3776, + "step": 16515 + }, + { + "epoch": 1.35, + "learning_rate": 1.102781399391569e-05, + "loss": 0.1398, + "step": 16516 + }, + { + "epoch": 1.35, + "learning_rate": 1.1027270751847023e-05, + "loss": 0.1998, + "step": 16517 + }, + { + "epoch": 1.35, + "learning_rate": 1.102672750977836e-05, + "loss": 0.2158, + "step": 16518 + }, + { + "epoch": 1.35, + "learning_rate": 1.1026184267709692e-05, + "loss": 0.3217, + "step": 16519 + }, + { + "epoch": 1.35, + "learning_rate": 1.1025641025641028e-05, + "loss": 0.1969, + "step": 16520 + }, + { + "epoch": 1.35, + "learning_rate": 1.102509778357236e-05, + "loss": 0.3382, + "step": 16521 + }, + { + "epoch": 1.35, + "learning_rate": 1.1024554541503696e-05, + "loss": 0.2267, + "step": 16522 + }, + { + "epoch": 1.35, + "learning_rate": 1.1024011299435029e-05, + "loss": 0.3294, + "step": 16523 + }, + { + "epoch": 1.35, + "learning_rate": 1.1023468057366365e-05, + "loss": 0.5255, + "step": 16524 + }, + { + "epoch": 1.35, + "learning_rate": 1.1022924815297697e-05, + "loss": 0.4888, + "step": 16525 + }, + { + "epoch": 1.35, + "learning_rate": 1.1022381573229031e-05, + "loss": 0.3846, + "step": 16526 + }, + { + "epoch": 1.35, + "learning_rate": 1.1021838331160366e-05, + "loss": 0.371, + "step": 16527 + }, + { + "epoch": 1.35, + "learning_rate": 1.10212950890917e-05, + "loss": 0.173, + "step": 16528 + }, + { + "epoch": 1.35, + "learning_rate": 1.1020751847023034e-05, + "loss": 0.4222, + "step": 16529 + }, + { + "epoch": 1.35, + "learning_rate": 1.1020208604954368e-05, + "loss": 0.6375, + "step": 16530 + }, + { + "epoch": 1.35, + "learning_rate": 1.1019665362885703e-05, + "loss": 0.265, + "step": 16531 + }, + { + "epoch": 1.35, + "learning_rate": 1.1019122120817037e-05, + "loss": 0.3315, + "step": 16532 + }, + { + "epoch": 1.35, + "learning_rate": 1.1018578878748371e-05, + "loss": 0.216, + "step": 16533 + }, + { + "epoch": 1.35, + "learning_rate": 1.1018035636679705e-05, + "loss": 0.1891, + "step": 16534 + }, + { + "epoch": 1.35, + "learning_rate": 1.101749239461104e-05, + "loss": 0.4333, + "step": 16535 + }, + { + "epoch": 1.35, + "learning_rate": 1.1016949152542374e-05, + "loss": 0.1659, + "step": 16536 + }, + { + "epoch": 1.35, + "learning_rate": 1.1016405910473708e-05, + "loss": 0.3432, + "step": 16537 + }, + { + "epoch": 1.35, + "learning_rate": 1.1015862668405042e-05, + "loss": 0.3454, + "step": 16538 + }, + { + "epoch": 1.35, + "learning_rate": 1.1015319426336376e-05, + "loss": 0.4341, + "step": 16539 + }, + { + "epoch": 1.35, + "learning_rate": 1.101477618426771e-05, + "loss": 0.2634, + "step": 16540 + }, + { + "epoch": 1.35, + "learning_rate": 1.1014232942199045e-05, + "loss": 0.3286, + "step": 16541 + }, + { + "epoch": 1.35, + "learning_rate": 1.1013689700130379e-05, + "loss": 0.1438, + "step": 16542 + }, + { + "epoch": 1.35, + "learning_rate": 1.1013146458061715e-05, + "loss": 0.2547, + "step": 16543 + }, + { + "epoch": 1.35, + "learning_rate": 1.1012603215993048e-05, + "loss": 0.2853, + "step": 16544 + }, + { + "epoch": 1.35, + "learning_rate": 1.101205997392438e-05, + "loss": 0.4103, + "step": 16545 + }, + { + "epoch": 1.35, + "learning_rate": 1.1011516731855716e-05, + "loss": 0.5521, + "step": 16546 + }, + { + "epoch": 1.35, + "learning_rate": 1.1010973489787049e-05, + "loss": 0.2315, + "step": 16547 + }, + { + "epoch": 1.35, + "learning_rate": 1.1010430247718385e-05, + "loss": 0.3321, + "step": 16548 + }, + { + "epoch": 1.35, + "learning_rate": 1.1009887005649717e-05, + "loss": 0.5801, + "step": 16549 + }, + { + "epoch": 1.35, + "learning_rate": 1.1009343763581053e-05, + "loss": 0.2118, + "step": 16550 + }, + { + "epoch": 1.35, + "learning_rate": 1.1008800521512386e-05, + "loss": 0.2443, + "step": 16551 + }, + { + "epoch": 1.35, + "learning_rate": 1.1008257279443721e-05, + "loss": 0.3028, + "step": 16552 + }, + { + "epoch": 1.35, + "learning_rate": 1.1007714037375054e-05, + "loss": 0.4507, + "step": 16553 + }, + { + "epoch": 1.35, + "learning_rate": 1.100717079530639e-05, + "loss": 0.3005, + "step": 16554 + }, + { + "epoch": 1.35, + "learning_rate": 1.1006627553237722e-05, + "loss": 0.5069, + "step": 16555 + }, + { + "epoch": 1.35, + "learning_rate": 1.1006084311169058e-05, + "loss": 0.4014, + "step": 16556 + }, + { + "epoch": 1.35, + "learning_rate": 1.1005541069100391e-05, + "loss": 0.1812, + "step": 16557 + }, + { + "epoch": 1.35, + "learning_rate": 1.1004997827031727e-05, + "loss": 0.5428, + "step": 16558 + }, + { + "epoch": 1.35, + "learning_rate": 1.100445458496306e-05, + "loss": 0.418, + "step": 16559 + }, + { + "epoch": 1.35, + "learning_rate": 1.1003911342894395e-05, + "loss": 0.7427, + "step": 16560 + }, + { + "epoch": 1.35, + "learning_rate": 1.100336810082573e-05, + "loss": 0.3704, + "step": 16561 + }, + { + "epoch": 1.35, + "learning_rate": 1.1002824858757064e-05, + "loss": 0.5485, + "step": 16562 + }, + { + "epoch": 1.35, + "learning_rate": 1.1002281616688398e-05, + "loss": 0.2795, + "step": 16563 + }, + { + "epoch": 1.35, + "learning_rate": 1.100173837461973e-05, + "loss": 0.3696, + "step": 16564 + }, + { + "epoch": 1.35, + "learning_rate": 1.1001195132551066e-05, + "loss": 0.2683, + "step": 16565 + }, + { + "epoch": 1.35, + "learning_rate": 1.1000651890482399e-05, + "loss": 0.451, + "step": 16566 + }, + { + "epoch": 1.35, + "learning_rate": 1.1000108648413735e-05, + "loss": 0.3033, + "step": 16567 + }, + { + "epoch": 1.35, + "learning_rate": 1.0999565406345067e-05, + "loss": 0.5951, + "step": 16568 + }, + { + "epoch": 1.35, + "learning_rate": 1.0999022164276403e-05, + "loss": 0.4488, + "step": 16569 + }, + { + "epoch": 1.35, + "learning_rate": 1.0998478922207736e-05, + "loss": 0.4673, + "step": 16570 + }, + { + "epoch": 1.35, + "learning_rate": 1.0997935680139072e-05, + "loss": 0.1586, + "step": 16571 + }, + { + "epoch": 1.35, + "learning_rate": 1.0997392438070404e-05, + "loss": 0.3373, + "step": 16572 + }, + { + "epoch": 1.35, + "learning_rate": 1.099684919600174e-05, + "loss": 0.5519, + "step": 16573 + }, + { + "epoch": 1.35, + "learning_rate": 1.0996305953933073e-05, + "loss": 0.3775, + "step": 16574 + }, + { + "epoch": 1.35, + "learning_rate": 1.0995762711864409e-05, + "loss": 0.2473, + "step": 16575 + }, + { + "epoch": 1.35, + "learning_rate": 1.0995219469795741e-05, + "loss": 0.2471, + "step": 16576 + }, + { + "epoch": 1.35, + "learning_rate": 1.0994676227727077e-05, + "loss": 0.4157, + "step": 16577 + }, + { + "epoch": 1.35, + "learning_rate": 1.099413298565841e-05, + "loss": 0.3598, + "step": 16578 + }, + { + "epoch": 1.35, + "learning_rate": 1.0993589743589746e-05, + "loss": 0.3454, + "step": 16579 + }, + { + "epoch": 1.35, + "learning_rate": 1.0993046501521078e-05, + "loss": 0.1601, + "step": 16580 + }, + { + "epoch": 1.35, + "learning_rate": 1.0992503259452414e-05, + "loss": 0.4191, + "step": 16581 + }, + { + "epoch": 1.35, + "learning_rate": 1.0991960017383747e-05, + "loss": 0.4197, + "step": 16582 + }, + { + "epoch": 1.35, + "learning_rate": 1.0991416775315081e-05, + "loss": 0.3963, + "step": 16583 + }, + { + "epoch": 1.35, + "learning_rate": 1.0990873533246415e-05, + "loss": 0.4617, + "step": 16584 + }, + { + "epoch": 1.35, + "learning_rate": 1.099033029117775e-05, + "loss": 0.4334, + "step": 16585 + }, + { + "epoch": 1.35, + "learning_rate": 1.0989787049109084e-05, + "loss": 0.1845, + "step": 16586 + }, + { + "epoch": 1.35, + "learning_rate": 1.0989243807040418e-05, + "loss": 0.2953, + "step": 16587 + }, + { + "epoch": 1.35, + "learning_rate": 1.0988700564971752e-05, + "loss": 0.4039, + "step": 16588 + }, + { + "epoch": 1.35, + "learning_rate": 1.0988157322903086e-05, + "loss": 0.4663, + "step": 16589 + }, + { + "epoch": 1.35, + "learning_rate": 1.098761408083442e-05, + "loss": 0.5349, + "step": 16590 + }, + { + "epoch": 1.35, + "learning_rate": 1.0987070838765755e-05, + "loss": 0.3448, + "step": 16591 + }, + { + "epoch": 1.35, + "learning_rate": 1.0986527596697089e-05, + "loss": 0.3388, + "step": 16592 + }, + { + "epoch": 1.35, + "learning_rate": 1.0985984354628423e-05, + "loss": 0.3241, + "step": 16593 + }, + { + "epoch": 1.35, + "learning_rate": 1.0985441112559757e-05, + "loss": 0.1868, + "step": 16594 + }, + { + "epoch": 1.35, + "learning_rate": 1.0984897870491092e-05, + "loss": 0.3818, + "step": 16595 + }, + { + "epoch": 1.35, + "learning_rate": 1.0984354628422426e-05, + "loss": 0.2342, + "step": 16596 + }, + { + "epoch": 1.35, + "learning_rate": 1.098381138635376e-05, + "loss": 0.4307, + "step": 16597 + }, + { + "epoch": 1.35, + "learning_rate": 1.0983268144285096e-05, + "loss": 0.3611, + "step": 16598 + }, + { + "epoch": 1.35, + "learning_rate": 1.0982724902216429e-05, + "loss": 0.5459, + "step": 16599 + }, + { + "epoch": 1.35, + "learning_rate": 1.0982181660147765e-05, + "loss": 0.2408, + "step": 16600 + }, + { + "epoch": 1.35, + "learning_rate": 1.0981638418079097e-05, + "loss": 0.1475, + "step": 16601 + }, + { + "epoch": 1.35, + "learning_rate": 1.098109517601043e-05, + "loss": 0.2775, + "step": 16602 + }, + { + "epoch": 1.35, + "learning_rate": 1.0980551933941766e-05, + "loss": 0.5732, + "step": 16603 + }, + { + "epoch": 1.35, + "learning_rate": 1.0980008691873098e-05, + "loss": 0.2344, + "step": 16604 + }, + { + "epoch": 1.35, + "learning_rate": 1.0979465449804434e-05, + "loss": 0.6572, + "step": 16605 + }, + { + "epoch": 1.35, + "learning_rate": 1.0978922207735767e-05, + "loss": 0.4952, + "step": 16606 + }, + { + "epoch": 1.35, + "learning_rate": 1.0978378965667102e-05, + "loss": 0.2191, + "step": 16607 + }, + { + "epoch": 1.35, + "learning_rate": 1.0977835723598435e-05, + "loss": 0.4424, + "step": 16608 + }, + { + "epoch": 1.35, + "learning_rate": 1.0977292481529771e-05, + "loss": 0.3566, + "step": 16609 + }, + { + "epoch": 1.35, + "learning_rate": 1.0976749239461103e-05, + "loss": 0.264, + "step": 16610 + }, + { + "epoch": 1.35, + "learning_rate": 1.097620599739244e-05, + "loss": 0.296, + "step": 16611 + }, + { + "epoch": 1.35, + "learning_rate": 1.0975662755323772e-05, + "loss": 0.2016, + "step": 16612 + }, + { + "epoch": 1.35, + "learning_rate": 1.0975119513255108e-05, + "loss": 0.1434, + "step": 16613 + }, + { + "epoch": 1.35, + "learning_rate": 1.0974576271186442e-05, + "loss": 0.1614, + "step": 16614 + }, + { + "epoch": 1.35, + "learning_rate": 1.0974033029117776e-05, + "loss": 0.3877, + "step": 16615 + }, + { + "epoch": 1.35, + "learning_rate": 1.097348978704911e-05, + "loss": 0.3855, + "step": 16616 + }, + { + "epoch": 1.35, + "learning_rate": 1.0972946544980445e-05, + "loss": 0.206, + "step": 16617 + }, + { + "epoch": 1.35, + "learning_rate": 1.0972403302911779e-05, + "loss": 0.3656, + "step": 16618 + }, + { + "epoch": 1.35, + "learning_rate": 1.0971860060843113e-05, + "loss": 0.4778, + "step": 16619 + }, + { + "epoch": 1.35, + "learning_rate": 1.0971316818774447e-05, + "loss": 0.2925, + "step": 16620 + }, + { + "epoch": 1.35, + "learning_rate": 1.097077357670578e-05, + "loss": 0.3032, + "step": 16621 + }, + { + "epoch": 1.35, + "learning_rate": 1.0970230334637116e-05, + "loss": 0.6704, + "step": 16622 + }, + { + "epoch": 1.35, + "learning_rate": 1.0969687092568448e-05, + "loss": 0.3909, + "step": 16623 + }, + { + "epoch": 1.35, + "learning_rate": 1.0969143850499784e-05, + "loss": 0.5217, + "step": 16624 + }, + { + "epoch": 1.35, + "learning_rate": 1.0968600608431117e-05, + "loss": 0.2816, + "step": 16625 + }, + { + "epoch": 1.35, + "learning_rate": 1.0968057366362453e-05, + "loss": 0.5953, + "step": 16626 + }, + { + "epoch": 1.35, + "learning_rate": 1.0967514124293785e-05, + "loss": 0.2332, + "step": 16627 + }, + { + "epoch": 1.35, + "learning_rate": 1.0966970882225121e-05, + "loss": 0.3141, + "step": 16628 + }, + { + "epoch": 1.36, + "learning_rate": 1.0966427640156454e-05, + "loss": 0.2668, + "step": 16629 + }, + { + "epoch": 1.36, + "learning_rate": 1.096588439808779e-05, + "loss": 0.1639, + "step": 16630 + }, + { + "epoch": 1.36, + "learning_rate": 1.0965341156019122e-05, + "loss": 0.5644, + "step": 16631 + }, + { + "epoch": 1.36, + "learning_rate": 1.0964797913950458e-05, + "loss": 0.441, + "step": 16632 + }, + { + "epoch": 1.36, + "learning_rate": 1.096425467188179e-05, + "loss": 0.5653, + "step": 16633 + }, + { + "epoch": 1.36, + "learning_rate": 1.0963711429813127e-05, + "loss": 0.2242, + "step": 16634 + }, + { + "epoch": 1.36, + "learning_rate": 1.096316818774446e-05, + "loss": 0.4375, + "step": 16635 + }, + { + "epoch": 1.36, + "learning_rate": 1.0962624945675795e-05, + "loss": 0.5466, + "step": 16636 + }, + { + "epoch": 1.36, + "learning_rate": 1.0962081703607128e-05, + "loss": 0.3331, + "step": 16637 + }, + { + "epoch": 1.36, + "learning_rate": 1.0961538461538464e-05, + "loss": 0.4414, + "step": 16638 + }, + { + "epoch": 1.36, + "learning_rate": 1.0960995219469796e-05, + "loss": 0.1116, + "step": 16639 + }, + { + "epoch": 1.36, + "learning_rate": 1.096045197740113e-05, + "loss": 0.201, + "step": 16640 + }, + { + "epoch": 1.36, + "learning_rate": 1.0959908735332465e-05, + "loss": 0.1708, + "step": 16641 + }, + { + "epoch": 1.36, + "learning_rate": 1.0959365493263799e-05, + "loss": 0.3352, + "step": 16642 + }, + { + "epoch": 1.36, + "learning_rate": 1.0958822251195133e-05, + "loss": 0.1825, + "step": 16643 + }, + { + "epoch": 1.36, + "learning_rate": 1.0958279009126467e-05, + "loss": 0.5956, + "step": 16644 + }, + { + "epoch": 1.36, + "learning_rate": 1.0957735767057801e-05, + "loss": 0.2441, + "step": 16645 + }, + { + "epoch": 1.36, + "learning_rate": 1.0957192524989136e-05, + "loss": 0.3571, + "step": 16646 + }, + { + "epoch": 1.36, + "learning_rate": 1.095664928292047e-05, + "loss": 0.2457, + "step": 16647 + }, + { + "epoch": 1.36, + "learning_rate": 1.0956106040851804e-05, + "loss": 0.2277, + "step": 16648 + }, + { + "epoch": 1.36, + "learning_rate": 1.0955562798783138e-05, + "loss": 0.2014, + "step": 16649 + }, + { + "epoch": 1.36, + "learning_rate": 1.0955019556714473e-05, + "loss": 0.6649, + "step": 16650 + }, + { + "epoch": 1.36, + "learning_rate": 1.0954476314645809e-05, + "loss": 0.2347, + "step": 16651 + }, + { + "epoch": 1.36, + "learning_rate": 1.0953933072577141e-05, + "loss": 0.3672, + "step": 16652 + }, + { + "epoch": 1.36, + "learning_rate": 1.0953389830508477e-05, + "loss": 0.4354, + "step": 16653 + }, + { + "epoch": 1.36, + "learning_rate": 1.095284658843981e-05, + "loss": 0.1644, + "step": 16654 + }, + { + "epoch": 1.36, + "learning_rate": 1.0952303346371145e-05, + "loss": 0.4501, + "step": 16655 + }, + { + "epoch": 1.36, + "learning_rate": 1.0951760104302478e-05, + "loss": 0.2625, + "step": 16656 + }, + { + "epoch": 1.36, + "learning_rate": 1.0951216862233814e-05, + "loss": 0.102, + "step": 16657 + }, + { + "epoch": 1.36, + "learning_rate": 1.0950673620165146e-05, + "loss": 0.2414, + "step": 16658 + }, + { + "epoch": 1.36, + "learning_rate": 1.0950130378096479e-05, + "loss": 0.3707, + "step": 16659 + }, + { + "epoch": 1.36, + "learning_rate": 1.0949587136027815e-05, + "loss": 0.2873, + "step": 16660 + }, + { + "epoch": 1.36, + "learning_rate": 1.0949043893959147e-05, + "loss": 0.4481, + "step": 16661 + }, + { + "epoch": 1.36, + "learning_rate": 1.0948500651890483e-05, + "loss": 0.3575, + "step": 16662 + }, + { + "epoch": 1.36, + "learning_rate": 1.0947957409821816e-05, + "loss": 0.2293, + "step": 16663 + }, + { + "epoch": 1.36, + "learning_rate": 1.0947414167753152e-05, + "loss": 0.2761, + "step": 16664 + }, + { + "epoch": 1.36, + "learning_rate": 1.0946870925684484e-05, + "loss": 0.4093, + "step": 16665 + }, + { + "epoch": 1.36, + "learning_rate": 1.094632768361582e-05, + "loss": 0.2768, + "step": 16666 + }, + { + "epoch": 1.36, + "learning_rate": 1.0945784441547153e-05, + "loss": 0.2101, + "step": 16667 + }, + { + "epoch": 1.36, + "learning_rate": 1.0945241199478489e-05, + "loss": 0.2352, + "step": 16668 + }, + { + "epoch": 1.36, + "learning_rate": 1.0944697957409823e-05, + "loss": 0.4107, + "step": 16669 + }, + { + "epoch": 1.36, + "learning_rate": 1.0944154715341157e-05, + "loss": 0.3673, + "step": 16670 + }, + { + "epoch": 1.36, + "learning_rate": 1.0943611473272491e-05, + "loss": 0.2818, + "step": 16671 + }, + { + "epoch": 1.36, + "learning_rate": 1.0943068231203826e-05, + "loss": 0.2814, + "step": 16672 + }, + { + "epoch": 1.36, + "learning_rate": 1.094252498913516e-05, + "loss": 0.4198, + "step": 16673 + }, + { + "epoch": 1.36, + "learning_rate": 1.0941981747066494e-05, + "loss": 0.359, + "step": 16674 + }, + { + "epoch": 1.36, + "learning_rate": 1.0941438504997828e-05, + "loss": 0.3754, + "step": 16675 + }, + { + "epoch": 1.36, + "learning_rate": 1.0940895262929163e-05, + "loss": 0.1766, + "step": 16676 + }, + { + "epoch": 1.36, + "learning_rate": 1.0940352020860497e-05, + "loss": 0.2769, + "step": 16677 + }, + { + "epoch": 1.36, + "learning_rate": 1.093980877879183e-05, + "loss": 0.3552, + "step": 16678 + }, + { + "epoch": 1.36, + "learning_rate": 1.0939265536723165e-05, + "loss": 0.6358, + "step": 16679 + }, + { + "epoch": 1.36, + "learning_rate": 1.0938722294654498e-05, + "loss": 0.6767, + "step": 16680 + }, + { + "epoch": 1.36, + "learning_rate": 1.0938179052585834e-05, + "loss": 0.1946, + "step": 16681 + }, + { + "epoch": 1.36, + "learning_rate": 1.0937635810517166e-05, + "loss": 0.2289, + "step": 16682 + }, + { + "epoch": 1.36, + "learning_rate": 1.0937092568448502e-05, + "loss": 0.4686, + "step": 16683 + }, + { + "epoch": 1.36, + "learning_rate": 1.0936549326379835e-05, + "loss": 0.1572, + "step": 16684 + }, + { + "epoch": 1.36, + "learning_rate": 1.093600608431117e-05, + "loss": 0.3388, + "step": 16685 + }, + { + "epoch": 1.36, + "learning_rate": 1.0935462842242503e-05, + "loss": 0.3547, + "step": 16686 + }, + { + "epoch": 1.36, + "learning_rate": 1.093491960017384e-05, + "loss": 0.3224, + "step": 16687 + }, + { + "epoch": 1.36, + "learning_rate": 1.0934376358105172e-05, + "loss": 0.6376, + "step": 16688 + }, + { + "epoch": 1.36, + "learning_rate": 1.0933833116036508e-05, + "loss": 0.4125, + "step": 16689 + }, + { + "epoch": 1.36, + "learning_rate": 1.093328987396784e-05, + "loss": 0.5732, + "step": 16690 + }, + { + "epoch": 1.36, + "learning_rate": 1.0932746631899176e-05, + "loss": 0.6336, + "step": 16691 + }, + { + "epoch": 1.36, + "learning_rate": 1.0932203389830509e-05, + "loss": 0.5368, + "step": 16692 + }, + { + "epoch": 1.36, + "learning_rate": 1.0931660147761845e-05, + "loss": 0.2549, + "step": 16693 + }, + { + "epoch": 1.36, + "learning_rate": 1.0931116905693177e-05, + "loss": 0.3001, + "step": 16694 + }, + { + "epoch": 1.36, + "learning_rate": 1.0930573663624513e-05, + "loss": 0.3685, + "step": 16695 + }, + { + "epoch": 1.36, + "learning_rate": 1.0930030421555846e-05, + "loss": 0.4159, + "step": 16696 + }, + { + "epoch": 1.36, + "learning_rate": 1.092948717948718e-05, + "loss": 0.2692, + "step": 16697 + }, + { + "epoch": 1.36, + "learning_rate": 1.0928943937418514e-05, + "loss": 0.2649, + "step": 16698 + }, + { + "epoch": 1.36, + "learning_rate": 1.0928400695349848e-05, + "loss": 0.4557, + "step": 16699 + }, + { + "epoch": 1.36, + "learning_rate": 1.0927857453281182e-05, + "loss": 0.4286, + "step": 16700 + }, + { + "epoch": 1.36, + "learning_rate": 1.0927314211212517e-05, + "loss": 0.3716, + "step": 16701 + }, + { + "epoch": 1.36, + "learning_rate": 1.0926770969143851e-05, + "loss": 0.2713, + "step": 16702 + }, + { + "epoch": 1.36, + "learning_rate": 1.0926227727075185e-05, + "loss": 0.5069, + "step": 16703 + }, + { + "epoch": 1.36, + "learning_rate": 1.092568448500652e-05, + "loss": 0.3778, + "step": 16704 + }, + { + "epoch": 1.36, + "learning_rate": 1.0925141242937854e-05, + "loss": 0.2703, + "step": 16705 + }, + { + "epoch": 1.36, + "learning_rate": 1.092459800086919e-05, + "loss": 0.4353, + "step": 16706 + }, + { + "epoch": 1.36, + "learning_rate": 1.0924054758800522e-05, + "loss": 0.2708, + "step": 16707 + }, + { + "epoch": 1.36, + "learning_rate": 1.0923511516731858e-05, + "loss": 0.2646, + "step": 16708 + }, + { + "epoch": 1.36, + "learning_rate": 1.092296827466319e-05, + "loss": 0.2339, + "step": 16709 + }, + { + "epoch": 1.36, + "learning_rate": 1.0922425032594526e-05, + "loss": 0.2786, + "step": 16710 + }, + { + "epoch": 1.36, + "learning_rate": 1.0921881790525859e-05, + "loss": 0.239, + "step": 16711 + }, + { + "epoch": 1.36, + "learning_rate": 1.0921338548457195e-05, + "loss": 0.1872, + "step": 16712 + }, + { + "epoch": 1.36, + "learning_rate": 1.0920795306388527e-05, + "loss": 0.1565, + "step": 16713 + }, + { + "epoch": 1.36, + "learning_rate": 1.0920252064319863e-05, + "loss": 0.3053, + "step": 16714 + }, + { + "epoch": 1.36, + "learning_rate": 1.0919708822251196e-05, + "loss": 0.2848, + "step": 16715 + }, + { + "epoch": 1.36, + "learning_rate": 1.0919165580182528e-05, + "loss": 0.4098, + "step": 16716 + }, + { + "epoch": 1.36, + "learning_rate": 1.0918622338113864e-05, + "loss": 0.5092, + "step": 16717 + }, + { + "epoch": 1.36, + "learning_rate": 1.0918079096045197e-05, + "loss": 0.2531, + "step": 16718 + }, + { + "epoch": 1.36, + "learning_rate": 1.0917535853976533e-05, + "loss": 0.532, + "step": 16719 + }, + { + "epoch": 1.36, + "learning_rate": 1.0916992611907865e-05, + "loss": 0.201, + "step": 16720 + }, + { + "epoch": 1.36, + "learning_rate": 1.0916449369839201e-05, + "loss": 0.4696, + "step": 16721 + }, + { + "epoch": 1.36, + "learning_rate": 1.0915906127770536e-05, + "loss": 0.0854, + "step": 16722 + }, + { + "epoch": 1.36, + "learning_rate": 1.091536288570187e-05, + "loss": 0.3264, + "step": 16723 + }, + { + "epoch": 1.36, + "learning_rate": 1.0914819643633204e-05, + "loss": 0.2964, + "step": 16724 + }, + { + "epoch": 1.36, + "learning_rate": 1.0914276401564538e-05, + "loss": 0.4403, + "step": 16725 + }, + { + "epoch": 1.36, + "learning_rate": 1.0913733159495872e-05, + "loss": 0.4519, + "step": 16726 + }, + { + "epoch": 1.36, + "learning_rate": 1.0913189917427207e-05, + "loss": 0.2369, + "step": 16727 + }, + { + "epoch": 1.36, + "learning_rate": 1.0912646675358541e-05, + "loss": 0.2066, + "step": 16728 + }, + { + "epoch": 1.36, + "learning_rate": 1.0912103433289875e-05, + "loss": 0.313, + "step": 16729 + }, + { + "epoch": 1.36, + "learning_rate": 1.091156019122121e-05, + "loss": 0.17, + "step": 16730 + }, + { + "epoch": 1.36, + "learning_rate": 1.0911016949152544e-05, + "loss": 0.6309, + "step": 16731 + }, + { + "epoch": 1.36, + "learning_rate": 1.0910473707083878e-05, + "loss": 0.2463, + "step": 16732 + }, + { + "epoch": 1.36, + "learning_rate": 1.0909930465015212e-05, + "loss": 0.4819, + "step": 16733 + }, + { + "epoch": 1.36, + "learning_rate": 1.0909387222946546e-05, + "loss": 0.3332, + "step": 16734 + }, + { + "epoch": 1.36, + "learning_rate": 1.0908843980877879e-05, + "loss": 0.3177, + "step": 16735 + }, + { + "epoch": 1.36, + "learning_rate": 1.0908300738809215e-05, + "loss": 0.572, + "step": 16736 + }, + { + "epoch": 1.36, + "learning_rate": 1.0907757496740547e-05, + "loss": 0.1675, + "step": 16737 + }, + { + "epoch": 1.36, + "learning_rate": 1.0907214254671883e-05, + "loss": 0.452, + "step": 16738 + }, + { + "epoch": 1.36, + "learning_rate": 1.0906671012603216e-05, + "loss": 0.3409, + "step": 16739 + }, + { + "epoch": 1.36, + "learning_rate": 1.0906127770534552e-05, + "loss": 0.2928, + "step": 16740 + }, + { + "epoch": 1.36, + "learning_rate": 1.0905584528465884e-05, + "loss": 0.1614, + "step": 16741 + }, + { + "epoch": 1.36, + "learning_rate": 1.090504128639722e-05, + "loss": 0.2975, + "step": 16742 + }, + { + "epoch": 1.36, + "learning_rate": 1.0904498044328553e-05, + "loss": 0.4117, + "step": 16743 + }, + { + "epoch": 1.36, + "learning_rate": 1.0903954802259889e-05, + "loss": 0.1831, + "step": 16744 + }, + { + "epoch": 1.36, + "learning_rate": 1.0903411560191221e-05, + "loss": 0.3152, + "step": 16745 + }, + { + "epoch": 1.36, + "learning_rate": 1.0902868318122557e-05, + "loss": 0.2663, + "step": 16746 + }, + { + "epoch": 1.36, + "learning_rate": 1.090232507605389e-05, + "loss": 0.343, + "step": 16747 + }, + { + "epoch": 1.36, + "learning_rate": 1.0901781833985226e-05, + "loss": 0.2809, + "step": 16748 + }, + { + "epoch": 1.36, + "learning_rate": 1.0901238591916558e-05, + "loss": 0.3854, + "step": 16749 + }, + { + "epoch": 1.36, + "learning_rate": 1.0900695349847894e-05, + "loss": 0.2495, + "step": 16750 + }, + { + "epoch": 1.36, + "eval_accuracy": 0.839429444727458, + "eval_loss": 0.43423178791999817, + "eval_runtime": 22.3172, + "eval_samples_per_second": 439.796, + "eval_steps_per_second": 3.45, + "step": 16750 + }, + { + "epoch": 1.36, + "learning_rate": 1.0900152107779227e-05, + "loss": 0.498, + "step": 16751 + }, + { + "epoch": 1.37, + "learning_rate": 1.0899608865710562e-05, + "loss": 0.3409, + "step": 16752 + }, + { + "epoch": 1.37, + "learning_rate": 1.0899065623641895e-05, + "loss": 0.2105, + "step": 16753 + }, + { + "epoch": 1.37, + "learning_rate": 1.089852238157323e-05, + "loss": 0.2233, + "step": 16754 + }, + { + "epoch": 1.37, + "learning_rate": 1.0897979139504563e-05, + "loss": 0.7852, + "step": 16755 + }, + { + "epoch": 1.37, + "learning_rate": 1.0897435897435898e-05, + "loss": 0.5709, + "step": 16756 + }, + { + "epoch": 1.37, + "learning_rate": 1.0896892655367232e-05, + "loss": 0.3442, + "step": 16757 + }, + { + "epoch": 1.37, + "learning_rate": 1.0896349413298566e-05, + "loss": 0.5029, + "step": 16758 + }, + { + "epoch": 1.37, + "learning_rate": 1.0895806171229902e-05, + "loss": 0.2861, + "step": 16759 + }, + { + "epoch": 1.37, + "learning_rate": 1.0895262929161235e-05, + "loss": 0.1986, + "step": 16760 + }, + { + "epoch": 1.37, + "learning_rate": 1.089471968709257e-05, + "loss": 0.4254, + "step": 16761 + }, + { + "epoch": 1.37, + "learning_rate": 1.0894176445023903e-05, + "loss": 0.3769, + "step": 16762 + }, + { + "epoch": 1.37, + "learning_rate": 1.0893633202955239e-05, + "loss": 0.1532, + "step": 16763 + }, + { + "epoch": 1.37, + "learning_rate": 1.0893089960886572e-05, + "loss": 0.3866, + "step": 16764 + }, + { + "epoch": 1.37, + "learning_rate": 1.0892546718817907e-05, + "loss": 0.4147, + "step": 16765 + }, + { + "epoch": 1.37, + "learning_rate": 1.089200347674924e-05, + "loss": 0.1438, + "step": 16766 + }, + { + "epoch": 1.37, + "learning_rate": 1.0891460234680576e-05, + "loss": 0.1173, + "step": 16767 + }, + { + "epoch": 1.37, + "learning_rate": 1.0890916992611908e-05, + "loss": 0.2281, + "step": 16768 + }, + { + "epoch": 1.37, + "learning_rate": 1.0890373750543244e-05, + "loss": 0.2533, + "step": 16769 + }, + { + "epoch": 1.37, + "learning_rate": 1.0889830508474577e-05, + "loss": 0.26, + "step": 16770 + }, + { + "epoch": 1.37, + "learning_rate": 1.0889287266405913e-05, + "loss": 0.1981, + "step": 16771 + }, + { + "epoch": 1.37, + "learning_rate": 1.0888744024337245e-05, + "loss": 0.3098, + "step": 16772 + }, + { + "epoch": 1.37, + "learning_rate": 1.0888200782268578e-05, + "loss": 0.3621, + "step": 16773 + }, + { + "epoch": 1.37, + "learning_rate": 1.0887657540199914e-05, + "loss": 0.514, + "step": 16774 + }, + { + "epoch": 1.37, + "learning_rate": 1.0887114298131246e-05, + "loss": 0.3981, + "step": 16775 + }, + { + "epoch": 1.37, + "learning_rate": 1.0886571056062582e-05, + "loss": 0.4039, + "step": 16776 + }, + { + "epoch": 1.37, + "learning_rate": 1.0886027813993917e-05, + "loss": 0.2127, + "step": 16777 + }, + { + "epoch": 1.37, + "learning_rate": 1.088548457192525e-05, + "loss": 0.5551, + "step": 16778 + }, + { + "epoch": 1.37, + "learning_rate": 1.0884941329856585e-05, + "loss": 0.2085, + "step": 16779 + }, + { + "epoch": 1.37, + "learning_rate": 1.088439808778792e-05, + "loss": 0.434, + "step": 16780 + }, + { + "epoch": 1.37, + "learning_rate": 1.0883854845719253e-05, + "loss": 0.4971, + "step": 16781 + }, + { + "epoch": 1.37, + "learning_rate": 1.0883311603650588e-05, + "loss": 0.1675, + "step": 16782 + }, + { + "epoch": 1.37, + "learning_rate": 1.0882768361581922e-05, + "loss": 0.1507, + "step": 16783 + }, + { + "epoch": 1.37, + "learning_rate": 1.0882225119513256e-05, + "loss": 0.468, + "step": 16784 + }, + { + "epoch": 1.37, + "learning_rate": 1.088168187744459e-05, + "loss": 0.167, + "step": 16785 + }, + { + "epoch": 1.37, + "learning_rate": 1.0881138635375925e-05, + "loss": 0.2864, + "step": 16786 + }, + { + "epoch": 1.37, + "learning_rate": 1.0880595393307259e-05, + "loss": 0.6301, + "step": 16787 + }, + { + "epoch": 1.37, + "learning_rate": 1.0880052151238593e-05, + "loss": 0.3484, + "step": 16788 + }, + { + "epoch": 1.37, + "learning_rate": 1.0879508909169927e-05, + "loss": 0.2343, + "step": 16789 + }, + { + "epoch": 1.37, + "learning_rate": 1.0878965667101262e-05, + "loss": 0.3043, + "step": 16790 + }, + { + "epoch": 1.37, + "learning_rate": 1.0878422425032596e-05, + "loss": 0.3441, + "step": 16791 + }, + { + "epoch": 1.37, + "learning_rate": 1.0877879182963928e-05, + "loss": 0.557, + "step": 16792 + }, + { + "epoch": 1.37, + "learning_rate": 1.0877335940895264e-05, + "loss": 0.2704, + "step": 16793 + }, + { + "epoch": 1.37, + "learning_rate": 1.0876792698826597e-05, + "loss": 0.3237, + "step": 16794 + }, + { + "epoch": 1.37, + "learning_rate": 1.0876249456757933e-05, + "loss": 0.2139, + "step": 16795 + }, + { + "epoch": 1.37, + "learning_rate": 1.0875706214689265e-05, + "loss": 0.3608, + "step": 16796 + }, + { + "epoch": 1.37, + "learning_rate": 1.0875162972620601e-05, + "loss": 0.2397, + "step": 16797 + }, + { + "epoch": 1.37, + "learning_rate": 1.0874619730551934e-05, + "loss": 0.2108, + "step": 16798 + }, + { + "epoch": 1.37, + "learning_rate": 1.087407648848327e-05, + "loss": 0.306, + "step": 16799 + }, + { + "epoch": 1.37, + "learning_rate": 1.0873533246414602e-05, + "loss": 0.2005, + "step": 16800 + }, + { + "epoch": 1.37, + "learning_rate": 1.0872990004345938e-05, + "loss": 0.1961, + "step": 16801 + }, + { + "epoch": 1.37, + "learning_rate": 1.087244676227727e-05, + "loss": 0.2635, + "step": 16802 + }, + { + "epoch": 1.37, + "learning_rate": 1.0871903520208607e-05, + "loss": 0.2327, + "step": 16803 + }, + { + "epoch": 1.37, + "learning_rate": 1.0871360278139939e-05, + "loss": 0.2225, + "step": 16804 + }, + { + "epoch": 1.37, + "learning_rate": 1.0870817036071275e-05, + "loss": 0.3851, + "step": 16805 + }, + { + "epoch": 1.37, + "learning_rate": 1.0870273794002608e-05, + "loss": 0.469, + "step": 16806 + }, + { + "epoch": 1.37, + "learning_rate": 1.0869730551933943e-05, + "loss": 0.3111, + "step": 16807 + }, + { + "epoch": 1.37, + "learning_rate": 1.0869187309865276e-05, + "loss": 0.2557, + "step": 16808 + }, + { + "epoch": 1.37, + "learning_rate": 1.0868644067796612e-05, + "loss": 0.2286, + "step": 16809 + }, + { + "epoch": 1.37, + "learning_rate": 1.0868100825727944e-05, + "loss": 0.3229, + "step": 16810 + }, + { + "epoch": 1.37, + "learning_rate": 1.0867557583659279e-05, + "loss": 0.537, + "step": 16811 + }, + { + "epoch": 1.37, + "learning_rate": 1.0867014341590613e-05, + "loss": 0.3166, + "step": 16812 + }, + { + "epoch": 1.37, + "learning_rate": 1.0866471099521947e-05, + "loss": 0.5327, + "step": 16813 + }, + { + "epoch": 1.37, + "learning_rate": 1.0865927857453283e-05, + "loss": 0.3325, + "step": 16814 + }, + { + "epoch": 1.37, + "learning_rate": 1.0865384615384616e-05, + "loss": 0.4425, + "step": 16815 + }, + { + "epoch": 1.37, + "learning_rate": 1.0864841373315952e-05, + "loss": 0.2855, + "step": 16816 + }, + { + "epoch": 1.37, + "learning_rate": 1.0864298131247284e-05, + "loss": 0.2882, + "step": 16817 + }, + { + "epoch": 1.37, + "learning_rate": 1.086375488917862e-05, + "loss": 0.2743, + "step": 16818 + }, + { + "epoch": 1.37, + "learning_rate": 1.0863211647109953e-05, + "loss": 0.3307, + "step": 16819 + }, + { + "epoch": 1.37, + "learning_rate": 1.0862668405041288e-05, + "loss": 0.2799, + "step": 16820 + }, + { + "epoch": 1.37, + "learning_rate": 1.0862125162972621e-05, + "loss": 0.4507, + "step": 16821 + }, + { + "epoch": 1.37, + "learning_rate": 1.0861581920903957e-05, + "loss": 0.3566, + "step": 16822 + }, + { + "epoch": 1.37, + "learning_rate": 1.086103867883529e-05, + "loss": 0.2666, + "step": 16823 + }, + { + "epoch": 1.37, + "learning_rate": 1.0860495436766625e-05, + "loss": 0.2184, + "step": 16824 + }, + { + "epoch": 1.37, + "learning_rate": 1.0859952194697958e-05, + "loss": 0.2177, + "step": 16825 + }, + { + "epoch": 1.37, + "learning_rate": 1.0859408952629294e-05, + "loss": 0.7742, + "step": 16826 + }, + { + "epoch": 1.37, + "learning_rate": 1.0858865710560626e-05, + "loss": 0.1444, + "step": 16827 + }, + { + "epoch": 1.37, + "learning_rate": 1.0858322468491962e-05, + "loss": 0.3557, + "step": 16828 + }, + { + "epoch": 1.37, + "learning_rate": 1.0857779226423295e-05, + "loss": 0.2169, + "step": 16829 + }, + { + "epoch": 1.37, + "learning_rate": 1.0857235984354629e-05, + "loss": 0.2193, + "step": 16830 + }, + { + "epoch": 1.37, + "learning_rate": 1.0856692742285963e-05, + "loss": 0.2966, + "step": 16831 + }, + { + "epoch": 1.37, + "learning_rate": 1.0856149500217298e-05, + "loss": 0.1721, + "step": 16832 + }, + { + "epoch": 1.37, + "learning_rate": 1.0855606258148632e-05, + "loss": 0.1375, + "step": 16833 + }, + { + "epoch": 1.37, + "learning_rate": 1.0855063016079966e-05, + "loss": 0.4489, + "step": 16834 + }, + { + "epoch": 1.37, + "learning_rate": 1.08545197740113e-05, + "loss": 0.3906, + "step": 16835 + }, + { + "epoch": 1.37, + "learning_rate": 1.0853976531942634e-05, + "loss": 0.5325, + "step": 16836 + }, + { + "epoch": 1.37, + "learning_rate": 1.0853433289873969e-05, + "loss": 0.4512, + "step": 16837 + }, + { + "epoch": 1.37, + "learning_rate": 1.0852890047805303e-05, + "loss": 0.4106, + "step": 16838 + }, + { + "epoch": 1.37, + "learning_rate": 1.0852346805736637e-05, + "loss": 0.5235, + "step": 16839 + }, + { + "epoch": 1.37, + "learning_rate": 1.0851803563667971e-05, + "loss": 0.3083, + "step": 16840 + }, + { + "epoch": 1.37, + "learning_rate": 1.0851260321599306e-05, + "loss": 0.504, + "step": 16841 + }, + { + "epoch": 1.37, + "learning_rate": 1.085071707953064e-05, + "loss": 0.4352, + "step": 16842 + }, + { + "epoch": 1.37, + "learning_rate": 1.0850173837461974e-05, + "loss": 0.4787, + "step": 16843 + }, + { + "epoch": 1.37, + "learning_rate": 1.0849630595393308e-05, + "loss": 0.1787, + "step": 16844 + }, + { + "epoch": 1.37, + "learning_rate": 1.0849087353324643e-05, + "loss": 0.1811, + "step": 16845 + }, + { + "epoch": 1.37, + "learning_rate": 1.0848544111255977e-05, + "loss": 0.2865, + "step": 16846 + }, + { + "epoch": 1.37, + "learning_rate": 1.0848000869187311e-05, + "loss": 0.2788, + "step": 16847 + }, + { + "epoch": 1.37, + "learning_rate": 1.0847457627118645e-05, + "loss": 0.6662, + "step": 16848 + }, + { + "epoch": 1.37, + "learning_rate": 1.0846914385049978e-05, + "loss": 0.4479, + "step": 16849 + }, + { + "epoch": 1.37, + "learning_rate": 1.0846371142981314e-05, + "loss": 0.582, + "step": 16850 + }, + { + "epoch": 1.37, + "learning_rate": 1.0845827900912646e-05, + "loss": 0.1504, + "step": 16851 + }, + { + "epoch": 1.37, + "learning_rate": 1.0845284658843982e-05, + "loss": 0.2911, + "step": 16852 + }, + { + "epoch": 1.37, + "learning_rate": 1.0844741416775315e-05, + "loss": 0.5519, + "step": 16853 + }, + { + "epoch": 1.37, + "learning_rate": 1.084419817470665e-05, + "loss": 0.2398, + "step": 16854 + }, + { + "epoch": 1.37, + "learning_rate": 1.0843654932637983e-05, + "loss": 0.1769, + "step": 16855 + }, + { + "epoch": 1.37, + "learning_rate": 1.0843111690569319e-05, + "loss": 0.5176, + "step": 16856 + }, + { + "epoch": 1.37, + "learning_rate": 1.0842568448500652e-05, + "loss": 0.3722, + "step": 16857 + }, + { + "epoch": 1.37, + "learning_rate": 1.0842025206431988e-05, + "loss": 0.1975, + "step": 16858 + }, + { + "epoch": 1.37, + "learning_rate": 1.084148196436332e-05, + "loss": 0.1633, + "step": 16859 + }, + { + "epoch": 1.37, + "learning_rate": 1.0840938722294656e-05, + "loss": 0.2318, + "step": 16860 + }, + { + "epoch": 1.37, + "learning_rate": 1.0840395480225989e-05, + "loss": 0.2071, + "step": 16861 + }, + { + "epoch": 1.37, + "learning_rate": 1.0839852238157324e-05, + "loss": 0.2814, + "step": 16862 + }, + { + "epoch": 1.37, + "learning_rate": 1.0839308996088657e-05, + "loss": 0.221, + "step": 16863 + }, + { + "epoch": 1.37, + "learning_rate": 1.0838765754019993e-05, + "loss": 0.2985, + "step": 16864 + }, + { + "epoch": 1.37, + "learning_rate": 1.0838222511951325e-05, + "loss": 0.2538, + "step": 16865 + }, + { + "epoch": 1.37, + "learning_rate": 1.0837679269882661e-05, + "loss": 0.3759, + "step": 16866 + }, + { + "epoch": 1.37, + "learning_rate": 1.0837136027813996e-05, + "loss": 0.2656, + "step": 16867 + }, + { + "epoch": 1.37, + "learning_rate": 1.0836592785745328e-05, + "loss": 0.4904, + "step": 16868 + }, + { + "epoch": 1.37, + "learning_rate": 1.0836049543676664e-05, + "loss": 0.5765, + "step": 16869 + }, + { + "epoch": 1.37, + "learning_rate": 1.0835506301607997e-05, + "loss": 0.5233, + "step": 16870 + }, + { + "epoch": 1.37, + "learning_rate": 1.0834963059539333e-05, + "loss": 0.822, + "step": 16871 + }, + { + "epoch": 1.37, + "learning_rate": 1.0834419817470665e-05, + "loss": 0.3491, + "step": 16872 + }, + { + "epoch": 1.37, + "learning_rate": 1.0833876575402001e-05, + "loss": 0.4602, + "step": 16873 + }, + { + "epoch": 1.38, + "learning_rate": 1.0833333333333334e-05, + "loss": 0.402, + "step": 16874 + }, + { + "epoch": 1.38, + "learning_rate": 1.083279009126467e-05, + "loss": 0.2926, + "step": 16875 + }, + { + "epoch": 1.38, + "learning_rate": 1.0832246849196002e-05, + "loss": 0.325, + "step": 16876 + }, + { + "epoch": 1.38, + "learning_rate": 1.0831703607127338e-05, + "loss": 0.4925, + "step": 16877 + }, + { + "epoch": 1.38, + "learning_rate": 1.083116036505867e-05, + "loss": 0.1553, + "step": 16878 + }, + { + "epoch": 1.38, + "learning_rate": 1.0830617122990006e-05, + "loss": 0.2447, + "step": 16879 + }, + { + "epoch": 1.38, + "learning_rate": 1.0830073880921339e-05, + "loss": 0.2532, + "step": 16880 + }, + { + "epoch": 1.38, + "learning_rate": 1.0829530638852675e-05, + "loss": 0.3334, + "step": 16881 + }, + { + "epoch": 1.38, + "learning_rate": 1.0828987396784007e-05, + "loss": 0.3365, + "step": 16882 + }, + { + "epoch": 1.38, + "learning_rate": 1.0828444154715343e-05, + "loss": 0.3037, + "step": 16883 + }, + { + "epoch": 1.38, + "learning_rate": 1.0827900912646676e-05, + "loss": 0.3235, + "step": 16884 + }, + { + "epoch": 1.38, + "learning_rate": 1.0827357670578012e-05, + "loss": 0.1908, + "step": 16885 + }, + { + "epoch": 1.38, + "learning_rate": 1.0826814428509344e-05, + "loss": 0.1888, + "step": 16886 + }, + { + "epoch": 1.38, + "learning_rate": 1.0826271186440679e-05, + "loss": 0.2648, + "step": 16887 + }, + { + "epoch": 1.38, + "learning_rate": 1.0825727944372013e-05, + "loss": 0.3871, + "step": 16888 + }, + { + "epoch": 1.38, + "learning_rate": 1.0825184702303347e-05, + "loss": 0.3145, + "step": 16889 + }, + { + "epoch": 1.38, + "learning_rate": 1.0824641460234681e-05, + "loss": 0.4731, + "step": 16890 + }, + { + "epoch": 1.38, + "learning_rate": 1.0824098218166015e-05, + "loss": 0.4309, + "step": 16891 + }, + { + "epoch": 1.38, + "learning_rate": 1.082355497609735e-05, + "loss": 0.3518, + "step": 16892 + }, + { + "epoch": 1.38, + "learning_rate": 1.0823011734028684e-05, + "loss": 0.4941, + "step": 16893 + }, + { + "epoch": 1.38, + "learning_rate": 1.0822468491960018e-05, + "loss": 0.3894, + "step": 16894 + }, + { + "epoch": 1.38, + "learning_rate": 1.0821925249891352e-05, + "loss": 0.3908, + "step": 16895 + }, + { + "epoch": 1.38, + "learning_rate": 1.0821382007822687e-05, + "loss": 0.2186, + "step": 16896 + }, + { + "epoch": 1.38, + "learning_rate": 1.082083876575402e-05, + "loss": 0.4701, + "step": 16897 + }, + { + "epoch": 1.38, + "learning_rate": 1.0820295523685355e-05, + "loss": 0.2624, + "step": 16898 + }, + { + "epoch": 1.38, + "learning_rate": 1.081975228161669e-05, + "loss": 0.1626, + "step": 16899 + }, + { + "epoch": 1.38, + "learning_rate": 1.0819209039548024e-05, + "loss": 0.4305, + "step": 16900 + }, + { + "epoch": 1.38, + "learning_rate": 1.0818665797479358e-05, + "loss": 0.2107, + "step": 16901 + }, + { + "epoch": 1.38, + "learning_rate": 1.0818122555410692e-05, + "loss": 0.274, + "step": 16902 + }, + { + "epoch": 1.38, + "learning_rate": 1.0817579313342026e-05, + "loss": 0.4456, + "step": 16903 + }, + { + "epoch": 1.38, + "learning_rate": 1.0817036071273362e-05, + "loss": 0.3823, + "step": 16904 + }, + { + "epoch": 1.38, + "learning_rate": 1.0816492829204695e-05, + "loss": 0.4987, + "step": 16905 + }, + { + "epoch": 1.38, + "learning_rate": 1.0815949587136027e-05, + "loss": 0.2001, + "step": 16906 + }, + { + "epoch": 1.38, + "learning_rate": 1.0815406345067363e-05, + "loss": 0.2648, + "step": 16907 + }, + { + "epoch": 1.38, + "learning_rate": 1.0814863102998696e-05, + "loss": 0.1235, + "step": 16908 + }, + { + "epoch": 1.38, + "learning_rate": 1.0814319860930032e-05, + "loss": 0.4082, + "step": 16909 + }, + { + "epoch": 1.38, + "learning_rate": 1.0813776618861364e-05, + "loss": 0.5001, + "step": 16910 + }, + { + "epoch": 1.38, + "learning_rate": 1.08132333767927e-05, + "loss": 0.4691, + "step": 16911 + }, + { + "epoch": 1.38, + "learning_rate": 1.0812690134724033e-05, + "loss": 0.2857, + "step": 16912 + }, + { + "epoch": 1.38, + "learning_rate": 1.0812146892655369e-05, + "loss": 0.4559, + "step": 16913 + }, + { + "epoch": 1.38, + "learning_rate": 1.0811603650586701e-05, + "loss": 0.3965, + "step": 16914 + }, + { + "epoch": 1.38, + "learning_rate": 1.0811060408518037e-05, + "loss": 0.3499, + "step": 16915 + }, + { + "epoch": 1.38, + "learning_rate": 1.081051716644937e-05, + "loss": 0.1581, + "step": 16916 + }, + { + "epoch": 1.38, + "learning_rate": 1.0809973924380705e-05, + "loss": 0.2665, + "step": 16917 + }, + { + "epoch": 1.38, + "learning_rate": 1.0809430682312038e-05, + "loss": 0.279, + "step": 16918 + }, + { + "epoch": 1.38, + "learning_rate": 1.0808887440243374e-05, + "loss": 0.4585, + "step": 16919 + }, + { + "epoch": 1.38, + "learning_rate": 1.0808344198174706e-05, + "loss": 0.5016, + "step": 16920 + }, + { + "epoch": 1.38, + "learning_rate": 1.0807800956106042e-05, + "loss": 0.294, + "step": 16921 + }, + { + "epoch": 1.38, + "learning_rate": 1.0807257714037377e-05, + "loss": 0.3564, + "step": 16922 + }, + { + "epoch": 1.38, + "learning_rate": 1.080671447196871e-05, + "loss": 0.3804, + "step": 16923 + }, + { + "epoch": 1.38, + "learning_rate": 1.0806171229900045e-05, + "loss": 0.2006, + "step": 16924 + }, + { + "epoch": 1.38, + "learning_rate": 1.0805627987831378e-05, + "loss": 0.4293, + "step": 16925 + }, + { + "epoch": 1.38, + "learning_rate": 1.0805084745762714e-05, + "loss": 0.4663, + "step": 16926 + }, + { + "epoch": 1.38, + "learning_rate": 1.0804541503694046e-05, + "loss": 0.4742, + "step": 16927 + }, + { + "epoch": 1.38, + "learning_rate": 1.0803998261625382e-05, + "loss": 0.3593, + "step": 16928 + }, + { + "epoch": 1.38, + "learning_rate": 1.0803455019556714e-05, + "loss": 0.3647, + "step": 16929 + }, + { + "epoch": 1.38, + "learning_rate": 1.080291177748805e-05, + "loss": 0.5498, + "step": 16930 + }, + { + "epoch": 1.38, + "learning_rate": 1.0802368535419383e-05, + "loss": 0.3847, + "step": 16931 + }, + { + "epoch": 1.38, + "learning_rate": 1.0801825293350719e-05, + "loss": 0.4228, + "step": 16932 + }, + { + "epoch": 1.38, + "learning_rate": 1.0801282051282051e-05, + "loss": 0.5227, + "step": 16933 + }, + { + "epoch": 1.38, + "learning_rate": 1.0800738809213387e-05, + "loss": 0.4838, + "step": 16934 + }, + { + "epoch": 1.38, + "learning_rate": 1.080019556714472e-05, + "loss": 0.2329, + "step": 16935 + }, + { + "epoch": 1.38, + "learning_rate": 1.0799652325076056e-05, + "loss": 0.1408, + "step": 16936 + }, + { + "epoch": 1.38, + "learning_rate": 1.0799109083007388e-05, + "loss": 0.2406, + "step": 16937 + }, + { + "epoch": 1.38, + "learning_rate": 1.0798565840938724e-05, + "loss": 0.3998, + "step": 16938 + }, + { + "epoch": 1.38, + "learning_rate": 1.0798022598870057e-05, + "loss": 0.1851, + "step": 16939 + }, + { + "epoch": 1.38, + "learning_rate": 1.0797479356801393e-05, + "loss": 0.3941, + "step": 16940 + }, + { + "epoch": 1.38, + "learning_rate": 1.0796936114732725e-05, + "loss": 0.2868, + "step": 16941 + }, + { + "epoch": 1.38, + "learning_rate": 1.0796392872664061e-05, + "loss": 0.2076, + "step": 16942 + }, + { + "epoch": 1.38, + "learning_rate": 1.0795849630595394e-05, + "loss": 0.4037, + "step": 16943 + }, + { + "epoch": 1.38, + "learning_rate": 1.0795306388526728e-05, + "loss": 0.5317, + "step": 16944 + }, + { + "epoch": 1.38, + "learning_rate": 1.0794763146458062e-05, + "loss": 0.2876, + "step": 16945 + }, + { + "epoch": 1.38, + "learning_rate": 1.0794219904389396e-05, + "loss": 0.5428, + "step": 16946 + }, + { + "epoch": 1.38, + "learning_rate": 1.079367666232073e-05, + "loss": 0.419, + "step": 16947 + }, + { + "epoch": 1.38, + "learning_rate": 1.0793133420252065e-05, + "loss": 0.4388, + "step": 16948 + }, + { + "epoch": 1.38, + "learning_rate": 1.0792590178183399e-05, + "loss": 0.1685, + "step": 16949 + }, + { + "epoch": 1.38, + "learning_rate": 1.0792046936114733e-05, + "loss": 0.306, + "step": 16950 + }, + { + "epoch": 1.38, + "learning_rate": 1.0791503694046068e-05, + "loss": 0.6138, + "step": 16951 + }, + { + "epoch": 1.38, + "learning_rate": 1.0790960451977402e-05, + "loss": 0.222, + "step": 16952 + }, + { + "epoch": 1.38, + "learning_rate": 1.0790417209908736e-05, + "loss": 0.328, + "step": 16953 + }, + { + "epoch": 1.38, + "learning_rate": 1.078987396784007e-05, + "loss": 0.1282, + "step": 16954 + }, + { + "epoch": 1.38, + "learning_rate": 1.0789330725771404e-05, + "loss": 0.2494, + "step": 16955 + }, + { + "epoch": 1.38, + "learning_rate": 1.0788787483702739e-05, + "loss": 0.309, + "step": 16956 + }, + { + "epoch": 1.38, + "learning_rate": 1.0788244241634073e-05, + "loss": 0.2071, + "step": 16957 + }, + { + "epoch": 1.38, + "learning_rate": 1.0787700999565407e-05, + "loss": 0.3769, + "step": 16958 + }, + { + "epoch": 1.38, + "learning_rate": 1.0787157757496743e-05, + "loss": 0.4873, + "step": 16959 + }, + { + "epoch": 1.38, + "learning_rate": 1.0786614515428076e-05, + "loss": 0.4482, + "step": 16960 + }, + { + "epoch": 1.38, + "learning_rate": 1.0786071273359412e-05, + "loss": 0.3613, + "step": 16961 + }, + { + "epoch": 1.38, + "learning_rate": 1.0785528031290744e-05, + "loss": 0.2218, + "step": 16962 + }, + { + "epoch": 1.38, + "learning_rate": 1.0784984789222077e-05, + "loss": 0.3155, + "step": 16963 + }, + { + "epoch": 1.38, + "learning_rate": 1.0784441547153413e-05, + "loss": 0.3622, + "step": 16964 + }, + { + "epoch": 1.38, + "learning_rate": 1.0783898305084745e-05, + "loss": 0.1268, + "step": 16965 + }, + { + "epoch": 1.38, + "learning_rate": 1.0783355063016081e-05, + "loss": 0.3971, + "step": 16966 + }, + { + "epoch": 1.38, + "learning_rate": 1.0782811820947414e-05, + "loss": 0.304, + "step": 16967 + }, + { + "epoch": 1.38, + "learning_rate": 1.078226857887875e-05, + "loss": 0.2525, + "step": 16968 + }, + { + "epoch": 1.38, + "learning_rate": 1.0781725336810082e-05, + "loss": 0.3082, + "step": 16969 + }, + { + "epoch": 1.38, + "learning_rate": 1.0781182094741418e-05, + "loss": 0.4559, + "step": 16970 + }, + { + "epoch": 1.38, + "learning_rate": 1.078063885267275e-05, + "loss": 0.5684, + "step": 16971 + }, + { + "epoch": 1.38, + "learning_rate": 1.0780095610604086e-05, + "loss": 0.2628, + "step": 16972 + }, + { + "epoch": 1.38, + "learning_rate": 1.0779552368535419e-05, + "loss": 0.241, + "step": 16973 + }, + { + "epoch": 1.38, + "learning_rate": 1.0779009126466755e-05, + "loss": 0.6141, + "step": 16974 + }, + { + "epoch": 1.38, + "learning_rate": 1.0778465884398089e-05, + "loss": 0.2031, + "step": 16975 + }, + { + "epoch": 1.38, + "learning_rate": 1.0777922642329423e-05, + "loss": 0.5444, + "step": 16976 + }, + { + "epoch": 1.38, + "learning_rate": 1.0777379400260758e-05, + "loss": 0.3987, + "step": 16977 + }, + { + "epoch": 1.38, + "learning_rate": 1.0776836158192092e-05, + "loss": 0.2125, + "step": 16978 + }, + { + "epoch": 1.38, + "learning_rate": 1.0776292916123426e-05, + "loss": 0.5342, + "step": 16979 + }, + { + "epoch": 1.38, + "learning_rate": 1.077574967405476e-05, + "loss": 0.1778, + "step": 16980 + }, + { + "epoch": 1.38, + "learning_rate": 1.0775206431986094e-05, + "loss": 0.4132, + "step": 16981 + }, + { + "epoch": 1.38, + "learning_rate": 1.0774663189917427e-05, + "loss": 0.5375, + "step": 16982 + }, + { + "epoch": 1.38, + "learning_rate": 1.0774119947848763e-05, + "loss": 0.3636, + "step": 16983 + }, + { + "epoch": 1.38, + "learning_rate": 1.0773576705780095e-05, + "loss": 0.3054, + "step": 16984 + }, + { + "epoch": 1.38, + "learning_rate": 1.0773033463711431e-05, + "loss": 0.3965, + "step": 16985 + }, + { + "epoch": 1.38, + "learning_rate": 1.0772490221642764e-05, + "loss": 0.4112, + "step": 16986 + }, + { + "epoch": 1.38, + "learning_rate": 1.07719469795741e-05, + "loss": 0.2042, + "step": 16987 + }, + { + "epoch": 1.38, + "learning_rate": 1.0771403737505432e-05, + "loss": 0.401, + "step": 16988 + }, + { + "epoch": 1.38, + "learning_rate": 1.0770860495436768e-05, + "loss": 0.1284, + "step": 16989 + }, + { + "epoch": 1.38, + "learning_rate": 1.0770317253368101e-05, + "loss": 0.1739, + "step": 16990 + }, + { + "epoch": 1.38, + "learning_rate": 1.0769774011299437e-05, + "loss": 0.3595, + "step": 16991 + }, + { + "epoch": 1.38, + "learning_rate": 1.076923076923077e-05, + "loss": 0.2992, + "step": 16992 + }, + { + "epoch": 1.38, + "learning_rate": 1.0768687527162105e-05, + "loss": 0.677, + "step": 16993 + }, + { + "epoch": 1.38, + "learning_rate": 1.0768144285093438e-05, + "loss": 0.3283, + "step": 16994 + }, + { + "epoch": 1.38, + "learning_rate": 1.0767601043024774e-05, + "loss": 0.3512, + "step": 16995 + }, + { + "epoch": 1.38, + "learning_rate": 1.0767057800956106e-05, + "loss": 0.2754, + "step": 16996 + }, + { + "epoch": 1.39, + "learning_rate": 1.0766514558887442e-05, + "loss": 0.5329, + "step": 16997 + }, + { + "epoch": 1.39, + "learning_rate": 1.0765971316818775e-05, + "loss": 0.3573, + "step": 16998 + }, + { + "epoch": 1.39, + "learning_rate": 1.076542807475011e-05, + "loss": 0.5328, + "step": 16999 + }, + { + "epoch": 1.39, + "learning_rate": 1.0764884832681443e-05, + "loss": 0.2278, + "step": 17000 + }, + { + "epoch": 1.39, + "eval_accuracy": 0.840855832908813, + "eval_loss": 0.43903225660324097, + "eval_runtime": 22.3056, + "eval_samples_per_second": 440.025, + "eval_steps_per_second": 3.452, + "step": 17000 + }, + { + "epoch": 1.39, + "learning_rate": 1.0764341590612777e-05, + "loss": 0.3896, + "step": 17001 + }, + { + "epoch": 1.39, + "learning_rate": 1.0763798348544112e-05, + "loss": 0.2712, + "step": 17002 + }, + { + "epoch": 1.39, + "learning_rate": 1.0763255106475446e-05, + "loss": 0.3186, + "step": 17003 + }, + { + "epoch": 1.39, + "learning_rate": 1.076271186440678e-05, + "loss": 0.2762, + "step": 17004 + }, + { + "epoch": 1.39, + "learning_rate": 1.0762168622338114e-05, + "loss": 0.4422, + "step": 17005 + }, + { + "epoch": 1.39, + "learning_rate": 1.0761625380269449e-05, + "loss": 0.374, + "step": 17006 + }, + { + "epoch": 1.39, + "learning_rate": 1.0761082138200783e-05, + "loss": 0.2063, + "step": 17007 + }, + { + "epoch": 1.39, + "learning_rate": 1.0760538896132117e-05, + "loss": 0.2988, + "step": 17008 + }, + { + "epoch": 1.39, + "learning_rate": 1.0759995654063451e-05, + "loss": 0.6112, + "step": 17009 + }, + { + "epoch": 1.39, + "learning_rate": 1.0759452411994785e-05, + "loss": 0.2863, + "step": 17010 + }, + { + "epoch": 1.39, + "learning_rate": 1.075890916992612e-05, + "loss": 0.3546, + "step": 17011 + }, + { + "epoch": 1.39, + "learning_rate": 1.0758365927857456e-05, + "loss": 0.3738, + "step": 17012 + }, + { + "epoch": 1.39, + "learning_rate": 1.0757822685788788e-05, + "loss": 0.4897, + "step": 17013 + }, + { + "epoch": 1.39, + "learning_rate": 1.0757279443720124e-05, + "loss": 0.2568, + "step": 17014 + }, + { + "epoch": 1.39, + "learning_rate": 1.0756736201651457e-05, + "loss": 0.235, + "step": 17015 + }, + { + "epoch": 1.39, + "learning_rate": 1.0756192959582793e-05, + "loss": 0.3643, + "step": 17016 + }, + { + "epoch": 1.39, + "learning_rate": 1.0755649717514125e-05, + "loss": 0.5149, + "step": 17017 + }, + { + "epoch": 1.39, + "learning_rate": 1.0755106475445461e-05, + "loss": 0.3687, + "step": 17018 + }, + { + "epoch": 1.39, + "learning_rate": 1.0754563233376794e-05, + "loss": 0.272, + "step": 17019 + }, + { + "epoch": 1.39, + "learning_rate": 1.0754019991308126e-05, + "loss": 0.4001, + "step": 17020 + }, + { + "epoch": 1.39, + "learning_rate": 1.0753476749239462e-05, + "loss": 0.3639, + "step": 17021 + }, + { + "epoch": 1.39, + "learning_rate": 1.0752933507170795e-05, + "loss": 0.234, + "step": 17022 + }, + { + "epoch": 1.39, + "learning_rate": 1.075239026510213e-05, + "loss": 0.5583, + "step": 17023 + }, + { + "epoch": 1.39, + "learning_rate": 1.0751847023033463e-05, + "loss": 0.0832, + "step": 17024 + }, + { + "epoch": 1.39, + "learning_rate": 1.0751303780964799e-05, + "loss": 0.2337, + "step": 17025 + }, + { + "epoch": 1.39, + "learning_rate": 1.0750760538896131e-05, + "loss": 0.1366, + "step": 17026 + }, + { + "epoch": 1.39, + "learning_rate": 1.0750217296827467e-05, + "loss": 0.2769, + "step": 17027 + }, + { + "epoch": 1.39, + "learning_rate": 1.07496740547588e-05, + "loss": 0.209, + "step": 17028 + }, + { + "epoch": 1.39, + "learning_rate": 1.0749130812690136e-05, + "loss": 0.5237, + "step": 17029 + }, + { + "epoch": 1.39, + "learning_rate": 1.074858757062147e-05, + "loss": 0.6233, + "step": 17030 + }, + { + "epoch": 1.39, + "learning_rate": 1.0748044328552804e-05, + "loss": 0.4518, + "step": 17031 + }, + { + "epoch": 1.39, + "learning_rate": 1.0747501086484139e-05, + "loss": 0.4139, + "step": 17032 + }, + { + "epoch": 1.39, + "learning_rate": 1.0746957844415473e-05, + "loss": 0.5042, + "step": 17033 + }, + { + "epoch": 1.39, + "learning_rate": 1.0746414602346807e-05, + "loss": 0.3136, + "step": 17034 + }, + { + "epoch": 1.39, + "learning_rate": 1.0745871360278141e-05, + "loss": 0.6201, + "step": 17035 + }, + { + "epoch": 1.39, + "learning_rate": 1.0745328118209475e-05, + "loss": 0.5244, + "step": 17036 + }, + { + "epoch": 1.39, + "learning_rate": 1.074478487614081e-05, + "loss": 0.2165, + "step": 17037 + }, + { + "epoch": 1.39, + "learning_rate": 1.0744241634072144e-05, + "loss": 0.4954, + "step": 17038 + }, + { + "epoch": 1.39, + "learning_rate": 1.0743698392003476e-05, + "loss": 0.238, + "step": 17039 + }, + { + "epoch": 1.39, + "learning_rate": 1.0743155149934812e-05, + "loss": 0.1456, + "step": 17040 + }, + { + "epoch": 1.39, + "learning_rate": 1.0742611907866145e-05, + "loss": 0.3508, + "step": 17041 + }, + { + "epoch": 1.39, + "learning_rate": 1.0742068665797481e-05, + "loss": 0.2968, + "step": 17042 + }, + { + "epoch": 1.39, + "learning_rate": 1.0741525423728813e-05, + "loss": 0.5387, + "step": 17043 + }, + { + "epoch": 1.39, + "learning_rate": 1.074098218166015e-05, + "loss": 0.6058, + "step": 17044 + }, + { + "epoch": 1.39, + "learning_rate": 1.0740438939591482e-05, + "loss": 0.2897, + "step": 17045 + }, + { + "epoch": 1.39, + "learning_rate": 1.0739895697522818e-05, + "loss": 0.3356, + "step": 17046 + }, + { + "epoch": 1.39, + "learning_rate": 1.073935245545415e-05, + "loss": 0.3502, + "step": 17047 + }, + { + "epoch": 1.39, + "learning_rate": 1.0738809213385486e-05, + "loss": 0.6575, + "step": 17048 + }, + { + "epoch": 1.39, + "learning_rate": 1.0738265971316819e-05, + "loss": 0.4696, + "step": 17049 + }, + { + "epoch": 1.39, + "learning_rate": 1.0737722729248155e-05, + "loss": 0.2837, + "step": 17050 + }, + { + "epoch": 1.39, + "learning_rate": 1.0737179487179487e-05, + "loss": 0.6952, + "step": 17051 + }, + { + "epoch": 1.39, + "learning_rate": 1.0736636245110823e-05, + "loss": 0.2753, + "step": 17052 + }, + { + "epoch": 1.39, + "learning_rate": 1.0736093003042156e-05, + "loss": 0.2819, + "step": 17053 + }, + { + "epoch": 1.39, + "learning_rate": 1.0735549760973492e-05, + "loss": 0.2643, + "step": 17054 + }, + { + "epoch": 1.39, + "learning_rate": 1.0735006518904824e-05, + "loss": 0.2296, + "step": 17055 + }, + { + "epoch": 1.39, + "learning_rate": 1.073446327683616e-05, + "loss": 0.2489, + "step": 17056 + }, + { + "epoch": 1.39, + "learning_rate": 1.0733920034767493e-05, + "loss": 0.6085, + "step": 17057 + }, + { + "epoch": 1.39, + "learning_rate": 1.0733376792698827e-05, + "loss": 0.2403, + "step": 17058 + }, + { + "epoch": 1.39, + "learning_rate": 1.0732833550630161e-05, + "loss": 0.2262, + "step": 17059 + }, + { + "epoch": 1.39, + "learning_rate": 1.0732290308561495e-05, + "loss": 0.3346, + "step": 17060 + }, + { + "epoch": 1.39, + "learning_rate": 1.073174706649283e-05, + "loss": 0.2645, + "step": 17061 + }, + { + "epoch": 1.39, + "learning_rate": 1.0731203824424164e-05, + "loss": 0.2725, + "step": 17062 + }, + { + "epoch": 1.39, + "learning_rate": 1.0730660582355498e-05, + "loss": 0.363, + "step": 17063 + }, + { + "epoch": 1.39, + "learning_rate": 1.0730117340286832e-05, + "loss": 0.2942, + "step": 17064 + }, + { + "epoch": 1.39, + "learning_rate": 1.0729574098218166e-05, + "loss": 0.3713, + "step": 17065 + }, + { + "epoch": 1.39, + "learning_rate": 1.07290308561495e-05, + "loss": 0.4237, + "step": 17066 + }, + { + "epoch": 1.39, + "learning_rate": 1.0728487614080837e-05, + "loss": 0.2907, + "step": 17067 + }, + { + "epoch": 1.39, + "learning_rate": 1.072794437201217e-05, + "loss": 0.3062, + "step": 17068 + }, + { + "epoch": 1.39, + "learning_rate": 1.0727401129943505e-05, + "loss": 0.409, + "step": 17069 + }, + { + "epoch": 1.39, + "learning_rate": 1.0726857887874838e-05, + "loss": 0.2697, + "step": 17070 + }, + { + "epoch": 1.39, + "learning_rate": 1.0726314645806174e-05, + "loss": 0.2046, + "step": 17071 + }, + { + "epoch": 1.39, + "learning_rate": 1.0725771403737506e-05, + "loss": 0.0971, + "step": 17072 + }, + { + "epoch": 1.39, + "learning_rate": 1.0725228161668842e-05, + "loss": 0.4533, + "step": 17073 + }, + { + "epoch": 1.39, + "learning_rate": 1.0724684919600175e-05, + "loss": 0.2525, + "step": 17074 + }, + { + "epoch": 1.39, + "learning_rate": 1.072414167753151e-05, + "loss": 0.5319, + "step": 17075 + }, + { + "epoch": 1.39, + "learning_rate": 1.0723598435462843e-05, + "loss": 0.2241, + "step": 17076 + }, + { + "epoch": 1.39, + "learning_rate": 1.0723055193394176e-05, + "loss": 0.411, + "step": 17077 + }, + { + "epoch": 1.39, + "learning_rate": 1.0722511951325511e-05, + "loss": 0.3679, + "step": 17078 + }, + { + "epoch": 1.39, + "learning_rate": 1.0721968709256844e-05, + "loss": 0.2759, + "step": 17079 + }, + { + "epoch": 1.39, + "learning_rate": 1.072142546718818e-05, + "loss": 0.2576, + "step": 17080 + }, + { + "epoch": 1.39, + "learning_rate": 1.0720882225119512e-05, + "loss": 0.3574, + "step": 17081 + }, + { + "epoch": 1.39, + "learning_rate": 1.0720338983050848e-05, + "loss": 0.2488, + "step": 17082 + }, + { + "epoch": 1.39, + "learning_rate": 1.0719795740982183e-05, + "loss": 0.3971, + "step": 17083 + }, + { + "epoch": 1.39, + "learning_rate": 1.0719252498913517e-05, + "loss": 0.4016, + "step": 17084 + }, + { + "epoch": 1.39, + "learning_rate": 1.0718709256844851e-05, + "loss": 0.2322, + "step": 17085 + }, + { + "epoch": 1.39, + "learning_rate": 1.0718166014776185e-05, + "loss": 0.2401, + "step": 17086 + }, + { + "epoch": 1.39, + "learning_rate": 1.071762277270752e-05, + "loss": 0.3032, + "step": 17087 + }, + { + "epoch": 1.39, + "learning_rate": 1.0717079530638854e-05, + "loss": 0.2902, + "step": 17088 + }, + { + "epoch": 1.39, + "learning_rate": 1.0716536288570188e-05, + "loss": 0.3012, + "step": 17089 + }, + { + "epoch": 1.39, + "learning_rate": 1.0715993046501522e-05, + "loss": 0.2563, + "step": 17090 + }, + { + "epoch": 1.39, + "learning_rate": 1.0715449804432856e-05, + "loss": 0.2366, + "step": 17091 + }, + { + "epoch": 1.39, + "learning_rate": 1.071490656236419e-05, + "loss": 0.4775, + "step": 17092 + }, + { + "epoch": 1.39, + "learning_rate": 1.0714363320295525e-05, + "loss": 0.7731, + "step": 17093 + }, + { + "epoch": 1.39, + "learning_rate": 1.0713820078226859e-05, + "loss": 0.2762, + "step": 17094 + }, + { + "epoch": 1.39, + "learning_rate": 1.0713276836158193e-05, + "loss": 0.2817, + "step": 17095 + }, + { + "epoch": 1.39, + "learning_rate": 1.0712733594089526e-05, + "loss": 0.2656, + "step": 17096 + }, + { + "epoch": 1.39, + "learning_rate": 1.0712190352020862e-05, + "loss": 0.2988, + "step": 17097 + }, + { + "epoch": 1.39, + "learning_rate": 1.0711647109952194e-05, + "loss": 0.447, + "step": 17098 + }, + { + "epoch": 1.39, + "learning_rate": 1.071110386788353e-05, + "loss": 0.747, + "step": 17099 + }, + { + "epoch": 1.39, + "learning_rate": 1.0710560625814863e-05, + "loss": 0.3179, + "step": 17100 + }, + { + "epoch": 1.39, + "learning_rate": 1.0710017383746199e-05, + "loss": 0.0923, + "step": 17101 + }, + { + "epoch": 1.39, + "learning_rate": 1.0709474141677531e-05, + "loss": 0.2537, + "step": 17102 + }, + { + "epoch": 1.39, + "learning_rate": 1.0708930899608867e-05, + "loss": 0.4247, + "step": 17103 + }, + { + "epoch": 1.39, + "learning_rate": 1.07083876575402e-05, + "loss": 0.243, + "step": 17104 + }, + { + "epoch": 1.39, + "learning_rate": 1.0707844415471536e-05, + "loss": 0.2589, + "step": 17105 + }, + { + "epoch": 1.39, + "learning_rate": 1.0707301173402868e-05, + "loss": 0.0916, + "step": 17106 + }, + { + "epoch": 1.39, + "learning_rate": 1.0706757931334204e-05, + "loss": 0.3151, + "step": 17107 + }, + { + "epoch": 1.39, + "learning_rate": 1.0706214689265537e-05, + "loss": 0.2109, + "step": 17108 + }, + { + "epoch": 1.39, + "learning_rate": 1.0705671447196873e-05, + "loss": 0.3836, + "step": 17109 + }, + { + "epoch": 1.39, + "learning_rate": 1.0705128205128205e-05, + "loss": 0.318, + "step": 17110 + }, + { + "epoch": 1.39, + "learning_rate": 1.0704584963059541e-05, + "loss": 0.1722, + "step": 17111 + }, + { + "epoch": 1.39, + "learning_rate": 1.0704041720990874e-05, + "loss": 0.3106, + "step": 17112 + }, + { + "epoch": 1.39, + "learning_rate": 1.070349847892221e-05, + "loss": 0.3876, + "step": 17113 + }, + { + "epoch": 1.39, + "learning_rate": 1.0702955236853542e-05, + "loss": 0.2199, + "step": 17114 + }, + { + "epoch": 1.39, + "learning_rate": 1.0702411994784876e-05, + "loss": 0.3555, + "step": 17115 + }, + { + "epoch": 1.39, + "learning_rate": 1.070186875271621e-05, + "loss": 0.2923, + "step": 17116 + }, + { + "epoch": 1.39, + "learning_rate": 1.0701325510647545e-05, + "loss": 0.2751, + "step": 17117 + }, + { + "epoch": 1.39, + "learning_rate": 1.0700782268578879e-05, + "loss": 0.7258, + "step": 17118 + }, + { + "epoch": 1.39, + "learning_rate": 1.0700239026510213e-05, + "loss": 0.4745, + "step": 17119 + }, + { + "epoch": 1.4, + "learning_rate": 1.0699695784441549e-05, + "loss": 0.2117, + "step": 17120 + }, + { + "epoch": 1.4, + "learning_rate": 1.0699152542372882e-05, + "loss": 0.7664, + "step": 17121 + }, + { + "epoch": 1.4, + "learning_rate": 1.0698609300304218e-05, + "loss": 0.2582, + "step": 17122 + }, + { + "epoch": 1.4, + "learning_rate": 1.069806605823555e-05, + "loss": 0.2918, + "step": 17123 + }, + { + "epoch": 1.4, + "learning_rate": 1.0697522816166886e-05, + "loss": 0.329, + "step": 17124 + }, + { + "epoch": 1.4, + "learning_rate": 1.0696979574098219e-05, + "loss": 0.6609, + "step": 17125 + }, + { + "epoch": 1.4, + "learning_rate": 1.0696436332029555e-05, + "loss": 0.2522, + "step": 17126 + }, + { + "epoch": 1.4, + "learning_rate": 1.0695893089960887e-05, + "loss": 0.1946, + "step": 17127 + }, + { + "epoch": 1.4, + "learning_rate": 1.0695349847892223e-05, + "loss": 0.3318, + "step": 17128 + }, + { + "epoch": 1.4, + "learning_rate": 1.0694806605823556e-05, + "loss": 0.4099, + "step": 17129 + }, + { + "epoch": 1.4, + "learning_rate": 1.0694263363754891e-05, + "loss": 0.3597, + "step": 17130 + }, + { + "epoch": 1.4, + "learning_rate": 1.0693720121686224e-05, + "loss": 0.2565, + "step": 17131 + }, + { + "epoch": 1.4, + "learning_rate": 1.069317687961756e-05, + "loss": 0.3741, + "step": 17132 + }, + { + "epoch": 1.4, + "learning_rate": 1.0692633637548892e-05, + "loss": 0.4179, + "step": 17133 + }, + { + "epoch": 1.4, + "learning_rate": 1.0692090395480225e-05, + "loss": 0.4108, + "step": 17134 + }, + { + "epoch": 1.4, + "learning_rate": 1.0691547153411561e-05, + "loss": 0.3249, + "step": 17135 + }, + { + "epoch": 1.4, + "learning_rate": 1.0691003911342893e-05, + "loss": 0.3339, + "step": 17136 + }, + { + "epoch": 1.4, + "learning_rate": 1.069046066927423e-05, + "loss": 0.268, + "step": 17137 + }, + { + "epoch": 1.4, + "learning_rate": 1.0689917427205564e-05, + "loss": 0.3895, + "step": 17138 + }, + { + "epoch": 1.4, + "learning_rate": 1.0689374185136898e-05, + "loss": 0.1776, + "step": 17139 + }, + { + "epoch": 1.4, + "learning_rate": 1.0688830943068232e-05, + "loss": 0.1959, + "step": 17140 + }, + { + "epoch": 1.4, + "learning_rate": 1.0688287700999566e-05, + "loss": 0.2776, + "step": 17141 + }, + { + "epoch": 1.4, + "learning_rate": 1.06877444589309e-05, + "loss": 0.3872, + "step": 17142 + }, + { + "epoch": 1.4, + "learning_rate": 1.0687201216862235e-05, + "loss": 0.2949, + "step": 17143 + }, + { + "epoch": 1.4, + "learning_rate": 1.0686657974793569e-05, + "loss": 0.2174, + "step": 17144 + }, + { + "epoch": 1.4, + "learning_rate": 1.0686114732724903e-05, + "loss": 0.2439, + "step": 17145 + }, + { + "epoch": 1.4, + "learning_rate": 1.0685571490656237e-05, + "loss": 0.4556, + "step": 17146 + }, + { + "epoch": 1.4, + "learning_rate": 1.0685028248587572e-05, + "loss": 0.7063, + "step": 17147 + }, + { + "epoch": 1.4, + "learning_rate": 1.0684485006518906e-05, + "loss": 0.2476, + "step": 17148 + }, + { + "epoch": 1.4, + "learning_rate": 1.068394176445024e-05, + "loss": 0.2427, + "step": 17149 + }, + { + "epoch": 1.4, + "learning_rate": 1.0683398522381574e-05, + "loss": 0.1688, + "step": 17150 + }, + { + "epoch": 1.4, + "learning_rate": 1.0682855280312909e-05, + "loss": 0.3131, + "step": 17151 + }, + { + "epoch": 1.4, + "learning_rate": 1.0682312038244243e-05, + "loss": 0.3594, + "step": 17152 + }, + { + "epoch": 1.4, + "learning_rate": 1.0681768796175575e-05, + "loss": 0.3732, + "step": 17153 + }, + { + "epoch": 1.4, + "learning_rate": 1.0681225554106911e-05, + "loss": 0.18, + "step": 17154 + }, + { + "epoch": 1.4, + "learning_rate": 1.0680682312038244e-05, + "loss": 0.1564, + "step": 17155 + }, + { + "epoch": 1.4, + "learning_rate": 1.068013906996958e-05, + "loss": 0.4505, + "step": 17156 + }, + { + "epoch": 1.4, + "learning_rate": 1.0679595827900912e-05, + "loss": 0.3062, + "step": 17157 + }, + { + "epoch": 1.4, + "learning_rate": 1.0679052585832248e-05, + "loss": 0.2544, + "step": 17158 + }, + { + "epoch": 1.4, + "learning_rate": 1.067850934376358e-05, + "loss": 0.3891, + "step": 17159 + }, + { + "epoch": 1.4, + "learning_rate": 1.0677966101694917e-05, + "loss": 0.3597, + "step": 17160 + }, + { + "epoch": 1.4, + "learning_rate": 1.067742285962625e-05, + "loss": 0.3334, + "step": 17161 + }, + { + "epoch": 1.4, + "learning_rate": 1.0676879617557585e-05, + "loss": 0.2983, + "step": 17162 + }, + { + "epoch": 1.4, + "learning_rate": 1.0676336375488918e-05, + "loss": 0.3377, + "step": 17163 + }, + { + "epoch": 1.4, + "learning_rate": 1.0675793133420254e-05, + "loss": 0.4151, + "step": 17164 + }, + { + "epoch": 1.4, + "learning_rate": 1.0675249891351586e-05, + "loss": 0.3605, + "step": 17165 + }, + { + "epoch": 1.4, + "learning_rate": 1.0674706649282922e-05, + "loss": 0.3293, + "step": 17166 + }, + { + "epoch": 1.4, + "learning_rate": 1.0674163407214255e-05, + "loss": 0.3696, + "step": 17167 + }, + { + "epoch": 1.4, + "learning_rate": 1.067362016514559e-05, + "loss": 0.2721, + "step": 17168 + }, + { + "epoch": 1.4, + "learning_rate": 1.0673076923076923e-05, + "loss": 0.1567, + "step": 17169 + }, + { + "epoch": 1.4, + "learning_rate": 1.0672533681008259e-05, + "loss": 0.2821, + "step": 17170 + }, + { + "epoch": 1.4, + "learning_rate": 1.0671990438939592e-05, + "loss": 0.3065, + "step": 17171 + }, + { + "epoch": 1.4, + "learning_rate": 1.0671447196870926e-05, + "loss": 0.3006, + "step": 17172 + }, + { + "epoch": 1.4, + "learning_rate": 1.067090395480226e-05, + "loss": 0.2314, + "step": 17173 + }, + { + "epoch": 1.4, + "learning_rate": 1.0670360712733594e-05, + "loss": 0.5266, + "step": 17174 + }, + { + "epoch": 1.4, + "learning_rate": 1.066981747066493e-05, + "loss": 0.2849, + "step": 17175 + }, + { + "epoch": 1.4, + "learning_rate": 1.0669274228596263e-05, + "loss": 0.4547, + "step": 17176 + }, + { + "epoch": 1.4, + "learning_rate": 1.0668730986527599e-05, + "loss": 0.2918, + "step": 17177 + }, + { + "epoch": 1.4, + "learning_rate": 1.0668187744458931e-05, + "loss": 0.4978, + "step": 17178 + }, + { + "epoch": 1.4, + "learning_rate": 1.0667644502390267e-05, + "loss": 0.3034, + "step": 17179 + }, + { + "epoch": 1.4, + "learning_rate": 1.06671012603216e-05, + "loss": 0.3334, + "step": 17180 + }, + { + "epoch": 1.4, + "learning_rate": 1.0666558018252936e-05, + "loss": 0.2525, + "step": 17181 + }, + { + "epoch": 1.4, + "learning_rate": 1.0666014776184268e-05, + "loss": 0.2987, + "step": 17182 + }, + { + "epoch": 1.4, + "learning_rate": 1.0665471534115604e-05, + "loss": 0.1769, + "step": 17183 + }, + { + "epoch": 1.4, + "learning_rate": 1.0664928292046937e-05, + "loss": 0.3039, + "step": 17184 + }, + { + "epoch": 1.4, + "learning_rate": 1.0664385049978272e-05, + "loss": 0.3217, + "step": 17185 + }, + { + "epoch": 1.4, + "learning_rate": 1.0663841807909605e-05, + "loss": 0.3266, + "step": 17186 + }, + { + "epoch": 1.4, + "learning_rate": 1.0663298565840941e-05, + "loss": 0.2953, + "step": 17187 + }, + { + "epoch": 1.4, + "learning_rate": 1.0662755323772273e-05, + "loss": 0.5938, + "step": 17188 + }, + { + "epoch": 1.4, + "learning_rate": 1.066221208170361e-05, + "loss": 0.2861, + "step": 17189 + }, + { + "epoch": 1.4, + "learning_rate": 1.0661668839634942e-05, + "loss": 0.2149, + "step": 17190 + }, + { + "epoch": 1.4, + "learning_rate": 1.0661125597566276e-05, + "loss": 0.3308, + "step": 17191 + }, + { + "epoch": 1.4, + "learning_rate": 1.066058235549761e-05, + "loss": 0.3785, + "step": 17192 + }, + { + "epoch": 1.4, + "learning_rate": 1.0660039113428945e-05, + "loss": 0.3044, + "step": 17193 + }, + { + "epoch": 1.4, + "learning_rate": 1.0659495871360279e-05, + "loss": 0.3987, + "step": 17194 + }, + { + "epoch": 1.4, + "learning_rate": 1.0658952629291613e-05, + "loss": 0.3135, + "step": 17195 + }, + { + "epoch": 1.4, + "learning_rate": 1.0658409387222947e-05, + "loss": 0.2728, + "step": 17196 + }, + { + "epoch": 1.4, + "learning_rate": 1.0657866145154282e-05, + "loss": 0.2016, + "step": 17197 + }, + { + "epoch": 1.4, + "learning_rate": 1.0657322903085616e-05, + "loss": 0.2205, + "step": 17198 + }, + { + "epoch": 1.4, + "learning_rate": 1.065677966101695e-05, + "loss": 0.2175, + "step": 17199 + }, + { + "epoch": 1.4, + "learning_rate": 1.0656236418948284e-05, + "loss": 0.2574, + "step": 17200 + }, + { + "epoch": 1.4, + "learning_rate": 1.0655693176879618e-05, + "loss": 0.3542, + "step": 17201 + }, + { + "epoch": 1.4, + "learning_rate": 1.0655149934810953e-05, + "loss": 0.2025, + "step": 17202 + }, + { + "epoch": 1.4, + "learning_rate": 1.0654606692742287e-05, + "loss": 0.4354, + "step": 17203 + }, + { + "epoch": 1.4, + "learning_rate": 1.0654063450673621e-05, + "loss": 0.2867, + "step": 17204 + }, + { + "epoch": 1.4, + "learning_rate": 1.0653520208604955e-05, + "loss": 0.1881, + "step": 17205 + }, + { + "epoch": 1.4, + "learning_rate": 1.065297696653629e-05, + "loss": 0.3246, + "step": 17206 + }, + { + "epoch": 1.4, + "learning_rate": 1.0652433724467624e-05, + "loss": 0.3254, + "step": 17207 + }, + { + "epoch": 1.4, + "learning_rate": 1.0651890482398958e-05, + "loss": 0.2295, + "step": 17208 + }, + { + "epoch": 1.4, + "learning_rate": 1.0651347240330292e-05, + "loss": 0.5044, + "step": 17209 + }, + { + "epoch": 1.4, + "learning_rate": 1.0650803998261625e-05, + "loss": 0.21, + "step": 17210 + }, + { + "epoch": 1.4, + "learning_rate": 1.065026075619296e-05, + "loss": 0.3125, + "step": 17211 + }, + { + "epoch": 1.4, + "learning_rate": 1.0649717514124293e-05, + "loss": 0.3092, + "step": 17212 + }, + { + "epoch": 1.4, + "learning_rate": 1.064917427205563e-05, + "loss": 0.2445, + "step": 17213 + }, + { + "epoch": 1.4, + "learning_rate": 1.0648631029986962e-05, + "loss": 0.3091, + "step": 17214 + }, + { + "epoch": 1.4, + "learning_rate": 1.0648087787918298e-05, + "loss": 0.2877, + "step": 17215 + }, + { + "epoch": 1.4, + "learning_rate": 1.064754454584963e-05, + "loss": 0.3109, + "step": 17216 + }, + { + "epoch": 1.4, + "learning_rate": 1.0647001303780966e-05, + "loss": 0.4266, + "step": 17217 + }, + { + "epoch": 1.4, + "learning_rate": 1.0646458061712299e-05, + "loss": 0.1945, + "step": 17218 + }, + { + "epoch": 1.4, + "learning_rate": 1.0645914819643635e-05, + "loss": 0.2111, + "step": 17219 + }, + { + "epoch": 1.4, + "learning_rate": 1.0645371577574967e-05, + "loss": 0.5592, + "step": 17220 + }, + { + "epoch": 1.4, + "learning_rate": 1.0644828335506303e-05, + "loss": 0.2117, + "step": 17221 + }, + { + "epoch": 1.4, + "learning_rate": 1.0644285093437636e-05, + "loss": 0.503, + "step": 17222 + }, + { + "epoch": 1.4, + "learning_rate": 1.0643741851368972e-05, + "loss": 0.1847, + "step": 17223 + }, + { + "epoch": 1.4, + "learning_rate": 1.0643198609300304e-05, + "loss": 0.4823, + "step": 17224 + }, + { + "epoch": 1.4, + "learning_rate": 1.064265536723164e-05, + "loss": 0.2653, + "step": 17225 + }, + { + "epoch": 1.4, + "learning_rate": 1.0642112125162973e-05, + "loss": 0.1364, + "step": 17226 + }, + { + "epoch": 1.4, + "learning_rate": 1.0641568883094308e-05, + "loss": 0.3515, + "step": 17227 + }, + { + "epoch": 1.4, + "learning_rate": 1.0641025641025643e-05, + "loss": 0.2649, + "step": 17228 + }, + { + "epoch": 1.4, + "learning_rate": 1.0640482398956975e-05, + "loss": 0.0933, + "step": 17229 + }, + { + "epoch": 1.4, + "learning_rate": 1.0639939156888311e-05, + "loss": 0.4213, + "step": 17230 + }, + { + "epoch": 1.4, + "learning_rate": 1.0639395914819644e-05, + "loss": 0.1639, + "step": 17231 + }, + { + "epoch": 1.4, + "learning_rate": 1.063885267275098e-05, + "loss": 0.2031, + "step": 17232 + }, + { + "epoch": 1.4, + "learning_rate": 1.0638309430682312e-05, + "loss": 0.3404, + "step": 17233 + }, + { + "epoch": 1.4, + "learning_rate": 1.0637766188613648e-05, + "loss": 0.3853, + "step": 17234 + }, + { + "epoch": 1.4, + "learning_rate": 1.063722294654498e-05, + "loss": 0.3296, + "step": 17235 + }, + { + "epoch": 1.4, + "learning_rate": 1.0636679704476317e-05, + "loss": 0.3699, + "step": 17236 + }, + { + "epoch": 1.4, + "learning_rate": 1.0636136462407649e-05, + "loss": 0.1387, + "step": 17237 + }, + { + "epoch": 1.4, + "learning_rate": 1.0635593220338985e-05, + "loss": 0.4003, + "step": 17238 + }, + { + "epoch": 1.4, + "learning_rate": 1.0635049978270317e-05, + "loss": 0.2871, + "step": 17239 + }, + { + "epoch": 1.4, + "learning_rate": 1.0634506736201653e-05, + "loss": 0.2392, + "step": 17240 + }, + { + "epoch": 1.4, + "learning_rate": 1.0633963494132986e-05, + "loss": 0.1888, + "step": 17241 + }, + { + "epoch": 1.4, + "learning_rate": 1.0633420252064322e-05, + "loss": 0.2996, + "step": 17242 + }, + { + "epoch": 1.41, + "learning_rate": 1.0632877009995654e-05, + "loss": 0.2199, + "step": 17243 + }, + { + "epoch": 1.41, + "learning_rate": 1.063233376792699e-05, + "loss": 0.2909, + "step": 17244 + }, + { + "epoch": 1.41, + "learning_rate": 1.0631790525858323e-05, + "loss": 0.3924, + "step": 17245 + }, + { + "epoch": 1.41, + "learning_rate": 1.0631247283789659e-05, + "loss": 0.4881, + "step": 17246 + }, + { + "epoch": 1.41, + "learning_rate": 1.0630704041720991e-05, + "loss": 0.1981, + "step": 17247 + }, + { + "epoch": 1.41, + "learning_rate": 1.0630160799652326e-05, + "loss": 0.1984, + "step": 17248 + }, + { + "epoch": 1.41, + "learning_rate": 1.062961755758366e-05, + "loss": 0.1263, + "step": 17249 + }, + { + "epoch": 1.41, + "learning_rate": 1.0629074315514994e-05, + "loss": 0.2932, + "step": 17250 + }, + { + "epoch": 1.41, + "eval_accuracy": 0.8414671421293938, + "eval_loss": 0.4453674256801605, + "eval_runtime": 22.253, + "eval_samples_per_second": 441.064, + "eval_steps_per_second": 3.46, + "step": 17250 + }, + { + "epoch": 1.41, + "learning_rate": 1.0628531073446328e-05, + "loss": 0.2984, + "step": 17251 + }, + { + "epoch": 1.41, + "learning_rate": 1.0627987831377662e-05, + "loss": 0.1435, + "step": 17252 + }, + { + "epoch": 1.41, + "learning_rate": 1.0627444589308997e-05, + "loss": 0.2962, + "step": 17253 + }, + { + "epoch": 1.41, + "learning_rate": 1.0626901347240331e-05, + "loss": 0.5891, + "step": 17254 + }, + { + "epoch": 1.41, + "learning_rate": 1.0626358105171665e-05, + "loss": 0.3058, + "step": 17255 + }, + { + "epoch": 1.41, + "learning_rate": 1.0625814863103e-05, + "loss": 0.2823, + "step": 17256 + }, + { + "epoch": 1.41, + "learning_rate": 1.0625271621034334e-05, + "loss": 0.2862, + "step": 17257 + }, + { + "epoch": 1.41, + "learning_rate": 1.0624728378965668e-05, + "loss": 0.4669, + "step": 17258 + }, + { + "epoch": 1.41, + "learning_rate": 1.0624185136897002e-05, + "loss": 0.1348, + "step": 17259 + }, + { + "epoch": 1.41, + "learning_rate": 1.0623641894828336e-05, + "loss": 0.2952, + "step": 17260 + }, + { + "epoch": 1.41, + "learning_rate": 1.062309865275967e-05, + "loss": 0.3056, + "step": 17261 + }, + { + "epoch": 1.41, + "learning_rate": 1.0622555410691005e-05, + "loss": 0.7152, + "step": 17262 + }, + { + "epoch": 1.41, + "learning_rate": 1.0622012168622339e-05, + "loss": 0.2724, + "step": 17263 + }, + { + "epoch": 1.41, + "learning_rate": 1.0621468926553673e-05, + "loss": 0.466, + "step": 17264 + }, + { + "epoch": 1.41, + "learning_rate": 1.062092568448501e-05, + "loss": 0.5139, + "step": 17265 + }, + { + "epoch": 1.41, + "learning_rate": 1.0620382442416342e-05, + "loss": 0.144, + "step": 17266 + }, + { + "epoch": 1.41, + "learning_rate": 1.0619839200347678e-05, + "loss": 0.2628, + "step": 17267 + }, + { + "epoch": 1.41, + "learning_rate": 1.061929595827901e-05, + "loss": 0.2855, + "step": 17268 + }, + { + "epoch": 1.41, + "learning_rate": 1.0618752716210343e-05, + "loss": 0.35, + "step": 17269 + }, + { + "epoch": 1.41, + "learning_rate": 1.0618209474141679e-05, + "loss": 0.5997, + "step": 17270 + }, + { + "epoch": 1.41, + "learning_rate": 1.0617666232073011e-05, + "loss": 0.35, + "step": 17271 + }, + { + "epoch": 1.41, + "learning_rate": 1.0617122990004347e-05, + "loss": 0.4441, + "step": 17272 + }, + { + "epoch": 1.41, + "learning_rate": 1.061657974793568e-05, + "loss": 0.2811, + "step": 17273 + }, + { + "epoch": 1.41, + "learning_rate": 1.0616036505867016e-05, + "loss": 0.2424, + "step": 17274 + }, + { + "epoch": 1.41, + "learning_rate": 1.0615493263798348e-05, + "loss": 0.2483, + "step": 17275 + }, + { + "epoch": 1.41, + "learning_rate": 1.0614950021729684e-05, + "loss": 0.2111, + "step": 17276 + }, + { + "epoch": 1.41, + "learning_rate": 1.0614406779661017e-05, + "loss": 0.3703, + "step": 17277 + }, + { + "epoch": 1.41, + "learning_rate": 1.0613863537592352e-05, + "loss": 0.4222, + "step": 17278 + }, + { + "epoch": 1.41, + "learning_rate": 1.0613320295523685e-05, + "loss": 0.3418, + "step": 17279 + }, + { + "epoch": 1.41, + "learning_rate": 1.0612777053455021e-05, + "loss": 0.506, + "step": 17280 + }, + { + "epoch": 1.41, + "learning_rate": 1.0612233811386353e-05, + "loss": 0.7986, + "step": 17281 + }, + { + "epoch": 1.41, + "learning_rate": 1.061169056931769e-05, + "loss": 0.3017, + "step": 17282 + }, + { + "epoch": 1.41, + "learning_rate": 1.0611147327249024e-05, + "loss": 0.2428, + "step": 17283 + }, + { + "epoch": 1.41, + "learning_rate": 1.0610604085180358e-05, + "loss": 0.4835, + "step": 17284 + }, + { + "epoch": 1.41, + "learning_rate": 1.0610060843111692e-05, + "loss": 0.4775, + "step": 17285 + }, + { + "epoch": 1.41, + "learning_rate": 1.0609517601043026e-05, + "loss": 0.3764, + "step": 17286 + }, + { + "epoch": 1.41, + "learning_rate": 1.060897435897436e-05, + "loss": 0.4631, + "step": 17287 + }, + { + "epoch": 1.41, + "learning_rate": 1.0608431116905693e-05, + "loss": 0.3807, + "step": 17288 + }, + { + "epoch": 1.41, + "learning_rate": 1.0607887874837029e-05, + "loss": 0.3547, + "step": 17289 + }, + { + "epoch": 1.41, + "learning_rate": 1.0607344632768362e-05, + "loss": 0.5267, + "step": 17290 + }, + { + "epoch": 1.41, + "learning_rate": 1.0606801390699697e-05, + "loss": 0.5338, + "step": 17291 + }, + { + "epoch": 1.41, + "learning_rate": 1.060625814863103e-05, + "loss": 0.3074, + "step": 17292 + }, + { + "epoch": 1.41, + "learning_rate": 1.0605714906562366e-05, + "loss": 0.4966, + "step": 17293 + }, + { + "epoch": 1.41, + "learning_rate": 1.0605171664493698e-05, + "loss": 0.1514, + "step": 17294 + }, + { + "epoch": 1.41, + "learning_rate": 1.0604628422425034e-05, + "loss": 0.5567, + "step": 17295 + }, + { + "epoch": 1.41, + "learning_rate": 1.0604085180356367e-05, + "loss": 0.575, + "step": 17296 + }, + { + "epoch": 1.41, + "learning_rate": 1.0603541938287703e-05, + "loss": 0.3486, + "step": 17297 + }, + { + "epoch": 1.41, + "learning_rate": 1.0602998696219035e-05, + "loss": 0.3318, + "step": 17298 + }, + { + "epoch": 1.41, + "learning_rate": 1.0602455454150371e-05, + "loss": 0.2953, + "step": 17299 + }, + { + "epoch": 1.41, + "learning_rate": 1.0601912212081704e-05, + "loss": 0.5748, + "step": 17300 + }, + { + "epoch": 1.41, + "learning_rate": 1.060136897001304e-05, + "loss": 0.1819, + "step": 17301 + }, + { + "epoch": 1.41, + "learning_rate": 1.0600825727944372e-05, + "loss": 0.3532, + "step": 17302 + }, + { + "epoch": 1.41, + "learning_rate": 1.0600282485875708e-05, + "loss": 0.5468, + "step": 17303 + }, + { + "epoch": 1.41, + "learning_rate": 1.059973924380704e-05, + "loss": 0.3697, + "step": 17304 + }, + { + "epoch": 1.41, + "learning_rate": 1.0599196001738377e-05, + "loss": 0.453, + "step": 17305 + }, + { + "epoch": 1.41, + "learning_rate": 1.059865275966971e-05, + "loss": 0.4054, + "step": 17306 + }, + { + "epoch": 1.41, + "learning_rate": 1.0598109517601043e-05, + "loss": 0.3025, + "step": 17307 + }, + { + "epoch": 1.41, + "learning_rate": 1.0597566275532378e-05, + "loss": 0.4848, + "step": 17308 + }, + { + "epoch": 1.41, + "learning_rate": 1.0597023033463712e-05, + "loss": 0.2917, + "step": 17309 + }, + { + "epoch": 1.41, + "learning_rate": 1.0596479791395046e-05, + "loss": 0.3, + "step": 17310 + }, + { + "epoch": 1.41, + "learning_rate": 1.059593654932638e-05, + "loss": 0.176, + "step": 17311 + }, + { + "epoch": 1.41, + "learning_rate": 1.0595393307257715e-05, + "loss": 0.1264, + "step": 17312 + }, + { + "epoch": 1.41, + "learning_rate": 1.0594850065189049e-05, + "loss": 0.2941, + "step": 17313 + }, + { + "epoch": 1.41, + "learning_rate": 1.0594306823120383e-05, + "loss": 0.1392, + "step": 17314 + }, + { + "epoch": 1.41, + "learning_rate": 1.0593763581051717e-05, + "loss": 0.3131, + "step": 17315 + }, + { + "epoch": 1.41, + "learning_rate": 1.0593220338983052e-05, + "loss": 0.5206, + "step": 17316 + }, + { + "epoch": 1.41, + "learning_rate": 1.0592677096914386e-05, + "loss": 0.3156, + "step": 17317 + }, + { + "epoch": 1.41, + "learning_rate": 1.0592133854845722e-05, + "loss": 0.3252, + "step": 17318 + }, + { + "epoch": 1.41, + "learning_rate": 1.0591590612777054e-05, + "loss": 0.1515, + "step": 17319 + }, + { + "epoch": 1.41, + "learning_rate": 1.059104737070839e-05, + "loss": 0.5034, + "step": 17320 + }, + { + "epoch": 1.41, + "learning_rate": 1.0590504128639723e-05, + "loss": 0.6076, + "step": 17321 + }, + { + "epoch": 1.41, + "learning_rate": 1.0589960886571059e-05, + "loss": 0.4299, + "step": 17322 + }, + { + "epoch": 1.41, + "learning_rate": 1.0589417644502391e-05, + "loss": 0.2015, + "step": 17323 + }, + { + "epoch": 1.41, + "learning_rate": 1.0588874402433727e-05, + "loss": 0.3792, + "step": 17324 + }, + { + "epoch": 1.41, + "learning_rate": 1.058833116036506e-05, + "loss": 0.3927, + "step": 17325 + }, + { + "epoch": 1.41, + "learning_rate": 1.0587787918296392e-05, + "loss": 0.2461, + "step": 17326 + }, + { + "epoch": 1.41, + "learning_rate": 1.0587244676227728e-05, + "loss": 0.1268, + "step": 17327 + }, + { + "epoch": 1.41, + "learning_rate": 1.058670143415906e-05, + "loss": 0.265, + "step": 17328 + }, + { + "epoch": 1.41, + "learning_rate": 1.0586158192090397e-05, + "loss": 0.4193, + "step": 17329 + }, + { + "epoch": 1.41, + "learning_rate": 1.0585614950021729e-05, + "loss": 0.2529, + "step": 17330 + }, + { + "epoch": 1.41, + "learning_rate": 1.0585071707953065e-05, + "loss": 0.1558, + "step": 17331 + }, + { + "epoch": 1.41, + "learning_rate": 1.0584528465884398e-05, + "loss": 0.1657, + "step": 17332 + }, + { + "epoch": 1.41, + "learning_rate": 1.0583985223815733e-05, + "loss": 0.4308, + "step": 17333 + }, + { + "epoch": 1.41, + "learning_rate": 1.0583441981747066e-05, + "loss": 0.2254, + "step": 17334 + }, + { + "epoch": 1.41, + "learning_rate": 1.0582898739678402e-05, + "loss": 0.3734, + "step": 17335 + }, + { + "epoch": 1.41, + "learning_rate": 1.0582355497609736e-05, + "loss": 0.1903, + "step": 17336 + }, + { + "epoch": 1.41, + "learning_rate": 1.058181225554107e-05, + "loss": 0.5422, + "step": 17337 + }, + { + "epoch": 1.41, + "learning_rate": 1.0581269013472405e-05, + "loss": 0.1449, + "step": 17338 + }, + { + "epoch": 1.41, + "learning_rate": 1.0580725771403739e-05, + "loss": 0.2998, + "step": 17339 + }, + { + "epoch": 1.41, + "learning_rate": 1.0580182529335073e-05, + "loss": 0.4056, + "step": 17340 + }, + { + "epoch": 1.41, + "learning_rate": 1.0579639287266407e-05, + "loss": 0.3752, + "step": 17341 + }, + { + "epoch": 1.41, + "learning_rate": 1.0579096045197742e-05, + "loss": 0.2695, + "step": 17342 + }, + { + "epoch": 1.41, + "learning_rate": 1.0578552803129076e-05, + "loss": 0.2123, + "step": 17343 + }, + { + "epoch": 1.41, + "learning_rate": 1.057800956106041e-05, + "loss": 0.3987, + "step": 17344 + }, + { + "epoch": 1.41, + "learning_rate": 1.0577466318991743e-05, + "loss": 0.7195, + "step": 17345 + }, + { + "epoch": 1.41, + "learning_rate": 1.0576923076923078e-05, + "loss": 0.2674, + "step": 17346 + }, + { + "epoch": 1.41, + "learning_rate": 1.0576379834854411e-05, + "loss": 0.1574, + "step": 17347 + }, + { + "epoch": 1.41, + "learning_rate": 1.0575836592785747e-05, + "loss": 0.2874, + "step": 17348 + }, + { + "epoch": 1.41, + "learning_rate": 1.057529335071708e-05, + "loss": 0.5392, + "step": 17349 + }, + { + "epoch": 1.41, + "learning_rate": 1.0574750108648415e-05, + "loss": 0.4386, + "step": 17350 + }, + { + "epoch": 1.41, + "learning_rate": 1.0574206866579748e-05, + "loss": 0.2673, + "step": 17351 + }, + { + "epoch": 1.41, + "learning_rate": 1.0573663624511084e-05, + "loss": 0.3061, + "step": 17352 + }, + { + "epoch": 1.41, + "learning_rate": 1.0573120382442416e-05, + "loss": 0.3484, + "step": 17353 + }, + { + "epoch": 1.41, + "learning_rate": 1.0572577140373752e-05, + "loss": 0.1687, + "step": 17354 + }, + { + "epoch": 1.41, + "learning_rate": 1.0572033898305085e-05, + "loss": 0.1322, + "step": 17355 + }, + { + "epoch": 1.41, + "learning_rate": 1.057149065623642e-05, + "loss": 0.5802, + "step": 17356 + }, + { + "epoch": 1.41, + "learning_rate": 1.0570947414167753e-05, + "loss": 0.4623, + "step": 17357 + }, + { + "epoch": 1.41, + "learning_rate": 1.057040417209909e-05, + "loss": 0.2234, + "step": 17358 + }, + { + "epoch": 1.41, + "learning_rate": 1.0569860930030422e-05, + "loss": 0.2988, + "step": 17359 + }, + { + "epoch": 1.41, + "learning_rate": 1.0569317687961758e-05, + "loss": 0.2308, + "step": 17360 + }, + { + "epoch": 1.41, + "learning_rate": 1.056877444589309e-05, + "loss": 0.3131, + "step": 17361 + }, + { + "epoch": 1.41, + "learning_rate": 1.0568231203824426e-05, + "loss": 0.1362, + "step": 17362 + }, + { + "epoch": 1.41, + "learning_rate": 1.0567687961755759e-05, + "loss": 0.467, + "step": 17363 + }, + { + "epoch": 1.41, + "learning_rate": 1.0567144719687093e-05, + "loss": 0.278, + "step": 17364 + }, + { + "epoch": 1.42, + "learning_rate": 1.0566601477618427e-05, + "loss": 0.2644, + "step": 17365 + }, + { + "epoch": 1.42, + "learning_rate": 1.0566058235549761e-05, + "loss": 0.3142, + "step": 17366 + }, + { + "epoch": 1.42, + "learning_rate": 1.0565514993481096e-05, + "loss": 0.3339, + "step": 17367 + }, + { + "epoch": 1.42, + "learning_rate": 1.056497175141243e-05, + "loss": 0.5464, + "step": 17368 + }, + { + "epoch": 1.42, + "learning_rate": 1.0564428509343764e-05, + "loss": 0.2813, + "step": 17369 + }, + { + "epoch": 1.42, + "learning_rate": 1.0563885267275098e-05, + "loss": 0.2957, + "step": 17370 + }, + { + "epoch": 1.42, + "learning_rate": 1.0563342025206433e-05, + "loss": 0.2443, + "step": 17371 + }, + { + "epoch": 1.42, + "learning_rate": 1.0562798783137767e-05, + "loss": 0.3921, + "step": 17372 + }, + { + "epoch": 1.42, + "learning_rate": 1.0562255541069103e-05, + "loss": 0.415, + "step": 17373 + }, + { + "epoch": 1.42, + "learning_rate": 1.0561712299000435e-05, + "loss": 0.358, + "step": 17374 + }, + { + "epoch": 1.42, + "learning_rate": 1.0561169056931771e-05, + "loss": 0.3647, + "step": 17375 + }, + { + "epoch": 1.42, + "learning_rate": 1.0560625814863104e-05, + "loss": 0.343, + "step": 17376 + }, + { + "epoch": 1.42, + "learning_rate": 1.056008257279444e-05, + "loss": 0.3097, + "step": 17377 + }, + { + "epoch": 1.42, + "learning_rate": 1.0559539330725772e-05, + "loss": 0.3942, + "step": 17378 + }, + { + "epoch": 1.42, + "learning_rate": 1.0558996088657108e-05, + "loss": 0.5251, + "step": 17379 + }, + { + "epoch": 1.42, + "learning_rate": 1.055845284658844e-05, + "loss": 0.3171, + "step": 17380 + }, + { + "epoch": 1.42, + "learning_rate": 1.0557909604519777e-05, + "loss": 0.4923, + "step": 17381 + }, + { + "epoch": 1.42, + "learning_rate": 1.0557366362451109e-05, + "loss": 0.5788, + "step": 17382 + }, + { + "epoch": 1.42, + "learning_rate": 1.0556823120382442e-05, + "loss": 0.1896, + "step": 17383 + }, + { + "epoch": 1.42, + "learning_rate": 1.0556279878313778e-05, + "loss": 0.3454, + "step": 17384 + }, + { + "epoch": 1.42, + "learning_rate": 1.055573663624511e-05, + "loss": 0.5466, + "step": 17385 + }, + { + "epoch": 1.42, + "learning_rate": 1.0555193394176446e-05, + "loss": 0.5126, + "step": 17386 + }, + { + "epoch": 1.42, + "learning_rate": 1.0554650152107779e-05, + "loss": 0.7518, + "step": 17387 + }, + { + "epoch": 1.42, + "learning_rate": 1.0554106910039114e-05, + "loss": 0.1797, + "step": 17388 + }, + { + "epoch": 1.42, + "learning_rate": 1.0553563667970449e-05, + "loss": 0.2418, + "step": 17389 + }, + { + "epoch": 1.42, + "learning_rate": 1.0553020425901783e-05, + "loss": 0.3172, + "step": 17390 + }, + { + "epoch": 1.42, + "learning_rate": 1.0552477183833117e-05, + "loss": 0.5476, + "step": 17391 + }, + { + "epoch": 1.42, + "learning_rate": 1.0551933941764451e-05, + "loss": 0.6235, + "step": 17392 + }, + { + "epoch": 1.42, + "learning_rate": 1.0551390699695786e-05, + "loss": 0.4345, + "step": 17393 + }, + { + "epoch": 1.42, + "learning_rate": 1.055084745762712e-05, + "loss": 0.3625, + "step": 17394 + }, + { + "epoch": 1.42, + "learning_rate": 1.0550304215558454e-05, + "loss": 0.222, + "step": 17395 + }, + { + "epoch": 1.42, + "learning_rate": 1.0549760973489788e-05, + "loss": 0.3629, + "step": 17396 + }, + { + "epoch": 1.42, + "learning_rate": 1.0549217731421123e-05, + "loss": 0.3541, + "step": 17397 + }, + { + "epoch": 1.42, + "learning_rate": 1.0548674489352457e-05, + "loss": 0.2707, + "step": 17398 + }, + { + "epoch": 1.42, + "learning_rate": 1.0548131247283791e-05, + "loss": 0.3095, + "step": 17399 + }, + { + "epoch": 1.42, + "learning_rate": 1.0547588005215125e-05, + "loss": 0.4283, + "step": 17400 + }, + { + "epoch": 1.42, + "learning_rate": 1.054704476314646e-05, + "loss": 0.3725, + "step": 17401 + }, + { + "epoch": 1.42, + "learning_rate": 1.0546501521077792e-05, + "loss": 0.3282, + "step": 17402 + }, + { + "epoch": 1.42, + "learning_rate": 1.0545958279009128e-05, + "loss": 0.2246, + "step": 17403 + }, + { + "epoch": 1.42, + "learning_rate": 1.054541503694046e-05, + "loss": 0.5461, + "step": 17404 + }, + { + "epoch": 1.42, + "learning_rate": 1.0544871794871796e-05, + "loss": 0.2802, + "step": 17405 + }, + { + "epoch": 1.42, + "learning_rate": 1.0544328552803129e-05, + "loss": 0.2804, + "step": 17406 + }, + { + "epoch": 1.42, + "learning_rate": 1.0543785310734465e-05, + "loss": 0.2578, + "step": 17407 + }, + { + "epoch": 1.42, + "learning_rate": 1.0543242068665797e-05, + "loss": 0.2673, + "step": 17408 + }, + { + "epoch": 1.42, + "learning_rate": 1.0542698826597133e-05, + "loss": 0.4166, + "step": 17409 + }, + { + "epoch": 1.42, + "learning_rate": 1.0542155584528466e-05, + "loss": 0.3756, + "step": 17410 + }, + { + "epoch": 1.42, + "learning_rate": 1.0541612342459802e-05, + "loss": 0.3186, + "step": 17411 + }, + { + "epoch": 1.42, + "learning_rate": 1.0541069100391134e-05, + "loss": 0.3163, + "step": 17412 + }, + { + "epoch": 1.42, + "learning_rate": 1.054052585832247e-05, + "loss": 0.2112, + "step": 17413 + }, + { + "epoch": 1.42, + "learning_rate": 1.0539982616253803e-05, + "loss": 0.4385, + "step": 17414 + }, + { + "epoch": 1.42, + "learning_rate": 1.0539439374185139e-05, + "loss": 0.2071, + "step": 17415 + }, + { + "epoch": 1.42, + "learning_rate": 1.0538896132116471e-05, + "loss": 0.3062, + "step": 17416 + }, + { + "epoch": 1.42, + "learning_rate": 1.0538352890047807e-05, + "loss": 0.3612, + "step": 17417 + }, + { + "epoch": 1.42, + "learning_rate": 1.053780964797914e-05, + "loss": 0.3799, + "step": 17418 + }, + { + "epoch": 1.42, + "learning_rate": 1.0537266405910476e-05, + "loss": 0.1477, + "step": 17419 + }, + { + "epoch": 1.42, + "learning_rate": 1.0536723163841808e-05, + "loss": 0.4828, + "step": 17420 + }, + { + "epoch": 1.42, + "learning_rate": 1.0536179921773142e-05, + "loss": 0.4878, + "step": 17421 + }, + { + "epoch": 1.42, + "learning_rate": 1.0535636679704477e-05, + "loss": 0.5092, + "step": 17422 + }, + { + "epoch": 1.42, + "learning_rate": 1.053509343763581e-05, + "loss": 0.2236, + "step": 17423 + }, + { + "epoch": 1.42, + "learning_rate": 1.0534550195567145e-05, + "loss": 0.4961, + "step": 17424 + }, + { + "epoch": 1.42, + "learning_rate": 1.053400695349848e-05, + "loss": 0.2659, + "step": 17425 + }, + { + "epoch": 1.42, + "learning_rate": 1.0533463711429815e-05, + "loss": 0.5118, + "step": 17426 + }, + { + "epoch": 1.42, + "learning_rate": 1.0532920469361148e-05, + "loss": 0.4403, + "step": 17427 + }, + { + "epoch": 1.42, + "learning_rate": 1.0532377227292484e-05, + "loss": 0.2207, + "step": 17428 + }, + { + "epoch": 1.42, + "learning_rate": 1.0531833985223816e-05, + "loss": 0.4956, + "step": 17429 + }, + { + "epoch": 1.42, + "learning_rate": 1.0531290743155152e-05, + "loss": 0.349, + "step": 17430 + }, + { + "epoch": 1.42, + "learning_rate": 1.0530747501086485e-05, + "loss": 0.2637, + "step": 17431 + }, + { + "epoch": 1.42, + "learning_rate": 1.053020425901782e-05, + "loss": 0.2877, + "step": 17432 + }, + { + "epoch": 1.42, + "learning_rate": 1.0529661016949153e-05, + "loss": 0.6379, + "step": 17433 + }, + { + "epoch": 1.42, + "learning_rate": 1.0529117774880489e-05, + "loss": 0.5048, + "step": 17434 + }, + { + "epoch": 1.42, + "learning_rate": 1.0528574532811822e-05, + "loss": 0.2086, + "step": 17435 + }, + { + "epoch": 1.42, + "learning_rate": 1.0528031290743158e-05, + "loss": 0.2962, + "step": 17436 + }, + { + "epoch": 1.42, + "learning_rate": 1.052748804867449e-05, + "loss": 0.1183, + "step": 17437 + }, + { + "epoch": 1.42, + "learning_rate": 1.0526944806605826e-05, + "loss": 0.2788, + "step": 17438 + }, + { + "epoch": 1.42, + "learning_rate": 1.0526401564537159e-05, + "loss": 0.3584, + "step": 17439 + }, + { + "epoch": 1.42, + "learning_rate": 1.0525858322468491e-05, + "loss": 0.518, + "step": 17440 + }, + { + "epoch": 1.42, + "learning_rate": 1.0525315080399827e-05, + "loss": 0.3515, + "step": 17441 + }, + { + "epoch": 1.42, + "learning_rate": 1.052477183833116e-05, + "loss": 0.4134, + "step": 17442 + }, + { + "epoch": 1.42, + "learning_rate": 1.0524228596262495e-05, + "loss": 0.2859, + "step": 17443 + }, + { + "epoch": 1.42, + "learning_rate": 1.052368535419383e-05, + "loss": 0.402, + "step": 17444 + }, + { + "epoch": 1.42, + "learning_rate": 1.0523142112125164e-05, + "loss": 0.353, + "step": 17445 + }, + { + "epoch": 1.42, + "learning_rate": 1.0522598870056498e-05, + "loss": 0.4186, + "step": 17446 + }, + { + "epoch": 1.42, + "learning_rate": 1.0522055627987832e-05, + "loss": 0.2575, + "step": 17447 + }, + { + "epoch": 1.42, + "learning_rate": 1.0521512385919167e-05, + "loss": 0.4685, + "step": 17448 + }, + { + "epoch": 1.42, + "learning_rate": 1.05209691438505e-05, + "loss": 0.3557, + "step": 17449 + }, + { + "epoch": 1.42, + "learning_rate": 1.0520425901781835e-05, + "loss": 0.1925, + "step": 17450 + }, + { + "epoch": 1.42, + "learning_rate": 1.051988265971317e-05, + "loss": 0.2992, + "step": 17451 + }, + { + "epoch": 1.42, + "learning_rate": 1.0519339417644504e-05, + "loss": 0.3533, + "step": 17452 + }, + { + "epoch": 1.42, + "learning_rate": 1.0518796175575838e-05, + "loss": 0.3757, + "step": 17453 + }, + { + "epoch": 1.42, + "learning_rate": 1.0518252933507172e-05, + "loss": 0.2209, + "step": 17454 + }, + { + "epoch": 1.42, + "learning_rate": 1.0517709691438506e-05, + "loss": 0.4313, + "step": 17455 + }, + { + "epoch": 1.42, + "learning_rate": 1.051716644936984e-05, + "loss": 0.3882, + "step": 17456 + }, + { + "epoch": 1.42, + "learning_rate": 1.0516623207301175e-05, + "loss": 0.0917, + "step": 17457 + }, + { + "epoch": 1.42, + "learning_rate": 1.0516079965232509e-05, + "loss": 0.1826, + "step": 17458 + }, + { + "epoch": 1.42, + "learning_rate": 1.0515536723163841e-05, + "loss": 0.7301, + "step": 17459 + }, + { + "epoch": 1.42, + "learning_rate": 1.0514993481095177e-05, + "loss": 0.1323, + "step": 17460 + }, + { + "epoch": 1.42, + "learning_rate": 1.051445023902651e-05, + "loss": 0.2545, + "step": 17461 + }, + { + "epoch": 1.42, + "learning_rate": 1.0513906996957846e-05, + "loss": 0.2794, + "step": 17462 + }, + { + "epoch": 1.42, + "learning_rate": 1.0513363754889178e-05, + "loss": 0.2874, + "step": 17463 + }, + { + "epoch": 1.42, + "learning_rate": 1.0512820512820514e-05, + "loss": 0.323, + "step": 17464 + }, + { + "epoch": 1.42, + "learning_rate": 1.0512277270751847e-05, + "loss": 0.3207, + "step": 17465 + }, + { + "epoch": 1.42, + "learning_rate": 1.0511734028683183e-05, + "loss": 0.2348, + "step": 17466 + }, + { + "epoch": 1.42, + "learning_rate": 1.0511190786614515e-05, + "loss": 0.3265, + "step": 17467 + }, + { + "epoch": 1.42, + "learning_rate": 1.0510647544545851e-05, + "loss": 0.3647, + "step": 17468 + }, + { + "epoch": 1.42, + "learning_rate": 1.0510104302477184e-05, + "loss": 0.2262, + "step": 17469 + }, + { + "epoch": 1.42, + "learning_rate": 1.050956106040852e-05, + "loss": 0.4319, + "step": 17470 + }, + { + "epoch": 1.42, + "learning_rate": 1.0509017818339852e-05, + "loss": 0.3242, + "step": 17471 + }, + { + "epoch": 1.42, + "learning_rate": 1.0508474576271188e-05, + "loss": 0.4443, + "step": 17472 + }, + { + "epoch": 1.42, + "learning_rate": 1.050793133420252e-05, + "loss": 0.2604, + "step": 17473 + }, + { + "epoch": 1.42, + "learning_rate": 1.0507388092133857e-05, + "loss": 0.4192, + "step": 17474 + }, + { + "epoch": 1.42, + "learning_rate": 1.0506844850065189e-05, + "loss": 0.1823, + "step": 17475 + }, + { + "epoch": 1.42, + "learning_rate": 1.0506301607996525e-05, + "loss": 0.314, + "step": 17476 + }, + { + "epoch": 1.42, + "learning_rate": 1.0505758365927858e-05, + "loss": 0.3222, + "step": 17477 + }, + { + "epoch": 1.42, + "learning_rate": 1.0505215123859192e-05, + "loss": 0.5525, + "step": 17478 + }, + { + "epoch": 1.42, + "learning_rate": 1.0504671881790526e-05, + "loss": 0.253, + "step": 17479 + }, + { + "epoch": 1.42, + "learning_rate": 1.050412863972186e-05, + "loss": 0.2326, + "step": 17480 + }, + { + "epoch": 1.42, + "learning_rate": 1.0503585397653196e-05, + "loss": 0.434, + "step": 17481 + }, + { + "epoch": 1.42, + "learning_rate": 1.0503042155584529e-05, + "loss": 0.3147, + "step": 17482 + }, + { + "epoch": 1.42, + "learning_rate": 1.0502498913515865e-05, + "loss": 0.344, + "step": 17483 + }, + { + "epoch": 1.42, + "learning_rate": 1.0501955671447197e-05, + "loss": 0.2677, + "step": 17484 + }, + { + "epoch": 1.42, + "learning_rate": 1.0501412429378533e-05, + "loss": 0.3096, + "step": 17485 + }, + { + "epoch": 1.42, + "learning_rate": 1.0500869187309866e-05, + "loss": 0.5801, + "step": 17486 + }, + { + "epoch": 1.42, + "learning_rate": 1.0500325945241202e-05, + "loss": 0.223, + "step": 17487 + }, + { + "epoch": 1.43, + "learning_rate": 1.0499782703172534e-05, + "loss": 0.3972, + "step": 17488 + }, + { + "epoch": 1.43, + "learning_rate": 1.049923946110387e-05, + "loss": 0.4857, + "step": 17489 + }, + { + "epoch": 1.43, + "learning_rate": 1.0498696219035203e-05, + "loss": 0.135, + "step": 17490 + }, + { + "epoch": 1.43, + "learning_rate": 1.0498152976966539e-05, + "loss": 0.3671, + "step": 17491 + }, + { + "epoch": 1.43, + "learning_rate": 1.0497609734897871e-05, + "loss": 0.3475, + "step": 17492 + }, + { + "epoch": 1.43, + "learning_rate": 1.0497066492829207e-05, + "loss": 0.4266, + "step": 17493 + }, + { + "epoch": 1.43, + "learning_rate": 1.049652325076054e-05, + "loss": 0.264, + "step": 17494 + }, + { + "epoch": 1.43, + "learning_rate": 1.0495980008691875e-05, + "loss": 0.7252, + "step": 17495 + }, + { + "epoch": 1.43, + "learning_rate": 1.0495436766623208e-05, + "loss": 0.6894, + "step": 17496 + }, + { + "epoch": 1.43, + "learning_rate": 1.0494893524554542e-05, + "loss": 0.3539, + "step": 17497 + }, + { + "epoch": 1.43, + "learning_rate": 1.0494350282485876e-05, + "loss": 0.5819, + "step": 17498 + }, + { + "epoch": 1.43, + "learning_rate": 1.049380704041721e-05, + "loss": 0.3432, + "step": 17499 + }, + { + "epoch": 1.43, + "learning_rate": 1.0493263798348545e-05, + "loss": 0.278, + "step": 17500 + }, + { + "epoch": 1.43, + "eval_accuracy": 0.8370860927152318, + "eval_loss": 0.4455227255821228, + "eval_runtime": 22.2834, + "eval_samples_per_second": 440.463, + "eval_steps_per_second": 3.455, + "step": 17500 + }, + { + "epoch": 1.43, + "learning_rate": 1.0492720556279879e-05, + "loss": 0.3535, + "step": 17501 + }, + { + "epoch": 1.43, + "learning_rate": 1.0492177314211213e-05, + "loss": 0.2174, + "step": 17502 + }, + { + "epoch": 1.43, + "learning_rate": 1.0491634072142548e-05, + "loss": 0.2299, + "step": 17503 + }, + { + "epoch": 1.43, + "learning_rate": 1.0491090830073882e-05, + "loss": 0.1755, + "step": 17504 + }, + { + "epoch": 1.43, + "learning_rate": 1.0490547588005216e-05, + "loss": 0.1882, + "step": 17505 + }, + { + "epoch": 1.43, + "learning_rate": 1.049000434593655e-05, + "loss": 0.1594, + "step": 17506 + }, + { + "epoch": 1.43, + "learning_rate": 1.0489461103867885e-05, + "loss": 0.2556, + "step": 17507 + }, + { + "epoch": 1.43, + "learning_rate": 1.0488917861799219e-05, + "loss": 0.3065, + "step": 17508 + }, + { + "epoch": 1.43, + "learning_rate": 1.0488374619730553e-05, + "loss": 0.3255, + "step": 17509 + }, + { + "epoch": 1.43, + "learning_rate": 1.0487831377661887e-05, + "loss": 0.2244, + "step": 17510 + }, + { + "epoch": 1.43, + "learning_rate": 1.0487288135593221e-05, + "loss": 0.3484, + "step": 17511 + }, + { + "epoch": 1.43, + "learning_rate": 1.0486744893524556e-05, + "loss": 0.3335, + "step": 17512 + }, + { + "epoch": 1.43, + "learning_rate": 1.048620165145589e-05, + "loss": 0.3829, + "step": 17513 + }, + { + "epoch": 1.43, + "learning_rate": 1.0485658409387224e-05, + "loss": 0.2797, + "step": 17514 + }, + { + "epoch": 1.43, + "learning_rate": 1.0485115167318558e-05, + "loss": 0.3169, + "step": 17515 + }, + { + "epoch": 1.43, + "learning_rate": 1.0484571925249891e-05, + "loss": 0.1163, + "step": 17516 + }, + { + "epoch": 1.43, + "learning_rate": 1.0484028683181227e-05, + "loss": 0.1959, + "step": 17517 + }, + { + "epoch": 1.43, + "learning_rate": 1.048348544111256e-05, + "loss": 0.2951, + "step": 17518 + }, + { + "epoch": 1.43, + "learning_rate": 1.0482942199043895e-05, + "loss": 0.4016, + "step": 17519 + }, + { + "epoch": 1.43, + "learning_rate": 1.0482398956975228e-05, + "loss": 0.1917, + "step": 17520 + }, + { + "epoch": 1.43, + "learning_rate": 1.0481855714906564e-05, + "loss": 0.445, + "step": 17521 + }, + { + "epoch": 1.43, + "learning_rate": 1.0481312472837896e-05, + "loss": 0.2918, + "step": 17522 + }, + { + "epoch": 1.43, + "learning_rate": 1.0480769230769232e-05, + "loss": 0.3374, + "step": 17523 + }, + { + "epoch": 1.43, + "learning_rate": 1.0480225988700565e-05, + "loss": 0.3621, + "step": 17524 + }, + { + "epoch": 1.43, + "learning_rate": 1.04796827466319e-05, + "loss": 0.397, + "step": 17525 + }, + { + "epoch": 1.43, + "learning_rate": 1.0479139504563233e-05, + "loss": 0.4218, + "step": 17526 + }, + { + "epoch": 1.43, + "learning_rate": 1.0478596262494569e-05, + "loss": 0.3917, + "step": 17527 + }, + { + "epoch": 1.43, + "learning_rate": 1.0478053020425902e-05, + "loss": 0.1744, + "step": 17528 + }, + { + "epoch": 1.43, + "learning_rate": 1.0477509778357238e-05, + "loss": 0.2929, + "step": 17529 + }, + { + "epoch": 1.43, + "learning_rate": 1.047696653628857e-05, + "loss": 0.3192, + "step": 17530 + }, + { + "epoch": 1.43, + "learning_rate": 1.0476423294219906e-05, + "loss": 0.3951, + "step": 17531 + }, + { + "epoch": 1.43, + "learning_rate": 1.0475880052151239e-05, + "loss": 0.2364, + "step": 17532 + }, + { + "epoch": 1.43, + "learning_rate": 1.0475336810082575e-05, + "loss": 0.4745, + "step": 17533 + }, + { + "epoch": 1.43, + "learning_rate": 1.0474793568013909e-05, + "loss": 0.2916, + "step": 17534 + }, + { + "epoch": 1.43, + "learning_rate": 1.0474250325945241e-05, + "loss": 0.5124, + "step": 17535 + }, + { + "epoch": 1.43, + "learning_rate": 1.0473707083876577e-05, + "loss": 0.2335, + "step": 17536 + }, + { + "epoch": 1.43, + "learning_rate": 1.047316384180791e-05, + "loss": 0.3413, + "step": 17537 + }, + { + "epoch": 1.43, + "learning_rate": 1.0472620599739246e-05, + "loss": 0.3007, + "step": 17538 + }, + { + "epoch": 1.43, + "learning_rate": 1.0472077357670578e-05, + "loss": 0.2214, + "step": 17539 + }, + { + "epoch": 1.43, + "learning_rate": 1.0471534115601914e-05, + "loss": 0.4561, + "step": 17540 + }, + { + "epoch": 1.43, + "learning_rate": 1.0470990873533247e-05, + "loss": 0.2791, + "step": 17541 + }, + { + "epoch": 1.43, + "learning_rate": 1.0470447631464583e-05, + "loss": 0.2468, + "step": 17542 + }, + { + "epoch": 1.43, + "learning_rate": 1.0469904389395915e-05, + "loss": 0.3904, + "step": 17543 + }, + { + "epoch": 1.43, + "learning_rate": 1.0469361147327251e-05, + "loss": 0.1471, + "step": 17544 + }, + { + "epoch": 1.43, + "learning_rate": 1.0468817905258584e-05, + "loss": 0.4096, + "step": 17545 + }, + { + "epoch": 1.43, + "learning_rate": 1.046827466318992e-05, + "loss": 0.1575, + "step": 17546 + }, + { + "epoch": 1.43, + "learning_rate": 1.0467731421121252e-05, + "loss": 0.4249, + "step": 17547 + }, + { + "epoch": 1.43, + "learning_rate": 1.0467188179052588e-05, + "loss": 0.4944, + "step": 17548 + }, + { + "epoch": 1.43, + "learning_rate": 1.046664493698392e-05, + "loss": 0.2418, + "step": 17549 + }, + { + "epoch": 1.43, + "learning_rate": 1.0466101694915256e-05, + "loss": 0.2218, + "step": 17550 + }, + { + "epoch": 1.43, + "learning_rate": 1.0465558452846589e-05, + "loss": 0.1729, + "step": 17551 + }, + { + "epoch": 1.43, + "learning_rate": 1.0465015210777925e-05, + "loss": 0.4939, + "step": 17552 + }, + { + "epoch": 1.43, + "learning_rate": 1.0464471968709257e-05, + "loss": 0.3316, + "step": 17553 + }, + { + "epoch": 1.43, + "learning_rate": 1.0463928726640592e-05, + "loss": 0.5234, + "step": 17554 + }, + { + "epoch": 1.43, + "learning_rate": 1.0463385484571926e-05, + "loss": 0.208, + "step": 17555 + }, + { + "epoch": 1.43, + "learning_rate": 1.046284224250326e-05, + "loss": 0.4348, + "step": 17556 + }, + { + "epoch": 1.43, + "learning_rate": 1.0462299000434594e-05, + "loss": 0.297, + "step": 17557 + }, + { + "epoch": 1.43, + "learning_rate": 1.0461755758365929e-05, + "loss": 0.38, + "step": 17558 + }, + { + "epoch": 1.43, + "learning_rate": 1.0461212516297263e-05, + "loss": 0.4306, + "step": 17559 + }, + { + "epoch": 1.43, + "learning_rate": 1.0460669274228597e-05, + "loss": 0.2293, + "step": 17560 + }, + { + "epoch": 1.43, + "learning_rate": 1.0460126032159931e-05, + "loss": 0.2541, + "step": 17561 + }, + { + "epoch": 1.43, + "learning_rate": 1.0459582790091265e-05, + "loss": 0.4129, + "step": 17562 + }, + { + "epoch": 1.43, + "learning_rate": 1.04590395480226e-05, + "loss": 0.1824, + "step": 17563 + }, + { + "epoch": 1.43, + "learning_rate": 1.0458496305953934e-05, + "loss": 0.2433, + "step": 17564 + }, + { + "epoch": 1.43, + "learning_rate": 1.0457953063885268e-05, + "loss": 0.6406, + "step": 17565 + }, + { + "epoch": 1.43, + "learning_rate": 1.0457409821816602e-05, + "loss": 0.1963, + "step": 17566 + }, + { + "epoch": 1.43, + "learning_rate": 1.0456866579747937e-05, + "loss": 0.2722, + "step": 17567 + }, + { + "epoch": 1.43, + "learning_rate": 1.0456323337679271e-05, + "loss": 0.3604, + "step": 17568 + }, + { + "epoch": 1.43, + "learning_rate": 1.0455780095610605e-05, + "loss": 0.1946, + "step": 17569 + }, + { + "epoch": 1.43, + "learning_rate": 1.045523685354194e-05, + "loss": 0.4913, + "step": 17570 + }, + { + "epoch": 1.43, + "learning_rate": 1.0454693611473275e-05, + "loss": 0.3819, + "step": 17571 + }, + { + "epoch": 1.43, + "learning_rate": 1.0454150369404608e-05, + "loss": 0.1399, + "step": 17572 + }, + { + "epoch": 1.43, + "learning_rate": 1.045360712733594e-05, + "loss": 0.2483, + "step": 17573 + }, + { + "epoch": 1.43, + "learning_rate": 1.0453063885267276e-05, + "loss": 0.3782, + "step": 17574 + }, + { + "epoch": 1.43, + "learning_rate": 1.0452520643198609e-05, + "loss": 0.5124, + "step": 17575 + }, + { + "epoch": 1.43, + "learning_rate": 1.0451977401129945e-05, + "loss": 0.2488, + "step": 17576 + }, + { + "epoch": 1.43, + "learning_rate": 1.0451434159061277e-05, + "loss": 0.0461, + "step": 17577 + }, + { + "epoch": 1.43, + "learning_rate": 1.0450890916992613e-05, + "loss": 0.5475, + "step": 17578 + }, + { + "epoch": 1.43, + "learning_rate": 1.0450347674923946e-05, + "loss": 0.3049, + "step": 17579 + }, + { + "epoch": 1.43, + "learning_rate": 1.0449804432855282e-05, + "loss": 0.2584, + "step": 17580 + }, + { + "epoch": 1.43, + "learning_rate": 1.0449261190786614e-05, + "loss": 0.194, + "step": 17581 + }, + { + "epoch": 1.43, + "learning_rate": 1.044871794871795e-05, + "loss": 0.379, + "step": 17582 + }, + { + "epoch": 1.43, + "learning_rate": 1.0448174706649283e-05, + "loss": 0.7433, + "step": 17583 + }, + { + "epoch": 1.43, + "learning_rate": 1.0447631464580619e-05, + "loss": 0.3449, + "step": 17584 + }, + { + "epoch": 1.43, + "learning_rate": 1.0447088222511951e-05, + "loss": 0.3655, + "step": 17585 + }, + { + "epoch": 1.43, + "learning_rate": 1.0446544980443287e-05, + "loss": 0.2605, + "step": 17586 + }, + { + "epoch": 1.43, + "learning_rate": 1.044600173837462e-05, + "loss": 0.5942, + "step": 17587 + }, + { + "epoch": 1.43, + "learning_rate": 1.0445458496305955e-05, + "loss": 0.2616, + "step": 17588 + }, + { + "epoch": 1.43, + "learning_rate": 1.044491525423729e-05, + "loss": 0.3011, + "step": 17589 + }, + { + "epoch": 1.43, + "learning_rate": 1.0444372012168624e-05, + "loss": 0.3203, + "step": 17590 + }, + { + "epoch": 1.43, + "learning_rate": 1.0443828770099958e-05, + "loss": 0.3648, + "step": 17591 + }, + { + "epoch": 1.43, + "learning_rate": 1.044328552803129e-05, + "loss": 0.4463, + "step": 17592 + }, + { + "epoch": 1.43, + "learning_rate": 1.0442742285962627e-05, + "loss": 0.3573, + "step": 17593 + }, + { + "epoch": 1.43, + "learning_rate": 1.044219904389396e-05, + "loss": 0.3604, + "step": 17594 + }, + { + "epoch": 1.43, + "learning_rate": 1.0441655801825295e-05, + "loss": 0.2374, + "step": 17595 + }, + { + "epoch": 1.43, + "learning_rate": 1.0441112559756628e-05, + "loss": 0.2685, + "step": 17596 + }, + { + "epoch": 1.43, + "learning_rate": 1.0440569317687964e-05, + "loss": 0.2241, + "step": 17597 + }, + { + "epoch": 1.43, + "learning_rate": 1.0440026075619296e-05, + "loss": 0.3971, + "step": 17598 + }, + { + "epoch": 1.43, + "learning_rate": 1.0439482833550632e-05, + "loss": 0.418, + "step": 17599 + }, + { + "epoch": 1.43, + "learning_rate": 1.0438939591481965e-05, + "loss": 0.2552, + "step": 17600 + }, + { + "epoch": 1.43, + "learning_rate": 1.04383963494133e-05, + "loss": 0.2831, + "step": 17601 + }, + { + "epoch": 1.43, + "learning_rate": 1.0437853107344633e-05, + "loss": 0.5016, + "step": 17602 + }, + { + "epoch": 1.43, + "learning_rate": 1.0437309865275969e-05, + "loss": 0.172, + "step": 17603 + }, + { + "epoch": 1.43, + "learning_rate": 1.0436766623207301e-05, + "loss": 0.4574, + "step": 17604 + }, + { + "epoch": 1.43, + "learning_rate": 1.0436223381138637e-05, + "loss": 0.4579, + "step": 17605 + }, + { + "epoch": 1.43, + "learning_rate": 1.043568013906997e-05, + "loss": 0.4111, + "step": 17606 + }, + { + "epoch": 1.43, + "learning_rate": 1.0435136897001306e-05, + "loss": 0.2458, + "step": 17607 + }, + { + "epoch": 1.43, + "learning_rate": 1.0434593654932638e-05, + "loss": 0.4404, + "step": 17608 + }, + { + "epoch": 1.43, + "learning_rate": 1.0434050412863974e-05, + "loss": 0.277, + "step": 17609 + }, + { + "epoch": 1.43, + "learning_rate": 1.0433507170795307e-05, + "loss": 0.3848, + "step": 17610 + }, + { + "epoch": 1.44, + "learning_rate": 1.0432963928726641e-05, + "loss": 0.2771, + "step": 17611 + }, + { + "epoch": 1.44, + "learning_rate": 1.0432420686657975e-05, + "loss": 0.314, + "step": 17612 + }, + { + "epoch": 1.44, + "learning_rate": 1.043187744458931e-05, + "loss": 0.2386, + "step": 17613 + }, + { + "epoch": 1.44, + "learning_rate": 1.0431334202520644e-05, + "loss": 0.2891, + "step": 17614 + }, + { + "epoch": 1.44, + "learning_rate": 1.0430790960451978e-05, + "loss": 0.2061, + "step": 17615 + }, + { + "epoch": 1.44, + "learning_rate": 1.0430247718383312e-05, + "loss": 0.1692, + "step": 17616 + }, + { + "epoch": 1.44, + "learning_rate": 1.0429704476314646e-05, + "loss": 0.1577, + "step": 17617 + }, + { + "epoch": 1.44, + "learning_rate": 1.042916123424598e-05, + "loss": 0.4638, + "step": 17618 + }, + { + "epoch": 1.44, + "learning_rate": 1.0428617992177315e-05, + "loss": 0.4766, + "step": 17619 + }, + { + "epoch": 1.44, + "learning_rate": 1.042807475010865e-05, + "loss": 0.3057, + "step": 17620 + }, + { + "epoch": 1.44, + "learning_rate": 1.0427531508039983e-05, + "loss": 0.3145, + "step": 17621 + }, + { + "epoch": 1.44, + "learning_rate": 1.0426988265971318e-05, + "loss": 0.2544, + "step": 17622 + }, + { + "epoch": 1.44, + "learning_rate": 1.0426445023902652e-05, + "loss": 0.4056, + "step": 17623 + }, + { + "epoch": 1.44, + "learning_rate": 1.0425901781833986e-05, + "loss": 0.1643, + "step": 17624 + }, + { + "epoch": 1.44, + "learning_rate": 1.042535853976532e-05, + "loss": 0.4487, + "step": 17625 + }, + { + "epoch": 1.44, + "learning_rate": 1.0424815297696656e-05, + "loss": 0.3955, + "step": 17626 + }, + { + "epoch": 1.44, + "learning_rate": 1.0424272055627989e-05, + "loss": 0.3333, + "step": 17627 + }, + { + "epoch": 1.44, + "learning_rate": 1.0423728813559325e-05, + "loss": 0.1734, + "step": 17628 + }, + { + "epoch": 1.44, + "learning_rate": 1.0423185571490657e-05, + "loss": 0.279, + "step": 17629 + }, + { + "epoch": 1.44, + "learning_rate": 1.042264232942199e-05, + "loss": 0.1882, + "step": 17630 + }, + { + "epoch": 1.44, + "learning_rate": 1.0422099087353326e-05, + "loss": 0.4396, + "step": 17631 + }, + { + "epoch": 1.44, + "learning_rate": 1.0421555845284658e-05, + "loss": 0.4792, + "step": 17632 + }, + { + "epoch": 1.44, + "learning_rate": 1.0421012603215994e-05, + "loss": 0.4007, + "step": 17633 + }, + { + "epoch": 1.44, + "learning_rate": 1.0420469361147327e-05, + "loss": 0.1951, + "step": 17634 + }, + { + "epoch": 1.44, + "learning_rate": 1.0419926119078663e-05, + "loss": 0.4076, + "step": 17635 + }, + { + "epoch": 1.44, + "learning_rate": 1.0419382877009995e-05, + "loss": 0.5832, + "step": 17636 + }, + { + "epoch": 1.44, + "learning_rate": 1.0418839634941331e-05, + "loss": 0.2731, + "step": 17637 + }, + { + "epoch": 1.44, + "learning_rate": 1.0418296392872664e-05, + "loss": 0.5111, + "step": 17638 + }, + { + "epoch": 1.44, + "learning_rate": 1.0417753150804e-05, + "loss": 0.8707, + "step": 17639 + }, + { + "epoch": 1.44, + "learning_rate": 1.0417209908735332e-05, + "loss": 0.1927, + "step": 17640 + }, + { + "epoch": 1.44, + "learning_rate": 1.0416666666666668e-05, + "loss": 0.2727, + "step": 17641 + }, + { + "epoch": 1.44, + "learning_rate": 1.0416123424598002e-05, + "loss": 0.2777, + "step": 17642 + }, + { + "epoch": 1.44, + "learning_rate": 1.0415580182529336e-05, + "loss": 0.1913, + "step": 17643 + }, + { + "epoch": 1.44, + "learning_rate": 1.041503694046067e-05, + "loss": 0.3128, + "step": 17644 + }, + { + "epoch": 1.44, + "learning_rate": 1.0414493698392005e-05, + "loss": 0.2187, + "step": 17645 + }, + { + "epoch": 1.44, + "learning_rate": 1.041395045632334e-05, + "loss": 0.3502, + "step": 17646 + }, + { + "epoch": 1.44, + "learning_rate": 1.0413407214254673e-05, + "loss": 0.181, + "step": 17647 + }, + { + "epoch": 1.44, + "learning_rate": 1.0412863972186008e-05, + "loss": 0.297, + "step": 17648 + }, + { + "epoch": 1.44, + "learning_rate": 1.041232073011734e-05, + "loss": 0.3597, + "step": 17649 + }, + { + "epoch": 1.44, + "learning_rate": 1.0411777488048676e-05, + "loss": 0.2817, + "step": 17650 + }, + { + "epoch": 1.44, + "learning_rate": 1.0411234245980009e-05, + "loss": 0.5433, + "step": 17651 + }, + { + "epoch": 1.44, + "learning_rate": 1.0410691003911345e-05, + "loss": 0.3879, + "step": 17652 + }, + { + "epoch": 1.44, + "learning_rate": 1.0410147761842677e-05, + "loss": 0.1717, + "step": 17653 + }, + { + "epoch": 1.44, + "learning_rate": 1.0409604519774013e-05, + "loss": 0.6875, + "step": 17654 + }, + { + "epoch": 1.44, + "learning_rate": 1.0409061277705346e-05, + "loss": 0.3883, + "step": 17655 + }, + { + "epoch": 1.44, + "learning_rate": 1.0408518035636681e-05, + "loss": 0.3153, + "step": 17656 + }, + { + "epoch": 1.44, + "learning_rate": 1.0407974793568014e-05, + "loss": 0.3417, + "step": 17657 + }, + { + "epoch": 1.44, + "learning_rate": 1.040743155149935e-05, + "loss": 0.6569, + "step": 17658 + }, + { + "epoch": 1.44, + "learning_rate": 1.0406888309430682e-05, + "loss": 0.3602, + "step": 17659 + }, + { + "epoch": 1.44, + "learning_rate": 1.0406345067362018e-05, + "loss": 0.3436, + "step": 17660 + }, + { + "epoch": 1.44, + "learning_rate": 1.0405801825293351e-05, + "loss": 0.4625, + "step": 17661 + }, + { + "epoch": 1.44, + "learning_rate": 1.0405258583224687e-05, + "loss": 0.3979, + "step": 17662 + }, + { + "epoch": 1.44, + "learning_rate": 1.040471534115602e-05, + "loss": 0.5179, + "step": 17663 + }, + { + "epoch": 1.44, + "learning_rate": 1.0404172099087355e-05, + "loss": 0.2115, + "step": 17664 + }, + { + "epoch": 1.44, + "learning_rate": 1.0403628857018688e-05, + "loss": 0.4064, + "step": 17665 + }, + { + "epoch": 1.44, + "learning_rate": 1.0403085614950024e-05, + "loss": 0.4272, + "step": 17666 + }, + { + "epoch": 1.44, + "learning_rate": 1.0402542372881356e-05, + "loss": 0.3338, + "step": 17667 + }, + { + "epoch": 1.44, + "learning_rate": 1.040199913081269e-05, + "loss": 0.459, + "step": 17668 + }, + { + "epoch": 1.44, + "learning_rate": 1.0401455888744025e-05, + "loss": 0.259, + "step": 17669 + }, + { + "epoch": 1.44, + "learning_rate": 1.0400912646675359e-05, + "loss": 0.4525, + "step": 17670 + }, + { + "epoch": 1.44, + "learning_rate": 1.0400369404606693e-05, + "loss": 0.2025, + "step": 17671 + }, + { + "epoch": 1.44, + "learning_rate": 1.0399826162538027e-05, + "loss": 0.1507, + "step": 17672 + }, + { + "epoch": 1.44, + "learning_rate": 1.0399282920469362e-05, + "loss": 0.1986, + "step": 17673 + }, + { + "epoch": 1.44, + "learning_rate": 1.0398739678400696e-05, + "loss": 0.1858, + "step": 17674 + }, + { + "epoch": 1.44, + "learning_rate": 1.039819643633203e-05, + "loss": 0.2087, + "step": 17675 + }, + { + "epoch": 1.44, + "learning_rate": 1.0397653194263364e-05, + "loss": 0.32, + "step": 17676 + }, + { + "epoch": 1.44, + "learning_rate": 1.0397109952194699e-05, + "loss": 0.2931, + "step": 17677 + }, + { + "epoch": 1.44, + "learning_rate": 1.0396566710126033e-05, + "loss": 0.2338, + "step": 17678 + }, + { + "epoch": 1.44, + "learning_rate": 1.0396023468057369e-05, + "loss": 0.2722, + "step": 17679 + }, + { + "epoch": 1.44, + "learning_rate": 1.0395480225988701e-05, + "loss": 0.4129, + "step": 17680 + }, + { + "epoch": 1.44, + "learning_rate": 1.0394936983920037e-05, + "loss": 0.3196, + "step": 17681 + }, + { + "epoch": 1.44, + "learning_rate": 1.039439374185137e-05, + "loss": 0.2197, + "step": 17682 + }, + { + "epoch": 1.44, + "learning_rate": 1.0393850499782706e-05, + "loss": 0.1864, + "step": 17683 + }, + { + "epoch": 1.44, + "learning_rate": 1.0393307257714038e-05, + "loss": 0.1883, + "step": 17684 + }, + { + "epoch": 1.44, + "learning_rate": 1.0392764015645374e-05, + "loss": 0.3579, + "step": 17685 + }, + { + "epoch": 1.44, + "learning_rate": 1.0392220773576707e-05, + "loss": 0.2847, + "step": 17686 + }, + { + "epoch": 1.44, + "learning_rate": 1.039167753150804e-05, + "loss": 0.1046, + "step": 17687 + }, + { + "epoch": 1.44, + "learning_rate": 1.0391134289439375e-05, + "loss": 0.3665, + "step": 17688 + }, + { + "epoch": 1.44, + "learning_rate": 1.0390591047370708e-05, + "loss": 0.4668, + "step": 17689 + }, + { + "epoch": 1.44, + "learning_rate": 1.0390047805302044e-05, + "loss": 0.2548, + "step": 17690 + }, + { + "epoch": 1.44, + "learning_rate": 1.0389504563233376e-05, + "loss": 0.3386, + "step": 17691 + }, + { + "epoch": 1.44, + "learning_rate": 1.0388961321164712e-05, + "loss": 0.1876, + "step": 17692 + }, + { + "epoch": 1.44, + "learning_rate": 1.0388418079096045e-05, + "loss": 0.2003, + "step": 17693 + }, + { + "epoch": 1.44, + "learning_rate": 1.038787483702738e-05, + "loss": 0.1569, + "step": 17694 + }, + { + "epoch": 1.44, + "learning_rate": 1.0387331594958713e-05, + "loss": 0.2546, + "step": 17695 + }, + { + "epoch": 1.44, + "learning_rate": 1.0386788352890049e-05, + "loss": 0.4196, + "step": 17696 + }, + { + "epoch": 1.44, + "learning_rate": 1.0386245110821383e-05, + "loss": 0.2945, + "step": 17697 + }, + { + "epoch": 1.44, + "learning_rate": 1.0385701868752717e-05, + "loss": 0.2984, + "step": 17698 + }, + { + "epoch": 1.44, + "learning_rate": 1.0385158626684052e-05, + "loss": 0.2256, + "step": 17699 + }, + { + "epoch": 1.44, + "learning_rate": 1.0384615384615386e-05, + "loss": 0.1603, + "step": 17700 + }, + { + "epoch": 1.44, + "learning_rate": 1.038407214254672e-05, + "loss": 0.432, + "step": 17701 + }, + { + "epoch": 1.44, + "learning_rate": 1.0383528900478054e-05, + "loss": 0.5281, + "step": 17702 + }, + { + "epoch": 1.44, + "learning_rate": 1.0382985658409389e-05, + "loss": 0.2059, + "step": 17703 + }, + { + "epoch": 1.44, + "learning_rate": 1.0382442416340723e-05, + "loss": 0.4413, + "step": 17704 + }, + { + "epoch": 1.44, + "learning_rate": 1.0381899174272057e-05, + "loss": 0.2868, + "step": 17705 + }, + { + "epoch": 1.44, + "learning_rate": 1.038135593220339e-05, + "loss": 0.2478, + "step": 17706 + }, + { + "epoch": 1.44, + "learning_rate": 1.0380812690134726e-05, + "loss": 0.3558, + "step": 17707 + }, + { + "epoch": 1.44, + "learning_rate": 1.0380269448066058e-05, + "loss": 0.3717, + "step": 17708 + }, + { + "epoch": 1.44, + "learning_rate": 1.0379726205997394e-05, + "loss": 0.4155, + "step": 17709 + }, + { + "epoch": 1.44, + "learning_rate": 1.0379182963928727e-05, + "loss": 0.3421, + "step": 17710 + }, + { + "epoch": 1.44, + "learning_rate": 1.0378639721860062e-05, + "loss": 0.1256, + "step": 17711 + }, + { + "epoch": 1.44, + "learning_rate": 1.0378096479791395e-05, + "loss": 0.2194, + "step": 17712 + }, + { + "epoch": 1.44, + "learning_rate": 1.0377553237722731e-05, + "loss": 0.381, + "step": 17713 + }, + { + "epoch": 1.44, + "learning_rate": 1.0377009995654063e-05, + "loss": 0.5418, + "step": 17714 + }, + { + "epoch": 1.44, + "learning_rate": 1.03764667535854e-05, + "loss": 0.6549, + "step": 17715 + }, + { + "epoch": 1.44, + "learning_rate": 1.0375923511516732e-05, + "loss": 0.4482, + "step": 17716 + }, + { + "epoch": 1.44, + "learning_rate": 1.0375380269448068e-05, + "loss": 0.7526, + "step": 17717 + }, + { + "epoch": 1.44, + "learning_rate": 1.03748370273794e-05, + "loss": 0.2843, + "step": 17718 + }, + { + "epoch": 1.44, + "learning_rate": 1.0374293785310736e-05, + "loss": 0.2848, + "step": 17719 + }, + { + "epoch": 1.44, + "learning_rate": 1.0373750543242069e-05, + "loss": 0.5554, + "step": 17720 + }, + { + "epoch": 1.44, + "learning_rate": 1.0373207301173405e-05, + "loss": 0.1699, + "step": 17721 + }, + { + "epoch": 1.44, + "learning_rate": 1.0372664059104737e-05, + "loss": 0.1839, + "step": 17722 + }, + { + "epoch": 1.44, + "learning_rate": 1.0372120817036073e-05, + "loss": 0.5312, + "step": 17723 + }, + { + "epoch": 1.44, + "learning_rate": 1.0371577574967406e-05, + "loss": 0.216, + "step": 17724 + }, + { + "epoch": 1.44, + "learning_rate": 1.037103433289874e-05, + "loss": 0.2459, + "step": 17725 + }, + { + "epoch": 1.44, + "learning_rate": 1.0370491090830074e-05, + "loss": 0.4098, + "step": 17726 + }, + { + "epoch": 1.44, + "learning_rate": 1.0369947848761408e-05, + "loss": 0.3757, + "step": 17727 + }, + { + "epoch": 1.44, + "learning_rate": 1.0369404606692743e-05, + "loss": 0.3152, + "step": 17728 + }, + { + "epoch": 1.44, + "learning_rate": 1.0368861364624077e-05, + "loss": 0.2723, + "step": 17729 + }, + { + "epoch": 1.44, + "learning_rate": 1.0368318122555411e-05, + "loss": 0.5175, + "step": 17730 + }, + { + "epoch": 1.44, + "learning_rate": 1.0367774880486745e-05, + "loss": 0.2686, + "step": 17731 + }, + { + "epoch": 1.44, + "learning_rate": 1.036723163841808e-05, + "loss": 0.4652, + "step": 17732 + }, + { + "epoch": 1.44, + "learning_rate": 1.0366688396349414e-05, + "loss": 0.3023, + "step": 17733 + }, + { + "epoch": 1.45, + "learning_rate": 1.036614515428075e-05, + "loss": 0.4509, + "step": 17734 + }, + { + "epoch": 1.45, + "learning_rate": 1.0365601912212082e-05, + "loss": 0.2732, + "step": 17735 + }, + { + "epoch": 1.45, + "learning_rate": 1.0365058670143418e-05, + "loss": 0.4943, + "step": 17736 + }, + { + "epoch": 1.45, + "learning_rate": 1.036451542807475e-05, + "loss": 0.0644, + "step": 17737 + }, + { + "epoch": 1.45, + "learning_rate": 1.0363972186006087e-05, + "loss": 0.6406, + "step": 17738 + }, + { + "epoch": 1.45, + "learning_rate": 1.036342894393742e-05, + "loss": 0.3549, + "step": 17739 + }, + { + "epoch": 1.45, + "learning_rate": 1.0362885701868755e-05, + "loss": 0.2628, + "step": 17740 + }, + { + "epoch": 1.45, + "learning_rate": 1.0362342459800088e-05, + "loss": 0.2966, + "step": 17741 + }, + { + "epoch": 1.45, + "learning_rate": 1.0361799217731424e-05, + "loss": 0.7209, + "step": 17742 + }, + { + "epoch": 1.45, + "learning_rate": 1.0361255975662756e-05, + "loss": 0.2833, + "step": 17743 + }, + { + "epoch": 1.45, + "learning_rate": 1.0360712733594089e-05, + "loss": 0.5394, + "step": 17744 + }, + { + "epoch": 1.45, + "learning_rate": 1.0360169491525425e-05, + "loss": 0.3645, + "step": 17745 + }, + { + "epoch": 1.45, + "learning_rate": 1.0359626249456757e-05, + "loss": 0.2661, + "step": 17746 + }, + { + "epoch": 1.45, + "learning_rate": 1.0359083007388093e-05, + "loss": 0.5476, + "step": 17747 + }, + { + "epoch": 1.45, + "learning_rate": 1.0358539765319426e-05, + "loss": 0.423, + "step": 17748 + }, + { + "epoch": 1.45, + "learning_rate": 1.0357996523250762e-05, + "loss": 0.4269, + "step": 17749 + }, + { + "epoch": 1.45, + "learning_rate": 1.0357453281182096e-05, + "loss": 0.352, + "step": 17750 + }, + { + "epoch": 1.45, + "eval_accuracy": 0.8391237901171676, + "eval_loss": 0.4437371790409088, + "eval_runtime": 22.3951, + "eval_samples_per_second": 438.266, + "eval_steps_per_second": 3.438, + "step": 17750 + }, + { + "epoch": 1.45, + "learning_rate": 1.035691003911343e-05, + "loss": 0.6762, + "step": 17751 + }, + { + "epoch": 1.45, + "learning_rate": 1.0356366797044764e-05, + "loss": 0.1788, + "step": 17752 + }, + { + "epoch": 1.45, + "learning_rate": 1.0355823554976098e-05, + "loss": 0.4808, + "step": 17753 + }, + { + "epoch": 1.45, + "learning_rate": 1.0355280312907433e-05, + "loss": 0.1527, + "step": 17754 + }, + { + "epoch": 1.45, + "learning_rate": 1.0354737070838767e-05, + "loss": 0.2903, + "step": 17755 + }, + { + "epoch": 1.45, + "learning_rate": 1.0354193828770101e-05, + "loss": 0.3665, + "step": 17756 + }, + { + "epoch": 1.45, + "learning_rate": 1.0353650586701435e-05, + "loss": 0.1298, + "step": 17757 + }, + { + "epoch": 1.45, + "learning_rate": 1.035310734463277e-05, + "loss": 0.3016, + "step": 17758 + }, + { + "epoch": 1.45, + "learning_rate": 1.0352564102564104e-05, + "loss": 0.252, + "step": 17759 + }, + { + "epoch": 1.45, + "learning_rate": 1.0352020860495438e-05, + "loss": 0.2635, + "step": 17760 + }, + { + "epoch": 1.45, + "learning_rate": 1.0351477618426772e-05, + "loss": 0.319, + "step": 17761 + }, + { + "epoch": 1.45, + "learning_rate": 1.0350934376358107e-05, + "loss": 0.3487, + "step": 17762 + }, + { + "epoch": 1.45, + "learning_rate": 1.0350391134289439e-05, + "loss": 0.2726, + "step": 17763 + }, + { + "epoch": 1.45, + "learning_rate": 1.0349847892220775e-05, + "loss": 0.3239, + "step": 17764 + }, + { + "epoch": 1.45, + "learning_rate": 1.0349304650152108e-05, + "loss": 0.6531, + "step": 17765 + }, + { + "epoch": 1.45, + "learning_rate": 1.0348761408083443e-05, + "loss": 0.3809, + "step": 17766 + }, + { + "epoch": 1.45, + "learning_rate": 1.0348218166014776e-05, + "loss": 0.1431, + "step": 17767 + }, + { + "epoch": 1.45, + "learning_rate": 1.0347674923946112e-05, + "loss": 0.3534, + "step": 17768 + }, + { + "epoch": 1.45, + "learning_rate": 1.0347131681877444e-05, + "loss": 0.3023, + "step": 17769 + }, + { + "epoch": 1.45, + "learning_rate": 1.034658843980878e-05, + "loss": 0.3968, + "step": 17770 + }, + { + "epoch": 1.45, + "learning_rate": 1.0346045197740113e-05, + "loss": 0.3901, + "step": 17771 + }, + { + "epoch": 1.45, + "learning_rate": 1.0345501955671449e-05, + "loss": 0.3278, + "step": 17772 + }, + { + "epoch": 1.45, + "learning_rate": 1.0344958713602781e-05, + "loss": 0.1382, + "step": 17773 + }, + { + "epoch": 1.45, + "learning_rate": 1.0344415471534117e-05, + "loss": 0.3024, + "step": 17774 + }, + { + "epoch": 1.45, + "learning_rate": 1.034387222946545e-05, + "loss": 0.3273, + "step": 17775 + }, + { + "epoch": 1.45, + "learning_rate": 1.0343328987396786e-05, + "loss": 0.3743, + "step": 17776 + }, + { + "epoch": 1.45, + "learning_rate": 1.0342785745328118e-05, + "loss": 0.2534, + "step": 17777 + }, + { + "epoch": 1.45, + "learning_rate": 1.0342242503259454e-05, + "loss": 0.5158, + "step": 17778 + }, + { + "epoch": 1.45, + "learning_rate": 1.0341699261190787e-05, + "loss": 0.2146, + "step": 17779 + }, + { + "epoch": 1.45, + "learning_rate": 1.0341156019122123e-05, + "loss": 0.4741, + "step": 17780 + }, + { + "epoch": 1.45, + "learning_rate": 1.0340612777053455e-05, + "loss": 0.2642, + "step": 17781 + }, + { + "epoch": 1.45, + "learning_rate": 1.034006953498479e-05, + "loss": 0.375, + "step": 17782 + }, + { + "epoch": 1.45, + "learning_rate": 1.0339526292916124e-05, + "loss": 0.3358, + "step": 17783 + }, + { + "epoch": 1.45, + "learning_rate": 1.0338983050847458e-05, + "loss": 0.315, + "step": 17784 + }, + { + "epoch": 1.45, + "learning_rate": 1.0338439808778792e-05, + "loss": 0.2217, + "step": 17785 + }, + { + "epoch": 1.45, + "learning_rate": 1.0337896566710126e-05, + "loss": 0.2694, + "step": 17786 + }, + { + "epoch": 1.45, + "learning_rate": 1.0337353324641462e-05, + "loss": 0.4228, + "step": 17787 + }, + { + "epoch": 1.45, + "learning_rate": 1.0336810082572795e-05, + "loss": 0.3334, + "step": 17788 + }, + { + "epoch": 1.45, + "learning_rate": 1.033626684050413e-05, + "loss": 0.5273, + "step": 17789 + }, + { + "epoch": 1.45, + "learning_rate": 1.0335723598435463e-05, + "loss": 0.2898, + "step": 17790 + }, + { + "epoch": 1.45, + "learning_rate": 1.03351803563668e-05, + "loss": 0.2339, + "step": 17791 + }, + { + "epoch": 1.45, + "learning_rate": 1.0334637114298132e-05, + "loss": 0.289, + "step": 17792 + }, + { + "epoch": 1.45, + "learning_rate": 1.0334093872229468e-05, + "loss": 0.5229, + "step": 17793 + }, + { + "epoch": 1.45, + "learning_rate": 1.03335506301608e-05, + "loss": 0.3251, + "step": 17794 + }, + { + "epoch": 1.45, + "learning_rate": 1.0333007388092136e-05, + "loss": 0.269, + "step": 17795 + }, + { + "epoch": 1.45, + "learning_rate": 1.0332464146023469e-05, + "loss": 0.1802, + "step": 17796 + }, + { + "epoch": 1.45, + "learning_rate": 1.0331920903954805e-05, + "loss": 0.1716, + "step": 17797 + }, + { + "epoch": 1.45, + "learning_rate": 1.0331377661886137e-05, + "loss": 0.5565, + "step": 17798 + }, + { + "epoch": 1.45, + "learning_rate": 1.0330834419817473e-05, + "loss": 0.3389, + "step": 17799 + }, + { + "epoch": 1.45, + "learning_rate": 1.0330291177748806e-05, + "loss": 0.4251, + "step": 17800 + }, + { + "epoch": 1.45, + "learning_rate": 1.0329747935680138e-05, + "loss": 0.3775, + "step": 17801 + }, + { + "epoch": 1.45, + "learning_rate": 1.0329204693611474e-05, + "loss": 0.3235, + "step": 17802 + }, + { + "epoch": 1.45, + "learning_rate": 1.0328661451542807e-05, + "loss": 0.4368, + "step": 17803 + }, + { + "epoch": 1.45, + "learning_rate": 1.0328118209474143e-05, + "loss": 0.5568, + "step": 17804 + }, + { + "epoch": 1.45, + "learning_rate": 1.0327574967405477e-05, + "loss": 0.4865, + "step": 17805 + }, + { + "epoch": 1.45, + "learning_rate": 1.0327031725336811e-05, + "loss": 0.4204, + "step": 17806 + }, + { + "epoch": 1.45, + "learning_rate": 1.0326488483268145e-05, + "loss": 0.4599, + "step": 17807 + }, + { + "epoch": 1.45, + "learning_rate": 1.032594524119948e-05, + "loss": 0.4061, + "step": 17808 + }, + { + "epoch": 1.45, + "learning_rate": 1.0325401999130814e-05, + "loss": 0.177, + "step": 17809 + }, + { + "epoch": 1.45, + "learning_rate": 1.0324858757062148e-05, + "loss": 0.2089, + "step": 17810 + }, + { + "epoch": 1.45, + "learning_rate": 1.0324315514993482e-05, + "loss": 0.1469, + "step": 17811 + }, + { + "epoch": 1.45, + "learning_rate": 1.0323772272924816e-05, + "loss": 0.1905, + "step": 17812 + }, + { + "epoch": 1.45, + "learning_rate": 1.032322903085615e-05, + "loss": 0.0865, + "step": 17813 + }, + { + "epoch": 1.45, + "learning_rate": 1.0322685788787485e-05, + "loss": 0.2284, + "step": 17814 + }, + { + "epoch": 1.45, + "learning_rate": 1.0322142546718819e-05, + "loss": 0.212, + "step": 17815 + }, + { + "epoch": 1.45, + "learning_rate": 1.0321599304650153e-05, + "loss": 0.2919, + "step": 17816 + }, + { + "epoch": 1.45, + "learning_rate": 1.0321056062581488e-05, + "loss": 0.4266, + "step": 17817 + }, + { + "epoch": 1.45, + "learning_rate": 1.0320512820512822e-05, + "loss": 0.4029, + "step": 17818 + }, + { + "epoch": 1.45, + "learning_rate": 1.0319969578444156e-05, + "loss": 0.2942, + "step": 17819 + }, + { + "epoch": 1.45, + "learning_rate": 1.0319426336375489e-05, + "loss": 0.4363, + "step": 17820 + }, + { + "epoch": 1.45, + "learning_rate": 1.0318883094306824e-05, + "loss": 0.3759, + "step": 17821 + }, + { + "epoch": 1.45, + "learning_rate": 1.0318339852238157e-05, + "loss": 0.1786, + "step": 17822 + }, + { + "epoch": 1.45, + "learning_rate": 1.0317796610169493e-05, + "loss": 0.367, + "step": 17823 + }, + { + "epoch": 1.45, + "learning_rate": 1.0317253368100825e-05, + "loss": 0.0945, + "step": 17824 + }, + { + "epoch": 1.45, + "learning_rate": 1.0316710126032161e-05, + "loss": 0.2054, + "step": 17825 + }, + { + "epoch": 1.45, + "learning_rate": 1.0316166883963494e-05, + "loss": 0.3267, + "step": 17826 + }, + { + "epoch": 1.45, + "learning_rate": 1.031562364189483e-05, + "loss": 0.2612, + "step": 17827 + }, + { + "epoch": 1.45, + "learning_rate": 1.0315080399826162e-05, + "loss": 0.2565, + "step": 17828 + }, + { + "epoch": 1.45, + "learning_rate": 1.0314537157757498e-05, + "loss": 0.3413, + "step": 17829 + }, + { + "epoch": 1.45, + "learning_rate": 1.031399391568883e-05, + "loss": 0.2868, + "step": 17830 + }, + { + "epoch": 1.45, + "learning_rate": 1.0313450673620167e-05, + "loss": 0.2511, + "step": 17831 + }, + { + "epoch": 1.45, + "learning_rate": 1.03129074315515e-05, + "loss": 0.218, + "step": 17832 + }, + { + "epoch": 1.45, + "learning_rate": 1.0312364189482835e-05, + "loss": 0.3494, + "step": 17833 + }, + { + "epoch": 1.45, + "learning_rate": 1.0311820947414168e-05, + "loss": 0.5272, + "step": 17834 + }, + { + "epoch": 1.45, + "learning_rate": 1.0311277705345504e-05, + "loss": 0.2727, + "step": 17835 + }, + { + "epoch": 1.45, + "learning_rate": 1.0310734463276836e-05, + "loss": 0.153, + "step": 17836 + }, + { + "epoch": 1.45, + "learning_rate": 1.0310191221208172e-05, + "loss": 0.255, + "step": 17837 + }, + { + "epoch": 1.45, + "learning_rate": 1.0309647979139505e-05, + "loss": 0.3, + "step": 17838 + }, + { + "epoch": 1.45, + "learning_rate": 1.0309104737070839e-05, + "loss": 0.3694, + "step": 17839 + }, + { + "epoch": 1.45, + "learning_rate": 1.0308561495002173e-05, + "loss": 0.411, + "step": 17840 + }, + { + "epoch": 1.45, + "learning_rate": 1.0308018252933507e-05, + "loss": 0.4348, + "step": 17841 + }, + { + "epoch": 1.45, + "learning_rate": 1.0307475010864843e-05, + "loss": 0.5435, + "step": 17842 + }, + { + "epoch": 1.45, + "learning_rate": 1.0306931768796176e-05, + "loss": 0.408, + "step": 17843 + }, + { + "epoch": 1.45, + "learning_rate": 1.0306388526727512e-05, + "loss": 0.2936, + "step": 17844 + }, + { + "epoch": 1.45, + "learning_rate": 1.0305845284658844e-05, + "loss": 0.5813, + "step": 17845 + }, + { + "epoch": 1.45, + "learning_rate": 1.030530204259018e-05, + "loss": 0.1923, + "step": 17846 + }, + { + "epoch": 1.45, + "learning_rate": 1.0304758800521513e-05, + "loss": 0.5434, + "step": 17847 + }, + { + "epoch": 1.45, + "learning_rate": 1.0304215558452849e-05, + "loss": 0.2877, + "step": 17848 + }, + { + "epoch": 1.45, + "learning_rate": 1.0303672316384181e-05, + "loss": 0.4963, + "step": 17849 + }, + { + "epoch": 1.45, + "learning_rate": 1.0303129074315517e-05, + "loss": 0.3363, + "step": 17850 + }, + { + "epoch": 1.45, + "learning_rate": 1.030258583224685e-05, + "loss": 0.2722, + "step": 17851 + }, + { + "epoch": 1.45, + "learning_rate": 1.0302042590178186e-05, + "loss": 0.4536, + "step": 17852 + }, + { + "epoch": 1.45, + "learning_rate": 1.0301499348109518e-05, + "loss": 0.3496, + "step": 17853 + }, + { + "epoch": 1.45, + "learning_rate": 1.0300956106040854e-05, + "loss": 0.4572, + "step": 17854 + }, + { + "epoch": 1.45, + "learning_rate": 1.0300412863972187e-05, + "loss": 0.2118, + "step": 17855 + }, + { + "epoch": 1.46, + "learning_rate": 1.0299869621903522e-05, + "loss": 0.4118, + "step": 17856 + }, + { + "epoch": 1.46, + "learning_rate": 1.0299326379834855e-05, + "loss": 0.2465, + "step": 17857 + }, + { + "epoch": 1.46, + "learning_rate": 1.029878313776619e-05, + "loss": 0.3637, + "step": 17858 + }, + { + "epoch": 1.46, + "learning_rate": 1.0298239895697523e-05, + "loss": 0.4229, + "step": 17859 + }, + { + "epoch": 1.46, + "learning_rate": 1.0297696653628858e-05, + "loss": 0.3482, + "step": 17860 + }, + { + "epoch": 1.46, + "learning_rate": 1.0297153411560192e-05, + "loss": 0.2227, + "step": 17861 + }, + { + "epoch": 1.46, + "learning_rate": 1.0296610169491526e-05, + "loss": 0.0996, + "step": 17862 + }, + { + "epoch": 1.46, + "learning_rate": 1.029606692742286e-05, + "loss": 0.2462, + "step": 17863 + }, + { + "epoch": 1.46, + "learning_rate": 1.0295523685354195e-05, + "loss": 0.4269, + "step": 17864 + }, + { + "epoch": 1.46, + "learning_rate": 1.0294980443285529e-05, + "loss": 0.2356, + "step": 17865 + }, + { + "epoch": 1.46, + "learning_rate": 1.0294437201216863e-05, + "loss": 0.2648, + "step": 17866 + }, + { + "epoch": 1.46, + "learning_rate": 1.0293893959148197e-05, + "loss": 0.5338, + "step": 17867 + }, + { + "epoch": 1.46, + "learning_rate": 1.0293350717079532e-05, + "loss": 0.5089, + "step": 17868 + }, + { + "epoch": 1.46, + "learning_rate": 1.0292807475010866e-05, + "loss": 0.1914, + "step": 17869 + }, + { + "epoch": 1.46, + "learning_rate": 1.02922642329422e-05, + "loss": 0.4827, + "step": 17870 + }, + { + "epoch": 1.46, + "learning_rate": 1.0291720990873534e-05, + "loss": 0.4753, + "step": 17871 + }, + { + "epoch": 1.46, + "learning_rate": 1.0291177748804868e-05, + "loss": 0.25, + "step": 17872 + }, + { + "epoch": 1.46, + "learning_rate": 1.0290634506736203e-05, + "loss": 0.2999, + "step": 17873 + }, + { + "epoch": 1.46, + "learning_rate": 1.0290091264667537e-05, + "loss": 0.1937, + "step": 17874 + }, + { + "epoch": 1.46, + "learning_rate": 1.0289548022598871e-05, + "loss": 0.4344, + "step": 17875 + }, + { + "epoch": 1.46, + "learning_rate": 1.0289004780530205e-05, + "loss": 0.3235, + "step": 17876 + }, + { + "epoch": 1.46, + "learning_rate": 1.0288461538461538e-05, + "loss": 0.3861, + "step": 17877 + }, + { + "epoch": 1.46, + "learning_rate": 1.0287918296392874e-05, + "loss": 0.1983, + "step": 17878 + }, + { + "epoch": 1.46, + "learning_rate": 1.0287375054324206e-05, + "loss": 0.4655, + "step": 17879 + }, + { + "epoch": 1.46, + "learning_rate": 1.0286831812255542e-05, + "loss": 0.3564, + "step": 17880 + }, + { + "epoch": 1.46, + "learning_rate": 1.0286288570186875e-05, + "loss": 0.4887, + "step": 17881 + }, + { + "epoch": 1.46, + "learning_rate": 1.028574532811821e-05, + "loss": 0.3618, + "step": 17882 + }, + { + "epoch": 1.46, + "learning_rate": 1.0285202086049543e-05, + "loss": 0.1736, + "step": 17883 + }, + { + "epoch": 1.46, + "learning_rate": 1.028465884398088e-05, + "loss": 0.3545, + "step": 17884 + }, + { + "epoch": 1.46, + "learning_rate": 1.0284115601912212e-05, + "loss": 0.1973, + "step": 17885 + }, + { + "epoch": 1.46, + "learning_rate": 1.0283572359843548e-05, + "loss": 0.2917, + "step": 17886 + }, + { + "epoch": 1.46, + "learning_rate": 1.028302911777488e-05, + "loss": 0.2148, + "step": 17887 + }, + { + "epoch": 1.46, + "learning_rate": 1.0282485875706216e-05, + "loss": 0.3185, + "step": 17888 + }, + { + "epoch": 1.46, + "learning_rate": 1.0281942633637549e-05, + "loss": 0.1511, + "step": 17889 + }, + { + "epoch": 1.46, + "learning_rate": 1.0281399391568885e-05, + "loss": 0.3127, + "step": 17890 + }, + { + "epoch": 1.46, + "learning_rate": 1.0280856149500217e-05, + "loss": 0.1943, + "step": 17891 + }, + { + "epoch": 1.46, + "learning_rate": 1.0280312907431553e-05, + "loss": 0.4407, + "step": 17892 + }, + { + "epoch": 1.46, + "learning_rate": 1.0279769665362886e-05, + "loss": 0.4445, + "step": 17893 + }, + { + "epoch": 1.46, + "learning_rate": 1.0279226423294222e-05, + "loss": 0.235, + "step": 17894 + }, + { + "epoch": 1.46, + "learning_rate": 1.0278683181225556e-05, + "loss": 0.4202, + "step": 17895 + }, + { + "epoch": 1.46, + "learning_rate": 1.0278139939156888e-05, + "loss": 0.5082, + "step": 17896 + }, + { + "epoch": 1.46, + "learning_rate": 1.0277596697088224e-05, + "loss": 0.4293, + "step": 17897 + }, + { + "epoch": 1.46, + "learning_rate": 1.0277053455019557e-05, + "loss": 0.4251, + "step": 17898 + }, + { + "epoch": 1.46, + "learning_rate": 1.0276510212950893e-05, + "loss": 0.3322, + "step": 17899 + }, + { + "epoch": 1.46, + "learning_rate": 1.0275966970882225e-05, + "loss": 0.4059, + "step": 17900 + }, + { + "epoch": 1.46, + "learning_rate": 1.0275423728813561e-05, + "loss": 0.5323, + "step": 17901 + }, + { + "epoch": 1.46, + "learning_rate": 1.0274880486744894e-05, + "loss": 0.3011, + "step": 17902 + }, + { + "epoch": 1.46, + "learning_rate": 1.027433724467623e-05, + "loss": 0.2273, + "step": 17903 + }, + { + "epoch": 1.46, + "learning_rate": 1.0273794002607562e-05, + "loss": 0.3845, + "step": 17904 + }, + { + "epoch": 1.46, + "learning_rate": 1.0273250760538898e-05, + "loss": 0.1766, + "step": 17905 + }, + { + "epoch": 1.46, + "learning_rate": 1.027270751847023e-05, + "loss": 0.4049, + "step": 17906 + }, + { + "epoch": 1.46, + "learning_rate": 1.0272164276401567e-05, + "loss": 0.5509, + "step": 17907 + }, + { + "epoch": 1.46, + "learning_rate": 1.0271621034332899e-05, + "loss": 0.5406, + "step": 17908 + }, + { + "epoch": 1.46, + "learning_rate": 1.0271077792264235e-05, + "loss": 0.1819, + "step": 17909 + }, + { + "epoch": 1.46, + "learning_rate": 1.0270534550195568e-05, + "loss": 0.4113, + "step": 17910 + }, + { + "epoch": 1.46, + "learning_rate": 1.0269991308126903e-05, + "loss": 0.5346, + "step": 17911 + }, + { + "epoch": 1.46, + "learning_rate": 1.0269448066058236e-05, + "loss": 0.2822, + "step": 17912 + }, + { + "epoch": 1.46, + "learning_rate": 1.0268904823989572e-05, + "loss": 0.455, + "step": 17913 + }, + { + "epoch": 1.46, + "learning_rate": 1.0268361581920904e-05, + "loss": 0.4733, + "step": 17914 + }, + { + "epoch": 1.46, + "learning_rate": 1.0267818339852239e-05, + "loss": 0.5345, + "step": 17915 + }, + { + "epoch": 1.46, + "learning_rate": 1.0267275097783573e-05, + "loss": 0.0777, + "step": 17916 + }, + { + "epoch": 1.46, + "learning_rate": 1.0266731855714907e-05, + "loss": 0.2749, + "step": 17917 + }, + { + "epoch": 1.46, + "learning_rate": 1.0266188613646241e-05, + "loss": 0.1906, + "step": 17918 + }, + { + "epoch": 1.46, + "learning_rate": 1.0265645371577576e-05, + "loss": 0.4119, + "step": 17919 + }, + { + "epoch": 1.46, + "learning_rate": 1.026510212950891e-05, + "loss": 0.4562, + "step": 17920 + }, + { + "epoch": 1.46, + "learning_rate": 1.0264558887440244e-05, + "loss": 0.3692, + "step": 17921 + }, + { + "epoch": 1.46, + "learning_rate": 1.0264015645371578e-05, + "loss": 0.2813, + "step": 17922 + }, + { + "epoch": 1.46, + "learning_rate": 1.0263472403302913e-05, + "loss": 0.3684, + "step": 17923 + }, + { + "epoch": 1.46, + "learning_rate": 1.0262929161234247e-05, + "loss": 0.4584, + "step": 17924 + }, + { + "epoch": 1.46, + "learning_rate": 1.0262385919165581e-05, + "loss": 0.4371, + "step": 17925 + }, + { + "epoch": 1.46, + "learning_rate": 1.0261842677096915e-05, + "loss": 0.4733, + "step": 17926 + }, + { + "epoch": 1.46, + "learning_rate": 1.026129943502825e-05, + "loss": 0.1488, + "step": 17927 + }, + { + "epoch": 1.46, + "learning_rate": 1.0260756192959584e-05, + "loss": 0.3807, + "step": 17928 + }, + { + "epoch": 1.46, + "learning_rate": 1.0260212950890918e-05, + "loss": 0.2073, + "step": 17929 + }, + { + "epoch": 1.46, + "learning_rate": 1.0259669708822252e-05, + "loss": 0.3194, + "step": 17930 + }, + { + "epoch": 1.46, + "learning_rate": 1.0259126466753586e-05, + "loss": 0.384, + "step": 17931 + }, + { + "epoch": 1.46, + "learning_rate": 1.0258583224684922e-05, + "loss": 0.3401, + "step": 17932 + }, + { + "epoch": 1.46, + "learning_rate": 1.0258039982616255e-05, + "loss": 0.2869, + "step": 17933 + }, + { + "epoch": 1.46, + "learning_rate": 1.0257496740547587e-05, + "loss": 0.4063, + "step": 17934 + }, + { + "epoch": 1.46, + "learning_rate": 1.0256953498478923e-05, + "loss": 0.3868, + "step": 17935 + }, + { + "epoch": 1.46, + "learning_rate": 1.0256410256410256e-05, + "loss": 0.2948, + "step": 17936 + }, + { + "epoch": 1.46, + "learning_rate": 1.0255867014341592e-05, + "loss": 0.3916, + "step": 17937 + }, + { + "epoch": 1.46, + "learning_rate": 1.0255323772272924e-05, + "loss": 0.2899, + "step": 17938 + }, + { + "epoch": 1.46, + "learning_rate": 1.025478053020426e-05, + "loss": 0.2828, + "step": 17939 + }, + { + "epoch": 1.46, + "learning_rate": 1.0254237288135593e-05, + "loss": 0.2972, + "step": 17940 + }, + { + "epoch": 1.46, + "learning_rate": 1.0253694046066929e-05, + "loss": 0.1953, + "step": 17941 + }, + { + "epoch": 1.46, + "learning_rate": 1.0253150803998261e-05, + "loss": 0.5882, + "step": 17942 + }, + { + "epoch": 1.46, + "learning_rate": 1.0252607561929597e-05, + "loss": 0.3563, + "step": 17943 + }, + { + "epoch": 1.46, + "learning_rate": 1.025206431986093e-05, + "loss": 0.5005, + "step": 17944 + }, + { + "epoch": 1.46, + "learning_rate": 1.0251521077792266e-05, + "loss": 0.3013, + "step": 17945 + }, + { + "epoch": 1.46, + "learning_rate": 1.0250977835723598e-05, + "loss": 0.2764, + "step": 17946 + }, + { + "epoch": 1.46, + "learning_rate": 1.0250434593654934e-05, + "loss": 0.2308, + "step": 17947 + }, + { + "epoch": 1.46, + "learning_rate": 1.0249891351586267e-05, + "loss": 0.153, + "step": 17948 + }, + { + "epoch": 1.46, + "learning_rate": 1.0249348109517603e-05, + "loss": 0.1687, + "step": 17949 + }, + { + "epoch": 1.46, + "learning_rate": 1.0248804867448937e-05, + "loss": 0.33, + "step": 17950 + }, + { + "epoch": 1.46, + "learning_rate": 1.0248261625380271e-05, + "loss": 0.2856, + "step": 17951 + }, + { + "epoch": 1.46, + "learning_rate": 1.0247718383311605e-05, + "loss": 0.5699, + "step": 17952 + }, + { + "epoch": 1.46, + "learning_rate": 1.0247175141242938e-05, + "loss": 0.2573, + "step": 17953 + }, + { + "epoch": 1.46, + "learning_rate": 1.0246631899174274e-05, + "loss": 0.127, + "step": 17954 + }, + { + "epoch": 1.46, + "learning_rate": 1.0246088657105606e-05, + "loss": 0.2599, + "step": 17955 + }, + { + "epoch": 1.46, + "learning_rate": 1.0245545415036942e-05, + "loss": 0.2954, + "step": 17956 + }, + { + "epoch": 1.46, + "learning_rate": 1.0245002172968275e-05, + "loss": 0.1215, + "step": 17957 + }, + { + "epoch": 1.46, + "learning_rate": 1.024445893089961e-05, + "loss": 0.3211, + "step": 17958 + }, + { + "epoch": 1.46, + "learning_rate": 1.0243915688830943e-05, + "loss": 0.4463, + "step": 17959 + }, + { + "epoch": 1.46, + "learning_rate": 1.0243372446762279e-05, + "loss": 0.5544, + "step": 17960 + }, + { + "epoch": 1.46, + "learning_rate": 1.0242829204693612e-05, + "loss": 0.258, + "step": 17961 + }, + { + "epoch": 1.46, + "learning_rate": 1.0242285962624948e-05, + "loss": 0.509, + "step": 17962 + }, + { + "epoch": 1.46, + "learning_rate": 1.024174272055628e-05, + "loss": 0.3404, + "step": 17963 + }, + { + "epoch": 1.46, + "learning_rate": 1.0241199478487616e-05, + "loss": 0.417, + "step": 17964 + }, + { + "epoch": 1.46, + "learning_rate": 1.0240656236418949e-05, + "loss": 0.1921, + "step": 17965 + }, + { + "epoch": 1.46, + "learning_rate": 1.0240112994350284e-05, + "loss": 0.2657, + "step": 17966 + }, + { + "epoch": 1.46, + "learning_rate": 1.0239569752281617e-05, + "loss": 0.4108, + "step": 17967 + }, + { + "epoch": 1.46, + "learning_rate": 1.0239026510212953e-05, + "loss": 0.5643, + "step": 17968 + }, + { + "epoch": 1.46, + "learning_rate": 1.0238483268144285e-05, + "loss": 0.5831, + "step": 17969 + }, + { + "epoch": 1.46, + "learning_rate": 1.0237940026075621e-05, + "loss": 0.3753, + "step": 17970 + }, + { + "epoch": 1.46, + "learning_rate": 1.0237396784006954e-05, + "loss": 0.3485, + "step": 17971 + }, + { + "epoch": 1.46, + "learning_rate": 1.0236853541938288e-05, + "loss": 0.2507, + "step": 17972 + }, + { + "epoch": 1.46, + "learning_rate": 1.0236310299869622e-05, + "loss": 0.4045, + "step": 17973 + }, + { + "epoch": 1.46, + "learning_rate": 1.0235767057800957e-05, + "loss": 0.2477, + "step": 17974 + }, + { + "epoch": 1.46, + "learning_rate": 1.0235223815732291e-05, + "loss": 0.3852, + "step": 17975 + }, + { + "epoch": 1.46, + "learning_rate": 1.0234680573663625e-05, + "loss": 0.5747, + "step": 17976 + }, + { + "epoch": 1.46, + "learning_rate": 1.023413733159496e-05, + "loss": 0.4379, + "step": 17977 + }, + { + "epoch": 1.46, + "learning_rate": 1.0233594089526294e-05, + "loss": 0.5049, + "step": 17978 + }, + { + "epoch": 1.47, + "learning_rate": 1.0233050847457628e-05, + "loss": 0.2712, + "step": 17979 + }, + { + "epoch": 1.47, + "learning_rate": 1.0232507605388962e-05, + "loss": 0.4882, + "step": 17980 + }, + { + "epoch": 1.47, + "learning_rate": 1.0231964363320296e-05, + "loss": 0.2822, + "step": 17981 + }, + { + "epoch": 1.47, + "learning_rate": 1.023142112125163e-05, + "loss": 0.1759, + "step": 17982 + }, + { + "epoch": 1.47, + "learning_rate": 1.0230877879182965e-05, + "loss": 0.5687, + "step": 17983 + }, + { + "epoch": 1.47, + "learning_rate": 1.0230334637114299e-05, + "loss": 0.3521, + "step": 17984 + }, + { + "epoch": 1.47, + "learning_rate": 1.0229791395045635e-05, + "loss": 0.239, + "step": 17985 + }, + { + "epoch": 1.47, + "learning_rate": 1.0229248152976967e-05, + "loss": 0.4319, + "step": 17986 + }, + { + "epoch": 1.47, + "learning_rate": 1.0228704910908303e-05, + "loss": 0.3849, + "step": 17987 + }, + { + "epoch": 1.47, + "learning_rate": 1.0228161668839636e-05, + "loss": 0.1987, + "step": 17988 + }, + { + "epoch": 1.47, + "learning_rate": 1.0227618426770972e-05, + "loss": 0.1435, + "step": 17989 + }, + { + "epoch": 1.47, + "learning_rate": 1.0227075184702304e-05, + "loss": 0.3535, + "step": 17990 + }, + { + "epoch": 1.47, + "learning_rate": 1.0226531942633637e-05, + "loss": 0.1601, + "step": 17991 + }, + { + "epoch": 1.47, + "learning_rate": 1.0225988700564973e-05, + "loss": 0.5199, + "step": 17992 + }, + { + "epoch": 1.47, + "learning_rate": 1.0225445458496305e-05, + "loss": 0.3335, + "step": 17993 + }, + { + "epoch": 1.47, + "learning_rate": 1.0224902216427641e-05, + "loss": 0.3683, + "step": 17994 + }, + { + "epoch": 1.47, + "learning_rate": 1.0224358974358974e-05, + "loss": 0.3038, + "step": 17995 + }, + { + "epoch": 1.47, + "learning_rate": 1.022381573229031e-05, + "loss": 0.5021, + "step": 17996 + }, + { + "epoch": 1.47, + "learning_rate": 1.0223272490221642e-05, + "loss": 0.3435, + "step": 17997 + }, + { + "epoch": 1.47, + "learning_rate": 1.0222729248152978e-05, + "loss": 0.2274, + "step": 17998 + }, + { + "epoch": 1.47, + "learning_rate": 1.022218600608431e-05, + "loss": 0.1714, + "step": 17999 + }, + { + "epoch": 1.47, + "learning_rate": 1.0221642764015647e-05, + "loss": 0.3084, + "step": 18000 + }, + { + "epoch": 1.47, + "eval_accuracy": 0.8352521650534895, + "eval_loss": 0.44731462001800537, + "eval_runtime": 22.2648, + "eval_samples_per_second": 440.83, + "eval_steps_per_second": 3.458, + "step": 18000 + }, + { + "epoch": 1.47, + "learning_rate": 1.0221099521946979e-05, + "loss": 0.3314, + "step": 18001 + }, + { + "epoch": 1.47, + "learning_rate": 1.0220556279878315e-05, + "loss": 0.3316, + "step": 18002 + }, + { + "epoch": 1.47, + "learning_rate": 1.022001303780965e-05, + "loss": 0.2238, + "step": 18003 + }, + { + "epoch": 1.47, + "learning_rate": 1.0219469795740984e-05, + "loss": 0.4368, + "step": 18004 + }, + { + "epoch": 1.47, + "learning_rate": 1.0218926553672318e-05, + "loss": 0.2503, + "step": 18005 + }, + { + "epoch": 1.47, + "learning_rate": 1.0218383311603652e-05, + "loss": 0.4317, + "step": 18006 + }, + { + "epoch": 1.47, + "learning_rate": 1.0217840069534986e-05, + "loss": 0.2801, + "step": 18007 + }, + { + "epoch": 1.47, + "learning_rate": 1.021729682746632e-05, + "loss": 0.2935, + "step": 18008 + }, + { + "epoch": 1.47, + "learning_rate": 1.0216753585397655e-05, + "loss": 0.4114, + "step": 18009 + }, + { + "epoch": 1.47, + "learning_rate": 1.0216210343328987e-05, + "loss": 0.3608, + "step": 18010 + }, + { + "epoch": 1.47, + "learning_rate": 1.0215667101260323e-05, + "loss": 0.2148, + "step": 18011 + }, + { + "epoch": 1.47, + "learning_rate": 1.0215123859191656e-05, + "loss": 0.4834, + "step": 18012 + }, + { + "epoch": 1.47, + "learning_rate": 1.0214580617122992e-05, + "loss": 0.2664, + "step": 18013 + }, + { + "epoch": 1.47, + "learning_rate": 1.0214037375054324e-05, + "loss": 0.245, + "step": 18014 + }, + { + "epoch": 1.47, + "learning_rate": 1.021349413298566e-05, + "loss": 0.4564, + "step": 18015 + }, + { + "epoch": 1.47, + "learning_rate": 1.0212950890916993e-05, + "loss": 0.2631, + "step": 18016 + }, + { + "epoch": 1.47, + "learning_rate": 1.0212407648848329e-05, + "loss": 0.1987, + "step": 18017 + }, + { + "epoch": 1.47, + "learning_rate": 1.0211864406779661e-05, + "loss": 0.3329, + "step": 18018 + }, + { + "epoch": 1.47, + "learning_rate": 1.0211321164710997e-05, + "loss": 0.2313, + "step": 18019 + }, + { + "epoch": 1.47, + "learning_rate": 1.021077792264233e-05, + "loss": 0.228, + "step": 18020 + }, + { + "epoch": 1.47, + "learning_rate": 1.0210234680573665e-05, + "loss": 0.1485, + "step": 18021 + }, + { + "epoch": 1.47, + "learning_rate": 1.0209691438504998e-05, + "loss": 0.3641, + "step": 18022 + }, + { + "epoch": 1.47, + "learning_rate": 1.0209148196436334e-05, + "loss": 0.209, + "step": 18023 + }, + { + "epoch": 1.47, + "learning_rate": 1.0208604954367666e-05, + "loss": 0.2634, + "step": 18024 + }, + { + "epoch": 1.47, + "learning_rate": 1.0208061712299002e-05, + "loss": 0.3463, + "step": 18025 + }, + { + "epoch": 1.47, + "learning_rate": 1.0207518470230335e-05, + "loss": 0.2719, + "step": 18026 + }, + { + "epoch": 1.47, + "learning_rate": 1.020697522816167e-05, + "loss": 0.153, + "step": 18027 + }, + { + "epoch": 1.47, + "learning_rate": 1.0206431986093003e-05, + "loss": 0.134, + "step": 18028 + }, + { + "epoch": 1.47, + "learning_rate": 1.0205888744024338e-05, + "loss": 0.7415, + "step": 18029 + }, + { + "epoch": 1.47, + "learning_rate": 1.0205345501955672e-05, + "loss": 0.2352, + "step": 18030 + }, + { + "epoch": 1.47, + "learning_rate": 1.0204802259887006e-05, + "loss": 0.4644, + "step": 18031 + }, + { + "epoch": 1.47, + "learning_rate": 1.020425901781834e-05, + "loss": 0.1217, + "step": 18032 + }, + { + "epoch": 1.47, + "learning_rate": 1.0203715775749675e-05, + "loss": 0.303, + "step": 18033 + }, + { + "epoch": 1.47, + "learning_rate": 1.0203172533681009e-05, + "loss": 0.2826, + "step": 18034 + }, + { + "epoch": 1.47, + "learning_rate": 1.0202629291612343e-05, + "loss": 0.3056, + "step": 18035 + }, + { + "epoch": 1.47, + "learning_rate": 1.0202086049543677e-05, + "loss": 0.1808, + "step": 18036 + }, + { + "epoch": 1.47, + "learning_rate": 1.0201542807475011e-05, + "loss": 0.3752, + "step": 18037 + }, + { + "epoch": 1.47, + "learning_rate": 1.0200999565406346e-05, + "loss": 0.2293, + "step": 18038 + }, + { + "epoch": 1.47, + "learning_rate": 1.020045632333768e-05, + "loss": 0.3343, + "step": 18039 + }, + { + "epoch": 1.47, + "learning_rate": 1.0199913081269016e-05, + "loss": 0.28, + "step": 18040 + }, + { + "epoch": 1.47, + "learning_rate": 1.0199369839200348e-05, + "loss": 0.1175, + "step": 18041 + }, + { + "epoch": 1.47, + "learning_rate": 1.0198826597131684e-05, + "loss": 0.3429, + "step": 18042 + }, + { + "epoch": 1.47, + "learning_rate": 1.0198283355063017e-05, + "loss": 0.3179, + "step": 18043 + }, + { + "epoch": 1.47, + "learning_rate": 1.0197740112994353e-05, + "loss": 0.2208, + "step": 18044 + }, + { + "epoch": 1.47, + "learning_rate": 1.0197196870925685e-05, + "loss": 0.15, + "step": 18045 + }, + { + "epoch": 1.47, + "learning_rate": 1.0196653628857021e-05, + "loss": 0.3126, + "step": 18046 + }, + { + "epoch": 1.47, + "learning_rate": 1.0196110386788354e-05, + "loss": 0.4219, + "step": 18047 + }, + { + "epoch": 1.47, + "learning_rate": 1.0195567144719686e-05, + "loss": 0.1854, + "step": 18048 + }, + { + "epoch": 1.47, + "learning_rate": 1.0195023902651022e-05, + "loss": 0.1477, + "step": 18049 + }, + { + "epoch": 1.47, + "learning_rate": 1.0194480660582355e-05, + "loss": 0.2224, + "step": 18050 + }, + { + "epoch": 1.47, + "learning_rate": 1.019393741851369e-05, + "loss": 0.3153, + "step": 18051 + }, + { + "epoch": 1.47, + "learning_rate": 1.0193394176445023e-05, + "loss": 0.4676, + "step": 18052 + }, + { + "epoch": 1.47, + "learning_rate": 1.0192850934376359e-05, + "loss": 0.1635, + "step": 18053 + }, + { + "epoch": 1.47, + "learning_rate": 1.0192307692307692e-05, + "loss": 0.4424, + "step": 18054 + }, + { + "epoch": 1.47, + "learning_rate": 1.0191764450239028e-05, + "loss": 0.4073, + "step": 18055 + }, + { + "epoch": 1.47, + "learning_rate": 1.019122120817036e-05, + "loss": 0.3784, + "step": 18056 + }, + { + "epoch": 1.47, + "learning_rate": 1.0190677966101696e-05, + "loss": 0.3384, + "step": 18057 + }, + { + "epoch": 1.47, + "learning_rate": 1.019013472403303e-05, + "loss": 0.2003, + "step": 18058 + }, + { + "epoch": 1.47, + "learning_rate": 1.0189591481964365e-05, + "loss": 0.3146, + "step": 18059 + }, + { + "epoch": 1.47, + "learning_rate": 1.0189048239895699e-05, + "loss": 0.255, + "step": 18060 + }, + { + "epoch": 1.47, + "learning_rate": 1.0188504997827033e-05, + "loss": 0.7077, + "step": 18061 + }, + { + "epoch": 1.47, + "learning_rate": 1.0187961755758367e-05, + "loss": 0.232, + "step": 18062 + }, + { + "epoch": 1.47, + "learning_rate": 1.0187418513689701e-05, + "loss": 0.4191, + "step": 18063 + }, + { + "epoch": 1.47, + "learning_rate": 1.0186875271621036e-05, + "loss": 0.2305, + "step": 18064 + }, + { + "epoch": 1.47, + "learning_rate": 1.018633202955237e-05, + "loss": 0.3216, + "step": 18065 + }, + { + "epoch": 1.47, + "learning_rate": 1.0185788787483704e-05, + "loss": 0.288, + "step": 18066 + }, + { + "epoch": 1.47, + "learning_rate": 1.0185245545415037e-05, + "loss": 0.6623, + "step": 18067 + }, + { + "epoch": 1.47, + "learning_rate": 1.0184702303346373e-05, + "loss": 0.2819, + "step": 18068 + }, + { + "epoch": 1.47, + "learning_rate": 1.0184159061277705e-05, + "loss": 0.2065, + "step": 18069 + }, + { + "epoch": 1.47, + "learning_rate": 1.0183615819209041e-05, + "loss": 0.349, + "step": 18070 + }, + { + "epoch": 1.47, + "learning_rate": 1.0183072577140374e-05, + "loss": 0.3695, + "step": 18071 + }, + { + "epoch": 1.47, + "learning_rate": 1.018252933507171e-05, + "loss": 0.4425, + "step": 18072 + }, + { + "epoch": 1.47, + "learning_rate": 1.0181986093003042e-05, + "loss": 0.1684, + "step": 18073 + }, + { + "epoch": 1.47, + "learning_rate": 1.0181442850934378e-05, + "loss": 0.2639, + "step": 18074 + }, + { + "epoch": 1.47, + "learning_rate": 1.018089960886571e-05, + "loss": 0.3112, + "step": 18075 + }, + { + "epoch": 1.47, + "learning_rate": 1.0180356366797046e-05, + "loss": 0.2182, + "step": 18076 + }, + { + "epoch": 1.47, + "learning_rate": 1.0179813124728379e-05, + "loss": 0.4015, + "step": 18077 + }, + { + "epoch": 1.47, + "learning_rate": 1.0179269882659715e-05, + "loss": 0.5583, + "step": 18078 + }, + { + "epoch": 1.47, + "learning_rate": 1.0178726640591047e-05, + "loss": 0.2619, + "step": 18079 + }, + { + "epoch": 1.47, + "learning_rate": 1.0178183398522383e-05, + "loss": 0.3262, + "step": 18080 + }, + { + "epoch": 1.47, + "learning_rate": 1.0177640156453716e-05, + "loss": 0.3429, + "step": 18081 + }, + { + "epoch": 1.47, + "learning_rate": 1.0177096914385052e-05, + "loss": 0.1551, + "step": 18082 + }, + { + "epoch": 1.47, + "learning_rate": 1.0176553672316384e-05, + "loss": 0.3449, + "step": 18083 + }, + { + "epoch": 1.47, + "learning_rate": 1.017601043024772e-05, + "loss": 0.5234, + "step": 18084 + }, + { + "epoch": 1.47, + "learning_rate": 1.0175467188179053e-05, + "loss": 0.3536, + "step": 18085 + }, + { + "epoch": 1.47, + "learning_rate": 1.0174923946110387e-05, + "loss": 0.396, + "step": 18086 + }, + { + "epoch": 1.47, + "learning_rate": 1.0174380704041721e-05, + "loss": 0.3696, + "step": 18087 + }, + { + "epoch": 1.47, + "learning_rate": 1.0173837461973056e-05, + "loss": 0.1554, + "step": 18088 + }, + { + "epoch": 1.47, + "learning_rate": 1.017329421990439e-05, + "loss": 0.2786, + "step": 18089 + }, + { + "epoch": 1.47, + "learning_rate": 1.0172750977835724e-05, + "loss": 0.3417, + "step": 18090 + }, + { + "epoch": 1.47, + "learning_rate": 1.0172207735767058e-05, + "loss": 0.1956, + "step": 18091 + }, + { + "epoch": 1.47, + "learning_rate": 1.0171664493698392e-05, + "loss": 0.4525, + "step": 18092 + }, + { + "epoch": 1.47, + "learning_rate": 1.0171121251629728e-05, + "loss": 0.5788, + "step": 18093 + }, + { + "epoch": 1.47, + "learning_rate": 1.0170578009561061e-05, + "loss": 0.3621, + "step": 18094 + }, + { + "epoch": 1.47, + "learning_rate": 1.0170034767492397e-05, + "loss": 0.2127, + "step": 18095 + }, + { + "epoch": 1.47, + "learning_rate": 1.016949152542373e-05, + "loss": 0.4827, + "step": 18096 + }, + { + "epoch": 1.47, + "learning_rate": 1.0168948283355065e-05, + "loss": 0.2269, + "step": 18097 + }, + { + "epoch": 1.47, + "learning_rate": 1.0168405041286398e-05, + "loss": 0.311, + "step": 18098 + }, + { + "epoch": 1.47, + "learning_rate": 1.0167861799217734e-05, + "loss": 0.5142, + "step": 18099 + }, + { + "epoch": 1.47, + "learning_rate": 1.0167318557149066e-05, + "loss": 0.2368, + "step": 18100 + }, + { + "epoch": 1.47, + "learning_rate": 1.0166775315080402e-05, + "loss": 0.1766, + "step": 18101 + }, + { + "epoch": 1.48, + "learning_rate": 1.0166232073011735e-05, + "loss": 0.2319, + "step": 18102 + }, + { + "epoch": 1.48, + "learning_rate": 1.016568883094307e-05, + "loss": 0.1956, + "step": 18103 + }, + { + "epoch": 1.48, + "learning_rate": 1.0165145588874403e-05, + "loss": 0.2284, + "step": 18104 + }, + { + "epoch": 1.48, + "learning_rate": 1.0164602346805736e-05, + "loss": 0.3709, + "step": 18105 + }, + { + "epoch": 1.48, + "learning_rate": 1.0164059104737072e-05, + "loss": 0.168, + "step": 18106 + }, + { + "epoch": 1.48, + "learning_rate": 1.0163515862668404e-05, + "loss": 0.2626, + "step": 18107 + }, + { + "epoch": 1.48, + "learning_rate": 1.016297262059974e-05, + "loss": 0.4117, + "step": 18108 + }, + { + "epoch": 1.48, + "learning_rate": 1.0162429378531073e-05, + "loss": 0.1414, + "step": 18109 + }, + { + "epoch": 1.48, + "learning_rate": 1.0161886136462409e-05, + "loss": 0.4646, + "step": 18110 + }, + { + "epoch": 1.48, + "learning_rate": 1.0161342894393743e-05, + "loss": 0.1207, + "step": 18111 + }, + { + "epoch": 1.48, + "learning_rate": 1.0160799652325077e-05, + "loss": 0.1954, + "step": 18112 + }, + { + "epoch": 1.48, + "learning_rate": 1.0160256410256411e-05, + "loss": 0.2664, + "step": 18113 + }, + { + "epoch": 1.48, + "learning_rate": 1.0159713168187746e-05, + "loss": 0.5178, + "step": 18114 + }, + { + "epoch": 1.48, + "learning_rate": 1.015916992611908e-05, + "loss": 0.1512, + "step": 18115 + }, + { + "epoch": 1.48, + "learning_rate": 1.0158626684050414e-05, + "loss": 0.4253, + "step": 18116 + }, + { + "epoch": 1.48, + "learning_rate": 1.0158083441981748e-05, + "loss": 0.2511, + "step": 18117 + }, + { + "epoch": 1.48, + "learning_rate": 1.0157540199913082e-05, + "loss": 0.5563, + "step": 18118 + }, + { + "epoch": 1.48, + "learning_rate": 1.0156996957844417e-05, + "loss": 0.16, + "step": 18119 + }, + { + "epoch": 1.48, + "learning_rate": 1.0156453715775751e-05, + "loss": 0.2266, + "step": 18120 + }, + { + "epoch": 1.48, + "learning_rate": 1.0155910473707085e-05, + "loss": 0.1617, + "step": 18121 + }, + { + "epoch": 1.48, + "learning_rate": 1.015536723163842e-05, + "loss": 0.3202, + "step": 18122 + }, + { + "epoch": 1.48, + "learning_rate": 1.0154823989569754e-05, + "loss": 0.4156, + "step": 18123 + }, + { + "epoch": 1.48, + "learning_rate": 1.0154280747501086e-05, + "loss": 0.5124, + "step": 18124 + }, + { + "epoch": 1.48, + "learning_rate": 1.0153737505432422e-05, + "loss": 0.3327, + "step": 18125 + }, + { + "epoch": 1.48, + "learning_rate": 1.0153194263363755e-05, + "loss": 0.3506, + "step": 18126 + }, + { + "epoch": 1.48, + "learning_rate": 1.015265102129509e-05, + "loss": 0.399, + "step": 18127 + }, + { + "epoch": 1.48, + "learning_rate": 1.0152107779226423e-05, + "loss": 0.5212, + "step": 18128 + }, + { + "epoch": 1.48, + "learning_rate": 1.0151564537157759e-05, + "loss": 0.5964, + "step": 18129 + }, + { + "epoch": 1.48, + "learning_rate": 1.0151021295089092e-05, + "loss": 0.3989, + "step": 18130 + }, + { + "epoch": 1.48, + "learning_rate": 1.0150478053020427e-05, + "loss": 0.4306, + "step": 18131 + }, + { + "epoch": 1.48, + "learning_rate": 1.014993481095176e-05, + "loss": 0.5569, + "step": 18132 + }, + { + "epoch": 1.48, + "learning_rate": 1.0149391568883096e-05, + "loss": 0.3951, + "step": 18133 + }, + { + "epoch": 1.48, + "learning_rate": 1.0148848326814428e-05, + "loss": 0.2993, + "step": 18134 + }, + { + "epoch": 1.48, + "learning_rate": 1.0148305084745764e-05, + "loss": 0.4073, + "step": 18135 + }, + { + "epoch": 1.48, + "learning_rate": 1.0147761842677097e-05, + "loss": 0.31, + "step": 18136 + }, + { + "epoch": 1.48, + "learning_rate": 1.0147218600608433e-05, + "loss": 0.3932, + "step": 18137 + }, + { + "epoch": 1.48, + "learning_rate": 1.0146675358539765e-05, + "loss": 0.3482, + "step": 18138 + }, + { + "epoch": 1.48, + "learning_rate": 1.0146132116471101e-05, + "loss": 0.1807, + "step": 18139 + }, + { + "epoch": 1.48, + "learning_rate": 1.0145588874402434e-05, + "loss": 0.4151, + "step": 18140 + }, + { + "epoch": 1.48, + "learning_rate": 1.014504563233377e-05, + "loss": 0.3267, + "step": 18141 + }, + { + "epoch": 1.48, + "learning_rate": 1.0144502390265102e-05, + "loss": 0.6194, + "step": 18142 + }, + { + "epoch": 1.48, + "learning_rate": 1.0143959148196436e-05, + "loss": 0.358, + "step": 18143 + }, + { + "epoch": 1.48, + "learning_rate": 1.014341590612777e-05, + "loss": 0.7519, + "step": 18144 + }, + { + "epoch": 1.48, + "learning_rate": 1.0142872664059105e-05, + "loss": 0.4282, + "step": 18145 + }, + { + "epoch": 1.48, + "learning_rate": 1.014232942199044e-05, + "loss": 0.2518, + "step": 18146 + }, + { + "epoch": 1.48, + "learning_rate": 1.0141786179921773e-05, + "loss": 0.3878, + "step": 18147 + }, + { + "epoch": 1.48, + "learning_rate": 1.014124293785311e-05, + "loss": 0.2894, + "step": 18148 + }, + { + "epoch": 1.48, + "learning_rate": 1.0140699695784442e-05, + "loss": 0.3268, + "step": 18149 + }, + { + "epoch": 1.48, + "learning_rate": 1.0140156453715778e-05, + "loss": 0.5095, + "step": 18150 + }, + { + "epoch": 1.48, + "learning_rate": 1.013961321164711e-05, + "loss": 0.3654, + "step": 18151 + }, + { + "epoch": 1.48, + "learning_rate": 1.0139069969578446e-05, + "loss": 0.1599, + "step": 18152 + }, + { + "epoch": 1.48, + "learning_rate": 1.0138526727509779e-05, + "loss": 0.2905, + "step": 18153 + }, + { + "epoch": 1.48, + "learning_rate": 1.0137983485441115e-05, + "loss": 0.1028, + "step": 18154 + }, + { + "epoch": 1.48, + "learning_rate": 1.0137440243372447e-05, + "loss": 0.3667, + "step": 18155 + }, + { + "epoch": 1.48, + "learning_rate": 1.0136897001303783e-05, + "loss": 0.2749, + "step": 18156 + }, + { + "epoch": 1.48, + "learning_rate": 1.0136353759235116e-05, + "loss": 0.4433, + "step": 18157 + }, + { + "epoch": 1.48, + "learning_rate": 1.0135810517166452e-05, + "loss": 0.2527, + "step": 18158 + }, + { + "epoch": 1.48, + "learning_rate": 1.0135267275097784e-05, + "loss": 0.3262, + "step": 18159 + }, + { + "epoch": 1.48, + "learning_rate": 1.013472403302912e-05, + "loss": 0.561, + "step": 18160 + }, + { + "epoch": 1.48, + "learning_rate": 1.0134180790960453e-05, + "loss": 0.4799, + "step": 18161 + }, + { + "epoch": 1.48, + "learning_rate": 1.0133637548891785e-05, + "loss": 0.3105, + "step": 18162 + }, + { + "epoch": 1.48, + "learning_rate": 1.0133094306823121e-05, + "loss": 0.3633, + "step": 18163 + }, + { + "epoch": 1.48, + "learning_rate": 1.0132551064754454e-05, + "loss": 0.3468, + "step": 18164 + }, + { + "epoch": 1.48, + "learning_rate": 1.013200782268579e-05, + "loss": 0.4668, + "step": 18165 + }, + { + "epoch": 1.48, + "learning_rate": 1.0131464580617124e-05, + "loss": 0.4069, + "step": 18166 + }, + { + "epoch": 1.48, + "learning_rate": 1.0130921338548458e-05, + "loss": 0.2639, + "step": 18167 + }, + { + "epoch": 1.48, + "learning_rate": 1.0130378096479792e-05, + "loss": 0.1647, + "step": 18168 + }, + { + "epoch": 1.48, + "learning_rate": 1.0129834854411126e-05, + "loss": 0.3727, + "step": 18169 + }, + { + "epoch": 1.48, + "learning_rate": 1.012929161234246e-05, + "loss": 0.3392, + "step": 18170 + }, + { + "epoch": 1.48, + "learning_rate": 1.0128748370273795e-05, + "loss": 0.4396, + "step": 18171 + }, + { + "epoch": 1.48, + "learning_rate": 1.012820512820513e-05, + "loss": 0.1475, + "step": 18172 + }, + { + "epoch": 1.48, + "learning_rate": 1.0127661886136463e-05, + "loss": 0.2985, + "step": 18173 + }, + { + "epoch": 1.48, + "learning_rate": 1.0127118644067798e-05, + "loss": 0.3075, + "step": 18174 + }, + { + "epoch": 1.48, + "learning_rate": 1.0126575401999132e-05, + "loss": 0.221, + "step": 18175 + }, + { + "epoch": 1.48, + "learning_rate": 1.0126032159930466e-05, + "loss": 0.2627, + "step": 18176 + }, + { + "epoch": 1.48, + "learning_rate": 1.01254889178618e-05, + "loss": 0.4208, + "step": 18177 + }, + { + "epoch": 1.48, + "learning_rate": 1.0124945675793135e-05, + "loss": 0.3397, + "step": 18178 + }, + { + "epoch": 1.48, + "learning_rate": 1.0124402433724469e-05, + "loss": 0.5993, + "step": 18179 + }, + { + "epoch": 1.48, + "learning_rate": 1.0123859191655803e-05, + "loss": 0.2861, + "step": 18180 + }, + { + "epoch": 1.48, + "learning_rate": 1.0123315949587136e-05, + "loss": 0.3735, + "step": 18181 + }, + { + "epoch": 1.48, + "learning_rate": 1.0122772707518471e-05, + "loss": 0.2661, + "step": 18182 + }, + { + "epoch": 1.48, + "learning_rate": 1.0122229465449804e-05, + "loss": 0.3364, + "step": 18183 + }, + { + "epoch": 1.48, + "learning_rate": 1.012168622338114e-05, + "loss": 0.378, + "step": 18184 + }, + { + "epoch": 1.48, + "learning_rate": 1.0121142981312472e-05, + "loss": 0.2974, + "step": 18185 + }, + { + "epoch": 1.48, + "learning_rate": 1.0120599739243808e-05, + "loss": 0.2885, + "step": 18186 + }, + { + "epoch": 1.48, + "learning_rate": 1.0120056497175141e-05, + "loss": 0.1154, + "step": 18187 + }, + { + "epoch": 1.48, + "learning_rate": 1.0119513255106477e-05, + "loss": 0.5329, + "step": 18188 + }, + { + "epoch": 1.48, + "learning_rate": 1.011897001303781e-05, + "loss": 0.4046, + "step": 18189 + }, + { + "epoch": 1.48, + "learning_rate": 1.0118426770969145e-05, + "loss": 0.5253, + "step": 18190 + }, + { + "epoch": 1.48, + "learning_rate": 1.0117883528900478e-05, + "loss": 0.2431, + "step": 18191 + }, + { + "epoch": 1.48, + "learning_rate": 1.0117340286831814e-05, + "loss": 0.2164, + "step": 18192 + }, + { + "epoch": 1.48, + "learning_rate": 1.0116797044763146e-05, + "loss": 0.4031, + "step": 18193 + }, + { + "epoch": 1.48, + "learning_rate": 1.0116253802694482e-05, + "loss": 0.2558, + "step": 18194 + }, + { + "epoch": 1.48, + "learning_rate": 1.0115710560625815e-05, + "loss": 0.1733, + "step": 18195 + }, + { + "epoch": 1.48, + "learning_rate": 1.011516731855715e-05, + "loss": 0.3552, + "step": 18196 + }, + { + "epoch": 1.48, + "learning_rate": 1.0114624076488483e-05, + "loss": 0.3718, + "step": 18197 + }, + { + "epoch": 1.48, + "learning_rate": 1.011408083441982e-05, + "loss": 0.2234, + "step": 18198 + }, + { + "epoch": 1.48, + "learning_rate": 1.0113537592351152e-05, + "loss": 0.2594, + "step": 18199 + }, + { + "epoch": 1.48, + "learning_rate": 1.0112994350282486e-05, + "loss": 0.2125, + "step": 18200 + }, + { + "epoch": 1.48, + "learning_rate": 1.0112451108213822e-05, + "loss": 0.1988, + "step": 18201 + }, + { + "epoch": 1.48, + "learning_rate": 1.0111907866145154e-05, + "loss": 0.3122, + "step": 18202 + }, + { + "epoch": 1.48, + "learning_rate": 1.011136462407649e-05, + "loss": 0.2874, + "step": 18203 + }, + { + "epoch": 1.48, + "learning_rate": 1.0110821382007823e-05, + "loss": 0.3413, + "step": 18204 + }, + { + "epoch": 1.48, + "learning_rate": 1.0110278139939159e-05, + "loss": 0.311, + "step": 18205 + }, + { + "epoch": 1.48, + "learning_rate": 1.0109734897870491e-05, + "loss": 0.182, + "step": 18206 + }, + { + "epoch": 1.48, + "learning_rate": 1.0109191655801827e-05, + "loss": 0.3736, + "step": 18207 + }, + { + "epoch": 1.48, + "learning_rate": 1.010864841373316e-05, + "loss": 0.3648, + "step": 18208 + }, + { + "epoch": 1.48, + "learning_rate": 1.0108105171664496e-05, + "loss": 0.2866, + "step": 18209 + }, + { + "epoch": 1.48, + "learning_rate": 1.0107561929595828e-05, + "loss": 0.5291, + "step": 18210 + }, + { + "epoch": 1.48, + "learning_rate": 1.0107018687527164e-05, + "loss": 0.3015, + "step": 18211 + }, + { + "epoch": 1.48, + "learning_rate": 1.0106475445458497e-05, + "loss": 0.1238, + "step": 18212 + }, + { + "epoch": 1.48, + "learning_rate": 1.0105932203389833e-05, + "loss": 0.2256, + "step": 18213 + }, + { + "epoch": 1.48, + "learning_rate": 1.0105388961321165e-05, + "loss": 0.7976, + "step": 18214 + }, + { + "epoch": 1.48, + "learning_rate": 1.0104845719252501e-05, + "loss": 0.2047, + "step": 18215 + }, + { + "epoch": 1.48, + "learning_rate": 1.0104302477183834e-05, + "loss": 0.4823, + "step": 18216 + }, + { + "epoch": 1.48, + "learning_rate": 1.010375923511517e-05, + "loss": 0.6705, + "step": 18217 + }, + { + "epoch": 1.48, + "learning_rate": 1.0103215993046502e-05, + "loss": 0.3234, + "step": 18218 + }, + { + "epoch": 1.48, + "learning_rate": 1.0102672750977836e-05, + "loss": 0.1522, + "step": 18219 + }, + { + "epoch": 1.48, + "learning_rate": 1.010212950890917e-05, + "loss": 0.2738, + "step": 18220 + }, + { + "epoch": 1.48, + "learning_rate": 1.0101586266840505e-05, + "loss": 0.3813, + "step": 18221 + }, + { + "epoch": 1.48, + "learning_rate": 1.0101043024771839e-05, + "loss": 0.2047, + "step": 18222 + }, + { + "epoch": 1.48, + "learning_rate": 1.0100499782703173e-05, + "loss": 0.2567, + "step": 18223 + }, + { + "epoch": 1.49, + "learning_rate": 1.0099956540634507e-05, + "loss": 0.1187, + "step": 18224 + }, + { + "epoch": 1.49, + "learning_rate": 1.0099413298565842e-05, + "loss": 0.3326, + "step": 18225 + }, + { + "epoch": 1.49, + "learning_rate": 1.0098870056497176e-05, + "loss": 0.2239, + "step": 18226 + }, + { + "epoch": 1.49, + "learning_rate": 1.009832681442851e-05, + "loss": 0.3661, + "step": 18227 + }, + { + "epoch": 1.49, + "learning_rate": 1.0097783572359844e-05, + "loss": 0.2218, + "step": 18228 + }, + { + "epoch": 1.49, + "learning_rate": 1.0097240330291179e-05, + "loss": 0.2587, + "step": 18229 + }, + { + "epoch": 1.49, + "learning_rate": 1.0096697088222513e-05, + "loss": 0.3481, + "step": 18230 + }, + { + "epoch": 1.49, + "learning_rate": 1.0096153846153847e-05, + "loss": 0.3043, + "step": 18231 + }, + { + "epoch": 1.49, + "learning_rate": 1.0095610604085181e-05, + "loss": 0.4897, + "step": 18232 + }, + { + "epoch": 1.49, + "learning_rate": 1.0095067362016516e-05, + "loss": 0.4387, + "step": 18233 + }, + { + "epoch": 1.49, + "learning_rate": 1.009452411994785e-05, + "loss": 0.522, + "step": 18234 + }, + { + "epoch": 1.49, + "learning_rate": 1.0093980877879184e-05, + "loss": 0.3375, + "step": 18235 + }, + { + "epoch": 1.49, + "learning_rate": 1.0093437635810518e-05, + "loss": 0.5635, + "step": 18236 + }, + { + "epoch": 1.49, + "learning_rate": 1.0092894393741852e-05, + "loss": 0.1283, + "step": 18237 + }, + { + "epoch": 1.49, + "learning_rate": 1.0092351151673185e-05, + "loss": 0.2073, + "step": 18238 + }, + { + "epoch": 1.49, + "learning_rate": 1.0091807909604521e-05, + "loss": 0.1147, + "step": 18239 + }, + { + "epoch": 1.49, + "learning_rate": 1.0091264667535853e-05, + "loss": 0.6798, + "step": 18240 + }, + { + "epoch": 1.49, + "learning_rate": 1.009072142546719e-05, + "loss": 0.5028, + "step": 18241 + }, + { + "epoch": 1.49, + "learning_rate": 1.0090178183398522e-05, + "loss": 0.3393, + "step": 18242 + }, + { + "epoch": 1.49, + "learning_rate": 1.0089634941329858e-05, + "loss": 0.3241, + "step": 18243 + }, + { + "epoch": 1.49, + "learning_rate": 1.008909169926119e-05, + "loss": 0.1573, + "step": 18244 + }, + { + "epoch": 1.49, + "learning_rate": 1.0088548457192526e-05, + "loss": 0.5588, + "step": 18245 + }, + { + "epoch": 1.49, + "learning_rate": 1.0088005215123859e-05, + "loss": 0.6086, + "step": 18246 + }, + { + "epoch": 1.49, + "learning_rate": 1.0087461973055195e-05, + "loss": 0.2316, + "step": 18247 + }, + { + "epoch": 1.49, + "learning_rate": 1.0086918730986527e-05, + "loss": 0.3783, + "step": 18248 + }, + { + "epoch": 1.49, + "learning_rate": 1.0086375488917863e-05, + "loss": 0.3752, + "step": 18249 + }, + { + "epoch": 1.49, + "learning_rate": 1.0085832246849196e-05, + "loss": 0.4162, + "step": 18250 + }, + { + "epoch": 1.49, + "eval_accuracy": 0.8445236882322975, + "eval_loss": 0.43524983525276184, + "eval_runtime": 22.2855, + "eval_samples_per_second": 440.42, + "eval_steps_per_second": 3.455, + "step": 18250 + }, + { + "epoch": 1.49, + "learning_rate": 1.0085289004780532e-05, + "loss": 0.2992, + "step": 18251 + }, + { + "epoch": 1.49, + "learning_rate": 1.0084745762711864e-05, + "loss": 0.1501, + "step": 18252 + }, + { + "epoch": 1.49, + "learning_rate": 1.00842025206432e-05, + "loss": 0.4443, + "step": 18253 + }, + { + "epoch": 1.49, + "learning_rate": 1.0083659278574533e-05, + "loss": 0.2679, + "step": 18254 + }, + { + "epoch": 1.49, + "learning_rate": 1.0083116036505869e-05, + "loss": 0.2406, + "step": 18255 + }, + { + "epoch": 1.49, + "learning_rate": 1.0082572794437203e-05, + "loss": 0.314, + "step": 18256 + }, + { + "epoch": 1.49, + "learning_rate": 1.0082029552368535e-05, + "loss": 0.1863, + "step": 18257 + }, + { + "epoch": 1.49, + "learning_rate": 1.0081486310299871e-05, + "loss": 0.2455, + "step": 18258 + }, + { + "epoch": 1.49, + "learning_rate": 1.0080943068231204e-05, + "loss": 0.2398, + "step": 18259 + }, + { + "epoch": 1.49, + "learning_rate": 1.008039982616254e-05, + "loss": 0.3135, + "step": 18260 + }, + { + "epoch": 1.49, + "learning_rate": 1.0079856584093872e-05, + "loss": 0.1665, + "step": 18261 + }, + { + "epoch": 1.49, + "learning_rate": 1.0079313342025208e-05, + "loss": 0.2703, + "step": 18262 + }, + { + "epoch": 1.49, + "learning_rate": 1.007877009995654e-05, + "loss": 0.3243, + "step": 18263 + }, + { + "epoch": 1.49, + "learning_rate": 1.0078226857887877e-05, + "loss": 0.2924, + "step": 18264 + }, + { + "epoch": 1.49, + "learning_rate": 1.007768361581921e-05, + "loss": 0.288, + "step": 18265 + }, + { + "epoch": 1.49, + "learning_rate": 1.0077140373750545e-05, + "loss": 0.3428, + "step": 18266 + }, + { + "epoch": 1.49, + "learning_rate": 1.0076597131681878e-05, + "loss": 0.2771, + "step": 18267 + }, + { + "epoch": 1.49, + "learning_rate": 1.0076053889613214e-05, + "loss": 0.0917, + "step": 18268 + }, + { + "epoch": 1.49, + "learning_rate": 1.0075510647544546e-05, + "loss": 0.3708, + "step": 18269 + }, + { + "epoch": 1.49, + "learning_rate": 1.0074967405475882e-05, + "loss": 0.6004, + "step": 18270 + }, + { + "epoch": 1.49, + "learning_rate": 1.0074424163407215e-05, + "loss": 0.35, + "step": 18271 + }, + { + "epoch": 1.49, + "learning_rate": 1.007388092133855e-05, + "loss": 0.2993, + "step": 18272 + }, + { + "epoch": 1.49, + "learning_rate": 1.0073337679269883e-05, + "loss": 0.1936, + "step": 18273 + }, + { + "epoch": 1.49, + "learning_rate": 1.0072794437201219e-05, + "loss": 0.3106, + "step": 18274 + }, + { + "epoch": 1.49, + "learning_rate": 1.0072251195132552e-05, + "loss": 0.3356, + "step": 18275 + }, + { + "epoch": 1.49, + "learning_rate": 1.0071707953063886e-05, + "loss": 0.4991, + "step": 18276 + }, + { + "epoch": 1.49, + "learning_rate": 1.007116471099522e-05, + "loss": 0.2396, + "step": 18277 + }, + { + "epoch": 1.49, + "learning_rate": 1.0070621468926554e-05, + "loss": 0.3089, + "step": 18278 + }, + { + "epoch": 1.49, + "learning_rate": 1.0070078226857888e-05, + "loss": 0.3872, + "step": 18279 + }, + { + "epoch": 1.49, + "learning_rate": 1.0069534984789223e-05, + "loss": 0.2419, + "step": 18280 + }, + { + "epoch": 1.49, + "learning_rate": 1.0068991742720557e-05, + "loss": 0.2047, + "step": 18281 + }, + { + "epoch": 1.49, + "learning_rate": 1.0068448500651891e-05, + "loss": 0.3283, + "step": 18282 + }, + { + "epoch": 1.49, + "learning_rate": 1.0067905258583225e-05, + "loss": 0.3644, + "step": 18283 + }, + { + "epoch": 1.49, + "learning_rate": 1.006736201651456e-05, + "loss": 0.3274, + "step": 18284 + }, + { + "epoch": 1.49, + "learning_rate": 1.0066818774445894e-05, + "loss": 0.5558, + "step": 18285 + }, + { + "epoch": 1.49, + "learning_rate": 1.0066275532377228e-05, + "loss": 0.2192, + "step": 18286 + }, + { + "epoch": 1.49, + "learning_rate": 1.0065732290308562e-05, + "loss": 0.2915, + "step": 18287 + }, + { + "epoch": 1.49, + "learning_rate": 1.0065189048239897e-05, + "loss": 0.407, + "step": 18288 + }, + { + "epoch": 1.49, + "learning_rate": 1.006464580617123e-05, + "loss": 0.5038, + "step": 18289 + }, + { + "epoch": 1.49, + "learning_rate": 1.0064102564102565e-05, + "loss": 0.3811, + "step": 18290 + }, + { + "epoch": 1.49, + "learning_rate": 1.00635593220339e-05, + "loss": 0.3523, + "step": 18291 + }, + { + "epoch": 1.49, + "learning_rate": 1.0063016079965233e-05, + "loss": 0.428, + "step": 18292 + }, + { + "epoch": 1.49, + "learning_rate": 1.006247283789657e-05, + "loss": 0.2121, + "step": 18293 + }, + { + "epoch": 1.49, + "learning_rate": 1.0061929595827902e-05, + "loss": 0.1174, + "step": 18294 + }, + { + "epoch": 1.49, + "learning_rate": 1.0061386353759234e-05, + "loss": 0.2359, + "step": 18295 + }, + { + "epoch": 1.49, + "learning_rate": 1.006084311169057e-05, + "loss": 0.2323, + "step": 18296 + }, + { + "epoch": 1.49, + "learning_rate": 1.0060299869621903e-05, + "loss": 0.5531, + "step": 18297 + }, + { + "epoch": 1.49, + "learning_rate": 1.0059756627553239e-05, + "loss": 0.4408, + "step": 18298 + }, + { + "epoch": 1.49, + "learning_rate": 1.0059213385484571e-05, + "loss": 0.2113, + "step": 18299 + }, + { + "epoch": 1.49, + "learning_rate": 1.0058670143415907e-05, + "loss": 0.343, + "step": 18300 + }, + { + "epoch": 1.49, + "learning_rate": 1.005812690134724e-05, + "loss": 0.162, + "step": 18301 + }, + { + "epoch": 1.49, + "learning_rate": 1.0057583659278576e-05, + "loss": 0.1295, + "step": 18302 + }, + { + "epoch": 1.49, + "learning_rate": 1.0057040417209908e-05, + "loss": 0.4257, + "step": 18303 + }, + { + "epoch": 1.49, + "learning_rate": 1.0056497175141244e-05, + "loss": 0.3491, + "step": 18304 + }, + { + "epoch": 1.49, + "learning_rate": 1.0055953933072577e-05, + "loss": 0.35, + "step": 18305 + }, + { + "epoch": 1.49, + "learning_rate": 1.0055410691003913e-05, + "loss": 0.5618, + "step": 18306 + }, + { + "epoch": 1.49, + "learning_rate": 1.0054867448935245e-05, + "loss": 0.3199, + "step": 18307 + }, + { + "epoch": 1.49, + "learning_rate": 1.0054324206866581e-05, + "loss": 0.3159, + "step": 18308 + }, + { + "epoch": 1.49, + "learning_rate": 1.0053780964797915e-05, + "loss": 0.265, + "step": 18309 + }, + { + "epoch": 1.49, + "learning_rate": 1.005323772272925e-05, + "loss": 0.4796, + "step": 18310 + }, + { + "epoch": 1.49, + "learning_rate": 1.0052694480660584e-05, + "loss": 0.2985, + "step": 18311 + }, + { + "epoch": 1.49, + "learning_rate": 1.0052151238591918e-05, + "loss": 0.3446, + "step": 18312 + }, + { + "epoch": 1.49, + "learning_rate": 1.0051607996523252e-05, + "loss": 0.2069, + "step": 18313 + }, + { + "epoch": 1.49, + "learning_rate": 1.0051064754454585e-05, + "loss": 0.2999, + "step": 18314 + }, + { + "epoch": 1.49, + "learning_rate": 1.005052151238592e-05, + "loss": 0.1986, + "step": 18315 + }, + { + "epoch": 1.49, + "learning_rate": 1.0049978270317253e-05, + "loss": 0.3592, + "step": 18316 + }, + { + "epoch": 1.49, + "learning_rate": 1.004943502824859e-05, + "loss": 0.3741, + "step": 18317 + }, + { + "epoch": 1.49, + "learning_rate": 1.0048891786179922e-05, + "loss": 0.4512, + "step": 18318 + }, + { + "epoch": 1.49, + "learning_rate": 1.0048348544111258e-05, + "loss": 0.3968, + "step": 18319 + }, + { + "epoch": 1.49, + "learning_rate": 1.004780530204259e-05, + "loss": 0.3038, + "step": 18320 + }, + { + "epoch": 1.49, + "learning_rate": 1.0047262059973926e-05, + "loss": 0.2931, + "step": 18321 + }, + { + "epoch": 1.49, + "learning_rate": 1.0046718817905259e-05, + "loss": 0.345, + "step": 18322 + }, + { + "epoch": 1.49, + "learning_rate": 1.0046175575836595e-05, + "loss": 0.2723, + "step": 18323 + }, + { + "epoch": 1.49, + "learning_rate": 1.0045632333767927e-05, + "loss": 0.607, + "step": 18324 + }, + { + "epoch": 1.49, + "learning_rate": 1.0045089091699263e-05, + "loss": 0.316, + "step": 18325 + }, + { + "epoch": 1.49, + "learning_rate": 1.0044545849630596e-05, + "loss": 0.3331, + "step": 18326 + }, + { + "epoch": 1.49, + "learning_rate": 1.0044002607561932e-05, + "loss": 0.263, + "step": 18327 + }, + { + "epoch": 1.49, + "learning_rate": 1.0043459365493264e-05, + "loss": 0.3385, + "step": 18328 + }, + { + "epoch": 1.49, + "learning_rate": 1.00429161234246e-05, + "loss": 0.3227, + "step": 18329 + }, + { + "epoch": 1.49, + "learning_rate": 1.0042372881355933e-05, + "loss": 0.1742, + "step": 18330 + }, + { + "epoch": 1.49, + "learning_rate": 1.0041829639287268e-05, + "loss": 0.4415, + "step": 18331 + }, + { + "epoch": 1.49, + "learning_rate": 1.0041286397218601e-05, + "loss": 0.2529, + "step": 18332 + }, + { + "epoch": 1.49, + "learning_rate": 1.0040743155149935e-05, + "loss": 0.7468, + "step": 18333 + }, + { + "epoch": 1.49, + "learning_rate": 1.004019991308127e-05, + "loss": 0.3308, + "step": 18334 + }, + { + "epoch": 1.49, + "learning_rate": 1.0039656671012604e-05, + "loss": 0.4649, + "step": 18335 + }, + { + "epoch": 1.49, + "learning_rate": 1.0039113428943938e-05, + "loss": 0.3746, + "step": 18336 + }, + { + "epoch": 1.49, + "learning_rate": 1.0038570186875272e-05, + "loss": 0.1958, + "step": 18337 + }, + { + "epoch": 1.49, + "learning_rate": 1.0038026944806606e-05, + "loss": 0.4711, + "step": 18338 + }, + { + "epoch": 1.49, + "learning_rate": 1.003748370273794e-05, + "loss": 0.3763, + "step": 18339 + }, + { + "epoch": 1.49, + "learning_rate": 1.0036940460669275e-05, + "loss": 0.3595, + "step": 18340 + }, + { + "epoch": 1.49, + "learning_rate": 1.0036397218600609e-05, + "loss": 0.2598, + "step": 18341 + }, + { + "epoch": 1.49, + "learning_rate": 1.0035853976531943e-05, + "loss": 0.3806, + "step": 18342 + }, + { + "epoch": 1.49, + "learning_rate": 1.0035310734463278e-05, + "loss": 0.2998, + "step": 18343 + }, + { + "epoch": 1.49, + "learning_rate": 1.0034767492394612e-05, + "loss": 0.3298, + "step": 18344 + }, + { + "epoch": 1.49, + "learning_rate": 1.0034224250325946e-05, + "loss": 0.4043, + "step": 18345 + }, + { + "epoch": 1.49, + "learning_rate": 1.0033681008257282e-05, + "loss": 0.4102, + "step": 18346 + }, + { + "epoch": 1.5, + "learning_rate": 1.0033137766188614e-05, + "loss": 0.348, + "step": 18347 + }, + { + "epoch": 1.5, + "learning_rate": 1.003259452411995e-05, + "loss": 0.3072, + "step": 18348 + }, + { + "epoch": 1.5, + "learning_rate": 1.0032051282051283e-05, + "loss": 0.1713, + "step": 18349 + }, + { + "epoch": 1.5, + "learning_rate": 1.0031508039982619e-05, + "loss": 0.2936, + "step": 18350 + }, + { + "epoch": 1.5, + "learning_rate": 1.0030964797913951e-05, + "loss": 0.3723, + "step": 18351 + }, + { + "epoch": 1.5, + "learning_rate": 1.0030421555845284e-05, + "loss": 0.2267, + "step": 18352 + }, + { + "epoch": 1.5, + "learning_rate": 1.002987831377662e-05, + "loss": 0.3514, + "step": 18353 + }, + { + "epoch": 1.5, + "learning_rate": 1.0029335071707952e-05, + "loss": 0.3587, + "step": 18354 + }, + { + "epoch": 1.5, + "learning_rate": 1.0028791829639288e-05, + "loss": 0.2543, + "step": 18355 + }, + { + "epoch": 1.5, + "learning_rate": 1.002824858757062e-05, + "loss": 0.3313, + "step": 18356 + }, + { + "epoch": 1.5, + "learning_rate": 1.0027705345501957e-05, + "loss": 0.3359, + "step": 18357 + }, + { + "epoch": 1.5, + "learning_rate": 1.002716210343329e-05, + "loss": 0.4541, + "step": 18358 + }, + { + "epoch": 1.5, + "learning_rate": 1.0026618861364625e-05, + "loss": 0.1915, + "step": 18359 + }, + { + "epoch": 1.5, + "learning_rate": 1.0026075619295958e-05, + "loss": 0.5423, + "step": 18360 + }, + { + "epoch": 1.5, + "learning_rate": 1.0025532377227294e-05, + "loss": 0.1281, + "step": 18361 + }, + { + "epoch": 1.5, + "learning_rate": 1.0024989135158626e-05, + "loss": 0.1974, + "step": 18362 + }, + { + "epoch": 1.5, + "learning_rate": 1.0024445893089962e-05, + "loss": 0.2299, + "step": 18363 + }, + { + "epoch": 1.5, + "learning_rate": 1.0023902651021296e-05, + "loss": 0.2433, + "step": 18364 + }, + { + "epoch": 1.5, + "learning_rate": 1.002335940895263e-05, + "loss": 0.3084, + "step": 18365 + }, + { + "epoch": 1.5, + "learning_rate": 1.0022816166883965e-05, + "loss": 0.4541, + "step": 18366 + }, + { + "epoch": 1.5, + "learning_rate": 1.0022272924815299e-05, + "loss": 0.5981, + "step": 18367 + }, + { + "epoch": 1.5, + "learning_rate": 1.0021729682746633e-05, + "loss": 0.6241, + "step": 18368 + }, + { + "epoch": 1.5, + "learning_rate": 1.0021186440677968e-05, + "loss": 0.4643, + "step": 18369 + }, + { + "epoch": 1.5, + "learning_rate": 1.0020643198609302e-05, + "loss": 0.3695, + "step": 18370 + }, + { + "epoch": 1.5, + "learning_rate": 1.0020099956540634e-05, + "loss": 0.0777, + "step": 18371 + }, + { + "epoch": 1.5, + "learning_rate": 1.001955671447197e-05, + "loss": 0.1918, + "step": 18372 + }, + { + "epoch": 1.5, + "learning_rate": 1.0019013472403303e-05, + "loss": 0.2311, + "step": 18373 + }, + { + "epoch": 1.5, + "learning_rate": 1.0018470230334639e-05, + "loss": 0.4106, + "step": 18374 + }, + { + "epoch": 1.5, + "learning_rate": 1.0017926988265971e-05, + "loss": 0.3351, + "step": 18375 + }, + { + "epoch": 1.5, + "learning_rate": 1.0017383746197307e-05, + "loss": 0.3561, + "step": 18376 + }, + { + "epoch": 1.5, + "learning_rate": 1.001684050412864e-05, + "loss": 0.2207, + "step": 18377 + }, + { + "epoch": 1.5, + "learning_rate": 1.0016297262059976e-05, + "loss": 0.2249, + "step": 18378 + }, + { + "epoch": 1.5, + "learning_rate": 1.0015754019991308e-05, + "loss": 0.2812, + "step": 18379 + }, + { + "epoch": 1.5, + "learning_rate": 1.0015210777922644e-05, + "loss": 0.2822, + "step": 18380 + }, + { + "epoch": 1.5, + "learning_rate": 1.0014667535853977e-05, + "loss": 0.5652, + "step": 18381 + }, + { + "epoch": 1.5, + "learning_rate": 1.0014124293785313e-05, + "loss": 0.5103, + "step": 18382 + }, + { + "epoch": 1.5, + "learning_rate": 1.0013581051716645e-05, + "loss": 0.1916, + "step": 18383 + }, + { + "epoch": 1.5, + "learning_rate": 1.0013037809647981e-05, + "loss": 0.2145, + "step": 18384 + }, + { + "epoch": 1.5, + "learning_rate": 1.0012494567579314e-05, + "loss": 0.3258, + "step": 18385 + }, + { + "epoch": 1.5, + "learning_rate": 1.001195132551065e-05, + "loss": 0.5159, + "step": 18386 + }, + { + "epoch": 1.5, + "learning_rate": 1.0011408083441982e-05, + "loss": 0.4652, + "step": 18387 + }, + { + "epoch": 1.5, + "learning_rate": 1.0010864841373318e-05, + "loss": 0.1834, + "step": 18388 + }, + { + "epoch": 1.5, + "learning_rate": 1.001032159930465e-05, + "loss": 0.3148, + "step": 18389 + }, + { + "epoch": 1.5, + "learning_rate": 1.0009778357235985e-05, + "loss": 0.1985, + "step": 18390 + }, + { + "epoch": 1.5, + "learning_rate": 1.0009235115167319e-05, + "loss": 0.5199, + "step": 18391 + }, + { + "epoch": 1.5, + "learning_rate": 1.0008691873098653e-05, + "loss": 0.6885, + "step": 18392 + }, + { + "epoch": 1.5, + "learning_rate": 1.0008148631029987e-05, + "loss": 0.1108, + "step": 18393 + }, + { + "epoch": 1.5, + "learning_rate": 1.0007605388961322e-05, + "loss": 0.2995, + "step": 18394 + }, + { + "epoch": 1.5, + "learning_rate": 1.0007062146892656e-05, + "loss": 0.4049, + "step": 18395 + }, + { + "epoch": 1.5, + "learning_rate": 1.000651890482399e-05, + "loss": 0.2533, + "step": 18396 + }, + { + "epoch": 1.5, + "learning_rate": 1.0005975662755324e-05, + "loss": 0.3982, + "step": 18397 + }, + { + "epoch": 1.5, + "learning_rate": 1.0005432420686659e-05, + "loss": 0.1664, + "step": 18398 + }, + { + "epoch": 1.5, + "learning_rate": 1.0004889178617993e-05, + "loss": 0.8779, + "step": 18399 + }, + { + "epoch": 1.5, + "learning_rate": 1.0004345936549327e-05, + "loss": 0.2919, + "step": 18400 + }, + { + "epoch": 1.5, + "learning_rate": 1.0003802694480663e-05, + "loss": 0.281, + "step": 18401 + }, + { + "epoch": 1.5, + "learning_rate": 1.0003259452411995e-05, + "loss": 0.5128, + "step": 18402 + }, + { + "epoch": 1.5, + "learning_rate": 1.0002716210343331e-05, + "loss": 0.3411, + "step": 18403 + }, + { + "epoch": 1.5, + "learning_rate": 1.0002172968274664e-05, + "loss": 0.1982, + "step": 18404 + }, + { + "epoch": 1.5, + "learning_rate": 1.0001629726206e-05, + "loss": 0.2575, + "step": 18405 + }, + { + "epoch": 1.5, + "learning_rate": 1.0001086484137332e-05, + "loss": 0.5147, + "step": 18406 + }, + { + "epoch": 1.5, + "learning_rate": 1.0000543242068668e-05, + "loss": 0.3543, + "step": 18407 + }, + { + "epoch": 1.5, + "learning_rate": 1e-05, + "loss": 0.3773, + "step": 18408 + }, + { + "epoch": 1.5, + "learning_rate": 9.999456757931335e-06, + "loss": 0.2403, + "step": 18409 + }, + { + "epoch": 1.5, + "learning_rate": 9.99891351586267e-06, + "loss": 0.3346, + "step": 18410 + }, + { + "epoch": 1.5, + "learning_rate": 9.998370273794004e-06, + "loss": 0.5049, + "step": 18411 + }, + { + "epoch": 1.5, + "learning_rate": 9.997827031725338e-06, + "loss": 0.4535, + "step": 18412 + }, + { + "epoch": 1.5, + "learning_rate": 9.997283789656672e-06, + "loss": 0.2995, + "step": 18413 + }, + { + "epoch": 1.5, + "learning_rate": 9.996740547588006e-06, + "loss": 0.482, + "step": 18414 + }, + { + "epoch": 1.5, + "learning_rate": 9.99619730551934e-06, + "loss": 0.3457, + "step": 18415 + }, + { + "epoch": 1.5, + "learning_rate": 9.995654063450675e-06, + "loss": 0.3912, + "step": 18416 + }, + { + "epoch": 1.5, + "learning_rate": 9.995110821382009e-06, + "loss": 0.2683, + "step": 18417 + }, + { + "epoch": 1.5, + "learning_rate": 9.994567579313343e-06, + "loss": 0.6439, + "step": 18418 + }, + { + "epoch": 1.5, + "learning_rate": 9.994024337244677e-06, + "loss": 0.3731, + "step": 18419 + }, + { + "epoch": 1.5, + "learning_rate": 9.993481095176012e-06, + "loss": 0.3843, + "step": 18420 + }, + { + "epoch": 1.5, + "learning_rate": 9.992937853107346e-06, + "loss": 0.405, + "step": 18421 + }, + { + "epoch": 1.5, + "learning_rate": 9.99239461103868e-06, + "loss": 0.2174, + "step": 18422 + }, + { + "epoch": 1.5, + "learning_rate": 9.991851368970014e-06, + "loss": 0.2255, + "step": 18423 + }, + { + "epoch": 1.5, + "learning_rate": 9.991308126901349e-06, + "loss": 0.219, + "step": 18424 + }, + { + "epoch": 1.5, + "learning_rate": 9.990764884832683e-06, + "loss": 0.2479, + "step": 18425 + }, + { + "epoch": 1.5, + "learning_rate": 9.990221642764017e-06, + "loss": 0.3194, + "step": 18426 + }, + { + "epoch": 1.5, + "learning_rate": 9.989678400695351e-06, + "loss": 0.2343, + "step": 18427 + }, + { + "epoch": 1.5, + "learning_rate": 9.989135158626685e-06, + "loss": 0.6043, + "step": 18428 + }, + { + "epoch": 1.5, + "learning_rate": 9.98859191655802e-06, + "loss": 0.4781, + "step": 18429 + }, + { + "epoch": 1.5, + "learning_rate": 9.988048674489354e-06, + "loss": 0.2529, + "step": 18430 + }, + { + "epoch": 1.5, + "learning_rate": 9.987505432420688e-06, + "loss": 0.2976, + "step": 18431 + }, + { + "epoch": 1.5, + "learning_rate": 9.986962190352022e-06, + "loss": 0.7786, + "step": 18432 + }, + { + "epoch": 1.5, + "learning_rate": 9.986418948283357e-06, + "loss": 0.3092, + "step": 18433 + }, + { + "epoch": 1.5, + "learning_rate": 9.98587570621469e-06, + "loss": 0.1195, + "step": 18434 + }, + { + "epoch": 1.5, + "learning_rate": 9.985332464146025e-06, + "loss": 0.3367, + "step": 18435 + }, + { + "epoch": 1.5, + "learning_rate": 9.98478922207736e-06, + "loss": 0.1143, + "step": 18436 + }, + { + "epoch": 1.5, + "learning_rate": 9.984245980008692e-06, + "loss": 0.4908, + "step": 18437 + }, + { + "epoch": 1.5, + "learning_rate": 9.983702737940026e-06, + "loss": 0.3559, + "step": 18438 + }, + { + "epoch": 1.5, + "learning_rate": 9.98315949587136e-06, + "loss": 0.1766, + "step": 18439 + }, + { + "epoch": 1.5, + "learning_rate": 9.982616253802695e-06, + "loss": 0.3572, + "step": 18440 + }, + { + "epoch": 1.5, + "learning_rate": 9.982073011734029e-06, + "loss": 0.2354, + "step": 18441 + }, + { + "epoch": 1.5, + "learning_rate": 9.981529769665363e-06, + "loss": 0.4708, + "step": 18442 + }, + { + "epoch": 1.5, + "learning_rate": 9.980986527596697e-06, + "loss": 0.4981, + "step": 18443 + }, + { + "epoch": 1.5, + "learning_rate": 9.980443285528031e-06, + "loss": 0.4227, + "step": 18444 + }, + { + "epoch": 1.5, + "learning_rate": 9.979900043459366e-06, + "loss": 0.4646, + "step": 18445 + }, + { + "epoch": 1.5, + "learning_rate": 9.9793568013907e-06, + "loss": 0.4067, + "step": 18446 + }, + { + "epoch": 1.5, + "learning_rate": 9.978813559322034e-06, + "loss": 0.293, + "step": 18447 + }, + { + "epoch": 1.5, + "learning_rate": 9.978270317253368e-06, + "loss": 0.3978, + "step": 18448 + }, + { + "epoch": 1.5, + "learning_rate": 9.977727075184703e-06, + "loss": 0.2269, + "step": 18449 + }, + { + "epoch": 1.5, + "learning_rate": 9.977183833116037e-06, + "loss": 0.2284, + "step": 18450 + }, + { + "epoch": 1.5, + "learning_rate": 9.976640591047371e-06, + "loss": 0.2426, + "step": 18451 + }, + { + "epoch": 1.5, + "learning_rate": 9.976097348978705e-06, + "loss": 0.473, + "step": 18452 + }, + { + "epoch": 1.5, + "learning_rate": 9.97555410691004e-06, + "loss": 0.5513, + "step": 18453 + }, + { + "epoch": 1.5, + "learning_rate": 9.975010864841375e-06, + "loss": 0.3445, + "step": 18454 + }, + { + "epoch": 1.5, + "learning_rate": 9.97446762277271e-06, + "loss": 0.208, + "step": 18455 + }, + { + "epoch": 1.5, + "learning_rate": 9.973924380704042e-06, + "loss": 0.4188, + "step": 18456 + }, + { + "epoch": 1.5, + "learning_rate": 9.973381138635376e-06, + "loss": 0.4816, + "step": 18457 + }, + { + "epoch": 1.5, + "learning_rate": 9.97283789656671e-06, + "loss": 0.2311, + "step": 18458 + }, + { + "epoch": 1.5, + "learning_rate": 9.972294654498045e-06, + "loss": 0.4194, + "step": 18459 + }, + { + "epoch": 1.5, + "learning_rate": 9.971751412429379e-06, + "loss": 0.4209, + "step": 18460 + }, + { + "epoch": 1.5, + "learning_rate": 9.971208170360713e-06, + "loss": 0.5437, + "step": 18461 + }, + { + "epoch": 1.5, + "learning_rate": 9.970664928292048e-06, + "loss": 0.2193, + "step": 18462 + }, + { + "epoch": 1.5, + "learning_rate": 9.970121686223382e-06, + "loss": 0.4634, + "step": 18463 + }, + { + "epoch": 1.5, + "learning_rate": 9.969578444154716e-06, + "loss": 0.5287, + "step": 18464 + }, + { + "epoch": 1.5, + "learning_rate": 9.96903520208605e-06, + "loss": 0.3257, + "step": 18465 + }, + { + "epoch": 1.5, + "learning_rate": 9.968491960017384e-06, + "loss": 0.1599, + "step": 18466 + }, + { + "epoch": 1.5, + "learning_rate": 9.967948717948719e-06, + "loss": 0.2544, + "step": 18467 + }, + { + "epoch": 1.5, + "learning_rate": 9.967405475880053e-06, + "loss": 0.3416, + "step": 18468 + }, + { + "epoch": 1.5, + "learning_rate": 9.966862233811387e-06, + "loss": 0.1528, + "step": 18469 + }, + { + "epoch": 1.51, + "learning_rate": 9.966318991742721e-06, + "loss": 0.3051, + "step": 18470 + }, + { + "epoch": 1.51, + "learning_rate": 9.965775749674056e-06, + "loss": 0.3187, + "step": 18471 + }, + { + "epoch": 1.51, + "learning_rate": 9.96523250760539e-06, + "loss": 0.2666, + "step": 18472 + }, + { + "epoch": 1.51, + "learning_rate": 9.964689265536724e-06, + "loss": 0.5623, + "step": 18473 + }, + { + "epoch": 1.51, + "learning_rate": 9.964146023468058e-06, + "loss": 0.3174, + "step": 18474 + }, + { + "epoch": 1.51, + "learning_rate": 9.963602781399393e-06, + "loss": 0.1803, + "step": 18475 + }, + { + "epoch": 1.51, + "learning_rate": 9.963059539330727e-06, + "loss": 0.6064, + "step": 18476 + }, + { + "epoch": 1.51, + "learning_rate": 9.962516297262061e-06, + "loss": 0.395, + "step": 18477 + }, + { + "epoch": 1.51, + "learning_rate": 9.961973055193395e-06, + "loss": 0.3723, + "step": 18478 + }, + { + "epoch": 1.51, + "learning_rate": 9.96142981312473e-06, + "loss": 0.6393, + "step": 18479 + }, + { + "epoch": 1.51, + "learning_rate": 9.960886571056064e-06, + "loss": 0.4691, + "step": 18480 + }, + { + "epoch": 1.51, + "learning_rate": 9.960343328987398e-06, + "loss": 0.3542, + "step": 18481 + }, + { + "epoch": 1.51, + "learning_rate": 9.959800086918732e-06, + "loss": 0.5378, + "step": 18482 + }, + { + "epoch": 1.51, + "learning_rate": 9.959256844850066e-06, + "loss": 0.1907, + "step": 18483 + }, + { + "epoch": 1.51, + "learning_rate": 9.9587136027814e-06, + "loss": 0.3778, + "step": 18484 + }, + { + "epoch": 1.51, + "learning_rate": 9.958170360712735e-06, + "loss": 0.3818, + "step": 18485 + }, + { + "epoch": 1.51, + "learning_rate": 9.957627118644069e-06, + "loss": 0.254, + "step": 18486 + }, + { + "epoch": 1.51, + "learning_rate": 9.957083876575403e-06, + "loss": 0.3806, + "step": 18487 + }, + { + "epoch": 1.51, + "learning_rate": 9.956540634506738e-06, + "loss": 0.5257, + "step": 18488 + }, + { + "epoch": 1.51, + "learning_rate": 9.955997392438072e-06, + "loss": 0.1652, + "step": 18489 + }, + { + "epoch": 1.51, + "learning_rate": 9.955454150369406e-06, + "loss": 0.2284, + "step": 18490 + }, + { + "epoch": 1.51, + "learning_rate": 9.95491090830074e-06, + "loss": 0.2329, + "step": 18491 + }, + { + "epoch": 1.51, + "learning_rate": 9.954367666232074e-06, + "loss": 0.2938, + "step": 18492 + }, + { + "epoch": 1.51, + "learning_rate": 9.953824424163409e-06, + "loss": 0.2265, + "step": 18493 + }, + { + "epoch": 1.51, + "learning_rate": 9.953281182094741e-06, + "loss": 0.3164, + "step": 18494 + }, + { + "epoch": 1.51, + "learning_rate": 9.952737940026075e-06, + "loss": 0.4021, + "step": 18495 + }, + { + "epoch": 1.51, + "learning_rate": 9.95219469795741e-06, + "loss": 0.5061, + "step": 18496 + }, + { + "epoch": 1.51, + "learning_rate": 9.951651455888744e-06, + "loss": 0.3206, + "step": 18497 + }, + { + "epoch": 1.51, + "learning_rate": 9.951108213820078e-06, + "loss": 0.3684, + "step": 18498 + }, + { + "epoch": 1.51, + "learning_rate": 9.950564971751412e-06, + "loss": 0.1835, + "step": 18499 + }, + { + "epoch": 1.51, + "learning_rate": 9.950021729682747e-06, + "loss": 0.306, + "step": 18500 + }, + { + "epoch": 1.51, + "eval_accuracy": 0.8412633723892002, + "eval_loss": 0.43748268485069275, + "eval_runtime": 22.3493, + "eval_samples_per_second": 439.163, + "eval_steps_per_second": 3.445, + "step": 18500 + }, + { + "epoch": 1.51, + "learning_rate": 9.949478487614081e-06, + "loss": 0.4302, + "step": 18501 + }, + { + "epoch": 1.51, + "learning_rate": 9.948935245545415e-06, + "loss": 0.3576, + "step": 18502 + }, + { + "epoch": 1.51, + "learning_rate": 9.94839200347675e-06, + "loss": 0.3517, + "step": 18503 + }, + { + "epoch": 1.51, + "learning_rate": 9.947848761408084e-06, + "loss": 0.2328, + "step": 18504 + }, + { + "epoch": 1.51, + "learning_rate": 9.947305519339418e-06, + "loss": 0.1866, + "step": 18505 + }, + { + "epoch": 1.51, + "learning_rate": 9.946762277270752e-06, + "loss": 0.2537, + "step": 18506 + }, + { + "epoch": 1.51, + "learning_rate": 9.946219035202086e-06, + "loss": 0.2487, + "step": 18507 + }, + { + "epoch": 1.51, + "learning_rate": 9.945675793133422e-06, + "loss": 0.2413, + "step": 18508 + }, + { + "epoch": 1.51, + "learning_rate": 9.945132551064756e-06, + "loss": 0.5463, + "step": 18509 + }, + { + "epoch": 1.51, + "learning_rate": 9.94458930899609e-06, + "loss": 0.4501, + "step": 18510 + }, + { + "epoch": 1.51, + "learning_rate": 9.944046066927425e-06, + "loss": 0.3765, + "step": 18511 + }, + { + "epoch": 1.51, + "learning_rate": 9.943502824858759e-06, + "loss": 0.4339, + "step": 18512 + }, + { + "epoch": 1.51, + "learning_rate": 9.942959582790092e-06, + "loss": 0.2907, + "step": 18513 + }, + { + "epoch": 1.51, + "learning_rate": 9.942416340721426e-06, + "loss": 0.3814, + "step": 18514 + }, + { + "epoch": 1.51, + "learning_rate": 9.94187309865276e-06, + "loss": 0.3426, + "step": 18515 + }, + { + "epoch": 1.51, + "learning_rate": 9.941329856584094e-06, + "loss": 0.2941, + "step": 18516 + }, + { + "epoch": 1.51, + "learning_rate": 9.940786614515429e-06, + "loss": 0.1858, + "step": 18517 + }, + { + "epoch": 1.51, + "learning_rate": 9.940243372446763e-06, + "loss": 0.3419, + "step": 18518 + }, + { + "epoch": 1.51, + "learning_rate": 9.939700130378097e-06, + "loss": 0.3483, + "step": 18519 + }, + { + "epoch": 1.51, + "learning_rate": 9.939156888309431e-06, + "loss": 0.2158, + "step": 18520 + }, + { + "epoch": 1.51, + "learning_rate": 9.938613646240765e-06, + "loss": 0.2067, + "step": 18521 + }, + { + "epoch": 1.51, + "learning_rate": 9.9380704041721e-06, + "loss": 0.3858, + "step": 18522 + }, + { + "epoch": 1.51, + "learning_rate": 9.937527162103434e-06, + "loss": 0.5294, + "step": 18523 + }, + { + "epoch": 1.51, + "learning_rate": 9.936983920034768e-06, + "loss": 0.225, + "step": 18524 + }, + { + "epoch": 1.51, + "learning_rate": 9.936440677966102e-06, + "loss": 0.3893, + "step": 18525 + }, + { + "epoch": 1.51, + "learning_rate": 9.935897435897437e-06, + "loss": 0.7154, + "step": 18526 + }, + { + "epoch": 1.51, + "learning_rate": 9.935354193828771e-06, + "loss": 0.5588, + "step": 18527 + }, + { + "epoch": 1.51, + "learning_rate": 9.934810951760105e-06, + "loss": 0.3847, + "step": 18528 + }, + { + "epoch": 1.51, + "learning_rate": 9.93426770969144e-06, + "loss": 0.4225, + "step": 18529 + }, + { + "epoch": 1.51, + "learning_rate": 9.933724467622774e-06, + "loss": 0.3904, + "step": 18530 + }, + { + "epoch": 1.51, + "learning_rate": 9.933181225554108e-06, + "loss": 0.4327, + "step": 18531 + }, + { + "epoch": 1.51, + "learning_rate": 9.932637983485442e-06, + "loss": 0.199, + "step": 18532 + }, + { + "epoch": 1.51, + "learning_rate": 9.932094741416776e-06, + "loss": 0.1775, + "step": 18533 + }, + { + "epoch": 1.51, + "learning_rate": 9.93155149934811e-06, + "loss": 0.1113, + "step": 18534 + }, + { + "epoch": 1.51, + "learning_rate": 9.931008257279445e-06, + "loss": 0.1996, + "step": 18535 + }, + { + "epoch": 1.51, + "learning_rate": 9.930465015210779e-06, + "loss": 0.2071, + "step": 18536 + }, + { + "epoch": 1.51, + "learning_rate": 9.929921773142113e-06, + "loss": 0.5852, + "step": 18537 + }, + { + "epoch": 1.51, + "learning_rate": 9.929378531073447e-06, + "loss": 0.4285, + "step": 18538 + }, + { + "epoch": 1.51, + "learning_rate": 9.928835289004782e-06, + "loss": 0.228, + "step": 18539 + }, + { + "epoch": 1.51, + "learning_rate": 9.928292046936116e-06, + "loss": 0.3518, + "step": 18540 + }, + { + "epoch": 1.51, + "learning_rate": 9.92774880486745e-06, + "loss": 0.3526, + "step": 18541 + }, + { + "epoch": 1.51, + "learning_rate": 9.927205562798784e-06, + "loss": 0.2619, + "step": 18542 + }, + { + "epoch": 1.51, + "learning_rate": 9.926662320730119e-06, + "loss": 0.1144, + "step": 18543 + }, + { + "epoch": 1.51, + "learning_rate": 9.926119078661453e-06, + "loss": 0.1756, + "step": 18544 + }, + { + "epoch": 1.51, + "learning_rate": 9.925575836592787e-06, + "loss": 0.3873, + "step": 18545 + }, + { + "epoch": 1.51, + "learning_rate": 9.925032594524121e-06, + "loss": 0.245, + "step": 18546 + }, + { + "epoch": 1.51, + "learning_rate": 9.924489352455455e-06, + "loss": 0.1941, + "step": 18547 + }, + { + "epoch": 1.51, + "learning_rate": 9.92394611038679e-06, + "loss": 0.4354, + "step": 18548 + }, + { + "epoch": 1.51, + "learning_rate": 9.923402868318124e-06, + "loss": 0.1578, + "step": 18549 + }, + { + "epoch": 1.51, + "learning_rate": 9.922859626249458e-06, + "loss": 0.1757, + "step": 18550 + }, + { + "epoch": 1.51, + "learning_rate": 9.92231638418079e-06, + "loss": 0.4285, + "step": 18551 + }, + { + "epoch": 1.51, + "learning_rate": 9.921773142112125e-06, + "loss": 0.3624, + "step": 18552 + }, + { + "epoch": 1.51, + "learning_rate": 9.92122990004346e-06, + "loss": 0.3979, + "step": 18553 + }, + { + "epoch": 1.51, + "learning_rate": 9.920686657974793e-06, + "loss": 0.5957, + "step": 18554 + }, + { + "epoch": 1.51, + "learning_rate": 9.920143415906128e-06, + "loss": 0.1763, + "step": 18555 + }, + { + "epoch": 1.51, + "learning_rate": 9.919600173837462e-06, + "loss": 0.7697, + "step": 18556 + }, + { + "epoch": 1.51, + "learning_rate": 9.919056931768796e-06, + "loss": 0.2691, + "step": 18557 + }, + { + "epoch": 1.51, + "learning_rate": 9.91851368970013e-06, + "loss": 0.2094, + "step": 18558 + }, + { + "epoch": 1.51, + "learning_rate": 9.917970447631465e-06, + "loss": 0.3226, + "step": 18559 + }, + { + "epoch": 1.51, + "learning_rate": 9.917427205562799e-06, + "loss": 0.4156, + "step": 18560 + }, + { + "epoch": 1.51, + "learning_rate": 9.916883963494133e-06, + "loss": 0.1884, + "step": 18561 + }, + { + "epoch": 1.51, + "learning_rate": 9.916340721425469e-06, + "loss": 0.4341, + "step": 18562 + }, + { + "epoch": 1.51, + "learning_rate": 9.915797479356803e-06, + "loss": 0.3471, + "step": 18563 + }, + { + "epoch": 1.51, + "learning_rate": 9.915254237288137e-06, + "loss": 0.4313, + "step": 18564 + }, + { + "epoch": 1.51, + "learning_rate": 9.914710995219472e-06, + "loss": 0.5383, + "step": 18565 + }, + { + "epoch": 1.51, + "learning_rate": 9.914167753150806e-06, + "loss": 0.3533, + "step": 18566 + }, + { + "epoch": 1.51, + "learning_rate": 9.91362451108214e-06, + "loss": 0.2421, + "step": 18567 + }, + { + "epoch": 1.51, + "learning_rate": 9.913081269013474e-06, + "loss": 0.2016, + "step": 18568 + }, + { + "epoch": 1.51, + "learning_rate": 9.912538026944809e-06, + "loss": 0.4618, + "step": 18569 + }, + { + "epoch": 1.51, + "learning_rate": 9.911994784876141e-06, + "loss": 0.1905, + "step": 18570 + }, + { + "epoch": 1.51, + "learning_rate": 9.911451542807475e-06, + "loss": 0.2664, + "step": 18571 + }, + { + "epoch": 1.51, + "learning_rate": 9.91090830073881e-06, + "loss": 0.1603, + "step": 18572 + }, + { + "epoch": 1.51, + "learning_rate": 9.910365058670144e-06, + "loss": 0.4226, + "step": 18573 + }, + { + "epoch": 1.51, + "learning_rate": 9.909821816601478e-06, + "loss": 0.2408, + "step": 18574 + }, + { + "epoch": 1.51, + "learning_rate": 9.909278574532812e-06, + "loss": 0.455, + "step": 18575 + }, + { + "epoch": 1.51, + "learning_rate": 9.908735332464146e-06, + "loss": 0.2455, + "step": 18576 + }, + { + "epoch": 1.51, + "learning_rate": 9.90819209039548e-06, + "loss": 0.3736, + "step": 18577 + }, + { + "epoch": 1.51, + "learning_rate": 9.907648848326815e-06, + "loss": 0.2818, + "step": 18578 + }, + { + "epoch": 1.51, + "learning_rate": 9.90710560625815e-06, + "loss": 0.322, + "step": 18579 + }, + { + "epoch": 1.51, + "learning_rate": 9.906562364189483e-06, + "loss": 0.3716, + "step": 18580 + }, + { + "epoch": 1.51, + "learning_rate": 9.906019122120818e-06, + "loss": 0.2848, + "step": 18581 + }, + { + "epoch": 1.51, + "learning_rate": 9.905475880052152e-06, + "loss": 0.3842, + "step": 18582 + }, + { + "epoch": 1.51, + "learning_rate": 9.904932637983486e-06, + "loss": 0.4075, + "step": 18583 + }, + { + "epoch": 1.51, + "learning_rate": 9.90438939591482e-06, + "loss": 0.1601, + "step": 18584 + }, + { + "epoch": 1.51, + "learning_rate": 9.903846153846155e-06, + "loss": 0.2662, + "step": 18585 + }, + { + "epoch": 1.51, + "learning_rate": 9.903302911777489e-06, + "loss": 0.2126, + "step": 18586 + }, + { + "epoch": 1.51, + "learning_rate": 9.902759669708823e-06, + "loss": 0.2017, + "step": 18587 + }, + { + "epoch": 1.51, + "learning_rate": 9.902216427640157e-06, + "loss": 0.4596, + "step": 18588 + }, + { + "epoch": 1.51, + "learning_rate": 9.901673185571491e-06, + "loss": 0.3537, + "step": 18589 + }, + { + "epoch": 1.51, + "learning_rate": 9.901129943502826e-06, + "loss": 0.2943, + "step": 18590 + }, + { + "epoch": 1.51, + "learning_rate": 9.90058670143416e-06, + "loss": 0.7052, + "step": 18591 + }, + { + "epoch": 1.51, + "learning_rate": 9.900043459365494e-06, + "loss": 0.4445, + "step": 18592 + }, + { + "epoch": 1.52, + "learning_rate": 9.899500217296828e-06, + "loss": 0.1874, + "step": 18593 + }, + { + "epoch": 1.52, + "learning_rate": 9.898956975228163e-06, + "loss": 0.2885, + "step": 18594 + }, + { + "epoch": 1.52, + "learning_rate": 9.898413733159497e-06, + "loss": 0.2596, + "step": 18595 + }, + { + "epoch": 1.52, + "learning_rate": 9.897870491090831e-06, + "loss": 0.5672, + "step": 18596 + }, + { + "epoch": 1.52, + "learning_rate": 9.897327249022165e-06, + "loss": 0.5157, + "step": 18597 + }, + { + "epoch": 1.52, + "learning_rate": 9.8967840069535e-06, + "loss": 0.1091, + "step": 18598 + }, + { + "epoch": 1.52, + "learning_rate": 9.896240764884834e-06, + "loss": 0.367, + "step": 18599 + }, + { + "epoch": 1.52, + "learning_rate": 9.895697522816168e-06, + "loss": 0.3642, + "step": 18600 + }, + { + "epoch": 1.52, + "learning_rate": 9.895154280747502e-06, + "loss": 0.3043, + "step": 18601 + }, + { + "epoch": 1.52, + "learning_rate": 9.894611038678836e-06, + "loss": 0.2657, + "step": 18602 + }, + { + "epoch": 1.52, + "learning_rate": 9.89406779661017e-06, + "loss": 0.4667, + "step": 18603 + }, + { + "epoch": 1.52, + "learning_rate": 9.893524554541505e-06, + "loss": 0.4157, + "step": 18604 + }, + { + "epoch": 1.52, + "learning_rate": 9.89298131247284e-06, + "loss": 0.3451, + "step": 18605 + }, + { + "epoch": 1.52, + "learning_rate": 9.892438070404173e-06, + "loss": 0.2096, + "step": 18606 + }, + { + "epoch": 1.52, + "learning_rate": 9.891894828335508e-06, + "loss": 0.155, + "step": 18607 + }, + { + "epoch": 1.52, + "learning_rate": 9.89135158626684e-06, + "loss": 0.187, + "step": 18608 + }, + { + "epoch": 1.52, + "learning_rate": 9.890808344198174e-06, + "loss": 0.2807, + "step": 18609 + }, + { + "epoch": 1.52, + "learning_rate": 9.890265102129509e-06, + "loss": 0.3148, + "step": 18610 + }, + { + "epoch": 1.52, + "learning_rate": 9.889721860060843e-06, + "loss": 0.4382, + "step": 18611 + }, + { + "epoch": 1.52, + "learning_rate": 9.889178617992177e-06, + "loss": 0.3654, + "step": 18612 + }, + { + "epoch": 1.52, + "learning_rate": 9.888635375923511e-06, + "loss": 0.1586, + "step": 18613 + }, + { + "epoch": 1.52, + "learning_rate": 9.888092133854846e-06, + "loss": 0.1888, + "step": 18614 + }, + { + "epoch": 1.52, + "learning_rate": 9.88754889178618e-06, + "loss": 0.2991, + "step": 18615 + }, + { + "epoch": 1.52, + "learning_rate": 9.887005649717516e-06, + "loss": 0.3065, + "step": 18616 + }, + { + "epoch": 1.52, + "learning_rate": 9.88646240764885e-06, + "loss": 0.3886, + "step": 18617 + }, + { + "epoch": 1.52, + "learning_rate": 9.885919165580184e-06, + "loss": 0.2505, + "step": 18618 + }, + { + "epoch": 1.52, + "learning_rate": 9.885375923511518e-06, + "loss": 0.2005, + "step": 18619 + }, + { + "epoch": 1.52, + "learning_rate": 9.884832681442853e-06, + "loss": 0.4519, + "step": 18620 + }, + { + "epoch": 1.52, + "learning_rate": 9.884289439374187e-06, + "loss": 0.5857, + "step": 18621 + }, + { + "epoch": 1.52, + "learning_rate": 9.883746197305521e-06, + "loss": 0.428, + "step": 18622 + }, + { + "epoch": 1.52, + "learning_rate": 9.883202955236855e-06, + "loss": 0.436, + "step": 18623 + }, + { + "epoch": 1.52, + "learning_rate": 9.88265971316819e-06, + "loss": 0.2648, + "step": 18624 + }, + { + "epoch": 1.52, + "learning_rate": 9.882116471099524e-06, + "loss": 0.4723, + "step": 18625 + }, + { + "epoch": 1.52, + "learning_rate": 9.881573229030858e-06, + "loss": 0.1681, + "step": 18626 + }, + { + "epoch": 1.52, + "learning_rate": 9.88102998696219e-06, + "loss": 0.0963, + "step": 18627 + }, + { + "epoch": 1.52, + "learning_rate": 9.880486744893525e-06, + "loss": 0.3361, + "step": 18628 + }, + { + "epoch": 1.52, + "learning_rate": 9.879943502824859e-06, + "loss": 0.5278, + "step": 18629 + }, + { + "epoch": 1.52, + "learning_rate": 9.879400260756193e-06, + "loss": 0.2568, + "step": 18630 + }, + { + "epoch": 1.52, + "learning_rate": 9.878857018687527e-06, + "loss": 0.207, + "step": 18631 + }, + { + "epoch": 1.52, + "learning_rate": 9.878313776618862e-06, + "loss": 0.2762, + "step": 18632 + }, + { + "epoch": 1.52, + "learning_rate": 9.877770534550196e-06, + "loss": 0.4229, + "step": 18633 + }, + { + "epoch": 1.52, + "learning_rate": 9.87722729248153e-06, + "loss": 0.5294, + "step": 18634 + }, + { + "epoch": 1.52, + "learning_rate": 9.876684050412864e-06, + "loss": 0.185, + "step": 18635 + }, + { + "epoch": 1.52, + "learning_rate": 9.876140808344199e-06, + "loss": 0.1922, + "step": 18636 + }, + { + "epoch": 1.52, + "learning_rate": 9.875597566275533e-06, + "loss": 0.2222, + "step": 18637 + }, + { + "epoch": 1.52, + "learning_rate": 9.875054324206867e-06, + "loss": 0.6335, + "step": 18638 + }, + { + "epoch": 1.52, + "learning_rate": 9.874511082138201e-06, + "loss": 0.3979, + "step": 18639 + }, + { + "epoch": 1.52, + "learning_rate": 9.873967840069536e-06, + "loss": 0.2719, + "step": 18640 + }, + { + "epoch": 1.52, + "learning_rate": 9.87342459800087e-06, + "loss": 0.4707, + "step": 18641 + }, + { + "epoch": 1.52, + "learning_rate": 9.872881355932204e-06, + "loss": 0.2404, + "step": 18642 + }, + { + "epoch": 1.52, + "learning_rate": 9.872338113863538e-06, + "loss": 0.3284, + "step": 18643 + }, + { + "epoch": 1.52, + "learning_rate": 9.871794871794872e-06, + "loss": 0.4021, + "step": 18644 + }, + { + "epoch": 1.52, + "learning_rate": 9.871251629726207e-06, + "loss": 0.4959, + "step": 18645 + }, + { + "epoch": 1.52, + "learning_rate": 9.870708387657541e-06, + "loss": 0.2401, + "step": 18646 + }, + { + "epoch": 1.52, + "learning_rate": 9.870165145588875e-06, + "loss": 0.5032, + "step": 18647 + }, + { + "epoch": 1.52, + "learning_rate": 9.86962190352021e-06, + "loss": 0.3337, + "step": 18648 + }, + { + "epoch": 1.52, + "learning_rate": 9.869078661451544e-06, + "loss": 0.4527, + "step": 18649 + }, + { + "epoch": 1.52, + "learning_rate": 9.868535419382878e-06, + "loss": 0.1979, + "step": 18650 + }, + { + "epoch": 1.52, + "learning_rate": 9.867992177314212e-06, + "loss": 0.1823, + "step": 18651 + }, + { + "epoch": 1.52, + "learning_rate": 9.867448935245546e-06, + "loss": 0.1889, + "step": 18652 + }, + { + "epoch": 1.52, + "learning_rate": 9.86690569317688e-06, + "loss": 0.2008, + "step": 18653 + }, + { + "epoch": 1.52, + "learning_rate": 9.866362451108215e-06, + "loss": 0.3365, + "step": 18654 + }, + { + "epoch": 1.52, + "learning_rate": 9.865819209039549e-06, + "loss": 0.2683, + "step": 18655 + }, + { + "epoch": 1.52, + "learning_rate": 9.865275966970883e-06, + "loss": 0.2245, + "step": 18656 + }, + { + "epoch": 1.52, + "learning_rate": 9.864732724902217e-06, + "loss": 0.1728, + "step": 18657 + }, + { + "epoch": 1.52, + "learning_rate": 9.864189482833552e-06, + "loss": 0.2467, + "step": 18658 + }, + { + "epoch": 1.52, + "learning_rate": 9.863646240764886e-06, + "loss": 0.6838, + "step": 18659 + }, + { + "epoch": 1.52, + "learning_rate": 9.86310299869622e-06, + "loss": 0.4515, + "step": 18660 + }, + { + "epoch": 1.52, + "learning_rate": 9.862559756627554e-06, + "loss": 0.324, + "step": 18661 + }, + { + "epoch": 1.52, + "learning_rate": 9.862016514558889e-06, + "loss": 0.2054, + "step": 18662 + }, + { + "epoch": 1.52, + "learning_rate": 9.861473272490223e-06, + "loss": 0.3333, + "step": 18663 + }, + { + "epoch": 1.52, + "learning_rate": 9.860930030421557e-06, + "loss": 0.4312, + "step": 18664 + }, + { + "epoch": 1.52, + "learning_rate": 9.86038678835289e-06, + "loss": 0.3691, + "step": 18665 + }, + { + "epoch": 1.52, + "learning_rate": 9.859843546284224e-06, + "loss": 0.3671, + "step": 18666 + }, + { + "epoch": 1.52, + "learning_rate": 9.859300304215558e-06, + "loss": 0.2247, + "step": 18667 + }, + { + "epoch": 1.52, + "learning_rate": 9.858757062146892e-06, + "loss": 0.3986, + "step": 18668 + }, + { + "epoch": 1.52, + "learning_rate": 9.858213820078227e-06, + "loss": 0.2006, + "step": 18669 + }, + { + "epoch": 1.52, + "learning_rate": 9.857670578009562e-06, + "loss": 0.1675, + "step": 18670 + }, + { + "epoch": 1.52, + "learning_rate": 9.857127335940897e-06, + "loss": 0.3547, + "step": 18671 + }, + { + "epoch": 1.52, + "learning_rate": 9.856584093872231e-06, + "loss": 0.2671, + "step": 18672 + }, + { + "epoch": 1.52, + "learning_rate": 9.856040851803565e-06, + "loss": 0.4086, + "step": 18673 + }, + { + "epoch": 1.52, + "learning_rate": 9.8554976097349e-06, + "loss": 0.395, + "step": 18674 + }, + { + "epoch": 1.52, + "learning_rate": 9.854954367666234e-06, + "loss": 0.4674, + "step": 18675 + }, + { + "epoch": 1.52, + "learning_rate": 9.854411125597568e-06, + "loss": 0.3266, + "step": 18676 + }, + { + "epoch": 1.52, + "learning_rate": 9.853867883528902e-06, + "loss": 0.1944, + "step": 18677 + }, + { + "epoch": 1.52, + "learning_rate": 9.853324641460236e-06, + "loss": 0.3281, + "step": 18678 + }, + { + "epoch": 1.52, + "learning_rate": 9.85278139939157e-06, + "loss": 0.4546, + "step": 18679 + }, + { + "epoch": 1.52, + "learning_rate": 9.852238157322905e-06, + "loss": 0.2253, + "step": 18680 + }, + { + "epoch": 1.52, + "learning_rate": 9.851694915254239e-06, + "loss": 0.2606, + "step": 18681 + }, + { + "epoch": 1.52, + "learning_rate": 9.851151673185573e-06, + "loss": 0.2571, + "step": 18682 + }, + { + "epoch": 1.52, + "learning_rate": 9.850608431116907e-06, + "loss": 0.2756, + "step": 18683 + }, + { + "epoch": 1.52, + "learning_rate": 9.85006518904824e-06, + "loss": 0.205, + "step": 18684 + }, + { + "epoch": 1.52, + "learning_rate": 9.849521946979574e-06, + "loss": 0.6442, + "step": 18685 + }, + { + "epoch": 1.52, + "learning_rate": 9.848978704910908e-06, + "loss": 0.4257, + "step": 18686 + }, + { + "epoch": 1.52, + "learning_rate": 9.848435462842243e-06, + "loss": 0.3584, + "step": 18687 + }, + { + "epoch": 1.52, + "learning_rate": 9.847892220773577e-06, + "loss": 0.3134, + "step": 18688 + }, + { + "epoch": 1.52, + "learning_rate": 9.847348978704911e-06, + "loss": 0.3624, + "step": 18689 + }, + { + "epoch": 1.52, + "learning_rate": 9.846805736636245e-06, + "loss": 0.4004, + "step": 18690 + }, + { + "epoch": 1.52, + "learning_rate": 9.84626249456758e-06, + "loss": 0.5152, + "step": 18691 + }, + { + "epoch": 1.52, + "learning_rate": 9.845719252498914e-06, + "loss": 0.3894, + "step": 18692 + }, + { + "epoch": 1.52, + "learning_rate": 9.845176010430248e-06, + "loss": 0.2209, + "step": 18693 + }, + { + "epoch": 1.52, + "learning_rate": 9.844632768361582e-06, + "loss": 0.2475, + "step": 18694 + }, + { + "epoch": 1.52, + "learning_rate": 9.844089526292917e-06, + "loss": 0.5101, + "step": 18695 + }, + { + "epoch": 1.52, + "learning_rate": 9.84354628422425e-06, + "loss": 0.479, + "step": 18696 + }, + { + "epoch": 1.52, + "learning_rate": 9.843003042155585e-06, + "loss": 0.2035, + "step": 18697 + }, + { + "epoch": 1.52, + "learning_rate": 9.84245980008692e-06, + "loss": 0.3554, + "step": 18698 + }, + { + "epoch": 1.52, + "learning_rate": 9.841916558018253e-06, + "loss": 0.4873, + "step": 18699 + }, + { + "epoch": 1.52, + "learning_rate": 9.841373315949588e-06, + "loss": 0.4206, + "step": 18700 + }, + { + "epoch": 1.52, + "learning_rate": 9.840830073880922e-06, + "loss": 0.6554, + "step": 18701 + }, + { + "epoch": 1.52, + "learning_rate": 9.840286831812256e-06, + "loss": 0.2719, + "step": 18702 + }, + { + "epoch": 1.52, + "learning_rate": 9.83974358974359e-06, + "loss": 0.3238, + "step": 18703 + }, + { + "epoch": 1.52, + "learning_rate": 9.839200347674925e-06, + "loss": 0.364, + "step": 18704 + }, + { + "epoch": 1.52, + "learning_rate": 9.838657105606259e-06, + "loss": 0.2048, + "step": 18705 + }, + { + "epoch": 1.52, + "learning_rate": 9.838113863537593e-06, + "loss": 0.2619, + "step": 18706 + }, + { + "epoch": 1.52, + "learning_rate": 9.837570621468927e-06, + "loss": 0.4749, + "step": 18707 + }, + { + "epoch": 1.52, + "learning_rate": 9.837027379400262e-06, + "loss": 0.2054, + "step": 18708 + }, + { + "epoch": 1.52, + "learning_rate": 9.836484137331596e-06, + "loss": 0.2603, + "step": 18709 + }, + { + "epoch": 1.52, + "learning_rate": 9.83594089526293e-06, + "loss": 0.6258, + "step": 18710 + }, + { + "epoch": 1.52, + "learning_rate": 9.835397653194264e-06, + "loss": 0.277, + "step": 18711 + }, + { + "epoch": 1.52, + "learning_rate": 9.834854411125598e-06, + "loss": 0.2077, + "step": 18712 + }, + { + "epoch": 1.52, + "learning_rate": 9.834311169056933e-06, + "loss": 0.2525, + "step": 18713 + }, + { + "epoch": 1.52, + "learning_rate": 9.833767926988267e-06, + "loss": 0.3249, + "step": 18714 + }, + { + "epoch": 1.53, + "learning_rate": 9.833224684919601e-06, + "loss": 0.2267, + "step": 18715 + }, + { + "epoch": 1.53, + "learning_rate": 9.832681442850935e-06, + "loss": 0.2452, + "step": 18716 + }, + { + "epoch": 1.53, + "learning_rate": 9.83213820078227e-06, + "loss": 0.3749, + "step": 18717 + }, + { + "epoch": 1.53, + "learning_rate": 9.831594958713604e-06, + "loss": 0.4934, + "step": 18718 + }, + { + "epoch": 1.53, + "learning_rate": 9.831051716644938e-06, + "loss": 0.2627, + "step": 18719 + }, + { + "epoch": 1.53, + "learning_rate": 9.830508474576272e-06, + "loss": 0.1659, + "step": 18720 + }, + { + "epoch": 1.53, + "learning_rate": 9.829965232507607e-06, + "loss": 0.3582, + "step": 18721 + }, + { + "epoch": 1.53, + "learning_rate": 9.829421990438939e-06, + "loss": 0.3409, + "step": 18722 + }, + { + "epoch": 1.53, + "learning_rate": 9.828878748370273e-06, + "loss": 0.5375, + "step": 18723 + }, + { + "epoch": 1.53, + "learning_rate": 9.82833550630161e-06, + "loss": 0.1373, + "step": 18724 + }, + { + "epoch": 1.53, + "learning_rate": 9.827792264232943e-06, + "loss": 0.3484, + "step": 18725 + }, + { + "epoch": 1.53, + "learning_rate": 9.827249022164278e-06, + "loss": 0.3902, + "step": 18726 + }, + { + "epoch": 1.53, + "learning_rate": 9.826705780095612e-06, + "loss": 0.3399, + "step": 18727 + }, + { + "epoch": 1.53, + "learning_rate": 9.826162538026946e-06, + "loss": 0.349, + "step": 18728 + }, + { + "epoch": 1.53, + "learning_rate": 9.82561929595828e-06, + "loss": 0.142, + "step": 18729 + }, + { + "epoch": 1.53, + "learning_rate": 9.825076053889615e-06, + "loss": 0.5351, + "step": 18730 + }, + { + "epoch": 1.53, + "learning_rate": 9.824532811820949e-06, + "loss": 0.4323, + "step": 18731 + }, + { + "epoch": 1.53, + "learning_rate": 9.823989569752283e-06, + "loss": 0.2973, + "step": 18732 + }, + { + "epoch": 1.53, + "learning_rate": 9.823446327683617e-06, + "loss": 0.4776, + "step": 18733 + }, + { + "epoch": 1.53, + "learning_rate": 9.822903085614952e-06, + "loss": 0.3518, + "step": 18734 + }, + { + "epoch": 1.53, + "learning_rate": 9.822359843546286e-06, + "loss": 0.1481, + "step": 18735 + }, + { + "epoch": 1.53, + "learning_rate": 9.82181660147762e-06, + "loss": 0.2289, + "step": 18736 + }, + { + "epoch": 1.53, + "learning_rate": 9.821273359408954e-06, + "loss": 0.3045, + "step": 18737 + }, + { + "epoch": 1.53, + "learning_rate": 9.820730117340288e-06, + "loss": 0.2916, + "step": 18738 + }, + { + "epoch": 1.53, + "learning_rate": 9.820186875271623e-06, + "loss": 0.4183, + "step": 18739 + }, + { + "epoch": 1.53, + "learning_rate": 9.819643633202957e-06, + "loss": 0.2122, + "step": 18740 + }, + { + "epoch": 1.53, + "learning_rate": 9.81910039113429e-06, + "loss": 0.3329, + "step": 18741 + }, + { + "epoch": 1.53, + "learning_rate": 9.818557149065624e-06, + "loss": 0.4203, + "step": 18742 + }, + { + "epoch": 1.53, + "learning_rate": 9.818013906996958e-06, + "loss": 0.1636, + "step": 18743 + }, + { + "epoch": 1.53, + "learning_rate": 9.817470664928292e-06, + "loss": 0.1956, + "step": 18744 + }, + { + "epoch": 1.53, + "learning_rate": 9.816927422859626e-06, + "loss": 0.1211, + "step": 18745 + }, + { + "epoch": 1.53, + "learning_rate": 9.81638418079096e-06, + "loss": 0.4873, + "step": 18746 + }, + { + "epoch": 1.53, + "learning_rate": 9.815840938722295e-06, + "loss": 0.2585, + "step": 18747 + }, + { + "epoch": 1.53, + "learning_rate": 9.815297696653629e-06, + "loss": 0.2182, + "step": 18748 + }, + { + "epoch": 1.53, + "learning_rate": 9.814754454584963e-06, + "loss": 0.358, + "step": 18749 + }, + { + "epoch": 1.53, + "learning_rate": 9.814211212516298e-06, + "loss": 0.2234, + "step": 18750 + }, + { + "epoch": 1.53, + "eval_accuracy": 0.8424859908303617, + "eval_loss": 0.43843233585357666, + "eval_runtime": 22.3066, + "eval_samples_per_second": 440.004, + "eval_steps_per_second": 3.452, + "step": 18750 + }, + { + "epoch": 1.53, + "learning_rate": 9.813667970447632e-06, + "loss": 0.4686, + "step": 18751 + }, + { + "epoch": 1.53, + "learning_rate": 9.813124728378966e-06, + "loss": 0.3384, + "step": 18752 + }, + { + "epoch": 1.53, + "learning_rate": 9.8125814863103e-06, + "loss": 0.2509, + "step": 18753 + }, + { + "epoch": 1.53, + "learning_rate": 9.812038244241634e-06, + "loss": 0.4512, + "step": 18754 + }, + { + "epoch": 1.53, + "learning_rate": 9.811495002172969e-06, + "loss": 0.3303, + "step": 18755 + }, + { + "epoch": 1.53, + "learning_rate": 9.810951760104303e-06, + "loss": 0.4767, + "step": 18756 + }, + { + "epoch": 1.53, + "learning_rate": 9.810408518035637e-06, + "loss": 0.4887, + "step": 18757 + }, + { + "epoch": 1.53, + "learning_rate": 9.809865275966971e-06, + "loss": 0.413, + "step": 18758 + }, + { + "epoch": 1.53, + "learning_rate": 9.809322033898306e-06, + "loss": 0.3857, + "step": 18759 + }, + { + "epoch": 1.53, + "learning_rate": 9.80877879182964e-06, + "loss": 0.3911, + "step": 18760 + }, + { + "epoch": 1.53, + "learning_rate": 9.808235549760974e-06, + "loss": 0.2534, + "step": 18761 + }, + { + "epoch": 1.53, + "learning_rate": 9.807692307692308e-06, + "loss": 0.3093, + "step": 18762 + }, + { + "epoch": 1.53, + "learning_rate": 9.807149065623642e-06, + "loss": 0.2331, + "step": 18763 + }, + { + "epoch": 1.53, + "learning_rate": 9.806605823554977e-06, + "loss": 0.3811, + "step": 18764 + }, + { + "epoch": 1.53, + "learning_rate": 9.806062581486311e-06, + "loss": 0.3862, + "step": 18765 + }, + { + "epoch": 1.53, + "learning_rate": 9.805519339417645e-06, + "loss": 0.452, + "step": 18766 + }, + { + "epoch": 1.53, + "learning_rate": 9.80497609734898e-06, + "loss": 0.1527, + "step": 18767 + }, + { + "epoch": 1.53, + "learning_rate": 9.804432855280314e-06, + "loss": 0.2762, + "step": 18768 + }, + { + "epoch": 1.53, + "learning_rate": 9.803889613211648e-06, + "loss": 0.4623, + "step": 18769 + }, + { + "epoch": 1.53, + "learning_rate": 9.803346371142982e-06, + "loss": 0.4683, + "step": 18770 + }, + { + "epoch": 1.53, + "learning_rate": 9.802803129074316e-06, + "loss": 0.2076, + "step": 18771 + }, + { + "epoch": 1.53, + "learning_rate": 9.80225988700565e-06, + "loss": 0.307, + "step": 18772 + }, + { + "epoch": 1.53, + "learning_rate": 9.801716644936985e-06, + "loss": 0.1874, + "step": 18773 + }, + { + "epoch": 1.53, + "learning_rate": 9.801173402868319e-06, + "loss": 0.2506, + "step": 18774 + }, + { + "epoch": 1.53, + "learning_rate": 9.800630160799653e-06, + "loss": 0.2789, + "step": 18775 + }, + { + "epoch": 1.53, + "learning_rate": 9.800086918730987e-06, + "loss": 0.129, + "step": 18776 + }, + { + "epoch": 1.53, + "learning_rate": 9.799543676662322e-06, + "loss": 0.2208, + "step": 18777 + }, + { + "epoch": 1.53, + "learning_rate": 9.799000434593656e-06, + "loss": 0.5609, + "step": 18778 + }, + { + "epoch": 1.53, + "learning_rate": 9.79845719252499e-06, + "loss": 0.3884, + "step": 18779 + }, + { + "epoch": 1.53, + "learning_rate": 9.797913950456324e-06, + "loss": 0.2613, + "step": 18780 + }, + { + "epoch": 1.53, + "learning_rate": 9.797370708387659e-06, + "loss": 0.1121, + "step": 18781 + }, + { + "epoch": 1.53, + "learning_rate": 9.796827466318993e-06, + "loss": 0.6201, + "step": 18782 + }, + { + "epoch": 1.53, + "learning_rate": 9.796284224250327e-06, + "loss": 0.2654, + "step": 18783 + }, + { + "epoch": 1.53, + "learning_rate": 9.795740982181661e-06, + "loss": 0.3106, + "step": 18784 + }, + { + "epoch": 1.53, + "learning_rate": 9.795197740112996e-06, + "loss": 0.4632, + "step": 18785 + }, + { + "epoch": 1.53, + "learning_rate": 9.79465449804433e-06, + "loss": 0.4047, + "step": 18786 + }, + { + "epoch": 1.53, + "learning_rate": 9.794111255975664e-06, + "loss": 0.2187, + "step": 18787 + }, + { + "epoch": 1.53, + "learning_rate": 9.793568013906998e-06, + "loss": 0.7865, + "step": 18788 + }, + { + "epoch": 1.53, + "learning_rate": 9.793024771838332e-06, + "loss": 0.2368, + "step": 18789 + }, + { + "epoch": 1.53, + "learning_rate": 9.792481529769667e-06, + "loss": 0.2375, + "step": 18790 + }, + { + "epoch": 1.53, + "learning_rate": 9.791938287701001e-06, + "loss": 0.3746, + "step": 18791 + }, + { + "epoch": 1.53, + "learning_rate": 9.791395045632335e-06, + "loss": 0.1904, + "step": 18792 + }, + { + "epoch": 1.53, + "learning_rate": 9.79085180356367e-06, + "loss": 0.2496, + "step": 18793 + }, + { + "epoch": 1.53, + "learning_rate": 9.790308561495004e-06, + "loss": 0.6245, + "step": 18794 + }, + { + "epoch": 1.53, + "learning_rate": 9.789765319426338e-06, + "loss": 0.1979, + "step": 18795 + }, + { + "epoch": 1.53, + "learning_rate": 9.789222077357672e-06, + "loss": 0.3681, + "step": 18796 + }, + { + "epoch": 1.53, + "learning_rate": 9.788678835289006e-06, + "loss": 0.1427, + "step": 18797 + }, + { + "epoch": 1.53, + "learning_rate": 9.788135593220339e-06, + "loss": 0.2855, + "step": 18798 + }, + { + "epoch": 1.53, + "learning_rate": 9.787592351151673e-06, + "loss": 0.3006, + "step": 18799 + }, + { + "epoch": 1.53, + "learning_rate": 9.787049109083007e-06, + "loss": 0.6045, + "step": 18800 + }, + { + "epoch": 1.53, + "learning_rate": 9.786505867014342e-06, + "loss": 0.2674, + "step": 18801 + }, + { + "epoch": 1.53, + "learning_rate": 9.785962624945676e-06, + "loss": 0.1512, + "step": 18802 + }, + { + "epoch": 1.53, + "learning_rate": 9.78541938287701e-06, + "loss": 0.5033, + "step": 18803 + }, + { + "epoch": 1.53, + "learning_rate": 9.784876140808344e-06, + "loss": 0.2645, + "step": 18804 + }, + { + "epoch": 1.53, + "learning_rate": 9.784332898739678e-06, + "loss": 0.327, + "step": 18805 + }, + { + "epoch": 1.53, + "learning_rate": 9.783789656671013e-06, + "loss": 0.3, + "step": 18806 + }, + { + "epoch": 1.53, + "learning_rate": 9.783246414602347e-06, + "loss": 0.5753, + "step": 18807 + }, + { + "epoch": 1.53, + "learning_rate": 9.782703172533681e-06, + "loss": 0.3981, + "step": 18808 + }, + { + "epoch": 1.53, + "learning_rate": 9.782159930465015e-06, + "loss": 0.4163, + "step": 18809 + }, + { + "epoch": 1.53, + "learning_rate": 9.78161668839635e-06, + "loss": 0.54, + "step": 18810 + }, + { + "epoch": 1.53, + "learning_rate": 9.781073446327684e-06, + "loss": 0.7449, + "step": 18811 + }, + { + "epoch": 1.53, + "learning_rate": 9.780530204259018e-06, + "loss": 0.3146, + "step": 18812 + }, + { + "epoch": 1.53, + "learning_rate": 9.779986962190352e-06, + "loss": 0.5825, + "step": 18813 + }, + { + "epoch": 1.53, + "learning_rate": 9.779443720121688e-06, + "loss": 0.3872, + "step": 18814 + }, + { + "epoch": 1.53, + "learning_rate": 9.778900478053022e-06, + "loss": 0.5512, + "step": 18815 + }, + { + "epoch": 1.53, + "learning_rate": 9.778357235984357e-06, + "loss": 0.3737, + "step": 18816 + }, + { + "epoch": 1.53, + "learning_rate": 9.77781399391569e-06, + "loss": 0.5476, + "step": 18817 + }, + { + "epoch": 1.53, + "learning_rate": 9.777270751847023e-06, + "loss": 0.4251, + "step": 18818 + }, + { + "epoch": 1.53, + "learning_rate": 9.776727509778358e-06, + "loss": 0.2676, + "step": 18819 + }, + { + "epoch": 1.53, + "learning_rate": 9.776184267709692e-06, + "loss": 0.1811, + "step": 18820 + }, + { + "epoch": 1.53, + "learning_rate": 9.775641025641026e-06, + "loss": 0.2305, + "step": 18821 + }, + { + "epoch": 1.53, + "learning_rate": 9.77509778357236e-06, + "loss": 0.2276, + "step": 18822 + }, + { + "epoch": 1.53, + "learning_rate": 9.774554541503695e-06, + "loss": 0.1261, + "step": 18823 + }, + { + "epoch": 1.53, + "learning_rate": 9.774011299435029e-06, + "loss": 0.4449, + "step": 18824 + }, + { + "epoch": 1.53, + "learning_rate": 9.773468057366363e-06, + "loss": 0.6509, + "step": 18825 + }, + { + "epoch": 1.53, + "learning_rate": 9.772924815297697e-06, + "loss": 0.5135, + "step": 18826 + }, + { + "epoch": 1.53, + "learning_rate": 9.772381573229032e-06, + "loss": 0.6531, + "step": 18827 + }, + { + "epoch": 1.53, + "learning_rate": 9.771838331160366e-06, + "loss": 0.232, + "step": 18828 + }, + { + "epoch": 1.53, + "learning_rate": 9.7712950890917e-06, + "loss": 0.1855, + "step": 18829 + }, + { + "epoch": 1.53, + "learning_rate": 9.770751847023034e-06, + "loss": 0.2854, + "step": 18830 + }, + { + "epoch": 1.53, + "learning_rate": 9.770208604954368e-06, + "loss": 0.3513, + "step": 18831 + }, + { + "epoch": 1.53, + "learning_rate": 9.769665362885703e-06, + "loss": 0.2828, + "step": 18832 + }, + { + "epoch": 1.53, + "learning_rate": 9.769122120817037e-06, + "loss": 0.2728, + "step": 18833 + }, + { + "epoch": 1.53, + "learning_rate": 9.768578878748371e-06, + "loss": 0.4804, + "step": 18834 + }, + { + "epoch": 1.53, + "learning_rate": 9.768035636679705e-06, + "loss": 0.3625, + "step": 18835 + }, + { + "epoch": 1.53, + "learning_rate": 9.76749239461104e-06, + "loss": 0.2047, + "step": 18836 + }, + { + "epoch": 1.53, + "learning_rate": 9.766949152542374e-06, + "loss": 0.3096, + "step": 18837 + }, + { + "epoch": 1.54, + "learning_rate": 9.766405910473708e-06, + "loss": 0.5171, + "step": 18838 + }, + { + "epoch": 1.54, + "learning_rate": 9.765862668405042e-06, + "loss": 0.2063, + "step": 18839 + }, + { + "epoch": 1.54, + "learning_rate": 9.765319426336377e-06, + "loss": 0.3711, + "step": 18840 + }, + { + "epoch": 1.54, + "learning_rate": 9.76477618426771e-06, + "loss": 0.4001, + "step": 18841 + }, + { + "epoch": 1.54, + "learning_rate": 9.764232942199045e-06, + "loss": 0.3288, + "step": 18842 + }, + { + "epoch": 1.54, + "learning_rate": 9.76368970013038e-06, + "loss": 0.1653, + "step": 18843 + }, + { + "epoch": 1.54, + "learning_rate": 9.763146458061713e-06, + "loss": 0.4031, + "step": 18844 + }, + { + "epoch": 1.54, + "learning_rate": 9.762603215993048e-06, + "loss": 0.357, + "step": 18845 + }, + { + "epoch": 1.54, + "learning_rate": 9.762059973924382e-06, + "loss": 0.3837, + "step": 18846 + }, + { + "epoch": 1.54, + "learning_rate": 9.761516731855716e-06, + "loss": 0.3837, + "step": 18847 + }, + { + "epoch": 1.54, + "learning_rate": 9.76097348978705e-06, + "loss": 0.4659, + "step": 18848 + }, + { + "epoch": 1.54, + "learning_rate": 9.760430247718385e-06, + "loss": 0.5035, + "step": 18849 + }, + { + "epoch": 1.54, + "learning_rate": 9.759887005649719e-06, + "loss": 0.3259, + "step": 18850 + }, + { + "epoch": 1.54, + "learning_rate": 9.759343763581053e-06, + "loss": 0.4355, + "step": 18851 + }, + { + "epoch": 1.54, + "learning_rate": 9.758800521512387e-06, + "loss": 0.289, + "step": 18852 + }, + { + "epoch": 1.54, + "learning_rate": 9.758257279443722e-06, + "loss": 0.3212, + "step": 18853 + }, + { + "epoch": 1.54, + "learning_rate": 9.757714037375056e-06, + "loss": 0.4104, + "step": 18854 + }, + { + "epoch": 1.54, + "learning_rate": 9.757170795306388e-06, + "loss": 0.4602, + "step": 18855 + }, + { + "epoch": 1.54, + "learning_rate": 9.756627553237723e-06, + "loss": 0.2252, + "step": 18856 + }, + { + "epoch": 1.54, + "learning_rate": 9.756084311169057e-06, + "loss": 0.4032, + "step": 18857 + }, + { + "epoch": 1.54, + "learning_rate": 9.755541069100391e-06, + "loss": 0.4358, + "step": 18858 + }, + { + "epoch": 1.54, + "learning_rate": 9.754997827031725e-06, + "loss": 0.3341, + "step": 18859 + }, + { + "epoch": 1.54, + "learning_rate": 9.75445458496306e-06, + "loss": 0.2346, + "step": 18860 + }, + { + "epoch": 1.54, + "learning_rate": 9.753911342894394e-06, + "loss": 0.5473, + "step": 18861 + }, + { + "epoch": 1.54, + "learning_rate": 9.753368100825728e-06, + "loss": 0.3789, + "step": 18862 + }, + { + "epoch": 1.54, + "learning_rate": 9.752824858757062e-06, + "loss": 0.1527, + "step": 18863 + }, + { + "epoch": 1.54, + "learning_rate": 9.752281616688396e-06, + "loss": 0.3524, + "step": 18864 + }, + { + "epoch": 1.54, + "learning_rate": 9.75173837461973e-06, + "loss": 0.3976, + "step": 18865 + }, + { + "epoch": 1.54, + "learning_rate": 9.751195132551065e-06, + "loss": 0.2803, + "step": 18866 + }, + { + "epoch": 1.54, + "learning_rate": 9.750651890482399e-06, + "loss": 0.167, + "step": 18867 + }, + { + "epoch": 1.54, + "learning_rate": 9.750108648413735e-06, + "loss": 0.2163, + "step": 18868 + }, + { + "epoch": 1.54, + "learning_rate": 9.74956540634507e-06, + "loss": 0.3313, + "step": 18869 + }, + { + "epoch": 1.54, + "learning_rate": 9.749022164276403e-06, + "loss": 0.2485, + "step": 18870 + }, + { + "epoch": 1.54, + "learning_rate": 9.748478922207738e-06, + "loss": 0.2628, + "step": 18871 + }, + { + "epoch": 1.54, + "learning_rate": 9.747935680139072e-06, + "loss": 0.368, + "step": 18872 + }, + { + "epoch": 1.54, + "learning_rate": 9.747392438070406e-06, + "loss": 0.3202, + "step": 18873 + }, + { + "epoch": 1.54, + "learning_rate": 9.746849196001739e-06, + "loss": 0.6681, + "step": 18874 + }, + { + "epoch": 1.54, + "learning_rate": 9.746305953933073e-06, + "loss": 0.2814, + "step": 18875 + }, + { + "epoch": 1.54, + "learning_rate": 9.745762711864407e-06, + "loss": 0.3897, + "step": 18876 + }, + { + "epoch": 1.54, + "learning_rate": 9.745219469795741e-06, + "loss": 0.2198, + "step": 18877 + }, + { + "epoch": 1.54, + "learning_rate": 9.744676227727076e-06, + "loss": 0.3406, + "step": 18878 + }, + { + "epoch": 1.54, + "learning_rate": 9.74413298565841e-06, + "loss": 0.3019, + "step": 18879 + }, + { + "epoch": 1.54, + "learning_rate": 9.743589743589744e-06, + "loss": 0.3086, + "step": 18880 + }, + { + "epoch": 1.54, + "learning_rate": 9.743046501521078e-06, + "loss": 0.3939, + "step": 18881 + }, + { + "epoch": 1.54, + "learning_rate": 9.742503259452413e-06, + "loss": 0.3523, + "step": 18882 + }, + { + "epoch": 1.54, + "learning_rate": 9.741960017383747e-06, + "loss": 0.1602, + "step": 18883 + }, + { + "epoch": 1.54, + "learning_rate": 9.741416775315081e-06, + "loss": 0.2634, + "step": 18884 + }, + { + "epoch": 1.54, + "learning_rate": 9.740873533246415e-06, + "loss": 0.2962, + "step": 18885 + }, + { + "epoch": 1.54, + "learning_rate": 9.74033029117775e-06, + "loss": 0.4917, + "step": 18886 + }, + { + "epoch": 1.54, + "learning_rate": 9.739787049109084e-06, + "loss": 0.3222, + "step": 18887 + }, + { + "epoch": 1.54, + "learning_rate": 9.739243807040418e-06, + "loss": 0.2788, + "step": 18888 + }, + { + "epoch": 1.54, + "learning_rate": 9.738700564971752e-06, + "loss": 0.4213, + "step": 18889 + }, + { + "epoch": 1.54, + "learning_rate": 9.738157322903086e-06, + "loss": 0.4149, + "step": 18890 + }, + { + "epoch": 1.54, + "learning_rate": 9.73761408083442e-06, + "loss": 0.2547, + "step": 18891 + }, + { + "epoch": 1.54, + "learning_rate": 9.737070838765755e-06, + "loss": 0.3536, + "step": 18892 + }, + { + "epoch": 1.54, + "learning_rate": 9.736527596697089e-06, + "loss": 0.1632, + "step": 18893 + }, + { + "epoch": 1.54, + "learning_rate": 9.735984354628423e-06, + "loss": 0.3839, + "step": 18894 + }, + { + "epoch": 1.54, + "learning_rate": 9.735441112559758e-06, + "loss": 0.2644, + "step": 18895 + }, + { + "epoch": 1.54, + "learning_rate": 9.734897870491092e-06, + "loss": 0.5416, + "step": 18896 + }, + { + "epoch": 1.54, + "learning_rate": 9.734354628422426e-06, + "loss": 0.3904, + "step": 18897 + }, + { + "epoch": 1.54, + "learning_rate": 9.73381138635376e-06, + "loss": 0.2831, + "step": 18898 + }, + { + "epoch": 1.54, + "learning_rate": 9.733268144285094e-06, + "loss": 0.2119, + "step": 18899 + }, + { + "epoch": 1.54, + "learning_rate": 9.732724902216429e-06, + "loss": 0.6938, + "step": 18900 + }, + { + "epoch": 1.54, + "learning_rate": 9.732181660147763e-06, + "loss": 0.4832, + "step": 18901 + }, + { + "epoch": 1.54, + "learning_rate": 9.731638418079097e-06, + "loss": 0.3398, + "step": 18902 + }, + { + "epoch": 1.54, + "learning_rate": 9.731095176010431e-06, + "loss": 0.3614, + "step": 18903 + }, + { + "epoch": 1.54, + "learning_rate": 9.730551933941766e-06, + "loss": 0.3501, + "step": 18904 + }, + { + "epoch": 1.54, + "learning_rate": 9.7300086918731e-06, + "loss": 0.346, + "step": 18905 + }, + { + "epoch": 1.54, + "learning_rate": 9.729465449804434e-06, + "loss": 0.19, + "step": 18906 + }, + { + "epoch": 1.54, + "learning_rate": 9.728922207735768e-06, + "loss": 0.3513, + "step": 18907 + }, + { + "epoch": 1.54, + "learning_rate": 9.728378965667103e-06, + "loss": 0.2396, + "step": 18908 + }, + { + "epoch": 1.54, + "learning_rate": 9.727835723598437e-06, + "loss": 0.2916, + "step": 18909 + }, + { + "epoch": 1.54, + "learning_rate": 9.727292481529771e-06, + "loss": 0.3374, + "step": 18910 + }, + { + "epoch": 1.54, + "learning_rate": 9.726749239461105e-06, + "loss": 0.4001, + "step": 18911 + }, + { + "epoch": 1.54, + "learning_rate": 9.726205997392438e-06, + "loss": 0.3917, + "step": 18912 + }, + { + "epoch": 1.54, + "learning_rate": 9.725662755323772e-06, + "loss": 0.2693, + "step": 18913 + }, + { + "epoch": 1.54, + "learning_rate": 9.725119513255106e-06, + "loss": 1.0467, + "step": 18914 + }, + { + "epoch": 1.54, + "learning_rate": 9.72457627118644e-06, + "loss": 0.3815, + "step": 18915 + }, + { + "epoch": 1.54, + "learning_rate": 9.724033029117775e-06, + "loss": 0.1157, + "step": 18916 + }, + { + "epoch": 1.54, + "learning_rate": 9.723489787049109e-06, + "loss": 0.1466, + "step": 18917 + }, + { + "epoch": 1.54, + "learning_rate": 9.722946544980443e-06, + "loss": 0.0935, + "step": 18918 + }, + { + "epoch": 1.54, + "learning_rate": 9.722403302911777e-06, + "loss": 0.2974, + "step": 18919 + }, + { + "epoch": 1.54, + "learning_rate": 9.721860060843112e-06, + "loss": 0.1533, + "step": 18920 + }, + { + "epoch": 1.54, + "learning_rate": 9.721316818774446e-06, + "loss": 0.3823, + "step": 18921 + }, + { + "epoch": 1.54, + "learning_rate": 9.720773576705782e-06, + "loss": 0.8312, + "step": 18922 + }, + { + "epoch": 1.54, + "learning_rate": 9.720230334637116e-06, + "loss": 0.4392, + "step": 18923 + }, + { + "epoch": 1.54, + "learning_rate": 9.71968709256845e-06, + "loss": 0.3437, + "step": 18924 + }, + { + "epoch": 1.54, + "learning_rate": 9.719143850499784e-06, + "loss": 0.4438, + "step": 18925 + }, + { + "epoch": 1.54, + "learning_rate": 9.718600608431119e-06, + "loss": 0.2278, + "step": 18926 + }, + { + "epoch": 1.54, + "learning_rate": 9.718057366362453e-06, + "loss": 0.2394, + "step": 18927 + }, + { + "epoch": 1.54, + "learning_rate": 9.717514124293787e-06, + "loss": 0.2959, + "step": 18928 + }, + { + "epoch": 1.54, + "learning_rate": 9.716970882225121e-06, + "loss": 0.175, + "step": 18929 + }, + { + "epoch": 1.54, + "learning_rate": 9.716427640156456e-06, + "loss": 0.3343, + "step": 18930 + }, + { + "epoch": 1.54, + "learning_rate": 9.715884398087788e-06, + "loss": 0.271, + "step": 18931 + }, + { + "epoch": 1.54, + "learning_rate": 9.715341156019122e-06, + "loss": 0.2852, + "step": 18932 + }, + { + "epoch": 1.54, + "learning_rate": 9.714797913950457e-06, + "loss": 0.2104, + "step": 18933 + }, + { + "epoch": 1.54, + "learning_rate": 9.71425467188179e-06, + "loss": 0.4546, + "step": 18934 + }, + { + "epoch": 1.54, + "learning_rate": 9.713711429813125e-06, + "loss": 0.2182, + "step": 18935 + }, + { + "epoch": 1.54, + "learning_rate": 9.71316818774446e-06, + "loss": 0.1861, + "step": 18936 + }, + { + "epoch": 1.54, + "learning_rate": 9.712624945675794e-06, + "loss": 0.3765, + "step": 18937 + }, + { + "epoch": 1.54, + "learning_rate": 9.712081703607128e-06, + "loss": 0.4967, + "step": 18938 + }, + { + "epoch": 1.54, + "learning_rate": 9.711538461538462e-06, + "loss": 0.5066, + "step": 18939 + }, + { + "epoch": 1.54, + "learning_rate": 9.710995219469796e-06, + "loss": 0.2179, + "step": 18940 + }, + { + "epoch": 1.54, + "learning_rate": 9.71045197740113e-06, + "loss": 0.2258, + "step": 18941 + }, + { + "epoch": 1.54, + "learning_rate": 9.709908735332465e-06, + "loss": 0.5952, + "step": 18942 + }, + { + "epoch": 1.54, + "learning_rate": 9.709365493263799e-06, + "loss": 0.313, + "step": 18943 + }, + { + "epoch": 1.54, + "learning_rate": 9.708822251195133e-06, + "loss": 0.5712, + "step": 18944 + }, + { + "epoch": 1.54, + "learning_rate": 9.708279009126467e-06, + "loss": 0.3829, + "step": 18945 + }, + { + "epoch": 1.54, + "learning_rate": 9.707735767057802e-06, + "loss": 0.4561, + "step": 18946 + }, + { + "epoch": 1.54, + "learning_rate": 9.707192524989136e-06, + "loss": 0.3584, + "step": 18947 + }, + { + "epoch": 1.54, + "learning_rate": 9.70664928292047e-06, + "loss": 0.3695, + "step": 18948 + }, + { + "epoch": 1.54, + "learning_rate": 9.706106040851804e-06, + "loss": 0.2121, + "step": 18949 + }, + { + "epoch": 1.54, + "learning_rate": 9.705562798783139e-06, + "loss": 0.1948, + "step": 18950 + }, + { + "epoch": 1.54, + "learning_rate": 9.705019556714473e-06, + "loss": 0.4041, + "step": 18951 + }, + { + "epoch": 1.54, + "learning_rate": 9.704476314645807e-06, + "loss": 0.388, + "step": 18952 + }, + { + "epoch": 1.54, + "learning_rate": 9.703933072577141e-06, + "loss": 0.2336, + "step": 18953 + }, + { + "epoch": 1.54, + "learning_rate": 9.703389830508475e-06, + "loss": 0.3403, + "step": 18954 + }, + { + "epoch": 1.54, + "learning_rate": 9.70284658843981e-06, + "loss": 0.4828, + "step": 18955 + }, + { + "epoch": 1.54, + "learning_rate": 9.702303346371144e-06, + "loss": 0.3701, + "step": 18956 + }, + { + "epoch": 1.54, + "learning_rate": 9.701760104302478e-06, + "loss": 0.4313, + "step": 18957 + }, + { + "epoch": 1.54, + "learning_rate": 9.701216862233812e-06, + "loss": 0.3684, + "step": 18958 + }, + { + "epoch": 1.54, + "learning_rate": 9.700673620165147e-06, + "loss": 0.3568, + "step": 18959 + }, + { + "epoch": 1.54, + "learning_rate": 9.70013037809648e-06, + "loss": 0.2736, + "step": 18960 + }, + { + "epoch": 1.55, + "learning_rate": 9.699587136027815e-06, + "loss": 0.2262, + "step": 18961 + }, + { + "epoch": 1.55, + "learning_rate": 9.69904389395915e-06, + "loss": 0.4407, + "step": 18962 + }, + { + "epoch": 1.55, + "learning_rate": 9.698500651890484e-06, + "loss": 0.3597, + "step": 18963 + }, + { + "epoch": 1.55, + "learning_rate": 9.697957409821818e-06, + "loss": 0.3129, + "step": 18964 + }, + { + "epoch": 1.55, + "learning_rate": 9.697414167753152e-06, + "loss": 0.1412, + "step": 18965 + }, + { + "epoch": 1.55, + "learning_rate": 9.696870925684486e-06, + "loss": 0.3118, + "step": 18966 + }, + { + "epoch": 1.55, + "learning_rate": 9.69632768361582e-06, + "loss": 0.2735, + "step": 18967 + }, + { + "epoch": 1.55, + "learning_rate": 9.695784441547155e-06, + "loss": 0.4721, + "step": 18968 + }, + { + "epoch": 1.55, + "learning_rate": 9.695241199478487e-06, + "loss": 0.119, + "step": 18969 + }, + { + "epoch": 1.55, + "learning_rate": 9.694697957409821e-06, + "loss": 0.2765, + "step": 18970 + }, + { + "epoch": 1.55, + "learning_rate": 9.694154715341156e-06, + "loss": 0.3617, + "step": 18971 + }, + { + "epoch": 1.55, + "learning_rate": 9.69361147327249e-06, + "loss": 0.3023, + "step": 18972 + }, + { + "epoch": 1.55, + "learning_rate": 9.693068231203824e-06, + "loss": 0.2454, + "step": 18973 + }, + { + "epoch": 1.55, + "learning_rate": 9.692524989135158e-06, + "loss": 0.2387, + "step": 18974 + }, + { + "epoch": 1.55, + "learning_rate": 9.691981747066493e-06, + "loss": 0.3292, + "step": 18975 + }, + { + "epoch": 1.55, + "learning_rate": 9.691438504997829e-06, + "loss": 0.3804, + "step": 18976 + }, + { + "epoch": 1.55, + "learning_rate": 9.690895262929163e-06, + "loss": 0.6483, + "step": 18977 + }, + { + "epoch": 1.55, + "learning_rate": 9.690352020860497e-06, + "loss": 0.3027, + "step": 18978 + }, + { + "epoch": 1.55, + "learning_rate": 9.689808778791831e-06, + "loss": 0.0989, + "step": 18979 + }, + { + "epoch": 1.55, + "learning_rate": 9.689265536723165e-06, + "loss": 0.4878, + "step": 18980 + }, + { + "epoch": 1.55, + "learning_rate": 9.6887222946545e-06, + "loss": 0.3784, + "step": 18981 + }, + { + "epoch": 1.55, + "learning_rate": 9.688179052585834e-06, + "loss": 0.2464, + "step": 18982 + }, + { + "epoch": 1.55, + "learning_rate": 9.687635810517168e-06, + "loss": 0.3909, + "step": 18983 + }, + { + "epoch": 1.55, + "learning_rate": 9.687092568448502e-06, + "loss": 0.1179, + "step": 18984 + }, + { + "epoch": 1.55, + "learning_rate": 9.686549326379837e-06, + "loss": 0.4967, + "step": 18985 + }, + { + "epoch": 1.55, + "learning_rate": 9.68600608431117e-06, + "loss": 0.2946, + "step": 18986 + }, + { + "epoch": 1.55, + "learning_rate": 9.685462842242505e-06, + "loss": 0.1435, + "step": 18987 + }, + { + "epoch": 1.55, + "learning_rate": 9.68491960017384e-06, + "loss": 0.4356, + "step": 18988 + }, + { + "epoch": 1.55, + "learning_rate": 9.684376358105172e-06, + "loss": 0.408, + "step": 18989 + }, + { + "epoch": 1.55, + "learning_rate": 9.683833116036506e-06, + "loss": 0.1511, + "step": 18990 + }, + { + "epoch": 1.55, + "learning_rate": 9.68328987396784e-06, + "loss": 0.2839, + "step": 18991 + }, + { + "epoch": 1.55, + "learning_rate": 9.682746631899175e-06, + "loss": 0.2842, + "step": 18992 + }, + { + "epoch": 1.55, + "learning_rate": 9.682203389830509e-06, + "loss": 0.2044, + "step": 18993 + }, + { + "epoch": 1.55, + "learning_rate": 9.681660147761843e-06, + "loss": 0.4073, + "step": 18994 + }, + { + "epoch": 1.55, + "learning_rate": 9.681116905693177e-06, + "loss": 0.2006, + "step": 18995 + }, + { + "epoch": 1.55, + "learning_rate": 9.680573663624511e-06, + "loss": 0.5329, + "step": 18996 + }, + { + "epoch": 1.55, + "learning_rate": 9.680030421555846e-06, + "loss": 0.3972, + "step": 18997 + }, + { + "epoch": 1.55, + "learning_rate": 9.67948717948718e-06, + "loss": 0.3111, + "step": 18998 + }, + { + "epoch": 1.55, + "learning_rate": 9.678943937418514e-06, + "loss": 0.4425, + "step": 18999 + }, + { + "epoch": 1.55, + "learning_rate": 9.678400695349848e-06, + "loss": 0.3199, + "step": 19000 + }, + { + "epoch": 1.55, + "eval_accuracy": 0.8421803362200713, + "eval_loss": 0.43715110421180725, + "eval_runtime": 22.3772, + "eval_samples_per_second": 438.615, + "eval_steps_per_second": 3.441, + "step": 19000 + }, + { + "epoch": 1.55, + "learning_rate": 9.677857453281183e-06, + "loss": 0.221, + "step": 19001 + }, + { + "epoch": 1.55, + "learning_rate": 9.677314211212517e-06, + "loss": 0.239, + "step": 19002 + }, + { + "epoch": 1.55, + "learning_rate": 9.676770969143851e-06, + "loss": 0.3758, + "step": 19003 + }, + { + "epoch": 1.55, + "learning_rate": 9.676227727075185e-06, + "loss": 0.2522, + "step": 19004 + }, + { + "epoch": 1.55, + "learning_rate": 9.67568448500652e-06, + "loss": 0.176, + "step": 19005 + }, + { + "epoch": 1.55, + "learning_rate": 9.675141242937854e-06, + "loss": 0.3053, + "step": 19006 + }, + { + "epoch": 1.55, + "learning_rate": 9.674598000869188e-06, + "loss": 0.4971, + "step": 19007 + }, + { + "epoch": 1.55, + "learning_rate": 9.674054758800522e-06, + "loss": 0.3185, + "step": 19008 + }, + { + "epoch": 1.55, + "learning_rate": 9.673511516731856e-06, + "loss": 0.2026, + "step": 19009 + }, + { + "epoch": 1.55, + "learning_rate": 9.67296827466319e-06, + "loss": 0.1889, + "step": 19010 + }, + { + "epoch": 1.55, + "learning_rate": 9.672425032594525e-06, + "loss": 0.2228, + "step": 19011 + }, + { + "epoch": 1.55, + "learning_rate": 9.671881790525859e-06, + "loss": 0.3785, + "step": 19012 + }, + { + "epoch": 1.55, + "learning_rate": 9.671338548457193e-06, + "loss": 0.2798, + "step": 19013 + }, + { + "epoch": 1.55, + "learning_rate": 9.670795306388528e-06, + "loss": 0.268, + "step": 19014 + }, + { + "epoch": 1.55, + "learning_rate": 9.670252064319862e-06, + "loss": 0.4194, + "step": 19015 + }, + { + "epoch": 1.55, + "learning_rate": 9.669708822251196e-06, + "loss": 0.3018, + "step": 19016 + }, + { + "epoch": 1.55, + "learning_rate": 9.66916558018253e-06, + "loss": 0.3583, + "step": 19017 + }, + { + "epoch": 1.55, + "learning_rate": 9.668622338113865e-06, + "loss": 0.2878, + "step": 19018 + }, + { + "epoch": 1.55, + "learning_rate": 9.668079096045199e-06, + "loss": 0.3337, + "step": 19019 + }, + { + "epoch": 1.55, + "learning_rate": 9.667535853976533e-06, + "loss": 0.2822, + "step": 19020 + }, + { + "epoch": 1.55, + "learning_rate": 9.666992611907867e-06, + "loss": 0.2909, + "step": 19021 + }, + { + "epoch": 1.55, + "learning_rate": 9.666449369839201e-06, + "loss": 0.2576, + "step": 19022 + }, + { + "epoch": 1.55, + "learning_rate": 9.665906127770536e-06, + "loss": 0.3062, + "step": 19023 + }, + { + "epoch": 1.55, + "learning_rate": 9.66536288570187e-06, + "loss": 0.1469, + "step": 19024 + }, + { + "epoch": 1.55, + "learning_rate": 9.664819643633204e-06, + "loss": 0.2742, + "step": 19025 + }, + { + "epoch": 1.55, + "learning_rate": 9.664276401564538e-06, + "loss": 0.2661, + "step": 19026 + }, + { + "epoch": 1.55, + "learning_rate": 9.663733159495871e-06, + "loss": 0.247, + "step": 19027 + }, + { + "epoch": 1.55, + "learning_rate": 9.663189917427205e-06, + "loss": 0.267, + "step": 19028 + }, + { + "epoch": 1.55, + "learning_rate": 9.66264667535854e-06, + "loss": 0.1718, + "step": 19029 + }, + { + "epoch": 1.55, + "learning_rate": 9.662103433289875e-06, + "loss": 0.1654, + "step": 19030 + }, + { + "epoch": 1.55, + "learning_rate": 9.66156019122121e-06, + "loss": 0.1896, + "step": 19031 + }, + { + "epoch": 1.55, + "learning_rate": 9.661016949152544e-06, + "loss": 0.2231, + "step": 19032 + }, + { + "epoch": 1.55, + "learning_rate": 9.660473707083878e-06, + "loss": 0.503, + "step": 19033 + }, + { + "epoch": 1.55, + "learning_rate": 9.659930465015212e-06, + "loss": 0.508, + "step": 19034 + }, + { + "epoch": 1.55, + "learning_rate": 9.659387222946546e-06, + "loss": 0.3763, + "step": 19035 + }, + { + "epoch": 1.55, + "learning_rate": 9.65884398087788e-06, + "loss": 0.2566, + "step": 19036 + }, + { + "epoch": 1.55, + "learning_rate": 9.658300738809215e-06, + "loss": 0.2818, + "step": 19037 + }, + { + "epoch": 1.55, + "learning_rate": 9.657757496740549e-06, + "loss": 0.353, + "step": 19038 + }, + { + "epoch": 1.55, + "learning_rate": 9.657214254671883e-06, + "loss": 0.2221, + "step": 19039 + }, + { + "epoch": 1.55, + "learning_rate": 9.656671012603218e-06, + "loss": 0.1384, + "step": 19040 + }, + { + "epoch": 1.55, + "learning_rate": 9.656127770534552e-06, + "loss": 0.2882, + "step": 19041 + }, + { + "epoch": 1.55, + "learning_rate": 9.655584528465886e-06, + "loss": 0.3334, + "step": 19042 + }, + { + "epoch": 1.55, + "learning_rate": 9.65504128639722e-06, + "loss": 0.3263, + "step": 19043 + }, + { + "epoch": 1.55, + "learning_rate": 9.654498044328555e-06, + "loss": 0.529, + "step": 19044 + }, + { + "epoch": 1.55, + "learning_rate": 9.653954802259889e-06, + "loss": 0.26, + "step": 19045 + }, + { + "epoch": 1.55, + "learning_rate": 9.653411560191221e-06, + "loss": 0.449, + "step": 19046 + }, + { + "epoch": 1.55, + "learning_rate": 9.652868318122556e-06, + "loss": 0.1555, + "step": 19047 + }, + { + "epoch": 1.55, + "learning_rate": 9.65232507605389e-06, + "loss": 0.2791, + "step": 19048 + }, + { + "epoch": 1.55, + "learning_rate": 9.651781833985224e-06, + "loss": 0.0959, + "step": 19049 + }, + { + "epoch": 1.55, + "learning_rate": 9.651238591916558e-06, + "loss": 0.4397, + "step": 19050 + }, + { + "epoch": 1.55, + "learning_rate": 9.650695349847892e-06, + "loss": 0.352, + "step": 19051 + }, + { + "epoch": 1.55, + "learning_rate": 9.650152107779227e-06, + "loss": 0.3617, + "step": 19052 + }, + { + "epoch": 1.55, + "learning_rate": 9.649608865710561e-06, + "loss": 0.4498, + "step": 19053 + }, + { + "epoch": 1.55, + "learning_rate": 9.649065623641895e-06, + "loss": 0.3276, + "step": 19054 + }, + { + "epoch": 1.55, + "learning_rate": 9.64852238157323e-06, + "loss": 0.4751, + "step": 19055 + }, + { + "epoch": 1.55, + "learning_rate": 9.647979139504564e-06, + "loss": 0.2854, + "step": 19056 + }, + { + "epoch": 1.55, + "learning_rate": 9.647435897435898e-06, + "loss": 0.2173, + "step": 19057 + }, + { + "epoch": 1.55, + "learning_rate": 9.646892655367232e-06, + "loss": 0.2546, + "step": 19058 + }, + { + "epoch": 1.55, + "learning_rate": 9.646349413298566e-06, + "loss": 0.8044, + "step": 19059 + }, + { + "epoch": 1.55, + "learning_rate": 9.6458061712299e-06, + "loss": 0.1982, + "step": 19060 + }, + { + "epoch": 1.55, + "learning_rate": 9.645262929161235e-06, + "loss": 0.5266, + "step": 19061 + }, + { + "epoch": 1.55, + "learning_rate": 9.644719687092569e-06, + "loss": 0.4479, + "step": 19062 + }, + { + "epoch": 1.55, + "learning_rate": 9.644176445023903e-06, + "loss": 0.3034, + "step": 19063 + }, + { + "epoch": 1.55, + "learning_rate": 9.643633202955237e-06, + "loss": 0.0788, + "step": 19064 + }, + { + "epoch": 1.55, + "learning_rate": 9.643089960886572e-06, + "loss": 0.6749, + "step": 19065 + }, + { + "epoch": 1.55, + "learning_rate": 9.642546718817906e-06, + "loss": 0.4178, + "step": 19066 + }, + { + "epoch": 1.55, + "learning_rate": 9.64200347674924e-06, + "loss": 0.3262, + "step": 19067 + }, + { + "epoch": 1.55, + "learning_rate": 9.641460234680574e-06, + "loss": 0.3303, + "step": 19068 + }, + { + "epoch": 1.55, + "learning_rate": 9.640916992611909e-06, + "loss": 0.3845, + "step": 19069 + }, + { + "epoch": 1.55, + "learning_rate": 9.640373750543243e-06, + "loss": 0.3914, + "step": 19070 + }, + { + "epoch": 1.55, + "learning_rate": 9.639830508474577e-06, + "loss": 0.4611, + "step": 19071 + }, + { + "epoch": 1.55, + "learning_rate": 9.639287266405911e-06, + "loss": 0.2717, + "step": 19072 + }, + { + "epoch": 1.55, + "learning_rate": 9.638744024337245e-06, + "loss": 0.3106, + "step": 19073 + }, + { + "epoch": 1.55, + "learning_rate": 9.63820078226858e-06, + "loss": 0.3692, + "step": 19074 + }, + { + "epoch": 1.55, + "learning_rate": 9.637657540199914e-06, + "loss": 0.4933, + "step": 19075 + }, + { + "epoch": 1.55, + "learning_rate": 9.637114298131248e-06, + "loss": 0.2902, + "step": 19076 + }, + { + "epoch": 1.55, + "learning_rate": 9.636571056062582e-06, + "loss": 0.3689, + "step": 19077 + }, + { + "epoch": 1.55, + "learning_rate": 9.636027813993917e-06, + "loss": 0.186, + "step": 19078 + }, + { + "epoch": 1.55, + "learning_rate": 9.635484571925251e-06, + "loss": 0.3004, + "step": 19079 + }, + { + "epoch": 1.55, + "learning_rate": 9.634941329856585e-06, + "loss": 0.3094, + "step": 19080 + }, + { + "epoch": 1.55, + "learning_rate": 9.63439808778792e-06, + "loss": 0.3506, + "step": 19081 + }, + { + "epoch": 1.55, + "learning_rate": 9.633854845719254e-06, + "loss": 0.2581, + "step": 19082 + }, + { + "epoch": 1.56, + "learning_rate": 9.633311603650588e-06, + "loss": 0.3079, + "step": 19083 + }, + { + "epoch": 1.56, + "learning_rate": 9.632768361581922e-06, + "loss": 0.2902, + "step": 19084 + }, + { + "epoch": 1.56, + "learning_rate": 9.632225119513256e-06, + "loss": 0.5327, + "step": 19085 + }, + { + "epoch": 1.56, + "learning_rate": 9.63168187744459e-06, + "loss": 0.2644, + "step": 19086 + }, + { + "epoch": 1.56, + "learning_rate": 9.631138635375925e-06, + "loss": 0.2869, + "step": 19087 + }, + { + "epoch": 1.56, + "learning_rate": 9.630595393307259e-06, + "loss": 0.2696, + "step": 19088 + }, + { + "epoch": 1.56, + "learning_rate": 9.630052151238593e-06, + "loss": 0.568, + "step": 19089 + }, + { + "epoch": 1.56, + "learning_rate": 9.629508909169927e-06, + "loss": 0.243, + "step": 19090 + }, + { + "epoch": 1.56, + "learning_rate": 9.628965667101262e-06, + "loss": 0.5171, + "step": 19091 + }, + { + "epoch": 1.56, + "learning_rate": 9.628422425032596e-06, + "loss": 0.3371, + "step": 19092 + }, + { + "epoch": 1.56, + "learning_rate": 9.62787918296393e-06, + "loss": 0.4125, + "step": 19093 + }, + { + "epoch": 1.56, + "learning_rate": 9.627335940895264e-06, + "loss": 0.2592, + "step": 19094 + }, + { + "epoch": 1.56, + "learning_rate": 9.626792698826599e-06, + "loss": 0.4716, + "step": 19095 + }, + { + "epoch": 1.56, + "learning_rate": 9.626249456757933e-06, + "loss": 0.5096, + "step": 19096 + }, + { + "epoch": 1.56, + "learning_rate": 9.625706214689267e-06, + "loss": 0.5913, + "step": 19097 + }, + { + "epoch": 1.56, + "learning_rate": 9.625162972620601e-06, + "loss": 0.4313, + "step": 19098 + }, + { + "epoch": 1.56, + "learning_rate": 9.624619730551935e-06, + "loss": 0.2812, + "step": 19099 + }, + { + "epoch": 1.56, + "learning_rate": 9.62407648848327e-06, + "loss": 0.1438, + "step": 19100 + }, + { + "epoch": 1.56, + "learning_rate": 9.623533246414604e-06, + "loss": 0.1867, + "step": 19101 + }, + { + "epoch": 1.56, + "learning_rate": 9.622990004345938e-06, + "loss": 0.3354, + "step": 19102 + }, + { + "epoch": 1.56, + "learning_rate": 9.62244676227727e-06, + "loss": 0.4389, + "step": 19103 + }, + { + "epoch": 1.56, + "learning_rate": 9.621903520208605e-06, + "loss": 0.629, + "step": 19104 + }, + { + "epoch": 1.56, + "learning_rate": 9.62136027813994e-06, + "loss": 0.3465, + "step": 19105 + }, + { + "epoch": 1.56, + "learning_rate": 9.620817036071273e-06, + "loss": 0.2278, + "step": 19106 + }, + { + "epoch": 1.56, + "learning_rate": 9.620273794002608e-06, + "loss": 0.1913, + "step": 19107 + }, + { + "epoch": 1.56, + "learning_rate": 9.619730551933942e-06, + "loss": 0.3723, + "step": 19108 + }, + { + "epoch": 1.56, + "learning_rate": 9.619187309865276e-06, + "loss": 0.2417, + "step": 19109 + }, + { + "epoch": 1.56, + "learning_rate": 9.61864406779661e-06, + "loss": 0.1916, + "step": 19110 + }, + { + "epoch": 1.56, + "learning_rate": 9.618100825727945e-06, + "loss": 0.4477, + "step": 19111 + }, + { + "epoch": 1.56, + "learning_rate": 9.617557583659279e-06, + "loss": 0.4157, + "step": 19112 + }, + { + "epoch": 1.56, + "learning_rate": 9.617014341590613e-06, + "loss": 0.332, + "step": 19113 + }, + { + "epoch": 1.56, + "learning_rate": 9.616471099521947e-06, + "loss": 0.4273, + "step": 19114 + }, + { + "epoch": 1.56, + "learning_rate": 9.615927857453281e-06, + "loss": 0.285, + "step": 19115 + }, + { + "epoch": 1.56, + "learning_rate": 9.615384615384616e-06, + "loss": 0.3704, + "step": 19116 + }, + { + "epoch": 1.56, + "learning_rate": 9.61484137331595e-06, + "loss": 0.4428, + "step": 19117 + }, + { + "epoch": 1.56, + "learning_rate": 9.614298131247284e-06, + "loss": 0.4325, + "step": 19118 + }, + { + "epoch": 1.56, + "learning_rate": 9.613754889178618e-06, + "loss": 0.4408, + "step": 19119 + }, + { + "epoch": 1.56, + "learning_rate": 9.613211647109953e-06, + "loss": 0.327, + "step": 19120 + }, + { + "epoch": 1.56, + "learning_rate": 9.612668405041289e-06, + "loss": 0.2955, + "step": 19121 + }, + { + "epoch": 1.56, + "learning_rate": 9.612125162972621e-06, + "loss": 0.1603, + "step": 19122 + }, + { + "epoch": 1.56, + "learning_rate": 9.611581920903955e-06, + "loss": 0.3104, + "step": 19123 + }, + { + "epoch": 1.56, + "learning_rate": 9.61103867883529e-06, + "loss": 0.1992, + "step": 19124 + }, + { + "epoch": 1.56, + "learning_rate": 9.610495436766624e-06, + "loss": 0.4, + "step": 19125 + }, + { + "epoch": 1.56, + "learning_rate": 9.609952194697958e-06, + "loss": 0.57, + "step": 19126 + }, + { + "epoch": 1.56, + "learning_rate": 9.609408952629292e-06, + "loss": 0.3953, + "step": 19127 + }, + { + "epoch": 1.56, + "learning_rate": 9.608865710560626e-06, + "loss": 0.3997, + "step": 19128 + }, + { + "epoch": 1.56, + "learning_rate": 9.60832246849196e-06, + "loss": 0.1769, + "step": 19129 + }, + { + "epoch": 1.56, + "learning_rate": 9.607779226423295e-06, + "loss": 0.4414, + "step": 19130 + }, + { + "epoch": 1.56, + "learning_rate": 9.60723598435463e-06, + "loss": 0.3494, + "step": 19131 + }, + { + "epoch": 1.56, + "learning_rate": 9.606692742285963e-06, + "loss": 0.386, + "step": 19132 + }, + { + "epoch": 1.56, + "learning_rate": 9.606149500217298e-06, + "loss": 0.5995, + "step": 19133 + }, + { + "epoch": 1.56, + "learning_rate": 9.605606258148632e-06, + "loss": 0.2565, + "step": 19134 + }, + { + "epoch": 1.56, + "learning_rate": 9.605063016079966e-06, + "loss": 0.4692, + "step": 19135 + }, + { + "epoch": 1.56, + "learning_rate": 9.6045197740113e-06, + "loss": 0.498, + "step": 19136 + }, + { + "epoch": 1.56, + "learning_rate": 9.603976531942635e-06, + "loss": 0.2718, + "step": 19137 + }, + { + "epoch": 1.56, + "learning_rate": 9.603433289873969e-06, + "loss": 0.3101, + "step": 19138 + }, + { + "epoch": 1.56, + "learning_rate": 9.602890047805303e-06, + "loss": 0.1661, + "step": 19139 + }, + { + "epoch": 1.56, + "learning_rate": 9.602346805736637e-06, + "loss": 0.1727, + "step": 19140 + }, + { + "epoch": 1.56, + "learning_rate": 9.601803563667971e-06, + "loss": 0.3067, + "step": 19141 + }, + { + "epoch": 1.56, + "learning_rate": 9.601260321599306e-06, + "loss": 0.4861, + "step": 19142 + }, + { + "epoch": 1.56, + "learning_rate": 9.60071707953064e-06, + "loss": 0.3074, + "step": 19143 + }, + { + "epoch": 1.56, + "learning_rate": 9.600173837461974e-06, + "loss": 0.3871, + "step": 19144 + }, + { + "epoch": 1.56, + "learning_rate": 9.599630595393308e-06, + "loss": 0.5467, + "step": 19145 + }, + { + "epoch": 1.56, + "learning_rate": 9.599087353324643e-06, + "loss": 0.2403, + "step": 19146 + }, + { + "epoch": 1.56, + "learning_rate": 9.598544111255977e-06, + "loss": 0.338, + "step": 19147 + }, + { + "epoch": 1.56, + "learning_rate": 9.598000869187311e-06, + "loss": 0.2988, + "step": 19148 + }, + { + "epoch": 1.56, + "learning_rate": 9.597457627118645e-06, + "loss": 0.2637, + "step": 19149 + }, + { + "epoch": 1.56, + "learning_rate": 9.59691438504998e-06, + "loss": 0.1795, + "step": 19150 + }, + { + "epoch": 1.56, + "learning_rate": 9.596371142981314e-06, + "loss": 0.2392, + "step": 19151 + }, + { + "epoch": 1.56, + "learning_rate": 9.595827900912648e-06, + "loss": 0.2623, + "step": 19152 + }, + { + "epoch": 1.56, + "learning_rate": 9.595284658843982e-06, + "loss": 0.2437, + "step": 19153 + }, + { + "epoch": 1.56, + "learning_rate": 9.594741416775316e-06, + "loss": 0.2488, + "step": 19154 + }, + { + "epoch": 1.56, + "learning_rate": 9.59419817470665e-06, + "loss": 0.645, + "step": 19155 + }, + { + "epoch": 1.56, + "learning_rate": 9.593654932637985e-06, + "loss": 0.5089, + "step": 19156 + }, + { + "epoch": 1.56, + "learning_rate": 9.59311169056932e-06, + "loss": 0.263, + "step": 19157 + }, + { + "epoch": 1.56, + "learning_rate": 9.592568448500653e-06, + "loss": 0.2962, + "step": 19158 + }, + { + "epoch": 1.56, + "learning_rate": 9.592025206431988e-06, + "loss": 0.6264, + "step": 19159 + }, + { + "epoch": 1.56, + "learning_rate": 9.59148196436332e-06, + "loss": 0.2284, + "step": 19160 + }, + { + "epoch": 1.56, + "learning_rate": 9.590938722294654e-06, + "loss": 0.4181, + "step": 19161 + }, + { + "epoch": 1.56, + "learning_rate": 9.590395480225989e-06, + "loss": 0.2605, + "step": 19162 + }, + { + "epoch": 1.56, + "learning_rate": 9.589852238157323e-06, + "loss": 0.4426, + "step": 19163 + }, + { + "epoch": 1.56, + "learning_rate": 9.589308996088657e-06, + "loss": 0.3653, + "step": 19164 + }, + { + "epoch": 1.56, + "learning_rate": 9.588765754019991e-06, + "loss": 0.5799, + "step": 19165 + }, + { + "epoch": 1.56, + "learning_rate": 9.588222511951326e-06, + "loss": 0.4616, + "step": 19166 + }, + { + "epoch": 1.56, + "learning_rate": 9.58767926988266e-06, + "loss": 0.4454, + "step": 19167 + }, + { + "epoch": 1.56, + "learning_rate": 9.587136027813994e-06, + "loss": 0.3878, + "step": 19168 + }, + { + "epoch": 1.56, + "learning_rate": 9.586592785745328e-06, + "loss": 0.396, + "step": 19169 + }, + { + "epoch": 1.56, + "learning_rate": 9.586049543676662e-06, + "loss": 0.3277, + "step": 19170 + }, + { + "epoch": 1.56, + "learning_rate": 9.585506301607997e-06, + "loss": 0.2764, + "step": 19171 + }, + { + "epoch": 1.56, + "learning_rate": 9.584963059539331e-06, + "loss": 0.2329, + "step": 19172 + }, + { + "epoch": 1.56, + "learning_rate": 9.584419817470665e-06, + "loss": 0.4938, + "step": 19173 + }, + { + "epoch": 1.56, + "learning_rate": 9.583876575402e-06, + "loss": 0.2017, + "step": 19174 + }, + { + "epoch": 1.56, + "learning_rate": 9.583333333333335e-06, + "loss": 0.5678, + "step": 19175 + }, + { + "epoch": 1.56, + "learning_rate": 9.58279009126467e-06, + "loss": 0.3338, + "step": 19176 + }, + { + "epoch": 1.56, + "learning_rate": 9.582246849196004e-06, + "loss": 0.307, + "step": 19177 + }, + { + "epoch": 1.56, + "learning_rate": 9.581703607127338e-06, + "loss": 0.4095, + "step": 19178 + }, + { + "epoch": 1.56, + "learning_rate": 9.58116036505867e-06, + "loss": 0.1883, + "step": 19179 + }, + { + "epoch": 1.56, + "learning_rate": 9.580617122990005e-06, + "loss": 0.4026, + "step": 19180 + }, + { + "epoch": 1.56, + "learning_rate": 9.580073880921339e-06, + "loss": 0.4947, + "step": 19181 + }, + { + "epoch": 1.56, + "learning_rate": 9.579530638852673e-06, + "loss": 0.2431, + "step": 19182 + }, + { + "epoch": 1.56, + "learning_rate": 9.578987396784007e-06, + "loss": 0.2527, + "step": 19183 + }, + { + "epoch": 1.56, + "learning_rate": 9.578444154715342e-06, + "loss": 0.4385, + "step": 19184 + }, + { + "epoch": 1.56, + "learning_rate": 9.577900912646676e-06, + "loss": 0.48, + "step": 19185 + }, + { + "epoch": 1.56, + "learning_rate": 9.57735767057801e-06, + "loss": 0.3281, + "step": 19186 + }, + { + "epoch": 1.56, + "learning_rate": 9.576814428509344e-06, + "loss": 0.436, + "step": 19187 + }, + { + "epoch": 1.56, + "learning_rate": 9.576271186440679e-06, + "loss": 0.3928, + "step": 19188 + }, + { + "epoch": 1.56, + "learning_rate": 9.575727944372013e-06, + "loss": 0.3459, + "step": 19189 + }, + { + "epoch": 1.56, + "learning_rate": 9.575184702303347e-06, + "loss": 0.2367, + "step": 19190 + }, + { + "epoch": 1.56, + "learning_rate": 9.574641460234681e-06, + "loss": 0.4726, + "step": 19191 + }, + { + "epoch": 1.56, + "learning_rate": 9.574098218166016e-06, + "loss": 0.419, + "step": 19192 + }, + { + "epoch": 1.56, + "learning_rate": 9.57355497609735e-06, + "loss": 0.2856, + "step": 19193 + }, + { + "epoch": 1.56, + "learning_rate": 9.573011734028684e-06, + "loss": 0.3376, + "step": 19194 + }, + { + "epoch": 1.56, + "learning_rate": 9.572468491960018e-06, + "loss": 0.5204, + "step": 19195 + }, + { + "epoch": 1.56, + "learning_rate": 9.571925249891352e-06, + "loss": 0.3465, + "step": 19196 + }, + { + "epoch": 1.56, + "learning_rate": 9.571382007822687e-06, + "loss": 0.4671, + "step": 19197 + }, + { + "epoch": 1.56, + "learning_rate": 9.570838765754021e-06, + "loss": 0.2721, + "step": 19198 + }, + { + "epoch": 1.56, + "learning_rate": 9.570295523685355e-06, + "loss": 0.1311, + "step": 19199 + }, + { + "epoch": 1.56, + "learning_rate": 9.56975228161669e-06, + "loss": 0.2505, + "step": 19200 + }, + { + "epoch": 1.56, + "learning_rate": 9.569209039548024e-06, + "loss": 0.3357, + "step": 19201 + }, + { + "epoch": 1.56, + "learning_rate": 9.568665797479358e-06, + "loss": 0.4092, + "step": 19202 + }, + { + "epoch": 1.56, + "learning_rate": 9.568122555410692e-06, + "loss": 0.2385, + "step": 19203 + }, + { + "epoch": 1.56, + "learning_rate": 9.567579313342026e-06, + "loss": 0.2097, + "step": 19204 + }, + { + "epoch": 1.56, + "learning_rate": 9.56703607127336e-06, + "loss": 0.5822, + "step": 19205 + }, + { + "epoch": 1.57, + "learning_rate": 9.566492829204695e-06, + "loss": 0.2746, + "step": 19206 + }, + { + "epoch": 1.57, + "learning_rate": 9.565949587136029e-06, + "loss": 0.1966, + "step": 19207 + }, + { + "epoch": 1.57, + "learning_rate": 9.565406345067363e-06, + "loss": 0.2103, + "step": 19208 + }, + { + "epoch": 1.57, + "learning_rate": 9.564863102998697e-06, + "loss": 0.4124, + "step": 19209 + }, + { + "epoch": 1.57, + "learning_rate": 9.564319860930032e-06, + "loss": 0.3517, + "step": 19210 + }, + { + "epoch": 1.57, + "learning_rate": 9.563776618861366e-06, + "loss": 0.2567, + "step": 19211 + }, + { + "epoch": 1.57, + "learning_rate": 9.5632333767927e-06, + "loss": 0.3003, + "step": 19212 + }, + { + "epoch": 1.57, + "learning_rate": 9.562690134724034e-06, + "loss": 0.2698, + "step": 19213 + }, + { + "epoch": 1.57, + "learning_rate": 9.562146892655369e-06, + "loss": 0.4032, + "step": 19214 + }, + { + "epoch": 1.57, + "learning_rate": 9.561603650586703e-06, + "loss": 0.2858, + "step": 19215 + }, + { + "epoch": 1.57, + "learning_rate": 9.561060408518037e-06, + "loss": 0.3034, + "step": 19216 + }, + { + "epoch": 1.57, + "learning_rate": 9.56051716644937e-06, + "loss": 0.3191, + "step": 19217 + }, + { + "epoch": 1.57, + "learning_rate": 9.559973924380704e-06, + "loss": 0.4563, + "step": 19218 + }, + { + "epoch": 1.57, + "learning_rate": 9.559430682312038e-06, + "loss": 0.3178, + "step": 19219 + }, + { + "epoch": 1.57, + "learning_rate": 9.558887440243372e-06, + "loss": 0.2448, + "step": 19220 + }, + { + "epoch": 1.57, + "learning_rate": 9.558344198174707e-06, + "loss": 0.3627, + "step": 19221 + }, + { + "epoch": 1.57, + "learning_rate": 9.55780095610604e-06, + "loss": 0.5526, + "step": 19222 + }, + { + "epoch": 1.57, + "learning_rate": 9.557257714037375e-06, + "loss": 0.2201, + "step": 19223 + }, + { + "epoch": 1.57, + "learning_rate": 9.55671447196871e-06, + "loss": 0.2096, + "step": 19224 + }, + { + "epoch": 1.57, + "learning_rate": 9.556171229900043e-06, + "loss": 0.2989, + "step": 19225 + }, + { + "epoch": 1.57, + "learning_rate": 9.555627987831378e-06, + "loss": 0.4585, + "step": 19226 + }, + { + "epoch": 1.57, + "learning_rate": 9.555084745762712e-06, + "loss": 0.4397, + "step": 19227 + }, + { + "epoch": 1.57, + "learning_rate": 9.554541503694046e-06, + "loss": 0.3569, + "step": 19228 + }, + { + "epoch": 1.57, + "learning_rate": 9.553998261625382e-06, + "loss": 0.4176, + "step": 19229 + }, + { + "epoch": 1.57, + "learning_rate": 9.553455019556716e-06, + "loss": 0.5563, + "step": 19230 + }, + { + "epoch": 1.57, + "learning_rate": 9.55291177748805e-06, + "loss": 0.3968, + "step": 19231 + }, + { + "epoch": 1.57, + "learning_rate": 9.552368535419385e-06, + "loss": 0.6993, + "step": 19232 + }, + { + "epoch": 1.57, + "learning_rate": 9.551825293350719e-06, + "loss": 0.1815, + "step": 19233 + }, + { + "epoch": 1.57, + "learning_rate": 9.551282051282053e-06, + "loss": 0.5843, + "step": 19234 + }, + { + "epoch": 1.57, + "learning_rate": 9.550738809213387e-06, + "loss": 0.2857, + "step": 19235 + }, + { + "epoch": 1.57, + "learning_rate": 9.55019556714472e-06, + "loss": 0.5128, + "step": 19236 + }, + { + "epoch": 1.57, + "learning_rate": 9.549652325076054e-06, + "loss": 0.1418, + "step": 19237 + }, + { + "epoch": 1.57, + "learning_rate": 9.549109083007388e-06, + "loss": 0.3693, + "step": 19238 + }, + { + "epoch": 1.57, + "learning_rate": 9.548565840938723e-06, + "loss": 0.5118, + "step": 19239 + }, + { + "epoch": 1.57, + "learning_rate": 9.548022598870057e-06, + "loss": 0.4386, + "step": 19240 + }, + { + "epoch": 1.57, + "learning_rate": 9.547479356801391e-06, + "loss": 0.4218, + "step": 19241 + }, + { + "epoch": 1.57, + "learning_rate": 9.546936114732725e-06, + "loss": 0.2347, + "step": 19242 + }, + { + "epoch": 1.57, + "learning_rate": 9.54639287266406e-06, + "loss": 0.4151, + "step": 19243 + }, + { + "epoch": 1.57, + "learning_rate": 9.545849630595394e-06, + "loss": 0.8376, + "step": 19244 + }, + { + "epoch": 1.57, + "learning_rate": 9.545306388526728e-06, + "loss": 0.564, + "step": 19245 + }, + { + "epoch": 1.57, + "learning_rate": 9.544763146458062e-06, + "loss": 0.5948, + "step": 19246 + }, + { + "epoch": 1.57, + "learning_rate": 9.544219904389397e-06, + "loss": 0.355, + "step": 19247 + }, + { + "epoch": 1.57, + "learning_rate": 9.54367666232073e-06, + "loss": 0.2023, + "step": 19248 + }, + { + "epoch": 1.57, + "learning_rate": 9.543133420252065e-06, + "loss": 0.4248, + "step": 19249 + }, + { + "epoch": 1.57, + "learning_rate": 9.5425901781834e-06, + "loss": 0.2844, + "step": 19250 + }, + { + "epoch": 1.57, + "eval_accuracy": 0.8441161487519103, + "eval_loss": 0.42748767137527466, + "eval_runtime": 22.3516, + "eval_samples_per_second": 439.118, + "eval_steps_per_second": 3.445, + "step": 19250 + }, + { + "epoch": 1.57, + "learning_rate": 9.542046936114733e-06, + "loss": 0.3599, + "step": 19251 + }, + { + "epoch": 1.57, + "learning_rate": 9.541503694046068e-06, + "loss": 0.2303, + "step": 19252 + }, + { + "epoch": 1.57, + "learning_rate": 9.540960451977402e-06, + "loss": 0.3849, + "step": 19253 + }, + { + "epoch": 1.57, + "learning_rate": 9.540417209908736e-06, + "loss": 0.3123, + "step": 19254 + }, + { + "epoch": 1.57, + "learning_rate": 9.53987396784007e-06, + "loss": 0.553, + "step": 19255 + }, + { + "epoch": 1.57, + "learning_rate": 9.539330725771405e-06, + "loss": 0.3348, + "step": 19256 + }, + { + "epoch": 1.57, + "learning_rate": 9.538787483702739e-06, + "loss": 0.6151, + "step": 19257 + }, + { + "epoch": 1.57, + "learning_rate": 9.538244241634073e-06, + "loss": 0.2624, + "step": 19258 + }, + { + "epoch": 1.57, + "learning_rate": 9.537700999565407e-06, + "loss": 0.476, + "step": 19259 + }, + { + "epoch": 1.57, + "learning_rate": 9.537157757496742e-06, + "loss": 0.2849, + "step": 19260 + }, + { + "epoch": 1.57, + "learning_rate": 9.536614515428076e-06, + "loss": 0.195, + "step": 19261 + }, + { + "epoch": 1.57, + "learning_rate": 9.53607127335941e-06, + "loss": 0.394, + "step": 19262 + }, + { + "epoch": 1.57, + "learning_rate": 9.535528031290744e-06, + "loss": 0.4397, + "step": 19263 + }, + { + "epoch": 1.57, + "learning_rate": 9.534984789222078e-06, + "loss": 0.5132, + "step": 19264 + }, + { + "epoch": 1.57, + "learning_rate": 9.534441547153413e-06, + "loss": 0.4674, + "step": 19265 + }, + { + "epoch": 1.57, + "learning_rate": 9.533898305084747e-06, + "loss": 0.3098, + "step": 19266 + }, + { + "epoch": 1.57, + "learning_rate": 9.533355063016081e-06, + "loss": 0.4872, + "step": 19267 + }, + { + "epoch": 1.57, + "learning_rate": 9.532811820947415e-06, + "loss": 0.3756, + "step": 19268 + }, + { + "epoch": 1.57, + "learning_rate": 9.53226857887875e-06, + "loss": 0.3936, + "step": 19269 + }, + { + "epoch": 1.57, + "learning_rate": 9.531725336810084e-06, + "loss": 0.3486, + "step": 19270 + }, + { + "epoch": 1.57, + "learning_rate": 9.531182094741418e-06, + "loss": 0.5156, + "step": 19271 + }, + { + "epoch": 1.57, + "learning_rate": 9.530638852672752e-06, + "loss": 0.3302, + "step": 19272 + }, + { + "epoch": 1.57, + "learning_rate": 9.530095610604087e-06, + "loss": 0.2236, + "step": 19273 + }, + { + "epoch": 1.57, + "learning_rate": 9.529552368535419e-06, + "loss": 0.3082, + "step": 19274 + }, + { + "epoch": 1.57, + "learning_rate": 9.529009126466753e-06, + "loss": 0.2463, + "step": 19275 + }, + { + "epoch": 1.57, + "learning_rate": 9.528465884398088e-06, + "loss": 0.3416, + "step": 19276 + }, + { + "epoch": 1.57, + "learning_rate": 9.527922642329422e-06, + "loss": 0.3101, + "step": 19277 + }, + { + "epoch": 1.57, + "learning_rate": 9.527379400260756e-06, + "loss": 0.238, + "step": 19278 + }, + { + "epoch": 1.57, + "learning_rate": 9.52683615819209e-06, + "loss": 0.213, + "step": 19279 + }, + { + "epoch": 1.57, + "learning_rate": 9.526292916123424e-06, + "loss": 0.2765, + "step": 19280 + }, + { + "epoch": 1.57, + "learning_rate": 9.525749674054759e-06, + "loss": 0.2927, + "step": 19281 + }, + { + "epoch": 1.57, + "learning_rate": 9.525206431986093e-06, + "loss": 0.2866, + "step": 19282 + }, + { + "epoch": 1.57, + "learning_rate": 9.524663189917429e-06, + "loss": 0.3142, + "step": 19283 + }, + { + "epoch": 1.57, + "learning_rate": 9.524119947848763e-06, + "loss": 0.5801, + "step": 19284 + }, + { + "epoch": 1.57, + "learning_rate": 9.523576705780097e-06, + "loss": 0.2665, + "step": 19285 + }, + { + "epoch": 1.57, + "learning_rate": 9.523033463711432e-06, + "loss": 0.2599, + "step": 19286 + }, + { + "epoch": 1.57, + "learning_rate": 9.522490221642766e-06, + "loss": 0.4101, + "step": 19287 + }, + { + "epoch": 1.57, + "learning_rate": 9.5219469795741e-06, + "loss": 0.168, + "step": 19288 + }, + { + "epoch": 1.57, + "learning_rate": 9.521403737505434e-06, + "loss": 0.1337, + "step": 19289 + }, + { + "epoch": 1.57, + "learning_rate": 9.520860495436768e-06, + "loss": 0.3116, + "step": 19290 + }, + { + "epoch": 1.57, + "learning_rate": 9.520317253368103e-06, + "loss": 0.1954, + "step": 19291 + }, + { + "epoch": 1.57, + "learning_rate": 9.519774011299437e-06, + "loss": 0.193, + "step": 19292 + }, + { + "epoch": 1.57, + "learning_rate": 9.51923076923077e-06, + "loss": 0.3496, + "step": 19293 + }, + { + "epoch": 1.57, + "learning_rate": 9.518687527162104e-06, + "loss": 0.1797, + "step": 19294 + }, + { + "epoch": 1.57, + "learning_rate": 9.518144285093438e-06, + "loss": 0.3646, + "step": 19295 + }, + { + "epoch": 1.57, + "learning_rate": 9.517601043024772e-06, + "loss": 0.2649, + "step": 19296 + }, + { + "epoch": 1.57, + "learning_rate": 9.517057800956106e-06, + "loss": 0.405, + "step": 19297 + }, + { + "epoch": 1.57, + "learning_rate": 9.51651455888744e-06, + "loss": 0.2455, + "step": 19298 + }, + { + "epoch": 1.57, + "learning_rate": 9.515971316818775e-06, + "loss": 0.2526, + "step": 19299 + }, + { + "epoch": 1.57, + "learning_rate": 9.515428074750109e-06, + "loss": 0.2461, + "step": 19300 + }, + { + "epoch": 1.57, + "learning_rate": 9.514884832681443e-06, + "loss": 0.4278, + "step": 19301 + }, + { + "epoch": 1.57, + "learning_rate": 9.514341590612778e-06, + "loss": 0.2813, + "step": 19302 + }, + { + "epoch": 1.57, + "learning_rate": 9.513798348544112e-06, + "loss": 0.43, + "step": 19303 + }, + { + "epoch": 1.57, + "learning_rate": 9.513255106475446e-06, + "loss": 0.4447, + "step": 19304 + }, + { + "epoch": 1.57, + "learning_rate": 9.51271186440678e-06, + "loss": 0.2448, + "step": 19305 + }, + { + "epoch": 1.57, + "learning_rate": 9.512168622338114e-06, + "loss": 0.1413, + "step": 19306 + }, + { + "epoch": 1.57, + "learning_rate": 9.511625380269449e-06, + "loss": 0.3358, + "step": 19307 + }, + { + "epoch": 1.57, + "learning_rate": 9.511082138200783e-06, + "loss": 0.3827, + "step": 19308 + }, + { + "epoch": 1.57, + "learning_rate": 9.510538896132117e-06, + "loss": 0.2771, + "step": 19309 + }, + { + "epoch": 1.57, + "learning_rate": 9.509995654063451e-06, + "loss": 0.2718, + "step": 19310 + }, + { + "epoch": 1.57, + "learning_rate": 9.509452411994786e-06, + "loss": 0.1699, + "step": 19311 + }, + { + "epoch": 1.57, + "learning_rate": 9.50890916992612e-06, + "loss": 0.25, + "step": 19312 + }, + { + "epoch": 1.57, + "learning_rate": 9.508365927857454e-06, + "loss": 0.5268, + "step": 19313 + }, + { + "epoch": 1.57, + "learning_rate": 9.507822685788788e-06, + "loss": 0.2566, + "step": 19314 + }, + { + "epoch": 1.57, + "learning_rate": 9.507279443720123e-06, + "loss": 0.345, + "step": 19315 + }, + { + "epoch": 1.57, + "learning_rate": 9.506736201651457e-06, + "loss": 0.2733, + "step": 19316 + }, + { + "epoch": 1.57, + "learning_rate": 9.506192959582791e-06, + "loss": 0.7514, + "step": 19317 + }, + { + "epoch": 1.57, + "learning_rate": 9.505649717514125e-06, + "loss": 0.2611, + "step": 19318 + }, + { + "epoch": 1.57, + "learning_rate": 9.50510647544546e-06, + "loss": 0.1942, + "step": 19319 + }, + { + "epoch": 1.57, + "learning_rate": 9.504563233376794e-06, + "loss": 0.1261, + "step": 19320 + }, + { + "epoch": 1.57, + "learning_rate": 9.504019991308128e-06, + "loss": 0.2255, + "step": 19321 + }, + { + "epoch": 1.57, + "learning_rate": 9.503476749239462e-06, + "loss": 0.1659, + "step": 19322 + }, + { + "epoch": 1.57, + "learning_rate": 9.502933507170796e-06, + "loss": 0.3474, + "step": 19323 + }, + { + "epoch": 1.57, + "learning_rate": 9.50239026510213e-06, + "loss": 0.382, + "step": 19324 + }, + { + "epoch": 1.57, + "learning_rate": 9.501847023033465e-06, + "loss": 0.2832, + "step": 19325 + }, + { + "epoch": 1.57, + "learning_rate": 9.501303780964799e-06, + "loss": 0.4813, + "step": 19326 + }, + { + "epoch": 1.57, + "learning_rate": 9.500760538896133e-06, + "loss": 0.2527, + "step": 19327 + }, + { + "epoch": 1.57, + "learning_rate": 9.500217296827468e-06, + "loss": 0.1622, + "step": 19328 + }, + { + "epoch": 1.58, + "learning_rate": 9.499674054758802e-06, + "loss": 0.3, + "step": 19329 + }, + { + "epoch": 1.58, + "learning_rate": 9.499130812690136e-06, + "loss": 0.3363, + "step": 19330 + }, + { + "epoch": 1.58, + "learning_rate": 9.498587570621469e-06, + "loss": 0.5162, + "step": 19331 + }, + { + "epoch": 1.58, + "learning_rate": 9.498044328552803e-06, + "loss": 0.2456, + "step": 19332 + }, + { + "epoch": 1.58, + "learning_rate": 9.497501086484137e-06, + "loss": 0.4183, + "step": 19333 + }, + { + "epoch": 1.58, + "learning_rate": 9.496957844415471e-06, + "loss": 0.4331, + "step": 19334 + }, + { + "epoch": 1.58, + "learning_rate": 9.496414602346805e-06, + "loss": 0.3526, + "step": 19335 + }, + { + "epoch": 1.58, + "learning_rate": 9.49587136027814e-06, + "loss": 0.4649, + "step": 19336 + }, + { + "epoch": 1.58, + "learning_rate": 9.495328118209476e-06, + "loss": 0.2132, + "step": 19337 + }, + { + "epoch": 1.58, + "learning_rate": 9.49478487614081e-06, + "loss": 0.4221, + "step": 19338 + }, + { + "epoch": 1.58, + "learning_rate": 9.494241634072144e-06, + "loss": 0.4082, + "step": 19339 + }, + { + "epoch": 1.58, + "learning_rate": 9.493698392003478e-06, + "loss": 0.2324, + "step": 19340 + }, + { + "epoch": 1.58, + "learning_rate": 9.493155149934813e-06, + "loss": 0.384, + "step": 19341 + }, + { + "epoch": 1.58, + "learning_rate": 9.492611907866147e-06, + "loss": 0.2768, + "step": 19342 + }, + { + "epoch": 1.58, + "learning_rate": 9.492068665797481e-06, + "loss": 0.3154, + "step": 19343 + }, + { + "epoch": 1.58, + "learning_rate": 9.491525423728815e-06, + "loss": 0.308, + "step": 19344 + }, + { + "epoch": 1.58, + "learning_rate": 9.49098218166015e-06, + "loss": 0.4746, + "step": 19345 + }, + { + "epoch": 1.58, + "learning_rate": 9.490438939591484e-06, + "loss": 0.4361, + "step": 19346 + }, + { + "epoch": 1.58, + "learning_rate": 9.489895697522818e-06, + "loss": 0.2469, + "step": 19347 + }, + { + "epoch": 1.58, + "learning_rate": 9.489352455454152e-06, + "loss": 0.3814, + "step": 19348 + }, + { + "epoch": 1.58, + "learning_rate": 9.488809213385486e-06, + "loss": 0.3805, + "step": 19349 + }, + { + "epoch": 1.58, + "learning_rate": 9.488265971316819e-06, + "loss": 0.2462, + "step": 19350 + }, + { + "epoch": 1.58, + "learning_rate": 9.487722729248153e-06, + "loss": 0.2598, + "step": 19351 + }, + { + "epoch": 1.58, + "learning_rate": 9.487179487179487e-06, + "loss": 0.3286, + "step": 19352 + }, + { + "epoch": 1.58, + "learning_rate": 9.486636245110822e-06, + "loss": 0.4705, + "step": 19353 + }, + { + "epoch": 1.58, + "learning_rate": 9.486093003042156e-06, + "loss": 0.1296, + "step": 19354 + }, + { + "epoch": 1.58, + "learning_rate": 9.48554976097349e-06, + "loss": 0.4725, + "step": 19355 + }, + { + "epoch": 1.58, + "learning_rate": 9.485006518904824e-06, + "loss": 0.2009, + "step": 19356 + }, + { + "epoch": 1.58, + "learning_rate": 9.484463276836159e-06, + "loss": 0.3494, + "step": 19357 + }, + { + "epoch": 1.58, + "learning_rate": 9.483920034767493e-06, + "loss": 0.4667, + "step": 19358 + }, + { + "epoch": 1.58, + "learning_rate": 9.483376792698827e-06, + "loss": 0.586, + "step": 19359 + }, + { + "epoch": 1.58, + "learning_rate": 9.482833550630161e-06, + "loss": 0.3896, + "step": 19360 + }, + { + "epoch": 1.58, + "learning_rate": 9.482290308561495e-06, + "loss": 0.2734, + "step": 19361 + }, + { + "epoch": 1.58, + "learning_rate": 9.48174706649283e-06, + "loss": 0.1812, + "step": 19362 + }, + { + "epoch": 1.58, + "learning_rate": 9.481203824424164e-06, + "loss": 0.5008, + "step": 19363 + }, + { + "epoch": 1.58, + "learning_rate": 9.480660582355498e-06, + "loss": 0.2924, + "step": 19364 + }, + { + "epoch": 1.58, + "learning_rate": 9.480117340286832e-06, + "loss": 0.2185, + "step": 19365 + }, + { + "epoch": 1.58, + "learning_rate": 9.479574098218167e-06, + "loss": 0.3603, + "step": 19366 + }, + { + "epoch": 1.58, + "learning_rate": 9.4790308561495e-06, + "loss": 0.1676, + "step": 19367 + }, + { + "epoch": 1.58, + "learning_rate": 9.478487614080835e-06, + "loss": 0.2987, + "step": 19368 + }, + { + "epoch": 1.58, + "learning_rate": 9.47794437201217e-06, + "loss": 0.4475, + "step": 19369 + }, + { + "epoch": 1.58, + "learning_rate": 9.477401129943503e-06, + "loss": 0.2691, + "step": 19370 + }, + { + "epoch": 1.58, + "learning_rate": 9.476857887874838e-06, + "loss": 0.6151, + "step": 19371 + }, + { + "epoch": 1.58, + "learning_rate": 9.476314645806172e-06, + "loss": 0.4303, + "step": 19372 + }, + { + "epoch": 1.58, + "learning_rate": 9.475771403737506e-06, + "loss": 0.5872, + "step": 19373 + }, + { + "epoch": 1.58, + "learning_rate": 9.47522816166884e-06, + "loss": 0.5874, + "step": 19374 + }, + { + "epoch": 1.58, + "learning_rate": 9.474684919600175e-06, + "loss": 0.2319, + "step": 19375 + }, + { + "epoch": 1.58, + "learning_rate": 9.474141677531509e-06, + "loss": 0.2879, + "step": 19376 + }, + { + "epoch": 1.58, + "learning_rate": 9.473598435462843e-06, + "loss": 0.405, + "step": 19377 + }, + { + "epoch": 1.58, + "learning_rate": 9.473055193394177e-06, + "loss": 0.2075, + "step": 19378 + }, + { + "epoch": 1.58, + "learning_rate": 9.472511951325512e-06, + "loss": 0.3625, + "step": 19379 + }, + { + "epoch": 1.58, + "learning_rate": 9.471968709256846e-06, + "loss": 0.3264, + "step": 19380 + }, + { + "epoch": 1.58, + "learning_rate": 9.47142546718818e-06, + "loss": 0.3541, + "step": 19381 + }, + { + "epoch": 1.58, + "learning_rate": 9.470882225119514e-06, + "loss": 0.2158, + "step": 19382 + }, + { + "epoch": 1.58, + "learning_rate": 9.470338983050848e-06, + "loss": 0.3907, + "step": 19383 + }, + { + "epoch": 1.58, + "learning_rate": 9.469795740982183e-06, + "loss": 0.3292, + "step": 19384 + }, + { + "epoch": 1.58, + "learning_rate": 9.469252498913517e-06, + "loss": 0.2242, + "step": 19385 + }, + { + "epoch": 1.58, + "learning_rate": 9.468709256844851e-06, + "loss": 0.2652, + "step": 19386 + }, + { + "epoch": 1.58, + "learning_rate": 9.468166014776185e-06, + "loss": 0.2055, + "step": 19387 + }, + { + "epoch": 1.58, + "learning_rate": 9.467622772707518e-06, + "loss": 0.3515, + "step": 19388 + }, + { + "epoch": 1.58, + "learning_rate": 9.467079530638852e-06, + "loss": 0.5235, + "step": 19389 + }, + { + "epoch": 1.58, + "learning_rate": 9.466536288570186e-06, + "loss": 0.2523, + "step": 19390 + }, + { + "epoch": 1.58, + "learning_rate": 9.465993046501522e-06, + "loss": 0.4699, + "step": 19391 + }, + { + "epoch": 1.58, + "learning_rate": 9.465449804432857e-06, + "loss": 0.4415, + "step": 19392 + }, + { + "epoch": 1.58, + "learning_rate": 9.46490656236419e-06, + "loss": 0.4241, + "step": 19393 + }, + { + "epoch": 1.58, + "learning_rate": 9.464363320295525e-06, + "loss": 0.257, + "step": 19394 + }, + { + "epoch": 1.58, + "learning_rate": 9.46382007822686e-06, + "loss": 0.3139, + "step": 19395 + }, + { + "epoch": 1.58, + "learning_rate": 9.463276836158193e-06, + "loss": 0.1873, + "step": 19396 + }, + { + "epoch": 1.58, + "learning_rate": 9.462733594089528e-06, + "loss": 0.3251, + "step": 19397 + }, + { + "epoch": 1.58, + "learning_rate": 9.462190352020862e-06, + "loss": 0.2921, + "step": 19398 + }, + { + "epoch": 1.58, + "learning_rate": 9.461647109952196e-06, + "loss": 0.3, + "step": 19399 + }, + { + "epoch": 1.58, + "learning_rate": 9.46110386788353e-06, + "loss": 0.4917, + "step": 19400 + }, + { + "epoch": 1.58, + "learning_rate": 9.460560625814865e-06, + "loss": 0.2839, + "step": 19401 + }, + { + "epoch": 1.58, + "learning_rate": 9.460017383746199e-06, + "loss": 0.6008, + "step": 19402 + }, + { + "epoch": 1.58, + "learning_rate": 9.459474141677533e-06, + "loss": 0.3607, + "step": 19403 + }, + { + "epoch": 1.58, + "learning_rate": 9.458930899608867e-06, + "loss": 0.6259, + "step": 19404 + }, + { + "epoch": 1.58, + "learning_rate": 9.458387657540202e-06, + "loss": 0.3622, + "step": 19405 + }, + { + "epoch": 1.58, + "learning_rate": 9.457844415471536e-06, + "loss": 0.087, + "step": 19406 + }, + { + "epoch": 1.58, + "learning_rate": 9.457301173402868e-06, + "loss": 0.6899, + "step": 19407 + }, + { + "epoch": 1.58, + "learning_rate": 9.456757931334203e-06, + "loss": 0.6473, + "step": 19408 + }, + { + "epoch": 1.58, + "learning_rate": 9.456214689265537e-06, + "loss": 0.105, + "step": 19409 + }, + { + "epoch": 1.58, + "learning_rate": 9.455671447196871e-06, + "loss": 0.1349, + "step": 19410 + }, + { + "epoch": 1.58, + "learning_rate": 9.455128205128205e-06, + "loss": 0.2766, + "step": 19411 + }, + { + "epoch": 1.58, + "learning_rate": 9.45458496305954e-06, + "loss": 0.1597, + "step": 19412 + }, + { + "epoch": 1.58, + "learning_rate": 9.454041720990874e-06, + "loss": 0.2135, + "step": 19413 + }, + { + "epoch": 1.58, + "learning_rate": 9.453498478922208e-06, + "loss": 0.2395, + "step": 19414 + }, + { + "epoch": 1.58, + "learning_rate": 9.452955236853542e-06, + "loss": 0.2296, + "step": 19415 + }, + { + "epoch": 1.58, + "learning_rate": 9.452411994784876e-06, + "loss": 0.2383, + "step": 19416 + }, + { + "epoch": 1.58, + "learning_rate": 9.45186875271621e-06, + "loss": 0.4319, + "step": 19417 + }, + { + "epoch": 1.58, + "learning_rate": 9.451325510647545e-06, + "loss": 0.1482, + "step": 19418 + }, + { + "epoch": 1.58, + "learning_rate": 9.450782268578879e-06, + "loss": 0.2479, + "step": 19419 + }, + { + "epoch": 1.58, + "learning_rate": 9.450239026510213e-06, + "loss": 0.2368, + "step": 19420 + }, + { + "epoch": 1.58, + "learning_rate": 9.449695784441548e-06, + "loss": 0.4431, + "step": 19421 + }, + { + "epoch": 1.58, + "learning_rate": 9.449152542372882e-06, + "loss": 0.2633, + "step": 19422 + }, + { + "epoch": 1.58, + "learning_rate": 9.448609300304216e-06, + "loss": 0.3872, + "step": 19423 + }, + { + "epoch": 1.58, + "learning_rate": 9.44806605823555e-06, + "loss": 0.3439, + "step": 19424 + }, + { + "epoch": 1.58, + "learning_rate": 9.447522816166884e-06, + "loss": 0.2957, + "step": 19425 + }, + { + "epoch": 1.58, + "learning_rate": 9.446979574098219e-06, + "loss": 0.1987, + "step": 19426 + }, + { + "epoch": 1.58, + "learning_rate": 9.446436332029553e-06, + "loss": 0.3559, + "step": 19427 + }, + { + "epoch": 1.58, + "learning_rate": 9.445893089960887e-06, + "loss": 0.4518, + "step": 19428 + }, + { + "epoch": 1.58, + "learning_rate": 9.445349847892221e-06, + "loss": 0.3192, + "step": 19429 + }, + { + "epoch": 1.58, + "learning_rate": 9.444806605823556e-06, + "loss": 0.4685, + "step": 19430 + }, + { + "epoch": 1.58, + "learning_rate": 9.44426336375489e-06, + "loss": 0.2218, + "step": 19431 + }, + { + "epoch": 1.58, + "learning_rate": 9.443720121686224e-06, + "loss": 0.2717, + "step": 19432 + }, + { + "epoch": 1.58, + "learning_rate": 9.443176879617558e-06, + "loss": 0.0991, + "step": 19433 + }, + { + "epoch": 1.58, + "learning_rate": 9.442633637548893e-06, + "loss": 0.437, + "step": 19434 + }, + { + "epoch": 1.58, + "learning_rate": 9.442090395480227e-06, + "loss": 0.4887, + "step": 19435 + }, + { + "epoch": 1.58, + "learning_rate": 9.441547153411561e-06, + "loss": 0.2243, + "step": 19436 + }, + { + "epoch": 1.58, + "learning_rate": 9.441003911342895e-06, + "loss": 0.3226, + "step": 19437 + }, + { + "epoch": 1.58, + "learning_rate": 9.44046066927423e-06, + "loss": 0.2309, + "step": 19438 + }, + { + "epoch": 1.58, + "learning_rate": 9.439917427205564e-06, + "loss": 0.2239, + "step": 19439 + }, + { + "epoch": 1.58, + "learning_rate": 9.439374185136898e-06, + "loss": 0.6667, + "step": 19440 + }, + { + "epoch": 1.58, + "learning_rate": 9.438830943068232e-06, + "loss": 0.5738, + "step": 19441 + }, + { + "epoch": 1.58, + "learning_rate": 9.438287700999566e-06, + "loss": 0.2782, + "step": 19442 + }, + { + "epoch": 1.58, + "learning_rate": 9.4377444589309e-06, + "loss": 0.3356, + "step": 19443 + }, + { + "epoch": 1.58, + "learning_rate": 9.437201216862235e-06, + "loss": 0.2398, + "step": 19444 + }, + { + "epoch": 1.58, + "learning_rate": 9.436657974793569e-06, + "loss": 0.4684, + "step": 19445 + }, + { + "epoch": 1.58, + "learning_rate": 9.436114732724903e-06, + "loss": 0.1966, + "step": 19446 + }, + { + "epoch": 1.58, + "learning_rate": 9.435571490656238e-06, + "loss": 0.3904, + "step": 19447 + }, + { + "epoch": 1.58, + "learning_rate": 9.435028248587572e-06, + "loss": 0.3166, + "step": 19448 + }, + { + "epoch": 1.58, + "learning_rate": 9.434485006518906e-06, + "loss": 0.3265, + "step": 19449 + }, + { + "epoch": 1.58, + "learning_rate": 9.43394176445024e-06, + "loss": 0.7311, + "step": 19450 + }, + { + "epoch": 1.58, + "learning_rate": 9.433398522381574e-06, + "loss": 0.262, + "step": 19451 + }, + { + "epoch": 1.59, + "learning_rate": 9.432855280312909e-06, + "loss": 0.3551, + "step": 19452 + }, + { + "epoch": 1.59, + "learning_rate": 9.432312038244243e-06, + "loss": 0.3134, + "step": 19453 + }, + { + "epoch": 1.59, + "learning_rate": 9.431768796175577e-06, + "loss": 0.4536, + "step": 19454 + }, + { + "epoch": 1.59, + "learning_rate": 9.431225554106911e-06, + "loss": 0.2789, + "step": 19455 + }, + { + "epoch": 1.59, + "learning_rate": 9.430682312038246e-06, + "loss": 0.4771, + "step": 19456 + }, + { + "epoch": 1.59, + "learning_rate": 9.43013906996958e-06, + "loss": 0.3016, + "step": 19457 + }, + { + "epoch": 1.59, + "learning_rate": 9.429595827900914e-06, + "loss": 0.3081, + "step": 19458 + }, + { + "epoch": 1.59, + "learning_rate": 9.429052585832248e-06, + "loss": 0.4062, + "step": 19459 + }, + { + "epoch": 1.59, + "learning_rate": 9.428509343763583e-06, + "loss": 0.2768, + "step": 19460 + }, + { + "epoch": 1.59, + "learning_rate": 9.427966101694917e-06, + "loss": 0.529, + "step": 19461 + }, + { + "epoch": 1.59, + "learning_rate": 9.427422859626251e-06, + "loss": 0.1728, + "step": 19462 + }, + { + "epoch": 1.59, + "learning_rate": 9.426879617557585e-06, + "loss": 0.2161, + "step": 19463 + }, + { + "epoch": 1.59, + "learning_rate": 9.426336375488918e-06, + "loss": 0.5235, + "step": 19464 + }, + { + "epoch": 1.59, + "learning_rate": 9.425793133420252e-06, + "loss": 0.4874, + "step": 19465 + }, + { + "epoch": 1.59, + "learning_rate": 9.425249891351586e-06, + "loss": 0.2554, + "step": 19466 + }, + { + "epoch": 1.59, + "learning_rate": 9.42470664928292e-06, + "loss": 0.188, + "step": 19467 + }, + { + "epoch": 1.59, + "learning_rate": 9.424163407214255e-06, + "loss": 0.192, + "step": 19468 + }, + { + "epoch": 1.59, + "learning_rate": 9.423620165145589e-06, + "loss": 0.4552, + "step": 19469 + }, + { + "epoch": 1.59, + "learning_rate": 9.423076923076923e-06, + "loss": 0.2864, + "step": 19470 + }, + { + "epoch": 1.59, + "learning_rate": 9.422533681008257e-06, + "loss": 0.2343, + "step": 19471 + }, + { + "epoch": 1.59, + "learning_rate": 9.421990438939592e-06, + "loss": 0.2986, + "step": 19472 + }, + { + "epoch": 1.59, + "learning_rate": 9.421447196870926e-06, + "loss": 0.4414, + "step": 19473 + }, + { + "epoch": 1.59, + "learning_rate": 9.42090395480226e-06, + "loss": 0.2429, + "step": 19474 + }, + { + "epoch": 1.59, + "learning_rate": 9.420360712733594e-06, + "loss": 0.1739, + "step": 19475 + }, + { + "epoch": 1.59, + "learning_rate": 9.419817470664929e-06, + "loss": 0.5338, + "step": 19476 + }, + { + "epoch": 1.59, + "learning_rate": 9.419274228596263e-06, + "loss": 0.4102, + "step": 19477 + }, + { + "epoch": 1.59, + "learning_rate": 9.418730986527597e-06, + "loss": 0.2407, + "step": 19478 + }, + { + "epoch": 1.59, + "learning_rate": 9.418187744458931e-06, + "loss": 0.634, + "step": 19479 + }, + { + "epoch": 1.59, + "learning_rate": 9.417644502390265e-06, + "loss": 0.1408, + "step": 19480 + }, + { + "epoch": 1.59, + "learning_rate": 9.4171012603216e-06, + "loss": 0.2111, + "step": 19481 + }, + { + "epoch": 1.59, + "learning_rate": 9.416558018252936e-06, + "loss": 0.3863, + "step": 19482 + }, + { + "epoch": 1.59, + "learning_rate": 9.416014776184268e-06, + "loss": 0.3349, + "step": 19483 + }, + { + "epoch": 1.59, + "learning_rate": 9.415471534115602e-06, + "loss": 0.3743, + "step": 19484 + }, + { + "epoch": 1.59, + "learning_rate": 9.414928292046937e-06, + "loss": 0.3459, + "step": 19485 + }, + { + "epoch": 1.59, + "learning_rate": 9.414385049978271e-06, + "loss": 0.2196, + "step": 19486 + }, + { + "epoch": 1.59, + "learning_rate": 9.413841807909605e-06, + "loss": 0.3105, + "step": 19487 + }, + { + "epoch": 1.59, + "learning_rate": 9.41329856584094e-06, + "loss": 0.3375, + "step": 19488 + }, + { + "epoch": 1.59, + "learning_rate": 9.412755323772274e-06, + "loss": 0.3285, + "step": 19489 + }, + { + "epoch": 1.59, + "learning_rate": 9.412212081703608e-06, + "loss": 0.3649, + "step": 19490 + }, + { + "epoch": 1.59, + "learning_rate": 9.411668839634942e-06, + "loss": 0.6631, + "step": 19491 + }, + { + "epoch": 1.59, + "learning_rate": 9.411125597566276e-06, + "loss": 0.2209, + "step": 19492 + }, + { + "epoch": 1.59, + "learning_rate": 9.41058235549761e-06, + "loss": 0.6743, + "step": 19493 + }, + { + "epoch": 1.59, + "learning_rate": 9.410039113428945e-06, + "loss": 0.3981, + "step": 19494 + }, + { + "epoch": 1.59, + "learning_rate": 9.409495871360279e-06, + "loss": 0.2979, + "step": 19495 + }, + { + "epoch": 1.59, + "learning_rate": 9.408952629291613e-06, + "loss": 0.4046, + "step": 19496 + }, + { + "epoch": 1.59, + "learning_rate": 9.408409387222947e-06, + "loss": 0.1525, + "step": 19497 + }, + { + "epoch": 1.59, + "learning_rate": 9.407866145154282e-06, + "loss": 0.3684, + "step": 19498 + }, + { + "epoch": 1.59, + "learning_rate": 9.407322903085616e-06, + "loss": 0.1723, + "step": 19499 + }, + { + "epoch": 1.59, + "learning_rate": 9.40677966101695e-06, + "loss": 0.1749, + "step": 19500 + }, + { + "epoch": 1.59, + "eval_accuracy": 0.839429444727458, + "eval_loss": 0.44520410895347595, + "eval_runtime": 22.315, + "eval_samples_per_second": 439.838, + "eval_steps_per_second": 3.451, + "step": 19500 + }, + { + "epoch": 1.59, + "learning_rate": 9.406236418948284e-06, + "loss": 0.4804, + "step": 19501 + }, + { + "epoch": 1.59, + "learning_rate": 9.405693176879619e-06, + "loss": 0.2358, + "step": 19502 + }, + { + "epoch": 1.59, + "learning_rate": 9.405149934810953e-06, + "loss": 0.5913, + "step": 19503 + }, + { + "epoch": 1.59, + "learning_rate": 9.404606692742287e-06, + "loss": 0.3838, + "step": 19504 + }, + { + "epoch": 1.59, + "learning_rate": 9.404063450673621e-06, + "loss": 0.4224, + "step": 19505 + }, + { + "epoch": 1.59, + "learning_rate": 9.403520208604955e-06, + "loss": 0.159, + "step": 19506 + }, + { + "epoch": 1.59, + "learning_rate": 9.40297696653629e-06, + "loss": 0.4992, + "step": 19507 + }, + { + "epoch": 1.59, + "learning_rate": 9.402433724467624e-06, + "loss": 0.441, + "step": 19508 + }, + { + "epoch": 1.59, + "learning_rate": 9.401890482398958e-06, + "loss": 0.7172, + "step": 19509 + }, + { + "epoch": 1.59, + "learning_rate": 9.401347240330292e-06, + "loss": 0.5784, + "step": 19510 + }, + { + "epoch": 1.59, + "learning_rate": 9.400803998261627e-06, + "loss": 0.4798, + "step": 19511 + }, + { + "epoch": 1.59, + "learning_rate": 9.40026075619296e-06, + "loss": 0.2275, + "step": 19512 + }, + { + "epoch": 1.59, + "learning_rate": 9.399717514124295e-06, + "loss": 0.4288, + "step": 19513 + }, + { + "epoch": 1.59, + "learning_rate": 9.39917427205563e-06, + "loss": 0.4262, + "step": 19514 + }, + { + "epoch": 1.59, + "learning_rate": 9.398631029986964e-06, + "loss": 0.3574, + "step": 19515 + }, + { + "epoch": 1.59, + "learning_rate": 9.398087787918298e-06, + "loss": 0.3231, + "step": 19516 + }, + { + "epoch": 1.59, + "learning_rate": 9.397544545849632e-06, + "loss": 0.3423, + "step": 19517 + }, + { + "epoch": 1.59, + "learning_rate": 9.397001303780966e-06, + "loss": 0.4176, + "step": 19518 + }, + { + "epoch": 1.59, + "learning_rate": 9.3964580617123e-06, + "loss": 0.3293, + "step": 19519 + }, + { + "epoch": 1.59, + "learning_rate": 9.395914819643635e-06, + "loss": 0.4505, + "step": 19520 + }, + { + "epoch": 1.59, + "learning_rate": 9.395371577574967e-06, + "loss": 0.3778, + "step": 19521 + }, + { + "epoch": 1.59, + "learning_rate": 9.394828335506301e-06, + "loss": 0.5352, + "step": 19522 + }, + { + "epoch": 1.59, + "learning_rate": 9.394285093437636e-06, + "loss": 0.294, + "step": 19523 + }, + { + "epoch": 1.59, + "learning_rate": 9.39374185136897e-06, + "loss": 0.2192, + "step": 19524 + }, + { + "epoch": 1.59, + "learning_rate": 9.393198609300304e-06, + "loss": 0.2223, + "step": 19525 + }, + { + "epoch": 1.59, + "learning_rate": 9.392655367231638e-06, + "loss": 0.266, + "step": 19526 + }, + { + "epoch": 1.59, + "learning_rate": 9.392112125162973e-06, + "loss": 0.2462, + "step": 19527 + }, + { + "epoch": 1.59, + "learning_rate": 9.391568883094307e-06, + "loss": 0.1934, + "step": 19528 + }, + { + "epoch": 1.59, + "learning_rate": 9.391025641025641e-06, + "loss": 0.2927, + "step": 19529 + }, + { + "epoch": 1.59, + "learning_rate": 9.390482398956975e-06, + "loss": 0.432, + "step": 19530 + }, + { + "epoch": 1.59, + "learning_rate": 9.38993915688831e-06, + "loss": 0.3531, + "step": 19531 + }, + { + "epoch": 1.59, + "learning_rate": 9.389395914819644e-06, + "loss": 0.4634, + "step": 19532 + }, + { + "epoch": 1.59, + "learning_rate": 9.388852672750978e-06, + "loss": 0.3723, + "step": 19533 + }, + { + "epoch": 1.59, + "learning_rate": 9.388309430682312e-06, + "loss": 0.34, + "step": 19534 + }, + { + "epoch": 1.59, + "learning_rate": 9.387766188613648e-06, + "loss": 0.453, + "step": 19535 + }, + { + "epoch": 1.59, + "learning_rate": 9.387222946544982e-06, + "loss": 0.437, + "step": 19536 + }, + { + "epoch": 1.59, + "learning_rate": 9.386679704476317e-06, + "loss": 0.3929, + "step": 19537 + }, + { + "epoch": 1.59, + "learning_rate": 9.38613646240765e-06, + "loss": 0.1835, + "step": 19538 + }, + { + "epoch": 1.59, + "learning_rate": 9.385593220338985e-06, + "loss": 0.3458, + "step": 19539 + }, + { + "epoch": 1.59, + "learning_rate": 9.385049978270318e-06, + "loss": 0.1336, + "step": 19540 + }, + { + "epoch": 1.59, + "learning_rate": 9.384506736201652e-06, + "loss": 0.3027, + "step": 19541 + }, + { + "epoch": 1.59, + "learning_rate": 9.383963494132986e-06, + "loss": 0.3741, + "step": 19542 + }, + { + "epoch": 1.59, + "learning_rate": 9.38342025206432e-06, + "loss": 0.3013, + "step": 19543 + }, + { + "epoch": 1.59, + "learning_rate": 9.382877009995655e-06, + "loss": 0.4664, + "step": 19544 + }, + { + "epoch": 1.59, + "learning_rate": 9.382333767926989e-06, + "loss": 0.3316, + "step": 19545 + }, + { + "epoch": 1.59, + "learning_rate": 9.381790525858323e-06, + "loss": 0.2768, + "step": 19546 + }, + { + "epoch": 1.59, + "learning_rate": 9.381247283789657e-06, + "loss": 0.674, + "step": 19547 + }, + { + "epoch": 1.59, + "learning_rate": 9.380704041720991e-06, + "loss": 0.4192, + "step": 19548 + }, + { + "epoch": 1.59, + "learning_rate": 9.380160799652326e-06, + "loss": 0.2638, + "step": 19549 + }, + { + "epoch": 1.59, + "learning_rate": 9.37961755758366e-06, + "loss": 0.2572, + "step": 19550 + }, + { + "epoch": 1.59, + "learning_rate": 9.379074315514994e-06, + "loss": 0.3911, + "step": 19551 + }, + { + "epoch": 1.59, + "learning_rate": 9.378531073446328e-06, + "loss": 0.4336, + "step": 19552 + }, + { + "epoch": 1.59, + "learning_rate": 9.377987831377663e-06, + "loss": 0.2634, + "step": 19553 + }, + { + "epoch": 1.59, + "learning_rate": 9.377444589308997e-06, + "loss": 0.21, + "step": 19554 + }, + { + "epoch": 1.59, + "learning_rate": 9.376901347240331e-06, + "loss": 0.5563, + "step": 19555 + }, + { + "epoch": 1.59, + "learning_rate": 9.376358105171665e-06, + "loss": 0.2741, + "step": 19556 + }, + { + "epoch": 1.59, + "learning_rate": 9.375814863103e-06, + "loss": 0.2072, + "step": 19557 + }, + { + "epoch": 1.59, + "learning_rate": 9.375271621034334e-06, + "loss": 0.4001, + "step": 19558 + }, + { + "epoch": 1.59, + "learning_rate": 9.374728378965668e-06, + "loss": 0.3358, + "step": 19559 + }, + { + "epoch": 1.59, + "learning_rate": 9.374185136897002e-06, + "loss": 0.29, + "step": 19560 + }, + { + "epoch": 1.59, + "learning_rate": 9.373641894828336e-06, + "loss": 0.1829, + "step": 19561 + }, + { + "epoch": 1.59, + "learning_rate": 9.37309865275967e-06, + "loss": 0.3438, + "step": 19562 + }, + { + "epoch": 1.59, + "learning_rate": 9.372555410691005e-06, + "loss": 0.328, + "step": 19563 + }, + { + "epoch": 1.59, + "learning_rate": 9.372012168622339e-06, + "loss": 0.2461, + "step": 19564 + }, + { + "epoch": 1.59, + "learning_rate": 9.371468926553673e-06, + "loss": 0.1935, + "step": 19565 + }, + { + "epoch": 1.59, + "learning_rate": 9.370925684485008e-06, + "loss": 0.4007, + "step": 19566 + }, + { + "epoch": 1.59, + "learning_rate": 9.370382442416342e-06, + "loss": 0.2151, + "step": 19567 + }, + { + "epoch": 1.59, + "learning_rate": 9.369839200347676e-06, + "loss": 0.477, + "step": 19568 + }, + { + "epoch": 1.59, + "learning_rate": 9.36929595827901e-06, + "loss": 0.2393, + "step": 19569 + }, + { + "epoch": 1.59, + "learning_rate": 9.368752716210345e-06, + "loss": 0.5189, + "step": 19570 + }, + { + "epoch": 1.59, + "learning_rate": 9.368209474141679e-06, + "loss": 0.5122, + "step": 19571 + }, + { + "epoch": 1.59, + "learning_rate": 9.367666232073013e-06, + "loss": 0.2178, + "step": 19572 + }, + { + "epoch": 1.59, + "learning_rate": 9.367122990004347e-06, + "loss": 0.322, + "step": 19573 + }, + { + "epoch": 1.6, + "learning_rate": 9.366579747935681e-06, + "loss": 0.1667, + "step": 19574 + }, + { + "epoch": 1.6, + "learning_rate": 9.366036505867016e-06, + "loss": 0.5644, + "step": 19575 + }, + { + "epoch": 1.6, + "learning_rate": 9.36549326379835e-06, + "loss": 0.1059, + "step": 19576 + }, + { + "epoch": 1.6, + "learning_rate": 9.364950021729684e-06, + "loss": 0.5242, + "step": 19577 + }, + { + "epoch": 1.6, + "learning_rate": 9.364406779661017e-06, + "loss": 0.3551, + "step": 19578 + }, + { + "epoch": 1.6, + "learning_rate": 9.363863537592351e-06, + "loss": 0.1727, + "step": 19579 + }, + { + "epoch": 1.6, + "learning_rate": 9.363320295523685e-06, + "loss": 0.2278, + "step": 19580 + }, + { + "epoch": 1.6, + "learning_rate": 9.36277705345502e-06, + "loss": 0.1604, + "step": 19581 + }, + { + "epoch": 1.6, + "learning_rate": 9.362233811386354e-06, + "loss": 0.2929, + "step": 19582 + }, + { + "epoch": 1.6, + "learning_rate": 9.361690569317688e-06, + "loss": 0.1948, + "step": 19583 + }, + { + "epoch": 1.6, + "learning_rate": 9.361147327249022e-06, + "loss": 0.1706, + "step": 19584 + }, + { + "epoch": 1.6, + "learning_rate": 9.360604085180356e-06, + "loss": 0.4281, + "step": 19585 + }, + { + "epoch": 1.6, + "learning_rate": 9.36006084311169e-06, + "loss": 0.3212, + "step": 19586 + }, + { + "epoch": 1.6, + "learning_rate": 9.359517601043025e-06, + "loss": 0.2528, + "step": 19587 + }, + { + "epoch": 1.6, + "learning_rate": 9.358974358974359e-06, + "loss": 0.3912, + "step": 19588 + }, + { + "epoch": 1.6, + "learning_rate": 9.358431116905695e-06, + "loss": 0.3253, + "step": 19589 + }, + { + "epoch": 1.6, + "learning_rate": 9.357887874837029e-06, + "loss": 0.2424, + "step": 19590 + }, + { + "epoch": 1.6, + "learning_rate": 9.357344632768363e-06, + "loss": 0.3353, + "step": 19591 + }, + { + "epoch": 1.6, + "learning_rate": 9.356801390699698e-06, + "loss": 0.158, + "step": 19592 + }, + { + "epoch": 1.6, + "learning_rate": 9.356258148631032e-06, + "loss": 0.3311, + "step": 19593 + }, + { + "epoch": 1.6, + "learning_rate": 9.355714906562366e-06, + "loss": 0.3425, + "step": 19594 + }, + { + "epoch": 1.6, + "learning_rate": 9.3551716644937e-06, + "loss": 0.3981, + "step": 19595 + }, + { + "epoch": 1.6, + "learning_rate": 9.354628422425035e-06, + "loss": 0.2594, + "step": 19596 + }, + { + "epoch": 1.6, + "learning_rate": 9.354085180356367e-06, + "loss": 0.2621, + "step": 19597 + }, + { + "epoch": 1.6, + "learning_rate": 9.353541938287701e-06, + "loss": 0.4714, + "step": 19598 + }, + { + "epoch": 1.6, + "learning_rate": 9.352998696219036e-06, + "loss": 0.3329, + "step": 19599 + }, + { + "epoch": 1.6, + "learning_rate": 9.35245545415037e-06, + "loss": 0.2236, + "step": 19600 + }, + { + "epoch": 1.6, + "learning_rate": 9.351912212081704e-06, + "loss": 0.377, + "step": 19601 + }, + { + "epoch": 1.6, + "learning_rate": 9.351368970013038e-06, + "loss": 0.337, + "step": 19602 + }, + { + "epoch": 1.6, + "learning_rate": 9.350825727944372e-06, + "loss": 0.6458, + "step": 19603 + }, + { + "epoch": 1.6, + "learning_rate": 9.350282485875707e-06, + "loss": 0.1632, + "step": 19604 + }, + { + "epoch": 1.6, + "learning_rate": 9.349739243807041e-06, + "loss": 0.1933, + "step": 19605 + }, + { + "epoch": 1.6, + "learning_rate": 9.349196001738375e-06, + "loss": 0.3938, + "step": 19606 + }, + { + "epoch": 1.6, + "learning_rate": 9.34865275966971e-06, + "loss": 0.4912, + "step": 19607 + }, + { + "epoch": 1.6, + "learning_rate": 9.348109517601044e-06, + "loss": 0.3638, + "step": 19608 + }, + { + "epoch": 1.6, + "learning_rate": 9.347566275532378e-06, + "loss": 0.1377, + "step": 19609 + }, + { + "epoch": 1.6, + "learning_rate": 9.347023033463712e-06, + "loss": 0.2809, + "step": 19610 + }, + { + "epoch": 1.6, + "learning_rate": 9.346479791395046e-06, + "loss": 0.4614, + "step": 19611 + }, + { + "epoch": 1.6, + "learning_rate": 9.34593654932638e-06, + "loss": 0.6698, + "step": 19612 + }, + { + "epoch": 1.6, + "learning_rate": 9.345393307257715e-06, + "loss": 0.423, + "step": 19613 + }, + { + "epoch": 1.6, + "learning_rate": 9.344850065189049e-06, + "loss": 0.1434, + "step": 19614 + }, + { + "epoch": 1.6, + "learning_rate": 9.344306823120383e-06, + "loss": 0.1755, + "step": 19615 + }, + { + "epoch": 1.6, + "learning_rate": 9.343763581051717e-06, + "loss": 0.3853, + "step": 19616 + }, + { + "epoch": 1.6, + "learning_rate": 9.343220338983052e-06, + "loss": 0.2706, + "step": 19617 + }, + { + "epoch": 1.6, + "learning_rate": 9.342677096914386e-06, + "loss": 0.3449, + "step": 19618 + }, + { + "epoch": 1.6, + "learning_rate": 9.34213385484572e-06, + "loss": 0.4088, + "step": 19619 + }, + { + "epoch": 1.6, + "learning_rate": 9.341590612777054e-06, + "loss": 0.2027, + "step": 19620 + }, + { + "epoch": 1.6, + "learning_rate": 9.341047370708389e-06, + "loss": 0.5209, + "step": 19621 + }, + { + "epoch": 1.6, + "learning_rate": 9.340504128639723e-06, + "loss": 0.2805, + "step": 19622 + }, + { + "epoch": 1.6, + "learning_rate": 9.339960886571057e-06, + "loss": 0.5578, + "step": 19623 + }, + { + "epoch": 1.6, + "learning_rate": 9.339417644502391e-06, + "loss": 0.3738, + "step": 19624 + }, + { + "epoch": 1.6, + "learning_rate": 9.338874402433726e-06, + "loss": 0.4066, + "step": 19625 + }, + { + "epoch": 1.6, + "learning_rate": 9.33833116036506e-06, + "loss": 0.3911, + "step": 19626 + }, + { + "epoch": 1.6, + "learning_rate": 9.337787918296394e-06, + "loss": 0.3841, + "step": 19627 + }, + { + "epoch": 1.6, + "learning_rate": 9.337244676227728e-06, + "loss": 0.2528, + "step": 19628 + }, + { + "epoch": 1.6, + "learning_rate": 9.336701434159062e-06, + "loss": 0.218, + "step": 19629 + }, + { + "epoch": 1.6, + "learning_rate": 9.336158192090397e-06, + "loss": 0.2202, + "step": 19630 + }, + { + "epoch": 1.6, + "learning_rate": 9.335614950021731e-06, + "loss": 0.275, + "step": 19631 + }, + { + "epoch": 1.6, + "learning_rate": 9.335071707953065e-06, + "loss": 0.1802, + "step": 19632 + }, + { + "epoch": 1.6, + "learning_rate": 9.3345284658844e-06, + "loss": 0.6451, + "step": 19633 + }, + { + "epoch": 1.6, + "learning_rate": 9.333985223815734e-06, + "loss": 0.6389, + "step": 19634 + }, + { + "epoch": 1.6, + "learning_rate": 9.333441981747066e-06, + "loss": 0.4094, + "step": 19635 + }, + { + "epoch": 1.6, + "learning_rate": 9.3328987396784e-06, + "loss": 0.5399, + "step": 19636 + }, + { + "epoch": 1.6, + "learning_rate": 9.332355497609735e-06, + "loss": 0.435, + "step": 19637 + }, + { + "epoch": 1.6, + "learning_rate": 9.331812255541069e-06, + "loss": 0.4582, + "step": 19638 + }, + { + "epoch": 1.6, + "learning_rate": 9.331269013472403e-06, + "loss": 0.4599, + "step": 19639 + }, + { + "epoch": 1.6, + "learning_rate": 9.330725771403737e-06, + "loss": 0.3404, + "step": 19640 + }, + { + "epoch": 1.6, + "learning_rate": 9.330182529335072e-06, + "loss": 0.1986, + "step": 19641 + }, + { + "epoch": 1.6, + "learning_rate": 9.329639287266406e-06, + "loss": 0.4015, + "step": 19642 + }, + { + "epoch": 1.6, + "learning_rate": 9.329096045197742e-06, + "loss": 0.4131, + "step": 19643 + }, + { + "epoch": 1.6, + "learning_rate": 9.328552803129076e-06, + "loss": 0.1777, + "step": 19644 + }, + { + "epoch": 1.6, + "learning_rate": 9.32800956106041e-06, + "loss": 0.1278, + "step": 19645 + }, + { + "epoch": 1.6, + "learning_rate": 9.327466318991744e-06, + "loss": 0.5102, + "step": 19646 + }, + { + "epoch": 1.6, + "learning_rate": 9.326923076923079e-06, + "loss": 0.4602, + "step": 19647 + }, + { + "epoch": 1.6, + "learning_rate": 9.326379834854413e-06, + "loss": 0.391, + "step": 19648 + }, + { + "epoch": 1.6, + "learning_rate": 9.325836592785747e-06, + "loss": 0.5767, + "step": 19649 + }, + { + "epoch": 1.6, + "learning_rate": 9.325293350717081e-06, + "loss": 0.5388, + "step": 19650 + }, + { + "epoch": 1.6, + "learning_rate": 9.324750108648416e-06, + "loss": 0.1637, + "step": 19651 + }, + { + "epoch": 1.6, + "learning_rate": 9.32420686657975e-06, + "loss": 0.4285, + "step": 19652 + }, + { + "epoch": 1.6, + "learning_rate": 9.323663624511084e-06, + "loss": 0.4334, + "step": 19653 + }, + { + "epoch": 1.6, + "learning_rate": 9.323120382442417e-06, + "loss": 0.2305, + "step": 19654 + }, + { + "epoch": 1.6, + "learning_rate": 9.32257714037375e-06, + "loss": 0.2535, + "step": 19655 + }, + { + "epoch": 1.6, + "learning_rate": 9.322033898305085e-06, + "loss": 0.3017, + "step": 19656 + }, + { + "epoch": 1.6, + "learning_rate": 9.32149065623642e-06, + "loss": 0.3429, + "step": 19657 + }, + { + "epoch": 1.6, + "learning_rate": 9.320947414167753e-06, + "loss": 0.6433, + "step": 19658 + }, + { + "epoch": 1.6, + "learning_rate": 9.320404172099088e-06, + "loss": 0.5653, + "step": 19659 + }, + { + "epoch": 1.6, + "learning_rate": 9.319860930030422e-06, + "loss": 0.1412, + "step": 19660 + }, + { + "epoch": 1.6, + "learning_rate": 9.319317687961756e-06, + "loss": 0.3841, + "step": 19661 + }, + { + "epoch": 1.6, + "learning_rate": 9.31877444589309e-06, + "loss": 0.1873, + "step": 19662 + }, + { + "epoch": 1.6, + "learning_rate": 9.318231203824425e-06, + "loss": 0.4312, + "step": 19663 + }, + { + "epoch": 1.6, + "learning_rate": 9.317687961755759e-06, + "loss": 0.387, + "step": 19664 + }, + { + "epoch": 1.6, + "learning_rate": 9.317144719687093e-06, + "loss": 0.4278, + "step": 19665 + }, + { + "epoch": 1.6, + "learning_rate": 9.316601477618427e-06, + "loss": 0.2913, + "step": 19666 + }, + { + "epoch": 1.6, + "learning_rate": 9.316058235549761e-06, + "loss": 0.3824, + "step": 19667 + }, + { + "epoch": 1.6, + "learning_rate": 9.315514993481096e-06, + "loss": 0.3188, + "step": 19668 + }, + { + "epoch": 1.6, + "learning_rate": 9.31497175141243e-06, + "loss": 0.4424, + "step": 19669 + }, + { + "epoch": 1.6, + "learning_rate": 9.314428509343764e-06, + "loss": 0.3333, + "step": 19670 + }, + { + "epoch": 1.6, + "learning_rate": 9.313885267275098e-06, + "loss": 0.198, + "step": 19671 + }, + { + "epoch": 1.6, + "learning_rate": 9.313342025206433e-06, + "loss": 0.3712, + "step": 19672 + }, + { + "epoch": 1.6, + "learning_rate": 9.312798783137767e-06, + "loss": 0.3453, + "step": 19673 + }, + { + "epoch": 1.6, + "learning_rate": 9.312255541069101e-06, + "loss": 0.1969, + "step": 19674 + }, + { + "epoch": 1.6, + "learning_rate": 9.311712299000435e-06, + "loss": 0.546, + "step": 19675 + }, + { + "epoch": 1.6, + "learning_rate": 9.31116905693177e-06, + "loss": 0.5453, + "step": 19676 + }, + { + "epoch": 1.6, + "learning_rate": 9.310625814863104e-06, + "loss": 0.3494, + "step": 19677 + }, + { + "epoch": 1.6, + "learning_rate": 9.310082572794438e-06, + "loss": 0.3714, + "step": 19678 + }, + { + "epoch": 1.6, + "learning_rate": 9.309539330725772e-06, + "loss": 0.3927, + "step": 19679 + }, + { + "epoch": 1.6, + "learning_rate": 9.308996088657106e-06, + "loss": 0.3166, + "step": 19680 + }, + { + "epoch": 1.6, + "learning_rate": 9.30845284658844e-06, + "loss": 0.3849, + "step": 19681 + }, + { + "epoch": 1.6, + "learning_rate": 9.307909604519775e-06, + "loss": 0.469, + "step": 19682 + }, + { + "epoch": 1.6, + "learning_rate": 9.30736636245111e-06, + "loss": 0.2255, + "step": 19683 + }, + { + "epoch": 1.6, + "learning_rate": 9.306823120382443e-06, + "loss": 0.4692, + "step": 19684 + }, + { + "epoch": 1.6, + "learning_rate": 9.306279878313778e-06, + "loss": 0.3203, + "step": 19685 + }, + { + "epoch": 1.6, + "learning_rate": 9.305736636245112e-06, + "loss": 0.2853, + "step": 19686 + }, + { + "epoch": 1.6, + "learning_rate": 9.305193394176446e-06, + "loss": 0.4973, + "step": 19687 + }, + { + "epoch": 1.6, + "learning_rate": 9.30465015210778e-06, + "loss": 0.4266, + "step": 19688 + }, + { + "epoch": 1.6, + "learning_rate": 9.304106910039115e-06, + "loss": 0.2119, + "step": 19689 + }, + { + "epoch": 1.6, + "learning_rate": 9.303563667970449e-06, + "loss": 0.4016, + "step": 19690 + }, + { + "epoch": 1.6, + "learning_rate": 9.303020425901783e-06, + "loss": 0.331, + "step": 19691 + }, + { + "epoch": 1.6, + "learning_rate": 9.302477183833116e-06, + "loss": 0.1534, + "step": 19692 + }, + { + "epoch": 1.6, + "learning_rate": 9.30193394176445e-06, + "loss": 0.3059, + "step": 19693 + }, + { + "epoch": 1.6, + "learning_rate": 9.301390699695784e-06, + "loss": 0.1756, + "step": 19694 + }, + { + "epoch": 1.6, + "learning_rate": 9.300847457627118e-06, + "loss": 0.4461, + "step": 19695 + }, + { + "epoch": 1.6, + "learning_rate": 9.300304215558452e-06, + "loss": 0.3716, + "step": 19696 + }, + { + "epoch": 1.61, + "learning_rate": 9.299760973489788e-06, + "loss": 0.3418, + "step": 19697 + }, + { + "epoch": 1.61, + "learning_rate": 9.299217731421123e-06, + "loss": 0.4452, + "step": 19698 + }, + { + "epoch": 1.61, + "learning_rate": 9.298674489352457e-06, + "loss": 0.3477, + "step": 19699 + }, + { + "epoch": 1.61, + "learning_rate": 9.298131247283791e-06, + "loss": 0.2654, + "step": 19700 + }, + { + "epoch": 1.61, + "learning_rate": 9.297588005215125e-06, + "loss": 0.1993, + "step": 19701 + }, + { + "epoch": 1.61, + "learning_rate": 9.29704476314646e-06, + "loss": 0.1524, + "step": 19702 + }, + { + "epoch": 1.61, + "learning_rate": 9.296501521077794e-06, + "loss": 0.1687, + "step": 19703 + }, + { + "epoch": 1.61, + "learning_rate": 9.295958279009128e-06, + "loss": 0.2242, + "step": 19704 + }, + { + "epoch": 1.61, + "learning_rate": 9.295415036940462e-06, + "loss": 0.267, + "step": 19705 + }, + { + "epoch": 1.61, + "learning_rate": 9.294871794871796e-06, + "loss": 0.3924, + "step": 19706 + }, + { + "epoch": 1.61, + "learning_rate": 9.29432855280313e-06, + "loss": 0.2353, + "step": 19707 + }, + { + "epoch": 1.61, + "learning_rate": 9.293785310734465e-06, + "loss": 0.2071, + "step": 19708 + }, + { + "epoch": 1.61, + "learning_rate": 9.2932420686658e-06, + "loss": 0.4127, + "step": 19709 + }, + { + "epoch": 1.61, + "learning_rate": 9.292698826597133e-06, + "loss": 0.2629, + "step": 19710 + }, + { + "epoch": 1.61, + "learning_rate": 9.292155584528466e-06, + "loss": 0.2413, + "step": 19711 + }, + { + "epoch": 1.61, + "learning_rate": 9.2916123424598e-06, + "loss": 0.4353, + "step": 19712 + }, + { + "epoch": 1.61, + "learning_rate": 9.291069100391134e-06, + "loss": 0.3018, + "step": 19713 + }, + { + "epoch": 1.61, + "learning_rate": 9.290525858322469e-06, + "loss": 0.3945, + "step": 19714 + }, + { + "epoch": 1.61, + "learning_rate": 9.289982616253803e-06, + "loss": 0.186, + "step": 19715 + }, + { + "epoch": 1.61, + "learning_rate": 9.289439374185137e-06, + "loss": 0.5122, + "step": 19716 + }, + { + "epoch": 1.61, + "learning_rate": 9.288896132116471e-06, + "loss": 0.2274, + "step": 19717 + }, + { + "epoch": 1.61, + "learning_rate": 9.288352890047806e-06, + "loss": 0.4812, + "step": 19718 + }, + { + "epoch": 1.61, + "learning_rate": 9.28780964797914e-06, + "loss": 0.1687, + "step": 19719 + }, + { + "epoch": 1.61, + "learning_rate": 9.287266405910474e-06, + "loss": 0.3876, + "step": 19720 + }, + { + "epoch": 1.61, + "learning_rate": 9.286723163841808e-06, + "loss": 0.2983, + "step": 19721 + }, + { + "epoch": 1.61, + "learning_rate": 9.286179921773142e-06, + "loss": 0.515, + "step": 19722 + }, + { + "epoch": 1.61, + "learning_rate": 9.285636679704477e-06, + "loss": 0.319, + "step": 19723 + }, + { + "epoch": 1.61, + "learning_rate": 9.285093437635811e-06, + "loss": 0.4579, + "step": 19724 + }, + { + "epoch": 1.61, + "learning_rate": 9.284550195567145e-06, + "loss": 0.5227, + "step": 19725 + }, + { + "epoch": 1.61, + "learning_rate": 9.28400695349848e-06, + "loss": 0.2602, + "step": 19726 + }, + { + "epoch": 1.61, + "learning_rate": 9.283463711429814e-06, + "loss": 0.3521, + "step": 19727 + }, + { + "epoch": 1.61, + "learning_rate": 9.282920469361148e-06, + "loss": 0.1624, + "step": 19728 + }, + { + "epoch": 1.61, + "learning_rate": 9.282377227292482e-06, + "loss": 0.3829, + "step": 19729 + }, + { + "epoch": 1.61, + "learning_rate": 9.281833985223816e-06, + "loss": 0.5607, + "step": 19730 + }, + { + "epoch": 1.61, + "learning_rate": 9.28129074315515e-06, + "loss": 0.228, + "step": 19731 + }, + { + "epoch": 1.61, + "learning_rate": 9.280747501086485e-06, + "loss": 0.3699, + "step": 19732 + }, + { + "epoch": 1.61, + "learning_rate": 9.280204259017819e-06, + "loss": 0.3454, + "step": 19733 + }, + { + "epoch": 1.61, + "learning_rate": 9.279661016949153e-06, + "loss": 0.2332, + "step": 19734 + }, + { + "epoch": 1.61, + "learning_rate": 9.279117774880487e-06, + "loss": 0.3305, + "step": 19735 + }, + { + "epoch": 1.61, + "learning_rate": 9.278574532811822e-06, + "loss": 0.2975, + "step": 19736 + }, + { + "epoch": 1.61, + "learning_rate": 9.278031290743156e-06, + "loss": 0.2863, + "step": 19737 + }, + { + "epoch": 1.61, + "learning_rate": 9.27748804867449e-06, + "loss": 0.2367, + "step": 19738 + }, + { + "epoch": 1.61, + "learning_rate": 9.276944806605824e-06, + "loss": 0.2302, + "step": 19739 + }, + { + "epoch": 1.61, + "learning_rate": 9.276401564537159e-06, + "loss": 0.3092, + "step": 19740 + }, + { + "epoch": 1.61, + "learning_rate": 9.275858322468493e-06, + "loss": 0.3257, + "step": 19741 + }, + { + "epoch": 1.61, + "learning_rate": 9.275315080399827e-06, + "loss": 0.3347, + "step": 19742 + }, + { + "epoch": 1.61, + "learning_rate": 9.274771838331161e-06, + "loss": 0.2592, + "step": 19743 + }, + { + "epoch": 1.61, + "learning_rate": 9.274228596262496e-06, + "loss": 0.3541, + "step": 19744 + }, + { + "epoch": 1.61, + "learning_rate": 9.27368535419383e-06, + "loss": 0.2307, + "step": 19745 + }, + { + "epoch": 1.61, + "learning_rate": 9.273142112125164e-06, + "loss": 0.2205, + "step": 19746 + }, + { + "epoch": 1.61, + "learning_rate": 9.272598870056498e-06, + "loss": 0.329, + "step": 19747 + }, + { + "epoch": 1.61, + "learning_rate": 9.272055627987832e-06, + "loss": 0.2318, + "step": 19748 + }, + { + "epoch": 1.61, + "learning_rate": 9.271512385919165e-06, + "loss": 0.5308, + "step": 19749 + }, + { + "epoch": 1.61, + "learning_rate": 9.2709691438505e-06, + "loss": 0.5006, + "step": 19750 + }, + { + "epoch": 1.61, + "eval_accuracy": 0.8399388690779419, + "eval_loss": 0.43916070461273193, + "eval_runtime": 22.3246, + "eval_samples_per_second": 439.649, + "eval_steps_per_second": 3.449, + "step": 19750 + }, + { + "epoch": 1.61, + "learning_rate": 9.270425901781835e-06, + "loss": 0.1604, + "step": 19751 + }, + { + "epoch": 1.61, + "learning_rate": 9.26988265971317e-06, + "loss": 0.3877, + "step": 19752 + }, + { + "epoch": 1.61, + "learning_rate": 9.269339417644504e-06, + "loss": 0.3759, + "step": 19753 + }, + { + "epoch": 1.61, + "learning_rate": 9.268796175575838e-06, + "loss": 0.3408, + "step": 19754 + }, + { + "epoch": 1.61, + "learning_rate": 9.268252933507172e-06, + "loss": 0.5459, + "step": 19755 + }, + { + "epoch": 1.61, + "learning_rate": 9.267709691438506e-06, + "loss": 0.3778, + "step": 19756 + }, + { + "epoch": 1.61, + "learning_rate": 9.26716644936984e-06, + "loss": 0.2654, + "step": 19757 + }, + { + "epoch": 1.61, + "learning_rate": 9.266623207301175e-06, + "loss": 0.4767, + "step": 19758 + }, + { + "epoch": 1.61, + "learning_rate": 9.266079965232509e-06, + "loss": 0.2796, + "step": 19759 + }, + { + "epoch": 1.61, + "learning_rate": 9.265536723163843e-06, + "loss": 0.365, + "step": 19760 + }, + { + "epoch": 1.61, + "learning_rate": 9.264993481095177e-06, + "loss": 0.3409, + "step": 19761 + }, + { + "epoch": 1.61, + "learning_rate": 9.264450239026512e-06, + "loss": 0.397, + "step": 19762 + }, + { + "epoch": 1.61, + "learning_rate": 9.263906996957846e-06, + "loss": 0.1813, + "step": 19763 + }, + { + "epoch": 1.61, + "learning_rate": 9.26336375488918e-06, + "loss": 0.3468, + "step": 19764 + }, + { + "epoch": 1.61, + "learning_rate": 9.262820512820514e-06, + "loss": 0.3285, + "step": 19765 + }, + { + "epoch": 1.61, + "learning_rate": 9.262277270751849e-06, + "loss": 0.1745, + "step": 19766 + }, + { + "epoch": 1.61, + "learning_rate": 9.261734028683183e-06, + "loss": 0.1626, + "step": 19767 + }, + { + "epoch": 1.61, + "learning_rate": 9.261190786614515e-06, + "loss": 0.489, + "step": 19768 + }, + { + "epoch": 1.61, + "learning_rate": 9.26064754454585e-06, + "loss": 0.3591, + "step": 19769 + }, + { + "epoch": 1.61, + "learning_rate": 9.260104302477184e-06, + "loss": 0.4167, + "step": 19770 + }, + { + "epoch": 1.61, + "learning_rate": 9.259561060408518e-06, + "loss": 0.3536, + "step": 19771 + }, + { + "epoch": 1.61, + "learning_rate": 9.259017818339852e-06, + "loss": 0.6249, + "step": 19772 + }, + { + "epoch": 1.61, + "learning_rate": 9.258474576271187e-06, + "loss": 0.308, + "step": 19773 + }, + { + "epoch": 1.61, + "learning_rate": 9.25793133420252e-06, + "loss": 0.1353, + "step": 19774 + }, + { + "epoch": 1.61, + "learning_rate": 9.257388092133855e-06, + "loss": 0.4609, + "step": 19775 + }, + { + "epoch": 1.61, + "learning_rate": 9.25684485006519e-06, + "loss": 0.3128, + "step": 19776 + }, + { + "epoch": 1.61, + "learning_rate": 9.256301607996523e-06, + "loss": 0.3139, + "step": 19777 + }, + { + "epoch": 1.61, + "learning_rate": 9.255758365927858e-06, + "loss": 0.1582, + "step": 19778 + }, + { + "epoch": 1.61, + "learning_rate": 9.255215123859192e-06, + "loss": 0.2058, + "step": 19779 + }, + { + "epoch": 1.61, + "learning_rate": 9.254671881790526e-06, + "loss": 0.1945, + "step": 19780 + }, + { + "epoch": 1.61, + "learning_rate": 9.25412863972186e-06, + "loss": 0.3683, + "step": 19781 + }, + { + "epoch": 1.61, + "learning_rate": 9.253585397653195e-06, + "loss": 0.4386, + "step": 19782 + }, + { + "epoch": 1.61, + "learning_rate": 9.253042155584529e-06, + "loss": 0.1418, + "step": 19783 + }, + { + "epoch": 1.61, + "learning_rate": 9.252498913515863e-06, + "loss": 0.3997, + "step": 19784 + }, + { + "epoch": 1.61, + "learning_rate": 9.251955671447197e-06, + "loss": 0.125, + "step": 19785 + }, + { + "epoch": 1.61, + "learning_rate": 9.251412429378532e-06, + "loss": 0.5909, + "step": 19786 + }, + { + "epoch": 1.61, + "learning_rate": 9.250869187309866e-06, + "loss": 0.3018, + "step": 19787 + }, + { + "epoch": 1.61, + "learning_rate": 9.2503259452412e-06, + "loss": 0.2451, + "step": 19788 + }, + { + "epoch": 1.61, + "learning_rate": 9.249782703172534e-06, + "loss": 0.1652, + "step": 19789 + }, + { + "epoch": 1.61, + "learning_rate": 9.249239461103868e-06, + "loss": 0.5483, + "step": 19790 + }, + { + "epoch": 1.61, + "learning_rate": 9.248696219035203e-06, + "loss": 0.3272, + "step": 19791 + }, + { + "epoch": 1.61, + "learning_rate": 9.248152976966537e-06, + "loss": 0.3599, + "step": 19792 + }, + { + "epoch": 1.61, + "learning_rate": 9.247609734897871e-06, + "loss": 0.5146, + "step": 19793 + }, + { + "epoch": 1.61, + "learning_rate": 9.247066492829205e-06, + "loss": 0.3107, + "step": 19794 + }, + { + "epoch": 1.61, + "learning_rate": 9.24652325076054e-06, + "loss": 0.181, + "step": 19795 + }, + { + "epoch": 1.61, + "learning_rate": 9.245980008691874e-06, + "loss": 0.3093, + "step": 19796 + }, + { + "epoch": 1.61, + "learning_rate": 9.245436766623208e-06, + "loss": 0.5981, + "step": 19797 + }, + { + "epoch": 1.61, + "learning_rate": 9.244893524554542e-06, + "loss": 0.3543, + "step": 19798 + }, + { + "epoch": 1.61, + "learning_rate": 9.244350282485877e-06, + "loss": 0.2742, + "step": 19799 + }, + { + "epoch": 1.61, + "learning_rate": 9.24380704041721e-06, + "loss": 0.1498, + "step": 19800 + }, + { + "epoch": 1.61, + "learning_rate": 9.243263798348545e-06, + "loss": 0.0837, + "step": 19801 + }, + { + "epoch": 1.61, + "learning_rate": 9.24272055627988e-06, + "loss": 0.3381, + "step": 19802 + }, + { + "epoch": 1.61, + "learning_rate": 9.242177314211213e-06, + "loss": 0.0972, + "step": 19803 + }, + { + "epoch": 1.61, + "learning_rate": 9.241634072142548e-06, + "loss": 0.3559, + "step": 19804 + }, + { + "epoch": 1.61, + "learning_rate": 9.241090830073882e-06, + "loss": 0.3069, + "step": 19805 + }, + { + "epoch": 1.61, + "learning_rate": 9.240547588005216e-06, + "loss": 0.4024, + "step": 19806 + }, + { + "epoch": 1.61, + "learning_rate": 9.24000434593655e-06, + "loss": 0.0926, + "step": 19807 + }, + { + "epoch": 1.61, + "learning_rate": 9.239461103867885e-06, + "loss": 0.5085, + "step": 19808 + }, + { + "epoch": 1.61, + "learning_rate": 9.238917861799219e-06, + "loss": 0.1443, + "step": 19809 + }, + { + "epoch": 1.61, + "learning_rate": 9.238374619730553e-06, + "loss": 0.3701, + "step": 19810 + }, + { + "epoch": 1.61, + "learning_rate": 9.237831377661887e-06, + "loss": 0.4517, + "step": 19811 + }, + { + "epoch": 1.61, + "learning_rate": 9.237288135593222e-06, + "loss": 0.3634, + "step": 19812 + }, + { + "epoch": 1.61, + "learning_rate": 9.236744893524556e-06, + "loss": 0.1592, + "step": 19813 + }, + { + "epoch": 1.61, + "learning_rate": 9.23620165145589e-06, + "loss": 0.0922, + "step": 19814 + }, + { + "epoch": 1.61, + "learning_rate": 9.235658409387224e-06, + "loss": 0.5618, + "step": 19815 + }, + { + "epoch": 1.61, + "learning_rate": 9.235115167318558e-06, + "loss": 0.3849, + "step": 19816 + }, + { + "epoch": 1.61, + "learning_rate": 9.234571925249893e-06, + "loss": 0.2826, + "step": 19817 + }, + { + "epoch": 1.61, + "learning_rate": 9.234028683181227e-06, + "loss": 0.3447, + "step": 19818 + }, + { + "epoch": 1.61, + "learning_rate": 9.233485441112561e-06, + "loss": 0.4417, + "step": 19819 + }, + { + "epoch": 1.62, + "learning_rate": 9.232942199043895e-06, + "loss": 0.2469, + "step": 19820 + }, + { + "epoch": 1.62, + "learning_rate": 9.23239895697523e-06, + "loss": 0.346, + "step": 19821 + }, + { + "epoch": 1.62, + "learning_rate": 9.231855714906564e-06, + "loss": 0.2721, + "step": 19822 + }, + { + "epoch": 1.62, + "learning_rate": 9.231312472837898e-06, + "loss": 0.1424, + "step": 19823 + }, + { + "epoch": 1.62, + "learning_rate": 9.230769230769232e-06, + "loss": 0.2788, + "step": 19824 + }, + { + "epoch": 1.62, + "learning_rate": 9.230225988700565e-06, + "loss": 0.5681, + "step": 19825 + }, + { + "epoch": 1.62, + "learning_rate": 9.229682746631899e-06, + "loss": 0.3962, + "step": 19826 + }, + { + "epoch": 1.62, + "learning_rate": 9.229139504563233e-06, + "loss": 0.3469, + "step": 19827 + }, + { + "epoch": 1.62, + "learning_rate": 9.228596262494568e-06, + "loss": 0.4005, + "step": 19828 + }, + { + "epoch": 1.62, + "learning_rate": 9.228053020425902e-06, + "loss": 0.1621, + "step": 19829 + }, + { + "epoch": 1.62, + "learning_rate": 9.227509778357236e-06, + "loss": 0.109, + "step": 19830 + }, + { + "epoch": 1.62, + "learning_rate": 9.22696653628857e-06, + "loss": 0.3415, + "step": 19831 + }, + { + "epoch": 1.62, + "learning_rate": 9.226423294219904e-06, + "loss": 0.1283, + "step": 19832 + }, + { + "epoch": 1.62, + "learning_rate": 9.225880052151239e-06, + "loss": 0.1697, + "step": 19833 + }, + { + "epoch": 1.62, + "learning_rate": 9.225336810082573e-06, + "loss": 0.3919, + "step": 19834 + }, + { + "epoch": 1.62, + "learning_rate": 9.224793568013907e-06, + "loss": 0.6265, + "step": 19835 + }, + { + "epoch": 1.62, + "learning_rate": 9.224250325945241e-06, + "loss": 0.3658, + "step": 19836 + }, + { + "epoch": 1.62, + "learning_rate": 9.223707083876576e-06, + "loss": 0.3237, + "step": 19837 + }, + { + "epoch": 1.62, + "learning_rate": 9.22316384180791e-06, + "loss": 0.3467, + "step": 19838 + }, + { + "epoch": 1.62, + "learning_rate": 9.222620599739244e-06, + "loss": 0.373, + "step": 19839 + }, + { + "epoch": 1.62, + "learning_rate": 9.222077357670578e-06, + "loss": 0.4595, + "step": 19840 + }, + { + "epoch": 1.62, + "learning_rate": 9.221534115601913e-06, + "loss": 0.379, + "step": 19841 + }, + { + "epoch": 1.62, + "learning_rate": 9.220990873533248e-06, + "loss": 0.6566, + "step": 19842 + }, + { + "epoch": 1.62, + "learning_rate": 9.220447631464583e-06, + "loss": 0.5687, + "step": 19843 + }, + { + "epoch": 1.62, + "learning_rate": 9.219904389395915e-06, + "loss": 0.4384, + "step": 19844 + }, + { + "epoch": 1.62, + "learning_rate": 9.21936114732725e-06, + "loss": 0.3022, + "step": 19845 + }, + { + "epoch": 1.62, + "learning_rate": 9.218817905258584e-06, + "loss": 0.2169, + "step": 19846 + }, + { + "epoch": 1.62, + "learning_rate": 9.218274663189918e-06, + "loss": 0.4806, + "step": 19847 + }, + { + "epoch": 1.62, + "learning_rate": 9.217731421121252e-06, + "loss": 0.2687, + "step": 19848 + }, + { + "epoch": 1.62, + "learning_rate": 9.217188179052586e-06, + "loss": 0.2495, + "step": 19849 + }, + { + "epoch": 1.62, + "learning_rate": 9.21664493698392e-06, + "loss": 0.2816, + "step": 19850 + }, + { + "epoch": 1.62, + "learning_rate": 9.216101694915255e-06, + "loss": 0.2864, + "step": 19851 + }, + { + "epoch": 1.62, + "learning_rate": 9.215558452846589e-06, + "loss": 0.3314, + "step": 19852 + }, + { + "epoch": 1.62, + "learning_rate": 9.215015210777923e-06, + "loss": 0.3067, + "step": 19853 + }, + { + "epoch": 1.62, + "learning_rate": 9.214471968709258e-06, + "loss": 0.3479, + "step": 19854 + }, + { + "epoch": 1.62, + "learning_rate": 9.213928726640592e-06, + "loss": 0.1422, + "step": 19855 + }, + { + "epoch": 1.62, + "learning_rate": 9.213385484571926e-06, + "loss": 0.6403, + "step": 19856 + }, + { + "epoch": 1.62, + "learning_rate": 9.21284224250326e-06, + "loss": 0.0838, + "step": 19857 + }, + { + "epoch": 1.62, + "learning_rate": 9.212299000434594e-06, + "loss": 0.3467, + "step": 19858 + }, + { + "epoch": 1.62, + "learning_rate": 9.211755758365929e-06, + "loss": 0.258, + "step": 19859 + }, + { + "epoch": 1.62, + "learning_rate": 9.211212516297263e-06, + "loss": 0.257, + "step": 19860 + }, + { + "epoch": 1.62, + "learning_rate": 9.210669274228597e-06, + "loss": 0.3148, + "step": 19861 + }, + { + "epoch": 1.62, + "learning_rate": 9.210126032159931e-06, + "loss": 0.2736, + "step": 19862 + }, + { + "epoch": 1.62, + "learning_rate": 9.209582790091266e-06, + "loss": 0.2094, + "step": 19863 + }, + { + "epoch": 1.62, + "learning_rate": 9.2090395480226e-06, + "loss": 0.7964, + "step": 19864 + }, + { + "epoch": 1.62, + "learning_rate": 9.208496305953934e-06, + "loss": 0.4268, + "step": 19865 + }, + { + "epoch": 1.62, + "learning_rate": 9.207953063885268e-06, + "loss": 0.4666, + "step": 19866 + }, + { + "epoch": 1.62, + "learning_rate": 9.207409821816603e-06, + "loss": 0.2833, + "step": 19867 + }, + { + "epoch": 1.62, + "learning_rate": 9.206866579747937e-06, + "loss": 0.2395, + "step": 19868 + }, + { + "epoch": 1.62, + "learning_rate": 9.206323337679271e-06, + "loss": 0.2917, + "step": 19869 + }, + { + "epoch": 1.62, + "learning_rate": 9.205780095610605e-06, + "loss": 0.4326, + "step": 19870 + }, + { + "epoch": 1.62, + "learning_rate": 9.20523685354194e-06, + "loss": 0.3477, + "step": 19871 + }, + { + "epoch": 1.62, + "learning_rate": 9.204693611473274e-06, + "loss": 0.3666, + "step": 19872 + }, + { + "epoch": 1.62, + "learning_rate": 9.204150369404608e-06, + "loss": 0.2793, + "step": 19873 + }, + { + "epoch": 1.62, + "learning_rate": 9.203607127335942e-06, + "loss": 0.3004, + "step": 19874 + }, + { + "epoch": 1.62, + "learning_rate": 9.203063885267276e-06, + "loss": 0.5259, + "step": 19875 + }, + { + "epoch": 1.62, + "learning_rate": 9.20252064319861e-06, + "loss": 0.3134, + "step": 19876 + }, + { + "epoch": 1.62, + "learning_rate": 9.201977401129945e-06, + "loss": 0.3253, + "step": 19877 + }, + { + "epoch": 1.62, + "learning_rate": 9.201434159061279e-06, + "loss": 0.272, + "step": 19878 + }, + { + "epoch": 1.62, + "learning_rate": 9.200890916992613e-06, + "loss": 0.3149, + "step": 19879 + }, + { + "epoch": 1.62, + "learning_rate": 9.200347674923948e-06, + "loss": 0.072, + "step": 19880 + }, + { + "epoch": 1.62, + "learning_rate": 9.199804432855282e-06, + "loss": 0.4524, + "step": 19881 + }, + { + "epoch": 1.62, + "learning_rate": 9.199261190786614e-06, + "loss": 0.2985, + "step": 19882 + }, + { + "epoch": 1.62, + "learning_rate": 9.198717948717949e-06, + "loss": 0.2816, + "step": 19883 + }, + { + "epoch": 1.62, + "learning_rate": 9.198174706649283e-06, + "loss": 0.3214, + "step": 19884 + }, + { + "epoch": 1.62, + "learning_rate": 9.197631464580617e-06, + "loss": 0.6326, + "step": 19885 + }, + { + "epoch": 1.62, + "learning_rate": 9.197088222511951e-06, + "loss": 0.4423, + "step": 19886 + }, + { + "epoch": 1.62, + "learning_rate": 9.196544980443285e-06, + "loss": 0.162, + "step": 19887 + }, + { + "epoch": 1.62, + "learning_rate": 9.19600173837462e-06, + "loss": 0.2293, + "step": 19888 + }, + { + "epoch": 1.62, + "learning_rate": 9.195458496305954e-06, + "loss": 0.2779, + "step": 19889 + }, + { + "epoch": 1.62, + "learning_rate": 9.194915254237288e-06, + "loss": 0.2337, + "step": 19890 + }, + { + "epoch": 1.62, + "learning_rate": 9.194372012168622e-06, + "loss": 0.2442, + "step": 19891 + }, + { + "epoch": 1.62, + "learning_rate": 9.193828770099957e-06, + "loss": 0.325, + "step": 19892 + }, + { + "epoch": 1.62, + "learning_rate": 9.19328552803129e-06, + "loss": 0.6042, + "step": 19893 + }, + { + "epoch": 1.62, + "learning_rate": 9.192742285962625e-06, + "loss": 0.1376, + "step": 19894 + }, + { + "epoch": 1.62, + "learning_rate": 9.19219904389396e-06, + "loss": 0.4007, + "step": 19895 + }, + { + "epoch": 1.62, + "learning_rate": 9.191655801825295e-06, + "loss": 0.4463, + "step": 19896 + }, + { + "epoch": 1.62, + "learning_rate": 9.19111255975663e-06, + "loss": 0.2336, + "step": 19897 + }, + { + "epoch": 1.62, + "learning_rate": 9.190569317687964e-06, + "loss": 0.1921, + "step": 19898 + }, + { + "epoch": 1.62, + "learning_rate": 9.190026075619298e-06, + "loss": 0.3213, + "step": 19899 + }, + { + "epoch": 1.62, + "learning_rate": 9.189482833550632e-06, + "loss": 0.3324, + "step": 19900 + }, + { + "epoch": 1.62, + "learning_rate": 9.188939591481965e-06, + "loss": 0.2687, + "step": 19901 + }, + { + "epoch": 1.62, + "learning_rate": 9.188396349413299e-06, + "loss": 0.3125, + "step": 19902 + }, + { + "epoch": 1.62, + "learning_rate": 9.187853107344633e-06, + "loss": 0.2628, + "step": 19903 + }, + { + "epoch": 1.62, + "learning_rate": 9.187309865275967e-06, + "loss": 0.2021, + "step": 19904 + }, + { + "epoch": 1.62, + "learning_rate": 9.186766623207302e-06, + "loss": 0.1951, + "step": 19905 + }, + { + "epoch": 1.62, + "learning_rate": 9.186223381138636e-06, + "loss": 0.6941, + "step": 19906 + }, + { + "epoch": 1.62, + "learning_rate": 9.18568013906997e-06, + "loss": 0.2972, + "step": 19907 + }, + { + "epoch": 1.62, + "learning_rate": 9.185136897001304e-06, + "loss": 0.1306, + "step": 19908 + }, + { + "epoch": 1.62, + "learning_rate": 9.184593654932639e-06, + "loss": 0.3868, + "step": 19909 + }, + { + "epoch": 1.62, + "learning_rate": 9.184050412863973e-06, + "loss": 0.2574, + "step": 19910 + }, + { + "epoch": 1.62, + "learning_rate": 9.183507170795307e-06, + "loss": 0.3097, + "step": 19911 + }, + { + "epoch": 1.62, + "learning_rate": 9.182963928726641e-06, + "loss": 0.2258, + "step": 19912 + }, + { + "epoch": 1.62, + "learning_rate": 9.182420686657975e-06, + "loss": 0.5085, + "step": 19913 + }, + { + "epoch": 1.62, + "learning_rate": 9.18187744458931e-06, + "loss": 0.2453, + "step": 19914 + }, + { + "epoch": 1.62, + "learning_rate": 9.181334202520644e-06, + "loss": 0.4909, + "step": 19915 + }, + { + "epoch": 1.62, + "learning_rate": 9.180790960451978e-06, + "loss": 0.287, + "step": 19916 + }, + { + "epoch": 1.62, + "learning_rate": 9.180247718383312e-06, + "loss": 0.3812, + "step": 19917 + }, + { + "epoch": 1.62, + "learning_rate": 9.179704476314647e-06, + "loss": 0.3593, + "step": 19918 + }, + { + "epoch": 1.62, + "learning_rate": 9.17916123424598e-06, + "loss": 0.1564, + "step": 19919 + }, + { + "epoch": 1.62, + "learning_rate": 9.178617992177315e-06, + "loss": 0.4412, + "step": 19920 + }, + { + "epoch": 1.62, + "learning_rate": 9.17807475010865e-06, + "loss": 0.3717, + "step": 19921 + }, + { + "epoch": 1.62, + "learning_rate": 9.177531508039984e-06, + "loss": 0.4132, + "step": 19922 + }, + { + "epoch": 1.62, + "learning_rate": 9.176988265971318e-06, + "loss": 0.2389, + "step": 19923 + }, + { + "epoch": 1.62, + "learning_rate": 9.176445023902652e-06, + "loss": 0.3248, + "step": 19924 + }, + { + "epoch": 1.62, + "learning_rate": 9.175901781833986e-06, + "loss": 0.3946, + "step": 19925 + }, + { + "epoch": 1.62, + "learning_rate": 9.17535853976532e-06, + "loss": 0.3652, + "step": 19926 + }, + { + "epoch": 1.62, + "learning_rate": 9.174815297696655e-06, + "loss": 0.2057, + "step": 19927 + }, + { + "epoch": 1.62, + "learning_rate": 9.174272055627989e-06, + "loss": 0.4125, + "step": 19928 + }, + { + "epoch": 1.62, + "learning_rate": 9.173728813559323e-06, + "loss": 0.6417, + "step": 19929 + }, + { + "epoch": 1.62, + "learning_rate": 9.173185571490657e-06, + "loss": 0.3637, + "step": 19930 + }, + { + "epoch": 1.62, + "learning_rate": 9.172642329421992e-06, + "loss": 0.2795, + "step": 19931 + }, + { + "epoch": 1.62, + "learning_rate": 9.172099087353326e-06, + "loss": 0.276, + "step": 19932 + }, + { + "epoch": 1.62, + "learning_rate": 9.17155584528466e-06, + "loss": 0.4056, + "step": 19933 + }, + { + "epoch": 1.62, + "learning_rate": 9.171012603215994e-06, + "loss": 0.4887, + "step": 19934 + }, + { + "epoch": 1.62, + "learning_rate": 9.170469361147329e-06, + "loss": 0.224, + "step": 19935 + }, + { + "epoch": 1.62, + "learning_rate": 9.169926119078663e-06, + "loss": 0.2451, + "step": 19936 + }, + { + "epoch": 1.62, + "learning_rate": 9.169382877009997e-06, + "loss": 0.327, + "step": 19937 + }, + { + "epoch": 1.62, + "learning_rate": 9.168839634941331e-06, + "loss": 0.4081, + "step": 19938 + }, + { + "epoch": 1.62, + "learning_rate": 9.168296392872664e-06, + "loss": 0.2914, + "step": 19939 + }, + { + "epoch": 1.62, + "learning_rate": 9.167753150803998e-06, + "loss": 0.3557, + "step": 19940 + }, + { + "epoch": 1.62, + "learning_rate": 9.167209908735332e-06, + "loss": 0.2956, + "step": 19941 + }, + { + "epoch": 1.62, + "learning_rate": 9.166666666666666e-06, + "loss": 0.276, + "step": 19942 + }, + { + "epoch": 1.63, + "learning_rate": 9.166123424598e-06, + "loss": 0.2087, + "step": 19943 + }, + { + "epoch": 1.63, + "learning_rate": 9.165580182529335e-06, + "loss": 0.408, + "step": 19944 + }, + { + "epoch": 1.63, + "learning_rate": 9.165036940460669e-06, + "loss": 0.4137, + "step": 19945 + }, + { + "epoch": 1.63, + "learning_rate": 9.164493698392003e-06, + "loss": 0.3674, + "step": 19946 + }, + { + "epoch": 1.63, + "learning_rate": 9.163950456323338e-06, + "loss": 0.3941, + "step": 19947 + }, + { + "epoch": 1.63, + "learning_rate": 9.163407214254672e-06, + "loss": 0.3775, + "step": 19948 + }, + { + "epoch": 1.63, + "learning_rate": 9.162863972186006e-06, + "loss": 0.4077, + "step": 19949 + }, + { + "epoch": 1.63, + "learning_rate": 9.162320730117342e-06, + "loss": 0.7156, + "step": 19950 + }, + { + "epoch": 1.63, + "learning_rate": 9.161777488048676e-06, + "loss": 0.5266, + "step": 19951 + }, + { + "epoch": 1.63, + "learning_rate": 9.16123424598001e-06, + "loss": 0.3051, + "step": 19952 + }, + { + "epoch": 1.63, + "learning_rate": 9.160691003911345e-06, + "loss": 0.2993, + "step": 19953 + }, + { + "epoch": 1.63, + "learning_rate": 9.160147761842679e-06, + "loss": 0.2013, + "step": 19954 + }, + { + "epoch": 1.63, + "learning_rate": 9.159604519774013e-06, + "loss": 0.3177, + "step": 19955 + }, + { + "epoch": 1.63, + "learning_rate": 9.159061277705347e-06, + "loss": 0.2335, + "step": 19956 + }, + { + "epoch": 1.63, + "learning_rate": 9.158518035636682e-06, + "loss": 0.5238, + "step": 19957 + }, + { + "epoch": 1.63, + "learning_rate": 9.157974793568014e-06, + "loss": 0.3516, + "step": 19958 + }, + { + "epoch": 1.63, + "learning_rate": 9.157431551499348e-06, + "loss": 0.3762, + "step": 19959 + }, + { + "epoch": 1.63, + "learning_rate": 9.156888309430683e-06, + "loss": 0.1652, + "step": 19960 + }, + { + "epoch": 1.63, + "learning_rate": 9.156345067362017e-06, + "loss": 0.4498, + "step": 19961 + }, + { + "epoch": 1.63, + "learning_rate": 9.155801825293351e-06, + "loss": 0.3314, + "step": 19962 + }, + { + "epoch": 1.63, + "learning_rate": 9.155258583224685e-06, + "loss": 0.3151, + "step": 19963 + }, + { + "epoch": 1.63, + "learning_rate": 9.15471534115602e-06, + "loss": 0.2809, + "step": 19964 + }, + { + "epoch": 1.63, + "learning_rate": 9.154172099087354e-06, + "loss": 0.2101, + "step": 19965 + }, + { + "epoch": 1.63, + "learning_rate": 9.153628857018688e-06, + "loss": 0.3112, + "step": 19966 + }, + { + "epoch": 1.63, + "learning_rate": 9.153085614950022e-06, + "loss": 0.3428, + "step": 19967 + }, + { + "epoch": 1.63, + "learning_rate": 9.152542372881356e-06, + "loss": 0.1211, + "step": 19968 + }, + { + "epoch": 1.63, + "learning_rate": 9.15199913081269e-06, + "loss": 0.2099, + "step": 19969 + }, + { + "epoch": 1.63, + "learning_rate": 9.151455888744025e-06, + "loss": 0.5125, + "step": 19970 + }, + { + "epoch": 1.63, + "learning_rate": 9.150912646675359e-06, + "loss": 0.2751, + "step": 19971 + }, + { + "epoch": 1.63, + "learning_rate": 9.150369404606693e-06, + "loss": 0.2857, + "step": 19972 + }, + { + "epoch": 1.63, + "learning_rate": 9.149826162538028e-06, + "loss": 0.3004, + "step": 19973 + }, + { + "epoch": 1.63, + "learning_rate": 9.149282920469362e-06, + "loss": 0.441, + "step": 19974 + }, + { + "epoch": 1.63, + "learning_rate": 9.148739678400696e-06, + "loss": 0.232, + "step": 19975 + }, + { + "epoch": 1.63, + "learning_rate": 9.14819643633203e-06, + "loss": 0.3681, + "step": 19976 + }, + { + "epoch": 1.63, + "learning_rate": 9.147653194263364e-06, + "loss": 0.4129, + "step": 19977 + }, + { + "epoch": 1.63, + "learning_rate": 9.147109952194699e-06, + "loss": 0.2401, + "step": 19978 + }, + { + "epoch": 1.63, + "learning_rate": 9.146566710126033e-06, + "loss": 0.3174, + "step": 19979 + }, + { + "epoch": 1.63, + "learning_rate": 9.146023468057367e-06, + "loss": 0.5558, + "step": 19980 + }, + { + "epoch": 1.63, + "learning_rate": 9.145480225988701e-06, + "loss": 0.2481, + "step": 19981 + }, + { + "epoch": 1.63, + "learning_rate": 9.144936983920036e-06, + "loss": 0.1907, + "step": 19982 + }, + { + "epoch": 1.63, + "learning_rate": 9.14439374185137e-06, + "loss": 0.1726, + "step": 19983 + }, + { + "epoch": 1.63, + "learning_rate": 9.143850499782704e-06, + "loss": 0.4521, + "step": 19984 + }, + { + "epoch": 1.63, + "learning_rate": 9.143307257714038e-06, + "loss": 0.3765, + "step": 19985 + }, + { + "epoch": 1.63, + "learning_rate": 9.142764015645373e-06, + "loss": 0.4351, + "step": 19986 + }, + { + "epoch": 1.63, + "learning_rate": 9.142220773576707e-06, + "loss": 0.4528, + "step": 19987 + }, + { + "epoch": 1.63, + "learning_rate": 9.141677531508041e-06, + "loss": 0.5219, + "step": 19988 + }, + { + "epoch": 1.63, + "learning_rate": 9.141134289439375e-06, + "loss": 0.3147, + "step": 19989 + }, + { + "epoch": 1.63, + "learning_rate": 9.14059104737071e-06, + "loss": 0.3014, + "step": 19990 + }, + { + "epoch": 1.63, + "learning_rate": 9.140047805302044e-06, + "loss": 0.5347, + "step": 19991 + }, + { + "epoch": 1.63, + "learning_rate": 9.139504563233378e-06, + "loss": 0.2322, + "step": 19992 + }, + { + "epoch": 1.63, + "learning_rate": 9.138961321164712e-06, + "loss": 0.362, + "step": 19993 + }, + { + "epoch": 1.63, + "learning_rate": 9.138418079096046e-06, + "loss": 0.5603, + "step": 19994 + }, + { + "epoch": 1.63, + "learning_rate": 9.13787483702738e-06, + "loss": 0.2305, + "step": 19995 + }, + { + "epoch": 1.63, + "learning_rate": 9.137331594958713e-06, + "loss": 0.4677, + "step": 19996 + }, + { + "epoch": 1.63, + "learning_rate": 9.136788352890047e-06, + "loss": 0.2242, + "step": 19997 + }, + { + "epoch": 1.63, + "learning_rate": 9.136245110821382e-06, + "loss": 0.1823, + "step": 19998 + }, + { + "epoch": 1.63, + "learning_rate": 9.135701868752716e-06, + "loss": 0.478, + "step": 19999 + }, + { + "epoch": 1.63, + "learning_rate": 9.13515862668405e-06, + "loss": 0.3699, + "step": 20000 + }, + { + "epoch": 1.63, + "eval_accuracy": 0.8358634742740703, + "eval_loss": 0.4463840425014496, + "eval_runtime": 22.3112, + "eval_samples_per_second": 439.913, + "eval_steps_per_second": 3.451, + "step": 20000 + }, + { + "epoch": 1.63, + "learning_rate": 9.134615384615384e-06, + "loss": 0.5105, + "step": 20001 + }, + { + "epoch": 1.63, + "learning_rate": 9.134072142546719e-06, + "loss": 0.2522, + "step": 20002 + }, + { + "epoch": 1.63, + "learning_rate": 9.133528900478053e-06, + "loss": 0.2808, + "step": 20003 + }, + { + "epoch": 1.63, + "learning_rate": 9.132985658409389e-06, + "loss": 0.1865, + "step": 20004 + }, + { + "epoch": 1.63, + "learning_rate": 9.132442416340723e-06, + "loss": 0.1347, + "step": 20005 + }, + { + "epoch": 1.63, + "learning_rate": 9.131899174272057e-06, + "loss": 0.4315, + "step": 20006 + }, + { + "epoch": 1.63, + "learning_rate": 9.131355932203391e-06, + "loss": 0.1352, + "step": 20007 + }, + { + "epoch": 1.63, + "learning_rate": 9.130812690134726e-06, + "loss": 0.2723, + "step": 20008 + }, + { + "epoch": 1.63, + "learning_rate": 9.13026944806606e-06, + "loss": 0.6443, + "step": 20009 + }, + { + "epoch": 1.63, + "learning_rate": 9.129726205997394e-06, + "loss": 0.2895, + "step": 20010 + }, + { + "epoch": 1.63, + "learning_rate": 9.129182963928728e-06, + "loss": 0.2193, + "step": 20011 + }, + { + "epoch": 1.63, + "learning_rate": 9.128639721860063e-06, + "loss": 0.1999, + "step": 20012 + }, + { + "epoch": 1.63, + "learning_rate": 9.128096479791397e-06, + "loss": 0.3595, + "step": 20013 + }, + { + "epoch": 1.63, + "learning_rate": 9.127553237722731e-06, + "loss": 0.3271, + "step": 20014 + }, + { + "epoch": 1.63, + "learning_rate": 9.127009995654064e-06, + "loss": 0.2102, + "step": 20015 + }, + { + "epoch": 1.63, + "learning_rate": 9.126466753585398e-06, + "loss": 0.1653, + "step": 20016 + }, + { + "epoch": 1.63, + "learning_rate": 9.125923511516732e-06, + "loss": 0.2004, + "step": 20017 + }, + { + "epoch": 1.63, + "learning_rate": 9.125380269448066e-06, + "loss": 0.4825, + "step": 20018 + }, + { + "epoch": 1.63, + "learning_rate": 9.1248370273794e-06, + "loss": 0.4162, + "step": 20019 + }, + { + "epoch": 1.63, + "learning_rate": 9.124293785310735e-06, + "loss": 0.1159, + "step": 20020 + }, + { + "epoch": 1.63, + "learning_rate": 9.123750543242069e-06, + "loss": 0.3978, + "step": 20021 + }, + { + "epoch": 1.63, + "learning_rate": 9.123207301173403e-06, + "loss": 0.3844, + "step": 20022 + }, + { + "epoch": 1.63, + "learning_rate": 9.122664059104737e-06, + "loss": 0.1589, + "step": 20023 + }, + { + "epoch": 1.63, + "learning_rate": 9.122120817036072e-06, + "loss": 0.3639, + "step": 20024 + }, + { + "epoch": 1.63, + "learning_rate": 9.121577574967406e-06, + "loss": 0.3315, + "step": 20025 + }, + { + "epoch": 1.63, + "learning_rate": 9.12103433289874e-06, + "loss": 0.6142, + "step": 20026 + }, + { + "epoch": 1.63, + "learning_rate": 9.120491090830074e-06, + "loss": 0.3457, + "step": 20027 + }, + { + "epoch": 1.63, + "learning_rate": 9.119947848761409e-06, + "loss": 0.3643, + "step": 20028 + }, + { + "epoch": 1.63, + "learning_rate": 9.119404606692743e-06, + "loss": 0.4021, + "step": 20029 + }, + { + "epoch": 1.63, + "learning_rate": 9.118861364624077e-06, + "loss": 0.1672, + "step": 20030 + }, + { + "epoch": 1.63, + "learning_rate": 9.118318122555411e-06, + "loss": 0.2644, + "step": 20031 + }, + { + "epoch": 1.63, + "learning_rate": 9.117774880486745e-06, + "loss": 0.2686, + "step": 20032 + }, + { + "epoch": 1.63, + "learning_rate": 9.11723163841808e-06, + "loss": 0.1858, + "step": 20033 + }, + { + "epoch": 1.63, + "learning_rate": 9.116688396349414e-06, + "loss": 0.4645, + "step": 20034 + }, + { + "epoch": 1.63, + "learning_rate": 9.116145154280748e-06, + "loss": 0.305, + "step": 20035 + }, + { + "epoch": 1.63, + "learning_rate": 9.115601912212082e-06, + "loss": 0.3546, + "step": 20036 + }, + { + "epoch": 1.63, + "learning_rate": 9.115058670143417e-06, + "loss": 0.2848, + "step": 20037 + }, + { + "epoch": 1.63, + "learning_rate": 9.114515428074751e-06, + "loss": 0.4767, + "step": 20038 + }, + { + "epoch": 1.63, + "learning_rate": 9.113972186006085e-06, + "loss": 0.169, + "step": 20039 + }, + { + "epoch": 1.63, + "learning_rate": 9.11342894393742e-06, + "loss": 0.4017, + "step": 20040 + }, + { + "epoch": 1.63, + "learning_rate": 9.112885701868754e-06, + "loss": 0.4389, + "step": 20041 + }, + { + "epoch": 1.63, + "learning_rate": 9.112342459800088e-06, + "loss": 0.5408, + "step": 20042 + }, + { + "epoch": 1.63, + "learning_rate": 9.111799217731422e-06, + "loss": 0.309, + "step": 20043 + }, + { + "epoch": 1.63, + "learning_rate": 9.111255975662756e-06, + "loss": 0.4834, + "step": 20044 + }, + { + "epoch": 1.63, + "learning_rate": 9.11071273359409e-06, + "loss": 0.3407, + "step": 20045 + }, + { + "epoch": 1.63, + "learning_rate": 9.110169491525425e-06, + "loss": 0.4386, + "step": 20046 + }, + { + "epoch": 1.63, + "learning_rate": 9.109626249456759e-06, + "loss": 0.2955, + "step": 20047 + }, + { + "epoch": 1.63, + "learning_rate": 9.109083007388093e-06, + "loss": 0.297, + "step": 20048 + }, + { + "epoch": 1.63, + "learning_rate": 9.108539765319427e-06, + "loss": 0.5819, + "step": 20049 + }, + { + "epoch": 1.63, + "learning_rate": 9.107996523250762e-06, + "loss": 0.6175, + "step": 20050 + }, + { + "epoch": 1.63, + "learning_rate": 9.107453281182096e-06, + "loss": 0.225, + "step": 20051 + }, + { + "epoch": 1.63, + "learning_rate": 9.10691003911343e-06, + "loss": 0.325, + "step": 20052 + }, + { + "epoch": 1.63, + "learning_rate": 9.106366797044763e-06, + "loss": 0.3397, + "step": 20053 + }, + { + "epoch": 1.63, + "learning_rate": 9.105823554976097e-06, + "loss": 0.2032, + "step": 20054 + }, + { + "epoch": 1.63, + "learning_rate": 9.105280312907431e-06, + "loss": 0.2455, + "step": 20055 + }, + { + "epoch": 1.63, + "learning_rate": 9.104737070838765e-06, + "loss": 0.286, + "step": 20056 + }, + { + "epoch": 1.63, + "learning_rate": 9.1041938287701e-06, + "loss": 0.2311, + "step": 20057 + }, + { + "epoch": 1.63, + "learning_rate": 9.103650586701435e-06, + "loss": 0.3434, + "step": 20058 + }, + { + "epoch": 1.63, + "learning_rate": 9.10310734463277e-06, + "loss": 0.5521, + "step": 20059 + }, + { + "epoch": 1.63, + "learning_rate": 9.102564102564104e-06, + "loss": 0.3911, + "step": 20060 + }, + { + "epoch": 1.63, + "learning_rate": 9.102020860495438e-06, + "loss": 0.2781, + "step": 20061 + }, + { + "epoch": 1.63, + "learning_rate": 9.101477618426772e-06, + "loss": 0.3793, + "step": 20062 + }, + { + "epoch": 1.63, + "learning_rate": 9.100934376358107e-06, + "loss": 0.3929, + "step": 20063 + }, + { + "epoch": 1.63, + "learning_rate": 9.100391134289441e-06, + "loss": 0.5605, + "step": 20064 + }, + { + "epoch": 1.64, + "learning_rate": 9.099847892220775e-06, + "loss": 0.4443, + "step": 20065 + }, + { + "epoch": 1.64, + "learning_rate": 9.09930465015211e-06, + "loss": 0.6591, + "step": 20066 + }, + { + "epoch": 1.64, + "learning_rate": 9.098761408083444e-06, + "loss": 0.3895, + "step": 20067 + }, + { + "epoch": 1.64, + "learning_rate": 9.098218166014778e-06, + "loss": 0.2916, + "step": 20068 + }, + { + "epoch": 1.64, + "learning_rate": 9.097674923946112e-06, + "loss": 0.2459, + "step": 20069 + }, + { + "epoch": 1.64, + "learning_rate": 9.097131681877446e-06, + "loss": 0.347, + "step": 20070 + }, + { + "epoch": 1.64, + "learning_rate": 9.09658843980878e-06, + "loss": 0.2377, + "step": 20071 + }, + { + "epoch": 1.64, + "learning_rate": 9.096045197740113e-06, + "loss": 0.4514, + "step": 20072 + }, + { + "epoch": 1.64, + "learning_rate": 9.095501955671447e-06, + "loss": 0.5775, + "step": 20073 + }, + { + "epoch": 1.64, + "learning_rate": 9.094958713602781e-06, + "loss": 0.3464, + "step": 20074 + }, + { + "epoch": 1.64, + "learning_rate": 9.094415471534116e-06, + "loss": 0.4013, + "step": 20075 + }, + { + "epoch": 1.64, + "learning_rate": 9.09387222946545e-06, + "loss": 0.4821, + "step": 20076 + }, + { + "epoch": 1.64, + "learning_rate": 9.093328987396784e-06, + "loss": 0.469, + "step": 20077 + }, + { + "epoch": 1.64, + "learning_rate": 9.092785745328118e-06, + "loss": 0.61, + "step": 20078 + }, + { + "epoch": 1.64, + "learning_rate": 9.092242503259453e-06, + "loss": 0.3338, + "step": 20079 + }, + { + "epoch": 1.64, + "learning_rate": 9.091699261190787e-06, + "loss": 0.4167, + "step": 20080 + }, + { + "epoch": 1.64, + "learning_rate": 9.091156019122121e-06, + "loss": 0.4146, + "step": 20081 + }, + { + "epoch": 1.64, + "learning_rate": 9.090612777053455e-06, + "loss": 0.2346, + "step": 20082 + }, + { + "epoch": 1.64, + "learning_rate": 9.09006953498479e-06, + "loss": 0.1321, + "step": 20083 + }, + { + "epoch": 1.64, + "learning_rate": 9.089526292916124e-06, + "loss": 0.1392, + "step": 20084 + }, + { + "epoch": 1.64, + "learning_rate": 9.088983050847458e-06, + "loss": 0.4448, + "step": 20085 + }, + { + "epoch": 1.64, + "learning_rate": 9.088439808778792e-06, + "loss": 0.3166, + "step": 20086 + }, + { + "epoch": 1.64, + "learning_rate": 9.087896566710126e-06, + "loss": 0.2702, + "step": 20087 + }, + { + "epoch": 1.64, + "learning_rate": 9.08735332464146e-06, + "loss": 0.3697, + "step": 20088 + }, + { + "epoch": 1.64, + "learning_rate": 9.086810082572795e-06, + "loss": 0.465, + "step": 20089 + }, + { + "epoch": 1.64, + "learning_rate": 9.08626684050413e-06, + "loss": 0.253, + "step": 20090 + }, + { + "epoch": 1.64, + "learning_rate": 9.085723598435463e-06, + "loss": 0.2555, + "step": 20091 + }, + { + "epoch": 1.64, + "learning_rate": 9.085180356366798e-06, + "loss": 0.2617, + "step": 20092 + }, + { + "epoch": 1.64, + "learning_rate": 9.084637114298132e-06, + "loss": 0.4751, + "step": 20093 + }, + { + "epoch": 1.64, + "learning_rate": 9.084093872229466e-06, + "loss": 0.3257, + "step": 20094 + }, + { + "epoch": 1.64, + "learning_rate": 9.0835506301608e-06, + "loss": 0.4249, + "step": 20095 + }, + { + "epoch": 1.64, + "learning_rate": 9.083007388092135e-06, + "loss": 0.486, + "step": 20096 + }, + { + "epoch": 1.64, + "learning_rate": 9.082464146023469e-06, + "loss": 0.3937, + "step": 20097 + }, + { + "epoch": 1.64, + "learning_rate": 9.081920903954803e-06, + "loss": 0.3105, + "step": 20098 + }, + { + "epoch": 1.64, + "learning_rate": 9.081377661886137e-06, + "loss": 0.2016, + "step": 20099 + }, + { + "epoch": 1.64, + "learning_rate": 9.080834419817471e-06, + "loss": 0.3092, + "step": 20100 + }, + { + "epoch": 1.64, + "learning_rate": 9.080291177748806e-06, + "loss": 0.1763, + "step": 20101 + }, + { + "epoch": 1.64, + "learning_rate": 9.07974793568014e-06, + "loss": 0.1762, + "step": 20102 + }, + { + "epoch": 1.64, + "learning_rate": 9.079204693611474e-06, + "loss": 0.1568, + "step": 20103 + }, + { + "epoch": 1.64, + "learning_rate": 9.078661451542808e-06, + "loss": 0.3757, + "step": 20104 + }, + { + "epoch": 1.64, + "learning_rate": 9.078118209474143e-06, + "loss": 0.201, + "step": 20105 + }, + { + "epoch": 1.64, + "learning_rate": 9.077574967405477e-06, + "loss": 0.3139, + "step": 20106 + }, + { + "epoch": 1.64, + "learning_rate": 9.077031725336811e-06, + "loss": 0.3393, + "step": 20107 + }, + { + "epoch": 1.64, + "learning_rate": 9.076488483268145e-06, + "loss": 0.1225, + "step": 20108 + }, + { + "epoch": 1.64, + "learning_rate": 9.07594524119948e-06, + "loss": 0.4166, + "step": 20109 + }, + { + "epoch": 1.64, + "learning_rate": 9.075401999130812e-06, + "loss": 0.3775, + "step": 20110 + }, + { + "epoch": 1.64, + "learning_rate": 9.074858757062146e-06, + "loss": 0.1392, + "step": 20111 + }, + { + "epoch": 1.64, + "learning_rate": 9.074315514993482e-06, + "loss": 0.3312, + "step": 20112 + }, + { + "epoch": 1.64, + "learning_rate": 9.073772272924816e-06, + "loss": 0.2824, + "step": 20113 + }, + { + "epoch": 1.64, + "learning_rate": 9.07322903085615e-06, + "loss": 0.3328, + "step": 20114 + }, + { + "epoch": 1.64, + "learning_rate": 9.072685788787485e-06, + "loss": 0.2587, + "step": 20115 + }, + { + "epoch": 1.64, + "learning_rate": 9.07214254671882e-06, + "loss": 0.4181, + "step": 20116 + }, + { + "epoch": 1.64, + "learning_rate": 9.071599304650153e-06, + "loss": 0.2604, + "step": 20117 + }, + { + "epoch": 1.64, + "learning_rate": 9.071056062581488e-06, + "loss": 0.276, + "step": 20118 + }, + { + "epoch": 1.64, + "learning_rate": 9.070512820512822e-06, + "loss": 0.1354, + "step": 20119 + }, + { + "epoch": 1.64, + "learning_rate": 9.069969578444156e-06, + "loss": 0.1935, + "step": 20120 + }, + { + "epoch": 1.64, + "learning_rate": 9.06942633637549e-06, + "loss": 0.2376, + "step": 20121 + }, + { + "epoch": 1.64, + "learning_rate": 9.068883094306825e-06, + "loss": 0.4002, + "step": 20122 + }, + { + "epoch": 1.64, + "learning_rate": 9.068339852238159e-06, + "loss": 0.3032, + "step": 20123 + }, + { + "epoch": 1.64, + "learning_rate": 9.067796610169493e-06, + "loss": 0.1283, + "step": 20124 + }, + { + "epoch": 1.64, + "learning_rate": 9.067253368100827e-06, + "loss": 0.3976, + "step": 20125 + }, + { + "epoch": 1.64, + "learning_rate": 9.066710126032161e-06, + "loss": 0.226, + "step": 20126 + }, + { + "epoch": 1.64, + "learning_rate": 9.066166883963496e-06, + "loss": 0.3081, + "step": 20127 + }, + { + "epoch": 1.64, + "learning_rate": 9.06562364189483e-06, + "loss": 0.1869, + "step": 20128 + }, + { + "epoch": 1.64, + "learning_rate": 9.065080399826162e-06, + "loss": 0.2745, + "step": 20129 + }, + { + "epoch": 1.64, + "learning_rate": 9.064537157757497e-06, + "loss": 0.3503, + "step": 20130 + }, + { + "epoch": 1.64, + "learning_rate": 9.063993915688831e-06, + "loss": 0.3103, + "step": 20131 + }, + { + "epoch": 1.64, + "learning_rate": 9.063450673620165e-06, + "loss": 0.309, + "step": 20132 + }, + { + "epoch": 1.64, + "learning_rate": 9.0629074315515e-06, + "loss": 0.3618, + "step": 20133 + }, + { + "epoch": 1.64, + "learning_rate": 9.062364189482834e-06, + "loss": 0.3084, + "step": 20134 + }, + { + "epoch": 1.64, + "learning_rate": 9.061820947414168e-06, + "loss": 0.2648, + "step": 20135 + }, + { + "epoch": 1.64, + "learning_rate": 9.061277705345502e-06, + "loss": 0.1984, + "step": 20136 + }, + { + "epoch": 1.64, + "learning_rate": 9.060734463276836e-06, + "loss": 0.2838, + "step": 20137 + }, + { + "epoch": 1.64, + "learning_rate": 9.06019122120817e-06, + "loss": 0.3805, + "step": 20138 + }, + { + "epoch": 1.64, + "learning_rate": 9.059647979139505e-06, + "loss": 0.3588, + "step": 20139 + }, + { + "epoch": 1.64, + "learning_rate": 9.059104737070839e-06, + "loss": 0.2361, + "step": 20140 + }, + { + "epoch": 1.64, + "learning_rate": 9.058561495002173e-06, + "loss": 0.3006, + "step": 20141 + }, + { + "epoch": 1.64, + "learning_rate": 9.058018252933507e-06, + "loss": 0.5131, + "step": 20142 + }, + { + "epoch": 1.64, + "learning_rate": 9.057475010864842e-06, + "loss": 0.2237, + "step": 20143 + }, + { + "epoch": 1.64, + "learning_rate": 9.056931768796176e-06, + "loss": 0.2947, + "step": 20144 + }, + { + "epoch": 1.64, + "learning_rate": 9.05638852672751e-06, + "loss": 0.3076, + "step": 20145 + }, + { + "epoch": 1.64, + "learning_rate": 9.055845284658844e-06, + "loss": 0.0905, + "step": 20146 + }, + { + "epoch": 1.64, + "learning_rate": 9.055302042590179e-06, + "loss": 0.2924, + "step": 20147 + }, + { + "epoch": 1.64, + "learning_rate": 9.054758800521513e-06, + "loss": 0.2785, + "step": 20148 + }, + { + "epoch": 1.64, + "learning_rate": 9.054215558452847e-06, + "loss": 0.6558, + "step": 20149 + }, + { + "epoch": 1.64, + "learning_rate": 9.053672316384181e-06, + "loss": 0.208, + "step": 20150 + }, + { + "epoch": 1.64, + "learning_rate": 9.053129074315516e-06, + "loss": 0.2048, + "step": 20151 + }, + { + "epoch": 1.64, + "learning_rate": 9.05258583224685e-06, + "loss": 0.2839, + "step": 20152 + }, + { + "epoch": 1.64, + "learning_rate": 9.052042590178184e-06, + "loss": 0.6456, + "step": 20153 + }, + { + "epoch": 1.64, + "learning_rate": 9.051499348109518e-06, + "loss": 0.2241, + "step": 20154 + }, + { + "epoch": 1.64, + "learning_rate": 9.050956106040852e-06, + "loss": 0.1924, + "step": 20155 + }, + { + "epoch": 1.64, + "learning_rate": 9.050412863972187e-06, + "loss": 0.2626, + "step": 20156 + }, + { + "epoch": 1.64, + "learning_rate": 9.049869621903521e-06, + "loss": 0.3664, + "step": 20157 + }, + { + "epoch": 1.64, + "learning_rate": 9.049326379834855e-06, + "loss": 0.4563, + "step": 20158 + }, + { + "epoch": 1.64, + "learning_rate": 9.04878313776619e-06, + "loss": 0.3656, + "step": 20159 + }, + { + "epoch": 1.64, + "learning_rate": 9.048239895697524e-06, + "loss": 0.3725, + "step": 20160 + }, + { + "epoch": 1.64, + "learning_rate": 9.047696653628858e-06, + "loss": 0.2655, + "step": 20161 + }, + { + "epoch": 1.64, + "learning_rate": 9.047153411560192e-06, + "loss": 0.3616, + "step": 20162 + }, + { + "epoch": 1.64, + "learning_rate": 9.046610169491526e-06, + "loss": 0.5495, + "step": 20163 + }, + { + "epoch": 1.64, + "learning_rate": 9.04606692742286e-06, + "loss": 0.2819, + "step": 20164 + }, + { + "epoch": 1.64, + "learning_rate": 9.045523685354195e-06, + "loss": 0.2686, + "step": 20165 + }, + { + "epoch": 1.64, + "learning_rate": 9.044980443285529e-06, + "loss": 0.4807, + "step": 20166 + }, + { + "epoch": 1.64, + "learning_rate": 9.044437201216863e-06, + "loss": 0.2484, + "step": 20167 + }, + { + "epoch": 1.64, + "learning_rate": 9.043893959148197e-06, + "loss": 0.1877, + "step": 20168 + }, + { + "epoch": 1.64, + "learning_rate": 9.043350717079532e-06, + "loss": 0.301, + "step": 20169 + }, + { + "epoch": 1.64, + "learning_rate": 9.042807475010866e-06, + "loss": 0.2231, + "step": 20170 + }, + { + "epoch": 1.64, + "learning_rate": 9.0422642329422e-06, + "loss": 0.2739, + "step": 20171 + }, + { + "epoch": 1.64, + "learning_rate": 9.041720990873534e-06, + "loss": 0.4929, + "step": 20172 + }, + { + "epoch": 1.64, + "learning_rate": 9.041177748804869e-06, + "loss": 0.2119, + "step": 20173 + }, + { + "epoch": 1.64, + "learning_rate": 9.040634506736203e-06, + "loss": 0.3382, + "step": 20174 + }, + { + "epoch": 1.64, + "learning_rate": 9.040091264667537e-06, + "loss": 0.2804, + "step": 20175 + }, + { + "epoch": 1.64, + "learning_rate": 9.039548022598871e-06, + "loss": 0.1826, + "step": 20176 + }, + { + "epoch": 1.64, + "learning_rate": 9.039004780530206e-06, + "loss": 0.3241, + "step": 20177 + }, + { + "epoch": 1.64, + "learning_rate": 9.03846153846154e-06, + "loss": 0.3722, + "step": 20178 + }, + { + "epoch": 1.64, + "learning_rate": 9.037918296392874e-06, + "loss": 0.3019, + "step": 20179 + }, + { + "epoch": 1.64, + "learning_rate": 9.037375054324208e-06, + "loss": 0.4832, + "step": 20180 + }, + { + "epoch": 1.64, + "learning_rate": 9.036831812255542e-06, + "loss": 0.4314, + "step": 20181 + }, + { + "epoch": 1.64, + "learning_rate": 9.036288570186877e-06, + "loss": 0.2155, + "step": 20182 + }, + { + "epoch": 1.64, + "learning_rate": 9.035745328118211e-06, + "loss": 0.1908, + "step": 20183 + }, + { + "epoch": 1.64, + "learning_rate": 9.035202086049545e-06, + "loss": 0.3584, + "step": 20184 + }, + { + "epoch": 1.64, + "learning_rate": 9.03465884398088e-06, + "loss": 0.3318, + "step": 20185 + }, + { + "epoch": 1.64, + "learning_rate": 9.034115601912214e-06, + "loss": 0.244, + "step": 20186 + }, + { + "epoch": 1.64, + "learning_rate": 9.033572359843546e-06, + "loss": 0.4326, + "step": 20187 + }, + { + "epoch": 1.65, + "learning_rate": 9.03302911777488e-06, + "loss": 0.2398, + "step": 20188 + }, + { + "epoch": 1.65, + "learning_rate": 9.032485875706215e-06, + "loss": 0.5046, + "step": 20189 + }, + { + "epoch": 1.65, + "learning_rate": 9.031942633637549e-06, + "loss": 0.337, + "step": 20190 + }, + { + "epoch": 1.65, + "learning_rate": 9.031399391568883e-06, + "loss": 0.2821, + "step": 20191 + }, + { + "epoch": 1.65, + "learning_rate": 9.030856149500217e-06, + "loss": 0.3001, + "step": 20192 + }, + { + "epoch": 1.65, + "learning_rate": 9.030312907431552e-06, + "loss": 0.1543, + "step": 20193 + }, + { + "epoch": 1.65, + "learning_rate": 9.029769665362886e-06, + "loss": 0.4649, + "step": 20194 + }, + { + "epoch": 1.65, + "learning_rate": 9.02922642329422e-06, + "loss": 0.4034, + "step": 20195 + }, + { + "epoch": 1.65, + "learning_rate": 9.028683181225554e-06, + "loss": 0.1781, + "step": 20196 + }, + { + "epoch": 1.65, + "learning_rate": 9.028139939156888e-06, + "loss": 0.248, + "step": 20197 + }, + { + "epoch": 1.65, + "learning_rate": 9.027596697088223e-06, + "loss": 0.1735, + "step": 20198 + }, + { + "epoch": 1.65, + "learning_rate": 9.027053455019557e-06, + "loss": 0.3738, + "step": 20199 + }, + { + "epoch": 1.65, + "learning_rate": 9.026510212950891e-06, + "loss": 0.615, + "step": 20200 + }, + { + "epoch": 1.65, + "learning_rate": 9.025966970882225e-06, + "loss": 0.1404, + "step": 20201 + }, + { + "epoch": 1.65, + "learning_rate": 9.02542372881356e-06, + "loss": 0.4025, + "step": 20202 + }, + { + "epoch": 1.65, + "learning_rate": 9.024880486744896e-06, + "loss": 0.3159, + "step": 20203 + }, + { + "epoch": 1.65, + "learning_rate": 9.02433724467623e-06, + "loss": 0.316, + "step": 20204 + }, + { + "epoch": 1.65, + "learning_rate": 9.023794002607564e-06, + "loss": 0.3799, + "step": 20205 + }, + { + "epoch": 1.65, + "learning_rate": 9.023250760538897e-06, + "loss": 0.2463, + "step": 20206 + }, + { + "epoch": 1.65, + "learning_rate": 9.02270751847023e-06, + "loss": 0.2251, + "step": 20207 + }, + { + "epoch": 1.65, + "learning_rate": 9.022164276401565e-06, + "loss": 0.3982, + "step": 20208 + }, + { + "epoch": 1.65, + "learning_rate": 9.0216210343329e-06, + "loss": 0.3604, + "step": 20209 + }, + { + "epoch": 1.65, + "learning_rate": 9.021077792264233e-06, + "loss": 0.3373, + "step": 20210 + }, + { + "epoch": 1.65, + "learning_rate": 9.020534550195568e-06, + "loss": 0.3741, + "step": 20211 + }, + { + "epoch": 1.65, + "learning_rate": 9.019991308126902e-06, + "loss": 0.4257, + "step": 20212 + }, + { + "epoch": 1.65, + "learning_rate": 9.019448066058236e-06, + "loss": 0.3479, + "step": 20213 + }, + { + "epoch": 1.65, + "learning_rate": 9.01890482398957e-06, + "loss": 0.7374, + "step": 20214 + }, + { + "epoch": 1.65, + "learning_rate": 9.018361581920905e-06, + "loss": 0.1663, + "step": 20215 + }, + { + "epoch": 1.65, + "learning_rate": 9.017818339852239e-06, + "loss": 0.383, + "step": 20216 + }, + { + "epoch": 1.65, + "learning_rate": 9.017275097783573e-06, + "loss": 0.1188, + "step": 20217 + }, + { + "epoch": 1.65, + "learning_rate": 9.016731855714907e-06, + "loss": 0.2569, + "step": 20218 + }, + { + "epoch": 1.65, + "learning_rate": 9.016188613646242e-06, + "loss": 0.1978, + "step": 20219 + }, + { + "epoch": 1.65, + "learning_rate": 9.015645371577576e-06, + "loss": 0.551, + "step": 20220 + }, + { + "epoch": 1.65, + "learning_rate": 9.01510212950891e-06, + "loss": 0.3975, + "step": 20221 + }, + { + "epoch": 1.65, + "learning_rate": 9.014558887440244e-06, + "loss": 0.5457, + "step": 20222 + }, + { + "epoch": 1.65, + "learning_rate": 9.014015645371578e-06, + "loss": 0.2277, + "step": 20223 + }, + { + "epoch": 1.65, + "learning_rate": 9.013472403302913e-06, + "loss": 0.2991, + "step": 20224 + }, + { + "epoch": 1.65, + "learning_rate": 9.012929161234247e-06, + "loss": 0.2592, + "step": 20225 + }, + { + "epoch": 1.65, + "learning_rate": 9.012385919165581e-06, + "loss": 0.4403, + "step": 20226 + }, + { + "epoch": 1.65, + "learning_rate": 9.011842677096915e-06, + "loss": 0.2391, + "step": 20227 + }, + { + "epoch": 1.65, + "learning_rate": 9.01129943502825e-06, + "loss": 0.1508, + "step": 20228 + }, + { + "epoch": 1.65, + "learning_rate": 9.010756192959584e-06, + "loss": 0.3394, + "step": 20229 + }, + { + "epoch": 1.65, + "learning_rate": 9.010212950890918e-06, + "loss": 0.2231, + "step": 20230 + }, + { + "epoch": 1.65, + "learning_rate": 9.009669708822252e-06, + "loss": 0.4025, + "step": 20231 + }, + { + "epoch": 1.65, + "learning_rate": 9.009126466753587e-06, + "loss": 0.392, + "step": 20232 + }, + { + "epoch": 1.65, + "learning_rate": 9.00858322468492e-06, + "loss": 0.3633, + "step": 20233 + }, + { + "epoch": 1.65, + "learning_rate": 9.008039982616255e-06, + "loss": 0.1718, + "step": 20234 + }, + { + "epoch": 1.65, + "learning_rate": 9.00749674054759e-06, + "loss": 0.3557, + "step": 20235 + }, + { + "epoch": 1.65, + "learning_rate": 9.006953498478923e-06, + "loss": 0.1926, + "step": 20236 + }, + { + "epoch": 1.65, + "learning_rate": 9.006410256410258e-06, + "loss": 0.4158, + "step": 20237 + }, + { + "epoch": 1.65, + "learning_rate": 9.005867014341592e-06, + "loss": 0.1222, + "step": 20238 + }, + { + "epoch": 1.65, + "learning_rate": 9.005323772272926e-06, + "loss": 0.4121, + "step": 20239 + }, + { + "epoch": 1.65, + "learning_rate": 9.00478053020426e-06, + "loss": 0.2357, + "step": 20240 + }, + { + "epoch": 1.65, + "learning_rate": 9.004237288135595e-06, + "loss": 0.5509, + "step": 20241 + }, + { + "epoch": 1.65, + "learning_rate": 9.003694046066929e-06, + "loss": 0.179, + "step": 20242 + }, + { + "epoch": 1.65, + "learning_rate": 9.003150803998263e-06, + "loss": 0.1872, + "step": 20243 + }, + { + "epoch": 1.65, + "learning_rate": 9.002607561929596e-06, + "loss": 0.2189, + "step": 20244 + }, + { + "epoch": 1.65, + "learning_rate": 9.00206431986093e-06, + "loss": 0.3833, + "step": 20245 + }, + { + "epoch": 1.65, + "learning_rate": 9.001521077792264e-06, + "loss": 0.4095, + "step": 20246 + }, + { + "epoch": 1.65, + "learning_rate": 9.000977835723598e-06, + "loss": 0.2169, + "step": 20247 + }, + { + "epoch": 1.65, + "learning_rate": 9.000434593654933e-06, + "loss": 0.3202, + "step": 20248 + }, + { + "epoch": 1.65, + "learning_rate": 8.999891351586267e-06, + "loss": 0.4243, + "step": 20249 + }, + { + "epoch": 1.65, + "learning_rate": 8.999348109517601e-06, + "loss": 0.2046, + "step": 20250 + }, + { + "epoch": 1.65, + "eval_accuracy": 0.841365257259297, + "eval_loss": 0.43142735958099365, + "eval_runtime": 22.2694, + "eval_samples_per_second": 440.739, + "eval_steps_per_second": 3.458, + "step": 20250 + }, + { + "epoch": 1.65, + "learning_rate": 8.998804867448935e-06, + "loss": 0.3804, + "step": 20251 + }, + { + "epoch": 1.65, + "learning_rate": 8.99826162538027e-06, + "loss": 0.221, + "step": 20252 + }, + { + "epoch": 1.65, + "learning_rate": 8.997718383311604e-06, + "loss": 0.1278, + "step": 20253 + }, + { + "epoch": 1.65, + "learning_rate": 8.997175141242938e-06, + "loss": 0.2903, + "step": 20254 + }, + { + "epoch": 1.65, + "learning_rate": 8.996631899174272e-06, + "loss": 0.1753, + "step": 20255 + }, + { + "epoch": 1.65, + "learning_rate": 8.996088657105606e-06, + "loss": 0.2881, + "step": 20256 + }, + { + "epoch": 1.65, + "learning_rate": 8.995545415036942e-06, + "loss": 0.6478, + "step": 20257 + }, + { + "epoch": 1.65, + "learning_rate": 8.995002172968277e-06, + "loss": 0.2181, + "step": 20258 + }, + { + "epoch": 1.65, + "learning_rate": 8.99445893089961e-06, + "loss": 0.5048, + "step": 20259 + }, + { + "epoch": 1.65, + "learning_rate": 8.993915688830945e-06, + "loss": 0.317, + "step": 20260 + }, + { + "epoch": 1.65, + "learning_rate": 8.99337244676228e-06, + "loss": 0.5174, + "step": 20261 + }, + { + "epoch": 1.65, + "learning_rate": 8.992829204693613e-06, + "loss": 0.3605, + "step": 20262 + }, + { + "epoch": 1.65, + "learning_rate": 8.992285962624946e-06, + "loss": 0.2481, + "step": 20263 + }, + { + "epoch": 1.65, + "learning_rate": 8.99174272055628e-06, + "loss": 0.2206, + "step": 20264 + }, + { + "epoch": 1.65, + "learning_rate": 8.991199478487614e-06, + "loss": 0.2995, + "step": 20265 + }, + { + "epoch": 1.65, + "learning_rate": 8.990656236418949e-06, + "loss": 0.2385, + "step": 20266 + }, + { + "epoch": 1.65, + "learning_rate": 8.990112994350283e-06, + "loss": 0.2056, + "step": 20267 + }, + { + "epoch": 1.65, + "learning_rate": 8.989569752281617e-06, + "loss": 0.6001, + "step": 20268 + }, + { + "epoch": 1.65, + "learning_rate": 8.989026510212951e-06, + "loss": 0.283, + "step": 20269 + }, + { + "epoch": 1.65, + "learning_rate": 8.988483268144286e-06, + "loss": 0.2758, + "step": 20270 + }, + { + "epoch": 1.65, + "learning_rate": 8.98794002607562e-06, + "loss": 0.243, + "step": 20271 + }, + { + "epoch": 1.65, + "learning_rate": 8.987396784006954e-06, + "loss": 0.3075, + "step": 20272 + }, + { + "epoch": 1.65, + "learning_rate": 8.986853541938288e-06, + "loss": 0.2567, + "step": 20273 + }, + { + "epoch": 1.65, + "learning_rate": 8.986310299869622e-06, + "loss": 0.3189, + "step": 20274 + }, + { + "epoch": 1.65, + "learning_rate": 8.985767057800957e-06, + "loss": 0.2526, + "step": 20275 + }, + { + "epoch": 1.65, + "learning_rate": 8.985223815732291e-06, + "loss": 0.2171, + "step": 20276 + }, + { + "epoch": 1.65, + "learning_rate": 8.984680573663625e-06, + "loss": 0.499, + "step": 20277 + }, + { + "epoch": 1.65, + "learning_rate": 8.98413733159496e-06, + "loss": 0.2922, + "step": 20278 + }, + { + "epoch": 1.65, + "learning_rate": 8.983594089526294e-06, + "loss": 0.1876, + "step": 20279 + }, + { + "epoch": 1.65, + "learning_rate": 8.983050847457628e-06, + "loss": 0.3157, + "step": 20280 + }, + { + "epoch": 1.65, + "learning_rate": 8.982507605388962e-06, + "loss": 0.2917, + "step": 20281 + }, + { + "epoch": 1.65, + "learning_rate": 8.981964363320296e-06, + "loss": 0.3797, + "step": 20282 + }, + { + "epoch": 1.65, + "learning_rate": 8.98142112125163e-06, + "loss": 0.4625, + "step": 20283 + }, + { + "epoch": 1.65, + "learning_rate": 8.980877879182965e-06, + "loss": 0.2006, + "step": 20284 + }, + { + "epoch": 1.65, + "learning_rate": 8.980334637114299e-06, + "loss": 0.5023, + "step": 20285 + }, + { + "epoch": 1.65, + "learning_rate": 8.979791395045633e-06, + "loss": 0.3804, + "step": 20286 + }, + { + "epoch": 1.65, + "learning_rate": 8.979248152976967e-06, + "loss": 0.2443, + "step": 20287 + }, + { + "epoch": 1.65, + "learning_rate": 8.978704910908302e-06, + "loss": 0.293, + "step": 20288 + }, + { + "epoch": 1.65, + "learning_rate": 8.978161668839636e-06, + "loss": 0.435, + "step": 20289 + }, + { + "epoch": 1.65, + "learning_rate": 8.97761842677097e-06, + "loss": 0.3587, + "step": 20290 + }, + { + "epoch": 1.65, + "learning_rate": 8.977075184702304e-06, + "loss": 0.3218, + "step": 20291 + }, + { + "epoch": 1.65, + "learning_rate": 8.976531942633639e-06, + "loss": 0.4193, + "step": 20292 + }, + { + "epoch": 1.65, + "learning_rate": 8.975988700564973e-06, + "loss": 0.2937, + "step": 20293 + }, + { + "epoch": 1.65, + "learning_rate": 8.975445458496307e-06, + "loss": 0.4788, + "step": 20294 + }, + { + "epoch": 1.65, + "learning_rate": 8.974902216427641e-06, + "loss": 0.4524, + "step": 20295 + }, + { + "epoch": 1.65, + "learning_rate": 8.974358974358976e-06, + "loss": 0.4321, + "step": 20296 + }, + { + "epoch": 1.65, + "learning_rate": 8.97381573229031e-06, + "loss": 0.3112, + "step": 20297 + }, + { + "epoch": 1.65, + "learning_rate": 8.973272490221644e-06, + "loss": 0.21, + "step": 20298 + }, + { + "epoch": 1.65, + "learning_rate": 8.972729248152978e-06, + "loss": 0.3919, + "step": 20299 + }, + { + "epoch": 1.65, + "learning_rate": 8.972186006084312e-06, + "loss": 0.2711, + "step": 20300 + }, + { + "epoch": 1.65, + "learning_rate": 8.971642764015645e-06, + "loss": 0.3868, + "step": 20301 + }, + { + "epoch": 1.65, + "learning_rate": 8.97109952194698e-06, + "loss": 0.4348, + "step": 20302 + }, + { + "epoch": 1.65, + "learning_rate": 8.970556279878313e-06, + "loss": 0.3071, + "step": 20303 + }, + { + "epoch": 1.65, + "learning_rate": 8.970013037809648e-06, + "loss": 0.1588, + "step": 20304 + }, + { + "epoch": 1.65, + "learning_rate": 8.969469795740982e-06, + "loss": 0.4033, + "step": 20305 + }, + { + "epoch": 1.65, + "learning_rate": 8.968926553672316e-06, + "loss": 0.1299, + "step": 20306 + }, + { + "epoch": 1.65, + "learning_rate": 8.96838331160365e-06, + "loss": 0.2936, + "step": 20307 + }, + { + "epoch": 1.65, + "learning_rate": 8.967840069534985e-06, + "loss": 0.2983, + "step": 20308 + }, + { + "epoch": 1.65, + "learning_rate": 8.967296827466319e-06, + "loss": 0.2142, + "step": 20309 + }, + { + "epoch": 1.65, + "learning_rate": 8.966753585397653e-06, + "loss": 0.2447, + "step": 20310 + }, + { + "epoch": 1.66, + "learning_rate": 8.966210343328989e-06, + "loss": 0.4218, + "step": 20311 + }, + { + "epoch": 1.66, + "learning_rate": 8.965667101260323e-06, + "loss": 0.2653, + "step": 20312 + }, + { + "epoch": 1.66, + "learning_rate": 8.965123859191657e-06, + "loss": 0.2758, + "step": 20313 + }, + { + "epoch": 1.66, + "learning_rate": 8.964580617122992e-06, + "loss": 0.5329, + "step": 20314 + }, + { + "epoch": 1.66, + "learning_rate": 8.964037375054326e-06, + "loss": 0.4959, + "step": 20315 + }, + { + "epoch": 1.66, + "learning_rate": 8.96349413298566e-06, + "loss": 0.3043, + "step": 20316 + }, + { + "epoch": 1.66, + "learning_rate": 8.962950890916994e-06, + "loss": 0.2679, + "step": 20317 + }, + { + "epoch": 1.66, + "learning_rate": 8.962407648848329e-06, + "loss": 0.1708, + "step": 20318 + }, + { + "epoch": 1.66, + "learning_rate": 8.961864406779663e-06, + "loss": 0.2582, + "step": 20319 + }, + { + "epoch": 1.66, + "learning_rate": 8.961321164710995e-06, + "loss": 0.4739, + "step": 20320 + }, + { + "epoch": 1.66, + "learning_rate": 8.96077792264233e-06, + "loss": 0.2086, + "step": 20321 + }, + { + "epoch": 1.66, + "learning_rate": 8.960234680573664e-06, + "loss": 0.2878, + "step": 20322 + }, + { + "epoch": 1.66, + "learning_rate": 8.959691438504998e-06, + "loss": 0.1658, + "step": 20323 + }, + { + "epoch": 1.66, + "learning_rate": 8.959148196436332e-06, + "loss": 0.4674, + "step": 20324 + }, + { + "epoch": 1.66, + "learning_rate": 8.958604954367667e-06, + "loss": 0.2848, + "step": 20325 + }, + { + "epoch": 1.66, + "learning_rate": 8.958061712299e-06, + "loss": 0.3617, + "step": 20326 + }, + { + "epoch": 1.66, + "learning_rate": 8.957518470230335e-06, + "loss": 0.334, + "step": 20327 + }, + { + "epoch": 1.66, + "learning_rate": 8.95697522816167e-06, + "loss": 0.3048, + "step": 20328 + }, + { + "epoch": 1.66, + "learning_rate": 8.956431986093003e-06, + "loss": 0.4265, + "step": 20329 + }, + { + "epoch": 1.66, + "learning_rate": 8.955888744024338e-06, + "loss": 0.3147, + "step": 20330 + }, + { + "epoch": 1.66, + "learning_rate": 8.955345501955672e-06, + "loss": 0.3455, + "step": 20331 + }, + { + "epoch": 1.66, + "learning_rate": 8.954802259887006e-06, + "loss": 0.2008, + "step": 20332 + }, + { + "epoch": 1.66, + "learning_rate": 8.95425901781834e-06, + "loss": 0.3004, + "step": 20333 + }, + { + "epoch": 1.66, + "learning_rate": 8.953715775749675e-06, + "loss": 0.6953, + "step": 20334 + }, + { + "epoch": 1.66, + "learning_rate": 8.953172533681009e-06, + "loss": 0.4429, + "step": 20335 + }, + { + "epoch": 1.66, + "learning_rate": 8.952629291612343e-06, + "loss": 0.2076, + "step": 20336 + }, + { + "epoch": 1.66, + "learning_rate": 8.952086049543677e-06, + "loss": 0.1857, + "step": 20337 + }, + { + "epoch": 1.66, + "learning_rate": 8.951542807475012e-06, + "loss": 0.2682, + "step": 20338 + }, + { + "epoch": 1.66, + "learning_rate": 8.950999565406346e-06, + "loss": 0.2381, + "step": 20339 + }, + { + "epoch": 1.66, + "learning_rate": 8.95045632333768e-06, + "loss": 0.1404, + "step": 20340 + }, + { + "epoch": 1.66, + "learning_rate": 8.949913081269014e-06, + "loss": 0.3769, + "step": 20341 + }, + { + "epoch": 1.66, + "learning_rate": 8.949369839200348e-06, + "loss": 0.5394, + "step": 20342 + }, + { + "epoch": 1.66, + "learning_rate": 8.948826597131683e-06, + "loss": 0.3002, + "step": 20343 + }, + { + "epoch": 1.66, + "learning_rate": 8.948283355063017e-06, + "loss": 0.2735, + "step": 20344 + }, + { + "epoch": 1.66, + "learning_rate": 8.947740112994351e-06, + "loss": 0.1861, + "step": 20345 + }, + { + "epoch": 1.66, + "learning_rate": 8.947196870925685e-06, + "loss": 0.2817, + "step": 20346 + }, + { + "epoch": 1.66, + "learning_rate": 8.94665362885702e-06, + "loss": 0.4084, + "step": 20347 + }, + { + "epoch": 1.66, + "learning_rate": 8.946110386788354e-06, + "loss": 0.3447, + "step": 20348 + }, + { + "epoch": 1.66, + "learning_rate": 8.945567144719688e-06, + "loss": 0.3974, + "step": 20349 + }, + { + "epoch": 1.66, + "learning_rate": 8.945023902651022e-06, + "loss": 0.5449, + "step": 20350 + }, + { + "epoch": 1.66, + "learning_rate": 8.944480660582357e-06, + "loss": 0.4954, + "step": 20351 + }, + { + "epoch": 1.66, + "learning_rate": 8.94393741851369e-06, + "loss": 0.6369, + "step": 20352 + }, + { + "epoch": 1.66, + "learning_rate": 8.943394176445025e-06, + "loss": 0.4567, + "step": 20353 + }, + { + "epoch": 1.66, + "learning_rate": 8.94285093437636e-06, + "loss": 0.1941, + "step": 20354 + }, + { + "epoch": 1.66, + "learning_rate": 8.942307692307693e-06, + "loss": 0.3731, + "step": 20355 + }, + { + "epoch": 1.66, + "learning_rate": 8.941764450239028e-06, + "loss": 0.2413, + "step": 20356 + }, + { + "epoch": 1.66, + "learning_rate": 8.941221208170362e-06, + "loss": 0.159, + "step": 20357 + }, + { + "epoch": 1.66, + "learning_rate": 8.940677966101694e-06, + "loss": 0.3574, + "step": 20358 + }, + { + "epoch": 1.66, + "learning_rate": 8.940134724033029e-06, + "loss": 0.1928, + "step": 20359 + }, + { + "epoch": 1.66, + "learning_rate": 8.939591481964363e-06, + "loss": 0.4316, + "step": 20360 + }, + { + "epoch": 1.66, + "learning_rate": 8.939048239895697e-06, + "loss": 0.5225, + "step": 20361 + }, + { + "epoch": 1.66, + "learning_rate": 8.938504997827031e-06, + "loss": 0.538, + "step": 20362 + }, + { + "epoch": 1.66, + "learning_rate": 8.937961755758366e-06, + "loss": 0.5651, + "step": 20363 + }, + { + "epoch": 1.66, + "learning_rate": 8.9374185136897e-06, + "loss": 0.2326, + "step": 20364 + }, + { + "epoch": 1.66, + "learning_rate": 8.936875271621036e-06, + "loss": 0.6808, + "step": 20365 + }, + { + "epoch": 1.66, + "learning_rate": 8.93633202955237e-06, + "loss": 0.5775, + "step": 20366 + }, + { + "epoch": 1.66, + "learning_rate": 8.935788787483704e-06, + "loss": 0.1296, + "step": 20367 + }, + { + "epoch": 1.66, + "learning_rate": 8.935245545415038e-06, + "loss": 0.2996, + "step": 20368 + }, + { + "epoch": 1.66, + "learning_rate": 8.934702303346373e-06, + "loss": 0.2578, + "step": 20369 + }, + { + "epoch": 1.66, + "learning_rate": 8.934159061277707e-06, + "loss": 0.2988, + "step": 20370 + }, + { + "epoch": 1.66, + "learning_rate": 8.933615819209041e-06, + "loss": 0.4021, + "step": 20371 + }, + { + "epoch": 1.66, + "learning_rate": 8.933072577140375e-06, + "loss": 0.2692, + "step": 20372 + }, + { + "epoch": 1.66, + "learning_rate": 8.93252933507171e-06, + "loss": 0.1705, + "step": 20373 + }, + { + "epoch": 1.66, + "learning_rate": 8.931986093003044e-06, + "loss": 0.4151, + "step": 20374 + }, + { + "epoch": 1.66, + "learning_rate": 8.931442850934378e-06, + "loss": 0.231, + "step": 20375 + }, + { + "epoch": 1.66, + "learning_rate": 8.930899608865712e-06, + "loss": 0.6122, + "step": 20376 + }, + { + "epoch": 1.66, + "learning_rate": 8.930356366797045e-06, + "loss": 0.4258, + "step": 20377 + }, + { + "epoch": 1.66, + "learning_rate": 8.929813124728379e-06, + "loss": 0.1874, + "step": 20378 + }, + { + "epoch": 1.66, + "learning_rate": 8.929269882659713e-06, + "loss": 0.2344, + "step": 20379 + }, + { + "epoch": 1.66, + "learning_rate": 8.928726640591048e-06, + "loss": 0.2923, + "step": 20380 + }, + { + "epoch": 1.66, + "learning_rate": 8.928183398522382e-06, + "loss": 0.369, + "step": 20381 + }, + { + "epoch": 1.66, + "learning_rate": 8.927640156453716e-06, + "loss": 0.2208, + "step": 20382 + }, + { + "epoch": 1.66, + "learning_rate": 8.92709691438505e-06, + "loss": 0.248, + "step": 20383 + }, + { + "epoch": 1.66, + "learning_rate": 8.926553672316384e-06, + "loss": 0.4779, + "step": 20384 + }, + { + "epoch": 1.66, + "learning_rate": 8.926010430247719e-06, + "loss": 0.3166, + "step": 20385 + }, + { + "epoch": 1.66, + "learning_rate": 8.925467188179053e-06, + "loss": 0.481, + "step": 20386 + }, + { + "epoch": 1.66, + "learning_rate": 8.924923946110387e-06, + "loss": 0.2335, + "step": 20387 + }, + { + "epoch": 1.66, + "learning_rate": 8.924380704041721e-06, + "loss": 0.3908, + "step": 20388 + }, + { + "epoch": 1.66, + "learning_rate": 8.923837461973056e-06, + "loss": 0.2098, + "step": 20389 + }, + { + "epoch": 1.66, + "learning_rate": 8.92329421990439e-06, + "loss": 0.3425, + "step": 20390 + }, + { + "epoch": 1.66, + "learning_rate": 8.922750977835724e-06, + "loss": 0.3251, + "step": 20391 + }, + { + "epoch": 1.66, + "learning_rate": 8.922207735767058e-06, + "loss": 0.4705, + "step": 20392 + }, + { + "epoch": 1.66, + "learning_rate": 8.921664493698393e-06, + "loss": 0.3138, + "step": 20393 + }, + { + "epoch": 1.66, + "learning_rate": 8.921121251629727e-06, + "loss": 0.4847, + "step": 20394 + }, + { + "epoch": 1.66, + "learning_rate": 8.920578009561061e-06, + "loss": 0.4168, + "step": 20395 + }, + { + "epoch": 1.66, + "learning_rate": 8.920034767492395e-06, + "loss": 0.1964, + "step": 20396 + }, + { + "epoch": 1.66, + "learning_rate": 8.91949152542373e-06, + "loss": 0.4537, + "step": 20397 + }, + { + "epoch": 1.66, + "learning_rate": 8.918948283355064e-06, + "loss": 0.4937, + "step": 20398 + }, + { + "epoch": 1.66, + "learning_rate": 8.918405041286398e-06, + "loss": 0.4374, + "step": 20399 + }, + { + "epoch": 1.66, + "learning_rate": 8.917861799217732e-06, + "loss": 0.3521, + "step": 20400 + }, + { + "epoch": 1.66, + "learning_rate": 8.917318557149066e-06, + "loss": 0.3049, + "step": 20401 + }, + { + "epoch": 1.66, + "learning_rate": 8.9167753150804e-06, + "loss": 0.1497, + "step": 20402 + }, + { + "epoch": 1.66, + "learning_rate": 8.916232073011735e-06, + "loss": 0.2798, + "step": 20403 + }, + { + "epoch": 1.66, + "learning_rate": 8.915688830943069e-06, + "loss": 0.3635, + "step": 20404 + }, + { + "epoch": 1.66, + "learning_rate": 8.915145588874403e-06, + "loss": 0.2369, + "step": 20405 + }, + { + "epoch": 1.66, + "learning_rate": 8.914602346805738e-06, + "loss": 0.3084, + "step": 20406 + }, + { + "epoch": 1.66, + "learning_rate": 8.914059104737072e-06, + "loss": 0.3545, + "step": 20407 + }, + { + "epoch": 1.66, + "learning_rate": 8.913515862668406e-06, + "loss": 0.3387, + "step": 20408 + }, + { + "epoch": 1.66, + "learning_rate": 8.91297262059974e-06, + "loss": 0.293, + "step": 20409 + }, + { + "epoch": 1.66, + "learning_rate": 8.912429378531074e-06, + "loss": 0.2557, + "step": 20410 + }, + { + "epoch": 1.66, + "learning_rate": 8.911886136462409e-06, + "loss": 0.1805, + "step": 20411 + }, + { + "epoch": 1.66, + "learning_rate": 8.911342894393743e-06, + "loss": 0.2519, + "step": 20412 + }, + { + "epoch": 1.66, + "learning_rate": 8.910799652325077e-06, + "loss": 0.1926, + "step": 20413 + }, + { + "epoch": 1.66, + "learning_rate": 8.910256410256411e-06, + "loss": 0.4675, + "step": 20414 + }, + { + "epoch": 1.66, + "learning_rate": 8.909713168187744e-06, + "loss": 0.2135, + "step": 20415 + }, + { + "epoch": 1.66, + "learning_rate": 8.909169926119078e-06, + "loss": 0.3087, + "step": 20416 + }, + { + "epoch": 1.66, + "learning_rate": 8.908626684050412e-06, + "loss": 0.413, + "step": 20417 + }, + { + "epoch": 1.66, + "learning_rate": 8.908083441981747e-06, + "loss": 0.5404, + "step": 20418 + }, + { + "epoch": 1.66, + "learning_rate": 8.907540199913083e-06, + "loss": 0.3588, + "step": 20419 + }, + { + "epoch": 1.66, + "learning_rate": 8.906996957844417e-06, + "loss": 0.1735, + "step": 20420 + }, + { + "epoch": 1.66, + "learning_rate": 8.906453715775751e-06, + "loss": 0.2985, + "step": 20421 + }, + { + "epoch": 1.66, + "learning_rate": 8.905910473707085e-06, + "loss": 0.3474, + "step": 20422 + }, + { + "epoch": 1.66, + "learning_rate": 8.90536723163842e-06, + "loss": 0.1654, + "step": 20423 + }, + { + "epoch": 1.66, + "learning_rate": 8.904823989569754e-06, + "loss": 0.658, + "step": 20424 + }, + { + "epoch": 1.66, + "learning_rate": 8.904280747501088e-06, + "loss": 0.1792, + "step": 20425 + }, + { + "epoch": 1.66, + "learning_rate": 8.903737505432422e-06, + "loss": 0.2523, + "step": 20426 + }, + { + "epoch": 1.66, + "learning_rate": 8.903194263363756e-06, + "loss": 0.4967, + "step": 20427 + }, + { + "epoch": 1.66, + "learning_rate": 8.90265102129509e-06, + "loss": 0.3618, + "step": 20428 + }, + { + "epoch": 1.66, + "learning_rate": 8.902107779226425e-06, + "loss": 0.3537, + "step": 20429 + }, + { + "epoch": 1.66, + "learning_rate": 8.901564537157759e-06, + "loss": 0.2914, + "step": 20430 + }, + { + "epoch": 1.66, + "learning_rate": 8.901021295089093e-06, + "loss": 0.2776, + "step": 20431 + }, + { + "epoch": 1.66, + "learning_rate": 8.900478053020428e-06, + "loss": 0.1787, + "step": 20432 + }, + { + "epoch": 1.67, + "learning_rate": 8.899934810951762e-06, + "loss": 0.2001, + "step": 20433 + }, + { + "epoch": 1.67, + "learning_rate": 8.899391568883094e-06, + "loss": 0.305, + "step": 20434 + }, + { + "epoch": 1.67, + "learning_rate": 8.898848326814429e-06, + "loss": 0.5674, + "step": 20435 + }, + { + "epoch": 1.67, + "learning_rate": 8.898305084745763e-06, + "loss": 0.2108, + "step": 20436 + }, + { + "epoch": 1.67, + "learning_rate": 8.897761842677097e-06, + "loss": 0.2601, + "step": 20437 + }, + { + "epoch": 1.67, + "learning_rate": 8.897218600608431e-06, + "loss": 0.3094, + "step": 20438 + }, + { + "epoch": 1.67, + "learning_rate": 8.896675358539765e-06, + "loss": 0.2321, + "step": 20439 + }, + { + "epoch": 1.67, + "learning_rate": 8.8961321164711e-06, + "loss": 0.2808, + "step": 20440 + }, + { + "epoch": 1.67, + "learning_rate": 8.895588874402434e-06, + "loss": 0.3324, + "step": 20441 + }, + { + "epoch": 1.67, + "learning_rate": 8.895045632333768e-06, + "loss": 0.3078, + "step": 20442 + }, + { + "epoch": 1.67, + "learning_rate": 8.894502390265102e-06, + "loss": 0.3881, + "step": 20443 + }, + { + "epoch": 1.67, + "learning_rate": 8.893959148196437e-06, + "loss": 0.1725, + "step": 20444 + }, + { + "epoch": 1.67, + "learning_rate": 8.89341590612777e-06, + "loss": 0.3366, + "step": 20445 + }, + { + "epoch": 1.67, + "learning_rate": 8.892872664059105e-06, + "loss": 0.2541, + "step": 20446 + }, + { + "epoch": 1.67, + "learning_rate": 8.89232942199044e-06, + "loss": 0.1962, + "step": 20447 + }, + { + "epoch": 1.67, + "learning_rate": 8.891786179921774e-06, + "loss": 0.6219, + "step": 20448 + }, + { + "epoch": 1.67, + "learning_rate": 8.891242937853108e-06, + "loss": 0.136, + "step": 20449 + }, + { + "epoch": 1.67, + "learning_rate": 8.890699695784442e-06, + "loss": 0.4048, + "step": 20450 + }, + { + "epoch": 1.67, + "learning_rate": 8.890156453715776e-06, + "loss": 0.3468, + "step": 20451 + }, + { + "epoch": 1.67, + "learning_rate": 8.88961321164711e-06, + "loss": 0.1234, + "step": 20452 + }, + { + "epoch": 1.67, + "learning_rate": 8.889069969578445e-06, + "loss": 0.4238, + "step": 20453 + }, + { + "epoch": 1.67, + "learning_rate": 8.888526727509779e-06, + "loss": 0.314, + "step": 20454 + }, + { + "epoch": 1.67, + "learning_rate": 8.887983485441113e-06, + "loss": 0.3592, + "step": 20455 + }, + { + "epoch": 1.67, + "learning_rate": 8.887440243372447e-06, + "loss": 0.1348, + "step": 20456 + }, + { + "epoch": 1.67, + "learning_rate": 8.886897001303782e-06, + "loss": 0.67, + "step": 20457 + }, + { + "epoch": 1.67, + "learning_rate": 8.886353759235116e-06, + "loss": 0.2235, + "step": 20458 + }, + { + "epoch": 1.67, + "learning_rate": 8.88581051716645e-06, + "loss": 0.264, + "step": 20459 + }, + { + "epoch": 1.67, + "learning_rate": 8.885267275097784e-06, + "loss": 0.4659, + "step": 20460 + }, + { + "epoch": 1.67, + "learning_rate": 8.884724033029119e-06, + "loss": 0.1931, + "step": 20461 + }, + { + "epoch": 1.67, + "learning_rate": 8.884180790960453e-06, + "loss": 0.3198, + "step": 20462 + }, + { + "epoch": 1.67, + "learning_rate": 8.883637548891787e-06, + "loss": 0.2456, + "step": 20463 + }, + { + "epoch": 1.67, + "learning_rate": 8.883094306823121e-06, + "loss": 0.1323, + "step": 20464 + }, + { + "epoch": 1.67, + "learning_rate": 8.882551064754455e-06, + "loss": 0.2987, + "step": 20465 + }, + { + "epoch": 1.67, + "learning_rate": 8.88200782268579e-06, + "loss": 0.4383, + "step": 20466 + }, + { + "epoch": 1.67, + "learning_rate": 8.881464580617124e-06, + "loss": 0.3819, + "step": 20467 + }, + { + "epoch": 1.67, + "learning_rate": 8.880921338548458e-06, + "loss": 0.4771, + "step": 20468 + }, + { + "epoch": 1.67, + "learning_rate": 8.880378096479792e-06, + "loss": 0.2249, + "step": 20469 + }, + { + "epoch": 1.67, + "learning_rate": 8.879834854411127e-06, + "loss": 0.2778, + "step": 20470 + }, + { + "epoch": 1.67, + "learning_rate": 8.87929161234246e-06, + "loss": 0.3253, + "step": 20471 + }, + { + "epoch": 1.67, + "learning_rate": 8.878748370273793e-06, + "loss": 0.3109, + "step": 20472 + }, + { + "epoch": 1.67, + "learning_rate": 8.87820512820513e-06, + "loss": 0.4983, + "step": 20473 + }, + { + "epoch": 1.67, + "learning_rate": 8.877661886136464e-06, + "loss": 0.2636, + "step": 20474 + }, + { + "epoch": 1.67, + "learning_rate": 8.877118644067798e-06, + "loss": 0.4127, + "step": 20475 + }, + { + "epoch": 1.67, + "learning_rate": 8.876575401999132e-06, + "loss": 0.4767, + "step": 20476 + }, + { + "epoch": 1.67, + "learning_rate": 8.876032159930466e-06, + "loss": 0.4513, + "step": 20477 + }, + { + "epoch": 1.67, + "learning_rate": 8.8754889178618e-06, + "loss": 0.4314, + "step": 20478 + }, + { + "epoch": 1.67, + "learning_rate": 8.874945675793135e-06, + "loss": 0.2869, + "step": 20479 + }, + { + "epoch": 1.67, + "learning_rate": 8.874402433724469e-06, + "loss": 0.388, + "step": 20480 + }, + { + "epoch": 1.67, + "learning_rate": 8.873859191655803e-06, + "loss": 0.3209, + "step": 20481 + }, + { + "epoch": 1.67, + "learning_rate": 8.873315949587137e-06, + "loss": 0.2826, + "step": 20482 + }, + { + "epoch": 1.67, + "learning_rate": 8.872772707518472e-06, + "loss": 0.3157, + "step": 20483 + }, + { + "epoch": 1.67, + "learning_rate": 8.872229465449806e-06, + "loss": 0.3222, + "step": 20484 + }, + { + "epoch": 1.67, + "learning_rate": 8.87168622338114e-06, + "loss": 0.7334, + "step": 20485 + }, + { + "epoch": 1.67, + "learning_rate": 8.871142981312474e-06, + "loss": 0.179, + "step": 20486 + }, + { + "epoch": 1.67, + "learning_rate": 8.870599739243809e-06, + "loss": 0.3544, + "step": 20487 + }, + { + "epoch": 1.67, + "learning_rate": 8.870056497175143e-06, + "loss": 0.3503, + "step": 20488 + }, + { + "epoch": 1.67, + "learning_rate": 8.869513255106477e-06, + "loss": 0.2235, + "step": 20489 + }, + { + "epoch": 1.67, + "learning_rate": 8.868970013037811e-06, + "loss": 0.4344, + "step": 20490 + }, + { + "epoch": 1.67, + "learning_rate": 8.868426770969144e-06, + "loss": 0.157, + "step": 20491 + }, + { + "epoch": 1.67, + "learning_rate": 8.867883528900478e-06, + "loss": 0.5006, + "step": 20492 + }, + { + "epoch": 1.67, + "learning_rate": 8.867340286831812e-06, + "loss": 0.4883, + "step": 20493 + }, + { + "epoch": 1.67, + "learning_rate": 8.866797044763146e-06, + "loss": 0.5092, + "step": 20494 + }, + { + "epoch": 1.67, + "learning_rate": 8.86625380269448e-06, + "loss": 0.3517, + "step": 20495 + }, + { + "epoch": 1.67, + "learning_rate": 8.865710560625815e-06, + "loss": 0.6542, + "step": 20496 + }, + { + "epoch": 1.67, + "learning_rate": 8.865167318557149e-06, + "loss": 0.1402, + "step": 20497 + }, + { + "epoch": 1.67, + "learning_rate": 8.864624076488483e-06, + "loss": 0.5536, + "step": 20498 + }, + { + "epoch": 1.67, + "learning_rate": 8.864080834419818e-06, + "loss": 0.4572, + "step": 20499 + }, + { + "epoch": 1.67, + "learning_rate": 8.863537592351152e-06, + "loss": 0.3266, + "step": 20500 + }, + { + "epoch": 1.67, + "eval_accuracy": 0.8344370860927153, + "eval_loss": 0.45341089367866516, + "eval_runtime": 22.3147, + "eval_samples_per_second": 439.844, + "eval_steps_per_second": 3.451, + "step": 20500 + }, + { + "epoch": 1.67, + "learning_rate": 8.862994350282486e-06, + "loss": 0.5674, + "step": 20501 + }, + { + "epoch": 1.67, + "learning_rate": 8.86245110821382e-06, + "loss": 0.2769, + "step": 20502 + }, + { + "epoch": 1.67, + "learning_rate": 8.861907866145155e-06, + "loss": 0.3373, + "step": 20503 + }, + { + "epoch": 1.67, + "learning_rate": 8.861364624076489e-06, + "loss": 0.1869, + "step": 20504 + }, + { + "epoch": 1.67, + "learning_rate": 8.860821382007823e-06, + "loss": 0.3759, + "step": 20505 + }, + { + "epoch": 1.67, + "learning_rate": 8.860278139939157e-06, + "loss": 0.3589, + "step": 20506 + }, + { + "epoch": 1.67, + "learning_rate": 8.859734897870491e-06, + "loss": 0.4083, + "step": 20507 + }, + { + "epoch": 1.67, + "learning_rate": 8.859191655801826e-06, + "loss": 0.2174, + "step": 20508 + }, + { + "epoch": 1.67, + "learning_rate": 8.858648413733162e-06, + "loss": 0.2769, + "step": 20509 + }, + { + "epoch": 1.67, + "learning_rate": 8.858105171664494e-06, + "loss": 0.2738, + "step": 20510 + }, + { + "epoch": 1.67, + "learning_rate": 8.857561929595828e-06, + "loss": 0.2522, + "step": 20511 + }, + { + "epoch": 1.67, + "learning_rate": 8.857018687527163e-06, + "loss": 0.4452, + "step": 20512 + }, + { + "epoch": 1.67, + "learning_rate": 8.856475445458497e-06, + "loss": 0.3294, + "step": 20513 + }, + { + "epoch": 1.67, + "learning_rate": 8.855932203389831e-06, + "loss": 0.3729, + "step": 20514 + }, + { + "epoch": 1.67, + "learning_rate": 8.855388961321165e-06, + "loss": 0.2603, + "step": 20515 + }, + { + "epoch": 1.67, + "learning_rate": 8.8548457192525e-06, + "loss": 0.2231, + "step": 20516 + }, + { + "epoch": 1.67, + "learning_rate": 8.854302477183834e-06, + "loss": 0.2532, + "step": 20517 + }, + { + "epoch": 1.67, + "learning_rate": 8.853759235115168e-06, + "loss": 0.2829, + "step": 20518 + }, + { + "epoch": 1.67, + "learning_rate": 8.853215993046502e-06, + "loss": 0.2702, + "step": 20519 + }, + { + "epoch": 1.67, + "learning_rate": 8.852672750977836e-06, + "loss": 0.2689, + "step": 20520 + }, + { + "epoch": 1.67, + "learning_rate": 8.85212950890917e-06, + "loss": 0.4471, + "step": 20521 + }, + { + "epoch": 1.67, + "learning_rate": 8.851586266840505e-06, + "loss": 0.2117, + "step": 20522 + }, + { + "epoch": 1.67, + "learning_rate": 8.851043024771839e-06, + "loss": 0.3246, + "step": 20523 + }, + { + "epoch": 1.67, + "learning_rate": 8.850499782703173e-06, + "loss": 0.1224, + "step": 20524 + }, + { + "epoch": 1.67, + "learning_rate": 8.849956540634508e-06, + "loss": 0.3566, + "step": 20525 + }, + { + "epoch": 1.67, + "learning_rate": 8.849413298565842e-06, + "loss": 0.3924, + "step": 20526 + }, + { + "epoch": 1.67, + "learning_rate": 8.848870056497176e-06, + "loss": 0.2832, + "step": 20527 + }, + { + "epoch": 1.67, + "learning_rate": 8.84832681442851e-06, + "loss": 0.2179, + "step": 20528 + }, + { + "epoch": 1.67, + "learning_rate": 8.847783572359845e-06, + "loss": 0.2539, + "step": 20529 + }, + { + "epoch": 1.67, + "learning_rate": 8.847240330291179e-06, + "loss": 0.4991, + "step": 20530 + }, + { + "epoch": 1.67, + "learning_rate": 8.846697088222513e-06, + "loss": 0.3299, + "step": 20531 + }, + { + "epoch": 1.67, + "learning_rate": 8.846153846153847e-06, + "loss": 0.4424, + "step": 20532 + }, + { + "epoch": 1.67, + "learning_rate": 8.845610604085181e-06, + "loss": 0.479, + "step": 20533 + }, + { + "epoch": 1.67, + "learning_rate": 8.845067362016516e-06, + "loss": 0.2695, + "step": 20534 + }, + { + "epoch": 1.67, + "learning_rate": 8.84452411994785e-06, + "loss": 0.4011, + "step": 20535 + }, + { + "epoch": 1.67, + "learning_rate": 8.843980877879184e-06, + "loss": 0.4109, + "step": 20536 + }, + { + "epoch": 1.67, + "learning_rate": 8.843437635810518e-06, + "loss": 0.185, + "step": 20537 + }, + { + "epoch": 1.67, + "learning_rate": 8.842894393741853e-06, + "loss": 0.1893, + "step": 20538 + }, + { + "epoch": 1.67, + "learning_rate": 8.842351151673187e-06, + "loss": 0.3911, + "step": 20539 + }, + { + "epoch": 1.67, + "learning_rate": 8.841807909604521e-06, + "loss": 0.3271, + "step": 20540 + }, + { + "epoch": 1.67, + "learning_rate": 8.841264667535855e-06, + "loss": 0.0696, + "step": 20541 + }, + { + "epoch": 1.67, + "learning_rate": 8.84072142546719e-06, + "loss": 0.3986, + "step": 20542 + }, + { + "epoch": 1.67, + "learning_rate": 8.840178183398524e-06, + "loss": 0.4712, + "step": 20543 + }, + { + "epoch": 1.67, + "learning_rate": 8.839634941329858e-06, + "loss": 0.1958, + "step": 20544 + }, + { + "epoch": 1.67, + "learning_rate": 8.839091699261192e-06, + "loss": 0.0857, + "step": 20545 + }, + { + "epoch": 1.67, + "learning_rate": 8.838548457192526e-06, + "loss": 0.3877, + "step": 20546 + }, + { + "epoch": 1.67, + "learning_rate": 8.83800521512386e-06, + "loss": 0.0795, + "step": 20547 + }, + { + "epoch": 1.67, + "learning_rate": 8.837461973055193e-06, + "loss": 0.435, + "step": 20548 + }, + { + "epoch": 1.67, + "learning_rate": 8.836918730986527e-06, + "loss": 0.2459, + "step": 20549 + }, + { + "epoch": 1.67, + "learning_rate": 8.836375488917862e-06, + "loss": 0.3365, + "step": 20550 + }, + { + "epoch": 1.67, + "learning_rate": 8.835832246849196e-06, + "loss": 0.3148, + "step": 20551 + }, + { + "epoch": 1.67, + "learning_rate": 8.83528900478053e-06, + "loss": 0.297, + "step": 20552 + }, + { + "epoch": 1.67, + "learning_rate": 8.834745762711864e-06, + "loss": 0.4536, + "step": 20553 + }, + { + "epoch": 1.67, + "learning_rate": 8.834202520643199e-06, + "loss": 0.3199, + "step": 20554 + }, + { + "epoch": 1.67, + "learning_rate": 8.833659278574533e-06, + "loss": 0.5301, + "step": 20555 + }, + { + "epoch": 1.68, + "learning_rate": 8.833116036505867e-06, + "loss": 0.1424, + "step": 20556 + }, + { + "epoch": 1.68, + "learning_rate": 8.832572794437201e-06, + "loss": 0.5081, + "step": 20557 + }, + { + "epoch": 1.68, + "learning_rate": 8.832029552368536e-06, + "loss": 0.3333, + "step": 20558 + }, + { + "epoch": 1.68, + "learning_rate": 8.83148631029987e-06, + "loss": 0.3152, + "step": 20559 + }, + { + "epoch": 1.68, + "learning_rate": 8.830943068231204e-06, + "loss": 0.3691, + "step": 20560 + }, + { + "epoch": 1.68, + "learning_rate": 8.830399826162538e-06, + "loss": 0.3043, + "step": 20561 + }, + { + "epoch": 1.68, + "learning_rate": 8.829856584093872e-06, + "loss": 0.1357, + "step": 20562 + }, + { + "epoch": 1.68, + "learning_rate": 8.829313342025208e-06, + "loss": 0.3735, + "step": 20563 + }, + { + "epoch": 1.68, + "learning_rate": 8.828770099956543e-06, + "loss": 0.3993, + "step": 20564 + }, + { + "epoch": 1.68, + "learning_rate": 8.828226857887877e-06, + "loss": 0.3486, + "step": 20565 + }, + { + "epoch": 1.68, + "learning_rate": 8.827683615819211e-06, + "loss": 0.4485, + "step": 20566 + }, + { + "epoch": 1.68, + "learning_rate": 8.827140373750544e-06, + "loss": 0.2867, + "step": 20567 + }, + { + "epoch": 1.68, + "learning_rate": 8.826597131681878e-06, + "loss": 0.284, + "step": 20568 + }, + { + "epoch": 1.68, + "learning_rate": 8.826053889613212e-06, + "loss": 0.5573, + "step": 20569 + }, + { + "epoch": 1.68, + "learning_rate": 8.825510647544546e-06, + "loss": 0.3289, + "step": 20570 + }, + { + "epoch": 1.68, + "learning_rate": 8.82496740547588e-06, + "loss": 0.2443, + "step": 20571 + }, + { + "epoch": 1.68, + "learning_rate": 8.824424163407215e-06, + "loss": 0.3783, + "step": 20572 + }, + { + "epoch": 1.68, + "learning_rate": 8.823880921338549e-06, + "loss": 0.4538, + "step": 20573 + }, + { + "epoch": 1.68, + "learning_rate": 8.823337679269883e-06, + "loss": 0.3054, + "step": 20574 + }, + { + "epoch": 1.68, + "learning_rate": 8.822794437201217e-06, + "loss": 0.1651, + "step": 20575 + }, + { + "epoch": 1.68, + "learning_rate": 8.822251195132552e-06, + "loss": 0.4755, + "step": 20576 + }, + { + "epoch": 1.68, + "learning_rate": 8.821707953063886e-06, + "loss": 0.1736, + "step": 20577 + }, + { + "epoch": 1.68, + "learning_rate": 8.82116471099522e-06, + "loss": 0.1885, + "step": 20578 + }, + { + "epoch": 1.68, + "learning_rate": 8.820621468926554e-06, + "loss": 0.3147, + "step": 20579 + }, + { + "epoch": 1.68, + "learning_rate": 8.820078226857889e-06, + "loss": 0.5158, + "step": 20580 + }, + { + "epoch": 1.68, + "learning_rate": 8.819534984789223e-06, + "loss": 0.6342, + "step": 20581 + }, + { + "epoch": 1.68, + "learning_rate": 8.818991742720557e-06, + "loss": 0.4548, + "step": 20582 + }, + { + "epoch": 1.68, + "learning_rate": 8.818448500651891e-06, + "loss": 0.5292, + "step": 20583 + }, + { + "epoch": 1.68, + "learning_rate": 8.817905258583225e-06, + "loss": 0.1643, + "step": 20584 + }, + { + "epoch": 1.68, + "learning_rate": 8.81736201651456e-06, + "loss": 0.5422, + "step": 20585 + }, + { + "epoch": 1.68, + "learning_rate": 8.816818774445894e-06, + "loss": 0.4229, + "step": 20586 + }, + { + "epoch": 1.68, + "learning_rate": 8.816275532377228e-06, + "loss": 0.2194, + "step": 20587 + }, + { + "epoch": 1.68, + "learning_rate": 8.815732290308562e-06, + "loss": 0.2384, + "step": 20588 + }, + { + "epoch": 1.68, + "learning_rate": 8.815189048239897e-06, + "loss": 0.2642, + "step": 20589 + }, + { + "epoch": 1.68, + "learning_rate": 8.814645806171231e-06, + "loss": 0.4359, + "step": 20590 + }, + { + "epoch": 1.68, + "learning_rate": 8.814102564102565e-06, + "loss": 0.0951, + "step": 20591 + }, + { + "epoch": 1.68, + "learning_rate": 8.8135593220339e-06, + "loss": 0.2018, + "step": 20592 + }, + { + "epoch": 1.68, + "learning_rate": 8.813016079965234e-06, + "loss": 0.181, + "step": 20593 + }, + { + "epoch": 1.68, + "learning_rate": 8.812472837896568e-06, + "loss": 0.3675, + "step": 20594 + }, + { + "epoch": 1.68, + "learning_rate": 8.811929595827902e-06, + "loss": 0.2639, + "step": 20595 + }, + { + "epoch": 1.68, + "learning_rate": 8.811386353759236e-06, + "loss": 0.6604, + "step": 20596 + }, + { + "epoch": 1.68, + "learning_rate": 8.81084311169057e-06, + "loss": 0.1272, + "step": 20597 + }, + { + "epoch": 1.68, + "learning_rate": 8.810299869621905e-06, + "loss": 0.4293, + "step": 20598 + }, + { + "epoch": 1.68, + "learning_rate": 8.809756627553239e-06, + "loss": 0.4671, + "step": 20599 + }, + { + "epoch": 1.68, + "learning_rate": 8.809213385484573e-06, + "loss": 0.287, + "step": 20600 + }, + { + "epoch": 1.68, + "learning_rate": 8.808670143415907e-06, + "loss": 0.357, + "step": 20601 + }, + { + "epoch": 1.68, + "learning_rate": 8.808126901347242e-06, + "loss": 0.3368, + "step": 20602 + }, + { + "epoch": 1.68, + "learning_rate": 8.807583659278576e-06, + "loss": 0.221, + "step": 20603 + }, + { + "epoch": 1.68, + "learning_rate": 8.80704041720991e-06, + "loss": 0.6945, + "step": 20604 + }, + { + "epoch": 1.68, + "learning_rate": 8.806497175141243e-06, + "loss": 0.3932, + "step": 20605 + }, + { + "epoch": 1.68, + "learning_rate": 8.805953933072577e-06, + "loss": 0.3826, + "step": 20606 + }, + { + "epoch": 1.68, + "learning_rate": 8.805410691003911e-06, + "loss": 0.36, + "step": 20607 + }, + { + "epoch": 1.68, + "learning_rate": 8.804867448935245e-06, + "loss": 0.2364, + "step": 20608 + }, + { + "epoch": 1.68, + "learning_rate": 8.80432420686658e-06, + "loss": 0.2167, + "step": 20609 + }, + { + "epoch": 1.68, + "learning_rate": 8.803780964797914e-06, + "loss": 0.3026, + "step": 20610 + }, + { + "epoch": 1.68, + "learning_rate": 8.803237722729248e-06, + "loss": 0.3054, + "step": 20611 + }, + { + "epoch": 1.68, + "learning_rate": 8.802694480660582e-06, + "loss": 0.2185, + "step": 20612 + }, + { + "epoch": 1.68, + "learning_rate": 8.802151238591916e-06, + "loss": 0.3985, + "step": 20613 + }, + { + "epoch": 1.68, + "learning_rate": 8.80160799652325e-06, + "loss": 0.2188, + "step": 20614 + }, + { + "epoch": 1.68, + "learning_rate": 8.801064754454585e-06, + "loss": 0.3425, + "step": 20615 + }, + { + "epoch": 1.68, + "learning_rate": 8.80052151238592e-06, + "loss": 0.208, + "step": 20616 + }, + { + "epoch": 1.68, + "learning_rate": 8.799978270317255e-06, + "loss": 0.1958, + "step": 20617 + }, + { + "epoch": 1.68, + "learning_rate": 8.79943502824859e-06, + "loss": 0.3924, + "step": 20618 + }, + { + "epoch": 1.68, + "learning_rate": 8.798891786179924e-06, + "loss": 0.2643, + "step": 20619 + }, + { + "epoch": 1.68, + "learning_rate": 8.798348544111258e-06, + "loss": 0.1778, + "step": 20620 + }, + { + "epoch": 1.68, + "learning_rate": 8.797805302042592e-06, + "loss": 0.2228, + "step": 20621 + }, + { + "epoch": 1.68, + "learning_rate": 8.797262059973926e-06, + "loss": 0.3378, + "step": 20622 + }, + { + "epoch": 1.68, + "learning_rate": 8.79671881790526e-06, + "loss": 0.3168, + "step": 20623 + }, + { + "epoch": 1.68, + "learning_rate": 8.796175575836593e-06, + "loss": 0.3, + "step": 20624 + }, + { + "epoch": 1.68, + "learning_rate": 8.795632333767927e-06, + "loss": 0.397, + "step": 20625 + }, + { + "epoch": 1.68, + "learning_rate": 8.795089091699261e-06, + "loss": 0.7355, + "step": 20626 + }, + { + "epoch": 1.68, + "learning_rate": 8.794545849630596e-06, + "loss": 0.5818, + "step": 20627 + }, + { + "epoch": 1.68, + "learning_rate": 8.79400260756193e-06, + "loss": 0.4662, + "step": 20628 + }, + { + "epoch": 1.68, + "learning_rate": 8.793459365493264e-06, + "loss": 0.3099, + "step": 20629 + }, + { + "epoch": 1.68, + "learning_rate": 8.792916123424598e-06, + "loss": 0.5874, + "step": 20630 + }, + { + "epoch": 1.68, + "learning_rate": 8.792372881355933e-06, + "loss": 0.3069, + "step": 20631 + }, + { + "epoch": 1.68, + "learning_rate": 8.791829639287267e-06, + "loss": 0.2627, + "step": 20632 + }, + { + "epoch": 1.68, + "learning_rate": 8.791286397218601e-06, + "loss": 0.2295, + "step": 20633 + }, + { + "epoch": 1.68, + "learning_rate": 8.790743155149935e-06, + "loss": 0.4181, + "step": 20634 + }, + { + "epoch": 1.68, + "learning_rate": 8.79019991308127e-06, + "loss": 0.383, + "step": 20635 + }, + { + "epoch": 1.68, + "learning_rate": 8.789656671012604e-06, + "loss": 0.4851, + "step": 20636 + }, + { + "epoch": 1.68, + "learning_rate": 8.789113428943938e-06, + "loss": 0.2664, + "step": 20637 + }, + { + "epoch": 1.68, + "learning_rate": 8.788570186875272e-06, + "loss": 0.2662, + "step": 20638 + }, + { + "epoch": 1.68, + "learning_rate": 8.788026944806606e-06, + "loss": 0.2854, + "step": 20639 + }, + { + "epoch": 1.68, + "learning_rate": 8.78748370273794e-06, + "loss": 0.1957, + "step": 20640 + }, + { + "epoch": 1.68, + "learning_rate": 8.786940460669275e-06, + "loss": 0.1688, + "step": 20641 + }, + { + "epoch": 1.68, + "learning_rate": 8.78639721860061e-06, + "loss": 0.2699, + "step": 20642 + }, + { + "epoch": 1.68, + "learning_rate": 8.785853976531943e-06, + "loss": 0.4385, + "step": 20643 + }, + { + "epoch": 1.68, + "learning_rate": 8.785310734463278e-06, + "loss": 0.1851, + "step": 20644 + }, + { + "epoch": 1.68, + "learning_rate": 8.784767492394612e-06, + "loss": 0.5388, + "step": 20645 + }, + { + "epoch": 1.68, + "learning_rate": 8.784224250325946e-06, + "loss": 0.3701, + "step": 20646 + }, + { + "epoch": 1.68, + "learning_rate": 8.78368100825728e-06, + "loss": 0.3786, + "step": 20647 + }, + { + "epoch": 1.68, + "learning_rate": 8.783137766188615e-06, + "loss": 0.2135, + "step": 20648 + }, + { + "epoch": 1.68, + "learning_rate": 8.782594524119949e-06, + "loss": 0.4279, + "step": 20649 + }, + { + "epoch": 1.68, + "learning_rate": 8.782051282051283e-06, + "loss": 0.5834, + "step": 20650 + }, + { + "epoch": 1.68, + "learning_rate": 8.781508039982617e-06, + "loss": 0.2723, + "step": 20651 + }, + { + "epoch": 1.68, + "learning_rate": 8.780964797913951e-06, + "loss": 0.4304, + "step": 20652 + }, + { + "epoch": 1.68, + "learning_rate": 8.780421555845286e-06, + "loss": 0.4732, + "step": 20653 + }, + { + "epoch": 1.68, + "learning_rate": 8.77987831377662e-06, + "loss": 0.5677, + "step": 20654 + }, + { + "epoch": 1.68, + "learning_rate": 8.779335071707954e-06, + "loss": 0.4786, + "step": 20655 + }, + { + "epoch": 1.68, + "learning_rate": 8.778791829639288e-06, + "loss": 0.3618, + "step": 20656 + }, + { + "epoch": 1.68, + "learning_rate": 8.778248587570623e-06, + "loss": 0.2452, + "step": 20657 + }, + { + "epoch": 1.68, + "learning_rate": 8.777705345501957e-06, + "loss": 0.2457, + "step": 20658 + }, + { + "epoch": 1.68, + "learning_rate": 8.777162103433291e-06, + "loss": 0.4893, + "step": 20659 + }, + { + "epoch": 1.68, + "learning_rate": 8.776618861364625e-06, + "loss": 0.2079, + "step": 20660 + }, + { + "epoch": 1.68, + "learning_rate": 8.77607561929596e-06, + "loss": 0.306, + "step": 20661 + }, + { + "epoch": 1.68, + "learning_rate": 8.775532377227292e-06, + "loss": 0.2777, + "step": 20662 + }, + { + "epoch": 1.68, + "learning_rate": 8.774989135158626e-06, + "loss": 0.4197, + "step": 20663 + }, + { + "epoch": 1.68, + "learning_rate": 8.77444589308996e-06, + "loss": 0.2486, + "step": 20664 + }, + { + "epoch": 1.68, + "learning_rate": 8.773902651021295e-06, + "loss": 0.2247, + "step": 20665 + }, + { + "epoch": 1.68, + "learning_rate": 8.773359408952629e-06, + "loss": 0.3721, + "step": 20666 + }, + { + "epoch": 1.68, + "learning_rate": 8.772816166883963e-06, + "loss": 0.3119, + "step": 20667 + }, + { + "epoch": 1.68, + "learning_rate": 8.772272924815297e-06, + "loss": 0.4098, + "step": 20668 + }, + { + "epoch": 1.68, + "learning_rate": 8.771729682746632e-06, + "loss": 0.1562, + "step": 20669 + }, + { + "epoch": 1.68, + "learning_rate": 8.771186440677966e-06, + "loss": 0.2052, + "step": 20670 + }, + { + "epoch": 1.68, + "learning_rate": 8.770643198609302e-06, + "loss": 0.1826, + "step": 20671 + }, + { + "epoch": 1.68, + "learning_rate": 8.770099956540636e-06, + "loss": 0.2427, + "step": 20672 + }, + { + "epoch": 1.68, + "learning_rate": 8.76955671447197e-06, + "loss": 0.3072, + "step": 20673 + }, + { + "epoch": 1.68, + "learning_rate": 8.769013472403305e-06, + "loss": 0.393, + "step": 20674 + }, + { + "epoch": 1.68, + "learning_rate": 8.768470230334639e-06, + "loss": 0.3657, + "step": 20675 + }, + { + "epoch": 1.68, + "learning_rate": 8.767926988265973e-06, + "loss": 0.1912, + "step": 20676 + }, + { + "epoch": 1.68, + "learning_rate": 8.767383746197307e-06, + "loss": 0.4688, + "step": 20677 + }, + { + "epoch": 1.68, + "learning_rate": 8.766840504128641e-06, + "loss": 0.5341, + "step": 20678 + }, + { + "epoch": 1.69, + "learning_rate": 8.766297262059976e-06, + "loss": 0.1876, + "step": 20679 + }, + { + "epoch": 1.69, + "learning_rate": 8.76575401999131e-06, + "loss": 0.5575, + "step": 20680 + }, + { + "epoch": 1.69, + "learning_rate": 8.765210777922642e-06, + "loss": 0.3074, + "step": 20681 + }, + { + "epoch": 1.69, + "learning_rate": 8.764667535853977e-06, + "loss": 0.201, + "step": 20682 + }, + { + "epoch": 1.69, + "learning_rate": 8.764124293785311e-06, + "loss": 0.6497, + "step": 20683 + }, + { + "epoch": 1.69, + "learning_rate": 8.763581051716645e-06, + "loss": 0.3333, + "step": 20684 + }, + { + "epoch": 1.69, + "learning_rate": 8.76303780964798e-06, + "loss": 0.4587, + "step": 20685 + }, + { + "epoch": 1.69, + "learning_rate": 8.762494567579314e-06, + "loss": 0.2814, + "step": 20686 + }, + { + "epoch": 1.69, + "learning_rate": 8.761951325510648e-06, + "loss": 0.1871, + "step": 20687 + }, + { + "epoch": 1.69, + "learning_rate": 8.761408083441982e-06, + "loss": 0.2328, + "step": 20688 + }, + { + "epoch": 1.69, + "learning_rate": 8.760864841373316e-06, + "loss": 0.246, + "step": 20689 + }, + { + "epoch": 1.69, + "learning_rate": 8.76032159930465e-06, + "loss": 0.2584, + "step": 20690 + }, + { + "epoch": 1.69, + "learning_rate": 8.759778357235985e-06, + "loss": 0.3018, + "step": 20691 + }, + { + "epoch": 1.69, + "learning_rate": 8.759235115167319e-06, + "loss": 0.3947, + "step": 20692 + }, + { + "epoch": 1.69, + "learning_rate": 8.758691873098653e-06, + "loss": 0.261, + "step": 20693 + }, + { + "epoch": 1.69, + "learning_rate": 8.758148631029987e-06, + "loss": 0.2274, + "step": 20694 + }, + { + "epoch": 1.69, + "learning_rate": 8.757605388961322e-06, + "loss": 0.3132, + "step": 20695 + }, + { + "epoch": 1.69, + "learning_rate": 8.757062146892656e-06, + "loss": 0.7596, + "step": 20696 + }, + { + "epoch": 1.69, + "learning_rate": 8.75651890482399e-06, + "loss": 0.3284, + "step": 20697 + }, + { + "epoch": 1.69, + "learning_rate": 8.755975662755324e-06, + "loss": 0.3223, + "step": 20698 + }, + { + "epoch": 1.69, + "learning_rate": 8.755432420686659e-06, + "loss": 0.2592, + "step": 20699 + }, + { + "epoch": 1.69, + "learning_rate": 8.754889178617993e-06, + "loss": 0.5944, + "step": 20700 + }, + { + "epoch": 1.69, + "learning_rate": 8.754345936549327e-06, + "loss": 0.1432, + "step": 20701 + }, + { + "epoch": 1.69, + "learning_rate": 8.753802694480661e-06, + "loss": 0.3984, + "step": 20702 + }, + { + "epoch": 1.69, + "learning_rate": 8.753259452411996e-06, + "loss": 0.4309, + "step": 20703 + }, + { + "epoch": 1.69, + "learning_rate": 8.75271621034333e-06, + "loss": 0.3442, + "step": 20704 + }, + { + "epoch": 1.69, + "learning_rate": 8.752172968274664e-06, + "loss": 0.4537, + "step": 20705 + }, + { + "epoch": 1.69, + "learning_rate": 8.751629726205998e-06, + "loss": 0.3011, + "step": 20706 + }, + { + "epoch": 1.69, + "learning_rate": 8.751086484137332e-06, + "loss": 0.4264, + "step": 20707 + }, + { + "epoch": 1.69, + "learning_rate": 8.750543242068667e-06, + "loss": 0.1589, + "step": 20708 + }, + { + "epoch": 1.69, + "learning_rate": 8.750000000000001e-06, + "loss": 0.2396, + "step": 20709 + }, + { + "epoch": 1.69, + "learning_rate": 8.749456757931335e-06, + "loss": 0.4236, + "step": 20710 + }, + { + "epoch": 1.69, + "learning_rate": 8.74891351586267e-06, + "loss": 0.2028, + "step": 20711 + }, + { + "epoch": 1.69, + "learning_rate": 8.748370273794004e-06, + "loss": 0.4459, + "step": 20712 + }, + { + "epoch": 1.69, + "learning_rate": 8.747827031725338e-06, + "loss": 0.5035, + "step": 20713 + }, + { + "epoch": 1.69, + "learning_rate": 8.747283789656672e-06, + "loss": 0.2299, + "step": 20714 + }, + { + "epoch": 1.69, + "learning_rate": 8.746740547588006e-06, + "loss": 0.376, + "step": 20715 + }, + { + "epoch": 1.69, + "learning_rate": 8.74619730551934e-06, + "loss": 0.3772, + "step": 20716 + }, + { + "epoch": 1.69, + "learning_rate": 8.745654063450675e-06, + "loss": 0.3122, + "step": 20717 + }, + { + "epoch": 1.69, + "learning_rate": 8.745110821382009e-06, + "loss": 0.3289, + "step": 20718 + }, + { + "epoch": 1.69, + "learning_rate": 8.744567579313342e-06, + "loss": 0.228, + "step": 20719 + }, + { + "epoch": 1.69, + "learning_rate": 8.744024337244676e-06, + "loss": 0.248, + "step": 20720 + }, + { + "epoch": 1.69, + "learning_rate": 8.74348109517601e-06, + "loss": 0.5016, + "step": 20721 + }, + { + "epoch": 1.69, + "learning_rate": 8.742937853107344e-06, + "loss": 0.2109, + "step": 20722 + }, + { + "epoch": 1.69, + "learning_rate": 8.742394611038678e-06, + "loss": 0.5961, + "step": 20723 + }, + { + "epoch": 1.69, + "learning_rate": 8.741851368970013e-06, + "loss": 0.2733, + "step": 20724 + }, + { + "epoch": 1.69, + "learning_rate": 8.741308126901349e-06, + "loss": 0.5506, + "step": 20725 + }, + { + "epoch": 1.69, + "learning_rate": 8.740764884832683e-06, + "loss": 0.3195, + "step": 20726 + }, + { + "epoch": 1.69, + "learning_rate": 8.740221642764017e-06, + "loss": 0.5574, + "step": 20727 + }, + { + "epoch": 1.69, + "learning_rate": 8.739678400695351e-06, + "loss": 0.1986, + "step": 20728 + }, + { + "epoch": 1.69, + "learning_rate": 8.739135158626686e-06, + "loss": 0.4418, + "step": 20729 + }, + { + "epoch": 1.69, + "learning_rate": 8.73859191655802e-06, + "loss": 0.2373, + "step": 20730 + }, + { + "epoch": 1.69, + "learning_rate": 8.738048674489354e-06, + "loss": 0.4107, + "step": 20731 + }, + { + "epoch": 1.69, + "learning_rate": 8.737505432420688e-06, + "loss": 0.3624, + "step": 20732 + }, + { + "epoch": 1.69, + "learning_rate": 8.736962190352022e-06, + "loss": 0.3087, + "step": 20733 + }, + { + "epoch": 1.69, + "learning_rate": 8.736418948283357e-06, + "loss": 0.4655, + "step": 20734 + }, + { + "epoch": 1.69, + "learning_rate": 8.735875706214691e-06, + "loss": 0.4265, + "step": 20735 + }, + { + "epoch": 1.69, + "learning_rate": 8.735332464146025e-06, + "loss": 0.3421, + "step": 20736 + }, + { + "epoch": 1.69, + "learning_rate": 8.73478922207736e-06, + "loss": 0.4684, + "step": 20737 + }, + { + "epoch": 1.69, + "learning_rate": 8.734245980008692e-06, + "loss": 0.2899, + "step": 20738 + }, + { + "epoch": 1.69, + "learning_rate": 8.733702737940026e-06, + "loss": 0.3602, + "step": 20739 + }, + { + "epoch": 1.69, + "learning_rate": 8.73315949587136e-06, + "loss": 0.4228, + "step": 20740 + }, + { + "epoch": 1.69, + "learning_rate": 8.732616253802695e-06, + "loss": 0.255, + "step": 20741 + }, + { + "epoch": 1.69, + "learning_rate": 8.732073011734029e-06, + "loss": 0.3873, + "step": 20742 + }, + { + "epoch": 1.69, + "learning_rate": 8.731529769665363e-06, + "loss": 0.3118, + "step": 20743 + }, + { + "epoch": 1.69, + "learning_rate": 8.730986527596697e-06, + "loss": 0.2844, + "step": 20744 + }, + { + "epoch": 1.69, + "learning_rate": 8.730443285528032e-06, + "loss": 0.3022, + "step": 20745 + }, + { + "epoch": 1.69, + "learning_rate": 8.729900043459366e-06, + "loss": 0.3537, + "step": 20746 + }, + { + "epoch": 1.69, + "learning_rate": 8.7293568013907e-06, + "loss": 0.4022, + "step": 20747 + }, + { + "epoch": 1.69, + "learning_rate": 8.728813559322034e-06, + "loss": 0.3683, + "step": 20748 + }, + { + "epoch": 1.69, + "learning_rate": 8.728270317253368e-06, + "loss": 0.3937, + "step": 20749 + }, + { + "epoch": 1.69, + "learning_rate": 8.727727075184703e-06, + "loss": 0.2308, + "step": 20750 + }, + { + "epoch": 1.69, + "eval_accuracy": 0.8396332144676516, + "eval_loss": 0.42785346508026123, + "eval_runtime": 22.2517, + "eval_samples_per_second": 441.089, + "eval_steps_per_second": 3.46, + "step": 20750 + }, + { + "epoch": 1.69, + "learning_rate": 8.727183833116037e-06, + "loss": 0.3882, + "step": 20751 + }, + { + "epoch": 1.69, + "learning_rate": 8.726640591047371e-06, + "loss": 0.1377, + "step": 20752 + }, + { + "epoch": 1.69, + "learning_rate": 8.726097348978705e-06, + "loss": 0.413, + "step": 20753 + }, + { + "epoch": 1.69, + "learning_rate": 8.72555410691004e-06, + "loss": 0.332, + "step": 20754 + }, + { + "epoch": 1.69, + "learning_rate": 8.725010864841374e-06, + "loss": 0.4607, + "step": 20755 + }, + { + "epoch": 1.69, + "learning_rate": 8.724467622772708e-06, + "loss": 0.3618, + "step": 20756 + }, + { + "epoch": 1.69, + "learning_rate": 8.723924380704042e-06, + "loss": 0.2538, + "step": 20757 + }, + { + "epoch": 1.69, + "learning_rate": 8.723381138635377e-06, + "loss": 0.1843, + "step": 20758 + }, + { + "epoch": 1.69, + "learning_rate": 8.72283789656671e-06, + "loss": 0.3114, + "step": 20759 + }, + { + "epoch": 1.69, + "learning_rate": 8.722294654498045e-06, + "loss": 0.6578, + "step": 20760 + }, + { + "epoch": 1.69, + "learning_rate": 8.72175141242938e-06, + "loss": 0.2949, + "step": 20761 + }, + { + "epoch": 1.69, + "learning_rate": 8.721208170360713e-06, + "loss": 0.3928, + "step": 20762 + }, + { + "epoch": 1.69, + "learning_rate": 8.720664928292048e-06, + "loss": 0.4446, + "step": 20763 + }, + { + "epoch": 1.69, + "learning_rate": 8.720121686223382e-06, + "loss": 0.5262, + "step": 20764 + }, + { + "epoch": 1.69, + "learning_rate": 8.719578444154716e-06, + "loss": 0.2574, + "step": 20765 + }, + { + "epoch": 1.69, + "learning_rate": 8.71903520208605e-06, + "loss": 0.3512, + "step": 20766 + }, + { + "epoch": 1.69, + "learning_rate": 8.718491960017385e-06, + "loss": 0.2753, + "step": 20767 + }, + { + "epoch": 1.69, + "learning_rate": 8.717948717948719e-06, + "loss": 0.3172, + "step": 20768 + }, + { + "epoch": 1.69, + "learning_rate": 8.717405475880053e-06, + "loss": 0.3435, + "step": 20769 + }, + { + "epoch": 1.69, + "learning_rate": 8.716862233811387e-06, + "loss": 0.2671, + "step": 20770 + }, + { + "epoch": 1.69, + "learning_rate": 8.716318991742722e-06, + "loss": 0.4588, + "step": 20771 + }, + { + "epoch": 1.69, + "learning_rate": 8.715775749674056e-06, + "loss": 0.5411, + "step": 20772 + }, + { + "epoch": 1.69, + "learning_rate": 8.71523250760539e-06, + "loss": 0.3151, + "step": 20773 + }, + { + "epoch": 1.69, + "learning_rate": 8.714689265536724e-06, + "loss": 0.1853, + "step": 20774 + }, + { + "epoch": 1.69, + "learning_rate": 8.714146023468058e-06, + "loss": 0.1386, + "step": 20775 + }, + { + "epoch": 1.69, + "learning_rate": 8.713602781399391e-06, + "loss": 0.3534, + "step": 20776 + }, + { + "epoch": 1.69, + "learning_rate": 8.713059539330725e-06, + "loss": 0.2416, + "step": 20777 + }, + { + "epoch": 1.69, + "learning_rate": 8.71251629726206e-06, + "loss": 0.3436, + "step": 20778 + }, + { + "epoch": 1.69, + "learning_rate": 8.711973055193395e-06, + "loss": 0.5184, + "step": 20779 + }, + { + "epoch": 1.69, + "learning_rate": 8.71142981312473e-06, + "loss": 0.2543, + "step": 20780 + }, + { + "epoch": 1.69, + "learning_rate": 8.710886571056064e-06, + "loss": 0.3362, + "step": 20781 + }, + { + "epoch": 1.69, + "learning_rate": 8.710343328987398e-06, + "loss": 0.2205, + "step": 20782 + }, + { + "epoch": 1.69, + "learning_rate": 8.709800086918732e-06, + "loss": 0.3608, + "step": 20783 + }, + { + "epoch": 1.69, + "learning_rate": 8.709256844850067e-06, + "loss": 0.1548, + "step": 20784 + }, + { + "epoch": 1.69, + "learning_rate": 8.7087136027814e-06, + "loss": 0.2678, + "step": 20785 + }, + { + "epoch": 1.69, + "learning_rate": 8.708170360712735e-06, + "loss": 0.4686, + "step": 20786 + }, + { + "epoch": 1.69, + "learning_rate": 8.70762711864407e-06, + "loss": 0.4114, + "step": 20787 + }, + { + "epoch": 1.69, + "learning_rate": 8.707083876575403e-06, + "loss": 0.3265, + "step": 20788 + }, + { + "epoch": 1.69, + "learning_rate": 8.706540634506738e-06, + "loss": 0.2912, + "step": 20789 + }, + { + "epoch": 1.69, + "learning_rate": 8.705997392438072e-06, + "loss": 0.2487, + "step": 20790 + }, + { + "epoch": 1.69, + "learning_rate": 8.705454150369406e-06, + "loss": 0.3326, + "step": 20791 + }, + { + "epoch": 1.69, + "learning_rate": 8.70491090830074e-06, + "loss": 0.1995, + "step": 20792 + }, + { + "epoch": 1.69, + "learning_rate": 8.704367666232075e-06, + "loss": 0.1756, + "step": 20793 + }, + { + "epoch": 1.69, + "learning_rate": 8.703824424163409e-06, + "loss": 0.1913, + "step": 20794 + }, + { + "epoch": 1.69, + "learning_rate": 8.703281182094741e-06, + "loss": 0.2785, + "step": 20795 + }, + { + "epoch": 1.69, + "learning_rate": 8.702737940026076e-06, + "loss": 0.3668, + "step": 20796 + }, + { + "epoch": 1.69, + "learning_rate": 8.70219469795741e-06, + "loss": 0.4714, + "step": 20797 + }, + { + "epoch": 1.69, + "learning_rate": 8.701651455888744e-06, + "loss": 0.2908, + "step": 20798 + }, + { + "epoch": 1.69, + "learning_rate": 8.701108213820078e-06, + "loss": 0.3045, + "step": 20799 + }, + { + "epoch": 1.69, + "learning_rate": 8.700564971751413e-06, + "loss": 0.245, + "step": 20800 + }, + { + "epoch": 1.69, + "learning_rate": 8.700021729682747e-06, + "loss": 0.3155, + "step": 20801 + }, + { + "epoch": 1.7, + "learning_rate": 8.699478487614081e-06, + "loss": 0.1809, + "step": 20802 + }, + { + "epoch": 1.7, + "learning_rate": 8.698935245545415e-06, + "loss": 0.4927, + "step": 20803 + }, + { + "epoch": 1.7, + "learning_rate": 8.69839200347675e-06, + "loss": 0.2892, + "step": 20804 + }, + { + "epoch": 1.7, + "learning_rate": 8.697848761408084e-06, + "loss": 0.4926, + "step": 20805 + }, + { + "epoch": 1.7, + "learning_rate": 8.697305519339418e-06, + "loss": 0.1421, + "step": 20806 + }, + { + "epoch": 1.7, + "learning_rate": 8.696762277270752e-06, + "loss": 0.1341, + "step": 20807 + }, + { + "epoch": 1.7, + "learning_rate": 8.696219035202086e-06, + "loss": 0.2617, + "step": 20808 + }, + { + "epoch": 1.7, + "learning_rate": 8.69567579313342e-06, + "loss": 0.3911, + "step": 20809 + }, + { + "epoch": 1.7, + "learning_rate": 8.695132551064755e-06, + "loss": 0.6497, + "step": 20810 + }, + { + "epoch": 1.7, + "learning_rate": 8.694589308996089e-06, + "loss": 0.258, + "step": 20811 + }, + { + "epoch": 1.7, + "learning_rate": 8.694046066927423e-06, + "loss": 0.2452, + "step": 20812 + }, + { + "epoch": 1.7, + "learning_rate": 8.693502824858758e-06, + "loss": 0.5081, + "step": 20813 + }, + { + "epoch": 1.7, + "learning_rate": 8.692959582790092e-06, + "loss": 0.386, + "step": 20814 + }, + { + "epoch": 1.7, + "learning_rate": 8.692416340721426e-06, + "loss": 0.5833, + "step": 20815 + }, + { + "epoch": 1.7, + "learning_rate": 8.69187309865276e-06, + "loss": 0.5552, + "step": 20816 + }, + { + "epoch": 1.7, + "learning_rate": 8.691329856584094e-06, + "loss": 0.4065, + "step": 20817 + }, + { + "epoch": 1.7, + "learning_rate": 8.690786614515429e-06, + "loss": 0.1122, + "step": 20818 + }, + { + "epoch": 1.7, + "learning_rate": 8.690243372446763e-06, + "loss": 0.3732, + "step": 20819 + }, + { + "epoch": 1.7, + "learning_rate": 8.689700130378097e-06, + "loss": 0.432, + "step": 20820 + }, + { + "epoch": 1.7, + "learning_rate": 8.689156888309431e-06, + "loss": 0.2715, + "step": 20821 + }, + { + "epoch": 1.7, + "learning_rate": 8.688613646240766e-06, + "loss": 0.1284, + "step": 20822 + }, + { + "epoch": 1.7, + "learning_rate": 8.6880704041721e-06, + "loss": 0.3369, + "step": 20823 + }, + { + "epoch": 1.7, + "learning_rate": 8.687527162103434e-06, + "loss": 0.2925, + "step": 20824 + }, + { + "epoch": 1.7, + "learning_rate": 8.686983920034768e-06, + "loss": 0.2638, + "step": 20825 + }, + { + "epoch": 1.7, + "learning_rate": 8.686440677966103e-06, + "loss": 0.4224, + "step": 20826 + }, + { + "epoch": 1.7, + "learning_rate": 8.685897435897437e-06, + "loss": 0.2794, + "step": 20827 + }, + { + "epoch": 1.7, + "learning_rate": 8.685354193828771e-06, + "loss": 0.1931, + "step": 20828 + }, + { + "epoch": 1.7, + "learning_rate": 8.684810951760105e-06, + "loss": 0.3071, + "step": 20829 + }, + { + "epoch": 1.7, + "learning_rate": 8.68426770969144e-06, + "loss": 0.2536, + "step": 20830 + }, + { + "epoch": 1.7, + "learning_rate": 8.683724467622774e-06, + "loss": 0.4022, + "step": 20831 + }, + { + "epoch": 1.7, + "learning_rate": 8.683181225554108e-06, + "loss": 0.2622, + "step": 20832 + }, + { + "epoch": 1.7, + "learning_rate": 8.682637983485442e-06, + "loss": 0.4574, + "step": 20833 + }, + { + "epoch": 1.7, + "learning_rate": 8.682094741416776e-06, + "loss": 0.357, + "step": 20834 + }, + { + "epoch": 1.7, + "learning_rate": 8.68155149934811e-06, + "loss": 0.1903, + "step": 20835 + }, + { + "epoch": 1.7, + "learning_rate": 8.681008257279445e-06, + "loss": 0.2681, + "step": 20836 + }, + { + "epoch": 1.7, + "learning_rate": 8.680465015210779e-06, + "loss": 0.6761, + "step": 20837 + }, + { + "epoch": 1.7, + "learning_rate": 8.679921773142113e-06, + "loss": 0.3397, + "step": 20838 + }, + { + "epoch": 1.7, + "learning_rate": 8.679378531073448e-06, + "loss": 0.2309, + "step": 20839 + }, + { + "epoch": 1.7, + "learning_rate": 8.678835289004782e-06, + "loss": 0.4195, + "step": 20840 + }, + { + "epoch": 1.7, + "learning_rate": 8.678292046936116e-06, + "loss": 0.2464, + "step": 20841 + }, + { + "epoch": 1.7, + "learning_rate": 8.67774880486745e-06, + "loss": 0.2772, + "step": 20842 + }, + { + "epoch": 1.7, + "learning_rate": 8.677205562798784e-06, + "loss": 0.201, + "step": 20843 + }, + { + "epoch": 1.7, + "learning_rate": 8.676662320730119e-06, + "loss": 0.2992, + "step": 20844 + }, + { + "epoch": 1.7, + "learning_rate": 8.676119078661453e-06, + "loss": 0.2835, + "step": 20845 + }, + { + "epoch": 1.7, + "learning_rate": 8.675575836592787e-06, + "loss": 0.6907, + "step": 20846 + }, + { + "epoch": 1.7, + "learning_rate": 8.675032594524121e-06, + "loss": 0.4684, + "step": 20847 + }, + { + "epoch": 1.7, + "learning_rate": 8.674489352455456e-06, + "loss": 0.3145, + "step": 20848 + }, + { + "epoch": 1.7, + "learning_rate": 8.67394611038679e-06, + "loss": 0.7793, + "step": 20849 + }, + { + "epoch": 1.7, + "learning_rate": 8.673402868318124e-06, + "loss": 0.509, + "step": 20850 + }, + { + "epoch": 1.7, + "learning_rate": 8.672859626249458e-06, + "loss": 0.4399, + "step": 20851 + }, + { + "epoch": 1.7, + "learning_rate": 8.67231638418079e-06, + "loss": 0.4169, + "step": 20852 + }, + { + "epoch": 1.7, + "learning_rate": 8.671773142112125e-06, + "loss": 0.1488, + "step": 20853 + }, + { + "epoch": 1.7, + "learning_rate": 8.67122990004346e-06, + "loss": 0.5013, + "step": 20854 + }, + { + "epoch": 1.7, + "learning_rate": 8.670686657974794e-06, + "loss": 0.1875, + "step": 20855 + }, + { + "epoch": 1.7, + "learning_rate": 8.670143415906128e-06, + "loss": 0.2605, + "step": 20856 + }, + { + "epoch": 1.7, + "learning_rate": 8.669600173837462e-06, + "loss": 0.4678, + "step": 20857 + }, + { + "epoch": 1.7, + "learning_rate": 8.669056931768796e-06, + "loss": 0.5627, + "step": 20858 + }, + { + "epoch": 1.7, + "learning_rate": 8.66851368970013e-06, + "loss": 0.2872, + "step": 20859 + }, + { + "epoch": 1.7, + "learning_rate": 8.667970447631465e-06, + "loss": 0.4345, + "step": 20860 + }, + { + "epoch": 1.7, + "learning_rate": 8.667427205562799e-06, + "loss": 0.1017, + "step": 20861 + }, + { + "epoch": 1.7, + "learning_rate": 8.666883963494133e-06, + "loss": 0.1677, + "step": 20862 + }, + { + "epoch": 1.7, + "learning_rate": 8.666340721425467e-06, + "loss": 0.4439, + "step": 20863 + }, + { + "epoch": 1.7, + "learning_rate": 8.665797479356802e-06, + "loss": 0.4994, + "step": 20864 + }, + { + "epoch": 1.7, + "learning_rate": 8.665254237288136e-06, + "loss": 0.3125, + "step": 20865 + }, + { + "epoch": 1.7, + "learning_rate": 8.66471099521947e-06, + "loss": 0.2116, + "step": 20866 + }, + { + "epoch": 1.7, + "learning_rate": 8.664167753150804e-06, + "loss": 0.2617, + "step": 20867 + }, + { + "epoch": 1.7, + "learning_rate": 8.663624511082139e-06, + "loss": 0.2732, + "step": 20868 + }, + { + "epoch": 1.7, + "learning_rate": 8.663081269013473e-06, + "loss": 0.2563, + "step": 20869 + }, + { + "epoch": 1.7, + "learning_rate": 8.662538026944809e-06, + "loss": 0.3528, + "step": 20870 + }, + { + "epoch": 1.7, + "learning_rate": 8.661994784876141e-06, + "loss": 0.4296, + "step": 20871 + }, + { + "epoch": 1.7, + "learning_rate": 8.661451542807475e-06, + "loss": 0.1474, + "step": 20872 + }, + { + "epoch": 1.7, + "learning_rate": 8.66090830073881e-06, + "loss": 0.3187, + "step": 20873 + }, + { + "epoch": 1.7, + "learning_rate": 8.660365058670144e-06, + "loss": 0.0768, + "step": 20874 + }, + { + "epoch": 1.7, + "learning_rate": 8.659821816601478e-06, + "loss": 0.2442, + "step": 20875 + }, + { + "epoch": 1.7, + "learning_rate": 8.659278574532812e-06, + "loss": 0.2873, + "step": 20876 + }, + { + "epoch": 1.7, + "learning_rate": 8.658735332464147e-06, + "loss": 0.1803, + "step": 20877 + }, + { + "epoch": 1.7, + "learning_rate": 8.65819209039548e-06, + "loss": 0.5048, + "step": 20878 + }, + { + "epoch": 1.7, + "learning_rate": 8.657648848326815e-06, + "loss": 0.4734, + "step": 20879 + }, + { + "epoch": 1.7, + "learning_rate": 8.65710560625815e-06, + "loss": 0.291, + "step": 20880 + }, + { + "epoch": 1.7, + "learning_rate": 8.656562364189483e-06, + "loss": 0.1859, + "step": 20881 + }, + { + "epoch": 1.7, + "learning_rate": 8.656019122120818e-06, + "loss": 0.4318, + "step": 20882 + }, + { + "epoch": 1.7, + "learning_rate": 8.655475880052152e-06, + "loss": 0.2279, + "step": 20883 + }, + { + "epoch": 1.7, + "learning_rate": 8.654932637983486e-06, + "loss": 0.1149, + "step": 20884 + }, + { + "epoch": 1.7, + "learning_rate": 8.65438939591482e-06, + "loss": 0.5055, + "step": 20885 + }, + { + "epoch": 1.7, + "learning_rate": 8.653846153846155e-06, + "loss": 0.2723, + "step": 20886 + }, + { + "epoch": 1.7, + "learning_rate": 8.653302911777489e-06, + "loss": 0.1435, + "step": 20887 + }, + { + "epoch": 1.7, + "learning_rate": 8.652759669708823e-06, + "loss": 0.4871, + "step": 20888 + }, + { + "epoch": 1.7, + "learning_rate": 8.652216427640157e-06, + "loss": 0.2775, + "step": 20889 + }, + { + "epoch": 1.7, + "learning_rate": 8.651673185571492e-06, + "loss": 0.2208, + "step": 20890 + }, + { + "epoch": 1.7, + "learning_rate": 8.651129943502826e-06, + "loss": 0.1687, + "step": 20891 + }, + { + "epoch": 1.7, + "learning_rate": 8.65058670143416e-06, + "loss": 0.3814, + "step": 20892 + }, + { + "epoch": 1.7, + "learning_rate": 8.650043459365494e-06, + "loss": 0.2391, + "step": 20893 + }, + { + "epoch": 1.7, + "learning_rate": 8.649500217296828e-06, + "loss": 0.3831, + "step": 20894 + }, + { + "epoch": 1.7, + "learning_rate": 8.648956975228163e-06, + "loss": 0.3593, + "step": 20895 + }, + { + "epoch": 1.7, + "learning_rate": 8.648413733159497e-06, + "loss": 0.1457, + "step": 20896 + }, + { + "epoch": 1.7, + "learning_rate": 8.647870491090831e-06, + "loss": 0.235, + "step": 20897 + }, + { + "epoch": 1.7, + "learning_rate": 8.647327249022165e-06, + "loss": 0.4084, + "step": 20898 + }, + { + "epoch": 1.7, + "learning_rate": 8.6467840069535e-06, + "loss": 0.2617, + "step": 20899 + }, + { + "epoch": 1.7, + "learning_rate": 8.646240764884834e-06, + "loss": 0.1795, + "step": 20900 + }, + { + "epoch": 1.7, + "learning_rate": 8.645697522816168e-06, + "loss": 0.2184, + "step": 20901 + }, + { + "epoch": 1.7, + "learning_rate": 8.645154280747502e-06, + "loss": 0.2407, + "step": 20902 + }, + { + "epoch": 1.7, + "learning_rate": 8.644611038678837e-06, + "loss": 0.5653, + "step": 20903 + }, + { + "epoch": 1.7, + "learning_rate": 8.64406779661017e-06, + "loss": 0.1707, + "step": 20904 + }, + { + "epoch": 1.7, + "learning_rate": 8.643524554541505e-06, + "loss": 0.3293, + "step": 20905 + }, + { + "epoch": 1.7, + "learning_rate": 8.64298131247284e-06, + "loss": 0.299, + "step": 20906 + }, + { + "epoch": 1.7, + "learning_rate": 8.642438070404173e-06, + "loss": 0.2248, + "step": 20907 + }, + { + "epoch": 1.7, + "learning_rate": 8.641894828335508e-06, + "loss": 0.1707, + "step": 20908 + }, + { + "epoch": 1.7, + "learning_rate": 8.64135158626684e-06, + "loss": 0.1208, + "step": 20909 + }, + { + "epoch": 1.7, + "learning_rate": 8.640808344198174e-06, + "loss": 0.4055, + "step": 20910 + }, + { + "epoch": 1.7, + "learning_rate": 8.640265102129509e-06, + "loss": 0.1759, + "step": 20911 + }, + { + "epoch": 1.7, + "learning_rate": 8.639721860060843e-06, + "loss": 0.4553, + "step": 20912 + }, + { + "epoch": 1.7, + "learning_rate": 8.639178617992177e-06, + "loss": 0.1933, + "step": 20913 + }, + { + "epoch": 1.7, + "learning_rate": 8.638635375923511e-06, + "loss": 0.3527, + "step": 20914 + }, + { + "epoch": 1.7, + "learning_rate": 8.638092133854846e-06, + "loss": 0.5634, + "step": 20915 + }, + { + "epoch": 1.7, + "learning_rate": 8.63754889178618e-06, + "loss": 0.2162, + "step": 20916 + }, + { + "epoch": 1.7, + "learning_rate": 8.637005649717514e-06, + "loss": 0.3919, + "step": 20917 + }, + { + "epoch": 1.7, + "learning_rate": 8.636462407648848e-06, + "loss": 0.1991, + "step": 20918 + }, + { + "epoch": 1.7, + "learning_rate": 8.635919165580183e-06, + "loss": 0.428, + "step": 20919 + }, + { + "epoch": 1.7, + "learning_rate": 8.635375923511517e-06, + "loss": 0.312, + "step": 20920 + }, + { + "epoch": 1.7, + "learning_rate": 8.634832681442851e-06, + "loss": 0.2668, + "step": 20921 + }, + { + "epoch": 1.7, + "learning_rate": 8.634289439374185e-06, + "loss": 0.2547, + "step": 20922 + }, + { + "epoch": 1.7, + "learning_rate": 8.63374619730552e-06, + "loss": 0.4853, + "step": 20923 + }, + { + "epoch": 1.71, + "learning_rate": 8.633202955236855e-06, + "loss": 0.6154, + "step": 20924 + }, + { + "epoch": 1.71, + "learning_rate": 8.63265971316819e-06, + "loss": 0.36, + "step": 20925 + }, + { + "epoch": 1.71, + "learning_rate": 8.632116471099524e-06, + "loss": 0.398, + "step": 20926 + }, + { + "epoch": 1.71, + "learning_rate": 8.631573229030858e-06, + "loss": 0.1109, + "step": 20927 + }, + { + "epoch": 1.71, + "learning_rate": 8.63102998696219e-06, + "loss": 0.473, + "step": 20928 + }, + { + "epoch": 1.71, + "learning_rate": 8.630486744893525e-06, + "loss": 0.2716, + "step": 20929 + }, + { + "epoch": 1.71, + "learning_rate": 8.629943502824859e-06, + "loss": 0.209, + "step": 20930 + }, + { + "epoch": 1.71, + "learning_rate": 8.629400260756193e-06, + "loss": 0.4825, + "step": 20931 + }, + { + "epoch": 1.71, + "learning_rate": 8.628857018687528e-06, + "loss": 0.1104, + "step": 20932 + }, + { + "epoch": 1.71, + "learning_rate": 8.628313776618862e-06, + "loss": 0.6348, + "step": 20933 + }, + { + "epoch": 1.71, + "learning_rate": 8.627770534550196e-06, + "loss": 0.3583, + "step": 20934 + }, + { + "epoch": 1.71, + "learning_rate": 8.62722729248153e-06, + "loss": 0.4115, + "step": 20935 + }, + { + "epoch": 1.71, + "learning_rate": 8.626684050412864e-06, + "loss": 0.597, + "step": 20936 + }, + { + "epoch": 1.71, + "learning_rate": 8.626140808344199e-06, + "loss": 0.6684, + "step": 20937 + }, + { + "epoch": 1.71, + "learning_rate": 8.625597566275533e-06, + "loss": 0.2846, + "step": 20938 + }, + { + "epoch": 1.71, + "learning_rate": 8.625054324206867e-06, + "loss": 0.2071, + "step": 20939 + }, + { + "epoch": 1.71, + "learning_rate": 8.624511082138201e-06, + "loss": 0.2711, + "step": 20940 + }, + { + "epoch": 1.71, + "learning_rate": 8.623967840069536e-06, + "loss": 0.283, + "step": 20941 + }, + { + "epoch": 1.71, + "learning_rate": 8.62342459800087e-06, + "loss": 0.1914, + "step": 20942 + }, + { + "epoch": 1.71, + "learning_rate": 8.622881355932204e-06, + "loss": 0.5829, + "step": 20943 + }, + { + "epoch": 1.71, + "learning_rate": 8.622338113863538e-06, + "loss": 0.5508, + "step": 20944 + }, + { + "epoch": 1.71, + "learning_rate": 8.621794871794873e-06, + "loss": 0.1631, + "step": 20945 + }, + { + "epoch": 1.71, + "learning_rate": 8.621251629726207e-06, + "loss": 0.2748, + "step": 20946 + }, + { + "epoch": 1.71, + "learning_rate": 8.620708387657541e-06, + "loss": 0.3905, + "step": 20947 + }, + { + "epoch": 1.71, + "learning_rate": 8.620165145588875e-06, + "loss": 0.1053, + "step": 20948 + }, + { + "epoch": 1.71, + "learning_rate": 8.61962190352021e-06, + "loss": 0.2065, + "step": 20949 + }, + { + "epoch": 1.71, + "learning_rate": 8.619078661451544e-06, + "loss": 0.1952, + "step": 20950 + }, + { + "epoch": 1.71, + "learning_rate": 8.618535419382878e-06, + "loss": 0.111, + "step": 20951 + }, + { + "epoch": 1.71, + "learning_rate": 8.617992177314212e-06, + "loss": 0.2777, + "step": 20952 + }, + { + "epoch": 1.71, + "learning_rate": 8.617448935245546e-06, + "loss": 0.4892, + "step": 20953 + }, + { + "epoch": 1.71, + "learning_rate": 8.61690569317688e-06, + "loss": 0.2038, + "step": 20954 + }, + { + "epoch": 1.71, + "learning_rate": 8.616362451108215e-06, + "loss": 0.4162, + "step": 20955 + }, + { + "epoch": 1.71, + "learning_rate": 8.615819209039549e-06, + "loss": 0.3391, + "step": 20956 + }, + { + "epoch": 1.71, + "learning_rate": 8.615275966970883e-06, + "loss": 0.2553, + "step": 20957 + }, + { + "epoch": 1.71, + "learning_rate": 8.614732724902218e-06, + "loss": 0.3005, + "step": 20958 + }, + { + "epoch": 1.71, + "learning_rate": 8.614189482833552e-06, + "loss": 0.7081, + "step": 20959 + }, + { + "epoch": 1.71, + "learning_rate": 8.613646240764886e-06, + "loss": 0.2752, + "step": 20960 + }, + { + "epoch": 1.71, + "learning_rate": 8.61310299869622e-06, + "loss": 0.4137, + "step": 20961 + }, + { + "epoch": 1.71, + "learning_rate": 8.612559756627554e-06, + "loss": 0.5727, + "step": 20962 + }, + { + "epoch": 1.71, + "learning_rate": 8.612016514558889e-06, + "loss": 0.3864, + "step": 20963 + }, + { + "epoch": 1.71, + "learning_rate": 8.611473272490223e-06, + "loss": 0.4372, + "step": 20964 + }, + { + "epoch": 1.71, + "learning_rate": 8.610930030421557e-06, + "loss": 0.3594, + "step": 20965 + }, + { + "epoch": 1.71, + "learning_rate": 8.61038678835289e-06, + "loss": 0.1378, + "step": 20966 + }, + { + "epoch": 1.71, + "learning_rate": 8.609843546284224e-06, + "loss": 0.2252, + "step": 20967 + }, + { + "epoch": 1.71, + "learning_rate": 8.609300304215558e-06, + "loss": 0.1967, + "step": 20968 + }, + { + "epoch": 1.71, + "learning_rate": 8.608757062146892e-06, + "loss": 0.2268, + "step": 20969 + }, + { + "epoch": 1.71, + "learning_rate": 8.608213820078227e-06, + "loss": 0.3638, + "step": 20970 + }, + { + "epoch": 1.71, + "learning_rate": 8.607670578009561e-06, + "loss": 0.4048, + "step": 20971 + }, + { + "epoch": 1.71, + "learning_rate": 8.607127335940895e-06, + "loss": 0.3761, + "step": 20972 + }, + { + "epoch": 1.71, + "learning_rate": 8.60658409387223e-06, + "loss": 0.3237, + "step": 20973 + }, + { + "epoch": 1.71, + "learning_rate": 8.606040851803564e-06, + "loss": 0.3283, + "step": 20974 + }, + { + "epoch": 1.71, + "learning_rate": 8.605497609734898e-06, + "loss": 0.6236, + "step": 20975 + }, + { + "epoch": 1.71, + "learning_rate": 8.604954367666232e-06, + "loss": 0.2638, + "step": 20976 + }, + { + "epoch": 1.71, + "learning_rate": 8.604411125597566e-06, + "loss": 0.8282, + "step": 20977 + }, + { + "epoch": 1.71, + "learning_rate": 8.603867883528902e-06, + "loss": 0.2595, + "step": 20978 + }, + { + "epoch": 1.71, + "learning_rate": 8.603324641460236e-06, + "loss": 0.46, + "step": 20979 + }, + { + "epoch": 1.71, + "learning_rate": 8.60278139939157e-06, + "loss": 0.3884, + "step": 20980 + }, + { + "epoch": 1.71, + "learning_rate": 8.602238157322905e-06, + "loss": 0.4414, + "step": 20981 + }, + { + "epoch": 1.71, + "learning_rate": 8.601694915254239e-06, + "loss": 0.7486, + "step": 20982 + }, + { + "epoch": 1.71, + "learning_rate": 8.601151673185573e-06, + "loss": 0.2485, + "step": 20983 + }, + { + "epoch": 1.71, + "learning_rate": 8.600608431116908e-06, + "loss": 0.1733, + "step": 20984 + }, + { + "epoch": 1.71, + "learning_rate": 8.60006518904824e-06, + "loss": 0.443, + "step": 20985 + }, + { + "epoch": 1.71, + "learning_rate": 8.599521946979574e-06, + "loss": 0.4626, + "step": 20986 + }, + { + "epoch": 1.71, + "learning_rate": 8.598978704910909e-06, + "loss": 0.4342, + "step": 20987 + }, + { + "epoch": 1.71, + "learning_rate": 8.598435462842243e-06, + "loss": 0.163, + "step": 20988 + }, + { + "epoch": 1.71, + "learning_rate": 8.597892220773577e-06, + "loss": 0.3243, + "step": 20989 + }, + { + "epoch": 1.71, + "learning_rate": 8.597348978704911e-06, + "loss": 0.2193, + "step": 20990 + }, + { + "epoch": 1.71, + "learning_rate": 8.596805736636245e-06, + "loss": 0.3289, + "step": 20991 + }, + { + "epoch": 1.71, + "learning_rate": 8.59626249456758e-06, + "loss": 0.2959, + "step": 20992 + }, + { + "epoch": 1.71, + "learning_rate": 8.595719252498914e-06, + "loss": 0.3875, + "step": 20993 + }, + { + "epoch": 1.71, + "learning_rate": 8.595176010430248e-06, + "loss": 0.602, + "step": 20994 + }, + { + "epoch": 1.71, + "learning_rate": 8.594632768361582e-06, + "loss": 0.1868, + "step": 20995 + }, + { + "epoch": 1.71, + "learning_rate": 8.594089526292917e-06, + "loss": 0.6505, + "step": 20996 + }, + { + "epoch": 1.71, + "learning_rate": 8.593546284224251e-06, + "loss": 0.2079, + "step": 20997 + }, + { + "epoch": 1.71, + "learning_rate": 8.593003042155585e-06, + "loss": 0.3502, + "step": 20998 + }, + { + "epoch": 1.71, + "learning_rate": 8.59245980008692e-06, + "loss": 0.7294, + "step": 20999 + }, + { + "epoch": 1.71, + "learning_rate": 8.591916558018254e-06, + "loss": 0.4309, + "step": 21000 + }, + { + "epoch": 1.71, + "eval_accuracy": 0.83841059602649, + "eval_loss": 0.440553218126297, + "eval_runtime": 22.2231, + "eval_samples_per_second": 441.658, + "eval_steps_per_second": 3.465, + "step": 21000 + }, + { + "epoch": 1.71, + "learning_rate": 8.591373315949588e-06, + "loss": 0.2715, + "step": 21001 + }, + { + "epoch": 1.71, + "learning_rate": 8.590830073880922e-06, + "loss": 0.3068, + "step": 21002 + }, + { + "epoch": 1.71, + "learning_rate": 8.590286831812256e-06, + "loss": 0.1798, + "step": 21003 + }, + { + "epoch": 1.71, + "learning_rate": 8.58974358974359e-06, + "loss": 0.2333, + "step": 21004 + }, + { + "epoch": 1.71, + "learning_rate": 8.589200347674925e-06, + "loss": 0.1817, + "step": 21005 + }, + { + "epoch": 1.71, + "learning_rate": 8.588657105606259e-06, + "loss": 0.1655, + "step": 21006 + }, + { + "epoch": 1.71, + "learning_rate": 8.588113863537593e-06, + "loss": 0.3564, + "step": 21007 + }, + { + "epoch": 1.71, + "learning_rate": 8.587570621468927e-06, + "loss": 0.1033, + "step": 21008 + }, + { + "epoch": 1.71, + "learning_rate": 8.587027379400262e-06, + "loss": 0.2495, + "step": 21009 + }, + { + "epoch": 1.71, + "learning_rate": 8.586484137331596e-06, + "loss": 0.2165, + "step": 21010 + }, + { + "epoch": 1.71, + "learning_rate": 8.58594089526293e-06, + "loss": 0.4538, + "step": 21011 + }, + { + "epoch": 1.71, + "learning_rate": 8.585397653194264e-06, + "loss": 0.2954, + "step": 21012 + }, + { + "epoch": 1.71, + "learning_rate": 8.584854411125599e-06, + "loss": 0.2189, + "step": 21013 + }, + { + "epoch": 1.71, + "learning_rate": 8.584311169056933e-06, + "loss": 0.213, + "step": 21014 + }, + { + "epoch": 1.71, + "learning_rate": 8.583767926988267e-06, + "loss": 0.5178, + "step": 21015 + }, + { + "epoch": 1.71, + "learning_rate": 8.583224684919601e-06, + "loss": 0.4509, + "step": 21016 + }, + { + "epoch": 1.71, + "learning_rate": 8.582681442850935e-06, + "loss": 0.3367, + "step": 21017 + }, + { + "epoch": 1.71, + "learning_rate": 8.58213820078227e-06, + "loss": 0.1913, + "step": 21018 + }, + { + "epoch": 1.71, + "learning_rate": 8.581594958713604e-06, + "loss": 0.1089, + "step": 21019 + }, + { + "epoch": 1.71, + "learning_rate": 8.581051716644938e-06, + "loss": 0.3621, + "step": 21020 + }, + { + "epoch": 1.71, + "learning_rate": 8.580508474576272e-06, + "loss": 0.2861, + "step": 21021 + }, + { + "epoch": 1.71, + "learning_rate": 8.579965232507607e-06, + "loss": 0.3763, + "step": 21022 + }, + { + "epoch": 1.71, + "learning_rate": 8.57942199043894e-06, + "loss": 0.2935, + "step": 21023 + }, + { + "epoch": 1.71, + "learning_rate": 8.578878748370273e-06, + "loss": 0.657, + "step": 21024 + }, + { + "epoch": 1.71, + "learning_rate": 8.578335506301608e-06, + "loss": 0.6031, + "step": 21025 + }, + { + "epoch": 1.71, + "learning_rate": 8.577792264232942e-06, + "loss": 0.2139, + "step": 21026 + }, + { + "epoch": 1.71, + "learning_rate": 8.577249022164276e-06, + "loss": 0.2088, + "step": 21027 + }, + { + "epoch": 1.71, + "learning_rate": 8.57670578009561e-06, + "loss": 0.2171, + "step": 21028 + }, + { + "epoch": 1.71, + "learning_rate": 8.576162538026945e-06, + "loss": 0.2779, + "step": 21029 + }, + { + "epoch": 1.71, + "learning_rate": 8.575619295958279e-06, + "loss": 0.4364, + "step": 21030 + }, + { + "epoch": 1.71, + "learning_rate": 8.575076053889613e-06, + "loss": 0.0525, + "step": 21031 + }, + { + "epoch": 1.71, + "learning_rate": 8.574532811820949e-06, + "loss": 0.6415, + "step": 21032 + }, + { + "epoch": 1.71, + "learning_rate": 8.573989569752283e-06, + "loss": 0.2014, + "step": 21033 + }, + { + "epoch": 1.71, + "learning_rate": 8.573446327683617e-06, + "loss": 0.3935, + "step": 21034 + }, + { + "epoch": 1.71, + "learning_rate": 8.572903085614952e-06, + "loss": 0.4672, + "step": 21035 + }, + { + "epoch": 1.71, + "learning_rate": 8.572359843546286e-06, + "loss": 0.2436, + "step": 21036 + }, + { + "epoch": 1.71, + "learning_rate": 8.57181660147762e-06, + "loss": 0.4869, + "step": 21037 + }, + { + "epoch": 1.71, + "learning_rate": 8.571273359408954e-06, + "loss": 0.2799, + "step": 21038 + }, + { + "epoch": 1.71, + "learning_rate": 8.570730117340289e-06, + "loss": 0.3527, + "step": 21039 + }, + { + "epoch": 1.71, + "learning_rate": 8.570186875271623e-06, + "loss": 0.1857, + "step": 21040 + }, + { + "epoch": 1.71, + "learning_rate": 8.569643633202957e-06, + "loss": 0.4105, + "step": 21041 + }, + { + "epoch": 1.71, + "learning_rate": 8.56910039113429e-06, + "loss": 0.2253, + "step": 21042 + }, + { + "epoch": 1.71, + "learning_rate": 8.568557149065624e-06, + "loss": 0.189, + "step": 21043 + }, + { + "epoch": 1.71, + "learning_rate": 8.568013906996958e-06, + "loss": 0.8661, + "step": 21044 + }, + { + "epoch": 1.71, + "learning_rate": 8.567470664928292e-06, + "loss": 0.3975, + "step": 21045 + }, + { + "epoch": 1.71, + "learning_rate": 8.566927422859626e-06, + "loss": 0.1257, + "step": 21046 + }, + { + "epoch": 1.72, + "learning_rate": 8.56638418079096e-06, + "loss": 0.4822, + "step": 21047 + }, + { + "epoch": 1.72, + "learning_rate": 8.565840938722295e-06, + "loss": 0.3527, + "step": 21048 + }, + { + "epoch": 1.72, + "learning_rate": 8.565297696653629e-06, + "loss": 0.3562, + "step": 21049 + }, + { + "epoch": 1.72, + "learning_rate": 8.564754454584963e-06, + "loss": 0.3449, + "step": 21050 + }, + { + "epoch": 1.72, + "learning_rate": 8.564211212516298e-06, + "loss": 0.2624, + "step": 21051 + }, + { + "epoch": 1.72, + "learning_rate": 8.563667970447632e-06, + "loss": 0.4331, + "step": 21052 + }, + { + "epoch": 1.72, + "learning_rate": 8.563124728378966e-06, + "loss": 0.6605, + "step": 21053 + }, + { + "epoch": 1.72, + "learning_rate": 8.5625814863103e-06, + "loss": 0.3487, + "step": 21054 + }, + { + "epoch": 1.72, + "learning_rate": 8.562038244241635e-06, + "loss": 0.2805, + "step": 21055 + }, + { + "epoch": 1.72, + "learning_rate": 8.561495002172969e-06, + "loss": 0.1798, + "step": 21056 + }, + { + "epoch": 1.72, + "learning_rate": 8.560951760104303e-06, + "loss": 0.3991, + "step": 21057 + }, + { + "epoch": 1.72, + "learning_rate": 8.560408518035637e-06, + "loss": 0.2435, + "step": 21058 + }, + { + "epoch": 1.72, + "learning_rate": 8.559865275966971e-06, + "loss": 0.2718, + "step": 21059 + }, + { + "epoch": 1.72, + "learning_rate": 8.559322033898306e-06, + "loss": 0.2414, + "step": 21060 + }, + { + "epoch": 1.72, + "learning_rate": 8.55877879182964e-06, + "loss": 0.3166, + "step": 21061 + }, + { + "epoch": 1.72, + "learning_rate": 8.558235549760974e-06, + "loss": 0.3735, + "step": 21062 + }, + { + "epoch": 1.72, + "learning_rate": 8.557692307692308e-06, + "loss": 0.4057, + "step": 21063 + }, + { + "epoch": 1.72, + "learning_rate": 8.557149065623643e-06, + "loss": 0.2372, + "step": 21064 + }, + { + "epoch": 1.72, + "learning_rate": 8.556605823554977e-06, + "loss": 0.3105, + "step": 21065 + }, + { + "epoch": 1.72, + "learning_rate": 8.556062581486311e-06, + "loss": 0.3429, + "step": 21066 + }, + { + "epoch": 1.72, + "learning_rate": 8.555519339417645e-06, + "loss": 0.3698, + "step": 21067 + }, + { + "epoch": 1.72, + "learning_rate": 8.55497609734898e-06, + "loss": 0.0699, + "step": 21068 + }, + { + "epoch": 1.72, + "learning_rate": 8.554432855280314e-06, + "loss": 0.3632, + "step": 21069 + }, + { + "epoch": 1.72, + "learning_rate": 8.553889613211648e-06, + "loss": 0.3283, + "step": 21070 + }, + { + "epoch": 1.72, + "learning_rate": 8.553346371142982e-06, + "loss": 0.3201, + "step": 21071 + }, + { + "epoch": 1.72, + "learning_rate": 8.552803129074316e-06, + "loss": 0.405, + "step": 21072 + }, + { + "epoch": 1.72, + "learning_rate": 8.55225988700565e-06, + "loss": 0.2705, + "step": 21073 + }, + { + "epoch": 1.72, + "learning_rate": 8.551716644936985e-06, + "loss": 0.1481, + "step": 21074 + }, + { + "epoch": 1.72, + "learning_rate": 8.551173402868319e-06, + "loss": 0.2731, + "step": 21075 + }, + { + "epoch": 1.72, + "learning_rate": 8.550630160799653e-06, + "loss": 0.2783, + "step": 21076 + }, + { + "epoch": 1.72, + "learning_rate": 8.550086918730988e-06, + "loss": 0.3389, + "step": 21077 + }, + { + "epoch": 1.72, + "learning_rate": 8.549543676662322e-06, + "loss": 0.2259, + "step": 21078 + }, + { + "epoch": 1.72, + "learning_rate": 8.549000434593656e-06, + "loss": 0.2867, + "step": 21079 + }, + { + "epoch": 1.72, + "learning_rate": 8.548457192524989e-06, + "loss": 0.276, + "step": 21080 + }, + { + "epoch": 1.72, + "learning_rate": 8.547913950456323e-06, + "loss": 0.1086, + "step": 21081 + }, + { + "epoch": 1.72, + "learning_rate": 8.547370708387657e-06, + "loss": 0.2341, + "step": 21082 + }, + { + "epoch": 1.72, + "learning_rate": 8.546827466318991e-06, + "loss": 0.4947, + "step": 21083 + }, + { + "epoch": 1.72, + "learning_rate": 8.546284224250326e-06, + "loss": 0.2423, + "step": 21084 + }, + { + "epoch": 1.72, + "learning_rate": 8.54574098218166e-06, + "loss": 0.2446, + "step": 21085 + }, + { + "epoch": 1.72, + "learning_rate": 8.545197740112996e-06, + "loss": 0.4037, + "step": 21086 + }, + { + "epoch": 1.72, + "learning_rate": 8.54465449804433e-06, + "loss": 0.0969, + "step": 21087 + }, + { + "epoch": 1.72, + "learning_rate": 8.544111255975664e-06, + "loss": 0.739, + "step": 21088 + }, + { + "epoch": 1.72, + "learning_rate": 8.543568013906998e-06, + "loss": 0.2515, + "step": 21089 + }, + { + "epoch": 1.72, + "learning_rate": 8.543024771838333e-06, + "loss": 0.3503, + "step": 21090 + }, + { + "epoch": 1.72, + "learning_rate": 8.542481529769667e-06, + "loss": 0.1284, + "step": 21091 + }, + { + "epoch": 1.72, + "learning_rate": 8.541938287701001e-06, + "loss": 0.1913, + "step": 21092 + }, + { + "epoch": 1.72, + "learning_rate": 8.541395045632335e-06, + "loss": 0.5124, + "step": 21093 + }, + { + "epoch": 1.72, + "learning_rate": 8.54085180356367e-06, + "loss": 0.472, + "step": 21094 + }, + { + "epoch": 1.72, + "learning_rate": 8.540308561495004e-06, + "loss": 0.4981, + "step": 21095 + }, + { + "epoch": 1.72, + "learning_rate": 8.539765319426338e-06, + "loss": 0.4564, + "step": 21096 + }, + { + "epoch": 1.72, + "learning_rate": 8.539222077357672e-06, + "loss": 0.231, + "step": 21097 + }, + { + "epoch": 1.72, + "learning_rate": 8.538678835289006e-06, + "loss": 0.4189, + "step": 21098 + }, + { + "epoch": 1.72, + "learning_rate": 8.538135593220339e-06, + "loss": 0.3538, + "step": 21099 + }, + { + "epoch": 1.72, + "learning_rate": 8.537592351151673e-06, + "loss": 0.2858, + "step": 21100 + }, + { + "epoch": 1.72, + "learning_rate": 8.537049109083007e-06, + "loss": 0.4343, + "step": 21101 + }, + { + "epoch": 1.72, + "learning_rate": 8.536505867014342e-06, + "loss": 0.2748, + "step": 21102 + }, + { + "epoch": 1.72, + "learning_rate": 8.535962624945676e-06, + "loss": 0.2344, + "step": 21103 + }, + { + "epoch": 1.72, + "learning_rate": 8.53541938287701e-06, + "loss": 0.3305, + "step": 21104 + }, + { + "epoch": 1.72, + "learning_rate": 8.534876140808344e-06, + "loss": 0.4761, + "step": 21105 + }, + { + "epoch": 1.72, + "learning_rate": 8.534332898739679e-06, + "loss": 0.1215, + "step": 21106 + }, + { + "epoch": 1.72, + "learning_rate": 8.533789656671013e-06, + "loss": 0.22, + "step": 21107 + }, + { + "epoch": 1.72, + "learning_rate": 8.533246414602347e-06, + "loss": 0.1929, + "step": 21108 + }, + { + "epoch": 1.72, + "learning_rate": 8.532703172533681e-06, + "loss": 0.5334, + "step": 21109 + }, + { + "epoch": 1.72, + "learning_rate": 8.532159930465016e-06, + "loss": 0.243, + "step": 21110 + }, + { + "epoch": 1.72, + "learning_rate": 8.53161668839635e-06, + "loss": 0.3616, + "step": 21111 + }, + { + "epoch": 1.72, + "learning_rate": 8.531073446327684e-06, + "loss": 0.3778, + "step": 21112 + }, + { + "epoch": 1.72, + "learning_rate": 8.530530204259018e-06, + "loss": 0.3119, + "step": 21113 + }, + { + "epoch": 1.72, + "learning_rate": 8.529986962190352e-06, + "loss": 0.2313, + "step": 21114 + }, + { + "epoch": 1.72, + "learning_rate": 8.529443720121687e-06, + "loss": 0.5292, + "step": 21115 + }, + { + "epoch": 1.72, + "learning_rate": 8.528900478053021e-06, + "loss": 0.2511, + "step": 21116 + }, + { + "epoch": 1.72, + "learning_rate": 8.528357235984355e-06, + "loss": 0.2933, + "step": 21117 + }, + { + "epoch": 1.72, + "learning_rate": 8.52781399391569e-06, + "loss": 0.5482, + "step": 21118 + }, + { + "epoch": 1.72, + "learning_rate": 8.527270751847024e-06, + "loss": 0.3068, + "step": 21119 + }, + { + "epoch": 1.72, + "learning_rate": 8.526727509778358e-06, + "loss": 0.5295, + "step": 21120 + }, + { + "epoch": 1.72, + "learning_rate": 8.526184267709692e-06, + "loss": 0.3652, + "step": 21121 + }, + { + "epoch": 1.72, + "learning_rate": 8.525641025641026e-06, + "loss": 0.459, + "step": 21122 + }, + { + "epoch": 1.72, + "learning_rate": 8.52509778357236e-06, + "loss": 0.1585, + "step": 21123 + }, + { + "epoch": 1.72, + "learning_rate": 8.524554541503695e-06, + "loss": 0.4558, + "step": 21124 + }, + { + "epoch": 1.72, + "learning_rate": 8.524011299435029e-06, + "loss": 0.5593, + "step": 21125 + }, + { + "epoch": 1.72, + "learning_rate": 8.523468057366363e-06, + "loss": 0.2062, + "step": 21126 + }, + { + "epoch": 1.72, + "learning_rate": 8.522924815297697e-06, + "loss": 0.5129, + "step": 21127 + }, + { + "epoch": 1.72, + "learning_rate": 8.522381573229032e-06, + "loss": 0.4738, + "step": 21128 + }, + { + "epoch": 1.72, + "learning_rate": 8.521838331160366e-06, + "loss": 0.4568, + "step": 21129 + }, + { + "epoch": 1.72, + "learning_rate": 8.5212950890917e-06, + "loss": 0.4281, + "step": 21130 + }, + { + "epoch": 1.72, + "learning_rate": 8.520751847023034e-06, + "loss": 0.4246, + "step": 21131 + }, + { + "epoch": 1.72, + "learning_rate": 8.520208604954369e-06, + "loss": 0.6949, + "step": 21132 + }, + { + "epoch": 1.72, + "learning_rate": 8.519665362885703e-06, + "loss": 0.2224, + "step": 21133 + }, + { + "epoch": 1.72, + "learning_rate": 8.519122120817037e-06, + "loss": 0.1564, + "step": 21134 + }, + { + "epoch": 1.72, + "learning_rate": 8.518578878748371e-06, + "loss": 0.6703, + "step": 21135 + }, + { + "epoch": 1.72, + "learning_rate": 8.518035636679706e-06, + "loss": 0.2453, + "step": 21136 + }, + { + "epoch": 1.72, + "learning_rate": 8.517492394611038e-06, + "loss": 0.3318, + "step": 21137 + }, + { + "epoch": 1.72, + "learning_rate": 8.516949152542372e-06, + "loss": 0.3095, + "step": 21138 + }, + { + "epoch": 1.72, + "learning_rate": 8.516405910473707e-06, + "loss": 0.3164, + "step": 21139 + }, + { + "epoch": 1.72, + "learning_rate": 8.515862668405042e-06, + "loss": 0.1721, + "step": 21140 + }, + { + "epoch": 1.72, + "learning_rate": 8.515319426336377e-06, + "loss": 0.519, + "step": 21141 + }, + { + "epoch": 1.72, + "learning_rate": 8.514776184267711e-06, + "loss": 0.2708, + "step": 21142 + }, + { + "epoch": 1.72, + "learning_rate": 8.514232942199045e-06, + "loss": 0.2762, + "step": 21143 + }, + { + "epoch": 1.72, + "learning_rate": 8.51368970013038e-06, + "loss": 0.2958, + "step": 21144 + }, + { + "epoch": 1.72, + "learning_rate": 8.513146458061714e-06, + "loss": 0.23, + "step": 21145 + }, + { + "epoch": 1.72, + "learning_rate": 8.512603215993048e-06, + "loss": 0.227, + "step": 21146 + }, + { + "epoch": 1.72, + "learning_rate": 8.512059973924382e-06, + "loss": 0.2584, + "step": 21147 + }, + { + "epoch": 1.72, + "learning_rate": 8.511516731855716e-06, + "loss": 0.2267, + "step": 21148 + }, + { + "epoch": 1.72, + "learning_rate": 8.51097348978705e-06, + "loss": 0.466, + "step": 21149 + }, + { + "epoch": 1.72, + "learning_rate": 8.510430247718385e-06, + "loss": 0.4803, + "step": 21150 + }, + { + "epoch": 1.72, + "learning_rate": 8.509887005649719e-06, + "loss": 0.1605, + "step": 21151 + }, + { + "epoch": 1.72, + "learning_rate": 8.509343763581053e-06, + "loss": 0.2722, + "step": 21152 + }, + { + "epoch": 1.72, + "learning_rate": 8.508800521512387e-06, + "loss": 0.287, + "step": 21153 + }, + { + "epoch": 1.72, + "learning_rate": 8.508257279443722e-06, + "loss": 0.4329, + "step": 21154 + }, + { + "epoch": 1.72, + "learning_rate": 8.507714037375056e-06, + "loss": 0.3503, + "step": 21155 + }, + { + "epoch": 1.72, + "learning_rate": 8.507170795306388e-06, + "loss": 0.2963, + "step": 21156 + }, + { + "epoch": 1.72, + "learning_rate": 8.506627553237723e-06, + "loss": 0.3557, + "step": 21157 + }, + { + "epoch": 1.72, + "learning_rate": 8.506084311169057e-06, + "loss": 0.3955, + "step": 21158 + }, + { + "epoch": 1.72, + "learning_rate": 8.505541069100391e-06, + "loss": 0.4219, + "step": 21159 + }, + { + "epoch": 1.72, + "learning_rate": 8.504997827031725e-06, + "loss": 0.5328, + "step": 21160 + }, + { + "epoch": 1.72, + "learning_rate": 8.50445458496306e-06, + "loss": 0.3207, + "step": 21161 + }, + { + "epoch": 1.72, + "learning_rate": 8.503911342894394e-06, + "loss": 0.1785, + "step": 21162 + }, + { + "epoch": 1.72, + "learning_rate": 8.503368100825728e-06, + "loss": 0.392, + "step": 21163 + }, + { + "epoch": 1.72, + "learning_rate": 8.502824858757062e-06, + "loss": 0.257, + "step": 21164 + }, + { + "epoch": 1.72, + "learning_rate": 8.502281616688397e-06, + "loss": 0.3402, + "step": 21165 + }, + { + "epoch": 1.72, + "learning_rate": 8.50173837461973e-06, + "loss": 0.5303, + "step": 21166 + }, + { + "epoch": 1.72, + "learning_rate": 8.501195132551065e-06, + "loss": 0.2564, + "step": 21167 + }, + { + "epoch": 1.72, + "learning_rate": 8.5006518904824e-06, + "loss": 0.1781, + "step": 21168 + }, + { + "epoch": 1.72, + "learning_rate": 8.500108648413733e-06, + "loss": 0.6415, + "step": 21169 + }, + { + "epoch": 1.73, + "learning_rate": 8.499565406345068e-06, + "loss": 0.2517, + "step": 21170 + }, + { + "epoch": 1.73, + "learning_rate": 8.499022164276402e-06, + "loss": 0.4706, + "step": 21171 + }, + { + "epoch": 1.73, + "learning_rate": 8.498478922207736e-06, + "loss": 0.3458, + "step": 21172 + }, + { + "epoch": 1.73, + "learning_rate": 8.49793568013907e-06, + "loss": 0.3655, + "step": 21173 + }, + { + "epoch": 1.73, + "learning_rate": 8.497392438070405e-06, + "loss": 0.3853, + "step": 21174 + }, + { + "epoch": 1.73, + "learning_rate": 8.496849196001739e-06, + "loss": 0.8553, + "step": 21175 + }, + { + "epoch": 1.73, + "learning_rate": 8.496305953933073e-06, + "loss": 0.3772, + "step": 21176 + }, + { + "epoch": 1.73, + "learning_rate": 8.495762711864407e-06, + "loss": 0.3334, + "step": 21177 + }, + { + "epoch": 1.73, + "learning_rate": 8.495219469795742e-06, + "loss": 0.4777, + "step": 21178 + }, + { + "epoch": 1.73, + "learning_rate": 8.494676227727076e-06, + "loss": 0.2206, + "step": 21179 + }, + { + "epoch": 1.73, + "learning_rate": 8.49413298565841e-06, + "loss": 0.2746, + "step": 21180 + }, + { + "epoch": 1.73, + "learning_rate": 8.493589743589744e-06, + "loss": 0.325, + "step": 21181 + }, + { + "epoch": 1.73, + "learning_rate": 8.493046501521078e-06, + "loss": 0.3521, + "step": 21182 + }, + { + "epoch": 1.73, + "learning_rate": 8.492503259452413e-06, + "loss": 0.3696, + "step": 21183 + }, + { + "epoch": 1.73, + "learning_rate": 8.491960017383747e-06, + "loss": 0.483, + "step": 21184 + }, + { + "epoch": 1.73, + "learning_rate": 8.491416775315081e-06, + "loss": 0.3739, + "step": 21185 + }, + { + "epoch": 1.73, + "learning_rate": 8.490873533246415e-06, + "loss": 0.4261, + "step": 21186 + }, + { + "epoch": 1.73, + "learning_rate": 8.49033029117775e-06, + "loss": 0.4508, + "step": 21187 + }, + { + "epoch": 1.73, + "learning_rate": 8.489787049109084e-06, + "loss": 0.437, + "step": 21188 + }, + { + "epoch": 1.73, + "learning_rate": 8.489243807040418e-06, + "loss": 0.3366, + "step": 21189 + }, + { + "epoch": 1.73, + "learning_rate": 8.488700564971752e-06, + "loss": 0.2344, + "step": 21190 + }, + { + "epoch": 1.73, + "learning_rate": 8.488157322903086e-06, + "loss": 0.5044, + "step": 21191 + }, + { + "epoch": 1.73, + "learning_rate": 8.48761408083442e-06, + "loss": 0.3388, + "step": 21192 + }, + { + "epoch": 1.73, + "learning_rate": 8.487070838765755e-06, + "loss": 0.4511, + "step": 21193 + }, + { + "epoch": 1.73, + "learning_rate": 8.48652759669709e-06, + "loss": 0.2392, + "step": 21194 + }, + { + "epoch": 1.73, + "learning_rate": 8.485984354628423e-06, + "loss": 0.4386, + "step": 21195 + }, + { + "epoch": 1.73, + "learning_rate": 8.485441112559758e-06, + "loss": 0.288, + "step": 21196 + }, + { + "epoch": 1.73, + "learning_rate": 8.484897870491092e-06, + "loss": 0.2922, + "step": 21197 + }, + { + "epoch": 1.73, + "learning_rate": 8.484354628422426e-06, + "loss": 0.5297, + "step": 21198 + }, + { + "epoch": 1.73, + "learning_rate": 8.48381138635376e-06, + "loss": 0.2758, + "step": 21199 + }, + { + "epoch": 1.73, + "learning_rate": 8.483268144285095e-06, + "loss": 0.3381, + "step": 21200 + }, + { + "epoch": 1.73, + "learning_rate": 8.482724902216429e-06, + "loss": 0.2415, + "step": 21201 + }, + { + "epoch": 1.73, + "learning_rate": 8.482181660147763e-06, + "loss": 0.2523, + "step": 21202 + }, + { + "epoch": 1.73, + "learning_rate": 8.481638418079097e-06, + "loss": 0.2105, + "step": 21203 + }, + { + "epoch": 1.73, + "learning_rate": 8.481095176010431e-06, + "loss": 0.1177, + "step": 21204 + }, + { + "epoch": 1.73, + "learning_rate": 8.480551933941766e-06, + "loss": 0.2637, + "step": 21205 + }, + { + "epoch": 1.73, + "learning_rate": 8.4800086918731e-06, + "loss": 0.2896, + "step": 21206 + }, + { + "epoch": 1.73, + "learning_rate": 8.479465449804434e-06, + "loss": 0.3953, + "step": 21207 + }, + { + "epoch": 1.73, + "learning_rate": 8.478922207735768e-06, + "loss": 0.7045, + "step": 21208 + }, + { + "epoch": 1.73, + "learning_rate": 8.478378965667103e-06, + "loss": 0.5272, + "step": 21209 + }, + { + "epoch": 1.73, + "learning_rate": 8.477835723598437e-06, + "loss": 0.2923, + "step": 21210 + }, + { + "epoch": 1.73, + "learning_rate": 8.477292481529771e-06, + "loss": 0.3523, + "step": 21211 + }, + { + "epoch": 1.73, + "learning_rate": 8.476749239461105e-06, + "loss": 0.4165, + "step": 21212 + }, + { + "epoch": 1.73, + "learning_rate": 8.476205997392438e-06, + "loss": 0.267, + "step": 21213 + }, + { + "epoch": 1.73, + "learning_rate": 8.475662755323772e-06, + "loss": 0.1705, + "step": 21214 + }, + { + "epoch": 1.73, + "learning_rate": 8.475119513255106e-06, + "loss": 0.3612, + "step": 21215 + }, + { + "epoch": 1.73, + "learning_rate": 8.47457627118644e-06, + "loss": 0.3274, + "step": 21216 + }, + { + "epoch": 1.73, + "learning_rate": 8.474033029117775e-06, + "loss": 0.2803, + "step": 21217 + }, + { + "epoch": 1.73, + "learning_rate": 8.473489787049109e-06, + "loss": 0.3242, + "step": 21218 + }, + { + "epoch": 1.73, + "learning_rate": 8.472946544980443e-06, + "loss": 0.2303, + "step": 21219 + }, + { + "epoch": 1.73, + "learning_rate": 8.472403302911777e-06, + "loss": 0.2883, + "step": 21220 + }, + { + "epoch": 1.73, + "learning_rate": 8.471860060843112e-06, + "loss": 0.4381, + "step": 21221 + }, + { + "epoch": 1.73, + "learning_rate": 8.471316818774446e-06, + "loss": 0.2826, + "step": 21222 + }, + { + "epoch": 1.73, + "learning_rate": 8.47077357670578e-06, + "loss": 0.2822, + "step": 21223 + }, + { + "epoch": 1.73, + "learning_rate": 8.470230334637114e-06, + "loss": 0.4434, + "step": 21224 + }, + { + "epoch": 1.73, + "learning_rate": 8.469687092568449e-06, + "loss": 0.3502, + "step": 21225 + }, + { + "epoch": 1.73, + "learning_rate": 8.469143850499783e-06, + "loss": 0.4394, + "step": 21226 + }, + { + "epoch": 1.73, + "learning_rate": 8.468600608431117e-06, + "loss": 0.1818, + "step": 21227 + }, + { + "epoch": 1.73, + "learning_rate": 8.468057366362451e-06, + "loss": 0.3059, + "step": 21228 + }, + { + "epoch": 1.73, + "learning_rate": 8.467514124293786e-06, + "loss": 0.2669, + "step": 21229 + }, + { + "epoch": 1.73, + "learning_rate": 8.466970882225121e-06, + "loss": 0.3552, + "step": 21230 + }, + { + "epoch": 1.73, + "learning_rate": 8.466427640156456e-06, + "loss": 0.2003, + "step": 21231 + }, + { + "epoch": 1.73, + "learning_rate": 8.465884398087788e-06, + "loss": 0.3237, + "step": 21232 + }, + { + "epoch": 1.73, + "learning_rate": 8.465341156019122e-06, + "loss": 0.2199, + "step": 21233 + }, + { + "epoch": 1.73, + "learning_rate": 8.464797913950457e-06, + "loss": 0.3507, + "step": 21234 + }, + { + "epoch": 1.73, + "learning_rate": 8.464254671881791e-06, + "loss": 0.3685, + "step": 21235 + }, + { + "epoch": 1.73, + "learning_rate": 8.463711429813125e-06, + "loss": 0.4785, + "step": 21236 + }, + { + "epoch": 1.73, + "learning_rate": 8.46316818774446e-06, + "loss": 0.2384, + "step": 21237 + }, + { + "epoch": 1.73, + "learning_rate": 8.462624945675794e-06, + "loss": 0.2173, + "step": 21238 + }, + { + "epoch": 1.73, + "learning_rate": 8.462081703607128e-06, + "loss": 0.1537, + "step": 21239 + }, + { + "epoch": 1.73, + "learning_rate": 8.461538461538462e-06, + "loss": 0.4442, + "step": 21240 + }, + { + "epoch": 1.73, + "learning_rate": 8.460995219469796e-06, + "loss": 0.1755, + "step": 21241 + }, + { + "epoch": 1.73, + "learning_rate": 8.46045197740113e-06, + "loss": 0.4082, + "step": 21242 + }, + { + "epoch": 1.73, + "learning_rate": 8.459908735332465e-06, + "loss": 0.159, + "step": 21243 + }, + { + "epoch": 1.73, + "learning_rate": 8.459365493263799e-06, + "loss": 0.1312, + "step": 21244 + }, + { + "epoch": 1.73, + "learning_rate": 8.458822251195133e-06, + "loss": 0.4877, + "step": 21245 + }, + { + "epoch": 1.73, + "learning_rate": 8.458279009126467e-06, + "loss": 0.1998, + "step": 21246 + }, + { + "epoch": 1.73, + "learning_rate": 8.457735767057802e-06, + "loss": 0.4757, + "step": 21247 + }, + { + "epoch": 1.73, + "learning_rate": 8.457192524989136e-06, + "loss": 0.6188, + "step": 21248 + }, + { + "epoch": 1.73, + "learning_rate": 8.45664928292047e-06, + "loss": 0.6429, + "step": 21249 + }, + { + "epoch": 1.73, + "learning_rate": 8.456106040851804e-06, + "loss": 0.3705, + "step": 21250 + }, + { + "epoch": 1.73, + "eval_accuracy": 0.8456444218033622, + "eval_loss": 0.43275195360183716, + "eval_runtime": 22.3436, + "eval_samples_per_second": 439.275, + "eval_steps_per_second": 3.446, + "step": 21250 + }, + { + "epoch": 1.73, + "learning_rate": 8.455562798783139e-06, + "loss": 0.3049, + "step": 21251 + }, + { + "epoch": 1.73, + "learning_rate": 8.455019556714473e-06, + "loss": 0.394, + "step": 21252 + }, + { + "epoch": 1.73, + "learning_rate": 8.454476314645807e-06, + "loss": 0.27, + "step": 21253 + }, + { + "epoch": 1.73, + "learning_rate": 8.453933072577141e-06, + "loss": 0.473, + "step": 21254 + }, + { + "epoch": 1.73, + "learning_rate": 8.453389830508476e-06, + "loss": 0.4442, + "step": 21255 + }, + { + "epoch": 1.73, + "learning_rate": 8.45284658843981e-06, + "loss": 0.2442, + "step": 21256 + }, + { + "epoch": 1.73, + "learning_rate": 8.452303346371144e-06, + "loss": 0.3661, + "step": 21257 + }, + { + "epoch": 1.73, + "learning_rate": 8.451760104302478e-06, + "loss": 0.4417, + "step": 21258 + }, + { + "epoch": 1.73, + "learning_rate": 8.451216862233812e-06, + "loss": 0.5099, + "step": 21259 + }, + { + "epoch": 1.73, + "learning_rate": 8.450673620165147e-06, + "loss": 0.2312, + "step": 21260 + }, + { + "epoch": 1.73, + "learning_rate": 8.450130378096481e-06, + "loss": 0.289, + "step": 21261 + }, + { + "epoch": 1.73, + "learning_rate": 8.449587136027815e-06, + "loss": 0.3334, + "step": 21262 + }, + { + "epoch": 1.73, + "learning_rate": 8.44904389395915e-06, + "loss": 0.2557, + "step": 21263 + }, + { + "epoch": 1.73, + "learning_rate": 8.448500651890484e-06, + "loss": 0.2923, + "step": 21264 + }, + { + "epoch": 1.73, + "learning_rate": 8.447957409821818e-06, + "loss": 0.3341, + "step": 21265 + }, + { + "epoch": 1.73, + "learning_rate": 8.447414167753152e-06, + "loss": 0.3578, + "step": 21266 + }, + { + "epoch": 1.73, + "learning_rate": 8.446870925684486e-06, + "loss": 0.1262, + "step": 21267 + }, + { + "epoch": 1.73, + "learning_rate": 8.44632768361582e-06, + "loss": 0.3865, + "step": 21268 + }, + { + "epoch": 1.73, + "learning_rate": 8.445784441547155e-06, + "loss": 0.4507, + "step": 21269 + }, + { + "epoch": 1.73, + "learning_rate": 8.445241199478487e-06, + "loss": 0.4994, + "step": 21270 + }, + { + "epoch": 1.73, + "learning_rate": 8.444697957409822e-06, + "loss": 0.2428, + "step": 21271 + }, + { + "epoch": 1.73, + "learning_rate": 8.444154715341156e-06, + "loss": 0.1266, + "step": 21272 + }, + { + "epoch": 1.73, + "learning_rate": 8.44361147327249e-06, + "loss": 0.2561, + "step": 21273 + }, + { + "epoch": 1.73, + "learning_rate": 8.443068231203824e-06, + "loss": 0.2215, + "step": 21274 + }, + { + "epoch": 1.73, + "learning_rate": 8.442524989135158e-06, + "loss": 0.1098, + "step": 21275 + }, + { + "epoch": 1.73, + "learning_rate": 8.441981747066493e-06, + "loss": 0.461, + "step": 21276 + }, + { + "epoch": 1.73, + "learning_rate": 8.441438504997827e-06, + "loss": 0.3954, + "step": 21277 + }, + { + "epoch": 1.73, + "learning_rate": 8.440895262929161e-06, + "loss": 0.2537, + "step": 21278 + }, + { + "epoch": 1.73, + "learning_rate": 8.440352020860495e-06, + "loss": 0.4003, + "step": 21279 + }, + { + "epoch": 1.73, + "learning_rate": 8.43980877879183e-06, + "loss": 0.2339, + "step": 21280 + }, + { + "epoch": 1.73, + "learning_rate": 8.439265536723164e-06, + "loss": 0.3833, + "step": 21281 + }, + { + "epoch": 1.73, + "learning_rate": 8.438722294654498e-06, + "loss": 0.2425, + "step": 21282 + }, + { + "epoch": 1.73, + "learning_rate": 8.438179052585832e-06, + "loss": 0.2677, + "step": 21283 + }, + { + "epoch": 1.73, + "learning_rate": 8.437635810517168e-06, + "loss": 0.2166, + "step": 21284 + }, + { + "epoch": 1.73, + "learning_rate": 8.437092568448502e-06, + "loss": 0.4984, + "step": 21285 + }, + { + "epoch": 1.73, + "learning_rate": 8.436549326379837e-06, + "loss": 0.4187, + "step": 21286 + }, + { + "epoch": 1.73, + "learning_rate": 8.436006084311171e-06, + "loss": 0.8948, + "step": 21287 + }, + { + "epoch": 1.73, + "learning_rate": 8.435462842242505e-06, + "loss": 0.4536, + "step": 21288 + }, + { + "epoch": 1.73, + "learning_rate": 8.43491960017384e-06, + "loss": 0.2035, + "step": 21289 + }, + { + "epoch": 1.73, + "learning_rate": 8.434376358105172e-06, + "loss": 0.4031, + "step": 21290 + }, + { + "epoch": 1.73, + "learning_rate": 8.433833116036506e-06, + "loss": 0.4921, + "step": 21291 + }, + { + "epoch": 1.74, + "learning_rate": 8.43328987396784e-06, + "loss": 0.2056, + "step": 21292 + }, + { + "epoch": 1.74, + "learning_rate": 8.432746631899175e-06, + "loss": 0.8871, + "step": 21293 + }, + { + "epoch": 1.74, + "learning_rate": 8.432203389830509e-06, + "loss": 0.1717, + "step": 21294 + }, + { + "epoch": 1.74, + "learning_rate": 8.431660147761843e-06, + "loss": 0.4597, + "step": 21295 + }, + { + "epoch": 1.74, + "learning_rate": 8.431116905693177e-06, + "loss": 0.1465, + "step": 21296 + }, + { + "epoch": 1.74, + "learning_rate": 8.430573663624512e-06, + "loss": 0.5201, + "step": 21297 + }, + { + "epoch": 1.74, + "learning_rate": 8.430030421555846e-06, + "loss": 0.2563, + "step": 21298 + }, + { + "epoch": 1.74, + "learning_rate": 8.42948717948718e-06, + "loss": 0.7092, + "step": 21299 + }, + { + "epoch": 1.74, + "learning_rate": 8.428943937418514e-06, + "loss": 0.4074, + "step": 21300 + }, + { + "epoch": 1.74, + "learning_rate": 8.428400695349848e-06, + "loss": 0.3583, + "step": 21301 + }, + { + "epoch": 1.74, + "learning_rate": 8.427857453281183e-06, + "loss": 0.4664, + "step": 21302 + }, + { + "epoch": 1.74, + "learning_rate": 8.427314211212517e-06, + "loss": 0.1814, + "step": 21303 + }, + { + "epoch": 1.74, + "learning_rate": 8.426770969143851e-06, + "loss": 0.1459, + "step": 21304 + }, + { + "epoch": 1.74, + "learning_rate": 8.426227727075185e-06, + "loss": 0.1449, + "step": 21305 + }, + { + "epoch": 1.74, + "learning_rate": 8.42568448500652e-06, + "loss": 0.3491, + "step": 21306 + }, + { + "epoch": 1.74, + "learning_rate": 8.425141242937854e-06, + "loss": 0.3264, + "step": 21307 + }, + { + "epoch": 1.74, + "learning_rate": 8.424598000869188e-06, + "loss": 0.4716, + "step": 21308 + }, + { + "epoch": 1.74, + "learning_rate": 8.424054758800522e-06, + "loss": 0.431, + "step": 21309 + }, + { + "epoch": 1.74, + "learning_rate": 8.423511516731857e-06, + "loss": 0.3614, + "step": 21310 + }, + { + "epoch": 1.74, + "learning_rate": 8.42296827466319e-06, + "loss": 0.4229, + "step": 21311 + }, + { + "epoch": 1.74, + "learning_rate": 8.422425032594525e-06, + "loss": 0.3521, + "step": 21312 + }, + { + "epoch": 1.74, + "learning_rate": 8.42188179052586e-06, + "loss": 0.4422, + "step": 21313 + }, + { + "epoch": 1.74, + "learning_rate": 8.421338548457193e-06, + "loss": 0.3438, + "step": 21314 + }, + { + "epoch": 1.74, + "learning_rate": 8.420795306388528e-06, + "loss": 0.26, + "step": 21315 + }, + { + "epoch": 1.74, + "learning_rate": 8.420252064319862e-06, + "loss": 0.3366, + "step": 21316 + }, + { + "epoch": 1.74, + "learning_rate": 8.419708822251196e-06, + "loss": 0.446, + "step": 21317 + }, + { + "epoch": 1.74, + "learning_rate": 8.41916558018253e-06, + "loss": 0.262, + "step": 21318 + }, + { + "epoch": 1.74, + "learning_rate": 8.418622338113865e-06, + "loss": 0.3537, + "step": 21319 + }, + { + "epoch": 1.74, + "learning_rate": 8.418079096045199e-06, + "loss": 0.4715, + "step": 21320 + }, + { + "epoch": 1.74, + "learning_rate": 8.417535853976533e-06, + "loss": 0.427, + "step": 21321 + }, + { + "epoch": 1.74, + "learning_rate": 8.416992611907867e-06, + "loss": 0.3656, + "step": 21322 + }, + { + "epoch": 1.74, + "learning_rate": 8.416449369839202e-06, + "loss": 0.2413, + "step": 21323 + }, + { + "epoch": 1.74, + "learning_rate": 8.415906127770536e-06, + "loss": 0.1153, + "step": 21324 + }, + { + "epoch": 1.74, + "learning_rate": 8.41536288570187e-06, + "loss": 0.463, + "step": 21325 + }, + { + "epoch": 1.74, + "learning_rate": 8.414819643633204e-06, + "loss": 0.3645, + "step": 21326 + }, + { + "epoch": 1.74, + "learning_rate": 8.414276401564538e-06, + "loss": 0.1635, + "step": 21327 + }, + { + "epoch": 1.74, + "learning_rate": 8.413733159495871e-06, + "loss": 0.3815, + "step": 21328 + }, + { + "epoch": 1.74, + "learning_rate": 8.413189917427205e-06, + "loss": 0.1315, + "step": 21329 + }, + { + "epoch": 1.74, + "learning_rate": 8.41264667535854e-06, + "loss": 0.3036, + "step": 21330 + }, + { + "epoch": 1.74, + "learning_rate": 8.412103433289874e-06, + "loss": 0.7232, + "step": 21331 + }, + { + "epoch": 1.74, + "learning_rate": 8.411560191221208e-06, + "loss": 0.758, + "step": 21332 + }, + { + "epoch": 1.74, + "learning_rate": 8.411016949152542e-06, + "loss": 0.3807, + "step": 21333 + }, + { + "epoch": 1.74, + "learning_rate": 8.410473707083876e-06, + "loss": 0.1579, + "step": 21334 + }, + { + "epoch": 1.74, + "learning_rate": 8.40993046501521e-06, + "loss": 0.3469, + "step": 21335 + }, + { + "epoch": 1.74, + "learning_rate": 8.409387222946545e-06, + "loss": 0.3559, + "step": 21336 + }, + { + "epoch": 1.74, + "learning_rate": 8.408843980877879e-06, + "loss": 0.3297, + "step": 21337 + }, + { + "epoch": 1.74, + "learning_rate": 8.408300738809215e-06, + "loss": 0.2866, + "step": 21338 + }, + { + "epoch": 1.74, + "learning_rate": 8.40775749674055e-06, + "loss": 0.4938, + "step": 21339 + }, + { + "epoch": 1.74, + "learning_rate": 8.407214254671883e-06, + "loss": 0.4747, + "step": 21340 + }, + { + "epoch": 1.74, + "learning_rate": 8.406671012603218e-06, + "loss": 0.3704, + "step": 21341 + }, + { + "epoch": 1.74, + "learning_rate": 8.406127770534552e-06, + "loss": 0.2106, + "step": 21342 + }, + { + "epoch": 1.74, + "learning_rate": 8.405584528465886e-06, + "loss": 0.1892, + "step": 21343 + }, + { + "epoch": 1.74, + "learning_rate": 8.40504128639722e-06, + "loss": 0.2107, + "step": 21344 + }, + { + "epoch": 1.74, + "learning_rate": 8.404498044328555e-06, + "loss": 0.2971, + "step": 21345 + }, + { + "epoch": 1.74, + "learning_rate": 8.403954802259889e-06, + "loss": 0.2581, + "step": 21346 + }, + { + "epoch": 1.74, + "learning_rate": 8.403411560191221e-06, + "loss": 0.4023, + "step": 21347 + }, + { + "epoch": 1.74, + "learning_rate": 8.402868318122556e-06, + "loss": 0.5118, + "step": 21348 + }, + { + "epoch": 1.74, + "learning_rate": 8.40232507605389e-06, + "loss": 0.7238, + "step": 21349 + }, + { + "epoch": 1.74, + "learning_rate": 8.401781833985224e-06, + "loss": 0.2229, + "step": 21350 + }, + { + "epoch": 1.74, + "learning_rate": 8.401238591916558e-06, + "loss": 0.2382, + "step": 21351 + }, + { + "epoch": 1.74, + "learning_rate": 8.400695349847893e-06, + "loss": 0.1459, + "step": 21352 + }, + { + "epoch": 1.74, + "learning_rate": 8.400152107779227e-06, + "loss": 0.2909, + "step": 21353 + }, + { + "epoch": 1.74, + "learning_rate": 8.399608865710561e-06, + "loss": 0.4369, + "step": 21354 + }, + { + "epoch": 1.74, + "learning_rate": 8.399065623641895e-06, + "loss": 0.3408, + "step": 21355 + }, + { + "epoch": 1.74, + "learning_rate": 8.39852238157323e-06, + "loss": 0.3266, + "step": 21356 + }, + { + "epoch": 1.74, + "learning_rate": 8.397979139504564e-06, + "loss": 0.2675, + "step": 21357 + }, + { + "epoch": 1.74, + "learning_rate": 8.397435897435898e-06, + "loss": 0.2295, + "step": 21358 + }, + { + "epoch": 1.74, + "learning_rate": 8.396892655367232e-06, + "loss": 0.2401, + "step": 21359 + }, + { + "epoch": 1.74, + "learning_rate": 8.396349413298566e-06, + "loss": 0.0792, + "step": 21360 + }, + { + "epoch": 1.74, + "learning_rate": 8.3958061712299e-06, + "loss": 0.4339, + "step": 21361 + }, + { + "epoch": 1.74, + "learning_rate": 8.395262929161235e-06, + "loss": 0.2545, + "step": 21362 + }, + { + "epoch": 1.74, + "learning_rate": 8.394719687092569e-06, + "loss": 0.5021, + "step": 21363 + }, + { + "epoch": 1.74, + "learning_rate": 8.394176445023903e-06, + "loss": 0.2046, + "step": 21364 + }, + { + "epoch": 1.74, + "learning_rate": 8.393633202955238e-06, + "loss": 0.4024, + "step": 21365 + }, + { + "epoch": 1.74, + "learning_rate": 8.393089960886572e-06, + "loss": 0.3106, + "step": 21366 + }, + { + "epoch": 1.74, + "learning_rate": 8.392546718817906e-06, + "loss": 0.1767, + "step": 21367 + }, + { + "epoch": 1.74, + "learning_rate": 8.39200347674924e-06, + "loss": 0.2976, + "step": 21368 + }, + { + "epoch": 1.74, + "learning_rate": 8.391460234680574e-06, + "loss": 0.2916, + "step": 21369 + }, + { + "epoch": 1.74, + "learning_rate": 8.390916992611909e-06, + "loss": 0.2851, + "step": 21370 + }, + { + "epoch": 1.74, + "learning_rate": 8.390373750543243e-06, + "loss": 0.2601, + "step": 21371 + }, + { + "epoch": 1.74, + "learning_rate": 8.389830508474577e-06, + "loss": 0.3731, + "step": 21372 + }, + { + "epoch": 1.74, + "learning_rate": 8.389287266405911e-06, + "loss": 0.2548, + "step": 21373 + }, + { + "epoch": 1.74, + "learning_rate": 8.388744024337246e-06, + "loss": 0.3424, + "step": 21374 + }, + { + "epoch": 1.74, + "learning_rate": 8.38820078226858e-06, + "loss": 0.2195, + "step": 21375 + }, + { + "epoch": 1.74, + "learning_rate": 8.387657540199914e-06, + "loss": 0.4947, + "step": 21376 + }, + { + "epoch": 1.74, + "learning_rate": 8.387114298131248e-06, + "loss": 0.0939, + "step": 21377 + }, + { + "epoch": 1.74, + "learning_rate": 8.386571056062583e-06, + "loss": 0.4369, + "step": 21378 + }, + { + "epoch": 1.74, + "learning_rate": 8.386027813993917e-06, + "loss": 0.146, + "step": 21379 + }, + { + "epoch": 1.74, + "learning_rate": 8.385484571925251e-06, + "loss": 0.2766, + "step": 21380 + }, + { + "epoch": 1.74, + "learning_rate": 8.384941329856585e-06, + "loss": 0.4284, + "step": 21381 + }, + { + "epoch": 1.74, + "learning_rate": 8.38439808778792e-06, + "loss": 0.6925, + "step": 21382 + }, + { + "epoch": 1.74, + "learning_rate": 8.383854845719254e-06, + "loss": 0.2812, + "step": 21383 + }, + { + "epoch": 1.74, + "learning_rate": 8.383311603650588e-06, + "loss": 0.4546, + "step": 21384 + }, + { + "epoch": 1.74, + "learning_rate": 8.38276836158192e-06, + "loss": 0.2163, + "step": 21385 + }, + { + "epoch": 1.74, + "learning_rate": 8.382225119513255e-06, + "loss": 0.3038, + "step": 21386 + }, + { + "epoch": 1.74, + "learning_rate": 8.381681877444589e-06, + "loss": 0.2553, + "step": 21387 + }, + { + "epoch": 1.74, + "learning_rate": 8.381138635375923e-06, + "loss": 0.0791, + "step": 21388 + }, + { + "epoch": 1.74, + "learning_rate": 8.380595393307257e-06, + "loss": 0.4419, + "step": 21389 + }, + { + "epoch": 1.74, + "learning_rate": 8.380052151238592e-06, + "loss": 0.1781, + "step": 21390 + }, + { + "epoch": 1.74, + "learning_rate": 8.379508909169926e-06, + "loss": 0.3649, + "step": 21391 + }, + { + "epoch": 1.74, + "learning_rate": 8.378965667101262e-06, + "loss": 0.2565, + "step": 21392 + }, + { + "epoch": 1.74, + "learning_rate": 8.378422425032596e-06, + "loss": 0.256, + "step": 21393 + }, + { + "epoch": 1.74, + "learning_rate": 8.37787918296393e-06, + "loss": 0.2253, + "step": 21394 + }, + { + "epoch": 1.74, + "learning_rate": 8.377335940895264e-06, + "loss": 0.141, + "step": 21395 + }, + { + "epoch": 1.74, + "learning_rate": 8.376792698826599e-06, + "loss": 0.4392, + "step": 21396 + }, + { + "epoch": 1.74, + "learning_rate": 8.376249456757933e-06, + "loss": 0.5114, + "step": 21397 + }, + { + "epoch": 1.74, + "learning_rate": 8.375706214689267e-06, + "loss": 0.2174, + "step": 21398 + }, + { + "epoch": 1.74, + "learning_rate": 8.375162972620601e-06, + "loss": 0.2093, + "step": 21399 + }, + { + "epoch": 1.74, + "learning_rate": 8.374619730551936e-06, + "loss": 0.2345, + "step": 21400 + }, + { + "epoch": 1.74, + "learning_rate": 8.37407648848327e-06, + "loss": 0.3736, + "step": 21401 + }, + { + "epoch": 1.74, + "learning_rate": 8.373533246414604e-06, + "loss": 0.3259, + "step": 21402 + }, + { + "epoch": 1.74, + "learning_rate": 8.372990004345938e-06, + "loss": 0.5067, + "step": 21403 + }, + { + "epoch": 1.74, + "learning_rate": 8.37244676227727e-06, + "loss": 0.2604, + "step": 21404 + }, + { + "epoch": 1.74, + "learning_rate": 8.371903520208605e-06, + "loss": 0.2103, + "step": 21405 + }, + { + "epoch": 1.74, + "learning_rate": 8.37136027813994e-06, + "loss": 0.2589, + "step": 21406 + }, + { + "epoch": 1.74, + "learning_rate": 8.370817036071274e-06, + "loss": 0.2101, + "step": 21407 + }, + { + "epoch": 1.74, + "learning_rate": 8.370273794002608e-06, + "loss": 0.119, + "step": 21408 + }, + { + "epoch": 1.74, + "learning_rate": 8.369730551933942e-06, + "loss": 0.1815, + "step": 21409 + }, + { + "epoch": 1.74, + "learning_rate": 8.369187309865276e-06, + "loss": 0.2724, + "step": 21410 + }, + { + "epoch": 1.74, + "learning_rate": 8.36864406779661e-06, + "loss": 0.1043, + "step": 21411 + }, + { + "epoch": 1.74, + "learning_rate": 8.368100825727945e-06, + "loss": 0.3019, + "step": 21412 + }, + { + "epoch": 1.74, + "learning_rate": 8.367557583659279e-06, + "loss": 0.3341, + "step": 21413 + }, + { + "epoch": 1.74, + "learning_rate": 8.367014341590613e-06, + "loss": 0.2497, + "step": 21414 + }, + { + "epoch": 1.75, + "learning_rate": 8.366471099521947e-06, + "loss": 0.3674, + "step": 21415 + }, + { + "epoch": 1.75, + "learning_rate": 8.365927857453282e-06, + "loss": 0.3339, + "step": 21416 + }, + { + "epoch": 1.75, + "learning_rate": 8.365384615384616e-06, + "loss": 0.3128, + "step": 21417 + }, + { + "epoch": 1.75, + "learning_rate": 8.36484137331595e-06, + "loss": 0.3873, + "step": 21418 + }, + { + "epoch": 1.75, + "learning_rate": 8.364298131247284e-06, + "loss": 0.2941, + "step": 21419 + }, + { + "epoch": 1.75, + "learning_rate": 8.363754889178619e-06, + "loss": 0.3447, + "step": 21420 + }, + { + "epoch": 1.75, + "learning_rate": 8.363211647109953e-06, + "loss": 0.4002, + "step": 21421 + }, + { + "epoch": 1.75, + "learning_rate": 8.362668405041287e-06, + "loss": 0.2315, + "step": 21422 + }, + { + "epoch": 1.75, + "learning_rate": 8.362125162972621e-06, + "loss": 0.3802, + "step": 21423 + }, + { + "epoch": 1.75, + "learning_rate": 8.361581920903955e-06, + "loss": 0.2596, + "step": 21424 + }, + { + "epoch": 1.75, + "learning_rate": 8.36103867883529e-06, + "loss": 0.5561, + "step": 21425 + }, + { + "epoch": 1.75, + "learning_rate": 8.360495436766624e-06, + "loss": 0.4568, + "step": 21426 + }, + { + "epoch": 1.75, + "learning_rate": 8.359952194697958e-06, + "loss": 0.4267, + "step": 21427 + }, + { + "epoch": 1.75, + "learning_rate": 8.359408952629292e-06, + "loss": 0.3011, + "step": 21428 + }, + { + "epoch": 1.75, + "learning_rate": 8.358865710560627e-06, + "loss": 0.4305, + "step": 21429 + }, + { + "epoch": 1.75, + "learning_rate": 8.35832246849196e-06, + "loss": 0.3893, + "step": 21430 + }, + { + "epoch": 1.75, + "learning_rate": 8.357779226423295e-06, + "loss": 0.3252, + "step": 21431 + }, + { + "epoch": 1.75, + "learning_rate": 8.35723598435463e-06, + "loss": 0.3073, + "step": 21432 + }, + { + "epoch": 1.75, + "learning_rate": 8.356692742285964e-06, + "loss": 0.3745, + "step": 21433 + }, + { + "epoch": 1.75, + "learning_rate": 8.356149500217298e-06, + "loss": 0.3389, + "step": 21434 + }, + { + "epoch": 1.75, + "learning_rate": 8.355606258148632e-06, + "loss": 0.3071, + "step": 21435 + }, + { + "epoch": 1.75, + "learning_rate": 8.355063016079966e-06, + "loss": 0.2485, + "step": 21436 + }, + { + "epoch": 1.75, + "learning_rate": 8.3545197740113e-06, + "loss": 0.3529, + "step": 21437 + }, + { + "epoch": 1.75, + "learning_rate": 8.353976531942635e-06, + "loss": 0.3115, + "step": 21438 + }, + { + "epoch": 1.75, + "learning_rate": 8.353433289873969e-06, + "loss": 0.2993, + "step": 21439 + }, + { + "epoch": 1.75, + "learning_rate": 8.352890047805303e-06, + "loss": 0.2283, + "step": 21440 + }, + { + "epoch": 1.75, + "learning_rate": 8.352346805736637e-06, + "loss": 0.1769, + "step": 21441 + }, + { + "epoch": 1.75, + "learning_rate": 8.35180356366797e-06, + "loss": 0.2369, + "step": 21442 + }, + { + "epoch": 1.75, + "learning_rate": 8.351260321599304e-06, + "loss": 0.3893, + "step": 21443 + }, + { + "epoch": 1.75, + "learning_rate": 8.350717079530638e-06, + "loss": 0.3946, + "step": 21444 + }, + { + "epoch": 1.75, + "learning_rate": 8.350173837461973e-06, + "loss": 0.2175, + "step": 21445 + }, + { + "epoch": 1.75, + "learning_rate": 8.349630595393309e-06, + "loss": 0.0833, + "step": 21446 + }, + { + "epoch": 1.75, + "learning_rate": 8.349087353324643e-06, + "loss": 0.5233, + "step": 21447 + }, + { + "epoch": 1.75, + "learning_rate": 8.348544111255977e-06, + "loss": 0.3359, + "step": 21448 + }, + { + "epoch": 1.75, + "learning_rate": 8.348000869187311e-06, + "loss": 0.3168, + "step": 21449 + }, + { + "epoch": 1.75, + "learning_rate": 8.347457627118645e-06, + "loss": 0.2153, + "step": 21450 + }, + { + "epoch": 1.75, + "learning_rate": 8.34691438504998e-06, + "loss": 0.4447, + "step": 21451 + }, + { + "epoch": 1.75, + "learning_rate": 8.346371142981314e-06, + "loss": 0.3307, + "step": 21452 + }, + { + "epoch": 1.75, + "learning_rate": 8.345827900912648e-06, + "loss": 0.284, + "step": 21453 + }, + { + "epoch": 1.75, + "learning_rate": 8.345284658843982e-06, + "loss": 0.3079, + "step": 21454 + }, + { + "epoch": 1.75, + "learning_rate": 8.344741416775317e-06, + "loss": 0.464, + "step": 21455 + }, + { + "epoch": 1.75, + "learning_rate": 8.34419817470665e-06, + "loss": 0.5824, + "step": 21456 + }, + { + "epoch": 1.75, + "learning_rate": 8.343654932637985e-06, + "loss": 0.5861, + "step": 21457 + }, + { + "epoch": 1.75, + "learning_rate": 8.34311169056932e-06, + "loss": 0.0861, + "step": 21458 + }, + { + "epoch": 1.75, + "learning_rate": 8.342568448500654e-06, + "loss": 0.3719, + "step": 21459 + }, + { + "epoch": 1.75, + "learning_rate": 8.342025206431988e-06, + "loss": 0.2478, + "step": 21460 + }, + { + "epoch": 1.75, + "learning_rate": 8.34148196436332e-06, + "loss": 0.2626, + "step": 21461 + }, + { + "epoch": 1.75, + "learning_rate": 8.340938722294655e-06, + "loss": 0.2073, + "step": 21462 + }, + { + "epoch": 1.75, + "learning_rate": 8.340395480225989e-06, + "loss": 0.2369, + "step": 21463 + }, + { + "epoch": 1.75, + "learning_rate": 8.339852238157323e-06, + "loss": 0.1677, + "step": 21464 + }, + { + "epoch": 1.75, + "learning_rate": 8.339308996088657e-06, + "loss": 0.2053, + "step": 21465 + }, + { + "epoch": 1.75, + "learning_rate": 8.338765754019991e-06, + "loss": 0.2177, + "step": 21466 + }, + { + "epoch": 1.75, + "learning_rate": 8.338222511951326e-06, + "loss": 0.3572, + "step": 21467 + }, + { + "epoch": 1.75, + "learning_rate": 8.33767926988266e-06, + "loss": 0.7112, + "step": 21468 + }, + { + "epoch": 1.75, + "learning_rate": 8.337136027813994e-06, + "loss": 0.2108, + "step": 21469 + }, + { + "epoch": 1.75, + "learning_rate": 8.336592785745328e-06, + "loss": 0.2718, + "step": 21470 + }, + { + "epoch": 1.75, + "learning_rate": 8.336049543676663e-06, + "loss": 0.1947, + "step": 21471 + }, + { + "epoch": 1.75, + "learning_rate": 8.335506301607997e-06, + "loss": 0.3949, + "step": 21472 + }, + { + "epoch": 1.75, + "learning_rate": 8.334963059539331e-06, + "loss": 0.1452, + "step": 21473 + }, + { + "epoch": 1.75, + "learning_rate": 8.334419817470665e-06, + "loss": 0.1923, + "step": 21474 + }, + { + "epoch": 1.75, + "learning_rate": 8.333876575402e-06, + "loss": 0.6611, + "step": 21475 + }, + { + "epoch": 1.75, + "learning_rate": 8.333333333333334e-06, + "loss": 0.2009, + "step": 21476 + }, + { + "epoch": 1.75, + "learning_rate": 8.332790091264668e-06, + "loss": 0.3907, + "step": 21477 + }, + { + "epoch": 1.75, + "learning_rate": 8.332246849196002e-06, + "loss": 0.3931, + "step": 21478 + }, + { + "epoch": 1.75, + "learning_rate": 8.331703607127336e-06, + "loss": 0.4182, + "step": 21479 + }, + { + "epoch": 1.75, + "learning_rate": 8.33116036505867e-06, + "loss": 0.1531, + "step": 21480 + }, + { + "epoch": 1.75, + "learning_rate": 8.330617122990005e-06, + "loss": 0.3122, + "step": 21481 + }, + { + "epoch": 1.75, + "learning_rate": 8.330073880921339e-06, + "loss": 0.3301, + "step": 21482 + }, + { + "epoch": 1.75, + "learning_rate": 8.329530638852673e-06, + "loss": 0.5666, + "step": 21483 + }, + { + "epoch": 1.75, + "learning_rate": 8.328987396784008e-06, + "loss": 0.4956, + "step": 21484 + }, + { + "epoch": 1.75, + "learning_rate": 8.328444154715342e-06, + "loss": 0.4152, + "step": 21485 + }, + { + "epoch": 1.75, + "learning_rate": 8.327900912646676e-06, + "loss": 0.4754, + "step": 21486 + }, + { + "epoch": 1.75, + "learning_rate": 8.32735767057801e-06, + "loss": 0.0791, + "step": 21487 + }, + { + "epoch": 1.75, + "learning_rate": 8.326814428509344e-06, + "loss": 0.1749, + "step": 21488 + }, + { + "epoch": 1.75, + "learning_rate": 8.326271186440679e-06, + "loss": 0.4629, + "step": 21489 + }, + { + "epoch": 1.75, + "learning_rate": 8.325727944372013e-06, + "loss": 0.1838, + "step": 21490 + }, + { + "epoch": 1.75, + "learning_rate": 8.325184702303347e-06, + "loss": 0.2771, + "step": 21491 + }, + { + "epoch": 1.75, + "learning_rate": 8.324641460234681e-06, + "loss": 0.5316, + "step": 21492 + }, + { + "epoch": 1.75, + "learning_rate": 8.324098218166016e-06, + "loss": 0.1854, + "step": 21493 + }, + { + "epoch": 1.75, + "learning_rate": 8.32355497609735e-06, + "loss": 0.4101, + "step": 21494 + }, + { + "epoch": 1.75, + "learning_rate": 8.323011734028684e-06, + "loss": 0.65, + "step": 21495 + }, + { + "epoch": 1.75, + "learning_rate": 8.322468491960018e-06, + "loss": 0.4325, + "step": 21496 + }, + { + "epoch": 1.75, + "learning_rate": 8.321925249891353e-06, + "loss": 0.1414, + "step": 21497 + }, + { + "epoch": 1.75, + "learning_rate": 8.321382007822687e-06, + "loss": 0.1409, + "step": 21498 + }, + { + "epoch": 1.75, + "learning_rate": 8.32083876575402e-06, + "loss": 0.3355, + "step": 21499 + }, + { + "epoch": 1.75, + "learning_rate": 8.320295523685355e-06, + "loss": 0.2711, + "step": 21500 + }, + { + "epoch": 1.75, + "eval_accuracy": 0.8393275598573612, + "eval_loss": 0.44132834672927856, + "eval_runtime": 22.3539, + "eval_samples_per_second": 439.073, + "eval_steps_per_second": 3.445, + "step": 21500 + }, + { + "epoch": 1.75, + "learning_rate": 8.31975228161669e-06, + "loss": 0.4069, + "step": 21501 + }, + { + "epoch": 1.75, + "learning_rate": 8.319209039548024e-06, + "loss": 0.2082, + "step": 21502 + }, + { + "epoch": 1.75, + "learning_rate": 8.318665797479358e-06, + "loss": 0.4013, + "step": 21503 + }, + { + "epoch": 1.75, + "learning_rate": 8.318122555410692e-06, + "loss": 0.3305, + "step": 21504 + }, + { + "epoch": 1.75, + "learning_rate": 8.317579313342026e-06, + "loss": 0.3983, + "step": 21505 + }, + { + "epoch": 1.75, + "learning_rate": 8.31703607127336e-06, + "loss": 0.3083, + "step": 21506 + }, + { + "epoch": 1.75, + "learning_rate": 8.316492829204695e-06, + "loss": 0.2409, + "step": 21507 + }, + { + "epoch": 1.75, + "learning_rate": 8.315949587136029e-06, + "loss": 0.2084, + "step": 21508 + }, + { + "epoch": 1.75, + "learning_rate": 8.315406345067363e-06, + "loss": 0.2989, + "step": 21509 + }, + { + "epoch": 1.75, + "learning_rate": 8.314863102998698e-06, + "loss": 0.458, + "step": 21510 + }, + { + "epoch": 1.75, + "learning_rate": 8.314319860930032e-06, + "loss": 0.1694, + "step": 21511 + }, + { + "epoch": 1.75, + "learning_rate": 8.313776618861366e-06, + "loss": 0.4799, + "step": 21512 + }, + { + "epoch": 1.75, + "learning_rate": 8.3132333767927e-06, + "loss": 0.3575, + "step": 21513 + }, + { + "epoch": 1.75, + "learning_rate": 8.312690134724034e-06, + "loss": 0.2875, + "step": 21514 + }, + { + "epoch": 1.75, + "learning_rate": 8.312146892655369e-06, + "loss": 0.3109, + "step": 21515 + }, + { + "epoch": 1.75, + "learning_rate": 8.311603650586703e-06, + "loss": 0.3853, + "step": 21516 + }, + { + "epoch": 1.75, + "learning_rate": 8.311060408518037e-06, + "loss": 0.1999, + "step": 21517 + }, + { + "epoch": 1.75, + "learning_rate": 8.31051716644937e-06, + "loss": 0.3208, + "step": 21518 + }, + { + "epoch": 1.75, + "learning_rate": 8.309973924380704e-06, + "loss": 0.2786, + "step": 21519 + }, + { + "epoch": 1.75, + "learning_rate": 8.309430682312038e-06, + "loss": 0.2991, + "step": 21520 + }, + { + "epoch": 1.75, + "learning_rate": 8.308887440243372e-06, + "loss": 0.3116, + "step": 21521 + }, + { + "epoch": 1.75, + "learning_rate": 8.308344198174707e-06, + "loss": 0.1398, + "step": 21522 + }, + { + "epoch": 1.75, + "learning_rate": 8.307800956106041e-06, + "loss": 0.4967, + "step": 21523 + }, + { + "epoch": 1.75, + "learning_rate": 8.307257714037375e-06, + "loss": 0.3715, + "step": 21524 + }, + { + "epoch": 1.75, + "learning_rate": 8.30671447196871e-06, + "loss": 0.3531, + "step": 21525 + }, + { + "epoch": 1.75, + "learning_rate": 8.306171229900044e-06, + "loss": 0.6167, + "step": 21526 + }, + { + "epoch": 1.75, + "learning_rate": 8.305627987831378e-06, + "loss": 0.3649, + "step": 21527 + }, + { + "epoch": 1.75, + "learning_rate": 8.305084745762712e-06, + "loss": 0.6294, + "step": 21528 + }, + { + "epoch": 1.75, + "learning_rate": 8.304541503694046e-06, + "loss": 0.3374, + "step": 21529 + }, + { + "epoch": 1.75, + "learning_rate": 8.30399826162538e-06, + "loss": 0.3372, + "step": 21530 + }, + { + "epoch": 1.75, + "learning_rate": 8.303455019556715e-06, + "loss": 0.5011, + "step": 21531 + }, + { + "epoch": 1.75, + "learning_rate": 8.302911777488049e-06, + "loss": 0.2231, + "step": 21532 + }, + { + "epoch": 1.75, + "learning_rate": 8.302368535419383e-06, + "loss": 0.5204, + "step": 21533 + }, + { + "epoch": 1.75, + "learning_rate": 8.301825293350717e-06, + "loss": 0.5375, + "step": 21534 + }, + { + "epoch": 1.75, + "learning_rate": 8.301282051282052e-06, + "loss": 0.4639, + "step": 21535 + }, + { + "epoch": 1.75, + "learning_rate": 8.300738809213386e-06, + "loss": 0.3429, + "step": 21536 + }, + { + "epoch": 1.75, + "learning_rate": 8.30019556714472e-06, + "loss": 0.3729, + "step": 21537 + }, + { + "epoch": 1.76, + "learning_rate": 8.299652325076054e-06, + "loss": 0.2303, + "step": 21538 + }, + { + "epoch": 1.76, + "learning_rate": 8.299109083007389e-06, + "loss": 0.1922, + "step": 21539 + }, + { + "epoch": 1.76, + "learning_rate": 8.298565840938723e-06, + "loss": 0.1496, + "step": 21540 + }, + { + "epoch": 1.76, + "learning_rate": 8.298022598870057e-06, + "loss": 0.3212, + "step": 21541 + }, + { + "epoch": 1.76, + "learning_rate": 8.297479356801391e-06, + "loss": 0.4339, + "step": 21542 + }, + { + "epoch": 1.76, + "learning_rate": 8.296936114732725e-06, + "loss": 0.4161, + "step": 21543 + }, + { + "epoch": 1.76, + "learning_rate": 8.29639287266406e-06, + "loss": 0.1724, + "step": 21544 + }, + { + "epoch": 1.76, + "learning_rate": 8.295849630595394e-06, + "loss": 0.3111, + "step": 21545 + }, + { + "epoch": 1.76, + "learning_rate": 8.295306388526728e-06, + "loss": 0.2168, + "step": 21546 + }, + { + "epoch": 1.76, + "learning_rate": 8.294763146458062e-06, + "loss": 0.5358, + "step": 21547 + }, + { + "epoch": 1.76, + "learning_rate": 8.294219904389397e-06, + "loss": 0.4698, + "step": 21548 + }, + { + "epoch": 1.76, + "learning_rate": 8.293676662320731e-06, + "loss": 0.2923, + "step": 21549 + }, + { + "epoch": 1.76, + "learning_rate": 8.293133420252065e-06, + "loss": 0.42, + "step": 21550 + }, + { + "epoch": 1.76, + "learning_rate": 8.2925901781834e-06, + "loss": 0.3946, + "step": 21551 + }, + { + "epoch": 1.76, + "learning_rate": 8.292046936114734e-06, + "loss": 0.3201, + "step": 21552 + }, + { + "epoch": 1.76, + "learning_rate": 8.291503694046068e-06, + "loss": 0.4113, + "step": 21553 + }, + { + "epoch": 1.76, + "learning_rate": 8.290960451977402e-06, + "loss": 0.3021, + "step": 21554 + }, + { + "epoch": 1.76, + "learning_rate": 8.290417209908736e-06, + "loss": 0.3939, + "step": 21555 + }, + { + "epoch": 1.76, + "learning_rate": 8.28987396784007e-06, + "loss": 0.3951, + "step": 21556 + }, + { + "epoch": 1.76, + "learning_rate": 8.289330725771405e-06, + "loss": 0.2551, + "step": 21557 + }, + { + "epoch": 1.76, + "learning_rate": 8.288787483702739e-06, + "loss": 0.1795, + "step": 21558 + }, + { + "epoch": 1.76, + "learning_rate": 8.288244241634073e-06, + "loss": 0.35, + "step": 21559 + }, + { + "epoch": 1.76, + "learning_rate": 8.287700999565407e-06, + "loss": 0.2765, + "step": 21560 + }, + { + "epoch": 1.76, + "learning_rate": 8.287157757496742e-06, + "loss": 0.252, + "step": 21561 + }, + { + "epoch": 1.76, + "learning_rate": 8.286614515428076e-06, + "loss": 0.2542, + "step": 21562 + }, + { + "epoch": 1.76, + "learning_rate": 8.28607127335941e-06, + "loss": 0.348, + "step": 21563 + }, + { + "epoch": 1.76, + "learning_rate": 8.285528031290744e-06, + "loss": 0.2962, + "step": 21564 + }, + { + "epoch": 1.76, + "learning_rate": 8.284984789222079e-06, + "loss": 0.4864, + "step": 21565 + }, + { + "epoch": 1.76, + "learning_rate": 8.284441547153413e-06, + "loss": 0.2944, + "step": 21566 + }, + { + "epoch": 1.76, + "learning_rate": 8.283898305084747e-06, + "loss": 0.5, + "step": 21567 + }, + { + "epoch": 1.76, + "learning_rate": 8.283355063016081e-06, + "loss": 0.5591, + "step": 21568 + }, + { + "epoch": 1.76, + "learning_rate": 8.282811820947415e-06, + "loss": 0.4921, + "step": 21569 + }, + { + "epoch": 1.76, + "learning_rate": 8.28226857887875e-06, + "loss": 0.1439, + "step": 21570 + }, + { + "epoch": 1.76, + "learning_rate": 8.281725336810084e-06, + "loss": 0.2134, + "step": 21571 + }, + { + "epoch": 1.76, + "learning_rate": 8.281182094741418e-06, + "loss": 0.5391, + "step": 21572 + }, + { + "epoch": 1.76, + "learning_rate": 8.280638852672752e-06, + "loss": 0.2995, + "step": 21573 + }, + { + "epoch": 1.76, + "learning_rate": 8.280095610604087e-06, + "loss": 0.4184, + "step": 21574 + }, + { + "epoch": 1.76, + "learning_rate": 8.27955236853542e-06, + "loss": 0.2587, + "step": 21575 + }, + { + "epoch": 1.76, + "learning_rate": 8.279009126466753e-06, + "loss": 0.208, + "step": 21576 + }, + { + "epoch": 1.76, + "learning_rate": 8.278465884398088e-06, + "loss": 0.4881, + "step": 21577 + }, + { + "epoch": 1.76, + "learning_rate": 8.277922642329422e-06, + "loss": 0.4897, + "step": 21578 + }, + { + "epoch": 1.76, + "learning_rate": 8.277379400260756e-06, + "loss": 0.3127, + "step": 21579 + }, + { + "epoch": 1.76, + "learning_rate": 8.27683615819209e-06, + "loss": 0.1861, + "step": 21580 + }, + { + "epoch": 1.76, + "learning_rate": 8.276292916123425e-06, + "loss": 0.4232, + "step": 21581 + }, + { + "epoch": 1.76, + "learning_rate": 8.275749674054759e-06, + "loss": 0.1716, + "step": 21582 + }, + { + "epoch": 1.76, + "learning_rate": 8.275206431986093e-06, + "loss": 0.4231, + "step": 21583 + }, + { + "epoch": 1.76, + "learning_rate": 8.274663189917427e-06, + "loss": 0.1807, + "step": 21584 + }, + { + "epoch": 1.76, + "learning_rate": 8.274119947848761e-06, + "loss": 0.1692, + "step": 21585 + }, + { + "epoch": 1.76, + "learning_rate": 8.273576705780096e-06, + "loss": 0.4121, + "step": 21586 + }, + { + "epoch": 1.76, + "learning_rate": 8.27303346371143e-06, + "loss": 0.3707, + "step": 21587 + }, + { + "epoch": 1.76, + "learning_rate": 8.272490221642764e-06, + "loss": 0.1817, + "step": 21588 + }, + { + "epoch": 1.76, + "learning_rate": 8.271946979574098e-06, + "loss": 0.5145, + "step": 21589 + }, + { + "epoch": 1.76, + "learning_rate": 8.271403737505433e-06, + "loss": 0.4415, + "step": 21590 + }, + { + "epoch": 1.76, + "learning_rate": 8.270860495436769e-06, + "loss": 0.3739, + "step": 21591 + }, + { + "epoch": 1.76, + "learning_rate": 8.270317253368103e-06, + "loss": 0.4319, + "step": 21592 + }, + { + "epoch": 1.76, + "learning_rate": 8.269774011299437e-06, + "loss": 0.2418, + "step": 21593 + }, + { + "epoch": 1.76, + "learning_rate": 8.26923076923077e-06, + "loss": 0.4507, + "step": 21594 + }, + { + "epoch": 1.76, + "learning_rate": 8.268687527162104e-06, + "loss": 0.4767, + "step": 21595 + }, + { + "epoch": 1.76, + "learning_rate": 8.268144285093438e-06, + "loss": 0.3121, + "step": 21596 + }, + { + "epoch": 1.76, + "learning_rate": 8.267601043024772e-06, + "loss": 0.4956, + "step": 21597 + }, + { + "epoch": 1.76, + "learning_rate": 8.267057800956106e-06, + "loss": 0.1989, + "step": 21598 + }, + { + "epoch": 1.76, + "learning_rate": 8.26651455888744e-06, + "loss": 0.4252, + "step": 21599 + }, + { + "epoch": 1.76, + "learning_rate": 8.265971316818775e-06, + "loss": 0.3819, + "step": 21600 + }, + { + "epoch": 1.76, + "learning_rate": 8.26542807475011e-06, + "loss": 0.4554, + "step": 21601 + }, + { + "epoch": 1.76, + "learning_rate": 8.264884832681443e-06, + "loss": 0.2693, + "step": 21602 + }, + { + "epoch": 1.76, + "learning_rate": 8.264341590612778e-06, + "loss": 0.242, + "step": 21603 + }, + { + "epoch": 1.76, + "learning_rate": 8.263798348544112e-06, + "loss": 0.3393, + "step": 21604 + }, + { + "epoch": 1.76, + "learning_rate": 8.263255106475446e-06, + "loss": 0.2822, + "step": 21605 + }, + { + "epoch": 1.76, + "learning_rate": 8.26271186440678e-06, + "loss": 0.2695, + "step": 21606 + }, + { + "epoch": 1.76, + "learning_rate": 8.262168622338115e-06, + "loss": 0.5866, + "step": 21607 + }, + { + "epoch": 1.76, + "learning_rate": 8.261625380269449e-06, + "loss": 0.213, + "step": 21608 + }, + { + "epoch": 1.76, + "learning_rate": 8.261082138200783e-06, + "loss": 0.1543, + "step": 21609 + }, + { + "epoch": 1.76, + "learning_rate": 8.260538896132117e-06, + "loss": 0.2316, + "step": 21610 + }, + { + "epoch": 1.76, + "learning_rate": 8.259995654063451e-06, + "loss": 0.4253, + "step": 21611 + }, + { + "epoch": 1.76, + "learning_rate": 8.259452411994786e-06, + "loss": 0.5138, + "step": 21612 + }, + { + "epoch": 1.76, + "learning_rate": 8.25890916992612e-06, + "loss": 0.2972, + "step": 21613 + }, + { + "epoch": 1.76, + "learning_rate": 8.258365927857454e-06, + "loss": 0.2355, + "step": 21614 + }, + { + "epoch": 1.76, + "learning_rate": 8.257822685788788e-06, + "loss": 0.2995, + "step": 21615 + }, + { + "epoch": 1.76, + "learning_rate": 8.257279443720123e-06, + "loss": 0.1462, + "step": 21616 + }, + { + "epoch": 1.76, + "learning_rate": 8.256736201651457e-06, + "loss": 0.2652, + "step": 21617 + }, + { + "epoch": 1.76, + "learning_rate": 8.256192959582791e-06, + "loss": 0.1017, + "step": 21618 + }, + { + "epoch": 1.76, + "learning_rate": 8.255649717514125e-06, + "loss": 0.1602, + "step": 21619 + }, + { + "epoch": 1.76, + "learning_rate": 8.25510647544546e-06, + "loss": 0.4944, + "step": 21620 + }, + { + "epoch": 1.76, + "learning_rate": 8.254563233376794e-06, + "loss": 0.3873, + "step": 21621 + }, + { + "epoch": 1.76, + "learning_rate": 8.254019991308128e-06, + "loss": 0.2897, + "step": 21622 + }, + { + "epoch": 1.76, + "learning_rate": 8.253476749239462e-06, + "loss": 0.3675, + "step": 21623 + }, + { + "epoch": 1.76, + "learning_rate": 8.252933507170796e-06, + "loss": 0.2409, + "step": 21624 + }, + { + "epoch": 1.76, + "learning_rate": 8.25239026510213e-06, + "loss": 0.1769, + "step": 21625 + }, + { + "epoch": 1.76, + "learning_rate": 8.251847023033465e-06, + "loss": 0.1277, + "step": 21626 + }, + { + "epoch": 1.76, + "learning_rate": 8.2513037809648e-06, + "loss": 0.4917, + "step": 21627 + }, + { + "epoch": 1.76, + "learning_rate": 8.250760538896133e-06, + "loss": 0.5119, + "step": 21628 + }, + { + "epoch": 1.76, + "learning_rate": 8.250217296827468e-06, + "loss": 0.3245, + "step": 21629 + }, + { + "epoch": 1.76, + "learning_rate": 8.249674054758802e-06, + "loss": 0.6044, + "step": 21630 + }, + { + "epoch": 1.76, + "learning_rate": 8.249130812690136e-06, + "loss": 0.3585, + "step": 21631 + }, + { + "epoch": 1.76, + "learning_rate": 8.248587570621469e-06, + "loss": 0.2309, + "step": 21632 + }, + { + "epoch": 1.76, + "learning_rate": 8.248044328552803e-06, + "loss": 0.3638, + "step": 21633 + }, + { + "epoch": 1.76, + "learning_rate": 8.247501086484137e-06, + "loss": 0.2288, + "step": 21634 + }, + { + "epoch": 1.76, + "learning_rate": 8.246957844415471e-06, + "loss": 0.2174, + "step": 21635 + }, + { + "epoch": 1.76, + "learning_rate": 8.246414602346806e-06, + "loss": 0.456, + "step": 21636 + }, + { + "epoch": 1.76, + "learning_rate": 8.24587136027814e-06, + "loss": 0.4073, + "step": 21637 + }, + { + "epoch": 1.76, + "learning_rate": 8.245328118209474e-06, + "loss": 0.3309, + "step": 21638 + }, + { + "epoch": 1.76, + "learning_rate": 8.244784876140808e-06, + "loss": 0.3496, + "step": 21639 + }, + { + "epoch": 1.76, + "learning_rate": 8.244241634072142e-06, + "loss": 0.4692, + "step": 21640 + }, + { + "epoch": 1.76, + "learning_rate": 8.243698392003477e-06, + "loss": 0.2864, + "step": 21641 + }, + { + "epoch": 1.76, + "learning_rate": 8.243155149934811e-06, + "loss": 0.4962, + "step": 21642 + }, + { + "epoch": 1.76, + "learning_rate": 8.242611907866145e-06, + "loss": 0.4689, + "step": 21643 + }, + { + "epoch": 1.76, + "learning_rate": 8.24206866579748e-06, + "loss": 0.0356, + "step": 21644 + }, + { + "epoch": 1.76, + "learning_rate": 8.241525423728815e-06, + "loss": 0.4232, + "step": 21645 + }, + { + "epoch": 1.76, + "learning_rate": 8.24098218166015e-06, + "loss": 0.1387, + "step": 21646 + }, + { + "epoch": 1.76, + "learning_rate": 8.240438939591484e-06, + "loss": 0.4848, + "step": 21647 + }, + { + "epoch": 1.76, + "learning_rate": 8.239895697522818e-06, + "loss": 0.1213, + "step": 21648 + }, + { + "epoch": 1.76, + "learning_rate": 8.239352455454152e-06, + "loss": 0.3811, + "step": 21649 + }, + { + "epoch": 1.76, + "learning_rate": 8.238809213385486e-06, + "loss": 0.4522, + "step": 21650 + }, + { + "epoch": 1.76, + "learning_rate": 8.238265971316819e-06, + "loss": 0.4166, + "step": 21651 + }, + { + "epoch": 1.76, + "learning_rate": 8.237722729248153e-06, + "loss": 0.1476, + "step": 21652 + }, + { + "epoch": 1.76, + "learning_rate": 8.237179487179487e-06, + "loss": 0.3204, + "step": 21653 + }, + { + "epoch": 1.76, + "learning_rate": 8.236636245110822e-06, + "loss": 0.4551, + "step": 21654 + }, + { + "epoch": 1.76, + "learning_rate": 8.236093003042156e-06, + "loss": 0.4031, + "step": 21655 + }, + { + "epoch": 1.76, + "learning_rate": 8.23554976097349e-06, + "loss": 0.217, + "step": 21656 + }, + { + "epoch": 1.76, + "learning_rate": 8.235006518904824e-06, + "loss": 0.1954, + "step": 21657 + }, + { + "epoch": 1.76, + "learning_rate": 8.234463276836159e-06, + "loss": 0.2448, + "step": 21658 + }, + { + "epoch": 1.76, + "learning_rate": 8.233920034767493e-06, + "loss": 0.5676, + "step": 21659 + }, + { + "epoch": 1.76, + "learning_rate": 8.233376792698827e-06, + "loss": 0.1804, + "step": 21660 + }, + { + "epoch": 1.77, + "learning_rate": 8.232833550630161e-06, + "loss": 0.2887, + "step": 21661 + }, + { + "epoch": 1.77, + "learning_rate": 8.232290308561496e-06, + "loss": 0.3365, + "step": 21662 + }, + { + "epoch": 1.77, + "learning_rate": 8.23174706649283e-06, + "loss": 0.1555, + "step": 21663 + }, + { + "epoch": 1.77, + "learning_rate": 8.231203824424164e-06, + "loss": 0.4523, + "step": 21664 + }, + { + "epoch": 1.77, + "learning_rate": 8.230660582355498e-06, + "loss": 0.6029, + "step": 21665 + }, + { + "epoch": 1.77, + "learning_rate": 8.230117340286832e-06, + "loss": 0.3289, + "step": 21666 + }, + { + "epoch": 1.77, + "learning_rate": 8.229574098218167e-06, + "loss": 0.4078, + "step": 21667 + }, + { + "epoch": 1.77, + "learning_rate": 8.229030856149501e-06, + "loss": 0.3724, + "step": 21668 + }, + { + "epoch": 1.77, + "learning_rate": 8.228487614080835e-06, + "loss": 0.2397, + "step": 21669 + }, + { + "epoch": 1.77, + "learning_rate": 8.22794437201217e-06, + "loss": 0.197, + "step": 21670 + }, + { + "epoch": 1.77, + "learning_rate": 8.227401129943504e-06, + "loss": 0.4609, + "step": 21671 + }, + { + "epoch": 1.77, + "learning_rate": 8.226857887874838e-06, + "loss": 0.3544, + "step": 21672 + }, + { + "epoch": 1.77, + "learning_rate": 8.226314645806172e-06, + "loss": 0.2655, + "step": 21673 + }, + { + "epoch": 1.77, + "learning_rate": 8.225771403737506e-06, + "loss": 0.3365, + "step": 21674 + }, + { + "epoch": 1.77, + "learning_rate": 8.22522816166884e-06, + "loss": 0.0949, + "step": 21675 + }, + { + "epoch": 1.77, + "learning_rate": 8.224684919600175e-06, + "loss": 0.4896, + "step": 21676 + }, + { + "epoch": 1.77, + "learning_rate": 8.224141677531509e-06, + "loss": 0.0937, + "step": 21677 + }, + { + "epoch": 1.77, + "learning_rate": 8.223598435462843e-06, + "loss": 0.1007, + "step": 21678 + }, + { + "epoch": 1.77, + "learning_rate": 8.223055193394177e-06, + "loss": 0.1843, + "step": 21679 + }, + { + "epoch": 1.77, + "learning_rate": 8.222511951325512e-06, + "loss": 0.4246, + "step": 21680 + }, + { + "epoch": 1.77, + "learning_rate": 8.221968709256846e-06, + "loss": 0.3135, + "step": 21681 + }, + { + "epoch": 1.77, + "learning_rate": 8.22142546718818e-06, + "loss": 0.22, + "step": 21682 + }, + { + "epoch": 1.77, + "learning_rate": 8.220882225119514e-06, + "loss": 0.5077, + "step": 21683 + }, + { + "epoch": 1.77, + "learning_rate": 8.220338983050849e-06, + "loss": 0.277, + "step": 21684 + }, + { + "epoch": 1.77, + "learning_rate": 8.219795740982183e-06, + "loss": 0.3951, + "step": 21685 + }, + { + "epoch": 1.77, + "learning_rate": 8.219252498913517e-06, + "loss": 0.4249, + "step": 21686 + }, + { + "epoch": 1.77, + "learning_rate": 8.218709256844851e-06, + "loss": 0.2697, + "step": 21687 + }, + { + "epoch": 1.77, + "learning_rate": 8.218166014776186e-06, + "loss": 0.6306, + "step": 21688 + }, + { + "epoch": 1.77, + "learning_rate": 8.217622772707518e-06, + "loss": 0.1728, + "step": 21689 + }, + { + "epoch": 1.77, + "learning_rate": 8.217079530638852e-06, + "loss": 0.3817, + "step": 21690 + }, + { + "epoch": 1.77, + "learning_rate": 8.216536288570187e-06, + "loss": 0.6607, + "step": 21691 + }, + { + "epoch": 1.77, + "learning_rate": 8.21599304650152e-06, + "loss": 0.2234, + "step": 21692 + }, + { + "epoch": 1.77, + "learning_rate": 8.215449804432855e-06, + "loss": 0.0704, + "step": 21693 + }, + { + "epoch": 1.77, + "learning_rate": 8.21490656236419e-06, + "loss": 0.3092, + "step": 21694 + }, + { + "epoch": 1.77, + "learning_rate": 8.214363320295523e-06, + "loss": 0.3749, + "step": 21695 + }, + { + "epoch": 1.77, + "learning_rate": 8.213820078226858e-06, + "loss": 0.2692, + "step": 21696 + }, + { + "epoch": 1.77, + "learning_rate": 8.213276836158192e-06, + "loss": 0.4645, + "step": 21697 + }, + { + "epoch": 1.77, + "learning_rate": 8.212733594089526e-06, + "loss": 0.2665, + "step": 21698 + }, + { + "epoch": 1.77, + "learning_rate": 8.212190352020862e-06, + "loss": 0.3609, + "step": 21699 + }, + { + "epoch": 1.77, + "learning_rate": 8.211647109952196e-06, + "loss": 0.3069, + "step": 21700 + }, + { + "epoch": 1.77, + "learning_rate": 8.21110386788353e-06, + "loss": 0.5037, + "step": 21701 + }, + { + "epoch": 1.77, + "learning_rate": 8.210560625814865e-06, + "loss": 0.6169, + "step": 21702 + }, + { + "epoch": 1.77, + "learning_rate": 8.210017383746199e-06, + "loss": 0.365, + "step": 21703 + }, + { + "epoch": 1.77, + "learning_rate": 8.209474141677533e-06, + "loss": 0.2707, + "step": 21704 + }, + { + "epoch": 1.77, + "learning_rate": 8.208930899608867e-06, + "loss": 0.3555, + "step": 21705 + }, + { + "epoch": 1.77, + "learning_rate": 8.208387657540202e-06, + "loss": 0.3647, + "step": 21706 + }, + { + "epoch": 1.77, + "learning_rate": 8.207844415471536e-06, + "loss": 0.2354, + "step": 21707 + }, + { + "epoch": 1.77, + "learning_rate": 8.207301173402868e-06, + "loss": 0.5413, + "step": 21708 + }, + { + "epoch": 1.77, + "learning_rate": 8.206757931334203e-06, + "loss": 0.1941, + "step": 21709 + }, + { + "epoch": 1.77, + "learning_rate": 8.206214689265537e-06, + "loss": 0.3617, + "step": 21710 + }, + { + "epoch": 1.77, + "learning_rate": 8.205671447196871e-06, + "loss": 0.4408, + "step": 21711 + }, + { + "epoch": 1.77, + "learning_rate": 8.205128205128205e-06, + "loss": 0.5744, + "step": 21712 + }, + { + "epoch": 1.77, + "learning_rate": 8.20458496305954e-06, + "loss": 0.3507, + "step": 21713 + }, + { + "epoch": 1.77, + "learning_rate": 8.204041720990874e-06, + "loss": 0.2645, + "step": 21714 + }, + { + "epoch": 1.77, + "learning_rate": 8.203498478922208e-06, + "loss": 0.2376, + "step": 21715 + }, + { + "epoch": 1.77, + "learning_rate": 8.202955236853542e-06, + "loss": 0.3308, + "step": 21716 + }, + { + "epoch": 1.77, + "learning_rate": 8.202411994784877e-06, + "loss": 0.2621, + "step": 21717 + }, + { + "epoch": 1.77, + "learning_rate": 8.20186875271621e-06, + "loss": 0.1508, + "step": 21718 + }, + { + "epoch": 1.77, + "learning_rate": 8.201325510647545e-06, + "loss": 0.3462, + "step": 21719 + }, + { + "epoch": 1.77, + "learning_rate": 8.20078226857888e-06, + "loss": 0.5821, + "step": 21720 + }, + { + "epoch": 1.77, + "learning_rate": 8.200239026510213e-06, + "loss": 0.4991, + "step": 21721 + }, + { + "epoch": 1.77, + "learning_rate": 8.199695784441548e-06, + "loss": 0.5569, + "step": 21722 + }, + { + "epoch": 1.77, + "learning_rate": 8.199152542372882e-06, + "loss": 0.2805, + "step": 21723 + }, + { + "epoch": 1.77, + "learning_rate": 8.198609300304216e-06, + "loss": 0.2639, + "step": 21724 + }, + { + "epoch": 1.77, + "learning_rate": 8.19806605823555e-06, + "loss": 0.6018, + "step": 21725 + }, + { + "epoch": 1.77, + "learning_rate": 8.197522816166885e-06, + "loss": 0.3129, + "step": 21726 + }, + { + "epoch": 1.77, + "learning_rate": 8.196979574098219e-06, + "loss": 0.2888, + "step": 21727 + }, + { + "epoch": 1.77, + "learning_rate": 8.196436332029553e-06, + "loss": 0.2699, + "step": 21728 + }, + { + "epoch": 1.77, + "learning_rate": 8.195893089960887e-06, + "loss": 0.2754, + "step": 21729 + }, + { + "epoch": 1.77, + "learning_rate": 8.195349847892222e-06, + "loss": 0.4761, + "step": 21730 + }, + { + "epoch": 1.77, + "learning_rate": 8.194806605823556e-06, + "loss": 0.3524, + "step": 21731 + }, + { + "epoch": 1.77, + "learning_rate": 8.19426336375489e-06, + "loss": 0.3694, + "step": 21732 + }, + { + "epoch": 1.77, + "learning_rate": 8.193720121686224e-06, + "loss": 0.2335, + "step": 21733 + }, + { + "epoch": 1.77, + "learning_rate": 8.193176879617558e-06, + "loss": 0.4708, + "step": 21734 + }, + { + "epoch": 1.77, + "learning_rate": 8.192633637548893e-06, + "loss": 0.2138, + "step": 21735 + }, + { + "epoch": 1.77, + "learning_rate": 8.192090395480227e-06, + "loss": 0.3705, + "step": 21736 + }, + { + "epoch": 1.77, + "learning_rate": 8.191547153411561e-06, + "loss": 0.4271, + "step": 21737 + }, + { + "epoch": 1.77, + "learning_rate": 8.191003911342895e-06, + "loss": 0.4821, + "step": 21738 + }, + { + "epoch": 1.77, + "learning_rate": 8.19046066927423e-06, + "loss": 0.4909, + "step": 21739 + }, + { + "epoch": 1.77, + "learning_rate": 8.189917427205564e-06, + "loss": 0.3628, + "step": 21740 + }, + { + "epoch": 1.77, + "learning_rate": 8.189374185136898e-06, + "loss": 0.3562, + "step": 21741 + }, + { + "epoch": 1.77, + "learning_rate": 8.188830943068232e-06, + "loss": 0.2033, + "step": 21742 + }, + { + "epoch": 1.77, + "learning_rate": 8.188287700999567e-06, + "loss": 0.212, + "step": 21743 + }, + { + "epoch": 1.77, + "learning_rate": 8.1877444589309e-06, + "loss": 0.2861, + "step": 21744 + }, + { + "epoch": 1.77, + "learning_rate": 8.187201216862235e-06, + "loss": 0.2681, + "step": 21745 + }, + { + "epoch": 1.77, + "learning_rate": 8.186657974793568e-06, + "loss": 0.4649, + "step": 21746 + }, + { + "epoch": 1.77, + "learning_rate": 8.186114732724902e-06, + "loss": 0.2539, + "step": 21747 + }, + { + "epoch": 1.77, + "learning_rate": 8.185571490656236e-06, + "loss": 0.5075, + "step": 21748 + }, + { + "epoch": 1.77, + "learning_rate": 8.18502824858757e-06, + "loss": 0.3764, + "step": 21749 + }, + { + "epoch": 1.77, + "learning_rate": 8.184485006518904e-06, + "loss": 0.4588, + "step": 21750 + }, + { + "epoch": 1.77, + "eval_accuracy": 0.8385124808965868, + "eval_loss": 0.42854541540145874, + "eval_runtime": 22.3707, + "eval_samples_per_second": 438.743, + "eval_steps_per_second": 3.442, + "step": 21750 + }, + { + "epoch": 1.77, + "learning_rate": 8.183941764450239e-06, + "loss": 0.417, + "step": 21751 + }, + { + "epoch": 1.77, + "learning_rate": 8.183398522381573e-06, + "loss": 0.2413, + "step": 21752 + }, + { + "epoch": 1.77, + "learning_rate": 8.182855280312909e-06, + "loss": 0.4657, + "step": 21753 + }, + { + "epoch": 1.77, + "learning_rate": 8.182312038244243e-06, + "loss": 0.5691, + "step": 21754 + }, + { + "epoch": 1.77, + "learning_rate": 8.181768796175577e-06, + "loss": 0.1678, + "step": 21755 + }, + { + "epoch": 1.77, + "learning_rate": 8.181225554106912e-06, + "loss": 0.1704, + "step": 21756 + }, + { + "epoch": 1.77, + "learning_rate": 8.180682312038246e-06, + "loss": 0.3562, + "step": 21757 + }, + { + "epoch": 1.77, + "learning_rate": 8.18013906996958e-06, + "loss": 0.3824, + "step": 21758 + }, + { + "epoch": 1.77, + "learning_rate": 8.179595827900914e-06, + "loss": 0.4201, + "step": 21759 + }, + { + "epoch": 1.77, + "learning_rate": 8.179052585832248e-06, + "loss": 0.3549, + "step": 21760 + }, + { + "epoch": 1.77, + "learning_rate": 8.178509343763583e-06, + "loss": 0.2659, + "step": 21761 + }, + { + "epoch": 1.77, + "learning_rate": 8.177966101694917e-06, + "loss": 0.18, + "step": 21762 + }, + { + "epoch": 1.77, + "learning_rate": 8.177422859626251e-06, + "loss": 0.3005, + "step": 21763 + }, + { + "epoch": 1.77, + "learning_rate": 8.176879617557585e-06, + "loss": 0.4163, + "step": 21764 + }, + { + "epoch": 1.77, + "learning_rate": 8.176336375488918e-06, + "loss": 0.3025, + "step": 21765 + }, + { + "epoch": 1.77, + "learning_rate": 8.175793133420252e-06, + "loss": 0.2099, + "step": 21766 + }, + { + "epoch": 1.77, + "learning_rate": 8.175249891351586e-06, + "loss": 0.2378, + "step": 21767 + }, + { + "epoch": 1.77, + "learning_rate": 8.17470664928292e-06, + "loss": 0.4925, + "step": 21768 + }, + { + "epoch": 1.77, + "learning_rate": 8.174163407214255e-06, + "loss": 0.2087, + "step": 21769 + }, + { + "epoch": 1.77, + "learning_rate": 8.173620165145589e-06, + "loss": 0.2634, + "step": 21770 + }, + { + "epoch": 1.77, + "learning_rate": 8.173076923076923e-06, + "loss": 0.3873, + "step": 21771 + }, + { + "epoch": 1.77, + "learning_rate": 8.172533681008258e-06, + "loss": 0.4542, + "step": 21772 + }, + { + "epoch": 1.77, + "learning_rate": 8.171990438939592e-06, + "loss": 0.3048, + "step": 21773 + }, + { + "epoch": 1.77, + "learning_rate": 8.171447196870926e-06, + "loss": 0.2357, + "step": 21774 + }, + { + "epoch": 1.77, + "learning_rate": 8.17090395480226e-06, + "loss": 0.3593, + "step": 21775 + }, + { + "epoch": 1.77, + "learning_rate": 8.170360712733594e-06, + "loss": 0.1853, + "step": 21776 + }, + { + "epoch": 1.77, + "learning_rate": 8.169817470664929e-06, + "loss": 0.15, + "step": 21777 + }, + { + "epoch": 1.77, + "learning_rate": 8.169274228596263e-06, + "loss": 0.2557, + "step": 21778 + }, + { + "epoch": 1.77, + "learning_rate": 8.168730986527597e-06, + "loss": 0.5896, + "step": 21779 + }, + { + "epoch": 1.77, + "learning_rate": 8.168187744458931e-06, + "loss": 0.2552, + "step": 21780 + }, + { + "epoch": 1.77, + "learning_rate": 8.167644502390266e-06, + "loss": 0.4363, + "step": 21781 + }, + { + "epoch": 1.77, + "learning_rate": 8.1671012603216e-06, + "loss": 0.155, + "step": 21782 + }, + { + "epoch": 1.78, + "learning_rate": 8.166558018252934e-06, + "loss": 0.2362, + "step": 21783 + }, + { + "epoch": 1.78, + "learning_rate": 8.166014776184268e-06, + "loss": 0.2398, + "step": 21784 + }, + { + "epoch": 1.78, + "learning_rate": 8.165471534115603e-06, + "loss": 0.5484, + "step": 21785 + }, + { + "epoch": 1.78, + "learning_rate": 8.164928292046937e-06, + "loss": 0.3388, + "step": 21786 + }, + { + "epoch": 1.78, + "learning_rate": 8.164385049978271e-06, + "loss": 0.4819, + "step": 21787 + }, + { + "epoch": 1.78, + "learning_rate": 8.163841807909605e-06, + "loss": 0.3881, + "step": 21788 + }, + { + "epoch": 1.78, + "learning_rate": 8.16329856584094e-06, + "loss": 0.2458, + "step": 21789 + }, + { + "epoch": 1.78, + "learning_rate": 8.162755323772274e-06, + "loss": 0.3055, + "step": 21790 + }, + { + "epoch": 1.78, + "learning_rate": 8.162212081703608e-06, + "loss": 0.2635, + "step": 21791 + }, + { + "epoch": 1.78, + "learning_rate": 8.161668839634942e-06, + "loss": 0.3086, + "step": 21792 + }, + { + "epoch": 1.78, + "learning_rate": 8.161125597566276e-06, + "loss": 0.348, + "step": 21793 + }, + { + "epoch": 1.78, + "learning_rate": 8.16058235549761e-06, + "loss": 0.317, + "step": 21794 + }, + { + "epoch": 1.78, + "learning_rate": 8.160039113428945e-06, + "loss": 0.1799, + "step": 21795 + }, + { + "epoch": 1.78, + "learning_rate": 8.159495871360279e-06, + "loss": 0.4524, + "step": 21796 + }, + { + "epoch": 1.78, + "learning_rate": 8.158952629291613e-06, + "loss": 0.9152, + "step": 21797 + }, + { + "epoch": 1.78, + "learning_rate": 8.158409387222947e-06, + "loss": 0.3562, + "step": 21798 + }, + { + "epoch": 1.78, + "learning_rate": 8.157866145154282e-06, + "loss": 0.2142, + "step": 21799 + }, + { + "epoch": 1.78, + "learning_rate": 8.157322903085616e-06, + "loss": 0.522, + "step": 21800 + }, + { + "epoch": 1.78, + "learning_rate": 8.15677966101695e-06, + "loss": 0.2263, + "step": 21801 + }, + { + "epoch": 1.78, + "learning_rate": 8.156236418948284e-06, + "loss": 0.2772, + "step": 21802 + }, + { + "epoch": 1.78, + "learning_rate": 8.155693176879617e-06, + "loss": 0.3016, + "step": 21803 + }, + { + "epoch": 1.78, + "learning_rate": 8.155149934810951e-06, + "loss": 0.2866, + "step": 21804 + }, + { + "epoch": 1.78, + "learning_rate": 8.154606692742285e-06, + "loss": 0.2847, + "step": 21805 + }, + { + "epoch": 1.78, + "learning_rate": 8.15406345067362e-06, + "loss": 0.2143, + "step": 21806 + }, + { + "epoch": 1.78, + "learning_rate": 8.153520208604956e-06, + "loss": 0.4383, + "step": 21807 + }, + { + "epoch": 1.78, + "learning_rate": 8.15297696653629e-06, + "loss": 0.473, + "step": 21808 + }, + { + "epoch": 1.78, + "learning_rate": 8.152433724467624e-06, + "loss": 0.1516, + "step": 21809 + }, + { + "epoch": 1.78, + "learning_rate": 8.151890482398958e-06, + "loss": 0.3305, + "step": 21810 + }, + { + "epoch": 1.78, + "learning_rate": 8.151347240330292e-06, + "loss": 0.5087, + "step": 21811 + }, + { + "epoch": 1.78, + "learning_rate": 8.150803998261627e-06, + "loss": 0.3711, + "step": 21812 + }, + { + "epoch": 1.78, + "learning_rate": 8.150260756192961e-06, + "loss": 0.1876, + "step": 21813 + }, + { + "epoch": 1.78, + "learning_rate": 8.149717514124295e-06, + "loss": 0.4573, + "step": 21814 + }, + { + "epoch": 1.78, + "learning_rate": 8.14917427205563e-06, + "loss": 0.2474, + "step": 21815 + }, + { + "epoch": 1.78, + "learning_rate": 8.148631029986964e-06, + "loss": 0.4083, + "step": 21816 + }, + { + "epoch": 1.78, + "learning_rate": 8.148087787918298e-06, + "loss": 0.4272, + "step": 21817 + }, + { + "epoch": 1.78, + "learning_rate": 8.147544545849632e-06, + "loss": 0.1896, + "step": 21818 + }, + { + "epoch": 1.78, + "learning_rate": 8.147001303780966e-06, + "loss": 0.2173, + "step": 21819 + }, + { + "epoch": 1.78, + "learning_rate": 8.1464580617123e-06, + "loss": 0.3263, + "step": 21820 + }, + { + "epoch": 1.78, + "learning_rate": 8.145914819643635e-06, + "loss": 0.2838, + "step": 21821 + }, + { + "epoch": 1.78, + "learning_rate": 8.145371577574967e-06, + "loss": 0.1469, + "step": 21822 + }, + { + "epoch": 1.78, + "learning_rate": 8.144828335506302e-06, + "loss": 0.1573, + "step": 21823 + }, + { + "epoch": 1.78, + "learning_rate": 8.144285093437636e-06, + "loss": 0.2068, + "step": 21824 + }, + { + "epoch": 1.78, + "learning_rate": 8.14374185136897e-06, + "loss": 0.3917, + "step": 21825 + }, + { + "epoch": 1.78, + "learning_rate": 8.143198609300304e-06, + "loss": 0.3488, + "step": 21826 + }, + { + "epoch": 1.78, + "learning_rate": 8.142655367231638e-06, + "loss": 0.3323, + "step": 21827 + }, + { + "epoch": 1.78, + "learning_rate": 8.142112125162973e-06, + "loss": 0.3988, + "step": 21828 + }, + { + "epoch": 1.78, + "learning_rate": 8.141568883094307e-06, + "loss": 0.237, + "step": 21829 + }, + { + "epoch": 1.78, + "learning_rate": 8.141025641025641e-06, + "loss": 0.4638, + "step": 21830 + }, + { + "epoch": 1.78, + "learning_rate": 8.140482398956975e-06, + "loss": 0.1137, + "step": 21831 + }, + { + "epoch": 1.78, + "learning_rate": 8.13993915688831e-06, + "loss": 0.332, + "step": 21832 + }, + { + "epoch": 1.78, + "learning_rate": 8.139395914819644e-06, + "loss": 0.2595, + "step": 21833 + }, + { + "epoch": 1.78, + "learning_rate": 8.138852672750978e-06, + "loss": 0.3612, + "step": 21834 + }, + { + "epoch": 1.78, + "learning_rate": 8.138309430682312e-06, + "loss": 0.3516, + "step": 21835 + }, + { + "epoch": 1.78, + "learning_rate": 8.137766188613647e-06, + "loss": 0.2979, + "step": 21836 + }, + { + "epoch": 1.78, + "learning_rate": 8.13722294654498e-06, + "loss": 0.1998, + "step": 21837 + }, + { + "epoch": 1.78, + "learning_rate": 8.136679704476315e-06, + "loss": 0.3012, + "step": 21838 + }, + { + "epoch": 1.78, + "learning_rate": 8.13613646240765e-06, + "loss": 0.324, + "step": 21839 + }, + { + "epoch": 1.78, + "learning_rate": 8.135593220338983e-06, + "loss": 0.3063, + "step": 21840 + }, + { + "epoch": 1.78, + "learning_rate": 8.135049978270318e-06, + "loss": 0.1587, + "step": 21841 + }, + { + "epoch": 1.78, + "learning_rate": 8.134506736201652e-06, + "loss": 0.195, + "step": 21842 + }, + { + "epoch": 1.78, + "learning_rate": 8.133963494132986e-06, + "loss": 0.2866, + "step": 21843 + }, + { + "epoch": 1.78, + "learning_rate": 8.13342025206432e-06, + "loss": 0.1298, + "step": 21844 + }, + { + "epoch": 1.78, + "learning_rate": 8.132877009995655e-06, + "loss": 0.2944, + "step": 21845 + }, + { + "epoch": 1.78, + "learning_rate": 8.132333767926989e-06, + "loss": 0.3944, + "step": 21846 + }, + { + "epoch": 1.78, + "learning_rate": 8.131790525858323e-06, + "loss": 0.1929, + "step": 21847 + }, + { + "epoch": 1.78, + "learning_rate": 8.131247283789657e-06, + "loss": 0.4777, + "step": 21848 + }, + { + "epoch": 1.78, + "learning_rate": 8.130704041720992e-06, + "loss": 0.3504, + "step": 21849 + }, + { + "epoch": 1.78, + "learning_rate": 8.130160799652326e-06, + "loss": 0.2865, + "step": 21850 + }, + { + "epoch": 1.78, + "learning_rate": 8.12961755758366e-06, + "loss": 0.1685, + "step": 21851 + }, + { + "epoch": 1.78, + "learning_rate": 8.129074315514994e-06, + "loss": 0.2346, + "step": 21852 + }, + { + "epoch": 1.78, + "learning_rate": 8.128531073446328e-06, + "loss": 0.3022, + "step": 21853 + }, + { + "epoch": 1.78, + "learning_rate": 8.127987831377663e-06, + "loss": 0.2883, + "step": 21854 + }, + { + "epoch": 1.78, + "learning_rate": 8.127444589308997e-06, + "loss": 0.3586, + "step": 21855 + }, + { + "epoch": 1.78, + "learning_rate": 8.126901347240331e-06, + "loss": 0.2287, + "step": 21856 + }, + { + "epoch": 1.78, + "learning_rate": 8.126358105171665e-06, + "loss": 0.1436, + "step": 21857 + }, + { + "epoch": 1.78, + "learning_rate": 8.125814863103e-06, + "loss": 0.4122, + "step": 21858 + }, + { + "epoch": 1.78, + "learning_rate": 8.125271621034334e-06, + "loss": 0.449, + "step": 21859 + }, + { + "epoch": 1.78, + "learning_rate": 8.124728378965666e-06, + "loss": 0.1822, + "step": 21860 + }, + { + "epoch": 1.78, + "learning_rate": 8.124185136897002e-06, + "loss": 0.4024, + "step": 21861 + }, + { + "epoch": 1.78, + "learning_rate": 8.123641894828337e-06, + "loss": 0.4217, + "step": 21862 + }, + { + "epoch": 1.78, + "learning_rate": 8.12309865275967e-06, + "loss": 0.1923, + "step": 21863 + }, + { + "epoch": 1.78, + "learning_rate": 8.122555410691005e-06, + "loss": 0.6396, + "step": 21864 + }, + { + "epoch": 1.78, + "learning_rate": 8.12201216862234e-06, + "loss": 0.3887, + "step": 21865 + }, + { + "epoch": 1.78, + "learning_rate": 8.121468926553673e-06, + "loss": 0.1163, + "step": 21866 + }, + { + "epoch": 1.78, + "learning_rate": 8.120925684485008e-06, + "loss": 0.4315, + "step": 21867 + }, + { + "epoch": 1.78, + "learning_rate": 8.120382442416342e-06, + "loss": 0.3659, + "step": 21868 + }, + { + "epoch": 1.78, + "learning_rate": 8.119839200347676e-06, + "loss": 0.5862, + "step": 21869 + }, + { + "epoch": 1.78, + "learning_rate": 8.11929595827901e-06, + "loss": 0.2138, + "step": 21870 + }, + { + "epoch": 1.78, + "learning_rate": 8.118752716210345e-06, + "loss": 0.6916, + "step": 21871 + }, + { + "epoch": 1.78, + "learning_rate": 8.118209474141679e-06, + "loss": 0.4169, + "step": 21872 + }, + { + "epoch": 1.78, + "learning_rate": 8.117666232073013e-06, + "loss": 0.1761, + "step": 21873 + }, + { + "epoch": 1.78, + "learning_rate": 8.117122990004347e-06, + "loss": 0.1718, + "step": 21874 + }, + { + "epoch": 1.78, + "learning_rate": 8.116579747935682e-06, + "loss": 0.5103, + "step": 21875 + }, + { + "epoch": 1.78, + "learning_rate": 8.116036505867016e-06, + "loss": 0.4198, + "step": 21876 + }, + { + "epoch": 1.78, + "learning_rate": 8.11549326379835e-06, + "loss": 0.406, + "step": 21877 + }, + { + "epoch": 1.78, + "learning_rate": 8.114950021729684e-06, + "loss": 0.2187, + "step": 21878 + }, + { + "epoch": 1.78, + "learning_rate": 8.114406779661017e-06, + "loss": 0.3218, + "step": 21879 + }, + { + "epoch": 1.78, + "learning_rate": 8.113863537592351e-06, + "loss": 0.1476, + "step": 21880 + }, + { + "epoch": 1.78, + "learning_rate": 8.113320295523685e-06, + "loss": 0.4543, + "step": 21881 + }, + { + "epoch": 1.78, + "learning_rate": 8.11277705345502e-06, + "loss": 0.428, + "step": 21882 + }, + { + "epoch": 1.78, + "learning_rate": 8.112233811386354e-06, + "loss": 0.3367, + "step": 21883 + }, + { + "epoch": 1.78, + "learning_rate": 8.111690569317688e-06, + "loss": 0.5619, + "step": 21884 + }, + { + "epoch": 1.78, + "learning_rate": 8.111147327249022e-06, + "loss": 0.45, + "step": 21885 + }, + { + "epoch": 1.78, + "learning_rate": 8.110604085180356e-06, + "loss": 0.366, + "step": 21886 + }, + { + "epoch": 1.78, + "learning_rate": 8.11006084311169e-06, + "loss": 0.2074, + "step": 21887 + }, + { + "epoch": 1.78, + "learning_rate": 8.109517601043025e-06, + "loss": 0.5153, + "step": 21888 + }, + { + "epoch": 1.78, + "learning_rate": 8.108974358974359e-06, + "loss": 0.4588, + "step": 21889 + }, + { + "epoch": 1.78, + "learning_rate": 8.108431116905693e-06, + "loss": 0.334, + "step": 21890 + }, + { + "epoch": 1.78, + "learning_rate": 8.107887874837028e-06, + "loss": 0.3917, + "step": 21891 + }, + { + "epoch": 1.78, + "learning_rate": 8.107344632768362e-06, + "loss": 0.1898, + "step": 21892 + }, + { + "epoch": 1.78, + "learning_rate": 8.106801390699696e-06, + "loss": 0.2748, + "step": 21893 + }, + { + "epoch": 1.78, + "learning_rate": 8.10625814863103e-06, + "loss": 0.3853, + "step": 21894 + }, + { + "epoch": 1.78, + "learning_rate": 8.105714906562364e-06, + "loss": 0.3345, + "step": 21895 + }, + { + "epoch": 1.78, + "learning_rate": 8.105171664493699e-06, + "loss": 0.3572, + "step": 21896 + }, + { + "epoch": 1.78, + "learning_rate": 8.104628422425035e-06, + "loss": 0.2761, + "step": 21897 + }, + { + "epoch": 1.78, + "learning_rate": 8.104085180356367e-06, + "loss": 0.4687, + "step": 21898 + }, + { + "epoch": 1.78, + "learning_rate": 8.103541938287701e-06, + "loss": 0.304, + "step": 21899 + }, + { + "epoch": 1.78, + "learning_rate": 8.102998696219036e-06, + "loss": 0.3731, + "step": 21900 + }, + { + "epoch": 1.78, + "learning_rate": 8.10245545415037e-06, + "loss": 0.438, + "step": 21901 + }, + { + "epoch": 1.78, + "learning_rate": 8.101912212081704e-06, + "loss": 0.473, + "step": 21902 + }, + { + "epoch": 1.78, + "learning_rate": 8.101368970013038e-06, + "loss": 0.247, + "step": 21903 + }, + { + "epoch": 1.78, + "learning_rate": 8.100825727944373e-06, + "loss": 0.3107, + "step": 21904 + }, + { + "epoch": 1.78, + "learning_rate": 8.100282485875707e-06, + "loss": 0.3163, + "step": 21905 + }, + { + "epoch": 1.79, + "learning_rate": 8.099739243807041e-06, + "loss": 0.3974, + "step": 21906 + }, + { + "epoch": 1.79, + "learning_rate": 8.099196001738375e-06, + "loss": 0.1071, + "step": 21907 + }, + { + "epoch": 1.79, + "learning_rate": 8.09865275966971e-06, + "loss": 0.4129, + "step": 21908 + }, + { + "epoch": 1.79, + "learning_rate": 8.098109517601044e-06, + "loss": 0.5952, + "step": 21909 + }, + { + "epoch": 1.79, + "learning_rate": 8.097566275532378e-06, + "loss": 0.4629, + "step": 21910 + }, + { + "epoch": 1.79, + "learning_rate": 8.097023033463712e-06, + "loss": 0.3553, + "step": 21911 + }, + { + "epoch": 1.79, + "learning_rate": 8.096479791395046e-06, + "loss": 0.3055, + "step": 21912 + }, + { + "epoch": 1.79, + "learning_rate": 8.09593654932638e-06, + "loss": 0.3471, + "step": 21913 + }, + { + "epoch": 1.79, + "learning_rate": 8.095393307257715e-06, + "loss": 0.207, + "step": 21914 + }, + { + "epoch": 1.79, + "learning_rate": 8.094850065189049e-06, + "loss": 0.4348, + "step": 21915 + }, + { + "epoch": 1.79, + "learning_rate": 8.094306823120383e-06, + "loss": 0.3519, + "step": 21916 + }, + { + "epoch": 1.79, + "learning_rate": 8.093763581051718e-06, + "loss": 0.4963, + "step": 21917 + }, + { + "epoch": 1.79, + "learning_rate": 8.093220338983052e-06, + "loss": 0.2531, + "step": 21918 + }, + { + "epoch": 1.79, + "learning_rate": 8.092677096914386e-06, + "loss": 0.2577, + "step": 21919 + }, + { + "epoch": 1.79, + "learning_rate": 8.09213385484572e-06, + "loss": 0.4108, + "step": 21920 + }, + { + "epoch": 1.79, + "learning_rate": 8.091590612777054e-06, + "loss": 0.2852, + "step": 21921 + }, + { + "epoch": 1.79, + "learning_rate": 8.091047370708389e-06, + "loss": 0.2507, + "step": 21922 + }, + { + "epoch": 1.79, + "learning_rate": 8.090504128639723e-06, + "loss": 0.3535, + "step": 21923 + }, + { + "epoch": 1.79, + "learning_rate": 8.089960886571057e-06, + "loss": 0.2836, + "step": 21924 + }, + { + "epoch": 1.79, + "learning_rate": 8.089417644502391e-06, + "loss": 0.4809, + "step": 21925 + }, + { + "epoch": 1.79, + "learning_rate": 8.088874402433726e-06, + "loss": 0.2071, + "step": 21926 + }, + { + "epoch": 1.79, + "learning_rate": 8.08833116036506e-06, + "loss": 0.1744, + "step": 21927 + }, + { + "epoch": 1.79, + "learning_rate": 8.087787918296394e-06, + "loss": 0.3022, + "step": 21928 + }, + { + "epoch": 1.79, + "learning_rate": 8.087244676227728e-06, + "loss": 0.5496, + "step": 21929 + }, + { + "epoch": 1.79, + "learning_rate": 8.086701434159063e-06, + "loss": 0.2295, + "step": 21930 + }, + { + "epoch": 1.79, + "learning_rate": 8.086158192090397e-06, + "loss": 0.2387, + "step": 21931 + }, + { + "epoch": 1.79, + "learning_rate": 8.085614950021731e-06, + "loss": 0.4249, + "step": 21932 + }, + { + "epoch": 1.79, + "learning_rate": 8.085071707953065e-06, + "loss": 0.4338, + "step": 21933 + }, + { + "epoch": 1.79, + "learning_rate": 8.0845284658844e-06, + "loss": 0.2604, + "step": 21934 + }, + { + "epoch": 1.79, + "learning_rate": 8.083985223815734e-06, + "loss": 0.5037, + "step": 21935 + }, + { + "epoch": 1.79, + "learning_rate": 8.083441981747066e-06, + "loss": 0.2319, + "step": 21936 + }, + { + "epoch": 1.79, + "learning_rate": 8.0828987396784e-06, + "loss": 0.7106, + "step": 21937 + }, + { + "epoch": 1.79, + "learning_rate": 8.082355497609735e-06, + "loss": 0.3889, + "step": 21938 + }, + { + "epoch": 1.79, + "learning_rate": 8.081812255541069e-06, + "loss": 0.4554, + "step": 21939 + }, + { + "epoch": 1.79, + "learning_rate": 8.081269013472403e-06, + "loss": 0.3993, + "step": 21940 + }, + { + "epoch": 1.79, + "learning_rate": 8.080725771403737e-06, + "loss": 0.5427, + "step": 21941 + }, + { + "epoch": 1.79, + "learning_rate": 8.080182529335072e-06, + "loss": 0.2143, + "step": 21942 + }, + { + "epoch": 1.79, + "learning_rate": 8.079639287266406e-06, + "loss": 0.3161, + "step": 21943 + }, + { + "epoch": 1.79, + "learning_rate": 8.07909604519774e-06, + "loss": 0.1655, + "step": 21944 + }, + { + "epoch": 1.79, + "learning_rate": 8.078552803129074e-06, + "loss": 0.4034, + "step": 21945 + }, + { + "epoch": 1.79, + "learning_rate": 8.078009561060409e-06, + "loss": 0.4719, + "step": 21946 + }, + { + "epoch": 1.79, + "learning_rate": 8.077466318991743e-06, + "loss": 0.5249, + "step": 21947 + }, + { + "epoch": 1.79, + "learning_rate": 8.076923076923077e-06, + "loss": 0.2878, + "step": 21948 + }, + { + "epoch": 1.79, + "learning_rate": 8.076379834854411e-06, + "loss": 0.3027, + "step": 21949 + }, + { + "epoch": 1.79, + "learning_rate": 8.075836592785745e-06, + "loss": 0.1355, + "step": 21950 + }, + { + "epoch": 1.79, + "learning_rate": 8.075293350717081e-06, + "loss": 0.2284, + "step": 21951 + }, + { + "epoch": 1.79, + "learning_rate": 8.074750108648416e-06, + "loss": 0.4305, + "step": 21952 + }, + { + "epoch": 1.79, + "learning_rate": 8.07420686657975e-06, + "loss": 0.4637, + "step": 21953 + }, + { + "epoch": 1.79, + "learning_rate": 8.073663624511084e-06, + "loss": 0.3762, + "step": 21954 + }, + { + "epoch": 1.79, + "learning_rate": 8.073120382442417e-06, + "loss": 0.341, + "step": 21955 + }, + { + "epoch": 1.79, + "learning_rate": 8.07257714037375e-06, + "loss": 0.116, + "step": 21956 + }, + { + "epoch": 1.79, + "learning_rate": 8.072033898305085e-06, + "loss": 0.333, + "step": 21957 + }, + { + "epoch": 1.79, + "learning_rate": 8.07149065623642e-06, + "loss": 0.2114, + "step": 21958 + }, + { + "epoch": 1.79, + "learning_rate": 8.070947414167754e-06, + "loss": 0.4781, + "step": 21959 + }, + { + "epoch": 1.79, + "learning_rate": 8.070404172099088e-06, + "loss": 0.1917, + "step": 21960 + }, + { + "epoch": 1.79, + "learning_rate": 8.069860930030422e-06, + "loss": 0.1757, + "step": 21961 + }, + { + "epoch": 1.79, + "learning_rate": 8.069317687961756e-06, + "loss": 0.3665, + "step": 21962 + }, + { + "epoch": 1.79, + "learning_rate": 8.06877444589309e-06, + "loss": 0.3721, + "step": 21963 + }, + { + "epoch": 1.79, + "learning_rate": 8.068231203824425e-06, + "loss": 0.2053, + "step": 21964 + }, + { + "epoch": 1.79, + "learning_rate": 8.067687961755759e-06, + "loss": 0.3792, + "step": 21965 + }, + { + "epoch": 1.79, + "learning_rate": 8.067144719687093e-06, + "loss": 0.2936, + "step": 21966 + }, + { + "epoch": 1.79, + "learning_rate": 8.066601477618427e-06, + "loss": 0.3524, + "step": 21967 + }, + { + "epoch": 1.79, + "learning_rate": 8.066058235549762e-06, + "loss": 0.2268, + "step": 21968 + }, + { + "epoch": 1.79, + "learning_rate": 8.065514993481096e-06, + "loss": 0.5502, + "step": 21969 + }, + { + "epoch": 1.79, + "learning_rate": 8.06497175141243e-06, + "loss": 0.5546, + "step": 21970 + }, + { + "epoch": 1.79, + "learning_rate": 8.064428509343764e-06, + "loss": 0.3702, + "step": 21971 + }, + { + "epoch": 1.79, + "learning_rate": 8.063885267275099e-06, + "loss": 0.2965, + "step": 21972 + }, + { + "epoch": 1.79, + "learning_rate": 8.063342025206433e-06, + "loss": 0.5192, + "step": 21973 + }, + { + "epoch": 1.79, + "learning_rate": 8.062798783137767e-06, + "loss": 0.4793, + "step": 21974 + }, + { + "epoch": 1.79, + "learning_rate": 8.062255541069101e-06, + "loss": 0.5979, + "step": 21975 + }, + { + "epoch": 1.79, + "learning_rate": 8.061712299000435e-06, + "loss": 0.2998, + "step": 21976 + }, + { + "epoch": 1.79, + "learning_rate": 8.06116905693177e-06, + "loss": 0.3258, + "step": 21977 + }, + { + "epoch": 1.79, + "learning_rate": 8.060625814863104e-06, + "loss": 0.2888, + "step": 21978 + }, + { + "epoch": 1.79, + "learning_rate": 8.060082572794438e-06, + "loss": 0.2077, + "step": 21979 + }, + { + "epoch": 1.79, + "learning_rate": 8.059539330725772e-06, + "loss": 0.3046, + "step": 21980 + }, + { + "epoch": 1.79, + "learning_rate": 8.058996088657107e-06, + "loss": 0.1189, + "step": 21981 + }, + { + "epoch": 1.79, + "learning_rate": 8.05845284658844e-06, + "loss": 0.3225, + "step": 21982 + }, + { + "epoch": 1.79, + "learning_rate": 8.057909604519775e-06, + "loss": 0.2656, + "step": 21983 + }, + { + "epoch": 1.79, + "learning_rate": 8.05736636245111e-06, + "loss": 0.171, + "step": 21984 + }, + { + "epoch": 1.79, + "learning_rate": 8.056823120382444e-06, + "loss": 0.2873, + "step": 21985 + }, + { + "epoch": 1.79, + "learning_rate": 8.056279878313778e-06, + "loss": 0.3096, + "step": 21986 + }, + { + "epoch": 1.79, + "learning_rate": 8.055736636245112e-06, + "loss": 0.2519, + "step": 21987 + }, + { + "epoch": 1.79, + "learning_rate": 8.055193394176446e-06, + "loss": 0.342, + "step": 21988 + }, + { + "epoch": 1.79, + "learning_rate": 8.05465015210778e-06, + "loss": 0.4334, + "step": 21989 + }, + { + "epoch": 1.79, + "learning_rate": 8.054106910039115e-06, + "loss": 0.4773, + "step": 21990 + }, + { + "epoch": 1.79, + "learning_rate": 8.053563667970449e-06, + "loss": 0.1402, + "step": 21991 + }, + { + "epoch": 1.79, + "learning_rate": 8.053020425901783e-06, + "loss": 0.4548, + "step": 21992 + }, + { + "epoch": 1.79, + "learning_rate": 8.052477183833116e-06, + "loss": 0.3045, + "step": 21993 + }, + { + "epoch": 1.79, + "learning_rate": 8.05193394176445e-06, + "loss": 0.3234, + "step": 21994 + }, + { + "epoch": 1.79, + "learning_rate": 8.051390699695784e-06, + "loss": 0.4684, + "step": 21995 + }, + { + "epoch": 1.79, + "learning_rate": 8.050847457627118e-06, + "loss": 0.2562, + "step": 21996 + }, + { + "epoch": 1.79, + "learning_rate": 8.050304215558453e-06, + "loss": 0.2188, + "step": 21997 + }, + { + "epoch": 1.79, + "learning_rate": 8.049760973489787e-06, + "loss": 0.4236, + "step": 21998 + }, + { + "epoch": 1.79, + "learning_rate": 8.049217731421121e-06, + "loss": 0.2699, + "step": 21999 + }, + { + "epoch": 1.79, + "learning_rate": 8.048674489352455e-06, + "loss": 0.1494, + "step": 22000 + }, + { + "epoch": 1.79, + "eval_accuracy": 0.8433010697911361, + "eval_loss": 0.4279337525367737, + "eval_runtime": 22.311, + "eval_samples_per_second": 439.917, + "eval_steps_per_second": 3.451, + "step": 22000 + }, + { + "epoch": 1.79, + "learning_rate": 8.04813124728379e-06, + "loss": 0.3269, + "step": 22001 + }, + { + "epoch": 1.79, + "learning_rate": 8.047588005215124e-06, + "loss": 0.2866, + "step": 22002 + }, + { + "epoch": 1.79, + "learning_rate": 8.047044763146458e-06, + "loss": 0.2951, + "step": 22003 + }, + { + "epoch": 1.79, + "learning_rate": 8.046501521077792e-06, + "loss": 0.402, + "step": 22004 + }, + { + "epoch": 1.79, + "learning_rate": 8.045958279009128e-06, + "loss": 0.3891, + "step": 22005 + }, + { + "epoch": 1.79, + "learning_rate": 8.045415036940462e-06, + "loss": 0.2587, + "step": 22006 + }, + { + "epoch": 1.79, + "learning_rate": 8.044871794871797e-06, + "loss": 0.3593, + "step": 22007 + }, + { + "epoch": 1.79, + "learning_rate": 8.04432855280313e-06, + "loss": 0.5015, + "step": 22008 + }, + { + "epoch": 1.79, + "learning_rate": 8.043785310734465e-06, + "loss": 0.472, + "step": 22009 + }, + { + "epoch": 1.79, + "learning_rate": 8.0432420686658e-06, + "loss": 0.3574, + "step": 22010 + }, + { + "epoch": 1.79, + "learning_rate": 8.042698826597134e-06, + "loss": 0.4143, + "step": 22011 + }, + { + "epoch": 1.79, + "learning_rate": 8.042155584528466e-06, + "loss": 0.4302, + "step": 22012 + }, + { + "epoch": 1.79, + "learning_rate": 8.0416123424598e-06, + "loss": 0.2984, + "step": 22013 + }, + { + "epoch": 1.79, + "learning_rate": 8.041069100391135e-06, + "loss": 0.2446, + "step": 22014 + }, + { + "epoch": 1.79, + "learning_rate": 8.040525858322469e-06, + "loss": 0.3915, + "step": 22015 + }, + { + "epoch": 1.79, + "learning_rate": 8.039982616253803e-06, + "loss": 0.1564, + "step": 22016 + }, + { + "epoch": 1.79, + "learning_rate": 8.039439374185137e-06, + "loss": 0.3662, + "step": 22017 + }, + { + "epoch": 1.79, + "learning_rate": 8.038896132116471e-06, + "loss": 0.5526, + "step": 22018 + }, + { + "epoch": 1.79, + "learning_rate": 8.038352890047806e-06, + "loss": 0.4992, + "step": 22019 + }, + { + "epoch": 1.79, + "learning_rate": 8.03780964797914e-06, + "loss": 0.2848, + "step": 22020 + }, + { + "epoch": 1.79, + "learning_rate": 8.037266405910474e-06, + "loss": 0.2502, + "step": 22021 + }, + { + "epoch": 1.79, + "learning_rate": 8.036723163841808e-06, + "loss": 0.3367, + "step": 22022 + }, + { + "epoch": 1.79, + "learning_rate": 8.036179921773143e-06, + "loss": 0.2981, + "step": 22023 + }, + { + "epoch": 1.79, + "learning_rate": 8.035636679704477e-06, + "loss": 0.449, + "step": 22024 + }, + { + "epoch": 1.79, + "learning_rate": 8.035093437635811e-06, + "loss": 0.3351, + "step": 22025 + }, + { + "epoch": 1.79, + "learning_rate": 8.034550195567145e-06, + "loss": 0.5175, + "step": 22026 + }, + { + "epoch": 1.79, + "learning_rate": 8.03400695349848e-06, + "loss": 0.2219, + "step": 22027 + }, + { + "epoch": 1.79, + "learning_rate": 8.033463711429814e-06, + "loss": 0.2399, + "step": 22028 + }, + { + "epoch": 1.8, + "learning_rate": 8.032920469361148e-06, + "loss": 0.2292, + "step": 22029 + }, + { + "epoch": 1.8, + "learning_rate": 8.032377227292482e-06, + "loss": 0.1303, + "step": 22030 + }, + { + "epoch": 1.8, + "learning_rate": 8.031833985223816e-06, + "loss": 0.5156, + "step": 22031 + }, + { + "epoch": 1.8, + "learning_rate": 8.03129074315515e-06, + "loss": 0.5326, + "step": 22032 + }, + { + "epoch": 1.8, + "learning_rate": 8.030747501086485e-06, + "loss": 0.3226, + "step": 22033 + }, + { + "epoch": 1.8, + "learning_rate": 8.030204259017819e-06, + "loss": 0.4088, + "step": 22034 + }, + { + "epoch": 1.8, + "learning_rate": 8.029661016949153e-06, + "loss": 0.5085, + "step": 22035 + }, + { + "epoch": 1.8, + "learning_rate": 8.029117774880488e-06, + "loss": 0.411, + "step": 22036 + }, + { + "epoch": 1.8, + "learning_rate": 8.028574532811822e-06, + "loss": 0.3652, + "step": 22037 + }, + { + "epoch": 1.8, + "learning_rate": 8.028031290743156e-06, + "loss": 0.2445, + "step": 22038 + }, + { + "epoch": 1.8, + "learning_rate": 8.02748804867449e-06, + "loss": 0.4218, + "step": 22039 + }, + { + "epoch": 1.8, + "learning_rate": 8.026944806605825e-06, + "loss": 0.3415, + "step": 22040 + }, + { + "epoch": 1.8, + "learning_rate": 8.026401564537159e-06, + "loss": 0.1719, + "step": 22041 + }, + { + "epoch": 1.8, + "learning_rate": 8.025858322468493e-06, + "loss": 0.4596, + "step": 22042 + }, + { + "epoch": 1.8, + "learning_rate": 8.025315080399827e-06, + "loss": 0.3591, + "step": 22043 + }, + { + "epoch": 1.8, + "learning_rate": 8.024771838331161e-06, + "loss": 0.4363, + "step": 22044 + }, + { + "epoch": 1.8, + "learning_rate": 8.024228596262496e-06, + "loss": 0.3868, + "step": 22045 + }, + { + "epoch": 1.8, + "learning_rate": 8.02368535419383e-06, + "loss": 0.4266, + "step": 22046 + }, + { + "epoch": 1.8, + "learning_rate": 8.023142112125164e-06, + "loss": 0.302, + "step": 22047 + }, + { + "epoch": 1.8, + "learning_rate": 8.022598870056498e-06, + "loss": 0.2498, + "step": 22048 + }, + { + "epoch": 1.8, + "learning_rate": 8.022055627987833e-06, + "loss": 0.2864, + "step": 22049 + }, + { + "epoch": 1.8, + "learning_rate": 8.021512385919165e-06, + "loss": 0.3556, + "step": 22050 + }, + { + "epoch": 1.8, + "learning_rate": 8.0209691438505e-06, + "loss": 0.3215, + "step": 22051 + }, + { + "epoch": 1.8, + "learning_rate": 8.020425901781834e-06, + "loss": 0.1143, + "step": 22052 + }, + { + "epoch": 1.8, + "learning_rate": 8.019882659713168e-06, + "loss": 0.1543, + "step": 22053 + }, + { + "epoch": 1.8, + "learning_rate": 8.019339417644502e-06, + "loss": 0.3094, + "step": 22054 + }, + { + "epoch": 1.8, + "learning_rate": 8.018796175575836e-06, + "loss": 0.1488, + "step": 22055 + }, + { + "epoch": 1.8, + "learning_rate": 8.01825293350717e-06, + "loss": 0.549, + "step": 22056 + }, + { + "epoch": 1.8, + "learning_rate": 8.017709691438505e-06, + "loss": 0.3993, + "step": 22057 + }, + { + "epoch": 1.8, + "learning_rate": 8.017166449369839e-06, + "loss": 0.3018, + "step": 22058 + }, + { + "epoch": 1.8, + "learning_rate": 8.016623207301175e-06, + "loss": 0.3685, + "step": 22059 + }, + { + "epoch": 1.8, + "learning_rate": 8.016079965232509e-06, + "loss": 0.5104, + "step": 22060 + }, + { + "epoch": 1.8, + "learning_rate": 8.015536723163843e-06, + "loss": 0.5626, + "step": 22061 + }, + { + "epoch": 1.8, + "learning_rate": 8.014993481095178e-06, + "loss": 0.358, + "step": 22062 + }, + { + "epoch": 1.8, + "learning_rate": 8.014450239026512e-06, + "loss": 0.37, + "step": 22063 + }, + { + "epoch": 1.8, + "learning_rate": 8.013906996957846e-06, + "loss": 0.2245, + "step": 22064 + }, + { + "epoch": 1.8, + "learning_rate": 8.01336375488918e-06, + "loss": 0.2052, + "step": 22065 + }, + { + "epoch": 1.8, + "learning_rate": 8.012820512820515e-06, + "loss": 0.2418, + "step": 22066 + }, + { + "epoch": 1.8, + "learning_rate": 8.012277270751849e-06, + "loss": 0.1267, + "step": 22067 + }, + { + "epoch": 1.8, + "learning_rate": 8.011734028683183e-06, + "loss": 0.5128, + "step": 22068 + }, + { + "epoch": 1.8, + "learning_rate": 8.011190786614516e-06, + "loss": 0.1034, + "step": 22069 + }, + { + "epoch": 1.8, + "learning_rate": 8.01064754454585e-06, + "loss": 0.1045, + "step": 22070 + }, + { + "epoch": 1.8, + "learning_rate": 8.010104302477184e-06, + "loss": 0.3081, + "step": 22071 + }, + { + "epoch": 1.8, + "learning_rate": 8.009561060408518e-06, + "loss": 0.2042, + "step": 22072 + }, + { + "epoch": 1.8, + "learning_rate": 8.009017818339852e-06, + "loss": 0.2881, + "step": 22073 + }, + { + "epoch": 1.8, + "learning_rate": 8.008474576271187e-06, + "loss": 0.2481, + "step": 22074 + }, + { + "epoch": 1.8, + "learning_rate": 8.007931334202521e-06, + "loss": 0.3405, + "step": 22075 + }, + { + "epoch": 1.8, + "learning_rate": 8.007388092133855e-06, + "loss": 0.3161, + "step": 22076 + }, + { + "epoch": 1.8, + "learning_rate": 8.00684485006519e-06, + "loss": 0.3832, + "step": 22077 + }, + { + "epoch": 1.8, + "learning_rate": 8.006301607996524e-06, + "loss": 0.3416, + "step": 22078 + }, + { + "epoch": 1.8, + "learning_rate": 8.005758365927858e-06, + "loss": 0.1461, + "step": 22079 + }, + { + "epoch": 1.8, + "learning_rate": 8.005215123859192e-06, + "loss": 0.5173, + "step": 22080 + }, + { + "epoch": 1.8, + "learning_rate": 8.004671881790526e-06, + "loss": 0.6833, + "step": 22081 + }, + { + "epoch": 1.8, + "learning_rate": 8.00412863972186e-06, + "loss": 0.4846, + "step": 22082 + }, + { + "epoch": 1.8, + "learning_rate": 8.003585397653195e-06, + "loss": 0.1525, + "step": 22083 + }, + { + "epoch": 1.8, + "learning_rate": 8.003042155584529e-06, + "loss": 0.3758, + "step": 22084 + }, + { + "epoch": 1.8, + "learning_rate": 8.002498913515863e-06, + "loss": 0.5219, + "step": 22085 + }, + { + "epoch": 1.8, + "learning_rate": 8.001955671447197e-06, + "loss": 0.2735, + "step": 22086 + }, + { + "epoch": 1.8, + "learning_rate": 8.001412429378532e-06, + "loss": 0.3395, + "step": 22087 + }, + { + "epoch": 1.8, + "learning_rate": 8.000869187309866e-06, + "loss": 0.3087, + "step": 22088 + }, + { + "epoch": 1.8, + "learning_rate": 8.0003259452412e-06, + "loss": 0.3165, + "step": 22089 + }, + { + "epoch": 1.8, + "learning_rate": 7.999782703172534e-06, + "loss": 0.5168, + "step": 22090 + }, + { + "epoch": 1.8, + "learning_rate": 7.999239461103869e-06, + "loss": 0.2862, + "step": 22091 + }, + { + "epoch": 1.8, + "learning_rate": 7.998696219035203e-06, + "loss": 0.2643, + "step": 22092 + }, + { + "epoch": 1.8, + "learning_rate": 7.998152976966537e-06, + "loss": 0.1897, + "step": 22093 + }, + { + "epoch": 1.8, + "learning_rate": 7.997609734897871e-06, + "loss": 0.0677, + "step": 22094 + }, + { + "epoch": 1.8, + "learning_rate": 7.997066492829205e-06, + "loss": 0.1861, + "step": 22095 + }, + { + "epoch": 1.8, + "learning_rate": 7.99652325076054e-06, + "loss": 0.3294, + "step": 22096 + }, + { + "epoch": 1.8, + "learning_rate": 7.995980008691874e-06, + "loss": 0.218, + "step": 22097 + }, + { + "epoch": 1.8, + "learning_rate": 7.995436766623208e-06, + "loss": 0.149, + "step": 22098 + }, + { + "epoch": 1.8, + "learning_rate": 7.994893524554542e-06, + "loss": 0.5193, + "step": 22099 + }, + { + "epoch": 1.8, + "learning_rate": 7.994350282485877e-06, + "loss": 0.2867, + "step": 22100 + }, + { + "epoch": 1.8, + "learning_rate": 7.993807040417211e-06, + "loss": 0.2464, + "step": 22101 + }, + { + "epoch": 1.8, + "learning_rate": 7.993263798348545e-06, + "loss": 0.5433, + "step": 22102 + }, + { + "epoch": 1.8, + "learning_rate": 7.99272055627988e-06, + "loss": 0.3554, + "step": 22103 + }, + { + "epoch": 1.8, + "learning_rate": 7.992177314211214e-06, + "loss": 0.3652, + "step": 22104 + }, + { + "epoch": 1.8, + "learning_rate": 7.991634072142548e-06, + "loss": 0.1811, + "step": 22105 + }, + { + "epoch": 1.8, + "learning_rate": 7.991090830073882e-06, + "loss": 0.6684, + "step": 22106 + }, + { + "epoch": 1.8, + "learning_rate": 7.990547588005215e-06, + "loss": 0.2575, + "step": 22107 + }, + { + "epoch": 1.8, + "learning_rate": 7.990004345936549e-06, + "loss": 0.2178, + "step": 22108 + }, + { + "epoch": 1.8, + "learning_rate": 7.989461103867883e-06, + "loss": 0.1973, + "step": 22109 + }, + { + "epoch": 1.8, + "learning_rate": 7.988917861799217e-06, + "loss": 0.3344, + "step": 22110 + }, + { + "epoch": 1.8, + "learning_rate": 7.988374619730551e-06, + "loss": 0.2287, + "step": 22111 + }, + { + "epoch": 1.8, + "learning_rate": 7.987831377661886e-06, + "loss": 0.3076, + "step": 22112 + }, + { + "epoch": 1.8, + "learning_rate": 7.987288135593222e-06, + "loss": 0.3839, + "step": 22113 + }, + { + "epoch": 1.8, + "learning_rate": 7.986744893524556e-06, + "loss": 0.2066, + "step": 22114 + }, + { + "epoch": 1.8, + "learning_rate": 7.98620165145589e-06, + "loss": 0.228, + "step": 22115 + }, + { + "epoch": 1.8, + "learning_rate": 7.985658409387224e-06, + "loss": 0.3214, + "step": 22116 + }, + { + "epoch": 1.8, + "learning_rate": 7.985115167318559e-06, + "loss": 0.35, + "step": 22117 + }, + { + "epoch": 1.8, + "learning_rate": 7.984571925249893e-06, + "loss": 0.192, + "step": 22118 + }, + { + "epoch": 1.8, + "learning_rate": 7.984028683181227e-06, + "loss": 0.7083, + "step": 22119 + }, + { + "epoch": 1.8, + "learning_rate": 7.983485441112561e-06, + "loss": 0.3332, + "step": 22120 + }, + { + "epoch": 1.8, + "learning_rate": 7.982942199043895e-06, + "loss": 0.2249, + "step": 22121 + }, + { + "epoch": 1.8, + "learning_rate": 7.98239895697523e-06, + "loss": 0.5424, + "step": 22122 + }, + { + "epoch": 1.8, + "learning_rate": 7.981855714906564e-06, + "loss": 0.2427, + "step": 22123 + }, + { + "epoch": 1.8, + "learning_rate": 7.981312472837898e-06, + "loss": 0.2791, + "step": 22124 + }, + { + "epoch": 1.8, + "learning_rate": 7.980769230769232e-06, + "loss": 0.4182, + "step": 22125 + }, + { + "epoch": 1.8, + "learning_rate": 7.980225988700565e-06, + "loss": 0.4483, + "step": 22126 + }, + { + "epoch": 1.8, + "learning_rate": 7.9796827466319e-06, + "loss": 0.3799, + "step": 22127 + }, + { + "epoch": 1.8, + "learning_rate": 7.979139504563233e-06, + "loss": 0.2699, + "step": 22128 + }, + { + "epoch": 1.8, + "learning_rate": 7.978596262494568e-06, + "loss": 0.2781, + "step": 22129 + }, + { + "epoch": 1.8, + "learning_rate": 7.978053020425902e-06, + "loss": 0.3294, + "step": 22130 + }, + { + "epoch": 1.8, + "learning_rate": 7.977509778357236e-06, + "loss": 0.4196, + "step": 22131 + }, + { + "epoch": 1.8, + "learning_rate": 7.97696653628857e-06, + "loss": 0.2282, + "step": 22132 + }, + { + "epoch": 1.8, + "learning_rate": 7.976423294219905e-06, + "loss": 0.2358, + "step": 22133 + }, + { + "epoch": 1.8, + "learning_rate": 7.975880052151239e-06, + "loss": 0.5132, + "step": 22134 + }, + { + "epoch": 1.8, + "learning_rate": 7.975336810082573e-06, + "loss": 0.3571, + "step": 22135 + }, + { + "epoch": 1.8, + "learning_rate": 7.974793568013907e-06, + "loss": 0.5647, + "step": 22136 + }, + { + "epoch": 1.8, + "learning_rate": 7.974250325945241e-06, + "loss": 0.3225, + "step": 22137 + }, + { + "epoch": 1.8, + "learning_rate": 7.973707083876576e-06, + "loss": 0.231, + "step": 22138 + }, + { + "epoch": 1.8, + "learning_rate": 7.97316384180791e-06, + "loss": 0.5029, + "step": 22139 + }, + { + "epoch": 1.8, + "learning_rate": 7.972620599739244e-06, + "loss": 0.3284, + "step": 22140 + }, + { + "epoch": 1.8, + "learning_rate": 7.972077357670578e-06, + "loss": 0.5844, + "step": 22141 + }, + { + "epoch": 1.8, + "learning_rate": 7.971534115601913e-06, + "loss": 0.3229, + "step": 22142 + }, + { + "epoch": 1.8, + "learning_rate": 7.970990873533247e-06, + "loss": 0.3942, + "step": 22143 + }, + { + "epoch": 1.8, + "learning_rate": 7.970447631464581e-06, + "loss": 0.2535, + "step": 22144 + }, + { + "epoch": 1.8, + "learning_rate": 7.969904389395915e-06, + "loss": 0.2351, + "step": 22145 + }, + { + "epoch": 1.8, + "learning_rate": 7.96936114732725e-06, + "loss": 0.3386, + "step": 22146 + }, + { + "epoch": 1.8, + "learning_rate": 7.968817905258584e-06, + "loss": 0.3539, + "step": 22147 + }, + { + "epoch": 1.8, + "learning_rate": 7.968274663189918e-06, + "loss": 0.4583, + "step": 22148 + }, + { + "epoch": 1.8, + "learning_rate": 7.967731421121252e-06, + "loss": 0.3752, + "step": 22149 + }, + { + "epoch": 1.8, + "learning_rate": 7.967188179052586e-06, + "loss": 0.529, + "step": 22150 + }, + { + "epoch": 1.81, + "learning_rate": 7.96664493698392e-06, + "loss": 0.3099, + "step": 22151 + }, + { + "epoch": 1.81, + "learning_rate": 7.966101694915255e-06, + "loss": 0.5943, + "step": 22152 + }, + { + "epoch": 1.81, + "learning_rate": 7.96555845284659e-06, + "loss": 0.1852, + "step": 22153 + }, + { + "epoch": 1.81, + "learning_rate": 7.965015210777923e-06, + "loss": 0.5076, + "step": 22154 + }, + { + "epoch": 1.81, + "learning_rate": 7.964471968709258e-06, + "loss": 0.2321, + "step": 22155 + }, + { + "epoch": 1.81, + "learning_rate": 7.963928726640592e-06, + "loss": 0.2382, + "step": 22156 + }, + { + "epoch": 1.81, + "learning_rate": 7.963385484571926e-06, + "loss": 0.2159, + "step": 22157 + }, + { + "epoch": 1.81, + "learning_rate": 7.96284224250326e-06, + "loss": 0.1975, + "step": 22158 + }, + { + "epoch": 1.81, + "learning_rate": 7.962299000434595e-06, + "loss": 0.3356, + "step": 22159 + }, + { + "epoch": 1.81, + "learning_rate": 7.961755758365929e-06, + "loss": 0.3212, + "step": 22160 + }, + { + "epoch": 1.81, + "learning_rate": 7.961212516297263e-06, + "loss": 0.4669, + "step": 22161 + }, + { + "epoch": 1.81, + "learning_rate": 7.960669274228597e-06, + "loss": 0.2922, + "step": 22162 + }, + { + "epoch": 1.81, + "learning_rate": 7.960126032159931e-06, + "loss": 0.3854, + "step": 22163 + }, + { + "epoch": 1.81, + "learning_rate": 7.959582790091264e-06, + "loss": 0.252, + "step": 22164 + }, + { + "epoch": 1.81, + "learning_rate": 7.959039548022598e-06, + "loss": 0.3916, + "step": 22165 + }, + { + "epoch": 1.81, + "learning_rate": 7.958496305953932e-06, + "loss": 0.2617, + "step": 22166 + }, + { + "epoch": 1.81, + "learning_rate": 7.957953063885268e-06, + "loss": 0.203, + "step": 22167 + }, + { + "epoch": 1.81, + "learning_rate": 7.957409821816603e-06, + "loss": 0.5698, + "step": 22168 + }, + { + "epoch": 1.81, + "learning_rate": 7.956866579747937e-06, + "loss": 0.2186, + "step": 22169 + }, + { + "epoch": 1.81, + "learning_rate": 7.956323337679271e-06, + "loss": 0.2917, + "step": 22170 + }, + { + "epoch": 1.81, + "learning_rate": 7.955780095610605e-06, + "loss": 0.3041, + "step": 22171 + }, + { + "epoch": 1.81, + "learning_rate": 7.95523685354194e-06, + "loss": 0.4837, + "step": 22172 + }, + { + "epoch": 1.81, + "learning_rate": 7.954693611473274e-06, + "loss": 0.3606, + "step": 22173 + }, + { + "epoch": 1.81, + "learning_rate": 7.954150369404608e-06, + "loss": 0.188, + "step": 22174 + }, + { + "epoch": 1.81, + "learning_rate": 7.953607127335942e-06, + "loss": 0.2684, + "step": 22175 + }, + { + "epoch": 1.81, + "learning_rate": 7.953063885267276e-06, + "loss": 0.3314, + "step": 22176 + }, + { + "epoch": 1.81, + "learning_rate": 7.95252064319861e-06, + "loss": 0.4296, + "step": 22177 + }, + { + "epoch": 1.81, + "learning_rate": 7.951977401129945e-06, + "loss": 0.2534, + "step": 22178 + }, + { + "epoch": 1.81, + "learning_rate": 7.95143415906128e-06, + "loss": 0.2706, + "step": 22179 + }, + { + "epoch": 1.81, + "learning_rate": 7.950890916992613e-06, + "loss": 0.7491, + "step": 22180 + }, + { + "epoch": 1.81, + "learning_rate": 7.950347674923948e-06, + "loss": 0.4429, + "step": 22181 + }, + { + "epoch": 1.81, + "learning_rate": 7.949804432855282e-06, + "loss": 0.2442, + "step": 22182 + }, + { + "epoch": 1.81, + "learning_rate": 7.949261190786614e-06, + "loss": 0.3308, + "step": 22183 + }, + { + "epoch": 1.81, + "learning_rate": 7.948717948717949e-06, + "loss": 0.1738, + "step": 22184 + }, + { + "epoch": 1.81, + "learning_rate": 7.948174706649283e-06, + "loss": 0.2778, + "step": 22185 + }, + { + "epoch": 1.81, + "learning_rate": 7.947631464580617e-06, + "loss": 0.5726, + "step": 22186 + }, + { + "epoch": 1.81, + "learning_rate": 7.947088222511951e-06, + "loss": 0.3856, + "step": 22187 + }, + { + "epoch": 1.81, + "learning_rate": 7.946544980443286e-06, + "loss": 0.4135, + "step": 22188 + }, + { + "epoch": 1.81, + "learning_rate": 7.94600173837462e-06, + "loss": 0.3726, + "step": 22189 + }, + { + "epoch": 1.81, + "learning_rate": 7.945458496305954e-06, + "loss": 0.354, + "step": 22190 + }, + { + "epoch": 1.81, + "learning_rate": 7.944915254237288e-06, + "loss": 0.4979, + "step": 22191 + }, + { + "epoch": 1.81, + "learning_rate": 7.944372012168622e-06, + "loss": 0.3569, + "step": 22192 + }, + { + "epoch": 1.81, + "learning_rate": 7.943828770099957e-06, + "loss": 0.357, + "step": 22193 + }, + { + "epoch": 1.81, + "learning_rate": 7.943285528031291e-06, + "loss": 0.2849, + "step": 22194 + }, + { + "epoch": 1.81, + "learning_rate": 7.942742285962625e-06, + "loss": 0.2103, + "step": 22195 + }, + { + "epoch": 1.81, + "learning_rate": 7.94219904389396e-06, + "loss": 0.2855, + "step": 22196 + }, + { + "epoch": 1.81, + "learning_rate": 7.941655801825294e-06, + "loss": 0.5107, + "step": 22197 + }, + { + "epoch": 1.81, + "learning_rate": 7.941112559756628e-06, + "loss": 0.1941, + "step": 22198 + }, + { + "epoch": 1.81, + "learning_rate": 7.940569317687962e-06, + "loss": 0.465, + "step": 22199 + }, + { + "epoch": 1.81, + "learning_rate": 7.940026075619296e-06, + "loss": 0.4158, + "step": 22200 + }, + { + "epoch": 1.81, + "learning_rate": 7.93948283355063e-06, + "loss": 0.1902, + "step": 22201 + }, + { + "epoch": 1.81, + "learning_rate": 7.938939591481965e-06, + "loss": 0.3639, + "step": 22202 + }, + { + "epoch": 1.81, + "learning_rate": 7.938396349413299e-06, + "loss": 0.1038, + "step": 22203 + }, + { + "epoch": 1.81, + "learning_rate": 7.937853107344633e-06, + "loss": 0.4227, + "step": 22204 + }, + { + "epoch": 1.81, + "learning_rate": 7.937309865275967e-06, + "loss": 0.4142, + "step": 22205 + }, + { + "epoch": 1.81, + "learning_rate": 7.936766623207302e-06, + "loss": 0.2486, + "step": 22206 + }, + { + "epoch": 1.81, + "learning_rate": 7.936223381138636e-06, + "loss": 0.6087, + "step": 22207 + }, + { + "epoch": 1.81, + "learning_rate": 7.93568013906997e-06, + "loss": 0.414, + "step": 22208 + }, + { + "epoch": 1.81, + "learning_rate": 7.935136897001304e-06, + "loss": 0.3996, + "step": 22209 + }, + { + "epoch": 1.81, + "learning_rate": 7.934593654932639e-06, + "loss": 0.4244, + "step": 22210 + }, + { + "epoch": 1.81, + "learning_rate": 7.934050412863973e-06, + "loss": 0.372, + "step": 22211 + }, + { + "epoch": 1.81, + "learning_rate": 7.933507170795307e-06, + "loss": 0.4246, + "step": 22212 + }, + { + "epoch": 1.81, + "learning_rate": 7.932963928726641e-06, + "loss": 0.4243, + "step": 22213 + }, + { + "epoch": 1.81, + "learning_rate": 7.932420686657976e-06, + "loss": 0.6814, + "step": 22214 + }, + { + "epoch": 1.81, + "learning_rate": 7.93187744458931e-06, + "loss": 0.2228, + "step": 22215 + }, + { + "epoch": 1.81, + "learning_rate": 7.931334202520644e-06, + "loss": 0.4944, + "step": 22216 + }, + { + "epoch": 1.81, + "learning_rate": 7.930790960451978e-06, + "loss": 0.4108, + "step": 22217 + }, + { + "epoch": 1.81, + "learning_rate": 7.930247718383312e-06, + "loss": 0.1956, + "step": 22218 + }, + { + "epoch": 1.81, + "learning_rate": 7.929704476314647e-06, + "loss": 0.6933, + "step": 22219 + }, + { + "epoch": 1.81, + "learning_rate": 7.929161234245981e-06, + "loss": 0.321, + "step": 22220 + }, + { + "epoch": 1.81, + "learning_rate": 7.928617992177315e-06, + "loss": 0.5656, + "step": 22221 + }, + { + "epoch": 1.81, + "learning_rate": 7.92807475010865e-06, + "loss": 0.2094, + "step": 22222 + }, + { + "epoch": 1.81, + "learning_rate": 7.927531508039984e-06, + "loss": 0.4156, + "step": 22223 + }, + { + "epoch": 1.81, + "learning_rate": 7.926988265971318e-06, + "loss": 0.4792, + "step": 22224 + }, + { + "epoch": 1.81, + "learning_rate": 7.926445023902652e-06, + "loss": 0.4492, + "step": 22225 + }, + { + "epoch": 1.81, + "learning_rate": 7.925901781833986e-06, + "loss": 0.2165, + "step": 22226 + }, + { + "epoch": 1.81, + "learning_rate": 7.92535853976532e-06, + "loss": 0.1995, + "step": 22227 + }, + { + "epoch": 1.81, + "learning_rate": 7.924815297696655e-06, + "loss": 0.2409, + "step": 22228 + }, + { + "epoch": 1.81, + "learning_rate": 7.924272055627989e-06, + "loss": 0.2796, + "step": 22229 + }, + { + "epoch": 1.81, + "learning_rate": 7.923728813559323e-06, + "loss": 0.3266, + "step": 22230 + }, + { + "epoch": 1.81, + "learning_rate": 7.923185571490657e-06, + "loss": 0.272, + "step": 22231 + }, + { + "epoch": 1.81, + "learning_rate": 7.922642329421992e-06, + "loss": 0.2152, + "step": 22232 + }, + { + "epoch": 1.81, + "learning_rate": 7.922099087353326e-06, + "loss": 0.4212, + "step": 22233 + }, + { + "epoch": 1.81, + "learning_rate": 7.92155584528466e-06, + "loss": 0.1892, + "step": 22234 + }, + { + "epoch": 1.81, + "learning_rate": 7.921012603215994e-06, + "loss": 0.4373, + "step": 22235 + }, + { + "epoch": 1.81, + "learning_rate": 7.920469361147329e-06, + "loss": 0.3277, + "step": 22236 + }, + { + "epoch": 1.81, + "learning_rate": 7.919926119078663e-06, + "loss": 0.2796, + "step": 22237 + }, + { + "epoch": 1.81, + "learning_rate": 7.919382877009997e-06, + "loss": 0.1646, + "step": 22238 + }, + { + "epoch": 1.81, + "learning_rate": 7.918839634941331e-06, + "loss": 0.5052, + "step": 22239 + }, + { + "epoch": 1.81, + "learning_rate": 7.918296392872664e-06, + "loss": 0.3225, + "step": 22240 + }, + { + "epoch": 1.81, + "learning_rate": 7.917753150803998e-06, + "loss": 0.2944, + "step": 22241 + }, + { + "epoch": 1.81, + "learning_rate": 7.917209908735332e-06, + "loss": 0.2004, + "step": 22242 + }, + { + "epoch": 1.81, + "learning_rate": 7.916666666666667e-06, + "loss": 0.123, + "step": 22243 + }, + { + "epoch": 1.81, + "learning_rate": 7.916123424598e-06, + "loss": 0.3002, + "step": 22244 + }, + { + "epoch": 1.81, + "learning_rate": 7.915580182529335e-06, + "loss": 0.2005, + "step": 22245 + }, + { + "epoch": 1.81, + "learning_rate": 7.91503694046067e-06, + "loss": 0.3659, + "step": 22246 + }, + { + "epoch": 1.81, + "learning_rate": 7.914493698392003e-06, + "loss": 0.252, + "step": 22247 + }, + { + "epoch": 1.81, + "learning_rate": 7.913950456323338e-06, + "loss": 0.2547, + "step": 22248 + }, + { + "epoch": 1.81, + "learning_rate": 7.913407214254672e-06, + "loss": 0.5997, + "step": 22249 + }, + { + "epoch": 1.81, + "learning_rate": 7.912863972186006e-06, + "loss": 0.3155, + "step": 22250 + }, + { + "epoch": 1.81, + "eval_accuracy": 0.8449312277126847, + "eval_loss": 0.431914746761322, + "eval_runtime": 22.2952, + "eval_samples_per_second": 440.229, + "eval_steps_per_second": 3.454, + "step": 22250 + }, + { + "epoch": 1.81, + "learning_rate": 7.91232073011734e-06, + "loss": 0.3912, + "step": 22251 + }, + { + "epoch": 1.81, + "learning_rate": 7.911777488048675e-06, + "loss": 0.4136, + "step": 22252 + }, + { + "epoch": 1.81, + "learning_rate": 7.911234245980009e-06, + "loss": 0.2927, + "step": 22253 + }, + { + "epoch": 1.81, + "learning_rate": 7.910691003911343e-06, + "loss": 0.2253, + "step": 22254 + }, + { + "epoch": 1.81, + "learning_rate": 7.910147761842677e-06, + "loss": 0.4644, + "step": 22255 + }, + { + "epoch": 1.81, + "learning_rate": 7.909604519774012e-06, + "loss": 0.155, + "step": 22256 + }, + { + "epoch": 1.81, + "learning_rate": 7.909061277705346e-06, + "loss": 0.4582, + "step": 22257 + }, + { + "epoch": 1.81, + "learning_rate": 7.908518035636682e-06, + "loss": 0.2862, + "step": 22258 + }, + { + "epoch": 1.81, + "learning_rate": 7.907974793568014e-06, + "loss": 0.34, + "step": 22259 + }, + { + "epoch": 1.81, + "learning_rate": 7.907431551499348e-06, + "loss": 0.2846, + "step": 22260 + }, + { + "epoch": 1.81, + "learning_rate": 7.906888309430683e-06, + "loss": 0.2689, + "step": 22261 + }, + { + "epoch": 1.81, + "learning_rate": 7.906345067362017e-06, + "loss": 0.5652, + "step": 22262 + }, + { + "epoch": 1.81, + "learning_rate": 7.905801825293351e-06, + "loss": 0.1834, + "step": 22263 + }, + { + "epoch": 1.81, + "learning_rate": 7.905258583224685e-06, + "loss": 0.5457, + "step": 22264 + }, + { + "epoch": 1.81, + "learning_rate": 7.90471534115602e-06, + "loss": 0.3645, + "step": 22265 + }, + { + "epoch": 1.81, + "learning_rate": 7.904172099087354e-06, + "loss": 0.3847, + "step": 22266 + }, + { + "epoch": 1.81, + "learning_rate": 7.903628857018688e-06, + "loss": 0.5268, + "step": 22267 + }, + { + "epoch": 1.81, + "learning_rate": 7.903085614950022e-06, + "loss": 0.2089, + "step": 22268 + }, + { + "epoch": 1.81, + "learning_rate": 7.902542372881357e-06, + "loss": 0.5335, + "step": 22269 + }, + { + "epoch": 1.81, + "learning_rate": 7.90199913081269e-06, + "loss": 0.3255, + "step": 22270 + }, + { + "epoch": 1.81, + "learning_rate": 7.901455888744025e-06, + "loss": 0.3549, + "step": 22271 + }, + { + "epoch": 1.81, + "learning_rate": 7.90091264667536e-06, + "loss": 0.4496, + "step": 22272 + }, + { + "epoch": 1.81, + "learning_rate": 7.900369404606693e-06, + "loss": 0.3436, + "step": 22273 + }, + { + "epoch": 1.82, + "learning_rate": 7.899826162538028e-06, + "loss": 0.2163, + "step": 22274 + }, + { + "epoch": 1.82, + "learning_rate": 7.899282920469362e-06, + "loss": 0.2724, + "step": 22275 + }, + { + "epoch": 1.82, + "learning_rate": 7.898739678400696e-06, + "loss": 0.3458, + "step": 22276 + }, + { + "epoch": 1.82, + "learning_rate": 7.89819643633203e-06, + "loss": 0.3847, + "step": 22277 + }, + { + "epoch": 1.82, + "learning_rate": 7.897653194263365e-06, + "loss": 0.3307, + "step": 22278 + }, + { + "epoch": 1.82, + "learning_rate": 7.897109952194699e-06, + "loss": 0.4288, + "step": 22279 + }, + { + "epoch": 1.82, + "learning_rate": 7.896566710126033e-06, + "loss": 0.4317, + "step": 22280 + }, + { + "epoch": 1.82, + "learning_rate": 7.896023468057367e-06, + "loss": 0.5491, + "step": 22281 + }, + { + "epoch": 1.82, + "learning_rate": 7.895480225988702e-06, + "loss": 0.3787, + "step": 22282 + }, + { + "epoch": 1.82, + "learning_rate": 7.894936983920036e-06, + "loss": 0.3152, + "step": 22283 + }, + { + "epoch": 1.82, + "learning_rate": 7.89439374185137e-06, + "loss": 0.5667, + "step": 22284 + }, + { + "epoch": 1.82, + "learning_rate": 7.893850499782704e-06, + "loss": 0.2721, + "step": 22285 + }, + { + "epoch": 1.82, + "learning_rate": 7.893307257714038e-06, + "loss": 0.3661, + "step": 22286 + }, + { + "epoch": 1.82, + "learning_rate": 7.892764015645373e-06, + "loss": 0.3816, + "step": 22287 + }, + { + "epoch": 1.82, + "learning_rate": 7.892220773576707e-06, + "loss": 0.3615, + "step": 22288 + }, + { + "epoch": 1.82, + "learning_rate": 7.891677531508041e-06, + "loss": 0.2688, + "step": 22289 + }, + { + "epoch": 1.82, + "learning_rate": 7.891134289439375e-06, + "loss": 0.2668, + "step": 22290 + }, + { + "epoch": 1.82, + "learning_rate": 7.89059104737071e-06, + "loss": 0.3276, + "step": 22291 + }, + { + "epoch": 1.82, + "learning_rate": 7.890047805302044e-06, + "loss": 0.4171, + "step": 22292 + }, + { + "epoch": 1.82, + "learning_rate": 7.889504563233378e-06, + "loss": 0.3978, + "step": 22293 + }, + { + "epoch": 1.82, + "learning_rate": 7.888961321164712e-06, + "loss": 0.1394, + "step": 22294 + }, + { + "epoch": 1.82, + "learning_rate": 7.888418079096047e-06, + "loss": 0.2631, + "step": 22295 + }, + { + "epoch": 1.82, + "learning_rate": 7.88787483702738e-06, + "loss": 0.2356, + "step": 22296 + }, + { + "epoch": 1.82, + "learning_rate": 7.887331594958713e-06, + "loss": 0.2043, + "step": 22297 + }, + { + "epoch": 1.82, + "learning_rate": 7.886788352890048e-06, + "loss": 0.4753, + "step": 22298 + }, + { + "epoch": 1.82, + "learning_rate": 7.886245110821382e-06, + "loss": 0.2811, + "step": 22299 + }, + { + "epoch": 1.82, + "learning_rate": 7.885701868752716e-06, + "loss": 0.3077, + "step": 22300 + }, + { + "epoch": 1.82, + "learning_rate": 7.88515862668405e-06, + "loss": 0.3581, + "step": 22301 + }, + { + "epoch": 1.82, + "learning_rate": 7.884615384615384e-06, + "loss": 0.4273, + "step": 22302 + }, + { + "epoch": 1.82, + "learning_rate": 7.884072142546719e-06, + "loss": 0.2352, + "step": 22303 + }, + { + "epoch": 1.82, + "learning_rate": 7.883528900478053e-06, + "loss": 0.3437, + "step": 22304 + }, + { + "epoch": 1.82, + "learning_rate": 7.882985658409387e-06, + "loss": 0.2906, + "step": 22305 + }, + { + "epoch": 1.82, + "learning_rate": 7.882442416340721e-06, + "loss": 0.2509, + "step": 22306 + }, + { + "epoch": 1.82, + "learning_rate": 7.881899174272056e-06, + "loss": 0.3556, + "step": 22307 + }, + { + "epoch": 1.82, + "learning_rate": 7.88135593220339e-06, + "loss": 0.3456, + "step": 22308 + }, + { + "epoch": 1.82, + "learning_rate": 7.880812690134724e-06, + "loss": 0.3603, + "step": 22309 + }, + { + "epoch": 1.82, + "learning_rate": 7.880269448066058e-06, + "loss": 0.397, + "step": 22310 + }, + { + "epoch": 1.82, + "learning_rate": 7.879726205997393e-06, + "loss": 0.1126, + "step": 22311 + }, + { + "epoch": 1.82, + "learning_rate": 7.879182963928728e-06, + "loss": 0.6312, + "step": 22312 + }, + { + "epoch": 1.82, + "learning_rate": 7.878639721860063e-06, + "loss": 0.426, + "step": 22313 + }, + { + "epoch": 1.82, + "learning_rate": 7.878096479791397e-06, + "loss": 0.4743, + "step": 22314 + }, + { + "epoch": 1.82, + "learning_rate": 7.877553237722731e-06, + "loss": 0.2096, + "step": 22315 + }, + { + "epoch": 1.82, + "learning_rate": 7.877009995654064e-06, + "loss": 0.7256, + "step": 22316 + }, + { + "epoch": 1.82, + "learning_rate": 7.876466753585398e-06, + "loss": 0.2733, + "step": 22317 + }, + { + "epoch": 1.82, + "learning_rate": 7.875923511516732e-06, + "loss": 0.5259, + "step": 22318 + }, + { + "epoch": 1.82, + "learning_rate": 7.875380269448066e-06, + "loss": 0.3547, + "step": 22319 + }, + { + "epoch": 1.82, + "learning_rate": 7.8748370273794e-06, + "loss": 0.2379, + "step": 22320 + }, + { + "epoch": 1.82, + "learning_rate": 7.874293785310735e-06, + "loss": 0.2269, + "step": 22321 + }, + { + "epoch": 1.82, + "learning_rate": 7.873750543242069e-06, + "loss": 0.4856, + "step": 22322 + }, + { + "epoch": 1.82, + "learning_rate": 7.873207301173403e-06, + "loss": 0.1041, + "step": 22323 + }, + { + "epoch": 1.82, + "learning_rate": 7.872664059104738e-06, + "loss": 0.3284, + "step": 22324 + }, + { + "epoch": 1.82, + "learning_rate": 7.872120817036072e-06, + "loss": 0.2408, + "step": 22325 + }, + { + "epoch": 1.82, + "learning_rate": 7.871577574967406e-06, + "loss": 0.422, + "step": 22326 + }, + { + "epoch": 1.82, + "learning_rate": 7.87103433289874e-06, + "loss": 0.4872, + "step": 22327 + }, + { + "epoch": 1.82, + "learning_rate": 7.870491090830074e-06, + "loss": 0.3086, + "step": 22328 + }, + { + "epoch": 1.82, + "learning_rate": 7.869947848761409e-06, + "loss": 0.2358, + "step": 22329 + }, + { + "epoch": 1.82, + "learning_rate": 7.869404606692743e-06, + "loss": 0.511, + "step": 22330 + }, + { + "epoch": 1.82, + "learning_rate": 7.868861364624077e-06, + "loss": 0.2351, + "step": 22331 + }, + { + "epoch": 1.82, + "learning_rate": 7.868318122555411e-06, + "loss": 0.4804, + "step": 22332 + }, + { + "epoch": 1.82, + "learning_rate": 7.867774880486746e-06, + "loss": 0.2503, + "step": 22333 + }, + { + "epoch": 1.82, + "learning_rate": 7.86723163841808e-06, + "loss": 0.1611, + "step": 22334 + }, + { + "epoch": 1.82, + "learning_rate": 7.866688396349414e-06, + "loss": 0.3615, + "step": 22335 + }, + { + "epoch": 1.82, + "learning_rate": 7.866145154280748e-06, + "loss": 0.2163, + "step": 22336 + }, + { + "epoch": 1.82, + "learning_rate": 7.865601912212083e-06, + "loss": 0.3614, + "step": 22337 + }, + { + "epoch": 1.82, + "learning_rate": 7.865058670143417e-06, + "loss": 0.2307, + "step": 22338 + }, + { + "epoch": 1.82, + "learning_rate": 7.864515428074751e-06, + "loss": 0.4096, + "step": 22339 + }, + { + "epoch": 1.82, + "learning_rate": 7.863972186006085e-06, + "loss": 0.2306, + "step": 22340 + }, + { + "epoch": 1.82, + "learning_rate": 7.86342894393742e-06, + "loss": 0.2634, + "step": 22341 + }, + { + "epoch": 1.82, + "learning_rate": 7.862885701868754e-06, + "loss": 0.3617, + "step": 22342 + }, + { + "epoch": 1.82, + "learning_rate": 7.862342459800088e-06, + "loss": 0.1739, + "step": 22343 + }, + { + "epoch": 1.82, + "learning_rate": 7.861799217731422e-06, + "loss": 0.5982, + "step": 22344 + }, + { + "epoch": 1.82, + "learning_rate": 7.861255975662756e-06, + "loss": 0.3569, + "step": 22345 + }, + { + "epoch": 1.82, + "learning_rate": 7.86071273359409e-06, + "loss": 0.3707, + "step": 22346 + }, + { + "epoch": 1.82, + "learning_rate": 7.860169491525425e-06, + "loss": 0.2391, + "step": 22347 + }, + { + "epoch": 1.82, + "learning_rate": 7.859626249456759e-06, + "loss": 0.3136, + "step": 22348 + }, + { + "epoch": 1.82, + "learning_rate": 7.859083007388093e-06, + "loss": 0.1796, + "step": 22349 + }, + { + "epoch": 1.82, + "learning_rate": 7.858539765319428e-06, + "loss": 0.4159, + "step": 22350 + }, + { + "epoch": 1.82, + "learning_rate": 7.857996523250762e-06, + "loss": 0.299, + "step": 22351 + }, + { + "epoch": 1.82, + "learning_rate": 7.857453281182096e-06, + "loss": 0.2978, + "step": 22352 + }, + { + "epoch": 1.82, + "learning_rate": 7.85691003911343e-06, + "loss": 0.4256, + "step": 22353 + }, + { + "epoch": 1.82, + "learning_rate": 7.856366797044763e-06, + "loss": 0.1578, + "step": 22354 + }, + { + "epoch": 1.82, + "learning_rate": 7.855823554976097e-06, + "loss": 0.3738, + "step": 22355 + }, + { + "epoch": 1.82, + "learning_rate": 7.855280312907431e-06, + "loss": 0.4639, + "step": 22356 + }, + { + "epoch": 1.82, + "learning_rate": 7.854737070838765e-06, + "loss": 0.4866, + "step": 22357 + }, + { + "epoch": 1.82, + "learning_rate": 7.8541938287701e-06, + "loss": 0.4745, + "step": 22358 + }, + { + "epoch": 1.82, + "learning_rate": 7.853650586701434e-06, + "loss": 0.3191, + "step": 22359 + }, + { + "epoch": 1.82, + "learning_rate": 7.853107344632768e-06, + "loss": 0.3516, + "step": 22360 + }, + { + "epoch": 1.82, + "learning_rate": 7.852564102564102e-06, + "loss": 0.4272, + "step": 22361 + }, + { + "epoch": 1.82, + "learning_rate": 7.852020860495437e-06, + "loss": 0.2647, + "step": 22362 + }, + { + "epoch": 1.82, + "learning_rate": 7.85147761842677e-06, + "loss": 0.4343, + "step": 22363 + }, + { + "epoch": 1.82, + "learning_rate": 7.850934376358105e-06, + "loss": 0.2241, + "step": 22364 + }, + { + "epoch": 1.82, + "learning_rate": 7.85039113428944e-06, + "loss": 0.3192, + "step": 22365 + }, + { + "epoch": 1.82, + "learning_rate": 7.849847892220775e-06, + "loss": 0.4027, + "step": 22366 + }, + { + "epoch": 1.82, + "learning_rate": 7.84930465015211e-06, + "loss": 0.6043, + "step": 22367 + }, + { + "epoch": 1.82, + "learning_rate": 7.848761408083444e-06, + "loss": 0.213, + "step": 22368 + }, + { + "epoch": 1.82, + "learning_rate": 7.848218166014778e-06, + "loss": 0.3496, + "step": 22369 + }, + { + "epoch": 1.82, + "learning_rate": 7.847674923946112e-06, + "loss": 0.519, + "step": 22370 + }, + { + "epoch": 1.82, + "learning_rate": 7.847131681877446e-06, + "loss": 0.3249, + "step": 22371 + }, + { + "epoch": 1.82, + "learning_rate": 7.84658843980878e-06, + "loss": 0.3101, + "step": 22372 + }, + { + "epoch": 1.82, + "learning_rate": 7.846045197740113e-06, + "loss": 0.3477, + "step": 22373 + }, + { + "epoch": 1.82, + "learning_rate": 7.845501955671447e-06, + "loss": 0.2216, + "step": 22374 + }, + { + "epoch": 1.82, + "learning_rate": 7.844958713602782e-06, + "loss": 0.1906, + "step": 22375 + }, + { + "epoch": 1.82, + "learning_rate": 7.844415471534116e-06, + "loss": 0.2498, + "step": 22376 + }, + { + "epoch": 1.82, + "learning_rate": 7.84387222946545e-06, + "loss": 0.1387, + "step": 22377 + }, + { + "epoch": 1.82, + "learning_rate": 7.843328987396784e-06, + "loss": 0.4925, + "step": 22378 + }, + { + "epoch": 1.82, + "learning_rate": 7.842785745328119e-06, + "loss": 0.3072, + "step": 22379 + }, + { + "epoch": 1.82, + "learning_rate": 7.842242503259453e-06, + "loss": 0.2632, + "step": 22380 + }, + { + "epoch": 1.82, + "learning_rate": 7.841699261190787e-06, + "loss": 0.3367, + "step": 22381 + }, + { + "epoch": 1.82, + "learning_rate": 7.841156019122121e-06, + "loss": 0.4323, + "step": 22382 + }, + { + "epoch": 1.82, + "learning_rate": 7.840612777053455e-06, + "loss": 0.2147, + "step": 22383 + }, + { + "epoch": 1.82, + "learning_rate": 7.84006953498479e-06, + "loss": 0.3901, + "step": 22384 + }, + { + "epoch": 1.82, + "learning_rate": 7.839526292916124e-06, + "loss": 0.293, + "step": 22385 + }, + { + "epoch": 1.82, + "learning_rate": 7.838983050847458e-06, + "loss": 0.3739, + "step": 22386 + }, + { + "epoch": 1.82, + "learning_rate": 7.838439808778792e-06, + "loss": 0.285, + "step": 22387 + }, + { + "epoch": 1.82, + "learning_rate": 7.837896566710127e-06, + "loss": 0.5546, + "step": 22388 + }, + { + "epoch": 1.82, + "learning_rate": 7.83735332464146e-06, + "loss": 0.5476, + "step": 22389 + }, + { + "epoch": 1.82, + "learning_rate": 7.836810082572795e-06, + "loss": 0.1179, + "step": 22390 + }, + { + "epoch": 1.82, + "learning_rate": 7.83626684050413e-06, + "loss": 0.3692, + "step": 22391 + }, + { + "epoch": 1.82, + "learning_rate": 7.835723598435464e-06, + "loss": 0.1779, + "step": 22392 + }, + { + "epoch": 1.82, + "learning_rate": 7.835180356366798e-06, + "loss": 0.3771, + "step": 22393 + }, + { + "epoch": 1.82, + "learning_rate": 7.834637114298132e-06, + "loss": 0.2876, + "step": 22394 + }, + { + "epoch": 1.82, + "learning_rate": 7.834093872229466e-06, + "loss": 0.3959, + "step": 22395 + }, + { + "epoch": 1.82, + "learning_rate": 7.8335506301608e-06, + "loss": 0.3257, + "step": 22396 + }, + { + "epoch": 1.83, + "learning_rate": 7.833007388092135e-06, + "loss": 0.1935, + "step": 22397 + }, + { + "epoch": 1.83, + "learning_rate": 7.832464146023469e-06, + "loss": 0.2808, + "step": 22398 + }, + { + "epoch": 1.83, + "learning_rate": 7.831920903954803e-06, + "loss": 0.3801, + "step": 22399 + }, + { + "epoch": 1.83, + "learning_rate": 7.831377661886137e-06, + "loss": 0.292, + "step": 22400 + }, + { + "epoch": 1.83, + "learning_rate": 7.830834419817472e-06, + "loss": 0.3137, + "step": 22401 + }, + { + "epoch": 1.83, + "learning_rate": 7.830291177748806e-06, + "loss": 0.4068, + "step": 22402 + }, + { + "epoch": 1.83, + "learning_rate": 7.82974793568014e-06, + "loss": 0.209, + "step": 22403 + }, + { + "epoch": 1.83, + "learning_rate": 7.829204693611474e-06, + "loss": 0.5282, + "step": 22404 + }, + { + "epoch": 1.83, + "learning_rate": 7.828661451542808e-06, + "loss": 0.1524, + "step": 22405 + }, + { + "epoch": 1.83, + "learning_rate": 7.828118209474143e-06, + "loss": 0.2608, + "step": 22406 + }, + { + "epoch": 1.83, + "learning_rate": 7.827574967405477e-06, + "loss": 0.1888, + "step": 22407 + }, + { + "epoch": 1.83, + "learning_rate": 7.827031725336811e-06, + "loss": 0.4375, + "step": 22408 + }, + { + "epoch": 1.83, + "learning_rate": 7.826488483268145e-06, + "loss": 0.2648, + "step": 22409 + }, + { + "epoch": 1.83, + "learning_rate": 7.82594524119948e-06, + "loss": 0.5066, + "step": 22410 + }, + { + "epoch": 1.83, + "learning_rate": 7.825401999130812e-06, + "loss": 0.2724, + "step": 22411 + }, + { + "epoch": 1.83, + "learning_rate": 7.824858757062146e-06, + "loss": 0.3137, + "step": 22412 + }, + { + "epoch": 1.83, + "learning_rate": 7.82431551499348e-06, + "loss": 0.3618, + "step": 22413 + }, + { + "epoch": 1.83, + "learning_rate": 7.823772272924815e-06, + "loss": 0.4788, + "step": 22414 + }, + { + "epoch": 1.83, + "learning_rate": 7.823229030856149e-06, + "loss": 0.4151, + "step": 22415 + }, + { + "epoch": 1.83, + "learning_rate": 7.822685788787483e-06, + "loss": 0.2769, + "step": 22416 + }, + { + "epoch": 1.83, + "learning_rate": 7.822142546718818e-06, + "loss": 0.4, + "step": 22417 + }, + { + "epoch": 1.83, + "learning_rate": 7.821599304650152e-06, + "loss": 0.3185, + "step": 22418 + }, + { + "epoch": 1.83, + "learning_rate": 7.821056062581486e-06, + "loss": 0.3027, + "step": 22419 + }, + { + "epoch": 1.83, + "learning_rate": 7.820512820512822e-06, + "loss": 0.2902, + "step": 22420 + }, + { + "epoch": 1.83, + "learning_rate": 7.819969578444156e-06, + "loss": 0.1997, + "step": 22421 + }, + { + "epoch": 1.83, + "learning_rate": 7.81942633637549e-06, + "loss": 0.3386, + "step": 22422 + }, + { + "epoch": 1.83, + "learning_rate": 7.818883094306825e-06, + "loss": 0.3216, + "step": 22423 + }, + { + "epoch": 1.83, + "learning_rate": 7.818339852238159e-06, + "loss": 0.5497, + "step": 22424 + }, + { + "epoch": 1.83, + "learning_rate": 7.817796610169493e-06, + "loss": 0.1365, + "step": 22425 + }, + { + "epoch": 1.83, + "learning_rate": 7.817253368100827e-06, + "loss": 0.4, + "step": 22426 + }, + { + "epoch": 1.83, + "learning_rate": 7.816710126032162e-06, + "loss": 0.2757, + "step": 22427 + }, + { + "epoch": 1.83, + "learning_rate": 7.816166883963496e-06, + "loss": 0.3844, + "step": 22428 + }, + { + "epoch": 1.83, + "learning_rate": 7.81562364189483e-06, + "loss": 0.1606, + "step": 22429 + }, + { + "epoch": 1.83, + "learning_rate": 7.815080399826163e-06, + "loss": 0.5799, + "step": 22430 + }, + { + "epoch": 1.83, + "learning_rate": 7.814537157757497e-06, + "loss": 0.4085, + "step": 22431 + }, + { + "epoch": 1.83, + "learning_rate": 7.813993915688831e-06, + "loss": 0.3719, + "step": 22432 + }, + { + "epoch": 1.83, + "learning_rate": 7.813450673620165e-06, + "loss": 0.1458, + "step": 22433 + }, + { + "epoch": 1.83, + "learning_rate": 7.8129074315515e-06, + "loss": 0.1937, + "step": 22434 + }, + { + "epoch": 1.83, + "learning_rate": 7.812364189482834e-06, + "loss": 0.1939, + "step": 22435 + }, + { + "epoch": 1.83, + "learning_rate": 7.811820947414168e-06, + "loss": 0.4693, + "step": 22436 + }, + { + "epoch": 1.83, + "learning_rate": 7.811277705345502e-06, + "loss": 0.1544, + "step": 22437 + }, + { + "epoch": 1.83, + "learning_rate": 7.810734463276836e-06, + "loss": 0.3305, + "step": 22438 + }, + { + "epoch": 1.83, + "learning_rate": 7.81019122120817e-06, + "loss": 0.5289, + "step": 22439 + }, + { + "epoch": 1.83, + "learning_rate": 7.809647979139505e-06, + "loss": 0.28, + "step": 22440 + }, + { + "epoch": 1.83, + "learning_rate": 7.809104737070839e-06, + "loss": 0.3309, + "step": 22441 + }, + { + "epoch": 1.83, + "learning_rate": 7.808561495002173e-06, + "loss": 0.521, + "step": 22442 + }, + { + "epoch": 1.83, + "learning_rate": 7.808018252933508e-06, + "loss": 0.1958, + "step": 22443 + }, + { + "epoch": 1.83, + "learning_rate": 7.807475010864842e-06, + "loss": 0.2308, + "step": 22444 + }, + { + "epoch": 1.83, + "learning_rate": 7.806931768796176e-06, + "loss": 0.174, + "step": 22445 + }, + { + "epoch": 1.83, + "learning_rate": 7.80638852672751e-06, + "loss": 0.3023, + "step": 22446 + }, + { + "epoch": 1.83, + "learning_rate": 7.805845284658844e-06, + "loss": 0.181, + "step": 22447 + }, + { + "epoch": 1.83, + "learning_rate": 7.805302042590179e-06, + "loss": 0.622, + "step": 22448 + }, + { + "epoch": 1.83, + "learning_rate": 7.804758800521513e-06, + "loss": 0.2203, + "step": 22449 + }, + { + "epoch": 1.83, + "learning_rate": 7.804215558452847e-06, + "loss": 0.388, + "step": 22450 + }, + { + "epoch": 1.83, + "learning_rate": 7.803672316384181e-06, + "loss": 0.2955, + "step": 22451 + }, + { + "epoch": 1.83, + "learning_rate": 7.803129074315516e-06, + "loss": 0.2256, + "step": 22452 + }, + { + "epoch": 1.83, + "learning_rate": 7.80258583224685e-06, + "loss": 0.3027, + "step": 22453 + }, + { + "epoch": 1.83, + "learning_rate": 7.802042590178184e-06, + "loss": 0.3521, + "step": 22454 + }, + { + "epoch": 1.83, + "learning_rate": 7.801499348109518e-06, + "loss": 0.1408, + "step": 22455 + }, + { + "epoch": 1.83, + "learning_rate": 7.800956106040853e-06, + "loss": 0.6405, + "step": 22456 + }, + { + "epoch": 1.83, + "learning_rate": 7.800412863972187e-06, + "loss": 0.3406, + "step": 22457 + }, + { + "epoch": 1.83, + "learning_rate": 7.799869621903521e-06, + "loss": 0.3473, + "step": 22458 + }, + { + "epoch": 1.83, + "learning_rate": 7.799326379834855e-06, + "loss": 0.2603, + "step": 22459 + }, + { + "epoch": 1.83, + "learning_rate": 7.79878313776619e-06, + "loss": 0.2899, + "step": 22460 + }, + { + "epoch": 1.83, + "learning_rate": 7.798239895697524e-06, + "loss": 0.1788, + "step": 22461 + }, + { + "epoch": 1.83, + "learning_rate": 7.797696653628858e-06, + "loss": 0.3178, + "step": 22462 + }, + { + "epoch": 1.83, + "learning_rate": 7.797153411560192e-06, + "loss": 0.2903, + "step": 22463 + }, + { + "epoch": 1.83, + "learning_rate": 7.796610169491526e-06, + "loss": 0.2505, + "step": 22464 + }, + { + "epoch": 1.83, + "learning_rate": 7.79606692742286e-06, + "loss": 0.2933, + "step": 22465 + }, + { + "epoch": 1.83, + "learning_rate": 7.795523685354195e-06, + "loss": 0.2573, + "step": 22466 + }, + { + "epoch": 1.83, + "learning_rate": 7.794980443285529e-06, + "loss": 0.2431, + "step": 22467 + }, + { + "epoch": 1.83, + "learning_rate": 7.794437201216863e-06, + "loss": 0.484, + "step": 22468 + }, + { + "epoch": 1.83, + "learning_rate": 7.793893959148196e-06, + "loss": 0.1703, + "step": 22469 + }, + { + "epoch": 1.83, + "learning_rate": 7.79335071707953e-06, + "loss": 0.3687, + "step": 22470 + }, + { + "epoch": 1.83, + "learning_rate": 7.792807475010864e-06, + "loss": 0.1293, + "step": 22471 + }, + { + "epoch": 1.83, + "learning_rate": 7.792264232942199e-06, + "loss": 0.4491, + "step": 22472 + }, + { + "epoch": 1.83, + "learning_rate": 7.791720990873533e-06, + "loss": 0.5115, + "step": 22473 + }, + { + "epoch": 1.83, + "learning_rate": 7.791177748804869e-06, + "loss": 0.2433, + "step": 22474 + }, + { + "epoch": 1.83, + "learning_rate": 7.790634506736203e-06, + "loss": 0.4325, + "step": 22475 + }, + { + "epoch": 1.83, + "learning_rate": 7.790091264667537e-06, + "loss": 0.242, + "step": 22476 + }, + { + "epoch": 1.83, + "learning_rate": 7.789548022598871e-06, + "loss": 0.2179, + "step": 22477 + }, + { + "epoch": 1.83, + "learning_rate": 7.789004780530206e-06, + "loss": 0.1721, + "step": 22478 + }, + { + "epoch": 1.83, + "learning_rate": 7.78846153846154e-06, + "loss": 0.3144, + "step": 22479 + }, + { + "epoch": 1.83, + "learning_rate": 7.787918296392874e-06, + "loss": 0.2589, + "step": 22480 + }, + { + "epoch": 1.83, + "learning_rate": 7.787375054324208e-06, + "loss": 0.3933, + "step": 22481 + }, + { + "epoch": 1.83, + "learning_rate": 7.786831812255543e-06, + "loss": 0.5242, + "step": 22482 + }, + { + "epoch": 1.83, + "learning_rate": 7.786288570186877e-06, + "loss": 0.5798, + "step": 22483 + }, + { + "epoch": 1.83, + "learning_rate": 7.785745328118211e-06, + "loss": 0.2674, + "step": 22484 + }, + { + "epoch": 1.83, + "learning_rate": 7.785202086049545e-06, + "loss": 0.149, + "step": 22485 + }, + { + "epoch": 1.83, + "learning_rate": 7.78465884398088e-06, + "loss": 0.3503, + "step": 22486 + }, + { + "epoch": 1.83, + "learning_rate": 7.784115601912214e-06, + "loss": 0.2186, + "step": 22487 + }, + { + "epoch": 1.83, + "learning_rate": 7.783572359843546e-06, + "loss": 0.1588, + "step": 22488 + }, + { + "epoch": 1.83, + "learning_rate": 7.78302911777488e-06, + "loss": 0.4748, + "step": 22489 + }, + { + "epoch": 1.83, + "learning_rate": 7.782485875706215e-06, + "loss": 0.1754, + "step": 22490 + }, + { + "epoch": 1.83, + "learning_rate": 7.781942633637549e-06, + "loss": 0.3699, + "step": 22491 + }, + { + "epoch": 1.83, + "learning_rate": 7.781399391568883e-06, + "loss": 0.5167, + "step": 22492 + }, + { + "epoch": 1.83, + "learning_rate": 7.780856149500217e-06, + "loss": 0.1911, + "step": 22493 + }, + { + "epoch": 1.83, + "learning_rate": 7.780312907431552e-06, + "loss": 0.2923, + "step": 22494 + }, + { + "epoch": 1.83, + "learning_rate": 7.779769665362886e-06, + "loss": 0.1962, + "step": 22495 + }, + { + "epoch": 1.83, + "learning_rate": 7.77922642329422e-06, + "loss": 0.2466, + "step": 22496 + }, + { + "epoch": 1.83, + "learning_rate": 7.778683181225554e-06, + "loss": 0.3136, + "step": 22497 + }, + { + "epoch": 1.83, + "learning_rate": 7.778139939156889e-06, + "loss": 0.3353, + "step": 22498 + }, + { + "epoch": 1.83, + "learning_rate": 7.777596697088223e-06, + "loss": 0.1573, + "step": 22499 + }, + { + "epoch": 1.83, + "learning_rate": 7.777053455019557e-06, + "loss": 0.3686, + "step": 22500 + }, + { + "epoch": 1.83, + "eval_accuracy": 0.8436067244014264, + "eval_loss": 0.4310610592365265, + "eval_runtime": 22.3445, + "eval_samples_per_second": 439.259, + "eval_steps_per_second": 3.446, + "step": 22500 + }, + { + "epoch": 1.83, + "learning_rate": 7.776510212950891e-06, + "loss": 0.3259, + "step": 22501 + }, + { + "epoch": 1.83, + "learning_rate": 7.775966970882225e-06, + "loss": 0.3016, + "step": 22502 + }, + { + "epoch": 1.83, + "learning_rate": 7.77542372881356e-06, + "loss": 0.5068, + "step": 22503 + }, + { + "epoch": 1.83, + "learning_rate": 7.774880486744894e-06, + "loss": 0.2295, + "step": 22504 + }, + { + "epoch": 1.83, + "learning_rate": 7.774337244676228e-06, + "loss": 0.322, + "step": 22505 + }, + { + "epoch": 1.83, + "learning_rate": 7.773794002607562e-06, + "loss": 0.2477, + "step": 22506 + }, + { + "epoch": 1.83, + "learning_rate": 7.773250760538897e-06, + "loss": 0.4825, + "step": 22507 + }, + { + "epoch": 1.83, + "learning_rate": 7.772707518470231e-06, + "loss": 0.2652, + "step": 22508 + }, + { + "epoch": 1.83, + "learning_rate": 7.772164276401565e-06, + "loss": 0.3493, + "step": 22509 + }, + { + "epoch": 1.83, + "learning_rate": 7.7716210343329e-06, + "loss": 0.3985, + "step": 22510 + }, + { + "epoch": 1.83, + "learning_rate": 7.771077792264234e-06, + "loss": 0.3596, + "step": 22511 + }, + { + "epoch": 1.83, + "learning_rate": 7.770534550195568e-06, + "loss": 0.1355, + "step": 22512 + }, + { + "epoch": 1.83, + "learning_rate": 7.769991308126902e-06, + "loss": 0.2327, + "step": 22513 + }, + { + "epoch": 1.83, + "learning_rate": 7.769448066058236e-06, + "loss": 0.2759, + "step": 22514 + }, + { + "epoch": 1.83, + "learning_rate": 7.76890482398957e-06, + "loss": 0.2068, + "step": 22515 + }, + { + "epoch": 1.83, + "learning_rate": 7.768361581920905e-06, + "loss": 0.1325, + "step": 22516 + }, + { + "epoch": 1.83, + "learning_rate": 7.767818339852239e-06, + "loss": 0.3057, + "step": 22517 + }, + { + "epoch": 1.83, + "learning_rate": 7.767275097783573e-06, + "loss": 0.3219, + "step": 22518 + }, + { + "epoch": 1.83, + "learning_rate": 7.766731855714907e-06, + "loss": 0.3599, + "step": 22519 + }, + { + "epoch": 1.84, + "learning_rate": 7.766188613646242e-06, + "loss": 0.1473, + "step": 22520 + }, + { + "epoch": 1.84, + "learning_rate": 7.765645371577576e-06, + "loss": 0.5767, + "step": 22521 + }, + { + "epoch": 1.84, + "learning_rate": 7.76510212950891e-06, + "loss": 0.3149, + "step": 22522 + }, + { + "epoch": 1.84, + "learning_rate": 7.764558887440244e-06, + "loss": 0.3168, + "step": 22523 + }, + { + "epoch": 1.84, + "learning_rate": 7.764015645371579e-06, + "loss": 0.2148, + "step": 22524 + }, + { + "epoch": 1.84, + "learning_rate": 7.763472403302913e-06, + "loss": 0.1755, + "step": 22525 + }, + { + "epoch": 1.84, + "learning_rate": 7.762929161234245e-06, + "loss": 0.238, + "step": 22526 + }, + { + "epoch": 1.84, + "learning_rate": 7.76238591916558e-06, + "loss": 0.6352, + "step": 22527 + }, + { + "epoch": 1.84, + "learning_rate": 7.761842677096915e-06, + "loss": 0.1331, + "step": 22528 + }, + { + "epoch": 1.84, + "learning_rate": 7.76129943502825e-06, + "loss": 0.2833, + "step": 22529 + }, + { + "epoch": 1.84, + "learning_rate": 7.760756192959584e-06, + "loss": 0.3169, + "step": 22530 + }, + { + "epoch": 1.84, + "learning_rate": 7.760212950890918e-06, + "loss": 0.1989, + "step": 22531 + }, + { + "epoch": 1.84, + "learning_rate": 7.759669708822252e-06, + "loss": 0.449, + "step": 22532 + }, + { + "epoch": 1.84, + "learning_rate": 7.759126466753587e-06, + "loss": 0.3226, + "step": 22533 + }, + { + "epoch": 1.84, + "learning_rate": 7.758583224684921e-06, + "loss": 0.4663, + "step": 22534 + }, + { + "epoch": 1.84, + "learning_rate": 7.758039982616255e-06, + "loss": 0.2926, + "step": 22535 + }, + { + "epoch": 1.84, + "learning_rate": 7.75749674054759e-06, + "loss": 0.2803, + "step": 22536 + }, + { + "epoch": 1.84, + "learning_rate": 7.756953498478924e-06, + "loss": 0.4235, + "step": 22537 + }, + { + "epoch": 1.84, + "learning_rate": 7.756410256410258e-06, + "loss": 0.5015, + "step": 22538 + }, + { + "epoch": 1.84, + "learning_rate": 7.755867014341592e-06, + "loss": 0.4892, + "step": 22539 + }, + { + "epoch": 1.84, + "learning_rate": 7.755323772272926e-06, + "loss": 0.2091, + "step": 22540 + }, + { + "epoch": 1.84, + "learning_rate": 7.75478053020426e-06, + "loss": 0.3685, + "step": 22541 + }, + { + "epoch": 1.84, + "learning_rate": 7.754237288135595e-06, + "loss": 0.3171, + "step": 22542 + }, + { + "epoch": 1.84, + "learning_rate": 7.753694046066929e-06, + "loss": 0.426, + "step": 22543 + }, + { + "epoch": 1.84, + "learning_rate": 7.753150803998263e-06, + "loss": 0.1735, + "step": 22544 + }, + { + "epoch": 1.84, + "learning_rate": 7.752607561929596e-06, + "loss": 0.3118, + "step": 22545 + }, + { + "epoch": 1.84, + "learning_rate": 7.75206431986093e-06, + "loss": 0.239, + "step": 22546 + }, + { + "epoch": 1.84, + "learning_rate": 7.751521077792264e-06, + "loss": 0.5054, + "step": 22547 + }, + { + "epoch": 1.84, + "learning_rate": 7.750977835723598e-06, + "loss": 0.5642, + "step": 22548 + }, + { + "epoch": 1.84, + "learning_rate": 7.750434593654933e-06, + "loss": 0.3566, + "step": 22549 + }, + { + "epoch": 1.84, + "learning_rate": 7.749891351586267e-06, + "loss": 0.2512, + "step": 22550 + }, + { + "epoch": 1.84, + "learning_rate": 7.749348109517601e-06, + "loss": 0.3858, + "step": 22551 + }, + { + "epoch": 1.84, + "learning_rate": 7.748804867448935e-06, + "loss": 0.3757, + "step": 22552 + }, + { + "epoch": 1.84, + "learning_rate": 7.74826162538027e-06, + "loss": 0.4776, + "step": 22553 + }, + { + "epoch": 1.84, + "learning_rate": 7.747718383311604e-06, + "loss": 0.1685, + "step": 22554 + }, + { + "epoch": 1.84, + "learning_rate": 7.747175141242938e-06, + "loss": 0.4331, + "step": 22555 + }, + { + "epoch": 1.84, + "learning_rate": 7.746631899174272e-06, + "loss": 0.2799, + "step": 22556 + }, + { + "epoch": 1.84, + "learning_rate": 7.746088657105606e-06, + "loss": 0.4314, + "step": 22557 + }, + { + "epoch": 1.84, + "learning_rate": 7.74554541503694e-06, + "loss": 0.1173, + "step": 22558 + }, + { + "epoch": 1.84, + "learning_rate": 7.745002172968275e-06, + "loss": 0.4659, + "step": 22559 + }, + { + "epoch": 1.84, + "learning_rate": 7.744458930899609e-06, + "loss": 0.1744, + "step": 22560 + }, + { + "epoch": 1.84, + "learning_rate": 7.743915688830943e-06, + "loss": 0.2773, + "step": 22561 + }, + { + "epoch": 1.84, + "learning_rate": 7.743372446762278e-06, + "loss": 0.3679, + "step": 22562 + }, + { + "epoch": 1.84, + "learning_rate": 7.742829204693612e-06, + "loss": 0.2254, + "step": 22563 + }, + { + "epoch": 1.84, + "learning_rate": 7.742285962624946e-06, + "loss": 0.5546, + "step": 22564 + }, + { + "epoch": 1.84, + "learning_rate": 7.74174272055628e-06, + "loss": 0.2212, + "step": 22565 + }, + { + "epoch": 1.84, + "learning_rate": 7.741199478487615e-06, + "loss": 0.2991, + "step": 22566 + }, + { + "epoch": 1.84, + "learning_rate": 7.740656236418949e-06, + "loss": 0.266, + "step": 22567 + }, + { + "epoch": 1.84, + "learning_rate": 7.740112994350283e-06, + "loss": 0.231, + "step": 22568 + }, + { + "epoch": 1.84, + "learning_rate": 7.739569752281617e-06, + "loss": 0.4398, + "step": 22569 + }, + { + "epoch": 1.84, + "learning_rate": 7.739026510212951e-06, + "loss": 0.378, + "step": 22570 + }, + { + "epoch": 1.84, + "learning_rate": 7.738483268144286e-06, + "loss": 0.1902, + "step": 22571 + }, + { + "epoch": 1.84, + "learning_rate": 7.73794002607562e-06, + "loss": 0.3269, + "step": 22572 + }, + { + "epoch": 1.84, + "learning_rate": 7.737396784006954e-06, + "loss": 0.2513, + "step": 22573 + }, + { + "epoch": 1.84, + "learning_rate": 7.736853541938288e-06, + "loss": 0.3489, + "step": 22574 + }, + { + "epoch": 1.84, + "learning_rate": 7.736310299869623e-06, + "loss": 0.332, + "step": 22575 + }, + { + "epoch": 1.84, + "learning_rate": 7.735767057800957e-06, + "loss": 0.1759, + "step": 22576 + }, + { + "epoch": 1.84, + "learning_rate": 7.735223815732291e-06, + "loss": 0.2948, + "step": 22577 + }, + { + "epoch": 1.84, + "learning_rate": 7.734680573663625e-06, + "loss": 0.2685, + "step": 22578 + }, + { + "epoch": 1.84, + "learning_rate": 7.73413733159496e-06, + "loss": 0.1458, + "step": 22579 + }, + { + "epoch": 1.84, + "learning_rate": 7.733594089526294e-06, + "loss": 0.273, + "step": 22580 + }, + { + "epoch": 1.84, + "learning_rate": 7.733050847457628e-06, + "loss": 0.2813, + "step": 22581 + }, + { + "epoch": 1.84, + "learning_rate": 7.732507605388962e-06, + "loss": 0.5052, + "step": 22582 + }, + { + "epoch": 1.84, + "learning_rate": 7.731964363320296e-06, + "loss": 0.1926, + "step": 22583 + }, + { + "epoch": 1.84, + "learning_rate": 7.73142112125163e-06, + "loss": 0.169, + "step": 22584 + }, + { + "epoch": 1.84, + "learning_rate": 7.730877879182965e-06, + "loss": 0.4701, + "step": 22585 + }, + { + "epoch": 1.84, + "learning_rate": 7.730334637114299e-06, + "loss": 0.2704, + "step": 22586 + }, + { + "epoch": 1.84, + "learning_rate": 7.729791395045633e-06, + "loss": 0.3965, + "step": 22587 + }, + { + "epoch": 1.84, + "learning_rate": 7.729248152976968e-06, + "loss": 0.287, + "step": 22588 + }, + { + "epoch": 1.84, + "learning_rate": 7.728704910908302e-06, + "loss": 0.2484, + "step": 22589 + }, + { + "epoch": 1.84, + "learning_rate": 7.728161668839636e-06, + "loss": 0.1545, + "step": 22590 + }, + { + "epoch": 1.84, + "learning_rate": 7.72761842677097e-06, + "loss": 0.4098, + "step": 22591 + }, + { + "epoch": 1.84, + "learning_rate": 7.727075184702305e-06, + "loss": 0.3583, + "step": 22592 + }, + { + "epoch": 1.84, + "learning_rate": 7.726531942633639e-06, + "loss": 0.4328, + "step": 22593 + }, + { + "epoch": 1.84, + "learning_rate": 7.725988700564973e-06, + "loss": 0.4623, + "step": 22594 + }, + { + "epoch": 1.84, + "learning_rate": 7.725445458496307e-06, + "loss": 0.4666, + "step": 22595 + }, + { + "epoch": 1.84, + "learning_rate": 7.724902216427641e-06, + "loss": 0.3063, + "step": 22596 + }, + { + "epoch": 1.84, + "learning_rate": 7.724358974358976e-06, + "loss": 0.2352, + "step": 22597 + }, + { + "epoch": 1.84, + "learning_rate": 7.72381573229031e-06, + "loss": 0.349, + "step": 22598 + }, + { + "epoch": 1.84, + "learning_rate": 7.723272490221644e-06, + "loss": 0.202, + "step": 22599 + }, + { + "epoch": 1.84, + "learning_rate": 7.722729248152978e-06, + "loss": 0.5233, + "step": 22600 + }, + { + "epoch": 1.84, + "learning_rate": 7.722186006084313e-06, + "loss": 0.4081, + "step": 22601 + }, + { + "epoch": 1.84, + "learning_rate": 7.721642764015645e-06, + "loss": 0.1229, + "step": 22602 + }, + { + "epoch": 1.84, + "learning_rate": 7.72109952194698e-06, + "loss": 0.3963, + "step": 22603 + }, + { + "epoch": 1.84, + "learning_rate": 7.720556279878314e-06, + "loss": 0.3329, + "step": 22604 + }, + { + "epoch": 1.84, + "learning_rate": 7.720013037809648e-06, + "loss": 0.2133, + "step": 22605 + }, + { + "epoch": 1.84, + "learning_rate": 7.719469795740982e-06, + "loss": 0.2205, + "step": 22606 + }, + { + "epoch": 1.84, + "learning_rate": 7.718926553672316e-06, + "loss": 0.1691, + "step": 22607 + }, + { + "epoch": 1.84, + "learning_rate": 7.71838331160365e-06, + "loss": 0.4965, + "step": 22608 + }, + { + "epoch": 1.84, + "learning_rate": 7.717840069534985e-06, + "loss": 0.3947, + "step": 22609 + }, + { + "epoch": 1.84, + "learning_rate": 7.717296827466319e-06, + "loss": 0.5091, + "step": 22610 + }, + { + "epoch": 1.84, + "learning_rate": 7.716753585397653e-06, + "loss": 0.3932, + "step": 22611 + }, + { + "epoch": 1.84, + "learning_rate": 7.716210343328987e-06, + "loss": 0.3903, + "step": 22612 + }, + { + "epoch": 1.84, + "learning_rate": 7.715667101260322e-06, + "loss": 0.3269, + "step": 22613 + }, + { + "epoch": 1.84, + "learning_rate": 7.715123859191656e-06, + "loss": 0.3058, + "step": 22614 + }, + { + "epoch": 1.84, + "learning_rate": 7.71458061712299e-06, + "loss": 0.2171, + "step": 22615 + }, + { + "epoch": 1.84, + "learning_rate": 7.714037375054324e-06, + "loss": 0.3171, + "step": 22616 + }, + { + "epoch": 1.84, + "learning_rate": 7.713494132985659e-06, + "loss": 0.3495, + "step": 22617 + }, + { + "epoch": 1.84, + "learning_rate": 7.712950890916993e-06, + "loss": 0.3714, + "step": 22618 + }, + { + "epoch": 1.84, + "learning_rate": 7.712407648848329e-06, + "loss": 0.1853, + "step": 22619 + }, + { + "epoch": 1.84, + "learning_rate": 7.711864406779663e-06, + "loss": 0.1678, + "step": 22620 + }, + { + "epoch": 1.84, + "learning_rate": 7.711321164710996e-06, + "loss": 0.2379, + "step": 22621 + }, + { + "epoch": 1.84, + "learning_rate": 7.71077792264233e-06, + "loss": 0.4724, + "step": 22622 + }, + { + "epoch": 1.84, + "learning_rate": 7.710234680573664e-06, + "loss": 0.1508, + "step": 22623 + }, + { + "epoch": 1.84, + "learning_rate": 7.709691438504998e-06, + "loss": 0.2628, + "step": 22624 + }, + { + "epoch": 1.84, + "learning_rate": 7.709148196436332e-06, + "loss": 0.506, + "step": 22625 + }, + { + "epoch": 1.84, + "learning_rate": 7.708604954367667e-06, + "loss": 0.1371, + "step": 22626 + }, + { + "epoch": 1.84, + "learning_rate": 7.708061712299001e-06, + "loss": 0.521, + "step": 22627 + }, + { + "epoch": 1.84, + "learning_rate": 7.707518470230335e-06, + "loss": 0.0851, + "step": 22628 + }, + { + "epoch": 1.84, + "learning_rate": 7.70697522816167e-06, + "loss": 0.4202, + "step": 22629 + }, + { + "epoch": 1.84, + "learning_rate": 7.706431986093004e-06, + "loss": 0.3981, + "step": 22630 + }, + { + "epoch": 1.84, + "learning_rate": 7.705888744024338e-06, + "loss": 0.612, + "step": 22631 + }, + { + "epoch": 1.84, + "learning_rate": 7.705345501955672e-06, + "loss": 0.2608, + "step": 22632 + }, + { + "epoch": 1.84, + "learning_rate": 7.704802259887006e-06, + "loss": 0.2678, + "step": 22633 + }, + { + "epoch": 1.84, + "learning_rate": 7.70425901781834e-06, + "loss": 0.344, + "step": 22634 + }, + { + "epoch": 1.84, + "learning_rate": 7.703715775749675e-06, + "loss": 0.4609, + "step": 22635 + }, + { + "epoch": 1.84, + "learning_rate": 7.703172533681009e-06, + "loss": 0.2996, + "step": 22636 + }, + { + "epoch": 1.84, + "learning_rate": 7.702629291612343e-06, + "loss": 0.1547, + "step": 22637 + }, + { + "epoch": 1.84, + "learning_rate": 7.702086049543677e-06, + "loss": 0.2133, + "step": 22638 + }, + { + "epoch": 1.84, + "learning_rate": 7.701542807475012e-06, + "loss": 0.2751, + "step": 22639 + }, + { + "epoch": 1.84, + "learning_rate": 7.700999565406346e-06, + "loss": 0.2022, + "step": 22640 + }, + { + "epoch": 1.84, + "learning_rate": 7.70045632333768e-06, + "loss": 0.2842, + "step": 22641 + }, + { + "epoch": 1.85, + "learning_rate": 7.699913081269014e-06, + "loss": 0.3598, + "step": 22642 + }, + { + "epoch": 1.85, + "learning_rate": 7.699369839200349e-06, + "loss": 0.2788, + "step": 22643 + }, + { + "epoch": 1.85, + "learning_rate": 7.698826597131683e-06, + "loss": 0.3666, + "step": 22644 + }, + { + "epoch": 1.85, + "learning_rate": 7.698283355063017e-06, + "loss": 0.2581, + "step": 22645 + }, + { + "epoch": 1.85, + "learning_rate": 7.697740112994351e-06, + "loss": 0.2441, + "step": 22646 + }, + { + "epoch": 1.85, + "learning_rate": 7.697196870925686e-06, + "loss": 0.2852, + "step": 22647 + }, + { + "epoch": 1.85, + "learning_rate": 7.69665362885702e-06, + "loss": 0.3123, + "step": 22648 + }, + { + "epoch": 1.85, + "learning_rate": 7.696110386788354e-06, + "loss": 0.3654, + "step": 22649 + }, + { + "epoch": 1.85, + "learning_rate": 7.695567144719688e-06, + "loss": 0.1396, + "step": 22650 + }, + { + "epoch": 1.85, + "learning_rate": 7.695023902651022e-06, + "loss": 0.1377, + "step": 22651 + }, + { + "epoch": 1.85, + "learning_rate": 7.694480660582357e-06, + "loss": 0.1997, + "step": 22652 + }, + { + "epoch": 1.85, + "learning_rate": 7.693937418513691e-06, + "loss": 0.2112, + "step": 22653 + }, + { + "epoch": 1.85, + "learning_rate": 7.693394176445025e-06, + "loss": 0.5443, + "step": 22654 + }, + { + "epoch": 1.85, + "learning_rate": 7.69285093437636e-06, + "loss": 0.3009, + "step": 22655 + }, + { + "epoch": 1.85, + "learning_rate": 7.692307692307694e-06, + "loss": 0.5641, + "step": 22656 + }, + { + "epoch": 1.85, + "learning_rate": 7.691764450239028e-06, + "loss": 0.2707, + "step": 22657 + }, + { + "epoch": 1.85, + "learning_rate": 7.691221208170362e-06, + "loss": 0.2108, + "step": 22658 + }, + { + "epoch": 1.85, + "learning_rate": 7.690677966101695e-06, + "loss": 0.1941, + "step": 22659 + }, + { + "epoch": 1.85, + "learning_rate": 7.690134724033029e-06, + "loss": 0.5868, + "step": 22660 + }, + { + "epoch": 1.85, + "learning_rate": 7.689591481964363e-06, + "loss": 0.3506, + "step": 22661 + }, + { + "epoch": 1.85, + "learning_rate": 7.689048239895697e-06, + "loss": 0.4887, + "step": 22662 + }, + { + "epoch": 1.85, + "learning_rate": 7.688504997827032e-06, + "loss": 0.1174, + "step": 22663 + }, + { + "epoch": 1.85, + "learning_rate": 7.687961755758366e-06, + "loss": 0.1816, + "step": 22664 + }, + { + "epoch": 1.85, + "learning_rate": 7.6874185136897e-06, + "loss": 0.3856, + "step": 22665 + }, + { + "epoch": 1.85, + "learning_rate": 7.686875271621034e-06, + "loss": 0.3883, + "step": 22666 + }, + { + "epoch": 1.85, + "learning_rate": 7.686332029552368e-06, + "loss": 0.2449, + "step": 22667 + }, + { + "epoch": 1.85, + "learning_rate": 7.685788787483703e-06, + "loss": 0.3262, + "step": 22668 + }, + { + "epoch": 1.85, + "learning_rate": 7.685245545415037e-06, + "loss": 0.2062, + "step": 22669 + }, + { + "epoch": 1.85, + "learning_rate": 7.684702303346371e-06, + "loss": 0.3443, + "step": 22670 + }, + { + "epoch": 1.85, + "learning_rate": 7.684159061277705e-06, + "loss": 0.1503, + "step": 22671 + }, + { + "epoch": 1.85, + "learning_rate": 7.68361581920904e-06, + "loss": 0.2881, + "step": 22672 + }, + { + "epoch": 1.85, + "learning_rate": 7.683072577140376e-06, + "loss": 0.3725, + "step": 22673 + }, + { + "epoch": 1.85, + "learning_rate": 7.68252933507171e-06, + "loss": 0.532, + "step": 22674 + }, + { + "epoch": 1.85, + "learning_rate": 7.681986093003044e-06, + "loss": 0.3867, + "step": 22675 + }, + { + "epoch": 1.85, + "learning_rate": 7.681442850934378e-06, + "loss": 0.303, + "step": 22676 + }, + { + "epoch": 1.85, + "learning_rate": 7.680899608865712e-06, + "loss": 0.2929, + "step": 22677 + }, + { + "epoch": 1.85, + "learning_rate": 7.680356366797045e-06, + "loss": 0.2878, + "step": 22678 + }, + { + "epoch": 1.85, + "learning_rate": 7.67981312472838e-06, + "loss": 0.3846, + "step": 22679 + }, + { + "epoch": 1.85, + "learning_rate": 7.679269882659713e-06, + "loss": 0.3746, + "step": 22680 + }, + { + "epoch": 1.85, + "learning_rate": 7.678726640591048e-06, + "loss": 0.235, + "step": 22681 + }, + { + "epoch": 1.85, + "learning_rate": 7.678183398522382e-06, + "loss": 0.2811, + "step": 22682 + }, + { + "epoch": 1.85, + "learning_rate": 7.677640156453716e-06, + "loss": 0.2555, + "step": 22683 + }, + { + "epoch": 1.85, + "learning_rate": 7.67709691438505e-06, + "loss": 0.1198, + "step": 22684 + }, + { + "epoch": 1.85, + "learning_rate": 7.676553672316385e-06, + "loss": 0.4156, + "step": 22685 + }, + { + "epoch": 1.85, + "learning_rate": 7.676010430247719e-06, + "loss": 0.2648, + "step": 22686 + }, + { + "epoch": 1.85, + "learning_rate": 7.675467188179053e-06, + "loss": 0.4541, + "step": 22687 + }, + { + "epoch": 1.85, + "learning_rate": 7.674923946110387e-06, + "loss": 0.1772, + "step": 22688 + }, + { + "epoch": 1.85, + "learning_rate": 7.674380704041722e-06, + "loss": 0.1642, + "step": 22689 + }, + { + "epoch": 1.85, + "learning_rate": 7.673837461973056e-06, + "loss": 0.4774, + "step": 22690 + }, + { + "epoch": 1.85, + "learning_rate": 7.67329421990439e-06, + "loss": 0.2454, + "step": 22691 + }, + { + "epoch": 1.85, + "learning_rate": 7.672750977835724e-06, + "loss": 0.252, + "step": 22692 + }, + { + "epoch": 1.85, + "learning_rate": 7.672207735767058e-06, + "loss": 0.4088, + "step": 22693 + }, + { + "epoch": 1.85, + "learning_rate": 7.671664493698393e-06, + "loss": 0.2232, + "step": 22694 + }, + { + "epoch": 1.85, + "learning_rate": 7.671121251629727e-06, + "loss": 0.3953, + "step": 22695 + }, + { + "epoch": 1.85, + "learning_rate": 7.670578009561061e-06, + "loss": 0.3056, + "step": 22696 + }, + { + "epoch": 1.85, + "learning_rate": 7.670034767492395e-06, + "loss": 0.2523, + "step": 22697 + }, + { + "epoch": 1.85, + "learning_rate": 7.66949152542373e-06, + "loss": 0.3038, + "step": 22698 + }, + { + "epoch": 1.85, + "learning_rate": 7.668948283355064e-06, + "loss": 0.3515, + "step": 22699 + }, + { + "epoch": 1.85, + "learning_rate": 7.668405041286398e-06, + "loss": 0.3203, + "step": 22700 + }, + { + "epoch": 1.85, + "learning_rate": 7.667861799217732e-06, + "loss": 0.4502, + "step": 22701 + }, + { + "epoch": 1.85, + "learning_rate": 7.667318557149066e-06, + "loss": 0.5679, + "step": 22702 + }, + { + "epoch": 1.85, + "learning_rate": 7.6667753150804e-06, + "loss": 0.2536, + "step": 22703 + }, + { + "epoch": 1.85, + "learning_rate": 7.666232073011735e-06, + "loss": 0.3875, + "step": 22704 + }, + { + "epoch": 1.85, + "learning_rate": 7.66568883094307e-06, + "loss": 0.2701, + "step": 22705 + }, + { + "epoch": 1.85, + "learning_rate": 7.665145588874403e-06, + "loss": 0.4586, + "step": 22706 + }, + { + "epoch": 1.85, + "learning_rate": 7.664602346805738e-06, + "loss": 0.3775, + "step": 22707 + }, + { + "epoch": 1.85, + "learning_rate": 7.664059104737072e-06, + "loss": 0.2229, + "step": 22708 + }, + { + "epoch": 1.85, + "learning_rate": 7.663515862668406e-06, + "loss": 0.3209, + "step": 22709 + }, + { + "epoch": 1.85, + "learning_rate": 7.66297262059974e-06, + "loss": 0.2928, + "step": 22710 + }, + { + "epoch": 1.85, + "learning_rate": 7.662429378531075e-06, + "loss": 0.2734, + "step": 22711 + }, + { + "epoch": 1.85, + "learning_rate": 7.661886136462409e-06, + "loss": 0.3457, + "step": 22712 + }, + { + "epoch": 1.85, + "learning_rate": 7.661342894393743e-06, + "loss": 0.2323, + "step": 22713 + }, + { + "epoch": 1.85, + "learning_rate": 7.660799652325077e-06, + "loss": 0.3964, + "step": 22714 + }, + { + "epoch": 1.85, + "learning_rate": 7.660256410256411e-06, + "loss": 0.3519, + "step": 22715 + }, + { + "epoch": 1.85, + "learning_rate": 7.659713168187744e-06, + "loss": 0.2963, + "step": 22716 + }, + { + "epoch": 1.85, + "learning_rate": 7.659169926119078e-06, + "loss": 0.3016, + "step": 22717 + }, + { + "epoch": 1.85, + "learning_rate": 7.658626684050412e-06, + "loss": 0.1643, + "step": 22718 + }, + { + "epoch": 1.85, + "learning_rate": 7.658083441981747e-06, + "loss": 0.2446, + "step": 22719 + }, + { + "epoch": 1.85, + "learning_rate": 7.657540199913081e-06, + "loss": 0.3088, + "step": 22720 + }, + { + "epoch": 1.85, + "learning_rate": 7.656996957844415e-06, + "loss": 0.2462, + "step": 22721 + }, + { + "epoch": 1.85, + "learning_rate": 7.65645371577575e-06, + "loss": 0.4729, + "step": 22722 + }, + { + "epoch": 1.85, + "learning_rate": 7.655910473707084e-06, + "loss": 0.1834, + "step": 22723 + }, + { + "epoch": 1.85, + "learning_rate": 7.655367231638418e-06, + "loss": 0.3135, + "step": 22724 + }, + { + "epoch": 1.85, + "learning_rate": 7.654823989569752e-06, + "loss": 0.172, + "step": 22725 + }, + { + "epoch": 1.85, + "learning_rate": 7.654280747501086e-06, + "loss": 0.2719, + "step": 22726 + }, + { + "epoch": 1.85, + "learning_rate": 7.653737505432422e-06, + "loss": 0.2291, + "step": 22727 + }, + { + "epoch": 1.85, + "learning_rate": 7.653194263363756e-06, + "loss": 0.3847, + "step": 22728 + }, + { + "epoch": 1.85, + "learning_rate": 7.65265102129509e-06, + "loss": 0.1988, + "step": 22729 + }, + { + "epoch": 1.85, + "learning_rate": 7.652107779226425e-06, + "loss": 0.2506, + "step": 22730 + }, + { + "epoch": 1.85, + "learning_rate": 7.65156453715776e-06, + "loss": 0.458, + "step": 22731 + }, + { + "epoch": 1.85, + "learning_rate": 7.651021295089093e-06, + "loss": 0.3939, + "step": 22732 + }, + { + "epoch": 1.85, + "learning_rate": 7.650478053020428e-06, + "loss": 0.3026, + "step": 22733 + }, + { + "epoch": 1.85, + "learning_rate": 7.649934810951762e-06, + "loss": 0.4209, + "step": 22734 + }, + { + "epoch": 1.85, + "learning_rate": 7.649391568883094e-06, + "loss": 0.1662, + "step": 22735 + }, + { + "epoch": 1.85, + "learning_rate": 7.648848326814429e-06, + "loss": 0.2343, + "step": 22736 + }, + { + "epoch": 1.85, + "learning_rate": 7.648305084745763e-06, + "loss": 0.2287, + "step": 22737 + }, + { + "epoch": 1.85, + "learning_rate": 7.647761842677097e-06, + "loss": 0.1027, + "step": 22738 + }, + { + "epoch": 1.85, + "learning_rate": 7.647218600608431e-06, + "loss": 0.3792, + "step": 22739 + }, + { + "epoch": 1.85, + "learning_rate": 7.646675358539766e-06, + "loss": 0.1956, + "step": 22740 + }, + { + "epoch": 1.85, + "learning_rate": 7.6461321164711e-06, + "loss": 0.4191, + "step": 22741 + }, + { + "epoch": 1.85, + "learning_rate": 7.645588874402434e-06, + "loss": 0.3622, + "step": 22742 + }, + { + "epoch": 1.85, + "learning_rate": 7.645045632333768e-06, + "loss": 0.3632, + "step": 22743 + }, + { + "epoch": 1.85, + "learning_rate": 7.644502390265102e-06, + "loss": 0.2448, + "step": 22744 + }, + { + "epoch": 1.85, + "learning_rate": 7.643959148196437e-06, + "loss": 0.3342, + "step": 22745 + }, + { + "epoch": 1.85, + "learning_rate": 7.643415906127771e-06, + "loss": 0.3375, + "step": 22746 + }, + { + "epoch": 1.85, + "learning_rate": 7.642872664059105e-06, + "loss": 0.3131, + "step": 22747 + }, + { + "epoch": 1.85, + "learning_rate": 7.64232942199044e-06, + "loss": 0.524, + "step": 22748 + }, + { + "epoch": 1.85, + "learning_rate": 7.641786179921774e-06, + "loss": 0.4286, + "step": 22749 + }, + { + "epoch": 1.85, + "learning_rate": 7.641242937853108e-06, + "loss": 0.3312, + "step": 22750 + }, + { + "epoch": 1.85, + "eval_accuracy": 0.841874681609781, + "eval_loss": 0.4434255361557007, + "eval_runtime": 22.2193, + "eval_samples_per_second": 441.733, + "eval_steps_per_second": 3.465, + "step": 22750 + }, + { + "epoch": 1.85, + "learning_rate": 7.640699695784442e-06, + "loss": 0.1869, + "step": 22751 + }, + { + "epoch": 1.85, + "learning_rate": 7.640156453715776e-06, + "loss": 0.276, + "step": 22752 + }, + { + "epoch": 1.85, + "learning_rate": 7.63961321164711e-06, + "loss": 0.4619, + "step": 22753 + }, + { + "epoch": 1.85, + "learning_rate": 7.639069969578445e-06, + "loss": 0.1197, + "step": 22754 + }, + { + "epoch": 1.85, + "learning_rate": 7.638526727509779e-06, + "loss": 0.3, + "step": 22755 + }, + { + "epoch": 1.85, + "learning_rate": 7.637983485441113e-06, + "loss": 0.462, + "step": 22756 + }, + { + "epoch": 1.85, + "learning_rate": 7.637440243372447e-06, + "loss": 0.2189, + "step": 22757 + }, + { + "epoch": 1.85, + "learning_rate": 7.636897001303782e-06, + "loss": 0.4533, + "step": 22758 + }, + { + "epoch": 1.85, + "learning_rate": 7.636353759235116e-06, + "loss": 0.483, + "step": 22759 + }, + { + "epoch": 1.85, + "learning_rate": 7.63581051716645e-06, + "loss": 0.4421, + "step": 22760 + }, + { + "epoch": 1.85, + "learning_rate": 7.635267275097784e-06, + "loss": 0.3284, + "step": 22761 + }, + { + "epoch": 1.85, + "learning_rate": 7.634724033029119e-06, + "loss": 0.3177, + "step": 22762 + }, + { + "epoch": 1.85, + "learning_rate": 7.634180790960453e-06, + "loss": 0.34, + "step": 22763 + }, + { + "epoch": 1.85, + "learning_rate": 7.633637548891787e-06, + "loss": 0.2419, + "step": 22764 + }, + { + "epoch": 1.86, + "learning_rate": 7.633094306823121e-06, + "loss": 0.1051, + "step": 22765 + }, + { + "epoch": 1.86, + "learning_rate": 7.632551064754456e-06, + "loss": 0.3777, + "step": 22766 + }, + { + "epoch": 1.86, + "learning_rate": 7.63200782268579e-06, + "loss": 0.3128, + "step": 22767 + }, + { + "epoch": 1.86, + "learning_rate": 7.631464580617124e-06, + "loss": 0.4126, + "step": 22768 + }, + { + "epoch": 1.86, + "learning_rate": 7.630921338548458e-06, + "loss": 0.3154, + "step": 22769 + }, + { + "epoch": 1.86, + "learning_rate": 7.630378096479792e-06, + "loss": 0.0776, + "step": 22770 + }, + { + "epoch": 1.86, + "learning_rate": 7.629834854411127e-06, + "loss": 0.2183, + "step": 22771 + }, + { + "epoch": 1.86, + "learning_rate": 7.629291612342461e-06, + "loss": 0.0852, + "step": 22772 + }, + { + "epoch": 1.86, + "learning_rate": 7.628748370273794e-06, + "loss": 0.2645, + "step": 22773 + }, + { + "epoch": 1.86, + "learning_rate": 7.6282051282051286e-06, + "loss": 0.3126, + "step": 22774 + }, + { + "epoch": 1.86, + "learning_rate": 7.627661886136463e-06, + "loss": 0.2702, + "step": 22775 + }, + { + "epoch": 1.86, + "learning_rate": 7.627118644067797e-06, + "loss": 0.3331, + "step": 22776 + }, + { + "epoch": 1.86, + "learning_rate": 7.626575401999131e-06, + "loss": 0.4078, + "step": 22777 + }, + { + "epoch": 1.86, + "learning_rate": 7.6260321599304655e-06, + "loss": 0.1843, + "step": 22778 + }, + { + "epoch": 1.86, + "learning_rate": 7.6254889178618e-06, + "loss": 0.3524, + "step": 22779 + }, + { + "epoch": 1.86, + "learning_rate": 7.624945675793134e-06, + "loss": 0.3285, + "step": 22780 + }, + { + "epoch": 1.86, + "learning_rate": 7.624402433724468e-06, + "loss": 0.2955, + "step": 22781 + }, + { + "epoch": 1.86, + "learning_rate": 7.623859191655802e-06, + "loss": 0.1533, + "step": 22782 + }, + { + "epoch": 1.86, + "learning_rate": 7.623315949587137e-06, + "loss": 0.479, + "step": 22783 + }, + { + "epoch": 1.86, + "learning_rate": 7.622772707518471e-06, + "loss": 0.2673, + "step": 22784 + }, + { + "epoch": 1.86, + "learning_rate": 7.622229465449805e-06, + "loss": 0.1698, + "step": 22785 + }, + { + "epoch": 1.86, + "learning_rate": 7.621686223381139e-06, + "loss": 0.4251, + "step": 22786 + }, + { + "epoch": 1.86, + "learning_rate": 7.6211429813124736e-06, + "loss": 0.3384, + "step": 22787 + }, + { + "epoch": 1.86, + "learning_rate": 7.620599739243808e-06, + "loss": 0.2143, + "step": 22788 + }, + { + "epoch": 1.86, + "learning_rate": 7.620056497175142e-06, + "loss": 0.4545, + "step": 22789 + }, + { + "epoch": 1.86, + "learning_rate": 7.619513255106476e-06, + "loss": 0.3966, + "step": 22790 + }, + { + "epoch": 1.86, + "learning_rate": 7.6189700130378105e-06, + "loss": 0.4344, + "step": 22791 + }, + { + "epoch": 1.86, + "learning_rate": 7.618426770969144e-06, + "loss": 0.2731, + "step": 22792 + }, + { + "epoch": 1.86, + "learning_rate": 7.617883528900478e-06, + "loss": 0.2191, + "step": 22793 + }, + { + "epoch": 1.86, + "learning_rate": 7.617340286831812e-06, + "loss": 0.368, + "step": 22794 + }, + { + "epoch": 1.86, + "learning_rate": 7.6167970447631466e-06, + "loss": 0.3345, + "step": 22795 + }, + { + "epoch": 1.86, + "learning_rate": 7.616253802694481e-06, + "loss": 0.1129, + "step": 22796 + }, + { + "epoch": 1.86, + "learning_rate": 7.615710560625815e-06, + "loss": 0.4872, + "step": 22797 + }, + { + "epoch": 1.86, + "learning_rate": 7.615167318557149e-06, + "loss": 0.1771, + "step": 22798 + }, + { + "epoch": 1.86, + "learning_rate": 7.6146240764884835e-06, + "loss": 0.4114, + "step": 22799 + }, + { + "epoch": 1.86, + "learning_rate": 7.614080834419818e-06, + "loss": 0.3462, + "step": 22800 + }, + { + "epoch": 1.86, + "learning_rate": 7.613537592351152e-06, + "loss": 0.3135, + "step": 22801 + }, + { + "epoch": 1.86, + "learning_rate": 7.612994350282486e-06, + "loss": 0.2744, + "step": 22802 + }, + { + "epoch": 1.86, + "learning_rate": 7.612451108213821e-06, + "loss": 0.2707, + "step": 22803 + }, + { + "epoch": 1.86, + "learning_rate": 7.6119078661451555e-06, + "loss": 0.3004, + "step": 22804 + }, + { + "epoch": 1.86, + "learning_rate": 7.61136462407649e-06, + "loss": 0.3299, + "step": 22805 + }, + { + "epoch": 1.86, + "learning_rate": 7.610821382007824e-06, + "loss": 0.3199, + "step": 22806 + }, + { + "epoch": 1.86, + "learning_rate": 7.610278139939158e-06, + "loss": 0.292, + "step": 22807 + }, + { + "epoch": 1.86, + "learning_rate": 7.609734897870492e-06, + "loss": 0.2362, + "step": 22808 + }, + { + "epoch": 1.86, + "learning_rate": 7.609191655801827e-06, + "loss": 0.4874, + "step": 22809 + }, + { + "epoch": 1.86, + "learning_rate": 7.608648413733161e-06, + "loss": 0.4483, + "step": 22810 + }, + { + "epoch": 1.86, + "learning_rate": 7.608105171664493e-06, + "loss": 0.4372, + "step": 22811 + }, + { + "epoch": 1.86, + "learning_rate": 7.6075619295958285e-06, + "loss": 0.4099, + "step": 22812 + }, + { + "epoch": 1.86, + "learning_rate": 7.607018687527163e-06, + "loss": 0.3495, + "step": 22813 + }, + { + "epoch": 1.86, + "learning_rate": 7.606475445458497e-06, + "loss": 0.397, + "step": 22814 + }, + { + "epoch": 1.86, + "learning_rate": 7.605932203389831e-06, + "loss": 0.3671, + "step": 22815 + }, + { + "epoch": 1.86, + "learning_rate": 7.605388961321165e-06, + "loss": 0.173, + "step": 22816 + }, + { + "epoch": 1.86, + "learning_rate": 7.6048457192525e-06, + "loss": 0.5153, + "step": 22817 + }, + { + "epoch": 1.86, + "learning_rate": 7.604302477183834e-06, + "loss": 0.2473, + "step": 22818 + }, + { + "epoch": 1.86, + "learning_rate": 7.603759235115168e-06, + "loss": 0.6194, + "step": 22819 + }, + { + "epoch": 1.86, + "learning_rate": 7.603215993046502e-06, + "loss": 0.3728, + "step": 22820 + }, + { + "epoch": 1.86, + "learning_rate": 7.6026727509778365e-06, + "loss": 0.4328, + "step": 22821 + }, + { + "epoch": 1.86, + "learning_rate": 7.602129508909171e-06, + "loss": 0.1679, + "step": 22822 + }, + { + "epoch": 1.86, + "learning_rate": 7.601586266840505e-06, + "loss": 0.1558, + "step": 22823 + }, + { + "epoch": 1.86, + "learning_rate": 7.601043024771839e-06, + "loss": 0.4644, + "step": 22824 + }, + { + "epoch": 1.86, + "learning_rate": 7.6004997827031735e-06, + "loss": 0.3564, + "step": 22825 + }, + { + "epoch": 1.86, + "learning_rate": 7.599956540634508e-06, + "loss": 0.2694, + "step": 22826 + }, + { + "epoch": 1.86, + "learning_rate": 7.599413298565842e-06, + "loss": 0.3678, + "step": 22827 + }, + { + "epoch": 1.86, + "learning_rate": 7.598870056497176e-06, + "loss": 0.1912, + "step": 22828 + }, + { + "epoch": 1.86, + "learning_rate": 7.59832681442851e-06, + "loss": 0.3075, + "step": 22829 + }, + { + "epoch": 1.86, + "learning_rate": 7.597783572359844e-06, + "loss": 0.2482, + "step": 22830 + }, + { + "epoch": 1.86, + "learning_rate": 7.597240330291178e-06, + "loss": 0.435, + "step": 22831 + }, + { + "epoch": 1.86, + "learning_rate": 7.596697088222512e-06, + "loss": 0.4057, + "step": 22832 + }, + { + "epoch": 1.86, + "learning_rate": 7.5961538461538465e-06, + "loss": 0.1748, + "step": 22833 + }, + { + "epoch": 1.86, + "learning_rate": 7.595610604085181e-06, + "loss": 0.3892, + "step": 22834 + }, + { + "epoch": 1.86, + "learning_rate": 7.595067362016515e-06, + "loss": 0.4351, + "step": 22835 + }, + { + "epoch": 1.86, + "learning_rate": 7.594524119947849e-06, + "loss": 0.221, + "step": 22836 + }, + { + "epoch": 1.86, + "learning_rate": 7.593980877879183e-06, + "loss": 0.1929, + "step": 22837 + }, + { + "epoch": 1.86, + "learning_rate": 7.593437635810518e-06, + "loss": 0.3698, + "step": 22838 + }, + { + "epoch": 1.86, + "learning_rate": 7.592894393741852e-06, + "loss": 0.1609, + "step": 22839 + }, + { + "epoch": 1.86, + "learning_rate": 7.592351151673186e-06, + "loss": 0.2105, + "step": 22840 + }, + { + "epoch": 1.86, + "learning_rate": 7.59180790960452e-06, + "loss": 0.2327, + "step": 22841 + }, + { + "epoch": 1.86, + "learning_rate": 7.5912646675358545e-06, + "loss": 0.3108, + "step": 22842 + }, + { + "epoch": 1.86, + "learning_rate": 7.590721425467189e-06, + "loss": 0.3794, + "step": 22843 + }, + { + "epoch": 1.86, + "learning_rate": 7.590178183398523e-06, + "loss": 0.151, + "step": 22844 + }, + { + "epoch": 1.86, + "learning_rate": 7.589634941329857e-06, + "loss": 0.344, + "step": 22845 + }, + { + "epoch": 1.86, + "learning_rate": 7.5890916992611915e-06, + "loss": 0.3129, + "step": 22846 + }, + { + "epoch": 1.86, + "learning_rate": 7.588548457192526e-06, + "loss": 0.2758, + "step": 22847 + }, + { + "epoch": 1.86, + "learning_rate": 7.58800521512386e-06, + "loss": 0.3248, + "step": 22848 + }, + { + "epoch": 1.86, + "learning_rate": 7.587461973055193e-06, + "loss": 0.2695, + "step": 22849 + }, + { + "epoch": 1.86, + "learning_rate": 7.5869187309865275e-06, + "loss": 0.2687, + "step": 22850 + }, + { + "epoch": 1.86, + "learning_rate": 7.586375488917862e-06, + "loss": 0.163, + "step": 22851 + }, + { + "epoch": 1.86, + "learning_rate": 7.585832246849196e-06, + "loss": 0.1906, + "step": 22852 + }, + { + "epoch": 1.86, + "learning_rate": 7.58528900478053e-06, + "loss": 0.2551, + "step": 22853 + }, + { + "epoch": 1.86, + "learning_rate": 7.5847457627118645e-06, + "loss": 0.6559, + "step": 22854 + }, + { + "epoch": 1.86, + "learning_rate": 7.584202520643199e-06, + "loss": 0.1912, + "step": 22855 + }, + { + "epoch": 1.86, + "learning_rate": 7.583659278574533e-06, + "loss": 0.3157, + "step": 22856 + }, + { + "epoch": 1.86, + "learning_rate": 7.583116036505868e-06, + "loss": 0.3931, + "step": 22857 + }, + { + "epoch": 1.86, + "learning_rate": 7.582572794437202e-06, + "loss": 0.3064, + "step": 22858 + }, + { + "epoch": 1.86, + "learning_rate": 7.5820295523685365e-06, + "loss": 0.2669, + "step": 22859 + }, + { + "epoch": 1.86, + "learning_rate": 7.581486310299871e-06, + "loss": 0.6001, + "step": 22860 + }, + { + "epoch": 1.86, + "learning_rate": 7.580943068231205e-06, + "loss": 0.2633, + "step": 22861 + }, + { + "epoch": 1.86, + "learning_rate": 7.580399826162539e-06, + "loss": 0.2805, + "step": 22862 + }, + { + "epoch": 1.86, + "learning_rate": 7.579856584093873e-06, + "loss": 0.3536, + "step": 22863 + }, + { + "epoch": 1.86, + "learning_rate": 7.579313342025208e-06, + "loss": 0.1533, + "step": 22864 + }, + { + "epoch": 1.86, + "learning_rate": 7.578770099956542e-06, + "loss": 0.1795, + "step": 22865 + }, + { + "epoch": 1.86, + "learning_rate": 7.578226857887876e-06, + "loss": 0.5099, + "step": 22866 + }, + { + "epoch": 1.86, + "learning_rate": 7.57768361581921e-06, + "loss": 0.5656, + "step": 22867 + }, + { + "epoch": 1.86, + "learning_rate": 7.577140373750544e-06, + "loss": 0.3363, + "step": 22868 + }, + { + "epoch": 1.86, + "learning_rate": 7.576597131681878e-06, + "loss": 0.4291, + "step": 22869 + }, + { + "epoch": 1.86, + "learning_rate": 7.576053889613212e-06, + "loss": 0.2014, + "step": 22870 + }, + { + "epoch": 1.86, + "learning_rate": 7.575510647544546e-06, + "loss": 0.487, + "step": 22871 + }, + { + "epoch": 1.86, + "learning_rate": 7.574967405475881e-06, + "loss": 0.3046, + "step": 22872 + }, + { + "epoch": 1.86, + "learning_rate": 7.574424163407215e-06, + "loss": 0.3551, + "step": 22873 + }, + { + "epoch": 1.86, + "learning_rate": 7.573880921338549e-06, + "loss": 0.2108, + "step": 22874 + }, + { + "epoch": 1.86, + "learning_rate": 7.573337679269883e-06, + "loss": 0.6159, + "step": 22875 + }, + { + "epoch": 1.86, + "learning_rate": 7.5727944372012175e-06, + "loss": 0.2867, + "step": 22876 + }, + { + "epoch": 1.86, + "learning_rate": 7.572251195132552e-06, + "loss": 0.2413, + "step": 22877 + }, + { + "epoch": 1.86, + "learning_rate": 7.571707953063886e-06, + "loss": 0.4225, + "step": 22878 + }, + { + "epoch": 1.86, + "learning_rate": 7.57116471099522e-06, + "loss": 0.0603, + "step": 22879 + }, + { + "epoch": 1.86, + "learning_rate": 7.5706214689265545e-06, + "loss": 0.1707, + "step": 22880 + }, + { + "epoch": 1.86, + "learning_rate": 7.570078226857889e-06, + "loss": 0.2217, + "step": 22881 + }, + { + "epoch": 1.86, + "learning_rate": 7.569534984789223e-06, + "loss": 0.2362, + "step": 22882 + }, + { + "epoch": 1.86, + "learning_rate": 7.568991742720557e-06, + "loss": 0.3694, + "step": 22883 + }, + { + "epoch": 1.86, + "learning_rate": 7.568448500651891e-06, + "loss": 0.2234, + "step": 22884 + }, + { + "epoch": 1.86, + "learning_rate": 7.567905258583226e-06, + "loss": 0.6794, + "step": 22885 + }, + { + "epoch": 1.86, + "learning_rate": 7.56736201651456e-06, + "loss": 0.3705, + "step": 22886 + }, + { + "epoch": 1.86, + "learning_rate": 7.566818774445893e-06, + "loss": 0.2621, + "step": 22887 + }, + { + "epoch": 1.87, + "learning_rate": 7.5662755323772275e-06, + "loss": 0.1465, + "step": 22888 + }, + { + "epoch": 1.87, + "learning_rate": 7.565732290308562e-06, + "loss": 0.277, + "step": 22889 + }, + { + "epoch": 1.87, + "learning_rate": 7.565189048239896e-06, + "loss": 0.387, + "step": 22890 + }, + { + "epoch": 1.87, + "learning_rate": 7.56464580617123e-06, + "loss": 0.179, + "step": 22891 + }, + { + "epoch": 1.87, + "learning_rate": 7.564102564102564e-06, + "loss": 0.3717, + "step": 22892 + }, + { + "epoch": 1.87, + "learning_rate": 7.563559322033899e-06, + "loss": 0.3768, + "step": 22893 + }, + { + "epoch": 1.87, + "learning_rate": 7.563016079965233e-06, + "loss": 0.2067, + "step": 22894 + }, + { + "epoch": 1.87, + "learning_rate": 7.562472837896567e-06, + "loss": 0.4354, + "step": 22895 + }, + { + "epoch": 1.87, + "learning_rate": 7.561929595827901e-06, + "loss": 0.4635, + "step": 22896 + }, + { + "epoch": 1.87, + "learning_rate": 7.5613863537592355e-06, + "loss": 0.2469, + "step": 22897 + }, + { + "epoch": 1.87, + "learning_rate": 7.56084311169057e-06, + "loss": 0.394, + "step": 22898 + }, + { + "epoch": 1.87, + "learning_rate": 7.560299869621904e-06, + "loss": 0.2062, + "step": 22899 + }, + { + "epoch": 1.87, + "learning_rate": 7.559756627553238e-06, + "loss": 0.2195, + "step": 22900 + }, + { + "epoch": 1.87, + "learning_rate": 7.5592133854845724e-06, + "loss": 0.2527, + "step": 22901 + }, + { + "epoch": 1.87, + "learning_rate": 7.558670143415907e-06, + "loss": 0.6136, + "step": 22902 + }, + { + "epoch": 1.87, + "learning_rate": 7.558126901347242e-06, + "loss": 0.4355, + "step": 22903 + }, + { + "epoch": 1.87, + "learning_rate": 7.557583659278576e-06, + "loss": 0.1787, + "step": 22904 + }, + { + "epoch": 1.87, + "learning_rate": 7.55704041720991e-06, + "loss": 0.5025, + "step": 22905 + }, + { + "epoch": 1.87, + "learning_rate": 7.556497175141243e-06, + "loss": 0.2841, + "step": 22906 + }, + { + "epoch": 1.87, + "learning_rate": 7.555953933072577e-06, + "loss": 0.3521, + "step": 22907 + }, + { + "epoch": 1.87, + "learning_rate": 7.555410691003911e-06, + "loss": 0.2534, + "step": 22908 + }, + { + "epoch": 1.87, + "learning_rate": 7.5548674489352454e-06, + "loss": 0.5002, + "step": 22909 + }, + { + "epoch": 1.87, + "learning_rate": 7.55432420686658e-06, + "loss": 0.4586, + "step": 22910 + }, + { + "epoch": 1.87, + "learning_rate": 7.553780964797915e-06, + "loss": 0.3297, + "step": 22911 + }, + { + "epoch": 1.87, + "learning_rate": 7.553237722729249e-06, + "loss": 0.3708, + "step": 22912 + }, + { + "epoch": 1.87, + "learning_rate": 7.552694480660583e-06, + "loss": 0.2649, + "step": 22913 + }, + { + "epoch": 1.87, + "learning_rate": 7.5521512385919174e-06, + "loss": 0.19, + "step": 22914 + }, + { + "epoch": 1.87, + "learning_rate": 7.551607996523252e-06, + "loss": 0.4746, + "step": 22915 + }, + { + "epoch": 1.87, + "learning_rate": 7.551064754454586e-06, + "loss": 0.5367, + "step": 22916 + }, + { + "epoch": 1.87, + "learning_rate": 7.55052151238592e-06, + "loss": 0.3666, + "step": 22917 + }, + { + "epoch": 1.87, + "learning_rate": 7.549978270317254e-06, + "loss": 0.4495, + "step": 22918 + }, + { + "epoch": 1.87, + "learning_rate": 7.549435028248589e-06, + "loss": 0.2454, + "step": 22919 + }, + { + "epoch": 1.87, + "learning_rate": 7.548891786179923e-06, + "loss": 0.1518, + "step": 22920 + }, + { + "epoch": 1.87, + "learning_rate": 7.548348544111257e-06, + "loss": 0.323, + "step": 22921 + }, + { + "epoch": 1.87, + "learning_rate": 7.547805302042591e-06, + "loss": 0.172, + "step": 22922 + }, + { + "epoch": 1.87, + "learning_rate": 7.5472620599739255e-06, + "loss": 0.2897, + "step": 22923 + }, + { + "epoch": 1.87, + "learning_rate": 7.54671881790526e-06, + "loss": 0.2073, + "step": 22924 + }, + { + "epoch": 1.87, + "learning_rate": 7.546175575836593e-06, + "loss": 0.3643, + "step": 22925 + }, + { + "epoch": 1.87, + "learning_rate": 7.545632333767927e-06, + "loss": 0.2865, + "step": 22926 + }, + { + "epoch": 1.87, + "learning_rate": 7.545089091699262e-06, + "loss": 0.4152, + "step": 22927 + }, + { + "epoch": 1.87, + "learning_rate": 7.544545849630596e-06, + "loss": 0.1598, + "step": 22928 + }, + { + "epoch": 1.87, + "learning_rate": 7.54400260756193e-06, + "loss": 0.2576, + "step": 22929 + }, + { + "epoch": 1.87, + "learning_rate": 7.543459365493264e-06, + "loss": 0.2691, + "step": 22930 + }, + { + "epoch": 1.87, + "learning_rate": 7.5429161234245985e-06, + "loss": 0.351, + "step": 22931 + }, + { + "epoch": 1.87, + "learning_rate": 7.542372881355933e-06, + "loss": 0.4832, + "step": 22932 + }, + { + "epoch": 1.87, + "learning_rate": 7.541829639287267e-06, + "loss": 0.1939, + "step": 22933 + }, + { + "epoch": 1.87, + "learning_rate": 7.541286397218601e-06, + "loss": 0.1378, + "step": 22934 + }, + { + "epoch": 1.87, + "learning_rate": 7.5407431551499354e-06, + "loss": 0.391, + "step": 22935 + }, + { + "epoch": 1.87, + "learning_rate": 7.54019991308127e-06, + "loss": 0.465, + "step": 22936 + }, + { + "epoch": 1.87, + "learning_rate": 7.539656671012604e-06, + "loss": 0.2737, + "step": 22937 + }, + { + "epoch": 1.87, + "learning_rate": 7.539113428943938e-06, + "loss": 0.2897, + "step": 22938 + }, + { + "epoch": 1.87, + "learning_rate": 7.538570186875272e-06, + "loss": 0.2118, + "step": 22939 + }, + { + "epoch": 1.87, + "learning_rate": 7.538026944806607e-06, + "loss": 0.3879, + "step": 22940 + }, + { + "epoch": 1.87, + "learning_rate": 7.537483702737941e-06, + "loss": 0.3136, + "step": 22941 + }, + { + "epoch": 1.87, + "learning_rate": 7.536940460669275e-06, + "loss": 0.3167, + "step": 22942 + }, + { + "epoch": 1.87, + "learning_rate": 7.536397218600609e-06, + "loss": 0.4107, + "step": 22943 + }, + { + "epoch": 1.87, + "learning_rate": 7.535853976531943e-06, + "loss": 0.2667, + "step": 22944 + }, + { + "epoch": 1.87, + "learning_rate": 7.535310734463277e-06, + "loss": 0.3772, + "step": 22945 + }, + { + "epoch": 1.87, + "learning_rate": 7.534767492394611e-06, + "loss": 0.397, + "step": 22946 + }, + { + "epoch": 1.87, + "learning_rate": 7.534224250325945e-06, + "loss": 0.2247, + "step": 22947 + }, + { + "epoch": 1.87, + "learning_rate": 7.53368100825728e-06, + "loss": 0.3201, + "step": 22948 + }, + { + "epoch": 1.87, + "learning_rate": 7.533137766188614e-06, + "loss": 0.2371, + "step": 22949 + }, + { + "epoch": 1.87, + "learning_rate": 7.532594524119948e-06, + "loss": 0.5493, + "step": 22950 + }, + { + "epoch": 1.87, + "learning_rate": 7.532051282051282e-06, + "loss": 0.1654, + "step": 22951 + }, + { + "epoch": 1.87, + "learning_rate": 7.5315080399826165e-06, + "loss": 0.3478, + "step": 22952 + }, + { + "epoch": 1.87, + "learning_rate": 7.530964797913951e-06, + "loss": 0.3994, + "step": 22953 + }, + { + "epoch": 1.87, + "learning_rate": 7.530421555845285e-06, + "loss": 0.1868, + "step": 22954 + }, + { + "epoch": 1.87, + "learning_rate": 7.529878313776619e-06, + "loss": 0.1262, + "step": 22955 + }, + { + "epoch": 1.87, + "learning_rate": 7.5293350717079534e-06, + "loss": 0.3347, + "step": 22956 + }, + { + "epoch": 1.87, + "learning_rate": 7.5287918296392885e-06, + "loss": 0.3242, + "step": 22957 + }, + { + "epoch": 1.87, + "learning_rate": 7.528248587570623e-06, + "loss": 0.3524, + "step": 22958 + }, + { + "epoch": 1.87, + "learning_rate": 7.527705345501957e-06, + "loss": 0.3882, + "step": 22959 + }, + { + "epoch": 1.87, + "learning_rate": 7.527162103433291e-06, + "loss": 0.6025, + "step": 22960 + }, + { + "epoch": 1.87, + "learning_rate": 7.5266188613646254e-06, + "loss": 0.3407, + "step": 22961 + }, + { + "epoch": 1.87, + "learning_rate": 7.52607561929596e-06, + "loss": 0.2633, + "step": 22962 + }, + { + "epoch": 1.87, + "learning_rate": 7.525532377227292e-06, + "loss": 0.4019, + "step": 22963 + }, + { + "epoch": 1.87, + "learning_rate": 7.5249891351586264e-06, + "loss": 0.5946, + "step": 22964 + }, + { + "epoch": 1.87, + "learning_rate": 7.5244458930899615e-06, + "loss": 0.4002, + "step": 22965 + }, + { + "epoch": 1.87, + "learning_rate": 7.523902651021296e-06, + "loss": 0.3462, + "step": 22966 + }, + { + "epoch": 1.87, + "learning_rate": 7.52335940895263e-06, + "loss": 0.3921, + "step": 22967 + }, + { + "epoch": 1.87, + "learning_rate": 7.522816166883964e-06, + "loss": 0.3765, + "step": 22968 + }, + { + "epoch": 1.87, + "learning_rate": 7.5222729248152984e-06, + "loss": 0.2418, + "step": 22969 + }, + { + "epoch": 1.87, + "learning_rate": 7.521729682746633e-06, + "loss": 0.4215, + "step": 22970 + }, + { + "epoch": 1.87, + "learning_rate": 7.521186440677967e-06, + "loss": 0.2714, + "step": 22971 + }, + { + "epoch": 1.87, + "learning_rate": 7.520643198609301e-06, + "loss": 0.417, + "step": 22972 + }, + { + "epoch": 1.87, + "learning_rate": 7.520099956540635e-06, + "loss": 0.4655, + "step": 22973 + }, + { + "epoch": 1.87, + "learning_rate": 7.51955671447197e-06, + "loss": 0.3082, + "step": 22974 + }, + { + "epoch": 1.87, + "learning_rate": 7.519013472403304e-06, + "loss": 0.396, + "step": 22975 + }, + { + "epoch": 1.87, + "learning_rate": 7.518470230334638e-06, + "loss": 0.2213, + "step": 22976 + }, + { + "epoch": 1.87, + "learning_rate": 7.517926988265972e-06, + "loss": 0.3277, + "step": 22977 + }, + { + "epoch": 1.87, + "learning_rate": 7.5173837461973065e-06, + "loss": 0.4691, + "step": 22978 + }, + { + "epoch": 1.87, + "learning_rate": 7.516840504128641e-06, + "loss": 0.2329, + "step": 22979 + }, + { + "epoch": 1.87, + "learning_rate": 7.516297262059975e-06, + "loss": 0.2799, + "step": 22980 + }, + { + "epoch": 1.87, + "learning_rate": 7.515754019991309e-06, + "loss": 0.4456, + "step": 22981 + }, + { + "epoch": 1.87, + "learning_rate": 7.515210777922643e-06, + "loss": 0.3488, + "step": 22982 + }, + { + "epoch": 1.87, + "learning_rate": 7.514667535853977e-06, + "loss": 0.3811, + "step": 22983 + }, + { + "epoch": 1.87, + "learning_rate": 7.514124293785311e-06, + "loss": 0.2007, + "step": 22984 + }, + { + "epoch": 1.87, + "learning_rate": 7.513581051716645e-06, + "loss": 0.2219, + "step": 22985 + }, + { + "epoch": 1.87, + "learning_rate": 7.5130378096479795e-06, + "loss": 0.3396, + "step": 22986 + }, + { + "epoch": 1.87, + "learning_rate": 7.512494567579314e-06, + "loss": 0.3971, + "step": 22987 + }, + { + "epoch": 1.87, + "learning_rate": 7.511951325510648e-06, + "loss": 0.5106, + "step": 22988 + }, + { + "epoch": 1.87, + "learning_rate": 7.511408083441982e-06, + "loss": 0.4032, + "step": 22989 + }, + { + "epoch": 1.87, + "learning_rate": 7.5108648413733164e-06, + "loss": 0.4083, + "step": 22990 + }, + { + "epoch": 1.87, + "learning_rate": 7.510321599304651e-06, + "loss": 0.2133, + "step": 22991 + }, + { + "epoch": 1.87, + "learning_rate": 7.509778357235985e-06, + "loss": 0.5037, + "step": 22992 + }, + { + "epoch": 1.87, + "learning_rate": 7.509235115167319e-06, + "loss": 0.4196, + "step": 22993 + }, + { + "epoch": 1.87, + "learning_rate": 7.508691873098653e-06, + "loss": 0.2585, + "step": 22994 + }, + { + "epoch": 1.87, + "learning_rate": 7.508148631029988e-06, + "loss": 0.3244, + "step": 22995 + }, + { + "epoch": 1.87, + "learning_rate": 7.507605388961322e-06, + "loss": 0.5166, + "step": 22996 + }, + { + "epoch": 1.87, + "learning_rate": 7.507062146892656e-06, + "loss": 0.5344, + "step": 22997 + }, + { + "epoch": 1.87, + "learning_rate": 7.50651890482399e-06, + "loss": 0.1656, + "step": 22998 + }, + { + "epoch": 1.87, + "learning_rate": 7.5059756627553245e-06, + "loss": 0.2425, + "step": 22999 + }, + { + "epoch": 1.87, + "learning_rate": 7.505432420686659e-06, + "loss": 0.3057, + "step": 23000 + }, + { + "epoch": 1.87, + "eval_accuracy": 0.8424859908303617, + "eval_loss": 0.41620948910713196, + "eval_runtime": 22.2942, + "eval_samples_per_second": 440.249, + "eval_steps_per_second": 3.454, + "step": 23000 + }, + { + "epoch": 1.87, + "learning_rate": 7.504889178617992e-06, + "loss": 0.2821, + "step": 23001 + }, + { + "epoch": 1.87, + "learning_rate": 7.504345936549326e-06, + "loss": 0.4264, + "step": 23002 + }, + { + "epoch": 1.87, + "learning_rate": 7.5038026944806606e-06, + "loss": 0.3323, + "step": 23003 + }, + { + "epoch": 1.87, + "learning_rate": 7.503259452411995e-06, + "loss": 0.3463, + "step": 23004 + }, + { + "epoch": 1.87, + "learning_rate": 7.502716210343329e-06, + "loss": 0.602, + "step": 23005 + }, + { + "epoch": 1.87, + "learning_rate": 7.502172968274663e-06, + "loss": 0.2345, + "step": 23006 + }, + { + "epoch": 1.87, + "learning_rate": 7.5016297262059975e-06, + "loss": 0.5302, + "step": 23007 + }, + { + "epoch": 1.87, + "learning_rate": 7.501086484137332e-06, + "loss": 0.1855, + "step": 23008 + }, + { + "epoch": 1.87, + "learning_rate": 7.500543242068666e-06, + "loss": 0.2218, + "step": 23009 + }, + { + "epoch": 1.88, + "learning_rate": 7.500000000000001e-06, + "loss": 0.3268, + "step": 23010 + }, + { + "epoch": 1.88, + "learning_rate": 7.499456757931335e-06, + "loss": 0.3185, + "step": 23011 + }, + { + "epoch": 1.88, + "learning_rate": 7.4989135158626695e-06, + "loss": 0.4955, + "step": 23012 + }, + { + "epoch": 1.88, + "learning_rate": 7.498370273794004e-06, + "loss": 0.2343, + "step": 23013 + }, + { + "epoch": 1.88, + "learning_rate": 7.497827031725338e-06, + "loss": 0.2875, + "step": 23014 + }, + { + "epoch": 1.88, + "learning_rate": 7.497283789656672e-06, + "loss": 0.3871, + "step": 23015 + }, + { + "epoch": 1.88, + "learning_rate": 7.496740547588006e-06, + "loss": 0.3293, + "step": 23016 + }, + { + "epoch": 1.88, + "learning_rate": 7.496197305519341e-06, + "loss": 0.2343, + "step": 23017 + }, + { + "epoch": 1.88, + "learning_rate": 7.495654063450675e-06, + "loss": 0.4923, + "step": 23018 + }, + { + "epoch": 1.88, + "learning_rate": 7.495110821382009e-06, + "loss": 0.1718, + "step": 23019 + }, + { + "epoch": 1.88, + "learning_rate": 7.4945675793133425e-06, + "loss": 0.3584, + "step": 23020 + }, + { + "epoch": 1.88, + "learning_rate": 7.494024337244677e-06, + "loss": 0.2807, + "step": 23021 + }, + { + "epoch": 1.88, + "learning_rate": 7.493481095176011e-06, + "loss": 0.2526, + "step": 23022 + }, + { + "epoch": 1.88, + "learning_rate": 7.492937853107345e-06, + "loss": 0.2856, + "step": 23023 + }, + { + "epoch": 1.88, + "learning_rate": 7.492394611038679e-06, + "loss": 0.3724, + "step": 23024 + }, + { + "epoch": 1.88, + "learning_rate": 7.491851368970014e-06, + "loss": 0.3369, + "step": 23025 + }, + { + "epoch": 1.88, + "learning_rate": 7.491308126901348e-06, + "loss": 0.2704, + "step": 23026 + }, + { + "epoch": 1.88, + "learning_rate": 7.490764884832682e-06, + "loss": 0.3502, + "step": 23027 + }, + { + "epoch": 1.88, + "learning_rate": 7.490221642764016e-06, + "loss": 0.3865, + "step": 23028 + }, + { + "epoch": 1.88, + "learning_rate": 7.4896784006953506e-06, + "loss": 0.7071, + "step": 23029 + }, + { + "epoch": 1.88, + "learning_rate": 7.489135158626685e-06, + "loss": 0.4869, + "step": 23030 + }, + { + "epoch": 1.88, + "learning_rate": 7.488591916558019e-06, + "loss": 0.3576, + "step": 23031 + }, + { + "epoch": 1.88, + "learning_rate": 7.488048674489353e-06, + "loss": 0.1906, + "step": 23032 + }, + { + "epoch": 1.88, + "learning_rate": 7.4875054324206875e-06, + "loss": 0.3701, + "step": 23033 + }, + { + "epoch": 1.88, + "learning_rate": 7.486962190352022e-06, + "loss": 0.3558, + "step": 23034 + }, + { + "epoch": 1.88, + "learning_rate": 7.486418948283356e-06, + "loss": 0.2802, + "step": 23035 + }, + { + "epoch": 1.88, + "learning_rate": 7.48587570621469e-06, + "loss": 0.2832, + "step": 23036 + }, + { + "epoch": 1.88, + "learning_rate": 7.485332464146024e-06, + "loss": 0.4732, + "step": 23037 + }, + { + "epoch": 1.88, + "learning_rate": 7.484789222077359e-06, + "loss": 0.3151, + "step": 23038 + }, + { + "epoch": 1.88, + "learning_rate": 7.484245980008692e-06, + "loss": 0.2839, + "step": 23039 + }, + { + "epoch": 1.88, + "learning_rate": 7.483702737940026e-06, + "loss": 0.292, + "step": 23040 + }, + { + "epoch": 1.88, + "learning_rate": 7.4831594958713605e-06, + "loss": 0.3294, + "step": 23041 + }, + { + "epoch": 1.88, + "learning_rate": 7.482616253802695e-06, + "loss": 0.3143, + "step": 23042 + }, + { + "epoch": 1.88, + "learning_rate": 7.482073011734029e-06, + "loss": 0.1864, + "step": 23043 + }, + { + "epoch": 1.88, + "learning_rate": 7.481529769665363e-06, + "loss": 0.236, + "step": 23044 + }, + { + "epoch": 1.88, + "learning_rate": 7.480986527596697e-06, + "loss": 0.4435, + "step": 23045 + }, + { + "epoch": 1.88, + "learning_rate": 7.480443285528032e-06, + "loss": 0.4094, + "step": 23046 + }, + { + "epoch": 1.88, + "learning_rate": 7.479900043459366e-06, + "loss": 0.3094, + "step": 23047 + }, + { + "epoch": 1.88, + "learning_rate": 7.4793568013907e-06, + "loss": 0.2944, + "step": 23048 + }, + { + "epoch": 1.88, + "learning_rate": 7.478813559322034e-06, + "loss": 0.2713, + "step": 23049 + }, + { + "epoch": 1.88, + "learning_rate": 7.4782703172533686e-06, + "loss": 0.4622, + "step": 23050 + }, + { + "epoch": 1.88, + "learning_rate": 7.477727075184703e-06, + "loss": 0.3019, + "step": 23051 + }, + { + "epoch": 1.88, + "learning_rate": 7.477183833116037e-06, + "loss": 0.2922, + "step": 23052 + }, + { + "epoch": 1.88, + "learning_rate": 7.476640591047371e-06, + "loss": 0.3744, + "step": 23053 + }, + { + "epoch": 1.88, + "learning_rate": 7.4760973489787055e-06, + "loss": 0.2154, + "step": 23054 + }, + { + "epoch": 1.88, + "learning_rate": 7.47555410691004e-06, + "loss": 0.4848, + "step": 23055 + }, + { + "epoch": 1.88, + "learning_rate": 7.475010864841375e-06, + "loss": 0.1761, + "step": 23056 + }, + { + "epoch": 1.88, + "learning_rate": 7.474467622772709e-06, + "loss": 0.428, + "step": 23057 + }, + { + "epoch": 1.88, + "learning_rate": 7.4739243807040416e-06, + "loss": 0.4696, + "step": 23058 + }, + { + "epoch": 1.88, + "learning_rate": 7.473381138635376e-06, + "loss": 0.2532, + "step": 23059 + }, + { + "epoch": 1.88, + "learning_rate": 7.47283789656671e-06, + "loss": 0.3283, + "step": 23060 + }, + { + "epoch": 1.88, + "learning_rate": 7.472294654498044e-06, + "loss": 0.3014, + "step": 23061 + }, + { + "epoch": 1.88, + "learning_rate": 7.4717514124293785e-06, + "loss": 0.2251, + "step": 23062 + }, + { + "epoch": 1.88, + "learning_rate": 7.471208170360713e-06, + "loss": 0.3639, + "step": 23063 + }, + { + "epoch": 1.88, + "learning_rate": 7.470664928292048e-06, + "loss": 0.1951, + "step": 23064 + }, + { + "epoch": 1.88, + "learning_rate": 7.470121686223382e-06, + "loss": 0.3492, + "step": 23065 + }, + { + "epoch": 1.88, + "learning_rate": 7.469578444154716e-06, + "loss": 0.4346, + "step": 23066 + }, + { + "epoch": 1.88, + "learning_rate": 7.4690352020860505e-06, + "loss": 0.2573, + "step": 23067 + }, + { + "epoch": 1.88, + "learning_rate": 7.468491960017385e-06, + "loss": 0.6028, + "step": 23068 + }, + { + "epoch": 1.88, + "learning_rate": 7.467948717948719e-06, + "loss": 0.4425, + "step": 23069 + }, + { + "epoch": 1.88, + "learning_rate": 7.467405475880053e-06, + "loss": 0.2362, + "step": 23070 + }, + { + "epoch": 1.88, + "learning_rate": 7.466862233811387e-06, + "loss": 0.5402, + "step": 23071 + }, + { + "epoch": 1.88, + "learning_rate": 7.466318991742722e-06, + "loss": 0.1557, + "step": 23072 + }, + { + "epoch": 1.88, + "learning_rate": 7.465775749674056e-06, + "loss": 0.2822, + "step": 23073 + }, + { + "epoch": 1.88, + "learning_rate": 7.46523250760539e-06, + "loss": 0.2394, + "step": 23074 + }, + { + "epoch": 1.88, + "learning_rate": 7.464689265536724e-06, + "loss": 0.4086, + "step": 23075 + }, + { + "epoch": 1.88, + "learning_rate": 7.4641460234680586e-06, + "loss": 0.1782, + "step": 23076 + }, + { + "epoch": 1.88, + "learning_rate": 7.463602781399392e-06, + "loss": 0.2632, + "step": 23077 + }, + { + "epoch": 1.88, + "learning_rate": 7.463059539330726e-06, + "loss": 0.3041, + "step": 23078 + }, + { + "epoch": 1.88, + "learning_rate": 7.46251629726206e-06, + "loss": 0.4051, + "step": 23079 + }, + { + "epoch": 1.88, + "learning_rate": 7.461973055193395e-06, + "loss": 0.1892, + "step": 23080 + }, + { + "epoch": 1.88, + "learning_rate": 7.461429813124729e-06, + "loss": 0.1589, + "step": 23081 + }, + { + "epoch": 1.88, + "learning_rate": 7.460886571056063e-06, + "loss": 0.1272, + "step": 23082 + }, + { + "epoch": 1.88, + "learning_rate": 7.460343328987397e-06, + "loss": 0.2461, + "step": 23083 + }, + { + "epoch": 1.88, + "learning_rate": 7.4598000869187316e-06, + "loss": 0.4553, + "step": 23084 + }, + { + "epoch": 1.88, + "learning_rate": 7.459256844850066e-06, + "loss": 0.2231, + "step": 23085 + }, + { + "epoch": 1.88, + "learning_rate": 7.4587136027814e-06, + "loss": 0.5259, + "step": 23086 + }, + { + "epoch": 1.88, + "learning_rate": 7.458170360712734e-06, + "loss": 0.464, + "step": 23087 + }, + { + "epoch": 1.88, + "learning_rate": 7.4576271186440685e-06, + "loss": 0.4149, + "step": 23088 + }, + { + "epoch": 1.88, + "learning_rate": 7.457083876575403e-06, + "loss": 0.2521, + "step": 23089 + }, + { + "epoch": 1.88, + "learning_rate": 7.456540634506737e-06, + "loss": 0.2738, + "step": 23090 + }, + { + "epoch": 1.88, + "learning_rate": 7.455997392438071e-06, + "loss": 0.3495, + "step": 23091 + }, + { + "epoch": 1.88, + "learning_rate": 7.455454150369405e-06, + "loss": 0.4353, + "step": 23092 + }, + { + "epoch": 1.88, + "learning_rate": 7.45491090830074e-06, + "loss": 0.2191, + "step": 23093 + }, + { + "epoch": 1.88, + "learning_rate": 7.454367666232074e-06, + "loss": 0.1793, + "step": 23094 + }, + { + "epoch": 1.88, + "learning_rate": 7.453824424163408e-06, + "loss": 0.3915, + "step": 23095 + }, + { + "epoch": 1.88, + "learning_rate": 7.4532811820947415e-06, + "loss": 0.5108, + "step": 23096 + }, + { + "epoch": 1.88, + "learning_rate": 7.452737940026076e-06, + "loss": 0.1635, + "step": 23097 + }, + { + "epoch": 1.88, + "learning_rate": 7.45219469795741e-06, + "loss": 0.2334, + "step": 23098 + }, + { + "epoch": 1.88, + "learning_rate": 7.451651455888744e-06, + "loss": 0.2459, + "step": 23099 + }, + { + "epoch": 1.88, + "learning_rate": 7.451108213820078e-06, + "loss": 0.2294, + "step": 23100 + }, + { + "epoch": 1.88, + "learning_rate": 7.450564971751413e-06, + "loss": 0.1571, + "step": 23101 + }, + { + "epoch": 1.88, + "learning_rate": 7.450021729682747e-06, + "loss": 0.599, + "step": 23102 + }, + { + "epoch": 1.88, + "learning_rate": 7.449478487614081e-06, + "loss": 0.1959, + "step": 23103 + }, + { + "epoch": 1.88, + "learning_rate": 7.448935245545415e-06, + "loss": 0.2321, + "step": 23104 + }, + { + "epoch": 1.88, + "learning_rate": 7.4483920034767496e-06, + "loss": 0.107, + "step": 23105 + }, + { + "epoch": 1.88, + "learning_rate": 7.447848761408084e-06, + "loss": 0.1804, + "step": 23106 + }, + { + "epoch": 1.88, + "learning_rate": 7.447305519339418e-06, + "loss": 0.203, + "step": 23107 + }, + { + "epoch": 1.88, + "learning_rate": 7.446762277270752e-06, + "loss": 0.2659, + "step": 23108 + }, + { + "epoch": 1.88, + "learning_rate": 7.4462190352020865e-06, + "loss": 0.1699, + "step": 23109 + }, + { + "epoch": 1.88, + "learning_rate": 7.4456757931334216e-06, + "loss": 0.4099, + "step": 23110 + }, + { + "epoch": 1.88, + "learning_rate": 7.445132551064756e-06, + "loss": 0.3166, + "step": 23111 + }, + { + "epoch": 1.88, + "learning_rate": 7.44458930899609e-06, + "loss": 0.3992, + "step": 23112 + }, + { + "epoch": 1.88, + "learning_rate": 7.444046066927424e-06, + "loss": 0.3633, + "step": 23113 + }, + { + "epoch": 1.88, + "learning_rate": 7.4435028248587585e-06, + "loss": 0.1214, + "step": 23114 + }, + { + "epoch": 1.88, + "learning_rate": 7.442959582790091e-06, + "loss": 0.2664, + "step": 23115 + }, + { + "epoch": 1.88, + "learning_rate": 7.442416340721425e-06, + "loss": 0.272, + "step": 23116 + }, + { + "epoch": 1.88, + "learning_rate": 7.4418730986527595e-06, + "loss": 0.3516, + "step": 23117 + }, + { + "epoch": 1.88, + "learning_rate": 7.4413298565840945e-06, + "loss": 0.3534, + "step": 23118 + }, + { + "epoch": 1.88, + "learning_rate": 7.440786614515429e-06, + "loss": 0.3454, + "step": 23119 + }, + { + "epoch": 1.88, + "learning_rate": 7.440243372446763e-06, + "loss": 0.2613, + "step": 23120 + }, + { + "epoch": 1.88, + "learning_rate": 7.439700130378097e-06, + "loss": 0.2071, + "step": 23121 + }, + { + "epoch": 1.88, + "learning_rate": 7.4391568883094315e-06, + "loss": 0.3169, + "step": 23122 + }, + { + "epoch": 1.88, + "learning_rate": 7.438613646240766e-06, + "loss": 0.6225, + "step": 23123 + }, + { + "epoch": 1.88, + "learning_rate": 7.4380704041721e-06, + "loss": 0.2918, + "step": 23124 + }, + { + "epoch": 1.88, + "learning_rate": 7.437527162103434e-06, + "loss": 0.4896, + "step": 23125 + }, + { + "epoch": 1.88, + "learning_rate": 7.436983920034768e-06, + "loss": 0.4657, + "step": 23126 + }, + { + "epoch": 1.88, + "learning_rate": 7.436440677966103e-06, + "loss": 0.6025, + "step": 23127 + }, + { + "epoch": 1.88, + "learning_rate": 7.435897435897437e-06, + "loss": 0.6131, + "step": 23128 + }, + { + "epoch": 1.88, + "learning_rate": 7.435354193828771e-06, + "loss": 0.2137, + "step": 23129 + }, + { + "epoch": 1.88, + "learning_rate": 7.434810951760105e-06, + "loss": 0.5251, + "step": 23130 + }, + { + "epoch": 1.88, + "learning_rate": 7.4342677096914395e-06, + "loss": 0.5115, + "step": 23131 + }, + { + "epoch": 1.88, + "learning_rate": 7.433724467622774e-06, + "loss": 0.3115, + "step": 23132 + }, + { + "epoch": 1.89, + "learning_rate": 7.433181225554108e-06, + "loss": 0.3329, + "step": 23133 + }, + { + "epoch": 1.89, + "learning_rate": 7.432637983485441e-06, + "loss": 0.1867, + "step": 23134 + }, + { + "epoch": 1.89, + "learning_rate": 7.432094741416776e-06, + "loss": 0.2935, + "step": 23135 + }, + { + "epoch": 1.89, + "learning_rate": 7.43155149934811e-06, + "loss": 0.4414, + "step": 23136 + }, + { + "epoch": 1.89, + "learning_rate": 7.431008257279444e-06, + "loss": 0.5068, + "step": 23137 + }, + { + "epoch": 1.89, + "learning_rate": 7.430465015210778e-06, + "loss": 0.2024, + "step": 23138 + }, + { + "epoch": 1.89, + "learning_rate": 7.4299217731421125e-06, + "loss": 0.2274, + "step": 23139 + }, + { + "epoch": 1.89, + "learning_rate": 7.429378531073447e-06, + "loss": 0.391, + "step": 23140 + }, + { + "epoch": 1.89, + "learning_rate": 7.428835289004781e-06, + "loss": 0.3789, + "step": 23141 + }, + { + "epoch": 1.89, + "learning_rate": 7.428292046936115e-06, + "loss": 0.5189, + "step": 23142 + }, + { + "epoch": 1.89, + "learning_rate": 7.4277488048674495e-06, + "loss": 0.2026, + "step": 23143 + }, + { + "epoch": 1.89, + "learning_rate": 7.427205562798784e-06, + "loss": 0.3653, + "step": 23144 + }, + { + "epoch": 1.89, + "learning_rate": 7.426662320730118e-06, + "loss": 0.3949, + "step": 23145 + }, + { + "epoch": 1.89, + "learning_rate": 7.426119078661452e-06, + "loss": 0.368, + "step": 23146 + }, + { + "epoch": 1.89, + "learning_rate": 7.425575836592786e-06, + "loss": 0.3033, + "step": 23147 + }, + { + "epoch": 1.89, + "learning_rate": 7.425032594524121e-06, + "loss": 0.3153, + "step": 23148 + }, + { + "epoch": 1.89, + "learning_rate": 7.424489352455455e-06, + "loss": 0.2114, + "step": 23149 + }, + { + "epoch": 1.89, + "learning_rate": 7.423946110386789e-06, + "loss": 0.3333, + "step": 23150 + }, + { + "epoch": 1.89, + "learning_rate": 7.423402868318123e-06, + "loss": 0.3646, + "step": 23151 + }, + { + "epoch": 1.89, + "learning_rate": 7.4228596262494575e-06, + "loss": 0.4708, + "step": 23152 + }, + { + "epoch": 1.89, + "learning_rate": 7.422316384180791e-06, + "loss": 0.381, + "step": 23153 + }, + { + "epoch": 1.89, + "learning_rate": 7.421773142112125e-06, + "loss": 0.4234, + "step": 23154 + }, + { + "epoch": 1.89, + "learning_rate": 7.421229900043459e-06, + "loss": 0.174, + "step": 23155 + }, + { + "epoch": 1.89, + "learning_rate": 7.420686657974794e-06, + "loss": 0.226, + "step": 23156 + }, + { + "epoch": 1.89, + "learning_rate": 7.420143415906128e-06, + "loss": 0.1368, + "step": 23157 + }, + { + "epoch": 1.89, + "learning_rate": 7.419600173837462e-06, + "loss": 0.4337, + "step": 23158 + }, + { + "epoch": 1.89, + "learning_rate": 7.419056931768796e-06, + "loss": 0.2965, + "step": 23159 + }, + { + "epoch": 1.89, + "learning_rate": 7.4185136897001305e-06, + "loss": 0.3132, + "step": 23160 + }, + { + "epoch": 1.89, + "learning_rate": 7.417970447631465e-06, + "loss": 0.6327, + "step": 23161 + }, + { + "epoch": 1.89, + "learning_rate": 7.417427205562799e-06, + "loss": 0.3419, + "step": 23162 + }, + { + "epoch": 1.89, + "learning_rate": 7.416883963494133e-06, + "loss": 0.3892, + "step": 23163 + }, + { + "epoch": 1.89, + "learning_rate": 7.416340721425468e-06, + "loss": 0.2923, + "step": 23164 + }, + { + "epoch": 1.89, + "learning_rate": 7.4157974793568025e-06, + "loss": 0.1866, + "step": 23165 + }, + { + "epoch": 1.89, + "learning_rate": 7.415254237288137e-06, + "loss": 0.1999, + "step": 23166 + }, + { + "epoch": 1.89, + "learning_rate": 7.414710995219471e-06, + "loss": 0.5398, + "step": 23167 + }, + { + "epoch": 1.89, + "learning_rate": 7.414167753150805e-06, + "loss": 0.1399, + "step": 23168 + }, + { + "epoch": 1.89, + "learning_rate": 7.4136245110821395e-06, + "loss": 0.506, + "step": 23169 + }, + { + "epoch": 1.89, + "learning_rate": 7.413081269013474e-06, + "loss": 0.2328, + "step": 23170 + }, + { + "epoch": 1.89, + "learning_rate": 7.412538026944808e-06, + "loss": 0.4955, + "step": 23171 + }, + { + "epoch": 1.89, + "learning_rate": 7.411994784876141e-06, + "loss": 0.407, + "step": 23172 + }, + { + "epoch": 1.89, + "learning_rate": 7.4114515428074755e-06, + "loss": 0.4178, + "step": 23173 + }, + { + "epoch": 1.89, + "learning_rate": 7.41090830073881e-06, + "loss": 0.5317, + "step": 23174 + }, + { + "epoch": 1.89, + "learning_rate": 7.410365058670144e-06, + "loss": 0.401, + "step": 23175 + }, + { + "epoch": 1.89, + "learning_rate": 7.409821816601478e-06, + "loss": 0.2183, + "step": 23176 + }, + { + "epoch": 1.89, + "learning_rate": 7.4092785745328125e-06, + "loss": 0.1809, + "step": 23177 + }, + { + "epoch": 1.89, + "learning_rate": 7.408735332464147e-06, + "loss": 0.41, + "step": 23178 + }, + { + "epoch": 1.89, + "learning_rate": 7.408192090395481e-06, + "loss": 0.1844, + "step": 23179 + }, + { + "epoch": 1.89, + "learning_rate": 7.407648848326815e-06, + "loss": 0.2419, + "step": 23180 + }, + { + "epoch": 1.89, + "learning_rate": 7.407105606258149e-06, + "loss": 0.4195, + "step": 23181 + }, + { + "epoch": 1.89, + "learning_rate": 7.406562364189484e-06, + "loss": 0.3476, + "step": 23182 + }, + { + "epoch": 1.89, + "learning_rate": 7.406019122120818e-06, + "loss": 0.3987, + "step": 23183 + }, + { + "epoch": 1.89, + "learning_rate": 7.405475880052152e-06, + "loss": 0.473, + "step": 23184 + }, + { + "epoch": 1.89, + "learning_rate": 7.404932637983486e-06, + "loss": 0.1164, + "step": 23185 + }, + { + "epoch": 1.89, + "learning_rate": 7.4043893959148205e-06, + "loss": 0.3448, + "step": 23186 + }, + { + "epoch": 1.89, + "learning_rate": 7.403846153846155e-06, + "loss": 0.4066, + "step": 23187 + }, + { + "epoch": 1.89, + "learning_rate": 7.403302911777489e-06, + "loss": 0.1726, + "step": 23188 + }, + { + "epoch": 1.89, + "learning_rate": 7.402759669708823e-06, + "loss": 0.5072, + "step": 23189 + }, + { + "epoch": 1.89, + "learning_rate": 7.4022164276401575e-06, + "loss": 0.2129, + "step": 23190 + }, + { + "epoch": 1.89, + "learning_rate": 7.401673185571491e-06, + "loss": 0.4292, + "step": 23191 + }, + { + "epoch": 1.89, + "learning_rate": 7.401129943502825e-06, + "loss": 0.3172, + "step": 23192 + }, + { + "epoch": 1.89, + "learning_rate": 7.400586701434159e-06, + "loss": 0.1208, + "step": 23193 + }, + { + "epoch": 1.89, + "learning_rate": 7.4000434593654935e-06, + "loss": 0.5361, + "step": 23194 + }, + { + "epoch": 1.89, + "learning_rate": 7.399500217296828e-06, + "loss": 0.1296, + "step": 23195 + }, + { + "epoch": 1.89, + "learning_rate": 7.398956975228162e-06, + "loss": 0.3536, + "step": 23196 + }, + { + "epoch": 1.89, + "learning_rate": 7.398413733159496e-06, + "loss": 0.1719, + "step": 23197 + }, + { + "epoch": 1.89, + "learning_rate": 7.3978704910908305e-06, + "loss": 0.4019, + "step": 23198 + }, + { + "epoch": 1.89, + "learning_rate": 7.397327249022165e-06, + "loss": 0.3725, + "step": 23199 + }, + { + "epoch": 1.89, + "learning_rate": 7.396784006953499e-06, + "loss": 0.285, + "step": 23200 + }, + { + "epoch": 1.89, + "learning_rate": 7.396240764884833e-06, + "loss": 0.0766, + "step": 23201 + }, + { + "epoch": 1.89, + "learning_rate": 7.395697522816167e-06, + "loss": 0.2582, + "step": 23202 + }, + { + "epoch": 1.89, + "learning_rate": 7.395154280747502e-06, + "loss": 0.2171, + "step": 23203 + }, + { + "epoch": 1.89, + "learning_rate": 7.394611038678836e-06, + "loss": 0.4321, + "step": 23204 + }, + { + "epoch": 1.89, + "learning_rate": 7.39406779661017e-06, + "loss": 0.4408, + "step": 23205 + }, + { + "epoch": 1.89, + "learning_rate": 7.393524554541504e-06, + "loss": 0.08, + "step": 23206 + }, + { + "epoch": 1.89, + "learning_rate": 7.3929813124728385e-06, + "loss": 0.5687, + "step": 23207 + }, + { + "epoch": 1.89, + "learning_rate": 7.392438070404173e-06, + "loss": 0.1091, + "step": 23208 + }, + { + "epoch": 1.89, + "learning_rate": 7.391894828335508e-06, + "loss": 0.3374, + "step": 23209 + }, + { + "epoch": 1.89, + "learning_rate": 7.39135158626684e-06, + "loss": 0.1861, + "step": 23210 + }, + { + "epoch": 1.89, + "learning_rate": 7.390808344198175e-06, + "loss": 0.2072, + "step": 23211 + }, + { + "epoch": 1.89, + "learning_rate": 7.390265102129509e-06, + "loss": 0.3592, + "step": 23212 + }, + { + "epoch": 1.89, + "learning_rate": 7.389721860060843e-06, + "loss": 0.347, + "step": 23213 + }, + { + "epoch": 1.89, + "learning_rate": 7.389178617992177e-06, + "loss": 0.0937, + "step": 23214 + }, + { + "epoch": 1.89, + "learning_rate": 7.3886353759235115e-06, + "loss": 0.3184, + "step": 23215 + }, + { + "epoch": 1.89, + "learning_rate": 7.388092133854846e-06, + "loss": 0.3955, + "step": 23216 + }, + { + "epoch": 1.89, + "learning_rate": 7.38754889178618e-06, + "loss": 0.2727, + "step": 23217 + }, + { + "epoch": 1.89, + "learning_rate": 7.387005649717515e-06, + "loss": 0.212, + "step": 23218 + }, + { + "epoch": 1.89, + "learning_rate": 7.386462407648849e-06, + "loss": 0.2878, + "step": 23219 + }, + { + "epoch": 1.89, + "learning_rate": 7.3859191655801835e-06, + "loss": 0.2135, + "step": 23220 + }, + { + "epoch": 1.89, + "learning_rate": 7.385375923511518e-06, + "loss": 0.4108, + "step": 23221 + }, + { + "epoch": 1.89, + "learning_rate": 7.384832681442852e-06, + "loss": 0.2783, + "step": 23222 + }, + { + "epoch": 1.89, + "learning_rate": 7.384289439374186e-06, + "loss": 0.3182, + "step": 23223 + }, + { + "epoch": 1.89, + "learning_rate": 7.3837461973055204e-06, + "loss": 0.2733, + "step": 23224 + }, + { + "epoch": 1.89, + "learning_rate": 7.383202955236855e-06, + "loss": 0.3514, + "step": 23225 + }, + { + "epoch": 1.89, + "learning_rate": 7.382659713168189e-06, + "loss": 0.3604, + "step": 23226 + }, + { + "epoch": 1.89, + "learning_rate": 7.382116471099523e-06, + "loss": 0.542, + "step": 23227 + }, + { + "epoch": 1.89, + "learning_rate": 7.381573229030857e-06, + "loss": 0.4475, + "step": 23228 + }, + { + "epoch": 1.89, + "learning_rate": 7.381029986962191e-06, + "loss": 0.3087, + "step": 23229 + }, + { + "epoch": 1.89, + "learning_rate": 7.380486744893525e-06, + "loss": 0.3809, + "step": 23230 + }, + { + "epoch": 1.89, + "learning_rate": 7.379943502824859e-06, + "loss": 0.2291, + "step": 23231 + }, + { + "epoch": 1.89, + "learning_rate": 7.3794002607561934e-06, + "loss": 0.3584, + "step": 23232 + }, + { + "epoch": 1.89, + "learning_rate": 7.378857018687528e-06, + "loss": 0.2941, + "step": 23233 + }, + { + "epoch": 1.89, + "learning_rate": 7.378313776618862e-06, + "loss": 0.3858, + "step": 23234 + }, + { + "epoch": 1.89, + "learning_rate": 7.377770534550196e-06, + "loss": 0.3742, + "step": 23235 + }, + { + "epoch": 1.89, + "learning_rate": 7.37722729248153e-06, + "loss": 0.3365, + "step": 23236 + }, + { + "epoch": 1.89, + "learning_rate": 7.376684050412865e-06, + "loss": 0.3074, + "step": 23237 + }, + { + "epoch": 1.89, + "learning_rate": 7.376140808344199e-06, + "loss": 0.3815, + "step": 23238 + }, + { + "epoch": 1.89, + "learning_rate": 7.375597566275533e-06, + "loss": 0.2577, + "step": 23239 + }, + { + "epoch": 1.89, + "learning_rate": 7.375054324206867e-06, + "loss": 0.3044, + "step": 23240 + }, + { + "epoch": 1.89, + "learning_rate": 7.3745110821382015e-06, + "loss": 0.5672, + "step": 23241 + }, + { + "epoch": 1.89, + "learning_rate": 7.373967840069536e-06, + "loss": 0.2484, + "step": 23242 + }, + { + "epoch": 1.89, + "learning_rate": 7.37342459800087e-06, + "loss": 0.2641, + "step": 23243 + }, + { + "epoch": 1.89, + "learning_rate": 7.372881355932204e-06, + "loss": 0.402, + "step": 23244 + }, + { + "epoch": 1.89, + "learning_rate": 7.3723381138635384e-06, + "loss": 0.3042, + "step": 23245 + }, + { + "epoch": 1.89, + "learning_rate": 7.371794871794873e-06, + "loss": 0.1528, + "step": 23246 + }, + { + "epoch": 1.89, + "learning_rate": 7.371251629726207e-06, + "loss": 0.3824, + "step": 23247 + }, + { + "epoch": 1.89, + "learning_rate": 7.37070838765754e-06, + "loss": 0.1993, + "step": 23248 + }, + { + "epoch": 1.89, + "learning_rate": 7.3701651455888745e-06, + "loss": 0.209, + "step": 23249 + }, + { + "epoch": 1.89, + "learning_rate": 7.369621903520209e-06, + "loss": 0.1705, + "step": 23250 + }, + { + "epoch": 1.89, + "eval_accuracy": 0.8459500764136526, + "eval_loss": 0.43096303939819336, + "eval_runtime": 22.3565, + "eval_samples_per_second": 439.022, + "eval_steps_per_second": 3.444, + "step": 23250 + }, + { + "epoch": 1.89, + "learning_rate": 7.369078661451543e-06, + "loss": 0.1967, + "step": 23251 + }, + { + "epoch": 1.89, + "learning_rate": 7.368535419382877e-06, + "loss": 0.3475, + "step": 23252 + }, + { + "epoch": 1.89, + "learning_rate": 7.3679921773142114e-06, + "loss": 0.4984, + "step": 23253 + }, + { + "epoch": 1.89, + "learning_rate": 7.367448935245546e-06, + "loss": 0.7083, + "step": 23254 + }, + { + "epoch": 1.89, + "learning_rate": 7.36690569317688e-06, + "loss": 0.2042, + "step": 23255 + }, + { + "epoch": 1.9, + "learning_rate": 7.366362451108214e-06, + "loss": 0.5086, + "step": 23256 + }, + { + "epoch": 1.9, + "learning_rate": 7.365819209039548e-06, + "loss": 0.2769, + "step": 23257 + }, + { + "epoch": 1.9, + "learning_rate": 7.365275966970883e-06, + "loss": 0.2754, + "step": 23258 + }, + { + "epoch": 1.9, + "learning_rate": 7.364732724902217e-06, + "loss": 0.682, + "step": 23259 + }, + { + "epoch": 1.9, + "learning_rate": 7.364189482833551e-06, + "loss": 0.3315, + "step": 23260 + }, + { + "epoch": 1.9, + "learning_rate": 7.363646240764885e-06, + "loss": 0.5043, + "step": 23261 + }, + { + "epoch": 1.9, + "learning_rate": 7.3631029986962195e-06, + "loss": 0.1277, + "step": 23262 + }, + { + "epoch": 1.9, + "learning_rate": 7.362559756627555e-06, + "loss": 0.6236, + "step": 23263 + }, + { + "epoch": 1.9, + "learning_rate": 7.362016514558889e-06, + "loss": 0.3734, + "step": 23264 + }, + { + "epoch": 1.9, + "learning_rate": 7.361473272490223e-06, + "loss": 0.3424, + "step": 23265 + }, + { + "epoch": 1.9, + "learning_rate": 7.360930030421557e-06, + "loss": 0.5109, + "step": 23266 + }, + { + "epoch": 1.9, + "learning_rate": 7.36038678835289e-06, + "loss": 0.2452, + "step": 23267 + }, + { + "epoch": 1.9, + "learning_rate": 7.359843546284224e-06, + "loss": 0.3497, + "step": 23268 + }, + { + "epoch": 1.9, + "learning_rate": 7.359300304215558e-06, + "loss": 0.4148, + "step": 23269 + }, + { + "epoch": 1.9, + "learning_rate": 7.3587570621468925e-06, + "loss": 0.3514, + "step": 23270 + }, + { + "epoch": 1.9, + "learning_rate": 7.358213820078227e-06, + "loss": 0.1772, + "step": 23271 + }, + { + "epoch": 1.9, + "learning_rate": 7.357670578009562e-06, + "loss": 0.2099, + "step": 23272 + }, + { + "epoch": 1.9, + "learning_rate": 7.357127335940896e-06, + "loss": 0.5086, + "step": 23273 + }, + { + "epoch": 1.9, + "learning_rate": 7.35658409387223e-06, + "loss": 0.4146, + "step": 23274 + }, + { + "epoch": 1.9, + "learning_rate": 7.3560408518035645e-06, + "loss": 0.2827, + "step": 23275 + }, + { + "epoch": 1.9, + "learning_rate": 7.355497609734899e-06, + "loss": 0.2585, + "step": 23276 + }, + { + "epoch": 1.9, + "learning_rate": 7.354954367666233e-06, + "loss": 0.3245, + "step": 23277 + }, + { + "epoch": 1.9, + "learning_rate": 7.354411125597567e-06, + "loss": 0.1676, + "step": 23278 + }, + { + "epoch": 1.9, + "learning_rate": 7.3538678835289014e-06, + "loss": 0.2029, + "step": 23279 + }, + { + "epoch": 1.9, + "learning_rate": 7.353324641460236e-06, + "loss": 0.366, + "step": 23280 + }, + { + "epoch": 1.9, + "learning_rate": 7.35278139939157e-06, + "loss": 0.5389, + "step": 23281 + }, + { + "epoch": 1.9, + "learning_rate": 7.352238157322904e-06, + "loss": 0.1363, + "step": 23282 + }, + { + "epoch": 1.9, + "learning_rate": 7.351694915254238e-06, + "loss": 0.4436, + "step": 23283 + }, + { + "epoch": 1.9, + "learning_rate": 7.351151673185573e-06, + "loss": 0.3539, + "step": 23284 + }, + { + "epoch": 1.9, + "learning_rate": 7.350608431116907e-06, + "loss": 0.3567, + "step": 23285 + }, + { + "epoch": 1.9, + "learning_rate": 7.35006518904824e-06, + "loss": 0.2535, + "step": 23286 + }, + { + "epoch": 1.9, + "learning_rate": 7.3495219469795744e-06, + "loss": 0.2112, + "step": 23287 + }, + { + "epoch": 1.9, + "learning_rate": 7.348978704910909e-06, + "loss": 0.2154, + "step": 23288 + }, + { + "epoch": 1.9, + "learning_rate": 7.348435462842243e-06, + "loss": 0.3611, + "step": 23289 + }, + { + "epoch": 1.9, + "learning_rate": 7.347892220773577e-06, + "loss": 0.2347, + "step": 23290 + }, + { + "epoch": 1.9, + "learning_rate": 7.347348978704911e-06, + "loss": 0.1037, + "step": 23291 + }, + { + "epoch": 1.9, + "learning_rate": 7.346805736636246e-06, + "loss": 0.3602, + "step": 23292 + }, + { + "epoch": 1.9, + "learning_rate": 7.34626249456758e-06, + "loss": 0.1446, + "step": 23293 + }, + { + "epoch": 1.9, + "learning_rate": 7.345719252498914e-06, + "loss": 0.2357, + "step": 23294 + }, + { + "epoch": 1.9, + "learning_rate": 7.345176010430248e-06, + "loss": 0.3085, + "step": 23295 + }, + { + "epoch": 1.9, + "learning_rate": 7.3446327683615825e-06, + "loss": 0.3318, + "step": 23296 + }, + { + "epoch": 1.9, + "learning_rate": 7.344089526292917e-06, + "loss": 0.2792, + "step": 23297 + }, + { + "epoch": 1.9, + "learning_rate": 7.343546284224251e-06, + "loss": 0.5674, + "step": 23298 + }, + { + "epoch": 1.9, + "learning_rate": 7.343003042155585e-06, + "loss": 0.1595, + "step": 23299 + }, + { + "epoch": 1.9, + "learning_rate": 7.3424598000869194e-06, + "loss": 0.4377, + "step": 23300 + }, + { + "epoch": 1.9, + "learning_rate": 7.341916558018254e-06, + "loss": 0.216, + "step": 23301 + }, + { + "epoch": 1.9, + "learning_rate": 7.341373315949588e-06, + "loss": 0.2555, + "step": 23302 + }, + { + "epoch": 1.9, + "learning_rate": 7.340830073880922e-06, + "loss": 0.5349, + "step": 23303 + }, + { + "epoch": 1.9, + "learning_rate": 7.340286831812256e-06, + "loss": 0.1352, + "step": 23304 + }, + { + "epoch": 1.9, + "learning_rate": 7.33974358974359e-06, + "loss": 0.3984, + "step": 23305 + }, + { + "epoch": 1.9, + "learning_rate": 7.339200347674924e-06, + "loss": 0.3108, + "step": 23306 + }, + { + "epoch": 1.9, + "learning_rate": 7.338657105606258e-06, + "loss": 0.2337, + "step": 23307 + }, + { + "epoch": 1.9, + "learning_rate": 7.338113863537592e-06, + "loss": 0.6506, + "step": 23308 + }, + { + "epoch": 1.9, + "learning_rate": 7.337570621468927e-06, + "loss": 0.1533, + "step": 23309 + }, + { + "epoch": 1.9, + "learning_rate": 7.337027379400261e-06, + "loss": 0.5668, + "step": 23310 + }, + { + "epoch": 1.9, + "learning_rate": 7.336484137331595e-06, + "loss": 0.2989, + "step": 23311 + }, + { + "epoch": 1.9, + "learning_rate": 7.335940895262929e-06, + "loss": 0.7709, + "step": 23312 + }, + { + "epoch": 1.9, + "learning_rate": 7.3353976531942636e-06, + "loss": 0.5321, + "step": 23313 + }, + { + "epoch": 1.9, + "learning_rate": 7.334854411125598e-06, + "loss": 0.3286, + "step": 23314 + }, + { + "epoch": 1.9, + "learning_rate": 7.334311169056932e-06, + "loss": 0.3154, + "step": 23315 + }, + { + "epoch": 1.9, + "learning_rate": 7.333767926988266e-06, + "loss": 0.3561, + "step": 23316 + }, + { + "epoch": 1.9, + "learning_rate": 7.333224684919601e-06, + "loss": 0.379, + "step": 23317 + }, + { + "epoch": 1.9, + "learning_rate": 7.3326814428509356e-06, + "loss": 0.2462, + "step": 23318 + }, + { + "epoch": 1.9, + "learning_rate": 7.33213820078227e-06, + "loss": 0.1967, + "step": 23319 + }, + { + "epoch": 1.9, + "learning_rate": 7.331594958713604e-06, + "loss": 0.3765, + "step": 23320 + }, + { + "epoch": 1.9, + "learning_rate": 7.331051716644938e-06, + "loss": 0.7178, + "step": 23321 + }, + { + "epoch": 1.9, + "learning_rate": 7.3305084745762725e-06, + "loss": 0.2119, + "step": 23322 + }, + { + "epoch": 1.9, + "learning_rate": 7.329965232507607e-06, + "loss": 0.4227, + "step": 23323 + }, + { + "epoch": 1.9, + "learning_rate": 7.329421990438939e-06, + "loss": 0.3037, + "step": 23324 + }, + { + "epoch": 1.9, + "learning_rate": 7.3288787483702735e-06, + "loss": 0.4432, + "step": 23325 + }, + { + "epoch": 1.9, + "learning_rate": 7.3283355063016086e-06, + "loss": 0.355, + "step": 23326 + }, + { + "epoch": 1.9, + "learning_rate": 7.327792264232943e-06, + "loss": 0.3696, + "step": 23327 + }, + { + "epoch": 1.9, + "learning_rate": 7.327249022164277e-06, + "loss": 0.2398, + "step": 23328 + }, + { + "epoch": 1.9, + "learning_rate": 7.326705780095611e-06, + "loss": 0.4179, + "step": 23329 + }, + { + "epoch": 1.9, + "learning_rate": 7.3261625380269455e-06, + "loss": 0.2164, + "step": 23330 + }, + { + "epoch": 1.9, + "learning_rate": 7.32561929595828e-06, + "loss": 0.5373, + "step": 23331 + }, + { + "epoch": 1.9, + "learning_rate": 7.325076053889614e-06, + "loss": 0.5413, + "step": 23332 + }, + { + "epoch": 1.9, + "learning_rate": 7.324532811820948e-06, + "loss": 0.4052, + "step": 23333 + }, + { + "epoch": 1.9, + "learning_rate": 7.323989569752282e-06, + "loss": 0.1574, + "step": 23334 + }, + { + "epoch": 1.9, + "learning_rate": 7.323446327683617e-06, + "loss": 0.2344, + "step": 23335 + }, + { + "epoch": 1.9, + "learning_rate": 7.322903085614951e-06, + "loss": 0.1755, + "step": 23336 + }, + { + "epoch": 1.9, + "learning_rate": 7.322359843546285e-06, + "loss": 0.3027, + "step": 23337 + }, + { + "epoch": 1.9, + "learning_rate": 7.321816601477619e-06, + "loss": 0.2057, + "step": 23338 + }, + { + "epoch": 1.9, + "learning_rate": 7.3212733594089536e-06, + "loss": 0.2849, + "step": 23339 + }, + { + "epoch": 1.9, + "learning_rate": 7.320730117340288e-06, + "loss": 0.3712, + "step": 23340 + }, + { + "epoch": 1.9, + "learning_rate": 7.320186875271622e-06, + "loss": 0.3322, + "step": 23341 + }, + { + "epoch": 1.9, + "learning_rate": 7.319643633202956e-06, + "loss": 0.468, + "step": 23342 + }, + { + "epoch": 1.9, + "learning_rate": 7.31910039113429e-06, + "loss": 0.3096, + "step": 23343 + }, + { + "epoch": 1.9, + "learning_rate": 7.318557149065624e-06, + "loss": 0.1904, + "step": 23344 + }, + { + "epoch": 1.9, + "learning_rate": 7.318013906996958e-06, + "loss": 0.2672, + "step": 23345 + }, + { + "epoch": 1.9, + "learning_rate": 7.317470664928292e-06, + "loss": 0.2905, + "step": 23346 + }, + { + "epoch": 1.9, + "learning_rate": 7.3169274228596266e-06, + "loss": 0.1563, + "step": 23347 + }, + { + "epoch": 1.9, + "learning_rate": 7.316384180790961e-06, + "loss": 0.2187, + "step": 23348 + }, + { + "epoch": 1.9, + "learning_rate": 7.315840938722295e-06, + "loss": 0.4096, + "step": 23349 + }, + { + "epoch": 1.9, + "learning_rate": 7.315297696653629e-06, + "loss": 0.3059, + "step": 23350 + }, + { + "epoch": 1.9, + "learning_rate": 7.3147544545849635e-06, + "loss": 0.5077, + "step": 23351 + }, + { + "epoch": 1.9, + "learning_rate": 7.314211212516298e-06, + "loss": 0.3554, + "step": 23352 + }, + { + "epoch": 1.9, + "learning_rate": 7.313667970447632e-06, + "loss": 0.2353, + "step": 23353 + }, + { + "epoch": 1.9, + "learning_rate": 7.313124728378966e-06, + "loss": 0.3477, + "step": 23354 + }, + { + "epoch": 1.9, + "learning_rate": 7.3125814863103e-06, + "loss": 0.2706, + "step": 23355 + }, + { + "epoch": 1.9, + "learning_rate": 7.312038244241635e-06, + "loss": 0.154, + "step": 23356 + }, + { + "epoch": 1.9, + "learning_rate": 7.311495002172969e-06, + "loss": 0.3436, + "step": 23357 + }, + { + "epoch": 1.9, + "learning_rate": 7.310951760104303e-06, + "loss": 0.5219, + "step": 23358 + }, + { + "epoch": 1.9, + "learning_rate": 7.310408518035637e-06, + "loss": 0.408, + "step": 23359 + }, + { + "epoch": 1.9, + "learning_rate": 7.3098652759669716e-06, + "loss": 0.2065, + "step": 23360 + }, + { + "epoch": 1.9, + "learning_rate": 7.309322033898306e-06, + "loss": 0.3805, + "step": 23361 + }, + { + "epoch": 1.9, + "learning_rate": 7.308778791829639e-06, + "loss": 0.3052, + "step": 23362 + }, + { + "epoch": 1.9, + "learning_rate": 7.308235549760973e-06, + "loss": 0.3036, + "step": 23363 + }, + { + "epoch": 1.9, + "learning_rate": 7.307692307692308e-06, + "loss": 0.1893, + "step": 23364 + }, + { + "epoch": 1.9, + "learning_rate": 7.307149065623642e-06, + "loss": 0.5128, + "step": 23365 + }, + { + "epoch": 1.9, + "learning_rate": 7.306605823554976e-06, + "loss": 0.3631, + "step": 23366 + }, + { + "epoch": 1.9, + "learning_rate": 7.30606258148631e-06, + "loss": 0.3927, + "step": 23367 + }, + { + "epoch": 1.9, + "learning_rate": 7.3055193394176446e-06, + "loss": 0.4992, + "step": 23368 + }, + { + "epoch": 1.9, + "learning_rate": 7.304976097348979e-06, + "loss": 0.1559, + "step": 23369 + }, + { + "epoch": 1.9, + "learning_rate": 7.304432855280313e-06, + "loss": 0.2751, + "step": 23370 + }, + { + "epoch": 1.9, + "learning_rate": 7.303889613211648e-06, + "loss": 0.1494, + "step": 23371 + }, + { + "epoch": 1.9, + "learning_rate": 7.303346371142982e-06, + "loss": 0.1888, + "step": 23372 + }, + { + "epoch": 1.9, + "learning_rate": 7.3028031290743166e-06, + "loss": 0.3966, + "step": 23373 + }, + { + "epoch": 1.9, + "learning_rate": 7.302259887005651e-06, + "loss": 0.236, + "step": 23374 + }, + { + "epoch": 1.9, + "learning_rate": 7.301716644936985e-06, + "loss": 0.3454, + "step": 23375 + }, + { + "epoch": 1.9, + "learning_rate": 7.301173402868319e-06, + "loss": 0.2741, + "step": 23376 + }, + { + "epoch": 1.9, + "learning_rate": 7.3006301607996535e-06, + "loss": 0.3768, + "step": 23377 + }, + { + "epoch": 1.9, + "learning_rate": 7.300086918730988e-06, + "loss": 0.5107, + "step": 23378 + }, + { + "epoch": 1.91, + "learning_rate": 7.299543676662322e-06, + "loss": 0.239, + "step": 23379 + }, + { + "epoch": 1.91, + "learning_rate": 7.299000434593656e-06, + "loss": 0.4331, + "step": 23380 + }, + { + "epoch": 1.91, + "learning_rate": 7.2984571925249896e-06, + "loss": 0.315, + "step": 23381 + }, + { + "epoch": 1.91, + "learning_rate": 7.297913950456324e-06, + "loss": 0.2314, + "step": 23382 + }, + { + "epoch": 1.91, + "learning_rate": 7.297370708387658e-06, + "loss": 0.5282, + "step": 23383 + }, + { + "epoch": 1.91, + "learning_rate": 7.296827466318992e-06, + "loss": 0.3729, + "step": 23384 + }, + { + "epoch": 1.91, + "learning_rate": 7.2962842242503265e-06, + "loss": 0.3373, + "step": 23385 + }, + { + "epoch": 1.91, + "learning_rate": 7.295740982181661e-06, + "loss": 0.488, + "step": 23386 + }, + { + "epoch": 1.91, + "learning_rate": 7.295197740112995e-06, + "loss": 0.2749, + "step": 23387 + }, + { + "epoch": 1.91, + "learning_rate": 7.294654498044329e-06, + "loss": 0.5018, + "step": 23388 + }, + { + "epoch": 1.91, + "learning_rate": 7.294111255975663e-06, + "loss": 0.1307, + "step": 23389 + }, + { + "epoch": 1.91, + "learning_rate": 7.293568013906998e-06, + "loss": 0.3656, + "step": 23390 + }, + { + "epoch": 1.91, + "learning_rate": 7.293024771838332e-06, + "loss": 0.1838, + "step": 23391 + }, + { + "epoch": 1.91, + "learning_rate": 7.292481529769666e-06, + "loss": 0.2499, + "step": 23392 + }, + { + "epoch": 1.91, + "learning_rate": 7.291938287701e-06, + "loss": 0.2802, + "step": 23393 + }, + { + "epoch": 1.91, + "learning_rate": 7.2913950456323346e-06, + "loss": 0.4171, + "step": 23394 + }, + { + "epoch": 1.91, + "learning_rate": 7.290851803563669e-06, + "loss": 0.6332, + "step": 23395 + }, + { + "epoch": 1.91, + "learning_rate": 7.290308561495003e-06, + "loss": 0.2046, + "step": 23396 + }, + { + "epoch": 1.91, + "learning_rate": 7.289765319426337e-06, + "loss": 0.2589, + "step": 23397 + }, + { + "epoch": 1.91, + "learning_rate": 7.2892220773576715e-06, + "loss": 0.5792, + "step": 23398 + }, + { + "epoch": 1.91, + "learning_rate": 7.288678835289006e-06, + "loss": 0.1479, + "step": 23399 + }, + { + "epoch": 1.91, + "learning_rate": 7.288135593220339e-06, + "loss": 0.5178, + "step": 23400 + }, + { + "epoch": 1.91, + "learning_rate": 7.287592351151673e-06, + "loss": 0.2306, + "step": 23401 + }, + { + "epoch": 1.91, + "learning_rate": 7.2870491090830076e-06, + "loss": 0.4712, + "step": 23402 + }, + { + "epoch": 1.91, + "learning_rate": 7.286505867014342e-06, + "loss": 0.4812, + "step": 23403 + }, + { + "epoch": 1.91, + "learning_rate": 7.285962624945676e-06, + "loss": 0.3918, + "step": 23404 + }, + { + "epoch": 1.91, + "learning_rate": 7.28541938287701e-06, + "loss": 0.2386, + "step": 23405 + }, + { + "epoch": 1.91, + "learning_rate": 7.2848761408083445e-06, + "loss": 0.2026, + "step": 23406 + }, + { + "epoch": 1.91, + "learning_rate": 7.284332898739679e-06, + "loss": 0.3301, + "step": 23407 + }, + { + "epoch": 1.91, + "learning_rate": 7.283789656671013e-06, + "loss": 0.233, + "step": 23408 + }, + { + "epoch": 1.91, + "learning_rate": 7.283246414602347e-06, + "loss": 0.2116, + "step": 23409 + }, + { + "epoch": 1.91, + "learning_rate": 7.282703172533681e-06, + "loss": 0.4731, + "step": 23410 + }, + { + "epoch": 1.91, + "learning_rate": 7.282159930465016e-06, + "loss": 0.3163, + "step": 23411 + }, + { + "epoch": 1.91, + "learning_rate": 7.28161668839635e-06, + "loss": 0.4792, + "step": 23412 + }, + { + "epoch": 1.91, + "learning_rate": 7.281073446327684e-06, + "loss": 0.309, + "step": 23413 + }, + { + "epoch": 1.91, + "learning_rate": 7.280530204259018e-06, + "loss": 0.3366, + "step": 23414 + }, + { + "epoch": 1.91, + "learning_rate": 7.2799869621903525e-06, + "loss": 0.3203, + "step": 23415 + }, + { + "epoch": 1.91, + "learning_rate": 7.279443720121688e-06, + "loss": 0.4469, + "step": 23416 + }, + { + "epoch": 1.91, + "learning_rate": 7.278900478053022e-06, + "loss": 0.1849, + "step": 23417 + }, + { + "epoch": 1.91, + "learning_rate": 7.278357235984356e-06, + "loss": 0.3546, + "step": 23418 + }, + { + "epoch": 1.91, + "learning_rate": 7.277813993915689e-06, + "loss": 0.2895, + "step": 23419 + }, + { + "epoch": 1.91, + "learning_rate": 7.277270751847023e-06, + "loss": 0.1388, + "step": 23420 + }, + { + "epoch": 1.91, + "learning_rate": 7.276727509778357e-06, + "loss": 0.3119, + "step": 23421 + }, + { + "epoch": 1.91, + "learning_rate": 7.276184267709691e-06, + "loss": 0.1582, + "step": 23422 + }, + { + "epoch": 1.91, + "learning_rate": 7.2756410256410255e-06, + "loss": 0.4362, + "step": 23423 + }, + { + "epoch": 1.91, + "learning_rate": 7.27509778357236e-06, + "loss": 0.2741, + "step": 23424 + }, + { + "epoch": 1.91, + "learning_rate": 7.274554541503695e-06, + "loss": 0.6804, + "step": 23425 + }, + { + "epoch": 1.91, + "learning_rate": 7.274011299435029e-06, + "loss": 0.2968, + "step": 23426 + }, + { + "epoch": 1.91, + "learning_rate": 7.273468057366363e-06, + "loss": 0.1587, + "step": 23427 + }, + { + "epoch": 1.91, + "learning_rate": 7.2729248152976975e-06, + "loss": 0.254, + "step": 23428 + }, + { + "epoch": 1.91, + "learning_rate": 7.272381573229032e-06, + "loss": 0.2677, + "step": 23429 + }, + { + "epoch": 1.91, + "learning_rate": 7.271838331160366e-06, + "loss": 0.4791, + "step": 23430 + }, + { + "epoch": 1.91, + "learning_rate": 7.2712950890917e-06, + "loss": 0.2646, + "step": 23431 + }, + { + "epoch": 1.91, + "learning_rate": 7.2707518470230345e-06, + "loss": 0.3054, + "step": 23432 + }, + { + "epoch": 1.91, + "learning_rate": 7.270208604954369e-06, + "loss": 0.254, + "step": 23433 + }, + { + "epoch": 1.91, + "learning_rate": 7.269665362885703e-06, + "loss": 0.285, + "step": 23434 + }, + { + "epoch": 1.91, + "learning_rate": 7.269122120817037e-06, + "loss": 0.301, + "step": 23435 + }, + { + "epoch": 1.91, + "learning_rate": 7.268578878748371e-06, + "loss": 0.3899, + "step": 23436 + }, + { + "epoch": 1.91, + "learning_rate": 7.268035636679706e-06, + "loss": 0.4035, + "step": 23437 + }, + { + "epoch": 1.91, + "learning_rate": 7.267492394611039e-06, + "loss": 0.2095, + "step": 23438 + }, + { + "epoch": 1.91, + "learning_rate": 7.266949152542373e-06, + "loss": 0.2127, + "step": 23439 + }, + { + "epoch": 1.91, + "learning_rate": 7.2664059104737075e-06, + "loss": 0.2231, + "step": 23440 + }, + { + "epoch": 1.91, + "learning_rate": 7.265862668405042e-06, + "loss": 0.3682, + "step": 23441 + }, + { + "epoch": 1.91, + "learning_rate": 7.265319426336376e-06, + "loss": 0.2193, + "step": 23442 + }, + { + "epoch": 1.91, + "learning_rate": 7.26477618426771e-06, + "loss": 0.1304, + "step": 23443 + }, + { + "epoch": 1.91, + "learning_rate": 7.264232942199044e-06, + "loss": 0.4391, + "step": 23444 + }, + { + "epoch": 1.91, + "learning_rate": 7.263689700130379e-06, + "loss": 0.1927, + "step": 23445 + }, + { + "epoch": 1.91, + "learning_rate": 7.263146458061713e-06, + "loss": 0.4125, + "step": 23446 + }, + { + "epoch": 1.91, + "learning_rate": 7.262603215993047e-06, + "loss": 0.2793, + "step": 23447 + }, + { + "epoch": 1.91, + "learning_rate": 7.262059973924381e-06, + "loss": 0.4196, + "step": 23448 + }, + { + "epoch": 1.91, + "learning_rate": 7.2615167318557155e-06, + "loss": 0.2982, + "step": 23449 + }, + { + "epoch": 1.91, + "learning_rate": 7.26097348978705e-06, + "loss": 0.4221, + "step": 23450 + }, + { + "epoch": 1.91, + "learning_rate": 7.260430247718384e-06, + "loss": 0.2803, + "step": 23451 + }, + { + "epoch": 1.91, + "learning_rate": 7.259887005649718e-06, + "loss": 0.2793, + "step": 23452 + }, + { + "epoch": 1.91, + "learning_rate": 7.2593437635810525e-06, + "loss": 0.3648, + "step": 23453 + }, + { + "epoch": 1.91, + "learning_rate": 7.258800521512387e-06, + "loss": 0.2937, + "step": 23454 + }, + { + "epoch": 1.91, + "learning_rate": 7.258257279443721e-06, + "loss": 0.5032, + "step": 23455 + }, + { + "epoch": 1.91, + "learning_rate": 7.257714037375055e-06, + "loss": 0.4324, + "step": 23456 + }, + { + "epoch": 1.91, + "learning_rate": 7.2571707953063885e-06, + "loss": 0.4145, + "step": 23457 + }, + { + "epoch": 1.91, + "learning_rate": 7.256627553237723e-06, + "loss": 0.1951, + "step": 23458 + }, + { + "epoch": 1.91, + "learning_rate": 7.256084311169057e-06, + "loss": 0.3748, + "step": 23459 + }, + { + "epoch": 1.91, + "learning_rate": 7.255541069100391e-06, + "loss": 0.4041, + "step": 23460 + }, + { + "epoch": 1.91, + "learning_rate": 7.2549978270317255e-06, + "loss": 0.1309, + "step": 23461 + }, + { + "epoch": 1.91, + "learning_rate": 7.25445458496306e-06, + "loss": 0.3213, + "step": 23462 + }, + { + "epoch": 1.91, + "learning_rate": 7.253911342894394e-06, + "loss": 0.1162, + "step": 23463 + }, + { + "epoch": 1.91, + "learning_rate": 7.253368100825728e-06, + "loss": 0.5038, + "step": 23464 + }, + { + "epoch": 1.91, + "learning_rate": 7.252824858757062e-06, + "loss": 0.4514, + "step": 23465 + }, + { + "epoch": 1.91, + "learning_rate": 7.252281616688397e-06, + "loss": 0.3008, + "step": 23466 + }, + { + "epoch": 1.91, + "learning_rate": 7.251738374619731e-06, + "loss": 0.1724, + "step": 23467 + }, + { + "epoch": 1.91, + "learning_rate": 7.251195132551065e-06, + "loss": 0.4905, + "step": 23468 + }, + { + "epoch": 1.91, + "learning_rate": 7.250651890482399e-06, + "loss": 0.2745, + "step": 23469 + }, + { + "epoch": 1.91, + "learning_rate": 7.250108648413734e-06, + "loss": 0.1193, + "step": 23470 + }, + { + "epoch": 1.91, + "learning_rate": 7.249565406345069e-06, + "loss": 0.382, + "step": 23471 + }, + { + "epoch": 1.91, + "learning_rate": 7.249022164276403e-06, + "loss": 0.3314, + "step": 23472 + }, + { + "epoch": 1.91, + "learning_rate": 7.248478922207737e-06, + "loss": 0.5547, + "step": 23473 + }, + { + "epoch": 1.91, + "learning_rate": 7.247935680139071e-06, + "loss": 0.3196, + "step": 23474 + }, + { + "epoch": 1.91, + "learning_rate": 7.2473924380704055e-06, + "loss": 0.3577, + "step": 23475 + }, + { + "epoch": 1.91, + "learning_rate": 7.246849196001738e-06, + "loss": 0.2087, + "step": 23476 + }, + { + "epoch": 1.91, + "learning_rate": 7.246305953933072e-06, + "loss": 0.3202, + "step": 23477 + }, + { + "epoch": 1.91, + "learning_rate": 7.2457627118644065e-06, + "loss": 0.4678, + "step": 23478 + }, + { + "epoch": 1.91, + "learning_rate": 7.245219469795742e-06, + "loss": 0.4061, + "step": 23479 + }, + { + "epoch": 1.91, + "learning_rate": 7.244676227727076e-06, + "loss": 0.2565, + "step": 23480 + }, + { + "epoch": 1.91, + "learning_rate": 7.24413298565841e-06, + "loss": 0.345, + "step": 23481 + }, + { + "epoch": 1.91, + "learning_rate": 7.243589743589744e-06, + "loss": 0.223, + "step": 23482 + }, + { + "epoch": 1.91, + "learning_rate": 7.2430465015210785e-06, + "loss": 0.2603, + "step": 23483 + }, + { + "epoch": 1.91, + "learning_rate": 7.242503259452413e-06, + "loss": 0.5627, + "step": 23484 + }, + { + "epoch": 1.91, + "learning_rate": 7.241960017383747e-06, + "loss": 0.191, + "step": 23485 + }, + { + "epoch": 1.91, + "learning_rate": 7.241416775315081e-06, + "loss": 0.583, + "step": 23486 + }, + { + "epoch": 1.91, + "learning_rate": 7.2408735332464155e-06, + "loss": 0.198, + "step": 23487 + }, + { + "epoch": 1.91, + "learning_rate": 7.24033029117775e-06, + "loss": 0.1253, + "step": 23488 + }, + { + "epoch": 1.91, + "learning_rate": 7.239787049109084e-06, + "loss": 0.2456, + "step": 23489 + }, + { + "epoch": 1.91, + "learning_rate": 7.239243807040418e-06, + "loss": 0.111, + "step": 23490 + }, + { + "epoch": 1.91, + "learning_rate": 7.238700564971752e-06, + "loss": 0.2331, + "step": 23491 + }, + { + "epoch": 1.91, + "learning_rate": 7.238157322903087e-06, + "loss": 0.3371, + "step": 23492 + }, + { + "epoch": 1.91, + "learning_rate": 7.237614080834421e-06, + "loss": 0.362, + "step": 23493 + }, + { + "epoch": 1.91, + "learning_rate": 7.237070838765755e-06, + "loss": 0.5641, + "step": 23494 + }, + { + "epoch": 1.91, + "learning_rate": 7.2365275966970885e-06, + "loss": 0.3307, + "step": 23495 + }, + { + "epoch": 1.91, + "learning_rate": 7.235984354628423e-06, + "loss": 0.2509, + "step": 23496 + }, + { + "epoch": 1.91, + "learning_rate": 7.235441112559757e-06, + "loss": 0.3943, + "step": 23497 + }, + { + "epoch": 1.91, + "learning_rate": 7.234897870491091e-06, + "loss": 0.2192, + "step": 23498 + }, + { + "epoch": 1.91, + "learning_rate": 7.234354628422425e-06, + "loss": 0.3751, + "step": 23499 + }, + { + "epoch": 1.91, + "learning_rate": 7.23381138635376e-06, + "loss": 0.1379, + "step": 23500 + }, + { + "epoch": 1.91, + "eval_accuracy": 0.8463576158940397, + "eval_loss": 0.4254840612411499, + "eval_runtime": 22.3408, + "eval_samples_per_second": 439.331, + "eval_steps_per_second": 3.447, + "step": 23500 + }, + { + "epoch": 1.92, + "learning_rate": 7.233268144285094e-06, + "loss": 0.2469, + "step": 23501 + }, + { + "epoch": 1.92, + "learning_rate": 7.232724902216428e-06, + "loss": 0.3513, + "step": 23502 + }, + { + "epoch": 1.92, + "learning_rate": 7.232181660147762e-06, + "loss": 0.4206, + "step": 23503 + }, + { + "epoch": 1.92, + "learning_rate": 7.2316384180790965e-06, + "loss": 0.4464, + "step": 23504 + }, + { + "epoch": 1.92, + "learning_rate": 7.231095176010431e-06, + "loss": 0.4056, + "step": 23505 + }, + { + "epoch": 1.92, + "learning_rate": 7.230551933941765e-06, + "loss": 0.3951, + "step": 23506 + }, + { + "epoch": 1.92, + "learning_rate": 7.230008691873099e-06, + "loss": 0.3736, + "step": 23507 + }, + { + "epoch": 1.92, + "learning_rate": 7.2294654498044334e-06, + "loss": 0.2158, + "step": 23508 + }, + { + "epoch": 1.92, + "learning_rate": 7.228922207735768e-06, + "loss": 0.2637, + "step": 23509 + }, + { + "epoch": 1.92, + "learning_rate": 7.228378965667102e-06, + "loss": 0.296, + "step": 23510 + }, + { + "epoch": 1.92, + "learning_rate": 7.227835723598436e-06, + "loss": 0.4024, + "step": 23511 + }, + { + "epoch": 1.92, + "learning_rate": 7.22729248152977e-06, + "loss": 0.2526, + "step": 23512 + }, + { + "epoch": 1.92, + "learning_rate": 7.226749239461105e-06, + "loss": 0.4448, + "step": 23513 + }, + { + "epoch": 1.92, + "learning_rate": 7.226205997392438e-06, + "loss": 0.2837, + "step": 23514 + }, + { + "epoch": 1.92, + "learning_rate": 7.225662755323772e-06, + "loss": 0.3544, + "step": 23515 + }, + { + "epoch": 1.92, + "learning_rate": 7.2251195132551064e-06, + "loss": 0.3596, + "step": 23516 + }, + { + "epoch": 1.92, + "learning_rate": 7.224576271186441e-06, + "loss": 0.5584, + "step": 23517 + }, + { + "epoch": 1.92, + "learning_rate": 7.224033029117775e-06, + "loss": 0.2257, + "step": 23518 + }, + { + "epoch": 1.92, + "learning_rate": 7.223489787049109e-06, + "loss": 0.193, + "step": 23519 + }, + { + "epoch": 1.92, + "learning_rate": 7.222946544980443e-06, + "loss": 0.1367, + "step": 23520 + }, + { + "epoch": 1.92, + "learning_rate": 7.222403302911778e-06, + "loss": 0.2322, + "step": 23521 + }, + { + "epoch": 1.92, + "learning_rate": 7.221860060843112e-06, + "loss": 0.2581, + "step": 23522 + }, + { + "epoch": 1.92, + "learning_rate": 7.221316818774446e-06, + "loss": 0.2393, + "step": 23523 + }, + { + "epoch": 1.92, + "learning_rate": 7.220773576705781e-06, + "loss": 0.4964, + "step": 23524 + }, + { + "epoch": 1.92, + "learning_rate": 7.220230334637115e-06, + "loss": 0.2073, + "step": 23525 + }, + { + "epoch": 1.92, + "learning_rate": 7.21968709256845e-06, + "loss": 0.1822, + "step": 23526 + }, + { + "epoch": 1.92, + "learning_rate": 7.219143850499784e-06, + "loss": 0.1472, + "step": 23527 + }, + { + "epoch": 1.92, + "learning_rate": 7.218600608431118e-06, + "loss": 0.2198, + "step": 23528 + }, + { + "epoch": 1.92, + "learning_rate": 7.218057366362452e-06, + "loss": 0.4203, + "step": 23529 + }, + { + "epoch": 1.92, + "learning_rate": 7.2175141242937865e-06, + "loss": 0.1863, + "step": 23530 + }, + { + "epoch": 1.92, + "learning_rate": 7.216970882225121e-06, + "loss": 0.1522, + "step": 23531 + }, + { + "epoch": 1.92, + "learning_rate": 7.216427640156455e-06, + "loss": 0.4174, + "step": 23532 + }, + { + "epoch": 1.92, + "learning_rate": 7.215884398087788e-06, + "loss": 0.1772, + "step": 23533 + }, + { + "epoch": 1.92, + "learning_rate": 7.215341156019123e-06, + "loss": 0.3436, + "step": 23534 + }, + { + "epoch": 1.92, + "learning_rate": 7.214797913950457e-06, + "loss": 0.4748, + "step": 23535 + }, + { + "epoch": 1.92, + "learning_rate": 7.214254671881791e-06, + "loss": 0.2359, + "step": 23536 + }, + { + "epoch": 1.92, + "learning_rate": 7.213711429813125e-06, + "loss": 0.3122, + "step": 23537 + }, + { + "epoch": 1.92, + "learning_rate": 7.2131681877444595e-06, + "loss": 0.4339, + "step": 23538 + }, + { + "epoch": 1.92, + "learning_rate": 7.212624945675794e-06, + "loss": 0.4846, + "step": 23539 + }, + { + "epoch": 1.92, + "learning_rate": 7.212081703607128e-06, + "loss": 0.3111, + "step": 23540 + }, + { + "epoch": 1.92, + "learning_rate": 7.211538461538462e-06, + "loss": 0.4685, + "step": 23541 + }, + { + "epoch": 1.92, + "learning_rate": 7.2109952194697964e-06, + "loss": 0.3582, + "step": 23542 + }, + { + "epoch": 1.92, + "learning_rate": 7.210451977401131e-06, + "loss": 0.1244, + "step": 23543 + }, + { + "epoch": 1.92, + "learning_rate": 7.209908735332465e-06, + "loss": 0.2246, + "step": 23544 + }, + { + "epoch": 1.92, + "learning_rate": 7.209365493263799e-06, + "loss": 0.4144, + "step": 23545 + }, + { + "epoch": 1.92, + "learning_rate": 7.208822251195133e-06, + "loss": 0.2001, + "step": 23546 + }, + { + "epoch": 1.92, + "learning_rate": 7.208279009126468e-06, + "loss": 0.7076, + "step": 23547 + }, + { + "epoch": 1.92, + "learning_rate": 7.207735767057802e-06, + "loss": 0.5111, + "step": 23548 + }, + { + "epoch": 1.92, + "learning_rate": 7.207192524989136e-06, + "loss": 0.1283, + "step": 23549 + }, + { + "epoch": 1.92, + "learning_rate": 7.20664928292047e-06, + "loss": 0.4324, + "step": 23550 + }, + { + "epoch": 1.92, + "learning_rate": 7.2061060408518045e-06, + "loss": 0.3349, + "step": 23551 + }, + { + "epoch": 1.92, + "learning_rate": 7.205562798783138e-06, + "loss": 0.5297, + "step": 23552 + }, + { + "epoch": 1.92, + "learning_rate": 7.205019556714472e-06, + "loss": 0.1939, + "step": 23553 + }, + { + "epoch": 1.92, + "learning_rate": 7.204476314645806e-06, + "loss": 0.1461, + "step": 23554 + }, + { + "epoch": 1.92, + "learning_rate": 7.203933072577141e-06, + "loss": 0.2525, + "step": 23555 + }, + { + "epoch": 1.92, + "learning_rate": 7.203389830508475e-06, + "loss": 0.1959, + "step": 23556 + }, + { + "epoch": 1.92, + "learning_rate": 7.202846588439809e-06, + "loss": 0.1714, + "step": 23557 + }, + { + "epoch": 1.92, + "learning_rate": 7.202303346371143e-06, + "loss": 0.1794, + "step": 23558 + }, + { + "epoch": 1.92, + "learning_rate": 7.2017601043024775e-06, + "loss": 0.4037, + "step": 23559 + }, + { + "epoch": 1.92, + "learning_rate": 7.201216862233812e-06, + "loss": 0.1744, + "step": 23560 + }, + { + "epoch": 1.92, + "learning_rate": 7.200673620165146e-06, + "loss": 0.437, + "step": 23561 + }, + { + "epoch": 1.92, + "learning_rate": 7.20013037809648e-06, + "loss": 0.3914, + "step": 23562 + }, + { + "epoch": 1.92, + "learning_rate": 7.1995871360278144e-06, + "loss": 0.3935, + "step": 23563 + }, + { + "epoch": 1.92, + "learning_rate": 7.199043893959149e-06, + "loss": 0.1858, + "step": 23564 + }, + { + "epoch": 1.92, + "learning_rate": 7.198500651890483e-06, + "loss": 0.2272, + "step": 23565 + }, + { + "epoch": 1.92, + "learning_rate": 7.197957409821817e-06, + "loss": 0.1085, + "step": 23566 + }, + { + "epoch": 1.92, + "learning_rate": 7.197414167753151e-06, + "loss": 0.3977, + "step": 23567 + }, + { + "epoch": 1.92, + "learning_rate": 7.196870925684486e-06, + "loss": 0.4222, + "step": 23568 + }, + { + "epoch": 1.92, + "learning_rate": 7.19632768361582e-06, + "loss": 0.2425, + "step": 23569 + }, + { + "epoch": 1.92, + "learning_rate": 7.195784441547155e-06, + "loss": 0.4141, + "step": 23570 + }, + { + "epoch": 1.92, + "learning_rate": 7.1952411994784874e-06, + "loss": 0.7427, + "step": 23571 + }, + { + "epoch": 1.92, + "learning_rate": 7.194697957409822e-06, + "loss": 0.2974, + "step": 23572 + }, + { + "epoch": 1.92, + "learning_rate": 7.194154715341156e-06, + "loss": 0.3834, + "step": 23573 + }, + { + "epoch": 1.92, + "learning_rate": 7.19361147327249e-06, + "loss": 0.5515, + "step": 23574 + }, + { + "epoch": 1.92, + "learning_rate": 7.193068231203824e-06, + "loss": 0.2966, + "step": 23575 + }, + { + "epoch": 1.92, + "learning_rate": 7.192524989135159e-06, + "loss": 0.3184, + "step": 23576 + }, + { + "epoch": 1.92, + "learning_rate": 7.191981747066493e-06, + "loss": 0.2758, + "step": 23577 + }, + { + "epoch": 1.92, + "learning_rate": 7.191438504997828e-06, + "loss": 0.2251, + "step": 23578 + }, + { + "epoch": 1.92, + "learning_rate": 7.190895262929162e-06, + "loss": 0.2203, + "step": 23579 + }, + { + "epoch": 1.92, + "learning_rate": 7.190352020860496e-06, + "loss": 0.4698, + "step": 23580 + }, + { + "epoch": 1.92, + "learning_rate": 7.189808778791831e-06, + "loss": 0.2877, + "step": 23581 + }, + { + "epoch": 1.92, + "learning_rate": 7.189265536723165e-06, + "loss": 0.5974, + "step": 23582 + }, + { + "epoch": 1.92, + "learning_rate": 7.188722294654499e-06, + "loss": 0.1814, + "step": 23583 + }, + { + "epoch": 1.92, + "learning_rate": 7.188179052585833e-06, + "loss": 0.2439, + "step": 23584 + }, + { + "epoch": 1.92, + "learning_rate": 7.1876358105171675e-06, + "loss": 0.1541, + "step": 23585 + }, + { + "epoch": 1.92, + "learning_rate": 7.187092568448502e-06, + "loss": 0.29, + "step": 23586 + }, + { + "epoch": 1.92, + "learning_rate": 7.186549326379836e-06, + "loss": 0.5581, + "step": 23587 + }, + { + "epoch": 1.92, + "learning_rate": 7.18600608431117e-06, + "loss": 0.4428, + "step": 23588 + }, + { + "epoch": 1.92, + "learning_rate": 7.1854628422425044e-06, + "loss": 0.2555, + "step": 23589 + }, + { + "epoch": 1.92, + "learning_rate": 7.184919600173839e-06, + "loss": 0.6051, + "step": 23590 + }, + { + "epoch": 1.92, + "learning_rate": 7.184376358105172e-06, + "loss": 0.2422, + "step": 23591 + }, + { + "epoch": 1.92, + "learning_rate": 7.183833116036506e-06, + "loss": 0.4228, + "step": 23592 + }, + { + "epoch": 1.92, + "learning_rate": 7.1832898739678405e-06, + "loss": 0.3664, + "step": 23593 + }, + { + "epoch": 1.92, + "learning_rate": 7.182746631899175e-06, + "loss": 0.3492, + "step": 23594 + }, + { + "epoch": 1.92, + "learning_rate": 7.182203389830509e-06, + "loss": 0.2368, + "step": 23595 + }, + { + "epoch": 1.92, + "learning_rate": 7.181660147761843e-06, + "loss": 0.3602, + "step": 23596 + }, + { + "epoch": 1.92, + "learning_rate": 7.1811169056931774e-06, + "loss": 0.2951, + "step": 23597 + }, + { + "epoch": 1.92, + "learning_rate": 7.180573663624512e-06, + "loss": 0.3624, + "step": 23598 + }, + { + "epoch": 1.92, + "learning_rate": 7.180030421555846e-06, + "loss": 0.2996, + "step": 23599 + }, + { + "epoch": 1.92, + "learning_rate": 7.17948717948718e-06, + "loss": 0.4841, + "step": 23600 + }, + { + "epoch": 1.92, + "learning_rate": 7.178943937418514e-06, + "loss": 0.4242, + "step": 23601 + }, + { + "epoch": 1.92, + "learning_rate": 7.178400695349849e-06, + "loss": 0.3196, + "step": 23602 + }, + { + "epoch": 1.92, + "learning_rate": 7.177857453281183e-06, + "loss": 0.2482, + "step": 23603 + }, + { + "epoch": 1.92, + "learning_rate": 7.177314211212517e-06, + "loss": 0.2745, + "step": 23604 + }, + { + "epoch": 1.92, + "learning_rate": 7.176770969143851e-06, + "loss": 0.475, + "step": 23605 + }, + { + "epoch": 1.92, + "learning_rate": 7.1762277270751855e-06, + "loss": 0.4822, + "step": 23606 + }, + { + "epoch": 1.92, + "learning_rate": 7.17568448500652e-06, + "loss": 0.2477, + "step": 23607 + }, + { + "epoch": 1.92, + "learning_rate": 7.175141242937854e-06, + "loss": 0.2975, + "step": 23608 + }, + { + "epoch": 1.92, + "learning_rate": 7.174598000869188e-06, + "loss": 0.3743, + "step": 23609 + }, + { + "epoch": 1.92, + "learning_rate": 7.1740547588005216e-06, + "loss": 0.372, + "step": 23610 + }, + { + "epoch": 1.92, + "learning_rate": 7.173511516731856e-06, + "loss": 0.3724, + "step": 23611 + }, + { + "epoch": 1.92, + "learning_rate": 7.17296827466319e-06, + "loss": 0.3303, + "step": 23612 + }, + { + "epoch": 1.92, + "learning_rate": 7.172425032594524e-06, + "loss": 0.3275, + "step": 23613 + }, + { + "epoch": 1.92, + "learning_rate": 7.1718817905258585e-06, + "loss": 0.388, + "step": 23614 + }, + { + "epoch": 1.92, + "learning_rate": 7.171338548457193e-06, + "loss": 0.337, + "step": 23615 + }, + { + "epoch": 1.92, + "learning_rate": 7.170795306388527e-06, + "loss": 0.2649, + "step": 23616 + }, + { + "epoch": 1.92, + "learning_rate": 7.170252064319861e-06, + "loss": 0.3516, + "step": 23617 + }, + { + "epoch": 1.92, + "learning_rate": 7.169708822251195e-06, + "loss": 0.5643, + "step": 23618 + }, + { + "epoch": 1.92, + "learning_rate": 7.16916558018253e-06, + "loss": 0.3608, + "step": 23619 + }, + { + "epoch": 1.92, + "learning_rate": 7.168622338113864e-06, + "loss": 0.3019, + "step": 23620 + }, + { + "epoch": 1.92, + "learning_rate": 7.168079096045198e-06, + "loss": 0.3498, + "step": 23621 + }, + { + "epoch": 1.92, + "learning_rate": 7.167535853976532e-06, + "loss": 0.6728, + "step": 23622 + }, + { + "epoch": 1.92, + "learning_rate": 7.1669926119078666e-06, + "loss": 0.3752, + "step": 23623 + }, + { + "epoch": 1.93, + "learning_rate": 7.166449369839202e-06, + "loss": 0.1776, + "step": 23624 + }, + { + "epoch": 1.93, + "learning_rate": 7.165906127770536e-06, + "loss": 0.2462, + "step": 23625 + }, + { + "epoch": 1.93, + "learning_rate": 7.16536288570187e-06, + "loss": 0.6207, + "step": 23626 + }, + { + "epoch": 1.93, + "learning_rate": 7.164819643633204e-06, + "loss": 0.4331, + "step": 23627 + }, + { + "epoch": 1.93, + "learning_rate": 7.1642764015645386e-06, + "loss": 0.173, + "step": 23628 + }, + { + "epoch": 1.93, + "learning_rate": 7.163733159495871e-06, + "loss": 0.3776, + "step": 23629 + }, + { + "epoch": 1.93, + "learning_rate": 7.163189917427205e-06, + "loss": 0.2999, + "step": 23630 + }, + { + "epoch": 1.93, + "learning_rate": 7.1626466753585396e-06, + "loss": 0.5356, + "step": 23631 + }, + { + "epoch": 1.93, + "learning_rate": 7.162103433289875e-06, + "loss": 0.3145, + "step": 23632 + }, + { + "epoch": 1.93, + "learning_rate": 7.161560191221209e-06, + "loss": 0.1887, + "step": 23633 + }, + { + "epoch": 1.93, + "learning_rate": 7.161016949152543e-06, + "loss": 0.2455, + "step": 23634 + }, + { + "epoch": 1.93, + "learning_rate": 7.160473707083877e-06, + "loss": 0.2625, + "step": 23635 + }, + { + "epoch": 1.93, + "learning_rate": 7.1599304650152116e-06, + "loss": 0.1136, + "step": 23636 + }, + { + "epoch": 1.93, + "learning_rate": 7.159387222946546e-06, + "loss": 0.325, + "step": 23637 + }, + { + "epoch": 1.93, + "learning_rate": 7.15884398087788e-06, + "loss": 0.4483, + "step": 23638 + }, + { + "epoch": 1.93, + "learning_rate": 7.158300738809214e-06, + "loss": 0.7648, + "step": 23639 + }, + { + "epoch": 1.93, + "learning_rate": 7.1577574967405485e-06, + "loss": 0.2194, + "step": 23640 + }, + { + "epoch": 1.93, + "learning_rate": 7.157214254671883e-06, + "loss": 0.5766, + "step": 23641 + }, + { + "epoch": 1.93, + "learning_rate": 7.156671012603217e-06, + "loss": 0.3345, + "step": 23642 + }, + { + "epoch": 1.93, + "learning_rate": 7.156127770534551e-06, + "loss": 0.2762, + "step": 23643 + }, + { + "epoch": 1.93, + "learning_rate": 7.155584528465885e-06, + "loss": 0.2785, + "step": 23644 + }, + { + "epoch": 1.93, + "learning_rate": 7.15504128639722e-06, + "loss": 0.3832, + "step": 23645 + }, + { + "epoch": 1.93, + "learning_rate": 7.154498044328554e-06, + "loss": 0.3131, + "step": 23646 + }, + { + "epoch": 1.93, + "learning_rate": 7.153954802259888e-06, + "loss": 0.1645, + "step": 23647 + }, + { + "epoch": 1.93, + "learning_rate": 7.1534115601912215e-06, + "loss": 0.3214, + "step": 23648 + }, + { + "epoch": 1.93, + "learning_rate": 7.152868318122556e-06, + "loss": 0.1968, + "step": 23649 + }, + { + "epoch": 1.93, + "learning_rate": 7.15232507605389e-06, + "loss": 0.2007, + "step": 23650 + }, + { + "epoch": 1.93, + "learning_rate": 7.151781833985224e-06, + "loss": 0.4235, + "step": 23651 + }, + { + "epoch": 1.93, + "learning_rate": 7.151238591916558e-06, + "loss": 0.1174, + "step": 23652 + }, + { + "epoch": 1.93, + "learning_rate": 7.150695349847893e-06, + "loss": 0.126, + "step": 23653 + }, + { + "epoch": 1.93, + "learning_rate": 7.150152107779227e-06, + "loss": 0.2916, + "step": 23654 + }, + { + "epoch": 1.93, + "learning_rate": 7.149608865710561e-06, + "loss": 0.6147, + "step": 23655 + }, + { + "epoch": 1.93, + "learning_rate": 7.149065623641895e-06, + "loss": 0.2873, + "step": 23656 + }, + { + "epoch": 1.93, + "learning_rate": 7.1485223815732296e-06, + "loss": 0.3931, + "step": 23657 + }, + { + "epoch": 1.93, + "learning_rate": 7.147979139504564e-06, + "loss": 0.2311, + "step": 23658 + }, + { + "epoch": 1.93, + "learning_rate": 7.147435897435898e-06, + "loss": 0.4766, + "step": 23659 + }, + { + "epoch": 1.93, + "learning_rate": 7.146892655367232e-06, + "loss": 0.3108, + "step": 23660 + }, + { + "epoch": 1.93, + "learning_rate": 7.1463494132985665e-06, + "loss": 0.2389, + "step": 23661 + }, + { + "epoch": 1.93, + "learning_rate": 7.145806171229901e-06, + "loss": 0.2159, + "step": 23662 + }, + { + "epoch": 1.93, + "learning_rate": 7.145262929161235e-06, + "loss": 0.3834, + "step": 23663 + }, + { + "epoch": 1.93, + "learning_rate": 7.144719687092569e-06, + "loss": 0.4332, + "step": 23664 + }, + { + "epoch": 1.93, + "learning_rate": 7.144176445023903e-06, + "loss": 0.2471, + "step": 23665 + }, + { + "epoch": 1.93, + "learning_rate": 7.143633202955238e-06, + "loss": 0.1884, + "step": 23666 + }, + { + "epoch": 1.93, + "learning_rate": 7.143089960886571e-06, + "loss": 0.2005, + "step": 23667 + }, + { + "epoch": 1.93, + "learning_rate": 7.142546718817905e-06, + "loss": 0.479, + "step": 23668 + }, + { + "epoch": 1.93, + "learning_rate": 7.1420034767492395e-06, + "loss": 0.5913, + "step": 23669 + }, + { + "epoch": 1.93, + "learning_rate": 7.141460234680574e-06, + "loss": 0.5977, + "step": 23670 + }, + { + "epoch": 1.93, + "learning_rate": 7.140916992611908e-06, + "loss": 0.2731, + "step": 23671 + }, + { + "epoch": 1.93, + "learning_rate": 7.140373750543242e-06, + "loss": 0.2469, + "step": 23672 + }, + { + "epoch": 1.93, + "learning_rate": 7.139830508474576e-06, + "loss": 0.5098, + "step": 23673 + }, + { + "epoch": 1.93, + "learning_rate": 7.139287266405911e-06, + "loss": 0.7135, + "step": 23674 + }, + { + "epoch": 1.93, + "learning_rate": 7.138744024337245e-06, + "loss": 0.2176, + "step": 23675 + }, + { + "epoch": 1.93, + "learning_rate": 7.138200782268579e-06, + "loss": 0.1039, + "step": 23676 + }, + { + "epoch": 1.93, + "learning_rate": 7.137657540199913e-06, + "loss": 0.238, + "step": 23677 + }, + { + "epoch": 1.93, + "learning_rate": 7.137114298131248e-06, + "loss": 0.3887, + "step": 23678 + }, + { + "epoch": 1.93, + "learning_rate": 7.136571056062583e-06, + "loss": 0.4312, + "step": 23679 + }, + { + "epoch": 1.93, + "learning_rate": 7.136027813993917e-06, + "loss": 0.5003, + "step": 23680 + }, + { + "epoch": 1.93, + "learning_rate": 7.135484571925251e-06, + "loss": 0.107, + "step": 23681 + }, + { + "epoch": 1.93, + "learning_rate": 7.134941329856585e-06, + "loss": 0.1889, + "step": 23682 + }, + { + "epoch": 1.93, + "learning_rate": 7.1343980877879196e-06, + "loss": 0.2904, + "step": 23683 + }, + { + "epoch": 1.93, + "learning_rate": 7.133854845719254e-06, + "loss": 0.2747, + "step": 23684 + }, + { + "epoch": 1.93, + "learning_rate": 7.133311603650588e-06, + "loss": 0.2694, + "step": 23685 + }, + { + "epoch": 1.93, + "learning_rate": 7.132768361581921e-06, + "loss": 0.5225, + "step": 23686 + }, + { + "epoch": 1.93, + "learning_rate": 7.132225119513256e-06, + "loss": 0.2554, + "step": 23687 + }, + { + "epoch": 1.93, + "learning_rate": 7.13168187744459e-06, + "loss": 0.517, + "step": 23688 + }, + { + "epoch": 1.93, + "learning_rate": 7.131138635375924e-06, + "loss": 0.4287, + "step": 23689 + }, + { + "epoch": 1.93, + "learning_rate": 7.130595393307258e-06, + "loss": 0.3713, + "step": 23690 + }, + { + "epoch": 1.93, + "learning_rate": 7.1300521512385926e-06, + "loss": 0.4969, + "step": 23691 + }, + { + "epoch": 1.93, + "learning_rate": 7.129508909169927e-06, + "loss": 0.2536, + "step": 23692 + }, + { + "epoch": 1.93, + "learning_rate": 7.128965667101261e-06, + "loss": 0.6443, + "step": 23693 + }, + { + "epoch": 1.93, + "learning_rate": 7.128422425032595e-06, + "loss": 0.2736, + "step": 23694 + }, + { + "epoch": 1.93, + "learning_rate": 7.1278791829639295e-06, + "loss": 0.1574, + "step": 23695 + }, + { + "epoch": 1.93, + "learning_rate": 7.127335940895264e-06, + "loss": 0.375, + "step": 23696 + }, + { + "epoch": 1.93, + "learning_rate": 7.126792698826598e-06, + "loss": 0.427, + "step": 23697 + }, + { + "epoch": 1.93, + "learning_rate": 7.126249456757932e-06, + "loss": 0.6135, + "step": 23698 + }, + { + "epoch": 1.93, + "learning_rate": 7.125706214689266e-06, + "loss": 0.2821, + "step": 23699 + }, + { + "epoch": 1.93, + "learning_rate": 7.125162972620601e-06, + "loss": 0.2911, + "step": 23700 + }, + { + "epoch": 1.93, + "learning_rate": 7.124619730551935e-06, + "loss": 0.2455, + "step": 23701 + }, + { + "epoch": 1.93, + "learning_rate": 7.124076488483269e-06, + "loss": 0.2483, + "step": 23702 + }, + { + "epoch": 1.93, + "learning_rate": 7.123533246414603e-06, + "loss": 0.4494, + "step": 23703 + }, + { + "epoch": 1.93, + "learning_rate": 7.1229900043459376e-06, + "loss": 0.4952, + "step": 23704 + }, + { + "epoch": 1.93, + "learning_rate": 7.122446762277271e-06, + "loss": 0.2629, + "step": 23705 + }, + { + "epoch": 1.93, + "learning_rate": 7.121903520208605e-06, + "loss": 0.3785, + "step": 23706 + }, + { + "epoch": 1.93, + "learning_rate": 7.121360278139939e-06, + "loss": 0.2192, + "step": 23707 + }, + { + "epoch": 1.93, + "learning_rate": 7.120817036071274e-06, + "loss": 0.199, + "step": 23708 + }, + { + "epoch": 1.93, + "learning_rate": 7.120273794002608e-06, + "loss": 0.2959, + "step": 23709 + }, + { + "epoch": 1.93, + "learning_rate": 7.119730551933942e-06, + "loss": 0.6797, + "step": 23710 + }, + { + "epoch": 1.93, + "learning_rate": 7.119187309865276e-06, + "loss": 0.4772, + "step": 23711 + }, + { + "epoch": 1.93, + "learning_rate": 7.1186440677966106e-06, + "loss": 0.284, + "step": 23712 + }, + { + "epoch": 1.93, + "learning_rate": 7.118100825727945e-06, + "loss": 0.4769, + "step": 23713 + }, + { + "epoch": 1.93, + "learning_rate": 7.117557583659279e-06, + "loss": 0.3059, + "step": 23714 + }, + { + "epoch": 1.93, + "learning_rate": 7.117014341590613e-06, + "loss": 0.5817, + "step": 23715 + }, + { + "epoch": 1.93, + "learning_rate": 7.1164710995219475e-06, + "loss": 0.577, + "step": 23716 + }, + { + "epoch": 1.93, + "learning_rate": 7.115927857453282e-06, + "loss": 0.2587, + "step": 23717 + }, + { + "epoch": 1.93, + "learning_rate": 7.115384615384616e-06, + "loss": 0.4979, + "step": 23718 + }, + { + "epoch": 1.93, + "learning_rate": 7.11484137331595e-06, + "loss": 0.2114, + "step": 23719 + }, + { + "epoch": 1.93, + "learning_rate": 7.114298131247284e-06, + "loss": 0.2095, + "step": 23720 + }, + { + "epoch": 1.93, + "learning_rate": 7.113754889178619e-06, + "loss": 0.1817, + "step": 23721 + }, + { + "epoch": 1.93, + "learning_rate": 7.113211647109953e-06, + "loss": 0.4183, + "step": 23722 + }, + { + "epoch": 1.93, + "learning_rate": 7.112668405041288e-06, + "loss": 0.423, + "step": 23723 + }, + { + "epoch": 1.93, + "learning_rate": 7.1121251629726205e-06, + "loss": 0.4092, + "step": 23724 + }, + { + "epoch": 1.93, + "learning_rate": 7.111581920903955e-06, + "loss": 0.327, + "step": 23725 + }, + { + "epoch": 1.93, + "learning_rate": 7.111038678835289e-06, + "loss": 0.1764, + "step": 23726 + }, + { + "epoch": 1.93, + "learning_rate": 7.110495436766623e-06, + "loss": 0.4803, + "step": 23727 + }, + { + "epoch": 1.93, + "learning_rate": 7.109952194697957e-06, + "loss": 0.3273, + "step": 23728 + }, + { + "epoch": 1.93, + "learning_rate": 7.109408952629292e-06, + "loss": 0.1913, + "step": 23729 + }, + { + "epoch": 1.93, + "learning_rate": 7.108865710560626e-06, + "loss": 0.5472, + "step": 23730 + }, + { + "epoch": 1.93, + "learning_rate": 7.10832246849196e-06, + "loss": 0.5648, + "step": 23731 + }, + { + "epoch": 1.93, + "learning_rate": 7.107779226423295e-06, + "loss": 0.2629, + "step": 23732 + }, + { + "epoch": 1.93, + "learning_rate": 7.107235984354629e-06, + "loss": 0.3781, + "step": 23733 + }, + { + "epoch": 1.93, + "learning_rate": 7.106692742285964e-06, + "loss": 0.4735, + "step": 23734 + }, + { + "epoch": 1.93, + "learning_rate": 7.106149500217298e-06, + "loss": 0.1947, + "step": 23735 + }, + { + "epoch": 1.93, + "learning_rate": 7.105606258148632e-06, + "loss": 0.2502, + "step": 23736 + }, + { + "epoch": 1.93, + "learning_rate": 7.105063016079966e-06, + "loss": 0.4137, + "step": 23737 + }, + { + "epoch": 1.93, + "learning_rate": 7.1045197740113005e-06, + "loss": 0.1979, + "step": 23738 + }, + { + "epoch": 1.93, + "learning_rate": 7.103976531942635e-06, + "loss": 0.2986, + "step": 23739 + }, + { + "epoch": 1.93, + "learning_rate": 7.103433289873969e-06, + "loss": 0.3335, + "step": 23740 + }, + { + "epoch": 1.93, + "learning_rate": 7.102890047805303e-06, + "loss": 0.4634, + "step": 23741 + }, + { + "epoch": 1.93, + "learning_rate": 7.1023468057366375e-06, + "loss": 0.2077, + "step": 23742 + }, + { + "epoch": 1.93, + "learning_rate": 7.101803563667971e-06, + "loss": 0.5217, + "step": 23743 + }, + { + "epoch": 1.93, + "learning_rate": 7.101260321599305e-06, + "loss": 0.3168, + "step": 23744 + }, + { + "epoch": 1.93, + "learning_rate": 7.100717079530639e-06, + "loss": 0.1687, + "step": 23745 + }, + { + "epoch": 1.93, + "learning_rate": 7.1001738374619735e-06, + "loss": 0.2384, + "step": 23746 + }, + { + "epoch": 1.94, + "learning_rate": 7.099630595393308e-06, + "loss": 0.4074, + "step": 23747 + }, + { + "epoch": 1.94, + "learning_rate": 7.099087353324642e-06, + "loss": 0.2337, + "step": 23748 + }, + { + "epoch": 1.94, + "learning_rate": 7.098544111255976e-06, + "loss": 0.509, + "step": 23749 + }, + { + "epoch": 1.94, + "learning_rate": 7.0980008691873105e-06, + "loss": 0.3239, + "step": 23750 + }, + { + "epoch": 1.94, + "eval_accuracy": 0.8446255731023943, + "eval_loss": 0.42166033387184143, + "eval_runtime": 22.2266, + "eval_samples_per_second": 441.587, + "eval_steps_per_second": 3.464, + "step": 23750 + }, + { + "epoch": 1.94, + "learning_rate": 7.097457627118645e-06, + "loss": 0.2225, + "step": 23751 + }, + { + "epoch": 1.94, + "learning_rate": 7.096914385049979e-06, + "loss": 0.3175, + "step": 23752 + }, + { + "epoch": 1.94, + "learning_rate": 7.096371142981313e-06, + "loss": 0.465, + "step": 23753 + }, + { + "epoch": 1.94, + "learning_rate": 7.095827900912647e-06, + "loss": 0.264, + "step": 23754 + }, + { + "epoch": 1.94, + "learning_rate": 7.095284658843982e-06, + "loss": 0.1896, + "step": 23755 + }, + { + "epoch": 1.94, + "learning_rate": 7.094741416775316e-06, + "loss": 0.4465, + "step": 23756 + }, + { + "epoch": 1.94, + "learning_rate": 7.09419817470665e-06, + "loss": 0.1829, + "step": 23757 + }, + { + "epoch": 1.94, + "learning_rate": 7.093654932637984e-06, + "loss": 0.3222, + "step": 23758 + }, + { + "epoch": 1.94, + "learning_rate": 7.0931116905693185e-06, + "loss": 0.3628, + "step": 23759 + }, + { + "epoch": 1.94, + "learning_rate": 7.092568448500653e-06, + "loss": 0.1397, + "step": 23760 + }, + { + "epoch": 1.94, + "learning_rate": 7.092025206431987e-06, + "loss": 0.3594, + "step": 23761 + }, + { + "epoch": 1.94, + "learning_rate": 7.09148196436332e-06, + "loss": 0.1359, + "step": 23762 + }, + { + "epoch": 1.94, + "learning_rate": 7.090938722294655e-06, + "loss": 0.6602, + "step": 23763 + }, + { + "epoch": 1.94, + "learning_rate": 7.090395480225989e-06, + "loss": 0.3929, + "step": 23764 + }, + { + "epoch": 1.94, + "learning_rate": 7.089852238157323e-06, + "loss": 0.2251, + "step": 23765 + }, + { + "epoch": 1.94, + "learning_rate": 7.089308996088657e-06, + "loss": 0.3414, + "step": 23766 + }, + { + "epoch": 1.94, + "learning_rate": 7.0887657540199915e-06, + "loss": 0.1134, + "step": 23767 + }, + { + "epoch": 1.94, + "learning_rate": 7.088222511951326e-06, + "loss": 0.5561, + "step": 23768 + }, + { + "epoch": 1.94, + "learning_rate": 7.08767926988266e-06, + "loss": 0.3039, + "step": 23769 + }, + { + "epoch": 1.94, + "learning_rate": 7.087136027813994e-06, + "loss": 0.2654, + "step": 23770 + }, + { + "epoch": 1.94, + "learning_rate": 7.0865927857453285e-06, + "loss": 0.4364, + "step": 23771 + }, + { + "epoch": 1.94, + "learning_rate": 7.086049543676663e-06, + "loss": 0.2167, + "step": 23772 + }, + { + "epoch": 1.94, + "learning_rate": 7.085506301607997e-06, + "loss": 0.4609, + "step": 23773 + }, + { + "epoch": 1.94, + "learning_rate": 7.084963059539331e-06, + "loss": 0.1359, + "step": 23774 + }, + { + "epoch": 1.94, + "learning_rate": 7.084419817470665e-06, + "loss": 0.2647, + "step": 23775 + }, + { + "epoch": 1.94, + "learning_rate": 7.083876575402e-06, + "loss": 0.2631, + "step": 23776 + }, + { + "epoch": 1.94, + "learning_rate": 7.083333333333335e-06, + "loss": 0.4312, + "step": 23777 + }, + { + "epoch": 1.94, + "learning_rate": 7.082790091264669e-06, + "loss": 0.7786, + "step": 23778 + }, + { + "epoch": 1.94, + "learning_rate": 7.082246849196003e-06, + "loss": 0.2966, + "step": 23779 + }, + { + "epoch": 1.94, + "learning_rate": 7.081703607127337e-06, + "loss": 0.2495, + "step": 23780 + }, + { + "epoch": 1.94, + "learning_rate": 7.08116036505867e-06, + "loss": 0.1868, + "step": 23781 + }, + { + "epoch": 1.94, + "learning_rate": 7.080617122990004e-06, + "loss": 0.1809, + "step": 23782 + }, + { + "epoch": 1.94, + "learning_rate": 7.080073880921338e-06, + "loss": 0.2916, + "step": 23783 + }, + { + "epoch": 1.94, + "learning_rate": 7.079530638852673e-06, + "loss": 0.2744, + "step": 23784 + }, + { + "epoch": 1.94, + "learning_rate": 7.078987396784007e-06, + "loss": 0.3007, + "step": 23785 + }, + { + "epoch": 1.94, + "learning_rate": 7.078444154715342e-06, + "loss": 0.2245, + "step": 23786 + }, + { + "epoch": 1.94, + "learning_rate": 7.077900912646676e-06, + "loss": 0.3233, + "step": 23787 + }, + { + "epoch": 1.94, + "learning_rate": 7.07735767057801e-06, + "loss": 0.3565, + "step": 23788 + }, + { + "epoch": 1.94, + "learning_rate": 7.076814428509345e-06, + "loss": 0.3895, + "step": 23789 + }, + { + "epoch": 1.94, + "learning_rate": 7.076271186440679e-06, + "loss": 0.2388, + "step": 23790 + }, + { + "epoch": 1.94, + "learning_rate": 7.075727944372013e-06, + "loss": 0.2396, + "step": 23791 + }, + { + "epoch": 1.94, + "learning_rate": 7.075184702303347e-06, + "loss": 0.3303, + "step": 23792 + }, + { + "epoch": 1.94, + "learning_rate": 7.0746414602346815e-06, + "loss": 0.3483, + "step": 23793 + }, + { + "epoch": 1.94, + "learning_rate": 7.074098218166016e-06, + "loss": 0.3533, + "step": 23794 + }, + { + "epoch": 1.94, + "learning_rate": 7.07355497609735e-06, + "loss": 0.478, + "step": 23795 + }, + { + "epoch": 1.94, + "learning_rate": 7.073011734028684e-06, + "loss": 0.1965, + "step": 23796 + }, + { + "epoch": 1.94, + "learning_rate": 7.0724684919600185e-06, + "loss": 0.1355, + "step": 23797 + }, + { + "epoch": 1.94, + "learning_rate": 7.071925249891353e-06, + "loss": 0.3682, + "step": 23798 + }, + { + "epoch": 1.94, + "learning_rate": 7.071382007822687e-06, + "loss": 0.1371, + "step": 23799 + }, + { + "epoch": 1.94, + "learning_rate": 7.07083876575402e-06, + "loss": 0.2245, + "step": 23800 + }, + { + "epoch": 1.94, + "learning_rate": 7.0702955236853545e-06, + "loss": 0.4437, + "step": 23801 + }, + { + "epoch": 1.94, + "learning_rate": 7.069752281616689e-06, + "loss": 0.1602, + "step": 23802 + }, + { + "epoch": 1.94, + "learning_rate": 7.069209039548023e-06, + "loss": 0.281, + "step": 23803 + }, + { + "epoch": 1.94, + "learning_rate": 7.068665797479357e-06, + "loss": 0.3561, + "step": 23804 + }, + { + "epoch": 1.94, + "learning_rate": 7.0681225554106915e-06, + "loss": 0.2593, + "step": 23805 + }, + { + "epoch": 1.94, + "learning_rate": 7.067579313342026e-06, + "loss": 0.6508, + "step": 23806 + }, + { + "epoch": 1.94, + "learning_rate": 7.06703607127336e-06, + "loss": 0.2754, + "step": 23807 + }, + { + "epoch": 1.94, + "learning_rate": 7.066492829204694e-06, + "loss": 0.0737, + "step": 23808 + }, + { + "epoch": 1.94, + "learning_rate": 7.065949587136028e-06, + "loss": 0.2178, + "step": 23809 + }, + { + "epoch": 1.94, + "learning_rate": 7.065406345067363e-06, + "loss": 0.171, + "step": 23810 + }, + { + "epoch": 1.94, + "learning_rate": 7.064863102998697e-06, + "loss": 0.2982, + "step": 23811 + }, + { + "epoch": 1.94, + "learning_rate": 7.064319860930031e-06, + "loss": 0.1804, + "step": 23812 + }, + { + "epoch": 1.94, + "learning_rate": 7.063776618861365e-06, + "loss": 0.4894, + "step": 23813 + }, + { + "epoch": 1.94, + "learning_rate": 7.0632333767926995e-06, + "loss": 0.3667, + "step": 23814 + }, + { + "epoch": 1.94, + "learning_rate": 7.062690134724034e-06, + "loss": 0.2009, + "step": 23815 + }, + { + "epoch": 1.94, + "learning_rate": 7.062146892655368e-06, + "loss": 0.3049, + "step": 23816 + }, + { + "epoch": 1.94, + "learning_rate": 7.061603650586702e-06, + "loss": 0.4441, + "step": 23817 + }, + { + "epoch": 1.94, + "learning_rate": 7.0610604085180364e-06, + "loss": 0.3853, + "step": 23818 + }, + { + "epoch": 1.94, + "learning_rate": 7.06051716644937e-06, + "loss": 0.2537, + "step": 23819 + }, + { + "epoch": 1.94, + "learning_rate": 7.059973924380704e-06, + "loss": 0.4674, + "step": 23820 + }, + { + "epoch": 1.94, + "learning_rate": 7.059430682312038e-06, + "loss": 0.5716, + "step": 23821 + }, + { + "epoch": 1.94, + "learning_rate": 7.0588874402433725e-06, + "loss": 0.4628, + "step": 23822 + }, + { + "epoch": 1.94, + "learning_rate": 7.058344198174707e-06, + "loss": 0.0979, + "step": 23823 + }, + { + "epoch": 1.94, + "learning_rate": 7.057800956106041e-06, + "loss": 0.2179, + "step": 23824 + }, + { + "epoch": 1.94, + "learning_rate": 7.057257714037375e-06, + "loss": 0.4434, + "step": 23825 + }, + { + "epoch": 1.94, + "learning_rate": 7.0567144719687094e-06, + "loss": 0.3269, + "step": 23826 + }, + { + "epoch": 1.94, + "learning_rate": 7.056171229900044e-06, + "loss": 0.207, + "step": 23827 + }, + { + "epoch": 1.94, + "learning_rate": 7.055627987831378e-06, + "loss": 0.2719, + "step": 23828 + }, + { + "epoch": 1.94, + "learning_rate": 7.055084745762712e-06, + "loss": 0.478, + "step": 23829 + }, + { + "epoch": 1.94, + "learning_rate": 7.054541503694046e-06, + "loss": 0.1747, + "step": 23830 + }, + { + "epoch": 1.94, + "learning_rate": 7.0539982616253814e-06, + "loss": 0.4639, + "step": 23831 + }, + { + "epoch": 1.94, + "learning_rate": 7.053455019556716e-06, + "loss": 0.2612, + "step": 23832 + }, + { + "epoch": 1.94, + "learning_rate": 7.05291177748805e-06, + "loss": 0.1423, + "step": 23833 + }, + { + "epoch": 1.94, + "learning_rate": 7.052368535419384e-06, + "loss": 0.369, + "step": 23834 + }, + { + "epoch": 1.94, + "learning_rate": 7.051825293350718e-06, + "loss": 0.1601, + "step": 23835 + }, + { + "epoch": 1.94, + "learning_rate": 7.051282051282053e-06, + "loss": 0.5418, + "step": 23836 + }, + { + "epoch": 1.94, + "learning_rate": 7.050738809213387e-06, + "loss": 0.2215, + "step": 23837 + }, + { + "epoch": 1.94, + "learning_rate": 7.050195567144719e-06, + "loss": 0.158, + "step": 23838 + }, + { + "epoch": 1.94, + "learning_rate": 7.049652325076054e-06, + "loss": 0.4564, + "step": 23839 + }, + { + "epoch": 1.94, + "learning_rate": 7.049109083007389e-06, + "loss": 0.4458, + "step": 23840 + }, + { + "epoch": 1.94, + "learning_rate": 7.048565840938723e-06, + "loss": 0.3492, + "step": 23841 + }, + { + "epoch": 1.94, + "learning_rate": 7.048022598870057e-06, + "loss": 0.3843, + "step": 23842 + }, + { + "epoch": 1.94, + "learning_rate": 7.047479356801391e-06, + "loss": 0.1662, + "step": 23843 + }, + { + "epoch": 1.94, + "learning_rate": 7.046936114732726e-06, + "loss": 0.1944, + "step": 23844 + }, + { + "epoch": 1.94, + "learning_rate": 7.04639287266406e-06, + "loss": 0.4802, + "step": 23845 + }, + { + "epoch": 1.94, + "learning_rate": 7.045849630595394e-06, + "loss": 0.2452, + "step": 23846 + }, + { + "epoch": 1.94, + "learning_rate": 7.045306388526728e-06, + "loss": 0.1209, + "step": 23847 + }, + { + "epoch": 1.94, + "learning_rate": 7.0447631464580625e-06, + "loss": 0.4413, + "step": 23848 + }, + { + "epoch": 1.94, + "learning_rate": 7.044219904389397e-06, + "loss": 0.2573, + "step": 23849 + }, + { + "epoch": 1.94, + "learning_rate": 7.043676662320731e-06, + "loss": 0.322, + "step": 23850 + }, + { + "epoch": 1.94, + "learning_rate": 7.043133420252065e-06, + "loss": 0.2901, + "step": 23851 + }, + { + "epoch": 1.94, + "learning_rate": 7.0425901781833994e-06, + "loss": 0.4686, + "step": 23852 + }, + { + "epoch": 1.94, + "learning_rate": 7.042046936114734e-06, + "loss": 0.515, + "step": 23853 + }, + { + "epoch": 1.94, + "learning_rate": 7.041503694046068e-06, + "loss": 0.5223, + "step": 23854 + }, + { + "epoch": 1.94, + "learning_rate": 7.040960451977402e-06, + "loss": 0.3162, + "step": 23855 + }, + { + "epoch": 1.94, + "learning_rate": 7.040417209908736e-06, + "loss": 0.1559, + "step": 23856 + }, + { + "epoch": 1.94, + "learning_rate": 7.03987396784007e-06, + "loss": 0.3396, + "step": 23857 + }, + { + "epoch": 1.94, + "learning_rate": 7.039330725771404e-06, + "loss": 0.4404, + "step": 23858 + }, + { + "epoch": 1.94, + "learning_rate": 7.038787483702738e-06, + "loss": 0.2001, + "step": 23859 + }, + { + "epoch": 1.94, + "learning_rate": 7.0382442416340724e-06, + "loss": 0.1783, + "step": 23860 + }, + { + "epoch": 1.94, + "learning_rate": 7.037700999565407e-06, + "loss": 0.2664, + "step": 23861 + }, + { + "epoch": 1.94, + "learning_rate": 7.037157757496741e-06, + "loss": 0.5298, + "step": 23862 + }, + { + "epoch": 1.94, + "learning_rate": 7.036614515428075e-06, + "loss": 0.3507, + "step": 23863 + }, + { + "epoch": 1.94, + "learning_rate": 7.036071273359409e-06, + "loss": 0.2778, + "step": 23864 + }, + { + "epoch": 1.94, + "learning_rate": 7.035528031290744e-06, + "loss": 0.2787, + "step": 23865 + }, + { + "epoch": 1.94, + "learning_rate": 7.034984789222078e-06, + "loss": 0.3085, + "step": 23866 + }, + { + "epoch": 1.94, + "learning_rate": 7.034441547153412e-06, + "loss": 0.2876, + "step": 23867 + }, + { + "epoch": 1.94, + "learning_rate": 7.033898305084746e-06, + "loss": 0.3434, + "step": 23868 + }, + { + "epoch": 1.94, + "learning_rate": 7.0333550630160805e-06, + "loss": 0.3102, + "step": 23869 + }, + { + "epoch": 1.95, + "learning_rate": 7.032811820947415e-06, + "loss": 0.3237, + "step": 23870 + }, + { + "epoch": 1.95, + "learning_rate": 7.032268578878749e-06, + "loss": 0.2963, + "step": 23871 + }, + { + "epoch": 1.95, + "learning_rate": 7.031725336810083e-06, + "loss": 0.2966, + "step": 23872 + }, + { + "epoch": 1.95, + "learning_rate": 7.0311820947414174e-06, + "loss": 0.222, + "step": 23873 + }, + { + "epoch": 1.95, + "learning_rate": 7.030638852672752e-06, + "loss": 0.2656, + "step": 23874 + }, + { + "epoch": 1.95, + "learning_rate": 7.030095610604086e-06, + "loss": 0.3614, + "step": 23875 + }, + { + "epoch": 1.95, + "learning_rate": 7.029552368535419e-06, + "loss": 0.1432, + "step": 23876 + }, + { + "epoch": 1.95, + "learning_rate": 7.0290091264667535e-06, + "loss": 0.2397, + "step": 23877 + }, + { + "epoch": 1.95, + "learning_rate": 7.028465884398088e-06, + "loss": 0.326, + "step": 23878 + }, + { + "epoch": 1.95, + "learning_rate": 7.027922642329422e-06, + "loss": 0.3089, + "step": 23879 + }, + { + "epoch": 1.95, + "learning_rate": 7.027379400260756e-06, + "loss": 0.5041, + "step": 23880 + }, + { + "epoch": 1.95, + "learning_rate": 7.0268361581920904e-06, + "loss": 0.508, + "step": 23881 + }, + { + "epoch": 1.95, + "learning_rate": 7.026292916123425e-06, + "loss": 0.3197, + "step": 23882 + }, + { + "epoch": 1.95, + "learning_rate": 7.025749674054759e-06, + "loss": 0.2813, + "step": 23883 + }, + { + "epoch": 1.95, + "learning_rate": 7.025206431986093e-06, + "loss": 0.212, + "step": 23884 + }, + { + "epoch": 1.95, + "learning_rate": 7.024663189917428e-06, + "loss": 0.3011, + "step": 23885 + }, + { + "epoch": 1.95, + "learning_rate": 7.0241199478487624e-06, + "loss": 0.3356, + "step": 23886 + }, + { + "epoch": 1.95, + "learning_rate": 7.023576705780097e-06, + "loss": 0.4279, + "step": 23887 + }, + { + "epoch": 1.95, + "learning_rate": 7.023033463711431e-06, + "loss": 0.3592, + "step": 23888 + }, + { + "epoch": 1.95, + "learning_rate": 7.022490221642765e-06, + "loss": 0.0417, + "step": 23889 + }, + { + "epoch": 1.95, + "learning_rate": 7.021946979574099e-06, + "loss": 0.3957, + "step": 23890 + }, + { + "epoch": 1.95, + "learning_rate": 7.021403737505434e-06, + "loss": 0.4701, + "step": 23891 + }, + { + "epoch": 1.95, + "learning_rate": 7.020860495436768e-06, + "loss": 0.4836, + "step": 23892 + }, + { + "epoch": 1.95, + "learning_rate": 7.020317253368102e-06, + "loss": 0.3324, + "step": 23893 + }, + { + "epoch": 1.95, + "learning_rate": 7.019774011299436e-06, + "loss": 0.3427, + "step": 23894 + }, + { + "epoch": 1.95, + "learning_rate": 7.01923076923077e-06, + "loss": 0.4272, + "step": 23895 + }, + { + "epoch": 1.95, + "learning_rate": 7.018687527162104e-06, + "loss": 0.4387, + "step": 23896 + }, + { + "epoch": 1.95, + "learning_rate": 7.018144285093438e-06, + "loss": 0.2568, + "step": 23897 + }, + { + "epoch": 1.95, + "learning_rate": 7.017601043024772e-06, + "loss": 0.312, + "step": 23898 + }, + { + "epoch": 1.95, + "learning_rate": 7.017057800956107e-06, + "loss": 0.193, + "step": 23899 + }, + { + "epoch": 1.95, + "learning_rate": 7.016514558887441e-06, + "loss": 0.2314, + "step": 23900 + }, + { + "epoch": 1.95, + "learning_rate": 7.015971316818775e-06, + "loss": 0.1941, + "step": 23901 + }, + { + "epoch": 1.95, + "learning_rate": 7.015428074750109e-06, + "loss": 0.3629, + "step": 23902 + }, + { + "epoch": 1.95, + "learning_rate": 7.0148848326814435e-06, + "loss": 0.1803, + "step": 23903 + }, + { + "epoch": 1.95, + "learning_rate": 7.014341590612778e-06, + "loss": 0.4159, + "step": 23904 + }, + { + "epoch": 1.95, + "learning_rate": 7.013798348544112e-06, + "loss": 0.1887, + "step": 23905 + }, + { + "epoch": 1.95, + "learning_rate": 7.013255106475446e-06, + "loss": 0.5213, + "step": 23906 + }, + { + "epoch": 1.95, + "learning_rate": 7.0127118644067804e-06, + "loss": 0.4192, + "step": 23907 + }, + { + "epoch": 1.95, + "learning_rate": 7.012168622338115e-06, + "loss": 0.278, + "step": 23908 + }, + { + "epoch": 1.95, + "learning_rate": 7.011625380269449e-06, + "loss": 0.3056, + "step": 23909 + }, + { + "epoch": 1.95, + "learning_rate": 7.011082138200783e-06, + "loss": 0.2918, + "step": 23910 + }, + { + "epoch": 1.95, + "learning_rate": 7.010538896132117e-06, + "loss": 0.2929, + "step": 23911 + }, + { + "epoch": 1.95, + "learning_rate": 7.009995654063452e-06, + "loss": 0.2927, + "step": 23912 + }, + { + "epoch": 1.95, + "learning_rate": 7.009452411994786e-06, + "loss": 0.4384, + "step": 23913 + }, + { + "epoch": 1.95, + "learning_rate": 7.008909169926119e-06, + "loss": 0.1661, + "step": 23914 + }, + { + "epoch": 1.95, + "learning_rate": 7.008365927857453e-06, + "loss": 0.4229, + "step": 23915 + }, + { + "epoch": 1.95, + "learning_rate": 7.007822685788788e-06, + "loss": 0.1839, + "step": 23916 + }, + { + "epoch": 1.95, + "learning_rate": 7.007279443720122e-06, + "loss": 0.3888, + "step": 23917 + }, + { + "epoch": 1.95, + "learning_rate": 7.006736201651456e-06, + "loss": 0.269, + "step": 23918 + }, + { + "epoch": 1.95, + "learning_rate": 7.00619295958279e-06, + "loss": 0.6324, + "step": 23919 + }, + { + "epoch": 1.95, + "learning_rate": 7.0056497175141246e-06, + "loss": 0.6714, + "step": 23920 + }, + { + "epoch": 1.95, + "learning_rate": 7.005106475445459e-06, + "loss": 0.2445, + "step": 23921 + }, + { + "epoch": 1.95, + "learning_rate": 7.004563233376793e-06, + "loss": 0.3599, + "step": 23922 + }, + { + "epoch": 1.95, + "learning_rate": 7.004019991308127e-06, + "loss": 0.2116, + "step": 23923 + }, + { + "epoch": 1.95, + "learning_rate": 7.0034767492394615e-06, + "loss": 0.322, + "step": 23924 + }, + { + "epoch": 1.95, + "learning_rate": 7.002933507170796e-06, + "loss": 0.3337, + "step": 23925 + }, + { + "epoch": 1.95, + "learning_rate": 7.00239026510213e-06, + "loss": 0.1496, + "step": 23926 + }, + { + "epoch": 1.95, + "learning_rate": 7.001847023033464e-06, + "loss": 0.2167, + "step": 23927 + }, + { + "epoch": 1.95, + "learning_rate": 7.001303780964798e-06, + "loss": 0.224, + "step": 23928 + }, + { + "epoch": 1.95, + "learning_rate": 7.000760538896133e-06, + "loss": 0.2015, + "step": 23929 + }, + { + "epoch": 1.95, + "learning_rate": 7.000217296827468e-06, + "loss": 0.1474, + "step": 23930 + }, + { + "epoch": 1.95, + "learning_rate": 6.999674054758802e-06, + "loss": 0.0881, + "step": 23931 + }, + { + "epoch": 1.95, + "learning_rate": 6.999130812690136e-06, + "loss": 0.1764, + "step": 23932 + }, + { + "epoch": 1.95, + "learning_rate": 6.998587570621469e-06, + "loss": 0.3285, + "step": 23933 + }, + { + "epoch": 1.95, + "learning_rate": 6.998044328552803e-06, + "loss": 0.3562, + "step": 23934 + }, + { + "epoch": 1.95, + "learning_rate": 6.997501086484137e-06, + "loss": 0.3615, + "step": 23935 + }, + { + "epoch": 1.95, + "learning_rate": 6.996957844415471e-06, + "loss": 0.3355, + "step": 23936 + }, + { + "epoch": 1.95, + "learning_rate": 6.996414602346806e-06, + "loss": 0.1522, + "step": 23937 + }, + { + "epoch": 1.95, + "learning_rate": 6.99587136027814e-06, + "loss": 0.1844, + "step": 23938 + }, + { + "epoch": 1.95, + "learning_rate": 6.995328118209475e-06, + "loss": 0.1966, + "step": 23939 + }, + { + "epoch": 1.95, + "learning_rate": 6.994784876140809e-06, + "loss": 0.207, + "step": 23940 + }, + { + "epoch": 1.95, + "learning_rate": 6.994241634072143e-06, + "loss": 0.567, + "step": 23941 + }, + { + "epoch": 1.95, + "learning_rate": 6.993698392003478e-06, + "loss": 0.2467, + "step": 23942 + }, + { + "epoch": 1.95, + "learning_rate": 6.993155149934812e-06, + "loss": 0.4248, + "step": 23943 + }, + { + "epoch": 1.95, + "learning_rate": 6.992611907866146e-06, + "loss": 0.4497, + "step": 23944 + }, + { + "epoch": 1.95, + "learning_rate": 6.99206866579748e-06, + "loss": 0.2353, + "step": 23945 + }, + { + "epoch": 1.95, + "learning_rate": 6.9915254237288146e-06, + "loss": 0.4251, + "step": 23946 + }, + { + "epoch": 1.95, + "learning_rate": 6.990982181660149e-06, + "loss": 0.3154, + "step": 23947 + }, + { + "epoch": 1.95, + "learning_rate": 6.990438939591483e-06, + "loss": 0.3657, + "step": 23948 + }, + { + "epoch": 1.95, + "learning_rate": 6.989895697522817e-06, + "loss": 0.372, + "step": 23949 + }, + { + "epoch": 1.95, + "learning_rate": 6.9893524554541515e-06, + "loss": 0.3112, + "step": 23950 + }, + { + "epoch": 1.95, + "learning_rate": 6.988809213385486e-06, + "loss": 0.3801, + "step": 23951 + }, + { + "epoch": 1.95, + "learning_rate": 6.988265971316819e-06, + "loss": 0.5746, + "step": 23952 + }, + { + "epoch": 1.95, + "learning_rate": 6.987722729248153e-06, + "loss": 0.3104, + "step": 23953 + }, + { + "epoch": 1.95, + "learning_rate": 6.9871794871794876e-06, + "loss": 0.3567, + "step": 23954 + }, + { + "epoch": 1.95, + "learning_rate": 6.986636245110822e-06, + "loss": 0.3378, + "step": 23955 + }, + { + "epoch": 1.95, + "learning_rate": 6.986093003042156e-06, + "loss": 0.3366, + "step": 23956 + }, + { + "epoch": 1.95, + "learning_rate": 6.98554976097349e-06, + "loss": 0.2739, + "step": 23957 + }, + { + "epoch": 1.95, + "learning_rate": 6.9850065189048245e-06, + "loss": 0.2866, + "step": 23958 + }, + { + "epoch": 1.95, + "learning_rate": 6.984463276836159e-06, + "loss": 0.3385, + "step": 23959 + }, + { + "epoch": 1.95, + "learning_rate": 6.983920034767493e-06, + "loss": 0.2977, + "step": 23960 + }, + { + "epoch": 1.95, + "learning_rate": 6.983376792698827e-06, + "loss": 0.2123, + "step": 23961 + }, + { + "epoch": 1.95, + "learning_rate": 6.982833550630161e-06, + "loss": 0.3739, + "step": 23962 + }, + { + "epoch": 1.95, + "learning_rate": 6.982290308561496e-06, + "loss": 0.4308, + "step": 23963 + }, + { + "epoch": 1.95, + "learning_rate": 6.98174706649283e-06, + "loss": 0.1128, + "step": 23964 + }, + { + "epoch": 1.95, + "learning_rate": 6.981203824424164e-06, + "loss": 0.3193, + "step": 23965 + }, + { + "epoch": 1.95, + "learning_rate": 6.980660582355498e-06, + "loss": 0.2887, + "step": 23966 + }, + { + "epoch": 1.95, + "learning_rate": 6.9801173402868326e-06, + "loss": 0.3213, + "step": 23967 + }, + { + "epoch": 1.95, + "learning_rate": 6.979574098218167e-06, + "loss": 0.3241, + "step": 23968 + }, + { + "epoch": 1.95, + "learning_rate": 6.979030856149501e-06, + "loss": 0.1697, + "step": 23969 + }, + { + "epoch": 1.95, + "learning_rate": 6.978487614080835e-06, + "loss": 0.2639, + "step": 23970 + }, + { + "epoch": 1.95, + "learning_rate": 6.977944372012169e-06, + "loss": 0.4671, + "step": 23971 + }, + { + "epoch": 1.95, + "learning_rate": 6.977401129943503e-06, + "loss": 0.1599, + "step": 23972 + }, + { + "epoch": 1.95, + "learning_rate": 6.976857887874837e-06, + "loss": 0.1791, + "step": 23973 + }, + { + "epoch": 1.95, + "learning_rate": 6.976314645806171e-06, + "loss": 0.1812, + "step": 23974 + }, + { + "epoch": 1.95, + "learning_rate": 6.9757714037375056e-06, + "loss": 0.4291, + "step": 23975 + }, + { + "epoch": 1.95, + "learning_rate": 6.97522816166884e-06, + "loss": 0.2574, + "step": 23976 + }, + { + "epoch": 1.95, + "learning_rate": 6.974684919600174e-06, + "loss": 0.6505, + "step": 23977 + }, + { + "epoch": 1.95, + "learning_rate": 6.974141677531508e-06, + "loss": 0.2607, + "step": 23978 + }, + { + "epoch": 1.95, + "learning_rate": 6.9735984354628425e-06, + "loss": 0.3878, + "step": 23979 + }, + { + "epoch": 1.95, + "learning_rate": 6.973055193394177e-06, + "loss": 0.2366, + "step": 23980 + }, + { + "epoch": 1.95, + "learning_rate": 6.972511951325511e-06, + "loss": 0.1281, + "step": 23981 + }, + { + "epoch": 1.95, + "learning_rate": 6.971968709256845e-06, + "loss": 0.5705, + "step": 23982 + }, + { + "epoch": 1.95, + "learning_rate": 6.971425467188179e-06, + "loss": 0.7288, + "step": 23983 + }, + { + "epoch": 1.95, + "learning_rate": 6.9708822251195145e-06, + "loss": 0.2716, + "step": 23984 + }, + { + "epoch": 1.95, + "learning_rate": 6.970338983050849e-06, + "loss": 0.1967, + "step": 23985 + }, + { + "epoch": 1.95, + "learning_rate": 6.969795740982183e-06, + "loss": 0.6512, + "step": 23986 + }, + { + "epoch": 1.95, + "learning_rate": 6.969252498913517e-06, + "loss": 0.1032, + "step": 23987 + }, + { + "epoch": 1.95, + "learning_rate": 6.968709256844851e-06, + "loss": 0.262, + "step": 23988 + }, + { + "epoch": 1.95, + "learning_rate": 6.968166014776186e-06, + "loss": 0.3706, + "step": 23989 + }, + { + "epoch": 1.95, + "learning_rate": 6.967622772707518e-06, + "loss": 0.3489, + "step": 23990 + }, + { + "epoch": 1.95, + "learning_rate": 6.967079530638852e-06, + "loss": 0.5272, + "step": 23991 + }, + { + "epoch": 1.96, + "learning_rate": 6.966536288570187e-06, + "loss": 0.5103, + "step": 23992 + }, + { + "epoch": 1.96, + "learning_rate": 6.965993046501522e-06, + "loss": 0.3873, + "step": 23993 + }, + { + "epoch": 1.96, + "learning_rate": 6.965449804432856e-06, + "loss": 0.128, + "step": 23994 + }, + { + "epoch": 1.96, + "learning_rate": 6.96490656236419e-06, + "loss": 0.2772, + "step": 23995 + }, + { + "epoch": 1.96, + "learning_rate": 6.964363320295524e-06, + "loss": 0.3239, + "step": 23996 + }, + { + "epoch": 1.96, + "learning_rate": 6.963820078226859e-06, + "loss": 0.2649, + "step": 23997 + }, + { + "epoch": 1.96, + "learning_rate": 6.963276836158193e-06, + "loss": 0.3382, + "step": 23998 + }, + { + "epoch": 1.96, + "learning_rate": 6.962733594089527e-06, + "loss": 0.3684, + "step": 23999 + }, + { + "epoch": 1.96, + "learning_rate": 6.962190352020861e-06, + "loss": 0.3128, + "step": 24000 + }, + { + "epoch": 1.96, + "eval_accuracy": 0.8436067244014264, + "eval_loss": 0.43074366450309753, + "eval_runtime": 22.3063, + "eval_samples_per_second": 440.009, + "eval_steps_per_second": 3.452, + "step": 24000 + }, + { + "epoch": 1.96, + "learning_rate": 6.9616471099521956e-06, + "loss": 0.3845, + "step": 24001 + }, + { + "epoch": 1.96, + "learning_rate": 6.96110386788353e-06, + "loss": 0.1247, + "step": 24002 + }, + { + "epoch": 1.96, + "learning_rate": 6.960560625814864e-06, + "loss": 0.1654, + "step": 24003 + }, + { + "epoch": 1.96, + "learning_rate": 6.960017383746198e-06, + "loss": 0.3452, + "step": 24004 + }, + { + "epoch": 1.96, + "learning_rate": 6.9594741416775325e-06, + "loss": 0.2161, + "step": 24005 + }, + { + "epoch": 1.96, + "learning_rate": 6.958930899608867e-06, + "loss": 0.2181, + "step": 24006 + }, + { + "epoch": 1.96, + "learning_rate": 6.958387657540201e-06, + "loss": 0.1395, + "step": 24007 + }, + { + "epoch": 1.96, + "learning_rate": 6.957844415471535e-06, + "loss": 0.2553, + "step": 24008 + }, + { + "epoch": 1.96, + "learning_rate": 6.9573011734028686e-06, + "loss": 0.3679, + "step": 24009 + }, + { + "epoch": 1.96, + "learning_rate": 6.956757931334203e-06, + "loss": 0.6231, + "step": 24010 + }, + { + "epoch": 1.96, + "learning_rate": 6.956214689265537e-06, + "loss": 0.4562, + "step": 24011 + }, + { + "epoch": 1.96, + "learning_rate": 6.955671447196871e-06, + "loss": 0.5139, + "step": 24012 + }, + { + "epoch": 1.96, + "learning_rate": 6.9551282051282055e-06, + "loss": 0.5569, + "step": 24013 + }, + { + "epoch": 1.96, + "learning_rate": 6.95458496305954e-06, + "loss": 0.3086, + "step": 24014 + }, + { + "epoch": 1.96, + "learning_rate": 6.954041720990874e-06, + "loss": 0.3659, + "step": 24015 + }, + { + "epoch": 1.96, + "learning_rate": 6.953498478922208e-06, + "loss": 0.4647, + "step": 24016 + }, + { + "epoch": 1.96, + "learning_rate": 6.952955236853542e-06, + "loss": 0.4227, + "step": 24017 + }, + { + "epoch": 1.96, + "learning_rate": 6.952411994784877e-06, + "loss": 0.355, + "step": 24018 + }, + { + "epoch": 1.96, + "learning_rate": 6.951868752716211e-06, + "loss": 0.1307, + "step": 24019 + }, + { + "epoch": 1.96, + "learning_rate": 6.951325510647545e-06, + "loss": 0.6687, + "step": 24020 + }, + { + "epoch": 1.96, + "learning_rate": 6.950782268578879e-06, + "loss": 0.2375, + "step": 24021 + }, + { + "epoch": 1.96, + "learning_rate": 6.9502390265102135e-06, + "loss": 0.3192, + "step": 24022 + }, + { + "epoch": 1.96, + "learning_rate": 6.949695784441548e-06, + "loss": 0.2969, + "step": 24023 + }, + { + "epoch": 1.96, + "learning_rate": 6.949152542372882e-06, + "loss": 0.4032, + "step": 24024 + }, + { + "epoch": 1.96, + "learning_rate": 6.948609300304216e-06, + "loss": 0.4025, + "step": 24025 + }, + { + "epoch": 1.96, + "learning_rate": 6.9480660582355505e-06, + "loss": 0.291, + "step": 24026 + }, + { + "epoch": 1.96, + "learning_rate": 6.947522816166885e-06, + "loss": 0.3929, + "step": 24027 + }, + { + "epoch": 1.96, + "learning_rate": 6.946979574098218e-06, + "loss": 0.205, + "step": 24028 + }, + { + "epoch": 1.96, + "learning_rate": 6.946436332029552e-06, + "loss": 0.3644, + "step": 24029 + }, + { + "epoch": 1.96, + "learning_rate": 6.9458930899608865e-06, + "loss": 0.5602, + "step": 24030 + }, + { + "epoch": 1.96, + "learning_rate": 6.945349847892221e-06, + "loss": 0.1054, + "step": 24031 + }, + { + "epoch": 1.96, + "learning_rate": 6.944806605823555e-06, + "loss": 0.4994, + "step": 24032 + }, + { + "epoch": 1.96, + "learning_rate": 6.944263363754889e-06, + "loss": 0.2328, + "step": 24033 + }, + { + "epoch": 1.96, + "learning_rate": 6.9437201216862235e-06, + "loss": 0.3673, + "step": 24034 + }, + { + "epoch": 1.96, + "learning_rate": 6.943176879617558e-06, + "loss": 0.2046, + "step": 24035 + }, + { + "epoch": 1.96, + "learning_rate": 6.942633637548892e-06, + "loss": 0.2703, + "step": 24036 + }, + { + "epoch": 1.96, + "learning_rate": 6.942090395480226e-06, + "loss": 0.426, + "step": 24037 + }, + { + "epoch": 1.96, + "learning_rate": 6.941547153411561e-06, + "loss": 0.3336, + "step": 24038 + }, + { + "epoch": 1.96, + "learning_rate": 6.9410039113428955e-06, + "loss": 0.3701, + "step": 24039 + }, + { + "epoch": 1.96, + "learning_rate": 6.94046066927423e-06, + "loss": 0.1758, + "step": 24040 + }, + { + "epoch": 1.96, + "learning_rate": 6.939917427205564e-06, + "loss": 0.283, + "step": 24041 + }, + { + "epoch": 1.96, + "learning_rate": 6.939374185136898e-06, + "loss": 0.2682, + "step": 24042 + }, + { + "epoch": 1.96, + "learning_rate": 6.938830943068232e-06, + "loss": 0.1863, + "step": 24043 + }, + { + "epoch": 1.96, + "learning_rate": 6.938287700999567e-06, + "loss": 0.1887, + "step": 24044 + }, + { + "epoch": 1.96, + "learning_rate": 6.937744458930901e-06, + "loss": 0.13, + "step": 24045 + }, + { + "epoch": 1.96, + "learning_rate": 6.937201216862235e-06, + "loss": 0.2827, + "step": 24046 + }, + { + "epoch": 1.96, + "learning_rate": 6.9366579747935685e-06, + "loss": 0.3686, + "step": 24047 + }, + { + "epoch": 1.96, + "learning_rate": 6.936114732724903e-06, + "loss": 0.355, + "step": 24048 + }, + { + "epoch": 1.96, + "learning_rate": 6.935571490656237e-06, + "loss": 0.572, + "step": 24049 + }, + { + "epoch": 1.96, + "learning_rate": 6.935028248587571e-06, + "loss": 0.1891, + "step": 24050 + }, + { + "epoch": 1.96, + "learning_rate": 6.934485006518905e-06, + "loss": 0.2931, + "step": 24051 + }, + { + "epoch": 1.96, + "learning_rate": 6.93394176445024e-06, + "loss": 0.2408, + "step": 24052 + }, + { + "epoch": 1.96, + "learning_rate": 6.933398522381574e-06, + "loss": 0.2757, + "step": 24053 + }, + { + "epoch": 1.96, + "learning_rate": 6.932855280312908e-06, + "loss": 0.4531, + "step": 24054 + }, + { + "epoch": 1.96, + "learning_rate": 6.932312038244242e-06, + "loss": 0.3033, + "step": 24055 + }, + { + "epoch": 1.96, + "learning_rate": 6.9317687961755765e-06, + "loss": 0.1768, + "step": 24056 + }, + { + "epoch": 1.96, + "learning_rate": 6.931225554106911e-06, + "loss": 0.4438, + "step": 24057 + }, + { + "epoch": 1.96, + "learning_rate": 6.930682312038245e-06, + "loss": 0.3459, + "step": 24058 + }, + { + "epoch": 1.96, + "learning_rate": 6.930139069969579e-06, + "loss": 0.3096, + "step": 24059 + }, + { + "epoch": 1.96, + "learning_rate": 6.9295958279009135e-06, + "loss": 0.3191, + "step": 24060 + }, + { + "epoch": 1.96, + "learning_rate": 6.929052585832248e-06, + "loss": 0.3333, + "step": 24061 + }, + { + "epoch": 1.96, + "learning_rate": 6.928509343763582e-06, + "loss": 0.2944, + "step": 24062 + }, + { + "epoch": 1.96, + "learning_rate": 6.927966101694916e-06, + "loss": 0.252, + "step": 24063 + }, + { + "epoch": 1.96, + "learning_rate": 6.92742285962625e-06, + "loss": 0.3271, + "step": 24064 + }, + { + "epoch": 1.96, + "learning_rate": 6.926879617557585e-06, + "loss": 0.2739, + "step": 24065 + }, + { + "epoch": 1.96, + "learning_rate": 6.926336375488918e-06, + "loss": 0.1756, + "step": 24066 + }, + { + "epoch": 1.96, + "learning_rate": 6.925793133420252e-06, + "loss": 0.2427, + "step": 24067 + }, + { + "epoch": 1.96, + "learning_rate": 6.9252498913515865e-06, + "loss": 0.1782, + "step": 24068 + }, + { + "epoch": 1.96, + "learning_rate": 6.924706649282921e-06, + "loss": 0.3989, + "step": 24069 + }, + { + "epoch": 1.96, + "learning_rate": 6.924163407214255e-06, + "loss": 0.2124, + "step": 24070 + }, + { + "epoch": 1.96, + "learning_rate": 6.923620165145589e-06, + "loss": 0.1831, + "step": 24071 + }, + { + "epoch": 1.96, + "learning_rate": 6.923076923076923e-06, + "loss": 0.2136, + "step": 24072 + }, + { + "epoch": 1.96, + "learning_rate": 6.922533681008258e-06, + "loss": 0.2111, + "step": 24073 + }, + { + "epoch": 1.96, + "learning_rate": 6.921990438939592e-06, + "loss": 0.1875, + "step": 24074 + }, + { + "epoch": 1.96, + "learning_rate": 6.921447196870926e-06, + "loss": 0.1558, + "step": 24075 + }, + { + "epoch": 1.96, + "learning_rate": 6.92090395480226e-06, + "loss": 0.1348, + "step": 24076 + }, + { + "epoch": 1.96, + "learning_rate": 6.9203607127335945e-06, + "loss": 0.4357, + "step": 24077 + }, + { + "epoch": 1.96, + "learning_rate": 6.919817470664929e-06, + "loss": 0.2812, + "step": 24078 + }, + { + "epoch": 1.96, + "learning_rate": 6.919274228596263e-06, + "loss": 0.1418, + "step": 24079 + }, + { + "epoch": 1.96, + "learning_rate": 6.918730986527597e-06, + "loss": 0.0733, + "step": 24080 + }, + { + "epoch": 1.96, + "learning_rate": 6.9181877444589315e-06, + "loss": 0.2394, + "step": 24081 + }, + { + "epoch": 1.96, + "learning_rate": 6.917644502390266e-06, + "loss": 0.5528, + "step": 24082 + }, + { + "epoch": 1.96, + "learning_rate": 6.9171012603216e-06, + "loss": 0.2583, + "step": 24083 + }, + { + "epoch": 1.96, + "learning_rate": 6.916558018252935e-06, + "loss": 0.1324, + "step": 24084 + }, + { + "epoch": 1.96, + "learning_rate": 6.9160147761842675e-06, + "loss": 0.2213, + "step": 24085 + }, + { + "epoch": 1.96, + "learning_rate": 6.915471534115602e-06, + "loss": 0.7214, + "step": 24086 + }, + { + "epoch": 1.96, + "learning_rate": 6.914928292046936e-06, + "loss": 0.2508, + "step": 24087 + }, + { + "epoch": 1.96, + "learning_rate": 6.91438504997827e-06, + "loss": 0.2187, + "step": 24088 + }, + { + "epoch": 1.96, + "learning_rate": 6.9138418079096045e-06, + "loss": 0.2147, + "step": 24089 + }, + { + "epoch": 1.96, + "learning_rate": 6.913298565840939e-06, + "loss": 0.3928, + "step": 24090 + }, + { + "epoch": 1.96, + "learning_rate": 6.912755323772273e-06, + "loss": 0.2548, + "step": 24091 + }, + { + "epoch": 1.96, + "learning_rate": 6.912212081703608e-06, + "loss": 0.2075, + "step": 24092 + }, + { + "epoch": 1.96, + "learning_rate": 6.911668839634942e-06, + "loss": 0.4023, + "step": 24093 + }, + { + "epoch": 1.96, + "learning_rate": 6.9111255975662765e-06, + "loss": 0.2636, + "step": 24094 + }, + { + "epoch": 1.96, + "learning_rate": 6.910582355497611e-06, + "loss": 0.2758, + "step": 24095 + }, + { + "epoch": 1.96, + "learning_rate": 6.910039113428945e-06, + "loss": 0.5842, + "step": 24096 + }, + { + "epoch": 1.96, + "learning_rate": 6.909495871360279e-06, + "loss": 0.4498, + "step": 24097 + }, + { + "epoch": 1.96, + "learning_rate": 6.908952629291613e-06, + "loss": 0.2885, + "step": 24098 + }, + { + "epoch": 1.96, + "learning_rate": 6.908409387222948e-06, + "loss": 0.4364, + "step": 24099 + }, + { + "epoch": 1.96, + "learning_rate": 6.907866145154282e-06, + "loss": 0.2013, + "step": 24100 + }, + { + "epoch": 1.96, + "learning_rate": 6.907322903085616e-06, + "loss": 0.1649, + "step": 24101 + }, + { + "epoch": 1.96, + "learning_rate": 6.90677966101695e-06, + "loss": 0.4056, + "step": 24102 + }, + { + "epoch": 1.96, + "learning_rate": 6.9062364189482845e-06, + "loss": 0.4019, + "step": 24103 + }, + { + "epoch": 1.96, + "learning_rate": 6.905693176879618e-06, + "loss": 0.4634, + "step": 24104 + }, + { + "epoch": 1.96, + "learning_rate": 6.905149934810952e-06, + "loss": 0.4345, + "step": 24105 + }, + { + "epoch": 1.96, + "learning_rate": 6.904606692742286e-06, + "loss": 0.3815, + "step": 24106 + }, + { + "epoch": 1.96, + "learning_rate": 6.904063450673621e-06, + "loss": 0.2541, + "step": 24107 + }, + { + "epoch": 1.96, + "learning_rate": 6.903520208604955e-06, + "loss": 0.4755, + "step": 24108 + }, + { + "epoch": 1.96, + "learning_rate": 6.902976966536289e-06, + "loss": 0.2464, + "step": 24109 + }, + { + "epoch": 1.96, + "learning_rate": 6.902433724467623e-06, + "loss": 0.3593, + "step": 24110 + }, + { + "epoch": 1.96, + "learning_rate": 6.9018904823989575e-06, + "loss": 0.5591, + "step": 24111 + }, + { + "epoch": 1.96, + "learning_rate": 6.901347240330292e-06, + "loss": 0.4165, + "step": 24112 + }, + { + "epoch": 1.96, + "learning_rate": 6.900803998261626e-06, + "loss": 0.3957, + "step": 24113 + }, + { + "epoch": 1.96, + "learning_rate": 6.90026075619296e-06, + "loss": 0.3223, + "step": 24114 + }, + { + "epoch": 1.97, + "learning_rate": 6.8997175141242944e-06, + "loss": 0.3469, + "step": 24115 + }, + { + "epoch": 1.97, + "learning_rate": 6.899174272055629e-06, + "loss": 0.2182, + "step": 24116 + }, + { + "epoch": 1.97, + "learning_rate": 6.898631029986963e-06, + "loss": 0.3671, + "step": 24117 + }, + { + "epoch": 1.97, + "learning_rate": 6.898087787918297e-06, + "loss": 0.3015, + "step": 24118 + }, + { + "epoch": 1.97, + "learning_rate": 6.897544545849631e-06, + "loss": 0.0787, + "step": 24119 + }, + { + "epoch": 1.97, + "learning_rate": 6.897001303780966e-06, + "loss": 0.5201, + "step": 24120 + }, + { + "epoch": 1.97, + "learning_rate": 6.8964580617123e-06, + "loss": 0.2278, + "step": 24121 + }, + { + "epoch": 1.97, + "learning_rate": 6.895914819643634e-06, + "loss": 0.4196, + "step": 24122 + }, + { + "epoch": 1.97, + "learning_rate": 6.8953715775749674e-06, + "loss": 0.1673, + "step": 24123 + }, + { + "epoch": 1.97, + "learning_rate": 6.894828335506302e-06, + "loss": 0.4284, + "step": 24124 + }, + { + "epoch": 1.97, + "learning_rate": 6.894285093437636e-06, + "loss": 0.1568, + "step": 24125 + }, + { + "epoch": 1.97, + "learning_rate": 6.89374185136897e-06, + "loss": 0.2852, + "step": 24126 + }, + { + "epoch": 1.97, + "learning_rate": 6.893198609300304e-06, + "loss": 0.337, + "step": 24127 + }, + { + "epoch": 1.97, + "learning_rate": 6.892655367231639e-06, + "loss": 0.1873, + "step": 24128 + }, + { + "epoch": 1.97, + "learning_rate": 6.892112125162973e-06, + "loss": 0.3981, + "step": 24129 + }, + { + "epoch": 1.97, + "learning_rate": 6.891568883094307e-06, + "loss": 0.4805, + "step": 24130 + }, + { + "epoch": 1.97, + "learning_rate": 6.891025641025641e-06, + "loss": 0.389, + "step": 24131 + }, + { + "epoch": 1.97, + "learning_rate": 6.8904823989569755e-06, + "loss": 0.4159, + "step": 24132 + }, + { + "epoch": 1.97, + "learning_rate": 6.88993915688831e-06, + "loss": 0.2314, + "step": 24133 + }, + { + "epoch": 1.97, + "learning_rate": 6.889395914819644e-06, + "loss": 0.2747, + "step": 24134 + }, + { + "epoch": 1.97, + "learning_rate": 6.888852672750978e-06, + "loss": 0.298, + "step": 24135 + }, + { + "epoch": 1.97, + "learning_rate": 6.8883094306823124e-06, + "loss": 0.1343, + "step": 24136 + }, + { + "epoch": 1.97, + "learning_rate": 6.8877661886136475e-06, + "loss": 0.5885, + "step": 24137 + }, + { + "epoch": 1.97, + "learning_rate": 6.887222946544982e-06, + "loss": 0.5621, + "step": 24138 + }, + { + "epoch": 1.97, + "learning_rate": 6.886679704476316e-06, + "loss": 0.3625, + "step": 24139 + }, + { + "epoch": 1.97, + "learning_rate": 6.88613646240765e-06, + "loss": 0.1573, + "step": 24140 + }, + { + "epoch": 1.97, + "learning_rate": 6.8855932203389844e-06, + "loss": 0.2072, + "step": 24141 + }, + { + "epoch": 1.97, + "learning_rate": 6.885049978270317e-06, + "loss": 0.6952, + "step": 24142 + }, + { + "epoch": 1.97, + "learning_rate": 6.884506736201651e-06, + "loss": 0.5378, + "step": 24143 + }, + { + "epoch": 1.97, + "learning_rate": 6.8839634941329854e-06, + "loss": 0.1158, + "step": 24144 + }, + { + "epoch": 1.97, + "learning_rate": 6.88342025206432e-06, + "loss": 0.262, + "step": 24145 + }, + { + "epoch": 1.97, + "learning_rate": 6.882877009995655e-06, + "loss": 0.6917, + "step": 24146 + }, + { + "epoch": 1.97, + "learning_rate": 6.882333767926989e-06, + "loss": 0.3582, + "step": 24147 + }, + { + "epoch": 1.97, + "learning_rate": 6.881790525858323e-06, + "loss": 0.2182, + "step": 24148 + }, + { + "epoch": 1.97, + "learning_rate": 6.8812472837896574e-06, + "loss": 0.3789, + "step": 24149 + }, + { + "epoch": 1.97, + "learning_rate": 6.880704041720992e-06, + "loss": 0.5018, + "step": 24150 + }, + { + "epoch": 1.97, + "learning_rate": 6.880160799652326e-06, + "loss": 0.3173, + "step": 24151 + }, + { + "epoch": 1.97, + "learning_rate": 6.87961755758366e-06, + "loss": 0.1997, + "step": 24152 + }, + { + "epoch": 1.97, + "learning_rate": 6.879074315514994e-06, + "loss": 0.2221, + "step": 24153 + }, + { + "epoch": 1.97, + "learning_rate": 6.878531073446329e-06, + "loss": 0.2424, + "step": 24154 + }, + { + "epoch": 1.97, + "learning_rate": 6.877987831377663e-06, + "loss": 0.3384, + "step": 24155 + }, + { + "epoch": 1.97, + "learning_rate": 6.877444589308997e-06, + "loss": 0.2404, + "step": 24156 + }, + { + "epoch": 1.97, + "learning_rate": 6.876901347240331e-06, + "loss": 0.2987, + "step": 24157 + }, + { + "epoch": 1.97, + "learning_rate": 6.8763581051716655e-06, + "loss": 0.2697, + "step": 24158 + }, + { + "epoch": 1.97, + "learning_rate": 6.875814863103e-06, + "loss": 0.1622, + "step": 24159 + }, + { + "epoch": 1.97, + "learning_rate": 6.875271621034334e-06, + "loss": 0.5335, + "step": 24160 + }, + { + "epoch": 1.97, + "learning_rate": 6.874728378965667e-06, + "loss": 0.4079, + "step": 24161 + }, + { + "epoch": 1.97, + "learning_rate": 6.874185136897002e-06, + "loss": 0.5418, + "step": 24162 + }, + { + "epoch": 1.97, + "learning_rate": 6.873641894828336e-06, + "loss": 0.4297, + "step": 24163 + }, + { + "epoch": 1.97, + "learning_rate": 6.87309865275967e-06, + "loss": 0.2543, + "step": 24164 + }, + { + "epoch": 1.97, + "learning_rate": 6.872555410691004e-06, + "loss": 0.2124, + "step": 24165 + }, + { + "epoch": 1.97, + "learning_rate": 6.8720121686223385e-06, + "loss": 0.2635, + "step": 24166 + }, + { + "epoch": 1.97, + "learning_rate": 6.871468926553673e-06, + "loss": 0.2502, + "step": 24167 + }, + { + "epoch": 1.97, + "learning_rate": 6.870925684485007e-06, + "loss": 0.3928, + "step": 24168 + }, + { + "epoch": 1.97, + "learning_rate": 6.870382442416341e-06, + "loss": 0.3243, + "step": 24169 + }, + { + "epoch": 1.97, + "learning_rate": 6.8698392003476754e-06, + "loss": 0.3027, + "step": 24170 + }, + { + "epoch": 1.97, + "learning_rate": 6.86929595827901e-06, + "loss": 0.3003, + "step": 24171 + }, + { + "epoch": 1.97, + "learning_rate": 6.868752716210344e-06, + "loss": 0.1839, + "step": 24172 + }, + { + "epoch": 1.97, + "learning_rate": 6.868209474141678e-06, + "loss": 0.3146, + "step": 24173 + }, + { + "epoch": 1.97, + "learning_rate": 6.867666232073012e-06, + "loss": 0.329, + "step": 24174 + }, + { + "epoch": 1.97, + "learning_rate": 6.867122990004347e-06, + "loss": 0.22, + "step": 24175 + }, + { + "epoch": 1.97, + "learning_rate": 6.866579747935681e-06, + "loss": 0.4392, + "step": 24176 + }, + { + "epoch": 1.97, + "learning_rate": 6.866036505867015e-06, + "loss": 0.2873, + "step": 24177 + }, + { + "epoch": 1.97, + "learning_rate": 6.865493263798349e-06, + "loss": 0.2803, + "step": 24178 + }, + { + "epoch": 1.97, + "learning_rate": 6.8649500217296835e-06, + "loss": 0.2401, + "step": 24179 + }, + { + "epoch": 1.97, + "learning_rate": 6.864406779661017e-06, + "loss": 0.3419, + "step": 24180 + }, + { + "epoch": 1.97, + "learning_rate": 6.863863537592351e-06, + "loss": 0.2277, + "step": 24181 + }, + { + "epoch": 1.97, + "learning_rate": 6.863320295523685e-06, + "loss": 0.5836, + "step": 24182 + }, + { + "epoch": 1.97, + "learning_rate": 6.86277705345502e-06, + "loss": 0.2317, + "step": 24183 + }, + { + "epoch": 1.97, + "learning_rate": 6.862233811386354e-06, + "loss": 0.2797, + "step": 24184 + }, + { + "epoch": 1.97, + "learning_rate": 6.861690569317688e-06, + "loss": 0.069, + "step": 24185 + }, + { + "epoch": 1.97, + "learning_rate": 6.861147327249022e-06, + "loss": 0.7416, + "step": 24186 + }, + { + "epoch": 1.97, + "learning_rate": 6.8606040851803565e-06, + "loss": 0.257, + "step": 24187 + }, + { + "epoch": 1.97, + "learning_rate": 6.860060843111691e-06, + "loss": 0.1889, + "step": 24188 + }, + { + "epoch": 1.97, + "learning_rate": 6.859517601043025e-06, + "loss": 0.3167, + "step": 24189 + }, + { + "epoch": 1.97, + "learning_rate": 6.858974358974359e-06, + "loss": 0.3318, + "step": 24190 + }, + { + "epoch": 1.97, + "learning_rate": 6.858431116905694e-06, + "loss": 0.5663, + "step": 24191 + }, + { + "epoch": 1.97, + "learning_rate": 6.8578878748370285e-06, + "loss": 0.449, + "step": 24192 + }, + { + "epoch": 1.97, + "learning_rate": 6.857344632768363e-06, + "loss": 0.4302, + "step": 24193 + }, + { + "epoch": 1.97, + "learning_rate": 6.856801390699697e-06, + "loss": 0.7085, + "step": 24194 + }, + { + "epoch": 1.97, + "learning_rate": 6.856258148631031e-06, + "loss": 0.2893, + "step": 24195 + }, + { + "epoch": 1.97, + "learning_rate": 6.8557149065623654e-06, + "loss": 0.2732, + "step": 24196 + }, + { + "epoch": 1.97, + "learning_rate": 6.8551716644937e-06, + "loss": 0.2245, + "step": 24197 + }, + { + "epoch": 1.97, + "learning_rate": 6.854628422425034e-06, + "loss": 0.4883, + "step": 24198 + }, + { + "epoch": 1.97, + "learning_rate": 6.8540851803563664e-06, + "loss": 0.311, + "step": 24199 + }, + { + "epoch": 1.97, + "learning_rate": 6.8535419382877015e-06, + "loss": 0.3278, + "step": 24200 + }, + { + "epoch": 1.97, + "learning_rate": 6.852998696219036e-06, + "loss": 0.5308, + "step": 24201 + }, + { + "epoch": 1.97, + "learning_rate": 6.85245545415037e-06, + "loss": 0.3243, + "step": 24202 + }, + { + "epoch": 1.97, + "learning_rate": 6.851912212081704e-06, + "loss": 0.3498, + "step": 24203 + }, + { + "epoch": 1.97, + "learning_rate": 6.8513689700130384e-06, + "loss": 0.5108, + "step": 24204 + }, + { + "epoch": 1.97, + "learning_rate": 6.850825727944373e-06, + "loss": 0.3879, + "step": 24205 + }, + { + "epoch": 1.97, + "learning_rate": 6.850282485875707e-06, + "loss": 0.3179, + "step": 24206 + }, + { + "epoch": 1.97, + "learning_rate": 6.849739243807041e-06, + "loss": 0.7509, + "step": 24207 + }, + { + "epoch": 1.97, + "learning_rate": 6.849196001738375e-06, + "loss": 0.2951, + "step": 24208 + }, + { + "epoch": 1.97, + "learning_rate": 6.84865275966971e-06, + "loss": 0.2585, + "step": 24209 + }, + { + "epoch": 1.97, + "learning_rate": 6.848109517601044e-06, + "loss": 0.4013, + "step": 24210 + }, + { + "epoch": 1.97, + "learning_rate": 6.847566275532378e-06, + "loss": 0.354, + "step": 24211 + }, + { + "epoch": 1.97, + "learning_rate": 6.847023033463712e-06, + "loss": 0.2622, + "step": 24212 + }, + { + "epoch": 1.97, + "learning_rate": 6.8464797913950465e-06, + "loss": 0.4213, + "step": 24213 + }, + { + "epoch": 1.97, + "learning_rate": 6.845936549326381e-06, + "loss": 0.2392, + "step": 24214 + }, + { + "epoch": 1.97, + "learning_rate": 6.845393307257715e-06, + "loss": 0.3283, + "step": 24215 + }, + { + "epoch": 1.97, + "learning_rate": 6.844850065189049e-06, + "loss": 0.121, + "step": 24216 + }, + { + "epoch": 1.97, + "learning_rate": 6.8443068231203834e-06, + "loss": 0.3088, + "step": 24217 + }, + { + "epoch": 1.97, + "learning_rate": 6.843763581051717e-06, + "loss": 0.478, + "step": 24218 + }, + { + "epoch": 1.97, + "learning_rate": 6.843220338983051e-06, + "loss": 0.2884, + "step": 24219 + }, + { + "epoch": 1.97, + "learning_rate": 6.842677096914385e-06, + "loss": 0.2299, + "step": 24220 + }, + { + "epoch": 1.97, + "learning_rate": 6.8421338548457195e-06, + "loss": 0.3187, + "step": 24221 + }, + { + "epoch": 1.97, + "learning_rate": 6.841590612777054e-06, + "loss": 0.3598, + "step": 24222 + }, + { + "epoch": 1.97, + "learning_rate": 6.841047370708388e-06, + "loss": 0.155, + "step": 24223 + }, + { + "epoch": 1.97, + "learning_rate": 6.840504128639722e-06, + "loss": 0.4953, + "step": 24224 + }, + { + "epoch": 1.97, + "learning_rate": 6.839960886571056e-06, + "loss": 0.2832, + "step": 24225 + }, + { + "epoch": 1.97, + "learning_rate": 6.839417644502391e-06, + "loss": 0.6476, + "step": 24226 + }, + { + "epoch": 1.97, + "learning_rate": 6.838874402433725e-06, + "loss": 0.1639, + "step": 24227 + }, + { + "epoch": 1.97, + "learning_rate": 6.838331160365059e-06, + "loss": 0.3549, + "step": 24228 + }, + { + "epoch": 1.97, + "learning_rate": 6.837787918296393e-06, + "loss": 0.2537, + "step": 24229 + }, + { + "epoch": 1.97, + "learning_rate": 6.8372446762277276e-06, + "loss": 0.5791, + "step": 24230 + }, + { + "epoch": 1.97, + "learning_rate": 6.836701434159062e-06, + "loss": 0.3431, + "step": 24231 + }, + { + "epoch": 1.97, + "learning_rate": 6.836158192090396e-06, + "loss": 0.208, + "step": 24232 + }, + { + "epoch": 1.97, + "learning_rate": 6.83561495002173e-06, + "loss": 0.3832, + "step": 24233 + }, + { + "epoch": 1.97, + "learning_rate": 6.8350717079530645e-06, + "loss": 0.3234, + "step": 24234 + }, + { + "epoch": 1.97, + "learning_rate": 6.834528465884399e-06, + "loss": 0.5688, + "step": 24235 + }, + { + "epoch": 1.97, + "learning_rate": 6.833985223815733e-06, + "loss": 0.262, + "step": 24236 + }, + { + "epoch": 1.97, + "learning_rate": 6.833441981747066e-06, + "loss": 0.3591, + "step": 24237 + }, + { + "epoch": 1.98, + "learning_rate": 6.8328987396784006e-06, + "loss": 0.3797, + "step": 24238 + }, + { + "epoch": 1.98, + "learning_rate": 6.832355497609735e-06, + "loss": 0.2686, + "step": 24239 + }, + { + "epoch": 1.98, + "learning_rate": 6.831812255541069e-06, + "loss": 0.1814, + "step": 24240 + }, + { + "epoch": 1.98, + "learning_rate": 6.831269013472403e-06, + "loss": 0.3883, + "step": 24241 + }, + { + "epoch": 1.98, + "learning_rate": 6.8307257714037375e-06, + "loss": 0.2484, + "step": 24242 + }, + { + "epoch": 1.98, + "learning_rate": 6.830182529335072e-06, + "loss": 0.3303, + "step": 24243 + }, + { + "epoch": 1.98, + "learning_rate": 6.829639287266406e-06, + "loss": 0.2294, + "step": 24244 + }, + { + "epoch": 1.98, + "learning_rate": 6.829096045197741e-06, + "loss": 0.6069, + "step": 24245 + }, + { + "epoch": 1.98, + "learning_rate": 6.828552803129075e-06, + "loss": 0.4208, + "step": 24246 + }, + { + "epoch": 1.98, + "learning_rate": 6.8280095610604095e-06, + "loss": 0.3021, + "step": 24247 + }, + { + "epoch": 1.98, + "learning_rate": 6.827466318991744e-06, + "loss": 0.3008, + "step": 24248 + }, + { + "epoch": 1.98, + "learning_rate": 6.826923076923078e-06, + "loss": 0.2692, + "step": 24249 + }, + { + "epoch": 1.98, + "learning_rate": 6.826379834854412e-06, + "loss": 0.4323, + "step": 24250 + }, + { + "epoch": 1.98, + "eval_accuracy": 0.8451349974528782, + "eval_loss": 0.4240292012691498, + "eval_runtime": 22.2087, + "eval_samples_per_second": 441.944, + "eval_steps_per_second": 3.467, + "step": 24250 + }, + { + "epoch": 1.98, + "learning_rate": 6.825836592785746e-06, + "loss": 0.4934, + "step": 24251 + }, + { + "epoch": 1.98, + "learning_rate": 6.825293350717081e-06, + "loss": 0.5067, + "step": 24252 + }, + { + "epoch": 1.98, + "learning_rate": 6.824750108648415e-06, + "loss": 0.4949, + "step": 24253 + }, + { + "epoch": 1.98, + "learning_rate": 6.824206866579749e-06, + "loss": 0.2331, + "step": 24254 + }, + { + "epoch": 1.98, + "learning_rate": 6.823663624511083e-06, + "loss": 0.3728, + "step": 24255 + }, + { + "epoch": 1.98, + "learning_rate": 6.823120382442417e-06, + "loss": 0.411, + "step": 24256 + }, + { + "epoch": 1.98, + "learning_rate": 6.822577140373751e-06, + "loss": 0.2432, + "step": 24257 + }, + { + "epoch": 1.98, + "learning_rate": 6.822033898305085e-06, + "loss": 0.2166, + "step": 24258 + }, + { + "epoch": 1.98, + "learning_rate": 6.821490656236419e-06, + "loss": 0.1789, + "step": 24259 + }, + { + "epoch": 1.98, + "learning_rate": 6.820947414167754e-06, + "loss": 0.1744, + "step": 24260 + }, + { + "epoch": 1.98, + "learning_rate": 6.820404172099088e-06, + "loss": 0.5512, + "step": 24261 + }, + { + "epoch": 1.98, + "learning_rate": 6.819860930030422e-06, + "loss": 0.4336, + "step": 24262 + }, + { + "epoch": 1.98, + "learning_rate": 6.819317687961756e-06, + "loss": 0.299, + "step": 24263 + }, + { + "epoch": 1.98, + "learning_rate": 6.8187744458930906e-06, + "loss": 0.4634, + "step": 24264 + }, + { + "epoch": 1.98, + "learning_rate": 6.818231203824425e-06, + "loss": 0.397, + "step": 24265 + }, + { + "epoch": 1.98, + "learning_rate": 6.817687961755759e-06, + "loss": 0.2533, + "step": 24266 + }, + { + "epoch": 1.98, + "learning_rate": 6.817144719687093e-06, + "loss": 0.4044, + "step": 24267 + }, + { + "epoch": 1.98, + "learning_rate": 6.8166014776184275e-06, + "loss": 0.3719, + "step": 24268 + }, + { + "epoch": 1.98, + "learning_rate": 6.816058235549762e-06, + "loss": 0.1635, + "step": 24269 + }, + { + "epoch": 1.98, + "learning_rate": 6.815514993481096e-06, + "loss": 0.3151, + "step": 24270 + }, + { + "epoch": 1.98, + "learning_rate": 6.81497175141243e-06, + "loss": 0.3965, + "step": 24271 + }, + { + "epoch": 1.98, + "learning_rate": 6.814428509343764e-06, + "loss": 0.3083, + "step": 24272 + }, + { + "epoch": 1.98, + "learning_rate": 6.813885267275099e-06, + "loss": 0.3939, + "step": 24273 + }, + { + "epoch": 1.98, + "learning_rate": 6.813342025206433e-06, + "loss": 0.3752, + "step": 24274 + }, + { + "epoch": 1.98, + "learning_rate": 6.812798783137766e-06, + "loss": 0.2555, + "step": 24275 + }, + { + "epoch": 1.98, + "learning_rate": 6.8122555410691005e-06, + "loss": 0.4171, + "step": 24276 + }, + { + "epoch": 1.98, + "learning_rate": 6.811712299000435e-06, + "loss": 0.3712, + "step": 24277 + }, + { + "epoch": 1.98, + "learning_rate": 6.811169056931769e-06, + "loss": 0.3886, + "step": 24278 + }, + { + "epoch": 1.98, + "learning_rate": 6.810625814863103e-06, + "loss": 0.3956, + "step": 24279 + }, + { + "epoch": 1.98, + "learning_rate": 6.810082572794437e-06, + "loss": 0.3584, + "step": 24280 + }, + { + "epoch": 1.98, + "learning_rate": 6.809539330725772e-06, + "loss": 0.3528, + "step": 24281 + }, + { + "epoch": 1.98, + "learning_rate": 6.808996088657106e-06, + "loss": 0.2595, + "step": 24282 + }, + { + "epoch": 1.98, + "learning_rate": 6.80845284658844e-06, + "loss": 0.0979, + "step": 24283 + }, + { + "epoch": 1.98, + "learning_rate": 6.807909604519774e-06, + "loss": 0.2122, + "step": 24284 + }, + { + "epoch": 1.98, + "learning_rate": 6.8073663624511086e-06, + "loss": 0.3316, + "step": 24285 + }, + { + "epoch": 1.98, + "learning_rate": 6.806823120382443e-06, + "loss": 0.2462, + "step": 24286 + }, + { + "epoch": 1.98, + "learning_rate": 6.806279878313777e-06, + "loss": 0.4412, + "step": 24287 + }, + { + "epoch": 1.98, + "learning_rate": 6.805736636245111e-06, + "loss": 0.5291, + "step": 24288 + }, + { + "epoch": 1.98, + "learning_rate": 6.8051933941764455e-06, + "loss": 0.3034, + "step": 24289 + }, + { + "epoch": 1.98, + "learning_rate": 6.80465015210778e-06, + "loss": 0.3917, + "step": 24290 + }, + { + "epoch": 1.98, + "learning_rate": 6.804106910039115e-06, + "loss": 0.4001, + "step": 24291 + }, + { + "epoch": 1.98, + "learning_rate": 6.803563667970449e-06, + "loss": 0.2433, + "step": 24292 + }, + { + "epoch": 1.98, + "learning_rate": 6.803020425901783e-06, + "loss": 0.3132, + "step": 24293 + }, + { + "epoch": 1.98, + "learning_rate": 6.802477183833116e-06, + "loss": 0.3345, + "step": 24294 + }, + { + "epoch": 1.98, + "learning_rate": 6.80193394176445e-06, + "loss": 0.2167, + "step": 24295 + }, + { + "epoch": 1.98, + "learning_rate": 6.801390699695784e-06, + "loss": 0.349, + "step": 24296 + }, + { + "epoch": 1.98, + "learning_rate": 6.8008474576271185e-06, + "loss": 0.103, + "step": 24297 + }, + { + "epoch": 1.98, + "learning_rate": 6.800304215558453e-06, + "loss": 0.2497, + "step": 24298 + }, + { + "epoch": 1.98, + "learning_rate": 6.799760973489788e-06, + "loss": 0.4249, + "step": 24299 + }, + { + "epoch": 1.98, + "learning_rate": 6.799217731421122e-06, + "loss": 0.4379, + "step": 24300 + }, + { + "epoch": 1.98, + "learning_rate": 6.798674489352456e-06, + "loss": 0.1745, + "step": 24301 + }, + { + "epoch": 1.98, + "learning_rate": 6.7981312472837905e-06, + "loss": 0.3705, + "step": 24302 + }, + { + "epoch": 1.98, + "learning_rate": 6.797588005215125e-06, + "loss": 0.3032, + "step": 24303 + }, + { + "epoch": 1.98, + "learning_rate": 6.797044763146459e-06, + "loss": 0.3158, + "step": 24304 + }, + { + "epoch": 1.98, + "learning_rate": 6.796501521077793e-06, + "loss": 0.1164, + "step": 24305 + }, + { + "epoch": 1.98, + "learning_rate": 6.795958279009127e-06, + "loss": 0.4739, + "step": 24306 + }, + { + "epoch": 1.98, + "learning_rate": 6.795415036940462e-06, + "loss": 0.424, + "step": 24307 + }, + { + "epoch": 1.98, + "learning_rate": 6.794871794871796e-06, + "loss": 0.2743, + "step": 24308 + }, + { + "epoch": 1.98, + "learning_rate": 6.79432855280313e-06, + "loss": 0.2027, + "step": 24309 + }, + { + "epoch": 1.98, + "learning_rate": 6.793785310734464e-06, + "loss": 0.183, + "step": 24310 + }, + { + "epoch": 1.98, + "learning_rate": 6.7932420686657986e-06, + "loss": 0.3794, + "step": 24311 + }, + { + "epoch": 1.98, + "learning_rate": 6.792698826597133e-06, + "loss": 0.1927, + "step": 24312 + }, + { + "epoch": 1.98, + "learning_rate": 6.792155584528466e-06, + "loss": 0.2812, + "step": 24313 + }, + { + "epoch": 1.98, + "learning_rate": 6.7916123424598e-06, + "loss": 0.4529, + "step": 24314 + }, + { + "epoch": 1.98, + "learning_rate": 6.791069100391135e-06, + "loss": 0.432, + "step": 24315 + }, + { + "epoch": 1.98, + "learning_rate": 6.790525858322469e-06, + "loss": 0.2476, + "step": 24316 + }, + { + "epoch": 1.98, + "learning_rate": 6.789982616253803e-06, + "loss": 0.3444, + "step": 24317 + }, + { + "epoch": 1.98, + "learning_rate": 6.789439374185137e-06, + "loss": 0.367, + "step": 24318 + }, + { + "epoch": 1.98, + "learning_rate": 6.7888961321164716e-06, + "loss": 0.3165, + "step": 24319 + }, + { + "epoch": 1.98, + "learning_rate": 6.788352890047806e-06, + "loss": 0.4319, + "step": 24320 + }, + { + "epoch": 1.98, + "learning_rate": 6.78780964797914e-06, + "loss": 0.2577, + "step": 24321 + }, + { + "epoch": 1.98, + "learning_rate": 6.787266405910474e-06, + "loss": 0.2499, + "step": 24322 + }, + { + "epoch": 1.98, + "learning_rate": 6.7867231638418085e-06, + "loss": 0.2105, + "step": 24323 + }, + { + "epoch": 1.98, + "learning_rate": 6.786179921773143e-06, + "loss": 0.5703, + "step": 24324 + }, + { + "epoch": 1.98, + "learning_rate": 6.785636679704477e-06, + "loss": 0.2435, + "step": 24325 + }, + { + "epoch": 1.98, + "learning_rate": 6.785093437635811e-06, + "loss": 0.3018, + "step": 24326 + }, + { + "epoch": 1.98, + "learning_rate": 6.784550195567145e-06, + "loss": 0.5133, + "step": 24327 + }, + { + "epoch": 1.98, + "learning_rate": 6.78400695349848e-06, + "loss": 0.2802, + "step": 24328 + }, + { + "epoch": 1.98, + "learning_rate": 6.783463711429814e-06, + "loss": 0.651, + "step": 24329 + }, + { + "epoch": 1.98, + "learning_rate": 6.782920469361148e-06, + "loss": 0.2912, + "step": 24330 + }, + { + "epoch": 1.98, + "learning_rate": 6.782377227292482e-06, + "loss": 0.3735, + "step": 24331 + }, + { + "epoch": 1.98, + "learning_rate": 6.781833985223816e-06, + "loss": 0.3101, + "step": 24332 + }, + { + "epoch": 1.98, + "learning_rate": 6.78129074315515e-06, + "loss": 0.3306, + "step": 24333 + }, + { + "epoch": 1.98, + "learning_rate": 6.780747501086484e-06, + "loss": 0.3927, + "step": 24334 + }, + { + "epoch": 1.98, + "learning_rate": 6.780204259017818e-06, + "loss": 0.2762, + "step": 24335 + }, + { + "epoch": 1.98, + "learning_rate": 6.779661016949153e-06, + "loss": 0.3206, + "step": 24336 + }, + { + "epoch": 1.98, + "learning_rate": 6.779117774880487e-06, + "loss": 0.3258, + "step": 24337 + }, + { + "epoch": 1.98, + "learning_rate": 6.778574532811821e-06, + "loss": 0.2994, + "step": 24338 + }, + { + "epoch": 1.98, + "learning_rate": 6.778031290743155e-06, + "loss": 0.1997, + "step": 24339 + }, + { + "epoch": 1.98, + "learning_rate": 6.7774880486744895e-06, + "loss": 0.485, + "step": 24340 + }, + { + "epoch": 1.98, + "learning_rate": 6.776944806605824e-06, + "loss": 0.23, + "step": 24341 + }, + { + "epoch": 1.98, + "learning_rate": 6.776401564537158e-06, + "loss": 0.2526, + "step": 24342 + }, + { + "epoch": 1.98, + "learning_rate": 6.775858322468492e-06, + "loss": 0.4894, + "step": 24343 + }, + { + "epoch": 1.98, + "learning_rate": 6.7753150803998265e-06, + "loss": 0.2702, + "step": 24344 + }, + { + "epoch": 1.98, + "learning_rate": 6.7747718383311615e-06, + "loss": 0.2693, + "step": 24345 + }, + { + "epoch": 1.98, + "learning_rate": 6.774228596262496e-06, + "loss": 0.4762, + "step": 24346 + }, + { + "epoch": 1.98, + "learning_rate": 6.77368535419383e-06, + "loss": 0.224, + "step": 24347 + }, + { + "epoch": 1.98, + "learning_rate": 6.773142112125164e-06, + "loss": 0.6279, + "step": 24348 + }, + { + "epoch": 1.98, + "learning_rate": 6.7725988700564985e-06, + "loss": 0.4457, + "step": 24349 + }, + { + "epoch": 1.98, + "learning_rate": 6.772055627987833e-06, + "loss": 0.2414, + "step": 24350 + }, + { + "epoch": 1.98, + "learning_rate": 6.771512385919165e-06, + "loss": 0.4866, + "step": 24351 + }, + { + "epoch": 1.98, + "learning_rate": 6.7709691438504995e-06, + "loss": 0.1916, + "step": 24352 + }, + { + "epoch": 1.98, + "learning_rate": 6.7704259017818345e-06, + "loss": 0.2616, + "step": 24353 + }, + { + "epoch": 1.98, + "learning_rate": 6.769882659713169e-06, + "loss": 0.2561, + "step": 24354 + }, + { + "epoch": 1.98, + "learning_rate": 6.769339417644503e-06, + "loss": 0.3125, + "step": 24355 + }, + { + "epoch": 1.98, + "learning_rate": 6.768796175575837e-06, + "loss": 0.4138, + "step": 24356 + }, + { + "epoch": 1.98, + "learning_rate": 6.7682529335071715e-06, + "loss": 0.2491, + "step": 24357 + }, + { + "epoch": 1.98, + "learning_rate": 6.767709691438506e-06, + "loss": 0.1471, + "step": 24358 + }, + { + "epoch": 1.98, + "learning_rate": 6.76716644936984e-06, + "loss": 0.3797, + "step": 24359 + }, + { + "epoch": 1.99, + "learning_rate": 6.766623207301174e-06, + "loss": 0.2535, + "step": 24360 + }, + { + "epoch": 1.99, + "learning_rate": 6.766079965232508e-06, + "loss": 0.5524, + "step": 24361 + }, + { + "epoch": 1.99, + "learning_rate": 6.765536723163843e-06, + "loss": 0.6165, + "step": 24362 + }, + { + "epoch": 1.99, + "learning_rate": 6.764993481095177e-06, + "loss": 0.5653, + "step": 24363 + }, + { + "epoch": 1.99, + "learning_rate": 6.764450239026511e-06, + "loss": 0.3978, + "step": 24364 + }, + { + "epoch": 1.99, + "learning_rate": 6.763906996957845e-06, + "loss": 0.1632, + "step": 24365 + }, + { + "epoch": 1.99, + "learning_rate": 6.7633637548891795e-06, + "loss": 0.3723, + "step": 24366 + }, + { + "epoch": 1.99, + "learning_rate": 6.762820512820514e-06, + "loss": 0.4196, + "step": 24367 + }, + { + "epoch": 1.99, + "learning_rate": 6.762277270751848e-06, + "loss": 0.2978, + "step": 24368 + }, + { + "epoch": 1.99, + "learning_rate": 6.761734028683182e-06, + "loss": 0.5006, + "step": 24369 + }, + { + "epoch": 1.99, + "learning_rate": 6.761190786614516e-06, + "loss": 0.1289, + "step": 24370 + }, + { + "epoch": 1.99, + "learning_rate": 6.76064754454585e-06, + "loss": 0.5593, + "step": 24371 + }, + { + "epoch": 1.99, + "learning_rate": 6.760104302477184e-06, + "loss": 0.2325, + "step": 24372 + }, + { + "epoch": 1.99, + "learning_rate": 6.759561060408518e-06, + "loss": 0.3948, + "step": 24373 + }, + { + "epoch": 1.99, + "learning_rate": 6.7590178183398525e-06, + "loss": 0.3278, + "step": 24374 + }, + { + "epoch": 1.99, + "learning_rate": 6.758474576271187e-06, + "loss": 0.3285, + "step": 24375 + }, + { + "epoch": 1.99, + "learning_rate": 6.757931334202521e-06, + "loss": 0.3656, + "step": 24376 + }, + { + "epoch": 1.99, + "learning_rate": 6.757388092133855e-06, + "loss": 0.2241, + "step": 24377 + }, + { + "epoch": 1.99, + "learning_rate": 6.7568448500651895e-06, + "loss": 0.4241, + "step": 24378 + }, + { + "epoch": 1.99, + "learning_rate": 6.756301607996524e-06, + "loss": 0.3202, + "step": 24379 + }, + { + "epoch": 1.99, + "learning_rate": 6.755758365927858e-06, + "loss": 0.1227, + "step": 24380 + }, + { + "epoch": 1.99, + "learning_rate": 6.755215123859192e-06, + "loss": 0.4907, + "step": 24381 + }, + { + "epoch": 1.99, + "learning_rate": 6.754671881790526e-06, + "loss": 0.3297, + "step": 24382 + }, + { + "epoch": 1.99, + "learning_rate": 6.754128639721861e-06, + "loss": 0.5168, + "step": 24383 + }, + { + "epoch": 1.99, + "learning_rate": 6.753585397653195e-06, + "loss": 0.3473, + "step": 24384 + }, + { + "epoch": 1.99, + "learning_rate": 6.753042155584529e-06, + "loss": 0.2776, + "step": 24385 + }, + { + "epoch": 1.99, + "learning_rate": 6.752498913515863e-06, + "loss": 0.2855, + "step": 24386 + }, + { + "epoch": 1.99, + "learning_rate": 6.7519556714471975e-06, + "loss": 0.2662, + "step": 24387 + }, + { + "epoch": 1.99, + "learning_rate": 6.751412429378532e-06, + "loss": 0.2138, + "step": 24388 + }, + { + "epoch": 1.99, + "learning_rate": 6.750869187309865e-06, + "loss": 0.1708, + "step": 24389 + }, + { + "epoch": 1.99, + "learning_rate": 6.750325945241199e-06, + "loss": 0.5274, + "step": 24390 + }, + { + "epoch": 1.99, + "learning_rate": 6.749782703172534e-06, + "loss": 0.3054, + "step": 24391 + }, + { + "epoch": 1.99, + "learning_rate": 6.749239461103868e-06, + "loss": 0.2389, + "step": 24392 + }, + { + "epoch": 1.99, + "learning_rate": 6.748696219035202e-06, + "loss": 0.4269, + "step": 24393 + }, + { + "epoch": 1.99, + "learning_rate": 6.748152976966536e-06, + "loss": 0.3607, + "step": 24394 + }, + { + "epoch": 1.99, + "learning_rate": 6.7476097348978705e-06, + "loss": 0.3772, + "step": 24395 + }, + { + "epoch": 1.99, + "learning_rate": 6.747066492829205e-06, + "loss": 0.2862, + "step": 24396 + }, + { + "epoch": 1.99, + "learning_rate": 6.746523250760539e-06, + "loss": 0.7645, + "step": 24397 + }, + { + "epoch": 1.99, + "learning_rate": 6.745980008691873e-06, + "loss": 0.4463, + "step": 24398 + }, + { + "epoch": 1.99, + "learning_rate": 6.745436766623208e-06, + "loss": 0.4087, + "step": 24399 + }, + { + "epoch": 1.99, + "learning_rate": 6.7448935245545425e-06, + "loss": 0.1857, + "step": 24400 + }, + { + "epoch": 1.99, + "learning_rate": 6.744350282485877e-06, + "loss": 0.2486, + "step": 24401 + }, + { + "epoch": 1.99, + "learning_rate": 6.743807040417211e-06, + "loss": 0.2987, + "step": 24402 + }, + { + "epoch": 1.99, + "learning_rate": 6.743263798348545e-06, + "loss": 0.4176, + "step": 24403 + }, + { + "epoch": 1.99, + "learning_rate": 6.7427205562798795e-06, + "loss": 0.2763, + "step": 24404 + }, + { + "epoch": 1.99, + "learning_rate": 6.742177314211214e-06, + "loss": 0.4839, + "step": 24405 + }, + { + "epoch": 1.99, + "learning_rate": 6.741634072142548e-06, + "loss": 0.7228, + "step": 24406 + }, + { + "epoch": 1.99, + "learning_rate": 6.741090830073882e-06, + "loss": 0.4656, + "step": 24407 + }, + { + "epoch": 1.99, + "learning_rate": 6.7405475880052155e-06, + "loss": 0.1895, + "step": 24408 + }, + { + "epoch": 1.99, + "learning_rate": 6.74000434593655e-06, + "loss": 0.3866, + "step": 24409 + }, + { + "epoch": 1.99, + "learning_rate": 6.739461103867884e-06, + "loss": 0.4151, + "step": 24410 + }, + { + "epoch": 1.99, + "learning_rate": 6.738917861799218e-06, + "loss": 0.3252, + "step": 24411 + }, + { + "epoch": 1.99, + "learning_rate": 6.7383746197305525e-06, + "loss": 0.2314, + "step": 24412 + }, + { + "epoch": 1.99, + "learning_rate": 6.737831377661887e-06, + "loss": 0.3209, + "step": 24413 + }, + { + "epoch": 1.99, + "learning_rate": 6.737288135593221e-06, + "loss": 0.2651, + "step": 24414 + }, + { + "epoch": 1.99, + "learning_rate": 6.736744893524555e-06, + "loss": 0.1971, + "step": 24415 + }, + { + "epoch": 1.99, + "learning_rate": 6.736201651455889e-06, + "loss": 0.2029, + "step": 24416 + }, + { + "epoch": 1.99, + "learning_rate": 6.735658409387224e-06, + "loss": 0.4001, + "step": 24417 + }, + { + "epoch": 1.99, + "learning_rate": 6.735115167318558e-06, + "loss": 0.2623, + "step": 24418 + }, + { + "epoch": 1.99, + "learning_rate": 6.734571925249892e-06, + "loss": 0.3281, + "step": 24419 + }, + { + "epoch": 1.99, + "learning_rate": 6.734028683181226e-06, + "loss": 0.3526, + "step": 24420 + }, + { + "epoch": 1.99, + "learning_rate": 6.7334854411125605e-06, + "loss": 0.397, + "step": 24421 + }, + { + "epoch": 1.99, + "learning_rate": 6.732942199043895e-06, + "loss": 0.2883, + "step": 24422 + }, + { + "epoch": 1.99, + "learning_rate": 6.732398956975229e-06, + "loss": 0.2525, + "step": 24423 + }, + { + "epoch": 1.99, + "learning_rate": 6.731855714906563e-06, + "loss": 0.3464, + "step": 24424 + }, + { + "epoch": 1.99, + "learning_rate": 6.7313124728378974e-06, + "loss": 0.1855, + "step": 24425 + }, + { + "epoch": 1.99, + "learning_rate": 6.730769230769232e-06, + "loss": 0.4105, + "step": 24426 + }, + { + "epoch": 1.99, + "learning_rate": 6.730225988700565e-06, + "loss": 0.4712, + "step": 24427 + }, + { + "epoch": 1.99, + "learning_rate": 6.729682746631899e-06, + "loss": 0.551, + "step": 24428 + }, + { + "epoch": 1.99, + "learning_rate": 6.7291395045632335e-06, + "loss": 0.1974, + "step": 24429 + }, + { + "epoch": 1.99, + "learning_rate": 6.728596262494568e-06, + "loss": 0.3612, + "step": 24430 + }, + { + "epoch": 1.99, + "learning_rate": 6.728053020425902e-06, + "loss": 0.2456, + "step": 24431 + }, + { + "epoch": 1.99, + "learning_rate": 6.727509778357236e-06, + "loss": 0.4279, + "step": 24432 + }, + { + "epoch": 1.99, + "learning_rate": 6.7269665362885704e-06, + "loss": 0.4493, + "step": 24433 + }, + { + "epoch": 1.99, + "learning_rate": 6.726423294219905e-06, + "loss": 0.2584, + "step": 24434 + }, + { + "epoch": 1.99, + "learning_rate": 6.725880052151239e-06, + "loss": 0.197, + "step": 24435 + }, + { + "epoch": 1.99, + "learning_rate": 6.725336810082573e-06, + "loss": 0.5767, + "step": 24436 + }, + { + "epoch": 1.99, + "learning_rate": 6.724793568013907e-06, + "loss": 0.3768, + "step": 24437 + }, + { + "epoch": 1.99, + "learning_rate": 6.724250325945242e-06, + "loss": 0.3306, + "step": 24438 + }, + { + "epoch": 1.99, + "learning_rate": 6.723707083876576e-06, + "loss": 0.3997, + "step": 24439 + }, + { + "epoch": 1.99, + "learning_rate": 6.72316384180791e-06, + "loss": 0.2965, + "step": 24440 + }, + { + "epoch": 1.99, + "learning_rate": 6.722620599739244e-06, + "loss": 0.2181, + "step": 24441 + }, + { + "epoch": 1.99, + "learning_rate": 6.7220773576705785e-06, + "loss": 0.2368, + "step": 24442 + }, + { + "epoch": 1.99, + "learning_rate": 6.721534115601913e-06, + "loss": 0.1932, + "step": 24443 + }, + { + "epoch": 1.99, + "learning_rate": 6.720990873533248e-06, + "loss": 0.4827, + "step": 24444 + }, + { + "epoch": 1.99, + "learning_rate": 6.720447631464582e-06, + "loss": 0.4921, + "step": 24445 + }, + { + "epoch": 1.99, + "learning_rate": 6.719904389395915e-06, + "loss": 0.5628, + "step": 24446 + }, + { + "epoch": 1.99, + "learning_rate": 6.719361147327249e-06, + "loss": 0.1839, + "step": 24447 + }, + { + "epoch": 1.99, + "learning_rate": 6.718817905258583e-06, + "loss": 0.2546, + "step": 24448 + }, + { + "epoch": 1.99, + "learning_rate": 6.718274663189917e-06, + "loss": 0.1394, + "step": 24449 + }, + { + "epoch": 1.99, + "learning_rate": 6.7177314211212515e-06, + "loss": 0.2568, + "step": 24450 + }, + { + "epoch": 1.99, + "learning_rate": 6.717188179052586e-06, + "loss": 0.3283, + "step": 24451 + }, + { + "epoch": 1.99, + "learning_rate": 6.71664493698392e-06, + "loss": 0.4715, + "step": 24452 + }, + { + "epoch": 1.99, + "learning_rate": 6.716101694915255e-06, + "loss": 0.2451, + "step": 24453 + }, + { + "epoch": 1.99, + "learning_rate": 6.715558452846589e-06, + "loss": 0.4174, + "step": 24454 + }, + { + "epoch": 1.99, + "learning_rate": 6.7150152107779235e-06, + "loss": 0.5241, + "step": 24455 + }, + { + "epoch": 1.99, + "learning_rate": 6.714471968709258e-06, + "loss": 0.3073, + "step": 24456 + }, + { + "epoch": 1.99, + "learning_rate": 6.713928726640592e-06, + "loss": 0.2, + "step": 24457 + }, + { + "epoch": 1.99, + "learning_rate": 6.713385484571926e-06, + "loss": 0.3391, + "step": 24458 + }, + { + "epoch": 1.99, + "learning_rate": 6.7128422425032604e-06, + "loss": 0.1977, + "step": 24459 + }, + { + "epoch": 1.99, + "learning_rate": 6.712299000434595e-06, + "loss": 0.2281, + "step": 24460 + }, + { + "epoch": 1.99, + "learning_rate": 6.711755758365929e-06, + "loss": 0.4107, + "step": 24461 + }, + { + "epoch": 1.99, + "learning_rate": 6.711212516297263e-06, + "loss": 0.1042, + "step": 24462 + }, + { + "epoch": 1.99, + "learning_rate": 6.710669274228597e-06, + "loss": 0.133, + "step": 24463 + }, + { + "epoch": 1.99, + "learning_rate": 6.710126032159932e-06, + "loss": 0.2501, + "step": 24464 + }, + { + "epoch": 1.99, + "learning_rate": 6.709582790091265e-06, + "loss": 0.3377, + "step": 24465 + }, + { + "epoch": 1.99, + "learning_rate": 6.709039548022599e-06, + "loss": 0.3059, + "step": 24466 + }, + { + "epoch": 1.99, + "learning_rate": 6.7084963059539334e-06, + "loss": 0.3695, + "step": 24467 + }, + { + "epoch": 1.99, + "learning_rate": 6.707953063885268e-06, + "loss": 0.291, + "step": 24468 + }, + { + "epoch": 1.99, + "learning_rate": 6.707409821816602e-06, + "loss": 0.2058, + "step": 24469 + }, + { + "epoch": 1.99, + "learning_rate": 6.706866579747936e-06, + "loss": 0.5286, + "step": 24470 + }, + { + "epoch": 1.99, + "learning_rate": 6.70632333767927e-06, + "loss": 0.2566, + "step": 24471 + }, + { + "epoch": 1.99, + "learning_rate": 6.705780095610605e-06, + "loss": 0.4713, + "step": 24472 + }, + { + "epoch": 1.99, + "learning_rate": 6.705236853541939e-06, + "loss": 0.3859, + "step": 24473 + }, + { + "epoch": 1.99, + "learning_rate": 6.704693611473273e-06, + "loss": 0.4142, + "step": 24474 + }, + { + "epoch": 1.99, + "learning_rate": 6.704150369404607e-06, + "loss": 0.5358, + "step": 24475 + }, + { + "epoch": 1.99, + "learning_rate": 6.7036071273359415e-06, + "loss": 0.1657, + "step": 24476 + }, + { + "epoch": 1.99, + "learning_rate": 6.703063885267276e-06, + "loss": 0.2238, + "step": 24477 + }, + { + "epoch": 1.99, + "learning_rate": 6.70252064319861e-06, + "loss": 0.5519, + "step": 24478 + }, + { + "epoch": 1.99, + "learning_rate": 6.701977401129944e-06, + "loss": 0.3472, + "step": 24479 + }, + { + "epoch": 1.99, + "learning_rate": 6.7014341590612784e-06, + "loss": 0.3331, + "step": 24480 + }, + { + "epoch": 1.99, + "learning_rate": 6.700890916992613e-06, + "loss": 0.3468, + "step": 24481 + }, + { + "epoch": 1.99, + "learning_rate": 6.700347674923947e-06, + "loss": 0.2682, + "step": 24482 + }, + { + "epoch": 2.0, + "learning_rate": 6.699804432855281e-06, + "loss": 0.2656, + "step": 24483 + }, + { + "epoch": 2.0, + "learning_rate": 6.6992611907866145e-06, + "loss": 0.1858, + "step": 24484 + }, + { + "epoch": 2.0, + "learning_rate": 6.698717948717949e-06, + "loss": 0.5435, + "step": 24485 + }, + { + "epoch": 2.0, + "learning_rate": 6.698174706649283e-06, + "loss": 0.419, + "step": 24486 + }, + { + "epoch": 2.0, + "learning_rate": 6.697631464580617e-06, + "loss": 0.2776, + "step": 24487 + }, + { + "epoch": 2.0, + "learning_rate": 6.6970882225119514e-06, + "loss": 0.5958, + "step": 24488 + }, + { + "epoch": 2.0, + "learning_rate": 6.696544980443286e-06, + "loss": 0.2409, + "step": 24489 + }, + { + "epoch": 2.0, + "learning_rate": 6.69600173837462e-06, + "loss": 0.2824, + "step": 24490 + }, + { + "epoch": 2.0, + "learning_rate": 6.695458496305954e-06, + "loss": 0.5372, + "step": 24491 + }, + { + "epoch": 2.0, + "learning_rate": 6.694915254237288e-06, + "loss": 0.3088, + "step": 24492 + }, + { + "epoch": 2.0, + "learning_rate": 6.694372012168623e-06, + "loss": 0.3219, + "step": 24493 + }, + { + "epoch": 2.0, + "learning_rate": 6.693828770099957e-06, + "loss": 0.145, + "step": 24494 + }, + { + "epoch": 2.0, + "learning_rate": 6.693285528031291e-06, + "loss": 0.2134, + "step": 24495 + }, + { + "epoch": 2.0, + "learning_rate": 6.692742285962625e-06, + "loss": 0.1857, + "step": 24496 + }, + { + "epoch": 2.0, + "learning_rate": 6.6921990438939595e-06, + "loss": 0.1226, + "step": 24497 + }, + { + "epoch": 2.0, + "learning_rate": 6.691655801825295e-06, + "loss": 0.2247, + "step": 24498 + }, + { + "epoch": 2.0, + "learning_rate": 6.691112559756629e-06, + "loss": 0.2569, + "step": 24499 + }, + { + "epoch": 2.0, + "learning_rate": 6.690569317687963e-06, + "loss": 0.5297, + "step": 24500 + }, + { + "epoch": 2.0, + "eval_accuracy": 0.841874681609781, + "eval_loss": 0.4331735372543335, + "eval_runtime": 22.3317, + "eval_samples_per_second": 439.509, + "eval_steps_per_second": 3.448, + "step": 24500 + }, + { + "epoch": 2.0, + "learning_rate": 6.690026075619297e-06, + "loss": 0.1115, + "step": 24501 + }, + { + "epoch": 2.0, + "learning_rate": 6.6894828335506315e-06, + "loss": 0.3987, + "step": 24502 + }, + { + "epoch": 2.0, + "learning_rate": 6.688939591481964e-06, + "loss": 0.3089, + "step": 24503 + }, + { + "epoch": 2.0, + "learning_rate": 6.688396349413298e-06, + "loss": 0.2489, + "step": 24504 + }, + { + "epoch": 2.0, + "learning_rate": 6.6878531073446325e-06, + "loss": 0.3505, + "step": 24505 + }, + { + "epoch": 2.0, + "learning_rate": 6.687309865275967e-06, + "loss": 0.3213, + "step": 24506 + }, + { + "epoch": 2.0, + "learning_rate": 6.686766623207302e-06, + "loss": 0.4331, + "step": 24507 + }, + { + "epoch": 2.0, + "learning_rate": 6.686223381138636e-06, + "loss": 0.2601, + "step": 24508 + }, + { + "epoch": 2.0, + "learning_rate": 6.68568013906997e-06, + "loss": 0.3115, + "step": 24509 + }, + { + "epoch": 2.0, + "learning_rate": 6.6851368970013045e-06, + "loss": 0.2605, + "step": 24510 + }, + { + "epoch": 2.0, + "learning_rate": 6.684593654932639e-06, + "loss": 0.2161, + "step": 24511 + }, + { + "epoch": 2.0, + "learning_rate": 6.684050412863973e-06, + "loss": 0.1994, + "step": 24512 + }, + { + "epoch": 2.0, + "learning_rate": 6.683507170795307e-06, + "loss": 0.3244, + "step": 24513 + }, + { + "epoch": 2.0, + "learning_rate": 6.6829639287266414e-06, + "loss": 0.1634, + "step": 24514 + }, + { + "epoch": 2.0, + "learning_rate": 6.682420686657976e-06, + "loss": 0.3709, + "step": 24515 + }, + { + "epoch": 2.0, + "learning_rate": 6.68187744458931e-06, + "loss": 0.3153, + "step": 24516 + }, + { + "epoch": 2.0, + "learning_rate": 6.681334202520644e-06, + "loss": 0.5523, + "step": 24517 + }, + { + "epoch": 2.0, + "learning_rate": 6.680790960451978e-06, + "loss": 0.5694, + "step": 24518 + }, + { + "epoch": 2.0, + "learning_rate": 6.680247718383313e-06, + "loss": 0.3483, + "step": 24519 + }, + { + "epoch": 2.0, + "learning_rate": 6.679704476314647e-06, + "loss": 0.2072, + "step": 24520 + }, + { + "epoch": 2.0, + "learning_rate": 6.679161234245981e-06, + "loss": 0.3168, + "step": 24521 + }, + { + "epoch": 2.0, + "learning_rate": 6.678617992177314e-06, + "loss": 0.272, + "step": 24522 + }, + { + "epoch": 2.0, + "learning_rate": 6.678074750108649e-06, + "loss": 0.2133, + "step": 24523 + }, + { + "epoch": 2.0, + "learning_rate": 6.677531508039983e-06, + "loss": 0.2326, + "step": 24524 + }, + { + "epoch": 2.0, + "learning_rate": 6.676988265971317e-06, + "loss": 0.1592, + "step": 24525 + }, + { + "epoch": 2.0, + "learning_rate": 6.676445023902651e-06, + "loss": 0.3886, + "step": 24526 + }, + { + "epoch": 2.0, + "learning_rate": 6.6759017818339856e-06, + "loss": 0.6846, + "step": 24527 + }, + { + "epoch": 2.0, + "learning_rate": 6.67535853976532e-06, + "loss": 0.1735, + "step": 24528 + }, + { + "epoch": 2.0, + "learning_rate": 6.674815297696654e-06, + "loss": 0.547, + "step": 24529 + }, + { + "epoch": 2.0, + "learning_rate": 6.674272055627988e-06, + "loss": 0.3104, + "step": 24530 + }, + { + "epoch": 2.0, + "learning_rate": 6.6737288135593225e-06, + "loss": 0.3823, + "step": 24531 + }, + { + "epoch": 2.0, + "learning_rate": 6.673185571490657e-06, + "loss": 0.2494, + "step": 24532 + }, + { + "epoch": 2.0, + "learning_rate": 6.672642329421991e-06, + "loss": 0.5259, + "step": 24533 + }, + { + "epoch": 2.0, + "learning_rate": 6.672099087353325e-06, + "loss": 0.3403, + "step": 24534 + }, + { + "epoch": 2.0, + "learning_rate": 6.671555845284659e-06, + "loss": 0.1489, + "step": 24535 + }, + { + "epoch": 2.0, + "learning_rate": 6.671012603215994e-06, + "loss": 0.1968, + "step": 24536 + }, + { + "epoch": 2.0, + "learning_rate": 6.670469361147328e-06, + "loss": 0.5294, + "step": 24537 + }, + { + "epoch": 2.0, + "learning_rate": 6.669926119078662e-06, + "loss": 0.341, + "step": 24538 + }, + { + "epoch": 2.0, + "learning_rate": 6.669382877009996e-06, + "loss": 0.1788, + "step": 24539 + }, + { + "epoch": 2.0, + "learning_rate": 6.6688396349413306e-06, + "loss": 0.4346, + "step": 24540 + }, + { + "epoch": 2.0, + "learning_rate": 6.668296392872664e-06, + "loss": 0.0968, + "step": 24541 + }, + { + "epoch": 2.0, + "learning_rate": 6.667753150803998e-06, + "loss": 0.2848, + "step": 24542 + }, + { + "epoch": 2.0, + "learning_rate": 6.667209908735332e-06, + "loss": 0.2182, + "step": 24543 + }, + { + "epoch": 2.0, + "learning_rate": 6.666666666666667e-06, + "loss": 0.2635, + "step": 24544 + }, + { + "epoch": 2.0, + "learning_rate": 6.666123424598001e-06, + "loss": 0.1436, + "step": 24545 + }, + { + "epoch": 2.0, + "learning_rate": 6.665580182529335e-06, + "loss": 0.2397, + "step": 24546 + }, + { + "epoch": 2.0, + "learning_rate": 6.665036940460669e-06, + "loss": 0.1375, + "step": 24547 + }, + { + "epoch": 2.0, + "learning_rate": 6.6644936983920036e-06, + "loss": 0.332, + "step": 24548 + }, + { + "epoch": 2.0, + "learning_rate": 6.663950456323338e-06, + "loss": 0.2557, + "step": 24549 + }, + { + "epoch": 2.0, + "learning_rate": 6.663407214254672e-06, + "loss": 0.1306, + "step": 24550 + }, + { + "epoch": 2.0, + "learning_rate": 6.662863972186006e-06, + "loss": 0.2073, + "step": 24551 + }, + { + "epoch": 2.0, + "learning_rate": 6.662320730117341e-06, + "loss": 0.1247, + "step": 24552 + }, + { + "epoch": 2.0, + "learning_rate": 6.6617774880486756e-06, + "loss": 0.3232, + "step": 24553 + }, + { + "epoch": 2.0, + "learning_rate": 6.66123424598001e-06, + "loss": 0.2672, + "step": 24554 + }, + { + "epoch": 2.0, + "learning_rate": 6.660691003911344e-06, + "loss": 0.1409, + "step": 24555 + }, + { + "epoch": 2.0, + "learning_rate": 6.660147761842678e-06, + "loss": 0.2119, + "step": 24556 + }, + { + "epoch": 2.0, + "learning_rate": 6.6596045197740125e-06, + "loss": 0.1818, + "step": 24557 + }, + { + "epoch": 2.0, + "learning_rate": 6.659061277705347e-06, + "loss": 0.1322, + "step": 24558 + }, + { + "epoch": 2.0, + "learning_rate": 6.658518035636681e-06, + "loss": 0.183, + "step": 24559 + }, + { + "epoch": 2.0, + "learning_rate": 6.6579747935680135e-06, + "loss": 0.2603, + "step": 24560 + }, + { + "epoch": 2.0, + "learning_rate": 6.6574315514993486e-06, + "loss": 0.409, + "step": 24561 + }, + { + "epoch": 2.0, + "learning_rate": 6.656888309430683e-06, + "loss": 0.1178, + "step": 24562 + }, + { + "epoch": 2.0, + "learning_rate": 6.656345067362017e-06, + "loss": 0.3719, + "step": 24563 + }, + { + "epoch": 2.0, + "learning_rate": 6.655801825293351e-06, + "loss": 0.225, + "step": 24564 + }, + { + "epoch": 2.0, + "learning_rate": 6.6552585832246855e-06, + "loss": 0.3141, + "step": 24565 + }, + { + "epoch": 2.0, + "learning_rate": 6.65471534115602e-06, + "loss": 0.2235, + "step": 24566 + }, + { + "epoch": 2.0, + "learning_rate": 6.654172099087354e-06, + "loss": 0.1592, + "step": 24567 + }, + { + "epoch": 2.0, + "learning_rate": 6.653628857018688e-06, + "loss": 0.302, + "step": 24568 + }, + { + "epoch": 2.0, + "learning_rate": 6.653085614950022e-06, + "loss": 0.1209, + "step": 24569 + }, + { + "epoch": 2.0, + "learning_rate": 6.652542372881357e-06, + "loss": 0.1105, + "step": 24570 + }, + { + "epoch": 2.0, + "learning_rate": 6.651999130812691e-06, + "loss": 0.4375, + "step": 24571 + }, + { + "epoch": 2.0, + "learning_rate": 6.651455888744025e-06, + "loss": 0.3195, + "step": 24572 + }, + { + "epoch": 2.0, + "learning_rate": 6.650912646675359e-06, + "loss": 0.1998, + "step": 24573 + }, + { + "epoch": 2.0, + "learning_rate": 6.6503694046066936e-06, + "loss": 0.1331, + "step": 24574 + }, + { + "epoch": 2.0, + "learning_rate": 6.649826162538028e-06, + "loss": 0.1181, + "step": 24575 + }, + { + "epoch": 2.0, + "learning_rate": 6.649282920469362e-06, + "loss": 0.3436, + "step": 24576 + }, + { + "epoch": 2.0, + "learning_rate": 6.648739678400696e-06, + "loss": 0.1082, + "step": 24577 + }, + { + "epoch": 2.0, + "learning_rate": 6.6481964363320305e-06, + "loss": 0.2354, + "step": 24578 + }, + { + "epoch": 2.0, + "learning_rate": 6.647653194263364e-06, + "loss": 0.1683, + "step": 24579 + }, + { + "epoch": 2.0, + "learning_rate": 6.647109952194698e-06, + "loss": 0.2254, + "step": 24580 + }, + { + "epoch": 2.0, + "learning_rate": 6.646566710126032e-06, + "loss": 0.3251, + "step": 24581 + }, + { + "epoch": 2.0, + "learning_rate": 6.6460234680573666e-06, + "loss": 0.0672, + "step": 24582 + }, + { + "epoch": 2.0, + "learning_rate": 6.645480225988701e-06, + "loss": 0.0691, + "step": 24583 + }, + { + "epoch": 2.0, + "learning_rate": 6.644936983920035e-06, + "loss": 0.3011, + "step": 24584 + }, + { + "epoch": 2.0, + "learning_rate": 6.644393741851369e-06, + "loss": 0.0824, + "step": 24585 + }, + { + "epoch": 2.0, + "learning_rate": 6.6438504997827035e-06, + "loss": 0.2838, + "step": 24586 + }, + { + "epoch": 2.0, + "learning_rate": 6.643307257714038e-06, + "loss": 0.1471, + "step": 24587 + }, + { + "epoch": 2.0, + "learning_rate": 6.642764015645372e-06, + "loss": 0.1751, + "step": 24588 + }, + { + "epoch": 2.0, + "learning_rate": 6.642220773576706e-06, + "loss": 0.2634, + "step": 24589 + }, + { + "epoch": 2.0, + "learning_rate": 6.64167753150804e-06, + "loss": 0.3976, + "step": 24590 + }, + { + "epoch": 2.0, + "learning_rate": 6.641134289439375e-06, + "loss": 0.1138, + "step": 24591 + }, + { + "epoch": 2.0, + "learning_rate": 6.640591047370709e-06, + "loss": 0.3033, + "step": 24592 + }, + { + "epoch": 2.0, + "learning_rate": 6.640047805302043e-06, + "loss": 0.3644, + "step": 24593 + }, + { + "epoch": 2.0, + "learning_rate": 6.639504563233377e-06, + "loss": 0.3012, + "step": 24594 + }, + { + "epoch": 2.0, + "learning_rate": 6.6389613211647116e-06, + "loss": 0.2876, + "step": 24595 + }, + { + "epoch": 2.0, + "learning_rate": 6.638418079096046e-06, + "loss": 0.169, + "step": 24596 + }, + { + "epoch": 2.0, + "learning_rate": 6.637874837027381e-06, + "loss": 0.175, + "step": 24597 + }, + { + "epoch": 2.0, + "learning_rate": 6.637331594958713e-06, + "loss": 0.3243, + "step": 24598 + }, + { + "epoch": 2.0, + "learning_rate": 6.636788352890048e-06, + "loss": 0.4413, + "step": 24599 + }, + { + "epoch": 2.0, + "learning_rate": 6.636245110821382e-06, + "loss": 0.1587, + "step": 24600 + }, + { + "epoch": 2.0, + "learning_rate": 6.635701868752716e-06, + "loss": 0.2052, + "step": 24601 + }, + { + "epoch": 2.0, + "learning_rate": 6.63515862668405e-06, + "loss": 0.3784, + "step": 24602 + }, + { + "epoch": 2.0, + "learning_rate": 6.6346153846153846e-06, + "loss": 0.3415, + "step": 24603 + }, + { + "epoch": 2.0, + "learning_rate": 6.634072142546719e-06, + "loss": 0.2324, + "step": 24604 + }, + { + "epoch": 2.0, + "learning_rate": 6.633528900478053e-06, + "loss": 0.4144, + "step": 24605 + }, + { + "epoch": 2.01, + "learning_rate": 6.632985658409388e-06, + "loss": 0.0882, + "step": 24606 + }, + { + "epoch": 2.01, + "learning_rate": 6.632442416340722e-06, + "loss": 0.5302, + "step": 24607 + }, + { + "epoch": 2.01, + "learning_rate": 6.6318991742720566e-06, + "loss": 0.107, + "step": 24608 + }, + { + "epoch": 2.01, + "learning_rate": 6.631355932203391e-06, + "loss": 0.2526, + "step": 24609 + }, + { + "epoch": 2.01, + "learning_rate": 6.630812690134725e-06, + "loss": 0.2737, + "step": 24610 + }, + { + "epoch": 2.01, + "learning_rate": 6.630269448066059e-06, + "loss": 0.3607, + "step": 24611 + }, + { + "epoch": 2.01, + "learning_rate": 6.6297262059973935e-06, + "loss": 0.3145, + "step": 24612 + }, + { + "epoch": 2.01, + "learning_rate": 6.629182963928728e-06, + "loss": 0.1446, + "step": 24613 + }, + { + "epoch": 2.01, + "learning_rate": 6.628639721860062e-06, + "loss": 0.1416, + "step": 24614 + }, + { + "epoch": 2.01, + "learning_rate": 6.628096479791396e-06, + "loss": 0.3799, + "step": 24615 + }, + { + "epoch": 2.01, + "learning_rate": 6.62755323772273e-06, + "loss": 0.3148, + "step": 24616 + }, + { + "epoch": 2.01, + "learning_rate": 6.627009995654064e-06, + "loss": 0.2215, + "step": 24617 + }, + { + "epoch": 2.01, + "learning_rate": 6.626466753585398e-06, + "loss": 0.1355, + "step": 24618 + }, + { + "epoch": 2.01, + "learning_rate": 6.625923511516732e-06, + "loss": 0.2111, + "step": 24619 + }, + { + "epoch": 2.01, + "learning_rate": 6.6253802694480665e-06, + "loss": 0.3718, + "step": 24620 + }, + { + "epoch": 2.01, + "learning_rate": 6.624837027379401e-06, + "loss": 0.2991, + "step": 24621 + }, + { + "epoch": 2.01, + "learning_rate": 6.624293785310735e-06, + "loss": 0.2444, + "step": 24622 + }, + { + "epoch": 2.01, + "learning_rate": 6.623750543242069e-06, + "loss": 0.1698, + "step": 24623 + }, + { + "epoch": 2.01, + "learning_rate": 6.623207301173403e-06, + "loss": 0.1545, + "step": 24624 + }, + { + "epoch": 2.01, + "learning_rate": 6.622664059104738e-06, + "loss": 0.1835, + "step": 24625 + }, + { + "epoch": 2.01, + "learning_rate": 6.622120817036072e-06, + "loss": 0.1275, + "step": 24626 + }, + { + "epoch": 2.01, + "learning_rate": 6.621577574967406e-06, + "loss": 0.3867, + "step": 24627 + }, + { + "epoch": 2.01, + "learning_rate": 6.62103433289874e-06, + "loss": 0.4655, + "step": 24628 + }, + { + "epoch": 2.01, + "learning_rate": 6.6204910908300745e-06, + "loss": 0.1042, + "step": 24629 + }, + { + "epoch": 2.01, + "learning_rate": 6.619947848761409e-06, + "loss": 0.2697, + "step": 24630 + }, + { + "epoch": 2.01, + "learning_rate": 6.619404606692743e-06, + "loss": 0.3243, + "step": 24631 + }, + { + "epoch": 2.01, + "learning_rate": 6.618861364624077e-06, + "loss": 0.1989, + "step": 24632 + }, + { + "epoch": 2.01, + "learning_rate": 6.6183181225554115e-06, + "loss": 0.2553, + "step": 24633 + }, + { + "epoch": 2.01, + "learning_rate": 6.617774880486746e-06, + "loss": 0.1452, + "step": 24634 + }, + { + "epoch": 2.01, + "learning_rate": 6.61723163841808e-06, + "loss": 0.1397, + "step": 24635 + }, + { + "epoch": 2.01, + "learning_rate": 6.616688396349413e-06, + "loss": 0.202, + "step": 24636 + }, + { + "epoch": 2.01, + "learning_rate": 6.6161451542807475e-06, + "loss": 0.0832, + "step": 24637 + }, + { + "epoch": 2.01, + "learning_rate": 6.615601912212082e-06, + "loss": 0.1974, + "step": 24638 + }, + { + "epoch": 2.01, + "learning_rate": 6.615058670143416e-06, + "loss": 0.1806, + "step": 24639 + }, + { + "epoch": 2.01, + "learning_rate": 6.61451542807475e-06, + "loss": 0.1762, + "step": 24640 + }, + { + "epoch": 2.01, + "learning_rate": 6.6139721860060845e-06, + "loss": 0.1282, + "step": 24641 + }, + { + "epoch": 2.01, + "learning_rate": 6.613428943937419e-06, + "loss": 0.1149, + "step": 24642 + }, + { + "epoch": 2.01, + "learning_rate": 6.612885701868753e-06, + "loss": 0.2043, + "step": 24643 + }, + { + "epoch": 2.01, + "learning_rate": 6.612342459800087e-06, + "loss": 0.3202, + "step": 24644 + }, + { + "epoch": 2.01, + "learning_rate": 6.611799217731421e-06, + "loss": 0.2727, + "step": 24645 + }, + { + "epoch": 2.01, + "learning_rate": 6.611255975662756e-06, + "loss": 0.1918, + "step": 24646 + }, + { + "epoch": 2.01, + "learning_rate": 6.61071273359409e-06, + "loss": 0.1564, + "step": 24647 + }, + { + "epoch": 2.01, + "learning_rate": 6.610169491525424e-06, + "loss": 0.2427, + "step": 24648 + }, + { + "epoch": 2.01, + "learning_rate": 6.609626249456758e-06, + "loss": 0.2795, + "step": 24649 + }, + { + "epoch": 2.01, + "learning_rate": 6.6090830073880925e-06, + "loss": 0.0576, + "step": 24650 + }, + { + "epoch": 2.01, + "learning_rate": 6.608539765319428e-06, + "loss": 0.4741, + "step": 24651 + }, + { + "epoch": 2.01, + "learning_rate": 6.607996523250762e-06, + "loss": 0.073, + "step": 24652 + }, + { + "epoch": 2.01, + "learning_rate": 6.607453281182096e-06, + "loss": 0.1922, + "step": 24653 + }, + { + "epoch": 2.01, + "learning_rate": 6.60691003911343e-06, + "loss": 0.137, + "step": 24654 + }, + { + "epoch": 2.01, + "learning_rate": 6.606366797044763e-06, + "loss": 0.2962, + "step": 24655 + }, + { + "epoch": 2.01, + "learning_rate": 6.605823554976097e-06, + "loss": 0.4488, + "step": 24656 + }, + { + "epoch": 2.01, + "learning_rate": 6.605280312907431e-06, + "loss": 0.2466, + "step": 24657 + }, + { + "epoch": 2.01, + "learning_rate": 6.6047370708387655e-06, + "loss": 0.2881, + "step": 24658 + }, + { + "epoch": 2.01, + "learning_rate": 6.6041938287701e-06, + "loss": 0.0888, + "step": 24659 + }, + { + "epoch": 2.01, + "learning_rate": 6.603650586701435e-06, + "loss": 0.155, + "step": 24660 + }, + { + "epoch": 2.01, + "learning_rate": 6.603107344632769e-06, + "loss": 0.3114, + "step": 24661 + }, + { + "epoch": 2.01, + "learning_rate": 6.602564102564103e-06, + "loss": 0.2517, + "step": 24662 + }, + { + "epoch": 2.01, + "learning_rate": 6.6020208604954375e-06, + "loss": 0.3449, + "step": 24663 + }, + { + "epoch": 2.01, + "learning_rate": 6.601477618426772e-06, + "loss": 0.1273, + "step": 24664 + }, + { + "epoch": 2.01, + "learning_rate": 6.600934376358106e-06, + "loss": 0.1243, + "step": 24665 + }, + { + "epoch": 2.01, + "learning_rate": 6.60039113428944e-06, + "loss": 0.3865, + "step": 24666 + }, + { + "epoch": 2.01, + "learning_rate": 6.5998478922207745e-06, + "loss": 0.2167, + "step": 24667 + }, + { + "epoch": 2.01, + "learning_rate": 6.599304650152109e-06, + "loss": 0.1749, + "step": 24668 + }, + { + "epoch": 2.01, + "learning_rate": 6.598761408083443e-06, + "loss": 0.1945, + "step": 24669 + }, + { + "epoch": 2.01, + "learning_rate": 6.598218166014777e-06, + "loss": 0.309, + "step": 24670 + }, + { + "epoch": 2.01, + "learning_rate": 6.597674923946111e-06, + "loss": 0.1956, + "step": 24671 + }, + { + "epoch": 2.01, + "learning_rate": 6.597131681877446e-06, + "loss": 0.2532, + "step": 24672 + }, + { + "epoch": 2.01, + "learning_rate": 6.59658843980878e-06, + "loss": 0.1509, + "step": 24673 + }, + { + "epoch": 2.01, + "learning_rate": 6.596045197740113e-06, + "loss": 0.2582, + "step": 24674 + }, + { + "epoch": 2.01, + "learning_rate": 6.5955019556714475e-06, + "loss": 0.3752, + "step": 24675 + }, + { + "epoch": 2.01, + "learning_rate": 6.594958713602782e-06, + "loss": 0.2253, + "step": 24676 + }, + { + "epoch": 2.01, + "learning_rate": 6.594415471534116e-06, + "loss": 0.2735, + "step": 24677 + }, + { + "epoch": 2.01, + "learning_rate": 6.59387222946545e-06, + "loss": 0.1038, + "step": 24678 + }, + { + "epoch": 2.01, + "learning_rate": 6.593328987396784e-06, + "loss": 0.1022, + "step": 24679 + }, + { + "epoch": 2.01, + "learning_rate": 6.592785745328119e-06, + "loss": 0.3215, + "step": 24680 + }, + { + "epoch": 2.01, + "learning_rate": 6.592242503259453e-06, + "loss": 0.2335, + "step": 24681 + }, + { + "epoch": 2.01, + "learning_rate": 6.591699261190787e-06, + "loss": 0.2512, + "step": 24682 + }, + { + "epoch": 2.01, + "learning_rate": 6.591156019122121e-06, + "loss": 0.2389, + "step": 24683 + }, + { + "epoch": 2.01, + "learning_rate": 6.5906127770534555e-06, + "loss": 0.0982, + "step": 24684 + }, + { + "epoch": 2.01, + "learning_rate": 6.59006953498479e-06, + "loss": 0.4136, + "step": 24685 + }, + { + "epoch": 2.01, + "learning_rate": 6.589526292916124e-06, + "loss": 0.3136, + "step": 24686 + }, + { + "epoch": 2.01, + "learning_rate": 6.588983050847458e-06, + "loss": 0.1596, + "step": 24687 + }, + { + "epoch": 2.01, + "learning_rate": 6.5884398087787925e-06, + "loss": 0.2694, + "step": 24688 + }, + { + "epoch": 2.01, + "learning_rate": 6.587896566710127e-06, + "loss": 0.4344, + "step": 24689 + }, + { + "epoch": 2.01, + "learning_rate": 6.587353324641461e-06, + "loss": 0.3415, + "step": 24690 + }, + { + "epoch": 2.01, + "learning_rate": 6.586810082572795e-06, + "loss": 0.1232, + "step": 24691 + }, + { + "epoch": 2.01, + "learning_rate": 6.586266840504129e-06, + "loss": 0.3502, + "step": 24692 + }, + { + "epoch": 2.01, + "learning_rate": 6.585723598435463e-06, + "loss": 0.3143, + "step": 24693 + }, + { + "epoch": 2.01, + "learning_rate": 6.585180356366797e-06, + "loss": 0.1647, + "step": 24694 + }, + { + "epoch": 2.01, + "learning_rate": 6.584637114298131e-06, + "loss": 0.105, + "step": 24695 + }, + { + "epoch": 2.01, + "learning_rate": 6.5840938722294655e-06, + "loss": 0.1779, + "step": 24696 + }, + { + "epoch": 2.01, + "learning_rate": 6.5835506301608e-06, + "loss": 0.3598, + "step": 24697 + }, + { + "epoch": 2.01, + "learning_rate": 6.583007388092134e-06, + "loss": 0.3355, + "step": 24698 + }, + { + "epoch": 2.01, + "learning_rate": 6.582464146023468e-06, + "loss": 0.2308, + "step": 24699 + }, + { + "epoch": 2.01, + "learning_rate": 6.581920903954802e-06, + "loss": 0.4652, + "step": 24700 + }, + { + "epoch": 2.01, + "learning_rate": 6.581377661886137e-06, + "loss": 0.1601, + "step": 24701 + }, + { + "epoch": 2.01, + "learning_rate": 6.580834419817471e-06, + "loss": 0.37, + "step": 24702 + }, + { + "epoch": 2.01, + "learning_rate": 6.580291177748805e-06, + "loss": 0.1551, + "step": 24703 + }, + { + "epoch": 2.01, + "learning_rate": 6.579747935680139e-06, + "loss": 0.3352, + "step": 24704 + }, + { + "epoch": 2.01, + "learning_rate": 6.579204693611474e-06, + "loss": 0.1794, + "step": 24705 + }, + { + "epoch": 2.01, + "learning_rate": 6.578661451542809e-06, + "loss": 0.1321, + "step": 24706 + }, + { + "epoch": 2.01, + "learning_rate": 6.578118209474143e-06, + "loss": 0.1835, + "step": 24707 + }, + { + "epoch": 2.01, + "learning_rate": 6.577574967405477e-06, + "loss": 0.2319, + "step": 24708 + }, + { + "epoch": 2.01, + "learning_rate": 6.577031725336811e-06, + "loss": 0.166, + "step": 24709 + }, + { + "epoch": 2.01, + "learning_rate": 6.5764884832681455e-06, + "loss": 0.2472, + "step": 24710 + }, + { + "epoch": 2.01, + "learning_rate": 6.57594524119948e-06, + "loss": 0.166, + "step": 24711 + }, + { + "epoch": 2.01, + "learning_rate": 6.575401999130812e-06, + "loss": 0.4794, + "step": 24712 + }, + { + "epoch": 2.01, + "learning_rate": 6.5748587570621465e-06, + "loss": 0.2833, + "step": 24713 + }, + { + "epoch": 2.01, + "learning_rate": 6.574315514993482e-06, + "loss": 0.1128, + "step": 24714 + }, + { + "epoch": 2.01, + "learning_rate": 6.573772272924816e-06, + "loss": 0.2643, + "step": 24715 + }, + { + "epoch": 2.01, + "learning_rate": 6.57322903085615e-06, + "loss": 0.3371, + "step": 24716 + }, + { + "epoch": 2.01, + "learning_rate": 6.572685788787484e-06, + "loss": 0.0602, + "step": 24717 + }, + { + "epoch": 2.01, + "learning_rate": 6.5721425467188185e-06, + "loss": 0.2374, + "step": 24718 + }, + { + "epoch": 2.01, + "learning_rate": 6.571599304650153e-06, + "loss": 0.2735, + "step": 24719 + }, + { + "epoch": 2.01, + "learning_rate": 6.571056062581487e-06, + "loss": 0.1419, + "step": 24720 + }, + { + "epoch": 2.01, + "learning_rate": 6.570512820512821e-06, + "loss": 0.1461, + "step": 24721 + }, + { + "epoch": 2.01, + "learning_rate": 6.5699695784441554e-06, + "loss": 0.1795, + "step": 24722 + }, + { + "epoch": 2.01, + "learning_rate": 6.56942633637549e-06, + "loss": 0.1757, + "step": 24723 + }, + { + "epoch": 2.01, + "learning_rate": 6.568883094306824e-06, + "loss": 0.4918, + "step": 24724 + }, + { + "epoch": 2.01, + "learning_rate": 6.568339852238158e-06, + "loss": 0.2314, + "step": 24725 + }, + { + "epoch": 2.01, + "learning_rate": 6.567796610169492e-06, + "loss": 0.2768, + "step": 24726 + }, + { + "epoch": 2.01, + "learning_rate": 6.567253368100827e-06, + "loss": 0.1397, + "step": 24727 + }, + { + "epoch": 2.01, + "learning_rate": 6.566710126032161e-06, + "loss": 0.3579, + "step": 24728 + }, + { + "epoch": 2.02, + "learning_rate": 6.566166883963495e-06, + "loss": 0.1834, + "step": 24729 + }, + { + "epoch": 2.02, + "learning_rate": 6.565623641894829e-06, + "loss": 0.1543, + "step": 24730 + }, + { + "epoch": 2.02, + "learning_rate": 6.565080399826163e-06, + "loss": 0.0609, + "step": 24731 + }, + { + "epoch": 2.02, + "learning_rate": 6.564537157757497e-06, + "loss": 0.2412, + "step": 24732 + }, + { + "epoch": 2.02, + "learning_rate": 6.563993915688831e-06, + "loss": 0.2122, + "step": 24733 + }, + { + "epoch": 2.02, + "learning_rate": 6.563450673620165e-06, + "loss": 0.2273, + "step": 24734 + }, + { + "epoch": 2.02, + "learning_rate": 6.5629074315515e-06, + "loss": 0.3227, + "step": 24735 + }, + { + "epoch": 2.02, + "learning_rate": 6.562364189482834e-06, + "loss": 0.7645, + "step": 24736 + }, + { + "epoch": 2.02, + "learning_rate": 6.561820947414168e-06, + "loss": 0.0525, + "step": 24737 + }, + { + "epoch": 2.02, + "learning_rate": 6.561277705345502e-06, + "loss": 0.4064, + "step": 24738 + }, + { + "epoch": 2.02, + "learning_rate": 6.5607344632768365e-06, + "loss": 0.3292, + "step": 24739 + }, + { + "epoch": 2.02, + "learning_rate": 6.560191221208171e-06, + "loss": 0.0674, + "step": 24740 + }, + { + "epoch": 2.02, + "learning_rate": 6.559647979139505e-06, + "loss": 0.42, + "step": 24741 + }, + { + "epoch": 2.02, + "learning_rate": 6.559104737070839e-06, + "loss": 0.106, + "step": 24742 + }, + { + "epoch": 2.02, + "learning_rate": 6.5585614950021734e-06, + "loss": 0.2381, + "step": 24743 + }, + { + "epoch": 2.02, + "learning_rate": 6.558018252933508e-06, + "loss": 0.1366, + "step": 24744 + }, + { + "epoch": 2.02, + "learning_rate": 6.557475010864842e-06, + "loss": 0.131, + "step": 24745 + }, + { + "epoch": 2.02, + "learning_rate": 6.556931768796176e-06, + "loss": 0.152, + "step": 24746 + }, + { + "epoch": 2.02, + "learning_rate": 6.55638852672751e-06, + "loss": 0.1516, + "step": 24747 + }, + { + "epoch": 2.02, + "learning_rate": 6.555845284658845e-06, + "loss": 0.2764, + "step": 24748 + }, + { + "epoch": 2.02, + "learning_rate": 6.555302042590179e-06, + "loss": 0.1853, + "step": 24749 + }, + { + "epoch": 2.02, + "learning_rate": 6.554758800521513e-06, + "loss": 0.2869, + "step": 24750 + }, + { + "epoch": 2.02, + "eval_accuracy": 0.8412633723892002, + "eval_loss": 0.4797918200492859, + "eval_runtime": 22.197, + "eval_samples_per_second": 442.176, + "eval_steps_per_second": 3.469, + "step": 24750 + }, + { + "epoch": 2.02, + "learning_rate": 6.5542155584528464e-06, + "loss": 0.0557, + "step": 24751 + }, + { + "epoch": 2.02, + "learning_rate": 6.553672316384181e-06, + "loss": 0.287, + "step": 24752 + }, + { + "epoch": 2.02, + "learning_rate": 6.553129074315515e-06, + "loss": 0.2034, + "step": 24753 + }, + { + "epoch": 2.02, + "learning_rate": 6.552585832246849e-06, + "loss": 0.2229, + "step": 24754 + }, + { + "epoch": 2.02, + "learning_rate": 6.552042590178183e-06, + "loss": 0.2646, + "step": 24755 + }, + { + "epoch": 2.02, + "learning_rate": 6.551499348109518e-06, + "loss": 0.2615, + "step": 24756 + }, + { + "epoch": 2.02, + "learning_rate": 6.550956106040852e-06, + "loss": 0.4107, + "step": 24757 + }, + { + "epoch": 2.02, + "learning_rate": 6.550412863972186e-06, + "loss": 0.2986, + "step": 24758 + }, + { + "epoch": 2.02, + "learning_rate": 6.549869621903521e-06, + "loss": 0.0515, + "step": 24759 + }, + { + "epoch": 2.02, + "learning_rate": 6.549326379834855e-06, + "loss": 0.1859, + "step": 24760 + }, + { + "epoch": 2.02, + "learning_rate": 6.54878313776619e-06, + "loss": 0.2908, + "step": 24761 + }, + { + "epoch": 2.02, + "learning_rate": 6.548239895697524e-06, + "loss": 0.4491, + "step": 24762 + }, + { + "epoch": 2.02, + "learning_rate": 6.547696653628858e-06, + "loss": 0.1523, + "step": 24763 + }, + { + "epoch": 2.02, + "learning_rate": 6.547153411560192e-06, + "loss": 0.1182, + "step": 24764 + }, + { + "epoch": 2.02, + "learning_rate": 6.5466101694915265e-06, + "loss": 0.2471, + "step": 24765 + }, + { + "epoch": 2.02, + "learning_rate": 6.546066927422861e-06, + "loss": 0.1681, + "step": 24766 + }, + { + "epoch": 2.02, + "learning_rate": 6.545523685354195e-06, + "loss": 0.3987, + "step": 24767 + }, + { + "epoch": 2.02, + "learning_rate": 6.544980443285529e-06, + "loss": 0.0922, + "step": 24768 + }, + { + "epoch": 2.02, + "learning_rate": 6.5444372012168634e-06, + "loss": 0.4648, + "step": 24769 + }, + { + "epoch": 2.02, + "learning_rate": 6.543893959148197e-06, + "loss": 0.1482, + "step": 24770 + }, + { + "epoch": 2.02, + "learning_rate": 6.543350717079531e-06, + "loss": 0.0463, + "step": 24771 + }, + { + "epoch": 2.02, + "learning_rate": 6.542807475010865e-06, + "loss": 0.1922, + "step": 24772 + }, + { + "epoch": 2.02, + "learning_rate": 6.5422642329421995e-06, + "loss": 0.1374, + "step": 24773 + }, + { + "epoch": 2.02, + "learning_rate": 6.541720990873534e-06, + "loss": 0.1201, + "step": 24774 + }, + { + "epoch": 2.02, + "learning_rate": 6.541177748804868e-06, + "loss": 0.156, + "step": 24775 + }, + { + "epoch": 2.02, + "learning_rate": 6.540634506736202e-06, + "loss": 0.0705, + "step": 24776 + }, + { + "epoch": 2.02, + "learning_rate": 6.5400912646675364e-06, + "loss": 0.3686, + "step": 24777 + }, + { + "epoch": 2.02, + "learning_rate": 6.539548022598871e-06, + "loss": 0.094, + "step": 24778 + }, + { + "epoch": 2.02, + "learning_rate": 6.539004780530205e-06, + "loss": 0.2616, + "step": 24779 + }, + { + "epoch": 2.02, + "learning_rate": 6.538461538461539e-06, + "loss": 0.0936, + "step": 24780 + }, + { + "epoch": 2.02, + "learning_rate": 6.537918296392873e-06, + "loss": 0.3574, + "step": 24781 + }, + { + "epoch": 2.02, + "learning_rate": 6.537375054324208e-06, + "loss": 0.3085, + "step": 24782 + }, + { + "epoch": 2.02, + "learning_rate": 6.536831812255542e-06, + "loss": 0.2011, + "step": 24783 + }, + { + "epoch": 2.02, + "learning_rate": 6.536288570186876e-06, + "loss": 0.1994, + "step": 24784 + }, + { + "epoch": 2.02, + "learning_rate": 6.53574532811821e-06, + "loss": 0.2855, + "step": 24785 + }, + { + "epoch": 2.02, + "learning_rate": 6.5352020860495445e-06, + "loss": 0.2212, + "step": 24786 + }, + { + "epoch": 2.02, + "learning_rate": 6.534658843980879e-06, + "loss": 0.1824, + "step": 24787 + }, + { + "epoch": 2.02, + "learning_rate": 6.534115601912213e-06, + "loss": 0.2585, + "step": 24788 + }, + { + "epoch": 2.02, + "learning_rate": 6.533572359843546e-06, + "loss": 0.3636, + "step": 24789 + }, + { + "epoch": 2.02, + "learning_rate": 6.533029117774881e-06, + "loss": 0.5618, + "step": 24790 + }, + { + "epoch": 2.02, + "learning_rate": 6.532485875706215e-06, + "loss": 0.0525, + "step": 24791 + }, + { + "epoch": 2.02, + "learning_rate": 6.531942633637549e-06, + "loss": 0.4583, + "step": 24792 + }, + { + "epoch": 2.02, + "learning_rate": 6.531399391568883e-06, + "loss": 0.1826, + "step": 24793 + }, + { + "epoch": 2.02, + "learning_rate": 6.5308561495002175e-06, + "loss": 0.2684, + "step": 24794 + }, + { + "epoch": 2.02, + "learning_rate": 6.530312907431552e-06, + "loss": 0.4671, + "step": 24795 + }, + { + "epoch": 2.02, + "learning_rate": 6.529769665362886e-06, + "loss": 0.283, + "step": 24796 + }, + { + "epoch": 2.02, + "learning_rate": 6.52922642329422e-06, + "loss": 0.1612, + "step": 24797 + }, + { + "epoch": 2.02, + "learning_rate": 6.5286831812255544e-06, + "loss": 0.4695, + "step": 24798 + }, + { + "epoch": 2.02, + "learning_rate": 6.528139939156889e-06, + "loss": 0.0917, + "step": 24799 + }, + { + "epoch": 2.02, + "learning_rate": 6.527596697088223e-06, + "loss": 0.23, + "step": 24800 + }, + { + "epoch": 2.02, + "learning_rate": 6.527053455019557e-06, + "loss": 0.314, + "step": 24801 + }, + { + "epoch": 2.02, + "learning_rate": 6.526510212950891e-06, + "loss": 0.3149, + "step": 24802 + }, + { + "epoch": 2.02, + "learning_rate": 6.525966970882226e-06, + "loss": 0.4833, + "step": 24803 + }, + { + "epoch": 2.02, + "learning_rate": 6.52542372881356e-06, + "loss": 0.3869, + "step": 24804 + }, + { + "epoch": 2.02, + "learning_rate": 6.524880486744895e-06, + "loss": 0.1432, + "step": 24805 + }, + { + "epoch": 2.02, + "learning_rate": 6.524337244676229e-06, + "loss": 0.56, + "step": 24806 + }, + { + "epoch": 2.02, + "learning_rate": 6.523794002607563e-06, + "loss": 0.4142, + "step": 24807 + }, + { + "epoch": 2.02, + "learning_rate": 6.523250760538896e-06, + "loss": 0.3618, + "step": 24808 + }, + { + "epoch": 2.02, + "learning_rate": 6.52270751847023e-06, + "loss": 0.4465, + "step": 24809 + }, + { + "epoch": 2.02, + "learning_rate": 6.522164276401564e-06, + "loss": 0.1067, + "step": 24810 + }, + { + "epoch": 2.02, + "learning_rate": 6.521621034332899e-06, + "loss": 0.2144, + "step": 24811 + }, + { + "epoch": 2.02, + "learning_rate": 6.521077792264233e-06, + "loss": 0.1869, + "step": 24812 + }, + { + "epoch": 2.02, + "learning_rate": 6.520534550195568e-06, + "loss": 0.5457, + "step": 24813 + }, + { + "epoch": 2.02, + "learning_rate": 6.519991308126902e-06, + "loss": 0.1806, + "step": 24814 + }, + { + "epoch": 2.02, + "learning_rate": 6.519448066058236e-06, + "loss": 0.194, + "step": 24815 + }, + { + "epoch": 2.02, + "learning_rate": 6.518904823989571e-06, + "loss": 0.2126, + "step": 24816 + }, + { + "epoch": 2.02, + "learning_rate": 6.518361581920905e-06, + "loss": 0.329, + "step": 24817 + }, + { + "epoch": 2.02, + "learning_rate": 6.517818339852239e-06, + "loss": 0.172, + "step": 24818 + }, + { + "epoch": 2.02, + "learning_rate": 6.517275097783573e-06, + "loss": 0.2136, + "step": 24819 + }, + { + "epoch": 2.02, + "learning_rate": 6.5167318557149075e-06, + "loss": 0.1702, + "step": 24820 + }, + { + "epoch": 2.02, + "learning_rate": 6.516188613646242e-06, + "loss": 0.2501, + "step": 24821 + }, + { + "epoch": 2.02, + "learning_rate": 6.515645371577576e-06, + "loss": 0.8139, + "step": 24822 + }, + { + "epoch": 2.02, + "learning_rate": 6.51510212950891e-06, + "loss": 0.3859, + "step": 24823 + }, + { + "epoch": 2.02, + "learning_rate": 6.5145588874402444e-06, + "loss": 0.3442, + "step": 24824 + }, + { + "epoch": 2.02, + "learning_rate": 6.514015645371579e-06, + "loss": 0.1722, + "step": 24825 + }, + { + "epoch": 2.02, + "learning_rate": 6.513472403302913e-06, + "loss": 0.1824, + "step": 24826 + }, + { + "epoch": 2.02, + "learning_rate": 6.512929161234246e-06, + "loss": 0.2686, + "step": 24827 + }, + { + "epoch": 2.02, + "learning_rate": 6.5123859191655805e-06, + "loss": 0.0817, + "step": 24828 + }, + { + "epoch": 2.02, + "learning_rate": 6.511842677096915e-06, + "loss": 0.4208, + "step": 24829 + }, + { + "epoch": 2.02, + "learning_rate": 6.511299435028249e-06, + "loss": 0.3113, + "step": 24830 + }, + { + "epoch": 2.02, + "learning_rate": 6.510756192959583e-06, + "loss": 0.3806, + "step": 24831 + }, + { + "epoch": 2.02, + "learning_rate": 6.510212950890917e-06, + "loss": 0.1254, + "step": 24832 + }, + { + "epoch": 2.02, + "learning_rate": 6.509669708822252e-06, + "loss": 0.3286, + "step": 24833 + }, + { + "epoch": 2.02, + "learning_rate": 6.509126466753586e-06, + "loss": 0.0593, + "step": 24834 + }, + { + "epoch": 2.02, + "learning_rate": 6.50858322468492e-06, + "loss": 0.331, + "step": 24835 + }, + { + "epoch": 2.02, + "learning_rate": 6.508039982616254e-06, + "loss": 0.221, + "step": 24836 + }, + { + "epoch": 2.02, + "learning_rate": 6.5074967405475886e-06, + "loss": 0.3603, + "step": 24837 + }, + { + "epoch": 2.02, + "learning_rate": 6.506953498478923e-06, + "loss": 0.1232, + "step": 24838 + }, + { + "epoch": 2.02, + "learning_rate": 6.506410256410257e-06, + "loss": 0.226, + "step": 24839 + }, + { + "epoch": 2.02, + "learning_rate": 6.505867014341591e-06, + "loss": 0.4385, + "step": 24840 + }, + { + "epoch": 2.02, + "learning_rate": 6.5053237722729255e-06, + "loss": 0.3342, + "step": 24841 + }, + { + "epoch": 2.02, + "learning_rate": 6.50478053020426e-06, + "loss": 0.2437, + "step": 24842 + }, + { + "epoch": 2.02, + "learning_rate": 6.504237288135594e-06, + "loss": 0.2417, + "step": 24843 + }, + { + "epoch": 2.02, + "learning_rate": 6.503694046066928e-06, + "loss": 0.1124, + "step": 24844 + }, + { + "epoch": 2.02, + "learning_rate": 6.503150803998262e-06, + "loss": 0.3063, + "step": 24845 + }, + { + "epoch": 2.02, + "learning_rate": 6.502607561929596e-06, + "loss": 0.3636, + "step": 24846 + }, + { + "epoch": 2.02, + "learning_rate": 6.50206431986093e-06, + "loss": 0.1465, + "step": 24847 + }, + { + "epoch": 2.02, + "learning_rate": 6.501521077792264e-06, + "loss": 0.1604, + "step": 24848 + }, + { + "epoch": 2.02, + "learning_rate": 6.5009778357235985e-06, + "loss": 0.6396, + "step": 24849 + }, + { + "epoch": 2.02, + "learning_rate": 6.500434593654933e-06, + "loss": 0.2443, + "step": 24850 + }, + { + "epoch": 2.03, + "learning_rate": 6.499891351586267e-06, + "loss": 0.258, + "step": 24851 + }, + { + "epoch": 2.03, + "learning_rate": 6.499348109517601e-06, + "loss": 0.0854, + "step": 24852 + }, + { + "epoch": 2.03, + "learning_rate": 6.498804867448935e-06, + "loss": 0.5342, + "step": 24853 + }, + { + "epoch": 2.03, + "learning_rate": 6.49826162538027e-06, + "loss": 0.2409, + "step": 24854 + }, + { + "epoch": 2.03, + "learning_rate": 6.497718383311604e-06, + "loss": 0.2833, + "step": 24855 + }, + { + "epoch": 2.03, + "learning_rate": 6.497175141242938e-06, + "loss": 0.118, + "step": 24856 + }, + { + "epoch": 2.03, + "learning_rate": 6.496631899174272e-06, + "loss": 0.2402, + "step": 24857 + }, + { + "epoch": 2.03, + "learning_rate": 6.4960886571056066e-06, + "loss": 0.2036, + "step": 24858 + }, + { + "epoch": 2.03, + "learning_rate": 6.495545415036942e-06, + "loss": 0.2459, + "step": 24859 + }, + { + "epoch": 2.03, + "learning_rate": 6.495002172968276e-06, + "loss": 0.3207, + "step": 24860 + }, + { + "epoch": 2.03, + "learning_rate": 6.49445893089961e-06, + "loss": 0.1412, + "step": 24861 + }, + { + "epoch": 2.03, + "learning_rate": 6.493915688830944e-06, + "loss": 0.1397, + "step": 24862 + }, + { + "epoch": 2.03, + "learning_rate": 6.4933724467622786e-06, + "loss": 0.4158, + "step": 24863 + }, + { + "epoch": 2.03, + "learning_rate": 6.492829204693613e-06, + "loss": 0.3921, + "step": 24864 + }, + { + "epoch": 2.03, + "learning_rate": 6.492285962624945e-06, + "loss": 0.1149, + "step": 24865 + }, + { + "epoch": 2.03, + "learning_rate": 6.4917427205562796e-06, + "loss": 0.2371, + "step": 24866 + }, + { + "epoch": 2.03, + "learning_rate": 6.491199478487615e-06, + "loss": 0.4487, + "step": 24867 + }, + { + "epoch": 2.03, + "learning_rate": 6.490656236418949e-06, + "loss": 0.059, + "step": 24868 + }, + { + "epoch": 2.03, + "learning_rate": 6.490112994350283e-06, + "loss": 0.1243, + "step": 24869 + }, + { + "epoch": 2.03, + "learning_rate": 6.489569752281617e-06, + "loss": 0.2625, + "step": 24870 + }, + { + "epoch": 2.03, + "learning_rate": 6.4890265102129516e-06, + "loss": 0.1387, + "step": 24871 + }, + { + "epoch": 2.03, + "learning_rate": 6.488483268144286e-06, + "loss": 0.2467, + "step": 24872 + }, + { + "epoch": 2.03, + "learning_rate": 6.48794002607562e-06, + "loss": 0.1784, + "step": 24873 + }, + { + "epoch": 2.03, + "learning_rate": 6.487396784006954e-06, + "loss": 0.5389, + "step": 24874 + }, + { + "epoch": 2.03, + "learning_rate": 6.4868535419382885e-06, + "loss": 0.1223, + "step": 24875 + }, + { + "epoch": 2.03, + "learning_rate": 6.486310299869623e-06, + "loss": 0.2526, + "step": 24876 + }, + { + "epoch": 2.03, + "learning_rate": 6.485767057800957e-06, + "loss": 0.2206, + "step": 24877 + }, + { + "epoch": 2.03, + "learning_rate": 6.485223815732291e-06, + "loss": 0.0646, + "step": 24878 + }, + { + "epoch": 2.03, + "learning_rate": 6.484680573663625e-06, + "loss": 0.2827, + "step": 24879 + }, + { + "epoch": 2.03, + "learning_rate": 6.48413733159496e-06, + "loss": 0.4264, + "step": 24880 + }, + { + "epoch": 2.03, + "learning_rate": 6.483594089526294e-06, + "loss": 0.2944, + "step": 24881 + }, + { + "epoch": 2.03, + "learning_rate": 6.483050847457628e-06, + "loss": 0.1364, + "step": 24882 + }, + { + "epoch": 2.03, + "learning_rate": 6.482507605388962e-06, + "loss": 0.5286, + "step": 24883 + }, + { + "epoch": 2.03, + "learning_rate": 6.481964363320296e-06, + "loss": 0.184, + "step": 24884 + }, + { + "epoch": 2.03, + "learning_rate": 6.48142112125163e-06, + "loss": 0.2715, + "step": 24885 + }, + { + "epoch": 2.03, + "learning_rate": 6.480877879182964e-06, + "loss": 0.3857, + "step": 24886 + }, + { + "epoch": 2.03, + "learning_rate": 6.480334637114298e-06, + "loss": 0.1905, + "step": 24887 + }, + { + "epoch": 2.03, + "learning_rate": 6.479791395045633e-06, + "loss": 0.1287, + "step": 24888 + }, + { + "epoch": 2.03, + "learning_rate": 6.479248152976967e-06, + "loss": 0.153, + "step": 24889 + }, + { + "epoch": 2.03, + "learning_rate": 6.478704910908301e-06, + "loss": 0.301, + "step": 24890 + }, + { + "epoch": 2.03, + "learning_rate": 6.478161668839635e-06, + "loss": 0.2546, + "step": 24891 + }, + { + "epoch": 2.03, + "learning_rate": 6.4776184267709696e-06, + "loss": 0.2172, + "step": 24892 + }, + { + "epoch": 2.03, + "learning_rate": 6.477075184702304e-06, + "loss": 0.2551, + "step": 24893 + }, + { + "epoch": 2.03, + "learning_rate": 6.476531942633638e-06, + "loss": 0.2494, + "step": 24894 + }, + { + "epoch": 2.03, + "learning_rate": 6.475988700564972e-06, + "loss": 0.1094, + "step": 24895 + }, + { + "epoch": 2.03, + "learning_rate": 6.4754454584963065e-06, + "loss": 0.2764, + "step": 24896 + }, + { + "epoch": 2.03, + "learning_rate": 6.474902216427641e-06, + "loss": 0.2787, + "step": 24897 + }, + { + "epoch": 2.03, + "learning_rate": 6.474358974358975e-06, + "loss": 0.1359, + "step": 24898 + }, + { + "epoch": 2.03, + "learning_rate": 6.473815732290309e-06, + "loss": 0.2096, + "step": 24899 + }, + { + "epoch": 2.03, + "learning_rate": 6.473272490221643e-06, + "loss": 0.1586, + "step": 24900 + }, + { + "epoch": 2.03, + "learning_rate": 6.472729248152978e-06, + "loss": 0.0942, + "step": 24901 + }, + { + "epoch": 2.03, + "learning_rate": 6.472186006084312e-06, + "loss": 0.1483, + "step": 24902 + }, + { + "epoch": 2.03, + "learning_rate": 6.471642764015645e-06, + "loss": 0.2012, + "step": 24903 + }, + { + "epoch": 2.03, + "learning_rate": 6.4710995219469795e-06, + "loss": 0.3614, + "step": 24904 + }, + { + "epoch": 2.03, + "learning_rate": 6.470556279878314e-06, + "loss": 0.3045, + "step": 24905 + }, + { + "epoch": 2.03, + "learning_rate": 6.470013037809648e-06, + "loss": 0.5276, + "step": 24906 + }, + { + "epoch": 2.03, + "learning_rate": 6.469469795740982e-06, + "loss": 0.4801, + "step": 24907 + }, + { + "epoch": 2.03, + "learning_rate": 6.468926553672316e-06, + "loss": 0.4573, + "step": 24908 + }, + { + "epoch": 2.03, + "learning_rate": 6.468383311603651e-06, + "loss": 0.346, + "step": 24909 + }, + { + "epoch": 2.03, + "learning_rate": 6.467840069534985e-06, + "loss": 0.3305, + "step": 24910 + }, + { + "epoch": 2.03, + "learning_rate": 6.467296827466319e-06, + "loss": 0.1922, + "step": 24911 + }, + { + "epoch": 2.03, + "learning_rate": 6.466753585397653e-06, + "loss": 0.1957, + "step": 24912 + }, + { + "epoch": 2.03, + "learning_rate": 6.466210343328988e-06, + "loss": 0.0932, + "step": 24913 + }, + { + "epoch": 2.03, + "learning_rate": 6.465667101260323e-06, + "loss": 0.1764, + "step": 24914 + }, + { + "epoch": 2.03, + "learning_rate": 6.465123859191657e-06, + "loss": 0.1135, + "step": 24915 + }, + { + "epoch": 2.03, + "learning_rate": 6.464580617122991e-06, + "loss": 0.0245, + "step": 24916 + }, + { + "epoch": 2.03, + "learning_rate": 6.464037375054325e-06, + "loss": 0.2358, + "step": 24917 + }, + { + "epoch": 2.03, + "learning_rate": 6.4634941329856596e-06, + "loss": 0.2132, + "step": 24918 + }, + { + "epoch": 2.03, + "learning_rate": 6.462950890916994e-06, + "loss": 0.2149, + "step": 24919 + }, + { + "epoch": 2.03, + "learning_rate": 6.462407648848328e-06, + "loss": 0.1824, + "step": 24920 + }, + { + "epoch": 2.03, + "learning_rate": 6.461864406779662e-06, + "loss": 0.1946, + "step": 24921 + }, + { + "epoch": 2.03, + "learning_rate": 6.461321164710996e-06, + "loss": 0.4113, + "step": 24922 + }, + { + "epoch": 2.03, + "learning_rate": 6.46077792264233e-06, + "loss": 0.0874, + "step": 24923 + }, + { + "epoch": 2.03, + "learning_rate": 6.460234680573664e-06, + "loss": 0.1721, + "step": 24924 + }, + { + "epoch": 2.03, + "learning_rate": 6.459691438504998e-06, + "loss": 0.1269, + "step": 24925 + }, + { + "epoch": 2.03, + "learning_rate": 6.4591481964363326e-06, + "loss": 0.2712, + "step": 24926 + }, + { + "epoch": 2.03, + "learning_rate": 6.458604954367667e-06, + "loss": 0.1791, + "step": 24927 + }, + { + "epoch": 2.03, + "learning_rate": 6.458061712299001e-06, + "loss": 0.344, + "step": 24928 + }, + { + "epoch": 2.03, + "learning_rate": 6.457518470230335e-06, + "loss": 0.694, + "step": 24929 + }, + { + "epoch": 2.03, + "learning_rate": 6.4569752281616695e-06, + "loss": 0.1775, + "step": 24930 + }, + { + "epoch": 2.03, + "learning_rate": 6.456431986093004e-06, + "loss": 0.1615, + "step": 24931 + }, + { + "epoch": 2.03, + "learning_rate": 6.455888744024338e-06, + "loss": 0.0527, + "step": 24932 + }, + { + "epoch": 2.03, + "learning_rate": 6.455345501955672e-06, + "loss": 0.1145, + "step": 24933 + }, + { + "epoch": 2.03, + "learning_rate": 6.454802259887006e-06, + "loss": 0.4331, + "step": 24934 + }, + { + "epoch": 2.03, + "learning_rate": 6.454259017818341e-06, + "loss": 0.2653, + "step": 24935 + }, + { + "epoch": 2.03, + "learning_rate": 6.453715775749675e-06, + "loss": 0.1088, + "step": 24936 + }, + { + "epoch": 2.03, + "learning_rate": 6.453172533681009e-06, + "loss": 0.3014, + "step": 24937 + }, + { + "epoch": 2.03, + "learning_rate": 6.452629291612343e-06, + "loss": 0.2044, + "step": 24938 + }, + { + "epoch": 2.03, + "learning_rate": 6.4520860495436775e-06, + "loss": 0.3959, + "step": 24939 + }, + { + "epoch": 2.03, + "learning_rate": 6.451542807475012e-06, + "loss": 0.251, + "step": 24940 + }, + { + "epoch": 2.03, + "learning_rate": 6.450999565406345e-06, + "loss": 0.1624, + "step": 24941 + }, + { + "epoch": 2.03, + "learning_rate": 6.450456323337679e-06, + "loss": 0.2852, + "step": 24942 + }, + { + "epoch": 2.03, + "learning_rate": 6.449913081269014e-06, + "loss": 0.178, + "step": 24943 + }, + { + "epoch": 2.03, + "learning_rate": 6.449369839200348e-06, + "loss": 0.2287, + "step": 24944 + }, + { + "epoch": 2.03, + "learning_rate": 6.448826597131682e-06, + "loss": 0.1896, + "step": 24945 + }, + { + "epoch": 2.03, + "learning_rate": 6.448283355063016e-06, + "loss": 0.2834, + "step": 24946 + }, + { + "epoch": 2.03, + "learning_rate": 6.4477401129943505e-06, + "loss": 0.3735, + "step": 24947 + }, + { + "epoch": 2.03, + "learning_rate": 6.447196870925685e-06, + "loss": 0.1093, + "step": 24948 + }, + { + "epoch": 2.03, + "learning_rate": 6.446653628857019e-06, + "loss": 0.4087, + "step": 24949 + }, + { + "epoch": 2.03, + "learning_rate": 6.446110386788353e-06, + "loss": 0.0664, + "step": 24950 + }, + { + "epoch": 2.03, + "learning_rate": 6.4455671447196875e-06, + "loss": 0.2555, + "step": 24951 + }, + { + "epoch": 2.03, + "learning_rate": 6.445023902651022e-06, + "loss": 0.0976, + "step": 24952 + }, + { + "epoch": 2.03, + "learning_rate": 6.444480660582356e-06, + "loss": 0.2315, + "step": 24953 + }, + { + "epoch": 2.03, + "learning_rate": 6.44393741851369e-06, + "loss": 0.1696, + "step": 24954 + }, + { + "epoch": 2.03, + "learning_rate": 6.443394176445024e-06, + "loss": 0.1158, + "step": 24955 + }, + { + "epoch": 2.03, + "learning_rate": 6.442850934376359e-06, + "loss": 0.315, + "step": 24956 + }, + { + "epoch": 2.03, + "learning_rate": 6.442307692307693e-06, + "loss": 0.2756, + "step": 24957 + }, + { + "epoch": 2.03, + "learning_rate": 6.441764450239028e-06, + "loss": 0.2177, + "step": 24958 + }, + { + "epoch": 2.03, + "learning_rate": 6.441221208170362e-06, + "loss": 0.0281, + "step": 24959 + }, + { + "epoch": 2.03, + "learning_rate": 6.440677966101695e-06, + "loss": 0.3338, + "step": 24960 + }, + { + "epoch": 2.03, + "learning_rate": 6.440134724033029e-06, + "loss": 0.3384, + "step": 24961 + }, + { + "epoch": 2.03, + "learning_rate": 6.439591481964363e-06, + "loss": 0.3263, + "step": 24962 + }, + { + "epoch": 2.03, + "learning_rate": 6.439048239895697e-06, + "loss": 0.1757, + "step": 24963 + }, + { + "epoch": 2.03, + "learning_rate": 6.438504997827032e-06, + "loss": 0.2298, + "step": 24964 + }, + { + "epoch": 2.03, + "learning_rate": 6.437961755758366e-06, + "loss": 0.5602, + "step": 24965 + }, + { + "epoch": 2.03, + "learning_rate": 6.4374185136897e-06, + "loss": 0.29, + "step": 24966 + }, + { + "epoch": 2.03, + "learning_rate": 6.436875271621035e-06, + "loss": 0.5258, + "step": 24967 + }, + { + "epoch": 2.03, + "learning_rate": 6.436332029552369e-06, + "loss": 0.2541, + "step": 24968 + }, + { + "epoch": 2.03, + "learning_rate": 6.435788787483704e-06, + "loss": 0.1653, + "step": 24969 + }, + { + "epoch": 2.03, + "learning_rate": 6.435245545415038e-06, + "loss": 0.3215, + "step": 24970 + }, + { + "epoch": 2.03, + "learning_rate": 6.434702303346372e-06, + "loss": 0.228, + "step": 24971 + }, + { + "epoch": 2.03, + "learning_rate": 6.434159061277706e-06, + "loss": 0.0957, + "step": 24972 + }, + { + "epoch": 2.03, + "learning_rate": 6.4336158192090405e-06, + "loss": 0.489, + "step": 24973 + }, + { + "epoch": 2.04, + "learning_rate": 6.433072577140375e-06, + "loss": 0.1683, + "step": 24974 + }, + { + "epoch": 2.04, + "learning_rate": 6.432529335071709e-06, + "loss": 0.218, + "step": 24975 + }, + { + "epoch": 2.04, + "learning_rate": 6.431986093003043e-06, + "loss": 0.1753, + "step": 24976 + }, + { + "epoch": 2.04, + "learning_rate": 6.4314428509343775e-06, + "loss": 0.1785, + "step": 24977 + }, + { + "epoch": 2.04, + "learning_rate": 6.430899608865712e-06, + "loss": 0.1228, + "step": 24978 + }, + { + "epoch": 2.04, + "learning_rate": 6.430356366797045e-06, + "loss": 0.2228, + "step": 24979 + }, + { + "epoch": 2.04, + "learning_rate": 6.429813124728379e-06, + "loss": 0.3583, + "step": 24980 + }, + { + "epoch": 2.04, + "learning_rate": 6.4292698826597135e-06, + "loss": 0.4529, + "step": 24981 + }, + { + "epoch": 2.04, + "learning_rate": 6.428726640591048e-06, + "loss": 0.057, + "step": 24982 + }, + { + "epoch": 2.04, + "learning_rate": 6.428183398522382e-06, + "loss": 0.3691, + "step": 24983 + }, + { + "epoch": 2.04, + "learning_rate": 6.427640156453716e-06, + "loss": 0.2351, + "step": 24984 + }, + { + "epoch": 2.04, + "learning_rate": 6.4270969143850505e-06, + "loss": 0.2343, + "step": 24985 + }, + { + "epoch": 2.04, + "learning_rate": 6.426553672316385e-06, + "loss": 0.2198, + "step": 24986 + }, + { + "epoch": 2.04, + "learning_rate": 6.426010430247719e-06, + "loss": 0.2291, + "step": 24987 + }, + { + "epoch": 2.04, + "learning_rate": 6.425467188179053e-06, + "loss": 0.3844, + "step": 24988 + }, + { + "epoch": 2.04, + "learning_rate": 6.424923946110387e-06, + "loss": 0.1432, + "step": 24989 + }, + { + "epoch": 2.04, + "learning_rate": 6.424380704041722e-06, + "loss": 0.1837, + "step": 24990 + }, + { + "epoch": 2.04, + "learning_rate": 6.423837461973056e-06, + "loss": 0.5663, + "step": 24991 + }, + { + "epoch": 2.04, + "learning_rate": 6.42329421990439e-06, + "loss": 0.3096, + "step": 24992 + }, + { + "epoch": 2.04, + "learning_rate": 6.422750977835724e-06, + "loss": 0.2663, + "step": 24993 + }, + { + "epoch": 2.04, + "learning_rate": 6.4222077357670585e-06, + "loss": 0.2025, + "step": 24994 + }, + { + "epoch": 2.04, + "learning_rate": 6.421664493698393e-06, + "loss": 0.095, + "step": 24995 + }, + { + "epoch": 2.04, + "learning_rate": 6.421121251629727e-06, + "loss": 0.1686, + "step": 24996 + }, + { + "epoch": 2.04, + "learning_rate": 6.420578009561061e-06, + "loss": 0.2109, + "step": 24997 + }, + { + "epoch": 2.04, + "learning_rate": 6.420034767492395e-06, + "loss": 0.2157, + "step": 24998 + }, + { + "epoch": 2.04, + "learning_rate": 6.419491525423729e-06, + "loss": 0.264, + "step": 24999 + }, + { + "epoch": 2.04, + "learning_rate": 6.418948283355063e-06, + "loss": 0.3329, + "step": 25000 + }, + { + "epoch": 2.04, + "eval_accuracy": 0.8395313295975547, + "eval_loss": 0.48388317227363586, + "eval_runtime": 22.2075, + "eval_samples_per_second": 441.969, + "eval_steps_per_second": 3.467, + "step": 25000 + }, + { + "epoch": 2.04, + "learning_rate": 6.418405041286397e-06, + "loss": 0.4439, + "step": 25001 + }, + { + "epoch": 2.04, + "learning_rate": 6.4178617992177315e-06, + "loss": 0.3222, + "step": 25002 + }, + { + "epoch": 2.04, + "learning_rate": 6.417318557149066e-06, + "loss": 0.2362, + "step": 25003 + }, + { + "epoch": 2.04, + "learning_rate": 6.4167753150804e-06, + "loss": 0.341, + "step": 25004 + }, + { + "epoch": 2.04, + "learning_rate": 6.416232073011734e-06, + "loss": 0.3079, + "step": 25005 + }, + { + "epoch": 2.04, + "learning_rate": 6.4156888309430685e-06, + "loss": 0.239, + "step": 25006 + }, + { + "epoch": 2.04, + "learning_rate": 6.415145588874403e-06, + "loss": 0.1095, + "step": 25007 + }, + { + "epoch": 2.04, + "learning_rate": 6.414602346805737e-06, + "loss": 0.5467, + "step": 25008 + }, + { + "epoch": 2.04, + "learning_rate": 6.414059104737071e-06, + "loss": 0.3408, + "step": 25009 + }, + { + "epoch": 2.04, + "learning_rate": 6.413515862668405e-06, + "loss": 0.2311, + "step": 25010 + }, + { + "epoch": 2.04, + "learning_rate": 6.41297262059974e-06, + "loss": 0.246, + "step": 25011 + }, + { + "epoch": 2.04, + "learning_rate": 6.412429378531075e-06, + "loss": 0.2584, + "step": 25012 + }, + { + "epoch": 2.04, + "learning_rate": 6.411886136462409e-06, + "loss": 0.1571, + "step": 25013 + }, + { + "epoch": 2.04, + "learning_rate": 6.411342894393743e-06, + "loss": 0.2372, + "step": 25014 + }, + { + "epoch": 2.04, + "learning_rate": 6.410799652325077e-06, + "loss": 0.1929, + "step": 25015 + }, + { + "epoch": 2.04, + "learning_rate": 6.410256410256412e-06, + "loss": 0.3996, + "step": 25016 + }, + { + "epoch": 2.04, + "learning_rate": 6.409713168187744e-06, + "loss": 0.0896, + "step": 25017 + }, + { + "epoch": 2.04, + "learning_rate": 6.409169926119078e-06, + "loss": 0.0516, + "step": 25018 + }, + { + "epoch": 2.04, + "learning_rate": 6.408626684050413e-06, + "loss": 0.2434, + "step": 25019 + }, + { + "epoch": 2.04, + "learning_rate": 6.408083441981747e-06, + "loss": 0.1515, + "step": 25020 + }, + { + "epoch": 2.04, + "learning_rate": 6.407540199913082e-06, + "loss": 0.2321, + "step": 25021 + }, + { + "epoch": 2.04, + "learning_rate": 6.406996957844416e-06, + "loss": 0.391, + "step": 25022 + }, + { + "epoch": 2.04, + "learning_rate": 6.40645371577575e-06, + "loss": 0.3101, + "step": 25023 + }, + { + "epoch": 2.04, + "learning_rate": 6.405910473707085e-06, + "loss": 0.0528, + "step": 25024 + }, + { + "epoch": 2.04, + "learning_rate": 6.405367231638419e-06, + "loss": 0.2713, + "step": 25025 + }, + { + "epoch": 2.04, + "learning_rate": 6.404823989569753e-06, + "loss": 0.3676, + "step": 25026 + }, + { + "epoch": 2.04, + "learning_rate": 6.404280747501087e-06, + "loss": 0.1749, + "step": 25027 + }, + { + "epoch": 2.04, + "learning_rate": 6.4037375054324215e-06, + "loss": 0.1474, + "step": 25028 + }, + { + "epoch": 2.04, + "learning_rate": 6.403194263363756e-06, + "loss": 0.2497, + "step": 25029 + }, + { + "epoch": 2.04, + "learning_rate": 6.40265102129509e-06, + "loss": 0.3723, + "step": 25030 + }, + { + "epoch": 2.04, + "learning_rate": 6.402107779226424e-06, + "loss": 0.0606, + "step": 25031 + }, + { + "epoch": 2.04, + "learning_rate": 6.4015645371577584e-06, + "loss": 0.3387, + "step": 25032 + }, + { + "epoch": 2.04, + "learning_rate": 6.401021295089093e-06, + "loss": 0.3352, + "step": 25033 + }, + { + "epoch": 2.04, + "learning_rate": 6.400478053020427e-06, + "loss": 0.2282, + "step": 25034 + }, + { + "epoch": 2.04, + "learning_rate": 6.399934810951761e-06, + "loss": 0.2682, + "step": 25035 + }, + { + "epoch": 2.04, + "learning_rate": 6.3993915688830945e-06, + "loss": 0.2935, + "step": 25036 + }, + { + "epoch": 2.04, + "learning_rate": 6.398848326814429e-06, + "loss": 0.1704, + "step": 25037 + }, + { + "epoch": 2.04, + "learning_rate": 6.398305084745763e-06, + "loss": 0.1977, + "step": 25038 + }, + { + "epoch": 2.04, + "learning_rate": 6.397761842677097e-06, + "loss": 0.2067, + "step": 25039 + }, + { + "epoch": 2.04, + "learning_rate": 6.3972186006084314e-06, + "loss": 0.1333, + "step": 25040 + }, + { + "epoch": 2.04, + "learning_rate": 6.396675358539766e-06, + "loss": 0.1201, + "step": 25041 + }, + { + "epoch": 2.04, + "learning_rate": 6.3961321164711e-06, + "loss": 0.2187, + "step": 25042 + }, + { + "epoch": 2.04, + "learning_rate": 6.395588874402434e-06, + "loss": 0.3768, + "step": 25043 + }, + { + "epoch": 2.04, + "learning_rate": 6.395045632333768e-06, + "loss": 0.3759, + "step": 25044 + }, + { + "epoch": 2.04, + "learning_rate": 6.394502390265103e-06, + "loss": 0.23, + "step": 25045 + }, + { + "epoch": 2.04, + "learning_rate": 6.393959148196437e-06, + "loss": 0.3108, + "step": 25046 + }, + { + "epoch": 2.04, + "learning_rate": 6.393415906127771e-06, + "loss": 0.4847, + "step": 25047 + }, + { + "epoch": 2.04, + "learning_rate": 6.392872664059105e-06, + "loss": 0.2429, + "step": 25048 + }, + { + "epoch": 2.04, + "learning_rate": 6.3923294219904395e-06, + "loss": 0.1554, + "step": 25049 + }, + { + "epoch": 2.04, + "learning_rate": 6.391786179921774e-06, + "loss": 0.0695, + "step": 25050 + }, + { + "epoch": 2.04, + "learning_rate": 6.391242937853108e-06, + "loss": 0.3323, + "step": 25051 + }, + { + "epoch": 2.04, + "learning_rate": 6.390699695784442e-06, + "loss": 0.3032, + "step": 25052 + }, + { + "epoch": 2.04, + "learning_rate": 6.3901564537157764e-06, + "loss": 0.1097, + "step": 25053 + }, + { + "epoch": 2.04, + "learning_rate": 6.389613211647111e-06, + "loss": 0.3721, + "step": 25054 + }, + { + "epoch": 2.04, + "learning_rate": 6.389069969578444e-06, + "loss": 0.0987, + "step": 25055 + }, + { + "epoch": 2.04, + "learning_rate": 6.388526727509778e-06, + "loss": 0.1056, + "step": 25056 + }, + { + "epoch": 2.04, + "learning_rate": 6.3879834854411125e-06, + "loss": 0.0856, + "step": 25057 + }, + { + "epoch": 2.04, + "learning_rate": 6.387440243372447e-06, + "loss": 0.3295, + "step": 25058 + }, + { + "epoch": 2.04, + "learning_rate": 6.386897001303781e-06, + "loss": 0.0884, + "step": 25059 + }, + { + "epoch": 2.04, + "learning_rate": 6.386353759235115e-06, + "loss": 0.4278, + "step": 25060 + }, + { + "epoch": 2.04, + "learning_rate": 6.3858105171664494e-06, + "loss": 0.1214, + "step": 25061 + }, + { + "epoch": 2.04, + "learning_rate": 6.385267275097784e-06, + "loss": 0.5389, + "step": 25062 + }, + { + "epoch": 2.04, + "learning_rate": 6.384724033029118e-06, + "loss": 0.3412, + "step": 25063 + }, + { + "epoch": 2.04, + "learning_rate": 6.384180790960452e-06, + "loss": 0.1248, + "step": 25064 + }, + { + "epoch": 2.04, + "learning_rate": 6.383637548891786e-06, + "loss": 0.0527, + "step": 25065 + }, + { + "epoch": 2.04, + "learning_rate": 6.3830943068231214e-06, + "loss": 0.307, + "step": 25066 + }, + { + "epoch": 2.04, + "learning_rate": 6.382551064754456e-06, + "loss": 0.1227, + "step": 25067 + }, + { + "epoch": 2.04, + "learning_rate": 6.38200782268579e-06, + "loss": 0.162, + "step": 25068 + }, + { + "epoch": 2.04, + "learning_rate": 6.381464580617124e-06, + "loss": 0.2127, + "step": 25069 + }, + { + "epoch": 2.04, + "learning_rate": 6.380921338548458e-06, + "loss": 0.2008, + "step": 25070 + }, + { + "epoch": 2.04, + "learning_rate": 6.380378096479793e-06, + "loss": 0.1423, + "step": 25071 + }, + { + "epoch": 2.04, + "learning_rate": 6.379834854411127e-06, + "loss": 0.0364, + "step": 25072 + }, + { + "epoch": 2.04, + "learning_rate": 6.379291612342461e-06, + "loss": 0.2381, + "step": 25073 + }, + { + "epoch": 2.04, + "learning_rate": 6.378748370273794e-06, + "loss": 0.265, + "step": 25074 + }, + { + "epoch": 2.04, + "learning_rate": 6.378205128205129e-06, + "loss": 0.1815, + "step": 25075 + }, + { + "epoch": 2.04, + "learning_rate": 6.377661886136463e-06, + "loss": 0.3221, + "step": 25076 + }, + { + "epoch": 2.04, + "learning_rate": 6.377118644067797e-06, + "loss": 0.0774, + "step": 25077 + }, + { + "epoch": 2.04, + "learning_rate": 6.376575401999131e-06, + "loss": 0.1599, + "step": 25078 + }, + { + "epoch": 2.04, + "learning_rate": 6.376032159930466e-06, + "loss": 0.0967, + "step": 25079 + }, + { + "epoch": 2.04, + "learning_rate": 6.3754889178618e-06, + "loss": 0.1325, + "step": 25080 + }, + { + "epoch": 2.04, + "learning_rate": 6.374945675793134e-06, + "loss": 0.1721, + "step": 25081 + }, + { + "epoch": 2.04, + "learning_rate": 6.374402433724468e-06, + "loss": 0.3133, + "step": 25082 + }, + { + "epoch": 2.04, + "learning_rate": 6.3738591916558025e-06, + "loss": 0.2591, + "step": 25083 + }, + { + "epoch": 2.04, + "learning_rate": 6.373315949587137e-06, + "loss": 0.3593, + "step": 25084 + }, + { + "epoch": 2.04, + "learning_rate": 6.372772707518471e-06, + "loss": 0.1325, + "step": 25085 + }, + { + "epoch": 2.04, + "learning_rate": 6.372229465449805e-06, + "loss": 0.0967, + "step": 25086 + }, + { + "epoch": 2.04, + "learning_rate": 6.3716862233811394e-06, + "loss": 0.0762, + "step": 25087 + }, + { + "epoch": 2.04, + "learning_rate": 6.371142981312474e-06, + "loss": 0.2466, + "step": 25088 + }, + { + "epoch": 2.04, + "learning_rate": 6.370599739243808e-06, + "loss": 0.2924, + "step": 25089 + }, + { + "epoch": 2.04, + "learning_rate": 6.370056497175142e-06, + "loss": 0.3336, + "step": 25090 + }, + { + "epoch": 2.04, + "learning_rate": 6.369513255106476e-06, + "loss": 0.1126, + "step": 25091 + }, + { + "epoch": 2.04, + "learning_rate": 6.368970013037811e-06, + "loss": 0.2116, + "step": 25092 + }, + { + "epoch": 2.04, + "learning_rate": 6.368426770969144e-06, + "loss": 0.1431, + "step": 25093 + }, + { + "epoch": 2.04, + "learning_rate": 6.367883528900478e-06, + "loss": 0.2647, + "step": 25094 + }, + { + "epoch": 2.04, + "learning_rate": 6.3673402868318124e-06, + "loss": 0.0826, + "step": 25095 + }, + { + "epoch": 2.04, + "learning_rate": 6.366797044763147e-06, + "loss": 0.1282, + "step": 25096 + }, + { + "epoch": 2.05, + "learning_rate": 6.366253802694481e-06, + "loss": 0.2565, + "step": 25097 + }, + { + "epoch": 2.05, + "learning_rate": 6.365710560625815e-06, + "loss": 0.2479, + "step": 25098 + }, + { + "epoch": 2.05, + "learning_rate": 6.365167318557149e-06, + "loss": 0.1088, + "step": 25099 + }, + { + "epoch": 2.05, + "learning_rate": 6.364624076488484e-06, + "loss": 0.12, + "step": 25100 + }, + { + "epoch": 2.05, + "learning_rate": 6.364080834419818e-06, + "loss": 0.2957, + "step": 25101 + }, + { + "epoch": 2.05, + "learning_rate": 6.363537592351152e-06, + "loss": 0.07, + "step": 25102 + }, + { + "epoch": 2.05, + "learning_rate": 6.362994350282486e-06, + "loss": 0.3076, + "step": 25103 + }, + { + "epoch": 2.05, + "learning_rate": 6.3624511082138205e-06, + "loss": 0.1729, + "step": 25104 + }, + { + "epoch": 2.05, + "learning_rate": 6.361907866145155e-06, + "loss": 0.1154, + "step": 25105 + }, + { + "epoch": 2.05, + "learning_rate": 6.361364624076489e-06, + "loss": 0.2438, + "step": 25106 + }, + { + "epoch": 2.05, + "learning_rate": 6.360821382007823e-06, + "loss": 0.2373, + "step": 25107 + }, + { + "epoch": 2.05, + "learning_rate": 6.3602781399391574e-06, + "loss": 0.2373, + "step": 25108 + }, + { + "epoch": 2.05, + "learning_rate": 6.359734897870492e-06, + "loss": 0.1887, + "step": 25109 + }, + { + "epoch": 2.05, + "learning_rate": 6.359191655801826e-06, + "loss": 0.4154, + "step": 25110 + }, + { + "epoch": 2.05, + "learning_rate": 6.358648413733161e-06, + "loss": 0.2202, + "step": 25111 + }, + { + "epoch": 2.05, + "learning_rate": 6.3581051716644935e-06, + "loss": 0.7111, + "step": 25112 + }, + { + "epoch": 2.05, + "learning_rate": 6.357561929595828e-06, + "loss": 0.0918, + "step": 25113 + }, + { + "epoch": 2.05, + "learning_rate": 6.357018687527162e-06, + "loss": 0.0885, + "step": 25114 + }, + { + "epoch": 2.05, + "learning_rate": 6.356475445458496e-06, + "loss": 0.1219, + "step": 25115 + }, + { + "epoch": 2.05, + "learning_rate": 6.3559322033898304e-06, + "loss": 0.1368, + "step": 25116 + }, + { + "epoch": 2.05, + "learning_rate": 6.355388961321165e-06, + "loss": 0.3194, + "step": 25117 + }, + { + "epoch": 2.05, + "learning_rate": 6.354845719252499e-06, + "loss": 0.4391, + "step": 25118 + }, + { + "epoch": 2.05, + "learning_rate": 6.354302477183833e-06, + "loss": 0.3683, + "step": 25119 + }, + { + "epoch": 2.05, + "learning_rate": 6.353759235115168e-06, + "loss": 0.2486, + "step": 25120 + }, + { + "epoch": 2.05, + "learning_rate": 6.3532159930465024e-06, + "loss": 0.3362, + "step": 25121 + }, + { + "epoch": 2.05, + "learning_rate": 6.352672750977837e-06, + "loss": 0.3312, + "step": 25122 + }, + { + "epoch": 2.05, + "learning_rate": 6.352129508909171e-06, + "loss": 0.1466, + "step": 25123 + }, + { + "epoch": 2.05, + "learning_rate": 6.351586266840505e-06, + "loss": 0.3057, + "step": 25124 + }, + { + "epoch": 2.05, + "learning_rate": 6.351043024771839e-06, + "loss": 0.2335, + "step": 25125 + }, + { + "epoch": 2.05, + "learning_rate": 6.350499782703174e-06, + "loss": 0.1932, + "step": 25126 + }, + { + "epoch": 2.05, + "learning_rate": 6.349956540634508e-06, + "loss": 0.2418, + "step": 25127 + }, + { + "epoch": 2.05, + "learning_rate": 6.349413298565842e-06, + "loss": 0.1448, + "step": 25128 + }, + { + "epoch": 2.05, + "learning_rate": 6.348870056497176e-06, + "loss": 0.3105, + "step": 25129 + }, + { + "epoch": 2.05, + "learning_rate": 6.3483268144285105e-06, + "loss": 0.2939, + "step": 25130 + }, + { + "epoch": 2.05, + "learning_rate": 6.347783572359844e-06, + "loss": 0.2801, + "step": 25131 + }, + { + "epoch": 2.05, + "learning_rate": 6.347240330291178e-06, + "loss": 0.1027, + "step": 25132 + }, + { + "epoch": 2.05, + "learning_rate": 6.346697088222512e-06, + "loss": 0.059, + "step": 25133 + }, + { + "epoch": 2.05, + "learning_rate": 6.3461538461538466e-06, + "loss": 0.4291, + "step": 25134 + }, + { + "epoch": 2.05, + "learning_rate": 6.345610604085181e-06, + "loss": 0.1119, + "step": 25135 + }, + { + "epoch": 2.05, + "learning_rate": 6.345067362016515e-06, + "loss": 0.2346, + "step": 25136 + }, + { + "epoch": 2.05, + "learning_rate": 6.344524119947849e-06, + "loss": 0.458, + "step": 25137 + }, + { + "epoch": 2.05, + "learning_rate": 6.3439808778791835e-06, + "loss": 0.0412, + "step": 25138 + }, + { + "epoch": 2.05, + "learning_rate": 6.343437635810518e-06, + "loss": 0.1565, + "step": 25139 + }, + { + "epoch": 2.05, + "learning_rate": 6.342894393741852e-06, + "loss": 0.2299, + "step": 25140 + }, + { + "epoch": 2.05, + "learning_rate": 6.342351151673186e-06, + "loss": 0.2114, + "step": 25141 + }, + { + "epoch": 2.05, + "learning_rate": 6.34180790960452e-06, + "loss": 0.1038, + "step": 25142 + }, + { + "epoch": 2.05, + "learning_rate": 6.341264667535855e-06, + "loss": 0.4346, + "step": 25143 + }, + { + "epoch": 2.05, + "learning_rate": 6.340721425467189e-06, + "loss": 0.0808, + "step": 25144 + }, + { + "epoch": 2.05, + "learning_rate": 6.340178183398523e-06, + "loss": 0.2864, + "step": 25145 + }, + { + "epoch": 2.05, + "learning_rate": 6.339634941329857e-06, + "loss": 0.1277, + "step": 25146 + }, + { + "epoch": 2.05, + "learning_rate": 6.3390916992611916e-06, + "loss": 0.1689, + "step": 25147 + }, + { + "epoch": 2.05, + "learning_rate": 6.338548457192526e-06, + "loss": 0.2076, + "step": 25148 + }, + { + "epoch": 2.05, + "learning_rate": 6.33800521512386e-06, + "loss": 0.0979, + "step": 25149 + }, + { + "epoch": 2.05, + "learning_rate": 6.337461973055193e-06, + "loss": 0.2287, + "step": 25150 + }, + { + "epoch": 2.05, + "learning_rate": 6.336918730986528e-06, + "loss": 0.1365, + "step": 25151 + }, + { + "epoch": 2.05, + "learning_rate": 6.336375488917862e-06, + "loss": 0.2306, + "step": 25152 + }, + { + "epoch": 2.05, + "learning_rate": 6.335832246849196e-06, + "loss": 0.3336, + "step": 25153 + }, + { + "epoch": 2.05, + "learning_rate": 6.33528900478053e-06, + "loss": 0.3405, + "step": 25154 + }, + { + "epoch": 2.05, + "learning_rate": 6.3347457627118646e-06, + "loss": 0.1278, + "step": 25155 + }, + { + "epoch": 2.05, + "learning_rate": 6.334202520643199e-06, + "loss": 0.1572, + "step": 25156 + }, + { + "epoch": 2.05, + "learning_rate": 6.333659278574533e-06, + "loss": 0.436, + "step": 25157 + }, + { + "epoch": 2.05, + "learning_rate": 6.333116036505867e-06, + "loss": 0.122, + "step": 25158 + }, + { + "epoch": 2.05, + "learning_rate": 6.3325727944372015e-06, + "loss": 0.2109, + "step": 25159 + }, + { + "epoch": 2.05, + "learning_rate": 6.332029552368536e-06, + "loss": 0.2597, + "step": 25160 + }, + { + "epoch": 2.05, + "learning_rate": 6.33148631029987e-06, + "loss": 0.1992, + "step": 25161 + }, + { + "epoch": 2.05, + "learning_rate": 6.330943068231204e-06, + "loss": 0.2464, + "step": 25162 + }, + { + "epoch": 2.05, + "learning_rate": 6.330399826162538e-06, + "loss": 0.2342, + "step": 25163 + }, + { + "epoch": 2.05, + "learning_rate": 6.329856584093873e-06, + "loss": 0.2473, + "step": 25164 + }, + { + "epoch": 2.05, + "learning_rate": 6.329313342025208e-06, + "loss": 0.187, + "step": 25165 + }, + { + "epoch": 2.05, + "learning_rate": 6.328770099956542e-06, + "loss": 0.1057, + "step": 25166 + }, + { + "epoch": 2.05, + "learning_rate": 6.328226857887876e-06, + "loss": 0.2652, + "step": 25167 + }, + { + "epoch": 2.05, + "learning_rate": 6.32768361581921e-06, + "loss": 0.2856, + "step": 25168 + }, + { + "epoch": 2.05, + "learning_rate": 6.327140373750543e-06, + "loss": 0.428, + "step": 25169 + }, + { + "epoch": 2.05, + "learning_rate": 6.326597131681877e-06, + "loss": 0.2393, + "step": 25170 + }, + { + "epoch": 2.05, + "learning_rate": 6.326053889613211e-06, + "loss": 0.3968, + "step": 25171 + }, + { + "epoch": 2.05, + "learning_rate": 6.325510647544546e-06, + "loss": 0.1702, + "step": 25172 + }, + { + "epoch": 2.05, + "learning_rate": 6.32496740547588e-06, + "loss": 0.2382, + "step": 25173 + }, + { + "epoch": 2.05, + "learning_rate": 6.324424163407215e-06, + "loss": 0.2074, + "step": 25174 + }, + { + "epoch": 2.05, + "learning_rate": 6.323880921338549e-06, + "loss": 0.1301, + "step": 25175 + }, + { + "epoch": 2.05, + "learning_rate": 6.323337679269883e-06, + "loss": 0.2571, + "step": 25176 + }, + { + "epoch": 2.05, + "learning_rate": 6.322794437201218e-06, + "loss": 0.1195, + "step": 25177 + }, + { + "epoch": 2.05, + "learning_rate": 6.322251195132552e-06, + "loss": 0.2, + "step": 25178 + }, + { + "epoch": 2.05, + "learning_rate": 6.321707953063886e-06, + "loss": 0.1817, + "step": 25179 + }, + { + "epoch": 2.05, + "learning_rate": 6.32116471099522e-06, + "loss": 0.1742, + "step": 25180 + }, + { + "epoch": 2.05, + "learning_rate": 6.3206214689265546e-06, + "loss": 0.2117, + "step": 25181 + }, + { + "epoch": 2.05, + "learning_rate": 6.320078226857889e-06, + "loss": 0.0864, + "step": 25182 + }, + { + "epoch": 2.05, + "learning_rate": 6.319534984789223e-06, + "loss": 0.1779, + "step": 25183 + }, + { + "epoch": 2.05, + "learning_rate": 6.318991742720557e-06, + "loss": 0.435, + "step": 25184 + }, + { + "epoch": 2.05, + "learning_rate": 6.3184485006518915e-06, + "loss": 0.222, + "step": 25185 + }, + { + "epoch": 2.05, + "learning_rate": 6.317905258583226e-06, + "loss": 0.2962, + "step": 25186 + }, + { + "epoch": 2.05, + "learning_rate": 6.31736201651456e-06, + "loss": 0.3221, + "step": 25187 + }, + { + "epoch": 2.05, + "learning_rate": 6.316818774445893e-06, + "loss": 0.1098, + "step": 25188 + }, + { + "epoch": 2.05, + "learning_rate": 6.3162755323772276e-06, + "loss": 0.1678, + "step": 25189 + }, + { + "epoch": 2.05, + "learning_rate": 6.315732290308562e-06, + "loss": 0.2547, + "step": 25190 + }, + { + "epoch": 2.05, + "learning_rate": 6.315189048239896e-06, + "loss": 0.1944, + "step": 25191 + }, + { + "epoch": 2.05, + "learning_rate": 6.31464580617123e-06, + "loss": 0.2244, + "step": 25192 + }, + { + "epoch": 2.05, + "learning_rate": 6.3141025641025645e-06, + "loss": 0.1231, + "step": 25193 + }, + { + "epoch": 2.05, + "learning_rate": 6.313559322033899e-06, + "loss": 0.2076, + "step": 25194 + }, + { + "epoch": 2.05, + "learning_rate": 6.313016079965233e-06, + "loss": 0.3672, + "step": 25195 + }, + { + "epoch": 2.05, + "learning_rate": 6.312472837896567e-06, + "loss": 0.3618, + "step": 25196 + }, + { + "epoch": 2.05, + "learning_rate": 6.311929595827901e-06, + "loss": 0.2899, + "step": 25197 + }, + { + "epoch": 2.05, + "learning_rate": 6.311386353759236e-06, + "loss": 0.0968, + "step": 25198 + }, + { + "epoch": 2.05, + "learning_rate": 6.31084311169057e-06, + "loss": 0.4511, + "step": 25199 + }, + { + "epoch": 2.05, + "learning_rate": 6.310299869621904e-06, + "loss": 0.28, + "step": 25200 + }, + { + "epoch": 2.05, + "learning_rate": 6.309756627553238e-06, + "loss": 0.3837, + "step": 25201 + }, + { + "epoch": 2.05, + "learning_rate": 6.3092133854845726e-06, + "loss": 0.4086, + "step": 25202 + }, + { + "epoch": 2.05, + "learning_rate": 6.308670143415907e-06, + "loss": 0.2435, + "step": 25203 + }, + { + "epoch": 2.05, + "learning_rate": 6.308126901347241e-06, + "loss": 0.2452, + "step": 25204 + }, + { + "epoch": 2.05, + "learning_rate": 6.307583659278575e-06, + "loss": 0.0643, + "step": 25205 + }, + { + "epoch": 2.05, + "learning_rate": 6.3070404172099095e-06, + "loss": 0.3962, + "step": 25206 + }, + { + "epoch": 2.05, + "learning_rate": 6.306497175141243e-06, + "loss": 0.1434, + "step": 25207 + }, + { + "epoch": 2.05, + "learning_rate": 6.305953933072577e-06, + "loss": 0.1573, + "step": 25208 + }, + { + "epoch": 2.05, + "learning_rate": 6.305410691003911e-06, + "loss": 0.0926, + "step": 25209 + }, + { + "epoch": 2.05, + "learning_rate": 6.3048674489352456e-06, + "loss": 0.0852, + "step": 25210 + }, + { + "epoch": 2.05, + "learning_rate": 6.30432420686658e-06, + "loss": 0.1472, + "step": 25211 + }, + { + "epoch": 2.05, + "learning_rate": 6.303780964797914e-06, + "loss": 0.3102, + "step": 25212 + }, + { + "epoch": 2.05, + "learning_rate": 6.303237722729248e-06, + "loss": 0.0505, + "step": 25213 + }, + { + "epoch": 2.05, + "learning_rate": 6.3026944806605825e-06, + "loss": 0.3755, + "step": 25214 + }, + { + "epoch": 2.05, + "learning_rate": 6.302151238591917e-06, + "loss": 0.1589, + "step": 25215 + }, + { + "epoch": 2.05, + "learning_rate": 6.301607996523251e-06, + "loss": 0.3009, + "step": 25216 + }, + { + "epoch": 2.05, + "learning_rate": 6.301064754454585e-06, + "loss": 0.157, + "step": 25217 + }, + { + "epoch": 2.05, + "learning_rate": 6.300521512385919e-06, + "loss": 0.0883, + "step": 25218 + }, + { + "epoch": 2.06, + "learning_rate": 6.2999782703172545e-06, + "loss": 0.1456, + "step": 25219 + }, + { + "epoch": 2.06, + "learning_rate": 6.299435028248589e-06, + "loss": 0.4233, + "step": 25220 + }, + { + "epoch": 2.06, + "learning_rate": 6.298891786179923e-06, + "loss": 0.1904, + "step": 25221 + }, + { + "epoch": 2.06, + "learning_rate": 6.298348544111257e-06, + "loss": 0.3284, + "step": 25222 + }, + { + "epoch": 2.06, + "learning_rate": 6.297805302042591e-06, + "loss": 0.1842, + "step": 25223 + }, + { + "epoch": 2.06, + "learning_rate": 6.297262059973926e-06, + "loss": 0.3011, + "step": 25224 + }, + { + "epoch": 2.06, + "learning_rate": 6.29671881790526e-06, + "loss": 0.3476, + "step": 25225 + }, + { + "epoch": 2.06, + "learning_rate": 6.296175575836592e-06, + "loss": 0.2119, + "step": 25226 + }, + { + "epoch": 2.06, + "learning_rate": 6.295632333767927e-06, + "loss": 0.1555, + "step": 25227 + }, + { + "epoch": 2.06, + "learning_rate": 6.295089091699262e-06, + "loss": 0.2501, + "step": 25228 + }, + { + "epoch": 2.06, + "learning_rate": 6.294545849630596e-06, + "loss": 0.2434, + "step": 25229 + }, + { + "epoch": 2.06, + "learning_rate": 6.29400260756193e-06, + "loss": 0.284, + "step": 25230 + }, + { + "epoch": 2.06, + "learning_rate": 6.293459365493264e-06, + "loss": 0.1688, + "step": 25231 + }, + { + "epoch": 2.06, + "learning_rate": 6.292916123424599e-06, + "loss": 0.2043, + "step": 25232 + }, + { + "epoch": 2.06, + "learning_rate": 6.292372881355933e-06, + "loss": 0.115, + "step": 25233 + }, + { + "epoch": 2.06, + "learning_rate": 6.291829639287267e-06, + "loss": 0.156, + "step": 25234 + }, + { + "epoch": 2.06, + "learning_rate": 6.291286397218601e-06, + "loss": 0.2224, + "step": 25235 + }, + { + "epoch": 2.06, + "learning_rate": 6.2907431551499355e-06, + "loss": 0.3731, + "step": 25236 + }, + { + "epoch": 2.06, + "learning_rate": 6.29019991308127e-06, + "loss": 0.2277, + "step": 25237 + }, + { + "epoch": 2.06, + "learning_rate": 6.289656671012604e-06, + "loss": 0.2539, + "step": 25238 + }, + { + "epoch": 2.06, + "learning_rate": 6.289113428943938e-06, + "loss": 0.2946, + "step": 25239 + }, + { + "epoch": 2.06, + "learning_rate": 6.2885701868752725e-06, + "loss": 0.1534, + "step": 25240 + }, + { + "epoch": 2.06, + "learning_rate": 6.288026944806607e-06, + "loss": 0.1228, + "step": 25241 + }, + { + "epoch": 2.06, + "learning_rate": 6.287483702737941e-06, + "loss": 0.1485, + "step": 25242 + }, + { + "epoch": 2.06, + "learning_rate": 6.286940460669275e-06, + "loss": 0.1641, + "step": 25243 + }, + { + "epoch": 2.06, + "learning_rate": 6.286397218600609e-06, + "loss": 0.3002, + "step": 25244 + }, + { + "epoch": 2.06, + "learning_rate": 6.285853976531943e-06, + "loss": 0.4641, + "step": 25245 + }, + { + "epoch": 2.06, + "learning_rate": 6.285310734463277e-06, + "loss": 0.2836, + "step": 25246 + }, + { + "epoch": 2.06, + "learning_rate": 6.284767492394611e-06, + "loss": 0.3398, + "step": 25247 + }, + { + "epoch": 2.06, + "learning_rate": 6.2842242503259455e-06, + "loss": 0.1428, + "step": 25248 + }, + { + "epoch": 2.06, + "learning_rate": 6.28368100825728e-06, + "loss": 0.2588, + "step": 25249 + }, + { + "epoch": 2.06, + "learning_rate": 6.283137766188614e-06, + "loss": 0.222, + "step": 25250 + }, + { + "epoch": 2.06, + "eval_accuracy": 0.8421803362200713, + "eval_loss": 0.48668721318244934, + "eval_runtime": 22.2542, + "eval_samples_per_second": 441.041, + "eval_steps_per_second": 3.46, + "step": 25250 + }, + { + "epoch": 2.06, + "learning_rate": 6.282594524119948e-06, + "loss": 0.1801, + "step": 25251 + }, + { + "epoch": 2.06, + "learning_rate": 6.282051282051282e-06, + "loss": 0.1912, + "step": 25252 + }, + { + "epoch": 2.06, + "learning_rate": 6.281508039982617e-06, + "loss": 0.267, + "step": 25253 + }, + { + "epoch": 2.06, + "learning_rate": 6.280964797913951e-06, + "loss": 0.1845, + "step": 25254 + }, + { + "epoch": 2.06, + "learning_rate": 6.280421555845285e-06, + "loss": 0.1142, + "step": 25255 + }, + { + "epoch": 2.06, + "learning_rate": 6.279878313776619e-06, + "loss": 0.1331, + "step": 25256 + }, + { + "epoch": 2.06, + "learning_rate": 6.2793350717079535e-06, + "loss": 0.1735, + "step": 25257 + }, + { + "epoch": 2.06, + "learning_rate": 6.278791829639288e-06, + "loss": 0.1626, + "step": 25258 + }, + { + "epoch": 2.06, + "learning_rate": 6.278248587570622e-06, + "loss": 0.1675, + "step": 25259 + }, + { + "epoch": 2.06, + "learning_rate": 6.277705345501956e-06, + "loss": 0.2701, + "step": 25260 + }, + { + "epoch": 2.06, + "learning_rate": 6.2771621034332905e-06, + "loss": 0.0911, + "step": 25261 + }, + { + "epoch": 2.06, + "learning_rate": 6.276618861364625e-06, + "loss": 0.1773, + "step": 25262 + }, + { + "epoch": 2.06, + "learning_rate": 6.276075619295959e-06, + "loss": 0.0455, + "step": 25263 + }, + { + "epoch": 2.06, + "learning_rate": 6.275532377227292e-06, + "loss": 0.2347, + "step": 25264 + }, + { + "epoch": 2.06, + "learning_rate": 6.2749891351586265e-06, + "loss": 0.134, + "step": 25265 + }, + { + "epoch": 2.06, + "learning_rate": 6.274445893089961e-06, + "loss": 0.2005, + "step": 25266 + }, + { + "epoch": 2.06, + "learning_rate": 6.273902651021295e-06, + "loss": 0.2259, + "step": 25267 + }, + { + "epoch": 2.06, + "learning_rate": 6.273359408952629e-06, + "loss": 0.2162, + "step": 25268 + }, + { + "epoch": 2.06, + "learning_rate": 6.2728161668839635e-06, + "loss": 0.2052, + "step": 25269 + }, + { + "epoch": 2.06, + "learning_rate": 6.272272924815298e-06, + "loss": 0.3022, + "step": 25270 + }, + { + "epoch": 2.06, + "learning_rate": 6.271729682746632e-06, + "loss": 0.2171, + "step": 25271 + }, + { + "epoch": 2.06, + "learning_rate": 6.271186440677966e-06, + "loss": 0.2143, + "step": 25272 + }, + { + "epoch": 2.06, + "learning_rate": 6.270643198609301e-06, + "loss": 0.3815, + "step": 25273 + }, + { + "epoch": 2.06, + "learning_rate": 6.2700999565406355e-06, + "loss": 0.5033, + "step": 25274 + }, + { + "epoch": 2.06, + "learning_rate": 6.26955671447197e-06, + "loss": 0.2739, + "step": 25275 + }, + { + "epoch": 2.06, + "learning_rate": 6.269013472403304e-06, + "loss": 0.1934, + "step": 25276 + }, + { + "epoch": 2.06, + "learning_rate": 6.268470230334638e-06, + "loss": 0.2155, + "step": 25277 + }, + { + "epoch": 2.06, + "learning_rate": 6.267926988265972e-06, + "loss": 0.2252, + "step": 25278 + }, + { + "epoch": 2.06, + "learning_rate": 6.267383746197307e-06, + "loss": 0.1444, + "step": 25279 + }, + { + "epoch": 2.06, + "learning_rate": 6.266840504128641e-06, + "loss": 0.1232, + "step": 25280 + }, + { + "epoch": 2.06, + "learning_rate": 6.266297262059975e-06, + "loss": 0.0468, + "step": 25281 + }, + { + "epoch": 2.06, + "learning_rate": 6.265754019991309e-06, + "loss": 0.2029, + "step": 25282 + }, + { + "epoch": 2.06, + "learning_rate": 6.265210777922643e-06, + "loss": 0.1332, + "step": 25283 + }, + { + "epoch": 2.06, + "learning_rate": 6.264667535853977e-06, + "loss": 0.3768, + "step": 25284 + }, + { + "epoch": 2.06, + "learning_rate": 6.264124293785311e-06, + "loss": 0.1531, + "step": 25285 + }, + { + "epoch": 2.06, + "learning_rate": 6.263581051716645e-06, + "loss": 0.2504, + "step": 25286 + }, + { + "epoch": 2.06, + "learning_rate": 6.26303780964798e-06, + "loss": 0.2673, + "step": 25287 + }, + { + "epoch": 2.06, + "learning_rate": 6.262494567579314e-06, + "loss": 0.2402, + "step": 25288 + }, + { + "epoch": 2.06, + "learning_rate": 6.261951325510648e-06, + "loss": 0.2802, + "step": 25289 + }, + { + "epoch": 2.06, + "learning_rate": 6.261408083441982e-06, + "loss": 0.3419, + "step": 25290 + }, + { + "epoch": 2.06, + "learning_rate": 6.2608648413733165e-06, + "loss": 0.1764, + "step": 25291 + }, + { + "epoch": 2.06, + "learning_rate": 6.260321599304651e-06, + "loss": 0.263, + "step": 25292 + }, + { + "epoch": 2.06, + "learning_rate": 6.259778357235985e-06, + "loss": 0.2684, + "step": 25293 + }, + { + "epoch": 2.06, + "learning_rate": 6.259235115167319e-06, + "loss": 0.1926, + "step": 25294 + }, + { + "epoch": 2.06, + "learning_rate": 6.2586918730986535e-06, + "loss": 0.2673, + "step": 25295 + }, + { + "epoch": 2.06, + "learning_rate": 6.258148631029988e-06, + "loss": 0.1182, + "step": 25296 + }, + { + "epoch": 2.06, + "learning_rate": 6.257605388961322e-06, + "loss": 0.0855, + "step": 25297 + }, + { + "epoch": 2.06, + "learning_rate": 6.257062146892656e-06, + "loss": 0.2247, + "step": 25298 + }, + { + "epoch": 2.06, + "learning_rate": 6.25651890482399e-06, + "loss": 0.4878, + "step": 25299 + }, + { + "epoch": 2.06, + "learning_rate": 6.255975662755325e-06, + "loss": 0.498, + "step": 25300 + }, + { + "epoch": 2.06, + "learning_rate": 6.255432420686659e-06, + "loss": 0.1308, + "step": 25301 + }, + { + "epoch": 2.06, + "learning_rate": 6.254889178617992e-06, + "loss": 0.1739, + "step": 25302 + }, + { + "epoch": 2.06, + "learning_rate": 6.2543459365493265e-06, + "loss": 0.2063, + "step": 25303 + }, + { + "epoch": 2.06, + "learning_rate": 6.253802694480661e-06, + "loss": 0.0968, + "step": 25304 + }, + { + "epoch": 2.06, + "learning_rate": 6.253259452411995e-06, + "loss": 0.1175, + "step": 25305 + }, + { + "epoch": 2.06, + "learning_rate": 6.252716210343329e-06, + "loss": 0.1342, + "step": 25306 + }, + { + "epoch": 2.06, + "learning_rate": 6.252172968274663e-06, + "loss": 0.0892, + "step": 25307 + }, + { + "epoch": 2.06, + "learning_rate": 6.251629726205998e-06, + "loss": 0.242, + "step": 25308 + }, + { + "epoch": 2.06, + "learning_rate": 6.251086484137332e-06, + "loss": 0.1857, + "step": 25309 + }, + { + "epoch": 2.06, + "learning_rate": 6.250543242068666e-06, + "loss": 0.3034, + "step": 25310 + }, + { + "epoch": 2.06, + "learning_rate": 6.25e-06, + "loss": 0.0808, + "step": 25311 + }, + { + "epoch": 2.06, + "learning_rate": 6.2494567579313345e-06, + "loss": 0.2804, + "step": 25312 + }, + { + "epoch": 2.06, + "learning_rate": 6.248913515862669e-06, + "loss": 0.2584, + "step": 25313 + }, + { + "epoch": 2.06, + "learning_rate": 6.248370273794003e-06, + "loss": 0.0945, + "step": 25314 + }, + { + "epoch": 2.06, + "learning_rate": 6.247827031725337e-06, + "loss": 0.0312, + "step": 25315 + }, + { + "epoch": 2.06, + "learning_rate": 6.2472837896566715e-06, + "loss": 0.1895, + "step": 25316 + }, + { + "epoch": 2.06, + "learning_rate": 6.246740547588006e-06, + "loss": 0.1974, + "step": 25317 + }, + { + "epoch": 2.06, + "learning_rate": 6.246197305519341e-06, + "loss": 0.2144, + "step": 25318 + }, + { + "epoch": 2.06, + "learning_rate": 6.245654063450675e-06, + "loss": 0.241, + "step": 25319 + }, + { + "epoch": 2.06, + "learning_rate": 6.245110821382009e-06, + "loss": 0.2237, + "step": 25320 + }, + { + "epoch": 2.06, + "learning_rate": 6.244567579313342e-06, + "loss": 0.1717, + "step": 25321 + }, + { + "epoch": 2.06, + "learning_rate": 6.244024337244676e-06, + "loss": 0.338, + "step": 25322 + }, + { + "epoch": 2.06, + "learning_rate": 6.24348109517601e-06, + "loss": 0.3927, + "step": 25323 + }, + { + "epoch": 2.06, + "learning_rate": 6.2429378531073444e-06, + "loss": 0.2484, + "step": 25324 + }, + { + "epoch": 2.06, + "learning_rate": 6.242394611038679e-06, + "loss": 0.2209, + "step": 25325 + }, + { + "epoch": 2.06, + "learning_rate": 6.241851368970013e-06, + "loss": 0.363, + "step": 25326 + }, + { + "epoch": 2.06, + "learning_rate": 6.241308126901348e-06, + "loss": 0.0978, + "step": 25327 + }, + { + "epoch": 2.06, + "learning_rate": 6.240764884832682e-06, + "loss": 0.0659, + "step": 25328 + }, + { + "epoch": 2.06, + "learning_rate": 6.2402216427640164e-06, + "loss": 0.3124, + "step": 25329 + }, + { + "epoch": 2.06, + "learning_rate": 6.239678400695351e-06, + "loss": 0.1887, + "step": 25330 + }, + { + "epoch": 2.06, + "learning_rate": 6.239135158626685e-06, + "loss": 0.2091, + "step": 25331 + }, + { + "epoch": 2.06, + "learning_rate": 6.238591916558019e-06, + "loss": 0.1253, + "step": 25332 + }, + { + "epoch": 2.06, + "learning_rate": 6.238048674489353e-06, + "loss": 0.1974, + "step": 25333 + }, + { + "epoch": 2.06, + "learning_rate": 6.237505432420688e-06, + "loss": 0.2593, + "step": 25334 + }, + { + "epoch": 2.06, + "learning_rate": 6.236962190352022e-06, + "loss": 0.5193, + "step": 25335 + }, + { + "epoch": 2.06, + "learning_rate": 6.236418948283356e-06, + "loss": 0.1198, + "step": 25336 + }, + { + "epoch": 2.06, + "learning_rate": 6.23587570621469e-06, + "loss": 0.2461, + "step": 25337 + }, + { + "epoch": 2.06, + "learning_rate": 6.2353324641460245e-06, + "loss": 0.1823, + "step": 25338 + }, + { + "epoch": 2.06, + "learning_rate": 6.234789222077359e-06, + "loss": 0.1633, + "step": 25339 + }, + { + "epoch": 2.06, + "learning_rate": 6.234245980008692e-06, + "loss": 0.0672, + "step": 25340 + }, + { + "epoch": 2.06, + "learning_rate": 6.233702737940026e-06, + "loss": 0.229, + "step": 25341 + }, + { + "epoch": 2.07, + "learning_rate": 6.233159495871361e-06, + "loss": 0.1807, + "step": 25342 + }, + { + "epoch": 2.07, + "learning_rate": 6.232616253802695e-06, + "loss": 0.1553, + "step": 25343 + }, + { + "epoch": 2.07, + "learning_rate": 6.232073011734029e-06, + "loss": 0.1143, + "step": 25344 + }, + { + "epoch": 2.07, + "learning_rate": 6.231529769665363e-06, + "loss": 0.3086, + "step": 25345 + }, + { + "epoch": 2.07, + "learning_rate": 6.2309865275966975e-06, + "loss": 0.1941, + "step": 25346 + }, + { + "epoch": 2.07, + "learning_rate": 6.230443285528032e-06, + "loss": 0.1053, + "step": 25347 + }, + { + "epoch": 2.07, + "learning_rate": 6.229900043459366e-06, + "loss": 0.0807, + "step": 25348 + }, + { + "epoch": 2.07, + "learning_rate": 6.2293568013907e-06, + "loss": 0.0797, + "step": 25349 + }, + { + "epoch": 2.07, + "learning_rate": 6.2288135593220344e-06, + "loss": 0.2737, + "step": 25350 + }, + { + "epoch": 2.07, + "learning_rate": 6.228270317253369e-06, + "loss": 0.5753, + "step": 25351 + }, + { + "epoch": 2.07, + "learning_rate": 6.227727075184703e-06, + "loss": 0.226, + "step": 25352 + }, + { + "epoch": 2.07, + "learning_rate": 6.227183833116037e-06, + "loss": 0.1819, + "step": 25353 + }, + { + "epoch": 2.07, + "learning_rate": 6.226640591047371e-06, + "loss": 0.2063, + "step": 25354 + }, + { + "epoch": 2.07, + "learning_rate": 6.226097348978706e-06, + "loss": 0.2948, + "step": 25355 + }, + { + "epoch": 2.07, + "learning_rate": 6.22555410691004e-06, + "loss": 0.2111, + "step": 25356 + }, + { + "epoch": 2.07, + "learning_rate": 6.225010864841374e-06, + "loss": 0.1799, + "step": 25357 + }, + { + "epoch": 2.07, + "learning_rate": 6.224467622772708e-06, + "loss": 0.3725, + "step": 25358 + }, + { + "epoch": 2.07, + "learning_rate": 6.223924380704042e-06, + "loss": 0.4277, + "step": 25359 + }, + { + "epoch": 2.07, + "learning_rate": 6.223381138635376e-06, + "loss": 0.208, + "step": 25360 + }, + { + "epoch": 2.07, + "learning_rate": 6.22283789656671e-06, + "loss": 0.1226, + "step": 25361 + }, + { + "epoch": 2.07, + "learning_rate": 6.222294654498044e-06, + "loss": 0.1111, + "step": 25362 + }, + { + "epoch": 2.07, + "learning_rate": 6.221751412429379e-06, + "loss": 0.2522, + "step": 25363 + }, + { + "epoch": 2.07, + "learning_rate": 6.221208170360713e-06, + "loss": 0.1561, + "step": 25364 + }, + { + "epoch": 2.07, + "learning_rate": 6.220664928292047e-06, + "loss": 0.3229, + "step": 25365 + }, + { + "epoch": 2.07, + "learning_rate": 6.220121686223381e-06, + "loss": 0.1839, + "step": 25366 + }, + { + "epoch": 2.07, + "learning_rate": 6.2195784441547155e-06, + "loss": 0.0805, + "step": 25367 + }, + { + "epoch": 2.07, + "learning_rate": 6.21903520208605e-06, + "loss": 0.1531, + "step": 25368 + }, + { + "epoch": 2.07, + "learning_rate": 6.218491960017384e-06, + "loss": 0.1681, + "step": 25369 + }, + { + "epoch": 2.07, + "learning_rate": 6.217948717948718e-06, + "loss": 0.0653, + "step": 25370 + }, + { + "epoch": 2.07, + "learning_rate": 6.2174054758800524e-06, + "loss": 0.0807, + "step": 25371 + }, + { + "epoch": 2.07, + "learning_rate": 6.2168622338113875e-06, + "loss": 0.395, + "step": 25372 + }, + { + "epoch": 2.07, + "learning_rate": 6.216318991742722e-06, + "loss": 0.2414, + "step": 25373 + }, + { + "epoch": 2.07, + "learning_rate": 6.215775749674056e-06, + "loss": 0.2816, + "step": 25374 + }, + { + "epoch": 2.07, + "learning_rate": 6.21523250760539e-06, + "loss": 0.1131, + "step": 25375 + }, + { + "epoch": 2.07, + "learning_rate": 6.2146892655367244e-06, + "loss": 0.1672, + "step": 25376 + }, + { + "epoch": 2.07, + "learning_rate": 6.214146023468059e-06, + "loss": 0.1168, + "step": 25377 + }, + { + "epoch": 2.07, + "learning_rate": 6.213602781399391e-06, + "loss": 0.4189, + "step": 25378 + }, + { + "epoch": 2.07, + "learning_rate": 6.2130595393307254e-06, + "loss": 0.1982, + "step": 25379 + }, + { + "epoch": 2.07, + "learning_rate": 6.21251629726206e-06, + "loss": 0.1644, + "step": 25380 + }, + { + "epoch": 2.07, + "learning_rate": 6.211973055193395e-06, + "loss": 0.1719, + "step": 25381 + }, + { + "epoch": 2.07, + "learning_rate": 6.211429813124729e-06, + "loss": 0.2511, + "step": 25382 + }, + { + "epoch": 2.07, + "learning_rate": 6.210886571056063e-06, + "loss": 0.0782, + "step": 25383 + }, + { + "epoch": 2.07, + "learning_rate": 6.2103433289873974e-06, + "loss": 0.338, + "step": 25384 + }, + { + "epoch": 2.07, + "learning_rate": 6.209800086918732e-06, + "loss": 0.4065, + "step": 25385 + }, + { + "epoch": 2.07, + "learning_rate": 6.209256844850066e-06, + "loss": 0.0519, + "step": 25386 + }, + { + "epoch": 2.07, + "learning_rate": 6.2087136027814e-06, + "loss": 0.2112, + "step": 25387 + }, + { + "epoch": 2.07, + "learning_rate": 6.208170360712734e-06, + "loss": 0.1821, + "step": 25388 + }, + { + "epoch": 2.07, + "learning_rate": 6.207627118644069e-06, + "loss": 0.0854, + "step": 25389 + }, + { + "epoch": 2.07, + "learning_rate": 6.207083876575403e-06, + "loss": 0.1742, + "step": 25390 + }, + { + "epoch": 2.07, + "learning_rate": 6.206540634506737e-06, + "loss": 0.2185, + "step": 25391 + }, + { + "epoch": 2.07, + "learning_rate": 6.205997392438071e-06, + "loss": 0.2783, + "step": 25392 + }, + { + "epoch": 2.07, + "learning_rate": 6.2054541503694055e-06, + "loss": 0.1771, + "step": 25393 + }, + { + "epoch": 2.07, + "learning_rate": 6.20491090830074e-06, + "loss": 0.277, + "step": 25394 + }, + { + "epoch": 2.07, + "learning_rate": 6.204367666232074e-06, + "loss": 0.0715, + "step": 25395 + }, + { + "epoch": 2.07, + "learning_rate": 6.203824424163408e-06, + "loss": 0.1589, + "step": 25396 + }, + { + "epoch": 2.07, + "learning_rate": 6.203281182094742e-06, + "loss": 0.1942, + "step": 25397 + }, + { + "epoch": 2.07, + "learning_rate": 6.202737940026076e-06, + "loss": 0.0854, + "step": 25398 + }, + { + "epoch": 2.07, + "learning_rate": 6.20219469795741e-06, + "loss": 0.3457, + "step": 25399 + }, + { + "epoch": 2.07, + "learning_rate": 6.201651455888744e-06, + "loss": 0.2031, + "step": 25400 + }, + { + "epoch": 2.07, + "learning_rate": 6.2011082138200785e-06, + "loss": 0.0317, + "step": 25401 + }, + { + "epoch": 2.07, + "learning_rate": 6.200564971751413e-06, + "loss": 0.2236, + "step": 25402 + }, + { + "epoch": 2.07, + "learning_rate": 6.200021729682747e-06, + "loss": 0.0689, + "step": 25403 + }, + { + "epoch": 2.07, + "learning_rate": 6.199478487614081e-06, + "loss": 0.3911, + "step": 25404 + }, + { + "epoch": 2.07, + "learning_rate": 6.1989352455454154e-06, + "loss": 0.0775, + "step": 25405 + }, + { + "epoch": 2.07, + "learning_rate": 6.19839200347675e-06, + "loss": 0.4464, + "step": 25406 + }, + { + "epoch": 2.07, + "learning_rate": 6.197848761408084e-06, + "loss": 0.2705, + "step": 25407 + }, + { + "epoch": 2.07, + "learning_rate": 6.197305519339418e-06, + "loss": 0.1751, + "step": 25408 + }, + { + "epoch": 2.07, + "learning_rate": 6.196762277270752e-06, + "loss": 0.2861, + "step": 25409 + }, + { + "epoch": 2.07, + "learning_rate": 6.196219035202087e-06, + "loss": 0.182, + "step": 25410 + }, + { + "epoch": 2.07, + "learning_rate": 6.195675793133421e-06, + "loss": 0.2976, + "step": 25411 + }, + { + "epoch": 2.07, + "learning_rate": 6.195132551064755e-06, + "loss": 0.3324, + "step": 25412 + }, + { + "epoch": 2.07, + "learning_rate": 6.194589308996089e-06, + "loss": 0.1506, + "step": 25413 + }, + { + "epoch": 2.07, + "learning_rate": 6.1940460669274235e-06, + "loss": 0.0659, + "step": 25414 + }, + { + "epoch": 2.07, + "learning_rate": 6.193502824858758e-06, + "loss": 0.1263, + "step": 25415 + }, + { + "epoch": 2.07, + "learning_rate": 6.192959582790091e-06, + "loss": 0.3689, + "step": 25416 + }, + { + "epoch": 2.07, + "learning_rate": 6.192416340721425e-06, + "loss": 0.1229, + "step": 25417 + }, + { + "epoch": 2.07, + "learning_rate": 6.19187309865276e-06, + "loss": 0.2408, + "step": 25418 + }, + { + "epoch": 2.07, + "learning_rate": 6.191329856584094e-06, + "loss": 0.3787, + "step": 25419 + }, + { + "epoch": 2.07, + "learning_rate": 6.190786614515428e-06, + "loss": 0.488, + "step": 25420 + }, + { + "epoch": 2.07, + "learning_rate": 6.190243372446762e-06, + "loss": 0.4002, + "step": 25421 + }, + { + "epoch": 2.07, + "learning_rate": 6.1897001303780965e-06, + "loss": 0.2828, + "step": 25422 + }, + { + "epoch": 2.07, + "learning_rate": 6.189156888309431e-06, + "loss": 0.4574, + "step": 25423 + }, + { + "epoch": 2.07, + "learning_rate": 6.188613646240765e-06, + "loss": 0.2789, + "step": 25424 + }, + { + "epoch": 2.07, + "learning_rate": 6.188070404172099e-06, + "loss": 0.3253, + "step": 25425 + }, + { + "epoch": 2.07, + "learning_rate": 6.187527162103434e-06, + "loss": 0.0747, + "step": 25426 + }, + { + "epoch": 2.07, + "learning_rate": 6.1869839200347685e-06, + "loss": 0.2025, + "step": 25427 + }, + { + "epoch": 2.07, + "learning_rate": 6.186440677966103e-06, + "loss": 0.4866, + "step": 25428 + }, + { + "epoch": 2.07, + "learning_rate": 6.185897435897437e-06, + "loss": 0.3541, + "step": 25429 + }, + { + "epoch": 2.07, + "learning_rate": 6.185354193828771e-06, + "loss": 0.5293, + "step": 25430 + }, + { + "epoch": 2.07, + "learning_rate": 6.1848109517601054e-06, + "loss": 0.292, + "step": 25431 + }, + { + "epoch": 2.07, + "learning_rate": 6.18426770969144e-06, + "loss": 0.4881, + "step": 25432 + }, + { + "epoch": 2.07, + "learning_rate": 6.183724467622774e-06, + "loss": 0.3623, + "step": 25433 + }, + { + "epoch": 2.07, + "learning_rate": 6.183181225554108e-06, + "loss": 0.17, + "step": 25434 + }, + { + "epoch": 2.07, + "learning_rate": 6.1826379834854415e-06, + "loss": 0.5972, + "step": 25435 + }, + { + "epoch": 2.07, + "learning_rate": 6.182094741416776e-06, + "loss": 0.2966, + "step": 25436 + }, + { + "epoch": 2.07, + "learning_rate": 6.18155149934811e-06, + "loss": 0.2731, + "step": 25437 + }, + { + "epoch": 2.07, + "learning_rate": 6.181008257279444e-06, + "loss": 0.4306, + "step": 25438 + }, + { + "epoch": 2.07, + "learning_rate": 6.180465015210778e-06, + "loss": 0.373, + "step": 25439 + }, + { + "epoch": 2.07, + "learning_rate": 6.179921773142113e-06, + "loss": 0.0597, + "step": 25440 + }, + { + "epoch": 2.07, + "learning_rate": 6.179378531073447e-06, + "loss": 0.1549, + "step": 25441 + }, + { + "epoch": 2.07, + "learning_rate": 6.178835289004781e-06, + "loss": 0.2815, + "step": 25442 + }, + { + "epoch": 2.07, + "learning_rate": 6.178292046936115e-06, + "loss": 0.0704, + "step": 25443 + }, + { + "epoch": 2.07, + "learning_rate": 6.1777488048674496e-06, + "loss": 0.6852, + "step": 25444 + }, + { + "epoch": 2.07, + "learning_rate": 6.177205562798784e-06, + "loss": 0.1671, + "step": 25445 + }, + { + "epoch": 2.07, + "learning_rate": 6.176662320730118e-06, + "loss": 0.123, + "step": 25446 + }, + { + "epoch": 2.07, + "learning_rate": 6.176119078661452e-06, + "loss": 0.3297, + "step": 25447 + }, + { + "epoch": 2.07, + "learning_rate": 6.1755758365927865e-06, + "loss": 0.2491, + "step": 25448 + }, + { + "epoch": 2.07, + "learning_rate": 6.175032594524121e-06, + "loss": 0.283, + "step": 25449 + }, + { + "epoch": 2.07, + "learning_rate": 6.174489352455455e-06, + "loss": 0.1245, + "step": 25450 + }, + { + "epoch": 2.07, + "learning_rate": 6.173946110386789e-06, + "loss": 0.1873, + "step": 25451 + }, + { + "epoch": 2.07, + "learning_rate": 6.173402868318123e-06, + "loss": 0.2695, + "step": 25452 + }, + { + "epoch": 2.07, + "learning_rate": 6.172859626249458e-06, + "loss": 0.181, + "step": 25453 + }, + { + "epoch": 2.07, + "learning_rate": 6.172316384180791e-06, + "loss": 0.1226, + "step": 25454 + }, + { + "epoch": 2.07, + "learning_rate": 6.171773142112125e-06, + "loss": 0.194, + "step": 25455 + }, + { + "epoch": 2.07, + "learning_rate": 6.1712299000434595e-06, + "loss": 0.2444, + "step": 25456 + }, + { + "epoch": 2.07, + "learning_rate": 6.170686657974794e-06, + "loss": 0.1874, + "step": 25457 + }, + { + "epoch": 2.07, + "learning_rate": 6.170143415906128e-06, + "loss": 0.2381, + "step": 25458 + }, + { + "epoch": 2.07, + "learning_rate": 6.169600173837462e-06, + "loss": 0.3361, + "step": 25459 + }, + { + "epoch": 2.07, + "learning_rate": 6.169056931768796e-06, + "loss": 0.3337, + "step": 25460 + }, + { + "epoch": 2.07, + "learning_rate": 6.168513689700131e-06, + "loss": 0.1538, + "step": 25461 + }, + { + "epoch": 2.07, + "learning_rate": 6.167970447631465e-06, + "loss": 0.1005, + "step": 25462 + }, + { + "epoch": 2.07, + "learning_rate": 6.167427205562799e-06, + "loss": 0.1798, + "step": 25463 + }, + { + "epoch": 2.07, + "learning_rate": 6.166883963494133e-06, + "loss": 0.2915, + "step": 25464 + }, + { + "epoch": 2.08, + "learning_rate": 6.1663407214254676e-06, + "loss": 0.3119, + "step": 25465 + }, + { + "epoch": 2.08, + "learning_rate": 6.165797479356802e-06, + "loss": 0.196, + "step": 25466 + }, + { + "epoch": 2.08, + "learning_rate": 6.165254237288136e-06, + "loss": 0.2594, + "step": 25467 + }, + { + "epoch": 2.08, + "learning_rate": 6.16471099521947e-06, + "loss": 0.2501, + "step": 25468 + }, + { + "epoch": 2.08, + "learning_rate": 6.1641677531508045e-06, + "loss": 0.1171, + "step": 25469 + }, + { + "epoch": 2.08, + "learning_rate": 6.163624511082139e-06, + "loss": 0.1597, + "step": 25470 + }, + { + "epoch": 2.08, + "learning_rate": 6.163081269013473e-06, + "loss": 0.2635, + "step": 25471 + }, + { + "epoch": 2.08, + "learning_rate": 6.162538026944808e-06, + "loss": 0.2882, + "step": 25472 + }, + { + "epoch": 2.08, + "learning_rate": 6.1619947848761406e-06, + "loss": 0.4302, + "step": 25473 + }, + { + "epoch": 2.08, + "learning_rate": 6.161451542807475e-06, + "loss": 0.1392, + "step": 25474 + }, + { + "epoch": 2.08, + "learning_rate": 6.160908300738809e-06, + "loss": 0.1704, + "step": 25475 + }, + { + "epoch": 2.08, + "learning_rate": 6.160365058670143e-06, + "loss": 0.2645, + "step": 25476 + }, + { + "epoch": 2.08, + "learning_rate": 6.1598218166014775e-06, + "loss": 0.162, + "step": 25477 + }, + { + "epoch": 2.08, + "learning_rate": 6.159278574532812e-06, + "loss": 0.2542, + "step": 25478 + }, + { + "epoch": 2.08, + "learning_rate": 6.158735332464146e-06, + "loss": 0.1311, + "step": 25479 + }, + { + "epoch": 2.08, + "learning_rate": 6.158192090395481e-06, + "loss": 0.2558, + "step": 25480 + }, + { + "epoch": 2.08, + "learning_rate": 6.157648848326815e-06, + "loss": 0.146, + "step": 25481 + }, + { + "epoch": 2.08, + "learning_rate": 6.1571056062581495e-06, + "loss": 0.3027, + "step": 25482 + }, + { + "epoch": 2.08, + "learning_rate": 6.156562364189484e-06, + "loss": 0.2992, + "step": 25483 + }, + { + "epoch": 2.08, + "learning_rate": 6.156019122120818e-06, + "loss": 0.1409, + "step": 25484 + }, + { + "epoch": 2.08, + "learning_rate": 6.155475880052152e-06, + "loss": 0.3282, + "step": 25485 + }, + { + "epoch": 2.08, + "learning_rate": 6.154932637983486e-06, + "loss": 0.2939, + "step": 25486 + }, + { + "epoch": 2.08, + "learning_rate": 6.154389395914821e-06, + "loss": 0.2454, + "step": 25487 + }, + { + "epoch": 2.08, + "learning_rate": 6.153846153846155e-06, + "loss": 0.2916, + "step": 25488 + }, + { + "epoch": 2.08, + "learning_rate": 6.153302911777489e-06, + "loss": 0.3281, + "step": 25489 + }, + { + "epoch": 2.08, + "learning_rate": 6.152759669708823e-06, + "loss": 0.1105, + "step": 25490 + }, + { + "epoch": 2.08, + "learning_rate": 6.1522164276401576e-06, + "loss": 0.0412, + "step": 25491 + }, + { + "epoch": 2.08, + "learning_rate": 6.151673185571491e-06, + "loss": 0.1573, + "step": 25492 + }, + { + "epoch": 2.08, + "learning_rate": 6.151129943502825e-06, + "loss": 0.2425, + "step": 25493 + }, + { + "epoch": 2.08, + "learning_rate": 6.150586701434159e-06, + "loss": 0.1312, + "step": 25494 + }, + { + "epoch": 2.08, + "learning_rate": 6.150043459365494e-06, + "loss": 0.23, + "step": 25495 + }, + { + "epoch": 2.08, + "learning_rate": 6.149500217296828e-06, + "loss": 0.1315, + "step": 25496 + }, + { + "epoch": 2.08, + "learning_rate": 6.148956975228162e-06, + "loss": 0.4295, + "step": 25497 + }, + { + "epoch": 2.08, + "learning_rate": 6.148413733159496e-06, + "loss": 0.0493, + "step": 25498 + }, + { + "epoch": 2.08, + "learning_rate": 6.1478704910908306e-06, + "loss": 0.1602, + "step": 25499 + }, + { + "epoch": 2.08, + "learning_rate": 6.147327249022165e-06, + "loss": 0.1465, + "step": 25500 + }, + { + "epoch": 2.08, + "eval_accuracy": 0.845236882322975, + "eval_loss": 0.4808719754219055, + "eval_runtime": 22.2682, + "eval_samples_per_second": 440.763, + "eval_steps_per_second": 3.458, + "step": 25500 + }, + { + "epoch": 2.08, + "learning_rate": 6.146784006953499e-06, + "loss": 0.1807, + "step": 25501 + }, + { + "epoch": 2.08, + "learning_rate": 6.146240764884833e-06, + "loss": 0.4958, + "step": 25502 + }, + { + "epoch": 2.08, + "learning_rate": 6.1456975228161675e-06, + "loss": 0.2112, + "step": 25503 + }, + { + "epoch": 2.08, + "learning_rate": 6.145154280747502e-06, + "loss": 0.1175, + "step": 25504 + }, + { + "epoch": 2.08, + "learning_rate": 6.144611038678836e-06, + "loss": 0.2451, + "step": 25505 + }, + { + "epoch": 2.08, + "learning_rate": 6.14406779661017e-06, + "loss": 0.2414, + "step": 25506 + }, + { + "epoch": 2.08, + "learning_rate": 6.143524554541504e-06, + "loss": 0.3306, + "step": 25507 + }, + { + "epoch": 2.08, + "learning_rate": 6.142981312472839e-06, + "loss": 0.0928, + "step": 25508 + }, + { + "epoch": 2.08, + "learning_rate": 6.142438070404173e-06, + "loss": 0.3039, + "step": 25509 + }, + { + "epoch": 2.08, + "learning_rate": 6.141894828335507e-06, + "loss": 0.2917, + "step": 25510 + }, + { + "epoch": 2.08, + "learning_rate": 6.1413515862668405e-06, + "loss": 0.4559, + "step": 25511 + }, + { + "epoch": 2.08, + "learning_rate": 6.140808344198175e-06, + "loss": 0.0716, + "step": 25512 + }, + { + "epoch": 2.08, + "learning_rate": 6.140265102129509e-06, + "loss": 0.1734, + "step": 25513 + }, + { + "epoch": 2.08, + "learning_rate": 6.139721860060843e-06, + "loss": 0.2349, + "step": 25514 + }, + { + "epoch": 2.08, + "learning_rate": 6.139178617992177e-06, + "loss": 0.1402, + "step": 25515 + }, + { + "epoch": 2.08, + "learning_rate": 6.138635375923512e-06, + "loss": 0.3751, + "step": 25516 + }, + { + "epoch": 2.08, + "learning_rate": 6.138092133854846e-06, + "loss": 0.4764, + "step": 25517 + }, + { + "epoch": 2.08, + "learning_rate": 6.13754889178618e-06, + "loss": 0.3239, + "step": 25518 + }, + { + "epoch": 2.08, + "learning_rate": 6.137005649717514e-06, + "loss": 0.2556, + "step": 25519 + }, + { + "epoch": 2.08, + "learning_rate": 6.1364624076488486e-06, + "loss": 0.3653, + "step": 25520 + }, + { + "epoch": 2.08, + "learning_rate": 6.135919165580183e-06, + "loss": 0.2117, + "step": 25521 + }, + { + "epoch": 2.08, + "learning_rate": 6.135375923511517e-06, + "loss": 0.184, + "step": 25522 + }, + { + "epoch": 2.08, + "learning_rate": 6.134832681442851e-06, + "loss": 0.0878, + "step": 25523 + }, + { + "epoch": 2.08, + "learning_rate": 6.1342894393741855e-06, + "loss": 0.2666, + "step": 25524 + }, + { + "epoch": 2.08, + "learning_rate": 6.13374619730552e-06, + "loss": 0.2829, + "step": 25525 + }, + { + "epoch": 2.08, + "learning_rate": 6.133202955236855e-06, + "loss": 0.121, + "step": 25526 + }, + { + "epoch": 2.08, + "learning_rate": 6.132659713168189e-06, + "loss": 0.1959, + "step": 25527 + }, + { + "epoch": 2.08, + "learning_rate": 6.132116471099523e-06, + "loss": 0.145, + "step": 25528 + }, + { + "epoch": 2.08, + "learning_rate": 6.1315732290308575e-06, + "loss": 0.1261, + "step": 25529 + }, + { + "epoch": 2.08, + "learning_rate": 6.13102998696219e-06, + "loss": 0.1037, + "step": 25530 + }, + { + "epoch": 2.08, + "learning_rate": 6.130486744893524e-06, + "loss": 0.1914, + "step": 25531 + }, + { + "epoch": 2.08, + "learning_rate": 6.1299435028248585e-06, + "loss": 0.1308, + "step": 25532 + }, + { + "epoch": 2.08, + "learning_rate": 6.129400260756193e-06, + "loss": 0.0818, + "step": 25533 + }, + { + "epoch": 2.08, + "learning_rate": 6.128857018687528e-06, + "loss": 0.3023, + "step": 25534 + }, + { + "epoch": 2.08, + "learning_rate": 6.128313776618862e-06, + "loss": 0.0705, + "step": 25535 + }, + { + "epoch": 2.08, + "learning_rate": 6.127770534550196e-06, + "loss": 0.0598, + "step": 25536 + }, + { + "epoch": 2.08, + "learning_rate": 6.1272272924815305e-06, + "loss": 0.5601, + "step": 25537 + }, + { + "epoch": 2.08, + "learning_rate": 6.126684050412865e-06, + "loss": 0.3311, + "step": 25538 + }, + { + "epoch": 2.08, + "learning_rate": 6.126140808344199e-06, + "loss": 0.427, + "step": 25539 + }, + { + "epoch": 2.08, + "learning_rate": 6.125597566275533e-06, + "loss": 0.1326, + "step": 25540 + }, + { + "epoch": 2.08, + "learning_rate": 6.125054324206867e-06, + "loss": 0.188, + "step": 25541 + }, + { + "epoch": 2.08, + "learning_rate": 6.124511082138202e-06, + "loss": 0.1243, + "step": 25542 + }, + { + "epoch": 2.08, + "learning_rate": 6.123967840069536e-06, + "loss": 0.0607, + "step": 25543 + }, + { + "epoch": 2.08, + "learning_rate": 6.12342459800087e-06, + "loss": 0.1872, + "step": 25544 + }, + { + "epoch": 2.08, + "learning_rate": 6.122881355932204e-06, + "loss": 0.4238, + "step": 25545 + }, + { + "epoch": 2.08, + "learning_rate": 6.1223381138635385e-06, + "loss": 0.1407, + "step": 25546 + }, + { + "epoch": 2.08, + "learning_rate": 6.121794871794873e-06, + "loss": 0.3756, + "step": 25547 + }, + { + "epoch": 2.08, + "learning_rate": 6.121251629726207e-06, + "loss": 0.1947, + "step": 25548 + }, + { + "epoch": 2.08, + "learning_rate": 6.12070838765754e-06, + "loss": 0.2684, + "step": 25549 + }, + { + "epoch": 2.08, + "learning_rate": 6.120165145588875e-06, + "loss": 0.2114, + "step": 25550 + }, + { + "epoch": 2.08, + "learning_rate": 6.119621903520209e-06, + "loss": 0.1794, + "step": 25551 + }, + { + "epoch": 2.08, + "learning_rate": 6.119078661451543e-06, + "loss": 0.2133, + "step": 25552 + }, + { + "epoch": 2.08, + "learning_rate": 6.118535419382877e-06, + "loss": 0.1156, + "step": 25553 + }, + { + "epoch": 2.08, + "learning_rate": 6.1179921773142115e-06, + "loss": 0.0852, + "step": 25554 + }, + { + "epoch": 2.08, + "learning_rate": 6.117448935245546e-06, + "loss": 0.2092, + "step": 25555 + }, + { + "epoch": 2.08, + "learning_rate": 6.11690569317688e-06, + "loss": 0.4247, + "step": 25556 + }, + { + "epoch": 2.08, + "learning_rate": 6.116362451108214e-06, + "loss": 0.4128, + "step": 25557 + }, + { + "epoch": 2.08, + "learning_rate": 6.1158192090395485e-06, + "loss": 0.2708, + "step": 25558 + }, + { + "epoch": 2.08, + "learning_rate": 6.115275966970883e-06, + "loss": 0.0617, + "step": 25559 + }, + { + "epoch": 2.08, + "learning_rate": 6.114732724902217e-06, + "loss": 0.1284, + "step": 25560 + }, + { + "epoch": 2.08, + "learning_rate": 6.114189482833551e-06, + "loss": 0.1598, + "step": 25561 + }, + { + "epoch": 2.08, + "learning_rate": 6.113646240764885e-06, + "loss": 0.1914, + "step": 25562 + }, + { + "epoch": 2.08, + "learning_rate": 6.11310299869622e-06, + "loss": 0.2549, + "step": 25563 + }, + { + "epoch": 2.08, + "learning_rate": 6.112559756627554e-06, + "loss": 0.1091, + "step": 25564 + }, + { + "epoch": 2.08, + "learning_rate": 6.112016514558888e-06, + "loss": 0.206, + "step": 25565 + }, + { + "epoch": 2.08, + "learning_rate": 6.111473272490222e-06, + "loss": 0.3345, + "step": 25566 + }, + { + "epoch": 2.08, + "learning_rate": 6.1109300304215565e-06, + "loss": 0.2252, + "step": 25567 + }, + { + "epoch": 2.08, + "learning_rate": 6.11038678835289e-06, + "loss": 0.2057, + "step": 25568 + }, + { + "epoch": 2.08, + "learning_rate": 6.109843546284224e-06, + "loss": 0.2988, + "step": 25569 + }, + { + "epoch": 2.08, + "learning_rate": 6.109300304215558e-06, + "loss": 0.2944, + "step": 25570 + }, + { + "epoch": 2.08, + "learning_rate": 6.108757062146893e-06, + "loss": 0.4338, + "step": 25571 + }, + { + "epoch": 2.08, + "learning_rate": 6.108213820078227e-06, + "loss": 0.1867, + "step": 25572 + }, + { + "epoch": 2.08, + "learning_rate": 6.107670578009561e-06, + "loss": 0.0225, + "step": 25573 + }, + { + "epoch": 2.08, + "learning_rate": 6.107127335940895e-06, + "loss": 0.2291, + "step": 25574 + }, + { + "epoch": 2.08, + "learning_rate": 6.1065840938722295e-06, + "loss": 0.2126, + "step": 25575 + }, + { + "epoch": 2.08, + "learning_rate": 6.106040851803564e-06, + "loss": 0.3577, + "step": 25576 + }, + { + "epoch": 2.08, + "learning_rate": 6.105497609734898e-06, + "loss": 0.4108, + "step": 25577 + }, + { + "epoch": 2.08, + "learning_rate": 6.104954367666232e-06, + "loss": 0.1534, + "step": 25578 + }, + { + "epoch": 2.08, + "learning_rate": 6.1044111255975665e-06, + "loss": 0.1496, + "step": 25579 + }, + { + "epoch": 2.08, + "learning_rate": 6.1038678835289015e-06, + "loss": 0.2211, + "step": 25580 + }, + { + "epoch": 2.08, + "learning_rate": 6.103324641460236e-06, + "loss": 0.2288, + "step": 25581 + }, + { + "epoch": 2.08, + "learning_rate": 6.10278139939157e-06, + "loss": 0.2014, + "step": 25582 + }, + { + "epoch": 2.08, + "learning_rate": 6.102238157322904e-06, + "loss": 0.2895, + "step": 25583 + }, + { + "epoch": 2.08, + "learning_rate": 6.1016949152542385e-06, + "loss": 0.3635, + "step": 25584 + }, + { + "epoch": 2.08, + "learning_rate": 6.101151673185573e-06, + "loss": 0.4648, + "step": 25585 + }, + { + "epoch": 2.08, + "learning_rate": 6.100608431116907e-06, + "loss": 0.3925, + "step": 25586 + }, + { + "epoch": 2.08, + "learning_rate": 6.1000651890482395e-06, + "loss": 0.1094, + "step": 25587 + }, + { + "epoch": 2.09, + "learning_rate": 6.0995219469795745e-06, + "loss": 0.2177, + "step": 25588 + }, + { + "epoch": 2.09, + "learning_rate": 6.098978704910909e-06, + "loss": 0.3844, + "step": 25589 + }, + { + "epoch": 2.09, + "learning_rate": 6.098435462842243e-06, + "loss": 0.4285, + "step": 25590 + }, + { + "epoch": 2.09, + "learning_rate": 6.097892220773577e-06, + "loss": 0.2033, + "step": 25591 + }, + { + "epoch": 2.09, + "learning_rate": 6.0973489787049115e-06, + "loss": 0.2, + "step": 25592 + }, + { + "epoch": 2.09, + "learning_rate": 6.096805736636246e-06, + "loss": 0.6046, + "step": 25593 + }, + { + "epoch": 2.09, + "learning_rate": 6.09626249456758e-06, + "loss": 0.4054, + "step": 25594 + }, + { + "epoch": 2.09, + "learning_rate": 6.095719252498914e-06, + "loss": 0.3376, + "step": 25595 + }, + { + "epoch": 2.09, + "learning_rate": 6.095176010430248e-06, + "loss": 0.297, + "step": 25596 + }, + { + "epoch": 2.09, + "learning_rate": 6.094632768361583e-06, + "loss": 0.1302, + "step": 25597 + }, + { + "epoch": 2.09, + "learning_rate": 6.094089526292917e-06, + "loss": 0.3211, + "step": 25598 + }, + { + "epoch": 2.09, + "learning_rate": 6.093546284224251e-06, + "loss": 0.4478, + "step": 25599 + }, + { + "epoch": 2.09, + "learning_rate": 6.093003042155585e-06, + "loss": 0.2386, + "step": 25600 + }, + { + "epoch": 2.09, + "learning_rate": 6.0924598000869195e-06, + "loss": 0.1786, + "step": 25601 + }, + { + "epoch": 2.09, + "learning_rate": 6.091916558018254e-06, + "loss": 0.1617, + "step": 25602 + }, + { + "epoch": 2.09, + "learning_rate": 6.091373315949588e-06, + "loss": 0.2792, + "step": 25603 + }, + { + "epoch": 2.09, + "learning_rate": 6.090830073880922e-06, + "loss": 0.1721, + "step": 25604 + }, + { + "epoch": 2.09, + "learning_rate": 6.0902868318122565e-06, + "loss": 0.2313, + "step": 25605 + }, + { + "epoch": 2.09, + "learning_rate": 6.08974358974359e-06, + "loss": 0.0694, + "step": 25606 + }, + { + "epoch": 2.09, + "learning_rate": 6.089200347674924e-06, + "loss": 0.0926, + "step": 25607 + }, + { + "epoch": 2.09, + "learning_rate": 6.088657105606258e-06, + "loss": 0.2148, + "step": 25608 + }, + { + "epoch": 2.09, + "learning_rate": 6.0881138635375925e-06, + "loss": 0.2783, + "step": 25609 + }, + { + "epoch": 2.09, + "learning_rate": 6.087570621468927e-06, + "loss": 0.6045, + "step": 25610 + }, + { + "epoch": 2.09, + "learning_rate": 6.087027379400261e-06, + "loss": 0.1445, + "step": 25611 + }, + { + "epoch": 2.09, + "learning_rate": 6.086484137331595e-06, + "loss": 0.4045, + "step": 25612 + }, + { + "epoch": 2.09, + "learning_rate": 6.0859408952629295e-06, + "loss": 0.2737, + "step": 25613 + }, + { + "epoch": 2.09, + "learning_rate": 6.085397653194264e-06, + "loss": 0.1935, + "step": 25614 + }, + { + "epoch": 2.09, + "learning_rate": 6.084854411125598e-06, + "loss": 0.211, + "step": 25615 + }, + { + "epoch": 2.09, + "learning_rate": 6.084311169056932e-06, + "loss": 0.2299, + "step": 25616 + }, + { + "epoch": 2.09, + "learning_rate": 6.083767926988266e-06, + "loss": 0.2881, + "step": 25617 + }, + { + "epoch": 2.09, + "learning_rate": 6.083224684919601e-06, + "loss": 0.1255, + "step": 25618 + }, + { + "epoch": 2.09, + "learning_rate": 6.082681442850935e-06, + "loss": 0.2454, + "step": 25619 + }, + { + "epoch": 2.09, + "learning_rate": 6.082138200782269e-06, + "loss": 0.2394, + "step": 25620 + }, + { + "epoch": 2.09, + "learning_rate": 6.081594958713603e-06, + "loss": 0.1604, + "step": 25621 + }, + { + "epoch": 2.09, + "learning_rate": 6.0810517166449375e-06, + "loss": 0.1026, + "step": 25622 + }, + { + "epoch": 2.09, + "learning_rate": 6.080508474576272e-06, + "loss": 0.2052, + "step": 25623 + }, + { + "epoch": 2.09, + "learning_rate": 6.079965232507606e-06, + "loss": 0.2141, + "step": 25624 + }, + { + "epoch": 2.09, + "learning_rate": 6.079421990438939e-06, + "loss": 0.3924, + "step": 25625 + }, + { + "epoch": 2.09, + "learning_rate": 6.078878748370274e-06, + "loss": 0.1489, + "step": 25626 + }, + { + "epoch": 2.09, + "learning_rate": 6.078335506301608e-06, + "loss": 0.3106, + "step": 25627 + }, + { + "epoch": 2.09, + "learning_rate": 6.077792264232942e-06, + "loss": 0.2288, + "step": 25628 + }, + { + "epoch": 2.09, + "learning_rate": 6.077249022164276e-06, + "loss": 0.365, + "step": 25629 + }, + { + "epoch": 2.09, + "learning_rate": 6.0767057800956105e-06, + "loss": 0.2141, + "step": 25630 + }, + { + "epoch": 2.09, + "learning_rate": 6.076162538026945e-06, + "loss": 0.2163, + "step": 25631 + }, + { + "epoch": 2.09, + "learning_rate": 6.075619295958279e-06, + "loss": 0.1602, + "step": 25632 + }, + { + "epoch": 2.09, + "learning_rate": 6.075076053889613e-06, + "loss": 0.2757, + "step": 25633 + }, + { + "epoch": 2.09, + "learning_rate": 6.074532811820948e-06, + "loss": 0.3794, + "step": 25634 + }, + { + "epoch": 2.09, + "learning_rate": 6.0739895697522825e-06, + "loss": 0.2425, + "step": 25635 + }, + { + "epoch": 2.09, + "learning_rate": 6.073446327683617e-06, + "loss": 0.4144, + "step": 25636 + }, + { + "epoch": 2.09, + "learning_rate": 6.072903085614951e-06, + "loss": 0.1482, + "step": 25637 + }, + { + "epoch": 2.09, + "learning_rate": 6.072359843546285e-06, + "loss": 0.2815, + "step": 25638 + }, + { + "epoch": 2.09, + "learning_rate": 6.0718166014776194e-06, + "loss": 0.1676, + "step": 25639 + }, + { + "epoch": 2.09, + "learning_rate": 6.071273359408954e-06, + "loss": 0.212, + "step": 25640 + }, + { + "epoch": 2.09, + "learning_rate": 6.070730117340288e-06, + "loss": 0.2546, + "step": 25641 + }, + { + "epoch": 2.09, + "learning_rate": 6.070186875271622e-06, + "loss": 0.1842, + "step": 25642 + }, + { + "epoch": 2.09, + "learning_rate": 6.069643633202956e-06, + "loss": 0.1578, + "step": 25643 + }, + { + "epoch": 2.09, + "learning_rate": 6.06910039113429e-06, + "loss": 0.1578, + "step": 25644 + }, + { + "epoch": 2.09, + "learning_rate": 6.068557149065624e-06, + "loss": 0.2961, + "step": 25645 + }, + { + "epoch": 2.09, + "learning_rate": 6.068013906996958e-06, + "loss": 0.2196, + "step": 25646 + }, + { + "epoch": 2.09, + "learning_rate": 6.0674706649282924e-06, + "loss": 0.2805, + "step": 25647 + }, + { + "epoch": 2.09, + "learning_rate": 6.066927422859627e-06, + "loss": 0.1403, + "step": 25648 + }, + { + "epoch": 2.09, + "learning_rate": 6.066384180790961e-06, + "loss": 0.0608, + "step": 25649 + }, + { + "epoch": 2.09, + "learning_rate": 6.065840938722295e-06, + "loss": 0.1938, + "step": 25650 + }, + { + "epoch": 2.09, + "learning_rate": 6.065297696653629e-06, + "loss": 0.1348, + "step": 25651 + }, + { + "epoch": 2.09, + "learning_rate": 6.064754454584964e-06, + "loss": 0.1394, + "step": 25652 + }, + { + "epoch": 2.09, + "learning_rate": 6.064211212516298e-06, + "loss": 0.7023, + "step": 25653 + }, + { + "epoch": 2.09, + "learning_rate": 6.063667970447632e-06, + "loss": 0.1696, + "step": 25654 + }, + { + "epoch": 2.09, + "learning_rate": 6.063124728378966e-06, + "loss": 0.3871, + "step": 25655 + }, + { + "epoch": 2.09, + "learning_rate": 6.0625814863103005e-06, + "loss": 0.3166, + "step": 25656 + }, + { + "epoch": 2.09, + "learning_rate": 6.062038244241635e-06, + "loss": 0.1964, + "step": 25657 + }, + { + "epoch": 2.09, + "learning_rate": 6.061495002172969e-06, + "loss": 0.3658, + "step": 25658 + }, + { + "epoch": 2.09, + "learning_rate": 6.060951760104303e-06, + "loss": 0.2754, + "step": 25659 + }, + { + "epoch": 2.09, + "learning_rate": 6.0604085180356374e-06, + "loss": 0.3607, + "step": 25660 + }, + { + "epoch": 2.09, + "learning_rate": 6.059865275966972e-06, + "loss": 0.1502, + "step": 25661 + }, + { + "epoch": 2.09, + "learning_rate": 6.059322033898306e-06, + "loss": 0.4141, + "step": 25662 + }, + { + "epoch": 2.09, + "learning_rate": 6.058778791829639e-06, + "loss": 0.2099, + "step": 25663 + }, + { + "epoch": 2.09, + "learning_rate": 6.0582355497609735e-06, + "loss": 0.1914, + "step": 25664 + }, + { + "epoch": 2.09, + "learning_rate": 6.057692307692308e-06, + "loss": 0.1852, + "step": 25665 + }, + { + "epoch": 2.09, + "learning_rate": 6.057149065623642e-06, + "loss": 0.2496, + "step": 25666 + }, + { + "epoch": 2.09, + "learning_rate": 6.056605823554976e-06, + "loss": 0.3041, + "step": 25667 + }, + { + "epoch": 2.09, + "learning_rate": 6.0560625814863104e-06, + "loss": 0.1929, + "step": 25668 + }, + { + "epoch": 2.09, + "learning_rate": 6.055519339417645e-06, + "loss": 0.3123, + "step": 25669 + }, + { + "epoch": 2.09, + "learning_rate": 6.054976097348979e-06, + "loss": 0.033, + "step": 25670 + }, + { + "epoch": 2.09, + "learning_rate": 6.054432855280313e-06, + "loss": 0.1352, + "step": 25671 + }, + { + "epoch": 2.09, + "learning_rate": 6.053889613211647e-06, + "loss": 0.2576, + "step": 25672 + }, + { + "epoch": 2.09, + "learning_rate": 6.053346371142982e-06, + "loss": 0.2444, + "step": 25673 + }, + { + "epoch": 2.09, + "learning_rate": 6.052803129074316e-06, + "loss": 0.1518, + "step": 25674 + }, + { + "epoch": 2.09, + "learning_rate": 6.05225988700565e-06, + "loss": 0.0477, + "step": 25675 + }, + { + "epoch": 2.09, + "learning_rate": 6.051716644936984e-06, + "loss": 0.1814, + "step": 25676 + }, + { + "epoch": 2.09, + "learning_rate": 6.0511734028683185e-06, + "loss": 0.1639, + "step": 25677 + }, + { + "epoch": 2.09, + "learning_rate": 6.050630160799653e-06, + "loss": 0.3497, + "step": 25678 + }, + { + "epoch": 2.09, + "learning_rate": 6.050086918730988e-06, + "loss": 0.3135, + "step": 25679 + }, + { + "epoch": 2.09, + "learning_rate": 6.049543676662322e-06, + "loss": 0.4633, + "step": 25680 + }, + { + "epoch": 2.09, + "learning_rate": 6.049000434593656e-06, + "loss": 0.2973, + "step": 25681 + }, + { + "epoch": 2.09, + "learning_rate": 6.048457192524989e-06, + "loss": 0.1374, + "step": 25682 + }, + { + "epoch": 2.09, + "learning_rate": 6.047913950456323e-06, + "loss": 0.3383, + "step": 25683 + }, + { + "epoch": 2.09, + "learning_rate": 6.047370708387657e-06, + "loss": 0.0942, + "step": 25684 + }, + { + "epoch": 2.09, + "learning_rate": 6.0468274663189915e-06, + "loss": 0.315, + "step": 25685 + }, + { + "epoch": 2.09, + "learning_rate": 6.046284224250326e-06, + "loss": 0.43, + "step": 25686 + }, + { + "epoch": 2.09, + "learning_rate": 6.04574098218166e-06, + "loss": 0.281, + "step": 25687 + }, + { + "epoch": 2.09, + "learning_rate": 6.045197740112995e-06, + "loss": 0.027, + "step": 25688 + }, + { + "epoch": 2.09, + "learning_rate": 6.044654498044329e-06, + "loss": 0.5639, + "step": 25689 + }, + { + "epoch": 2.09, + "learning_rate": 6.0441112559756635e-06, + "loss": 0.3084, + "step": 25690 + }, + { + "epoch": 2.09, + "learning_rate": 6.043568013906998e-06, + "loss": 0.3999, + "step": 25691 + }, + { + "epoch": 2.09, + "learning_rate": 6.043024771838332e-06, + "loss": 0.1672, + "step": 25692 + }, + { + "epoch": 2.09, + "learning_rate": 6.042481529769666e-06, + "loss": 0.3636, + "step": 25693 + }, + { + "epoch": 2.09, + "learning_rate": 6.0419382877010004e-06, + "loss": 0.134, + "step": 25694 + }, + { + "epoch": 2.09, + "learning_rate": 6.041395045632335e-06, + "loss": 0.3382, + "step": 25695 + }, + { + "epoch": 2.09, + "learning_rate": 6.040851803563669e-06, + "loss": 0.1524, + "step": 25696 + }, + { + "epoch": 2.09, + "learning_rate": 6.040308561495003e-06, + "loss": 0.1858, + "step": 25697 + }, + { + "epoch": 2.09, + "learning_rate": 6.039765319426337e-06, + "loss": 0.096, + "step": 25698 + }, + { + "epoch": 2.09, + "learning_rate": 6.039222077357672e-06, + "loss": 0.3787, + "step": 25699 + }, + { + "epoch": 2.09, + "learning_rate": 6.038678835289006e-06, + "loss": 0.1619, + "step": 25700 + }, + { + "epoch": 2.09, + "learning_rate": 6.038135593220339e-06, + "loss": 0.2797, + "step": 25701 + }, + { + "epoch": 2.09, + "learning_rate": 6.0375923511516734e-06, + "loss": 0.1764, + "step": 25702 + }, + { + "epoch": 2.09, + "learning_rate": 6.037049109083008e-06, + "loss": 0.1658, + "step": 25703 + }, + { + "epoch": 2.09, + "learning_rate": 6.036505867014342e-06, + "loss": 0.1409, + "step": 25704 + }, + { + "epoch": 2.09, + "learning_rate": 6.035962624945676e-06, + "loss": 0.3305, + "step": 25705 + }, + { + "epoch": 2.09, + "learning_rate": 6.03541938287701e-06, + "loss": 0.3014, + "step": 25706 + }, + { + "epoch": 2.09, + "learning_rate": 6.034876140808345e-06, + "loss": 0.1714, + "step": 25707 + }, + { + "epoch": 2.09, + "learning_rate": 6.034332898739679e-06, + "loss": 0.1292, + "step": 25708 + }, + { + "epoch": 2.09, + "learning_rate": 6.033789656671013e-06, + "loss": 0.3055, + "step": 25709 + }, + { + "epoch": 2.1, + "learning_rate": 6.033246414602347e-06, + "loss": 0.2463, + "step": 25710 + }, + { + "epoch": 2.1, + "learning_rate": 6.0327031725336815e-06, + "loss": 0.1247, + "step": 25711 + }, + { + "epoch": 2.1, + "learning_rate": 6.032159930465016e-06, + "loss": 0.2138, + "step": 25712 + }, + { + "epoch": 2.1, + "learning_rate": 6.03161668839635e-06, + "loss": 0.2546, + "step": 25713 + }, + { + "epoch": 2.1, + "learning_rate": 6.031073446327684e-06, + "loss": 0.1303, + "step": 25714 + }, + { + "epoch": 2.1, + "learning_rate": 6.0305302042590184e-06, + "loss": 0.3059, + "step": 25715 + }, + { + "epoch": 2.1, + "learning_rate": 6.029986962190353e-06, + "loss": 0.2793, + "step": 25716 + }, + { + "epoch": 2.1, + "learning_rate": 6.029443720121687e-06, + "loss": 0.2652, + "step": 25717 + }, + { + "epoch": 2.1, + "learning_rate": 6.028900478053021e-06, + "loss": 0.315, + "step": 25718 + }, + { + "epoch": 2.1, + "learning_rate": 6.028357235984355e-06, + "loss": 0.3283, + "step": 25719 + }, + { + "epoch": 2.1, + "learning_rate": 6.027813993915689e-06, + "loss": 0.1975, + "step": 25720 + }, + { + "epoch": 2.1, + "learning_rate": 6.027270751847023e-06, + "loss": 0.3647, + "step": 25721 + }, + { + "epoch": 2.1, + "learning_rate": 6.026727509778357e-06, + "loss": 0.3219, + "step": 25722 + }, + { + "epoch": 2.1, + "learning_rate": 6.0261842677096914e-06, + "loss": 0.3001, + "step": 25723 + }, + { + "epoch": 2.1, + "learning_rate": 6.025641025641026e-06, + "loss": 0.1422, + "step": 25724 + }, + { + "epoch": 2.1, + "learning_rate": 6.02509778357236e-06, + "loss": 0.2253, + "step": 25725 + }, + { + "epoch": 2.1, + "learning_rate": 6.024554541503694e-06, + "loss": 0.1697, + "step": 25726 + }, + { + "epoch": 2.1, + "learning_rate": 6.024011299435028e-06, + "loss": 0.1493, + "step": 25727 + }, + { + "epoch": 2.1, + "learning_rate": 6.023468057366363e-06, + "loss": 0.2857, + "step": 25728 + }, + { + "epoch": 2.1, + "learning_rate": 6.022924815297697e-06, + "loss": 0.1365, + "step": 25729 + }, + { + "epoch": 2.1, + "learning_rate": 6.022381573229031e-06, + "loss": 0.0927, + "step": 25730 + }, + { + "epoch": 2.1, + "learning_rate": 6.021838331160365e-06, + "loss": 0.1839, + "step": 25731 + }, + { + "epoch": 2.1, + "learning_rate": 6.0212950890916995e-06, + "loss": 0.3704, + "step": 25732 + }, + { + "epoch": 2.1, + "learning_rate": 6.020751847023035e-06, + "loss": 0.3379, + "step": 25733 + }, + { + "epoch": 2.1, + "learning_rate": 6.020208604954369e-06, + "loss": 0.1334, + "step": 25734 + }, + { + "epoch": 2.1, + "learning_rate": 6.019665362885703e-06, + "loss": 0.292, + "step": 25735 + }, + { + "epoch": 2.1, + "learning_rate": 6.019122120817037e-06, + "loss": 0.1022, + "step": 25736 + }, + { + "epoch": 2.1, + "learning_rate": 6.0185788787483715e-06, + "loss": 0.2109, + "step": 25737 + }, + { + "epoch": 2.1, + "learning_rate": 6.018035636679706e-06, + "loss": 0.209, + "step": 25738 + }, + { + "epoch": 2.1, + "learning_rate": 6.017492394611038e-06, + "loss": 0.1963, + "step": 25739 + }, + { + "epoch": 2.1, + "learning_rate": 6.0169491525423725e-06, + "loss": 0.1016, + "step": 25740 + }, + { + "epoch": 2.1, + "learning_rate": 6.016405910473707e-06, + "loss": 0.0369, + "step": 25741 + }, + { + "epoch": 2.1, + "learning_rate": 6.015862668405042e-06, + "loss": 0.1773, + "step": 25742 + }, + { + "epoch": 2.1, + "learning_rate": 6.015319426336376e-06, + "loss": 0.5482, + "step": 25743 + }, + { + "epoch": 2.1, + "learning_rate": 6.01477618426771e-06, + "loss": 0.1829, + "step": 25744 + }, + { + "epoch": 2.1, + "learning_rate": 6.0142329421990445e-06, + "loss": 0.2019, + "step": 25745 + }, + { + "epoch": 2.1, + "learning_rate": 6.013689700130379e-06, + "loss": 0.2859, + "step": 25746 + }, + { + "epoch": 2.1, + "learning_rate": 6.013146458061713e-06, + "loss": 0.1808, + "step": 25747 + }, + { + "epoch": 2.1, + "learning_rate": 6.012603215993047e-06, + "loss": 0.0977, + "step": 25748 + }, + { + "epoch": 2.1, + "learning_rate": 6.012059973924381e-06, + "loss": 0.2432, + "step": 25749 + }, + { + "epoch": 2.1, + "learning_rate": 6.011516731855716e-06, + "loss": 0.1821, + "step": 25750 + }, + { + "epoch": 2.1, + "eval_accuracy": 0.841365257259297, + "eval_loss": 0.4912662208080292, + "eval_runtime": 22.29, + "eval_samples_per_second": 440.332, + "eval_steps_per_second": 3.454, + "step": 25750 + }, + { + "epoch": 2.1, + "learning_rate": 6.01097348978705e-06, + "loss": 0.2556, + "step": 25751 + }, + { + "epoch": 2.1, + "learning_rate": 6.010430247718384e-06, + "loss": 0.6257, + "step": 25752 + }, + { + "epoch": 2.1, + "learning_rate": 6.009887005649718e-06, + "loss": 0.2877, + "step": 25753 + }, + { + "epoch": 2.1, + "learning_rate": 6.0093437635810526e-06, + "loss": 0.1622, + "step": 25754 + }, + { + "epoch": 2.1, + "learning_rate": 6.008800521512387e-06, + "loss": 0.046, + "step": 25755 + }, + { + "epoch": 2.1, + "learning_rate": 6.008257279443721e-06, + "loss": 0.1192, + "step": 25756 + }, + { + "epoch": 2.1, + "learning_rate": 6.007714037375055e-06, + "loss": 0.1923, + "step": 25757 + }, + { + "epoch": 2.1, + "learning_rate": 6.007170795306389e-06, + "loss": 0.3562, + "step": 25758 + }, + { + "epoch": 2.1, + "learning_rate": 6.006627553237723e-06, + "loss": 0.2939, + "step": 25759 + }, + { + "epoch": 2.1, + "learning_rate": 6.006084311169057e-06, + "loss": 0.2009, + "step": 25760 + }, + { + "epoch": 2.1, + "learning_rate": 6.005541069100391e-06, + "loss": 0.2969, + "step": 25761 + }, + { + "epoch": 2.1, + "learning_rate": 6.0049978270317256e-06, + "loss": 0.0585, + "step": 25762 + }, + { + "epoch": 2.1, + "learning_rate": 6.00445458496306e-06, + "loss": 0.1181, + "step": 25763 + }, + { + "epoch": 2.1, + "learning_rate": 6.003911342894394e-06, + "loss": 0.2209, + "step": 25764 + }, + { + "epoch": 2.1, + "learning_rate": 6.003368100825728e-06, + "loss": 0.2109, + "step": 25765 + }, + { + "epoch": 2.1, + "learning_rate": 6.0028248587570625e-06, + "loss": 0.2064, + "step": 25766 + }, + { + "epoch": 2.1, + "learning_rate": 6.002281616688397e-06, + "loss": 0.1326, + "step": 25767 + }, + { + "epoch": 2.1, + "learning_rate": 6.001738374619731e-06, + "loss": 0.2251, + "step": 25768 + }, + { + "epoch": 2.1, + "learning_rate": 6.001195132551065e-06, + "loss": 0.2499, + "step": 25769 + }, + { + "epoch": 2.1, + "learning_rate": 6.000651890482399e-06, + "loss": 0.3182, + "step": 25770 + }, + { + "epoch": 2.1, + "learning_rate": 6.000108648413734e-06, + "loss": 0.0894, + "step": 25771 + }, + { + "epoch": 2.1, + "learning_rate": 5.999565406345068e-06, + "loss": 0.1446, + "step": 25772 + }, + { + "epoch": 2.1, + "learning_rate": 5.999022164276402e-06, + "loss": 0.401, + "step": 25773 + }, + { + "epoch": 2.1, + "learning_rate": 5.998478922207736e-06, + "loss": 0.5721, + "step": 25774 + }, + { + "epoch": 2.1, + "learning_rate": 5.9979356801390706e-06, + "loss": 0.2957, + "step": 25775 + }, + { + "epoch": 2.1, + "learning_rate": 5.997392438070405e-06, + "loss": 0.1251, + "step": 25776 + }, + { + "epoch": 2.1, + "learning_rate": 5.996849196001738e-06, + "loss": 0.2412, + "step": 25777 + }, + { + "epoch": 2.1, + "learning_rate": 5.996305953933072e-06, + "loss": 0.1994, + "step": 25778 + }, + { + "epoch": 2.1, + "learning_rate": 5.995762711864407e-06, + "loss": 0.316, + "step": 25779 + }, + { + "epoch": 2.1, + "learning_rate": 5.995219469795741e-06, + "loss": 0.1009, + "step": 25780 + }, + { + "epoch": 2.1, + "learning_rate": 5.994676227727075e-06, + "loss": 0.2236, + "step": 25781 + }, + { + "epoch": 2.1, + "learning_rate": 5.994132985658409e-06, + "loss": 0.7017, + "step": 25782 + }, + { + "epoch": 2.1, + "learning_rate": 5.9935897435897436e-06, + "loss": 0.2723, + "step": 25783 + }, + { + "epoch": 2.1, + "learning_rate": 5.993046501521078e-06, + "loss": 0.0944, + "step": 25784 + }, + { + "epoch": 2.1, + "learning_rate": 5.992503259452412e-06, + "loss": 0.2625, + "step": 25785 + }, + { + "epoch": 2.1, + "learning_rate": 5.991960017383746e-06, + "loss": 0.2893, + "step": 25786 + }, + { + "epoch": 2.1, + "learning_rate": 5.991416775315081e-06, + "loss": 0.0602, + "step": 25787 + }, + { + "epoch": 2.1, + "learning_rate": 5.9908735332464156e-06, + "loss": 0.27, + "step": 25788 + }, + { + "epoch": 2.1, + "learning_rate": 5.99033029117775e-06, + "loss": 0.1809, + "step": 25789 + }, + { + "epoch": 2.1, + "learning_rate": 5.989787049109084e-06, + "loss": 0.5005, + "step": 25790 + }, + { + "epoch": 2.1, + "learning_rate": 5.989243807040418e-06, + "loss": 0.1348, + "step": 25791 + }, + { + "epoch": 2.1, + "learning_rate": 5.9887005649717525e-06, + "loss": 0.1613, + "step": 25792 + }, + { + "epoch": 2.1, + "learning_rate": 5.988157322903087e-06, + "loss": 0.1014, + "step": 25793 + }, + { + "epoch": 2.1, + "learning_rate": 5.987614080834421e-06, + "loss": 0.2538, + "step": 25794 + }, + { + "epoch": 2.1, + "learning_rate": 5.987070838765755e-06, + "loss": 0.1425, + "step": 25795 + }, + { + "epoch": 2.1, + "learning_rate": 5.9865275966970886e-06, + "loss": 0.2183, + "step": 25796 + }, + { + "epoch": 2.1, + "learning_rate": 5.985984354628423e-06, + "loss": 0.4336, + "step": 25797 + }, + { + "epoch": 2.1, + "learning_rate": 5.985441112559757e-06, + "loss": 0.4097, + "step": 25798 + }, + { + "epoch": 2.1, + "learning_rate": 5.984897870491091e-06, + "loss": 0.1288, + "step": 25799 + }, + { + "epoch": 2.1, + "learning_rate": 5.9843546284224255e-06, + "loss": 0.262, + "step": 25800 + }, + { + "epoch": 2.1, + "learning_rate": 5.98381138635376e-06, + "loss": 0.2524, + "step": 25801 + }, + { + "epoch": 2.1, + "learning_rate": 5.983268144285094e-06, + "loss": 0.1627, + "step": 25802 + }, + { + "epoch": 2.1, + "learning_rate": 5.982724902216428e-06, + "loss": 0.2737, + "step": 25803 + }, + { + "epoch": 2.1, + "learning_rate": 5.982181660147762e-06, + "loss": 0.0723, + "step": 25804 + }, + { + "epoch": 2.1, + "learning_rate": 5.981638418079097e-06, + "loss": 0.1776, + "step": 25805 + }, + { + "epoch": 2.1, + "learning_rate": 5.981095176010431e-06, + "loss": 0.3472, + "step": 25806 + }, + { + "epoch": 2.1, + "learning_rate": 5.980551933941765e-06, + "loss": 0.1152, + "step": 25807 + }, + { + "epoch": 2.1, + "learning_rate": 5.980008691873099e-06, + "loss": 0.1559, + "step": 25808 + }, + { + "epoch": 2.1, + "learning_rate": 5.9794654498044336e-06, + "loss": 0.1568, + "step": 25809 + }, + { + "epoch": 2.1, + "learning_rate": 5.978922207735768e-06, + "loss": 0.2027, + "step": 25810 + }, + { + "epoch": 2.1, + "learning_rate": 5.978378965667102e-06, + "loss": 0.296, + "step": 25811 + }, + { + "epoch": 2.1, + "learning_rate": 5.977835723598436e-06, + "loss": 0.152, + "step": 25812 + }, + { + "epoch": 2.1, + "learning_rate": 5.9772924815297705e-06, + "loss": 0.239, + "step": 25813 + }, + { + "epoch": 2.1, + "learning_rate": 5.976749239461105e-06, + "loss": 0.0851, + "step": 25814 + }, + { + "epoch": 2.1, + "learning_rate": 5.976205997392438e-06, + "loss": 0.1853, + "step": 25815 + }, + { + "epoch": 2.1, + "learning_rate": 5.975662755323772e-06, + "loss": 0.3452, + "step": 25816 + }, + { + "epoch": 2.1, + "learning_rate": 5.9751195132551066e-06, + "loss": 0.155, + "step": 25817 + }, + { + "epoch": 2.1, + "learning_rate": 5.974576271186441e-06, + "loss": 0.2156, + "step": 25818 + }, + { + "epoch": 2.1, + "learning_rate": 5.974033029117775e-06, + "loss": 0.1784, + "step": 25819 + }, + { + "epoch": 2.1, + "learning_rate": 5.973489787049109e-06, + "loss": 0.3065, + "step": 25820 + }, + { + "epoch": 2.1, + "learning_rate": 5.9729465449804435e-06, + "loss": 0.3886, + "step": 25821 + }, + { + "epoch": 2.1, + "learning_rate": 5.972403302911778e-06, + "loss": 0.3201, + "step": 25822 + }, + { + "epoch": 2.1, + "learning_rate": 5.971860060843112e-06, + "loss": 0.5159, + "step": 25823 + }, + { + "epoch": 2.1, + "learning_rate": 5.971316818774446e-06, + "loss": 0.3145, + "step": 25824 + }, + { + "epoch": 2.1, + "learning_rate": 5.97077357670578e-06, + "loss": 0.2438, + "step": 25825 + }, + { + "epoch": 2.1, + "learning_rate": 5.970230334637115e-06, + "loss": 0.2037, + "step": 25826 + }, + { + "epoch": 2.1, + "learning_rate": 5.969687092568449e-06, + "loss": 0.3993, + "step": 25827 + }, + { + "epoch": 2.1, + "learning_rate": 5.969143850499783e-06, + "loss": 0.2115, + "step": 25828 + }, + { + "epoch": 2.1, + "learning_rate": 5.968600608431117e-06, + "loss": 0.2167, + "step": 25829 + }, + { + "epoch": 2.1, + "learning_rate": 5.9680573663624516e-06, + "loss": 0.0718, + "step": 25830 + }, + { + "epoch": 2.1, + "learning_rate": 5.967514124293786e-06, + "loss": 0.247, + "step": 25831 + }, + { + "epoch": 2.1, + "learning_rate": 5.966970882225121e-06, + "loss": 0.2972, + "step": 25832 + }, + { + "epoch": 2.11, + "learning_rate": 5.966427640156455e-06, + "loss": 0.2058, + "step": 25833 + }, + { + "epoch": 2.11, + "learning_rate": 5.965884398087788e-06, + "loss": 0.3034, + "step": 25834 + }, + { + "epoch": 2.11, + "learning_rate": 5.965341156019122e-06, + "loss": 0.2898, + "step": 25835 + }, + { + "epoch": 2.11, + "learning_rate": 5.964797913950456e-06, + "loss": 0.1127, + "step": 25836 + }, + { + "epoch": 2.11, + "learning_rate": 5.96425467188179e-06, + "loss": 0.2929, + "step": 25837 + }, + { + "epoch": 2.11, + "learning_rate": 5.9637114298131246e-06, + "loss": 0.3335, + "step": 25838 + }, + { + "epoch": 2.11, + "learning_rate": 5.963168187744459e-06, + "loss": 0.1137, + "step": 25839 + }, + { + "epoch": 2.11, + "learning_rate": 5.962624945675793e-06, + "loss": 0.2115, + "step": 25840 + }, + { + "epoch": 2.11, + "learning_rate": 5.962081703607128e-06, + "loss": 0.2366, + "step": 25841 + }, + { + "epoch": 2.11, + "learning_rate": 5.961538461538462e-06, + "loss": 0.1538, + "step": 25842 + }, + { + "epoch": 2.11, + "learning_rate": 5.9609952194697965e-06, + "loss": 0.0817, + "step": 25843 + }, + { + "epoch": 2.11, + "learning_rate": 5.960451977401131e-06, + "loss": 0.175, + "step": 25844 + }, + { + "epoch": 2.11, + "learning_rate": 5.959908735332465e-06, + "loss": 0.0961, + "step": 25845 + }, + { + "epoch": 2.11, + "learning_rate": 5.959365493263799e-06, + "loss": 0.2305, + "step": 25846 + }, + { + "epoch": 2.11, + "learning_rate": 5.9588222511951335e-06, + "loss": 0.3521, + "step": 25847 + }, + { + "epoch": 2.11, + "learning_rate": 5.958279009126468e-06, + "loss": 0.1001, + "step": 25848 + }, + { + "epoch": 2.11, + "learning_rate": 5.957735767057802e-06, + "loss": 0.4559, + "step": 25849 + }, + { + "epoch": 2.11, + "learning_rate": 5.957192524989136e-06, + "loss": 0.2452, + "step": 25850 + }, + { + "epoch": 2.11, + "learning_rate": 5.95664928292047e-06, + "loss": 0.386, + "step": 25851 + }, + { + "epoch": 2.11, + "learning_rate": 5.956106040851805e-06, + "loss": 0.2708, + "step": 25852 + }, + { + "epoch": 2.11, + "learning_rate": 5.955562798783138e-06, + "loss": 0.2809, + "step": 25853 + }, + { + "epoch": 2.11, + "learning_rate": 5.955019556714472e-06, + "loss": 0.1564, + "step": 25854 + }, + { + "epoch": 2.11, + "learning_rate": 5.9544763146458065e-06, + "loss": 0.4022, + "step": 25855 + }, + { + "epoch": 2.11, + "learning_rate": 5.953933072577141e-06, + "loss": 0.2816, + "step": 25856 + }, + { + "epoch": 2.11, + "learning_rate": 5.953389830508475e-06, + "loss": 0.5649, + "step": 25857 + }, + { + "epoch": 2.11, + "learning_rate": 5.952846588439809e-06, + "loss": 0.2323, + "step": 25858 + }, + { + "epoch": 2.11, + "learning_rate": 5.952303346371143e-06, + "loss": 0.1519, + "step": 25859 + }, + { + "epoch": 2.11, + "learning_rate": 5.951760104302478e-06, + "loss": 0.1464, + "step": 25860 + }, + { + "epoch": 2.11, + "learning_rate": 5.951216862233812e-06, + "loss": 0.3585, + "step": 25861 + }, + { + "epoch": 2.11, + "learning_rate": 5.950673620165146e-06, + "loss": 0.5817, + "step": 25862 + }, + { + "epoch": 2.11, + "learning_rate": 5.95013037809648e-06, + "loss": 0.1368, + "step": 25863 + }, + { + "epoch": 2.11, + "learning_rate": 5.9495871360278145e-06, + "loss": 0.0913, + "step": 25864 + }, + { + "epoch": 2.11, + "learning_rate": 5.949043893959149e-06, + "loss": 0.2498, + "step": 25865 + }, + { + "epoch": 2.11, + "learning_rate": 5.948500651890483e-06, + "loss": 0.1738, + "step": 25866 + }, + { + "epoch": 2.11, + "learning_rate": 5.947957409821817e-06, + "loss": 0.1984, + "step": 25867 + }, + { + "epoch": 2.11, + "learning_rate": 5.9474141677531515e-06, + "loss": 0.2283, + "step": 25868 + }, + { + "epoch": 2.11, + "learning_rate": 5.946870925684486e-06, + "loss": 0.1307, + "step": 25869 + }, + { + "epoch": 2.11, + "learning_rate": 5.94632768361582e-06, + "loss": 0.2766, + "step": 25870 + }, + { + "epoch": 2.11, + "learning_rate": 5.945784441547154e-06, + "loss": 0.2421, + "step": 25871 + }, + { + "epoch": 2.11, + "learning_rate": 5.9452411994784875e-06, + "loss": 0.2855, + "step": 25872 + }, + { + "epoch": 2.11, + "learning_rate": 5.944697957409822e-06, + "loss": 0.1413, + "step": 25873 + }, + { + "epoch": 2.11, + "learning_rate": 5.944154715341156e-06, + "loss": 0.2982, + "step": 25874 + }, + { + "epoch": 2.11, + "learning_rate": 5.94361147327249e-06, + "loss": 0.2118, + "step": 25875 + }, + { + "epoch": 2.11, + "learning_rate": 5.9430682312038245e-06, + "loss": 0.1218, + "step": 25876 + }, + { + "epoch": 2.11, + "learning_rate": 5.942524989135159e-06, + "loss": 0.2649, + "step": 25877 + }, + { + "epoch": 2.11, + "learning_rate": 5.941981747066493e-06, + "loss": 0.265, + "step": 25878 + }, + { + "epoch": 2.11, + "learning_rate": 5.941438504997827e-06, + "loss": 0.195, + "step": 25879 + }, + { + "epoch": 2.11, + "learning_rate": 5.940895262929161e-06, + "loss": 0.4163, + "step": 25880 + }, + { + "epoch": 2.11, + "learning_rate": 5.940352020860496e-06, + "loss": 0.0708, + "step": 25881 + }, + { + "epoch": 2.11, + "learning_rate": 5.93980877879183e-06, + "loss": 0.1624, + "step": 25882 + }, + { + "epoch": 2.11, + "learning_rate": 5.939265536723164e-06, + "loss": 0.1191, + "step": 25883 + }, + { + "epoch": 2.11, + "learning_rate": 5.938722294654498e-06, + "loss": 0.1563, + "step": 25884 + }, + { + "epoch": 2.11, + "learning_rate": 5.9381790525858325e-06, + "loss": 0.088, + "step": 25885 + }, + { + "epoch": 2.11, + "learning_rate": 5.937635810517168e-06, + "loss": 0.1057, + "step": 25886 + }, + { + "epoch": 2.11, + "learning_rate": 5.937092568448502e-06, + "loss": 0.3572, + "step": 25887 + }, + { + "epoch": 2.11, + "learning_rate": 5.936549326379836e-06, + "loss": 0.1172, + "step": 25888 + }, + { + "epoch": 2.11, + "learning_rate": 5.93600608431117e-06, + "loss": 0.2074, + "step": 25889 + }, + { + "epoch": 2.11, + "learning_rate": 5.9354628422425045e-06, + "loss": 0.1722, + "step": 25890 + }, + { + "epoch": 2.11, + "learning_rate": 5.934919600173839e-06, + "loss": 0.1832, + "step": 25891 + }, + { + "epoch": 2.11, + "learning_rate": 5.934376358105171e-06, + "loss": 0.1431, + "step": 25892 + }, + { + "epoch": 2.11, + "learning_rate": 5.9338331160365055e-06, + "loss": 0.1773, + "step": 25893 + }, + { + "epoch": 2.11, + "learning_rate": 5.93328987396784e-06, + "loss": 0.3492, + "step": 25894 + }, + { + "epoch": 2.11, + "learning_rate": 5.932746631899175e-06, + "loss": 0.2672, + "step": 25895 + }, + { + "epoch": 2.11, + "learning_rate": 5.932203389830509e-06, + "loss": 0.1138, + "step": 25896 + }, + { + "epoch": 2.11, + "learning_rate": 5.931660147761843e-06, + "loss": 0.3002, + "step": 25897 + }, + { + "epoch": 2.11, + "learning_rate": 5.9311169056931775e-06, + "loss": 0.1563, + "step": 25898 + }, + { + "epoch": 2.11, + "learning_rate": 5.930573663624512e-06, + "loss": 0.2908, + "step": 25899 + }, + { + "epoch": 2.11, + "learning_rate": 5.930030421555846e-06, + "loss": 0.1692, + "step": 25900 + }, + { + "epoch": 2.11, + "learning_rate": 5.92948717948718e-06, + "loss": 0.0593, + "step": 25901 + }, + { + "epoch": 2.11, + "learning_rate": 5.9289439374185145e-06, + "loss": 0.3494, + "step": 25902 + }, + { + "epoch": 2.11, + "learning_rate": 5.928400695349849e-06, + "loss": 0.1755, + "step": 25903 + }, + { + "epoch": 2.11, + "learning_rate": 5.927857453281183e-06, + "loss": 0.2677, + "step": 25904 + }, + { + "epoch": 2.11, + "learning_rate": 5.927314211212517e-06, + "loss": 0.2813, + "step": 25905 + }, + { + "epoch": 2.11, + "learning_rate": 5.926770969143851e-06, + "loss": 0.2066, + "step": 25906 + }, + { + "epoch": 2.11, + "learning_rate": 5.926227727075186e-06, + "loss": 0.2664, + "step": 25907 + }, + { + "epoch": 2.11, + "learning_rate": 5.92568448500652e-06, + "loss": 0.0955, + "step": 25908 + }, + { + "epoch": 2.11, + "learning_rate": 5.925141242937854e-06, + "loss": 0.295, + "step": 25909 + }, + { + "epoch": 2.11, + "learning_rate": 5.924598000869188e-06, + "loss": 0.1326, + "step": 25910 + }, + { + "epoch": 2.11, + "learning_rate": 5.924054758800522e-06, + "loss": 0.2158, + "step": 25911 + }, + { + "epoch": 2.11, + "learning_rate": 5.923511516731856e-06, + "loss": 0.1774, + "step": 25912 + }, + { + "epoch": 2.11, + "learning_rate": 5.92296827466319e-06, + "loss": 0.0875, + "step": 25913 + }, + { + "epoch": 2.11, + "learning_rate": 5.922425032594524e-06, + "loss": 0.3439, + "step": 25914 + }, + { + "epoch": 2.11, + "learning_rate": 5.921881790525859e-06, + "loss": 0.3868, + "step": 25915 + }, + { + "epoch": 2.11, + "learning_rate": 5.921338548457193e-06, + "loss": 0.5112, + "step": 25916 + }, + { + "epoch": 2.11, + "learning_rate": 5.920795306388527e-06, + "loss": 0.2049, + "step": 25917 + }, + { + "epoch": 2.11, + "learning_rate": 5.920252064319861e-06, + "loss": 0.3348, + "step": 25918 + }, + { + "epoch": 2.11, + "learning_rate": 5.9197088222511955e-06, + "loss": 0.2447, + "step": 25919 + }, + { + "epoch": 2.11, + "learning_rate": 5.91916558018253e-06, + "loss": 0.4185, + "step": 25920 + }, + { + "epoch": 2.11, + "learning_rate": 5.918622338113864e-06, + "loss": 0.2775, + "step": 25921 + }, + { + "epoch": 2.11, + "learning_rate": 5.918079096045198e-06, + "loss": 0.1266, + "step": 25922 + }, + { + "epoch": 2.11, + "learning_rate": 5.9175358539765325e-06, + "loss": 0.1169, + "step": 25923 + }, + { + "epoch": 2.11, + "learning_rate": 5.916992611907867e-06, + "loss": 0.2713, + "step": 25924 + }, + { + "epoch": 2.11, + "learning_rate": 5.916449369839201e-06, + "loss": 0.1629, + "step": 25925 + }, + { + "epoch": 2.11, + "learning_rate": 5.915906127770535e-06, + "loss": 0.306, + "step": 25926 + }, + { + "epoch": 2.11, + "learning_rate": 5.915362885701869e-06, + "loss": 0.1264, + "step": 25927 + }, + { + "epoch": 2.11, + "learning_rate": 5.914819643633204e-06, + "loss": 0.1624, + "step": 25928 + }, + { + "epoch": 2.11, + "learning_rate": 5.914276401564538e-06, + "loss": 0.1377, + "step": 25929 + }, + { + "epoch": 2.11, + "learning_rate": 5.913733159495871e-06, + "loss": 0.2741, + "step": 25930 + }, + { + "epoch": 2.11, + "learning_rate": 5.9131899174272054e-06, + "loss": 0.2855, + "step": 25931 + }, + { + "epoch": 2.11, + "learning_rate": 5.91264667535854e-06, + "loss": 0.2172, + "step": 25932 + }, + { + "epoch": 2.11, + "learning_rate": 5.912103433289874e-06, + "loss": 0.088, + "step": 25933 + }, + { + "epoch": 2.11, + "learning_rate": 5.911560191221208e-06, + "loss": 0.1968, + "step": 25934 + }, + { + "epoch": 2.11, + "learning_rate": 5.911016949152542e-06, + "loss": 0.2609, + "step": 25935 + }, + { + "epoch": 2.11, + "learning_rate": 5.910473707083877e-06, + "loss": 0.0912, + "step": 25936 + }, + { + "epoch": 2.11, + "learning_rate": 5.909930465015211e-06, + "loss": 0.1263, + "step": 25937 + }, + { + "epoch": 2.11, + "learning_rate": 5.909387222946545e-06, + "loss": 0.0941, + "step": 25938 + }, + { + "epoch": 2.11, + "learning_rate": 5.908843980877879e-06, + "loss": 0.3324, + "step": 25939 + }, + { + "epoch": 2.11, + "learning_rate": 5.908300738809214e-06, + "loss": 0.3537, + "step": 25940 + }, + { + "epoch": 2.11, + "learning_rate": 5.907757496740549e-06, + "loss": 0.1868, + "step": 25941 + }, + { + "epoch": 2.11, + "learning_rate": 5.907214254671883e-06, + "loss": 0.3881, + "step": 25942 + }, + { + "epoch": 2.11, + "learning_rate": 5.906671012603217e-06, + "loss": 0.327, + "step": 25943 + }, + { + "epoch": 2.11, + "learning_rate": 5.906127770534551e-06, + "loss": 0.116, + "step": 25944 + }, + { + "epoch": 2.11, + "learning_rate": 5.9055845284658855e-06, + "loss": 0.3359, + "step": 25945 + }, + { + "epoch": 2.11, + "learning_rate": 5.90504128639722e-06, + "loss": 0.1601, + "step": 25946 + }, + { + "epoch": 2.11, + "learning_rate": 5.904498044328554e-06, + "loss": 0.1073, + "step": 25947 + }, + { + "epoch": 2.11, + "learning_rate": 5.903954802259888e-06, + "loss": 0.2431, + "step": 25948 + }, + { + "epoch": 2.11, + "learning_rate": 5.903411560191222e-06, + "loss": 0.1373, + "step": 25949 + }, + { + "epoch": 2.11, + "learning_rate": 5.902868318122556e-06, + "loss": 0.2315, + "step": 25950 + }, + { + "epoch": 2.11, + "learning_rate": 5.90232507605389e-06, + "loss": 0.2702, + "step": 25951 + }, + { + "epoch": 2.11, + "learning_rate": 5.901781833985224e-06, + "loss": 0.0945, + "step": 25952 + }, + { + "epoch": 2.11, + "learning_rate": 5.9012385919165585e-06, + "loss": 0.3265, + "step": 25953 + }, + { + "epoch": 2.11, + "learning_rate": 5.900695349847893e-06, + "loss": 0.1102, + "step": 25954 + }, + { + "epoch": 2.11, + "learning_rate": 5.900152107779227e-06, + "loss": 0.1528, + "step": 25955 + }, + { + "epoch": 2.12, + "learning_rate": 5.899608865710561e-06, + "loss": 0.3351, + "step": 25956 + }, + { + "epoch": 2.12, + "learning_rate": 5.8990656236418954e-06, + "loss": 0.2083, + "step": 25957 + }, + { + "epoch": 2.12, + "learning_rate": 5.89852238157323e-06, + "loss": 0.4232, + "step": 25958 + }, + { + "epoch": 2.12, + "learning_rate": 5.897979139504564e-06, + "loss": 0.2166, + "step": 25959 + }, + { + "epoch": 2.12, + "learning_rate": 5.897435897435898e-06, + "loss": 0.3666, + "step": 25960 + }, + { + "epoch": 2.12, + "learning_rate": 5.896892655367232e-06, + "loss": 0.2098, + "step": 25961 + }, + { + "epoch": 2.12, + "learning_rate": 5.896349413298567e-06, + "loss": 0.1882, + "step": 25962 + }, + { + "epoch": 2.12, + "learning_rate": 5.895806171229901e-06, + "loss": 0.1753, + "step": 25963 + }, + { + "epoch": 2.12, + "learning_rate": 5.895262929161235e-06, + "loss": 0.1059, + "step": 25964 + }, + { + "epoch": 2.12, + "learning_rate": 5.894719687092569e-06, + "loss": 0.2253, + "step": 25965 + }, + { + "epoch": 2.12, + "learning_rate": 5.8941764450239035e-06, + "loss": 0.3096, + "step": 25966 + }, + { + "epoch": 2.12, + "learning_rate": 5.893633202955238e-06, + "loss": 0.3021, + "step": 25967 + }, + { + "epoch": 2.12, + "learning_rate": 5.893089960886571e-06, + "loss": 0.203, + "step": 25968 + }, + { + "epoch": 2.12, + "learning_rate": 5.892546718817905e-06, + "loss": 0.2155, + "step": 25969 + }, + { + "epoch": 2.12, + "learning_rate": 5.89200347674924e-06, + "loss": 0.3209, + "step": 25970 + }, + { + "epoch": 2.12, + "learning_rate": 5.891460234680574e-06, + "loss": 0.2057, + "step": 25971 + }, + { + "epoch": 2.12, + "learning_rate": 5.890916992611908e-06, + "loss": 0.1486, + "step": 25972 + }, + { + "epoch": 2.12, + "learning_rate": 5.890373750543242e-06, + "loss": 0.6305, + "step": 25973 + }, + { + "epoch": 2.12, + "learning_rate": 5.8898305084745765e-06, + "loss": 0.1603, + "step": 25974 + }, + { + "epoch": 2.12, + "learning_rate": 5.889287266405911e-06, + "loss": 0.1875, + "step": 25975 + }, + { + "epoch": 2.12, + "learning_rate": 5.888744024337245e-06, + "loss": 0.2522, + "step": 25976 + }, + { + "epoch": 2.12, + "learning_rate": 5.888200782268579e-06, + "loss": 0.1928, + "step": 25977 + }, + { + "epoch": 2.12, + "learning_rate": 5.8876575401999134e-06, + "loss": 0.1903, + "step": 25978 + }, + { + "epoch": 2.12, + "learning_rate": 5.887114298131248e-06, + "loss": 0.2999, + "step": 25979 + }, + { + "epoch": 2.12, + "learning_rate": 5.886571056062582e-06, + "loss": 0.1454, + "step": 25980 + }, + { + "epoch": 2.12, + "learning_rate": 5.886027813993916e-06, + "loss": 0.2102, + "step": 25981 + }, + { + "epoch": 2.12, + "learning_rate": 5.88548457192525e-06, + "loss": 0.0959, + "step": 25982 + }, + { + "epoch": 2.12, + "learning_rate": 5.884941329856585e-06, + "loss": 0.42, + "step": 25983 + }, + { + "epoch": 2.12, + "learning_rate": 5.884398087787919e-06, + "loss": 0.2757, + "step": 25984 + }, + { + "epoch": 2.12, + "learning_rate": 5.883854845719253e-06, + "loss": 0.2817, + "step": 25985 + }, + { + "epoch": 2.12, + "learning_rate": 5.883311603650588e-06, + "loss": 0.2844, + "step": 25986 + }, + { + "epoch": 2.12, + "learning_rate": 5.882768361581921e-06, + "loss": 0.1723, + "step": 25987 + }, + { + "epoch": 2.12, + "learning_rate": 5.882225119513255e-06, + "loss": 0.112, + "step": 25988 + }, + { + "epoch": 2.12, + "learning_rate": 5.881681877444589e-06, + "loss": 0.5403, + "step": 25989 + }, + { + "epoch": 2.12, + "learning_rate": 5.881138635375923e-06, + "loss": 0.2885, + "step": 25990 + }, + { + "epoch": 2.12, + "learning_rate": 5.880595393307258e-06, + "loss": 0.1943, + "step": 25991 + }, + { + "epoch": 2.12, + "learning_rate": 5.880052151238592e-06, + "loss": 0.2558, + "step": 25992 + }, + { + "epoch": 2.12, + "learning_rate": 5.879508909169926e-06, + "loss": 0.1399, + "step": 25993 + }, + { + "epoch": 2.12, + "learning_rate": 5.878965667101261e-06, + "loss": 0.2295, + "step": 25994 + }, + { + "epoch": 2.12, + "learning_rate": 5.878422425032595e-06, + "loss": 0.2185, + "step": 25995 + }, + { + "epoch": 2.12, + "learning_rate": 5.87787918296393e-06, + "loss": 0.2139, + "step": 25996 + }, + { + "epoch": 2.12, + "learning_rate": 5.877335940895264e-06, + "loss": 0.2811, + "step": 25997 + }, + { + "epoch": 2.12, + "learning_rate": 5.876792698826598e-06, + "loss": 0.4255, + "step": 25998 + }, + { + "epoch": 2.12, + "learning_rate": 5.876249456757932e-06, + "loss": 0.2201, + "step": 25999 + }, + { + "epoch": 2.12, + "learning_rate": 5.8757062146892665e-06, + "loss": 0.3414, + "step": 26000 + }, + { + "epoch": 2.12, + "eval_accuracy": 0.83841059602649, + "eval_loss": 0.5015293955802917, + "eval_runtime": 22.2625, + "eval_samples_per_second": 440.876, + "eval_steps_per_second": 3.459, + "step": 26000 + }, + { + "epoch": 2.12, + "learning_rate": 5.875162972620601e-06, + "loss": 0.0876, + "step": 26001 + }, + { + "epoch": 2.12, + "learning_rate": 5.874619730551935e-06, + "loss": 0.1994, + "step": 26002 + }, + { + "epoch": 2.12, + "learning_rate": 5.874076488483269e-06, + "loss": 0.3064, + "step": 26003 + }, + { + "epoch": 2.12, + "learning_rate": 5.8735332464146034e-06, + "loss": 0.3935, + "step": 26004 + }, + { + "epoch": 2.12, + "learning_rate": 5.872990004345938e-06, + "loss": 0.1278, + "step": 26005 + }, + { + "epoch": 2.12, + "learning_rate": 5.872446762277271e-06, + "loss": 0.2095, + "step": 26006 + }, + { + "epoch": 2.12, + "learning_rate": 5.871903520208605e-06, + "loss": 0.1803, + "step": 26007 + }, + { + "epoch": 2.12, + "learning_rate": 5.8713602781399395e-06, + "loss": 0.1115, + "step": 26008 + }, + { + "epoch": 2.12, + "learning_rate": 5.870817036071274e-06, + "loss": 0.1162, + "step": 26009 + }, + { + "epoch": 2.12, + "learning_rate": 5.870273794002608e-06, + "loss": 0.1806, + "step": 26010 + }, + { + "epoch": 2.12, + "learning_rate": 5.869730551933942e-06, + "loss": 0.3361, + "step": 26011 + }, + { + "epoch": 2.12, + "learning_rate": 5.8691873098652764e-06, + "loss": 0.4005, + "step": 26012 + }, + { + "epoch": 2.12, + "learning_rate": 5.868644067796611e-06, + "loss": 0.1974, + "step": 26013 + }, + { + "epoch": 2.12, + "learning_rate": 5.868100825727945e-06, + "loss": 0.1518, + "step": 26014 + }, + { + "epoch": 2.12, + "learning_rate": 5.867557583659279e-06, + "loss": 0.1362, + "step": 26015 + }, + { + "epoch": 2.12, + "learning_rate": 5.867014341590613e-06, + "loss": 0.1852, + "step": 26016 + }, + { + "epoch": 2.12, + "learning_rate": 5.866471099521948e-06, + "loss": 0.0972, + "step": 26017 + }, + { + "epoch": 2.12, + "learning_rate": 5.865927857453282e-06, + "loss": 0.3157, + "step": 26018 + }, + { + "epoch": 2.12, + "learning_rate": 5.865384615384616e-06, + "loss": 0.1404, + "step": 26019 + }, + { + "epoch": 2.12, + "learning_rate": 5.86484137331595e-06, + "loss": 0.3431, + "step": 26020 + }, + { + "epoch": 2.12, + "learning_rate": 5.8642981312472845e-06, + "loss": 0.2556, + "step": 26021 + }, + { + "epoch": 2.12, + "learning_rate": 5.863754889178619e-06, + "loss": 0.3394, + "step": 26022 + }, + { + "epoch": 2.12, + "learning_rate": 5.863211647109953e-06, + "loss": 0.0842, + "step": 26023 + }, + { + "epoch": 2.12, + "learning_rate": 5.862668405041287e-06, + "loss": 0.0392, + "step": 26024 + }, + { + "epoch": 2.12, + "learning_rate": 5.862125162972621e-06, + "loss": 0.2651, + "step": 26025 + }, + { + "epoch": 2.12, + "learning_rate": 5.861581920903955e-06, + "loss": 0.1447, + "step": 26026 + }, + { + "epoch": 2.12, + "learning_rate": 5.861038678835289e-06, + "loss": 0.2828, + "step": 26027 + }, + { + "epoch": 2.12, + "learning_rate": 5.860495436766623e-06, + "loss": 0.2059, + "step": 26028 + }, + { + "epoch": 2.12, + "learning_rate": 5.8599521946979575e-06, + "loss": 0.3897, + "step": 26029 + }, + { + "epoch": 2.12, + "learning_rate": 5.859408952629292e-06, + "loss": 0.1538, + "step": 26030 + }, + { + "epoch": 2.12, + "learning_rate": 5.858865710560626e-06, + "loss": 0.0237, + "step": 26031 + }, + { + "epoch": 2.12, + "learning_rate": 5.85832246849196e-06, + "loss": 0.0938, + "step": 26032 + }, + { + "epoch": 2.12, + "learning_rate": 5.8577792264232944e-06, + "loss": 0.522, + "step": 26033 + }, + { + "epoch": 2.12, + "learning_rate": 5.857235984354629e-06, + "loss": 0.0945, + "step": 26034 + }, + { + "epoch": 2.12, + "learning_rate": 5.856692742285963e-06, + "loss": 0.1853, + "step": 26035 + }, + { + "epoch": 2.12, + "learning_rate": 5.856149500217297e-06, + "loss": 0.4477, + "step": 26036 + }, + { + "epoch": 2.12, + "learning_rate": 5.855606258148631e-06, + "loss": 0.4258, + "step": 26037 + }, + { + "epoch": 2.12, + "learning_rate": 5.855063016079966e-06, + "loss": 0.0608, + "step": 26038 + }, + { + "epoch": 2.12, + "learning_rate": 5.8545197740113e-06, + "loss": 0.2855, + "step": 26039 + }, + { + "epoch": 2.12, + "learning_rate": 5.853976531942635e-06, + "loss": 0.312, + "step": 26040 + }, + { + "epoch": 2.12, + "learning_rate": 5.853433289873969e-06, + "loss": 0.2094, + "step": 26041 + }, + { + "epoch": 2.12, + "learning_rate": 5.852890047805303e-06, + "loss": 0.3017, + "step": 26042 + }, + { + "epoch": 2.12, + "learning_rate": 5.852346805736638e-06, + "loss": 0.3295, + "step": 26043 + }, + { + "epoch": 2.12, + "learning_rate": 5.85180356366797e-06, + "loss": 0.3288, + "step": 26044 + }, + { + "epoch": 2.12, + "learning_rate": 5.851260321599304e-06, + "loss": 0.4293, + "step": 26045 + }, + { + "epoch": 2.12, + "learning_rate": 5.8507170795306386e-06, + "loss": 0.1953, + "step": 26046 + }, + { + "epoch": 2.12, + "learning_rate": 5.850173837461973e-06, + "loss": 0.1787, + "step": 26047 + }, + { + "epoch": 2.12, + "learning_rate": 5.849630595393308e-06, + "loss": 0.2134, + "step": 26048 + }, + { + "epoch": 2.12, + "learning_rate": 5.849087353324642e-06, + "loss": 0.4267, + "step": 26049 + }, + { + "epoch": 2.12, + "learning_rate": 5.848544111255976e-06, + "loss": 0.2392, + "step": 26050 + }, + { + "epoch": 2.12, + "learning_rate": 5.8480008691873106e-06, + "loss": 0.2232, + "step": 26051 + }, + { + "epoch": 2.12, + "learning_rate": 5.847457627118645e-06, + "loss": 0.3071, + "step": 26052 + }, + { + "epoch": 2.12, + "learning_rate": 5.846914385049979e-06, + "loss": 0.0474, + "step": 26053 + }, + { + "epoch": 2.12, + "learning_rate": 5.846371142981313e-06, + "loss": 0.3897, + "step": 26054 + }, + { + "epoch": 2.12, + "learning_rate": 5.8458279009126475e-06, + "loss": 0.3444, + "step": 26055 + }, + { + "epoch": 2.12, + "learning_rate": 5.845284658843982e-06, + "loss": 0.2628, + "step": 26056 + }, + { + "epoch": 2.12, + "learning_rate": 5.844741416775316e-06, + "loss": 0.0714, + "step": 26057 + }, + { + "epoch": 2.12, + "learning_rate": 5.84419817470665e-06, + "loss": 0.054, + "step": 26058 + }, + { + "epoch": 2.12, + "learning_rate": 5.843654932637984e-06, + "loss": 0.1783, + "step": 26059 + }, + { + "epoch": 2.12, + "learning_rate": 5.843111690569319e-06, + "loss": 0.0798, + "step": 26060 + }, + { + "epoch": 2.12, + "learning_rate": 5.842568448500653e-06, + "loss": 0.2415, + "step": 26061 + }, + { + "epoch": 2.12, + "learning_rate": 5.842025206431987e-06, + "loss": 0.0587, + "step": 26062 + }, + { + "epoch": 2.12, + "learning_rate": 5.8414819643633205e-06, + "loss": 0.4177, + "step": 26063 + }, + { + "epoch": 2.12, + "learning_rate": 5.840938722294655e-06, + "loss": 0.2171, + "step": 26064 + }, + { + "epoch": 2.12, + "learning_rate": 5.840395480225989e-06, + "loss": 0.3272, + "step": 26065 + }, + { + "epoch": 2.12, + "learning_rate": 5.839852238157323e-06, + "loss": 0.2225, + "step": 26066 + }, + { + "epoch": 2.12, + "learning_rate": 5.839308996088657e-06, + "loss": 0.2937, + "step": 26067 + }, + { + "epoch": 2.12, + "learning_rate": 5.838765754019992e-06, + "loss": 0.1667, + "step": 26068 + }, + { + "epoch": 2.12, + "learning_rate": 5.838222511951326e-06, + "loss": 0.1466, + "step": 26069 + }, + { + "epoch": 2.12, + "learning_rate": 5.83767926988266e-06, + "loss": 0.2002, + "step": 26070 + }, + { + "epoch": 2.12, + "learning_rate": 5.837136027813994e-06, + "loss": 0.2357, + "step": 26071 + }, + { + "epoch": 2.12, + "learning_rate": 5.8365927857453286e-06, + "loss": 0.2159, + "step": 26072 + }, + { + "epoch": 2.12, + "learning_rate": 5.836049543676663e-06, + "loss": 0.275, + "step": 26073 + }, + { + "epoch": 2.12, + "learning_rate": 5.835506301607997e-06, + "loss": 0.0654, + "step": 26074 + }, + { + "epoch": 2.12, + "learning_rate": 5.834963059539331e-06, + "loss": 0.3758, + "step": 26075 + }, + { + "epoch": 2.12, + "learning_rate": 5.8344198174706655e-06, + "loss": 0.3758, + "step": 26076 + }, + { + "epoch": 2.12, + "learning_rate": 5.833876575402e-06, + "loss": 0.3249, + "step": 26077 + }, + { + "epoch": 2.12, + "learning_rate": 5.833333333333334e-06, + "loss": 0.162, + "step": 26078 + }, + { + "epoch": 2.13, + "learning_rate": 5.832790091264668e-06, + "loss": 0.2549, + "step": 26079 + }, + { + "epoch": 2.13, + "learning_rate": 5.832246849196002e-06, + "loss": 0.1814, + "step": 26080 + }, + { + "epoch": 2.13, + "learning_rate": 5.831703607127337e-06, + "loss": 0.0323, + "step": 26081 + }, + { + "epoch": 2.13, + "learning_rate": 5.83116036505867e-06, + "loss": 0.2568, + "step": 26082 + }, + { + "epoch": 2.13, + "learning_rate": 5.830617122990004e-06, + "loss": 0.1551, + "step": 26083 + }, + { + "epoch": 2.13, + "learning_rate": 5.8300738809213385e-06, + "loss": 0.0906, + "step": 26084 + }, + { + "epoch": 2.13, + "learning_rate": 5.829530638852673e-06, + "loss": 0.2738, + "step": 26085 + }, + { + "epoch": 2.13, + "learning_rate": 5.828987396784007e-06, + "loss": 0.1278, + "step": 26086 + }, + { + "epoch": 2.13, + "learning_rate": 5.828444154715341e-06, + "loss": 0.3237, + "step": 26087 + }, + { + "epoch": 2.13, + "learning_rate": 5.827900912646675e-06, + "loss": 0.1855, + "step": 26088 + }, + { + "epoch": 2.13, + "learning_rate": 5.82735767057801e-06, + "loss": 0.2276, + "step": 26089 + }, + { + "epoch": 2.13, + "learning_rate": 5.826814428509344e-06, + "loss": 0.315, + "step": 26090 + }, + { + "epoch": 2.13, + "learning_rate": 5.826271186440678e-06, + "loss": 0.3516, + "step": 26091 + }, + { + "epoch": 2.13, + "learning_rate": 5.825727944372012e-06, + "loss": 0.4152, + "step": 26092 + }, + { + "epoch": 2.13, + "learning_rate": 5.8251847023033466e-06, + "loss": 0.1823, + "step": 26093 + }, + { + "epoch": 2.13, + "learning_rate": 5.824641460234682e-06, + "loss": 0.3597, + "step": 26094 + }, + { + "epoch": 2.13, + "learning_rate": 5.824098218166016e-06, + "loss": 0.3579, + "step": 26095 + }, + { + "epoch": 2.13, + "learning_rate": 5.82355497609735e-06, + "loss": 0.149, + "step": 26096 + }, + { + "epoch": 2.13, + "learning_rate": 5.823011734028684e-06, + "loss": 0.1967, + "step": 26097 + }, + { + "epoch": 2.13, + "learning_rate": 5.8224684919600186e-06, + "loss": 0.4516, + "step": 26098 + }, + { + "epoch": 2.13, + "learning_rate": 5.821925249891353e-06, + "loss": 0.4685, + "step": 26099 + }, + { + "epoch": 2.13, + "learning_rate": 5.821382007822687e-06, + "loss": 0.1341, + "step": 26100 + }, + { + "epoch": 2.13, + "learning_rate": 5.8208387657540196e-06, + "loss": 0.5455, + "step": 26101 + }, + { + "epoch": 2.13, + "learning_rate": 5.820295523685355e-06, + "loss": 0.0359, + "step": 26102 + }, + { + "epoch": 2.13, + "learning_rate": 5.819752281616689e-06, + "loss": 0.1144, + "step": 26103 + }, + { + "epoch": 2.13, + "learning_rate": 5.819209039548023e-06, + "loss": 0.2723, + "step": 26104 + }, + { + "epoch": 2.13, + "learning_rate": 5.818665797479357e-06, + "loss": 0.1331, + "step": 26105 + }, + { + "epoch": 2.13, + "learning_rate": 5.8181225554106916e-06, + "loss": 0.2519, + "step": 26106 + }, + { + "epoch": 2.13, + "learning_rate": 5.817579313342026e-06, + "loss": 0.1602, + "step": 26107 + }, + { + "epoch": 2.13, + "learning_rate": 5.81703607127336e-06, + "loss": 0.155, + "step": 26108 + }, + { + "epoch": 2.13, + "learning_rate": 5.816492829204694e-06, + "loss": 0.1383, + "step": 26109 + }, + { + "epoch": 2.13, + "learning_rate": 5.8159495871360285e-06, + "loss": 0.3687, + "step": 26110 + }, + { + "epoch": 2.13, + "learning_rate": 5.815406345067363e-06, + "loss": 0.2376, + "step": 26111 + }, + { + "epoch": 2.13, + "learning_rate": 5.814863102998697e-06, + "loss": 0.2448, + "step": 26112 + }, + { + "epoch": 2.13, + "learning_rate": 5.814319860930031e-06, + "loss": 0.3787, + "step": 26113 + }, + { + "epoch": 2.13, + "learning_rate": 5.813776618861365e-06, + "loss": 0.6513, + "step": 26114 + }, + { + "epoch": 2.13, + "learning_rate": 5.8132333767927e-06, + "loss": 0.1662, + "step": 26115 + }, + { + "epoch": 2.13, + "learning_rate": 5.812690134724034e-06, + "loss": 0.1837, + "step": 26116 + }, + { + "epoch": 2.13, + "learning_rate": 5.812146892655368e-06, + "loss": 0.279, + "step": 26117 + }, + { + "epoch": 2.13, + "learning_rate": 5.811603650586702e-06, + "loss": 0.492, + "step": 26118 + }, + { + "epoch": 2.13, + "learning_rate": 5.8110604085180366e-06, + "loss": 0.0188, + "step": 26119 + }, + { + "epoch": 2.13, + "learning_rate": 5.81051716644937e-06, + "loss": 0.2144, + "step": 26120 + }, + { + "epoch": 2.13, + "learning_rate": 5.809973924380704e-06, + "loss": 0.2861, + "step": 26121 + }, + { + "epoch": 2.13, + "learning_rate": 5.809430682312038e-06, + "loss": 0.1186, + "step": 26122 + }, + { + "epoch": 2.13, + "learning_rate": 5.808887440243373e-06, + "loss": 0.3283, + "step": 26123 + }, + { + "epoch": 2.13, + "learning_rate": 5.808344198174707e-06, + "loss": 0.2529, + "step": 26124 + }, + { + "epoch": 2.13, + "learning_rate": 5.807800956106041e-06, + "loss": 0.0395, + "step": 26125 + }, + { + "epoch": 2.13, + "learning_rate": 5.807257714037375e-06, + "loss": 0.0983, + "step": 26126 + }, + { + "epoch": 2.13, + "learning_rate": 5.8067144719687096e-06, + "loss": 0.1781, + "step": 26127 + }, + { + "epoch": 2.13, + "learning_rate": 5.806171229900044e-06, + "loss": 0.1023, + "step": 26128 + }, + { + "epoch": 2.13, + "learning_rate": 5.805627987831378e-06, + "loss": 0.2709, + "step": 26129 + }, + { + "epoch": 2.13, + "learning_rate": 5.805084745762712e-06, + "loss": 0.1403, + "step": 26130 + }, + { + "epoch": 2.13, + "learning_rate": 5.8045415036940465e-06, + "loss": 0.1622, + "step": 26131 + }, + { + "epoch": 2.13, + "learning_rate": 5.803998261625381e-06, + "loss": 0.352, + "step": 26132 + }, + { + "epoch": 2.13, + "learning_rate": 5.803455019556715e-06, + "loss": 0.2347, + "step": 26133 + }, + { + "epoch": 2.13, + "learning_rate": 5.802911777488049e-06, + "loss": 0.1481, + "step": 26134 + }, + { + "epoch": 2.13, + "learning_rate": 5.802368535419383e-06, + "loss": 0.2495, + "step": 26135 + }, + { + "epoch": 2.13, + "learning_rate": 5.801825293350718e-06, + "loss": 0.3688, + "step": 26136 + }, + { + "epoch": 2.13, + "learning_rate": 5.801282051282052e-06, + "loss": 0.2154, + "step": 26137 + }, + { + "epoch": 2.13, + "learning_rate": 5.800738809213386e-06, + "loss": 0.2218, + "step": 26138 + }, + { + "epoch": 2.13, + "learning_rate": 5.8001955671447195e-06, + "loss": 0.4449, + "step": 26139 + }, + { + "epoch": 2.13, + "learning_rate": 5.799652325076054e-06, + "loss": 0.1421, + "step": 26140 + }, + { + "epoch": 2.13, + "learning_rate": 5.799109083007388e-06, + "loss": 0.0565, + "step": 26141 + }, + { + "epoch": 2.13, + "learning_rate": 5.798565840938722e-06, + "loss": 0.2492, + "step": 26142 + }, + { + "epoch": 2.13, + "learning_rate": 5.798022598870056e-06, + "loss": 0.4112, + "step": 26143 + }, + { + "epoch": 2.13, + "learning_rate": 5.797479356801391e-06, + "loss": 0.3011, + "step": 26144 + }, + { + "epoch": 2.13, + "learning_rate": 5.796936114732725e-06, + "loss": 0.2385, + "step": 26145 + }, + { + "epoch": 2.13, + "learning_rate": 5.796392872664059e-06, + "loss": 0.2438, + "step": 26146 + }, + { + "epoch": 2.13, + "learning_rate": 5.795849630595393e-06, + "loss": 0.0844, + "step": 26147 + }, + { + "epoch": 2.13, + "learning_rate": 5.795306388526728e-06, + "loss": 0.1551, + "step": 26148 + }, + { + "epoch": 2.13, + "learning_rate": 5.794763146458063e-06, + "loss": 0.2253, + "step": 26149 + }, + { + "epoch": 2.13, + "learning_rate": 5.794219904389397e-06, + "loss": 0.2029, + "step": 26150 + }, + { + "epoch": 2.13, + "learning_rate": 5.793676662320731e-06, + "loss": 0.274, + "step": 26151 + }, + { + "epoch": 2.13, + "learning_rate": 5.793133420252065e-06, + "loss": 0.2338, + "step": 26152 + }, + { + "epoch": 2.13, + "learning_rate": 5.7925901781833995e-06, + "loss": 0.1781, + "step": 26153 + }, + { + "epoch": 2.13, + "learning_rate": 5.792046936114734e-06, + "loss": 0.2218, + "step": 26154 + }, + { + "epoch": 2.13, + "learning_rate": 5.791503694046068e-06, + "loss": 0.1424, + "step": 26155 + }, + { + "epoch": 2.13, + "learning_rate": 5.790960451977402e-06, + "loss": 0.0633, + "step": 26156 + }, + { + "epoch": 2.13, + "learning_rate": 5.7904172099087365e-06, + "loss": 0.2007, + "step": 26157 + }, + { + "epoch": 2.13, + "learning_rate": 5.78987396784007e-06, + "loss": 0.4291, + "step": 26158 + }, + { + "epoch": 2.13, + "learning_rate": 5.789330725771404e-06, + "loss": 0.1681, + "step": 26159 + }, + { + "epoch": 2.13, + "learning_rate": 5.788787483702738e-06, + "loss": 0.2626, + "step": 26160 + }, + { + "epoch": 2.13, + "learning_rate": 5.7882442416340725e-06, + "loss": 0.2439, + "step": 26161 + }, + { + "epoch": 2.13, + "learning_rate": 5.787700999565407e-06, + "loss": 0.3192, + "step": 26162 + }, + { + "epoch": 2.13, + "learning_rate": 5.787157757496741e-06, + "loss": 0.1532, + "step": 26163 + }, + { + "epoch": 2.13, + "learning_rate": 5.786614515428075e-06, + "loss": 0.1586, + "step": 26164 + }, + { + "epoch": 2.13, + "learning_rate": 5.7860712733594095e-06, + "loss": 0.11, + "step": 26165 + }, + { + "epoch": 2.13, + "learning_rate": 5.785528031290744e-06, + "loss": 0.1936, + "step": 26166 + }, + { + "epoch": 2.13, + "learning_rate": 5.784984789222078e-06, + "loss": 0.1071, + "step": 26167 + }, + { + "epoch": 2.13, + "learning_rate": 5.784441547153412e-06, + "loss": 0.1508, + "step": 26168 + }, + { + "epoch": 2.13, + "learning_rate": 5.783898305084746e-06, + "loss": 0.2444, + "step": 26169 + }, + { + "epoch": 2.13, + "learning_rate": 5.783355063016081e-06, + "loss": 0.179, + "step": 26170 + }, + { + "epoch": 2.13, + "learning_rate": 5.782811820947415e-06, + "loss": 0.1948, + "step": 26171 + }, + { + "epoch": 2.13, + "learning_rate": 5.782268578878749e-06, + "loss": 0.1056, + "step": 26172 + }, + { + "epoch": 2.13, + "learning_rate": 5.781725336810083e-06, + "loss": 0.0986, + "step": 26173 + }, + { + "epoch": 2.13, + "learning_rate": 5.7811820947414175e-06, + "loss": 0.0962, + "step": 26174 + }, + { + "epoch": 2.13, + "learning_rate": 5.780638852672752e-06, + "loss": 0.1079, + "step": 26175 + }, + { + "epoch": 2.13, + "learning_rate": 5.780095610604086e-06, + "loss": 0.1308, + "step": 26176 + }, + { + "epoch": 2.13, + "learning_rate": 5.779552368535419e-06, + "loss": 0.1553, + "step": 26177 + }, + { + "epoch": 2.13, + "learning_rate": 5.779009126466754e-06, + "loss": 0.0579, + "step": 26178 + }, + { + "epoch": 2.13, + "learning_rate": 5.778465884398088e-06, + "loss": 0.169, + "step": 26179 + }, + { + "epoch": 2.13, + "learning_rate": 5.777922642329422e-06, + "loss": 0.3995, + "step": 26180 + }, + { + "epoch": 2.13, + "learning_rate": 5.777379400260756e-06, + "loss": 0.2887, + "step": 26181 + }, + { + "epoch": 2.13, + "learning_rate": 5.7768361581920905e-06, + "loss": 0.4517, + "step": 26182 + }, + { + "epoch": 2.13, + "learning_rate": 5.776292916123425e-06, + "loss": 0.2953, + "step": 26183 + }, + { + "epoch": 2.13, + "learning_rate": 5.775749674054759e-06, + "loss": 0.392, + "step": 26184 + }, + { + "epoch": 2.13, + "learning_rate": 5.775206431986093e-06, + "loss": 0.1515, + "step": 26185 + }, + { + "epoch": 2.13, + "learning_rate": 5.7746631899174275e-06, + "loss": 0.3162, + "step": 26186 + }, + { + "epoch": 2.13, + "learning_rate": 5.774119947848762e-06, + "loss": 0.3775, + "step": 26187 + }, + { + "epoch": 2.13, + "learning_rate": 5.773576705780096e-06, + "loss": 0.2397, + "step": 26188 + }, + { + "epoch": 2.13, + "learning_rate": 5.77303346371143e-06, + "loss": 0.3106, + "step": 26189 + }, + { + "epoch": 2.13, + "learning_rate": 5.772490221642764e-06, + "loss": 0.3233, + "step": 26190 + }, + { + "epoch": 2.13, + "learning_rate": 5.771946979574099e-06, + "loss": 0.2197, + "step": 26191 + }, + { + "epoch": 2.13, + "learning_rate": 5.771403737505433e-06, + "loss": 0.5649, + "step": 26192 + }, + { + "epoch": 2.13, + "learning_rate": 5.770860495436768e-06, + "loss": 0.1869, + "step": 26193 + }, + { + "epoch": 2.13, + "learning_rate": 5.770317253368102e-06, + "loss": 0.2593, + "step": 26194 + }, + { + "epoch": 2.13, + "learning_rate": 5.769774011299436e-06, + "loss": 0.1321, + "step": 26195 + }, + { + "epoch": 2.13, + "learning_rate": 5.769230769230769e-06, + "loss": 0.6225, + "step": 26196 + }, + { + "epoch": 2.13, + "learning_rate": 5.768687527162103e-06, + "loss": 0.5556, + "step": 26197 + }, + { + "epoch": 2.13, + "learning_rate": 5.768144285093437e-06, + "loss": 0.2928, + "step": 26198 + }, + { + "epoch": 2.13, + "learning_rate": 5.767601043024772e-06, + "loss": 0.1617, + "step": 26199 + }, + { + "epoch": 2.13, + "learning_rate": 5.767057800956106e-06, + "loss": 0.3222, + "step": 26200 + }, + { + "epoch": 2.14, + "learning_rate": 5.76651455888744e-06, + "loss": 0.0941, + "step": 26201 + }, + { + "epoch": 2.14, + "learning_rate": 5.765971316818775e-06, + "loss": 0.1096, + "step": 26202 + }, + { + "epoch": 2.14, + "learning_rate": 5.765428074750109e-06, + "loss": 0.1402, + "step": 26203 + }, + { + "epoch": 2.14, + "learning_rate": 5.764884832681444e-06, + "loss": 0.3801, + "step": 26204 + }, + { + "epoch": 2.14, + "learning_rate": 5.764341590612778e-06, + "loss": 0.2005, + "step": 26205 + }, + { + "epoch": 2.14, + "learning_rate": 5.763798348544112e-06, + "loss": 0.2408, + "step": 26206 + }, + { + "epoch": 2.14, + "learning_rate": 5.763255106475446e-06, + "loss": 0.3588, + "step": 26207 + }, + { + "epoch": 2.14, + "learning_rate": 5.7627118644067805e-06, + "loss": 0.1, + "step": 26208 + }, + { + "epoch": 2.14, + "learning_rate": 5.762168622338115e-06, + "loss": 0.0997, + "step": 26209 + }, + { + "epoch": 2.14, + "learning_rate": 5.761625380269449e-06, + "loss": 0.5677, + "step": 26210 + }, + { + "epoch": 2.14, + "learning_rate": 5.761082138200783e-06, + "loss": 0.0516, + "step": 26211 + }, + { + "epoch": 2.14, + "learning_rate": 5.7605388961321175e-06, + "loss": 0.4136, + "step": 26212 + }, + { + "epoch": 2.14, + "learning_rate": 5.759995654063452e-06, + "loss": 0.5403, + "step": 26213 + }, + { + "epoch": 2.14, + "learning_rate": 5.759452411994786e-06, + "loss": 0.3951, + "step": 26214 + }, + { + "epoch": 2.14, + "learning_rate": 5.758909169926119e-06, + "loss": 0.1386, + "step": 26215 + }, + { + "epoch": 2.14, + "learning_rate": 5.7583659278574535e-06, + "loss": 0.1233, + "step": 26216 + }, + { + "epoch": 2.14, + "learning_rate": 5.757822685788788e-06, + "loss": 0.066, + "step": 26217 + }, + { + "epoch": 2.14, + "learning_rate": 5.757279443720122e-06, + "loss": 0.3343, + "step": 26218 + }, + { + "epoch": 2.14, + "learning_rate": 5.756736201651456e-06, + "loss": 0.2673, + "step": 26219 + }, + { + "epoch": 2.14, + "learning_rate": 5.7561929595827905e-06, + "loss": 0.1896, + "step": 26220 + }, + { + "epoch": 2.14, + "learning_rate": 5.755649717514125e-06, + "loss": 0.2292, + "step": 26221 + }, + { + "epoch": 2.14, + "learning_rate": 5.755106475445459e-06, + "loss": 0.1086, + "step": 26222 + }, + { + "epoch": 2.14, + "learning_rate": 5.754563233376793e-06, + "loss": 0.1124, + "step": 26223 + }, + { + "epoch": 2.14, + "learning_rate": 5.754019991308127e-06, + "loss": 0.2656, + "step": 26224 + }, + { + "epoch": 2.14, + "learning_rate": 5.753476749239462e-06, + "loss": 0.2277, + "step": 26225 + }, + { + "epoch": 2.14, + "learning_rate": 5.752933507170796e-06, + "loss": 0.5084, + "step": 26226 + }, + { + "epoch": 2.14, + "learning_rate": 5.75239026510213e-06, + "loss": 0.1394, + "step": 26227 + }, + { + "epoch": 2.14, + "learning_rate": 5.751847023033464e-06, + "loss": 0.0708, + "step": 26228 + }, + { + "epoch": 2.14, + "learning_rate": 5.7513037809647985e-06, + "loss": 0.1857, + "step": 26229 + }, + { + "epoch": 2.14, + "learning_rate": 5.750760538896133e-06, + "loss": 0.0947, + "step": 26230 + }, + { + "epoch": 2.14, + "learning_rate": 5.750217296827467e-06, + "loss": 0.4322, + "step": 26231 + }, + { + "epoch": 2.14, + "learning_rate": 5.749674054758801e-06, + "loss": 0.1872, + "step": 26232 + }, + { + "epoch": 2.14, + "learning_rate": 5.7491308126901355e-06, + "loss": 0.0883, + "step": 26233 + }, + { + "epoch": 2.14, + "learning_rate": 5.748587570621469e-06, + "loss": 0.293, + "step": 26234 + }, + { + "epoch": 2.14, + "learning_rate": 5.748044328552803e-06, + "loss": 0.2748, + "step": 26235 + }, + { + "epoch": 2.14, + "learning_rate": 5.747501086484137e-06, + "loss": 0.2846, + "step": 26236 + }, + { + "epoch": 2.14, + "learning_rate": 5.7469578444154715e-06, + "loss": 0.1478, + "step": 26237 + }, + { + "epoch": 2.14, + "learning_rate": 5.746414602346806e-06, + "loss": 0.2899, + "step": 26238 + }, + { + "epoch": 2.14, + "learning_rate": 5.74587136027814e-06, + "loss": 0.139, + "step": 26239 + }, + { + "epoch": 2.14, + "learning_rate": 5.745328118209474e-06, + "loss": 0.1985, + "step": 26240 + }, + { + "epoch": 2.14, + "learning_rate": 5.7447848761408084e-06, + "loss": 0.1127, + "step": 26241 + }, + { + "epoch": 2.14, + "learning_rate": 5.744241634072143e-06, + "loss": 0.212, + "step": 26242 + }, + { + "epoch": 2.14, + "learning_rate": 5.743698392003477e-06, + "loss": 0.2584, + "step": 26243 + }, + { + "epoch": 2.14, + "learning_rate": 5.743155149934811e-06, + "loss": 0.1202, + "step": 26244 + }, + { + "epoch": 2.14, + "learning_rate": 5.742611907866145e-06, + "loss": 0.0704, + "step": 26245 + }, + { + "epoch": 2.14, + "learning_rate": 5.74206866579748e-06, + "loss": 0.4145, + "step": 26246 + }, + { + "epoch": 2.14, + "learning_rate": 5.741525423728815e-06, + "loss": 0.2379, + "step": 26247 + }, + { + "epoch": 2.14, + "learning_rate": 5.740982181660149e-06, + "loss": 0.2142, + "step": 26248 + }, + { + "epoch": 2.14, + "learning_rate": 5.740438939591483e-06, + "loss": 0.3459, + "step": 26249 + }, + { + "epoch": 2.14, + "learning_rate": 5.739895697522817e-06, + "loss": 0.2683, + "step": 26250 + }, + { + "epoch": 2.14, + "eval_accuracy": 0.841365257259297, + "eval_loss": 0.49769267439842224, + "eval_runtime": 22.2568, + "eval_samples_per_second": 440.988, + "eval_steps_per_second": 3.46, + "step": 26250 + }, + { + "epoch": 2.14, + "learning_rate": 5.739352455454152e-06, + "loss": 0.3001, + "step": 26251 + }, + { + "epoch": 2.14, + "learning_rate": 5.738809213385486e-06, + "loss": 0.0829, + "step": 26252 + }, + { + "epoch": 2.14, + "learning_rate": 5.738265971316818e-06, + "loss": 0.302, + "step": 26253 + }, + { + "epoch": 2.14, + "learning_rate": 5.737722729248153e-06, + "loss": 0.2203, + "step": 26254 + }, + { + "epoch": 2.14, + "learning_rate": 5.737179487179487e-06, + "loss": 0.383, + "step": 26255 + }, + { + "epoch": 2.14, + "learning_rate": 5.736636245110822e-06, + "loss": 0.0423, + "step": 26256 + }, + { + "epoch": 2.14, + "learning_rate": 5.736093003042156e-06, + "loss": 0.3127, + "step": 26257 + }, + { + "epoch": 2.14, + "learning_rate": 5.73554976097349e-06, + "loss": 0.3159, + "step": 26258 + }, + { + "epoch": 2.14, + "learning_rate": 5.735006518904825e-06, + "loss": 0.1474, + "step": 26259 + }, + { + "epoch": 2.14, + "learning_rate": 5.734463276836159e-06, + "loss": 0.1829, + "step": 26260 + }, + { + "epoch": 2.14, + "learning_rate": 5.733920034767493e-06, + "loss": 0.6327, + "step": 26261 + }, + { + "epoch": 2.14, + "learning_rate": 5.733376792698827e-06, + "loss": 0.0696, + "step": 26262 + }, + { + "epoch": 2.14, + "learning_rate": 5.7328335506301615e-06, + "loss": 0.2715, + "step": 26263 + }, + { + "epoch": 2.14, + "learning_rate": 5.732290308561496e-06, + "loss": 0.2205, + "step": 26264 + }, + { + "epoch": 2.14, + "learning_rate": 5.73174706649283e-06, + "loss": 0.0602, + "step": 26265 + }, + { + "epoch": 2.14, + "learning_rate": 5.731203824424164e-06, + "loss": 0.2724, + "step": 26266 + }, + { + "epoch": 2.14, + "learning_rate": 5.7306605823554984e-06, + "loss": 0.3914, + "step": 26267 + }, + { + "epoch": 2.14, + "learning_rate": 5.730117340286833e-06, + "loss": 0.1876, + "step": 26268 + }, + { + "epoch": 2.14, + "learning_rate": 5.729574098218167e-06, + "loss": 0.2359, + "step": 26269 + }, + { + "epoch": 2.14, + "learning_rate": 5.729030856149501e-06, + "loss": 0.1319, + "step": 26270 + }, + { + "epoch": 2.14, + "learning_rate": 5.728487614080835e-06, + "loss": 0.3959, + "step": 26271 + }, + { + "epoch": 2.14, + "learning_rate": 5.727944372012169e-06, + "loss": 0.2334, + "step": 26272 + }, + { + "epoch": 2.14, + "learning_rate": 5.727401129943503e-06, + "loss": 0.1146, + "step": 26273 + }, + { + "epoch": 2.14, + "learning_rate": 5.726857887874837e-06, + "loss": 0.314, + "step": 26274 + }, + { + "epoch": 2.14, + "learning_rate": 5.7263146458061714e-06, + "loss": 0.3819, + "step": 26275 + }, + { + "epoch": 2.14, + "learning_rate": 5.725771403737506e-06, + "loss": 0.0624, + "step": 26276 + }, + { + "epoch": 2.14, + "learning_rate": 5.72522816166884e-06, + "loss": 0.4234, + "step": 26277 + }, + { + "epoch": 2.14, + "learning_rate": 5.724684919600174e-06, + "loss": 0.3839, + "step": 26278 + }, + { + "epoch": 2.14, + "learning_rate": 5.724141677531508e-06, + "loss": 0.0793, + "step": 26279 + }, + { + "epoch": 2.14, + "learning_rate": 5.723598435462843e-06, + "loss": 0.2074, + "step": 26280 + }, + { + "epoch": 2.14, + "learning_rate": 5.723055193394177e-06, + "loss": 0.0497, + "step": 26281 + }, + { + "epoch": 2.14, + "learning_rate": 5.722511951325511e-06, + "loss": 0.1738, + "step": 26282 + }, + { + "epoch": 2.14, + "learning_rate": 5.721968709256845e-06, + "loss": 0.2141, + "step": 26283 + }, + { + "epoch": 2.14, + "learning_rate": 5.7214254671881795e-06, + "loss": 0.0497, + "step": 26284 + }, + { + "epoch": 2.14, + "learning_rate": 5.720882225119514e-06, + "loss": 0.2497, + "step": 26285 + }, + { + "epoch": 2.14, + "learning_rate": 5.720338983050848e-06, + "loss": 0.0929, + "step": 26286 + }, + { + "epoch": 2.14, + "learning_rate": 5.719795740982182e-06, + "loss": 0.1993, + "step": 26287 + }, + { + "epoch": 2.14, + "learning_rate": 5.7192524989135164e-06, + "loss": 0.084, + "step": 26288 + }, + { + "epoch": 2.14, + "learning_rate": 5.718709256844851e-06, + "loss": 0.0684, + "step": 26289 + }, + { + "epoch": 2.14, + "learning_rate": 5.718166014776185e-06, + "loss": 0.273, + "step": 26290 + }, + { + "epoch": 2.14, + "learning_rate": 5.717622772707518e-06, + "loss": 0.0489, + "step": 26291 + }, + { + "epoch": 2.14, + "learning_rate": 5.7170795306388525e-06, + "loss": 0.2626, + "step": 26292 + }, + { + "epoch": 2.14, + "learning_rate": 5.716536288570187e-06, + "loss": 0.1076, + "step": 26293 + }, + { + "epoch": 2.14, + "learning_rate": 5.715993046501521e-06, + "loss": 0.2407, + "step": 26294 + }, + { + "epoch": 2.14, + "learning_rate": 5.715449804432855e-06, + "loss": 0.065, + "step": 26295 + }, + { + "epoch": 2.14, + "learning_rate": 5.7149065623641894e-06, + "loss": 0.0902, + "step": 26296 + }, + { + "epoch": 2.14, + "learning_rate": 5.714363320295524e-06, + "loss": 0.3162, + "step": 26297 + }, + { + "epoch": 2.14, + "learning_rate": 5.713820078226858e-06, + "loss": 0.1359, + "step": 26298 + }, + { + "epoch": 2.14, + "learning_rate": 5.713276836158192e-06, + "loss": 0.2767, + "step": 26299 + }, + { + "epoch": 2.14, + "learning_rate": 5.712733594089526e-06, + "loss": 0.2492, + "step": 26300 + }, + { + "epoch": 2.14, + "learning_rate": 5.7121903520208614e-06, + "loss": 0.3787, + "step": 26301 + }, + { + "epoch": 2.14, + "learning_rate": 5.711647109952196e-06, + "loss": 0.214, + "step": 26302 + }, + { + "epoch": 2.14, + "learning_rate": 5.71110386788353e-06, + "loss": 0.2013, + "step": 26303 + }, + { + "epoch": 2.14, + "learning_rate": 5.710560625814864e-06, + "loss": 0.3053, + "step": 26304 + }, + { + "epoch": 2.14, + "learning_rate": 5.710017383746198e-06, + "loss": 0.236, + "step": 26305 + }, + { + "epoch": 2.14, + "learning_rate": 5.709474141677533e-06, + "loss": 0.1512, + "step": 26306 + }, + { + "epoch": 2.14, + "learning_rate": 5.708930899608867e-06, + "loss": 0.3961, + "step": 26307 + }, + { + "epoch": 2.14, + "learning_rate": 5.708387657540201e-06, + "loss": 0.2146, + "step": 26308 + }, + { + "epoch": 2.14, + "learning_rate": 5.707844415471535e-06, + "loss": 0.2859, + "step": 26309 + }, + { + "epoch": 2.14, + "learning_rate": 5.707301173402869e-06, + "loss": 0.2382, + "step": 26310 + }, + { + "epoch": 2.14, + "learning_rate": 5.706757931334203e-06, + "loss": 0.1397, + "step": 26311 + }, + { + "epoch": 2.14, + "learning_rate": 5.706214689265537e-06, + "loss": 0.121, + "step": 26312 + }, + { + "epoch": 2.14, + "learning_rate": 5.705671447196871e-06, + "loss": 0.4718, + "step": 26313 + }, + { + "epoch": 2.14, + "learning_rate": 5.705128205128206e-06, + "loss": 0.1122, + "step": 26314 + }, + { + "epoch": 2.14, + "learning_rate": 5.70458496305954e-06, + "loss": 0.1405, + "step": 26315 + }, + { + "epoch": 2.14, + "learning_rate": 5.704041720990874e-06, + "loss": 0.4753, + "step": 26316 + }, + { + "epoch": 2.14, + "learning_rate": 5.703498478922208e-06, + "loss": 0.0762, + "step": 26317 + }, + { + "epoch": 2.14, + "learning_rate": 5.7029552368535425e-06, + "loss": 0.3425, + "step": 26318 + }, + { + "epoch": 2.14, + "learning_rate": 5.702411994784877e-06, + "loss": 0.1845, + "step": 26319 + }, + { + "epoch": 2.14, + "learning_rate": 5.701868752716211e-06, + "loss": 0.1828, + "step": 26320 + }, + { + "epoch": 2.14, + "learning_rate": 5.701325510647545e-06, + "loss": 0.0655, + "step": 26321 + }, + { + "epoch": 2.14, + "learning_rate": 5.7007822685788794e-06, + "loss": 0.0953, + "step": 26322 + }, + { + "epoch": 2.14, + "learning_rate": 5.700239026510214e-06, + "loss": 0.2642, + "step": 26323 + }, + { + "epoch": 2.15, + "learning_rate": 5.699695784441548e-06, + "loss": 0.2396, + "step": 26324 + }, + { + "epoch": 2.15, + "learning_rate": 5.699152542372882e-06, + "loss": 0.1401, + "step": 26325 + }, + { + "epoch": 2.15, + "learning_rate": 5.698609300304216e-06, + "loss": 0.6301, + "step": 26326 + }, + { + "epoch": 2.15, + "learning_rate": 5.698066058235551e-06, + "loss": 0.1528, + "step": 26327 + }, + { + "epoch": 2.15, + "learning_rate": 5.697522816166885e-06, + "loss": 0.0906, + "step": 26328 + }, + { + "epoch": 2.15, + "learning_rate": 5.696979574098218e-06, + "loss": 0.2117, + "step": 26329 + }, + { + "epoch": 2.15, + "learning_rate": 5.6964363320295524e-06, + "loss": 0.0815, + "step": 26330 + }, + { + "epoch": 2.15, + "learning_rate": 5.695893089960887e-06, + "loss": 0.089, + "step": 26331 + }, + { + "epoch": 2.15, + "learning_rate": 5.695349847892221e-06, + "loss": 0.1252, + "step": 26332 + }, + { + "epoch": 2.15, + "learning_rate": 5.694806605823555e-06, + "loss": 0.1588, + "step": 26333 + }, + { + "epoch": 2.15, + "learning_rate": 5.694263363754889e-06, + "loss": 0.2986, + "step": 26334 + }, + { + "epoch": 2.15, + "learning_rate": 5.693720121686224e-06, + "loss": 0.14, + "step": 26335 + }, + { + "epoch": 2.15, + "learning_rate": 5.693176879617558e-06, + "loss": 0.204, + "step": 26336 + }, + { + "epoch": 2.15, + "learning_rate": 5.692633637548892e-06, + "loss": 0.1471, + "step": 26337 + }, + { + "epoch": 2.15, + "learning_rate": 5.692090395480226e-06, + "loss": 0.2434, + "step": 26338 + }, + { + "epoch": 2.15, + "learning_rate": 5.6915471534115605e-06, + "loss": 0.3037, + "step": 26339 + }, + { + "epoch": 2.15, + "learning_rate": 5.691003911342895e-06, + "loss": 0.1569, + "step": 26340 + }, + { + "epoch": 2.15, + "learning_rate": 5.690460669274229e-06, + "loss": 0.1221, + "step": 26341 + }, + { + "epoch": 2.15, + "learning_rate": 5.689917427205563e-06, + "loss": 0.197, + "step": 26342 + }, + { + "epoch": 2.15, + "learning_rate": 5.689374185136897e-06, + "loss": 0.5053, + "step": 26343 + }, + { + "epoch": 2.15, + "learning_rate": 5.688830943068232e-06, + "loss": 0.2968, + "step": 26344 + }, + { + "epoch": 2.15, + "learning_rate": 5.688287700999566e-06, + "loss": 0.3063, + "step": 26345 + }, + { + "epoch": 2.15, + "learning_rate": 5.687744458930901e-06, + "loss": 0.2888, + "step": 26346 + }, + { + "epoch": 2.15, + "learning_rate": 5.687201216862235e-06, + "loss": 0.4142, + "step": 26347 + }, + { + "epoch": 2.15, + "learning_rate": 5.686657974793568e-06, + "loss": 0.1155, + "step": 26348 + }, + { + "epoch": 2.15, + "learning_rate": 5.686114732724902e-06, + "loss": 0.1745, + "step": 26349 + }, + { + "epoch": 2.15, + "learning_rate": 5.685571490656236e-06, + "loss": 0.2182, + "step": 26350 + }, + { + "epoch": 2.15, + "learning_rate": 5.68502824858757e-06, + "loss": 0.1808, + "step": 26351 + }, + { + "epoch": 2.15, + "learning_rate": 5.684485006518905e-06, + "loss": 0.1158, + "step": 26352 + }, + { + "epoch": 2.15, + "learning_rate": 5.683941764450239e-06, + "loss": 0.3182, + "step": 26353 + }, + { + "epoch": 2.15, + "learning_rate": 5.683398522381573e-06, + "loss": 0.2177, + "step": 26354 + }, + { + "epoch": 2.15, + "learning_rate": 5.682855280312908e-06, + "loss": 0.2988, + "step": 26355 + }, + { + "epoch": 2.15, + "learning_rate": 5.682312038244242e-06, + "loss": 0.113, + "step": 26356 + }, + { + "epoch": 2.15, + "learning_rate": 5.681768796175577e-06, + "loss": 0.3427, + "step": 26357 + }, + { + "epoch": 2.15, + "learning_rate": 5.681225554106911e-06, + "loss": 0.3334, + "step": 26358 + }, + { + "epoch": 2.15, + "learning_rate": 5.680682312038245e-06, + "loss": 0.394, + "step": 26359 + }, + { + "epoch": 2.15, + "learning_rate": 5.680139069969579e-06, + "loss": 0.088, + "step": 26360 + }, + { + "epoch": 2.15, + "learning_rate": 5.6795958279009136e-06, + "loss": 0.2145, + "step": 26361 + }, + { + "epoch": 2.15, + "learning_rate": 5.679052585832248e-06, + "loss": 0.1744, + "step": 26362 + }, + { + "epoch": 2.15, + "learning_rate": 5.678509343763582e-06, + "loss": 0.2536, + "step": 26363 + }, + { + "epoch": 2.15, + "learning_rate": 5.677966101694916e-06, + "loss": 0.1232, + "step": 26364 + }, + { + "epoch": 2.15, + "learning_rate": 5.6774228596262505e-06, + "loss": 0.2479, + "step": 26365 + }, + { + "epoch": 2.15, + "learning_rate": 5.676879617557585e-06, + "loss": 0.2304, + "step": 26366 + }, + { + "epoch": 2.15, + "learning_rate": 5.676336375488918e-06, + "loss": 0.2712, + "step": 26367 + }, + { + "epoch": 2.15, + "learning_rate": 5.675793133420252e-06, + "loss": 0.2537, + "step": 26368 + }, + { + "epoch": 2.15, + "learning_rate": 5.6752498913515866e-06, + "loss": 0.2317, + "step": 26369 + }, + { + "epoch": 2.15, + "learning_rate": 5.674706649282921e-06, + "loss": 0.2479, + "step": 26370 + }, + { + "epoch": 2.15, + "learning_rate": 5.674163407214255e-06, + "loss": 0.0628, + "step": 26371 + }, + { + "epoch": 2.15, + "learning_rate": 5.673620165145589e-06, + "loss": 0.5246, + "step": 26372 + }, + { + "epoch": 2.15, + "learning_rate": 5.6730769230769235e-06, + "loss": 0.0845, + "step": 26373 + }, + { + "epoch": 2.15, + "learning_rate": 5.672533681008258e-06, + "loss": 0.1351, + "step": 26374 + }, + { + "epoch": 2.15, + "learning_rate": 5.671990438939592e-06, + "loss": 0.1783, + "step": 26375 + }, + { + "epoch": 2.15, + "learning_rate": 5.671447196870926e-06, + "loss": 0.2878, + "step": 26376 + }, + { + "epoch": 2.15, + "learning_rate": 5.67090395480226e-06, + "loss": 0.2636, + "step": 26377 + }, + { + "epoch": 2.15, + "learning_rate": 5.670360712733595e-06, + "loss": 0.2541, + "step": 26378 + }, + { + "epoch": 2.15, + "learning_rate": 5.669817470664929e-06, + "loss": 0.328, + "step": 26379 + }, + { + "epoch": 2.15, + "learning_rate": 5.669274228596263e-06, + "loss": 0.2137, + "step": 26380 + }, + { + "epoch": 2.15, + "learning_rate": 5.668730986527597e-06, + "loss": 0.2628, + "step": 26381 + }, + { + "epoch": 2.15, + "learning_rate": 5.6681877444589316e-06, + "loss": 0.2352, + "step": 26382 + }, + { + "epoch": 2.15, + "learning_rate": 5.667644502390266e-06, + "loss": 0.1714, + "step": 26383 + }, + { + "epoch": 2.15, + "learning_rate": 5.6671012603216e-06, + "loss": 0.2123, + "step": 26384 + }, + { + "epoch": 2.15, + "learning_rate": 5.666558018252934e-06, + "loss": 0.3211, + "step": 26385 + }, + { + "epoch": 2.15, + "learning_rate": 5.666014776184268e-06, + "loss": 0.2004, + "step": 26386 + }, + { + "epoch": 2.15, + "learning_rate": 5.665471534115602e-06, + "loss": 0.1805, + "step": 26387 + }, + { + "epoch": 2.15, + "learning_rate": 5.664928292046936e-06, + "loss": 0.1068, + "step": 26388 + }, + { + "epoch": 2.15, + "learning_rate": 5.66438504997827e-06, + "loss": 0.1295, + "step": 26389 + }, + { + "epoch": 2.15, + "learning_rate": 5.6638418079096046e-06, + "loss": 0.2117, + "step": 26390 + }, + { + "epoch": 2.15, + "learning_rate": 5.663298565840939e-06, + "loss": 0.244, + "step": 26391 + }, + { + "epoch": 2.15, + "learning_rate": 5.662755323772273e-06, + "loss": 0.1669, + "step": 26392 + }, + { + "epoch": 2.15, + "learning_rate": 5.662212081703607e-06, + "loss": 0.5383, + "step": 26393 + }, + { + "epoch": 2.15, + "learning_rate": 5.6616688396349415e-06, + "loss": 0.3367, + "step": 26394 + }, + { + "epoch": 2.15, + "learning_rate": 5.661125597566276e-06, + "loss": 0.1023, + "step": 26395 + }, + { + "epoch": 2.15, + "learning_rate": 5.66058235549761e-06, + "loss": 0.1505, + "step": 26396 + }, + { + "epoch": 2.15, + "learning_rate": 5.660039113428944e-06, + "loss": 0.2336, + "step": 26397 + }, + { + "epoch": 2.15, + "learning_rate": 5.659495871360278e-06, + "loss": 0.1786, + "step": 26398 + }, + { + "epoch": 2.15, + "learning_rate": 5.658952629291613e-06, + "loss": 0.2468, + "step": 26399 + }, + { + "epoch": 2.15, + "learning_rate": 5.658409387222948e-06, + "loss": 0.2047, + "step": 26400 + }, + { + "epoch": 2.15, + "learning_rate": 5.657866145154282e-06, + "loss": 0.1118, + "step": 26401 + }, + { + "epoch": 2.15, + "learning_rate": 5.657322903085616e-06, + "loss": 0.2581, + "step": 26402 + }, + { + "epoch": 2.15, + "learning_rate": 5.65677966101695e-06, + "loss": 0.2656, + "step": 26403 + }, + { + "epoch": 2.15, + "learning_rate": 5.656236418948285e-06, + "loss": 0.2191, + "step": 26404 + }, + { + "epoch": 2.15, + "learning_rate": 5.655693176879617e-06, + "loss": 0.1369, + "step": 26405 + }, + { + "epoch": 2.15, + "learning_rate": 5.655149934810951e-06, + "loss": 0.1882, + "step": 26406 + }, + { + "epoch": 2.15, + "learning_rate": 5.654606692742286e-06, + "loss": 0.2403, + "step": 26407 + }, + { + "epoch": 2.15, + "learning_rate": 5.65406345067362e-06, + "loss": 0.2073, + "step": 26408 + }, + { + "epoch": 2.15, + "learning_rate": 5.653520208604955e-06, + "loss": 0.1265, + "step": 26409 + }, + { + "epoch": 2.15, + "learning_rate": 5.652976966536289e-06, + "loss": 0.3382, + "step": 26410 + }, + { + "epoch": 2.15, + "learning_rate": 5.652433724467623e-06, + "loss": 0.3014, + "step": 26411 + }, + { + "epoch": 2.15, + "learning_rate": 5.651890482398958e-06, + "loss": 0.0748, + "step": 26412 + }, + { + "epoch": 2.15, + "learning_rate": 5.651347240330292e-06, + "loss": 0.141, + "step": 26413 + }, + { + "epoch": 2.15, + "learning_rate": 5.650803998261626e-06, + "loss": 0.0352, + "step": 26414 + }, + { + "epoch": 2.15, + "learning_rate": 5.65026075619296e-06, + "loss": 0.1584, + "step": 26415 + }, + { + "epoch": 2.15, + "learning_rate": 5.6497175141242946e-06, + "loss": 0.3298, + "step": 26416 + }, + { + "epoch": 2.15, + "learning_rate": 5.649174272055629e-06, + "loss": 0.618, + "step": 26417 + }, + { + "epoch": 2.15, + "learning_rate": 5.648631029986963e-06, + "loss": 0.3186, + "step": 26418 + }, + { + "epoch": 2.15, + "learning_rate": 5.648087787918297e-06, + "loss": 0.335, + "step": 26419 + }, + { + "epoch": 2.15, + "learning_rate": 5.6475445458496315e-06, + "loss": 0.3246, + "step": 26420 + }, + { + "epoch": 2.15, + "learning_rate": 5.647001303780966e-06, + "loss": 0.184, + "step": 26421 + }, + { + "epoch": 2.15, + "learning_rate": 5.6464580617123e-06, + "loss": 0.2149, + "step": 26422 + }, + { + "epoch": 2.15, + "learning_rate": 5.645914819643634e-06, + "loss": 0.1211, + "step": 26423 + }, + { + "epoch": 2.15, + "learning_rate": 5.6453715775749676e-06, + "loss": 0.2305, + "step": 26424 + }, + { + "epoch": 2.15, + "learning_rate": 5.644828335506302e-06, + "loss": 0.172, + "step": 26425 + }, + { + "epoch": 2.15, + "learning_rate": 5.644285093437636e-06, + "loss": 0.1716, + "step": 26426 + }, + { + "epoch": 2.15, + "learning_rate": 5.64374185136897e-06, + "loss": 0.1303, + "step": 26427 + }, + { + "epoch": 2.15, + "learning_rate": 5.6431986093003045e-06, + "loss": 0.4305, + "step": 26428 + }, + { + "epoch": 2.15, + "learning_rate": 5.642655367231639e-06, + "loss": 0.2558, + "step": 26429 + }, + { + "epoch": 2.15, + "learning_rate": 5.642112125162973e-06, + "loss": 0.2849, + "step": 26430 + }, + { + "epoch": 2.15, + "learning_rate": 5.641568883094307e-06, + "loss": 0.1971, + "step": 26431 + }, + { + "epoch": 2.15, + "learning_rate": 5.641025641025641e-06, + "loss": 0.0835, + "step": 26432 + }, + { + "epoch": 2.15, + "learning_rate": 5.640482398956976e-06, + "loss": 0.075, + "step": 26433 + }, + { + "epoch": 2.15, + "learning_rate": 5.63993915688831e-06, + "loss": 0.122, + "step": 26434 + }, + { + "epoch": 2.15, + "learning_rate": 5.639395914819644e-06, + "loss": 0.1608, + "step": 26435 + }, + { + "epoch": 2.15, + "learning_rate": 5.638852672750978e-06, + "loss": 0.433, + "step": 26436 + }, + { + "epoch": 2.15, + "learning_rate": 5.6383094306823126e-06, + "loss": 0.1426, + "step": 26437 + }, + { + "epoch": 2.15, + "learning_rate": 5.637766188613647e-06, + "loss": 0.165, + "step": 26438 + }, + { + "epoch": 2.15, + "learning_rate": 5.637222946544981e-06, + "loss": 0.049, + "step": 26439 + }, + { + "epoch": 2.15, + "learning_rate": 5.636679704476315e-06, + "loss": 0.1212, + "step": 26440 + }, + { + "epoch": 2.15, + "learning_rate": 5.6361364624076495e-06, + "loss": 0.3363, + "step": 26441 + }, + { + "epoch": 2.15, + "learning_rate": 5.635593220338984e-06, + "loss": 0.1683, + "step": 26442 + }, + { + "epoch": 2.15, + "learning_rate": 5.635049978270317e-06, + "loss": 0.1477, + "step": 26443 + }, + { + "epoch": 2.15, + "learning_rate": 5.634506736201651e-06, + "loss": 0.0431, + "step": 26444 + }, + { + "epoch": 2.15, + "learning_rate": 5.6339634941329856e-06, + "loss": 0.1398, + "step": 26445 + }, + { + "epoch": 2.15, + "learning_rate": 5.63342025206432e-06, + "loss": 0.3421, + "step": 26446 + }, + { + "epoch": 2.16, + "learning_rate": 5.632877009995654e-06, + "loss": 0.289, + "step": 26447 + }, + { + "epoch": 2.16, + "learning_rate": 5.632333767926988e-06, + "loss": 0.3031, + "step": 26448 + }, + { + "epoch": 2.16, + "learning_rate": 5.6317905258583225e-06, + "loss": 0.0918, + "step": 26449 + }, + { + "epoch": 2.16, + "learning_rate": 5.631247283789657e-06, + "loss": 0.1083, + "step": 26450 + }, + { + "epoch": 2.16, + "learning_rate": 5.630704041720991e-06, + "loss": 0.23, + "step": 26451 + }, + { + "epoch": 2.16, + "learning_rate": 5.630160799652325e-06, + "loss": 0.4626, + "step": 26452 + }, + { + "epoch": 2.16, + "learning_rate": 5.629617557583659e-06, + "loss": 0.0444, + "step": 26453 + }, + { + "epoch": 2.16, + "learning_rate": 5.6290743155149945e-06, + "loss": 0.2851, + "step": 26454 + }, + { + "epoch": 2.16, + "learning_rate": 5.628531073446329e-06, + "loss": 0.1055, + "step": 26455 + }, + { + "epoch": 2.16, + "learning_rate": 5.627987831377663e-06, + "loss": 0.1669, + "step": 26456 + }, + { + "epoch": 2.16, + "learning_rate": 5.627444589308997e-06, + "loss": 0.289, + "step": 26457 + }, + { + "epoch": 2.16, + "learning_rate": 5.626901347240331e-06, + "loss": 0.1571, + "step": 26458 + }, + { + "epoch": 2.16, + "learning_rate": 5.626358105171666e-06, + "loss": 0.3748, + "step": 26459 + }, + { + "epoch": 2.16, + "learning_rate": 5.625814863103e-06, + "loss": 0.1148, + "step": 26460 + }, + { + "epoch": 2.16, + "learning_rate": 5.625271621034334e-06, + "loss": 0.2046, + "step": 26461 + }, + { + "epoch": 2.16, + "learning_rate": 5.624728378965667e-06, + "loss": 0.1531, + "step": 26462 + }, + { + "epoch": 2.16, + "learning_rate": 5.624185136897002e-06, + "loss": 0.2342, + "step": 26463 + }, + { + "epoch": 2.16, + "learning_rate": 5.623641894828336e-06, + "loss": 0.1545, + "step": 26464 + }, + { + "epoch": 2.16, + "learning_rate": 5.62309865275967e-06, + "loss": 0.1717, + "step": 26465 + }, + { + "epoch": 2.16, + "learning_rate": 5.622555410691004e-06, + "loss": 0.2865, + "step": 26466 + }, + { + "epoch": 2.16, + "learning_rate": 5.622012168622339e-06, + "loss": 0.3925, + "step": 26467 + }, + { + "epoch": 2.16, + "learning_rate": 5.621468926553673e-06, + "loss": 0.3583, + "step": 26468 + }, + { + "epoch": 2.16, + "learning_rate": 5.620925684485007e-06, + "loss": 0.2494, + "step": 26469 + }, + { + "epoch": 2.16, + "learning_rate": 5.620382442416341e-06, + "loss": 0.1576, + "step": 26470 + }, + { + "epoch": 2.16, + "learning_rate": 5.6198392003476755e-06, + "loss": 0.1776, + "step": 26471 + }, + { + "epoch": 2.16, + "learning_rate": 5.61929595827901e-06, + "loss": 0.1018, + "step": 26472 + }, + { + "epoch": 2.16, + "learning_rate": 5.618752716210344e-06, + "loss": 0.2467, + "step": 26473 + }, + { + "epoch": 2.16, + "learning_rate": 5.618209474141678e-06, + "loss": 0.2459, + "step": 26474 + }, + { + "epoch": 2.16, + "learning_rate": 5.6176662320730125e-06, + "loss": 0.4265, + "step": 26475 + }, + { + "epoch": 2.16, + "learning_rate": 5.617122990004347e-06, + "loss": 0.1986, + "step": 26476 + }, + { + "epoch": 2.16, + "learning_rate": 5.616579747935681e-06, + "loss": 0.0878, + "step": 26477 + }, + { + "epoch": 2.16, + "learning_rate": 5.616036505867015e-06, + "loss": 0.2909, + "step": 26478 + }, + { + "epoch": 2.16, + "learning_rate": 5.615493263798349e-06, + "loss": 0.1821, + "step": 26479 + }, + { + "epoch": 2.16, + "learning_rate": 5.614950021729684e-06, + "loss": 0.2516, + "step": 26480 + }, + { + "epoch": 2.16, + "learning_rate": 5.614406779661017e-06, + "loss": 0.3909, + "step": 26481 + }, + { + "epoch": 2.16, + "learning_rate": 5.613863537592351e-06, + "loss": 0.0764, + "step": 26482 + }, + { + "epoch": 2.16, + "learning_rate": 5.6133202955236855e-06, + "loss": 0.1718, + "step": 26483 + }, + { + "epoch": 2.16, + "learning_rate": 5.61277705345502e-06, + "loss": 0.296, + "step": 26484 + }, + { + "epoch": 2.16, + "learning_rate": 5.612233811386354e-06, + "loss": 0.1355, + "step": 26485 + }, + { + "epoch": 2.16, + "learning_rate": 5.611690569317688e-06, + "loss": 0.236, + "step": 26486 + }, + { + "epoch": 2.16, + "learning_rate": 5.611147327249022e-06, + "loss": 0.1669, + "step": 26487 + }, + { + "epoch": 2.16, + "learning_rate": 5.610604085180357e-06, + "loss": 0.1317, + "step": 26488 + }, + { + "epoch": 2.16, + "learning_rate": 5.610060843111691e-06, + "loss": 0.1819, + "step": 26489 + }, + { + "epoch": 2.16, + "learning_rate": 5.609517601043025e-06, + "loss": 0.0905, + "step": 26490 + }, + { + "epoch": 2.16, + "learning_rate": 5.608974358974359e-06, + "loss": 0.1065, + "step": 26491 + }, + { + "epoch": 2.16, + "learning_rate": 5.6084311169056935e-06, + "loss": 0.1666, + "step": 26492 + }, + { + "epoch": 2.16, + "learning_rate": 5.607887874837028e-06, + "loss": 0.2959, + "step": 26493 + }, + { + "epoch": 2.16, + "learning_rate": 5.607344632768362e-06, + "loss": 0.2598, + "step": 26494 + }, + { + "epoch": 2.16, + "learning_rate": 5.606801390699696e-06, + "loss": 0.1133, + "step": 26495 + }, + { + "epoch": 2.16, + "learning_rate": 5.6062581486310305e-06, + "loss": 0.2892, + "step": 26496 + }, + { + "epoch": 2.16, + "learning_rate": 5.605714906562365e-06, + "loss": 0.3154, + "step": 26497 + }, + { + "epoch": 2.16, + "learning_rate": 5.605171664493699e-06, + "loss": 0.1239, + "step": 26498 + }, + { + "epoch": 2.16, + "learning_rate": 5.604628422425034e-06, + "loss": 0.3464, + "step": 26499 + }, + { + "epoch": 2.16, + "learning_rate": 5.6040851803563665e-06, + "loss": 0.1774, + "step": 26500 + }, + { + "epoch": 2.16, + "eval_accuracy": 0.8403464085583291, + "eval_loss": 0.5082084536552429, + "eval_runtime": 22.3717, + "eval_samples_per_second": 438.724, + "eval_steps_per_second": 3.442, + "step": 26500 + }, + { + "epoch": 2.16, + "learning_rate": 5.603541938287701e-06, + "loss": 0.3165, + "step": 26501 + }, + { + "epoch": 2.16, + "learning_rate": 5.602998696219035e-06, + "loss": 0.2568, + "step": 26502 + }, + { + "epoch": 2.16, + "learning_rate": 5.602455454150369e-06, + "loss": 0.0865, + "step": 26503 + }, + { + "epoch": 2.16, + "learning_rate": 5.6019122120817035e-06, + "loss": 0.1475, + "step": 26504 + }, + { + "epoch": 2.16, + "learning_rate": 5.601368970013038e-06, + "loss": 0.2477, + "step": 26505 + }, + { + "epoch": 2.16, + "learning_rate": 5.600825727944372e-06, + "loss": 0.2015, + "step": 26506 + }, + { + "epoch": 2.16, + "learning_rate": 5.600282485875706e-06, + "loss": 0.1154, + "step": 26507 + }, + { + "epoch": 2.16, + "learning_rate": 5.599739243807041e-06, + "loss": 0.0687, + "step": 26508 + }, + { + "epoch": 2.16, + "learning_rate": 5.5991960017383755e-06, + "loss": 0.1279, + "step": 26509 + }, + { + "epoch": 2.16, + "learning_rate": 5.59865275966971e-06, + "loss": 0.2319, + "step": 26510 + }, + { + "epoch": 2.16, + "learning_rate": 5.598109517601044e-06, + "loss": 0.1924, + "step": 26511 + }, + { + "epoch": 2.16, + "learning_rate": 5.597566275532378e-06, + "loss": 0.2318, + "step": 26512 + }, + { + "epoch": 2.16, + "learning_rate": 5.597023033463712e-06, + "loss": 0.2159, + "step": 26513 + }, + { + "epoch": 2.16, + "learning_rate": 5.596479791395047e-06, + "loss": 0.092, + "step": 26514 + }, + { + "epoch": 2.16, + "learning_rate": 5.595936549326381e-06, + "loss": 0.1453, + "step": 26515 + }, + { + "epoch": 2.16, + "learning_rate": 5.595393307257715e-06, + "loss": 0.3991, + "step": 26516 + }, + { + "epoch": 2.16, + "learning_rate": 5.594850065189049e-06, + "loss": 0.3128, + "step": 26517 + }, + { + "epoch": 2.16, + "learning_rate": 5.5943068231203835e-06, + "loss": 0.2839, + "step": 26518 + }, + { + "epoch": 2.16, + "learning_rate": 5.593763581051717e-06, + "loss": 0.1393, + "step": 26519 + }, + { + "epoch": 2.16, + "learning_rate": 5.593220338983051e-06, + "loss": 0.4984, + "step": 26520 + }, + { + "epoch": 2.16, + "learning_rate": 5.592677096914385e-06, + "loss": 0.2422, + "step": 26521 + }, + { + "epoch": 2.16, + "learning_rate": 5.59213385484572e-06, + "loss": 0.1429, + "step": 26522 + }, + { + "epoch": 2.16, + "learning_rate": 5.591590612777054e-06, + "loss": 0.0547, + "step": 26523 + }, + { + "epoch": 2.16, + "learning_rate": 5.591047370708388e-06, + "loss": 0.1241, + "step": 26524 + }, + { + "epoch": 2.16, + "learning_rate": 5.590504128639722e-06, + "loss": 0.2255, + "step": 26525 + }, + { + "epoch": 2.16, + "learning_rate": 5.5899608865710565e-06, + "loss": 0.0976, + "step": 26526 + }, + { + "epoch": 2.16, + "learning_rate": 5.589417644502391e-06, + "loss": 0.306, + "step": 26527 + }, + { + "epoch": 2.16, + "learning_rate": 5.588874402433725e-06, + "loss": 0.311, + "step": 26528 + }, + { + "epoch": 2.16, + "learning_rate": 5.588331160365059e-06, + "loss": 0.0781, + "step": 26529 + }, + { + "epoch": 2.16, + "learning_rate": 5.5877879182963935e-06, + "loss": 0.2795, + "step": 26530 + }, + { + "epoch": 2.16, + "learning_rate": 5.587244676227728e-06, + "loss": 0.3484, + "step": 26531 + }, + { + "epoch": 2.16, + "learning_rate": 5.586701434159062e-06, + "loss": 0.5066, + "step": 26532 + }, + { + "epoch": 2.16, + "learning_rate": 5.586158192090396e-06, + "loss": 0.1688, + "step": 26533 + }, + { + "epoch": 2.16, + "learning_rate": 5.58561495002173e-06, + "loss": 0.1681, + "step": 26534 + }, + { + "epoch": 2.16, + "learning_rate": 5.585071707953065e-06, + "loss": 0.4067, + "step": 26535 + }, + { + "epoch": 2.16, + "learning_rate": 5.584528465884399e-06, + "loss": 0.0554, + "step": 26536 + }, + { + "epoch": 2.16, + "learning_rate": 5.583985223815733e-06, + "loss": 0.1381, + "step": 26537 + }, + { + "epoch": 2.16, + "learning_rate": 5.5834419817470664e-06, + "loss": 0.3705, + "step": 26538 + }, + { + "epoch": 2.16, + "learning_rate": 5.582898739678401e-06, + "loss": 0.1381, + "step": 26539 + }, + { + "epoch": 2.16, + "learning_rate": 5.582355497609735e-06, + "loss": 0.0413, + "step": 26540 + }, + { + "epoch": 2.16, + "learning_rate": 5.581812255541069e-06, + "loss": 0.085, + "step": 26541 + }, + { + "epoch": 2.16, + "learning_rate": 5.581269013472403e-06, + "loss": 0.0645, + "step": 26542 + }, + { + "epoch": 2.16, + "learning_rate": 5.580725771403738e-06, + "loss": 0.3656, + "step": 26543 + }, + { + "epoch": 2.16, + "learning_rate": 5.580182529335072e-06, + "loss": 0.1504, + "step": 26544 + }, + { + "epoch": 2.16, + "learning_rate": 5.579639287266406e-06, + "loss": 0.2035, + "step": 26545 + }, + { + "epoch": 2.16, + "learning_rate": 5.57909604519774e-06, + "loss": 0.1516, + "step": 26546 + }, + { + "epoch": 2.16, + "learning_rate": 5.5785528031290745e-06, + "loss": 0.155, + "step": 26547 + }, + { + "epoch": 2.16, + "learning_rate": 5.578009561060409e-06, + "loss": 0.1586, + "step": 26548 + }, + { + "epoch": 2.16, + "learning_rate": 5.577466318991743e-06, + "loss": 0.2162, + "step": 26549 + }, + { + "epoch": 2.16, + "learning_rate": 5.576923076923077e-06, + "loss": 0.1617, + "step": 26550 + }, + { + "epoch": 2.16, + "learning_rate": 5.5763798348544114e-06, + "loss": 0.231, + "step": 26551 + }, + { + "epoch": 2.16, + "learning_rate": 5.575836592785746e-06, + "loss": 0.206, + "step": 26552 + }, + { + "epoch": 2.16, + "learning_rate": 5.575293350717081e-06, + "loss": 0.2265, + "step": 26553 + }, + { + "epoch": 2.16, + "learning_rate": 5.574750108648415e-06, + "loss": 0.1738, + "step": 26554 + }, + { + "epoch": 2.16, + "learning_rate": 5.574206866579749e-06, + "loss": 0.1025, + "step": 26555 + }, + { + "epoch": 2.16, + "learning_rate": 5.5736636245110834e-06, + "loss": 0.4382, + "step": 26556 + }, + { + "epoch": 2.16, + "learning_rate": 5.573120382442416e-06, + "loss": 0.0822, + "step": 26557 + }, + { + "epoch": 2.16, + "learning_rate": 5.57257714037375e-06, + "loss": 0.1201, + "step": 26558 + }, + { + "epoch": 2.16, + "learning_rate": 5.5720338983050844e-06, + "loss": 0.0877, + "step": 26559 + }, + { + "epoch": 2.16, + "learning_rate": 5.571490656236419e-06, + "loss": 0.2547, + "step": 26560 + }, + { + "epoch": 2.16, + "learning_rate": 5.570947414167753e-06, + "loss": 0.1596, + "step": 26561 + }, + { + "epoch": 2.16, + "learning_rate": 5.570404172099088e-06, + "loss": 0.2025, + "step": 26562 + }, + { + "epoch": 2.16, + "learning_rate": 5.569860930030422e-06, + "loss": 0.2222, + "step": 26563 + }, + { + "epoch": 2.16, + "learning_rate": 5.5693176879617564e-06, + "loss": 0.3794, + "step": 26564 + }, + { + "epoch": 2.16, + "learning_rate": 5.568774445893091e-06, + "loss": 0.1299, + "step": 26565 + }, + { + "epoch": 2.16, + "learning_rate": 5.568231203824425e-06, + "loss": 0.1745, + "step": 26566 + }, + { + "epoch": 2.16, + "learning_rate": 5.567687961755759e-06, + "loss": 0.1402, + "step": 26567 + }, + { + "epoch": 2.16, + "learning_rate": 5.567144719687093e-06, + "loss": 0.1822, + "step": 26568 + }, + { + "epoch": 2.17, + "learning_rate": 5.566601477618428e-06, + "loss": 0.176, + "step": 26569 + }, + { + "epoch": 2.17, + "learning_rate": 5.566058235549762e-06, + "loss": 0.2172, + "step": 26570 + }, + { + "epoch": 2.17, + "learning_rate": 5.565514993481096e-06, + "loss": 0.3192, + "step": 26571 + }, + { + "epoch": 2.17, + "learning_rate": 5.56497175141243e-06, + "loss": 0.2207, + "step": 26572 + }, + { + "epoch": 2.17, + "learning_rate": 5.5644285093437645e-06, + "loss": 0.3517, + "step": 26573 + }, + { + "epoch": 2.17, + "learning_rate": 5.563885267275099e-06, + "loss": 0.2031, + "step": 26574 + }, + { + "epoch": 2.17, + "learning_rate": 5.563342025206433e-06, + "loss": 0.0738, + "step": 26575 + }, + { + "epoch": 2.17, + "learning_rate": 5.562798783137766e-06, + "loss": 0.1766, + "step": 26576 + }, + { + "epoch": 2.17, + "learning_rate": 5.562255541069101e-06, + "loss": 0.5085, + "step": 26577 + }, + { + "epoch": 2.17, + "learning_rate": 5.561712299000435e-06, + "loss": 0.186, + "step": 26578 + }, + { + "epoch": 2.17, + "learning_rate": 5.561169056931769e-06, + "loss": 0.6335, + "step": 26579 + }, + { + "epoch": 2.17, + "learning_rate": 5.560625814863103e-06, + "loss": 0.2844, + "step": 26580 + }, + { + "epoch": 2.17, + "learning_rate": 5.5600825727944375e-06, + "loss": 0.1183, + "step": 26581 + }, + { + "epoch": 2.17, + "learning_rate": 5.559539330725772e-06, + "loss": 0.0973, + "step": 26582 + }, + { + "epoch": 2.17, + "learning_rate": 5.558996088657106e-06, + "loss": 0.2555, + "step": 26583 + }, + { + "epoch": 2.17, + "learning_rate": 5.55845284658844e-06, + "loss": 0.339, + "step": 26584 + }, + { + "epoch": 2.17, + "learning_rate": 5.5579096045197744e-06, + "loss": 0.2101, + "step": 26585 + }, + { + "epoch": 2.17, + "learning_rate": 5.557366362451109e-06, + "loss": 0.318, + "step": 26586 + }, + { + "epoch": 2.17, + "learning_rate": 5.556823120382443e-06, + "loss": 0.17, + "step": 26587 + }, + { + "epoch": 2.17, + "learning_rate": 5.556279878313777e-06, + "loss": 0.2556, + "step": 26588 + }, + { + "epoch": 2.17, + "learning_rate": 5.555736636245111e-06, + "loss": 0.196, + "step": 26589 + }, + { + "epoch": 2.17, + "learning_rate": 5.555193394176446e-06, + "loss": 0.1768, + "step": 26590 + }, + { + "epoch": 2.17, + "learning_rate": 5.55465015210778e-06, + "loss": 0.2211, + "step": 26591 + }, + { + "epoch": 2.17, + "learning_rate": 5.554106910039114e-06, + "loss": 0.2372, + "step": 26592 + }, + { + "epoch": 2.17, + "learning_rate": 5.553563667970448e-06, + "loss": 0.3581, + "step": 26593 + }, + { + "epoch": 2.17, + "learning_rate": 5.5530204259017825e-06, + "loss": 0.232, + "step": 26594 + }, + { + "epoch": 2.17, + "learning_rate": 5.552477183833116e-06, + "loss": 0.2503, + "step": 26595 + }, + { + "epoch": 2.17, + "learning_rate": 5.55193394176445e-06, + "loss": 0.1663, + "step": 26596 + }, + { + "epoch": 2.17, + "learning_rate": 5.551390699695784e-06, + "loss": 0.141, + "step": 26597 + }, + { + "epoch": 2.17, + "learning_rate": 5.550847457627119e-06, + "loss": 0.6126, + "step": 26598 + }, + { + "epoch": 2.17, + "learning_rate": 5.550304215558453e-06, + "loss": 0.212, + "step": 26599 + }, + { + "epoch": 2.17, + "learning_rate": 5.549760973489787e-06, + "loss": 0.3409, + "step": 26600 + }, + { + "epoch": 2.17, + "learning_rate": 5.549217731421121e-06, + "loss": 0.1989, + "step": 26601 + }, + { + "epoch": 2.17, + "learning_rate": 5.5486744893524555e-06, + "loss": 0.2091, + "step": 26602 + }, + { + "epoch": 2.17, + "learning_rate": 5.54813124728379e-06, + "loss": 0.0888, + "step": 26603 + }, + { + "epoch": 2.17, + "learning_rate": 5.547588005215124e-06, + "loss": 0.1048, + "step": 26604 + }, + { + "epoch": 2.17, + "learning_rate": 5.547044763146458e-06, + "loss": 0.225, + "step": 26605 + }, + { + "epoch": 2.17, + "learning_rate": 5.5465015210777924e-06, + "loss": 0.1355, + "step": 26606 + }, + { + "epoch": 2.17, + "learning_rate": 5.5459582790091275e-06, + "loss": 0.1075, + "step": 26607 + }, + { + "epoch": 2.17, + "learning_rate": 5.545415036940462e-06, + "loss": 0.2486, + "step": 26608 + }, + { + "epoch": 2.17, + "learning_rate": 5.544871794871796e-06, + "loss": 0.1672, + "step": 26609 + }, + { + "epoch": 2.17, + "learning_rate": 5.54432855280313e-06, + "loss": 0.1838, + "step": 26610 + }, + { + "epoch": 2.17, + "learning_rate": 5.5437853107344644e-06, + "loss": 0.238, + "step": 26611 + }, + { + "epoch": 2.17, + "learning_rate": 5.543242068665799e-06, + "loss": 0.2074, + "step": 26612 + }, + { + "epoch": 2.17, + "learning_rate": 5.542698826597133e-06, + "loss": 0.3789, + "step": 26613 + }, + { + "epoch": 2.17, + "learning_rate": 5.5421555845284654e-06, + "loss": 0.1972, + "step": 26614 + }, + { + "epoch": 2.17, + "learning_rate": 5.5416123424598e-06, + "loss": 0.1722, + "step": 26615 + }, + { + "epoch": 2.17, + "learning_rate": 5.541069100391135e-06, + "loss": 0.138, + "step": 26616 + }, + { + "epoch": 2.17, + "learning_rate": 5.540525858322469e-06, + "loss": 0.1302, + "step": 26617 + }, + { + "epoch": 2.17, + "learning_rate": 5.539982616253803e-06, + "loss": 0.1, + "step": 26618 + }, + { + "epoch": 2.17, + "learning_rate": 5.5394393741851374e-06, + "loss": 0.2546, + "step": 26619 + }, + { + "epoch": 2.17, + "learning_rate": 5.538896132116472e-06, + "loss": 0.3209, + "step": 26620 + }, + { + "epoch": 2.17, + "learning_rate": 5.538352890047806e-06, + "loss": 0.5272, + "step": 26621 + }, + { + "epoch": 2.17, + "learning_rate": 5.53780964797914e-06, + "loss": 0.1532, + "step": 26622 + }, + { + "epoch": 2.17, + "learning_rate": 5.537266405910474e-06, + "loss": 0.1319, + "step": 26623 + }, + { + "epoch": 2.17, + "learning_rate": 5.536723163841809e-06, + "loss": 0.2465, + "step": 26624 + }, + { + "epoch": 2.17, + "learning_rate": 5.536179921773143e-06, + "loss": 0.1676, + "step": 26625 + }, + { + "epoch": 2.17, + "learning_rate": 5.535636679704477e-06, + "loss": 0.2902, + "step": 26626 + }, + { + "epoch": 2.17, + "learning_rate": 5.535093437635811e-06, + "loss": 0.1443, + "step": 26627 + }, + { + "epoch": 2.17, + "learning_rate": 5.5345501955671455e-06, + "loss": 0.0911, + "step": 26628 + }, + { + "epoch": 2.17, + "learning_rate": 5.53400695349848e-06, + "loss": 0.1179, + "step": 26629 + }, + { + "epoch": 2.17, + "learning_rate": 5.533463711429814e-06, + "loss": 0.2376, + "step": 26630 + }, + { + "epoch": 2.17, + "learning_rate": 5.532920469361148e-06, + "loss": 0.1793, + "step": 26631 + }, + { + "epoch": 2.17, + "learning_rate": 5.5323772272924824e-06, + "loss": 0.2521, + "step": 26632 + }, + { + "epoch": 2.17, + "learning_rate": 5.531833985223816e-06, + "loss": 0.3499, + "step": 26633 + }, + { + "epoch": 2.17, + "learning_rate": 5.53129074315515e-06, + "loss": 0.1875, + "step": 26634 + }, + { + "epoch": 2.17, + "learning_rate": 5.530747501086484e-06, + "loss": 0.4178, + "step": 26635 + }, + { + "epoch": 2.17, + "learning_rate": 5.5302042590178185e-06, + "loss": 0.2125, + "step": 26636 + }, + { + "epoch": 2.17, + "learning_rate": 5.529661016949153e-06, + "loss": 0.1942, + "step": 26637 + }, + { + "epoch": 2.17, + "learning_rate": 5.529117774880487e-06, + "loss": 0.1742, + "step": 26638 + }, + { + "epoch": 2.17, + "learning_rate": 5.528574532811821e-06, + "loss": 0.2362, + "step": 26639 + }, + { + "epoch": 2.17, + "learning_rate": 5.5280312907431554e-06, + "loss": 0.2391, + "step": 26640 + }, + { + "epoch": 2.17, + "learning_rate": 5.52748804867449e-06, + "loss": 0.0355, + "step": 26641 + }, + { + "epoch": 2.17, + "learning_rate": 5.526944806605824e-06, + "loss": 0.3458, + "step": 26642 + }, + { + "epoch": 2.17, + "learning_rate": 5.526401564537158e-06, + "loss": 0.1953, + "step": 26643 + }, + { + "epoch": 2.17, + "learning_rate": 5.525858322468492e-06, + "loss": 0.2516, + "step": 26644 + }, + { + "epoch": 2.17, + "learning_rate": 5.525315080399827e-06, + "loss": 0.113, + "step": 26645 + }, + { + "epoch": 2.17, + "learning_rate": 5.524771838331161e-06, + "loss": 0.1833, + "step": 26646 + }, + { + "epoch": 2.17, + "learning_rate": 5.524228596262495e-06, + "loss": 0.2938, + "step": 26647 + }, + { + "epoch": 2.17, + "learning_rate": 5.523685354193829e-06, + "loss": 0.3123, + "step": 26648 + }, + { + "epoch": 2.17, + "learning_rate": 5.5231421121251635e-06, + "loss": 0.1209, + "step": 26649 + }, + { + "epoch": 2.17, + "learning_rate": 5.522598870056498e-06, + "loss": 0.3886, + "step": 26650 + }, + { + "epoch": 2.17, + "learning_rate": 5.522055627987832e-06, + "loss": 0.2436, + "step": 26651 + }, + { + "epoch": 2.17, + "learning_rate": 5.521512385919165e-06, + "loss": 0.3861, + "step": 26652 + }, + { + "epoch": 2.17, + "learning_rate": 5.5209691438504996e-06, + "loss": 0.4498, + "step": 26653 + }, + { + "epoch": 2.17, + "learning_rate": 5.520425901781834e-06, + "loss": 0.1713, + "step": 26654 + }, + { + "epoch": 2.17, + "learning_rate": 5.519882659713168e-06, + "loss": 0.4773, + "step": 26655 + }, + { + "epoch": 2.17, + "learning_rate": 5.519339417644502e-06, + "loss": 0.115, + "step": 26656 + }, + { + "epoch": 2.17, + "learning_rate": 5.5187961755758365e-06, + "loss": 0.1874, + "step": 26657 + }, + { + "epoch": 2.17, + "learning_rate": 5.518252933507171e-06, + "loss": 0.3513, + "step": 26658 + }, + { + "epoch": 2.17, + "learning_rate": 5.517709691438505e-06, + "loss": 0.2065, + "step": 26659 + }, + { + "epoch": 2.17, + "learning_rate": 5.517166449369839e-06, + "loss": 0.1096, + "step": 26660 + }, + { + "epoch": 2.17, + "learning_rate": 5.516623207301174e-06, + "loss": 0.197, + "step": 26661 + }, + { + "epoch": 2.17, + "learning_rate": 5.5160799652325085e-06, + "loss": 0.2667, + "step": 26662 + }, + { + "epoch": 2.17, + "learning_rate": 5.515536723163843e-06, + "loss": 0.0964, + "step": 26663 + }, + { + "epoch": 2.17, + "learning_rate": 5.514993481095177e-06, + "loss": 0.4798, + "step": 26664 + }, + { + "epoch": 2.17, + "learning_rate": 5.514450239026511e-06, + "loss": 0.1784, + "step": 26665 + }, + { + "epoch": 2.17, + "learning_rate": 5.513906996957845e-06, + "loss": 0.0692, + "step": 26666 + }, + { + "epoch": 2.17, + "learning_rate": 5.51336375488918e-06, + "loss": 0.2796, + "step": 26667 + }, + { + "epoch": 2.17, + "learning_rate": 5.512820512820514e-06, + "loss": 0.2655, + "step": 26668 + }, + { + "epoch": 2.17, + "learning_rate": 5.512277270751848e-06, + "loss": 0.1662, + "step": 26669 + }, + { + "epoch": 2.17, + "learning_rate": 5.511734028683182e-06, + "loss": 0.2279, + "step": 26670 + }, + { + "epoch": 2.17, + "learning_rate": 5.511190786614516e-06, + "loss": 0.1904, + "step": 26671 + }, + { + "epoch": 2.17, + "learning_rate": 5.51064754454585e-06, + "loss": 0.2192, + "step": 26672 + }, + { + "epoch": 2.17, + "learning_rate": 5.510104302477184e-06, + "loss": 0.2141, + "step": 26673 + }, + { + "epoch": 2.17, + "learning_rate": 5.509561060408518e-06, + "loss": 0.094, + "step": 26674 + }, + { + "epoch": 2.17, + "learning_rate": 5.509017818339853e-06, + "loss": 0.3325, + "step": 26675 + }, + { + "epoch": 2.17, + "learning_rate": 5.508474576271187e-06, + "loss": 0.2392, + "step": 26676 + }, + { + "epoch": 2.17, + "learning_rate": 5.507931334202521e-06, + "loss": 0.1922, + "step": 26677 + }, + { + "epoch": 2.17, + "learning_rate": 5.507388092133855e-06, + "loss": 0.0904, + "step": 26678 + }, + { + "epoch": 2.17, + "learning_rate": 5.5068448500651896e-06, + "loss": 0.2196, + "step": 26679 + }, + { + "epoch": 2.17, + "learning_rate": 5.506301607996524e-06, + "loss": 0.2909, + "step": 26680 + }, + { + "epoch": 2.17, + "learning_rate": 5.505758365927858e-06, + "loss": 0.2679, + "step": 26681 + }, + { + "epoch": 2.17, + "learning_rate": 5.505215123859192e-06, + "loss": 0.2776, + "step": 26682 + }, + { + "epoch": 2.17, + "learning_rate": 5.5046718817905265e-06, + "loss": 0.1778, + "step": 26683 + }, + { + "epoch": 2.17, + "learning_rate": 5.504128639721861e-06, + "loss": 0.2235, + "step": 26684 + }, + { + "epoch": 2.17, + "learning_rate": 5.503585397653195e-06, + "loss": 0.471, + "step": 26685 + }, + { + "epoch": 2.17, + "learning_rate": 5.503042155584529e-06, + "loss": 0.3776, + "step": 26686 + }, + { + "epoch": 2.17, + "learning_rate": 5.502498913515863e-06, + "loss": 0.274, + "step": 26687 + }, + { + "epoch": 2.17, + "learning_rate": 5.501955671447198e-06, + "loss": 0.3458, + "step": 26688 + }, + { + "epoch": 2.17, + "learning_rate": 5.501412429378532e-06, + "loss": 0.0933, + "step": 26689 + }, + { + "epoch": 2.17, + "learning_rate": 5.500869187309865e-06, + "loss": 0.2149, + "step": 26690 + }, + { + "epoch": 2.17, + "learning_rate": 5.5003259452411995e-06, + "loss": 0.0649, + "step": 26691 + }, + { + "epoch": 2.18, + "learning_rate": 5.499782703172534e-06, + "loss": 0.3294, + "step": 26692 + }, + { + "epoch": 2.18, + "learning_rate": 5.499239461103868e-06, + "loss": 0.3044, + "step": 26693 + }, + { + "epoch": 2.18, + "learning_rate": 5.498696219035202e-06, + "loss": 0.1282, + "step": 26694 + }, + { + "epoch": 2.18, + "learning_rate": 5.498152976966536e-06, + "loss": 0.2414, + "step": 26695 + }, + { + "epoch": 2.18, + "learning_rate": 5.497609734897871e-06, + "loss": 0.3159, + "step": 26696 + }, + { + "epoch": 2.18, + "learning_rate": 5.497066492829205e-06, + "loss": 0.3775, + "step": 26697 + }, + { + "epoch": 2.18, + "learning_rate": 5.496523250760539e-06, + "loss": 0.1507, + "step": 26698 + }, + { + "epoch": 2.18, + "learning_rate": 5.495980008691873e-06, + "loss": 0.1843, + "step": 26699 + }, + { + "epoch": 2.18, + "learning_rate": 5.4954367666232076e-06, + "loss": 0.2275, + "step": 26700 + }, + { + "epoch": 2.18, + "learning_rate": 5.494893524554542e-06, + "loss": 0.1438, + "step": 26701 + }, + { + "epoch": 2.18, + "learning_rate": 5.494350282485876e-06, + "loss": 0.1433, + "step": 26702 + }, + { + "epoch": 2.18, + "learning_rate": 5.49380704041721e-06, + "loss": 0.0955, + "step": 26703 + }, + { + "epoch": 2.18, + "learning_rate": 5.4932637983485445e-06, + "loss": 0.1035, + "step": 26704 + }, + { + "epoch": 2.18, + "learning_rate": 5.492720556279879e-06, + "loss": 0.2962, + "step": 26705 + }, + { + "epoch": 2.18, + "learning_rate": 5.492177314211213e-06, + "loss": 0.1036, + "step": 26706 + }, + { + "epoch": 2.18, + "learning_rate": 5.491634072142548e-06, + "loss": 0.4173, + "step": 26707 + }, + { + "epoch": 2.18, + "learning_rate": 5.491090830073882e-06, + "loss": 0.2761, + "step": 26708 + }, + { + "epoch": 2.18, + "learning_rate": 5.490547588005215e-06, + "loss": 0.2824, + "step": 26709 + }, + { + "epoch": 2.18, + "learning_rate": 5.490004345936549e-06, + "loss": 0.2458, + "step": 26710 + }, + { + "epoch": 2.18, + "learning_rate": 5.489461103867883e-06, + "loss": 0.2397, + "step": 26711 + }, + { + "epoch": 2.18, + "learning_rate": 5.4889178617992175e-06, + "loss": 0.3268, + "step": 26712 + }, + { + "epoch": 2.18, + "learning_rate": 5.488374619730552e-06, + "loss": 0.2102, + "step": 26713 + }, + { + "epoch": 2.18, + "learning_rate": 5.487831377661886e-06, + "loss": 0.4987, + "step": 26714 + }, + { + "epoch": 2.18, + "learning_rate": 5.487288135593221e-06, + "loss": 0.0813, + "step": 26715 + }, + { + "epoch": 2.18, + "learning_rate": 5.486744893524555e-06, + "loss": 0.2117, + "step": 26716 + }, + { + "epoch": 2.18, + "learning_rate": 5.4862016514558895e-06, + "loss": 0.2016, + "step": 26717 + }, + { + "epoch": 2.18, + "learning_rate": 5.485658409387224e-06, + "loss": 0.2892, + "step": 26718 + }, + { + "epoch": 2.18, + "learning_rate": 5.485115167318558e-06, + "loss": 0.2218, + "step": 26719 + }, + { + "epoch": 2.18, + "learning_rate": 5.484571925249892e-06, + "loss": 0.0949, + "step": 26720 + }, + { + "epoch": 2.18, + "learning_rate": 5.484028683181226e-06, + "loss": 0.1235, + "step": 26721 + }, + { + "epoch": 2.18, + "learning_rate": 5.483485441112561e-06, + "loss": 0.3598, + "step": 26722 + }, + { + "epoch": 2.18, + "learning_rate": 5.482942199043895e-06, + "loss": 0.0856, + "step": 26723 + }, + { + "epoch": 2.18, + "learning_rate": 5.482398956975229e-06, + "loss": 0.1286, + "step": 26724 + }, + { + "epoch": 2.18, + "learning_rate": 5.481855714906563e-06, + "loss": 0.2045, + "step": 26725 + }, + { + "epoch": 2.18, + "learning_rate": 5.4813124728378976e-06, + "loss": 0.2547, + "step": 26726 + }, + { + "epoch": 2.18, + "learning_rate": 5.480769230769232e-06, + "loss": 0.1935, + "step": 26727 + }, + { + "epoch": 2.18, + "learning_rate": 5.480225988700565e-06, + "loss": 0.1773, + "step": 26728 + }, + { + "epoch": 2.18, + "learning_rate": 5.479682746631899e-06, + "loss": 0.0589, + "step": 26729 + }, + { + "epoch": 2.18, + "learning_rate": 5.479139504563234e-06, + "loss": 0.1304, + "step": 26730 + }, + { + "epoch": 2.18, + "learning_rate": 5.478596262494568e-06, + "loss": 0.4236, + "step": 26731 + }, + { + "epoch": 2.18, + "learning_rate": 5.478053020425902e-06, + "loss": 0.3403, + "step": 26732 + }, + { + "epoch": 2.18, + "learning_rate": 5.477509778357236e-06, + "loss": 0.4134, + "step": 26733 + }, + { + "epoch": 2.18, + "learning_rate": 5.4769665362885706e-06, + "loss": 0.2011, + "step": 26734 + }, + { + "epoch": 2.18, + "learning_rate": 5.476423294219905e-06, + "loss": 0.2334, + "step": 26735 + }, + { + "epoch": 2.18, + "learning_rate": 5.475880052151239e-06, + "loss": 0.0997, + "step": 26736 + }, + { + "epoch": 2.18, + "learning_rate": 5.475336810082573e-06, + "loss": 0.5533, + "step": 26737 + }, + { + "epoch": 2.18, + "learning_rate": 5.4747935680139075e-06, + "loss": 0.2485, + "step": 26738 + }, + { + "epoch": 2.18, + "learning_rate": 5.474250325945242e-06, + "loss": 0.1889, + "step": 26739 + }, + { + "epoch": 2.18, + "learning_rate": 5.473707083876576e-06, + "loss": 0.1759, + "step": 26740 + }, + { + "epoch": 2.18, + "learning_rate": 5.47316384180791e-06, + "loss": 0.0943, + "step": 26741 + }, + { + "epoch": 2.18, + "learning_rate": 5.472620599739244e-06, + "loss": 0.1695, + "step": 26742 + }, + { + "epoch": 2.18, + "learning_rate": 5.472077357670579e-06, + "loss": 0.5008, + "step": 26743 + }, + { + "epoch": 2.18, + "learning_rate": 5.471534115601913e-06, + "loss": 0.1702, + "step": 26744 + }, + { + "epoch": 2.18, + "learning_rate": 5.470990873533247e-06, + "loss": 0.1851, + "step": 26745 + }, + { + "epoch": 2.18, + "learning_rate": 5.470447631464581e-06, + "loss": 0.1366, + "step": 26746 + }, + { + "epoch": 2.18, + "learning_rate": 5.469904389395915e-06, + "loss": 0.3355, + "step": 26747 + }, + { + "epoch": 2.18, + "learning_rate": 5.469361147327249e-06, + "loss": 0.1633, + "step": 26748 + }, + { + "epoch": 2.18, + "learning_rate": 5.468817905258583e-06, + "loss": 0.2268, + "step": 26749 + }, + { + "epoch": 2.18, + "learning_rate": 5.468274663189917e-06, + "loss": 0.2037, + "step": 26750 + }, + { + "epoch": 2.18, + "eval_accuracy": 0.839429444727458, + "eval_loss": 0.49961644411087036, + "eval_runtime": 22.1964, + "eval_samples_per_second": 442.189, + "eval_steps_per_second": 3.469, + "step": 26750 + }, + { + "epoch": 2.18, + "learning_rate": 5.467731421121252e-06, + "loss": 0.2591, + "step": 26751 + }, + { + "epoch": 2.18, + "learning_rate": 5.467188179052586e-06, + "loss": 0.2376, + "step": 26752 + }, + { + "epoch": 2.18, + "learning_rate": 5.46664493698392e-06, + "loss": 0.1932, + "step": 26753 + }, + { + "epoch": 2.18, + "learning_rate": 5.466101694915254e-06, + "loss": 0.2658, + "step": 26754 + }, + { + "epoch": 2.18, + "learning_rate": 5.4655584528465885e-06, + "loss": 0.2112, + "step": 26755 + }, + { + "epoch": 2.18, + "learning_rate": 5.465015210777923e-06, + "loss": 0.1381, + "step": 26756 + }, + { + "epoch": 2.18, + "learning_rate": 5.464471968709257e-06, + "loss": 0.1667, + "step": 26757 + }, + { + "epoch": 2.18, + "learning_rate": 5.463928726640591e-06, + "loss": 0.1796, + "step": 26758 + }, + { + "epoch": 2.18, + "learning_rate": 5.4633854845719255e-06, + "loss": 0.4024, + "step": 26759 + }, + { + "epoch": 2.18, + "learning_rate": 5.46284224250326e-06, + "loss": 0.3059, + "step": 26760 + }, + { + "epoch": 2.18, + "learning_rate": 5.462299000434595e-06, + "loss": 0.3282, + "step": 26761 + }, + { + "epoch": 2.18, + "learning_rate": 5.461755758365929e-06, + "loss": 0.4011, + "step": 26762 + }, + { + "epoch": 2.18, + "learning_rate": 5.461212516297263e-06, + "loss": 0.2557, + "step": 26763 + }, + { + "epoch": 2.18, + "learning_rate": 5.4606692742285975e-06, + "loss": 0.0586, + "step": 26764 + }, + { + "epoch": 2.18, + "learning_rate": 5.460126032159932e-06, + "loss": 0.1171, + "step": 26765 + }, + { + "epoch": 2.18, + "learning_rate": 5.459582790091264e-06, + "loss": 0.2759, + "step": 26766 + }, + { + "epoch": 2.18, + "learning_rate": 5.4590395480225985e-06, + "loss": 0.1551, + "step": 26767 + }, + { + "epoch": 2.18, + "learning_rate": 5.458496305953933e-06, + "loss": 0.169, + "step": 26768 + }, + { + "epoch": 2.18, + "learning_rate": 5.457953063885268e-06, + "loss": 0.2894, + "step": 26769 + }, + { + "epoch": 2.18, + "learning_rate": 5.457409821816602e-06, + "loss": 0.4258, + "step": 26770 + }, + { + "epoch": 2.18, + "learning_rate": 5.456866579747936e-06, + "loss": 0.157, + "step": 26771 + }, + { + "epoch": 2.18, + "learning_rate": 5.4563233376792705e-06, + "loss": 0.124, + "step": 26772 + }, + { + "epoch": 2.18, + "learning_rate": 5.455780095610605e-06, + "loss": 0.5406, + "step": 26773 + }, + { + "epoch": 2.18, + "learning_rate": 5.455236853541939e-06, + "loss": 0.3944, + "step": 26774 + }, + { + "epoch": 2.18, + "learning_rate": 5.454693611473273e-06, + "loss": 0.1702, + "step": 26775 + }, + { + "epoch": 2.18, + "learning_rate": 5.454150369404607e-06, + "loss": 0.2717, + "step": 26776 + }, + { + "epoch": 2.18, + "learning_rate": 5.453607127335942e-06, + "loss": 0.2786, + "step": 26777 + }, + { + "epoch": 2.18, + "learning_rate": 5.453063885267276e-06, + "loss": 0.2668, + "step": 26778 + }, + { + "epoch": 2.18, + "learning_rate": 5.45252064319861e-06, + "loss": 0.0902, + "step": 26779 + }, + { + "epoch": 2.18, + "learning_rate": 5.451977401129944e-06, + "loss": 0.5076, + "step": 26780 + }, + { + "epoch": 2.18, + "learning_rate": 5.4514341590612785e-06, + "loss": 0.2014, + "step": 26781 + }, + { + "epoch": 2.18, + "learning_rate": 5.450890916992613e-06, + "loss": 0.1131, + "step": 26782 + }, + { + "epoch": 2.18, + "learning_rate": 5.450347674923947e-06, + "loss": 0.2301, + "step": 26783 + }, + { + "epoch": 2.18, + "learning_rate": 5.449804432855281e-06, + "loss": 0.2385, + "step": 26784 + }, + { + "epoch": 2.18, + "learning_rate": 5.449261190786615e-06, + "loss": 0.1496, + "step": 26785 + }, + { + "epoch": 2.18, + "learning_rate": 5.448717948717949e-06, + "loss": 0.2038, + "step": 26786 + }, + { + "epoch": 2.18, + "learning_rate": 5.448174706649283e-06, + "loss": 0.1036, + "step": 26787 + }, + { + "epoch": 2.18, + "learning_rate": 5.447631464580617e-06, + "loss": 0.1747, + "step": 26788 + }, + { + "epoch": 2.18, + "learning_rate": 5.4470882225119515e-06, + "loss": 0.333, + "step": 26789 + }, + { + "epoch": 2.18, + "learning_rate": 5.446544980443286e-06, + "loss": 0.2353, + "step": 26790 + }, + { + "epoch": 2.18, + "learning_rate": 5.44600173837462e-06, + "loss": 0.1119, + "step": 26791 + }, + { + "epoch": 2.18, + "learning_rate": 5.445458496305954e-06, + "loss": 0.1579, + "step": 26792 + }, + { + "epoch": 2.18, + "learning_rate": 5.4449152542372885e-06, + "loss": 0.1951, + "step": 26793 + }, + { + "epoch": 2.18, + "learning_rate": 5.444372012168623e-06, + "loss": 0.3282, + "step": 26794 + }, + { + "epoch": 2.18, + "learning_rate": 5.443828770099957e-06, + "loss": 0.3227, + "step": 26795 + }, + { + "epoch": 2.18, + "learning_rate": 5.443285528031291e-06, + "loss": 0.065, + "step": 26796 + }, + { + "epoch": 2.18, + "learning_rate": 5.442742285962625e-06, + "loss": 0.1394, + "step": 26797 + }, + { + "epoch": 2.18, + "learning_rate": 5.44219904389396e-06, + "loss": 0.2845, + "step": 26798 + }, + { + "epoch": 2.18, + "learning_rate": 5.441655801825294e-06, + "loss": 0.3951, + "step": 26799 + }, + { + "epoch": 2.18, + "learning_rate": 5.441112559756628e-06, + "loss": 0.1547, + "step": 26800 + }, + { + "epoch": 2.18, + "learning_rate": 5.440569317687962e-06, + "loss": 0.157, + "step": 26801 + }, + { + "epoch": 2.18, + "learning_rate": 5.4400260756192965e-06, + "loss": 0.3572, + "step": 26802 + }, + { + "epoch": 2.18, + "learning_rate": 5.439482833550631e-06, + "loss": 0.2931, + "step": 26803 + }, + { + "epoch": 2.18, + "learning_rate": 5.438939591481964e-06, + "loss": 0.2363, + "step": 26804 + }, + { + "epoch": 2.18, + "learning_rate": 5.438396349413298e-06, + "loss": 0.3381, + "step": 26805 + }, + { + "epoch": 2.18, + "learning_rate": 5.437853107344633e-06, + "loss": 0.4123, + "step": 26806 + }, + { + "epoch": 2.18, + "learning_rate": 5.437309865275967e-06, + "loss": 0.1054, + "step": 26807 + }, + { + "epoch": 2.18, + "learning_rate": 5.436766623207301e-06, + "loss": 0.2591, + "step": 26808 + }, + { + "epoch": 2.18, + "learning_rate": 5.436223381138635e-06, + "loss": 0.3246, + "step": 26809 + }, + { + "epoch": 2.18, + "learning_rate": 5.4356801390699695e-06, + "loss": 0.1968, + "step": 26810 + }, + { + "epoch": 2.18, + "learning_rate": 5.435136897001304e-06, + "loss": 0.094, + "step": 26811 + }, + { + "epoch": 2.18, + "learning_rate": 5.434593654932638e-06, + "loss": 0.2206, + "step": 26812 + }, + { + "epoch": 2.18, + "learning_rate": 5.434050412863972e-06, + "loss": 0.3028, + "step": 26813 + }, + { + "epoch": 2.18, + "learning_rate": 5.4335071707953065e-06, + "loss": 0.1899, + "step": 26814 + }, + { + "epoch": 2.19, + "learning_rate": 5.4329639287266415e-06, + "loss": 0.2108, + "step": 26815 + }, + { + "epoch": 2.19, + "learning_rate": 5.432420686657976e-06, + "loss": 0.1509, + "step": 26816 + }, + { + "epoch": 2.19, + "learning_rate": 5.43187744458931e-06, + "loss": 0.4545, + "step": 26817 + }, + { + "epoch": 2.19, + "learning_rate": 5.431334202520644e-06, + "loss": 0.3404, + "step": 26818 + }, + { + "epoch": 2.19, + "learning_rate": 5.4307909604519785e-06, + "loss": 0.2034, + "step": 26819 + }, + { + "epoch": 2.19, + "learning_rate": 5.430247718383313e-06, + "loss": 0.1669, + "step": 26820 + }, + { + "epoch": 2.19, + "learning_rate": 5.429704476314647e-06, + "loss": 0.3871, + "step": 26821 + }, + { + "epoch": 2.19, + "learning_rate": 5.429161234245981e-06, + "loss": 0.3056, + "step": 26822 + }, + { + "epoch": 2.19, + "learning_rate": 5.4286179921773145e-06, + "loss": 0.1878, + "step": 26823 + }, + { + "epoch": 2.19, + "learning_rate": 5.428074750108649e-06, + "loss": 0.08, + "step": 26824 + }, + { + "epoch": 2.19, + "learning_rate": 5.427531508039983e-06, + "loss": 0.1881, + "step": 26825 + }, + { + "epoch": 2.19, + "learning_rate": 5.426988265971317e-06, + "loss": 0.215, + "step": 26826 + }, + { + "epoch": 2.19, + "learning_rate": 5.4264450239026515e-06, + "loss": 0.1613, + "step": 26827 + }, + { + "epoch": 2.19, + "learning_rate": 5.425901781833986e-06, + "loss": 0.2044, + "step": 26828 + }, + { + "epoch": 2.19, + "learning_rate": 5.42535853976532e-06, + "loss": 0.3601, + "step": 26829 + }, + { + "epoch": 2.19, + "learning_rate": 5.424815297696654e-06, + "loss": 0.1451, + "step": 26830 + }, + { + "epoch": 2.19, + "learning_rate": 5.424272055627988e-06, + "loss": 0.2801, + "step": 26831 + }, + { + "epoch": 2.19, + "learning_rate": 5.423728813559323e-06, + "loss": 0.1483, + "step": 26832 + }, + { + "epoch": 2.19, + "learning_rate": 5.423185571490657e-06, + "loss": 0.4409, + "step": 26833 + }, + { + "epoch": 2.19, + "learning_rate": 5.422642329421991e-06, + "loss": 0.0325, + "step": 26834 + }, + { + "epoch": 2.19, + "learning_rate": 5.422099087353325e-06, + "loss": 0.2366, + "step": 26835 + }, + { + "epoch": 2.19, + "learning_rate": 5.4215558452846595e-06, + "loss": 0.2715, + "step": 26836 + }, + { + "epoch": 2.19, + "learning_rate": 5.421012603215994e-06, + "loss": 0.1257, + "step": 26837 + }, + { + "epoch": 2.19, + "learning_rate": 5.420469361147328e-06, + "loss": 0.3677, + "step": 26838 + }, + { + "epoch": 2.19, + "learning_rate": 5.419926119078662e-06, + "loss": 0.1653, + "step": 26839 + }, + { + "epoch": 2.19, + "learning_rate": 5.4193828770099965e-06, + "loss": 0.1389, + "step": 26840 + }, + { + "epoch": 2.19, + "learning_rate": 5.418839634941331e-06, + "loss": 0.3905, + "step": 26841 + }, + { + "epoch": 2.19, + "learning_rate": 5.418296392872664e-06, + "loss": 0.1761, + "step": 26842 + }, + { + "epoch": 2.19, + "learning_rate": 5.417753150803998e-06, + "loss": 0.2652, + "step": 26843 + }, + { + "epoch": 2.19, + "learning_rate": 5.4172099087353325e-06, + "loss": 0.2156, + "step": 26844 + }, + { + "epoch": 2.19, + "learning_rate": 5.416666666666667e-06, + "loss": 0.1355, + "step": 26845 + }, + { + "epoch": 2.19, + "learning_rate": 5.416123424598001e-06, + "loss": 0.2697, + "step": 26846 + }, + { + "epoch": 2.19, + "learning_rate": 5.415580182529335e-06, + "loss": 0.3813, + "step": 26847 + }, + { + "epoch": 2.19, + "learning_rate": 5.4150369404606694e-06, + "loss": 0.156, + "step": 26848 + }, + { + "epoch": 2.19, + "learning_rate": 5.414493698392004e-06, + "loss": 0.4138, + "step": 26849 + }, + { + "epoch": 2.19, + "learning_rate": 5.413950456323338e-06, + "loss": 0.1337, + "step": 26850 + }, + { + "epoch": 2.19, + "learning_rate": 5.413407214254672e-06, + "loss": 0.3228, + "step": 26851 + }, + { + "epoch": 2.19, + "learning_rate": 5.412863972186006e-06, + "loss": 0.4054, + "step": 26852 + }, + { + "epoch": 2.19, + "learning_rate": 5.412320730117341e-06, + "loss": 0.2303, + "step": 26853 + }, + { + "epoch": 2.19, + "learning_rate": 5.411777488048675e-06, + "loss": 0.1452, + "step": 26854 + }, + { + "epoch": 2.19, + "learning_rate": 5.411234245980009e-06, + "loss": 0.3676, + "step": 26855 + }, + { + "epoch": 2.19, + "learning_rate": 5.410691003911343e-06, + "loss": 0.1215, + "step": 26856 + }, + { + "epoch": 2.19, + "learning_rate": 5.4101477618426775e-06, + "loss": 0.201, + "step": 26857 + }, + { + "epoch": 2.19, + "learning_rate": 5.409604519774012e-06, + "loss": 0.1389, + "step": 26858 + }, + { + "epoch": 2.19, + "learning_rate": 5.409061277705346e-06, + "loss": 0.2818, + "step": 26859 + }, + { + "epoch": 2.19, + "learning_rate": 5.408518035636681e-06, + "loss": 0.0563, + "step": 26860 + }, + { + "epoch": 2.19, + "learning_rate": 5.407974793568014e-06, + "loss": 0.1676, + "step": 26861 + }, + { + "epoch": 2.19, + "learning_rate": 5.407431551499348e-06, + "loss": 0.2214, + "step": 26862 + }, + { + "epoch": 2.19, + "learning_rate": 5.406888309430682e-06, + "loss": 0.3014, + "step": 26863 + }, + { + "epoch": 2.19, + "learning_rate": 5.406345067362016e-06, + "loss": 0.2958, + "step": 26864 + }, + { + "epoch": 2.19, + "learning_rate": 5.4058018252933505e-06, + "loss": 0.1995, + "step": 26865 + }, + { + "epoch": 2.19, + "learning_rate": 5.405258583224685e-06, + "loss": 0.3026, + "step": 26866 + }, + { + "epoch": 2.19, + "learning_rate": 5.404715341156019e-06, + "loss": 0.1453, + "step": 26867 + }, + { + "epoch": 2.19, + "learning_rate": 5.404172099087353e-06, + "loss": 0.3211, + "step": 26868 + }, + { + "epoch": 2.19, + "learning_rate": 5.403628857018688e-06, + "loss": 0.1652, + "step": 26869 + }, + { + "epoch": 2.19, + "learning_rate": 5.4030856149500225e-06, + "loss": 0.3498, + "step": 26870 + }, + { + "epoch": 2.19, + "learning_rate": 5.402542372881357e-06, + "loss": 0.0687, + "step": 26871 + }, + { + "epoch": 2.19, + "learning_rate": 5.401999130812691e-06, + "loss": 0.1459, + "step": 26872 + }, + { + "epoch": 2.19, + "learning_rate": 5.401455888744025e-06, + "loss": 0.2652, + "step": 26873 + }, + { + "epoch": 2.19, + "learning_rate": 5.4009126466753594e-06, + "loss": 0.2562, + "step": 26874 + }, + { + "epoch": 2.19, + "learning_rate": 5.400369404606694e-06, + "loss": 0.2942, + "step": 26875 + }, + { + "epoch": 2.19, + "learning_rate": 5.399826162538028e-06, + "loss": 0.1803, + "step": 26876 + }, + { + "epoch": 2.19, + "learning_rate": 5.399282920469362e-06, + "loss": 0.1555, + "step": 26877 + }, + { + "epoch": 2.19, + "learning_rate": 5.398739678400696e-06, + "loss": 0.095, + "step": 26878 + }, + { + "epoch": 2.19, + "learning_rate": 5.398196436332031e-06, + "loss": 0.2927, + "step": 26879 + }, + { + "epoch": 2.19, + "learning_rate": 5.397653194263364e-06, + "loss": 0.1526, + "step": 26880 + }, + { + "epoch": 2.19, + "learning_rate": 5.397109952194698e-06, + "loss": 0.1387, + "step": 26881 + }, + { + "epoch": 2.19, + "learning_rate": 5.3965667101260324e-06, + "loss": 0.0876, + "step": 26882 + }, + { + "epoch": 2.19, + "learning_rate": 5.396023468057367e-06, + "loss": 0.1212, + "step": 26883 + }, + { + "epoch": 2.19, + "learning_rate": 5.395480225988701e-06, + "loss": 0.3298, + "step": 26884 + }, + { + "epoch": 2.19, + "learning_rate": 5.394936983920035e-06, + "loss": 0.2691, + "step": 26885 + }, + { + "epoch": 2.19, + "learning_rate": 5.394393741851369e-06, + "loss": 0.4451, + "step": 26886 + }, + { + "epoch": 2.19, + "learning_rate": 5.393850499782704e-06, + "loss": 0.0601, + "step": 26887 + }, + { + "epoch": 2.19, + "learning_rate": 5.393307257714038e-06, + "loss": 0.2104, + "step": 26888 + }, + { + "epoch": 2.19, + "learning_rate": 5.392764015645372e-06, + "loss": 0.2065, + "step": 26889 + }, + { + "epoch": 2.19, + "learning_rate": 5.392220773576706e-06, + "loss": 0.1417, + "step": 26890 + }, + { + "epoch": 2.19, + "learning_rate": 5.3916775315080405e-06, + "loss": 0.2257, + "step": 26891 + }, + { + "epoch": 2.19, + "learning_rate": 5.391134289439375e-06, + "loss": 0.0894, + "step": 26892 + }, + { + "epoch": 2.19, + "learning_rate": 5.390591047370709e-06, + "loss": 0.4557, + "step": 26893 + }, + { + "epoch": 2.19, + "learning_rate": 5.390047805302043e-06, + "loss": 0.1647, + "step": 26894 + }, + { + "epoch": 2.19, + "learning_rate": 5.3895045632333774e-06, + "loss": 0.1144, + "step": 26895 + }, + { + "epoch": 2.19, + "learning_rate": 5.388961321164712e-06, + "loss": 0.1001, + "step": 26896 + }, + { + "epoch": 2.19, + "learning_rate": 5.388418079096046e-06, + "loss": 0.2835, + "step": 26897 + }, + { + "epoch": 2.19, + "learning_rate": 5.38787483702738e-06, + "loss": 0.205, + "step": 26898 + }, + { + "epoch": 2.19, + "learning_rate": 5.3873315949587135e-06, + "loss": 0.2981, + "step": 26899 + }, + { + "epoch": 2.19, + "learning_rate": 5.386788352890048e-06, + "loss": 0.0821, + "step": 26900 + }, + { + "epoch": 2.19, + "learning_rate": 5.386245110821382e-06, + "loss": 0.1075, + "step": 26901 + }, + { + "epoch": 2.19, + "learning_rate": 5.385701868752716e-06, + "loss": 0.2345, + "step": 26902 + }, + { + "epoch": 2.19, + "learning_rate": 5.3851586266840504e-06, + "loss": 0.4506, + "step": 26903 + }, + { + "epoch": 2.19, + "learning_rate": 5.384615384615385e-06, + "loss": 0.2823, + "step": 26904 + }, + { + "epoch": 2.19, + "learning_rate": 5.384072142546719e-06, + "loss": 0.118, + "step": 26905 + }, + { + "epoch": 2.19, + "learning_rate": 5.383528900478053e-06, + "loss": 0.3826, + "step": 26906 + }, + { + "epoch": 2.19, + "learning_rate": 5.382985658409387e-06, + "loss": 0.5785, + "step": 26907 + }, + { + "epoch": 2.19, + "learning_rate": 5.382442416340722e-06, + "loss": 0.2298, + "step": 26908 + }, + { + "epoch": 2.19, + "learning_rate": 5.381899174272056e-06, + "loss": 0.0968, + "step": 26909 + }, + { + "epoch": 2.19, + "learning_rate": 5.38135593220339e-06, + "loss": 0.2037, + "step": 26910 + }, + { + "epoch": 2.19, + "learning_rate": 5.380812690134724e-06, + "loss": 0.3894, + "step": 26911 + }, + { + "epoch": 2.19, + "learning_rate": 5.3802694480660585e-06, + "loss": 0.2949, + "step": 26912 + }, + { + "epoch": 2.19, + "learning_rate": 5.379726205997393e-06, + "loss": 0.1118, + "step": 26913 + }, + { + "epoch": 2.19, + "learning_rate": 5.379182963928728e-06, + "loss": 0.1485, + "step": 26914 + }, + { + "epoch": 2.19, + "learning_rate": 5.378639721860062e-06, + "loss": 0.4805, + "step": 26915 + }, + { + "epoch": 2.19, + "learning_rate": 5.378096479791396e-06, + "loss": 0.2746, + "step": 26916 + }, + { + "epoch": 2.19, + "learning_rate": 5.3775532377227305e-06, + "loss": 0.1959, + "step": 26917 + }, + { + "epoch": 2.19, + "learning_rate": 5.377009995654063e-06, + "loss": 0.0833, + "step": 26918 + }, + { + "epoch": 2.19, + "learning_rate": 5.376466753585397e-06, + "loss": 0.3033, + "step": 26919 + }, + { + "epoch": 2.19, + "learning_rate": 5.3759235115167315e-06, + "loss": 0.2563, + "step": 26920 + }, + { + "epoch": 2.19, + "learning_rate": 5.375380269448066e-06, + "loss": 0.3267, + "step": 26921 + }, + { + "epoch": 2.19, + "learning_rate": 5.3748370273794e-06, + "loss": 0.1869, + "step": 26922 + }, + { + "epoch": 2.19, + "learning_rate": 5.374293785310735e-06, + "loss": 0.329, + "step": 26923 + }, + { + "epoch": 2.19, + "learning_rate": 5.373750543242069e-06, + "loss": 0.3633, + "step": 26924 + }, + { + "epoch": 2.19, + "learning_rate": 5.3732073011734035e-06, + "loss": 0.2499, + "step": 26925 + }, + { + "epoch": 2.19, + "learning_rate": 5.372664059104738e-06, + "loss": 0.0299, + "step": 26926 + }, + { + "epoch": 2.19, + "learning_rate": 5.372120817036072e-06, + "loss": 0.095, + "step": 26927 + }, + { + "epoch": 2.19, + "learning_rate": 5.371577574967406e-06, + "loss": 0.223, + "step": 26928 + }, + { + "epoch": 2.19, + "learning_rate": 5.3710343328987404e-06, + "loss": 0.1701, + "step": 26929 + }, + { + "epoch": 2.19, + "learning_rate": 5.370491090830075e-06, + "loss": 0.1172, + "step": 26930 + }, + { + "epoch": 2.19, + "learning_rate": 5.369947848761409e-06, + "loss": 0.2115, + "step": 26931 + }, + { + "epoch": 2.19, + "learning_rate": 5.369404606692743e-06, + "loss": 0.1602, + "step": 26932 + }, + { + "epoch": 2.19, + "learning_rate": 5.368861364624077e-06, + "loss": 0.1433, + "step": 26933 + }, + { + "epoch": 2.19, + "learning_rate": 5.368318122555412e-06, + "loss": 0.2066, + "step": 26934 + }, + { + "epoch": 2.19, + "learning_rate": 5.367774880486746e-06, + "loss": 0.1999, + "step": 26935 + }, + { + "epoch": 2.19, + "learning_rate": 5.36723163841808e-06, + "loss": 0.2404, + "step": 26936 + }, + { + "epoch": 2.19, + "learning_rate": 5.3666883963494134e-06, + "loss": 0.3673, + "step": 26937 + }, + { + "epoch": 2.2, + "learning_rate": 5.366145154280748e-06, + "loss": 0.2408, + "step": 26938 + }, + { + "epoch": 2.2, + "learning_rate": 5.365601912212082e-06, + "loss": 0.2304, + "step": 26939 + }, + { + "epoch": 2.2, + "learning_rate": 5.365058670143416e-06, + "loss": 0.0747, + "step": 26940 + }, + { + "epoch": 2.2, + "learning_rate": 5.36451542807475e-06, + "loss": 0.336, + "step": 26941 + }, + { + "epoch": 2.2, + "learning_rate": 5.363972186006085e-06, + "loss": 0.2822, + "step": 26942 + }, + { + "epoch": 2.2, + "learning_rate": 5.363428943937419e-06, + "loss": 0.2848, + "step": 26943 + }, + { + "epoch": 2.2, + "learning_rate": 5.362885701868753e-06, + "loss": 0.1857, + "step": 26944 + }, + { + "epoch": 2.2, + "learning_rate": 5.362342459800087e-06, + "loss": 0.3812, + "step": 26945 + }, + { + "epoch": 2.2, + "learning_rate": 5.3617992177314215e-06, + "loss": 0.1152, + "step": 26946 + }, + { + "epoch": 2.2, + "learning_rate": 5.361255975662756e-06, + "loss": 0.1368, + "step": 26947 + }, + { + "epoch": 2.2, + "learning_rate": 5.36071273359409e-06, + "loss": 0.3895, + "step": 26948 + }, + { + "epoch": 2.2, + "learning_rate": 5.360169491525424e-06, + "loss": 0.1428, + "step": 26949 + }, + { + "epoch": 2.2, + "learning_rate": 5.359626249456758e-06, + "loss": 0.4761, + "step": 26950 + }, + { + "epoch": 2.2, + "learning_rate": 5.359083007388093e-06, + "loss": 0.2131, + "step": 26951 + }, + { + "epoch": 2.2, + "learning_rate": 5.358539765319427e-06, + "loss": 0.2393, + "step": 26952 + }, + { + "epoch": 2.2, + "learning_rate": 5.357996523250761e-06, + "loss": 0.2788, + "step": 26953 + }, + { + "epoch": 2.2, + "learning_rate": 5.357453281182095e-06, + "loss": 0.2463, + "step": 26954 + }, + { + "epoch": 2.2, + "learning_rate": 5.3569100391134296e-06, + "loss": 0.122, + "step": 26955 + }, + { + "epoch": 2.2, + "learning_rate": 5.356366797044763e-06, + "loss": 0.3716, + "step": 26956 + }, + { + "epoch": 2.2, + "learning_rate": 5.355823554976097e-06, + "loss": 0.3922, + "step": 26957 + }, + { + "epoch": 2.2, + "learning_rate": 5.355280312907431e-06, + "loss": 0.4869, + "step": 26958 + }, + { + "epoch": 2.2, + "learning_rate": 5.354737070838766e-06, + "loss": 0.0857, + "step": 26959 + }, + { + "epoch": 2.2, + "learning_rate": 5.3541938287701e-06, + "loss": 0.2425, + "step": 26960 + }, + { + "epoch": 2.2, + "learning_rate": 5.353650586701434e-06, + "loss": 0.0507, + "step": 26961 + }, + { + "epoch": 2.2, + "learning_rate": 5.353107344632768e-06, + "loss": 0.1419, + "step": 26962 + }, + { + "epoch": 2.2, + "learning_rate": 5.3525641025641026e-06, + "loss": 0.1777, + "step": 26963 + }, + { + "epoch": 2.2, + "learning_rate": 5.352020860495437e-06, + "loss": 0.2197, + "step": 26964 + }, + { + "epoch": 2.2, + "learning_rate": 5.351477618426771e-06, + "loss": 0.2452, + "step": 26965 + }, + { + "epoch": 2.2, + "learning_rate": 5.350934376358105e-06, + "loss": 0.1965, + "step": 26966 + }, + { + "epoch": 2.2, + "learning_rate": 5.3503911342894395e-06, + "loss": 0.1276, + "step": 26967 + }, + { + "epoch": 2.2, + "learning_rate": 5.3498478922207746e-06, + "loss": 0.2035, + "step": 26968 + }, + { + "epoch": 2.2, + "learning_rate": 5.349304650152109e-06, + "loss": 0.1965, + "step": 26969 + }, + { + "epoch": 2.2, + "learning_rate": 5.348761408083443e-06, + "loss": 0.1665, + "step": 26970 + }, + { + "epoch": 2.2, + "learning_rate": 5.348218166014777e-06, + "loss": 0.2229, + "step": 26971 + }, + { + "epoch": 2.2, + "learning_rate": 5.3476749239461115e-06, + "loss": 0.0586, + "step": 26972 + }, + { + "epoch": 2.2, + "learning_rate": 5.347131681877446e-06, + "loss": 0.1543, + "step": 26973 + }, + { + "epoch": 2.2, + "learning_rate": 5.34658843980878e-06, + "loss": 0.134, + "step": 26974 + }, + { + "epoch": 2.2, + "learning_rate": 5.3460451977401125e-06, + "loss": 0.1611, + "step": 26975 + }, + { + "epoch": 2.2, + "learning_rate": 5.345501955671447e-06, + "loss": 0.4536, + "step": 26976 + }, + { + "epoch": 2.2, + "learning_rate": 5.344958713602782e-06, + "loss": 0.1526, + "step": 26977 + }, + { + "epoch": 2.2, + "learning_rate": 5.344415471534116e-06, + "loss": 0.3061, + "step": 26978 + }, + { + "epoch": 2.2, + "learning_rate": 5.34387222946545e-06, + "loss": 0.1243, + "step": 26979 + }, + { + "epoch": 2.2, + "learning_rate": 5.3433289873967845e-06, + "loss": 0.1955, + "step": 26980 + }, + { + "epoch": 2.2, + "learning_rate": 5.342785745328119e-06, + "loss": 0.3423, + "step": 26981 + }, + { + "epoch": 2.2, + "learning_rate": 5.342242503259453e-06, + "loss": 0.1811, + "step": 26982 + }, + { + "epoch": 2.2, + "learning_rate": 5.341699261190787e-06, + "loss": 0.4082, + "step": 26983 + }, + { + "epoch": 2.2, + "learning_rate": 5.341156019122121e-06, + "loss": 0.3657, + "step": 26984 + }, + { + "epoch": 2.2, + "learning_rate": 5.340612777053456e-06, + "loss": 0.2509, + "step": 26985 + }, + { + "epoch": 2.2, + "learning_rate": 5.34006953498479e-06, + "loss": 0.1427, + "step": 26986 + }, + { + "epoch": 2.2, + "learning_rate": 5.339526292916124e-06, + "loss": 0.1625, + "step": 26987 + }, + { + "epoch": 2.2, + "learning_rate": 5.338983050847458e-06, + "loss": 0.264, + "step": 26988 + }, + { + "epoch": 2.2, + "learning_rate": 5.3384398087787926e-06, + "loss": 0.0605, + "step": 26989 + }, + { + "epoch": 2.2, + "learning_rate": 5.337896566710127e-06, + "loss": 0.3991, + "step": 26990 + }, + { + "epoch": 2.2, + "learning_rate": 5.337353324641461e-06, + "loss": 0.3565, + "step": 26991 + }, + { + "epoch": 2.2, + "learning_rate": 5.336810082572795e-06, + "loss": 0.1999, + "step": 26992 + }, + { + "epoch": 2.2, + "learning_rate": 5.3362668405041295e-06, + "loss": 0.0603, + "step": 26993 + }, + { + "epoch": 2.2, + "learning_rate": 5.335723598435463e-06, + "loss": 0.143, + "step": 26994 + }, + { + "epoch": 2.2, + "learning_rate": 5.335180356366797e-06, + "loss": 0.2491, + "step": 26995 + }, + { + "epoch": 2.2, + "learning_rate": 5.334637114298131e-06, + "loss": 0.144, + "step": 26996 + }, + { + "epoch": 2.2, + "learning_rate": 5.3340938722294656e-06, + "loss": 0.2609, + "step": 26997 + }, + { + "epoch": 2.2, + "learning_rate": 5.3335506301608e-06, + "loss": 0.3849, + "step": 26998 + }, + { + "epoch": 2.2, + "learning_rate": 5.333007388092134e-06, + "loss": 0.0939, + "step": 26999 + }, + { + "epoch": 2.2, + "learning_rate": 5.332464146023468e-06, + "loss": 0.4806, + "step": 27000 + }, + { + "epoch": 2.2, + "eval_accuracy": 0.839429444727458, + "eval_loss": 0.5039880871772766, + "eval_runtime": 22.3071, + "eval_samples_per_second": 439.995, + "eval_steps_per_second": 3.452, + "step": 27000 + }, + { + "epoch": 2.2, + "learning_rate": 5.3319209039548025e-06, + "loss": 0.1324, + "step": 27001 + }, + { + "epoch": 2.2, + "learning_rate": 5.331377661886137e-06, + "loss": 0.2384, + "step": 27002 + }, + { + "epoch": 2.2, + "learning_rate": 5.330834419817471e-06, + "loss": 0.3352, + "step": 27003 + }, + { + "epoch": 2.2, + "learning_rate": 5.330291177748805e-06, + "loss": 0.1508, + "step": 27004 + }, + { + "epoch": 2.2, + "learning_rate": 5.329747935680139e-06, + "loss": 0.36, + "step": 27005 + }, + { + "epoch": 2.2, + "learning_rate": 5.329204693611474e-06, + "loss": 0.3441, + "step": 27006 + }, + { + "epoch": 2.2, + "learning_rate": 5.328661451542808e-06, + "loss": 0.3196, + "step": 27007 + }, + { + "epoch": 2.2, + "learning_rate": 5.328118209474142e-06, + "loss": 0.2685, + "step": 27008 + }, + { + "epoch": 2.2, + "learning_rate": 5.327574967405476e-06, + "loss": 0.5359, + "step": 27009 + }, + { + "epoch": 2.2, + "learning_rate": 5.3270317253368106e-06, + "loss": 0.2723, + "step": 27010 + }, + { + "epoch": 2.2, + "learning_rate": 5.326488483268145e-06, + "loss": 0.3217, + "step": 27011 + }, + { + "epoch": 2.2, + "learning_rate": 5.325945241199479e-06, + "loss": 0.3025, + "step": 27012 + }, + { + "epoch": 2.2, + "learning_rate": 5.325401999130812e-06, + "loss": 0.1095, + "step": 27013 + }, + { + "epoch": 2.2, + "learning_rate": 5.324858757062147e-06, + "loss": 0.2471, + "step": 27014 + }, + { + "epoch": 2.2, + "learning_rate": 5.324315514993481e-06, + "loss": 0.1273, + "step": 27015 + }, + { + "epoch": 2.2, + "learning_rate": 5.323772272924815e-06, + "loss": 0.5084, + "step": 27016 + }, + { + "epoch": 2.2, + "learning_rate": 5.323229030856149e-06, + "loss": 0.1225, + "step": 27017 + }, + { + "epoch": 2.2, + "learning_rate": 5.3226857887874836e-06, + "loss": 0.1332, + "step": 27018 + }, + { + "epoch": 2.2, + "learning_rate": 5.322142546718818e-06, + "loss": 0.2081, + "step": 27019 + }, + { + "epoch": 2.2, + "learning_rate": 5.321599304650152e-06, + "loss": 0.1815, + "step": 27020 + }, + { + "epoch": 2.2, + "learning_rate": 5.321056062581486e-06, + "loss": 0.1641, + "step": 27021 + }, + { + "epoch": 2.2, + "learning_rate": 5.320512820512821e-06, + "loss": 0.152, + "step": 27022 + }, + { + "epoch": 2.2, + "learning_rate": 5.3199695784441556e-06, + "loss": 0.1351, + "step": 27023 + }, + { + "epoch": 2.2, + "learning_rate": 5.31942633637549e-06, + "loss": 0.2345, + "step": 27024 + }, + { + "epoch": 2.2, + "learning_rate": 5.318883094306824e-06, + "loss": 0.0519, + "step": 27025 + }, + { + "epoch": 2.2, + "learning_rate": 5.318339852238158e-06, + "loss": 0.1374, + "step": 27026 + }, + { + "epoch": 2.2, + "learning_rate": 5.3177966101694925e-06, + "loss": 0.4284, + "step": 27027 + }, + { + "epoch": 2.2, + "learning_rate": 5.317253368100827e-06, + "loss": 0.1314, + "step": 27028 + }, + { + "epoch": 2.2, + "learning_rate": 5.316710126032161e-06, + "loss": 0.1722, + "step": 27029 + }, + { + "epoch": 2.2, + "learning_rate": 5.316166883963495e-06, + "loss": 0.281, + "step": 27030 + }, + { + "epoch": 2.2, + "learning_rate": 5.315623641894829e-06, + "loss": 0.1128, + "step": 27031 + }, + { + "epoch": 2.2, + "learning_rate": 5.315080399826163e-06, + "loss": 0.2558, + "step": 27032 + }, + { + "epoch": 2.2, + "learning_rate": 5.314537157757497e-06, + "loss": 0.2442, + "step": 27033 + }, + { + "epoch": 2.2, + "learning_rate": 5.313993915688831e-06, + "loss": 0.2089, + "step": 27034 + }, + { + "epoch": 2.2, + "learning_rate": 5.3134506736201655e-06, + "loss": 0.182, + "step": 27035 + }, + { + "epoch": 2.2, + "learning_rate": 5.3129074315515e-06, + "loss": 0.1854, + "step": 27036 + }, + { + "epoch": 2.2, + "learning_rate": 5.312364189482834e-06, + "loss": 0.1343, + "step": 27037 + }, + { + "epoch": 2.2, + "learning_rate": 5.311820947414168e-06, + "loss": 0.0355, + "step": 27038 + }, + { + "epoch": 2.2, + "learning_rate": 5.311277705345502e-06, + "loss": 0.1264, + "step": 27039 + }, + { + "epoch": 2.2, + "learning_rate": 5.310734463276837e-06, + "loss": 0.3545, + "step": 27040 + }, + { + "epoch": 2.2, + "learning_rate": 5.310191221208171e-06, + "loss": 0.313, + "step": 27041 + }, + { + "epoch": 2.2, + "learning_rate": 5.309647979139505e-06, + "loss": 0.2259, + "step": 27042 + }, + { + "epoch": 2.2, + "learning_rate": 5.309104737070839e-06, + "loss": 0.5294, + "step": 27043 + }, + { + "epoch": 2.2, + "learning_rate": 5.3085614950021736e-06, + "loss": 0.1164, + "step": 27044 + }, + { + "epoch": 2.2, + "learning_rate": 5.308018252933508e-06, + "loss": 0.1597, + "step": 27045 + }, + { + "epoch": 2.2, + "learning_rate": 5.307475010864842e-06, + "loss": 0.1381, + "step": 27046 + }, + { + "epoch": 2.2, + "learning_rate": 5.306931768796176e-06, + "loss": 0.2461, + "step": 27047 + }, + { + "epoch": 2.2, + "learning_rate": 5.3063885267275105e-06, + "loss": 0.2725, + "step": 27048 + }, + { + "epoch": 2.2, + "learning_rate": 5.305845284658845e-06, + "loss": 0.2567, + "step": 27049 + }, + { + "epoch": 2.2, + "learning_rate": 5.305302042590179e-06, + "loss": 0.4562, + "step": 27050 + }, + { + "epoch": 2.2, + "learning_rate": 5.304758800521513e-06, + "loss": 0.2249, + "step": 27051 + }, + { + "epoch": 2.2, + "learning_rate": 5.3042155584528466e-06, + "loss": 0.1676, + "step": 27052 + }, + { + "epoch": 2.2, + "learning_rate": 5.303672316384181e-06, + "loss": 0.1696, + "step": 27053 + }, + { + "epoch": 2.2, + "learning_rate": 5.303129074315515e-06, + "loss": 0.4077, + "step": 27054 + }, + { + "epoch": 2.2, + "learning_rate": 5.302585832246849e-06, + "loss": 0.5936, + "step": 27055 + }, + { + "epoch": 2.2, + "learning_rate": 5.3020425901781835e-06, + "loss": 0.244, + "step": 27056 + }, + { + "epoch": 2.2, + "learning_rate": 5.301499348109518e-06, + "loss": 0.146, + "step": 27057 + }, + { + "epoch": 2.2, + "learning_rate": 5.300956106040852e-06, + "loss": 0.0591, + "step": 27058 + }, + { + "epoch": 2.2, + "learning_rate": 5.300412863972186e-06, + "loss": 0.3081, + "step": 27059 + }, + { + "epoch": 2.21, + "learning_rate": 5.29986962190352e-06, + "loss": 0.2417, + "step": 27060 + }, + { + "epoch": 2.21, + "learning_rate": 5.299326379834855e-06, + "loss": 0.5094, + "step": 27061 + }, + { + "epoch": 2.21, + "learning_rate": 5.298783137766189e-06, + "loss": 0.145, + "step": 27062 + }, + { + "epoch": 2.21, + "learning_rate": 5.298239895697523e-06, + "loss": 0.3297, + "step": 27063 + }, + { + "epoch": 2.21, + "learning_rate": 5.297696653628857e-06, + "loss": 0.2968, + "step": 27064 + }, + { + "epoch": 2.21, + "learning_rate": 5.2971534115601915e-06, + "loss": 0.3954, + "step": 27065 + }, + { + "epoch": 2.21, + "learning_rate": 5.296610169491526e-06, + "loss": 0.2445, + "step": 27066 + }, + { + "epoch": 2.21, + "learning_rate": 5.296066927422861e-06, + "loss": 0.1446, + "step": 27067 + }, + { + "epoch": 2.21, + "learning_rate": 5.295523685354195e-06, + "loss": 0.0809, + "step": 27068 + }, + { + "epoch": 2.21, + "learning_rate": 5.294980443285529e-06, + "loss": 0.3152, + "step": 27069 + }, + { + "epoch": 2.21, + "learning_rate": 5.2944372012168635e-06, + "loss": 0.1558, + "step": 27070 + }, + { + "epoch": 2.21, + "learning_rate": 5.293893959148196e-06, + "loss": 0.1861, + "step": 27071 + }, + { + "epoch": 2.21, + "learning_rate": 5.29335071707953e-06, + "loss": 0.161, + "step": 27072 + }, + { + "epoch": 2.21, + "learning_rate": 5.2928074750108645e-06, + "loss": 0.2671, + "step": 27073 + }, + { + "epoch": 2.21, + "learning_rate": 5.292264232942199e-06, + "loss": 0.4917, + "step": 27074 + }, + { + "epoch": 2.21, + "learning_rate": 5.291720990873533e-06, + "loss": 0.2677, + "step": 27075 + }, + { + "epoch": 2.21, + "learning_rate": 5.291177748804868e-06, + "loss": 0.1548, + "step": 27076 + }, + { + "epoch": 2.21, + "learning_rate": 5.290634506736202e-06, + "loss": 0.2107, + "step": 27077 + }, + { + "epoch": 2.21, + "learning_rate": 5.2900912646675365e-06, + "loss": 0.4246, + "step": 27078 + }, + { + "epoch": 2.21, + "learning_rate": 5.289548022598871e-06, + "loss": 0.2553, + "step": 27079 + }, + { + "epoch": 2.21, + "learning_rate": 5.289004780530205e-06, + "loss": 0.1638, + "step": 27080 + }, + { + "epoch": 2.21, + "learning_rate": 5.288461538461539e-06, + "loss": 0.1318, + "step": 27081 + }, + { + "epoch": 2.21, + "learning_rate": 5.2879182963928735e-06, + "loss": 0.3835, + "step": 27082 + }, + { + "epoch": 2.21, + "learning_rate": 5.287375054324208e-06, + "loss": 0.1135, + "step": 27083 + }, + { + "epoch": 2.21, + "learning_rate": 5.286831812255542e-06, + "loss": 0.1389, + "step": 27084 + }, + { + "epoch": 2.21, + "learning_rate": 5.286288570186876e-06, + "loss": 0.2772, + "step": 27085 + }, + { + "epoch": 2.21, + "learning_rate": 5.28574532811821e-06, + "loss": 0.3737, + "step": 27086 + }, + { + "epoch": 2.21, + "learning_rate": 5.285202086049545e-06, + "loss": 0.3157, + "step": 27087 + }, + { + "epoch": 2.21, + "learning_rate": 5.284658843980879e-06, + "loss": 0.3148, + "step": 27088 + }, + { + "epoch": 2.21, + "learning_rate": 5.284115601912213e-06, + "loss": 0.2528, + "step": 27089 + }, + { + "epoch": 2.21, + "learning_rate": 5.2835723598435465e-06, + "loss": 0.1884, + "step": 27090 + }, + { + "epoch": 2.21, + "learning_rate": 5.283029117774881e-06, + "loss": 0.1572, + "step": 27091 + }, + { + "epoch": 2.21, + "learning_rate": 5.282485875706215e-06, + "loss": 0.1715, + "step": 27092 + }, + { + "epoch": 2.21, + "learning_rate": 5.281942633637549e-06, + "loss": 0.1024, + "step": 27093 + }, + { + "epoch": 2.21, + "learning_rate": 5.281399391568883e-06, + "loss": 0.1874, + "step": 27094 + }, + { + "epoch": 2.21, + "learning_rate": 5.280856149500218e-06, + "loss": 0.1335, + "step": 27095 + }, + { + "epoch": 2.21, + "learning_rate": 5.280312907431552e-06, + "loss": 0.2905, + "step": 27096 + }, + { + "epoch": 2.21, + "learning_rate": 5.279769665362886e-06, + "loss": 0.127, + "step": 27097 + }, + { + "epoch": 2.21, + "learning_rate": 5.27922642329422e-06, + "loss": 0.2693, + "step": 27098 + }, + { + "epoch": 2.21, + "learning_rate": 5.2786831812255545e-06, + "loss": 0.3097, + "step": 27099 + }, + { + "epoch": 2.21, + "learning_rate": 5.278139939156889e-06, + "loss": 0.2144, + "step": 27100 + }, + { + "epoch": 2.21, + "learning_rate": 5.277596697088223e-06, + "loss": 0.2405, + "step": 27101 + }, + { + "epoch": 2.21, + "learning_rate": 5.277053455019557e-06, + "loss": 0.2071, + "step": 27102 + }, + { + "epoch": 2.21, + "learning_rate": 5.2765102129508915e-06, + "loss": 0.3548, + "step": 27103 + }, + { + "epoch": 2.21, + "learning_rate": 5.275966970882226e-06, + "loss": 0.1314, + "step": 27104 + }, + { + "epoch": 2.21, + "learning_rate": 5.27542372881356e-06, + "loss": 0.2004, + "step": 27105 + }, + { + "epoch": 2.21, + "learning_rate": 5.274880486744894e-06, + "loss": 0.538, + "step": 27106 + }, + { + "epoch": 2.21, + "learning_rate": 5.274337244676228e-06, + "loss": 0.1274, + "step": 27107 + }, + { + "epoch": 2.21, + "learning_rate": 5.273794002607563e-06, + "loss": 0.0953, + "step": 27108 + }, + { + "epoch": 2.21, + "learning_rate": 5.273250760538896e-06, + "loss": 0.114, + "step": 27109 + }, + { + "epoch": 2.21, + "learning_rate": 5.27270751847023e-06, + "loss": 0.3124, + "step": 27110 + }, + { + "epoch": 2.21, + "learning_rate": 5.2721642764015645e-06, + "loss": 0.0412, + "step": 27111 + }, + { + "epoch": 2.21, + "learning_rate": 5.271621034332899e-06, + "loss": 0.2138, + "step": 27112 + }, + { + "epoch": 2.21, + "learning_rate": 5.271077792264233e-06, + "loss": 0.1889, + "step": 27113 + }, + { + "epoch": 2.21, + "learning_rate": 5.270534550195567e-06, + "loss": 0.0902, + "step": 27114 + }, + { + "epoch": 2.21, + "learning_rate": 5.269991308126901e-06, + "loss": 0.0647, + "step": 27115 + }, + { + "epoch": 2.21, + "learning_rate": 5.269448066058236e-06, + "loss": 0.2016, + "step": 27116 + }, + { + "epoch": 2.21, + "learning_rate": 5.26890482398957e-06, + "loss": 0.0663, + "step": 27117 + }, + { + "epoch": 2.21, + "learning_rate": 5.268361581920904e-06, + "loss": 0.2139, + "step": 27118 + }, + { + "epoch": 2.21, + "learning_rate": 5.267818339852238e-06, + "loss": 0.1391, + "step": 27119 + }, + { + "epoch": 2.21, + "learning_rate": 5.2672750977835725e-06, + "loss": 0.1452, + "step": 27120 + }, + { + "epoch": 2.21, + "learning_rate": 5.266731855714908e-06, + "loss": 0.2943, + "step": 27121 + }, + { + "epoch": 2.21, + "learning_rate": 5.266188613646242e-06, + "loss": 0.3083, + "step": 27122 + }, + { + "epoch": 2.21, + "learning_rate": 5.265645371577576e-06, + "loss": 0.1639, + "step": 27123 + }, + { + "epoch": 2.21, + "learning_rate": 5.26510212950891e-06, + "loss": 0.1766, + "step": 27124 + }, + { + "epoch": 2.21, + "learning_rate": 5.2645588874402445e-06, + "loss": 0.3132, + "step": 27125 + }, + { + "epoch": 2.21, + "learning_rate": 5.264015645371579e-06, + "loss": 0.3897, + "step": 27126 + }, + { + "epoch": 2.21, + "learning_rate": 5.263472403302913e-06, + "loss": 0.0794, + "step": 27127 + }, + { + "epoch": 2.21, + "learning_rate": 5.2629291612342455e-06, + "loss": 0.2265, + "step": 27128 + }, + { + "epoch": 2.21, + "learning_rate": 5.26238591916558e-06, + "loss": 0.1807, + "step": 27129 + }, + { + "epoch": 2.21, + "learning_rate": 5.261842677096915e-06, + "loss": 0.5074, + "step": 27130 + }, + { + "epoch": 2.21, + "learning_rate": 5.261299435028249e-06, + "loss": 0.1997, + "step": 27131 + }, + { + "epoch": 2.21, + "learning_rate": 5.260756192959583e-06, + "loss": 0.0506, + "step": 27132 + }, + { + "epoch": 2.21, + "learning_rate": 5.2602129508909175e-06, + "loss": 0.2068, + "step": 27133 + }, + { + "epoch": 2.21, + "learning_rate": 5.259669708822252e-06, + "loss": 0.2061, + "step": 27134 + }, + { + "epoch": 2.21, + "learning_rate": 5.259126466753586e-06, + "loss": 0.2385, + "step": 27135 + }, + { + "epoch": 2.21, + "learning_rate": 5.25858322468492e-06, + "loss": 0.2602, + "step": 27136 + }, + { + "epoch": 2.21, + "learning_rate": 5.2580399826162545e-06, + "loss": 0.1592, + "step": 27137 + }, + { + "epoch": 2.21, + "learning_rate": 5.257496740547589e-06, + "loss": 0.3966, + "step": 27138 + }, + { + "epoch": 2.21, + "learning_rate": 5.256953498478923e-06, + "loss": 0.2774, + "step": 27139 + }, + { + "epoch": 2.21, + "learning_rate": 5.256410256410257e-06, + "loss": 0.3248, + "step": 27140 + }, + { + "epoch": 2.21, + "learning_rate": 5.255867014341591e-06, + "loss": 0.0881, + "step": 27141 + }, + { + "epoch": 2.21, + "learning_rate": 5.255323772272926e-06, + "loss": 0.2861, + "step": 27142 + }, + { + "epoch": 2.21, + "learning_rate": 5.25478053020426e-06, + "loss": 0.3012, + "step": 27143 + }, + { + "epoch": 2.21, + "learning_rate": 5.254237288135594e-06, + "loss": 0.2672, + "step": 27144 + }, + { + "epoch": 2.21, + "learning_rate": 5.253694046066928e-06, + "loss": 0.385, + "step": 27145 + }, + { + "epoch": 2.21, + "learning_rate": 5.2531508039982625e-06, + "loss": 0.2702, + "step": 27146 + }, + { + "epoch": 2.21, + "learning_rate": 5.252607561929596e-06, + "loss": 0.1217, + "step": 27147 + }, + { + "epoch": 2.21, + "learning_rate": 5.25206431986093e-06, + "loss": 0.2451, + "step": 27148 + }, + { + "epoch": 2.21, + "learning_rate": 5.251521077792264e-06, + "loss": 0.2369, + "step": 27149 + }, + { + "epoch": 2.21, + "learning_rate": 5.250977835723599e-06, + "loss": 0.3106, + "step": 27150 + }, + { + "epoch": 2.21, + "learning_rate": 5.250434593654933e-06, + "loss": 0.1525, + "step": 27151 + }, + { + "epoch": 2.21, + "learning_rate": 5.249891351586267e-06, + "loss": 0.2214, + "step": 27152 + }, + { + "epoch": 2.21, + "learning_rate": 5.249348109517601e-06, + "loss": 0.1029, + "step": 27153 + }, + { + "epoch": 2.21, + "learning_rate": 5.2488048674489355e-06, + "loss": 0.1827, + "step": 27154 + }, + { + "epoch": 2.21, + "learning_rate": 5.24826162538027e-06, + "loss": 0.1042, + "step": 27155 + }, + { + "epoch": 2.21, + "learning_rate": 5.247718383311604e-06, + "loss": 0.2706, + "step": 27156 + }, + { + "epoch": 2.21, + "learning_rate": 5.247175141242938e-06, + "loss": 0.3463, + "step": 27157 + }, + { + "epoch": 2.21, + "learning_rate": 5.2466318991742724e-06, + "loss": 0.2163, + "step": 27158 + }, + { + "epoch": 2.21, + "learning_rate": 5.246088657105607e-06, + "loss": 0.1047, + "step": 27159 + }, + { + "epoch": 2.21, + "learning_rate": 5.245545415036941e-06, + "loss": 0.1115, + "step": 27160 + }, + { + "epoch": 2.21, + "learning_rate": 5.245002172968275e-06, + "loss": 0.3254, + "step": 27161 + }, + { + "epoch": 2.21, + "learning_rate": 5.244458930899609e-06, + "loss": 0.1226, + "step": 27162 + }, + { + "epoch": 2.21, + "learning_rate": 5.243915688830944e-06, + "loss": 0.3318, + "step": 27163 + }, + { + "epoch": 2.21, + "learning_rate": 5.243372446762278e-06, + "loss": 0.409, + "step": 27164 + }, + { + "epoch": 2.21, + "learning_rate": 5.242829204693612e-06, + "loss": 0.2272, + "step": 27165 + }, + { + "epoch": 2.21, + "learning_rate": 5.2422859626249454e-06, + "loss": 0.1336, + "step": 27166 + }, + { + "epoch": 2.21, + "learning_rate": 5.24174272055628e-06, + "loss": 0.1076, + "step": 27167 + }, + { + "epoch": 2.21, + "learning_rate": 5.241199478487614e-06, + "loss": 0.2599, + "step": 27168 + }, + { + "epoch": 2.21, + "learning_rate": 5.240656236418948e-06, + "loss": 0.0959, + "step": 27169 + }, + { + "epoch": 2.21, + "learning_rate": 5.240112994350282e-06, + "loss": 0.0776, + "step": 27170 + }, + { + "epoch": 2.21, + "learning_rate": 5.239569752281617e-06, + "loss": 0.2581, + "step": 27171 + }, + { + "epoch": 2.21, + "learning_rate": 5.239026510212951e-06, + "loss": 0.1798, + "step": 27172 + }, + { + "epoch": 2.21, + "learning_rate": 5.238483268144285e-06, + "loss": 0.334, + "step": 27173 + }, + { + "epoch": 2.21, + "learning_rate": 5.237940026075619e-06, + "loss": 0.2187, + "step": 27174 + }, + { + "epoch": 2.21, + "learning_rate": 5.237396784006954e-06, + "loss": 0.1357, + "step": 27175 + }, + { + "epoch": 2.21, + "learning_rate": 5.236853541938289e-06, + "loss": 0.248, + "step": 27176 + }, + { + "epoch": 2.21, + "learning_rate": 5.236310299869623e-06, + "loss": 0.1069, + "step": 27177 + }, + { + "epoch": 2.21, + "learning_rate": 5.235767057800957e-06, + "loss": 0.0757, + "step": 27178 + }, + { + "epoch": 2.21, + "learning_rate": 5.235223815732291e-06, + "loss": 0.1497, + "step": 27179 + }, + { + "epoch": 2.21, + "learning_rate": 5.2346805736636255e-06, + "loss": 0.2601, + "step": 27180 + }, + { + "epoch": 2.21, + "learning_rate": 5.23413733159496e-06, + "loss": 0.4444, + "step": 27181 + }, + { + "epoch": 2.21, + "learning_rate": 5.233594089526294e-06, + "loss": 0.3874, + "step": 27182 + }, + { + "epoch": 2.22, + "learning_rate": 5.233050847457628e-06, + "loss": 0.1656, + "step": 27183 + }, + { + "epoch": 2.22, + "learning_rate": 5.2325076053889624e-06, + "loss": 0.3636, + "step": 27184 + }, + { + "epoch": 2.22, + "learning_rate": 5.231964363320296e-06, + "loss": 0.154, + "step": 27185 + }, + { + "epoch": 2.22, + "learning_rate": 5.23142112125163e-06, + "loss": 0.2192, + "step": 27186 + }, + { + "epoch": 2.22, + "learning_rate": 5.230877879182964e-06, + "loss": 0.7764, + "step": 27187 + }, + { + "epoch": 2.22, + "learning_rate": 5.2303346371142985e-06, + "loss": 0.1898, + "step": 27188 + }, + { + "epoch": 2.22, + "learning_rate": 5.229791395045633e-06, + "loss": 0.0954, + "step": 27189 + }, + { + "epoch": 2.22, + "learning_rate": 5.229248152976967e-06, + "loss": 0.1696, + "step": 27190 + }, + { + "epoch": 2.22, + "learning_rate": 5.228704910908301e-06, + "loss": 0.2561, + "step": 27191 + }, + { + "epoch": 2.22, + "learning_rate": 5.2281616688396354e-06, + "loss": 0.3505, + "step": 27192 + }, + { + "epoch": 2.22, + "learning_rate": 5.22761842677097e-06, + "loss": 0.298, + "step": 27193 + }, + { + "epoch": 2.22, + "learning_rate": 5.227075184702304e-06, + "loss": 0.2127, + "step": 27194 + }, + { + "epoch": 2.22, + "learning_rate": 5.226531942633638e-06, + "loss": 0.4199, + "step": 27195 + }, + { + "epoch": 2.22, + "learning_rate": 5.225988700564972e-06, + "loss": 0.2197, + "step": 27196 + }, + { + "epoch": 2.22, + "learning_rate": 5.225445458496307e-06, + "loss": 0.1548, + "step": 27197 + }, + { + "epoch": 2.22, + "learning_rate": 5.224902216427641e-06, + "loss": 0.1754, + "step": 27198 + }, + { + "epoch": 2.22, + "learning_rate": 5.224358974358975e-06, + "loss": 0.1751, + "step": 27199 + }, + { + "epoch": 2.22, + "learning_rate": 5.223815732290309e-06, + "loss": 0.0697, + "step": 27200 + }, + { + "epoch": 2.22, + "learning_rate": 5.2232724902216435e-06, + "loss": 0.2559, + "step": 27201 + }, + { + "epoch": 2.22, + "learning_rate": 5.222729248152978e-06, + "loss": 0.248, + "step": 27202 + }, + { + "epoch": 2.22, + "learning_rate": 5.222186006084312e-06, + "loss": 0.4974, + "step": 27203 + }, + { + "epoch": 2.22, + "learning_rate": 5.221642764015645e-06, + "loss": 0.1605, + "step": 27204 + }, + { + "epoch": 2.22, + "learning_rate": 5.22109952194698e-06, + "loss": 0.2703, + "step": 27205 + }, + { + "epoch": 2.22, + "learning_rate": 5.220556279878314e-06, + "loss": 0.1003, + "step": 27206 + }, + { + "epoch": 2.22, + "learning_rate": 5.220013037809648e-06, + "loss": 0.2245, + "step": 27207 + }, + { + "epoch": 2.22, + "learning_rate": 5.219469795740982e-06, + "loss": 0.195, + "step": 27208 + }, + { + "epoch": 2.22, + "learning_rate": 5.2189265536723165e-06, + "loss": 0.2397, + "step": 27209 + }, + { + "epoch": 2.22, + "learning_rate": 5.218383311603651e-06, + "loss": 0.1316, + "step": 27210 + }, + { + "epoch": 2.22, + "learning_rate": 5.217840069534985e-06, + "loss": 0.168, + "step": 27211 + }, + { + "epoch": 2.22, + "learning_rate": 5.217296827466319e-06, + "loss": 0.4512, + "step": 27212 + }, + { + "epoch": 2.22, + "learning_rate": 5.2167535853976534e-06, + "loss": 0.0869, + "step": 27213 + }, + { + "epoch": 2.22, + "learning_rate": 5.216210343328988e-06, + "loss": 0.1448, + "step": 27214 + }, + { + "epoch": 2.22, + "learning_rate": 5.215667101260322e-06, + "loss": 0.3126, + "step": 27215 + }, + { + "epoch": 2.22, + "learning_rate": 5.215123859191656e-06, + "loss": 0.2516, + "step": 27216 + }, + { + "epoch": 2.22, + "learning_rate": 5.21458061712299e-06, + "loss": 0.0835, + "step": 27217 + }, + { + "epoch": 2.22, + "learning_rate": 5.214037375054325e-06, + "loss": 0.1177, + "step": 27218 + }, + { + "epoch": 2.22, + "learning_rate": 5.213494132985659e-06, + "loss": 0.408, + "step": 27219 + }, + { + "epoch": 2.22, + "learning_rate": 5.212950890916993e-06, + "loss": 0.0836, + "step": 27220 + }, + { + "epoch": 2.22, + "learning_rate": 5.212407648848328e-06, + "loss": 0.1276, + "step": 27221 + }, + { + "epoch": 2.22, + "learning_rate": 5.211864406779662e-06, + "loss": 0.2477, + "step": 27222 + }, + { + "epoch": 2.22, + "learning_rate": 5.211321164710995e-06, + "loss": 0.1196, + "step": 27223 + }, + { + "epoch": 2.22, + "learning_rate": 5.210777922642329e-06, + "loss": 0.1284, + "step": 27224 + }, + { + "epoch": 2.22, + "learning_rate": 5.210234680573663e-06, + "loss": 0.1347, + "step": 27225 + }, + { + "epoch": 2.22, + "learning_rate": 5.209691438504998e-06, + "loss": 0.1611, + "step": 27226 + }, + { + "epoch": 2.22, + "learning_rate": 5.209148196436332e-06, + "loss": 0.2016, + "step": 27227 + }, + { + "epoch": 2.22, + "learning_rate": 5.208604954367666e-06, + "loss": 0.4676, + "step": 27228 + }, + { + "epoch": 2.22, + "learning_rate": 5.208061712299001e-06, + "loss": 0.3468, + "step": 27229 + }, + { + "epoch": 2.22, + "learning_rate": 5.207518470230335e-06, + "loss": 0.1813, + "step": 27230 + }, + { + "epoch": 2.22, + "learning_rate": 5.20697522816167e-06, + "loss": 0.3191, + "step": 27231 + }, + { + "epoch": 2.22, + "learning_rate": 5.206431986093004e-06, + "loss": 0.3183, + "step": 27232 + }, + { + "epoch": 2.22, + "learning_rate": 5.205888744024338e-06, + "loss": 0.2312, + "step": 27233 + }, + { + "epoch": 2.22, + "learning_rate": 5.205345501955672e-06, + "loss": 0.1705, + "step": 27234 + }, + { + "epoch": 2.22, + "learning_rate": 5.2048022598870065e-06, + "loss": 0.1739, + "step": 27235 + }, + { + "epoch": 2.22, + "learning_rate": 5.204259017818341e-06, + "loss": 0.2, + "step": 27236 + }, + { + "epoch": 2.22, + "learning_rate": 5.203715775749675e-06, + "loss": 0.1563, + "step": 27237 + }, + { + "epoch": 2.22, + "learning_rate": 5.203172533681009e-06, + "loss": 0.3469, + "step": 27238 + }, + { + "epoch": 2.22, + "learning_rate": 5.2026292916123434e-06, + "loss": 0.1522, + "step": 27239 + }, + { + "epoch": 2.22, + "learning_rate": 5.202086049543678e-06, + "loss": 0.0876, + "step": 27240 + }, + { + "epoch": 2.22, + "learning_rate": 5.201542807475012e-06, + "loss": 0.2402, + "step": 27241 + }, + { + "epoch": 2.22, + "learning_rate": 5.200999565406345e-06, + "loss": 0.1061, + "step": 27242 + }, + { + "epoch": 2.22, + "learning_rate": 5.2004563233376795e-06, + "loss": 0.2337, + "step": 27243 + }, + { + "epoch": 2.22, + "learning_rate": 5.199913081269014e-06, + "loss": 0.1402, + "step": 27244 + }, + { + "epoch": 2.22, + "learning_rate": 5.199369839200348e-06, + "loss": 0.1331, + "step": 27245 + }, + { + "epoch": 2.22, + "learning_rate": 5.198826597131682e-06, + "loss": 0.3038, + "step": 27246 + }, + { + "epoch": 2.22, + "learning_rate": 5.1982833550630164e-06, + "loss": 0.1069, + "step": 27247 + }, + { + "epoch": 2.22, + "learning_rate": 5.197740112994351e-06, + "loss": 0.2733, + "step": 27248 + }, + { + "epoch": 2.22, + "learning_rate": 5.197196870925685e-06, + "loss": 0.2291, + "step": 27249 + }, + { + "epoch": 2.22, + "learning_rate": 5.196653628857019e-06, + "loss": 0.1809, + "step": 27250 + }, + { + "epoch": 2.22, + "eval_accuracy": 0.8430973000509424, + "eval_loss": 0.5010885000228882, + "eval_runtime": 22.2295, + "eval_samples_per_second": 441.531, + "eval_steps_per_second": 3.464, + "step": 27250 + }, + { + "epoch": 2.22, + "learning_rate": 5.196110386788353e-06, + "loss": 0.3394, + "step": 27251 + }, + { + "epoch": 2.22, + "learning_rate": 5.195567144719688e-06, + "loss": 0.2302, + "step": 27252 + }, + { + "epoch": 2.22, + "learning_rate": 5.195023902651022e-06, + "loss": 0.1503, + "step": 27253 + }, + { + "epoch": 2.22, + "learning_rate": 5.194480660582356e-06, + "loss": 0.1358, + "step": 27254 + }, + { + "epoch": 2.22, + "learning_rate": 5.19393741851369e-06, + "loss": 0.2021, + "step": 27255 + }, + { + "epoch": 2.22, + "learning_rate": 5.1933941764450245e-06, + "loss": 0.5046, + "step": 27256 + }, + { + "epoch": 2.22, + "learning_rate": 5.192850934376359e-06, + "loss": 0.2422, + "step": 27257 + }, + { + "epoch": 2.22, + "learning_rate": 5.192307692307693e-06, + "loss": 0.5242, + "step": 27258 + }, + { + "epoch": 2.22, + "learning_rate": 5.191764450239027e-06, + "loss": 0.0282, + "step": 27259 + }, + { + "epoch": 2.22, + "learning_rate": 5.191221208170361e-06, + "loss": 0.0845, + "step": 27260 + }, + { + "epoch": 2.22, + "learning_rate": 5.190677966101695e-06, + "loss": 0.4483, + "step": 27261 + }, + { + "epoch": 2.22, + "learning_rate": 5.190134724033029e-06, + "loss": 0.2264, + "step": 27262 + }, + { + "epoch": 2.22, + "learning_rate": 5.189591481964363e-06, + "loss": 0.138, + "step": 27263 + }, + { + "epoch": 2.22, + "learning_rate": 5.1890482398956975e-06, + "loss": 0.1732, + "step": 27264 + }, + { + "epoch": 2.22, + "learning_rate": 5.188504997827032e-06, + "loss": 0.4047, + "step": 27265 + }, + { + "epoch": 2.22, + "learning_rate": 5.187961755758366e-06, + "loss": 0.3015, + "step": 27266 + }, + { + "epoch": 2.22, + "learning_rate": 5.1874185136897e-06, + "loss": 0.151, + "step": 27267 + }, + { + "epoch": 2.22, + "learning_rate": 5.186875271621034e-06, + "loss": 0.1831, + "step": 27268 + }, + { + "epoch": 2.22, + "learning_rate": 5.186332029552369e-06, + "loss": 0.2899, + "step": 27269 + }, + { + "epoch": 2.22, + "learning_rate": 5.185788787483703e-06, + "loss": 0.1808, + "step": 27270 + }, + { + "epoch": 2.22, + "learning_rate": 5.185245545415037e-06, + "loss": 0.1156, + "step": 27271 + }, + { + "epoch": 2.22, + "learning_rate": 5.184702303346371e-06, + "loss": 0.2795, + "step": 27272 + }, + { + "epoch": 2.22, + "learning_rate": 5.1841590612777056e-06, + "loss": 0.1477, + "step": 27273 + }, + { + "epoch": 2.22, + "learning_rate": 5.18361581920904e-06, + "loss": 0.0992, + "step": 27274 + }, + { + "epoch": 2.22, + "learning_rate": 5.183072577140375e-06, + "loss": 0.2184, + "step": 27275 + }, + { + "epoch": 2.22, + "learning_rate": 5.182529335071709e-06, + "loss": 0.2651, + "step": 27276 + }, + { + "epoch": 2.22, + "learning_rate": 5.181986093003043e-06, + "loss": 0.358, + "step": 27277 + }, + { + "epoch": 2.22, + "learning_rate": 5.1814428509343776e-06, + "loss": 0.2105, + "step": 27278 + }, + { + "epoch": 2.22, + "learning_rate": 5.180899608865712e-06, + "loss": 0.109, + "step": 27279 + }, + { + "epoch": 2.22, + "learning_rate": 5.180356366797044e-06, + "loss": 0.2541, + "step": 27280 + }, + { + "epoch": 2.22, + "learning_rate": 5.1798131247283786e-06, + "loss": 0.2222, + "step": 27281 + }, + { + "epoch": 2.22, + "learning_rate": 5.179269882659713e-06, + "loss": 0.0417, + "step": 27282 + }, + { + "epoch": 2.22, + "learning_rate": 5.178726640591048e-06, + "loss": 0.4112, + "step": 27283 + }, + { + "epoch": 2.22, + "learning_rate": 5.178183398522382e-06, + "loss": 0.2686, + "step": 27284 + }, + { + "epoch": 2.22, + "learning_rate": 5.177640156453716e-06, + "loss": 0.3787, + "step": 27285 + }, + { + "epoch": 2.22, + "learning_rate": 5.1770969143850506e-06, + "loss": 0.414, + "step": 27286 + }, + { + "epoch": 2.22, + "learning_rate": 5.176553672316385e-06, + "loss": 0.1911, + "step": 27287 + }, + { + "epoch": 2.22, + "learning_rate": 5.176010430247719e-06, + "loss": 0.3466, + "step": 27288 + }, + { + "epoch": 2.22, + "learning_rate": 5.175467188179053e-06, + "loss": 0.2442, + "step": 27289 + }, + { + "epoch": 2.22, + "learning_rate": 5.1749239461103875e-06, + "loss": 0.1869, + "step": 27290 + }, + { + "epoch": 2.22, + "learning_rate": 5.174380704041722e-06, + "loss": 0.3196, + "step": 27291 + }, + { + "epoch": 2.22, + "learning_rate": 5.173837461973056e-06, + "loss": 0.1842, + "step": 27292 + }, + { + "epoch": 2.22, + "learning_rate": 5.17329421990439e-06, + "loss": 0.2355, + "step": 27293 + }, + { + "epoch": 2.22, + "learning_rate": 5.172750977835724e-06, + "loss": 0.1186, + "step": 27294 + }, + { + "epoch": 2.22, + "learning_rate": 5.172207735767059e-06, + "loss": 0.1566, + "step": 27295 + }, + { + "epoch": 2.22, + "learning_rate": 5.171664493698393e-06, + "loss": 0.2586, + "step": 27296 + }, + { + "epoch": 2.22, + "learning_rate": 5.171121251629727e-06, + "loss": 0.1559, + "step": 27297 + }, + { + "epoch": 2.22, + "learning_rate": 5.170578009561061e-06, + "loss": 0.1087, + "step": 27298 + }, + { + "epoch": 2.22, + "learning_rate": 5.170034767492395e-06, + "loss": 0.1084, + "step": 27299 + }, + { + "epoch": 2.22, + "learning_rate": 5.169491525423729e-06, + "loss": 0.2777, + "step": 27300 + }, + { + "epoch": 2.22, + "learning_rate": 5.168948283355063e-06, + "loss": 0.6181, + "step": 27301 + }, + { + "epoch": 2.22, + "learning_rate": 5.168405041286397e-06, + "loss": 0.1598, + "step": 27302 + }, + { + "epoch": 2.22, + "learning_rate": 5.167861799217732e-06, + "loss": 0.1942, + "step": 27303 + }, + { + "epoch": 2.22, + "learning_rate": 5.167318557149066e-06, + "loss": 0.1746, + "step": 27304 + }, + { + "epoch": 2.22, + "learning_rate": 5.1667753150804e-06, + "loss": 0.1575, + "step": 27305 + }, + { + "epoch": 2.23, + "learning_rate": 5.166232073011734e-06, + "loss": 0.1446, + "step": 27306 + }, + { + "epoch": 2.23, + "learning_rate": 5.1656888309430686e-06, + "loss": 0.0805, + "step": 27307 + }, + { + "epoch": 2.23, + "learning_rate": 5.165145588874403e-06, + "loss": 0.4638, + "step": 27308 + }, + { + "epoch": 2.23, + "learning_rate": 5.164602346805737e-06, + "loss": 0.453, + "step": 27309 + }, + { + "epoch": 2.23, + "learning_rate": 5.164059104737071e-06, + "loss": 0.3855, + "step": 27310 + }, + { + "epoch": 2.23, + "learning_rate": 5.1635158626684055e-06, + "loss": 0.2113, + "step": 27311 + }, + { + "epoch": 2.23, + "learning_rate": 5.16297262059974e-06, + "loss": 0.1448, + "step": 27312 + }, + { + "epoch": 2.23, + "learning_rate": 5.162429378531074e-06, + "loss": 0.34, + "step": 27313 + }, + { + "epoch": 2.23, + "learning_rate": 5.161886136462408e-06, + "loss": 0.3269, + "step": 27314 + }, + { + "epoch": 2.23, + "learning_rate": 5.161342894393742e-06, + "loss": 0.1318, + "step": 27315 + }, + { + "epoch": 2.23, + "learning_rate": 5.160799652325077e-06, + "loss": 0.1768, + "step": 27316 + }, + { + "epoch": 2.23, + "learning_rate": 5.160256410256411e-06, + "loss": 0.3119, + "step": 27317 + }, + { + "epoch": 2.23, + "learning_rate": 5.159713168187744e-06, + "loss": 0.2642, + "step": 27318 + }, + { + "epoch": 2.23, + "learning_rate": 5.1591699261190785e-06, + "loss": 0.2779, + "step": 27319 + }, + { + "epoch": 2.23, + "learning_rate": 5.158626684050413e-06, + "loss": 0.2096, + "step": 27320 + }, + { + "epoch": 2.23, + "learning_rate": 5.158083441981747e-06, + "loss": 0.1718, + "step": 27321 + }, + { + "epoch": 2.23, + "learning_rate": 5.157540199913081e-06, + "loss": 0.3494, + "step": 27322 + }, + { + "epoch": 2.23, + "learning_rate": 5.156996957844415e-06, + "loss": 0.1186, + "step": 27323 + }, + { + "epoch": 2.23, + "learning_rate": 5.15645371577575e-06, + "loss": 0.1101, + "step": 27324 + }, + { + "epoch": 2.23, + "learning_rate": 5.155910473707084e-06, + "loss": 0.3777, + "step": 27325 + }, + { + "epoch": 2.23, + "learning_rate": 5.155367231638418e-06, + "loss": 0.0999, + "step": 27326 + }, + { + "epoch": 2.23, + "learning_rate": 5.154823989569752e-06, + "loss": 0.234, + "step": 27327 + }, + { + "epoch": 2.23, + "learning_rate": 5.1542807475010866e-06, + "loss": 0.3546, + "step": 27328 + }, + { + "epoch": 2.23, + "learning_rate": 5.153737505432422e-06, + "loss": 0.1954, + "step": 27329 + }, + { + "epoch": 2.23, + "learning_rate": 5.153194263363756e-06, + "loss": 0.1383, + "step": 27330 + }, + { + "epoch": 2.23, + "learning_rate": 5.15265102129509e-06, + "loss": 0.171, + "step": 27331 + }, + { + "epoch": 2.23, + "learning_rate": 5.152107779226424e-06, + "loss": 0.235, + "step": 27332 + }, + { + "epoch": 2.23, + "learning_rate": 5.1515645371577586e-06, + "loss": 0.2045, + "step": 27333 + }, + { + "epoch": 2.23, + "learning_rate": 5.151021295089093e-06, + "loss": 0.1132, + "step": 27334 + }, + { + "epoch": 2.23, + "learning_rate": 5.150478053020427e-06, + "loss": 0.1624, + "step": 27335 + }, + { + "epoch": 2.23, + "learning_rate": 5.149934810951761e-06, + "loss": 0.3583, + "step": 27336 + }, + { + "epoch": 2.23, + "learning_rate": 5.149391568883095e-06, + "loss": 0.0493, + "step": 27337 + }, + { + "epoch": 2.23, + "learning_rate": 5.148848326814429e-06, + "loss": 0.237, + "step": 27338 + }, + { + "epoch": 2.23, + "learning_rate": 5.148305084745763e-06, + "loss": 0.1136, + "step": 27339 + }, + { + "epoch": 2.23, + "learning_rate": 5.147761842677097e-06, + "loss": 0.2032, + "step": 27340 + }, + { + "epoch": 2.23, + "learning_rate": 5.1472186006084316e-06, + "loss": 0.3857, + "step": 27341 + }, + { + "epoch": 2.23, + "learning_rate": 5.146675358539766e-06, + "loss": 0.121, + "step": 27342 + }, + { + "epoch": 2.23, + "learning_rate": 5.1461321164711e-06, + "loss": 0.3219, + "step": 27343 + }, + { + "epoch": 2.23, + "learning_rate": 5.145588874402434e-06, + "loss": 0.4011, + "step": 27344 + }, + { + "epoch": 2.23, + "learning_rate": 5.1450456323337685e-06, + "loss": 0.4303, + "step": 27345 + }, + { + "epoch": 2.23, + "learning_rate": 5.144502390265103e-06, + "loss": 0.2522, + "step": 27346 + }, + { + "epoch": 2.23, + "learning_rate": 5.143959148196437e-06, + "loss": 0.2212, + "step": 27347 + }, + { + "epoch": 2.23, + "learning_rate": 5.143415906127771e-06, + "loss": 0.2856, + "step": 27348 + }, + { + "epoch": 2.23, + "learning_rate": 5.142872664059105e-06, + "loss": 0.2076, + "step": 27349 + }, + { + "epoch": 2.23, + "learning_rate": 5.14232942199044e-06, + "loss": 0.3477, + "step": 27350 + }, + { + "epoch": 2.23, + "learning_rate": 5.141786179921774e-06, + "loss": 0.2938, + "step": 27351 + }, + { + "epoch": 2.23, + "learning_rate": 5.141242937853108e-06, + "loss": 0.1053, + "step": 27352 + }, + { + "epoch": 2.23, + "learning_rate": 5.140699695784442e-06, + "loss": 0.1357, + "step": 27353 + }, + { + "epoch": 2.23, + "learning_rate": 5.1401564537157766e-06, + "loss": 0.0842, + "step": 27354 + }, + { + "epoch": 2.23, + "learning_rate": 5.139613211647111e-06, + "loss": 0.1768, + "step": 27355 + }, + { + "epoch": 2.23, + "learning_rate": 5.139069969578444e-06, + "loss": 0.1452, + "step": 27356 + }, + { + "epoch": 2.23, + "learning_rate": 5.138526727509778e-06, + "loss": 0.464, + "step": 27357 + }, + { + "epoch": 2.23, + "learning_rate": 5.137983485441113e-06, + "loss": 0.5205, + "step": 27358 + }, + { + "epoch": 2.23, + "learning_rate": 5.137440243372447e-06, + "loss": 0.2143, + "step": 27359 + }, + { + "epoch": 2.23, + "learning_rate": 5.136897001303781e-06, + "loss": 0.2993, + "step": 27360 + }, + { + "epoch": 2.23, + "learning_rate": 5.136353759235115e-06, + "loss": 0.2264, + "step": 27361 + }, + { + "epoch": 2.23, + "learning_rate": 5.1358105171664495e-06, + "loss": 0.2861, + "step": 27362 + }, + { + "epoch": 2.23, + "learning_rate": 5.135267275097784e-06, + "loss": 0.1178, + "step": 27363 + }, + { + "epoch": 2.23, + "learning_rate": 5.134724033029118e-06, + "loss": 0.3324, + "step": 27364 + }, + { + "epoch": 2.23, + "learning_rate": 5.134180790960452e-06, + "loss": 0.4569, + "step": 27365 + }, + { + "epoch": 2.23, + "learning_rate": 5.1336375488917865e-06, + "loss": 0.2535, + "step": 27366 + }, + { + "epoch": 2.23, + "learning_rate": 5.133094306823121e-06, + "loss": 0.2503, + "step": 27367 + }, + { + "epoch": 2.23, + "learning_rate": 5.132551064754455e-06, + "loss": 0.3061, + "step": 27368 + }, + { + "epoch": 2.23, + "learning_rate": 5.132007822685789e-06, + "loss": 0.2092, + "step": 27369 + }, + { + "epoch": 2.23, + "learning_rate": 5.131464580617123e-06, + "loss": 0.093, + "step": 27370 + }, + { + "epoch": 2.23, + "learning_rate": 5.130921338548458e-06, + "loss": 0.3355, + "step": 27371 + }, + { + "epoch": 2.23, + "learning_rate": 5.130378096479792e-06, + "loss": 0.3214, + "step": 27372 + }, + { + "epoch": 2.23, + "learning_rate": 5.129834854411126e-06, + "loss": 0.253, + "step": 27373 + }, + { + "epoch": 2.23, + "learning_rate": 5.129291612342461e-06, + "loss": 0.1405, + "step": 27374 + }, + { + "epoch": 2.23, + "learning_rate": 5.128748370273794e-06, + "loss": 0.0447, + "step": 27375 + }, + { + "epoch": 2.23, + "learning_rate": 5.128205128205128e-06, + "loss": 0.1791, + "step": 27376 + }, + { + "epoch": 2.23, + "learning_rate": 5.127661886136462e-06, + "loss": 0.1863, + "step": 27377 + }, + { + "epoch": 2.23, + "learning_rate": 5.127118644067796e-06, + "loss": 0.1172, + "step": 27378 + }, + { + "epoch": 2.23, + "learning_rate": 5.126575401999131e-06, + "loss": 0.4849, + "step": 27379 + }, + { + "epoch": 2.23, + "learning_rate": 5.126032159930465e-06, + "loss": 0.3187, + "step": 27380 + }, + { + "epoch": 2.23, + "learning_rate": 5.125488917861799e-06, + "loss": 0.0683, + "step": 27381 + }, + { + "epoch": 2.23, + "learning_rate": 5.124945675793133e-06, + "loss": 0.319, + "step": 27382 + }, + { + "epoch": 2.23, + "learning_rate": 5.124402433724468e-06, + "loss": 0.4503, + "step": 27383 + }, + { + "epoch": 2.23, + "learning_rate": 5.123859191655803e-06, + "loss": 0.3356, + "step": 27384 + }, + { + "epoch": 2.23, + "learning_rate": 5.123315949587137e-06, + "loss": 0.2645, + "step": 27385 + }, + { + "epoch": 2.23, + "learning_rate": 5.122772707518471e-06, + "loss": 0.243, + "step": 27386 + }, + { + "epoch": 2.23, + "learning_rate": 5.122229465449805e-06, + "loss": 0.142, + "step": 27387 + }, + { + "epoch": 2.23, + "learning_rate": 5.1216862233811395e-06, + "loss": 0.2228, + "step": 27388 + }, + { + "epoch": 2.23, + "learning_rate": 5.121142981312474e-06, + "loss": 0.2942, + "step": 27389 + }, + { + "epoch": 2.23, + "learning_rate": 5.120599739243808e-06, + "loss": 0.2001, + "step": 27390 + }, + { + "epoch": 2.23, + "learning_rate": 5.120056497175142e-06, + "loss": 0.0629, + "step": 27391 + }, + { + "epoch": 2.23, + "learning_rate": 5.1195132551064765e-06, + "loss": 0.2219, + "step": 27392 + }, + { + "epoch": 2.23, + "learning_rate": 5.118970013037811e-06, + "loss": 0.2077, + "step": 27393 + }, + { + "epoch": 2.23, + "learning_rate": 5.118426770969144e-06, + "loss": 0.0887, + "step": 27394 + }, + { + "epoch": 2.23, + "learning_rate": 5.117883528900478e-06, + "loss": 0.0464, + "step": 27395 + }, + { + "epoch": 2.23, + "learning_rate": 5.1173402868318125e-06, + "loss": 0.3496, + "step": 27396 + }, + { + "epoch": 2.23, + "learning_rate": 5.116797044763147e-06, + "loss": 0.0802, + "step": 27397 + }, + { + "epoch": 2.23, + "learning_rate": 5.116253802694481e-06, + "loss": 0.1359, + "step": 27398 + }, + { + "epoch": 2.23, + "learning_rate": 5.115710560625815e-06, + "loss": 0.3115, + "step": 27399 + }, + { + "epoch": 2.23, + "learning_rate": 5.1151673185571495e-06, + "loss": 0.4456, + "step": 27400 + }, + { + "epoch": 2.23, + "learning_rate": 5.114624076488484e-06, + "loss": 0.1907, + "step": 27401 + }, + { + "epoch": 2.23, + "learning_rate": 5.114080834419818e-06, + "loss": 0.225, + "step": 27402 + }, + { + "epoch": 2.23, + "learning_rate": 5.113537592351152e-06, + "loss": 0.2138, + "step": 27403 + }, + { + "epoch": 2.23, + "learning_rate": 5.112994350282486e-06, + "loss": 0.3464, + "step": 27404 + }, + { + "epoch": 2.23, + "learning_rate": 5.112451108213821e-06, + "loss": 0.081, + "step": 27405 + }, + { + "epoch": 2.23, + "learning_rate": 5.111907866145155e-06, + "loss": 0.1626, + "step": 27406 + }, + { + "epoch": 2.23, + "learning_rate": 5.111364624076489e-06, + "loss": 0.2873, + "step": 27407 + }, + { + "epoch": 2.23, + "learning_rate": 5.110821382007823e-06, + "loss": 0.1188, + "step": 27408 + }, + { + "epoch": 2.23, + "learning_rate": 5.1102781399391575e-06, + "loss": 0.1685, + "step": 27409 + }, + { + "epoch": 2.23, + "learning_rate": 5.109734897870492e-06, + "loss": 0.2727, + "step": 27410 + }, + { + "epoch": 2.23, + "learning_rate": 5.109191655801826e-06, + "loss": 0.4933, + "step": 27411 + }, + { + "epoch": 2.23, + "learning_rate": 5.10864841373316e-06, + "loss": 0.1094, + "step": 27412 + }, + { + "epoch": 2.23, + "learning_rate": 5.108105171664494e-06, + "loss": 0.3618, + "step": 27413 + }, + { + "epoch": 2.23, + "learning_rate": 5.107561929595828e-06, + "loss": 0.1516, + "step": 27414 + }, + { + "epoch": 2.23, + "learning_rate": 5.107018687527162e-06, + "loss": 0.0992, + "step": 27415 + }, + { + "epoch": 2.23, + "learning_rate": 5.106475445458496e-06, + "loss": 0.3374, + "step": 27416 + }, + { + "epoch": 2.23, + "learning_rate": 5.1059322033898305e-06, + "loss": 0.2122, + "step": 27417 + }, + { + "epoch": 2.23, + "learning_rate": 5.105388961321165e-06, + "loss": 0.1122, + "step": 27418 + }, + { + "epoch": 2.23, + "learning_rate": 5.104845719252499e-06, + "loss": 0.3347, + "step": 27419 + }, + { + "epoch": 2.23, + "learning_rate": 5.104302477183833e-06, + "loss": 0.2656, + "step": 27420 + }, + { + "epoch": 2.23, + "learning_rate": 5.1037592351151675e-06, + "loss": 0.0715, + "step": 27421 + }, + { + "epoch": 2.23, + "learning_rate": 5.103215993046502e-06, + "loss": 0.1702, + "step": 27422 + }, + { + "epoch": 2.23, + "learning_rate": 5.102672750977836e-06, + "loss": 0.1751, + "step": 27423 + }, + { + "epoch": 2.23, + "learning_rate": 5.10212950890917e-06, + "loss": 0.3217, + "step": 27424 + }, + { + "epoch": 2.23, + "learning_rate": 5.101586266840504e-06, + "loss": 0.1347, + "step": 27425 + }, + { + "epoch": 2.23, + "learning_rate": 5.101043024771839e-06, + "loss": 0.29, + "step": 27426 + }, + { + "epoch": 2.23, + "learning_rate": 5.100499782703173e-06, + "loss": 0.239, + "step": 27427 + }, + { + "epoch": 2.24, + "learning_rate": 5.099956540634508e-06, + "loss": 0.1523, + "step": 27428 + }, + { + "epoch": 2.24, + "learning_rate": 5.099413298565842e-06, + "loss": 0.2339, + "step": 27429 + }, + { + "epoch": 2.24, + "learning_rate": 5.098870056497176e-06, + "loss": 0.2412, + "step": 27430 + }, + { + "epoch": 2.24, + "learning_rate": 5.098326814428511e-06, + "loss": 0.0616, + "step": 27431 + }, + { + "epoch": 2.24, + "learning_rate": 5.097783572359843e-06, + "loss": 0.0851, + "step": 27432 + }, + { + "epoch": 2.24, + "learning_rate": 5.097240330291177e-06, + "loss": 0.0549, + "step": 27433 + }, + { + "epoch": 2.24, + "learning_rate": 5.096697088222512e-06, + "loss": 0.1501, + "step": 27434 + }, + { + "epoch": 2.24, + "learning_rate": 5.096153846153846e-06, + "loss": 0.1339, + "step": 27435 + }, + { + "epoch": 2.24, + "learning_rate": 5.09561060408518e-06, + "loss": 0.2738, + "step": 27436 + }, + { + "epoch": 2.24, + "learning_rate": 5.095067362016515e-06, + "loss": 0.1169, + "step": 27437 + }, + { + "epoch": 2.24, + "learning_rate": 5.094524119947849e-06, + "loss": 0.1969, + "step": 27438 + }, + { + "epoch": 2.24, + "learning_rate": 5.093980877879184e-06, + "loss": 0.3012, + "step": 27439 + }, + { + "epoch": 2.24, + "learning_rate": 5.093437635810518e-06, + "loss": 0.2683, + "step": 27440 + }, + { + "epoch": 2.24, + "learning_rate": 5.092894393741852e-06, + "loss": 0.4569, + "step": 27441 + }, + { + "epoch": 2.24, + "learning_rate": 5.092351151673186e-06, + "loss": 0.3889, + "step": 27442 + }, + { + "epoch": 2.24, + "learning_rate": 5.0918079096045205e-06, + "loss": 0.226, + "step": 27443 + }, + { + "epoch": 2.24, + "learning_rate": 5.091264667535855e-06, + "loss": 0.1705, + "step": 27444 + }, + { + "epoch": 2.24, + "learning_rate": 5.090721425467189e-06, + "loss": 0.4584, + "step": 27445 + }, + { + "epoch": 2.24, + "learning_rate": 5.090178183398523e-06, + "loss": 0.136, + "step": 27446 + }, + { + "epoch": 2.24, + "learning_rate": 5.0896349413298575e-06, + "loss": 0.221, + "step": 27447 + }, + { + "epoch": 2.24, + "learning_rate": 5.089091699261192e-06, + "loss": 0.1549, + "step": 27448 + }, + { + "epoch": 2.24, + "learning_rate": 5.088548457192526e-06, + "loss": 0.2611, + "step": 27449 + }, + { + "epoch": 2.24, + "learning_rate": 5.08800521512386e-06, + "loss": 0.1886, + "step": 27450 + }, + { + "epoch": 2.24, + "learning_rate": 5.0874619730551935e-06, + "loss": 0.0393, + "step": 27451 + }, + { + "epoch": 2.24, + "learning_rate": 5.086918730986528e-06, + "loss": 0.1666, + "step": 27452 + }, + { + "epoch": 2.24, + "learning_rate": 5.086375488917862e-06, + "loss": 0.0941, + "step": 27453 + }, + { + "epoch": 2.24, + "learning_rate": 5.085832246849196e-06, + "loss": 0.1046, + "step": 27454 + }, + { + "epoch": 2.24, + "learning_rate": 5.0852890047805304e-06, + "loss": 0.1137, + "step": 27455 + }, + { + "epoch": 2.24, + "learning_rate": 5.084745762711865e-06, + "loss": 0.2807, + "step": 27456 + }, + { + "epoch": 2.24, + "learning_rate": 5.084202520643199e-06, + "loss": 0.4326, + "step": 27457 + }, + { + "epoch": 2.24, + "learning_rate": 5.083659278574533e-06, + "loss": 0.1796, + "step": 27458 + }, + { + "epoch": 2.24, + "learning_rate": 5.083116036505867e-06, + "loss": 0.092, + "step": 27459 + }, + { + "epoch": 2.24, + "learning_rate": 5.082572794437202e-06, + "loss": 0.3326, + "step": 27460 + }, + { + "epoch": 2.24, + "learning_rate": 5.082029552368536e-06, + "loss": 0.2563, + "step": 27461 + }, + { + "epoch": 2.24, + "learning_rate": 5.08148631029987e-06, + "loss": 0.4611, + "step": 27462 + }, + { + "epoch": 2.24, + "learning_rate": 5.080943068231204e-06, + "loss": 0.1864, + "step": 27463 + }, + { + "epoch": 2.24, + "learning_rate": 5.0803998261625385e-06, + "loss": 0.3065, + "step": 27464 + }, + { + "epoch": 2.24, + "learning_rate": 5.079856584093873e-06, + "loss": 0.3909, + "step": 27465 + }, + { + "epoch": 2.24, + "learning_rate": 5.079313342025207e-06, + "loss": 0.2401, + "step": 27466 + }, + { + "epoch": 2.24, + "learning_rate": 5.078770099956541e-06, + "loss": 0.2055, + "step": 27467 + }, + { + "epoch": 2.24, + "learning_rate": 5.0782268578878754e-06, + "loss": 0.3521, + "step": 27468 + }, + { + "epoch": 2.24, + "learning_rate": 5.07768361581921e-06, + "loss": 0.316, + "step": 27469 + }, + { + "epoch": 2.24, + "learning_rate": 5.077140373750543e-06, + "loss": 0.3689, + "step": 27470 + }, + { + "epoch": 2.24, + "learning_rate": 5.076597131681877e-06, + "loss": 0.1353, + "step": 27471 + }, + { + "epoch": 2.24, + "learning_rate": 5.0760538896132115e-06, + "loss": 0.275, + "step": 27472 + }, + { + "epoch": 2.24, + "learning_rate": 5.075510647544546e-06, + "loss": 0.2769, + "step": 27473 + }, + { + "epoch": 2.24, + "learning_rate": 5.07496740547588e-06, + "loss": 0.1709, + "step": 27474 + }, + { + "epoch": 2.24, + "learning_rate": 5.074424163407214e-06, + "loss": 0.1004, + "step": 27475 + }, + { + "epoch": 2.24, + "learning_rate": 5.0738809213385484e-06, + "loss": 0.291, + "step": 27476 + }, + { + "epoch": 2.24, + "learning_rate": 5.073337679269883e-06, + "loss": 0.1944, + "step": 27477 + }, + { + "epoch": 2.24, + "learning_rate": 5.072794437201217e-06, + "loss": 0.1604, + "step": 27478 + }, + { + "epoch": 2.24, + "learning_rate": 5.072251195132551e-06, + "loss": 0.1565, + "step": 27479 + }, + { + "epoch": 2.24, + "learning_rate": 5.071707953063885e-06, + "loss": 0.3044, + "step": 27480 + }, + { + "epoch": 2.24, + "learning_rate": 5.07116471099522e-06, + "loss": 0.0933, + "step": 27481 + }, + { + "epoch": 2.24, + "learning_rate": 5.070621468926555e-06, + "loss": 0.2032, + "step": 27482 + }, + { + "epoch": 2.24, + "learning_rate": 5.070078226857889e-06, + "loss": 0.0843, + "step": 27483 + }, + { + "epoch": 2.24, + "learning_rate": 5.069534984789223e-06, + "loss": 0.2749, + "step": 27484 + }, + { + "epoch": 2.24, + "learning_rate": 5.068991742720557e-06, + "loss": 0.2314, + "step": 27485 + }, + { + "epoch": 2.24, + "learning_rate": 5.068448500651892e-06, + "loss": 0.2432, + "step": 27486 + }, + { + "epoch": 2.24, + "learning_rate": 5.067905258583226e-06, + "loss": 0.2201, + "step": 27487 + }, + { + "epoch": 2.24, + "learning_rate": 5.06736201651456e-06, + "loss": 0.1538, + "step": 27488 + }, + { + "epoch": 2.24, + "learning_rate": 5.066818774445893e-06, + "loss": 0.4046, + "step": 27489 + }, + { + "epoch": 2.24, + "learning_rate": 5.066275532377227e-06, + "loss": 0.199, + "step": 27490 + }, + { + "epoch": 2.24, + "learning_rate": 5.065732290308562e-06, + "loss": 0.3062, + "step": 27491 + }, + { + "epoch": 2.24, + "learning_rate": 5.065189048239896e-06, + "loss": 0.3062, + "step": 27492 + }, + { + "epoch": 2.24, + "learning_rate": 5.06464580617123e-06, + "loss": 0.3749, + "step": 27493 + }, + { + "epoch": 2.24, + "learning_rate": 5.064102564102565e-06, + "loss": 0.0553, + "step": 27494 + }, + { + "epoch": 2.24, + "learning_rate": 5.063559322033899e-06, + "loss": 0.3559, + "step": 27495 + }, + { + "epoch": 2.24, + "learning_rate": 5.063016079965233e-06, + "loss": 0.3828, + "step": 27496 + }, + { + "epoch": 2.24, + "learning_rate": 5.062472837896567e-06, + "loss": 0.0871, + "step": 27497 + }, + { + "epoch": 2.24, + "learning_rate": 5.0619295958279015e-06, + "loss": 0.0823, + "step": 27498 + }, + { + "epoch": 2.24, + "learning_rate": 5.061386353759236e-06, + "loss": 0.1462, + "step": 27499 + }, + { + "epoch": 2.24, + "learning_rate": 5.06084311169057e-06, + "loss": 0.3025, + "step": 27500 + }, + { + "epoch": 2.24, + "eval_accuracy": 0.8423841059602649, + "eval_loss": 0.49978578090667725, + "eval_runtime": 22.2748, + "eval_samples_per_second": 440.633, + "eval_steps_per_second": 3.457, + "step": 27500 + }, + { + "epoch": 2.24, + "learning_rate": 5.060299869621904e-06, + "loss": 0.1369, + "step": 27501 + }, + { + "epoch": 2.24, + "learning_rate": 5.0597566275532384e-06, + "loss": 0.2916, + "step": 27502 + }, + { + "epoch": 2.24, + "learning_rate": 5.059213385484573e-06, + "loss": 0.1906, + "step": 27503 + }, + { + "epoch": 2.24, + "learning_rate": 5.058670143415907e-06, + "loss": 0.0762, + "step": 27504 + }, + { + "epoch": 2.24, + "learning_rate": 5.058126901347241e-06, + "loss": 0.109, + "step": 27505 + }, + { + "epoch": 2.24, + "learning_rate": 5.057583659278575e-06, + "loss": 0.1769, + "step": 27506 + }, + { + "epoch": 2.24, + "learning_rate": 5.05704041720991e-06, + "loss": 0.2154, + "step": 27507 + }, + { + "epoch": 2.24, + "learning_rate": 5.056497175141243e-06, + "loss": 0.1114, + "step": 27508 + }, + { + "epoch": 2.24, + "learning_rate": 5.055953933072577e-06, + "loss": 0.0832, + "step": 27509 + }, + { + "epoch": 2.24, + "learning_rate": 5.0554106910039114e-06, + "loss": 0.3234, + "step": 27510 + }, + { + "epoch": 2.24, + "learning_rate": 5.054867448935246e-06, + "loss": 0.2794, + "step": 27511 + }, + { + "epoch": 2.24, + "learning_rate": 5.05432420686658e-06, + "loss": 0.1577, + "step": 27512 + }, + { + "epoch": 2.24, + "learning_rate": 5.053780964797914e-06, + "loss": 0.0685, + "step": 27513 + }, + { + "epoch": 2.24, + "learning_rate": 5.053237722729248e-06, + "loss": 0.0459, + "step": 27514 + }, + { + "epoch": 2.24, + "learning_rate": 5.052694480660583e-06, + "loss": 0.1454, + "step": 27515 + }, + { + "epoch": 2.24, + "learning_rate": 5.052151238591917e-06, + "loss": 0.2267, + "step": 27516 + }, + { + "epoch": 2.24, + "learning_rate": 5.051607996523251e-06, + "loss": 0.1792, + "step": 27517 + }, + { + "epoch": 2.24, + "learning_rate": 5.051064754454585e-06, + "loss": 0.2465, + "step": 27518 + }, + { + "epoch": 2.24, + "learning_rate": 5.0505215123859195e-06, + "loss": 0.1853, + "step": 27519 + }, + { + "epoch": 2.24, + "learning_rate": 5.049978270317254e-06, + "loss": 0.1195, + "step": 27520 + }, + { + "epoch": 2.24, + "learning_rate": 5.049435028248588e-06, + "loss": 0.0819, + "step": 27521 + }, + { + "epoch": 2.24, + "learning_rate": 5.048891786179922e-06, + "loss": 0.5461, + "step": 27522 + }, + { + "epoch": 2.24, + "learning_rate": 5.0483485441112564e-06, + "loss": 0.3408, + "step": 27523 + }, + { + "epoch": 2.24, + "learning_rate": 5.047805302042591e-06, + "loss": 0.1366, + "step": 27524 + }, + { + "epoch": 2.24, + "learning_rate": 5.047262059973925e-06, + "loss": 0.197, + "step": 27525 + }, + { + "epoch": 2.24, + "learning_rate": 5.046718817905259e-06, + "loss": 0.2353, + "step": 27526 + }, + { + "epoch": 2.24, + "learning_rate": 5.0461755758365925e-06, + "loss": 0.3253, + "step": 27527 + }, + { + "epoch": 2.24, + "learning_rate": 5.045632333767927e-06, + "loss": 0.1485, + "step": 27528 + }, + { + "epoch": 2.24, + "learning_rate": 5.045089091699261e-06, + "loss": 0.3281, + "step": 27529 + }, + { + "epoch": 2.24, + "learning_rate": 5.044545849630595e-06, + "loss": 0.0518, + "step": 27530 + }, + { + "epoch": 2.24, + "learning_rate": 5.0440026075619294e-06, + "loss": 0.5124, + "step": 27531 + }, + { + "epoch": 2.24, + "learning_rate": 5.043459365493264e-06, + "loss": 0.2405, + "step": 27532 + }, + { + "epoch": 2.24, + "learning_rate": 5.042916123424598e-06, + "loss": 0.2624, + "step": 27533 + }, + { + "epoch": 2.24, + "learning_rate": 5.042372881355932e-06, + "loss": 0.2718, + "step": 27534 + }, + { + "epoch": 2.24, + "learning_rate": 5.041829639287266e-06, + "loss": 0.1755, + "step": 27535 + }, + { + "epoch": 2.24, + "learning_rate": 5.0412863972186014e-06, + "loss": 0.3473, + "step": 27536 + }, + { + "epoch": 2.24, + "learning_rate": 5.040743155149936e-06, + "loss": 0.2858, + "step": 27537 + }, + { + "epoch": 2.24, + "learning_rate": 5.04019991308127e-06, + "loss": 0.2953, + "step": 27538 + }, + { + "epoch": 2.24, + "learning_rate": 5.039656671012604e-06, + "loss": 0.2631, + "step": 27539 + }, + { + "epoch": 2.24, + "learning_rate": 5.039113428943938e-06, + "loss": 0.091, + "step": 27540 + }, + { + "epoch": 2.24, + "learning_rate": 5.038570186875273e-06, + "loss": 0.1743, + "step": 27541 + }, + { + "epoch": 2.24, + "learning_rate": 5.038026944806607e-06, + "loss": 0.1399, + "step": 27542 + }, + { + "epoch": 2.24, + "learning_rate": 5.037483702737941e-06, + "loss": 0.1787, + "step": 27543 + }, + { + "epoch": 2.24, + "learning_rate": 5.036940460669275e-06, + "loss": 0.0961, + "step": 27544 + }, + { + "epoch": 2.24, + "learning_rate": 5.0363972186006095e-06, + "loss": 0.3348, + "step": 27545 + }, + { + "epoch": 2.24, + "learning_rate": 5.035853976531943e-06, + "loss": 0.1533, + "step": 27546 + }, + { + "epoch": 2.24, + "learning_rate": 5.035310734463277e-06, + "loss": 0.0797, + "step": 27547 + }, + { + "epoch": 2.24, + "learning_rate": 5.034767492394611e-06, + "loss": 0.2249, + "step": 27548 + }, + { + "epoch": 2.24, + "learning_rate": 5.034224250325946e-06, + "loss": 0.4613, + "step": 27549 + }, + { + "epoch": 2.24, + "learning_rate": 5.03368100825728e-06, + "loss": 0.2262, + "step": 27550 + }, + { + "epoch": 2.25, + "learning_rate": 5.033137766188614e-06, + "loss": 0.3291, + "step": 27551 + }, + { + "epoch": 2.25, + "learning_rate": 5.032594524119948e-06, + "loss": 0.0916, + "step": 27552 + }, + { + "epoch": 2.25, + "learning_rate": 5.0320512820512825e-06, + "loss": 0.0957, + "step": 27553 + }, + { + "epoch": 2.25, + "learning_rate": 5.031508039982617e-06, + "loss": 0.1713, + "step": 27554 + }, + { + "epoch": 2.25, + "learning_rate": 5.030964797913951e-06, + "loss": 0.3024, + "step": 27555 + }, + { + "epoch": 2.25, + "learning_rate": 5.030421555845285e-06, + "loss": 0.1449, + "step": 27556 + }, + { + "epoch": 2.25, + "learning_rate": 5.029878313776619e-06, + "loss": 0.2257, + "step": 27557 + }, + { + "epoch": 2.25, + "learning_rate": 5.029335071707954e-06, + "loss": 0.2498, + "step": 27558 + }, + { + "epoch": 2.25, + "learning_rate": 5.028791829639288e-06, + "loss": 0.1024, + "step": 27559 + }, + { + "epoch": 2.25, + "learning_rate": 5.028248587570622e-06, + "loss": 0.1476, + "step": 27560 + }, + { + "epoch": 2.25, + "learning_rate": 5.027705345501956e-06, + "loss": 0.1577, + "step": 27561 + }, + { + "epoch": 2.25, + "learning_rate": 5.0271621034332906e-06, + "loss": 0.2605, + "step": 27562 + }, + { + "epoch": 2.25, + "learning_rate": 5.026618861364625e-06, + "loss": 0.4233, + "step": 27563 + }, + { + "epoch": 2.25, + "learning_rate": 5.026075619295959e-06, + "loss": 0.1849, + "step": 27564 + }, + { + "epoch": 2.25, + "learning_rate": 5.025532377227292e-06, + "loss": 0.1565, + "step": 27565 + }, + { + "epoch": 2.25, + "learning_rate": 5.024989135158627e-06, + "loss": 0.2056, + "step": 27566 + }, + { + "epoch": 2.25, + "learning_rate": 5.024445893089961e-06, + "loss": 0.1171, + "step": 27567 + }, + { + "epoch": 2.25, + "learning_rate": 5.023902651021295e-06, + "loss": 0.1824, + "step": 27568 + }, + { + "epoch": 2.25, + "learning_rate": 5.023359408952629e-06, + "loss": 0.2723, + "step": 27569 + }, + { + "epoch": 2.25, + "learning_rate": 5.0228161668839636e-06, + "loss": 0.2429, + "step": 27570 + }, + { + "epoch": 2.25, + "learning_rate": 5.022272924815298e-06, + "loss": 0.154, + "step": 27571 + }, + { + "epoch": 2.25, + "learning_rate": 5.021729682746632e-06, + "loss": 0.0972, + "step": 27572 + }, + { + "epoch": 2.25, + "learning_rate": 5.021186440677966e-06, + "loss": 0.2415, + "step": 27573 + }, + { + "epoch": 2.25, + "learning_rate": 5.0206431986093005e-06, + "loss": 0.3328, + "step": 27574 + }, + { + "epoch": 2.25, + "learning_rate": 5.020099956540635e-06, + "loss": 0.0719, + "step": 27575 + }, + { + "epoch": 2.25, + "learning_rate": 5.019556714471969e-06, + "loss": 0.135, + "step": 27576 + }, + { + "epoch": 2.25, + "learning_rate": 5.019013472403303e-06, + "loss": 0.4153, + "step": 27577 + }, + { + "epoch": 2.25, + "learning_rate": 5.018470230334637e-06, + "loss": 0.4684, + "step": 27578 + }, + { + "epoch": 2.25, + "learning_rate": 5.017926988265972e-06, + "loss": 0.3856, + "step": 27579 + }, + { + "epoch": 2.25, + "learning_rate": 5.017383746197306e-06, + "loss": 0.2012, + "step": 27580 + }, + { + "epoch": 2.25, + "learning_rate": 5.016840504128641e-06, + "loss": 0.2896, + "step": 27581 + }, + { + "epoch": 2.25, + "learning_rate": 5.016297262059975e-06, + "loss": 0.1549, + "step": 27582 + }, + { + "epoch": 2.25, + "learning_rate": 5.015754019991309e-06, + "loss": 0.301, + "step": 27583 + }, + { + "epoch": 2.25, + "learning_rate": 5.015210777922642e-06, + "loss": 0.1986, + "step": 27584 + }, + { + "epoch": 2.25, + "learning_rate": 5.014667535853976e-06, + "loss": 0.0753, + "step": 27585 + }, + { + "epoch": 2.25, + "learning_rate": 5.01412429378531e-06, + "loss": 0.0449, + "step": 27586 + }, + { + "epoch": 2.25, + "learning_rate": 5.013581051716645e-06, + "loss": 0.1967, + "step": 27587 + }, + { + "epoch": 2.25, + "learning_rate": 5.013037809647979e-06, + "loss": 0.1551, + "step": 27588 + }, + { + "epoch": 2.25, + "learning_rate": 5.012494567579313e-06, + "loss": 0.2166, + "step": 27589 + }, + { + "epoch": 2.25, + "learning_rate": 5.011951325510648e-06, + "loss": 0.6724, + "step": 27590 + }, + { + "epoch": 2.25, + "learning_rate": 5.011408083441982e-06, + "loss": 0.1337, + "step": 27591 + }, + { + "epoch": 2.25, + "learning_rate": 5.010864841373317e-06, + "loss": 0.1488, + "step": 27592 + }, + { + "epoch": 2.25, + "learning_rate": 5.010321599304651e-06, + "loss": 0.1248, + "step": 27593 + }, + { + "epoch": 2.25, + "learning_rate": 5.009778357235985e-06, + "loss": 0.5441, + "step": 27594 + }, + { + "epoch": 2.25, + "learning_rate": 5.009235115167319e-06, + "loss": 0.1174, + "step": 27595 + }, + { + "epoch": 2.25, + "learning_rate": 5.0086918730986536e-06, + "loss": 0.1609, + "step": 27596 + }, + { + "epoch": 2.25, + "learning_rate": 5.008148631029988e-06, + "loss": 0.3971, + "step": 27597 + }, + { + "epoch": 2.25, + "learning_rate": 5.007605388961322e-06, + "loss": 0.2898, + "step": 27598 + }, + { + "epoch": 2.25, + "learning_rate": 5.007062146892656e-06, + "loss": 0.5051, + "step": 27599 + }, + { + "epoch": 2.25, + "learning_rate": 5.0065189048239905e-06, + "loss": 0.0275, + "step": 27600 + }, + { + "epoch": 2.25, + "learning_rate": 5.005975662755325e-06, + "loss": 0.0955, + "step": 27601 + }, + { + "epoch": 2.25, + "learning_rate": 5.005432420686659e-06, + "loss": 0.5245, + "step": 27602 + }, + { + "epoch": 2.25, + "learning_rate": 5.004889178617992e-06, + "loss": 0.2968, + "step": 27603 + }, + { + "epoch": 2.25, + "learning_rate": 5.0043459365493266e-06, + "loss": 0.0732, + "step": 27604 + }, + { + "epoch": 2.25, + "learning_rate": 5.003802694480661e-06, + "loss": 0.5505, + "step": 27605 + }, + { + "epoch": 2.25, + "learning_rate": 5.003259452411995e-06, + "loss": 0.1215, + "step": 27606 + }, + { + "epoch": 2.25, + "learning_rate": 5.002716210343329e-06, + "loss": 0.0681, + "step": 27607 + }, + { + "epoch": 2.25, + "learning_rate": 5.0021729682746635e-06, + "loss": 0.3665, + "step": 27608 + }, + { + "epoch": 2.25, + "learning_rate": 5.001629726205998e-06, + "loss": 0.0343, + "step": 27609 + }, + { + "epoch": 2.25, + "learning_rate": 5.001086484137332e-06, + "loss": 0.3287, + "step": 27610 + }, + { + "epoch": 2.25, + "learning_rate": 5.000543242068666e-06, + "loss": 0.1232, + "step": 27611 + }, + { + "epoch": 2.25, + "learning_rate": 5e-06, + "loss": 0.3786, + "step": 27612 + }, + { + "epoch": 2.25, + "learning_rate": 4.999456757931335e-06, + "loss": 0.293, + "step": 27613 + }, + { + "epoch": 2.25, + "learning_rate": 4.998913515862669e-06, + "loss": 0.3143, + "step": 27614 + }, + { + "epoch": 2.25, + "learning_rate": 4.998370273794003e-06, + "loss": 0.1136, + "step": 27615 + }, + { + "epoch": 2.25, + "learning_rate": 4.997827031725337e-06, + "loss": 0.1858, + "step": 27616 + }, + { + "epoch": 2.25, + "learning_rate": 4.9972837896566716e-06, + "loss": 0.2315, + "step": 27617 + }, + { + "epoch": 2.25, + "learning_rate": 4.996740547588006e-06, + "loss": 0.2943, + "step": 27618 + }, + { + "epoch": 2.25, + "learning_rate": 4.99619730551934e-06, + "loss": 0.4283, + "step": 27619 + }, + { + "epoch": 2.25, + "learning_rate": 4.995654063450674e-06, + "loss": 0.3148, + "step": 27620 + }, + { + "epoch": 2.25, + "learning_rate": 4.9951108213820085e-06, + "loss": 0.1323, + "step": 27621 + }, + { + "epoch": 2.25, + "learning_rate": 4.994567579313343e-06, + "loss": 0.3232, + "step": 27622 + }, + { + "epoch": 2.25, + "learning_rate": 4.994024337244677e-06, + "loss": 0.3263, + "step": 27623 + }, + { + "epoch": 2.25, + "learning_rate": 4.993481095176011e-06, + "loss": 0.3852, + "step": 27624 + }, + { + "epoch": 2.25, + "learning_rate": 4.992937853107345e-06, + "loss": 0.3661, + "step": 27625 + }, + { + "epoch": 2.25, + "learning_rate": 4.99239461103868e-06, + "loss": 0.2663, + "step": 27626 + }, + { + "epoch": 2.25, + "learning_rate": 4.991851368970013e-06, + "loss": 0.0904, + "step": 27627 + }, + { + "epoch": 2.25, + "learning_rate": 4.991308126901347e-06, + "loss": 0.1825, + "step": 27628 + }, + { + "epoch": 2.25, + "learning_rate": 4.9907648848326815e-06, + "loss": 0.3388, + "step": 27629 + }, + { + "epoch": 2.25, + "learning_rate": 4.990221642764016e-06, + "loss": 0.2017, + "step": 27630 + }, + { + "epoch": 2.25, + "learning_rate": 4.98967840069535e-06, + "loss": 0.0968, + "step": 27631 + }, + { + "epoch": 2.25, + "learning_rate": 4.989135158626684e-06, + "loss": 0.1623, + "step": 27632 + }, + { + "epoch": 2.25, + "learning_rate": 4.988591916558018e-06, + "loss": 0.2503, + "step": 27633 + }, + { + "epoch": 2.25, + "learning_rate": 4.988048674489353e-06, + "loss": 0.2705, + "step": 27634 + }, + { + "epoch": 2.25, + "learning_rate": 4.987505432420688e-06, + "loss": 0.1282, + "step": 27635 + }, + { + "epoch": 2.25, + "learning_rate": 4.986962190352021e-06, + "loss": 0.2442, + "step": 27636 + }, + { + "epoch": 2.25, + "learning_rate": 4.986418948283355e-06, + "loss": 0.2415, + "step": 27637 + }, + { + "epoch": 2.25, + "learning_rate": 4.9858757062146896e-06, + "loss": 0.4775, + "step": 27638 + }, + { + "epoch": 2.25, + "learning_rate": 4.985332464146024e-06, + "loss": 0.1009, + "step": 27639 + }, + { + "epoch": 2.25, + "learning_rate": 4.984789222077358e-06, + "loss": 0.1832, + "step": 27640 + }, + { + "epoch": 2.25, + "learning_rate": 4.984245980008692e-06, + "loss": 0.3541, + "step": 27641 + }, + { + "epoch": 2.25, + "learning_rate": 4.9837027379400265e-06, + "loss": 0.0745, + "step": 27642 + }, + { + "epoch": 2.25, + "learning_rate": 4.983159495871361e-06, + "loss": 0.1863, + "step": 27643 + }, + { + "epoch": 2.25, + "learning_rate": 4.982616253802695e-06, + "loss": 0.2757, + "step": 27644 + }, + { + "epoch": 2.25, + "learning_rate": 4.982073011734029e-06, + "loss": 0.0792, + "step": 27645 + }, + { + "epoch": 2.25, + "learning_rate": 4.981529769665363e-06, + "loss": 0.3306, + "step": 27646 + }, + { + "epoch": 2.25, + "learning_rate": 4.980986527596698e-06, + "loss": 0.1184, + "step": 27647 + }, + { + "epoch": 2.25, + "learning_rate": 4.980443285528032e-06, + "loss": 0.2212, + "step": 27648 + }, + { + "epoch": 2.25, + "learning_rate": 4.979900043459366e-06, + "loss": 0.3832, + "step": 27649 + }, + { + "epoch": 2.25, + "learning_rate": 4.9793568013907e-06, + "loss": 0.2073, + "step": 27650 + }, + { + "epoch": 2.25, + "learning_rate": 4.9788135593220346e-06, + "loss": 0.2117, + "step": 27651 + }, + { + "epoch": 2.25, + "learning_rate": 4.978270317253369e-06, + "loss": 0.3519, + "step": 27652 + }, + { + "epoch": 2.25, + "learning_rate": 4.977727075184703e-06, + "loss": 0.3548, + "step": 27653 + }, + { + "epoch": 2.25, + "learning_rate": 4.977183833116037e-06, + "loss": 0.3405, + "step": 27654 + }, + { + "epoch": 2.25, + "learning_rate": 4.976640591047371e-06, + "loss": 0.2382, + "step": 27655 + }, + { + "epoch": 2.25, + "learning_rate": 4.976097348978705e-06, + "loss": 0.0844, + "step": 27656 + }, + { + "epoch": 2.25, + "learning_rate": 4.975554106910039e-06, + "loss": 0.2148, + "step": 27657 + }, + { + "epoch": 2.25, + "learning_rate": 4.975010864841373e-06, + "loss": 0.1878, + "step": 27658 + }, + { + "epoch": 2.25, + "learning_rate": 4.9744676227727076e-06, + "loss": 0.2975, + "step": 27659 + }, + { + "epoch": 2.25, + "learning_rate": 4.973924380704042e-06, + "loss": 0.2597, + "step": 27660 + }, + { + "epoch": 2.25, + "learning_rate": 4.973381138635376e-06, + "loss": 0.5787, + "step": 27661 + }, + { + "epoch": 2.25, + "learning_rate": 4.972837896566711e-06, + "loss": 0.0837, + "step": 27662 + }, + { + "epoch": 2.25, + "learning_rate": 4.972294654498045e-06, + "loss": 0.1266, + "step": 27663 + }, + { + "epoch": 2.25, + "learning_rate": 4.9717514124293796e-06, + "loss": 0.4394, + "step": 27664 + }, + { + "epoch": 2.25, + "learning_rate": 4.971208170360713e-06, + "loss": 0.2236, + "step": 27665 + }, + { + "epoch": 2.25, + "learning_rate": 4.970664928292047e-06, + "loss": 0.4574, + "step": 27666 + }, + { + "epoch": 2.25, + "learning_rate": 4.970121686223381e-06, + "loss": 0.2565, + "step": 27667 + }, + { + "epoch": 2.25, + "learning_rate": 4.969578444154716e-06, + "loss": 0.1203, + "step": 27668 + }, + { + "epoch": 2.25, + "learning_rate": 4.96903520208605e-06, + "loss": 0.0819, + "step": 27669 + }, + { + "epoch": 2.25, + "learning_rate": 4.968491960017384e-06, + "loss": 0.3411, + "step": 27670 + }, + { + "epoch": 2.25, + "learning_rate": 4.967948717948718e-06, + "loss": 0.3094, + "step": 27671 + }, + { + "epoch": 2.25, + "learning_rate": 4.9674054758800525e-06, + "loss": 0.1655, + "step": 27672 + }, + { + "epoch": 2.25, + "learning_rate": 4.966862233811387e-06, + "loss": 0.1364, + "step": 27673 + }, + { + "epoch": 2.26, + "learning_rate": 4.966318991742721e-06, + "loss": 0.4296, + "step": 27674 + }, + { + "epoch": 2.26, + "learning_rate": 4.965775749674055e-06, + "loss": 0.1801, + "step": 27675 + }, + { + "epoch": 2.26, + "learning_rate": 4.9652325076053895e-06, + "loss": 0.194, + "step": 27676 + }, + { + "epoch": 2.26, + "learning_rate": 4.964689265536724e-06, + "loss": 0.0548, + "step": 27677 + }, + { + "epoch": 2.26, + "learning_rate": 4.964146023468058e-06, + "loss": 0.3254, + "step": 27678 + }, + { + "epoch": 2.26, + "learning_rate": 4.963602781399392e-06, + "loss": 0.1317, + "step": 27679 + }, + { + "epoch": 2.26, + "learning_rate": 4.963059539330726e-06, + "loss": 0.1395, + "step": 27680 + }, + { + "epoch": 2.26, + "learning_rate": 4.962516297262061e-06, + "loss": 0.2561, + "step": 27681 + }, + { + "epoch": 2.26, + "learning_rate": 4.961973055193395e-06, + "loss": 0.1152, + "step": 27682 + }, + { + "epoch": 2.26, + "learning_rate": 4.961429813124729e-06, + "loss": 0.206, + "step": 27683 + }, + { + "epoch": 2.26, + "learning_rate": 4.9608865710560625e-06, + "loss": 0.1479, + "step": 27684 + }, + { + "epoch": 2.26, + "learning_rate": 4.960343328987397e-06, + "loss": 0.2902, + "step": 27685 + }, + { + "epoch": 2.26, + "learning_rate": 4.959800086918731e-06, + "loss": 0.4935, + "step": 27686 + }, + { + "epoch": 2.26, + "learning_rate": 4.959256844850065e-06, + "loss": 0.2017, + "step": 27687 + }, + { + "epoch": 2.26, + "learning_rate": 4.958713602781399e-06, + "loss": 0.3296, + "step": 27688 + }, + { + "epoch": 2.26, + "learning_rate": 4.9581703607127345e-06, + "loss": 0.1043, + "step": 27689 + }, + { + "epoch": 2.26, + "learning_rate": 4.957627118644069e-06, + "loss": 0.1198, + "step": 27690 + }, + { + "epoch": 2.26, + "learning_rate": 4.957083876575403e-06, + "loss": 0.1925, + "step": 27691 + }, + { + "epoch": 2.26, + "learning_rate": 4.956540634506737e-06, + "loss": 0.2042, + "step": 27692 + }, + { + "epoch": 2.26, + "learning_rate": 4.9559973924380705e-06, + "loss": 0.2091, + "step": 27693 + }, + { + "epoch": 2.26, + "learning_rate": 4.955454150369405e-06, + "loss": 0.1922, + "step": 27694 + }, + { + "epoch": 2.26, + "learning_rate": 4.954910908300739e-06, + "loss": 0.1142, + "step": 27695 + }, + { + "epoch": 2.26, + "learning_rate": 4.954367666232073e-06, + "loss": 0.1507, + "step": 27696 + }, + { + "epoch": 2.26, + "learning_rate": 4.9538244241634075e-06, + "loss": 0.3301, + "step": 27697 + }, + { + "epoch": 2.26, + "learning_rate": 4.953281182094742e-06, + "loss": 0.2492, + "step": 27698 + }, + { + "epoch": 2.26, + "learning_rate": 4.952737940026076e-06, + "loss": 0.1971, + "step": 27699 + }, + { + "epoch": 2.26, + "learning_rate": 4.95219469795741e-06, + "loss": 0.242, + "step": 27700 + }, + { + "epoch": 2.26, + "learning_rate": 4.951651455888744e-06, + "loss": 0.18, + "step": 27701 + }, + { + "epoch": 2.26, + "learning_rate": 4.951108213820079e-06, + "loss": 0.0732, + "step": 27702 + }, + { + "epoch": 2.26, + "learning_rate": 4.950564971751413e-06, + "loss": 0.2416, + "step": 27703 + }, + { + "epoch": 2.26, + "learning_rate": 4.950021729682747e-06, + "loss": 0.1894, + "step": 27704 + }, + { + "epoch": 2.26, + "learning_rate": 4.949478487614081e-06, + "loss": 0.1656, + "step": 27705 + }, + { + "epoch": 2.26, + "learning_rate": 4.9489352455454155e-06, + "loss": 0.2306, + "step": 27706 + }, + { + "epoch": 2.26, + "learning_rate": 4.94839200347675e-06, + "loss": 0.2343, + "step": 27707 + }, + { + "epoch": 2.26, + "learning_rate": 4.947848761408084e-06, + "loss": 0.3336, + "step": 27708 + }, + { + "epoch": 2.26, + "learning_rate": 4.947305519339418e-06, + "loss": 0.1985, + "step": 27709 + }, + { + "epoch": 2.26, + "learning_rate": 4.9467622772707525e-06, + "loss": 0.0919, + "step": 27710 + }, + { + "epoch": 2.26, + "learning_rate": 4.946219035202087e-06, + "loss": 0.2441, + "step": 27711 + }, + { + "epoch": 2.26, + "learning_rate": 4.94567579313342e-06, + "loss": 0.1721, + "step": 27712 + }, + { + "epoch": 2.26, + "learning_rate": 4.945132551064754e-06, + "loss": 0.0507, + "step": 27713 + }, + { + "epoch": 2.26, + "learning_rate": 4.9445893089960885e-06, + "loss": 0.1963, + "step": 27714 + }, + { + "epoch": 2.26, + "learning_rate": 4.944046066927423e-06, + "loss": 0.2355, + "step": 27715 + }, + { + "epoch": 2.26, + "learning_rate": 4.943502824858758e-06, + "loss": 0.3, + "step": 27716 + }, + { + "epoch": 2.26, + "learning_rate": 4.942959582790092e-06, + "loss": 0.2396, + "step": 27717 + }, + { + "epoch": 2.26, + "learning_rate": 4.942416340721426e-06, + "loss": 0.3669, + "step": 27718 + }, + { + "epoch": 2.26, + "learning_rate": 4.9418730986527605e-06, + "loss": 0.239, + "step": 27719 + }, + { + "epoch": 2.26, + "learning_rate": 4.941329856584095e-06, + "loss": 0.2143, + "step": 27720 + }, + { + "epoch": 2.26, + "learning_rate": 4.940786614515429e-06, + "loss": 0.1628, + "step": 27721 + }, + { + "epoch": 2.26, + "learning_rate": 4.940243372446762e-06, + "loss": 0.2242, + "step": 27722 + }, + { + "epoch": 2.26, + "learning_rate": 4.939700130378097e-06, + "loss": 0.1572, + "step": 27723 + }, + { + "epoch": 2.26, + "learning_rate": 4.939156888309431e-06, + "loss": 0.2219, + "step": 27724 + }, + { + "epoch": 2.26, + "learning_rate": 4.938613646240765e-06, + "loss": 0.3491, + "step": 27725 + }, + { + "epoch": 2.26, + "learning_rate": 4.938070404172099e-06, + "loss": 0.0893, + "step": 27726 + }, + { + "epoch": 2.26, + "learning_rate": 4.9375271621034335e-06, + "loss": 0.2387, + "step": 27727 + }, + { + "epoch": 2.26, + "learning_rate": 4.936983920034768e-06, + "loss": 0.0911, + "step": 27728 + }, + { + "epoch": 2.26, + "learning_rate": 4.936440677966102e-06, + "loss": 0.2394, + "step": 27729 + }, + { + "epoch": 2.26, + "learning_rate": 4.935897435897436e-06, + "loss": 0.1632, + "step": 27730 + }, + { + "epoch": 2.26, + "learning_rate": 4.9353541938287705e-06, + "loss": 0.1824, + "step": 27731 + }, + { + "epoch": 2.26, + "learning_rate": 4.934810951760105e-06, + "loss": 0.384, + "step": 27732 + }, + { + "epoch": 2.26, + "learning_rate": 4.934267709691439e-06, + "loss": 0.1009, + "step": 27733 + }, + { + "epoch": 2.26, + "learning_rate": 4.933724467622773e-06, + "loss": 0.058, + "step": 27734 + }, + { + "epoch": 2.26, + "learning_rate": 4.933181225554107e-06, + "loss": 0.1247, + "step": 27735 + }, + { + "epoch": 2.26, + "learning_rate": 4.932637983485442e-06, + "loss": 0.0675, + "step": 27736 + }, + { + "epoch": 2.26, + "learning_rate": 4.932094741416776e-06, + "loss": 0.1458, + "step": 27737 + }, + { + "epoch": 2.26, + "learning_rate": 4.93155149934811e-06, + "loss": 0.1523, + "step": 27738 + }, + { + "epoch": 2.26, + "learning_rate": 4.931008257279444e-06, + "loss": 0.1094, + "step": 27739 + }, + { + "epoch": 2.26, + "learning_rate": 4.9304650152107785e-06, + "loss": 0.1071, + "step": 27740 + }, + { + "epoch": 2.26, + "learning_rate": 4.929921773142112e-06, + "loss": 0.1209, + "step": 27741 + }, + { + "epoch": 2.26, + "learning_rate": 4.929378531073446e-06, + "loss": 0.0893, + "step": 27742 + }, + { + "epoch": 2.26, + "learning_rate": 4.928835289004781e-06, + "loss": 0.2261, + "step": 27743 + }, + { + "epoch": 2.26, + "learning_rate": 4.9282920469361155e-06, + "loss": 0.2621, + "step": 27744 + }, + { + "epoch": 2.26, + "learning_rate": 4.92774880486745e-06, + "loss": 0.0625, + "step": 27745 + }, + { + "epoch": 2.26, + "learning_rate": 4.927205562798784e-06, + "loss": 0.2146, + "step": 27746 + }, + { + "epoch": 2.26, + "learning_rate": 4.926662320730118e-06, + "loss": 0.1948, + "step": 27747 + }, + { + "epoch": 2.26, + "learning_rate": 4.926119078661452e-06, + "loss": 0.1901, + "step": 27748 + }, + { + "epoch": 2.26, + "learning_rate": 4.925575836592787e-06, + "loss": 0.3441, + "step": 27749 + }, + { + "epoch": 2.26, + "learning_rate": 4.92503259452412e-06, + "loss": 0.2746, + "step": 27750 + }, + { + "epoch": 2.26, + "eval_accuracy": 0.8441161487519103, + "eval_loss": 0.4992291033267975, + "eval_runtime": 22.2266, + "eval_samples_per_second": 441.588, + "eval_steps_per_second": 3.464, + "step": 27750 + }, + { + "epoch": 2.26, + "learning_rate": 4.924489352455454e-06, + "loss": 0.3387, + "step": 27751 + }, + { + "epoch": 2.26, + "learning_rate": 4.9239461103867885e-06, + "loss": 0.1973, + "step": 27752 + }, + { + "epoch": 2.26, + "learning_rate": 4.923402868318123e-06, + "loss": 0.258, + "step": 27753 + }, + { + "epoch": 2.26, + "learning_rate": 4.922859626249457e-06, + "loss": 0.3251, + "step": 27754 + }, + { + "epoch": 2.26, + "learning_rate": 4.922316384180791e-06, + "loss": 0.2028, + "step": 27755 + }, + { + "epoch": 2.26, + "learning_rate": 4.921773142112125e-06, + "loss": 0.1729, + "step": 27756 + }, + { + "epoch": 2.26, + "learning_rate": 4.92122990004346e-06, + "loss": 0.0931, + "step": 27757 + }, + { + "epoch": 2.26, + "learning_rate": 4.920686657974794e-06, + "loss": 0.0975, + "step": 27758 + }, + { + "epoch": 2.26, + "learning_rate": 4.920143415906128e-06, + "loss": 0.1068, + "step": 27759 + }, + { + "epoch": 2.26, + "learning_rate": 4.919600173837462e-06, + "loss": 0.2121, + "step": 27760 + }, + { + "epoch": 2.26, + "learning_rate": 4.9190569317687965e-06, + "loss": 0.1601, + "step": 27761 + }, + { + "epoch": 2.26, + "learning_rate": 4.918513689700131e-06, + "loss": 0.1249, + "step": 27762 + }, + { + "epoch": 2.26, + "learning_rate": 4.917970447631465e-06, + "loss": 0.3093, + "step": 27763 + }, + { + "epoch": 2.26, + "learning_rate": 4.917427205562799e-06, + "loss": 0.4138, + "step": 27764 + }, + { + "epoch": 2.26, + "learning_rate": 4.9168839634941334e-06, + "loss": 0.2674, + "step": 27765 + }, + { + "epoch": 2.26, + "learning_rate": 4.916340721425468e-06, + "loss": 0.167, + "step": 27766 + }, + { + "epoch": 2.26, + "learning_rate": 4.915797479356802e-06, + "loss": 0.0847, + "step": 27767 + }, + { + "epoch": 2.26, + "learning_rate": 4.915254237288136e-06, + "loss": 0.3132, + "step": 27768 + }, + { + "epoch": 2.26, + "learning_rate": 4.9147109952194695e-06, + "loss": 0.1476, + "step": 27769 + }, + { + "epoch": 2.26, + "learning_rate": 4.914167753150805e-06, + "loss": 0.4837, + "step": 27770 + }, + { + "epoch": 2.26, + "learning_rate": 4.913624511082139e-06, + "loss": 0.2732, + "step": 27771 + }, + { + "epoch": 2.26, + "learning_rate": 4.913081269013473e-06, + "loss": 0.179, + "step": 27772 + }, + { + "epoch": 2.26, + "learning_rate": 4.912538026944807e-06, + "loss": 0.1048, + "step": 27773 + }, + { + "epoch": 2.26, + "learning_rate": 4.9119947848761415e-06, + "loss": 0.1866, + "step": 27774 + }, + { + "epoch": 2.26, + "learning_rate": 4.911451542807476e-06, + "loss": 0.5091, + "step": 27775 + }, + { + "epoch": 2.26, + "learning_rate": 4.91090830073881e-06, + "loss": 0.3692, + "step": 27776 + }, + { + "epoch": 2.26, + "learning_rate": 4.910365058670144e-06, + "loss": 0.4607, + "step": 27777 + }, + { + "epoch": 2.26, + "learning_rate": 4.9098218166014784e-06, + "loss": 0.0312, + "step": 27778 + }, + { + "epoch": 2.26, + "learning_rate": 4.909278574532812e-06, + "loss": 0.2517, + "step": 27779 + }, + { + "epoch": 2.26, + "learning_rate": 4.908735332464146e-06, + "loss": 0.3881, + "step": 27780 + }, + { + "epoch": 2.26, + "learning_rate": 4.90819209039548e-06, + "loss": 0.126, + "step": 27781 + }, + { + "epoch": 2.26, + "learning_rate": 4.9076488483268145e-06, + "loss": 0.2507, + "step": 27782 + }, + { + "epoch": 2.26, + "learning_rate": 4.907105606258149e-06, + "loss": 0.5995, + "step": 27783 + }, + { + "epoch": 2.26, + "learning_rate": 4.906562364189483e-06, + "loss": 0.1745, + "step": 27784 + }, + { + "epoch": 2.26, + "learning_rate": 4.906019122120817e-06, + "loss": 0.4427, + "step": 27785 + }, + { + "epoch": 2.26, + "learning_rate": 4.9054758800521514e-06, + "loss": 0.3164, + "step": 27786 + }, + { + "epoch": 2.26, + "learning_rate": 4.904932637983486e-06, + "loss": 0.3785, + "step": 27787 + }, + { + "epoch": 2.26, + "learning_rate": 4.90438939591482e-06, + "loss": 0.4286, + "step": 27788 + }, + { + "epoch": 2.26, + "learning_rate": 4.903846153846154e-06, + "loss": 0.1358, + "step": 27789 + }, + { + "epoch": 2.26, + "learning_rate": 4.903302911777488e-06, + "loss": 0.2351, + "step": 27790 + }, + { + "epoch": 2.26, + "learning_rate": 4.902759669708823e-06, + "loss": 0.4202, + "step": 27791 + }, + { + "epoch": 2.26, + "learning_rate": 4.902216427640157e-06, + "loss": 0.2656, + "step": 27792 + }, + { + "epoch": 2.26, + "learning_rate": 4.901673185571491e-06, + "loss": 0.2181, + "step": 27793 + }, + { + "epoch": 2.26, + "learning_rate": 4.901129943502825e-06, + "loss": 0.4594, + "step": 27794 + }, + { + "epoch": 2.26, + "learning_rate": 4.9005867014341595e-06, + "loss": 0.2746, + "step": 27795 + }, + { + "epoch": 2.26, + "learning_rate": 4.900043459365494e-06, + "loss": 0.2262, + "step": 27796 + }, + { + "epoch": 2.27, + "learning_rate": 4.899500217296828e-06, + "loss": 0.3258, + "step": 27797 + }, + { + "epoch": 2.27, + "learning_rate": 4.898956975228162e-06, + "loss": 0.2906, + "step": 27798 + }, + { + "epoch": 2.27, + "learning_rate": 4.8984137331594964e-06, + "loss": 0.107, + "step": 27799 + }, + { + "epoch": 2.27, + "learning_rate": 4.897870491090831e-06, + "loss": 0.1063, + "step": 27800 + }, + { + "epoch": 2.27, + "learning_rate": 4.897327249022165e-06, + "loss": 0.1361, + "step": 27801 + }, + { + "epoch": 2.27, + "learning_rate": 4.896784006953499e-06, + "loss": 0.2318, + "step": 27802 + }, + { + "epoch": 2.27, + "learning_rate": 4.896240764884833e-06, + "loss": 0.1986, + "step": 27803 + }, + { + "epoch": 2.27, + "learning_rate": 4.895697522816168e-06, + "loss": 0.2832, + "step": 27804 + }, + { + "epoch": 2.27, + "learning_rate": 4.895154280747502e-06, + "loss": 0.2969, + "step": 27805 + }, + { + "epoch": 2.27, + "learning_rate": 4.894611038678836e-06, + "loss": 0.4258, + "step": 27806 + }, + { + "epoch": 2.27, + "learning_rate": 4.8940677966101694e-06, + "loss": 0.3208, + "step": 27807 + }, + { + "epoch": 2.27, + "learning_rate": 4.893524554541504e-06, + "loss": 0.3507, + "step": 27808 + }, + { + "epoch": 2.27, + "learning_rate": 4.892981312472838e-06, + "loss": 0.2464, + "step": 27809 + }, + { + "epoch": 2.27, + "learning_rate": 4.892438070404172e-06, + "loss": 0.119, + "step": 27810 + }, + { + "epoch": 2.27, + "learning_rate": 4.891894828335506e-06, + "loss": 0.2513, + "step": 27811 + }, + { + "epoch": 2.27, + "learning_rate": 4.891351586266841e-06, + "loss": 0.3465, + "step": 27812 + }, + { + "epoch": 2.27, + "learning_rate": 4.890808344198175e-06, + "loss": 0.1946, + "step": 27813 + }, + { + "epoch": 2.27, + "learning_rate": 4.890265102129509e-06, + "loss": 0.2635, + "step": 27814 + }, + { + "epoch": 2.27, + "learning_rate": 4.889721860060844e-06, + "loss": 0.3633, + "step": 27815 + }, + { + "epoch": 2.27, + "learning_rate": 4.889178617992178e-06, + "loss": 0.2439, + "step": 27816 + }, + { + "epoch": 2.27, + "learning_rate": 4.888635375923512e-06, + "loss": 0.0931, + "step": 27817 + }, + { + "epoch": 2.27, + "learning_rate": 4.888092133854846e-06, + "loss": 0.124, + "step": 27818 + }, + { + "epoch": 2.27, + "learning_rate": 4.88754889178618e-06, + "loss": 0.0275, + "step": 27819 + }, + { + "epoch": 2.27, + "learning_rate": 4.8870056497175144e-06, + "loss": 0.4786, + "step": 27820 + }, + { + "epoch": 2.27, + "learning_rate": 4.886462407648849e-06, + "loss": 0.1187, + "step": 27821 + }, + { + "epoch": 2.27, + "learning_rate": 4.885919165580183e-06, + "loss": 0.2529, + "step": 27822 + }, + { + "epoch": 2.27, + "learning_rate": 4.885375923511517e-06, + "loss": 0.1575, + "step": 27823 + }, + { + "epoch": 2.27, + "learning_rate": 4.884832681442851e-06, + "loss": 0.2967, + "step": 27824 + }, + { + "epoch": 2.27, + "learning_rate": 4.884289439374186e-06, + "loss": 0.2519, + "step": 27825 + }, + { + "epoch": 2.27, + "learning_rate": 4.88374619730552e-06, + "loss": 0.2852, + "step": 27826 + }, + { + "epoch": 2.27, + "learning_rate": 4.883202955236854e-06, + "loss": 0.1256, + "step": 27827 + }, + { + "epoch": 2.27, + "learning_rate": 4.882659713168188e-06, + "loss": 0.3918, + "step": 27828 + }, + { + "epoch": 2.27, + "learning_rate": 4.8821164710995225e-06, + "loss": 0.3042, + "step": 27829 + }, + { + "epoch": 2.27, + "learning_rate": 4.881573229030857e-06, + "loss": 0.2353, + "step": 27830 + }, + { + "epoch": 2.27, + "learning_rate": 4.881029986962191e-06, + "loss": 0.1165, + "step": 27831 + }, + { + "epoch": 2.27, + "learning_rate": 4.880486744893525e-06, + "loss": 0.344, + "step": 27832 + }, + { + "epoch": 2.27, + "learning_rate": 4.8799435028248594e-06, + "loss": 0.1131, + "step": 27833 + }, + { + "epoch": 2.27, + "learning_rate": 4.879400260756194e-06, + "loss": 0.3425, + "step": 27834 + }, + { + "epoch": 2.27, + "learning_rate": 4.878857018687528e-06, + "loss": 0.0747, + "step": 27835 + }, + { + "epoch": 2.27, + "learning_rate": 4.878313776618861e-06, + "loss": 0.2316, + "step": 27836 + }, + { + "epoch": 2.27, + "learning_rate": 4.8777705345501955e-06, + "loss": 0.205, + "step": 27837 + }, + { + "epoch": 2.27, + "learning_rate": 4.87722729248153e-06, + "loss": 0.1577, + "step": 27838 + }, + { + "epoch": 2.27, + "learning_rate": 4.876684050412864e-06, + "loss": 0.2642, + "step": 27839 + }, + { + "epoch": 2.27, + "learning_rate": 4.876140808344198e-06, + "loss": 0.192, + "step": 27840 + }, + { + "epoch": 2.27, + "learning_rate": 4.8755975662755324e-06, + "loss": 0.1815, + "step": 27841 + }, + { + "epoch": 2.27, + "learning_rate": 4.8750543242068675e-06, + "loss": 0.1141, + "step": 27842 + }, + { + "epoch": 2.27, + "learning_rate": 4.874511082138202e-06, + "loss": 0.4432, + "step": 27843 + }, + { + "epoch": 2.27, + "learning_rate": 4.873967840069536e-06, + "loss": 0.1954, + "step": 27844 + }, + { + "epoch": 2.27, + "learning_rate": 4.873424598000869e-06, + "loss": 0.3861, + "step": 27845 + }, + { + "epoch": 2.27, + "learning_rate": 4.872881355932204e-06, + "loss": 0.2473, + "step": 27846 + }, + { + "epoch": 2.27, + "learning_rate": 4.872338113863538e-06, + "loss": 0.1237, + "step": 27847 + }, + { + "epoch": 2.27, + "learning_rate": 4.871794871794872e-06, + "loss": 0.0513, + "step": 27848 + }, + { + "epoch": 2.27, + "learning_rate": 4.871251629726206e-06, + "loss": 0.1783, + "step": 27849 + }, + { + "epoch": 2.27, + "learning_rate": 4.8707083876575405e-06, + "loss": 0.3474, + "step": 27850 + }, + { + "epoch": 2.27, + "learning_rate": 4.870165145588875e-06, + "loss": 0.1494, + "step": 27851 + }, + { + "epoch": 2.27, + "learning_rate": 4.869621903520209e-06, + "loss": 0.1747, + "step": 27852 + }, + { + "epoch": 2.27, + "learning_rate": 4.869078661451543e-06, + "loss": 0.1903, + "step": 27853 + }, + { + "epoch": 2.27, + "learning_rate": 4.8685354193828774e-06, + "loss": 0.1463, + "step": 27854 + }, + { + "epoch": 2.27, + "learning_rate": 4.867992177314212e-06, + "loss": 0.153, + "step": 27855 + }, + { + "epoch": 2.27, + "learning_rate": 4.867448935245546e-06, + "loss": 0.1607, + "step": 27856 + }, + { + "epoch": 2.27, + "learning_rate": 4.86690569317688e-06, + "loss": 0.2383, + "step": 27857 + }, + { + "epoch": 2.27, + "learning_rate": 4.866362451108214e-06, + "loss": 0.2533, + "step": 27858 + }, + { + "epoch": 2.27, + "learning_rate": 4.865819209039549e-06, + "loss": 0.0848, + "step": 27859 + }, + { + "epoch": 2.27, + "learning_rate": 4.865275966970883e-06, + "loss": 0.2951, + "step": 27860 + }, + { + "epoch": 2.27, + "learning_rate": 4.864732724902217e-06, + "loss": 0.3159, + "step": 27861 + }, + { + "epoch": 2.27, + "learning_rate": 4.864189482833551e-06, + "loss": 0.1104, + "step": 27862 + }, + { + "epoch": 2.27, + "learning_rate": 4.8636462407648855e-06, + "loss": 0.1534, + "step": 27863 + }, + { + "epoch": 2.27, + "learning_rate": 4.863102998696219e-06, + "loss": 0.1716, + "step": 27864 + }, + { + "epoch": 2.27, + "learning_rate": 4.862559756627553e-06, + "loss": 0.3811, + "step": 27865 + }, + { + "epoch": 2.27, + "learning_rate": 4.862016514558887e-06, + "loss": 0.4287, + "step": 27866 + }, + { + "epoch": 2.27, + "learning_rate": 4.8614732724902216e-06, + "loss": 0.1484, + "step": 27867 + }, + { + "epoch": 2.27, + "learning_rate": 4.860930030421556e-06, + "loss": 0.2044, + "step": 27868 + }, + { + "epoch": 2.27, + "learning_rate": 4.860386788352891e-06, + "loss": 0.1666, + "step": 27869 + }, + { + "epoch": 2.27, + "learning_rate": 4.859843546284225e-06, + "loss": 0.2265, + "step": 27870 + }, + { + "epoch": 2.27, + "learning_rate": 4.859300304215559e-06, + "loss": 0.1051, + "step": 27871 + }, + { + "epoch": 2.27, + "learning_rate": 4.8587570621468936e-06, + "loss": 0.3176, + "step": 27872 + }, + { + "epoch": 2.27, + "learning_rate": 4.858213820078228e-06, + "loss": 0.0432, + "step": 27873 + }, + { + "epoch": 2.27, + "learning_rate": 4.857670578009561e-06, + "loss": 0.056, + "step": 27874 + }, + { + "epoch": 2.27, + "learning_rate": 4.857127335940895e-06, + "loss": 0.2928, + "step": 27875 + }, + { + "epoch": 2.27, + "learning_rate": 4.85658409387223e-06, + "loss": 0.3899, + "step": 27876 + }, + { + "epoch": 2.27, + "learning_rate": 4.856040851803564e-06, + "loss": 0.1322, + "step": 27877 + }, + { + "epoch": 2.27, + "learning_rate": 4.855497609734898e-06, + "loss": 0.1458, + "step": 27878 + }, + { + "epoch": 2.27, + "learning_rate": 4.854954367666232e-06, + "loss": 0.2198, + "step": 27879 + }, + { + "epoch": 2.27, + "learning_rate": 4.8544111255975666e-06, + "loss": 0.0623, + "step": 27880 + }, + { + "epoch": 2.27, + "learning_rate": 4.853867883528901e-06, + "loss": 0.3294, + "step": 27881 + }, + { + "epoch": 2.27, + "learning_rate": 4.853324641460235e-06, + "loss": 0.2394, + "step": 27882 + }, + { + "epoch": 2.27, + "learning_rate": 4.852781399391569e-06, + "loss": 0.2996, + "step": 27883 + }, + { + "epoch": 2.27, + "learning_rate": 4.8522381573229035e-06, + "loss": 0.3506, + "step": 27884 + }, + { + "epoch": 2.27, + "learning_rate": 4.851694915254238e-06, + "loss": 0.4548, + "step": 27885 + }, + { + "epoch": 2.27, + "learning_rate": 4.851151673185572e-06, + "loss": 0.1655, + "step": 27886 + }, + { + "epoch": 2.27, + "learning_rate": 4.850608431116906e-06, + "loss": 0.211, + "step": 27887 + }, + { + "epoch": 2.27, + "learning_rate": 4.85006518904824e-06, + "loss": 0.1916, + "step": 27888 + }, + { + "epoch": 2.27, + "learning_rate": 4.849521946979575e-06, + "loss": 0.2494, + "step": 27889 + }, + { + "epoch": 2.27, + "learning_rate": 4.848978704910909e-06, + "loss": 0.2789, + "step": 27890 + }, + { + "epoch": 2.27, + "learning_rate": 4.848435462842243e-06, + "loss": 0.0772, + "step": 27891 + }, + { + "epoch": 2.27, + "learning_rate": 4.847892220773577e-06, + "loss": 0.1202, + "step": 27892 + }, + { + "epoch": 2.27, + "learning_rate": 4.847348978704911e-06, + "loss": 0.3247, + "step": 27893 + }, + { + "epoch": 2.27, + "learning_rate": 4.846805736636245e-06, + "loss": 0.0547, + "step": 27894 + }, + { + "epoch": 2.27, + "learning_rate": 4.846262494567579e-06, + "loss": 0.1881, + "step": 27895 + }, + { + "epoch": 2.27, + "learning_rate": 4.845719252498914e-06, + "loss": 0.2234, + "step": 27896 + }, + { + "epoch": 2.27, + "learning_rate": 4.8451760104302485e-06, + "loss": 0.1863, + "step": 27897 + }, + { + "epoch": 2.27, + "learning_rate": 4.844632768361583e-06, + "loss": 0.1793, + "step": 27898 + }, + { + "epoch": 2.27, + "learning_rate": 4.844089526292917e-06, + "loss": 0.3082, + "step": 27899 + }, + { + "epoch": 2.27, + "learning_rate": 4.843546284224251e-06, + "loss": 0.3376, + "step": 27900 + }, + { + "epoch": 2.27, + "learning_rate": 4.843003042155585e-06, + "loss": 0.242, + "step": 27901 + }, + { + "epoch": 2.27, + "learning_rate": 4.84245980008692e-06, + "loss": 0.249, + "step": 27902 + }, + { + "epoch": 2.27, + "learning_rate": 4.841916558018253e-06, + "loss": 0.1027, + "step": 27903 + }, + { + "epoch": 2.27, + "learning_rate": 4.841373315949587e-06, + "loss": 0.2531, + "step": 27904 + }, + { + "epoch": 2.27, + "learning_rate": 4.8408300738809215e-06, + "loss": 0.0598, + "step": 27905 + }, + { + "epoch": 2.27, + "learning_rate": 4.840286831812256e-06, + "loss": 0.1521, + "step": 27906 + }, + { + "epoch": 2.27, + "learning_rate": 4.83974358974359e-06, + "loss": 0.1963, + "step": 27907 + }, + { + "epoch": 2.27, + "learning_rate": 4.839200347674924e-06, + "loss": 0.144, + "step": 27908 + }, + { + "epoch": 2.27, + "learning_rate": 4.838657105606258e-06, + "loss": 0.0885, + "step": 27909 + }, + { + "epoch": 2.27, + "learning_rate": 4.838113863537593e-06, + "loss": 0.0565, + "step": 27910 + }, + { + "epoch": 2.27, + "learning_rate": 4.837570621468927e-06, + "loss": 0.1861, + "step": 27911 + }, + { + "epoch": 2.27, + "learning_rate": 4.837027379400261e-06, + "loss": 0.1366, + "step": 27912 + }, + { + "epoch": 2.27, + "learning_rate": 4.836484137331595e-06, + "loss": 0.1678, + "step": 27913 + }, + { + "epoch": 2.27, + "learning_rate": 4.8359408952629296e-06, + "loss": 0.1339, + "step": 27914 + }, + { + "epoch": 2.27, + "learning_rate": 4.835397653194264e-06, + "loss": 0.2149, + "step": 27915 + }, + { + "epoch": 2.27, + "learning_rate": 4.834854411125598e-06, + "loss": 0.4308, + "step": 27916 + }, + { + "epoch": 2.27, + "learning_rate": 4.834311169056932e-06, + "loss": 0.1937, + "step": 27917 + }, + { + "epoch": 2.27, + "learning_rate": 4.8337679269882665e-06, + "loss": 0.23, + "step": 27918 + }, + { + "epoch": 2.28, + "learning_rate": 4.833224684919601e-06, + "loss": 0.3135, + "step": 27919 + }, + { + "epoch": 2.28, + "learning_rate": 4.832681442850935e-06, + "loss": 0.4214, + "step": 27920 + }, + { + "epoch": 2.28, + "learning_rate": 4.832138200782269e-06, + "loss": 0.1788, + "step": 27921 + }, + { + "epoch": 2.28, + "learning_rate": 4.8315949587136026e-06, + "loss": 0.2567, + "step": 27922 + }, + { + "epoch": 2.28, + "learning_rate": 4.831051716644938e-06, + "loss": 0.2383, + "step": 27923 + }, + { + "epoch": 2.28, + "learning_rate": 4.830508474576272e-06, + "loss": 0.615, + "step": 27924 + }, + { + "epoch": 2.28, + "learning_rate": 4.829965232507606e-06, + "loss": 0.0245, + "step": 27925 + }, + { + "epoch": 2.28, + "learning_rate": 4.82942199043894e-06, + "loss": 0.2512, + "step": 27926 + }, + { + "epoch": 2.28, + "learning_rate": 4.8288787483702746e-06, + "loss": 0.1252, + "step": 27927 + }, + { + "epoch": 2.28, + "learning_rate": 4.828335506301609e-06, + "loss": 0.2471, + "step": 27928 + }, + { + "epoch": 2.28, + "learning_rate": 4.827792264232943e-06, + "loss": 0.2256, + "step": 27929 + }, + { + "epoch": 2.28, + "learning_rate": 4.827249022164277e-06, + "loss": 0.111, + "step": 27930 + }, + { + "epoch": 2.28, + "learning_rate": 4.826705780095611e-06, + "loss": 0.158, + "step": 27931 + }, + { + "epoch": 2.28, + "learning_rate": 4.826162538026945e-06, + "loss": 0.4885, + "step": 27932 + }, + { + "epoch": 2.28, + "learning_rate": 4.825619295958279e-06, + "loss": 0.2921, + "step": 27933 + }, + { + "epoch": 2.28, + "learning_rate": 4.825076053889613e-06, + "loss": 0.1474, + "step": 27934 + }, + { + "epoch": 2.28, + "learning_rate": 4.8245328118209476e-06, + "loss": 0.1122, + "step": 27935 + }, + { + "epoch": 2.28, + "learning_rate": 4.823989569752282e-06, + "loss": 0.1835, + "step": 27936 + }, + { + "epoch": 2.28, + "learning_rate": 4.823446327683616e-06, + "loss": 0.401, + "step": 27937 + }, + { + "epoch": 2.28, + "learning_rate": 4.82290308561495e-06, + "loss": 0.2768, + "step": 27938 + }, + { + "epoch": 2.28, + "learning_rate": 4.8223598435462845e-06, + "loss": 0.0678, + "step": 27939 + }, + { + "epoch": 2.28, + "learning_rate": 4.821816601477619e-06, + "loss": 0.18, + "step": 27940 + }, + { + "epoch": 2.28, + "learning_rate": 4.821273359408953e-06, + "loss": 0.1869, + "step": 27941 + }, + { + "epoch": 2.28, + "learning_rate": 4.820730117340287e-06, + "loss": 0.1302, + "step": 27942 + }, + { + "epoch": 2.28, + "learning_rate": 4.820186875271621e-06, + "loss": 0.1035, + "step": 27943 + }, + { + "epoch": 2.28, + "learning_rate": 4.819643633202956e-06, + "loss": 0.2498, + "step": 27944 + }, + { + "epoch": 2.28, + "learning_rate": 4.81910039113429e-06, + "loss": 0.0603, + "step": 27945 + }, + { + "epoch": 2.28, + "learning_rate": 4.818557149065624e-06, + "loss": 0.1097, + "step": 27946 + }, + { + "epoch": 2.28, + "learning_rate": 4.818013906996958e-06, + "loss": 0.1838, + "step": 27947 + }, + { + "epoch": 2.28, + "learning_rate": 4.8174706649282926e-06, + "loss": 0.203, + "step": 27948 + }, + { + "epoch": 2.28, + "learning_rate": 4.816927422859627e-06, + "loss": 0.3229, + "step": 27949 + }, + { + "epoch": 2.28, + "learning_rate": 4.816384180790961e-06, + "loss": 0.2202, + "step": 27950 + }, + { + "epoch": 2.28, + "learning_rate": 4.815840938722295e-06, + "loss": 0.3742, + "step": 27951 + }, + { + "epoch": 2.28, + "learning_rate": 4.8152976966536295e-06, + "loss": 0.1789, + "step": 27952 + }, + { + "epoch": 2.28, + "learning_rate": 4.814754454584964e-06, + "loss": 0.054, + "step": 27953 + }, + { + "epoch": 2.28, + "learning_rate": 4.814211212516298e-06, + "loss": 0.16, + "step": 27954 + }, + { + "epoch": 2.28, + "learning_rate": 4.813667970447632e-06, + "loss": 0.1707, + "step": 27955 + }, + { + "epoch": 2.28, + "learning_rate": 4.813124728378966e-06, + "loss": 0.2978, + "step": 27956 + }, + { + "epoch": 2.28, + "learning_rate": 4.812581486310301e-06, + "loss": 0.2365, + "step": 27957 + }, + { + "epoch": 2.28, + "learning_rate": 4.812038244241635e-06, + "loss": 0.0878, + "step": 27958 + }, + { + "epoch": 2.28, + "learning_rate": 4.811495002172969e-06, + "loss": 0.1775, + "step": 27959 + }, + { + "epoch": 2.28, + "learning_rate": 4.8109517601043025e-06, + "loss": 0.0256, + "step": 27960 + }, + { + "epoch": 2.28, + "learning_rate": 4.810408518035637e-06, + "loss": 0.1792, + "step": 27961 + }, + { + "epoch": 2.28, + "learning_rate": 4.809865275966971e-06, + "loss": 0.2106, + "step": 27962 + }, + { + "epoch": 2.28, + "learning_rate": 4.809322033898305e-06, + "loss": 0.2106, + "step": 27963 + }, + { + "epoch": 2.28, + "learning_rate": 4.808778791829639e-06, + "loss": 0.3067, + "step": 27964 + }, + { + "epoch": 2.28, + "learning_rate": 4.808235549760974e-06, + "loss": 0.2658, + "step": 27965 + }, + { + "epoch": 2.28, + "learning_rate": 4.807692307692308e-06, + "loss": 0.4915, + "step": 27966 + }, + { + "epoch": 2.28, + "learning_rate": 4.807149065623642e-06, + "loss": 0.069, + "step": 27967 + }, + { + "epoch": 2.28, + "learning_rate": 4.806605823554976e-06, + "loss": 0.1842, + "step": 27968 + }, + { + "epoch": 2.28, + "learning_rate": 4.8060625814863105e-06, + "loss": 0.0961, + "step": 27969 + }, + { + "epoch": 2.28, + "learning_rate": 4.805519339417645e-06, + "loss": 0.2591, + "step": 27970 + }, + { + "epoch": 2.28, + "learning_rate": 4.804976097348979e-06, + "loss": 0.1364, + "step": 27971 + }, + { + "epoch": 2.28, + "learning_rate": 4.804432855280313e-06, + "loss": 0.133, + "step": 27972 + }, + { + "epoch": 2.28, + "learning_rate": 4.8038896132116475e-06, + "loss": 0.1703, + "step": 27973 + }, + { + "epoch": 2.28, + "learning_rate": 4.803346371142982e-06, + "loss": 0.1223, + "step": 27974 + }, + { + "epoch": 2.28, + "learning_rate": 4.802803129074316e-06, + "loss": 0.1847, + "step": 27975 + }, + { + "epoch": 2.28, + "learning_rate": 4.80225988700565e-06, + "loss": 0.2005, + "step": 27976 + }, + { + "epoch": 2.28, + "learning_rate": 4.801716644936984e-06, + "loss": 0.1762, + "step": 27977 + }, + { + "epoch": 2.28, + "learning_rate": 4.801173402868319e-06, + "loss": 0.2735, + "step": 27978 + }, + { + "epoch": 2.28, + "learning_rate": 4.800630160799653e-06, + "loss": 0.3757, + "step": 27979 + }, + { + "epoch": 2.28, + "learning_rate": 4.800086918730987e-06, + "loss": 0.1429, + "step": 27980 + }, + { + "epoch": 2.28, + "learning_rate": 4.799543676662321e-06, + "loss": 0.3066, + "step": 27981 + }, + { + "epoch": 2.28, + "learning_rate": 4.7990004345936555e-06, + "loss": 0.0823, + "step": 27982 + }, + { + "epoch": 2.28, + "learning_rate": 4.79845719252499e-06, + "loss": 0.1278, + "step": 27983 + }, + { + "epoch": 2.28, + "learning_rate": 4.797913950456324e-06, + "loss": 0.2768, + "step": 27984 + }, + { + "epoch": 2.28, + "learning_rate": 4.797370708387658e-06, + "loss": 0.2797, + "step": 27985 + }, + { + "epoch": 2.28, + "learning_rate": 4.7968274663189925e-06, + "loss": 0.1535, + "step": 27986 + }, + { + "epoch": 2.28, + "learning_rate": 4.796284224250327e-06, + "loss": 0.1781, + "step": 27987 + }, + { + "epoch": 2.28, + "learning_rate": 4.79574098218166e-06, + "loss": 0.1517, + "step": 27988 + }, + { + "epoch": 2.28, + "learning_rate": 4.795197740112994e-06, + "loss": 0.2131, + "step": 27989 + }, + { + "epoch": 2.28, + "learning_rate": 4.7946544980443285e-06, + "loss": 0.3815, + "step": 27990 + }, + { + "epoch": 2.28, + "learning_rate": 4.794111255975663e-06, + "loss": 0.3312, + "step": 27991 + }, + { + "epoch": 2.28, + "learning_rate": 4.793568013906997e-06, + "loss": 0.0639, + "step": 27992 + }, + { + "epoch": 2.28, + "learning_rate": 4.793024771838331e-06, + "loss": 0.0655, + "step": 27993 + }, + { + "epoch": 2.28, + "learning_rate": 4.7924815297696655e-06, + "loss": 0.0762, + "step": 27994 + }, + { + "epoch": 2.28, + "learning_rate": 4.791938287701e-06, + "loss": 0.3872, + "step": 27995 + }, + { + "epoch": 2.28, + "learning_rate": 4.791395045632335e-06, + "loss": 0.1608, + "step": 27996 + }, + { + "epoch": 2.28, + "learning_rate": 4.790851803563669e-06, + "loss": 0.065, + "step": 27997 + }, + { + "epoch": 2.28, + "learning_rate": 4.790308561495002e-06, + "loss": 0.2942, + "step": 27998 + }, + { + "epoch": 2.28, + "learning_rate": 4.789765319426337e-06, + "loss": 0.2357, + "step": 27999 + }, + { + "epoch": 2.28, + "learning_rate": 4.789222077357671e-06, + "loss": 0.1824, + "step": 28000 + }, + { + "epoch": 2.28, + "eval_accuracy": 0.8426897605705552, + "eval_loss": 0.5015740394592285, + "eval_runtime": 22.2144, + "eval_samples_per_second": 441.831, + "eval_steps_per_second": 3.466, + "step": 28000 + }, + { + "epoch": 2.28, + "learning_rate": 4.788678835289005e-06, + "loss": 0.2116, + "step": 28001 + }, + { + "epoch": 2.28, + "learning_rate": 4.788135593220339e-06, + "loss": 0.2984, + "step": 28002 + }, + { + "epoch": 2.28, + "learning_rate": 4.7875923511516735e-06, + "loss": 0.1493, + "step": 28003 + }, + { + "epoch": 2.28, + "learning_rate": 4.787049109083008e-06, + "loss": 0.2034, + "step": 28004 + }, + { + "epoch": 2.28, + "learning_rate": 4.786505867014342e-06, + "loss": 0.3021, + "step": 28005 + }, + { + "epoch": 2.28, + "learning_rate": 4.785962624945676e-06, + "loss": 0.0758, + "step": 28006 + }, + { + "epoch": 2.28, + "learning_rate": 4.7854193828770105e-06, + "loss": 0.0846, + "step": 28007 + }, + { + "epoch": 2.28, + "learning_rate": 4.784876140808345e-06, + "loss": 0.2121, + "step": 28008 + }, + { + "epoch": 2.28, + "learning_rate": 4.784332898739679e-06, + "loss": 0.31, + "step": 28009 + }, + { + "epoch": 2.28, + "learning_rate": 4.783789656671013e-06, + "loss": 0.3866, + "step": 28010 + }, + { + "epoch": 2.28, + "learning_rate": 4.783246414602347e-06, + "loss": 0.2157, + "step": 28011 + }, + { + "epoch": 2.28, + "learning_rate": 4.782703172533682e-06, + "loss": 0.3808, + "step": 28012 + }, + { + "epoch": 2.28, + "learning_rate": 4.782159930465016e-06, + "loss": 0.3618, + "step": 28013 + }, + { + "epoch": 2.28, + "learning_rate": 4.78161668839635e-06, + "loss": 0.3463, + "step": 28014 + }, + { + "epoch": 2.28, + "learning_rate": 4.781073446327684e-06, + "loss": 0.4103, + "step": 28015 + }, + { + "epoch": 2.28, + "learning_rate": 4.7805302042590185e-06, + "loss": 0.2735, + "step": 28016 + }, + { + "epoch": 2.28, + "learning_rate": 4.779986962190352e-06, + "loss": 0.3283, + "step": 28017 + }, + { + "epoch": 2.28, + "learning_rate": 4.779443720121686e-06, + "loss": 0.2405, + "step": 28018 + }, + { + "epoch": 2.28, + "learning_rate": 4.77890047805302e-06, + "loss": 0.058, + "step": 28019 + }, + { + "epoch": 2.28, + "learning_rate": 4.778357235984355e-06, + "loss": 0.2544, + "step": 28020 + }, + { + "epoch": 2.28, + "learning_rate": 4.777813993915689e-06, + "loss": 0.2515, + "step": 28021 + }, + { + "epoch": 2.28, + "learning_rate": 4.777270751847023e-06, + "loss": 0.044, + "step": 28022 + }, + { + "epoch": 2.28, + "learning_rate": 4.776727509778358e-06, + "loss": 0.081, + "step": 28023 + }, + { + "epoch": 2.28, + "learning_rate": 4.776184267709692e-06, + "loss": 0.682, + "step": 28024 + }, + { + "epoch": 2.28, + "learning_rate": 4.775641025641027e-06, + "loss": 0.2249, + "step": 28025 + }, + { + "epoch": 2.28, + "learning_rate": 4.77509778357236e-06, + "loss": 0.1137, + "step": 28026 + }, + { + "epoch": 2.28, + "learning_rate": 4.774554541503694e-06, + "loss": 0.4664, + "step": 28027 + }, + { + "epoch": 2.28, + "learning_rate": 4.7740112994350285e-06, + "loss": 0.1141, + "step": 28028 + }, + { + "epoch": 2.28, + "learning_rate": 4.773468057366363e-06, + "loss": 0.3362, + "step": 28029 + }, + { + "epoch": 2.28, + "learning_rate": 4.772924815297697e-06, + "loss": 0.1333, + "step": 28030 + }, + { + "epoch": 2.28, + "learning_rate": 4.772381573229031e-06, + "loss": 0.5152, + "step": 28031 + }, + { + "epoch": 2.28, + "learning_rate": 4.771838331160365e-06, + "loss": 0.2684, + "step": 28032 + }, + { + "epoch": 2.28, + "learning_rate": 4.7712950890917e-06, + "loss": 0.1389, + "step": 28033 + }, + { + "epoch": 2.28, + "learning_rate": 4.770751847023034e-06, + "loss": 0.2083, + "step": 28034 + }, + { + "epoch": 2.28, + "learning_rate": 4.770208604954368e-06, + "loss": 0.2657, + "step": 28035 + }, + { + "epoch": 2.28, + "learning_rate": 4.769665362885702e-06, + "loss": 0.2147, + "step": 28036 + }, + { + "epoch": 2.28, + "learning_rate": 4.7691221208170365e-06, + "loss": 0.1376, + "step": 28037 + }, + { + "epoch": 2.28, + "learning_rate": 4.768578878748371e-06, + "loss": 0.1887, + "step": 28038 + }, + { + "epoch": 2.28, + "learning_rate": 4.768035636679705e-06, + "loss": 0.3127, + "step": 28039 + }, + { + "epoch": 2.28, + "learning_rate": 4.767492394611039e-06, + "loss": 0.2603, + "step": 28040 + }, + { + "epoch": 2.28, + "learning_rate": 4.7669491525423735e-06, + "loss": 0.1394, + "step": 28041 + }, + { + "epoch": 2.29, + "learning_rate": 4.766405910473708e-06, + "loss": 0.3333, + "step": 28042 + }, + { + "epoch": 2.29, + "learning_rate": 4.765862668405042e-06, + "loss": 0.3592, + "step": 28043 + }, + { + "epoch": 2.29, + "learning_rate": 4.765319426336376e-06, + "loss": 0.0758, + "step": 28044 + }, + { + "epoch": 2.29, + "learning_rate": 4.7647761842677095e-06, + "loss": 0.2375, + "step": 28045 + }, + { + "epoch": 2.29, + "learning_rate": 4.764232942199044e-06, + "loss": 0.1849, + "step": 28046 + }, + { + "epoch": 2.29, + "learning_rate": 4.763689700130378e-06, + "loss": 0.3853, + "step": 28047 + }, + { + "epoch": 2.29, + "learning_rate": 4.763146458061712e-06, + "loss": 0.1571, + "step": 28048 + }, + { + "epoch": 2.29, + "learning_rate": 4.7626032159930465e-06, + "loss": 0.1344, + "step": 28049 + }, + { + "epoch": 2.29, + "learning_rate": 4.7620599739243815e-06, + "loss": 0.3864, + "step": 28050 + }, + { + "epoch": 2.29, + "learning_rate": 4.761516731855716e-06, + "loss": 0.5041, + "step": 28051 + }, + { + "epoch": 2.29, + "learning_rate": 4.76097348978705e-06, + "loss": 0.1352, + "step": 28052 + }, + { + "epoch": 2.29, + "learning_rate": 4.760430247718384e-06, + "loss": 0.2227, + "step": 28053 + }, + { + "epoch": 2.29, + "learning_rate": 4.7598870056497185e-06, + "loss": 0.1576, + "step": 28054 + }, + { + "epoch": 2.29, + "learning_rate": 4.759343763581052e-06, + "loss": 0.1733, + "step": 28055 + }, + { + "epoch": 2.29, + "learning_rate": 4.758800521512386e-06, + "loss": 0.3734, + "step": 28056 + }, + { + "epoch": 2.29, + "learning_rate": 4.75825727944372e-06, + "loss": 0.2164, + "step": 28057 + }, + { + "epoch": 2.29, + "learning_rate": 4.7577140373750545e-06, + "loss": 0.0935, + "step": 28058 + }, + { + "epoch": 2.29, + "learning_rate": 4.757170795306389e-06, + "loss": 0.355, + "step": 28059 + }, + { + "epoch": 2.29, + "learning_rate": 4.756627553237723e-06, + "loss": 0.1582, + "step": 28060 + }, + { + "epoch": 2.29, + "learning_rate": 4.756084311169057e-06, + "loss": 0.2812, + "step": 28061 + }, + { + "epoch": 2.29, + "learning_rate": 4.7555410691003914e-06, + "loss": 0.0737, + "step": 28062 + }, + { + "epoch": 2.29, + "learning_rate": 4.754997827031726e-06, + "loss": 0.1301, + "step": 28063 + }, + { + "epoch": 2.29, + "learning_rate": 4.75445458496306e-06, + "loss": 0.2737, + "step": 28064 + }, + { + "epoch": 2.29, + "learning_rate": 4.753911342894394e-06, + "loss": 0.1072, + "step": 28065 + }, + { + "epoch": 2.29, + "learning_rate": 4.753368100825728e-06, + "loss": 0.0884, + "step": 28066 + }, + { + "epoch": 2.29, + "learning_rate": 4.752824858757063e-06, + "loss": 0.1015, + "step": 28067 + }, + { + "epoch": 2.29, + "learning_rate": 4.752281616688397e-06, + "loss": 0.1702, + "step": 28068 + }, + { + "epoch": 2.29, + "learning_rate": 4.751738374619731e-06, + "loss": 0.0253, + "step": 28069 + }, + { + "epoch": 2.29, + "learning_rate": 4.751195132551065e-06, + "loss": 0.4488, + "step": 28070 + }, + { + "epoch": 2.29, + "learning_rate": 4.7506518904823995e-06, + "loss": 0.1667, + "step": 28071 + }, + { + "epoch": 2.29, + "learning_rate": 4.750108648413734e-06, + "loss": 0.2291, + "step": 28072 + }, + { + "epoch": 2.29, + "learning_rate": 4.749565406345068e-06, + "loss": 0.0914, + "step": 28073 + }, + { + "epoch": 2.29, + "learning_rate": 4.749022164276401e-06, + "loss": 0.248, + "step": 28074 + }, + { + "epoch": 2.29, + "learning_rate": 4.748478922207736e-06, + "loss": 0.3377, + "step": 28075 + }, + { + "epoch": 2.29, + "learning_rate": 4.74793568013907e-06, + "loss": 0.2938, + "step": 28076 + }, + { + "epoch": 2.29, + "learning_rate": 4.747392438070405e-06, + "loss": 0.0422, + "step": 28077 + }, + { + "epoch": 2.29, + "learning_rate": 4.746849196001739e-06, + "loss": 0.1178, + "step": 28078 + }, + { + "epoch": 2.29, + "learning_rate": 4.746305953933073e-06, + "loss": 0.2271, + "step": 28079 + }, + { + "epoch": 2.29, + "learning_rate": 4.745762711864408e-06, + "loss": 0.398, + "step": 28080 + }, + { + "epoch": 2.29, + "learning_rate": 4.745219469795742e-06, + "loss": 0.0645, + "step": 28081 + }, + { + "epoch": 2.29, + "learning_rate": 4.744676227727076e-06, + "loss": 0.2679, + "step": 28082 + }, + { + "epoch": 2.29, + "learning_rate": 4.7441329856584094e-06, + "loss": 0.2359, + "step": 28083 + }, + { + "epoch": 2.29, + "learning_rate": 4.743589743589744e-06, + "loss": 0.1341, + "step": 28084 + }, + { + "epoch": 2.29, + "learning_rate": 4.743046501521078e-06, + "loss": 0.2563, + "step": 28085 + }, + { + "epoch": 2.29, + "learning_rate": 4.742503259452412e-06, + "loss": 0.0818, + "step": 28086 + }, + { + "epoch": 2.29, + "learning_rate": 4.741960017383746e-06, + "loss": 0.1339, + "step": 28087 + }, + { + "epoch": 2.29, + "learning_rate": 4.741416775315081e-06, + "loss": 0.1686, + "step": 28088 + }, + { + "epoch": 2.29, + "learning_rate": 4.740873533246415e-06, + "loss": 0.0482, + "step": 28089 + }, + { + "epoch": 2.29, + "learning_rate": 4.740330291177749e-06, + "loss": 0.1871, + "step": 28090 + }, + { + "epoch": 2.29, + "learning_rate": 4.739787049109083e-06, + "loss": 0.1739, + "step": 28091 + }, + { + "epoch": 2.29, + "learning_rate": 4.7392438070404175e-06, + "loss": 0.4859, + "step": 28092 + }, + { + "epoch": 2.29, + "learning_rate": 4.738700564971752e-06, + "loss": 0.4269, + "step": 28093 + }, + { + "epoch": 2.29, + "learning_rate": 4.738157322903086e-06, + "loss": 0.3068, + "step": 28094 + }, + { + "epoch": 2.29, + "learning_rate": 4.73761408083442e-06, + "loss": 0.2565, + "step": 28095 + }, + { + "epoch": 2.29, + "learning_rate": 4.7370708387657544e-06, + "loss": 0.0695, + "step": 28096 + }, + { + "epoch": 2.29, + "learning_rate": 4.736527596697089e-06, + "loss": 0.3597, + "step": 28097 + }, + { + "epoch": 2.29, + "learning_rate": 4.735984354628423e-06, + "loss": 0.2967, + "step": 28098 + }, + { + "epoch": 2.29, + "learning_rate": 4.735441112559757e-06, + "loss": 0.2777, + "step": 28099 + }, + { + "epoch": 2.29, + "learning_rate": 4.734897870491091e-06, + "loss": 0.379, + "step": 28100 + }, + { + "epoch": 2.29, + "learning_rate": 4.734354628422426e-06, + "loss": 0.0844, + "step": 28101 + }, + { + "epoch": 2.29, + "learning_rate": 4.733811386353759e-06, + "loss": 0.0566, + "step": 28102 + }, + { + "epoch": 2.29, + "learning_rate": 4.733268144285093e-06, + "loss": 0.166, + "step": 28103 + }, + { + "epoch": 2.29, + "learning_rate": 4.732724902216428e-06, + "loss": 0.3186, + "step": 28104 + }, + { + "epoch": 2.29, + "learning_rate": 4.7321816601477625e-06, + "loss": 0.1953, + "step": 28105 + }, + { + "epoch": 2.29, + "learning_rate": 4.731638418079097e-06, + "loss": 0.3935, + "step": 28106 + }, + { + "epoch": 2.29, + "learning_rate": 4.731095176010431e-06, + "loss": 0.2241, + "step": 28107 + }, + { + "epoch": 2.29, + "learning_rate": 4.730551933941765e-06, + "loss": 0.1827, + "step": 28108 + }, + { + "epoch": 2.29, + "learning_rate": 4.7300086918730994e-06, + "loss": 0.2471, + "step": 28109 + }, + { + "epoch": 2.29, + "learning_rate": 4.729465449804434e-06, + "loss": 0.1116, + "step": 28110 + }, + { + "epoch": 2.29, + "learning_rate": 4.728922207735768e-06, + "loss": 0.5808, + "step": 28111 + }, + { + "epoch": 2.29, + "learning_rate": 4.728378965667101e-06, + "loss": 0.2792, + "step": 28112 + }, + { + "epoch": 2.29, + "learning_rate": 4.7278357235984355e-06, + "loss": 0.1559, + "step": 28113 + }, + { + "epoch": 2.29, + "learning_rate": 4.72729248152977e-06, + "loss": 0.1769, + "step": 28114 + }, + { + "epoch": 2.29, + "learning_rate": 4.726749239461104e-06, + "loss": 0.0988, + "step": 28115 + }, + { + "epoch": 2.29, + "learning_rate": 4.726205997392438e-06, + "loss": 0.2461, + "step": 28116 + }, + { + "epoch": 2.29, + "learning_rate": 4.7256627553237724e-06, + "loss": 0.0916, + "step": 28117 + }, + { + "epoch": 2.29, + "learning_rate": 4.725119513255107e-06, + "loss": 0.2521, + "step": 28118 + }, + { + "epoch": 2.29, + "learning_rate": 4.724576271186441e-06, + "loss": 0.1999, + "step": 28119 + }, + { + "epoch": 2.29, + "learning_rate": 4.724033029117775e-06, + "loss": 0.1205, + "step": 28120 + }, + { + "epoch": 2.29, + "learning_rate": 4.723489787049109e-06, + "loss": 0.5549, + "step": 28121 + }, + { + "epoch": 2.29, + "learning_rate": 4.722946544980444e-06, + "loss": 0.2147, + "step": 28122 + }, + { + "epoch": 2.29, + "learning_rate": 4.722403302911778e-06, + "loss": 0.1215, + "step": 28123 + }, + { + "epoch": 2.29, + "learning_rate": 4.721860060843112e-06, + "loss": 0.402, + "step": 28124 + }, + { + "epoch": 2.29, + "learning_rate": 4.721316818774446e-06, + "loss": 0.4149, + "step": 28125 + }, + { + "epoch": 2.29, + "learning_rate": 4.7207735767057805e-06, + "loss": 0.0952, + "step": 28126 + }, + { + "epoch": 2.29, + "learning_rate": 4.720230334637115e-06, + "loss": 0.0631, + "step": 28127 + }, + { + "epoch": 2.29, + "learning_rate": 4.719687092568449e-06, + "loss": 0.2205, + "step": 28128 + }, + { + "epoch": 2.29, + "learning_rate": 4.719143850499783e-06, + "loss": 0.2714, + "step": 28129 + }, + { + "epoch": 2.29, + "learning_rate": 4.7186006084311174e-06, + "loss": 0.2296, + "step": 28130 + }, + { + "epoch": 2.29, + "learning_rate": 4.718057366362452e-06, + "loss": 0.1802, + "step": 28131 + }, + { + "epoch": 2.29, + "learning_rate": 4.717514124293786e-06, + "loss": 0.1493, + "step": 28132 + }, + { + "epoch": 2.29, + "learning_rate": 4.71697088222512e-06, + "loss": 0.4315, + "step": 28133 + }, + { + "epoch": 2.29, + "learning_rate": 4.716427640156454e-06, + "loss": 0.244, + "step": 28134 + }, + { + "epoch": 2.29, + "learning_rate": 4.715884398087789e-06, + "loss": 0.3062, + "step": 28135 + }, + { + "epoch": 2.29, + "learning_rate": 4.715341156019123e-06, + "loss": 0.0768, + "step": 28136 + }, + { + "epoch": 2.29, + "learning_rate": 4.714797913950457e-06, + "loss": 0.3235, + "step": 28137 + }, + { + "epoch": 2.29, + "learning_rate": 4.714254671881791e-06, + "loss": 0.1081, + "step": 28138 + }, + { + "epoch": 2.29, + "learning_rate": 4.7137114298131255e-06, + "loss": 0.0891, + "step": 28139 + }, + { + "epoch": 2.29, + "learning_rate": 4.713168187744459e-06, + "loss": 0.4233, + "step": 28140 + }, + { + "epoch": 2.29, + "learning_rate": 4.712624945675793e-06, + "loss": 0.2148, + "step": 28141 + }, + { + "epoch": 2.29, + "learning_rate": 4.712081703607127e-06, + "loss": 0.2694, + "step": 28142 + }, + { + "epoch": 2.29, + "learning_rate": 4.711538461538462e-06, + "loss": 0.2789, + "step": 28143 + }, + { + "epoch": 2.29, + "learning_rate": 4.710995219469796e-06, + "loss": 0.1825, + "step": 28144 + }, + { + "epoch": 2.29, + "learning_rate": 4.71045197740113e-06, + "loss": 0.257, + "step": 28145 + }, + { + "epoch": 2.29, + "learning_rate": 4.709908735332464e-06, + "loss": 0.2417, + "step": 28146 + }, + { + "epoch": 2.29, + "learning_rate": 4.7093654932637985e-06, + "loss": 0.1006, + "step": 28147 + }, + { + "epoch": 2.29, + "learning_rate": 4.708822251195133e-06, + "loss": 0.3085, + "step": 28148 + }, + { + "epoch": 2.29, + "learning_rate": 4.708279009126468e-06, + "loss": 0.1718, + "step": 28149 + }, + { + "epoch": 2.29, + "learning_rate": 4.707735767057801e-06, + "loss": 0.1108, + "step": 28150 + }, + { + "epoch": 2.29, + "learning_rate": 4.7071925249891354e-06, + "loss": 0.0628, + "step": 28151 + }, + { + "epoch": 2.29, + "learning_rate": 4.70664928292047e-06, + "loss": 0.1732, + "step": 28152 + }, + { + "epoch": 2.29, + "learning_rate": 4.706106040851804e-06, + "loss": 0.0576, + "step": 28153 + }, + { + "epoch": 2.29, + "learning_rate": 4.705562798783138e-06, + "loss": 0.1932, + "step": 28154 + }, + { + "epoch": 2.29, + "learning_rate": 4.705019556714472e-06, + "loss": 0.0701, + "step": 28155 + }, + { + "epoch": 2.29, + "learning_rate": 4.704476314645807e-06, + "loss": 0.2267, + "step": 28156 + }, + { + "epoch": 2.29, + "learning_rate": 4.703933072577141e-06, + "loss": 0.1383, + "step": 28157 + }, + { + "epoch": 2.29, + "learning_rate": 4.703389830508475e-06, + "loss": 0.2865, + "step": 28158 + }, + { + "epoch": 2.29, + "learning_rate": 4.702846588439809e-06, + "loss": 0.2116, + "step": 28159 + }, + { + "epoch": 2.29, + "learning_rate": 4.7023033463711435e-06, + "loss": 0.4172, + "step": 28160 + }, + { + "epoch": 2.29, + "learning_rate": 4.701760104302478e-06, + "loss": 0.2473, + "step": 28161 + }, + { + "epoch": 2.29, + "learning_rate": 4.701216862233812e-06, + "loss": 0.3686, + "step": 28162 + }, + { + "epoch": 2.29, + "learning_rate": 4.700673620165146e-06, + "loss": 0.039, + "step": 28163 + }, + { + "epoch": 2.29, + "learning_rate": 4.70013037809648e-06, + "loss": 0.2808, + "step": 28164 + }, + { + "epoch": 2.3, + "learning_rate": 4.699587136027815e-06, + "loss": 0.3649, + "step": 28165 + }, + { + "epoch": 2.3, + "learning_rate": 4.699043893959149e-06, + "loss": 0.5929, + "step": 28166 + }, + { + "epoch": 2.3, + "learning_rate": 4.698500651890483e-06, + "loss": 0.0832, + "step": 28167 + }, + { + "epoch": 2.3, + "learning_rate": 4.697957409821817e-06, + "loss": 0.2199, + "step": 28168 + }, + { + "epoch": 2.3, + "learning_rate": 4.697414167753151e-06, + "loss": 0.1855, + "step": 28169 + }, + { + "epoch": 2.3, + "learning_rate": 4.696870925684485e-06, + "loss": 0.133, + "step": 28170 + }, + { + "epoch": 2.3, + "learning_rate": 4.696327683615819e-06, + "loss": 0.1474, + "step": 28171 + }, + { + "epoch": 2.3, + "learning_rate": 4.695784441547153e-06, + "loss": 0.3792, + "step": 28172 + }, + { + "epoch": 2.3, + "learning_rate": 4.695241199478488e-06, + "loss": 0.1498, + "step": 28173 + }, + { + "epoch": 2.3, + "learning_rate": 4.694697957409822e-06, + "loss": 0.3841, + "step": 28174 + }, + { + "epoch": 2.3, + "learning_rate": 4.694154715341156e-06, + "loss": 0.1364, + "step": 28175 + }, + { + "epoch": 2.3, + "learning_rate": 4.693611473272491e-06, + "loss": 0.2064, + "step": 28176 + }, + { + "epoch": 2.3, + "learning_rate": 4.693068231203825e-06, + "loss": 0.0982, + "step": 28177 + }, + { + "epoch": 2.3, + "learning_rate": 4.692524989135159e-06, + "loss": 0.2423, + "step": 28178 + }, + { + "epoch": 2.3, + "learning_rate": 4.691981747066493e-06, + "loss": 0.1202, + "step": 28179 + }, + { + "epoch": 2.3, + "learning_rate": 4.691438504997827e-06, + "loss": 0.1035, + "step": 28180 + }, + { + "epoch": 2.3, + "learning_rate": 4.6908952629291615e-06, + "loss": 0.1835, + "step": 28181 + }, + { + "epoch": 2.3, + "learning_rate": 4.690352020860496e-06, + "loss": 0.3405, + "step": 28182 + }, + { + "epoch": 2.3, + "learning_rate": 4.68980877879183e-06, + "loss": 0.2472, + "step": 28183 + }, + { + "epoch": 2.3, + "learning_rate": 4.689265536723164e-06, + "loss": 0.0541, + "step": 28184 + }, + { + "epoch": 2.3, + "learning_rate": 4.688722294654498e-06, + "loss": 0.4279, + "step": 28185 + }, + { + "epoch": 2.3, + "learning_rate": 4.688179052585833e-06, + "loss": 0.2866, + "step": 28186 + }, + { + "epoch": 2.3, + "learning_rate": 4.687635810517167e-06, + "loss": 0.1474, + "step": 28187 + }, + { + "epoch": 2.3, + "learning_rate": 4.687092568448501e-06, + "loss": 0.1421, + "step": 28188 + }, + { + "epoch": 2.3, + "learning_rate": 4.686549326379835e-06, + "loss": 0.2567, + "step": 28189 + }, + { + "epoch": 2.3, + "learning_rate": 4.6860060843111696e-06, + "loss": 0.1039, + "step": 28190 + }, + { + "epoch": 2.3, + "learning_rate": 4.685462842242504e-06, + "loss": 0.2823, + "step": 28191 + }, + { + "epoch": 2.3, + "learning_rate": 4.684919600173838e-06, + "loss": 0.2486, + "step": 28192 + }, + { + "epoch": 2.3, + "learning_rate": 4.684376358105172e-06, + "loss": 0.3463, + "step": 28193 + }, + { + "epoch": 2.3, + "learning_rate": 4.6838331160365065e-06, + "loss": 0.2453, + "step": 28194 + }, + { + "epoch": 2.3, + "learning_rate": 4.683289873967841e-06, + "loss": 0.2504, + "step": 28195 + }, + { + "epoch": 2.3, + "learning_rate": 4.682746631899175e-06, + "loss": 0.116, + "step": 28196 + }, + { + "epoch": 2.3, + "learning_rate": 4.682203389830508e-06, + "loss": 0.4483, + "step": 28197 + }, + { + "epoch": 2.3, + "learning_rate": 4.6816601477618426e-06, + "loss": 0.1735, + "step": 28198 + }, + { + "epoch": 2.3, + "learning_rate": 4.681116905693177e-06, + "loss": 0.2646, + "step": 28199 + }, + { + "epoch": 2.3, + "learning_rate": 4.680573663624511e-06, + "loss": 0.3383, + "step": 28200 + }, + { + "epoch": 2.3, + "learning_rate": 4.680030421555845e-06, + "loss": 0.2037, + "step": 28201 + }, + { + "epoch": 2.3, + "learning_rate": 4.6794871794871795e-06, + "loss": 0.4422, + "step": 28202 + }, + { + "epoch": 2.3, + "learning_rate": 4.6789439374185146e-06, + "loss": 0.1865, + "step": 28203 + }, + { + "epoch": 2.3, + "learning_rate": 4.678400695349849e-06, + "loss": 0.1242, + "step": 28204 + }, + { + "epoch": 2.3, + "learning_rate": 4.677857453281183e-06, + "loss": 0.378, + "step": 28205 + }, + { + "epoch": 2.3, + "learning_rate": 4.677314211212517e-06, + "loss": 0.2107, + "step": 28206 + }, + { + "epoch": 2.3, + "learning_rate": 4.676770969143851e-06, + "loss": 0.1685, + "step": 28207 + }, + { + "epoch": 2.3, + "learning_rate": 4.676227727075185e-06, + "loss": 0.2224, + "step": 28208 + }, + { + "epoch": 2.3, + "learning_rate": 4.675684485006519e-06, + "loss": 0.1468, + "step": 28209 + }, + { + "epoch": 2.3, + "learning_rate": 4.675141242937853e-06, + "loss": 0.1253, + "step": 28210 + }, + { + "epoch": 2.3, + "learning_rate": 4.6745980008691876e-06, + "loss": 0.4873, + "step": 28211 + }, + { + "epoch": 2.3, + "learning_rate": 4.674054758800522e-06, + "loss": 0.1361, + "step": 28212 + }, + { + "epoch": 2.3, + "learning_rate": 4.673511516731856e-06, + "loss": 0.1203, + "step": 28213 + }, + { + "epoch": 2.3, + "learning_rate": 4.67296827466319e-06, + "loss": 0.1905, + "step": 28214 + }, + { + "epoch": 2.3, + "learning_rate": 4.6724250325945245e-06, + "loss": 0.1624, + "step": 28215 + }, + { + "epoch": 2.3, + "learning_rate": 4.671881790525859e-06, + "loss": 0.1474, + "step": 28216 + }, + { + "epoch": 2.3, + "learning_rate": 4.671338548457193e-06, + "loss": 0.3217, + "step": 28217 + }, + { + "epoch": 2.3, + "learning_rate": 4.670795306388527e-06, + "loss": 0.1298, + "step": 28218 + }, + { + "epoch": 2.3, + "learning_rate": 4.670252064319861e-06, + "loss": 0.2348, + "step": 28219 + }, + { + "epoch": 2.3, + "learning_rate": 4.669708822251196e-06, + "loss": 0.4152, + "step": 28220 + }, + { + "epoch": 2.3, + "learning_rate": 4.66916558018253e-06, + "loss": 0.3374, + "step": 28221 + }, + { + "epoch": 2.3, + "learning_rate": 4.668622338113864e-06, + "loss": 0.3168, + "step": 28222 + }, + { + "epoch": 2.3, + "learning_rate": 4.668079096045198e-06, + "loss": 0.1204, + "step": 28223 + }, + { + "epoch": 2.3, + "learning_rate": 4.6675358539765326e-06, + "loss": 0.0995, + "step": 28224 + }, + { + "epoch": 2.3, + "learning_rate": 4.666992611907867e-06, + "loss": 0.1941, + "step": 28225 + }, + { + "epoch": 2.3, + "learning_rate": 4.6664493698392e-06, + "loss": 0.2085, + "step": 28226 + }, + { + "epoch": 2.3, + "learning_rate": 4.665906127770534e-06, + "loss": 0.1413, + "step": 28227 + }, + { + "epoch": 2.3, + "learning_rate": 4.665362885701869e-06, + "loss": 0.0959, + "step": 28228 + }, + { + "epoch": 2.3, + "learning_rate": 4.664819643633203e-06, + "loss": 0.1254, + "step": 28229 + }, + { + "epoch": 2.3, + "learning_rate": 4.664276401564538e-06, + "loss": 0.1448, + "step": 28230 + }, + { + "epoch": 2.3, + "learning_rate": 4.663733159495872e-06, + "loss": 0.1799, + "step": 28231 + }, + { + "epoch": 2.3, + "learning_rate": 4.663189917427206e-06, + "loss": 0.1683, + "step": 28232 + }, + { + "epoch": 2.3, + "learning_rate": 4.662646675358541e-06, + "loss": 0.3238, + "step": 28233 + }, + { + "epoch": 2.3, + "learning_rate": 4.662103433289875e-06, + "loss": 0.1876, + "step": 28234 + }, + { + "epoch": 2.3, + "learning_rate": 4.661560191221208e-06, + "loss": 0.324, + "step": 28235 + }, + { + "epoch": 2.3, + "learning_rate": 4.6610169491525425e-06, + "loss": 0.343, + "step": 28236 + }, + { + "epoch": 2.3, + "learning_rate": 4.660473707083877e-06, + "loss": 0.2921, + "step": 28237 + }, + { + "epoch": 2.3, + "learning_rate": 4.659930465015211e-06, + "loss": 0.3812, + "step": 28238 + }, + { + "epoch": 2.3, + "learning_rate": 4.659387222946545e-06, + "loss": 0.1146, + "step": 28239 + }, + { + "epoch": 2.3, + "learning_rate": 4.658843980877879e-06, + "loss": 0.1446, + "step": 28240 + }, + { + "epoch": 2.3, + "learning_rate": 4.658300738809214e-06, + "loss": 0.0707, + "step": 28241 + }, + { + "epoch": 2.3, + "learning_rate": 4.657757496740548e-06, + "loss": 0.0952, + "step": 28242 + }, + { + "epoch": 2.3, + "learning_rate": 4.657214254671882e-06, + "loss": 0.0893, + "step": 28243 + }, + { + "epoch": 2.3, + "learning_rate": 4.656671012603216e-06, + "loss": 0.4402, + "step": 28244 + }, + { + "epoch": 2.3, + "learning_rate": 4.6561277705345506e-06, + "loss": 0.3676, + "step": 28245 + }, + { + "epoch": 2.3, + "learning_rate": 4.655584528465885e-06, + "loss": 0.2142, + "step": 28246 + }, + { + "epoch": 2.3, + "learning_rate": 4.655041286397219e-06, + "loss": 0.2489, + "step": 28247 + }, + { + "epoch": 2.3, + "learning_rate": 4.654498044328553e-06, + "loss": 0.6974, + "step": 28248 + }, + { + "epoch": 2.3, + "learning_rate": 4.6539548022598875e-06, + "loss": 0.3517, + "step": 28249 + }, + { + "epoch": 2.3, + "learning_rate": 4.653411560191222e-06, + "loss": 0.3382, + "step": 28250 + }, + { + "epoch": 2.3, + "eval_accuracy": 0.8427916454406521, + "eval_loss": 0.49643558263778687, + "eval_runtime": 22.2586, + "eval_samples_per_second": 440.952, + "eval_steps_per_second": 3.459, + "step": 28250 + }, + { + "epoch": 2.3, + "learning_rate": 4.652868318122556e-06, + "loss": 0.348, + "step": 28251 + }, + { + "epoch": 2.3, + "learning_rate": 4.65232507605389e-06, + "loss": 0.3481, + "step": 28252 + }, + { + "epoch": 2.3, + "learning_rate": 4.651781833985224e-06, + "loss": 0.1284, + "step": 28253 + }, + { + "epoch": 2.3, + "learning_rate": 4.651238591916558e-06, + "loss": 0.2119, + "step": 28254 + }, + { + "epoch": 2.3, + "learning_rate": 4.650695349847892e-06, + "loss": 0.2541, + "step": 28255 + }, + { + "epoch": 2.3, + "learning_rate": 4.650152107779226e-06, + "loss": 0.4831, + "step": 28256 + }, + { + "epoch": 2.3, + "learning_rate": 4.649608865710561e-06, + "loss": 0.2063, + "step": 28257 + }, + { + "epoch": 2.3, + "learning_rate": 4.6490656236418956e-06, + "loss": 0.1454, + "step": 28258 + }, + { + "epoch": 2.3, + "learning_rate": 4.64852238157323e-06, + "loss": 0.2076, + "step": 28259 + }, + { + "epoch": 2.3, + "learning_rate": 4.647979139504564e-06, + "loss": 0.2507, + "step": 28260 + }, + { + "epoch": 2.3, + "learning_rate": 4.647435897435898e-06, + "loss": 0.2827, + "step": 28261 + }, + { + "epoch": 2.3, + "learning_rate": 4.6468926553672325e-06, + "loss": 0.213, + "step": 28262 + }, + { + "epoch": 2.3, + "learning_rate": 4.646349413298567e-06, + "loss": 0.0821, + "step": 28263 + }, + { + "epoch": 2.3, + "learning_rate": 4.6458061712299e-06, + "loss": 0.1512, + "step": 28264 + }, + { + "epoch": 2.3, + "learning_rate": 4.645262929161234e-06, + "loss": 0.1756, + "step": 28265 + }, + { + "epoch": 2.3, + "learning_rate": 4.6447196870925686e-06, + "loss": 0.3607, + "step": 28266 + }, + { + "epoch": 2.3, + "learning_rate": 4.644176445023903e-06, + "loss": 0.4178, + "step": 28267 + }, + { + "epoch": 2.3, + "learning_rate": 4.643633202955237e-06, + "loss": 0.2457, + "step": 28268 + }, + { + "epoch": 2.3, + "learning_rate": 4.643089960886571e-06, + "loss": 0.2138, + "step": 28269 + }, + { + "epoch": 2.3, + "learning_rate": 4.6425467188179055e-06, + "loss": 0.3839, + "step": 28270 + }, + { + "epoch": 2.3, + "learning_rate": 4.64200347674924e-06, + "loss": 0.3498, + "step": 28271 + }, + { + "epoch": 2.3, + "learning_rate": 4.641460234680574e-06, + "loss": 0.514, + "step": 28272 + }, + { + "epoch": 2.3, + "learning_rate": 4.640916992611908e-06, + "loss": 0.1554, + "step": 28273 + }, + { + "epoch": 2.3, + "learning_rate": 4.640373750543242e-06, + "loss": 0.561, + "step": 28274 + }, + { + "epoch": 2.3, + "learning_rate": 4.639830508474577e-06, + "loss": 0.0486, + "step": 28275 + }, + { + "epoch": 2.3, + "learning_rate": 4.639287266405911e-06, + "loss": 0.2976, + "step": 28276 + }, + { + "epoch": 2.3, + "learning_rate": 4.638744024337245e-06, + "loss": 0.2471, + "step": 28277 + }, + { + "epoch": 2.3, + "learning_rate": 4.638200782268579e-06, + "loss": 0.1755, + "step": 28278 + }, + { + "epoch": 2.3, + "learning_rate": 4.6376575401999135e-06, + "loss": 0.4991, + "step": 28279 + }, + { + "epoch": 2.3, + "learning_rate": 4.637114298131248e-06, + "loss": 0.0977, + "step": 28280 + }, + { + "epoch": 2.3, + "learning_rate": 4.636571056062582e-06, + "loss": 0.133, + "step": 28281 + }, + { + "epoch": 2.3, + "learning_rate": 4.636027813993916e-06, + "loss": 0.4545, + "step": 28282 + }, + { + "epoch": 2.3, + "learning_rate": 4.63548457192525e-06, + "loss": 0.1192, + "step": 28283 + }, + { + "epoch": 2.3, + "learning_rate": 4.634941329856585e-06, + "loss": 0.3117, + "step": 28284 + }, + { + "epoch": 2.3, + "learning_rate": 4.634398087787919e-06, + "loss": 0.1171, + "step": 28285 + }, + { + "epoch": 2.3, + "learning_rate": 4.633854845719253e-06, + "loss": 0.2646, + "step": 28286 + }, + { + "epoch": 2.31, + "learning_rate": 4.633311603650587e-06, + "loss": 0.2247, + "step": 28287 + }, + { + "epoch": 2.31, + "learning_rate": 4.632768361581922e-06, + "loss": 0.1632, + "step": 28288 + }, + { + "epoch": 2.31, + "learning_rate": 4.632225119513256e-06, + "loss": 0.2837, + "step": 28289 + }, + { + "epoch": 2.31, + "learning_rate": 4.63168187744459e-06, + "loss": 0.1388, + "step": 28290 + }, + { + "epoch": 2.31, + "learning_rate": 4.631138635375924e-06, + "loss": 0.3856, + "step": 28291 + }, + { + "epoch": 2.31, + "learning_rate": 4.630595393307258e-06, + "loss": 0.0816, + "step": 28292 + }, + { + "epoch": 2.31, + "learning_rate": 4.630052151238592e-06, + "loss": 0.3342, + "step": 28293 + }, + { + "epoch": 2.31, + "learning_rate": 4.629508909169926e-06, + "loss": 0.2636, + "step": 28294 + }, + { + "epoch": 2.31, + "learning_rate": 4.62896566710126e-06, + "loss": 0.4198, + "step": 28295 + }, + { + "epoch": 2.31, + "learning_rate": 4.628422425032595e-06, + "loss": 0.1019, + "step": 28296 + }, + { + "epoch": 2.31, + "learning_rate": 4.627879182963929e-06, + "loss": 0.0331, + "step": 28297 + }, + { + "epoch": 2.31, + "learning_rate": 4.627335940895263e-06, + "loss": 0.187, + "step": 28298 + }, + { + "epoch": 2.31, + "learning_rate": 4.626792698826597e-06, + "loss": 0.1817, + "step": 28299 + }, + { + "epoch": 2.31, + "learning_rate": 4.6262494567579315e-06, + "loss": 0.1411, + "step": 28300 + }, + { + "epoch": 2.31, + "learning_rate": 4.625706214689266e-06, + "loss": 0.4734, + "step": 28301 + }, + { + "epoch": 2.31, + "learning_rate": 4.6251629726206e-06, + "loss": 0.4043, + "step": 28302 + }, + { + "epoch": 2.31, + "learning_rate": 4.624619730551934e-06, + "loss": 0.0856, + "step": 28303 + }, + { + "epoch": 2.31, + "learning_rate": 4.6240764884832685e-06, + "loss": 0.0999, + "step": 28304 + }, + { + "epoch": 2.31, + "learning_rate": 4.623533246414603e-06, + "loss": 0.2498, + "step": 28305 + }, + { + "epoch": 2.31, + "learning_rate": 4.622990004345937e-06, + "loss": 0.2069, + "step": 28306 + }, + { + "epoch": 2.31, + "learning_rate": 4.622446762277271e-06, + "loss": 0.2966, + "step": 28307 + }, + { + "epoch": 2.31, + "learning_rate": 4.621903520208605e-06, + "loss": 0.2564, + "step": 28308 + }, + { + "epoch": 2.31, + "learning_rate": 4.62136027813994e-06, + "loss": 0.3382, + "step": 28309 + }, + { + "epoch": 2.31, + "learning_rate": 4.620817036071274e-06, + "loss": 0.0305, + "step": 28310 + }, + { + "epoch": 2.31, + "learning_rate": 4.620273794002608e-06, + "loss": 0.2351, + "step": 28311 + }, + { + "epoch": 2.31, + "learning_rate": 4.619730551933942e-06, + "loss": 0.0419, + "step": 28312 + }, + { + "epoch": 2.31, + "learning_rate": 4.6191873098652765e-06, + "loss": 0.1576, + "step": 28313 + }, + { + "epoch": 2.31, + "learning_rate": 4.618644067796611e-06, + "loss": 0.3864, + "step": 28314 + }, + { + "epoch": 2.31, + "learning_rate": 4.618100825727945e-06, + "loss": 0.2124, + "step": 28315 + }, + { + "epoch": 2.31, + "learning_rate": 4.617557583659279e-06, + "loss": 0.088, + "step": 28316 + }, + { + "epoch": 2.31, + "learning_rate": 4.6170143415906135e-06, + "loss": 0.3318, + "step": 28317 + }, + { + "epoch": 2.31, + "learning_rate": 4.616471099521948e-06, + "loss": 0.5155, + "step": 28318 + }, + { + "epoch": 2.31, + "learning_rate": 4.615927857453282e-06, + "loss": 0.1653, + "step": 28319 + }, + { + "epoch": 2.31, + "learning_rate": 4.615384615384616e-06, + "loss": 0.202, + "step": 28320 + }, + { + "epoch": 2.31, + "learning_rate": 4.6148413733159495e-06, + "loss": 0.0836, + "step": 28321 + }, + { + "epoch": 2.31, + "learning_rate": 4.614298131247284e-06, + "loss": 0.2515, + "step": 28322 + }, + { + "epoch": 2.31, + "learning_rate": 4.613754889178618e-06, + "loss": 0.1225, + "step": 28323 + }, + { + "epoch": 2.31, + "learning_rate": 4.613211647109952e-06, + "loss": 0.095, + "step": 28324 + }, + { + "epoch": 2.31, + "learning_rate": 4.6126684050412865e-06, + "loss": 0.151, + "step": 28325 + }, + { + "epoch": 2.31, + "learning_rate": 4.612125162972621e-06, + "loss": 0.5303, + "step": 28326 + }, + { + "epoch": 2.31, + "learning_rate": 4.611581920903955e-06, + "loss": 0.089, + "step": 28327 + }, + { + "epoch": 2.31, + "learning_rate": 4.611038678835289e-06, + "loss": 0.3757, + "step": 28328 + }, + { + "epoch": 2.31, + "learning_rate": 4.610495436766624e-06, + "loss": 0.2591, + "step": 28329 + }, + { + "epoch": 2.31, + "learning_rate": 4.609952194697958e-06, + "loss": 0.2349, + "step": 28330 + }, + { + "epoch": 2.31, + "learning_rate": 4.609408952629292e-06, + "loss": 0.0858, + "step": 28331 + }, + { + "epoch": 2.31, + "learning_rate": 4.608865710560626e-06, + "loss": 0.0681, + "step": 28332 + }, + { + "epoch": 2.31, + "learning_rate": 4.60832246849196e-06, + "loss": 0.4644, + "step": 28333 + }, + { + "epoch": 2.31, + "learning_rate": 4.6077792264232945e-06, + "loss": 0.3011, + "step": 28334 + }, + { + "epoch": 2.31, + "learning_rate": 4.607235984354629e-06, + "loss": 0.4263, + "step": 28335 + }, + { + "epoch": 2.31, + "learning_rate": 4.606692742285963e-06, + "loss": 0.1466, + "step": 28336 + }, + { + "epoch": 2.31, + "learning_rate": 4.606149500217297e-06, + "loss": 0.302, + "step": 28337 + }, + { + "epoch": 2.31, + "learning_rate": 4.6056062581486315e-06, + "loss": 0.3652, + "step": 28338 + }, + { + "epoch": 2.31, + "learning_rate": 4.605063016079966e-06, + "loss": 0.1145, + "step": 28339 + }, + { + "epoch": 2.31, + "learning_rate": 4.6045197740113e-06, + "loss": 0.1846, + "step": 28340 + }, + { + "epoch": 2.31, + "learning_rate": 4.603976531942634e-06, + "loss": 0.1874, + "step": 28341 + }, + { + "epoch": 2.31, + "learning_rate": 4.603433289873968e-06, + "loss": 0.2568, + "step": 28342 + }, + { + "epoch": 2.31, + "learning_rate": 4.602890047805303e-06, + "loss": 0.4013, + "step": 28343 + }, + { + "epoch": 2.31, + "learning_rate": 4.602346805736637e-06, + "loss": 0.2762, + "step": 28344 + }, + { + "epoch": 2.31, + "learning_rate": 4.601803563667971e-06, + "loss": 0.4064, + "step": 28345 + }, + { + "epoch": 2.31, + "learning_rate": 4.601260321599305e-06, + "loss": 0.0966, + "step": 28346 + }, + { + "epoch": 2.31, + "learning_rate": 4.6007170795306395e-06, + "loss": 0.3443, + "step": 28347 + }, + { + "epoch": 2.31, + "learning_rate": 4.600173837461974e-06, + "loss": 0.1081, + "step": 28348 + }, + { + "epoch": 2.31, + "learning_rate": 4.599630595393307e-06, + "loss": 0.106, + "step": 28349 + }, + { + "epoch": 2.31, + "learning_rate": 4.599087353324641e-06, + "loss": 0.0679, + "step": 28350 + }, + { + "epoch": 2.31, + "learning_rate": 4.598544111255976e-06, + "loss": 0.0746, + "step": 28351 + }, + { + "epoch": 2.31, + "learning_rate": 4.59800086918731e-06, + "loss": 0.2699, + "step": 28352 + }, + { + "epoch": 2.31, + "learning_rate": 4.597457627118644e-06, + "loss": 0.1076, + "step": 28353 + }, + { + "epoch": 2.31, + "learning_rate": 4.596914385049978e-06, + "loss": 0.4546, + "step": 28354 + }, + { + "epoch": 2.31, + "learning_rate": 4.5963711429813125e-06, + "loss": 0.1931, + "step": 28355 + }, + { + "epoch": 2.31, + "learning_rate": 4.595827900912648e-06, + "loss": 0.2144, + "step": 28356 + }, + { + "epoch": 2.31, + "learning_rate": 4.595284658843982e-06, + "loss": 0.4444, + "step": 28357 + }, + { + "epoch": 2.31, + "learning_rate": 4.594741416775316e-06, + "loss": 0.2116, + "step": 28358 + }, + { + "epoch": 2.31, + "learning_rate": 4.5941981747066495e-06, + "loss": 0.1523, + "step": 28359 + }, + { + "epoch": 2.31, + "learning_rate": 4.593654932637984e-06, + "loss": 0.1829, + "step": 28360 + }, + { + "epoch": 2.31, + "learning_rate": 4.593111690569318e-06, + "loss": 0.0638, + "step": 28361 + }, + { + "epoch": 2.31, + "learning_rate": 4.592568448500652e-06, + "loss": 0.1179, + "step": 28362 + }, + { + "epoch": 2.31, + "learning_rate": 4.592025206431986e-06, + "loss": 0.6419, + "step": 28363 + }, + { + "epoch": 2.31, + "learning_rate": 4.591481964363321e-06, + "loss": 0.1866, + "step": 28364 + }, + { + "epoch": 2.31, + "learning_rate": 4.590938722294655e-06, + "loss": 0.1494, + "step": 28365 + }, + { + "epoch": 2.31, + "learning_rate": 4.590395480225989e-06, + "loss": 0.4057, + "step": 28366 + }, + { + "epoch": 2.31, + "learning_rate": 4.589852238157323e-06, + "loss": 0.2971, + "step": 28367 + }, + { + "epoch": 2.31, + "learning_rate": 4.5893089960886575e-06, + "loss": 0.1205, + "step": 28368 + }, + { + "epoch": 2.31, + "learning_rate": 4.588765754019992e-06, + "loss": 0.0891, + "step": 28369 + }, + { + "epoch": 2.31, + "learning_rate": 4.588222511951326e-06, + "loss": 0.1356, + "step": 28370 + }, + { + "epoch": 2.31, + "learning_rate": 4.58767926988266e-06, + "loss": 0.2593, + "step": 28371 + }, + { + "epoch": 2.31, + "learning_rate": 4.5871360278139944e-06, + "loss": 0.4113, + "step": 28372 + }, + { + "epoch": 2.31, + "learning_rate": 4.586592785745329e-06, + "loss": 0.2977, + "step": 28373 + }, + { + "epoch": 2.31, + "learning_rate": 4.586049543676663e-06, + "loss": 0.1455, + "step": 28374 + }, + { + "epoch": 2.31, + "learning_rate": 4.585506301607997e-06, + "loss": 0.2416, + "step": 28375 + }, + { + "epoch": 2.31, + "learning_rate": 4.584963059539331e-06, + "loss": 0.1881, + "step": 28376 + }, + { + "epoch": 2.31, + "learning_rate": 4.584419817470666e-06, + "loss": 0.2248, + "step": 28377 + }, + { + "epoch": 2.31, + "learning_rate": 4.583876575401999e-06, + "loss": 0.5549, + "step": 28378 + }, + { + "epoch": 2.31, + "learning_rate": 4.583333333333333e-06, + "loss": 0.2205, + "step": 28379 + }, + { + "epoch": 2.31, + "learning_rate": 4.5827900912646674e-06, + "loss": 0.1219, + "step": 28380 + }, + { + "epoch": 2.31, + "learning_rate": 4.582246849196002e-06, + "loss": 0.1166, + "step": 28381 + }, + { + "epoch": 2.31, + "learning_rate": 4.581703607127336e-06, + "loss": 0.1315, + "step": 28382 + }, + { + "epoch": 2.31, + "learning_rate": 4.581160365058671e-06, + "loss": 0.3095, + "step": 28383 + }, + { + "epoch": 2.31, + "learning_rate": 4.580617122990005e-06, + "loss": 0.5088, + "step": 28384 + }, + { + "epoch": 2.31, + "learning_rate": 4.5800738809213394e-06, + "loss": 0.1962, + "step": 28385 + }, + { + "epoch": 2.31, + "learning_rate": 4.579530638852674e-06, + "loss": 0.1715, + "step": 28386 + }, + { + "epoch": 2.31, + "learning_rate": 4.578987396784007e-06, + "loss": 0.0695, + "step": 28387 + }, + { + "epoch": 2.31, + "learning_rate": 4.578444154715341e-06, + "loss": 0.3121, + "step": 28388 + }, + { + "epoch": 2.31, + "learning_rate": 4.5779009126466755e-06, + "loss": 0.3272, + "step": 28389 + }, + { + "epoch": 2.31, + "learning_rate": 4.57735767057801e-06, + "loss": 0.1409, + "step": 28390 + }, + { + "epoch": 2.31, + "learning_rate": 4.576814428509344e-06, + "loss": 0.1992, + "step": 28391 + }, + { + "epoch": 2.31, + "learning_rate": 4.576271186440678e-06, + "loss": 0.1504, + "step": 28392 + }, + { + "epoch": 2.31, + "learning_rate": 4.5757279443720124e-06, + "loss": 0.3686, + "step": 28393 + }, + { + "epoch": 2.31, + "learning_rate": 4.575184702303347e-06, + "loss": 0.3275, + "step": 28394 + }, + { + "epoch": 2.31, + "learning_rate": 4.574641460234681e-06, + "loss": 0.3593, + "step": 28395 + }, + { + "epoch": 2.31, + "learning_rate": 4.574098218166015e-06, + "loss": 0.4683, + "step": 28396 + }, + { + "epoch": 2.31, + "learning_rate": 4.573554976097349e-06, + "loss": 0.3635, + "step": 28397 + }, + { + "epoch": 2.31, + "learning_rate": 4.573011734028684e-06, + "loss": 0.2046, + "step": 28398 + }, + { + "epoch": 2.31, + "learning_rate": 4.572468491960018e-06, + "loss": 0.1367, + "step": 28399 + }, + { + "epoch": 2.31, + "learning_rate": 4.571925249891352e-06, + "loss": 0.0375, + "step": 28400 + }, + { + "epoch": 2.31, + "learning_rate": 4.571382007822686e-06, + "loss": 0.0955, + "step": 28401 + }, + { + "epoch": 2.31, + "learning_rate": 4.5708387657540205e-06, + "loss": 0.0748, + "step": 28402 + }, + { + "epoch": 2.31, + "learning_rate": 4.570295523685355e-06, + "loss": 0.1472, + "step": 28403 + }, + { + "epoch": 2.31, + "learning_rate": 4.569752281616689e-06, + "loss": 0.2432, + "step": 28404 + }, + { + "epoch": 2.31, + "learning_rate": 4.569209039548023e-06, + "loss": 0.3669, + "step": 28405 + }, + { + "epoch": 2.31, + "learning_rate": 4.568665797479357e-06, + "loss": 0.3251, + "step": 28406 + }, + { + "epoch": 2.31, + "learning_rate": 4.568122555410691e-06, + "loss": 0.2378, + "step": 28407 + }, + { + "epoch": 2.31, + "learning_rate": 4.567579313342025e-06, + "loss": 0.18, + "step": 28408 + }, + { + "epoch": 2.31, + "learning_rate": 4.567036071273359e-06, + "loss": 0.1397, + "step": 28409 + }, + { + "epoch": 2.32, + "learning_rate": 4.566492829204694e-06, + "loss": 0.3477, + "step": 28410 + }, + { + "epoch": 2.32, + "learning_rate": 4.565949587136029e-06, + "loss": 0.2627, + "step": 28411 + }, + { + "epoch": 2.32, + "learning_rate": 4.565406345067363e-06, + "loss": 0.1033, + "step": 28412 + }, + { + "epoch": 2.32, + "learning_rate": 4.564863102998697e-06, + "loss": 0.2756, + "step": 28413 + }, + { + "epoch": 2.32, + "learning_rate": 4.564319860930031e-06, + "loss": 0.0859, + "step": 28414 + }, + { + "epoch": 2.32, + "learning_rate": 4.5637766188613655e-06, + "loss": 0.5426, + "step": 28415 + }, + { + "epoch": 2.32, + "learning_rate": 4.563233376792699e-06, + "loss": 0.1801, + "step": 28416 + }, + { + "epoch": 2.32, + "learning_rate": 4.562690134724033e-06, + "loss": 0.179, + "step": 28417 + }, + { + "epoch": 2.32, + "learning_rate": 4.562146892655367e-06, + "loss": 0.2214, + "step": 28418 + }, + { + "epoch": 2.32, + "learning_rate": 4.561603650586702e-06, + "loss": 0.13, + "step": 28419 + }, + { + "epoch": 2.32, + "learning_rate": 4.561060408518036e-06, + "loss": 0.3788, + "step": 28420 + }, + { + "epoch": 2.32, + "learning_rate": 4.56051716644937e-06, + "loss": 0.1558, + "step": 28421 + }, + { + "epoch": 2.32, + "learning_rate": 4.559973924380704e-06, + "loss": 0.2288, + "step": 28422 + }, + { + "epoch": 2.32, + "learning_rate": 4.5594306823120385e-06, + "loss": 0.5689, + "step": 28423 + }, + { + "epoch": 2.32, + "learning_rate": 4.558887440243373e-06, + "loss": 0.122, + "step": 28424 + }, + { + "epoch": 2.32, + "learning_rate": 4.558344198174707e-06, + "loss": 0.1775, + "step": 28425 + }, + { + "epoch": 2.32, + "learning_rate": 4.557800956106041e-06, + "loss": 0.2057, + "step": 28426 + }, + { + "epoch": 2.32, + "learning_rate": 4.5572577140373754e-06, + "loss": 0.1954, + "step": 28427 + }, + { + "epoch": 2.32, + "learning_rate": 4.55671447196871e-06, + "loss": 0.1014, + "step": 28428 + }, + { + "epoch": 2.32, + "learning_rate": 4.556171229900044e-06, + "loss": 0.1605, + "step": 28429 + }, + { + "epoch": 2.32, + "learning_rate": 4.555627987831378e-06, + "loss": 0.3164, + "step": 28430 + }, + { + "epoch": 2.32, + "learning_rate": 4.555084745762712e-06, + "loss": 0.0672, + "step": 28431 + }, + { + "epoch": 2.32, + "learning_rate": 4.554541503694047e-06, + "loss": 0.3856, + "step": 28432 + }, + { + "epoch": 2.32, + "learning_rate": 4.553998261625381e-06, + "loss": 0.1335, + "step": 28433 + }, + { + "epoch": 2.32, + "learning_rate": 4.553455019556715e-06, + "loss": 0.0648, + "step": 28434 + }, + { + "epoch": 2.32, + "learning_rate": 4.5529117774880484e-06, + "loss": 0.1634, + "step": 28435 + }, + { + "epoch": 2.32, + "learning_rate": 4.552368535419383e-06, + "loss": 0.1476, + "step": 28436 + }, + { + "epoch": 2.32, + "learning_rate": 4.551825293350718e-06, + "loss": 0.1669, + "step": 28437 + }, + { + "epoch": 2.32, + "learning_rate": 4.551282051282052e-06, + "loss": 0.1547, + "step": 28438 + }, + { + "epoch": 2.32, + "learning_rate": 4.550738809213386e-06, + "loss": 0.095, + "step": 28439 + }, + { + "epoch": 2.32, + "learning_rate": 4.5501955671447204e-06, + "loss": 0.2851, + "step": 28440 + }, + { + "epoch": 2.32, + "learning_rate": 4.549652325076055e-06, + "loss": 0.2899, + "step": 28441 + }, + { + "epoch": 2.32, + "learning_rate": 4.549109083007389e-06, + "loss": 0.1597, + "step": 28442 + }, + { + "epoch": 2.32, + "learning_rate": 4.548565840938723e-06, + "loss": 0.1835, + "step": 28443 + }, + { + "epoch": 2.32, + "learning_rate": 4.5480225988700565e-06, + "loss": 0.0845, + "step": 28444 + }, + { + "epoch": 2.32, + "learning_rate": 4.547479356801391e-06, + "loss": 0.4004, + "step": 28445 + }, + { + "epoch": 2.32, + "learning_rate": 4.546936114732725e-06, + "loss": 0.1369, + "step": 28446 + }, + { + "epoch": 2.32, + "learning_rate": 4.546392872664059e-06, + "loss": 0.1186, + "step": 28447 + }, + { + "epoch": 2.32, + "learning_rate": 4.5458496305953934e-06, + "loss": 0.3239, + "step": 28448 + }, + { + "epoch": 2.32, + "learning_rate": 4.545306388526728e-06, + "loss": 0.219, + "step": 28449 + }, + { + "epoch": 2.32, + "learning_rate": 4.544763146458062e-06, + "loss": 0.2408, + "step": 28450 + }, + { + "epoch": 2.32, + "learning_rate": 4.544219904389396e-06, + "loss": 0.1692, + "step": 28451 + }, + { + "epoch": 2.32, + "learning_rate": 4.54367666232073e-06, + "loss": 0.2911, + "step": 28452 + }, + { + "epoch": 2.32, + "learning_rate": 4.543133420252065e-06, + "loss": 0.072, + "step": 28453 + }, + { + "epoch": 2.32, + "learning_rate": 4.542590178183399e-06, + "loss": 0.0736, + "step": 28454 + }, + { + "epoch": 2.32, + "learning_rate": 4.542046936114733e-06, + "loss": 0.2393, + "step": 28455 + }, + { + "epoch": 2.32, + "learning_rate": 4.541503694046067e-06, + "loss": 0.132, + "step": 28456 + }, + { + "epoch": 2.32, + "learning_rate": 4.5409604519774015e-06, + "loss": 0.2807, + "step": 28457 + }, + { + "epoch": 2.32, + "learning_rate": 4.540417209908736e-06, + "loss": 0.1513, + "step": 28458 + }, + { + "epoch": 2.32, + "learning_rate": 4.53987396784007e-06, + "loss": 0.2814, + "step": 28459 + }, + { + "epoch": 2.32, + "learning_rate": 4.539330725771404e-06, + "loss": 0.2102, + "step": 28460 + }, + { + "epoch": 2.32, + "learning_rate": 4.5387874837027384e-06, + "loss": 0.2249, + "step": 28461 + }, + { + "epoch": 2.32, + "learning_rate": 4.538244241634073e-06, + "loss": 0.2296, + "step": 28462 + }, + { + "epoch": 2.32, + "learning_rate": 4.537700999565406e-06, + "loss": 0.2937, + "step": 28463 + }, + { + "epoch": 2.32, + "learning_rate": 4.537157757496741e-06, + "loss": 0.2172, + "step": 28464 + }, + { + "epoch": 2.32, + "learning_rate": 4.536614515428075e-06, + "loss": 0.3472, + "step": 28465 + }, + { + "epoch": 2.32, + "learning_rate": 4.53607127335941e-06, + "loss": 0.3355, + "step": 28466 + }, + { + "epoch": 2.32, + "learning_rate": 4.535528031290744e-06, + "loss": 0.3173, + "step": 28467 + }, + { + "epoch": 2.32, + "learning_rate": 4.534984789222078e-06, + "loss": 0.2738, + "step": 28468 + }, + { + "epoch": 2.32, + "learning_rate": 4.534441547153412e-06, + "loss": 0.1072, + "step": 28469 + }, + { + "epoch": 2.32, + "learning_rate": 4.5338983050847465e-06, + "loss": 0.2641, + "step": 28470 + }, + { + "epoch": 2.32, + "learning_rate": 4.533355063016081e-06, + "loss": 0.3241, + "step": 28471 + }, + { + "epoch": 2.32, + "learning_rate": 4.532811820947415e-06, + "loss": 0.1182, + "step": 28472 + }, + { + "epoch": 2.32, + "learning_rate": 4.532268578878748e-06, + "loss": 0.0863, + "step": 28473 + }, + { + "epoch": 2.32, + "learning_rate": 4.5317253368100826e-06, + "loss": 0.15, + "step": 28474 + }, + { + "epoch": 2.32, + "learning_rate": 4.531182094741417e-06, + "loss": 0.2697, + "step": 28475 + }, + { + "epoch": 2.32, + "learning_rate": 4.530638852672751e-06, + "loss": 0.1468, + "step": 28476 + }, + { + "epoch": 2.32, + "learning_rate": 4.530095610604085e-06, + "loss": 0.1814, + "step": 28477 + }, + { + "epoch": 2.32, + "learning_rate": 4.5295523685354195e-06, + "loss": 0.2066, + "step": 28478 + }, + { + "epoch": 2.32, + "learning_rate": 4.529009126466754e-06, + "loss": 0.218, + "step": 28479 + }, + { + "epoch": 2.32, + "learning_rate": 4.528465884398088e-06, + "loss": 0.2279, + "step": 28480 + }, + { + "epoch": 2.32, + "learning_rate": 4.527922642329422e-06, + "loss": 0.1928, + "step": 28481 + }, + { + "epoch": 2.32, + "learning_rate": 4.527379400260756e-06, + "loss": 0.3201, + "step": 28482 + }, + { + "epoch": 2.32, + "learning_rate": 4.526836158192091e-06, + "loss": 0.5213, + "step": 28483 + }, + { + "epoch": 2.32, + "learning_rate": 4.526292916123425e-06, + "loss": 0.3321, + "step": 28484 + }, + { + "epoch": 2.32, + "learning_rate": 4.525749674054759e-06, + "loss": 0.11, + "step": 28485 + }, + { + "epoch": 2.32, + "learning_rate": 4.525206431986093e-06, + "loss": 0.1073, + "step": 28486 + }, + { + "epoch": 2.32, + "learning_rate": 4.5246631899174276e-06, + "loss": 0.4487, + "step": 28487 + }, + { + "epoch": 2.32, + "learning_rate": 4.524119947848762e-06, + "loss": 0.204, + "step": 28488 + }, + { + "epoch": 2.32, + "learning_rate": 4.523576705780096e-06, + "loss": 0.2934, + "step": 28489 + }, + { + "epoch": 2.32, + "learning_rate": 4.52303346371143e-06, + "loss": 0.1311, + "step": 28490 + }, + { + "epoch": 2.32, + "learning_rate": 4.5224902216427645e-06, + "loss": 0.3752, + "step": 28491 + }, + { + "epoch": 2.32, + "learning_rate": 4.521946979574099e-06, + "loss": 0.3313, + "step": 28492 + }, + { + "epoch": 2.32, + "learning_rate": 4.521403737505433e-06, + "loss": 0.1724, + "step": 28493 + }, + { + "epoch": 2.32, + "learning_rate": 4.520860495436767e-06, + "loss": 0.1989, + "step": 28494 + }, + { + "epoch": 2.32, + "learning_rate": 4.520317253368101e-06, + "loss": 0.2798, + "step": 28495 + }, + { + "epoch": 2.32, + "learning_rate": 4.519774011299436e-06, + "loss": 0.2681, + "step": 28496 + }, + { + "epoch": 2.32, + "learning_rate": 4.51923076923077e-06, + "loss": 0.3624, + "step": 28497 + }, + { + "epoch": 2.32, + "learning_rate": 4.518687527162104e-06, + "loss": 0.1877, + "step": 28498 + }, + { + "epoch": 2.32, + "learning_rate": 4.518144285093438e-06, + "loss": 0.2564, + "step": 28499 + }, + { + "epoch": 2.32, + "learning_rate": 4.5176010430247726e-06, + "loss": 0.1925, + "step": 28500 + }, + { + "epoch": 2.32, + "eval_accuracy": 0.8423841059602649, + "eval_loss": 0.499388188123703, + "eval_runtime": 22.3532, + "eval_samples_per_second": 439.087, + "eval_steps_per_second": 3.445, + "step": 28500 + }, + { + "epoch": 2.32, + "learning_rate": 4.517057800956107e-06, + "loss": 0.2929, + "step": 28501 + }, + { + "epoch": 2.32, + "learning_rate": 4.51651455888744e-06, + "loss": 0.0297, + "step": 28502 + }, + { + "epoch": 2.32, + "learning_rate": 4.515971316818774e-06, + "loss": 0.1461, + "step": 28503 + }, + { + "epoch": 2.32, + "learning_rate": 4.515428074750109e-06, + "loss": 0.1876, + "step": 28504 + }, + { + "epoch": 2.32, + "learning_rate": 4.514884832681443e-06, + "loss": 0.1198, + "step": 28505 + }, + { + "epoch": 2.32, + "learning_rate": 4.514341590612777e-06, + "loss": 0.1084, + "step": 28506 + }, + { + "epoch": 2.32, + "learning_rate": 4.513798348544111e-06, + "loss": 0.2409, + "step": 28507 + }, + { + "epoch": 2.32, + "learning_rate": 4.5132551064754456e-06, + "loss": 0.3188, + "step": 28508 + }, + { + "epoch": 2.32, + "learning_rate": 4.51271186440678e-06, + "loss": 0.2233, + "step": 28509 + }, + { + "epoch": 2.32, + "learning_rate": 4.512168622338115e-06, + "loss": 0.0692, + "step": 28510 + }, + { + "epoch": 2.32, + "learning_rate": 4.511625380269448e-06, + "loss": 0.2254, + "step": 28511 + }, + { + "epoch": 2.32, + "learning_rate": 4.5110821382007825e-06, + "loss": 0.3401, + "step": 28512 + }, + { + "epoch": 2.32, + "learning_rate": 4.510538896132117e-06, + "loss": 0.0673, + "step": 28513 + }, + { + "epoch": 2.32, + "learning_rate": 4.509995654063451e-06, + "loss": 0.163, + "step": 28514 + }, + { + "epoch": 2.32, + "learning_rate": 4.509452411994785e-06, + "loss": 0.2335, + "step": 28515 + }, + { + "epoch": 2.32, + "learning_rate": 4.508909169926119e-06, + "loss": 0.1971, + "step": 28516 + }, + { + "epoch": 2.32, + "learning_rate": 4.508365927857454e-06, + "loss": 0.2418, + "step": 28517 + }, + { + "epoch": 2.32, + "learning_rate": 4.507822685788788e-06, + "loss": 0.1231, + "step": 28518 + }, + { + "epoch": 2.32, + "learning_rate": 4.507279443720122e-06, + "loss": 0.1092, + "step": 28519 + }, + { + "epoch": 2.32, + "learning_rate": 4.506736201651456e-06, + "loss": 0.0716, + "step": 28520 + }, + { + "epoch": 2.32, + "learning_rate": 4.5061929595827906e-06, + "loss": 0.127, + "step": 28521 + }, + { + "epoch": 2.32, + "learning_rate": 4.505649717514125e-06, + "loss": 0.2071, + "step": 28522 + }, + { + "epoch": 2.32, + "learning_rate": 4.505106475445459e-06, + "loss": 0.1861, + "step": 28523 + }, + { + "epoch": 2.32, + "learning_rate": 4.504563233376793e-06, + "loss": 0.1925, + "step": 28524 + }, + { + "epoch": 2.32, + "learning_rate": 4.5040199913081275e-06, + "loss": 0.3485, + "step": 28525 + }, + { + "epoch": 2.32, + "learning_rate": 4.503476749239462e-06, + "loss": 0.1396, + "step": 28526 + }, + { + "epoch": 2.32, + "learning_rate": 4.502933507170796e-06, + "loss": 0.1876, + "step": 28527 + }, + { + "epoch": 2.32, + "learning_rate": 4.50239026510213e-06, + "loss": 0.2012, + "step": 28528 + }, + { + "epoch": 2.32, + "learning_rate": 4.501847023033464e-06, + "loss": 0.2281, + "step": 28529 + }, + { + "epoch": 2.32, + "learning_rate": 4.501303780964798e-06, + "loss": 0.2029, + "step": 28530 + }, + { + "epoch": 2.32, + "learning_rate": 4.500760538896132e-06, + "loss": 0.0695, + "step": 28531 + }, + { + "epoch": 2.32, + "learning_rate": 4.500217296827466e-06, + "loss": 0.0817, + "step": 28532 + }, + { + "epoch": 2.33, + "learning_rate": 4.4996740547588005e-06, + "loss": 0.2259, + "step": 28533 + }, + { + "epoch": 2.33, + "learning_rate": 4.499130812690135e-06, + "loss": 0.0628, + "step": 28534 + }, + { + "epoch": 2.33, + "learning_rate": 4.498587570621469e-06, + "loss": 0.1193, + "step": 28535 + }, + { + "epoch": 2.33, + "learning_rate": 4.498044328552803e-06, + "loss": 0.6547, + "step": 28536 + }, + { + "epoch": 2.33, + "learning_rate": 4.497501086484138e-06, + "loss": 0.1935, + "step": 28537 + }, + { + "epoch": 2.33, + "learning_rate": 4.4969578444154725e-06, + "loss": 0.4806, + "step": 28538 + }, + { + "epoch": 2.33, + "learning_rate": 4.496414602346807e-06, + "loss": 0.1322, + "step": 28539 + }, + { + "epoch": 2.33, + "learning_rate": 4.49587136027814e-06, + "loss": 0.2735, + "step": 28540 + }, + { + "epoch": 2.33, + "learning_rate": 4.495328118209474e-06, + "loss": 0.1506, + "step": 28541 + }, + { + "epoch": 2.33, + "learning_rate": 4.4947848761408086e-06, + "loss": 0.2832, + "step": 28542 + }, + { + "epoch": 2.33, + "learning_rate": 4.494241634072143e-06, + "loss": 0.2217, + "step": 28543 + }, + { + "epoch": 2.33, + "learning_rate": 4.493698392003477e-06, + "loss": 0.2799, + "step": 28544 + }, + { + "epoch": 2.33, + "learning_rate": 4.493155149934811e-06, + "loss": 0.2367, + "step": 28545 + }, + { + "epoch": 2.33, + "learning_rate": 4.4926119078661455e-06, + "loss": 0.078, + "step": 28546 + }, + { + "epoch": 2.33, + "learning_rate": 4.49206866579748e-06, + "loss": 0.252, + "step": 28547 + }, + { + "epoch": 2.33, + "learning_rate": 4.491525423728814e-06, + "loss": 0.1247, + "step": 28548 + }, + { + "epoch": 2.33, + "learning_rate": 4.490982181660148e-06, + "loss": 0.2046, + "step": 28549 + }, + { + "epoch": 2.33, + "learning_rate": 4.490438939591482e-06, + "loss": 0.4187, + "step": 28550 + }, + { + "epoch": 2.33, + "learning_rate": 4.489895697522817e-06, + "loss": 0.2428, + "step": 28551 + }, + { + "epoch": 2.33, + "learning_rate": 4.489352455454151e-06, + "loss": 0.3526, + "step": 28552 + }, + { + "epoch": 2.33, + "learning_rate": 4.488809213385485e-06, + "loss": 0.2071, + "step": 28553 + }, + { + "epoch": 2.33, + "learning_rate": 4.488265971316819e-06, + "loss": 0.1399, + "step": 28554 + }, + { + "epoch": 2.33, + "learning_rate": 4.4877227292481536e-06, + "loss": 0.0976, + "step": 28555 + }, + { + "epoch": 2.33, + "learning_rate": 4.487179487179488e-06, + "loss": 0.337, + "step": 28556 + }, + { + "epoch": 2.33, + "learning_rate": 4.486636245110822e-06, + "loss": 0.1084, + "step": 28557 + }, + { + "epoch": 2.33, + "learning_rate": 4.486093003042156e-06, + "loss": 0.3355, + "step": 28558 + }, + { + "epoch": 2.33, + "learning_rate": 4.48554976097349e-06, + "loss": 0.214, + "step": 28559 + }, + { + "epoch": 2.33, + "learning_rate": 4.485006518904824e-06, + "loss": 0.1571, + "step": 28560 + }, + { + "epoch": 2.33, + "learning_rate": 4.484463276836158e-06, + "loss": 0.45, + "step": 28561 + }, + { + "epoch": 2.33, + "learning_rate": 4.483920034767492e-06, + "loss": 0.068, + "step": 28562 + }, + { + "epoch": 2.33, + "learning_rate": 4.4833767926988266e-06, + "loss": 0.3606, + "step": 28563 + }, + { + "epoch": 2.33, + "learning_rate": 4.482833550630162e-06, + "loss": 0.2364, + "step": 28564 + }, + { + "epoch": 2.33, + "learning_rate": 4.482290308561496e-06, + "loss": 0.1205, + "step": 28565 + }, + { + "epoch": 2.33, + "learning_rate": 4.48174706649283e-06, + "loss": 0.0907, + "step": 28566 + }, + { + "epoch": 2.33, + "learning_rate": 4.481203824424164e-06, + "loss": 0.1355, + "step": 28567 + }, + { + "epoch": 2.33, + "learning_rate": 4.480660582355498e-06, + "loss": 0.1465, + "step": 28568 + }, + { + "epoch": 2.33, + "learning_rate": 4.480117340286832e-06, + "loss": 0.0695, + "step": 28569 + }, + { + "epoch": 2.33, + "learning_rate": 4.479574098218166e-06, + "loss": 0.1564, + "step": 28570 + }, + { + "epoch": 2.33, + "learning_rate": 4.4790308561495e-06, + "loss": 0.2846, + "step": 28571 + }, + { + "epoch": 2.33, + "learning_rate": 4.478487614080835e-06, + "loss": 0.3053, + "step": 28572 + }, + { + "epoch": 2.33, + "learning_rate": 4.477944372012169e-06, + "loss": 0.1973, + "step": 28573 + }, + { + "epoch": 2.33, + "learning_rate": 4.477401129943503e-06, + "loss": 0.1517, + "step": 28574 + }, + { + "epoch": 2.33, + "learning_rate": 4.476857887874837e-06, + "loss": 0.1566, + "step": 28575 + }, + { + "epoch": 2.33, + "learning_rate": 4.4763146458061715e-06, + "loss": 0.0665, + "step": 28576 + }, + { + "epoch": 2.33, + "learning_rate": 4.475771403737506e-06, + "loss": 0.1202, + "step": 28577 + }, + { + "epoch": 2.33, + "learning_rate": 4.47522816166884e-06, + "loss": 0.2461, + "step": 28578 + }, + { + "epoch": 2.33, + "learning_rate": 4.474684919600174e-06, + "loss": 0.3037, + "step": 28579 + }, + { + "epoch": 2.33, + "learning_rate": 4.4741416775315085e-06, + "loss": 0.1274, + "step": 28580 + }, + { + "epoch": 2.33, + "learning_rate": 4.473598435462843e-06, + "loss": 0.2051, + "step": 28581 + }, + { + "epoch": 2.33, + "learning_rate": 4.473055193394177e-06, + "loss": 0.383, + "step": 28582 + }, + { + "epoch": 2.33, + "learning_rate": 4.472511951325511e-06, + "loss": 0.2274, + "step": 28583 + }, + { + "epoch": 2.33, + "learning_rate": 4.471968709256845e-06, + "loss": 0.2501, + "step": 28584 + }, + { + "epoch": 2.33, + "learning_rate": 4.47142546718818e-06, + "loss": 0.3125, + "step": 28585 + }, + { + "epoch": 2.33, + "learning_rate": 4.470882225119514e-06, + "loss": 0.2432, + "step": 28586 + }, + { + "epoch": 2.33, + "learning_rate": 4.470338983050847e-06, + "loss": 0.2023, + "step": 28587 + }, + { + "epoch": 2.33, + "learning_rate": 4.4697957409821815e-06, + "loss": 0.1103, + "step": 28588 + }, + { + "epoch": 2.33, + "learning_rate": 4.469252498913516e-06, + "loss": 0.092, + "step": 28589 + }, + { + "epoch": 2.33, + "learning_rate": 4.46870925684485e-06, + "loss": 0.1278, + "step": 28590 + }, + { + "epoch": 2.33, + "learning_rate": 4.468166014776185e-06, + "loss": 0.2486, + "step": 28591 + }, + { + "epoch": 2.33, + "learning_rate": 4.467622772707519e-06, + "loss": 0.3648, + "step": 28592 + }, + { + "epoch": 2.33, + "learning_rate": 4.4670795306388535e-06, + "loss": 0.1448, + "step": 28593 + }, + { + "epoch": 2.33, + "learning_rate": 4.466536288570188e-06, + "loss": 0.3269, + "step": 28594 + }, + { + "epoch": 2.33, + "learning_rate": 4.465993046501522e-06, + "loss": 0.1625, + "step": 28595 + }, + { + "epoch": 2.33, + "learning_rate": 4.465449804432856e-06, + "loss": 0.0866, + "step": 28596 + }, + { + "epoch": 2.33, + "learning_rate": 4.4649065623641895e-06, + "loss": 0.0417, + "step": 28597 + }, + { + "epoch": 2.33, + "learning_rate": 4.464363320295524e-06, + "loss": 0.2037, + "step": 28598 + }, + { + "epoch": 2.33, + "learning_rate": 4.463820078226858e-06, + "loss": 0.0605, + "step": 28599 + }, + { + "epoch": 2.33, + "learning_rate": 4.463276836158192e-06, + "loss": 0.0448, + "step": 28600 + }, + { + "epoch": 2.33, + "learning_rate": 4.4627335940895265e-06, + "loss": 0.256, + "step": 28601 + }, + { + "epoch": 2.33, + "learning_rate": 4.462190352020861e-06, + "loss": 0.0893, + "step": 28602 + }, + { + "epoch": 2.33, + "learning_rate": 4.461647109952195e-06, + "loss": 0.2358, + "step": 28603 + }, + { + "epoch": 2.33, + "learning_rate": 4.461103867883529e-06, + "loss": 0.1329, + "step": 28604 + }, + { + "epoch": 2.33, + "learning_rate": 4.460560625814863e-06, + "loss": 0.134, + "step": 28605 + }, + { + "epoch": 2.33, + "learning_rate": 4.460017383746198e-06, + "loss": 0.2037, + "step": 28606 + }, + { + "epoch": 2.33, + "learning_rate": 4.459474141677532e-06, + "loss": 0.3119, + "step": 28607 + }, + { + "epoch": 2.33, + "learning_rate": 4.458930899608866e-06, + "loss": 0.2201, + "step": 28608 + }, + { + "epoch": 2.33, + "learning_rate": 4.4583876575402e-06, + "loss": 0.3514, + "step": 28609 + }, + { + "epoch": 2.33, + "learning_rate": 4.4578444154715345e-06, + "loss": 0.3182, + "step": 28610 + }, + { + "epoch": 2.33, + "learning_rate": 4.457301173402869e-06, + "loss": 0.2313, + "step": 28611 + }, + { + "epoch": 2.33, + "learning_rate": 4.456757931334203e-06, + "loss": 0.2315, + "step": 28612 + }, + { + "epoch": 2.33, + "learning_rate": 4.456214689265537e-06, + "loss": 0.2608, + "step": 28613 + }, + { + "epoch": 2.33, + "learning_rate": 4.4556714471968715e-06, + "loss": 0.0778, + "step": 28614 + }, + { + "epoch": 2.33, + "learning_rate": 4.455128205128206e-06, + "loss": 0.0755, + "step": 28615 + }, + { + "epoch": 2.33, + "learning_rate": 4.454584963059539e-06, + "loss": 0.0683, + "step": 28616 + }, + { + "epoch": 2.33, + "learning_rate": 4.454041720990873e-06, + "loss": 0.4376, + "step": 28617 + }, + { + "epoch": 2.33, + "learning_rate": 4.453498478922208e-06, + "loss": 0.222, + "step": 28618 + }, + { + "epoch": 2.33, + "learning_rate": 4.452955236853543e-06, + "loss": 0.2316, + "step": 28619 + }, + { + "epoch": 2.33, + "learning_rate": 4.452411994784877e-06, + "loss": 0.3897, + "step": 28620 + }, + { + "epoch": 2.33, + "learning_rate": 4.451868752716211e-06, + "loss": 0.0971, + "step": 28621 + }, + { + "epoch": 2.33, + "learning_rate": 4.451325510647545e-06, + "loss": 0.305, + "step": 28622 + }, + { + "epoch": 2.33, + "learning_rate": 4.4507822685788795e-06, + "loss": 0.1421, + "step": 28623 + }, + { + "epoch": 2.33, + "learning_rate": 4.450239026510214e-06, + "loss": 0.3366, + "step": 28624 + }, + { + "epoch": 2.33, + "learning_rate": 4.449695784441547e-06, + "loss": 0.3116, + "step": 28625 + }, + { + "epoch": 2.33, + "learning_rate": 4.449152542372881e-06, + "loss": 0.1404, + "step": 28626 + }, + { + "epoch": 2.33, + "learning_rate": 4.448609300304216e-06, + "loss": 0.1092, + "step": 28627 + }, + { + "epoch": 2.33, + "learning_rate": 4.44806605823555e-06, + "loss": 0.2519, + "step": 28628 + }, + { + "epoch": 2.33, + "learning_rate": 4.447522816166884e-06, + "loss": 0.2745, + "step": 28629 + }, + { + "epoch": 2.33, + "learning_rate": 4.446979574098218e-06, + "loss": 0.2124, + "step": 28630 + }, + { + "epoch": 2.33, + "learning_rate": 4.4464363320295525e-06, + "loss": 0.1649, + "step": 28631 + }, + { + "epoch": 2.33, + "learning_rate": 4.445893089960887e-06, + "loss": 0.2719, + "step": 28632 + }, + { + "epoch": 2.33, + "learning_rate": 4.445349847892221e-06, + "loss": 0.2991, + "step": 28633 + }, + { + "epoch": 2.33, + "learning_rate": 4.444806605823555e-06, + "loss": 0.4842, + "step": 28634 + }, + { + "epoch": 2.33, + "learning_rate": 4.4442633637548895e-06, + "loss": 0.1627, + "step": 28635 + }, + { + "epoch": 2.33, + "learning_rate": 4.443720121686224e-06, + "loss": 0.2075, + "step": 28636 + }, + { + "epoch": 2.33, + "learning_rate": 4.443176879617558e-06, + "loss": 0.4061, + "step": 28637 + }, + { + "epoch": 2.33, + "learning_rate": 4.442633637548892e-06, + "loss": 0.278, + "step": 28638 + }, + { + "epoch": 2.33, + "learning_rate": 4.442090395480226e-06, + "loss": 0.0861, + "step": 28639 + }, + { + "epoch": 2.33, + "learning_rate": 4.441547153411561e-06, + "loss": 0.0976, + "step": 28640 + }, + { + "epoch": 2.33, + "learning_rate": 4.441003911342895e-06, + "loss": 0.2622, + "step": 28641 + }, + { + "epoch": 2.33, + "learning_rate": 4.440460669274229e-06, + "loss": 0.1599, + "step": 28642 + }, + { + "epoch": 2.33, + "learning_rate": 4.439917427205563e-06, + "loss": 0.3091, + "step": 28643 + }, + { + "epoch": 2.33, + "learning_rate": 4.439374185136897e-06, + "loss": 0.1348, + "step": 28644 + }, + { + "epoch": 2.33, + "learning_rate": 4.438830943068232e-06, + "loss": 0.2609, + "step": 28645 + }, + { + "epoch": 2.33, + "learning_rate": 4.438287700999566e-06, + "loss": 0.4524, + "step": 28646 + }, + { + "epoch": 2.33, + "learning_rate": 4.4377444589309e-06, + "loss": 0.3273, + "step": 28647 + }, + { + "epoch": 2.33, + "learning_rate": 4.4372012168622345e-06, + "loss": 0.3324, + "step": 28648 + }, + { + "epoch": 2.33, + "learning_rate": 4.436657974793569e-06, + "loss": 0.1509, + "step": 28649 + }, + { + "epoch": 2.33, + "learning_rate": 4.436114732724903e-06, + "loss": 0.1234, + "step": 28650 + }, + { + "epoch": 2.33, + "learning_rate": 4.435571490656237e-06, + "loss": 0.532, + "step": 28651 + }, + { + "epoch": 2.33, + "learning_rate": 4.435028248587571e-06, + "loss": 0.162, + "step": 28652 + }, + { + "epoch": 2.33, + "learning_rate": 4.434485006518906e-06, + "loss": 0.0499, + "step": 28653 + }, + { + "epoch": 2.33, + "learning_rate": 4.433941764450239e-06, + "loss": 0.4119, + "step": 28654 + }, + { + "epoch": 2.33, + "learning_rate": 4.433398522381573e-06, + "loss": 0.2688, + "step": 28655 + }, + { + "epoch": 2.34, + "learning_rate": 4.4328552803129075e-06, + "loss": 0.2898, + "step": 28656 + }, + { + "epoch": 2.34, + "learning_rate": 4.432312038244242e-06, + "loss": 0.2047, + "step": 28657 + }, + { + "epoch": 2.34, + "learning_rate": 4.431768796175576e-06, + "loss": 0.2025, + "step": 28658 + }, + { + "epoch": 2.34, + "learning_rate": 4.43122555410691e-06, + "loss": 0.5601, + "step": 28659 + }, + { + "epoch": 2.34, + "learning_rate": 4.430682312038244e-06, + "loss": 0.4813, + "step": 28660 + }, + { + "epoch": 2.34, + "learning_rate": 4.430139069969579e-06, + "loss": 0.1671, + "step": 28661 + }, + { + "epoch": 2.34, + "learning_rate": 4.429595827900913e-06, + "loss": 0.2859, + "step": 28662 + }, + { + "epoch": 2.34, + "learning_rate": 4.429052585832247e-06, + "loss": 0.3137, + "step": 28663 + }, + { + "epoch": 2.34, + "learning_rate": 4.428509343763581e-06, + "loss": 0.0775, + "step": 28664 + }, + { + "epoch": 2.34, + "learning_rate": 4.4279661016949155e-06, + "loss": 0.4588, + "step": 28665 + }, + { + "epoch": 2.34, + "learning_rate": 4.42742285962625e-06, + "loss": 0.2919, + "step": 28666 + }, + { + "epoch": 2.34, + "learning_rate": 4.426879617557584e-06, + "loss": 0.1639, + "step": 28667 + }, + { + "epoch": 2.34, + "learning_rate": 4.426336375488918e-06, + "loss": 0.0767, + "step": 28668 + }, + { + "epoch": 2.34, + "learning_rate": 4.4257931334202524e-06, + "loss": 0.3998, + "step": 28669 + }, + { + "epoch": 2.34, + "learning_rate": 4.425249891351587e-06, + "loss": 0.2144, + "step": 28670 + }, + { + "epoch": 2.34, + "learning_rate": 4.424706649282921e-06, + "loss": 0.3041, + "step": 28671 + }, + { + "epoch": 2.34, + "learning_rate": 4.424163407214255e-06, + "loss": 0.2851, + "step": 28672 + }, + { + "epoch": 2.34, + "learning_rate": 4.423620165145589e-06, + "loss": 0.3374, + "step": 28673 + }, + { + "epoch": 2.34, + "learning_rate": 4.423076923076924e-06, + "loss": 0.196, + "step": 28674 + }, + { + "epoch": 2.34, + "learning_rate": 4.422533681008258e-06, + "loss": 0.2256, + "step": 28675 + }, + { + "epoch": 2.34, + "learning_rate": 4.421990438939592e-06, + "loss": 0.3102, + "step": 28676 + }, + { + "epoch": 2.34, + "learning_rate": 4.421447196870926e-06, + "loss": 0.3197, + "step": 28677 + }, + { + "epoch": 2.34, + "learning_rate": 4.4209039548022605e-06, + "loss": 0.1606, + "step": 28678 + }, + { + "epoch": 2.34, + "learning_rate": 4.420360712733595e-06, + "loss": 0.378, + "step": 28679 + }, + { + "epoch": 2.34, + "learning_rate": 4.419817470664929e-06, + "loss": 0.3547, + "step": 28680 + }, + { + "epoch": 2.34, + "learning_rate": 4.419274228596263e-06, + "loss": 0.0691, + "step": 28681 + }, + { + "epoch": 2.34, + "learning_rate": 4.418730986527597e-06, + "loss": 0.3475, + "step": 28682 + }, + { + "epoch": 2.34, + "learning_rate": 4.418187744458931e-06, + "loss": 0.3384, + "step": 28683 + }, + { + "epoch": 2.34, + "learning_rate": 4.417644502390265e-06, + "loss": 0.4676, + "step": 28684 + }, + { + "epoch": 2.34, + "learning_rate": 4.417101260321599e-06, + "loss": 0.3496, + "step": 28685 + }, + { + "epoch": 2.34, + "learning_rate": 4.4165580182529335e-06, + "loss": 0.3389, + "step": 28686 + }, + { + "epoch": 2.34, + "learning_rate": 4.416014776184268e-06, + "loss": 0.2337, + "step": 28687 + }, + { + "epoch": 2.34, + "learning_rate": 4.415471534115602e-06, + "loss": 0.2193, + "step": 28688 + }, + { + "epoch": 2.34, + "learning_rate": 4.414928292046936e-06, + "loss": 0.1333, + "step": 28689 + }, + { + "epoch": 2.34, + "learning_rate": 4.414385049978271e-06, + "loss": 0.1339, + "step": 28690 + }, + { + "epoch": 2.34, + "learning_rate": 4.4138418079096055e-06, + "loss": 0.047, + "step": 28691 + }, + { + "epoch": 2.34, + "learning_rate": 4.413298565840939e-06, + "loss": 0.2172, + "step": 28692 + }, + { + "epoch": 2.34, + "learning_rate": 4.412755323772273e-06, + "loss": 0.372, + "step": 28693 + }, + { + "epoch": 2.34, + "learning_rate": 4.412212081703607e-06, + "loss": 0.4654, + "step": 28694 + }, + { + "epoch": 2.34, + "learning_rate": 4.411668839634942e-06, + "loss": 0.2492, + "step": 28695 + }, + { + "epoch": 2.34, + "learning_rate": 4.411125597566276e-06, + "loss": 0.2667, + "step": 28696 + }, + { + "epoch": 2.34, + "learning_rate": 4.41058235549761e-06, + "loss": 0.1696, + "step": 28697 + }, + { + "epoch": 2.34, + "learning_rate": 4.410039113428944e-06, + "loss": 0.4424, + "step": 28698 + }, + { + "epoch": 2.34, + "learning_rate": 4.4094958713602785e-06, + "loss": 0.0755, + "step": 28699 + }, + { + "epoch": 2.34, + "learning_rate": 4.408952629291613e-06, + "loss": 0.2011, + "step": 28700 + }, + { + "epoch": 2.34, + "learning_rate": 4.408409387222947e-06, + "loss": 0.0862, + "step": 28701 + }, + { + "epoch": 2.34, + "learning_rate": 4.407866145154281e-06, + "loss": 0.1977, + "step": 28702 + }, + { + "epoch": 2.34, + "learning_rate": 4.4073229030856154e-06, + "loss": 0.0881, + "step": 28703 + }, + { + "epoch": 2.34, + "learning_rate": 4.40677966101695e-06, + "loss": 0.2911, + "step": 28704 + }, + { + "epoch": 2.34, + "learning_rate": 4.406236418948284e-06, + "loss": 0.0818, + "step": 28705 + }, + { + "epoch": 2.34, + "learning_rate": 4.405693176879618e-06, + "loss": 0.2383, + "step": 28706 + }, + { + "epoch": 2.34, + "learning_rate": 4.405149934810952e-06, + "loss": 0.2215, + "step": 28707 + }, + { + "epoch": 2.34, + "learning_rate": 4.404606692742287e-06, + "loss": 0.281, + "step": 28708 + }, + { + "epoch": 2.34, + "learning_rate": 4.404063450673621e-06, + "loss": 0.1687, + "step": 28709 + }, + { + "epoch": 2.34, + "learning_rate": 4.403520208604955e-06, + "loss": 0.2572, + "step": 28710 + }, + { + "epoch": 2.34, + "learning_rate": 4.4029769665362884e-06, + "loss": 0.2966, + "step": 28711 + }, + { + "epoch": 2.34, + "learning_rate": 4.402433724467623e-06, + "loss": 0.3881, + "step": 28712 + }, + { + "epoch": 2.34, + "learning_rate": 4.401890482398957e-06, + "loss": 0.2428, + "step": 28713 + }, + { + "epoch": 2.34, + "learning_rate": 4.401347240330291e-06, + "loss": 0.1672, + "step": 28714 + }, + { + "epoch": 2.34, + "learning_rate": 4.400803998261625e-06, + "loss": 0.5492, + "step": 28715 + }, + { + "epoch": 2.34, + "learning_rate": 4.40026075619296e-06, + "loss": 0.3675, + "step": 28716 + }, + { + "epoch": 2.34, + "learning_rate": 4.399717514124295e-06, + "loss": 0.2431, + "step": 28717 + }, + { + "epoch": 2.34, + "learning_rate": 4.399174272055629e-06, + "loss": 0.1292, + "step": 28718 + }, + { + "epoch": 2.34, + "learning_rate": 4.398631029986963e-06, + "loss": 0.2985, + "step": 28719 + }, + { + "epoch": 2.34, + "learning_rate": 4.3980877879182965e-06, + "loss": 0.3552, + "step": 28720 + }, + { + "epoch": 2.34, + "learning_rate": 4.397544545849631e-06, + "loss": 0.3229, + "step": 28721 + }, + { + "epoch": 2.34, + "learning_rate": 4.397001303780965e-06, + "loss": 0.285, + "step": 28722 + }, + { + "epoch": 2.34, + "learning_rate": 4.396458061712299e-06, + "loss": 0.1812, + "step": 28723 + }, + { + "epoch": 2.34, + "learning_rate": 4.3959148196436334e-06, + "loss": 0.5732, + "step": 28724 + }, + { + "epoch": 2.34, + "learning_rate": 4.395371577574968e-06, + "loss": 0.4558, + "step": 28725 + }, + { + "epoch": 2.34, + "learning_rate": 4.394828335506302e-06, + "loss": 0.2761, + "step": 28726 + }, + { + "epoch": 2.34, + "learning_rate": 4.394285093437636e-06, + "loss": 0.2642, + "step": 28727 + }, + { + "epoch": 2.34, + "learning_rate": 4.39374185136897e-06, + "loss": 0.3706, + "step": 28728 + }, + { + "epoch": 2.34, + "learning_rate": 4.393198609300305e-06, + "loss": 0.0565, + "step": 28729 + }, + { + "epoch": 2.34, + "learning_rate": 4.392655367231639e-06, + "loss": 0.3494, + "step": 28730 + }, + { + "epoch": 2.34, + "learning_rate": 4.392112125162973e-06, + "loss": 0.1728, + "step": 28731 + }, + { + "epoch": 2.34, + "learning_rate": 4.391568883094307e-06, + "loss": 0.5992, + "step": 28732 + }, + { + "epoch": 2.34, + "learning_rate": 4.3910256410256415e-06, + "loss": 0.2556, + "step": 28733 + }, + { + "epoch": 2.34, + "learning_rate": 4.390482398956976e-06, + "loss": 0.0603, + "step": 28734 + }, + { + "epoch": 2.34, + "learning_rate": 4.38993915688831e-06, + "loss": 0.2061, + "step": 28735 + }, + { + "epoch": 2.34, + "learning_rate": 4.389395914819644e-06, + "loss": 0.2042, + "step": 28736 + }, + { + "epoch": 2.34, + "learning_rate": 4.3888526727509784e-06, + "loss": 0.2784, + "step": 28737 + }, + { + "epoch": 2.34, + "learning_rate": 4.388309430682313e-06, + "loss": 0.1206, + "step": 28738 + }, + { + "epoch": 2.34, + "learning_rate": 4.387766188613646e-06, + "loss": 0.2428, + "step": 28739 + }, + { + "epoch": 2.34, + "learning_rate": 4.38722294654498e-06, + "loss": 0.259, + "step": 28740 + }, + { + "epoch": 2.34, + "learning_rate": 4.3866797044763145e-06, + "loss": 0.2275, + "step": 28741 + }, + { + "epoch": 2.34, + "learning_rate": 4.386136462407649e-06, + "loss": 0.0503, + "step": 28742 + }, + { + "epoch": 2.34, + "learning_rate": 4.385593220338983e-06, + "loss": 0.3544, + "step": 28743 + }, + { + "epoch": 2.34, + "learning_rate": 4.385049978270318e-06, + "loss": 0.1568, + "step": 28744 + }, + { + "epoch": 2.34, + "learning_rate": 4.384506736201652e-06, + "loss": 0.3226, + "step": 28745 + }, + { + "epoch": 2.34, + "learning_rate": 4.3839634941329865e-06, + "loss": 0.1523, + "step": 28746 + }, + { + "epoch": 2.34, + "learning_rate": 4.383420252064321e-06, + "loss": 0.301, + "step": 28747 + }, + { + "epoch": 2.34, + "learning_rate": 4.382877009995655e-06, + "loss": 0.4263, + "step": 28748 + }, + { + "epoch": 2.34, + "learning_rate": 4.382333767926988e-06, + "loss": 0.1829, + "step": 28749 + }, + { + "epoch": 2.34, + "learning_rate": 4.381790525858323e-06, + "loss": 0.3249, + "step": 28750 + }, + { + "epoch": 2.34, + "eval_accuracy": 0.8439123790117168, + "eval_loss": 0.48291608691215515, + "eval_runtime": 22.3389, + "eval_samples_per_second": 439.367, + "eval_steps_per_second": 3.447, + "step": 28750 + }, + { + "epoch": 2.34, + "learning_rate": 4.381247283789657e-06, + "loss": 0.1973, + "step": 28751 + }, + { + "epoch": 2.34, + "learning_rate": 4.380704041720991e-06, + "loss": 0.2066, + "step": 28752 + }, + { + "epoch": 2.34, + "learning_rate": 4.380160799652325e-06, + "loss": 0.238, + "step": 28753 + }, + { + "epoch": 2.34, + "learning_rate": 4.3796175575836595e-06, + "loss": 0.1179, + "step": 28754 + }, + { + "epoch": 2.34, + "learning_rate": 4.379074315514994e-06, + "loss": 0.2967, + "step": 28755 + }, + { + "epoch": 2.34, + "learning_rate": 4.378531073446328e-06, + "loss": 0.3733, + "step": 28756 + }, + { + "epoch": 2.34, + "learning_rate": 4.377987831377662e-06, + "loss": 0.1829, + "step": 28757 + }, + { + "epoch": 2.34, + "learning_rate": 4.3774445893089964e-06, + "loss": 0.177, + "step": 28758 + }, + { + "epoch": 2.34, + "learning_rate": 4.376901347240331e-06, + "loss": 0.2841, + "step": 28759 + }, + { + "epoch": 2.34, + "learning_rate": 4.376358105171665e-06, + "loss": 0.3074, + "step": 28760 + }, + { + "epoch": 2.34, + "learning_rate": 4.375814863102999e-06, + "loss": 0.0656, + "step": 28761 + }, + { + "epoch": 2.34, + "learning_rate": 4.375271621034333e-06, + "loss": 0.0977, + "step": 28762 + }, + { + "epoch": 2.34, + "learning_rate": 4.374728378965668e-06, + "loss": 0.1446, + "step": 28763 + }, + { + "epoch": 2.34, + "learning_rate": 4.374185136897002e-06, + "loss": 0.1462, + "step": 28764 + }, + { + "epoch": 2.34, + "learning_rate": 4.373641894828336e-06, + "loss": 0.2385, + "step": 28765 + }, + { + "epoch": 2.34, + "learning_rate": 4.37309865275967e-06, + "loss": 0.1142, + "step": 28766 + }, + { + "epoch": 2.34, + "learning_rate": 4.3725554106910045e-06, + "loss": 0.2162, + "step": 28767 + }, + { + "epoch": 2.34, + "learning_rate": 4.372012168622338e-06, + "loss": 0.1064, + "step": 28768 + }, + { + "epoch": 2.34, + "learning_rate": 4.371468926553672e-06, + "loss": 0.3974, + "step": 28769 + }, + { + "epoch": 2.34, + "learning_rate": 4.370925684485006e-06, + "loss": 0.283, + "step": 28770 + }, + { + "epoch": 2.34, + "learning_rate": 4.370382442416341e-06, + "loss": 0.3, + "step": 28771 + }, + { + "epoch": 2.34, + "learning_rate": 4.369839200347676e-06, + "loss": 0.2568, + "step": 28772 + }, + { + "epoch": 2.34, + "learning_rate": 4.36929595827901e-06, + "loss": 0.1929, + "step": 28773 + }, + { + "epoch": 2.34, + "learning_rate": 4.368752716210344e-06, + "loss": 0.4985, + "step": 28774 + }, + { + "epoch": 2.34, + "learning_rate": 4.368209474141678e-06, + "loss": 0.3323, + "step": 28775 + }, + { + "epoch": 2.34, + "learning_rate": 4.3676662320730126e-06, + "loss": 0.4581, + "step": 28776 + }, + { + "epoch": 2.34, + "learning_rate": 4.367122990004346e-06, + "loss": 0.1466, + "step": 28777 + }, + { + "epoch": 2.35, + "learning_rate": 4.36657974793568e-06, + "loss": 0.2259, + "step": 28778 + }, + { + "epoch": 2.35, + "learning_rate": 4.366036505867014e-06, + "loss": 0.2528, + "step": 28779 + }, + { + "epoch": 2.35, + "learning_rate": 4.365493263798349e-06, + "loss": 0.2847, + "step": 28780 + }, + { + "epoch": 2.35, + "learning_rate": 4.364950021729683e-06, + "loss": 0.2627, + "step": 28781 + }, + { + "epoch": 2.35, + "learning_rate": 4.364406779661017e-06, + "loss": 0.0933, + "step": 28782 + }, + { + "epoch": 2.35, + "learning_rate": 4.363863537592351e-06, + "loss": 0.4969, + "step": 28783 + }, + { + "epoch": 2.35, + "learning_rate": 4.3633202955236856e-06, + "loss": 0.2133, + "step": 28784 + }, + { + "epoch": 2.35, + "learning_rate": 4.36277705345502e-06, + "loss": 0.1776, + "step": 28785 + }, + { + "epoch": 2.35, + "learning_rate": 4.362233811386354e-06, + "loss": 0.2186, + "step": 28786 + }, + { + "epoch": 2.35, + "learning_rate": 4.361690569317688e-06, + "loss": 0.2177, + "step": 28787 + }, + { + "epoch": 2.35, + "learning_rate": 4.3611473272490225e-06, + "loss": 0.0829, + "step": 28788 + }, + { + "epoch": 2.35, + "learning_rate": 4.360604085180357e-06, + "loss": 0.3742, + "step": 28789 + }, + { + "epoch": 2.35, + "learning_rate": 4.360060843111691e-06, + "loss": 0.0716, + "step": 28790 + }, + { + "epoch": 2.35, + "learning_rate": 4.359517601043025e-06, + "loss": 0.2462, + "step": 28791 + }, + { + "epoch": 2.35, + "learning_rate": 4.358974358974359e-06, + "loss": 0.1053, + "step": 28792 + }, + { + "epoch": 2.35, + "learning_rate": 4.358431116905694e-06, + "loss": 0.2792, + "step": 28793 + }, + { + "epoch": 2.35, + "learning_rate": 4.357887874837028e-06, + "loss": 0.215, + "step": 28794 + }, + { + "epoch": 2.35, + "learning_rate": 4.357344632768362e-06, + "loss": 0.1753, + "step": 28795 + }, + { + "epoch": 2.35, + "learning_rate": 4.3568013906996955e-06, + "loss": 0.3116, + "step": 28796 + }, + { + "epoch": 2.35, + "learning_rate": 4.35625814863103e-06, + "loss": 0.2041, + "step": 28797 + }, + { + "epoch": 2.35, + "learning_rate": 4.355714906562365e-06, + "loss": 0.0728, + "step": 28798 + }, + { + "epoch": 2.35, + "learning_rate": 4.355171664493699e-06, + "loss": 0.215, + "step": 28799 + }, + { + "epoch": 2.35, + "learning_rate": 4.354628422425033e-06, + "loss": 0.2686, + "step": 28800 + }, + { + "epoch": 2.35, + "learning_rate": 4.3540851803563675e-06, + "loss": 0.2837, + "step": 28801 + }, + { + "epoch": 2.35, + "learning_rate": 4.353541938287702e-06, + "loss": 0.289, + "step": 28802 + }, + { + "epoch": 2.35, + "learning_rate": 4.352998696219036e-06, + "loss": 0.1796, + "step": 28803 + }, + { + "epoch": 2.35, + "learning_rate": 4.35245545415037e-06, + "loss": 0.2669, + "step": 28804 + }, + { + "epoch": 2.35, + "learning_rate": 4.351912212081704e-06, + "loss": 0.2213, + "step": 28805 + }, + { + "epoch": 2.35, + "learning_rate": 4.351368970013038e-06, + "loss": 0.0466, + "step": 28806 + }, + { + "epoch": 2.35, + "learning_rate": 4.350825727944372e-06, + "loss": 0.1815, + "step": 28807 + }, + { + "epoch": 2.35, + "learning_rate": 4.350282485875706e-06, + "loss": 0.1624, + "step": 28808 + }, + { + "epoch": 2.35, + "learning_rate": 4.3497392438070405e-06, + "loss": 0.1588, + "step": 28809 + }, + { + "epoch": 2.35, + "learning_rate": 4.349196001738375e-06, + "loss": 0.3774, + "step": 28810 + }, + { + "epoch": 2.35, + "learning_rate": 4.348652759669709e-06, + "loss": 0.2763, + "step": 28811 + }, + { + "epoch": 2.35, + "learning_rate": 4.348109517601043e-06, + "loss": 0.6834, + "step": 28812 + }, + { + "epoch": 2.35, + "learning_rate": 4.347566275532377e-06, + "loss": 0.2093, + "step": 28813 + }, + { + "epoch": 2.35, + "learning_rate": 4.347023033463712e-06, + "loss": 0.3348, + "step": 28814 + }, + { + "epoch": 2.35, + "learning_rate": 4.346479791395046e-06, + "loss": 0.082, + "step": 28815 + }, + { + "epoch": 2.35, + "learning_rate": 4.34593654932638e-06, + "loss": 0.1768, + "step": 28816 + }, + { + "epoch": 2.35, + "learning_rate": 4.345393307257714e-06, + "loss": 0.1526, + "step": 28817 + }, + { + "epoch": 2.35, + "learning_rate": 4.3448500651890486e-06, + "loss": 0.2346, + "step": 28818 + }, + { + "epoch": 2.35, + "learning_rate": 4.344306823120383e-06, + "loss": 0.1619, + "step": 28819 + }, + { + "epoch": 2.35, + "learning_rate": 4.343763581051717e-06, + "loss": 0.2367, + "step": 28820 + }, + { + "epoch": 2.35, + "learning_rate": 4.343220338983051e-06, + "loss": 0.2614, + "step": 28821 + }, + { + "epoch": 2.35, + "learning_rate": 4.3426770969143855e-06, + "loss": 0.1039, + "step": 28822 + }, + { + "epoch": 2.35, + "learning_rate": 4.34213385484572e-06, + "loss": 0.3204, + "step": 28823 + }, + { + "epoch": 2.35, + "learning_rate": 4.341590612777054e-06, + "loss": 0.1991, + "step": 28824 + }, + { + "epoch": 2.35, + "learning_rate": 4.341047370708388e-06, + "loss": 0.5134, + "step": 28825 + }, + { + "epoch": 2.35, + "learning_rate": 4.340504128639722e-06, + "loss": 0.3871, + "step": 28826 + }, + { + "epoch": 2.35, + "learning_rate": 4.339960886571057e-06, + "loss": 0.2218, + "step": 28827 + }, + { + "epoch": 2.35, + "learning_rate": 4.339417644502391e-06, + "loss": 0.1704, + "step": 28828 + }, + { + "epoch": 2.35, + "learning_rate": 4.338874402433725e-06, + "loss": 0.1454, + "step": 28829 + }, + { + "epoch": 2.35, + "learning_rate": 4.338331160365059e-06, + "loss": 0.3503, + "step": 28830 + }, + { + "epoch": 2.35, + "learning_rate": 4.3377879182963936e-06, + "loss": 0.3618, + "step": 28831 + }, + { + "epoch": 2.35, + "learning_rate": 4.337244676227728e-06, + "loss": 0.3476, + "step": 28832 + }, + { + "epoch": 2.35, + "learning_rate": 4.336701434159062e-06, + "loss": 0.0509, + "step": 28833 + }, + { + "epoch": 2.35, + "learning_rate": 4.336158192090395e-06, + "loss": 0.0963, + "step": 28834 + }, + { + "epoch": 2.35, + "learning_rate": 4.33561495002173e-06, + "loss": 0.3778, + "step": 28835 + }, + { + "epoch": 2.35, + "learning_rate": 4.335071707953064e-06, + "loss": 0.116, + "step": 28836 + }, + { + "epoch": 2.35, + "learning_rate": 4.334528465884398e-06, + "loss": 0.1701, + "step": 28837 + }, + { + "epoch": 2.35, + "learning_rate": 4.333985223815732e-06, + "loss": 0.3706, + "step": 28838 + }, + { + "epoch": 2.35, + "learning_rate": 4.3334419817470666e-06, + "loss": 0.3022, + "step": 28839 + }, + { + "epoch": 2.35, + "learning_rate": 4.332898739678401e-06, + "loss": 0.1625, + "step": 28840 + }, + { + "epoch": 2.35, + "learning_rate": 4.332355497609735e-06, + "loss": 0.115, + "step": 28841 + }, + { + "epoch": 2.35, + "learning_rate": 4.331812255541069e-06, + "loss": 0.2631, + "step": 28842 + }, + { + "epoch": 2.35, + "learning_rate": 4.331269013472404e-06, + "loss": 0.203, + "step": 28843 + }, + { + "epoch": 2.35, + "learning_rate": 4.330725771403738e-06, + "loss": 0.1038, + "step": 28844 + }, + { + "epoch": 2.35, + "learning_rate": 4.330182529335072e-06, + "loss": 0.1701, + "step": 28845 + }, + { + "epoch": 2.35, + "learning_rate": 4.329639287266406e-06, + "loss": 0.0534, + "step": 28846 + }, + { + "epoch": 2.35, + "learning_rate": 4.32909604519774e-06, + "loss": 0.1019, + "step": 28847 + }, + { + "epoch": 2.35, + "learning_rate": 4.328552803129075e-06, + "loss": 0.193, + "step": 28848 + }, + { + "epoch": 2.35, + "learning_rate": 4.328009561060409e-06, + "loss": 0.3135, + "step": 28849 + }, + { + "epoch": 2.35, + "learning_rate": 4.327466318991743e-06, + "loss": 0.1866, + "step": 28850 + }, + { + "epoch": 2.35, + "learning_rate": 4.326923076923077e-06, + "loss": 0.2481, + "step": 28851 + }, + { + "epoch": 2.35, + "learning_rate": 4.3263798348544116e-06, + "loss": 0.1078, + "step": 28852 + }, + { + "epoch": 2.35, + "learning_rate": 4.325836592785746e-06, + "loss": 0.3234, + "step": 28853 + }, + { + "epoch": 2.35, + "learning_rate": 4.32529335071708e-06, + "loss": 0.4077, + "step": 28854 + }, + { + "epoch": 2.35, + "learning_rate": 4.324750108648414e-06, + "loss": 0.3914, + "step": 28855 + }, + { + "epoch": 2.35, + "learning_rate": 4.3242068665797485e-06, + "loss": 0.3524, + "step": 28856 + }, + { + "epoch": 2.35, + "learning_rate": 4.323663624511083e-06, + "loss": 0.4193, + "step": 28857 + }, + { + "epoch": 2.35, + "learning_rate": 4.323120382442417e-06, + "loss": 0.1178, + "step": 28858 + }, + { + "epoch": 2.35, + "learning_rate": 4.322577140373751e-06, + "loss": 0.3161, + "step": 28859 + }, + { + "epoch": 2.35, + "learning_rate": 4.322033898305085e-06, + "loss": 0.2495, + "step": 28860 + }, + { + "epoch": 2.35, + "learning_rate": 4.32149065623642e-06, + "loss": 0.2158, + "step": 28861 + }, + { + "epoch": 2.35, + "learning_rate": 4.320947414167754e-06, + "loss": 0.3234, + "step": 28862 + }, + { + "epoch": 2.35, + "learning_rate": 4.320404172099087e-06, + "loss": 0.3065, + "step": 28863 + }, + { + "epoch": 2.35, + "learning_rate": 4.3198609300304215e-06, + "loss": 0.0915, + "step": 28864 + }, + { + "epoch": 2.35, + "learning_rate": 4.319317687961756e-06, + "loss": 0.3683, + "step": 28865 + }, + { + "epoch": 2.35, + "learning_rate": 4.31877444589309e-06, + "loss": 0.2945, + "step": 28866 + }, + { + "epoch": 2.35, + "learning_rate": 4.318231203824424e-06, + "loss": 0.0954, + "step": 28867 + }, + { + "epoch": 2.35, + "learning_rate": 4.317687961755758e-06, + "loss": 0.2255, + "step": 28868 + }, + { + "epoch": 2.35, + "learning_rate": 4.317144719687093e-06, + "loss": 0.3754, + "step": 28869 + }, + { + "epoch": 2.35, + "learning_rate": 4.316601477618428e-06, + "loss": 0.2082, + "step": 28870 + }, + { + "epoch": 2.35, + "learning_rate": 4.316058235549762e-06, + "loss": 0.2018, + "step": 28871 + }, + { + "epoch": 2.35, + "learning_rate": 4.315514993481095e-06, + "loss": 0.4653, + "step": 28872 + }, + { + "epoch": 2.35, + "learning_rate": 4.3149717514124296e-06, + "loss": 0.192, + "step": 28873 + }, + { + "epoch": 2.35, + "learning_rate": 4.314428509343764e-06, + "loss": 0.2987, + "step": 28874 + }, + { + "epoch": 2.35, + "learning_rate": 4.313885267275098e-06, + "loss": 0.2057, + "step": 28875 + }, + { + "epoch": 2.35, + "learning_rate": 4.313342025206432e-06, + "loss": 0.2172, + "step": 28876 + }, + { + "epoch": 2.35, + "learning_rate": 4.3127987831377665e-06, + "loss": 0.316, + "step": 28877 + }, + { + "epoch": 2.35, + "learning_rate": 4.312255541069101e-06, + "loss": 0.2086, + "step": 28878 + }, + { + "epoch": 2.35, + "learning_rate": 4.311712299000435e-06, + "loss": 0.1794, + "step": 28879 + }, + { + "epoch": 2.35, + "learning_rate": 4.311169056931769e-06, + "loss": 0.2754, + "step": 28880 + }, + { + "epoch": 2.35, + "learning_rate": 4.310625814863103e-06, + "loss": 0.4346, + "step": 28881 + }, + { + "epoch": 2.35, + "learning_rate": 4.310082572794438e-06, + "loss": 0.278, + "step": 28882 + }, + { + "epoch": 2.35, + "learning_rate": 4.309539330725772e-06, + "loss": 0.1882, + "step": 28883 + }, + { + "epoch": 2.35, + "learning_rate": 4.308996088657106e-06, + "loss": 0.1548, + "step": 28884 + }, + { + "epoch": 2.35, + "learning_rate": 4.30845284658844e-06, + "loss": 0.3164, + "step": 28885 + }, + { + "epoch": 2.35, + "learning_rate": 4.3079096045197745e-06, + "loss": 0.1438, + "step": 28886 + }, + { + "epoch": 2.35, + "learning_rate": 4.307366362451109e-06, + "loss": 0.1194, + "step": 28887 + }, + { + "epoch": 2.35, + "learning_rate": 4.306823120382443e-06, + "loss": 0.3277, + "step": 28888 + }, + { + "epoch": 2.35, + "learning_rate": 4.306279878313777e-06, + "loss": 0.315, + "step": 28889 + }, + { + "epoch": 2.35, + "learning_rate": 4.3057366362451115e-06, + "loss": 0.1905, + "step": 28890 + }, + { + "epoch": 2.35, + "learning_rate": 4.305193394176445e-06, + "loss": 0.1592, + "step": 28891 + }, + { + "epoch": 2.35, + "learning_rate": 4.304650152107779e-06, + "loss": 0.4007, + "step": 28892 + }, + { + "epoch": 2.35, + "learning_rate": 4.304106910039113e-06, + "loss": 0.2007, + "step": 28893 + }, + { + "epoch": 2.35, + "learning_rate": 4.3035636679704475e-06, + "loss": 0.1134, + "step": 28894 + }, + { + "epoch": 2.35, + "learning_rate": 4.303020425901782e-06, + "loss": 0.2835, + "step": 28895 + }, + { + "epoch": 2.35, + "learning_rate": 4.302477183833116e-06, + "loss": 0.2179, + "step": 28896 + }, + { + "epoch": 2.35, + "learning_rate": 4.301933941764451e-06, + "loss": 0.1344, + "step": 28897 + }, + { + "epoch": 2.35, + "learning_rate": 4.301390699695785e-06, + "loss": 0.1795, + "step": 28898 + }, + { + "epoch": 2.35, + "learning_rate": 4.3008474576271195e-06, + "loss": 0.1155, + "step": 28899 + }, + { + "epoch": 2.35, + "learning_rate": 4.300304215558454e-06, + "loss": 0.1719, + "step": 28900 + }, + { + "epoch": 2.36, + "learning_rate": 4.299760973489787e-06, + "loss": 0.5287, + "step": 28901 + }, + { + "epoch": 2.36, + "learning_rate": 4.299217731421121e-06, + "loss": 0.3148, + "step": 28902 + }, + { + "epoch": 2.36, + "learning_rate": 4.298674489352456e-06, + "loss": 0.4388, + "step": 28903 + }, + { + "epoch": 2.36, + "learning_rate": 4.29813124728379e-06, + "loss": 0.0939, + "step": 28904 + }, + { + "epoch": 2.36, + "learning_rate": 4.297588005215124e-06, + "loss": 0.298, + "step": 28905 + }, + { + "epoch": 2.36, + "learning_rate": 4.297044763146458e-06, + "loss": 0.3225, + "step": 28906 + }, + { + "epoch": 2.36, + "learning_rate": 4.2965015210777925e-06, + "loss": 0.2121, + "step": 28907 + }, + { + "epoch": 2.36, + "learning_rate": 4.295958279009127e-06, + "loss": 0.2045, + "step": 28908 + }, + { + "epoch": 2.36, + "learning_rate": 4.295415036940461e-06, + "loss": 0.2877, + "step": 28909 + }, + { + "epoch": 2.36, + "learning_rate": 4.294871794871795e-06, + "loss": 0.0955, + "step": 28910 + }, + { + "epoch": 2.36, + "learning_rate": 4.2943285528031295e-06, + "loss": 0.169, + "step": 28911 + }, + { + "epoch": 2.36, + "learning_rate": 4.293785310734464e-06, + "loss": 0.4327, + "step": 28912 + }, + { + "epoch": 2.36, + "learning_rate": 4.293242068665798e-06, + "loss": 0.2329, + "step": 28913 + }, + { + "epoch": 2.36, + "learning_rate": 4.292698826597132e-06, + "loss": 0.1233, + "step": 28914 + }, + { + "epoch": 2.36, + "learning_rate": 4.292155584528466e-06, + "loss": 0.2834, + "step": 28915 + }, + { + "epoch": 2.36, + "learning_rate": 4.291612342459801e-06, + "loss": 0.3769, + "step": 28916 + }, + { + "epoch": 2.36, + "learning_rate": 4.291069100391135e-06, + "loss": 0.3408, + "step": 28917 + }, + { + "epoch": 2.36, + "learning_rate": 4.290525858322469e-06, + "loss": 0.1823, + "step": 28918 + }, + { + "epoch": 2.36, + "learning_rate": 4.289982616253803e-06, + "loss": 0.0699, + "step": 28919 + }, + { + "epoch": 2.36, + "learning_rate": 4.289439374185137e-06, + "loss": 0.198, + "step": 28920 + }, + { + "epoch": 2.36, + "learning_rate": 4.288896132116471e-06, + "loss": 0.166, + "step": 28921 + }, + { + "epoch": 2.36, + "learning_rate": 4.288352890047805e-06, + "loss": 0.3593, + "step": 28922 + }, + { + "epoch": 2.36, + "learning_rate": 4.287809647979139e-06, + "loss": 0.2062, + "step": 28923 + }, + { + "epoch": 2.36, + "learning_rate": 4.2872664059104745e-06, + "loss": 0.2192, + "step": 28924 + }, + { + "epoch": 2.36, + "learning_rate": 4.286723163841809e-06, + "loss": 0.1385, + "step": 28925 + }, + { + "epoch": 2.36, + "learning_rate": 4.286179921773143e-06, + "loss": 0.3213, + "step": 28926 + }, + { + "epoch": 2.36, + "learning_rate": 4.285636679704477e-06, + "loss": 0.1162, + "step": 28927 + }, + { + "epoch": 2.36, + "learning_rate": 4.285093437635811e-06, + "loss": 0.2243, + "step": 28928 + }, + { + "epoch": 2.36, + "learning_rate": 4.284550195567145e-06, + "loss": 0.2023, + "step": 28929 + }, + { + "epoch": 2.36, + "learning_rate": 4.284006953498479e-06, + "loss": 0.2858, + "step": 28930 + }, + { + "epoch": 2.36, + "learning_rate": 4.283463711429813e-06, + "loss": 0.2523, + "step": 28931 + }, + { + "epoch": 2.36, + "learning_rate": 4.2829204693611475e-06, + "loss": 0.2289, + "step": 28932 + }, + { + "epoch": 2.36, + "learning_rate": 4.282377227292482e-06, + "loss": 0.3236, + "step": 28933 + }, + { + "epoch": 2.36, + "learning_rate": 4.281833985223816e-06, + "loss": 0.0327, + "step": 28934 + }, + { + "epoch": 2.36, + "learning_rate": 4.28129074315515e-06, + "loss": 0.2212, + "step": 28935 + }, + { + "epoch": 2.36, + "learning_rate": 4.280747501086484e-06, + "loss": 0.3122, + "step": 28936 + }, + { + "epoch": 2.36, + "learning_rate": 4.280204259017819e-06, + "loss": 0.3507, + "step": 28937 + }, + { + "epoch": 2.36, + "learning_rate": 4.279661016949153e-06, + "loss": 0.0703, + "step": 28938 + }, + { + "epoch": 2.36, + "learning_rate": 4.279117774880487e-06, + "loss": 0.1726, + "step": 28939 + }, + { + "epoch": 2.36, + "learning_rate": 4.278574532811821e-06, + "loss": 0.1402, + "step": 28940 + }, + { + "epoch": 2.36, + "learning_rate": 4.2780312907431555e-06, + "loss": 0.2601, + "step": 28941 + }, + { + "epoch": 2.36, + "learning_rate": 4.27748804867449e-06, + "loss": 0.3501, + "step": 28942 + }, + { + "epoch": 2.36, + "learning_rate": 4.276944806605824e-06, + "loss": 0.3651, + "step": 28943 + }, + { + "epoch": 2.36, + "learning_rate": 4.276401564537158e-06, + "loss": 0.4475, + "step": 28944 + }, + { + "epoch": 2.36, + "learning_rate": 4.2758583224684925e-06, + "loss": 0.1225, + "step": 28945 + }, + { + "epoch": 2.36, + "learning_rate": 4.275315080399827e-06, + "loss": 0.4828, + "step": 28946 + }, + { + "epoch": 2.36, + "learning_rate": 4.274771838331161e-06, + "loss": 0.2425, + "step": 28947 + }, + { + "epoch": 2.36, + "learning_rate": 4.274228596262494e-06, + "loss": 0.1686, + "step": 28948 + }, + { + "epoch": 2.36, + "learning_rate": 4.2736853541938285e-06, + "loss": 0.166, + "step": 28949 + }, + { + "epoch": 2.36, + "learning_rate": 4.273142112125163e-06, + "loss": 0.3689, + "step": 28950 + }, + { + "epoch": 2.36, + "learning_rate": 4.272598870056498e-06, + "loss": 0.1639, + "step": 28951 + }, + { + "epoch": 2.36, + "learning_rate": 4.272055627987832e-06, + "loss": 0.1942, + "step": 28952 + }, + { + "epoch": 2.36, + "learning_rate": 4.271512385919166e-06, + "loss": 0.0709, + "step": 28953 + }, + { + "epoch": 2.36, + "learning_rate": 4.2709691438505005e-06, + "loss": 0.1613, + "step": 28954 + }, + { + "epoch": 2.36, + "learning_rate": 4.270425901781835e-06, + "loss": 0.3469, + "step": 28955 + }, + { + "epoch": 2.36, + "learning_rate": 4.269882659713169e-06, + "loss": 0.1629, + "step": 28956 + }, + { + "epoch": 2.36, + "learning_rate": 4.269339417644503e-06, + "loss": 0.2939, + "step": 28957 + }, + { + "epoch": 2.36, + "learning_rate": 4.268796175575837e-06, + "loss": 0.4619, + "step": 28958 + }, + { + "epoch": 2.36, + "learning_rate": 4.268252933507171e-06, + "loss": 0.3416, + "step": 28959 + }, + { + "epoch": 2.36, + "learning_rate": 4.267709691438505e-06, + "loss": 0.1545, + "step": 28960 + }, + { + "epoch": 2.36, + "learning_rate": 4.267166449369839e-06, + "loss": 0.0622, + "step": 28961 + }, + { + "epoch": 2.36, + "learning_rate": 4.2666232073011735e-06, + "loss": 0.249, + "step": 28962 + }, + { + "epoch": 2.36, + "learning_rate": 4.266079965232508e-06, + "loss": 0.7773, + "step": 28963 + }, + { + "epoch": 2.36, + "learning_rate": 4.265536723163842e-06, + "loss": 0.331, + "step": 28964 + }, + { + "epoch": 2.36, + "learning_rate": 4.264993481095176e-06, + "loss": 0.2902, + "step": 28965 + }, + { + "epoch": 2.36, + "learning_rate": 4.2644502390265105e-06, + "loss": 0.1588, + "step": 28966 + }, + { + "epoch": 2.36, + "learning_rate": 4.263906996957845e-06, + "loss": 0.1574, + "step": 28967 + }, + { + "epoch": 2.36, + "learning_rate": 4.263363754889179e-06, + "loss": 0.7799, + "step": 28968 + }, + { + "epoch": 2.36, + "learning_rate": 4.262820512820513e-06, + "loss": 0.3641, + "step": 28969 + }, + { + "epoch": 2.36, + "learning_rate": 4.262277270751847e-06, + "loss": 0.1567, + "step": 28970 + }, + { + "epoch": 2.36, + "learning_rate": 4.261734028683182e-06, + "loss": 0.1874, + "step": 28971 + }, + { + "epoch": 2.36, + "learning_rate": 4.261190786614516e-06, + "loss": 0.0988, + "step": 28972 + }, + { + "epoch": 2.36, + "learning_rate": 4.26064754454585e-06, + "loss": 0.2453, + "step": 28973 + }, + { + "epoch": 2.36, + "learning_rate": 4.260104302477184e-06, + "loss": 0.1231, + "step": 28974 + }, + { + "epoch": 2.36, + "learning_rate": 4.2595610604085185e-06, + "loss": 0.2687, + "step": 28975 + }, + { + "epoch": 2.36, + "learning_rate": 4.259017818339853e-06, + "loss": 0.3126, + "step": 28976 + }, + { + "epoch": 2.36, + "learning_rate": 4.258474576271186e-06, + "loss": 0.1676, + "step": 28977 + }, + { + "epoch": 2.36, + "learning_rate": 4.257931334202521e-06, + "loss": 0.159, + "step": 28978 + }, + { + "epoch": 2.36, + "learning_rate": 4.2573880921338554e-06, + "loss": 0.1798, + "step": 28979 + }, + { + "epoch": 2.36, + "learning_rate": 4.25684485006519e-06, + "loss": 0.2245, + "step": 28980 + }, + { + "epoch": 2.36, + "learning_rate": 4.256301607996524e-06, + "loss": 0.0798, + "step": 28981 + }, + { + "epoch": 2.36, + "learning_rate": 4.255758365927858e-06, + "loss": 0.2196, + "step": 28982 + }, + { + "epoch": 2.36, + "learning_rate": 4.255215123859192e-06, + "loss": 0.2301, + "step": 28983 + }, + { + "epoch": 2.36, + "learning_rate": 4.254671881790527e-06, + "loss": 0.2402, + "step": 28984 + }, + { + "epoch": 2.36, + "learning_rate": 4.254128639721861e-06, + "loss": 0.15, + "step": 28985 + }, + { + "epoch": 2.36, + "learning_rate": 4.253585397653194e-06, + "loss": 0.2034, + "step": 28986 + }, + { + "epoch": 2.36, + "learning_rate": 4.2530421555845284e-06, + "loss": 0.2136, + "step": 28987 + }, + { + "epoch": 2.36, + "learning_rate": 4.252498913515863e-06, + "loss": 0.3054, + "step": 28988 + }, + { + "epoch": 2.36, + "learning_rate": 4.251955671447197e-06, + "loss": 0.2852, + "step": 28989 + }, + { + "epoch": 2.36, + "learning_rate": 4.251412429378531e-06, + "loss": 0.1404, + "step": 28990 + }, + { + "epoch": 2.36, + "learning_rate": 4.250869187309865e-06, + "loss": 0.1902, + "step": 28991 + }, + { + "epoch": 2.36, + "learning_rate": 4.2503259452412e-06, + "loss": 0.1804, + "step": 28992 + }, + { + "epoch": 2.36, + "learning_rate": 4.249782703172534e-06, + "loss": 0.2077, + "step": 28993 + }, + { + "epoch": 2.36, + "learning_rate": 4.249239461103868e-06, + "loss": 0.2032, + "step": 28994 + }, + { + "epoch": 2.36, + "learning_rate": 4.248696219035202e-06, + "loss": 0.2271, + "step": 28995 + }, + { + "epoch": 2.36, + "learning_rate": 4.2481529769665365e-06, + "loss": 0.4547, + "step": 28996 + }, + { + "epoch": 2.36, + "learning_rate": 4.247609734897871e-06, + "loss": 0.0966, + "step": 28997 + }, + { + "epoch": 2.36, + "learning_rate": 4.247066492829205e-06, + "loss": 0.2584, + "step": 28998 + }, + { + "epoch": 2.36, + "learning_rate": 4.246523250760539e-06, + "loss": 0.3511, + "step": 28999 + }, + { + "epoch": 2.36, + "learning_rate": 4.2459800086918734e-06, + "loss": 0.2708, + "step": 29000 + }, + { + "epoch": 2.36, + "eval_accuracy": 0.8407539480387163, + "eval_loss": 0.4971449375152588, + "eval_runtime": 22.4944, + "eval_samples_per_second": 436.331, + "eval_steps_per_second": 3.423, + "step": 29000 + }, + { + "epoch": 2.36, + "learning_rate": 4.245436766623208e-06, + "loss": 0.122, + "step": 29001 + }, + { + "epoch": 2.36, + "learning_rate": 4.244893524554542e-06, + "loss": 0.1233, + "step": 29002 + }, + { + "epoch": 2.36, + "learning_rate": 4.244350282485876e-06, + "loss": 0.4834, + "step": 29003 + }, + { + "epoch": 2.36, + "learning_rate": 4.24380704041721e-06, + "loss": 0.3965, + "step": 29004 + }, + { + "epoch": 2.36, + "learning_rate": 4.243263798348545e-06, + "loss": 0.0705, + "step": 29005 + }, + { + "epoch": 2.36, + "learning_rate": 4.242720556279879e-06, + "loss": 0.2356, + "step": 29006 + }, + { + "epoch": 2.36, + "learning_rate": 4.242177314211213e-06, + "loss": 0.316, + "step": 29007 + }, + { + "epoch": 2.36, + "learning_rate": 4.241634072142547e-06, + "loss": 0.2535, + "step": 29008 + }, + { + "epoch": 2.36, + "learning_rate": 4.2410908300738815e-06, + "loss": 0.2212, + "step": 29009 + }, + { + "epoch": 2.36, + "learning_rate": 4.240547588005216e-06, + "loss": 0.2341, + "step": 29010 + }, + { + "epoch": 2.36, + "learning_rate": 4.24000434593655e-06, + "loss": 0.1935, + "step": 29011 + }, + { + "epoch": 2.36, + "learning_rate": 4.239461103867884e-06, + "loss": 0.2781, + "step": 29012 + }, + { + "epoch": 2.36, + "learning_rate": 4.2389178617992184e-06, + "loss": 0.2733, + "step": 29013 + }, + { + "epoch": 2.36, + "learning_rate": 4.238374619730553e-06, + "loss": 0.1333, + "step": 29014 + }, + { + "epoch": 2.36, + "learning_rate": 4.237831377661886e-06, + "loss": 0.2083, + "step": 29015 + }, + { + "epoch": 2.36, + "learning_rate": 4.23728813559322e-06, + "loss": 0.2283, + "step": 29016 + }, + { + "epoch": 2.36, + "learning_rate": 4.2367448935245545e-06, + "loss": 0.3519, + "step": 29017 + }, + { + "epoch": 2.36, + "learning_rate": 4.236201651455889e-06, + "loss": 0.0619, + "step": 29018 + }, + { + "epoch": 2.36, + "learning_rate": 4.235658409387223e-06, + "loss": 0.092, + "step": 29019 + }, + { + "epoch": 2.36, + "learning_rate": 4.235115167318557e-06, + "loss": 0.2657, + "step": 29020 + }, + { + "epoch": 2.36, + "learning_rate": 4.2345719252498914e-06, + "loss": 0.4606, + "step": 29021 + }, + { + "epoch": 2.36, + "learning_rate": 4.234028683181226e-06, + "loss": 0.3128, + "step": 29022 + }, + { + "epoch": 2.36, + "learning_rate": 4.233485441112561e-06, + "loss": 0.0772, + "step": 29023 + }, + { + "epoch": 2.37, + "learning_rate": 4.232942199043894e-06, + "loss": 0.1677, + "step": 29024 + }, + { + "epoch": 2.37, + "learning_rate": 4.232398956975228e-06, + "loss": 0.0899, + "step": 29025 + }, + { + "epoch": 2.37, + "learning_rate": 4.231855714906563e-06, + "loss": 0.2425, + "step": 29026 + }, + { + "epoch": 2.37, + "learning_rate": 4.231312472837897e-06, + "loss": 0.1153, + "step": 29027 + }, + { + "epoch": 2.37, + "learning_rate": 4.230769230769231e-06, + "loss": 0.1389, + "step": 29028 + }, + { + "epoch": 2.37, + "learning_rate": 4.230225988700565e-06, + "loss": 0.3404, + "step": 29029 + }, + { + "epoch": 2.37, + "learning_rate": 4.2296827466318995e-06, + "loss": 0.043, + "step": 29030 + }, + { + "epoch": 2.37, + "learning_rate": 4.229139504563234e-06, + "loss": 0.4687, + "step": 29031 + }, + { + "epoch": 2.37, + "learning_rate": 4.228596262494568e-06, + "loss": 0.3422, + "step": 29032 + }, + { + "epoch": 2.37, + "learning_rate": 4.228053020425902e-06, + "loss": 0.1901, + "step": 29033 + }, + { + "epoch": 2.37, + "learning_rate": 4.2275097783572364e-06, + "loss": 0.152, + "step": 29034 + }, + { + "epoch": 2.37, + "learning_rate": 4.226966536288571e-06, + "loss": 0.2761, + "step": 29035 + }, + { + "epoch": 2.37, + "learning_rate": 4.226423294219905e-06, + "loss": 0.1148, + "step": 29036 + }, + { + "epoch": 2.37, + "learning_rate": 4.225880052151239e-06, + "loss": 0.3373, + "step": 29037 + }, + { + "epoch": 2.37, + "learning_rate": 4.225336810082573e-06, + "loss": 0.2356, + "step": 29038 + }, + { + "epoch": 2.37, + "learning_rate": 4.224793568013908e-06, + "loss": 0.1559, + "step": 29039 + }, + { + "epoch": 2.37, + "learning_rate": 4.224250325945242e-06, + "loss": 0.0868, + "step": 29040 + }, + { + "epoch": 2.37, + "learning_rate": 4.223707083876576e-06, + "loss": 0.1662, + "step": 29041 + }, + { + "epoch": 2.37, + "learning_rate": 4.22316384180791e-06, + "loss": 0.128, + "step": 29042 + }, + { + "epoch": 2.37, + "learning_rate": 4.222620599739244e-06, + "loss": 0.1381, + "step": 29043 + }, + { + "epoch": 2.37, + "learning_rate": 4.222077357670578e-06, + "loss": 0.1022, + "step": 29044 + }, + { + "epoch": 2.37, + "learning_rate": 4.221534115601912e-06, + "loss": 0.3087, + "step": 29045 + }, + { + "epoch": 2.37, + "learning_rate": 4.220990873533246e-06, + "loss": 0.2525, + "step": 29046 + }, + { + "epoch": 2.37, + "learning_rate": 4.220447631464581e-06, + "loss": 0.1775, + "step": 29047 + }, + { + "epoch": 2.37, + "learning_rate": 4.219904389395915e-06, + "loss": 0.3063, + "step": 29048 + }, + { + "epoch": 2.37, + "learning_rate": 4.219361147327249e-06, + "loss": 0.1652, + "step": 29049 + }, + { + "epoch": 2.37, + "learning_rate": 4.218817905258584e-06, + "loss": 0.0789, + "step": 29050 + }, + { + "epoch": 2.37, + "learning_rate": 4.218274663189918e-06, + "loss": 0.0704, + "step": 29051 + }, + { + "epoch": 2.37, + "learning_rate": 4.217731421121253e-06, + "loss": 0.3213, + "step": 29052 + }, + { + "epoch": 2.37, + "learning_rate": 4.217188179052586e-06, + "loss": 0.2537, + "step": 29053 + }, + { + "epoch": 2.37, + "learning_rate": 4.21664493698392e-06, + "loss": 0.3222, + "step": 29054 + }, + { + "epoch": 2.37, + "learning_rate": 4.2161016949152544e-06, + "loss": 0.1962, + "step": 29055 + }, + { + "epoch": 2.37, + "learning_rate": 4.215558452846589e-06, + "loss": 0.314, + "step": 29056 + }, + { + "epoch": 2.37, + "learning_rate": 4.215015210777923e-06, + "loss": 0.0603, + "step": 29057 + }, + { + "epoch": 2.37, + "learning_rate": 4.214471968709257e-06, + "loss": 0.2477, + "step": 29058 + }, + { + "epoch": 2.37, + "learning_rate": 4.213928726640591e-06, + "loss": 0.0522, + "step": 29059 + }, + { + "epoch": 2.37, + "learning_rate": 4.213385484571926e-06, + "loss": 0.4375, + "step": 29060 + }, + { + "epoch": 2.37, + "learning_rate": 4.21284224250326e-06, + "loss": 0.0573, + "step": 29061 + }, + { + "epoch": 2.37, + "learning_rate": 4.212299000434594e-06, + "loss": 0.4377, + "step": 29062 + }, + { + "epoch": 2.37, + "learning_rate": 4.211755758365928e-06, + "loss": 0.378, + "step": 29063 + }, + { + "epoch": 2.37, + "learning_rate": 4.2112125162972625e-06, + "loss": 0.1852, + "step": 29064 + }, + { + "epoch": 2.37, + "learning_rate": 4.210669274228597e-06, + "loss": 0.2287, + "step": 29065 + }, + { + "epoch": 2.37, + "learning_rate": 4.210126032159931e-06, + "loss": 0.2495, + "step": 29066 + }, + { + "epoch": 2.37, + "learning_rate": 4.209582790091265e-06, + "loss": 0.3436, + "step": 29067 + }, + { + "epoch": 2.37, + "learning_rate": 4.2090395480225994e-06, + "loss": 0.2, + "step": 29068 + }, + { + "epoch": 2.37, + "learning_rate": 4.208496305953934e-06, + "loss": 0.0441, + "step": 29069 + }, + { + "epoch": 2.37, + "learning_rate": 4.207953063885268e-06, + "loss": 0.1642, + "step": 29070 + }, + { + "epoch": 2.37, + "learning_rate": 4.207409821816602e-06, + "loss": 0.3174, + "step": 29071 + }, + { + "epoch": 2.37, + "learning_rate": 4.2068665797479355e-06, + "loss": 0.4161, + "step": 29072 + }, + { + "epoch": 2.37, + "learning_rate": 4.20632333767927e-06, + "loss": 0.1049, + "step": 29073 + }, + { + "epoch": 2.37, + "learning_rate": 4.205780095610604e-06, + "loss": 0.077, + "step": 29074 + }, + { + "epoch": 2.37, + "learning_rate": 4.205236853541938e-06, + "loss": 0.041, + "step": 29075 + }, + { + "epoch": 2.37, + "learning_rate": 4.204693611473272e-06, + "loss": 0.3038, + "step": 29076 + }, + { + "epoch": 2.37, + "learning_rate": 4.2041503694046075e-06, + "loss": 0.1877, + "step": 29077 + }, + { + "epoch": 2.37, + "learning_rate": 4.203607127335942e-06, + "loss": 0.3383, + "step": 29078 + }, + { + "epoch": 2.37, + "learning_rate": 4.203063885267276e-06, + "loss": 0.1456, + "step": 29079 + }, + { + "epoch": 2.37, + "learning_rate": 4.20252064319861e-06, + "loss": 0.1865, + "step": 29080 + }, + { + "epoch": 2.37, + "learning_rate": 4.201977401129944e-06, + "loss": 0.1574, + "step": 29081 + }, + { + "epoch": 2.37, + "learning_rate": 4.201434159061278e-06, + "loss": 0.1933, + "step": 29082 + }, + { + "epoch": 2.37, + "learning_rate": 4.200890916992612e-06, + "loss": 0.0698, + "step": 29083 + }, + { + "epoch": 2.37, + "learning_rate": 4.200347674923946e-06, + "loss": 0.2807, + "step": 29084 + }, + { + "epoch": 2.37, + "learning_rate": 4.1998044328552805e-06, + "loss": 0.1777, + "step": 29085 + }, + { + "epoch": 2.37, + "learning_rate": 4.199261190786615e-06, + "loss": 0.2467, + "step": 29086 + }, + { + "epoch": 2.37, + "learning_rate": 4.198717948717949e-06, + "loss": 0.2327, + "step": 29087 + }, + { + "epoch": 2.37, + "learning_rate": 4.198174706649283e-06, + "loss": 0.367, + "step": 29088 + }, + { + "epoch": 2.37, + "learning_rate": 4.197631464580617e-06, + "loss": 0.3278, + "step": 29089 + }, + { + "epoch": 2.37, + "learning_rate": 4.197088222511952e-06, + "loss": 0.0988, + "step": 29090 + }, + { + "epoch": 2.37, + "learning_rate": 4.196544980443286e-06, + "loss": 0.221, + "step": 29091 + }, + { + "epoch": 2.37, + "learning_rate": 4.19600173837462e-06, + "loss": 0.0967, + "step": 29092 + }, + { + "epoch": 2.37, + "learning_rate": 4.195458496305954e-06, + "loss": 0.4032, + "step": 29093 + }, + { + "epoch": 2.37, + "learning_rate": 4.1949152542372886e-06, + "loss": 0.5229, + "step": 29094 + }, + { + "epoch": 2.37, + "learning_rate": 4.194372012168623e-06, + "loss": 0.2332, + "step": 29095 + }, + { + "epoch": 2.37, + "learning_rate": 4.193828770099957e-06, + "loss": 0.2942, + "step": 29096 + }, + { + "epoch": 2.37, + "learning_rate": 4.193285528031291e-06, + "loss": 0.1765, + "step": 29097 + }, + { + "epoch": 2.37, + "learning_rate": 4.1927422859626255e-06, + "loss": 0.1546, + "step": 29098 + }, + { + "epoch": 2.37, + "learning_rate": 4.19219904389396e-06, + "loss": 0.116, + "step": 29099 + }, + { + "epoch": 2.37, + "learning_rate": 4.191655801825294e-06, + "loss": 0.2689, + "step": 29100 + }, + { + "epoch": 2.37, + "learning_rate": 4.191112559756627e-06, + "loss": 0.1571, + "step": 29101 + }, + { + "epoch": 2.37, + "learning_rate": 4.1905693176879616e-06, + "loss": 0.3732, + "step": 29102 + }, + { + "epoch": 2.37, + "learning_rate": 4.190026075619296e-06, + "loss": 0.5221, + "step": 29103 + }, + { + "epoch": 2.37, + "learning_rate": 4.189482833550631e-06, + "loss": 0.4462, + "step": 29104 + }, + { + "epoch": 2.37, + "learning_rate": 4.188939591481965e-06, + "loss": 0.3692, + "step": 29105 + }, + { + "epoch": 2.37, + "learning_rate": 4.188396349413299e-06, + "loss": 0.1148, + "step": 29106 + }, + { + "epoch": 2.37, + "learning_rate": 4.1878531073446336e-06, + "loss": 0.1046, + "step": 29107 + }, + { + "epoch": 2.37, + "learning_rate": 4.187309865275968e-06, + "loss": 0.2306, + "step": 29108 + }, + { + "epoch": 2.37, + "learning_rate": 4.186766623207302e-06, + "loss": 0.0518, + "step": 29109 + }, + { + "epoch": 2.37, + "learning_rate": 4.186223381138635e-06, + "loss": 0.4466, + "step": 29110 + }, + { + "epoch": 2.37, + "learning_rate": 4.18568013906997e-06, + "loss": 0.0544, + "step": 29111 + }, + { + "epoch": 2.37, + "learning_rate": 4.185136897001304e-06, + "loss": 0.2153, + "step": 29112 + }, + { + "epoch": 2.37, + "learning_rate": 4.184593654932638e-06, + "loss": 0.2277, + "step": 29113 + }, + { + "epoch": 2.37, + "learning_rate": 4.184050412863972e-06, + "loss": 0.1656, + "step": 29114 + }, + { + "epoch": 2.37, + "learning_rate": 4.1835071707953066e-06, + "loss": 0.142, + "step": 29115 + }, + { + "epoch": 2.37, + "learning_rate": 4.182963928726641e-06, + "loss": 0.0462, + "step": 29116 + }, + { + "epoch": 2.37, + "learning_rate": 4.182420686657975e-06, + "loss": 0.1928, + "step": 29117 + }, + { + "epoch": 2.37, + "learning_rate": 4.181877444589309e-06, + "loss": 0.2587, + "step": 29118 + }, + { + "epoch": 2.37, + "learning_rate": 4.1813342025206435e-06, + "loss": 0.0656, + "step": 29119 + }, + { + "epoch": 2.37, + "learning_rate": 4.180790960451978e-06, + "loss": 0.3303, + "step": 29120 + }, + { + "epoch": 2.37, + "learning_rate": 4.180247718383312e-06, + "loss": 0.0688, + "step": 29121 + }, + { + "epoch": 2.37, + "learning_rate": 4.179704476314646e-06, + "loss": 0.1515, + "step": 29122 + }, + { + "epoch": 2.37, + "learning_rate": 4.17916123424598e-06, + "loss": 0.3612, + "step": 29123 + }, + { + "epoch": 2.37, + "learning_rate": 4.178617992177315e-06, + "loss": 0.123, + "step": 29124 + }, + { + "epoch": 2.37, + "learning_rate": 4.178074750108649e-06, + "loss": 0.1434, + "step": 29125 + }, + { + "epoch": 2.37, + "learning_rate": 4.177531508039983e-06, + "loss": 0.1866, + "step": 29126 + }, + { + "epoch": 2.37, + "learning_rate": 4.176988265971317e-06, + "loss": 0.1662, + "step": 29127 + }, + { + "epoch": 2.37, + "learning_rate": 4.1764450239026516e-06, + "loss": 0.3325, + "step": 29128 + }, + { + "epoch": 2.37, + "learning_rate": 4.175901781833985e-06, + "loss": 0.1461, + "step": 29129 + }, + { + "epoch": 2.37, + "learning_rate": 4.175358539765319e-06, + "loss": 0.1998, + "step": 29130 + }, + { + "epoch": 2.37, + "learning_rate": 4.174815297696654e-06, + "loss": 0.0528, + "step": 29131 + }, + { + "epoch": 2.37, + "learning_rate": 4.1742720556279885e-06, + "loss": 0.1835, + "step": 29132 + }, + { + "epoch": 2.37, + "learning_rate": 4.173728813559323e-06, + "loss": 0.1426, + "step": 29133 + }, + { + "epoch": 2.37, + "learning_rate": 4.173185571490657e-06, + "loss": 0.2407, + "step": 29134 + }, + { + "epoch": 2.37, + "learning_rate": 4.172642329421991e-06, + "loss": 0.409, + "step": 29135 + }, + { + "epoch": 2.37, + "learning_rate": 4.172099087353325e-06, + "loss": 0.0769, + "step": 29136 + }, + { + "epoch": 2.37, + "learning_rate": 4.17155584528466e-06, + "loss": 0.1666, + "step": 29137 + }, + { + "epoch": 2.37, + "learning_rate": 4.171012603215994e-06, + "loss": 0.167, + "step": 29138 + }, + { + "epoch": 2.37, + "learning_rate": 4.170469361147327e-06, + "loss": 0.3042, + "step": 29139 + }, + { + "epoch": 2.37, + "learning_rate": 4.1699261190786615e-06, + "loss": 0.0799, + "step": 29140 + }, + { + "epoch": 2.37, + "learning_rate": 4.169382877009996e-06, + "loss": 0.198, + "step": 29141 + }, + { + "epoch": 2.37, + "learning_rate": 4.16883963494133e-06, + "loss": 0.0758, + "step": 29142 + }, + { + "epoch": 2.37, + "learning_rate": 4.168296392872664e-06, + "loss": 0.1097, + "step": 29143 + }, + { + "epoch": 2.37, + "learning_rate": 4.167753150803998e-06, + "loss": 0.1436, + "step": 29144 + }, + { + "epoch": 2.37, + "learning_rate": 4.167209908735333e-06, + "loss": 0.1082, + "step": 29145 + }, + { + "epoch": 2.38, + "learning_rate": 4.166666666666667e-06, + "loss": 0.036, + "step": 29146 + }, + { + "epoch": 2.38, + "learning_rate": 4.166123424598001e-06, + "loss": 0.1424, + "step": 29147 + }, + { + "epoch": 2.38, + "learning_rate": 4.165580182529335e-06, + "loss": 0.1075, + "step": 29148 + }, + { + "epoch": 2.38, + "learning_rate": 4.1650369404606696e-06, + "loss": 0.251, + "step": 29149 + }, + { + "epoch": 2.38, + "learning_rate": 4.164493698392004e-06, + "loss": 0.3696, + "step": 29150 + }, + { + "epoch": 2.38, + "learning_rate": 4.163950456323338e-06, + "loss": 0.0856, + "step": 29151 + }, + { + "epoch": 2.38, + "learning_rate": 4.163407214254672e-06, + "loss": 0.0362, + "step": 29152 + }, + { + "epoch": 2.38, + "learning_rate": 4.1628639721860065e-06, + "loss": 0.164, + "step": 29153 + }, + { + "epoch": 2.38, + "learning_rate": 4.162320730117341e-06, + "loss": 0.101, + "step": 29154 + }, + { + "epoch": 2.38, + "learning_rate": 4.161777488048675e-06, + "loss": 0.3469, + "step": 29155 + }, + { + "epoch": 2.38, + "learning_rate": 4.161234245980009e-06, + "loss": 0.283, + "step": 29156 + }, + { + "epoch": 2.38, + "learning_rate": 4.160691003911343e-06, + "loss": 0.1668, + "step": 29157 + }, + { + "epoch": 2.38, + "learning_rate": 4.160147761842678e-06, + "loss": 0.2928, + "step": 29158 + }, + { + "epoch": 2.38, + "learning_rate": 4.159604519774012e-06, + "loss": 0.0612, + "step": 29159 + }, + { + "epoch": 2.38, + "learning_rate": 4.159061277705346e-06, + "loss": 0.1999, + "step": 29160 + }, + { + "epoch": 2.38, + "learning_rate": 4.15851803563668e-06, + "loss": 0.2272, + "step": 29161 + }, + { + "epoch": 2.38, + "learning_rate": 4.1579747935680146e-06, + "loss": 0.2555, + "step": 29162 + }, + { + "epoch": 2.38, + "learning_rate": 4.157431551499349e-06, + "loss": 0.1804, + "step": 29163 + }, + { + "epoch": 2.38, + "learning_rate": 4.156888309430683e-06, + "loss": 0.1838, + "step": 29164 + }, + { + "epoch": 2.38, + "learning_rate": 4.156345067362017e-06, + "loss": 0.1277, + "step": 29165 + }, + { + "epoch": 2.38, + "learning_rate": 4.1558018252933515e-06, + "loss": 0.0764, + "step": 29166 + }, + { + "epoch": 2.38, + "learning_rate": 4.155258583224685e-06, + "loss": 0.0948, + "step": 29167 + }, + { + "epoch": 2.38, + "learning_rate": 4.154715341156019e-06, + "loss": 0.3289, + "step": 29168 + }, + { + "epoch": 2.38, + "learning_rate": 4.154172099087353e-06, + "loss": 0.1243, + "step": 29169 + }, + { + "epoch": 2.38, + "learning_rate": 4.1536288570186876e-06, + "loss": 0.1787, + "step": 29170 + }, + { + "epoch": 2.38, + "learning_rate": 4.153085614950022e-06, + "loss": 0.1732, + "step": 29171 + }, + { + "epoch": 2.38, + "learning_rate": 4.152542372881356e-06, + "loss": 0.356, + "step": 29172 + }, + { + "epoch": 2.38, + "learning_rate": 4.15199913081269e-06, + "loss": 0.0616, + "step": 29173 + }, + { + "epoch": 2.38, + "learning_rate": 4.1514558887440245e-06, + "loss": 0.3555, + "step": 29174 + }, + { + "epoch": 2.38, + "learning_rate": 4.150912646675359e-06, + "loss": 0.301, + "step": 29175 + }, + { + "epoch": 2.38, + "learning_rate": 4.150369404606693e-06, + "loss": 0.3521, + "step": 29176 + }, + { + "epoch": 2.38, + "learning_rate": 4.149826162538027e-06, + "loss": 0.4647, + "step": 29177 + }, + { + "epoch": 2.38, + "learning_rate": 4.149282920469361e-06, + "loss": 0.3299, + "step": 29178 + }, + { + "epoch": 2.38, + "learning_rate": 4.148739678400696e-06, + "loss": 0.4971, + "step": 29179 + }, + { + "epoch": 2.38, + "learning_rate": 4.14819643633203e-06, + "loss": 0.1581, + "step": 29180 + }, + { + "epoch": 2.38, + "learning_rate": 4.147653194263364e-06, + "loss": 0.2127, + "step": 29181 + }, + { + "epoch": 2.38, + "learning_rate": 4.147109952194698e-06, + "loss": 0.1158, + "step": 29182 + }, + { + "epoch": 2.38, + "learning_rate": 4.1465667101260325e-06, + "loss": 0.4252, + "step": 29183 + }, + { + "epoch": 2.38, + "learning_rate": 4.146023468057367e-06, + "loss": 0.1319, + "step": 29184 + }, + { + "epoch": 2.38, + "learning_rate": 4.145480225988701e-06, + "loss": 0.4035, + "step": 29185 + }, + { + "epoch": 2.38, + "learning_rate": 4.144936983920035e-06, + "loss": 0.3542, + "step": 29186 + }, + { + "epoch": 2.38, + "learning_rate": 4.1443937418513695e-06, + "loss": 0.1964, + "step": 29187 + }, + { + "epoch": 2.38, + "learning_rate": 4.143850499782704e-06, + "loss": 0.2647, + "step": 29188 + }, + { + "epoch": 2.38, + "learning_rate": 4.143307257714038e-06, + "loss": 0.1212, + "step": 29189 + }, + { + "epoch": 2.38, + "learning_rate": 4.142764015645372e-06, + "loss": 0.2651, + "step": 29190 + }, + { + "epoch": 2.38, + "learning_rate": 4.142220773576706e-06, + "loss": 0.2539, + "step": 29191 + }, + { + "epoch": 2.38, + "learning_rate": 4.141677531508041e-06, + "loss": 0.2703, + "step": 29192 + }, + { + "epoch": 2.38, + "learning_rate": 4.141134289439375e-06, + "loss": 0.468, + "step": 29193 + }, + { + "epoch": 2.38, + "learning_rate": 4.140591047370709e-06, + "loss": 0.2012, + "step": 29194 + }, + { + "epoch": 2.38, + "learning_rate": 4.140047805302043e-06, + "loss": 0.0285, + "step": 29195 + }, + { + "epoch": 2.38, + "learning_rate": 4.139504563233377e-06, + "loss": 0.3668, + "step": 29196 + }, + { + "epoch": 2.38, + "learning_rate": 4.138961321164711e-06, + "loss": 0.3152, + "step": 29197 + }, + { + "epoch": 2.38, + "learning_rate": 4.138418079096045e-06, + "loss": 0.3088, + "step": 29198 + }, + { + "epoch": 2.38, + "learning_rate": 4.137874837027379e-06, + "loss": 0.3695, + "step": 29199 + }, + { + "epoch": 2.38, + "learning_rate": 4.137331594958714e-06, + "loss": 0.3736, + "step": 29200 + }, + { + "epoch": 2.38, + "learning_rate": 4.136788352890048e-06, + "loss": 0.1604, + "step": 29201 + }, + { + "epoch": 2.38, + "learning_rate": 4.136245110821382e-06, + "loss": 0.3399, + "step": 29202 + }, + { + "epoch": 2.38, + "learning_rate": 4.135701868752716e-06, + "loss": 0.2132, + "step": 29203 + }, + { + "epoch": 2.38, + "learning_rate": 4.135158626684051e-06, + "loss": 0.2306, + "step": 29204 + }, + { + "epoch": 2.38, + "learning_rate": 4.134615384615385e-06, + "loss": 0.1377, + "step": 29205 + }, + { + "epoch": 2.38, + "learning_rate": 4.134072142546719e-06, + "loss": 0.0864, + "step": 29206 + }, + { + "epoch": 2.38, + "learning_rate": 4.133528900478053e-06, + "loss": 0.2529, + "step": 29207 + }, + { + "epoch": 2.38, + "learning_rate": 4.1329856584093875e-06, + "loss": 0.2012, + "step": 29208 + }, + { + "epoch": 2.38, + "learning_rate": 4.132442416340722e-06, + "loss": 0.2454, + "step": 29209 + }, + { + "epoch": 2.38, + "learning_rate": 4.131899174272056e-06, + "loss": 0.331, + "step": 29210 + }, + { + "epoch": 2.38, + "learning_rate": 4.13135593220339e-06, + "loss": 0.3334, + "step": 29211 + }, + { + "epoch": 2.38, + "learning_rate": 4.130812690134724e-06, + "loss": 0.377, + "step": 29212 + }, + { + "epoch": 2.38, + "learning_rate": 4.130269448066059e-06, + "loss": 0.1041, + "step": 29213 + }, + { + "epoch": 2.38, + "learning_rate": 4.129726205997393e-06, + "loss": 0.3452, + "step": 29214 + }, + { + "epoch": 2.38, + "learning_rate": 4.129182963928727e-06, + "loss": 0.1493, + "step": 29215 + }, + { + "epoch": 2.38, + "learning_rate": 4.128639721860061e-06, + "loss": 0.3418, + "step": 29216 + }, + { + "epoch": 2.38, + "learning_rate": 4.1280964797913955e-06, + "loss": 0.2142, + "step": 29217 + }, + { + "epoch": 2.38, + "learning_rate": 4.12755323772273e-06, + "loss": 0.3346, + "step": 29218 + }, + { + "epoch": 2.38, + "learning_rate": 4.127009995654064e-06, + "loss": 0.1782, + "step": 29219 + }, + { + "epoch": 2.38, + "learning_rate": 4.126466753585398e-06, + "loss": 0.5345, + "step": 29220 + }, + { + "epoch": 2.38, + "learning_rate": 4.1259235115167325e-06, + "loss": 0.2106, + "step": 29221 + }, + { + "epoch": 2.38, + "learning_rate": 4.125380269448067e-06, + "loss": 0.2907, + "step": 29222 + }, + { + "epoch": 2.38, + "learning_rate": 4.124837027379401e-06, + "loss": 0.3954, + "step": 29223 + }, + { + "epoch": 2.38, + "learning_rate": 4.124293785310734e-06, + "loss": 0.3256, + "step": 29224 + }, + { + "epoch": 2.38, + "learning_rate": 4.1237505432420685e-06, + "loss": 0.3734, + "step": 29225 + }, + { + "epoch": 2.38, + "learning_rate": 4.123207301173403e-06, + "loss": 0.0821, + "step": 29226 + }, + { + "epoch": 2.38, + "learning_rate": 4.122664059104737e-06, + "loss": 0.2504, + "step": 29227 + }, + { + "epoch": 2.38, + "learning_rate": 4.122120817036071e-06, + "loss": 0.2875, + "step": 29228 + }, + { + "epoch": 2.38, + "learning_rate": 4.1215775749674055e-06, + "loss": 0.3488, + "step": 29229 + }, + { + "epoch": 2.38, + "learning_rate": 4.12103433289874e-06, + "loss": 0.2908, + "step": 29230 + }, + { + "epoch": 2.38, + "learning_rate": 4.120491090830075e-06, + "loss": 0.1258, + "step": 29231 + }, + { + "epoch": 2.38, + "learning_rate": 4.119947848761409e-06, + "loss": 0.1769, + "step": 29232 + }, + { + "epoch": 2.38, + "learning_rate": 4.119404606692743e-06, + "loss": 0.248, + "step": 29233 + }, + { + "epoch": 2.38, + "learning_rate": 4.118861364624077e-06, + "loss": 0.0624, + "step": 29234 + }, + { + "epoch": 2.38, + "learning_rate": 4.118318122555411e-06, + "loss": 0.4243, + "step": 29235 + }, + { + "epoch": 2.38, + "learning_rate": 4.117774880486745e-06, + "loss": 0.2017, + "step": 29236 + }, + { + "epoch": 2.38, + "learning_rate": 4.117231638418079e-06, + "loss": 0.3213, + "step": 29237 + }, + { + "epoch": 2.38, + "learning_rate": 4.1166883963494135e-06, + "loss": 0.2973, + "step": 29238 + }, + { + "epoch": 2.38, + "learning_rate": 4.116145154280748e-06, + "loss": 0.3519, + "step": 29239 + }, + { + "epoch": 2.38, + "learning_rate": 4.115601912212082e-06, + "loss": 0.5515, + "step": 29240 + }, + { + "epoch": 2.38, + "learning_rate": 4.115058670143416e-06, + "loss": 0.0718, + "step": 29241 + }, + { + "epoch": 2.38, + "learning_rate": 4.1145154280747505e-06, + "loss": 0.1176, + "step": 29242 + }, + { + "epoch": 2.38, + "learning_rate": 4.113972186006085e-06, + "loss": 0.3306, + "step": 29243 + }, + { + "epoch": 2.38, + "learning_rate": 4.113428943937419e-06, + "loss": 0.129, + "step": 29244 + }, + { + "epoch": 2.38, + "learning_rate": 4.112885701868753e-06, + "loss": 0.1089, + "step": 29245 + }, + { + "epoch": 2.38, + "learning_rate": 4.112342459800087e-06, + "loss": 0.0953, + "step": 29246 + }, + { + "epoch": 2.38, + "learning_rate": 4.111799217731422e-06, + "loss": 0.2512, + "step": 29247 + }, + { + "epoch": 2.38, + "learning_rate": 4.111255975662756e-06, + "loss": 0.154, + "step": 29248 + }, + { + "epoch": 2.38, + "learning_rate": 4.11071273359409e-06, + "loss": 0.1931, + "step": 29249 + }, + { + "epoch": 2.38, + "learning_rate": 4.110169491525424e-06, + "loss": 0.0603, + "step": 29250 + }, + { + "epoch": 2.38, + "eval_accuracy": 0.844319918492104, + "eval_loss": 0.4872000217437744, + "eval_runtime": 22.3176, + "eval_samples_per_second": 439.788, + "eval_steps_per_second": 3.45, + "step": 29250 + }, + { + "epoch": 2.38, + "learning_rate": 4.1096262494567585e-06, + "loss": 0.3468, + "step": 29251 + }, + { + "epoch": 2.38, + "learning_rate": 4.109083007388093e-06, + "loss": 0.2079, + "step": 29252 + }, + { + "epoch": 2.38, + "learning_rate": 4.108539765319426e-06, + "loss": 0.3103, + "step": 29253 + }, + { + "epoch": 2.38, + "learning_rate": 4.10799652325076e-06, + "loss": 0.3096, + "step": 29254 + }, + { + "epoch": 2.38, + "learning_rate": 4.107453281182095e-06, + "loss": 0.0937, + "step": 29255 + }, + { + "epoch": 2.38, + "learning_rate": 4.106910039113429e-06, + "loss": 0.162, + "step": 29256 + }, + { + "epoch": 2.38, + "learning_rate": 4.106366797044763e-06, + "loss": 0.214, + "step": 29257 + }, + { + "epoch": 2.38, + "learning_rate": 4.105823554976098e-06, + "loss": 0.2202, + "step": 29258 + }, + { + "epoch": 2.38, + "learning_rate": 4.105280312907432e-06, + "loss": 0.3359, + "step": 29259 + }, + { + "epoch": 2.38, + "learning_rate": 4.104737070838767e-06, + "loss": 0.1324, + "step": 29260 + }, + { + "epoch": 2.38, + "learning_rate": 4.104193828770101e-06, + "loss": 0.2314, + "step": 29261 + }, + { + "epoch": 2.38, + "learning_rate": 4.103650586701434e-06, + "loss": 0.2201, + "step": 29262 + }, + { + "epoch": 2.38, + "learning_rate": 4.1031073446327685e-06, + "loss": 0.1674, + "step": 29263 + }, + { + "epoch": 2.38, + "learning_rate": 4.102564102564103e-06, + "loss": 0.2845, + "step": 29264 + }, + { + "epoch": 2.38, + "learning_rate": 4.102020860495437e-06, + "loss": 0.4014, + "step": 29265 + }, + { + "epoch": 2.38, + "learning_rate": 4.101477618426771e-06, + "loss": 0.1781, + "step": 29266 + }, + { + "epoch": 2.38, + "learning_rate": 4.100934376358105e-06, + "loss": 0.1382, + "step": 29267 + }, + { + "epoch": 2.38, + "learning_rate": 4.10039113428944e-06, + "loss": 0.0727, + "step": 29268 + }, + { + "epoch": 2.39, + "learning_rate": 4.099847892220774e-06, + "loss": 0.1363, + "step": 29269 + }, + { + "epoch": 2.39, + "learning_rate": 4.099304650152108e-06, + "loss": 0.2698, + "step": 29270 + }, + { + "epoch": 2.39, + "learning_rate": 4.098761408083442e-06, + "loss": 0.1284, + "step": 29271 + }, + { + "epoch": 2.39, + "learning_rate": 4.0982181660147765e-06, + "loss": 0.2722, + "step": 29272 + }, + { + "epoch": 2.39, + "learning_rate": 4.097674923946111e-06, + "loss": 0.1871, + "step": 29273 + }, + { + "epoch": 2.39, + "learning_rate": 4.097131681877445e-06, + "loss": 0.2039, + "step": 29274 + }, + { + "epoch": 2.39, + "learning_rate": 4.096588439808779e-06, + "loss": 0.4389, + "step": 29275 + }, + { + "epoch": 2.39, + "learning_rate": 4.0960451977401134e-06, + "loss": 0.1127, + "step": 29276 + }, + { + "epoch": 2.39, + "learning_rate": 4.095501955671448e-06, + "loss": 0.3545, + "step": 29277 + }, + { + "epoch": 2.39, + "learning_rate": 4.094958713602782e-06, + "loss": 0.2131, + "step": 29278 + }, + { + "epoch": 2.39, + "learning_rate": 4.094415471534116e-06, + "loss": 0.2811, + "step": 29279 + }, + { + "epoch": 2.39, + "learning_rate": 4.09387222946545e-06, + "loss": 0.3648, + "step": 29280 + }, + { + "epoch": 2.39, + "learning_rate": 4.093328987396784e-06, + "loss": 0.1591, + "step": 29281 + }, + { + "epoch": 2.39, + "learning_rate": 4.092785745328118e-06, + "loss": 0.176, + "step": 29282 + }, + { + "epoch": 2.39, + "learning_rate": 4.092242503259452e-06, + "loss": 0.3542, + "step": 29283 + }, + { + "epoch": 2.39, + "learning_rate": 4.0916992611907864e-06, + "loss": 0.2891, + "step": 29284 + }, + { + "epoch": 2.39, + "learning_rate": 4.0911560191221215e-06, + "loss": 0.2664, + "step": 29285 + }, + { + "epoch": 2.39, + "learning_rate": 4.090612777053456e-06, + "loss": 0.0995, + "step": 29286 + }, + { + "epoch": 2.39, + "learning_rate": 4.09006953498479e-06, + "loss": 0.4058, + "step": 29287 + }, + { + "epoch": 2.39, + "learning_rate": 4.089526292916124e-06, + "loss": 0.2016, + "step": 29288 + }, + { + "epoch": 2.39, + "learning_rate": 4.0889830508474584e-06, + "loss": 0.2251, + "step": 29289 + }, + { + "epoch": 2.39, + "learning_rate": 4.088439808778793e-06, + "loss": 0.2319, + "step": 29290 + }, + { + "epoch": 2.39, + "learning_rate": 4.087896566710126e-06, + "loss": 0.2672, + "step": 29291 + }, + { + "epoch": 2.39, + "learning_rate": 4.08735332464146e-06, + "loss": 0.162, + "step": 29292 + }, + { + "epoch": 2.39, + "learning_rate": 4.0868100825727945e-06, + "loss": 0.1486, + "step": 29293 + }, + { + "epoch": 2.39, + "learning_rate": 4.086266840504129e-06, + "loss": 0.3101, + "step": 29294 + }, + { + "epoch": 2.39, + "learning_rate": 4.085723598435463e-06, + "loss": 0.2433, + "step": 29295 + }, + { + "epoch": 2.39, + "learning_rate": 4.085180356366797e-06, + "loss": 0.4798, + "step": 29296 + }, + { + "epoch": 2.39, + "learning_rate": 4.0846371142981314e-06, + "loss": 0.1445, + "step": 29297 + }, + { + "epoch": 2.39, + "learning_rate": 4.084093872229466e-06, + "loss": 0.2652, + "step": 29298 + }, + { + "epoch": 2.39, + "learning_rate": 4.0835506301608e-06, + "loss": 0.2451, + "step": 29299 + }, + { + "epoch": 2.39, + "learning_rate": 4.083007388092134e-06, + "loss": 0.1073, + "step": 29300 + }, + { + "epoch": 2.39, + "learning_rate": 4.082464146023468e-06, + "loss": 0.2258, + "step": 29301 + }, + { + "epoch": 2.39, + "learning_rate": 4.081920903954803e-06, + "loss": 0.2215, + "step": 29302 + }, + { + "epoch": 2.39, + "learning_rate": 4.081377661886137e-06, + "loss": 0.1994, + "step": 29303 + }, + { + "epoch": 2.39, + "learning_rate": 4.080834419817471e-06, + "loss": 0.1843, + "step": 29304 + }, + { + "epoch": 2.39, + "learning_rate": 4.080291177748805e-06, + "loss": 0.1771, + "step": 29305 + }, + { + "epoch": 2.39, + "learning_rate": 4.0797479356801395e-06, + "loss": 0.0673, + "step": 29306 + }, + { + "epoch": 2.39, + "learning_rate": 4.079204693611474e-06, + "loss": 0.4415, + "step": 29307 + }, + { + "epoch": 2.39, + "learning_rate": 4.078661451542808e-06, + "loss": 0.301, + "step": 29308 + }, + { + "epoch": 2.39, + "learning_rate": 4.078118209474142e-06, + "loss": 0.3359, + "step": 29309 + }, + { + "epoch": 2.39, + "learning_rate": 4.077574967405476e-06, + "loss": 0.203, + "step": 29310 + }, + { + "epoch": 2.39, + "learning_rate": 4.07703172533681e-06, + "loss": 0.1451, + "step": 29311 + }, + { + "epoch": 2.39, + "learning_rate": 4.076488483268145e-06, + "loss": 0.2127, + "step": 29312 + }, + { + "epoch": 2.39, + "learning_rate": 4.075945241199479e-06, + "loss": 0.1338, + "step": 29313 + }, + { + "epoch": 2.39, + "learning_rate": 4.075401999130813e-06, + "loss": 0.283, + "step": 29314 + }, + { + "epoch": 2.39, + "learning_rate": 4.074858757062148e-06, + "loss": 0.2122, + "step": 29315 + }, + { + "epoch": 2.39, + "learning_rate": 4.074315514993482e-06, + "loss": 0.1399, + "step": 29316 + }, + { + "epoch": 2.39, + "learning_rate": 4.073772272924816e-06, + "loss": 0.2078, + "step": 29317 + }, + { + "epoch": 2.39, + "learning_rate": 4.07322903085615e-06, + "loss": 0.3226, + "step": 29318 + }, + { + "epoch": 2.39, + "learning_rate": 4.072685788787484e-06, + "loss": 0.1928, + "step": 29319 + }, + { + "epoch": 2.39, + "learning_rate": 4.072142546718818e-06, + "loss": 0.1379, + "step": 29320 + }, + { + "epoch": 2.39, + "learning_rate": 4.071599304650152e-06, + "loss": 0.1066, + "step": 29321 + }, + { + "epoch": 2.39, + "learning_rate": 4.071056062581486e-06, + "loss": 0.0692, + "step": 29322 + }, + { + "epoch": 2.39, + "learning_rate": 4.070512820512821e-06, + "loss": 0.1235, + "step": 29323 + }, + { + "epoch": 2.39, + "learning_rate": 4.069969578444155e-06, + "loss": 0.3219, + "step": 29324 + }, + { + "epoch": 2.39, + "learning_rate": 4.069426336375489e-06, + "loss": 0.2084, + "step": 29325 + }, + { + "epoch": 2.39, + "learning_rate": 4.068883094306823e-06, + "loss": 0.2485, + "step": 29326 + }, + { + "epoch": 2.39, + "learning_rate": 4.0683398522381575e-06, + "loss": 0.2456, + "step": 29327 + }, + { + "epoch": 2.39, + "learning_rate": 4.067796610169492e-06, + "loss": 0.2386, + "step": 29328 + }, + { + "epoch": 2.39, + "learning_rate": 4.067253368100826e-06, + "loss": 0.1321, + "step": 29329 + }, + { + "epoch": 2.39, + "learning_rate": 4.06671012603216e-06, + "loss": 0.0898, + "step": 29330 + }, + { + "epoch": 2.39, + "learning_rate": 4.0661668839634944e-06, + "loss": 0.1852, + "step": 29331 + }, + { + "epoch": 2.39, + "learning_rate": 4.065623641894829e-06, + "loss": 0.0646, + "step": 29332 + }, + { + "epoch": 2.39, + "learning_rate": 4.065080399826163e-06, + "loss": 0.0761, + "step": 29333 + }, + { + "epoch": 2.39, + "learning_rate": 4.064537157757497e-06, + "loss": 0.1142, + "step": 29334 + }, + { + "epoch": 2.39, + "learning_rate": 4.063993915688831e-06, + "loss": 0.34, + "step": 29335 + }, + { + "epoch": 2.39, + "learning_rate": 4.063450673620166e-06, + "loss": 0.2566, + "step": 29336 + }, + { + "epoch": 2.39, + "learning_rate": 4.0629074315515e-06, + "loss": 0.0759, + "step": 29337 + }, + { + "epoch": 2.39, + "learning_rate": 4.062364189482833e-06, + "loss": 0.1396, + "step": 29338 + }, + { + "epoch": 2.39, + "learning_rate": 4.061820947414168e-06, + "loss": 0.3916, + "step": 29339 + }, + { + "epoch": 2.39, + "learning_rate": 4.0612777053455025e-06, + "loss": 0.1921, + "step": 29340 + }, + { + "epoch": 2.39, + "learning_rate": 4.060734463276837e-06, + "loss": 0.0803, + "step": 29341 + }, + { + "epoch": 2.39, + "learning_rate": 4.060191221208171e-06, + "loss": 0.1466, + "step": 29342 + }, + { + "epoch": 2.39, + "learning_rate": 4.059647979139505e-06, + "loss": 0.2681, + "step": 29343 + }, + { + "epoch": 2.39, + "learning_rate": 4.0591047370708394e-06, + "loss": 0.1284, + "step": 29344 + }, + { + "epoch": 2.39, + "learning_rate": 4.058561495002174e-06, + "loss": 0.162, + "step": 29345 + }, + { + "epoch": 2.39, + "learning_rate": 4.058018252933508e-06, + "loss": 0.2627, + "step": 29346 + }, + { + "epoch": 2.39, + "learning_rate": 4.057475010864842e-06, + "loss": 0.2154, + "step": 29347 + }, + { + "epoch": 2.39, + "learning_rate": 4.0569317687961755e-06, + "loss": 0.2635, + "step": 29348 + }, + { + "epoch": 2.39, + "learning_rate": 4.05638852672751e-06, + "loss": 0.1009, + "step": 29349 + }, + { + "epoch": 2.39, + "learning_rate": 4.055845284658844e-06, + "loss": 0.2883, + "step": 29350 + }, + { + "epoch": 2.39, + "learning_rate": 4.055302042590178e-06, + "loss": 0.354, + "step": 29351 + }, + { + "epoch": 2.39, + "learning_rate": 4.0547588005215124e-06, + "loss": 0.2485, + "step": 29352 + }, + { + "epoch": 2.39, + "learning_rate": 4.054215558452847e-06, + "loss": 0.1509, + "step": 29353 + }, + { + "epoch": 2.39, + "learning_rate": 4.053672316384181e-06, + "loss": 0.2275, + "step": 29354 + }, + { + "epoch": 2.39, + "learning_rate": 4.053129074315515e-06, + "loss": 0.1075, + "step": 29355 + }, + { + "epoch": 2.39, + "learning_rate": 4.052585832246849e-06, + "loss": 0.1889, + "step": 29356 + }, + { + "epoch": 2.39, + "learning_rate": 4.052042590178184e-06, + "loss": 0.0426, + "step": 29357 + }, + { + "epoch": 2.39, + "learning_rate": 4.051499348109518e-06, + "loss": 0.2857, + "step": 29358 + }, + { + "epoch": 2.39, + "learning_rate": 4.050956106040852e-06, + "loss": 0.1346, + "step": 29359 + }, + { + "epoch": 2.39, + "learning_rate": 4.050412863972186e-06, + "loss": 0.344, + "step": 29360 + }, + { + "epoch": 2.39, + "learning_rate": 4.0498696219035205e-06, + "loss": 0.2957, + "step": 29361 + }, + { + "epoch": 2.39, + "learning_rate": 4.049326379834855e-06, + "loss": 0.1539, + "step": 29362 + }, + { + "epoch": 2.39, + "learning_rate": 4.048783137766189e-06, + "loss": 0.1121, + "step": 29363 + }, + { + "epoch": 2.39, + "learning_rate": 4.048239895697523e-06, + "loss": 0.1842, + "step": 29364 + }, + { + "epoch": 2.39, + "learning_rate": 4.0476966536288574e-06, + "loss": 0.2834, + "step": 29365 + }, + { + "epoch": 2.39, + "learning_rate": 4.047153411560192e-06, + "loss": 0.3567, + "step": 29366 + }, + { + "epoch": 2.39, + "learning_rate": 4.046610169491526e-06, + "loss": 0.1682, + "step": 29367 + }, + { + "epoch": 2.39, + "learning_rate": 4.04606692742286e-06, + "loss": 0.3306, + "step": 29368 + }, + { + "epoch": 2.39, + "learning_rate": 4.045523685354194e-06, + "loss": 0.2342, + "step": 29369 + }, + { + "epoch": 2.39, + "learning_rate": 4.044980443285529e-06, + "loss": 0.058, + "step": 29370 + }, + { + "epoch": 2.39, + "learning_rate": 4.044437201216863e-06, + "loss": 0.2419, + "step": 29371 + }, + { + "epoch": 2.39, + "learning_rate": 4.043893959148197e-06, + "loss": 0.352, + "step": 29372 + }, + { + "epoch": 2.39, + "learning_rate": 4.043350717079531e-06, + "loss": 0.1219, + "step": 29373 + }, + { + "epoch": 2.39, + "learning_rate": 4.0428074750108655e-06, + "loss": 0.3449, + "step": 29374 + }, + { + "epoch": 2.39, + "learning_rate": 4.0422642329422e-06, + "loss": 0.1607, + "step": 29375 + }, + { + "epoch": 2.39, + "learning_rate": 4.041720990873533e-06, + "loss": 0.15, + "step": 29376 + }, + { + "epoch": 2.39, + "learning_rate": 4.041177748804867e-06, + "loss": 0.12, + "step": 29377 + }, + { + "epoch": 2.39, + "learning_rate": 4.040634506736202e-06, + "loss": 0.1385, + "step": 29378 + }, + { + "epoch": 2.39, + "learning_rate": 4.040091264667536e-06, + "loss": 0.0615, + "step": 29379 + }, + { + "epoch": 2.39, + "learning_rate": 4.03954802259887e-06, + "loss": 0.2651, + "step": 29380 + }, + { + "epoch": 2.39, + "learning_rate": 4.039004780530204e-06, + "loss": 0.3352, + "step": 29381 + }, + { + "epoch": 2.39, + "learning_rate": 4.0384615384615385e-06, + "loss": 0.2345, + "step": 29382 + }, + { + "epoch": 2.39, + "learning_rate": 4.037918296392873e-06, + "loss": 0.5874, + "step": 29383 + }, + { + "epoch": 2.39, + "learning_rate": 4.037375054324208e-06, + "loss": 0.154, + "step": 29384 + }, + { + "epoch": 2.39, + "learning_rate": 4.036831812255542e-06, + "loss": 0.5084, + "step": 29385 + }, + { + "epoch": 2.39, + "learning_rate": 4.036288570186875e-06, + "loss": 0.3449, + "step": 29386 + }, + { + "epoch": 2.39, + "learning_rate": 4.03574532811821e-06, + "loss": 0.1996, + "step": 29387 + }, + { + "epoch": 2.39, + "learning_rate": 4.035202086049544e-06, + "loss": 0.2299, + "step": 29388 + }, + { + "epoch": 2.39, + "learning_rate": 4.034658843980878e-06, + "loss": 0.299, + "step": 29389 + }, + { + "epoch": 2.39, + "learning_rate": 4.034115601912212e-06, + "loss": 0.3757, + "step": 29390 + }, + { + "epoch": 2.39, + "learning_rate": 4.0335723598435466e-06, + "loss": 0.1517, + "step": 29391 + }, + { + "epoch": 2.4, + "learning_rate": 4.033029117774881e-06, + "loss": 0.3032, + "step": 29392 + }, + { + "epoch": 2.4, + "learning_rate": 4.032485875706215e-06, + "loss": 0.2255, + "step": 29393 + }, + { + "epoch": 2.4, + "learning_rate": 4.031942633637549e-06, + "loss": 0.178, + "step": 29394 + }, + { + "epoch": 2.4, + "learning_rate": 4.0313993915688835e-06, + "loss": 0.23, + "step": 29395 + }, + { + "epoch": 2.4, + "learning_rate": 4.030856149500218e-06, + "loss": 0.2886, + "step": 29396 + }, + { + "epoch": 2.4, + "learning_rate": 4.030312907431552e-06, + "loss": 0.1128, + "step": 29397 + }, + { + "epoch": 2.4, + "learning_rate": 4.029769665362886e-06, + "loss": 0.4377, + "step": 29398 + }, + { + "epoch": 2.4, + "learning_rate": 4.02922642329422e-06, + "loss": 0.1591, + "step": 29399 + }, + { + "epoch": 2.4, + "learning_rate": 4.028683181225555e-06, + "loss": 0.261, + "step": 29400 + }, + { + "epoch": 2.4, + "learning_rate": 4.028139939156889e-06, + "loss": 0.0982, + "step": 29401 + }, + { + "epoch": 2.4, + "learning_rate": 4.027596697088223e-06, + "loss": 0.2191, + "step": 29402 + }, + { + "epoch": 2.4, + "learning_rate": 4.027053455019557e-06, + "loss": 0.1301, + "step": 29403 + }, + { + "epoch": 2.4, + "learning_rate": 4.0265102129508916e-06, + "loss": 0.2664, + "step": 29404 + }, + { + "epoch": 2.4, + "learning_rate": 4.025966970882225e-06, + "loss": 0.1987, + "step": 29405 + }, + { + "epoch": 2.4, + "learning_rate": 4.025423728813559e-06, + "loss": 0.1254, + "step": 29406 + }, + { + "epoch": 2.4, + "learning_rate": 4.024880486744893e-06, + "loss": 0.354, + "step": 29407 + }, + { + "epoch": 2.4, + "learning_rate": 4.024337244676228e-06, + "loss": 0.4363, + "step": 29408 + }, + { + "epoch": 2.4, + "learning_rate": 4.023794002607562e-06, + "loss": 0.2096, + "step": 29409 + }, + { + "epoch": 2.4, + "learning_rate": 4.023250760538896e-06, + "loss": 0.1256, + "step": 29410 + }, + { + "epoch": 2.4, + "learning_rate": 4.022707518470231e-06, + "loss": 0.2529, + "step": 29411 + }, + { + "epoch": 2.4, + "learning_rate": 4.022164276401565e-06, + "loss": 0.2302, + "step": 29412 + }, + { + "epoch": 2.4, + "learning_rate": 4.0216210343329e-06, + "loss": 0.3756, + "step": 29413 + }, + { + "epoch": 2.4, + "learning_rate": 4.021077792264233e-06, + "loss": 0.3594, + "step": 29414 + }, + { + "epoch": 2.4, + "learning_rate": 4.020534550195567e-06, + "loss": 0.6986, + "step": 29415 + }, + { + "epoch": 2.4, + "learning_rate": 4.0199913081269015e-06, + "loss": 0.1645, + "step": 29416 + }, + { + "epoch": 2.4, + "learning_rate": 4.019448066058236e-06, + "loss": 0.4017, + "step": 29417 + }, + { + "epoch": 2.4, + "learning_rate": 4.01890482398957e-06, + "loss": 0.3636, + "step": 29418 + }, + { + "epoch": 2.4, + "learning_rate": 4.018361581920904e-06, + "loss": 0.1237, + "step": 29419 + }, + { + "epoch": 2.4, + "learning_rate": 4.017818339852238e-06, + "loss": 0.1387, + "step": 29420 + }, + { + "epoch": 2.4, + "learning_rate": 4.017275097783573e-06, + "loss": 0.4784, + "step": 29421 + }, + { + "epoch": 2.4, + "learning_rate": 4.016731855714907e-06, + "loss": 0.1624, + "step": 29422 + }, + { + "epoch": 2.4, + "learning_rate": 4.016188613646241e-06, + "loss": 0.1985, + "step": 29423 + }, + { + "epoch": 2.4, + "learning_rate": 4.015645371577575e-06, + "loss": 0.1052, + "step": 29424 + }, + { + "epoch": 2.4, + "learning_rate": 4.0151021295089096e-06, + "loss": 0.1665, + "step": 29425 + }, + { + "epoch": 2.4, + "learning_rate": 4.014558887440244e-06, + "loss": 0.0289, + "step": 29426 + }, + { + "epoch": 2.4, + "learning_rate": 4.014015645371578e-06, + "loss": 0.2396, + "step": 29427 + }, + { + "epoch": 2.4, + "learning_rate": 4.013472403302912e-06, + "loss": 0.1764, + "step": 29428 + }, + { + "epoch": 2.4, + "learning_rate": 4.0129291612342465e-06, + "loss": 0.1926, + "step": 29429 + }, + { + "epoch": 2.4, + "learning_rate": 4.012385919165581e-06, + "loss": 0.0965, + "step": 29430 + }, + { + "epoch": 2.4, + "learning_rate": 4.011842677096915e-06, + "loss": 0.1532, + "step": 29431 + }, + { + "epoch": 2.4, + "learning_rate": 4.011299435028249e-06, + "loss": 0.2274, + "step": 29432 + }, + { + "epoch": 2.4, + "learning_rate": 4.0107561929595826e-06, + "loss": 0.2176, + "step": 29433 + }, + { + "epoch": 2.4, + "learning_rate": 4.010212950890917e-06, + "loss": 0.2359, + "step": 29434 + }, + { + "epoch": 2.4, + "learning_rate": 4.009669708822251e-06, + "loss": 0.0569, + "step": 29435 + }, + { + "epoch": 2.4, + "learning_rate": 4.009126466753585e-06, + "loss": 0.2964, + "step": 29436 + }, + { + "epoch": 2.4, + "learning_rate": 4.0085832246849195e-06, + "loss": 0.2202, + "step": 29437 + }, + { + "epoch": 2.4, + "learning_rate": 4.0080399826162546e-06, + "loss": 0.3069, + "step": 29438 + }, + { + "epoch": 2.4, + "learning_rate": 4.007496740547589e-06, + "loss": 0.2737, + "step": 29439 + }, + { + "epoch": 2.4, + "learning_rate": 4.006953498478923e-06, + "loss": 0.4409, + "step": 29440 + }, + { + "epoch": 2.4, + "learning_rate": 4.006410256410257e-06, + "loss": 0.2702, + "step": 29441 + }, + { + "epoch": 2.4, + "learning_rate": 4.0058670143415915e-06, + "loss": 0.3897, + "step": 29442 + }, + { + "epoch": 2.4, + "learning_rate": 4.005323772272925e-06, + "loss": 0.3628, + "step": 29443 + }, + { + "epoch": 2.4, + "learning_rate": 4.004780530204259e-06, + "loss": 0.1112, + "step": 29444 + }, + { + "epoch": 2.4, + "learning_rate": 4.004237288135593e-06, + "loss": 0.2777, + "step": 29445 + }, + { + "epoch": 2.4, + "learning_rate": 4.0036940460669276e-06, + "loss": 0.1262, + "step": 29446 + }, + { + "epoch": 2.4, + "learning_rate": 4.003150803998262e-06, + "loss": 0.322, + "step": 29447 + }, + { + "epoch": 2.4, + "learning_rate": 4.002607561929596e-06, + "loss": 0.2773, + "step": 29448 + }, + { + "epoch": 2.4, + "learning_rate": 4.00206431986093e-06, + "loss": 0.3096, + "step": 29449 + }, + { + "epoch": 2.4, + "learning_rate": 4.0015210777922645e-06, + "loss": 0.0458, + "step": 29450 + }, + { + "epoch": 2.4, + "learning_rate": 4.000977835723599e-06, + "loss": 0.3581, + "step": 29451 + }, + { + "epoch": 2.4, + "learning_rate": 4.000434593654933e-06, + "loss": 0.2333, + "step": 29452 + }, + { + "epoch": 2.4, + "learning_rate": 3.999891351586267e-06, + "loss": 0.1768, + "step": 29453 + }, + { + "epoch": 2.4, + "learning_rate": 3.999348109517601e-06, + "loss": 0.1825, + "step": 29454 + }, + { + "epoch": 2.4, + "learning_rate": 3.998804867448936e-06, + "loss": 0.2251, + "step": 29455 + }, + { + "epoch": 2.4, + "learning_rate": 3.99826162538027e-06, + "loss": 0.1269, + "step": 29456 + }, + { + "epoch": 2.4, + "learning_rate": 3.997718383311604e-06, + "loss": 0.1102, + "step": 29457 + }, + { + "epoch": 2.4, + "learning_rate": 3.997175141242938e-06, + "loss": 0.3403, + "step": 29458 + }, + { + "epoch": 2.4, + "learning_rate": 3.9966318991742726e-06, + "loss": 0.3955, + "step": 29459 + }, + { + "epoch": 2.4, + "learning_rate": 3.996088657105607e-06, + "loss": 0.1374, + "step": 29460 + }, + { + "epoch": 2.4, + "learning_rate": 3.995545415036941e-06, + "loss": 0.03, + "step": 29461 + }, + { + "epoch": 2.4, + "learning_rate": 3.995002172968274e-06, + "loss": 0.0975, + "step": 29462 + }, + { + "epoch": 2.4, + "learning_rate": 3.994458930899609e-06, + "loss": 0.0759, + "step": 29463 + }, + { + "epoch": 2.4, + "learning_rate": 3.993915688830943e-06, + "loss": 0.3796, + "step": 29464 + }, + { + "epoch": 2.4, + "learning_rate": 3.993372446762278e-06, + "loss": 0.2117, + "step": 29465 + }, + { + "epoch": 2.4, + "learning_rate": 3.992829204693612e-06, + "loss": 0.5164, + "step": 29466 + }, + { + "epoch": 2.4, + "learning_rate": 3.992285962624946e-06, + "loss": 0.3327, + "step": 29467 + }, + { + "epoch": 2.4, + "learning_rate": 3.991742720556281e-06, + "loss": 0.2523, + "step": 29468 + }, + { + "epoch": 2.4, + "learning_rate": 3.991199478487615e-06, + "loss": 0.0766, + "step": 29469 + }, + { + "epoch": 2.4, + "learning_rate": 3.990656236418949e-06, + "loss": 0.28, + "step": 29470 + }, + { + "epoch": 2.4, + "learning_rate": 3.9901129943502825e-06, + "loss": 0.1999, + "step": 29471 + }, + { + "epoch": 2.4, + "learning_rate": 3.989569752281617e-06, + "loss": 0.3564, + "step": 29472 + }, + { + "epoch": 2.4, + "learning_rate": 3.989026510212951e-06, + "loss": 0.0867, + "step": 29473 + }, + { + "epoch": 2.4, + "learning_rate": 3.988483268144285e-06, + "loss": 0.3472, + "step": 29474 + }, + { + "epoch": 2.4, + "learning_rate": 3.987940026075619e-06, + "loss": 0.327, + "step": 29475 + }, + { + "epoch": 2.4, + "learning_rate": 3.987396784006954e-06, + "loss": 0.113, + "step": 29476 + }, + { + "epoch": 2.4, + "learning_rate": 3.986853541938288e-06, + "loss": 0.1318, + "step": 29477 + }, + { + "epoch": 2.4, + "learning_rate": 3.986310299869622e-06, + "loss": 0.0825, + "step": 29478 + }, + { + "epoch": 2.4, + "learning_rate": 3.985767057800956e-06, + "loss": 0.2114, + "step": 29479 + }, + { + "epoch": 2.4, + "learning_rate": 3.9852238157322906e-06, + "loss": 0.1514, + "step": 29480 + }, + { + "epoch": 2.4, + "learning_rate": 3.984680573663625e-06, + "loss": 0.2213, + "step": 29481 + }, + { + "epoch": 2.4, + "learning_rate": 3.984137331594959e-06, + "loss": 0.1187, + "step": 29482 + }, + { + "epoch": 2.4, + "learning_rate": 3.983594089526293e-06, + "loss": 0.1865, + "step": 29483 + }, + { + "epoch": 2.4, + "learning_rate": 3.9830508474576275e-06, + "loss": 0.1978, + "step": 29484 + }, + { + "epoch": 2.4, + "learning_rate": 3.982507605388962e-06, + "loss": 0.2348, + "step": 29485 + }, + { + "epoch": 2.4, + "learning_rate": 3.981964363320296e-06, + "loss": 0.1053, + "step": 29486 + }, + { + "epoch": 2.4, + "learning_rate": 3.98142112125163e-06, + "loss": 0.1054, + "step": 29487 + }, + { + "epoch": 2.4, + "learning_rate": 3.980877879182964e-06, + "loss": 0.259, + "step": 29488 + }, + { + "epoch": 2.4, + "learning_rate": 3.980334637114299e-06, + "loss": 0.2398, + "step": 29489 + }, + { + "epoch": 2.4, + "learning_rate": 3.979791395045632e-06, + "loss": 0.1605, + "step": 29490 + }, + { + "epoch": 2.4, + "learning_rate": 3.979248152976966e-06, + "loss": 0.1527, + "step": 29491 + }, + { + "epoch": 2.4, + "learning_rate": 3.978704910908301e-06, + "loss": 0.1302, + "step": 29492 + }, + { + "epoch": 2.4, + "learning_rate": 3.9781616688396355e-06, + "loss": 0.3119, + "step": 29493 + }, + { + "epoch": 2.4, + "learning_rate": 3.97761842677097e-06, + "loss": 0.1977, + "step": 29494 + }, + { + "epoch": 2.4, + "learning_rate": 3.977075184702304e-06, + "loss": 0.1285, + "step": 29495 + }, + { + "epoch": 2.4, + "learning_rate": 3.976531942633638e-06, + "loss": 0.1469, + "step": 29496 + }, + { + "epoch": 2.4, + "learning_rate": 3.9759887005649725e-06, + "loss": 0.2259, + "step": 29497 + }, + { + "epoch": 2.4, + "learning_rate": 3.975445458496307e-06, + "loss": 0.349, + "step": 29498 + }, + { + "epoch": 2.4, + "learning_rate": 3.974902216427641e-06, + "loss": 0.1183, + "step": 29499 + }, + { + "epoch": 2.4, + "learning_rate": 3.974358974358974e-06, + "loss": 0.2552, + "step": 29500 + }, + { + "epoch": 2.4, + "eval_accuracy": 0.8448293428425879, + "eval_loss": 0.4919016361236572, + "eval_runtime": 22.3052, + "eval_samples_per_second": 440.031, + "eval_steps_per_second": 3.452, + "step": 29500 + }, + { + "epoch": 2.4, + "learning_rate": 3.9738157322903085e-06, + "loss": 0.2896, + "step": 29501 + }, + { + "epoch": 2.4, + "learning_rate": 3.973272490221643e-06, + "loss": 0.0232, + "step": 29502 + }, + { + "epoch": 2.4, + "learning_rate": 3.972729248152977e-06, + "loss": 0.0985, + "step": 29503 + }, + { + "epoch": 2.4, + "learning_rate": 3.972186006084311e-06, + "loss": 0.2059, + "step": 29504 + }, + { + "epoch": 2.4, + "learning_rate": 3.9716427640156455e-06, + "loss": 0.1038, + "step": 29505 + }, + { + "epoch": 2.4, + "learning_rate": 3.97109952194698e-06, + "loss": 0.2974, + "step": 29506 + }, + { + "epoch": 2.4, + "learning_rate": 3.970556279878314e-06, + "loss": 0.1865, + "step": 29507 + }, + { + "epoch": 2.4, + "learning_rate": 3.970013037809648e-06, + "loss": 0.179, + "step": 29508 + }, + { + "epoch": 2.4, + "learning_rate": 3.969469795740982e-06, + "loss": 0.4376, + "step": 29509 + }, + { + "epoch": 2.4, + "learning_rate": 3.968926553672317e-06, + "loss": 0.1415, + "step": 29510 + }, + { + "epoch": 2.4, + "learning_rate": 3.968383311603651e-06, + "loss": 0.2063, + "step": 29511 + }, + { + "epoch": 2.4, + "learning_rate": 3.967840069534985e-06, + "loss": 0.2061, + "step": 29512 + }, + { + "epoch": 2.4, + "learning_rate": 3.967296827466319e-06, + "loss": 0.0805, + "step": 29513 + }, + { + "epoch": 2.4, + "learning_rate": 3.9667535853976535e-06, + "loss": 0.1745, + "step": 29514 + }, + { + "epoch": 2.41, + "learning_rate": 3.966210343328988e-06, + "loss": 0.1726, + "step": 29515 + }, + { + "epoch": 2.41, + "learning_rate": 3.965667101260322e-06, + "loss": 0.2942, + "step": 29516 + }, + { + "epoch": 2.41, + "learning_rate": 3.965123859191656e-06, + "loss": 0.2641, + "step": 29517 + }, + { + "epoch": 2.41, + "learning_rate": 3.9645806171229905e-06, + "loss": 0.2135, + "step": 29518 + }, + { + "epoch": 2.41, + "learning_rate": 3.964037375054325e-06, + "loss": 0.2433, + "step": 29519 + }, + { + "epoch": 2.41, + "learning_rate": 3.963494132985659e-06, + "loss": 0.1698, + "step": 29520 + }, + { + "epoch": 2.41, + "learning_rate": 3.962950890916993e-06, + "loss": 0.1502, + "step": 29521 + }, + { + "epoch": 2.41, + "learning_rate": 3.962407648848327e-06, + "loss": 0.2584, + "step": 29522 + }, + { + "epoch": 2.41, + "learning_rate": 3.961864406779662e-06, + "loss": 0.3742, + "step": 29523 + }, + { + "epoch": 2.41, + "learning_rate": 3.961321164710996e-06, + "loss": 0.209, + "step": 29524 + }, + { + "epoch": 2.41, + "learning_rate": 3.96077792264233e-06, + "loss": 0.0746, + "step": 29525 + }, + { + "epoch": 2.41, + "learning_rate": 3.960234680573664e-06, + "loss": 0.1482, + "step": 29526 + }, + { + "epoch": 2.41, + "learning_rate": 3.9596914385049985e-06, + "loss": 0.3407, + "step": 29527 + }, + { + "epoch": 2.41, + "learning_rate": 3.959148196436332e-06, + "loss": 0.1938, + "step": 29528 + }, + { + "epoch": 2.41, + "learning_rate": 3.958604954367666e-06, + "loss": 0.118, + "step": 29529 + }, + { + "epoch": 2.41, + "learning_rate": 3.958061712299e-06, + "loss": 0.053, + "step": 29530 + }, + { + "epoch": 2.41, + "learning_rate": 3.957518470230335e-06, + "loss": 0.1416, + "step": 29531 + }, + { + "epoch": 2.41, + "learning_rate": 3.956975228161669e-06, + "loss": 0.1158, + "step": 29532 + }, + { + "epoch": 2.41, + "learning_rate": 3.956431986093003e-06, + "loss": 0.3137, + "step": 29533 + }, + { + "epoch": 2.41, + "learning_rate": 3.955888744024337e-06, + "loss": 0.0695, + "step": 29534 + }, + { + "epoch": 2.41, + "learning_rate": 3.9553455019556715e-06, + "loss": 0.24, + "step": 29535 + }, + { + "epoch": 2.41, + "learning_rate": 3.954802259887006e-06, + "loss": 0.2167, + "step": 29536 + }, + { + "epoch": 2.41, + "learning_rate": 3.954259017818341e-06, + "loss": 0.1161, + "step": 29537 + }, + { + "epoch": 2.41, + "learning_rate": 3.953715775749674e-06, + "loss": 0.3448, + "step": 29538 + }, + { + "epoch": 2.41, + "learning_rate": 3.9531725336810085e-06, + "loss": 0.2995, + "step": 29539 + }, + { + "epoch": 2.41, + "learning_rate": 3.952629291612343e-06, + "loss": 0.0902, + "step": 29540 + }, + { + "epoch": 2.41, + "learning_rate": 3.952086049543677e-06, + "loss": 0.1641, + "step": 29541 + }, + { + "epoch": 2.41, + "learning_rate": 3.951542807475011e-06, + "loss": 0.3551, + "step": 29542 + }, + { + "epoch": 2.41, + "learning_rate": 3.950999565406345e-06, + "loss": 0.3258, + "step": 29543 + }, + { + "epoch": 2.41, + "learning_rate": 3.95045632333768e-06, + "loss": 0.3991, + "step": 29544 + }, + { + "epoch": 2.41, + "learning_rate": 3.949913081269014e-06, + "loss": 0.1794, + "step": 29545 + }, + { + "epoch": 2.41, + "learning_rate": 3.949369839200348e-06, + "loss": 0.0642, + "step": 29546 + }, + { + "epoch": 2.41, + "learning_rate": 3.948826597131682e-06, + "loss": 0.2413, + "step": 29547 + }, + { + "epoch": 2.41, + "learning_rate": 3.9482833550630165e-06, + "loss": 0.0292, + "step": 29548 + }, + { + "epoch": 2.41, + "learning_rate": 3.947740112994351e-06, + "loss": 0.1931, + "step": 29549 + }, + { + "epoch": 2.41, + "learning_rate": 3.947196870925685e-06, + "loss": 0.0548, + "step": 29550 + }, + { + "epoch": 2.41, + "learning_rate": 3.946653628857019e-06, + "loss": 0.3555, + "step": 29551 + }, + { + "epoch": 2.41, + "learning_rate": 3.9461103867883535e-06, + "loss": 0.4077, + "step": 29552 + }, + { + "epoch": 2.41, + "learning_rate": 3.945567144719688e-06, + "loss": 0.1886, + "step": 29553 + }, + { + "epoch": 2.41, + "learning_rate": 3.945023902651022e-06, + "loss": 0.6683, + "step": 29554 + }, + { + "epoch": 2.41, + "learning_rate": 3.944480660582356e-06, + "loss": 0.3222, + "step": 29555 + }, + { + "epoch": 2.41, + "learning_rate": 3.94393741851369e-06, + "loss": 0.1947, + "step": 29556 + }, + { + "epoch": 2.41, + "learning_rate": 3.943394176445024e-06, + "loss": 0.2361, + "step": 29557 + }, + { + "epoch": 2.41, + "learning_rate": 3.942850934376358e-06, + "loss": 0.5009, + "step": 29558 + }, + { + "epoch": 2.41, + "learning_rate": 3.942307692307692e-06, + "loss": 0.313, + "step": 29559 + }, + { + "epoch": 2.41, + "learning_rate": 3.9417644502390265e-06, + "loss": 0.0821, + "step": 29560 + }, + { + "epoch": 2.41, + "learning_rate": 3.941221208170361e-06, + "loss": 0.3037, + "step": 29561 + }, + { + "epoch": 2.41, + "learning_rate": 3.940677966101695e-06, + "loss": 0.1336, + "step": 29562 + }, + { + "epoch": 2.41, + "learning_rate": 3.940134724033029e-06, + "loss": 0.4382, + "step": 29563 + }, + { + "epoch": 2.41, + "learning_rate": 3.939591481964364e-06, + "loss": 0.313, + "step": 29564 + }, + { + "epoch": 2.41, + "learning_rate": 3.9390482398956985e-06, + "loss": 0.1676, + "step": 29565 + }, + { + "epoch": 2.41, + "learning_rate": 3.938504997827032e-06, + "loss": 0.1264, + "step": 29566 + }, + { + "epoch": 2.41, + "learning_rate": 3.937961755758366e-06, + "loss": 0.4174, + "step": 29567 + }, + { + "epoch": 2.41, + "learning_rate": 3.9374185136897e-06, + "loss": 0.1796, + "step": 29568 + }, + { + "epoch": 2.41, + "learning_rate": 3.9368752716210345e-06, + "loss": 0.2385, + "step": 29569 + }, + { + "epoch": 2.41, + "learning_rate": 3.936332029552369e-06, + "loss": 0.2106, + "step": 29570 + }, + { + "epoch": 2.41, + "learning_rate": 3.935788787483703e-06, + "loss": 0.3281, + "step": 29571 + }, + { + "epoch": 2.41, + "learning_rate": 3.935245545415037e-06, + "loss": 0.2557, + "step": 29572 + }, + { + "epoch": 2.41, + "learning_rate": 3.9347023033463715e-06, + "loss": 0.1739, + "step": 29573 + }, + { + "epoch": 2.41, + "learning_rate": 3.934159061277706e-06, + "loss": 0.1781, + "step": 29574 + }, + { + "epoch": 2.41, + "learning_rate": 3.93361581920904e-06, + "loss": 0.1472, + "step": 29575 + }, + { + "epoch": 2.41, + "learning_rate": 3.933072577140374e-06, + "loss": 0.2071, + "step": 29576 + }, + { + "epoch": 2.41, + "learning_rate": 3.932529335071708e-06, + "loss": 0.3322, + "step": 29577 + }, + { + "epoch": 2.41, + "learning_rate": 3.931986093003043e-06, + "loss": 0.1546, + "step": 29578 + }, + { + "epoch": 2.41, + "learning_rate": 3.931442850934377e-06, + "loss": 0.1513, + "step": 29579 + }, + { + "epoch": 2.41, + "learning_rate": 3.930899608865711e-06, + "loss": 0.2802, + "step": 29580 + }, + { + "epoch": 2.41, + "learning_rate": 3.930356366797045e-06, + "loss": 0.0697, + "step": 29581 + }, + { + "epoch": 2.41, + "learning_rate": 3.9298131247283795e-06, + "loss": 0.0746, + "step": 29582 + }, + { + "epoch": 2.41, + "learning_rate": 3.929269882659714e-06, + "loss": 0.1, + "step": 29583 + }, + { + "epoch": 2.41, + "learning_rate": 3.928726640591048e-06, + "loss": 0.0529, + "step": 29584 + }, + { + "epoch": 2.41, + "learning_rate": 3.928183398522381e-06, + "loss": 0.1982, + "step": 29585 + }, + { + "epoch": 2.41, + "learning_rate": 3.927640156453716e-06, + "loss": 0.0524, + "step": 29586 + }, + { + "epoch": 2.41, + "learning_rate": 3.92709691438505e-06, + "loss": 0.172, + "step": 29587 + }, + { + "epoch": 2.41, + "learning_rate": 3.926553672316384e-06, + "loss": 0.122, + "step": 29588 + }, + { + "epoch": 2.41, + "learning_rate": 3.926010430247718e-06, + "loss": 0.2638, + "step": 29589 + }, + { + "epoch": 2.41, + "learning_rate": 3.9254671881790525e-06, + "loss": 0.286, + "step": 29590 + }, + { + "epoch": 2.41, + "learning_rate": 3.924923946110388e-06, + "loss": 0.3221, + "step": 29591 + }, + { + "epoch": 2.41, + "learning_rate": 3.924380704041722e-06, + "loss": 0.3328, + "step": 29592 + }, + { + "epoch": 2.41, + "learning_rate": 3.923837461973056e-06, + "loss": 0.4755, + "step": 29593 + }, + { + "epoch": 2.41, + "learning_rate": 3.92329421990439e-06, + "loss": 0.0595, + "step": 29594 + }, + { + "epoch": 2.41, + "learning_rate": 3.922750977835724e-06, + "loss": 0.1634, + "step": 29595 + }, + { + "epoch": 2.41, + "learning_rate": 3.922207735767058e-06, + "loss": 0.1584, + "step": 29596 + }, + { + "epoch": 2.41, + "learning_rate": 3.921664493698392e-06, + "loss": 0.0841, + "step": 29597 + }, + { + "epoch": 2.41, + "learning_rate": 3.921121251629726e-06, + "loss": 0.2491, + "step": 29598 + }, + { + "epoch": 2.41, + "learning_rate": 3.920578009561061e-06, + "loss": 0.1946, + "step": 29599 + }, + { + "epoch": 2.41, + "learning_rate": 3.920034767492395e-06, + "loss": 0.2448, + "step": 29600 + }, + { + "epoch": 2.41, + "learning_rate": 3.919491525423729e-06, + "loss": 0.1489, + "step": 29601 + }, + { + "epoch": 2.41, + "learning_rate": 3.918948283355063e-06, + "loss": 0.6193, + "step": 29602 + }, + { + "epoch": 2.41, + "learning_rate": 3.9184050412863975e-06, + "loss": 0.2135, + "step": 29603 + }, + { + "epoch": 2.41, + "learning_rate": 3.917861799217732e-06, + "loss": 0.1748, + "step": 29604 + }, + { + "epoch": 2.41, + "learning_rate": 3.917318557149066e-06, + "loss": 0.0644, + "step": 29605 + }, + { + "epoch": 2.41, + "learning_rate": 3.9167753150804e-06, + "loss": 0.2376, + "step": 29606 + }, + { + "epoch": 2.41, + "learning_rate": 3.9162320730117344e-06, + "loss": 0.2276, + "step": 29607 + }, + { + "epoch": 2.41, + "learning_rate": 3.915688830943069e-06, + "loss": 0.3508, + "step": 29608 + }, + { + "epoch": 2.41, + "learning_rate": 3.915145588874403e-06, + "loss": 0.2312, + "step": 29609 + }, + { + "epoch": 2.41, + "learning_rate": 3.914602346805737e-06, + "loss": 0.1548, + "step": 29610 + }, + { + "epoch": 2.41, + "learning_rate": 3.914059104737071e-06, + "loss": 0.4507, + "step": 29611 + }, + { + "epoch": 2.41, + "learning_rate": 3.913515862668406e-06, + "loss": 0.2779, + "step": 29612 + }, + { + "epoch": 2.41, + "learning_rate": 3.91297262059974e-06, + "loss": 0.1636, + "step": 29613 + }, + { + "epoch": 2.41, + "learning_rate": 3.912429378531073e-06, + "loss": 0.3834, + "step": 29614 + }, + { + "epoch": 2.41, + "learning_rate": 3.9118861364624074e-06, + "loss": 0.3178, + "step": 29615 + }, + { + "epoch": 2.41, + "learning_rate": 3.911342894393742e-06, + "loss": 0.0941, + "step": 29616 + }, + { + "epoch": 2.41, + "learning_rate": 3.910799652325076e-06, + "loss": 0.2227, + "step": 29617 + }, + { + "epoch": 2.41, + "learning_rate": 3.910256410256411e-06, + "loss": 0.3865, + "step": 29618 + }, + { + "epoch": 2.41, + "learning_rate": 3.909713168187745e-06, + "loss": 0.2755, + "step": 29619 + }, + { + "epoch": 2.41, + "learning_rate": 3.9091699261190794e-06, + "loss": 0.3837, + "step": 29620 + }, + { + "epoch": 2.41, + "learning_rate": 3.908626684050414e-06, + "loss": 0.1315, + "step": 29621 + }, + { + "epoch": 2.41, + "learning_rate": 3.908083441981748e-06, + "loss": 0.1742, + "step": 29622 + }, + { + "epoch": 2.41, + "learning_rate": 3.907540199913081e-06, + "loss": 0.156, + "step": 29623 + }, + { + "epoch": 2.41, + "learning_rate": 3.9069969578444155e-06, + "loss": 0.2627, + "step": 29624 + }, + { + "epoch": 2.41, + "learning_rate": 3.90645371577575e-06, + "loss": 0.1307, + "step": 29625 + }, + { + "epoch": 2.41, + "learning_rate": 3.905910473707084e-06, + "loss": 0.2755, + "step": 29626 + }, + { + "epoch": 2.41, + "learning_rate": 3.905367231638418e-06, + "loss": 0.1564, + "step": 29627 + }, + { + "epoch": 2.41, + "learning_rate": 3.9048239895697524e-06, + "loss": 0.2973, + "step": 29628 + }, + { + "epoch": 2.41, + "learning_rate": 3.904280747501087e-06, + "loss": 0.2427, + "step": 29629 + }, + { + "epoch": 2.41, + "learning_rate": 3.903737505432421e-06, + "loss": 0.2731, + "step": 29630 + }, + { + "epoch": 2.41, + "learning_rate": 3.903194263363755e-06, + "loss": 0.1216, + "step": 29631 + }, + { + "epoch": 2.41, + "learning_rate": 3.902651021295089e-06, + "loss": 0.1712, + "step": 29632 + }, + { + "epoch": 2.41, + "learning_rate": 3.902107779226424e-06, + "loss": 0.0481, + "step": 29633 + }, + { + "epoch": 2.41, + "learning_rate": 3.901564537157758e-06, + "loss": 0.0524, + "step": 29634 + }, + { + "epoch": 2.41, + "learning_rate": 3.901021295089092e-06, + "loss": 0.4058, + "step": 29635 + }, + { + "epoch": 2.41, + "learning_rate": 3.900478053020426e-06, + "loss": 0.256, + "step": 29636 + }, + { + "epoch": 2.42, + "learning_rate": 3.8999348109517605e-06, + "loss": 0.2119, + "step": 29637 + }, + { + "epoch": 2.42, + "learning_rate": 3.899391568883095e-06, + "loss": 0.1513, + "step": 29638 + }, + { + "epoch": 2.42, + "learning_rate": 3.898848326814429e-06, + "loss": 0.1358, + "step": 29639 + }, + { + "epoch": 2.42, + "learning_rate": 3.898305084745763e-06, + "loss": 0.1401, + "step": 29640 + }, + { + "epoch": 2.42, + "learning_rate": 3.8977618426770974e-06, + "loss": 0.2428, + "step": 29641 + }, + { + "epoch": 2.42, + "learning_rate": 3.897218600608432e-06, + "loss": 0.1478, + "step": 29642 + }, + { + "epoch": 2.42, + "learning_rate": 3.896675358539765e-06, + "loss": 0.1938, + "step": 29643 + }, + { + "epoch": 2.42, + "learning_rate": 3.896132116471099e-06, + "loss": 0.2675, + "step": 29644 + }, + { + "epoch": 2.42, + "learning_rate": 3.895588874402434e-06, + "loss": 0.3337, + "step": 29645 + }, + { + "epoch": 2.42, + "learning_rate": 3.895045632333769e-06, + "loss": 0.2545, + "step": 29646 + }, + { + "epoch": 2.42, + "learning_rate": 3.894502390265103e-06, + "loss": 0.207, + "step": 29647 + }, + { + "epoch": 2.42, + "learning_rate": 3.893959148196437e-06, + "loss": 0.3514, + "step": 29648 + }, + { + "epoch": 2.42, + "learning_rate": 3.893415906127771e-06, + "loss": 0.0964, + "step": 29649 + }, + { + "epoch": 2.42, + "learning_rate": 3.8928726640591055e-06, + "loss": 0.1577, + "step": 29650 + }, + { + "epoch": 2.42, + "learning_rate": 3.89232942199044e-06, + "loss": 0.4667, + "step": 29651 + }, + { + "epoch": 2.42, + "learning_rate": 3.891786179921773e-06, + "loss": 0.1251, + "step": 29652 + }, + { + "epoch": 2.42, + "learning_rate": 3.891242937853107e-06, + "loss": 0.3214, + "step": 29653 + }, + { + "epoch": 2.42, + "learning_rate": 3.890699695784442e-06, + "loss": 0.0552, + "step": 29654 + }, + { + "epoch": 2.42, + "learning_rate": 3.890156453715776e-06, + "loss": 0.2482, + "step": 29655 + }, + { + "epoch": 2.42, + "learning_rate": 3.88961321164711e-06, + "loss": 0.3747, + "step": 29656 + }, + { + "epoch": 2.42, + "learning_rate": 3.889069969578444e-06, + "loss": 0.1276, + "step": 29657 + }, + { + "epoch": 2.42, + "learning_rate": 3.8885267275097785e-06, + "loss": 0.1259, + "step": 29658 + }, + { + "epoch": 2.42, + "learning_rate": 3.887983485441113e-06, + "loss": 0.1098, + "step": 29659 + }, + { + "epoch": 2.42, + "learning_rate": 3.887440243372447e-06, + "loss": 0.1942, + "step": 29660 + }, + { + "epoch": 2.42, + "learning_rate": 3.886897001303781e-06, + "loss": 0.1259, + "step": 29661 + }, + { + "epoch": 2.42, + "learning_rate": 3.8863537592351154e-06, + "loss": 0.1866, + "step": 29662 + }, + { + "epoch": 2.42, + "learning_rate": 3.88581051716645e-06, + "loss": 0.3223, + "step": 29663 + }, + { + "epoch": 2.42, + "learning_rate": 3.885267275097784e-06, + "loss": 0.3183, + "step": 29664 + }, + { + "epoch": 2.42, + "learning_rate": 3.884724033029118e-06, + "loss": 0.3472, + "step": 29665 + }, + { + "epoch": 2.42, + "learning_rate": 3.884180790960452e-06, + "loss": 0.1687, + "step": 29666 + }, + { + "epoch": 2.42, + "learning_rate": 3.883637548891787e-06, + "loss": 0.0737, + "step": 29667 + }, + { + "epoch": 2.42, + "learning_rate": 3.883094306823121e-06, + "loss": 0.1881, + "step": 29668 + }, + { + "epoch": 2.42, + "learning_rate": 3.882551064754455e-06, + "loss": 0.229, + "step": 29669 + }, + { + "epoch": 2.42, + "learning_rate": 3.882007822685789e-06, + "loss": 0.2739, + "step": 29670 + }, + { + "epoch": 2.42, + "learning_rate": 3.881464580617123e-06, + "loss": 0.1967, + "step": 29671 + }, + { + "epoch": 2.42, + "learning_rate": 3.880921338548458e-06, + "loss": 0.6347, + "step": 29672 + }, + { + "epoch": 2.42, + "learning_rate": 3.880378096479792e-06, + "loss": 0.0878, + "step": 29673 + }, + { + "epoch": 2.42, + "learning_rate": 3.879834854411126e-06, + "loss": 0.3478, + "step": 29674 + }, + { + "epoch": 2.42, + "learning_rate": 3.8792916123424604e-06, + "loss": 0.0822, + "step": 29675 + }, + { + "epoch": 2.42, + "learning_rate": 3.878748370273795e-06, + "loss": 0.2696, + "step": 29676 + }, + { + "epoch": 2.42, + "learning_rate": 3.878205128205129e-06, + "loss": 0.1957, + "step": 29677 + }, + { + "epoch": 2.42, + "learning_rate": 3.877661886136463e-06, + "loss": 0.5673, + "step": 29678 + }, + { + "epoch": 2.42, + "learning_rate": 3.877118644067797e-06, + "loss": 0.1404, + "step": 29679 + }, + { + "epoch": 2.42, + "learning_rate": 3.876575401999132e-06, + "loss": 0.0676, + "step": 29680 + }, + { + "epoch": 2.42, + "learning_rate": 3.876032159930465e-06, + "loss": 0.1819, + "step": 29681 + }, + { + "epoch": 2.42, + "learning_rate": 3.875488917861799e-06, + "loss": 0.0814, + "step": 29682 + }, + { + "epoch": 2.42, + "learning_rate": 3.874945675793133e-06, + "loss": 0.6439, + "step": 29683 + }, + { + "epoch": 2.42, + "learning_rate": 3.874402433724468e-06, + "loss": 0.1711, + "step": 29684 + }, + { + "epoch": 2.42, + "learning_rate": 3.873859191655802e-06, + "loss": 0.2465, + "step": 29685 + }, + { + "epoch": 2.42, + "learning_rate": 3.873315949587136e-06, + "loss": 0.1994, + "step": 29686 + }, + { + "epoch": 2.42, + "learning_rate": 3.87277270751847e-06, + "loss": 0.2068, + "step": 29687 + }, + { + "epoch": 2.42, + "learning_rate": 3.8722294654498046e-06, + "loss": 0.1292, + "step": 29688 + }, + { + "epoch": 2.42, + "learning_rate": 3.871686223381139e-06, + "loss": 0.3168, + "step": 29689 + }, + { + "epoch": 2.42, + "learning_rate": 3.871142981312473e-06, + "loss": 0.1355, + "step": 29690 + }, + { + "epoch": 2.42, + "learning_rate": 3.870599739243807e-06, + "loss": 0.2725, + "step": 29691 + }, + { + "epoch": 2.42, + "learning_rate": 3.8700564971751415e-06, + "loss": 0.2712, + "step": 29692 + }, + { + "epoch": 2.42, + "learning_rate": 3.869513255106476e-06, + "loss": 0.4862, + "step": 29693 + }, + { + "epoch": 2.42, + "learning_rate": 3.86897001303781e-06, + "loss": 0.1156, + "step": 29694 + }, + { + "epoch": 2.42, + "learning_rate": 3.868426770969144e-06, + "loss": 0.2528, + "step": 29695 + }, + { + "epoch": 2.42, + "learning_rate": 3.867883528900478e-06, + "loss": 0.1244, + "step": 29696 + }, + { + "epoch": 2.42, + "learning_rate": 3.867340286831813e-06, + "loss": 0.2536, + "step": 29697 + }, + { + "epoch": 2.42, + "learning_rate": 3.866797044763147e-06, + "loss": 0.1884, + "step": 29698 + }, + { + "epoch": 2.42, + "learning_rate": 3.866253802694481e-06, + "loss": 0.1683, + "step": 29699 + }, + { + "epoch": 2.42, + "learning_rate": 3.865710560625815e-06, + "loss": 0.0413, + "step": 29700 + }, + { + "epoch": 2.42, + "learning_rate": 3.8651673185571496e-06, + "loss": 0.149, + "step": 29701 + }, + { + "epoch": 2.42, + "learning_rate": 3.864624076488484e-06, + "loss": 0.4264, + "step": 29702 + }, + { + "epoch": 2.42, + "learning_rate": 3.864080834419818e-06, + "loss": 0.365, + "step": 29703 + }, + { + "epoch": 2.42, + "learning_rate": 3.863537592351152e-06, + "loss": 0.2936, + "step": 29704 + }, + { + "epoch": 2.42, + "learning_rate": 3.8629943502824865e-06, + "loss": 0.1418, + "step": 29705 + }, + { + "epoch": 2.42, + "learning_rate": 3.862451108213821e-06, + "loss": 0.1835, + "step": 29706 + }, + { + "epoch": 2.42, + "learning_rate": 3.861907866145155e-06, + "loss": 0.2544, + "step": 29707 + }, + { + "epoch": 2.42, + "learning_rate": 3.861364624076489e-06, + "loss": 0.447, + "step": 29708 + }, + { + "epoch": 2.42, + "learning_rate": 3.8608213820078226e-06, + "loss": 0.416, + "step": 29709 + }, + { + "epoch": 2.42, + "learning_rate": 3.860278139939157e-06, + "loss": 0.3825, + "step": 29710 + }, + { + "epoch": 2.42, + "learning_rate": 3.859734897870491e-06, + "loss": 0.172, + "step": 29711 + }, + { + "epoch": 2.42, + "learning_rate": 3.859191655801825e-06, + "loss": 0.2424, + "step": 29712 + }, + { + "epoch": 2.42, + "learning_rate": 3.8586484137331595e-06, + "loss": 0.1054, + "step": 29713 + }, + { + "epoch": 2.42, + "learning_rate": 3.858105171664494e-06, + "loss": 0.3646, + "step": 29714 + }, + { + "epoch": 2.42, + "learning_rate": 3.857561929595828e-06, + "loss": 0.2006, + "step": 29715 + }, + { + "epoch": 2.42, + "learning_rate": 3.857018687527162e-06, + "loss": 0.3554, + "step": 29716 + }, + { + "epoch": 2.42, + "learning_rate": 3.856475445458496e-06, + "loss": 0.1622, + "step": 29717 + }, + { + "epoch": 2.42, + "learning_rate": 3.8559322033898315e-06, + "loss": 0.1595, + "step": 29718 + }, + { + "epoch": 2.42, + "learning_rate": 3.855388961321165e-06, + "loss": 0.3102, + "step": 29719 + }, + { + "epoch": 2.42, + "learning_rate": 3.854845719252499e-06, + "loss": 0.215, + "step": 29720 + }, + { + "epoch": 2.42, + "learning_rate": 3.854302477183833e-06, + "loss": 0.2763, + "step": 29721 + }, + { + "epoch": 2.42, + "learning_rate": 3.8537592351151676e-06, + "loss": 0.3568, + "step": 29722 + }, + { + "epoch": 2.42, + "learning_rate": 3.853215993046502e-06, + "loss": 0.1196, + "step": 29723 + }, + { + "epoch": 2.42, + "learning_rate": 3.852672750977836e-06, + "loss": 0.3189, + "step": 29724 + }, + { + "epoch": 2.42, + "learning_rate": 3.85212950890917e-06, + "loss": 0.2716, + "step": 29725 + }, + { + "epoch": 2.42, + "learning_rate": 3.8515862668405045e-06, + "loss": 0.1648, + "step": 29726 + }, + { + "epoch": 2.42, + "learning_rate": 3.851043024771839e-06, + "loss": 0.3442, + "step": 29727 + }, + { + "epoch": 2.42, + "learning_rate": 3.850499782703173e-06, + "loss": 0.1765, + "step": 29728 + }, + { + "epoch": 2.42, + "learning_rate": 3.849956540634507e-06, + "loss": 0.1723, + "step": 29729 + }, + { + "epoch": 2.42, + "learning_rate": 3.849413298565841e-06, + "loss": 0.2158, + "step": 29730 + }, + { + "epoch": 2.42, + "learning_rate": 3.848870056497176e-06, + "loss": 0.2288, + "step": 29731 + }, + { + "epoch": 2.42, + "learning_rate": 3.84832681442851e-06, + "loss": 0.1949, + "step": 29732 + }, + { + "epoch": 2.42, + "learning_rate": 3.847783572359844e-06, + "loss": 0.2377, + "step": 29733 + }, + { + "epoch": 2.42, + "learning_rate": 3.847240330291178e-06, + "loss": 0.2837, + "step": 29734 + }, + { + "epoch": 2.42, + "learning_rate": 3.8466970882225126e-06, + "loss": 0.1104, + "step": 29735 + }, + { + "epoch": 2.42, + "learning_rate": 3.846153846153847e-06, + "loss": 0.3261, + "step": 29736 + }, + { + "epoch": 2.42, + "learning_rate": 3.845610604085181e-06, + "loss": 0.19, + "step": 29737 + }, + { + "epoch": 2.42, + "learning_rate": 3.845067362016514e-06, + "loss": 0.1813, + "step": 29738 + }, + { + "epoch": 2.42, + "learning_rate": 3.844524119947849e-06, + "loss": 0.1646, + "step": 29739 + }, + { + "epoch": 2.42, + "learning_rate": 3.843980877879183e-06, + "loss": 0.2, + "step": 29740 + }, + { + "epoch": 2.42, + "learning_rate": 3.843437635810517e-06, + "loss": 0.1171, + "step": 29741 + }, + { + "epoch": 2.42, + "learning_rate": 3.842894393741851e-06, + "loss": 0.1908, + "step": 29742 + }, + { + "epoch": 2.42, + "learning_rate": 3.8423511516731856e-06, + "loss": 0.1838, + "step": 29743 + }, + { + "epoch": 2.42, + "learning_rate": 3.84180790960452e-06, + "loss": 0.09, + "step": 29744 + }, + { + "epoch": 2.42, + "learning_rate": 3.841264667535855e-06, + "loss": 0.1569, + "step": 29745 + }, + { + "epoch": 2.42, + "learning_rate": 3.840721425467189e-06, + "loss": 0.388, + "step": 29746 + }, + { + "epoch": 2.42, + "learning_rate": 3.8401781833985225e-06, + "loss": 0.2471, + "step": 29747 + }, + { + "epoch": 2.42, + "learning_rate": 3.839634941329857e-06, + "loss": 0.2129, + "step": 29748 + }, + { + "epoch": 2.42, + "learning_rate": 3.839091699261191e-06, + "loss": 0.1353, + "step": 29749 + }, + { + "epoch": 2.42, + "learning_rate": 3.838548457192525e-06, + "loss": 0.0635, + "step": 29750 + }, + { + "epoch": 2.42, + "eval_accuracy": 0.8415690269994905, + "eval_loss": 0.49731338024139404, + "eval_runtime": 22.2653, + "eval_samples_per_second": 440.821, + "eval_steps_per_second": 3.458, + "step": 29750 + }, + { + "epoch": 2.42, + "learning_rate": 3.838005215123859e-06, + "loss": 0.2312, + "step": 29751 + }, + { + "epoch": 2.42, + "learning_rate": 3.837461973055194e-06, + "loss": 0.3339, + "step": 29752 + }, + { + "epoch": 2.42, + "learning_rate": 3.836918730986528e-06, + "loss": 0.1037, + "step": 29753 + }, + { + "epoch": 2.42, + "learning_rate": 3.836375488917862e-06, + "loss": 0.3407, + "step": 29754 + }, + { + "epoch": 2.42, + "learning_rate": 3.835832246849196e-06, + "loss": 0.0599, + "step": 29755 + }, + { + "epoch": 2.42, + "learning_rate": 3.8352890047805306e-06, + "loss": 0.0814, + "step": 29756 + }, + { + "epoch": 2.42, + "learning_rate": 3.834745762711865e-06, + "loss": 0.085, + "step": 29757 + }, + { + "epoch": 2.42, + "learning_rate": 3.834202520643199e-06, + "loss": 0.1463, + "step": 29758 + }, + { + "epoch": 2.42, + "learning_rate": 3.833659278574533e-06, + "loss": 0.1415, + "step": 29759 + }, + { + "epoch": 2.43, + "learning_rate": 3.8331160365058675e-06, + "loss": 0.0949, + "step": 29760 + }, + { + "epoch": 2.43, + "learning_rate": 3.832572794437202e-06, + "loss": 0.1579, + "step": 29761 + }, + { + "epoch": 2.43, + "learning_rate": 3.832029552368536e-06, + "loss": 0.1634, + "step": 29762 + }, + { + "epoch": 2.43, + "learning_rate": 3.83148631029987e-06, + "loss": 0.1528, + "step": 29763 + }, + { + "epoch": 2.43, + "learning_rate": 3.830943068231204e-06, + "loss": 0.194, + "step": 29764 + }, + { + "epoch": 2.43, + "learning_rate": 3.830399826162539e-06, + "loss": 0.0821, + "step": 29765 + }, + { + "epoch": 2.43, + "learning_rate": 3.829856584093872e-06, + "loss": 0.1829, + "step": 29766 + }, + { + "epoch": 2.43, + "learning_rate": 3.829313342025206e-06, + "loss": 0.1794, + "step": 29767 + }, + { + "epoch": 2.43, + "learning_rate": 3.8287700999565405e-06, + "loss": 0.4874, + "step": 29768 + }, + { + "epoch": 2.43, + "learning_rate": 3.828226857887875e-06, + "loss": 0.3065, + "step": 29769 + }, + { + "epoch": 2.43, + "learning_rate": 3.827683615819209e-06, + "loss": 0.1431, + "step": 29770 + }, + { + "epoch": 2.43, + "learning_rate": 3.827140373750543e-06, + "loss": 0.3466, + "step": 29771 + }, + { + "epoch": 2.43, + "learning_rate": 3.826597131681878e-06, + "loss": 0.2334, + "step": 29772 + }, + { + "epoch": 2.43, + "learning_rate": 3.8260538896132125e-06, + "loss": 0.3783, + "step": 29773 + }, + { + "epoch": 2.43, + "learning_rate": 3.825510647544547e-06, + "loss": 0.2339, + "step": 29774 + }, + { + "epoch": 2.43, + "learning_rate": 3.824967405475881e-06, + "loss": 0.3885, + "step": 29775 + }, + { + "epoch": 2.43, + "learning_rate": 3.824424163407214e-06, + "loss": 0.2015, + "step": 29776 + }, + { + "epoch": 2.43, + "learning_rate": 3.8238809213385486e-06, + "loss": 0.216, + "step": 29777 + }, + { + "epoch": 2.43, + "learning_rate": 3.823337679269883e-06, + "loss": 0.0633, + "step": 29778 + }, + { + "epoch": 2.43, + "learning_rate": 3.822794437201217e-06, + "loss": 0.1311, + "step": 29779 + }, + { + "epoch": 2.43, + "learning_rate": 3.822251195132551e-06, + "loss": 0.2727, + "step": 29780 + }, + { + "epoch": 2.43, + "learning_rate": 3.8217079530638855e-06, + "loss": 0.2128, + "step": 29781 + }, + { + "epoch": 2.43, + "learning_rate": 3.82116471099522e-06, + "loss": 0.0817, + "step": 29782 + }, + { + "epoch": 2.43, + "learning_rate": 3.820621468926554e-06, + "loss": 0.169, + "step": 29783 + }, + { + "epoch": 2.43, + "learning_rate": 3.820078226857888e-06, + "loss": 0.2412, + "step": 29784 + }, + { + "epoch": 2.43, + "learning_rate": 3.819534984789222e-06, + "loss": 0.3564, + "step": 29785 + }, + { + "epoch": 2.43, + "learning_rate": 3.818991742720557e-06, + "loss": 0.215, + "step": 29786 + }, + { + "epoch": 2.43, + "learning_rate": 3.818448500651891e-06, + "loss": 0.1841, + "step": 29787 + }, + { + "epoch": 2.43, + "learning_rate": 3.817905258583225e-06, + "loss": 0.1924, + "step": 29788 + }, + { + "epoch": 2.43, + "learning_rate": 3.817362016514559e-06, + "loss": 0.2983, + "step": 29789 + }, + { + "epoch": 2.43, + "learning_rate": 3.8168187744458935e-06, + "loss": 0.2754, + "step": 29790 + }, + { + "epoch": 2.43, + "learning_rate": 3.816275532377228e-06, + "loss": 0.1679, + "step": 29791 + }, + { + "epoch": 2.43, + "learning_rate": 3.815732290308562e-06, + "loss": 0.1719, + "step": 29792 + }, + { + "epoch": 2.43, + "learning_rate": 3.815189048239896e-06, + "loss": 0.274, + "step": 29793 + }, + { + "epoch": 2.43, + "learning_rate": 3.8146458061712305e-06, + "loss": 0.3568, + "step": 29794 + }, + { + "epoch": 2.43, + "learning_rate": 3.8141025641025643e-06, + "loss": 0.1634, + "step": 29795 + }, + { + "epoch": 2.43, + "learning_rate": 3.8135593220338985e-06, + "loss": 0.3393, + "step": 29796 + }, + { + "epoch": 2.43, + "learning_rate": 3.8130160799652327e-06, + "loss": 0.1131, + "step": 29797 + }, + { + "epoch": 2.43, + "learning_rate": 3.812472837896567e-06, + "loss": 0.1204, + "step": 29798 + }, + { + "epoch": 2.43, + "learning_rate": 3.811929595827901e-06, + "loss": 0.209, + "step": 29799 + }, + { + "epoch": 2.43, + "learning_rate": 3.8113863537592354e-06, + "loss": 0.137, + "step": 29800 + }, + { + "epoch": 2.43, + "learning_rate": 3.8108431116905697e-06, + "loss": 0.1428, + "step": 29801 + }, + { + "epoch": 2.43, + "learning_rate": 3.810299869621904e-06, + "loss": 0.2524, + "step": 29802 + }, + { + "epoch": 2.43, + "learning_rate": 3.809756627553238e-06, + "loss": 0.1096, + "step": 29803 + }, + { + "epoch": 2.43, + "learning_rate": 3.809213385484572e-06, + "loss": 0.1097, + "step": 29804 + }, + { + "epoch": 2.43, + "learning_rate": 3.808670143415906e-06, + "loss": 0.1549, + "step": 29805 + }, + { + "epoch": 2.43, + "learning_rate": 3.8081269013472404e-06, + "loss": 0.2159, + "step": 29806 + }, + { + "epoch": 2.43, + "learning_rate": 3.8075836592785746e-06, + "loss": 0.0645, + "step": 29807 + }, + { + "epoch": 2.43, + "learning_rate": 3.807040417209909e-06, + "loss": 0.2226, + "step": 29808 + }, + { + "epoch": 2.43, + "learning_rate": 3.806497175141243e-06, + "loss": 0.1752, + "step": 29809 + }, + { + "epoch": 2.43, + "learning_rate": 3.8059539330725777e-06, + "loss": 0.137, + "step": 29810 + }, + { + "epoch": 2.43, + "learning_rate": 3.805410691003912e-06, + "loss": 0.1652, + "step": 29811 + }, + { + "epoch": 2.43, + "learning_rate": 3.804867448935246e-06, + "loss": 0.2924, + "step": 29812 + }, + { + "epoch": 2.43, + "learning_rate": 3.8043242068665804e-06, + "loss": 0.2265, + "step": 29813 + }, + { + "epoch": 2.43, + "learning_rate": 3.8037809647979142e-06, + "loss": 0.0594, + "step": 29814 + }, + { + "epoch": 2.43, + "learning_rate": 3.8032377227292485e-06, + "loss": 0.3579, + "step": 29815 + }, + { + "epoch": 2.43, + "learning_rate": 3.8026944806605827e-06, + "loss": 0.3856, + "step": 29816 + }, + { + "epoch": 2.43, + "learning_rate": 3.802151238591917e-06, + "loss": 0.345, + "step": 29817 + }, + { + "epoch": 2.43, + "learning_rate": 3.801607996523251e-06, + "loss": 0.5323, + "step": 29818 + }, + { + "epoch": 2.43, + "learning_rate": 3.8010647544545854e-06, + "loss": 0.1899, + "step": 29819 + }, + { + "epoch": 2.43, + "learning_rate": 3.8005215123859196e-06, + "loss": 0.2241, + "step": 29820 + }, + { + "epoch": 2.43, + "learning_rate": 3.799978270317254e-06, + "loss": 0.0567, + "step": 29821 + }, + { + "epoch": 2.43, + "learning_rate": 3.799435028248588e-06, + "loss": 0.4183, + "step": 29822 + }, + { + "epoch": 2.43, + "learning_rate": 3.798891786179922e-06, + "loss": 0.4618, + "step": 29823 + }, + { + "epoch": 2.43, + "learning_rate": 3.798348544111256e-06, + "loss": 0.5549, + "step": 29824 + }, + { + "epoch": 2.43, + "learning_rate": 3.7978053020425903e-06, + "loss": 0.2198, + "step": 29825 + }, + { + "epoch": 2.43, + "learning_rate": 3.7972620599739246e-06, + "loss": 0.1153, + "step": 29826 + }, + { + "epoch": 2.43, + "learning_rate": 3.796718817905259e-06, + "loss": 0.2222, + "step": 29827 + }, + { + "epoch": 2.43, + "learning_rate": 3.796175575836593e-06, + "loss": 0.6181, + "step": 29828 + }, + { + "epoch": 2.43, + "learning_rate": 3.7956323337679273e-06, + "loss": 0.1119, + "step": 29829 + }, + { + "epoch": 2.43, + "learning_rate": 3.7950890916992615e-06, + "loss": 0.2475, + "step": 29830 + }, + { + "epoch": 2.43, + "learning_rate": 3.7945458496305957e-06, + "loss": 0.2633, + "step": 29831 + }, + { + "epoch": 2.43, + "learning_rate": 3.79400260756193e-06, + "loss": 0.2332, + "step": 29832 + }, + { + "epoch": 2.43, + "learning_rate": 3.7934593654932638e-06, + "loss": 0.4089, + "step": 29833 + }, + { + "epoch": 2.43, + "learning_rate": 3.792916123424598e-06, + "loss": 0.0888, + "step": 29834 + }, + { + "epoch": 2.43, + "learning_rate": 3.7923728813559322e-06, + "loss": 0.3998, + "step": 29835 + }, + { + "epoch": 2.43, + "learning_rate": 3.7918296392872665e-06, + "loss": 0.1343, + "step": 29836 + }, + { + "epoch": 2.43, + "learning_rate": 3.791286397218601e-06, + "loss": 0.1025, + "step": 29837 + }, + { + "epoch": 2.43, + "learning_rate": 3.7907431551499353e-06, + "loss": 0.1717, + "step": 29838 + }, + { + "epoch": 2.43, + "learning_rate": 3.7901999130812696e-06, + "loss": 0.1964, + "step": 29839 + }, + { + "epoch": 2.43, + "learning_rate": 3.789656671012604e-06, + "loss": 0.3368, + "step": 29840 + }, + { + "epoch": 2.43, + "learning_rate": 3.789113428943938e-06, + "loss": 0.2539, + "step": 29841 + }, + { + "epoch": 2.43, + "learning_rate": 3.788570186875272e-06, + "loss": 0.3929, + "step": 29842 + }, + { + "epoch": 2.43, + "learning_rate": 3.788026944806606e-06, + "loss": 0.225, + "step": 29843 + }, + { + "epoch": 2.43, + "learning_rate": 3.7874837027379403e-06, + "loss": 0.1349, + "step": 29844 + }, + { + "epoch": 2.43, + "learning_rate": 3.7869404606692745e-06, + "loss": 0.099, + "step": 29845 + }, + { + "epoch": 2.43, + "learning_rate": 3.7863972186006088e-06, + "loss": 0.09, + "step": 29846 + }, + { + "epoch": 2.43, + "learning_rate": 3.785853976531943e-06, + "loss": 0.1651, + "step": 29847 + }, + { + "epoch": 2.43, + "learning_rate": 3.7853107344632772e-06, + "loss": 0.2975, + "step": 29848 + }, + { + "epoch": 2.43, + "learning_rate": 3.7847674923946115e-06, + "loss": 0.0417, + "step": 29849 + }, + { + "epoch": 2.43, + "learning_rate": 3.7842242503259457e-06, + "loss": 0.2436, + "step": 29850 + }, + { + "epoch": 2.43, + "learning_rate": 3.78368100825728e-06, + "loss": 0.0844, + "step": 29851 + }, + { + "epoch": 2.43, + "learning_rate": 3.7831377661886137e-06, + "loss": 0.3576, + "step": 29852 + }, + { + "epoch": 2.43, + "learning_rate": 3.782594524119948e-06, + "loss": 0.2286, + "step": 29853 + }, + { + "epoch": 2.43, + "learning_rate": 3.782051282051282e-06, + "loss": 0.1137, + "step": 29854 + }, + { + "epoch": 2.43, + "learning_rate": 3.7815080399826164e-06, + "loss": 0.1559, + "step": 29855 + }, + { + "epoch": 2.43, + "learning_rate": 3.7809647979139506e-06, + "loss": 0.0921, + "step": 29856 + }, + { + "epoch": 2.43, + "learning_rate": 3.780421555845285e-06, + "loss": 0.1851, + "step": 29857 + }, + { + "epoch": 2.43, + "learning_rate": 3.779878313776619e-06, + "loss": 0.102, + "step": 29858 + }, + { + "epoch": 2.43, + "learning_rate": 3.7793350717079533e-06, + "loss": 0.634, + "step": 29859 + }, + { + "epoch": 2.43, + "learning_rate": 3.778791829639288e-06, + "loss": 0.1615, + "step": 29860 + }, + { + "epoch": 2.43, + "learning_rate": 3.7782485875706214e-06, + "loss": 0.2483, + "step": 29861 + }, + { + "epoch": 2.43, + "learning_rate": 3.7777053455019556e-06, + "loss": 0.1543, + "step": 29862 + }, + { + "epoch": 2.43, + "learning_rate": 3.77716210343329e-06, + "loss": 0.0475, + "step": 29863 + }, + { + "epoch": 2.43, + "learning_rate": 3.7766188613646245e-06, + "loss": 0.0668, + "step": 29864 + }, + { + "epoch": 2.43, + "learning_rate": 3.7760756192959587e-06, + "loss": 0.079, + "step": 29865 + }, + { + "epoch": 2.43, + "learning_rate": 3.775532377227293e-06, + "loss": 0.1426, + "step": 29866 + }, + { + "epoch": 2.43, + "learning_rate": 3.774989135158627e-06, + "loss": 0.253, + "step": 29867 + }, + { + "epoch": 2.43, + "learning_rate": 3.7744458930899614e-06, + "loss": 0.1202, + "step": 29868 + }, + { + "epoch": 2.43, + "learning_rate": 3.7739026510212956e-06, + "loss": 0.2427, + "step": 29869 + }, + { + "epoch": 2.43, + "learning_rate": 3.77335940895263e-06, + "loss": 0.4069, + "step": 29870 + }, + { + "epoch": 2.43, + "learning_rate": 3.7728161668839637e-06, + "loss": 0.1754, + "step": 29871 + }, + { + "epoch": 2.43, + "learning_rate": 3.772272924815298e-06, + "loss": 0.0915, + "step": 29872 + }, + { + "epoch": 2.43, + "learning_rate": 3.771729682746632e-06, + "loss": 0.0459, + "step": 29873 + }, + { + "epoch": 2.43, + "learning_rate": 3.7711864406779664e-06, + "loss": 0.1561, + "step": 29874 + }, + { + "epoch": 2.43, + "learning_rate": 3.7706431986093006e-06, + "loss": 0.2565, + "step": 29875 + }, + { + "epoch": 2.43, + "learning_rate": 3.770099956540635e-06, + "loss": 0.1157, + "step": 29876 + }, + { + "epoch": 2.43, + "learning_rate": 3.769556714471969e-06, + "loss": 0.3689, + "step": 29877 + }, + { + "epoch": 2.43, + "learning_rate": 3.7690134724033033e-06, + "loss": 0.0542, + "step": 29878 + }, + { + "epoch": 2.43, + "learning_rate": 3.7684702303346375e-06, + "loss": 0.3199, + "step": 29879 + }, + { + "epoch": 2.43, + "learning_rate": 3.7679269882659713e-06, + "loss": 0.2874, + "step": 29880 + }, + { + "epoch": 2.43, + "learning_rate": 3.7673837461973056e-06, + "loss": 0.1355, + "step": 29881 + }, + { + "epoch": 2.43, + "learning_rate": 3.76684050412864e-06, + "loss": 0.1093, + "step": 29882 + }, + { + "epoch": 2.44, + "learning_rate": 3.766297262059974e-06, + "loss": 0.3739, + "step": 29883 + }, + { + "epoch": 2.44, + "learning_rate": 3.7657540199913083e-06, + "loss": 0.1493, + "step": 29884 + }, + { + "epoch": 2.44, + "learning_rate": 3.7652107779226425e-06, + "loss": 0.2755, + "step": 29885 + }, + { + "epoch": 2.44, + "learning_rate": 3.7646675358539767e-06, + "loss": 0.2092, + "step": 29886 + }, + { + "epoch": 2.44, + "learning_rate": 3.7641242937853114e-06, + "loss": 0.2891, + "step": 29887 + }, + { + "epoch": 2.44, + "learning_rate": 3.7635810517166456e-06, + "loss": 0.4218, + "step": 29888 + }, + { + "epoch": 2.44, + "learning_rate": 3.76303780964798e-06, + "loss": 0.2202, + "step": 29889 + }, + { + "epoch": 2.44, + "learning_rate": 3.7624945675793132e-06, + "loss": 0.355, + "step": 29890 + }, + { + "epoch": 2.44, + "learning_rate": 3.761951325510648e-06, + "loss": 0.2427, + "step": 29891 + }, + { + "epoch": 2.44, + "learning_rate": 3.761408083441982e-06, + "loss": 0.2366, + "step": 29892 + }, + { + "epoch": 2.44, + "learning_rate": 3.7608648413733163e-06, + "loss": 0.1161, + "step": 29893 + }, + { + "epoch": 2.44, + "learning_rate": 3.7603215993046506e-06, + "loss": 0.4254, + "step": 29894 + }, + { + "epoch": 2.44, + "learning_rate": 3.759778357235985e-06, + "loss": 0.2267, + "step": 29895 + }, + { + "epoch": 2.44, + "learning_rate": 3.759235115167319e-06, + "loss": 0.2181, + "step": 29896 + }, + { + "epoch": 2.44, + "learning_rate": 3.7586918730986533e-06, + "loss": 0.4573, + "step": 29897 + }, + { + "epoch": 2.44, + "learning_rate": 3.7581486310299875e-06, + "loss": 0.2959, + "step": 29898 + }, + { + "epoch": 2.44, + "learning_rate": 3.7576053889613213e-06, + "loss": 0.1115, + "step": 29899 + }, + { + "epoch": 2.44, + "learning_rate": 3.7570621468926555e-06, + "loss": 0.3132, + "step": 29900 + }, + { + "epoch": 2.44, + "learning_rate": 3.7565189048239898e-06, + "loss": 0.4644, + "step": 29901 + }, + { + "epoch": 2.44, + "learning_rate": 3.755975662755324e-06, + "loss": 0.3028, + "step": 29902 + }, + { + "epoch": 2.44, + "learning_rate": 3.7554324206866582e-06, + "loss": 0.2919, + "step": 29903 + }, + { + "epoch": 2.44, + "learning_rate": 3.7548891786179924e-06, + "loss": 0.087, + "step": 29904 + }, + { + "epoch": 2.44, + "learning_rate": 3.7543459365493267e-06, + "loss": 0.1014, + "step": 29905 + }, + { + "epoch": 2.44, + "learning_rate": 3.753802694480661e-06, + "loss": 0.2454, + "step": 29906 + }, + { + "epoch": 2.44, + "learning_rate": 3.753259452411995e-06, + "loss": 0.2417, + "step": 29907 + }, + { + "epoch": 2.44, + "learning_rate": 3.7527162103433294e-06, + "loss": 0.089, + "step": 29908 + }, + { + "epoch": 2.44, + "learning_rate": 3.752172968274663e-06, + "loss": 0.1999, + "step": 29909 + }, + { + "epoch": 2.44, + "learning_rate": 3.7516297262059974e-06, + "loss": 0.0957, + "step": 29910 + }, + { + "epoch": 2.44, + "learning_rate": 3.7510864841373316e-06, + "loss": 0.085, + "step": 29911 + }, + { + "epoch": 2.44, + "learning_rate": 3.750543242068666e-06, + "loss": 0.3053, + "step": 29912 + }, + { + "epoch": 2.44, + "learning_rate": 3.7500000000000005e-06, + "loss": 0.1532, + "step": 29913 + }, + { + "epoch": 2.44, + "learning_rate": 3.7494567579313347e-06, + "loss": 0.17, + "step": 29914 + }, + { + "epoch": 2.44, + "learning_rate": 3.748913515862669e-06, + "loss": 0.3662, + "step": 29915 + }, + { + "epoch": 2.44, + "learning_rate": 3.748370273794003e-06, + "loss": 0.1064, + "step": 29916 + }, + { + "epoch": 2.44, + "learning_rate": 3.7478270317253374e-06, + "loss": 0.2388, + "step": 29917 + }, + { + "epoch": 2.44, + "learning_rate": 3.7472837896566712e-06, + "loss": 0.156, + "step": 29918 + }, + { + "epoch": 2.44, + "learning_rate": 3.7467405475880055e-06, + "loss": 0.0732, + "step": 29919 + }, + { + "epoch": 2.44, + "learning_rate": 3.7461973055193397e-06, + "loss": 0.2147, + "step": 29920 + }, + { + "epoch": 2.44, + "learning_rate": 3.745654063450674e-06, + "loss": 0.3457, + "step": 29921 + }, + { + "epoch": 2.44, + "learning_rate": 3.745110821382008e-06, + "loss": 0.5159, + "step": 29922 + }, + { + "epoch": 2.44, + "learning_rate": 3.7445675793133424e-06, + "loss": 0.2104, + "step": 29923 + }, + { + "epoch": 2.44, + "learning_rate": 3.7440243372446766e-06, + "loss": 0.5972, + "step": 29924 + }, + { + "epoch": 2.44, + "learning_rate": 3.743481095176011e-06, + "loss": 0.2864, + "step": 29925 + }, + { + "epoch": 2.44, + "learning_rate": 3.742937853107345e-06, + "loss": 0.4669, + "step": 29926 + }, + { + "epoch": 2.44, + "learning_rate": 3.7423946110386793e-06, + "loss": 0.2479, + "step": 29927 + }, + { + "epoch": 2.44, + "learning_rate": 3.741851368970013e-06, + "loss": 0.0612, + "step": 29928 + }, + { + "epoch": 2.44, + "learning_rate": 3.7413081269013474e-06, + "loss": 0.1715, + "step": 29929 + }, + { + "epoch": 2.44, + "learning_rate": 3.7407648848326816e-06, + "loss": 0.1611, + "step": 29930 + }, + { + "epoch": 2.44, + "learning_rate": 3.740221642764016e-06, + "loss": 0.2123, + "step": 29931 + }, + { + "epoch": 2.44, + "learning_rate": 3.73967840069535e-06, + "loss": 0.0715, + "step": 29932 + }, + { + "epoch": 2.44, + "learning_rate": 3.7391351586266843e-06, + "loss": 0.2212, + "step": 29933 + }, + { + "epoch": 2.44, + "learning_rate": 3.7385919165580185e-06, + "loss": 0.2253, + "step": 29934 + }, + { + "epoch": 2.44, + "learning_rate": 3.7380486744893527e-06, + "loss": 0.1469, + "step": 29935 + }, + { + "epoch": 2.44, + "learning_rate": 3.7375054324206874e-06, + "loss": 0.2248, + "step": 29936 + }, + { + "epoch": 2.44, + "learning_rate": 3.7369621903520208e-06, + "loss": 0.0723, + "step": 29937 + }, + { + "epoch": 2.44, + "learning_rate": 3.736418948283355e-06, + "loss": 0.3447, + "step": 29938 + }, + { + "epoch": 2.44, + "learning_rate": 3.7358757062146892e-06, + "loss": 0.1565, + "step": 29939 + }, + { + "epoch": 2.44, + "learning_rate": 3.735332464146024e-06, + "loss": 0.2194, + "step": 29940 + }, + { + "epoch": 2.44, + "learning_rate": 3.734789222077358e-06, + "loss": 0.0973, + "step": 29941 + }, + { + "epoch": 2.44, + "learning_rate": 3.7342459800086924e-06, + "loss": 0.1318, + "step": 29942 + }, + { + "epoch": 2.44, + "learning_rate": 3.7337027379400266e-06, + "loss": 0.3108, + "step": 29943 + }, + { + "epoch": 2.44, + "learning_rate": 3.733159495871361e-06, + "loss": 0.3265, + "step": 29944 + }, + { + "epoch": 2.44, + "learning_rate": 3.732616253802695e-06, + "loss": 0.2805, + "step": 29945 + }, + { + "epoch": 2.44, + "learning_rate": 3.7320730117340293e-06, + "loss": 0.2897, + "step": 29946 + }, + { + "epoch": 2.44, + "learning_rate": 3.731529769665363e-06, + "loss": 0.2977, + "step": 29947 + }, + { + "epoch": 2.44, + "learning_rate": 3.7309865275966973e-06, + "loss": 0.277, + "step": 29948 + }, + { + "epoch": 2.44, + "learning_rate": 3.7304432855280315e-06, + "loss": 0.1492, + "step": 29949 + }, + { + "epoch": 2.44, + "learning_rate": 3.7299000434593658e-06, + "loss": 0.1659, + "step": 29950 + }, + { + "epoch": 2.44, + "learning_rate": 3.7293568013907e-06, + "loss": 0.1841, + "step": 29951 + }, + { + "epoch": 2.44, + "learning_rate": 3.7288135593220342e-06, + "loss": 0.2629, + "step": 29952 + }, + { + "epoch": 2.44, + "learning_rate": 3.7282703172533685e-06, + "loss": 0.418, + "step": 29953 + }, + { + "epoch": 2.44, + "learning_rate": 3.7277270751847027e-06, + "loss": 0.1425, + "step": 29954 + }, + { + "epoch": 2.44, + "learning_rate": 3.727183833116037e-06, + "loss": 0.1165, + "step": 29955 + }, + { + "epoch": 2.44, + "learning_rate": 3.7266405910473707e-06, + "loss": 0.4059, + "step": 29956 + }, + { + "epoch": 2.44, + "learning_rate": 3.726097348978705e-06, + "loss": 0.219, + "step": 29957 + }, + { + "epoch": 2.44, + "learning_rate": 3.725554106910039e-06, + "loss": 0.3805, + "step": 29958 + }, + { + "epoch": 2.44, + "learning_rate": 3.7250108648413734e-06, + "loss": 0.1404, + "step": 29959 + }, + { + "epoch": 2.44, + "learning_rate": 3.7244676227727077e-06, + "loss": 0.0939, + "step": 29960 + }, + { + "epoch": 2.44, + "learning_rate": 3.723924380704042e-06, + "loss": 0.4544, + "step": 29961 + }, + { + "epoch": 2.44, + "learning_rate": 3.723381138635376e-06, + "loss": 0.1833, + "step": 29962 + }, + { + "epoch": 2.44, + "learning_rate": 3.7228378965667108e-06, + "loss": 0.1385, + "step": 29963 + }, + { + "epoch": 2.44, + "learning_rate": 3.722294654498045e-06, + "loss": 0.3267, + "step": 29964 + }, + { + "epoch": 2.44, + "learning_rate": 3.7217514124293792e-06, + "loss": 0.1328, + "step": 29965 + }, + { + "epoch": 2.44, + "learning_rate": 3.7212081703607126e-06, + "loss": 0.3571, + "step": 29966 + }, + { + "epoch": 2.44, + "learning_rate": 3.7206649282920473e-06, + "loss": 0.2475, + "step": 29967 + }, + { + "epoch": 2.44, + "learning_rate": 3.7201216862233815e-06, + "loss": 0.1461, + "step": 29968 + }, + { + "epoch": 2.44, + "learning_rate": 3.7195784441547157e-06, + "loss": 0.1837, + "step": 29969 + }, + { + "epoch": 2.44, + "learning_rate": 3.71903520208605e-06, + "loss": 0.1433, + "step": 29970 + }, + { + "epoch": 2.44, + "learning_rate": 3.718491960017384e-06, + "loss": 0.1488, + "step": 29971 + }, + { + "epoch": 2.44, + "learning_rate": 3.7179487179487184e-06, + "loss": 0.0741, + "step": 29972 + }, + { + "epoch": 2.44, + "learning_rate": 3.7174054758800527e-06, + "loss": 0.3256, + "step": 29973 + }, + { + "epoch": 2.44, + "learning_rate": 3.716862233811387e-06, + "loss": 0.2558, + "step": 29974 + }, + { + "epoch": 2.44, + "learning_rate": 3.7163189917427207e-06, + "loss": 0.2258, + "step": 29975 + }, + { + "epoch": 2.44, + "learning_rate": 3.715775749674055e-06, + "loss": 0.2546, + "step": 29976 + }, + { + "epoch": 2.44, + "learning_rate": 3.715232507605389e-06, + "loss": 0.5737, + "step": 29977 + }, + { + "epoch": 2.44, + "learning_rate": 3.7146892655367234e-06, + "loss": 0.2892, + "step": 29978 + }, + { + "epoch": 2.44, + "learning_rate": 3.7141460234680576e-06, + "loss": 0.2128, + "step": 29979 + }, + { + "epoch": 2.44, + "learning_rate": 3.713602781399392e-06, + "loss": 0.2904, + "step": 29980 + }, + { + "epoch": 2.44, + "learning_rate": 3.713059539330726e-06, + "loss": 0.2553, + "step": 29981 + }, + { + "epoch": 2.44, + "learning_rate": 3.7125162972620603e-06, + "loss": 0.3049, + "step": 29982 + }, + { + "epoch": 2.44, + "learning_rate": 3.7119730551933945e-06, + "loss": 0.1484, + "step": 29983 + }, + { + "epoch": 2.44, + "learning_rate": 3.7114298131247288e-06, + "loss": 0.2498, + "step": 29984 + }, + { + "epoch": 2.44, + "learning_rate": 3.7108865710560626e-06, + "loss": 0.4887, + "step": 29985 + }, + { + "epoch": 2.44, + "learning_rate": 3.710343328987397e-06, + "loss": 0.0862, + "step": 29986 + }, + { + "epoch": 2.44, + "learning_rate": 3.709800086918731e-06, + "loss": 0.0952, + "step": 29987 + }, + { + "epoch": 2.44, + "learning_rate": 3.7092568448500653e-06, + "loss": 0.1771, + "step": 29988 + }, + { + "epoch": 2.44, + "learning_rate": 3.7087136027813995e-06, + "loss": 0.0593, + "step": 29989 + }, + { + "epoch": 2.44, + "learning_rate": 3.708170360712734e-06, + "loss": 0.1848, + "step": 29990 + }, + { + "epoch": 2.44, + "learning_rate": 3.7076271186440684e-06, + "loss": 0.3056, + "step": 29991 + }, + { + "epoch": 2.44, + "learning_rate": 3.7070838765754026e-06, + "loss": 0.0253, + "step": 29992 + }, + { + "epoch": 2.44, + "learning_rate": 3.706540634506737e-06, + "loss": 0.0563, + "step": 29993 + }, + { + "epoch": 2.44, + "learning_rate": 3.7059973924380707e-06, + "loss": 0.1163, + "step": 29994 + }, + { + "epoch": 2.44, + "learning_rate": 3.705454150369405e-06, + "loss": 0.056, + "step": 29995 + }, + { + "epoch": 2.44, + "learning_rate": 3.704910908300739e-06, + "loss": 0.2036, + "step": 29996 + }, + { + "epoch": 2.44, + "learning_rate": 3.7043676662320733e-06, + "loss": 0.0955, + "step": 29997 + }, + { + "epoch": 2.44, + "learning_rate": 3.7038244241634076e-06, + "loss": 0.2129, + "step": 29998 + }, + { + "epoch": 2.44, + "learning_rate": 3.703281182094742e-06, + "loss": 0.2105, + "step": 29999 + }, + { + "epoch": 2.44, + "learning_rate": 3.702737940026076e-06, + "loss": 0.2572, + "step": 30000 + }, + { + "epoch": 2.44, + "eval_accuracy": 0.8451349974528782, + "eval_loss": 0.49851760268211365, + "eval_runtime": 22.2764, + "eval_samples_per_second": 440.6, + "eval_steps_per_second": 3.457, + "step": 30000 + }, + { + "epoch": 2.44, + "learning_rate": 3.7021946979574103e-06, + "loss": 0.4602, + "step": 30001 + }, + { + "epoch": 2.44, + "learning_rate": 3.7016514558887445e-06, + "loss": 0.2685, + "step": 30002 + }, + { + "epoch": 2.44, + "learning_rate": 3.7011082138200787e-06, + "loss": 0.2173, + "step": 30003 + }, + { + "epoch": 2.44, + "learning_rate": 3.7005649717514125e-06, + "loss": 0.1324, + "step": 30004 + }, + { + "epoch": 2.44, + "learning_rate": 3.7000217296827468e-06, + "loss": 0.2275, + "step": 30005 + }, + { + "epoch": 2.45, + "learning_rate": 3.699478487614081e-06, + "loss": 0.3263, + "step": 30006 + }, + { + "epoch": 2.45, + "learning_rate": 3.6989352455454152e-06, + "loss": 0.2966, + "step": 30007 + }, + { + "epoch": 2.45, + "learning_rate": 3.6983920034767495e-06, + "loss": 0.301, + "step": 30008 + }, + { + "epoch": 2.45, + "learning_rate": 3.6978487614080837e-06, + "loss": 0.3862, + "step": 30009 + }, + { + "epoch": 2.45, + "learning_rate": 3.697305519339418e-06, + "loss": 0.2047, + "step": 30010 + }, + { + "epoch": 2.45, + "learning_rate": 3.696762277270752e-06, + "loss": 0.3415, + "step": 30011 + }, + { + "epoch": 2.45, + "learning_rate": 3.6962190352020864e-06, + "loss": 0.3179, + "step": 30012 + }, + { + "epoch": 2.45, + "learning_rate": 3.69567579313342e-06, + "loss": 0.1395, + "step": 30013 + }, + { + "epoch": 2.45, + "learning_rate": 3.6951325510647544e-06, + "loss": 0.1445, + "step": 30014 + }, + { + "epoch": 2.45, + "learning_rate": 3.6945893089960886e-06, + "loss": 0.2685, + "step": 30015 + }, + { + "epoch": 2.45, + "learning_rate": 3.694046066927423e-06, + "loss": 0.3614, + "step": 30016 + }, + { + "epoch": 2.45, + "learning_rate": 3.6935028248587575e-06, + "loss": 0.2944, + "step": 30017 + }, + { + "epoch": 2.45, + "learning_rate": 3.6929595827900918e-06, + "loss": 0.6122, + "step": 30018 + }, + { + "epoch": 2.45, + "learning_rate": 3.692416340721426e-06, + "loss": 0.2301, + "step": 30019 + }, + { + "epoch": 2.45, + "learning_rate": 3.6918730986527602e-06, + "loss": 0.115, + "step": 30020 + }, + { + "epoch": 2.45, + "learning_rate": 3.6913298565840945e-06, + "loss": 0.1859, + "step": 30021 + }, + { + "epoch": 2.45, + "learning_rate": 3.6907866145154287e-06, + "loss": 0.1674, + "step": 30022 + }, + { + "epoch": 2.45, + "learning_rate": 3.6902433724467625e-06, + "loss": 0.2866, + "step": 30023 + }, + { + "epoch": 2.45, + "learning_rate": 3.6897001303780967e-06, + "loss": 0.2392, + "step": 30024 + }, + { + "epoch": 2.45, + "learning_rate": 3.689156888309431e-06, + "loss": 0.3536, + "step": 30025 + }, + { + "epoch": 2.45, + "learning_rate": 3.688613646240765e-06, + "loss": 0.0915, + "step": 30026 + }, + { + "epoch": 2.45, + "learning_rate": 3.6880704041720994e-06, + "loss": 0.088, + "step": 30027 + }, + { + "epoch": 2.45, + "learning_rate": 3.6875271621034336e-06, + "loss": 0.1382, + "step": 30028 + }, + { + "epoch": 2.45, + "learning_rate": 3.686983920034768e-06, + "loss": 0.3467, + "step": 30029 + }, + { + "epoch": 2.45, + "learning_rate": 3.686440677966102e-06, + "loss": 0.2446, + "step": 30030 + }, + { + "epoch": 2.45, + "learning_rate": 3.6858974358974363e-06, + "loss": 0.4716, + "step": 30031 + }, + { + "epoch": 2.45, + "learning_rate": 3.68535419382877e-06, + "loss": 0.3787, + "step": 30032 + }, + { + "epoch": 2.45, + "learning_rate": 3.6848109517601044e-06, + "loss": 0.2833, + "step": 30033 + }, + { + "epoch": 2.45, + "learning_rate": 3.6842677096914386e-06, + "loss": 0.1698, + "step": 30034 + }, + { + "epoch": 2.45, + "learning_rate": 3.683724467622773e-06, + "loss": 0.101, + "step": 30035 + }, + { + "epoch": 2.45, + "learning_rate": 3.683181225554107e-06, + "loss": 0.3217, + "step": 30036 + }, + { + "epoch": 2.45, + "learning_rate": 3.6826379834854413e-06, + "loss": 0.0933, + "step": 30037 + }, + { + "epoch": 2.45, + "learning_rate": 3.6820947414167755e-06, + "loss": 0.0942, + "step": 30038 + }, + { + "epoch": 2.45, + "learning_rate": 3.6815514993481098e-06, + "loss": 0.1979, + "step": 30039 + }, + { + "epoch": 2.45, + "learning_rate": 3.6810082572794444e-06, + "loss": 0.1757, + "step": 30040 + }, + { + "epoch": 2.45, + "learning_rate": 3.6804650152107786e-06, + "loss": 0.3506, + "step": 30041 + }, + { + "epoch": 2.45, + "learning_rate": 3.679921773142112e-06, + "loss": 0.1988, + "step": 30042 + }, + { + "epoch": 2.45, + "learning_rate": 3.6793785310734463e-06, + "loss": 0.3551, + "step": 30043 + }, + { + "epoch": 2.45, + "learning_rate": 3.678835289004781e-06, + "loss": 0.1653, + "step": 30044 + }, + { + "epoch": 2.45, + "learning_rate": 3.678292046936115e-06, + "loss": 0.4774, + "step": 30045 + }, + { + "epoch": 2.45, + "learning_rate": 3.6777488048674494e-06, + "loss": 0.2261, + "step": 30046 + }, + { + "epoch": 2.45, + "learning_rate": 3.6772055627987836e-06, + "loss": 0.4156, + "step": 30047 + }, + { + "epoch": 2.45, + "learning_rate": 3.676662320730118e-06, + "loss": 0.192, + "step": 30048 + }, + { + "epoch": 2.45, + "learning_rate": 3.676119078661452e-06, + "loss": 0.1829, + "step": 30049 + }, + { + "epoch": 2.45, + "learning_rate": 3.6755758365927863e-06, + "loss": 0.1762, + "step": 30050 + }, + { + "epoch": 2.45, + "learning_rate": 3.67503259452412e-06, + "loss": 0.109, + "step": 30051 + }, + { + "epoch": 2.45, + "learning_rate": 3.6744893524554543e-06, + "loss": 0.3823, + "step": 30052 + }, + { + "epoch": 2.45, + "learning_rate": 3.6739461103867886e-06, + "loss": 0.3189, + "step": 30053 + }, + { + "epoch": 2.45, + "learning_rate": 3.673402868318123e-06, + "loss": 0.1642, + "step": 30054 + }, + { + "epoch": 2.45, + "learning_rate": 3.672859626249457e-06, + "loss": 0.1877, + "step": 30055 + }, + { + "epoch": 2.45, + "learning_rate": 3.6723163841807913e-06, + "loss": 0.1074, + "step": 30056 + }, + { + "epoch": 2.45, + "learning_rate": 3.6717731421121255e-06, + "loss": 0.4706, + "step": 30057 + }, + { + "epoch": 2.45, + "learning_rate": 3.6712299000434597e-06, + "loss": 0.0896, + "step": 30058 + }, + { + "epoch": 2.45, + "learning_rate": 3.670686657974794e-06, + "loss": 0.1848, + "step": 30059 + }, + { + "epoch": 2.45, + "learning_rate": 3.670143415906128e-06, + "loss": 0.1154, + "step": 30060 + }, + { + "epoch": 2.45, + "learning_rate": 3.669600173837462e-06, + "loss": 0.288, + "step": 30061 + }, + { + "epoch": 2.45, + "learning_rate": 3.669056931768796e-06, + "loss": 0.2121, + "step": 30062 + }, + { + "epoch": 2.45, + "learning_rate": 3.6685136897001304e-06, + "loss": 0.2181, + "step": 30063 + }, + { + "epoch": 2.45, + "learning_rate": 3.6679704476314647e-06, + "loss": 0.1294, + "step": 30064 + }, + { + "epoch": 2.45, + "learning_rate": 3.667427205562799e-06, + "loss": 0.3523, + "step": 30065 + }, + { + "epoch": 2.45, + "learning_rate": 3.666883963494133e-06, + "loss": 0.3327, + "step": 30066 + }, + { + "epoch": 2.45, + "learning_rate": 3.6663407214254678e-06, + "loss": 0.3259, + "step": 30067 + }, + { + "epoch": 2.45, + "learning_rate": 3.665797479356802e-06, + "loss": 0.5388, + "step": 30068 + }, + { + "epoch": 2.45, + "learning_rate": 3.6652542372881362e-06, + "loss": 0.4416, + "step": 30069 + }, + { + "epoch": 2.45, + "learning_rate": 3.6647109952194696e-06, + "loss": 0.2255, + "step": 30070 + }, + { + "epoch": 2.45, + "learning_rate": 3.6641677531508043e-06, + "loss": 0.1829, + "step": 30071 + }, + { + "epoch": 2.45, + "learning_rate": 3.6636245110821385e-06, + "loss": 0.2602, + "step": 30072 + }, + { + "epoch": 2.45, + "learning_rate": 3.6630812690134727e-06, + "loss": 0.2152, + "step": 30073 + }, + { + "epoch": 2.45, + "learning_rate": 3.662538026944807e-06, + "loss": 0.3301, + "step": 30074 + }, + { + "epoch": 2.45, + "learning_rate": 3.661994784876141e-06, + "loss": 0.2088, + "step": 30075 + }, + { + "epoch": 2.45, + "learning_rate": 3.6614515428074754e-06, + "loss": 0.1868, + "step": 30076 + }, + { + "epoch": 2.45, + "learning_rate": 3.6609083007388097e-06, + "loss": 0.2337, + "step": 30077 + }, + { + "epoch": 2.45, + "learning_rate": 3.660365058670144e-06, + "loss": 0.2637, + "step": 30078 + }, + { + "epoch": 2.45, + "learning_rate": 3.659821816601478e-06, + "loss": 0.1756, + "step": 30079 + }, + { + "epoch": 2.45, + "learning_rate": 3.659278574532812e-06, + "loss": 0.2027, + "step": 30080 + }, + { + "epoch": 2.45, + "learning_rate": 3.658735332464146e-06, + "loss": 0.2727, + "step": 30081 + }, + { + "epoch": 2.45, + "learning_rate": 3.6581920903954804e-06, + "loss": 0.4589, + "step": 30082 + }, + { + "epoch": 2.45, + "learning_rate": 3.6576488483268146e-06, + "loss": 0.1302, + "step": 30083 + }, + { + "epoch": 2.45, + "learning_rate": 3.657105606258149e-06, + "loss": 0.076, + "step": 30084 + }, + { + "epoch": 2.45, + "learning_rate": 3.656562364189483e-06, + "loss": 0.2778, + "step": 30085 + }, + { + "epoch": 2.45, + "learning_rate": 3.6560191221208173e-06, + "loss": 0.2727, + "step": 30086 + }, + { + "epoch": 2.45, + "learning_rate": 3.6554758800521516e-06, + "loss": 0.2977, + "step": 30087 + }, + { + "epoch": 2.45, + "learning_rate": 3.6549326379834858e-06, + "loss": 0.2342, + "step": 30088 + }, + { + "epoch": 2.45, + "learning_rate": 3.6543893959148196e-06, + "loss": 0.0846, + "step": 30089 + }, + { + "epoch": 2.45, + "learning_rate": 3.653846153846154e-06, + "loss": 0.1439, + "step": 30090 + }, + { + "epoch": 2.45, + "learning_rate": 3.653302911777488e-06, + "loss": 0.076, + "step": 30091 + }, + { + "epoch": 2.45, + "learning_rate": 3.6527596697088223e-06, + "loss": 0.274, + "step": 30092 + }, + { + "epoch": 2.45, + "learning_rate": 3.6522164276401565e-06, + "loss": 0.1881, + "step": 30093 + }, + { + "epoch": 2.45, + "learning_rate": 3.651673185571491e-06, + "loss": 0.4868, + "step": 30094 + }, + { + "epoch": 2.45, + "learning_rate": 3.6511299435028254e-06, + "loss": 0.1791, + "step": 30095 + }, + { + "epoch": 2.45, + "learning_rate": 3.6505867014341596e-06, + "loss": 0.132, + "step": 30096 + }, + { + "epoch": 2.45, + "learning_rate": 3.650043459365494e-06, + "loss": 0.2717, + "step": 30097 + }, + { + "epoch": 2.45, + "learning_rate": 3.649500217296828e-06, + "loss": 0.0987, + "step": 30098 + }, + { + "epoch": 2.45, + "learning_rate": 3.648956975228162e-06, + "loss": 0.3373, + "step": 30099 + }, + { + "epoch": 2.45, + "learning_rate": 3.648413733159496e-06, + "loss": 0.447, + "step": 30100 + }, + { + "epoch": 2.45, + "learning_rate": 3.6478704910908304e-06, + "loss": 0.2041, + "step": 30101 + }, + { + "epoch": 2.45, + "learning_rate": 3.6473272490221646e-06, + "loss": 0.1893, + "step": 30102 + }, + { + "epoch": 2.45, + "learning_rate": 3.646784006953499e-06, + "loss": 0.1639, + "step": 30103 + }, + { + "epoch": 2.45, + "learning_rate": 3.646240764884833e-06, + "loss": 0.2162, + "step": 30104 + }, + { + "epoch": 2.45, + "learning_rate": 3.6456975228161673e-06, + "loss": 0.2603, + "step": 30105 + }, + { + "epoch": 2.45, + "learning_rate": 3.6451542807475015e-06, + "loss": 0.1236, + "step": 30106 + }, + { + "epoch": 2.45, + "learning_rate": 3.6446110386788357e-06, + "loss": 0.0772, + "step": 30107 + }, + { + "epoch": 2.45, + "learning_rate": 3.6440677966101695e-06, + "loss": 0.1758, + "step": 30108 + }, + { + "epoch": 2.45, + "learning_rate": 3.6435245545415038e-06, + "loss": 0.2163, + "step": 30109 + }, + { + "epoch": 2.45, + "learning_rate": 3.642981312472838e-06, + "loss": 0.0869, + "step": 30110 + }, + { + "epoch": 2.45, + "learning_rate": 3.6424380704041722e-06, + "loss": 0.3077, + "step": 30111 + }, + { + "epoch": 2.45, + "learning_rate": 3.6418948283355065e-06, + "loss": 0.2752, + "step": 30112 + }, + { + "epoch": 2.45, + "learning_rate": 3.6413515862668407e-06, + "loss": 0.3037, + "step": 30113 + }, + { + "epoch": 2.45, + "learning_rate": 3.640808344198175e-06, + "loss": 0.1867, + "step": 30114 + }, + { + "epoch": 2.45, + "learning_rate": 3.640265102129509e-06, + "loss": 0.1514, + "step": 30115 + }, + { + "epoch": 2.45, + "learning_rate": 3.639721860060844e-06, + "loss": 0.1678, + "step": 30116 + }, + { + "epoch": 2.45, + "learning_rate": 3.639178617992178e-06, + "loss": 0.3486, + "step": 30117 + }, + { + "epoch": 2.45, + "learning_rate": 3.6386353759235114e-06, + "loss": 0.1764, + "step": 30118 + }, + { + "epoch": 2.45, + "learning_rate": 3.6380921338548457e-06, + "loss": 0.3083, + "step": 30119 + }, + { + "epoch": 2.45, + "learning_rate": 3.63754889178618e-06, + "loss": 0.207, + "step": 30120 + }, + { + "epoch": 2.45, + "learning_rate": 3.6370056497175145e-06, + "loss": 0.4708, + "step": 30121 + }, + { + "epoch": 2.45, + "learning_rate": 3.6364624076488488e-06, + "loss": 0.2517, + "step": 30122 + }, + { + "epoch": 2.45, + "learning_rate": 3.635919165580183e-06, + "loss": 0.1554, + "step": 30123 + }, + { + "epoch": 2.45, + "learning_rate": 3.6353759235115172e-06, + "loss": 0.1225, + "step": 30124 + }, + { + "epoch": 2.45, + "learning_rate": 3.6348326814428515e-06, + "loss": 0.2748, + "step": 30125 + }, + { + "epoch": 2.45, + "learning_rate": 3.6342894393741857e-06, + "loss": 0.224, + "step": 30126 + }, + { + "epoch": 2.45, + "learning_rate": 3.6337461973055195e-06, + "loss": 0.0977, + "step": 30127 + }, + { + "epoch": 2.46, + "learning_rate": 3.6332029552368537e-06, + "loss": 0.1529, + "step": 30128 + }, + { + "epoch": 2.46, + "learning_rate": 3.632659713168188e-06, + "loss": 0.0569, + "step": 30129 + }, + { + "epoch": 2.46, + "learning_rate": 3.632116471099522e-06, + "loss": 0.19, + "step": 30130 + }, + { + "epoch": 2.46, + "learning_rate": 3.6315732290308564e-06, + "loss": 0.1682, + "step": 30131 + }, + { + "epoch": 2.46, + "learning_rate": 3.6310299869621907e-06, + "loss": 0.1435, + "step": 30132 + }, + { + "epoch": 2.46, + "learning_rate": 3.630486744893525e-06, + "loss": 0.2745, + "step": 30133 + }, + { + "epoch": 2.46, + "learning_rate": 3.629943502824859e-06, + "loss": 0.2835, + "step": 30134 + }, + { + "epoch": 2.46, + "learning_rate": 3.6294002607561933e-06, + "loss": 0.102, + "step": 30135 + }, + { + "epoch": 2.46, + "learning_rate": 3.6288570186875276e-06, + "loss": 0.2723, + "step": 30136 + }, + { + "epoch": 2.46, + "learning_rate": 3.6283137766188614e-06, + "loss": 0.4179, + "step": 30137 + }, + { + "epoch": 2.46, + "learning_rate": 3.6277705345501956e-06, + "loss": 0.1379, + "step": 30138 + }, + { + "epoch": 2.46, + "learning_rate": 3.62722729248153e-06, + "loss": 0.4153, + "step": 30139 + }, + { + "epoch": 2.46, + "learning_rate": 3.626684050412864e-06, + "loss": 0.0623, + "step": 30140 + }, + { + "epoch": 2.46, + "learning_rate": 3.6261408083441983e-06, + "loss": 0.1385, + "step": 30141 + }, + { + "epoch": 2.46, + "learning_rate": 3.6255975662755325e-06, + "loss": 0.296, + "step": 30142 + }, + { + "epoch": 2.46, + "learning_rate": 3.625054324206867e-06, + "loss": 0.0612, + "step": 30143 + }, + { + "epoch": 2.46, + "learning_rate": 3.6245110821382014e-06, + "loss": 0.1567, + "step": 30144 + }, + { + "epoch": 2.46, + "learning_rate": 3.6239678400695357e-06, + "loss": 0.345, + "step": 30145 + }, + { + "epoch": 2.46, + "learning_rate": 3.623424598000869e-06, + "loss": 0.0865, + "step": 30146 + }, + { + "epoch": 2.46, + "learning_rate": 3.6228813559322033e-06, + "loss": 0.1505, + "step": 30147 + }, + { + "epoch": 2.46, + "learning_rate": 3.622338113863538e-06, + "loss": 0.1054, + "step": 30148 + }, + { + "epoch": 2.46, + "learning_rate": 3.621794871794872e-06, + "loss": 0.4196, + "step": 30149 + }, + { + "epoch": 2.46, + "learning_rate": 3.6212516297262064e-06, + "loss": 0.0405, + "step": 30150 + }, + { + "epoch": 2.46, + "learning_rate": 3.6207083876575406e-06, + "loss": 0.1074, + "step": 30151 + }, + { + "epoch": 2.46, + "learning_rate": 3.620165145588875e-06, + "loss": 0.2927, + "step": 30152 + }, + { + "epoch": 2.46, + "learning_rate": 3.619621903520209e-06, + "loss": 0.3479, + "step": 30153 + }, + { + "epoch": 2.46, + "learning_rate": 3.6190786614515433e-06, + "loss": 0.412, + "step": 30154 + }, + { + "epoch": 2.46, + "learning_rate": 3.6185354193828775e-06, + "loss": 0.372, + "step": 30155 + }, + { + "epoch": 2.46, + "learning_rate": 3.6179921773142113e-06, + "loss": 0.3237, + "step": 30156 + }, + { + "epoch": 2.46, + "learning_rate": 3.6174489352455456e-06, + "loss": 0.0661, + "step": 30157 + }, + { + "epoch": 2.46, + "learning_rate": 3.61690569317688e-06, + "loss": 0.4477, + "step": 30158 + }, + { + "epoch": 2.46, + "learning_rate": 3.616362451108214e-06, + "loss": 0.0981, + "step": 30159 + }, + { + "epoch": 2.46, + "learning_rate": 3.6158192090395483e-06, + "loss": 0.188, + "step": 30160 + }, + { + "epoch": 2.46, + "learning_rate": 3.6152759669708825e-06, + "loss": 0.1111, + "step": 30161 + }, + { + "epoch": 2.46, + "learning_rate": 3.6147327249022167e-06, + "loss": 0.2563, + "step": 30162 + }, + { + "epoch": 2.46, + "learning_rate": 3.614189482833551e-06, + "loss": 0.2128, + "step": 30163 + }, + { + "epoch": 2.46, + "learning_rate": 3.613646240764885e-06, + "loss": 0.2394, + "step": 30164 + }, + { + "epoch": 2.46, + "learning_rate": 3.613102998696219e-06, + "loss": 0.1216, + "step": 30165 + }, + { + "epoch": 2.46, + "learning_rate": 3.6125597566275532e-06, + "loss": 0.2548, + "step": 30166 + }, + { + "epoch": 2.46, + "learning_rate": 3.6120165145588875e-06, + "loss": 0.0575, + "step": 30167 + }, + { + "epoch": 2.46, + "learning_rate": 3.6114732724902217e-06, + "loss": 0.4982, + "step": 30168 + }, + { + "epoch": 2.46, + "learning_rate": 3.610930030421556e-06, + "loss": 0.1421, + "step": 30169 + }, + { + "epoch": 2.46, + "learning_rate": 3.6103867883528906e-06, + "loss": 0.1434, + "step": 30170 + }, + { + "epoch": 2.46, + "learning_rate": 3.609843546284225e-06, + "loss": 0.1594, + "step": 30171 + }, + { + "epoch": 2.46, + "learning_rate": 3.609300304215559e-06, + "loss": 0.085, + "step": 30172 + }, + { + "epoch": 2.46, + "learning_rate": 3.6087570621468933e-06, + "loss": 0.2015, + "step": 30173 + }, + { + "epoch": 2.46, + "learning_rate": 3.6082138200782275e-06, + "loss": 0.3158, + "step": 30174 + }, + { + "epoch": 2.46, + "learning_rate": 3.6076705780095613e-06, + "loss": 0.2769, + "step": 30175 + }, + { + "epoch": 2.46, + "learning_rate": 3.6071273359408955e-06, + "loss": 0.1595, + "step": 30176 + }, + { + "epoch": 2.46, + "learning_rate": 3.6065840938722298e-06, + "loss": 0.1237, + "step": 30177 + }, + { + "epoch": 2.46, + "learning_rate": 3.606040851803564e-06, + "loss": 0.361, + "step": 30178 + }, + { + "epoch": 2.46, + "learning_rate": 3.6054976097348982e-06, + "loss": 0.2412, + "step": 30179 + }, + { + "epoch": 2.46, + "learning_rate": 3.6049543676662325e-06, + "loss": 0.1685, + "step": 30180 + }, + { + "epoch": 2.46, + "learning_rate": 3.6044111255975667e-06, + "loss": 0.1553, + "step": 30181 + }, + { + "epoch": 2.46, + "learning_rate": 3.603867883528901e-06, + "loss": 0.2191, + "step": 30182 + }, + { + "epoch": 2.46, + "learning_rate": 3.603324641460235e-06, + "loss": 0.1359, + "step": 30183 + }, + { + "epoch": 2.46, + "learning_rate": 3.602781399391569e-06, + "loss": 0.1336, + "step": 30184 + }, + { + "epoch": 2.46, + "learning_rate": 3.602238157322903e-06, + "loss": 0.2435, + "step": 30185 + }, + { + "epoch": 2.46, + "learning_rate": 3.6016949152542374e-06, + "loss": 0.3393, + "step": 30186 + }, + { + "epoch": 2.46, + "learning_rate": 3.6011516731855716e-06, + "loss": 0.19, + "step": 30187 + }, + { + "epoch": 2.46, + "learning_rate": 3.600608431116906e-06, + "loss": 0.1618, + "step": 30188 + }, + { + "epoch": 2.46, + "learning_rate": 3.60006518904824e-06, + "loss": 0.3996, + "step": 30189 + }, + { + "epoch": 2.46, + "learning_rate": 3.5995219469795743e-06, + "loss": 0.1486, + "step": 30190 + }, + { + "epoch": 2.46, + "learning_rate": 3.5989787049109086e-06, + "loss": 0.1151, + "step": 30191 + }, + { + "epoch": 2.46, + "learning_rate": 3.598435462842243e-06, + "loss": 0.0317, + "step": 30192 + }, + { + "epoch": 2.46, + "learning_rate": 3.5978922207735774e-06, + "loss": 0.2968, + "step": 30193 + }, + { + "epoch": 2.46, + "learning_rate": 3.597348978704911e-06, + "loss": 0.2104, + "step": 30194 + }, + { + "epoch": 2.46, + "learning_rate": 3.596805736636245e-06, + "loss": 0.2209, + "step": 30195 + }, + { + "epoch": 2.46, + "learning_rate": 3.5962624945675793e-06, + "loss": 0.4479, + "step": 30196 + }, + { + "epoch": 2.46, + "learning_rate": 3.595719252498914e-06, + "loss": 0.3041, + "step": 30197 + }, + { + "epoch": 2.46, + "learning_rate": 3.595176010430248e-06, + "loss": 0.1399, + "step": 30198 + }, + { + "epoch": 2.46, + "learning_rate": 3.5946327683615824e-06, + "loss": 0.0847, + "step": 30199 + }, + { + "epoch": 2.46, + "learning_rate": 3.5940895262929166e-06, + "loss": 0.0469, + "step": 30200 + }, + { + "epoch": 2.46, + "learning_rate": 3.593546284224251e-06, + "loss": 0.348, + "step": 30201 + }, + { + "epoch": 2.46, + "learning_rate": 3.593003042155585e-06, + "loss": 0.1812, + "step": 30202 + }, + { + "epoch": 2.46, + "learning_rate": 3.5924598000869193e-06, + "loss": 0.3505, + "step": 30203 + }, + { + "epoch": 2.46, + "learning_rate": 3.591916558018253e-06, + "loss": 0.2375, + "step": 30204 + }, + { + "epoch": 2.46, + "learning_rate": 3.5913733159495874e-06, + "loss": 0.1179, + "step": 30205 + }, + { + "epoch": 2.46, + "learning_rate": 3.5908300738809216e-06, + "loss": 0.134, + "step": 30206 + }, + { + "epoch": 2.46, + "learning_rate": 3.590286831812256e-06, + "loss": 0.1432, + "step": 30207 + }, + { + "epoch": 2.46, + "learning_rate": 3.58974358974359e-06, + "loss": 0.1018, + "step": 30208 + }, + { + "epoch": 2.46, + "learning_rate": 3.5892003476749243e-06, + "loss": 0.2217, + "step": 30209 + }, + { + "epoch": 2.46, + "learning_rate": 3.5886571056062585e-06, + "loss": 0.1594, + "step": 30210 + }, + { + "epoch": 2.46, + "learning_rate": 3.5881138635375928e-06, + "loss": 0.3346, + "step": 30211 + }, + { + "epoch": 2.46, + "learning_rate": 3.587570621468927e-06, + "loss": 0.136, + "step": 30212 + }, + { + "epoch": 2.46, + "learning_rate": 3.5870273794002608e-06, + "loss": 0.3614, + "step": 30213 + }, + { + "epoch": 2.46, + "learning_rate": 3.586484137331595e-06, + "loss": 0.3786, + "step": 30214 + }, + { + "epoch": 2.46, + "learning_rate": 3.5859408952629292e-06, + "loss": 0.1189, + "step": 30215 + }, + { + "epoch": 2.46, + "learning_rate": 3.5853976531942635e-06, + "loss": 0.1845, + "step": 30216 + }, + { + "epoch": 2.46, + "learning_rate": 3.5848544111255977e-06, + "loss": 0.1786, + "step": 30217 + }, + { + "epoch": 2.46, + "learning_rate": 3.584311169056932e-06, + "loss": 0.0985, + "step": 30218 + }, + { + "epoch": 2.46, + "learning_rate": 3.583767926988266e-06, + "loss": 0.0774, + "step": 30219 + }, + { + "epoch": 2.46, + "learning_rate": 3.583224684919601e-06, + "loss": 0.1373, + "step": 30220 + }, + { + "epoch": 2.46, + "learning_rate": 3.582681442850935e-06, + "loss": 0.1965, + "step": 30221 + }, + { + "epoch": 2.46, + "learning_rate": 3.5821382007822693e-06, + "loss": 0.1769, + "step": 30222 + }, + { + "epoch": 2.46, + "learning_rate": 3.5815949587136027e-06, + "loss": 0.1361, + "step": 30223 + }, + { + "epoch": 2.46, + "learning_rate": 3.5810517166449373e-06, + "loss": 0.2555, + "step": 30224 + }, + { + "epoch": 2.46, + "learning_rate": 3.5805084745762716e-06, + "loss": 0.3188, + "step": 30225 + }, + { + "epoch": 2.46, + "learning_rate": 3.5799652325076058e-06, + "loss": 0.2403, + "step": 30226 + }, + { + "epoch": 2.46, + "learning_rate": 3.57942199043894e-06, + "loss": 0.0742, + "step": 30227 + }, + { + "epoch": 2.46, + "learning_rate": 3.5788787483702742e-06, + "loss": 0.0558, + "step": 30228 + }, + { + "epoch": 2.46, + "learning_rate": 3.5783355063016085e-06, + "loss": 0.1762, + "step": 30229 + }, + { + "epoch": 2.46, + "learning_rate": 3.5777922642329427e-06, + "loss": 0.183, + "step": 30230 + }, + { + "epoch": 2.46, + "learning_rate": 3.577249022164277e-06, + "loss": 0.2282, + "step": 30231 + }, + { + "epoch": 2.46, + "learning_rate": 3.5767057800956107e-06, + "loss": 0.0446, + "step": 30232 + }, + { + "epoch": 2.46, + "learning_rate": 3.576162538026945e-06, + "loss": 0.2563, + "step": 30233 + }, + { + "epoch": 2.46, + "learning_rate": 3.575619295958279e-06, + "loss": 0.2137, + "step": 30234 + }, + { + "epoch": 2.46, + "learning_rate": 3.5750760538896134e-06, + "loss": 0.0756, + "step": 30235 + }, + { + "epoch": 2.46, + "learning_rate": 3.5745328118209477e-06, + "loss": 0.3519, + "step": 30236 + }, + { + "epoch": 2.46, + "learning_rate": 3.573989569752282e-06, + "loss": 0.2031, + "step": 30237 + }, + { + "epoch": 2.46, + "learning_rate": 3.573446327683616e-06, + "loss": 0.2242, + "step": 30238 + }, + { + "epoch": 2.46, + "learning_rate": 3.5729030856149504e-06, + "loss": 0.2053, + "step": 30239 + }, + { + "epoch": 2.46, + "learning_rate": 3.5723598435462846e-06, + "loss": 0.3268, + "step": 30240 + }, + { + "epoch": 2.46, + "learning_rate": 3.571816601477619e-06, + "loss": 0.0888, + "step": 30241 + }, + { + "epoch": 2.46, + "learning_rate": 3.5712733594089526e-06, + "loss": 0.3304, + "step": 30242 + }, + { + "epoch": 2.46, + "learning_rate": 3.570730117340287e-06, + "loss": 0.172, + "step": 30243 + }, + { + "epoch": 2.46, + "learning_rate": 3.570186875271621e-06, + "loss": 0.1173, + "step": 30244 + }, + { + "epoch": 2.46, + "learning_rate": 3.5696436332029553e-06, + "loss": 0.3549, + "step": 30245 + }, + { + "epoch": 2.46, + "learning_rate": 3.5691003911342895e-06, + "loss": 0.2535, + "step": 30246 + }, + { + "epoch": 2.46, + "learning_rate": 3.568557149065624e-06, + "loss": 0.4635, + "step": 30247 + }, + { + "epoch": 2.46, + "learning_rate": 3.5680139069969584e-06, + "loss": 0.3685, + "step": 30248 + }, + { + "epoch": 2.46, + "learning_rate": 3.5674706649282927e-06, + "loss": 0.3671, + "step": 30249 + }, + { + "epoch": 2.46, + "learning_rate": 3.566927422859627e-06, + "loss": 0.2033, + "step": 30250 + }, + { + "epoch": 2.46, + "eval_accuracy": 0.8445236882322975, + "eval_loss": 0.4996941387653351, + "eval_runtime": 22.2069, + "eval_samples_per_second": 441.979, + "eval_steps_per_second": 3.467, + "step": 30250 + }, + { + "epoch": 2.47, + "learning_rate": 3.5663841807909607e-06, + "loss": 0.1585, + "step": 30251 + }, + { + "epoch": 2.47, + "learning_rate": 3.565840938722295e-06, + "loss": 0.2128, + "step": 30252 + }, + { + "epoch": 2.47, + "learning_rate": 3.565297696653629e-06, + "loss": 0.3973, + "step": 30253 + }, + { + "epoch": 2.47, + "learning_rate": 3.5647544545849634e-06, + "loss": 0.3357, + "step": 30254 + }, + { + "epoch": 2.47, + "learning_rate": 3.5642112125162976e-06, + "loss": 0.3246, + "step": 30255 + }, + { + "epoch": 2.47, + "learning_rate": 3.563667970447632e-06, + "loss": 0.0835, + "step": 30256 + }, + { + "epoch": 2.47, + "learning_rate": 3.563124728378966e-06, + "loss": 0.3668, + "step": 30257 + }, + { + "epoch": 2.47, + "learning_rate": 3.5625814863103003e-06, + "loss": 0.3867, + "step": 30258 + }, + { + "epoch": 2.47, + "learning_rate": 3.5620382442416345e-06, + "loss": 0.0322, + "step": 30259 + }, + { + "epoch": 2.47, + "learning_rate": 3.5614950021729688e-06, + "loss": 0.0918, + "step": 30260 + }, + { + "epoch": 2.47, + "learning_rate": 3.5609517601043026e-06, + "loss": 0.4335, + "step": 30261 + }, + { + "epoch": 2.47, + "learning_rate": 3.560408518035637e-06, + "loss": 0.1985, + "step": 30262 + }, + { + "epoch": 2.47, + "learning_rate": 3.559865275966971e-06, + "loss": 0.091, + "step": 30263 + }, + { + "epoch": 2.47, + "learning_rate": 3.5593220338983053e-06, + "loss": 0.4234, + "step": 30264 + }, + { + "epoch": 2.47, + "learning_rate": 3.5587787918296395e-06, + "loss": 0.1923, + "step": 30265 + }, + { + "epoch": 2.47, + "learning_rate": 3.5582355497609737e-06, + "loss": 0.0811, + "step": 30266 + }, + { + "epoch": 2.47, + "learning_rate": 3.557692307692308e-06, + "loss": 0.3878, + "step": 30267 + }, + { + "epoch": 2.47, + "learning_rate": 3.557149065623642e-06, + "loss": 0.1047, + "step": 30268 + }, + { + "epoch": 2.47, + "learning_rate": 3.5566058235549764e-06, + "loss": 0.0784, + "step": 30269 + }, + { + "epoch": 2.47, + "learning_rate": 3.5560625814863102e-06, + "loss": 0.3484, + "step": 30270 + }, + { + "epoch": 2.47, + "learning_rate": 3.5555193394176445e-06, + "loss": 0.3739, + "step": 30271 + }, + { + "epoch": 2.47, + "learning_rate": 3.5549760973489787e-06, + "loss": 0.2292, + "step": 30272 + }, + { + "epoch": 2.47, + "learning_rate": 3.554432855280313e-06, + "loss": 0.3912, + "step": 30273 + }, + { + "epoch": 2.47, + "learning_rate": 3.5538896132116476e-06, + "loss": 0.1228, + "step": 30274 + }, + { + "epoch": 2.47, + "learning_rate": 3.553346371142982e-06, + "loss": 0.1256, + "step": 30275 + }, + { + "epoch": 2.47, + "learning_rate": 3.552803129074316e-06, + "loss": 0.0704, + "step": 30276 + }, + { + "epoch": 2.47, + "learning_rate": 3.5522598870056503e-06, + "loss": 0.2173, + "step": 30277 + }, + { + "epoch": 2.47, + "learning_rate": 3.5517166449369845e-06, + "loss": 0.3773, + "step": 30278 + }, + { + "epoch": 2.47, + "learning_rate": 3.5511734028683187e-06, + "loss": 0.0712, + "step": 30279 + }, + { + "epoch": 2.47, + "learning_rate": 3.5506301607996525e-06, + "loss": 0.2267, + "step": 30280 + }, + { + "epoch": 2.47, + "learning_rate": 3.5500869187309868e-06, + "loss": 0.2535, + "step": 30281 + }, + { + "epoch": 2.47, + "learning_rate": 3.549543676662321e-06, + "loss": 0.2755, + "step": 30282 + }, + { + "epoch": 2.47, + "learning_rate": 3.5490004345936552e-06, + "loss": 0.2778, + "step": 30283 + }, + { + "epoch": 2.47, + "learning_rate": 3.5484571925249895e-06, + "loss": 0.1044, + "step": 30284 + }, + { + "epoch": 2.47, + "learning_rate": 3.5479139504563237e-06, + "loss": 0.0994, + "step": 30285 + }, + { + "epoch": 2.47, + "learning_rate": 3.547370708387658e-06, + "loss": 0.3589, + "step": 30286 + }, + { + "epoch": 2.47, + "learning_rate": 3.546827466318992e-06, + "loss": 0.4448, + "step": 30287 + }, + { + "epoch": 2.47, + "learning_rate": 3.5462842242503264e-06, + "loss": 0.1752, + "step": 30288 + }, + { + "epoch": 2.47, + "learning_rate": 3.54574098218166e-06, + "loss": 0.1835, + "step": 30289 + }, + { + "epoch": 2.47, + "learning_rate": 3.5451977401129944e-06, + "loss": 0.1003, + "step": 30290 + }, + { + "epoch": 2.47, + "learning_rate": 3.5446544980443287e-06, + "loss": 0.2156, + "step": 30291 + }, + { + "epoch": 2.47, + "learning_rate": 3.544111255975663e-06, + "loss": 0.2774, + "step": 30292 + }, + { + "epoch": 2.47, + "learning_rate": 3.543568013906997e-06, + "loss": 0.0414, + "step": 30293 + }, + { + "epoch": 2.47, + "learning_rate": 3.5430247718383313e-06, + "loss": 0.2694, + "step": 30294 + }, + { + "epoch": 2.47, + "learning_rate": 3.5424815297696656e-06, + "loss": 0.0999, + "step": 30295 + }, + { + "epoch": 2.47, + "learning_rate": 3.541938287701e-06, + "loss": 0.1344, + "step": 30296 + }, + { + "epoch": 2.47, + "learning_rate": 3.5413950456323345e-06, + "loss": 0.5884, + "step": 30297 + }, + { + "epoch": 2.47, + "learning_rate": 3.5408518035636687e-06, + "loss": 0.213, + "step": 30298 + }, + { + "epoch": 2.47, + "learning_rate": 3.540308561495002e-06, + "loss": 0.218, + "step": 30299 + }, + { + "epoch": 2.47, + "learning_rate": 3.5397653194263363e-06, + "loss": 0.2904, + "step": 30300 + }, + { + "epoch": 2.47, + "learning_rate": 3.539222077357671e-06, + "loss": 0.2627, + "step": 30301 + }, + { + "epoch": 2.47, + "learning_rate": 3.538678835289005e-06, + "loss": 0.1046, + "step": 30302 + }, + { + "epoch": 2.47, + "learning_rate": 3.5381355932203394e-06, + "loss": 0.1163, + "step": 30303 + }, + { + "epoch": 2.47, + "learning_rate": 3.5375923511516737e-06, + "loss": 0.3115, + "step": 30304 + }, + { + "epoch": 2.47, + "learning_rate": 3.537049109083008e-06, + "loss": 0.0942, + "step": 30305 + }, + { + "epoch": 2.47, + "learning_rate": 3.536505867014342e-06, + "loss": 0.1775, + "step": 30306 + }, + { + "epoch": 2.47, + "learning_rate": 3.5359626249456763e-06, + "loss": 0.5541, + "step": 30307 + }, + { + "epoch": 2.47, + "learning_rate": 3.53541938287701e-06, + "loss": 0.2024, + "step": 30308 + }, + { + "epoch": 2.47, + "learning_rate": 3.5348761408083444e-06, + "loss": 0.1881, + "step": 30309 + }, + { + "epoch": 2.47, + "learning_rate": 3.5343328987396786e-06, + "loss": 0.1991, + "step": 30310 + }, + { + "epoch": 2.47, + "learning_rate": 3.533789656671013e-06, + "loss": 0.1124, + "step": 30311 + }, + { + "epoch": 2.47, + "learning_rate": 3.533246414602347e-06, + "loss": 0.2137, + "step": 30312 + }, + { + "epoch": 2.47, + "learning_rate": 3.5327031725336813e-06, + "loss": 0.1829, + "step": 30313 + }, + { + "epoch": 2.47, + "learning_rate": 3.5321599304650155e-06, + "loss": 0.2139, + "step": 30314 + }, + { + "epoch": 2.47, + "learning_rate": 3.5316166883963498e-06, + "loss": 0.3703, + "step": 30315 + }, + { + "epoch": 2.47, + "learning_rate": 3.531073446327684e-06, + "loss": 0.0837, + "step": 30316 + }, + { + "epoch": 2.47, + "learning_rate": 3.5305302042590182e-06, + "loss": 0.4482, + "step": 30317 + }, + { + "epoch": 2.47, + "learning_rate": 3.529986962190352e-06, + "loss": 0.2127, + "step": 30318 + }, + { + "epoch": 2.47, + "learning_rate": 3.5294437201216863e-06, + "loss": 0.1425, + "step": 30319 + }, + { + "epoch": 2.47, + "learning_rate": 3.5289004780530205e-06, + "loss": 0.2709, + "step": 30320 + }, + { + "epoch": 2.47, + "learning_rate": 3.5283572359843547e-06, + "loss": 0.0764, + "step": 30321 + }, + { + "epoch": 2.47, + "learning_rate": 3.527813993915689e-06, + "loss": 0.5462, + "step": 30322 + }, + { + "epoch": 2.47, + "learning_rate": 3.527270751847023e-06, + "loss": 0.2098, + "step": 30323 + }, + { + "epoch": 2.47, + "learning_rate": 3.526727509778358e-06, + "loss": 0.3056, + "step": 30324 + }, + { + "epoch": 2.47, + "learning_rate": 3.526184267709692e-06, + "loss": 0.3424, + "step": 30325 + }, + { + "epoch": 2.47, + "learning_rate": 3.5256410256410263e-06, + "loss": 0.1379, + "step": 30326 + }, + { + "epoch": 2.47, + "learning_rate": 3.5250977835723597e-06, + "loss": 0.1379, + "step": 30327 + }, + { + "epoch": 2.47, + "learning_rate": 3.5245545415036943e-06, + "loss": 0.3859, + "step": 30328 + }, + { + "epoch": 2.47, + "learning_rate": 3.5240112994350286e-06, + "loss": 0.1755, + "step": 30329 + }, + { + "epoch": 2.47, + "learning_rate": 3.523468057366363e-06, + "loss": 0.2222, + "step": 30330 + }, + { + "epoch": 2.47, + "learning_rate": 3.522924815297697e-06, + "loss": 0.0921, + "step": 30331 + }, + { + "epoch": 2.47, + "learning_rate": 3.5223815732290313e-06, + "loss": 0.1903, + "step": 30332 + }, + { + "epoch": 2.47, + "learning_rate": 3.5218383311603655e-06, + "loss": 0.4673, + "step": 30333 + }, + { + "epoch": 2.47, + "learning_rate": 3.5212950890916997e-06, + "loss": 0.057, + "step": 30334 + }, + { + "epoch": 2.47, + "learning_rate": 3.520751847023034e-06, + "loss": 0.062, + "step": 30335 + }, + { + "epoch": 2.47, + "learning_rate": 3.520208604954368e-06, + "loss": 0.1229, + "step": 30336 + }, + { + "epoch": 2.47, + "learning_rate": 3.519665362885702e-06, + "loss": 0.2621, + "step": 30337 + }, + { + "epoch": 2.47, + "learning_rate": 3.5191221208170362e-06, + "loss": 0.2342, + "step": 30338 + }, + { + "epoch": 2.47, + "learning_rate": 3.5185788787483704e-06, + "loss": 0.1522, + "step": 30339 + }, + { + "epoch": 2.47, + "learning_rate": 3.5180356366797047e-06, + "loss": 0.2496, + "step": 30340 + }, + { + "epoch": 2.47, + "learning_rate": 3.517492394611039e-06, + "loss": 0.229, + "step": 30341 + }, + { + "epoch": 2.47, + "learning_rate": 3.516949152542373e-06, + "loss": 0.159, + "step": 30342 + }, + { + "epoch": 2.47, + "learning_rate": 3.5164059104737074e-06, + "loss": 0.2272, + "step": 30343 + }, + { + "epoch": 2.47, + "learning_rate": 3.5158626684050416e-06, + "loss": 0.3745, + "step": 30344 + }, + { + "epoch": 2.47, + "learning_rate": 3.515319426336376e-06, + "loss": 0.0475, + "step": 30345 + }, + { + "epoch": 2.47, + "learning_rate": 3.5147761842677096e-06, + "loss": 0.3792, + "step": 30346 + }, + { + "epoch": 2.47, + "learning_rate": 3.514232942199044e-06, + "loss": 0.1872, + "step": 30347 + }, + { + "epoch": 2.47, + "learning_rate": 3.513689700130378e-06, + "loss": 0.2541, + "step": 30348 + }, + { + "epoch": 2.47, + "learning_rate": 3.5131464580617123e-06, + "loss": 0.4589, + "step": 30349 + }, + { + "epoch": 2.47, + "learning_rate": 3.5126032159930466e-06, + "loss": 0.1318, + "step": 30350 + }, + { + "epoch": 2.47, + "learning_rate": 3.5120599739243812e-06, + "loss": 0.2519, + "step": 30351 + }, + { + "epoch": 2.47, + "learning_rate": 3.5115167318557154e-06, + "loss": 0.2135, + "step": 30352 + }, + { + "epoch": 2.47, + "learning_rate": 3.5109734897870497e-06, + "loss": 0.0628, + "step": 30353 + }, + { + "epoch": 2.47, + "learning_rate": 3.510430247718384e-06, + "loss": 0.3112, + "step": 30354 + }, + { + "epoch": 2.47, + "learning_rate": 3.509887005649718e-06, + "loss": 0.0854, + "step": 30355 + }, + { + "epoch": 2.47, + "learning_rate": 3.509343763581052e-06, + "loss": 0.155, + "step": 30356 + }, + { + "epoch": 2.47, + "learning_rate": 3.508800521512386e-06, + "loss": 0.4376, + "step": 30357 + }, + { + "epoch": 2.47, + "learning_rate": 3.5082572794437204e-06, + "loss": 0.5128, + "step": 30358 + }, + { + "epoch": 2.47, + "learning_rate": 3.5077140373750546e-06, + "loss": 0.1657, + "step": 30359 + }, + { + "epoch": 2.47, + "learning_rate": 3.507170795306389e-06, + "loss": 0.1117, + "step": 30360 + }, + { + "epoch": 2.47, + "learning_rate": 3.506627553237723e-06, + "loss": 0.0855, + "step": 30361 + }, + { + "epoch": 2.47, + "learning_rate": 3.5060843111690573e-06, + "loss": 0.2166, + "step": 30362 + }, + { + "epoch": 2.47, + "learning_rate": 3.5055410691003916e-06, + "loss": 0.0799, + "step": 30363 + }, + { + "epoch": 2.47, + "learning_rate": 3.504997827031726e-06, + "loss": 0.071, + "step": 30364 + }, + { + "epoch": 2.47, + "learning_rate": 3.5044545849630596e-06, + "loss": 0.301, + "step": 30365 + }, + { + "epoch": 2.47, + "learning_rate": 3.503911342894394e-06, + "loss": 0.0841, + "step": 30366 + }, + { + "epoch": 2.47, + "learning_rate": 3.503368100825728e-06, + "loss": 0.1801, + "step": 30367 + }, + { + "epoch": 2.47, + "learning_rate": 3.5028248587570623e-06, + "loss": 0.502, + "step": 30368 + }, + { + "epoch": 2.47, + "learning_rate": 3.5022816166883965e-06, + "loss": 0.4804, + "step": 30369 + }, + { + "epoch": 2.47, + "learning_rate": 3.5017383746197307e-06, + "loss": 0.3005, + "step": 30370 + }, + { + "epoch": 2.47, + "learning_rate": 3.501195132551065e-06, + "loss": 0.0685, + "step": 30371 + }, + { + "epoch": 2.47, + "learning_rate": 3.500651890482399e-06, + "loss": 0.1315, + "step": 30372 + }, + { + "epoch": 2.47, + "learning_rate": 3.500108648413734e-06, + "loss": 0.2601, + "step": 30373 + }, + { + "epoch": 2.48, + "learning_rate": 3.499565406345068e-06, + "loss": 0.2505, + "step": 30374 + }, + { + "epoch": 2.48, + "learning_rate": 3.4990221642764015e-06, + "loss": 0.2555, + "step": 30375 + }, + { + "epoch": 2.48, + "learning_rate": 3.4984789222077357e-06, + "loss": 0.2199, + "step": 30376 + }, + { + "epoch": 2.48, + "learning_rate": 3.49793568013907e-06, + "loss": 0.2254, + "step": 30377 + }, + { + "epoch": 2.48, + "learning_rate": 3.4973924380704046e-06, + "loss": 0.1505, + "step": 30378 + }, + { + "epoch": 2.48, + "learning_rate": 3.496849196001739e-06, + "loss": 0.0989, + "step": 30379 + }, + { + "epoch": 2.48, + "learning_rate": 3.496305953933073e-06, + "loss": 0.0747, + "step": 30380 + }, + { + "epoch": 2.48, + "learning_rate": 3.4957627118644073e-06, + "loss": 0.4132, + "step": 30381 + }, + { + "epoch": 2.48, + "learning_rate": 3.4952194697957415e-06, + "loss": 0.1619, + "step": 30382 + }, + { + "epoch": 2.48, + "learning_rate": 3.4946762277270757e-06, + "loss": 0.219, + "step": 30383 + }, + { + "epoch": 2.48, + "learning_rate": 3.4941329856584096e-06, + "loss": 0.1194, + "step": 30384 + }, + { + "epoch": 2.48, + "learning_rate": 3.4935897435897438e-06, + "loss": 0.1445, + "step": 30385 + }, + { + "epoch": 2.48, + "learning_rate": 3.493046501521078e-06, + "loss": 0.1099, + "step": 30386 + }, + { + "epoch": 2.48, + "learning_rate": 3.4925032594524122e-06, + "loss": 0.1601, + "step": 30387 + }, + { + "epoch": 2.48, + "learning_rate": 3.4919600173837465e-06, + "loss": 0.1308, + "step": 30388 + }, + { + "epoch": 2.48, + "learning_rate": 3.4914167753150807e-06, + "loss": 0.2981, + "step": 30389 + }, + { + "epoch": 2.48, + "learning_rate": 3.490873533246415e-06, + "loss": 0.1154, + "step": 30390 + }, + { + "epoch": 2.48, + "learning_rate": 3.490330291177749e-06, + "loss": 0.1334, + "step": 30391 + }, + { + "epoch": 2.48, + "learning_rate": 3.4897870491090834e-06, + "loss": 0.0794, + "step": 30392 + }, + { + "epoch": 2.48, + "learning_rate": 3.4892438070404176e-06, + "loss": 0.1049, + "step": 30393 + }, + { + "epoch": 2.48, + "learning_rate": 3.4887005649717514e-06, + "loss": 0.1087, + "step": 30394 + }, + { + "epoch": 2.48, + "learning_rate": 3.4881573229030857e-06, + "loss": 0.3517, + "step": 30395 + }, + { + "epoch": 2.48, + "learning_rate": 3.48761408083442e-06, + "loss": 0.4195, + "step": 30396 + }, + { + "epoch": 2.48, + "learning_rate": 3.487070838765754e-06, + "loss": 0.2452, + "step": 30397 + }, + { + "epoch": 2.48, + "learning_rate": 3.4865275966970884e-06, + "loss": 0.0497, + "step": 30398 + }, + { + "epoch": 2.48, + "learning_rate": 3.4859843546284226e-06, + "loss": 0.0595, + "step": 30399 + }, + { + "epoch": 2.48, + "learning_rate": 3.4854411125597572e-06, + "loss": 0.6455, + "step": 30400 + }, + { + "epoch": 2.48, + "learning_rate": 3.4848978704910915e-06, + "loss": 0.4143, + "step": 30401 + }, + { + "epoch": 2.48, + "learning_rate": 3.4843546284224257e-06, + "loss": 0.1432, + "step": 30402 + }, + { + "epoch": 2.48, + "learning_rate": 3.483811386353759e-06, + "loss": 0.0934, + "step": 30403 + }, + { + "epoch": 2.48, + "learning_rate": 3.4832681442850933e-06, + "loss": 0.0343, + "step": 30404 + }, + { + "epoch": 2.48, + "learning_rate": 3.482724902216428e-06, + "loss": 0.2056, + "step": 30405 + }, + { + "epoch": 2.48, + "learning_rate": 3.482181660147762e-06, + "loss": 0.0786, + "step": 30406 + }, + { + "epoch": 2.48, + "learning_rate": 3.4816384180790964e-06, + "loss": 0.0741, + "step": 30407 + }, + { + "epoch": 2.48, + "learning_rate": 3.4810951760104307e-06, + "loss": 0.103, + "step": 30408 + }, + { + "epoch": 2.48, + "learning_rate": 3.480551933941765e-06, + "loss": 0.4401, + "step": 30409 + }, + { + "epoch": 2.48, + "learning_rate": 3.480008691873099e-06, + "loss": 0.5897, + "step": 30410 + }, + { + "epoch": 2.48, + "learning_rate": 3.4794654498044334e-06, + "loss": 0.2049, + "step": 30411 + }, + { + "epoch": 2.48, + "learning_rate": 3.4789222077357676e-06, + "loss": 0.2307, + "step": 30412 + }, + { + "epoch": 2.48, + "learning_rate": 3.4783789656671014e-06, + "loss": 0.2475, + "step": 30413 + }, + { + "epoch": 2.48, + "learning_rate": 3.4778357235984356e-06, + "loss": 0.27, + "step": 30414 + }, + { + "epoch": 2.48, + "learning_rate": 3.47729248152977e-06, + "loss": 0.0576, + "step": 30415 + }, + { + "epoch": 2.48, + "learning_rate": 3.476749239461104e-06, + "loss": 0.2051, + "step": 30416 + }, + { + "epoch": 2.48, + "learning_rate": 3.4762059973924383e-06, + "loss": 0.1255, + "step": 30417 + }, + { + "epoch": 2.48, + "learning_rate": 3.4756627553237725e-06, + "loss": 0.2624, + "step": 30418 + }, + { + "epoch": 2.48, + "learning_rate": 3.4751195132551068e-06, + "loss": 0.2164, + "step": 30419 + }, + { + "epoch": 2.48, + "learning_rate": 3.474576271186441e-06, + "loss": 0.1673, + "step": 30420 + }, + { + "epoch": 2.48, + "learning_rate": 3.4740330291177752e-06, + "loss": 0.1863, + "step": 30421 + }, + { + "epoch": 2.48, + "learning_rate": 3.473489787049109e-06, + "loss": 0.2487, + "step": 30422 + }, + { + "epoch": 2.48, + "learning_rate": 3.4729465449804433e-06, + "loss": 0.1449, + "step": 30423 + }, + { + "epoch": 2.48, + "learning_rate": 3.4724033029117775e-06, + "loss": 0.1598, + "step": 30424 + }, + { + "epoch": 2.48, + "learning_rate": 3.4718600608431117e-06, + "loss": 0.2176, + "step": 30425 + }, + { + "epoch": 2.48, + "learning_rate": 3.471316818774446e-06, + "loss": 0.3013, + "step": 30426 + }, + { + "epoch": 2.48, + "learning_rate": 3.4707735767057806e-06, + "loss": 0.1866, + "step": 30427 + }, + { + "epoch": 2.48, + "learning_rate": 3.470230334637115e-06, + "loss": 0.2044, + "step": 30428 + }, + { + "epoch": 2.48, + "learning_rate": 3.469687092568449e-06, + "loss": 0.3679, + "step": 30429 + }, + { + "epoch": 2.48, + "learning_rate": 3.4691438504997833e-06, + "loss": 0.0653, + "step": 30430 + }, + { + "epoch": 2.48, + "learning_rate": 3.4686006084311175e-06, + "loss": 0.1258, + "step": 30431 + }, + { + "epoch": 2.48, + "learning_rate": 3.4680573663624513e-06, + "loss": 0.3267, + "step": 30432 + }, + { + "epoch": 2.48, + "learning_rate": 3.4675141242937856e-06, + "loss": 0.4195, + "step": 30433 + }, + { + "epoch": 2.48, + "learning_rate": 3.46697088222512e-06, + "loss": 0.1816, + "step": 30434 + }, + { + "epoch": 2.48, + "learning_rate": 3.466427640156454e-06, + "loss": 0.0514, + "step": 30435 + }, + { + "epoch": 2.48, + "learning_rate": 3.4658843980877883e-06, + "loss": 0.5308, + "step": 30436 + }, + { + "epoch": 2.48, + "learning_rate": 3.4653411560191225e-06, + "loss": 0.0521, + "step": 30437 + }, + { + "epoch": 2.48, + "learning_rate": 3.4647979139504567e-06, + "loss": 0.2452, + "step": 30438 + }, + { + "epoch": 2.48, + "learning_rate": 3.464254671881791e-06, + "loss": 0.369, + "step": 30439 + }, + { + "epoch": 2.48, + "learning_rate": 3.463711429813125e-06, + "loss": 0.1915, + "step": 30440 + }, + { + "epoch": 2.48, + "learning_rate": 3.463168187744459e-06, + "loss": 0.2919, + "step": 30441 + }, + { + "epoch": 2.48, + "learning_rate": 3.4626249456757932e-06, + "loss": 0.1552, + "step": 30442 + }, + { + "epoch": 2.48, + "learning_rate": 3.4620817036071275e-06, + "loss": 0.1335, + "step": 30443 + }, + { + "epoch": 2.48, + "learning_rate": 3.4615384615384617e-06, + "loss": 0.3182, + "step": 30444 + }, + { + "epoch": 2.48, + "learning_rate": 3.460995219469796e-06, + "loss": 0.2071, + "step": 30445 + }, + { + "epoch": 2.48, + "learning_rate": 3.46045197740113e-06, + "loss": 0.127, + "step": 30446 + }, + { + "epoch": 2.48, + "learning_rate": 3.4599087353324644e-06, + "loss": 0.4089, + "step": 30447 + }, + { + "epoch": 2.48, + "learning_rate": 3.4593654932637986e-06, + "loss": 0.1309, + "step": 30448 + }, + { + "epoch": 2.48, + "learning_rate": 3.458822251195133e-06, + "loss": 0.2048, + "step": 30449 + }, + { + "epoch": 2.48, + "learning_rate": 3.4582790091264675e-06, + "loss": 0.3303, + "step": 30450 + }, + { + "epoch": 2.48, + "learning_rate": 3.457735767057801e-06, + "loss": 0.1327, + "step": 30451 + }, + { + "epoch": 2.48, + "learning_rate": 3.457192524989135e-06, + "loss": 0.0874, + "step": 30452 + }, + { + "epoch": 2.48, + "learning_rate": 3.4566492829204693e-06, + "loss": 0.152, + "step": 30453 + }, + { + "epoch": 2.48, + "learning_rate": 3.456106040851804e-06, + "loss": 0.0614, + "step": 30454 + }, + { + "epoch": 2.48, + "learning_rate": 3.4555627987831382e-06, + "loss": 0.3176, + "step": 30455 + }, + { + "epoch": 2.48, + "learning_rate": 3.4550195567144725e-06, + "loss": 0.0993, + "step": 30456 + }, + { + "epoch": 2.48, + "learning_rate": 3.4544763146458067e-06, + "loss": 0.4367, + "step": 30457 + }, + { + "epoch": 2.48, + "learning_rate": 3.453933072577141e-06, + "loss": 0.1666, + "step": 30458 + }, + { + "epoch": 2.48, + "learning_rate": 3.453389830508475e-06, + "loss": 0.1626, + "step": 30459 + }, + { + "epoch": 2.48, + "learning_rate": 3.452846588439809e-06, + "loss": 0.49, + "step": 30460 + }, + { + "epoch": 2.48, + "learning_rate": 3.452303346371143e-06, + "loss": 0.2658, + "step": 30461 + }, + { + "epoch": 2.48, + "learning_rate": 3.4517601043024774e-06, + "loss": 0.1668, + "step": 30462 + }, + { + "epoch": 2.48, + "learning_rate": 3.4512168622338116e-06, + "loss": 0.1574, + "step": 30463 + }, + { + "epoch": 2.48, + "learning_rate": 3.450673620165146e-06, + "loss": 0.1743, + "step": 30464 + }, + { + "epoch": 2.48, + "learning_rate": 3.45013037809648e-06, + "loss": 0.2684, + "step": 30465 + }, + { + "epoch": 2.48, + "learning_rate": 3.4495871360278143e-06, + "loss": 0.2016, + "step": 30466 + }, + { + "epoch": 2.48, + "learning_rate": 3.4490438939591486e-06, + "loss": 0.1469, + "step": 30467 + }, + { + "epoch": 2.48, + "learning_rate": 3.448500651890483e-06, + "loss": 0.1821, + "step": 30468 + }, + { + "epoch": 2.48, + "learning_rate": 3.447957409821817e-06, + "loss": 0.3703, + "step": 30469 + }, + { + "epoch": 2.48, + "learning_rate": 3.447414167753151e-06, + "loss": 0.1974, + "step": 30470 + }, + { + "epoch": 2.48, + "learning_rate": 3.446870925684485e-06, + "loss": 0.2049, + "step": 30471 + }, + { + "epoch": 2.48, + "learning_rate": 3.4463276836158193e-06, + "loss": 0.1284, + "step": 30472 + }, + { + "epoch": 2.48, + "learning_rate": 3.4457844415471535e-06, + "loss": 0.1348, + "step": 30473 + }, + { + "epoch": 2.48, + "learning_rate": 3.4452411994784878e-06, + "loss": 0.3607, + "step": 30474 + }, + { + "epoch": 2.48, + "learning_rate": 3.444697957409822e-06, + "loss": 0.1532, + "step": 30475 + }, + { + "epoch": 2.48, + "learning_rate": 3.4441547153411562e-06, + "loss": 0.2055, + "step": 30476 + }, + { + "epoch": 2.48, + "learning_rate": 3.443611473272491e-06, + "loss": 0.135, + "step": 30477 + }, + { + "epoch": 2.48, + "learning_rate": 3.443068231203825e-06, + "loss": 0.0877, + "step": 30478 + }, + { + "epoch": 2.48, + "learning_rate": 3.4425249891351585e-06, + "loss": 0.3182, + "step": 30479 + }, + { + "epoch": 2.48, + "learning_rate": 3.4419817470664927e-06, + "loss": 0.4976, + "step": 30480 + }, + { + "epoch": 2.48, + "learning_rate": 3.4414385049978274e-06, + "loss": 0.1432, + "step": 30481 + }, + { + "epoch": 2.48, + "learning_rate": 3.4408952629291616e-06, + "loss": 0.2117, + "step": 30482 + }, + { + "epoch": 2.48, + "learning_rate": 3.440352020860496e-06, + "loss": 0.2572, + "step": 30483 + }, + { + "epoch": 2.48, + "learning_rate": 3.43980877879183e-06, + "loss": 0.2511, + "step": 30484 + }, + { + "epoch": 2.48, + "learning_rate": 3.4392655367231643e-06, + "loss": 0.3265, + "step": 30485 + }, + { + "epoch": 2.48, + "learning_rate": 3.4387222946544985e-06, + "loss": 0.399, + "step": 30486 + }, + { + "epoch": 2.48, + "learning_rate": 3.4381790525858328e-06, + "loss": 0.0842, + "step": 30487 + }, + { + "epoch": 2.48, + "learning_rate": 3.437635810517167e-06, + "loss": 0.384, + "step": 30488 + }, + { + "epoch": 2.48, + "learning_rate": 3.437092568448501e-06, + "loss": 0.1949, + "step": 30489 + }, + { + "epoch": 2.48, + "learning_rate": 3.436549326379835e-06, + "loss": 0.1607, + "step": 30490 + }, + { + "epoch": 2.48, + "learning_rate": 3.4360060843111693e-06, + "loss": 0.3675, + "step": 30491 + }, + { + "epoch": 2.48, + "learning_rate": 3.4354628422425035e-06, + "loss": 0.4873, + "step": 30492 + }, + { + "epoch": 2.48, + "learning_rate": 3.4349196001738377e-06, + "loss": 0.0938, + "step": 30493 + }, + { + "epoch": 2.48, + "learning_rate": 3.434376358105172e-06, + "loss": 0.1275, + "step": 30494 + }, + { + "epoch": 2.48, + "learning_rate": 3.433833116036506e-06, + "loss": 0.4869, + "step": 30495 + }, + { + "epoch": 2.49, + "learning_rate": 3.4332898739678404e-06, + "loss": 0.2119, + "step": 30496 + }, + { + "epoch": 2.49, + "learning_rate": 3.4327466318991746e-06, + "loss": 0.2155, + "step": 30497 + }, + { + "epoch": 2.49, + "learning_rate": 3.4322033898305084e-06, + "loss": 0.3543, + "step": 30498 + }, + { + "epoch": 2.49, + "learning_rate": 3.4316601477618427e-06, + "loss": 0.2717, + "step": 30499 + }, + { + "epoch": 2.49, + "learning_rate": 3.431116905693177e-06, + "loss": 0.0965, + "step": 30500 + }, + { + "epoch": 2.49, + "eval_accuracy": 0.8412633723892002, + "eval_loss": 0.4981120824813843, + "eval_runtime": 22.3431, + "eval_samples_per_second": 439.286, + "eval_steps_per_second": 3.446, + "step": 30500 + }, + { + "epoch": 2.49, + "learning_rate": 3.430573663624511e-06, + "loss": 0.0645, + "step": 30501 + }, + { + "epoch": 2.49, + "learning_rate": 3.4300304215558454e-06, + "loss": 0.3621, + "step": 30502 + }, + { + "epoch": 2.49, + "learning_rate": 3.4294871794871796e-06, + "loss": 0.0825, + "step": 30503 + }, + { + "epoch": 2.49, + "learning_rate": 3.4289439374185143e-06, + "loss": 0.1758, + "step": 30504 + }, + { + "epoch": 2.49, + "learning_rate": 3.4284006953498485e-06, + "loss": 0.2669, + "step": 30505 + }, + { + "epoch": 2.49, + "learning_rate": 3.4278574532811827e-06, + "loss": 0.2206, + "step": 30506 + }, + { + "epoch": 2.49, + "learning_rate": 3.427314211212517e-06, + "loss": 0.3584, + "step": 30507 + }, + { + "epoch": 2.49, + "learning_rate": 3.4267709691438508e-06, + "loss": 0.1981, + "step": 30508 + }, + { + "epoch": 2.49, + "learning_rate": 3.426227727075185e-06, + "loss": 0.4498, + "step": 30509 + }, + { + "epoch": 2.49, + "learning_rate": 3.4256844850065192e-06, + "loss": 0.0878, + "step": 30510 + }, + { + "epoch": 2.49, + "learning_rate": 3.4251412429378534e-06, + "loss": 0.1837, + "step": 30511 + }, + { + "epoch": 2.49, + "learning_rate": 3.4245980008691877e-06, + "loss": 0.1518, + "step": 30512 + }, + { + "epoch": 2.49, + "learning_rate": 3.424054758800522e-06, + "loss": 0.1742, + "step": 30513 + }, + { + "epoch": 2.49, + "learning_rate": 3.423511516731856e-06, + "loss": 0.3025, + "step": 30514 + }, + { + "epoch": 2.49, + "learning_rate": 3.4229682746631904e-06, + "loss": 0.1764, + "step": 30515 + }, + { + "epoch": 2.49, + "learning_rate": 3.4224250325945246e-06, + "loss": 0.1523, + "step": 30516 + }, + { + "epoch": 2.49, + "learning_rate": 3.4218817905258584e-06, + "loss": 0.1615, + "step": 30517 + }, + { + "epoch": 2.49, + "learning_rate": 3.4213385484571926e-06, + "loss": 0.3096, + "step": 30518 + }, + { + "epoch": 2.49, + "learning_rate": 3.420795306388527e-06, + "loss": 0.1328, + "step": 30519 + }, + { + "epoch": 2.49, + "learning_rate": 3.420252064319861e-06, + "loss": 0.2191, + "step": 30520 + }, + { + "epoch": 2.49, + "learning_rate": 3.4197088222511953e-06, + "loss": 0.106, + "step": 30521 + }, + { + "epoch": 2.49, + "learning_rate": 3.4191655801825296e-06, + "loss": 0.2131, + "step": 30522 + }, + { + "epoch": 2.49, + "learning_rate": 3.4186223381138638e-06, + "loss": 0.3112, + "step": 30523 + }, + { + "epoch": 2.49, + "learning_rate": 3.418079096045198e-06, + "loss": 0.1655, + "step": 30524 + }, + { + "epoch": 2.49, + "learning_rate": 3.4175358539765322e-06, + "loss": 0.2431, + "step": 30525 + }, + { + "epoch": 2.49, + "learning_rate": 3.4169926119078665e-06, + "loss": 0.3177, + "step": 30526 + }, + { + "epoch": 2.49, + "learning_rate": 3.4164493698392003e-06, + "loss": 0.0369, + "step": 30527 + }, + { + "epoch": 2.49, + "learning_rate": 3.4159061277705345e-06, + "loss": 0.1322, + "step": 30528 + }, + { + "epoch": 2.49, + "learning_rate": 3.4153628857018687e-06, + "loss": 0.2714, + "step": 30529 + }, + { + "epoch": 2.49, + "learning_rate": 3.414819643633203e-06, + "loss": 0.1732, + "step": 30530 + }, + { + "epoch": 2.49, + "learning_rate": 3.4142764015645376e-06, + "loss": 0.3628, + "step": 30531 + }, + { + "epoch": 2.49, + "learning_rate": 3.413733159495872e-06, + "loss": 0.2682, + "step": 30532 + }, + { + "epoch": 2.49, + "learning_rate": 3.413189917427206e-06, + "loss": 0.3553, + "step": 30533 + }, + { + "epoch": 2.49, + "learning_rate": 3.4126466753585403e-06, + "loss": 0.1874, + "step": 30534 + }, + { + "epoch": 2.49, + "learning_rate": 3.4121034332898746e-06, + "loss": 0.2866, + "step": 30535 + }, + { + "epoch": 2.49, + "learning_rate": 3.4115601912212084e-06, + "loss": 0.0681, + "step": 30536 + }, + { + "epoch": 2.49, + "learning_rate": 3.4110169491525426e-06, + "loss": 0.377, + "step": 30537 + }, + { + "epoch": 2.49, + "learning_rate": 3.410473707083877e-06, + "loss": 0.1262, + "step": 30538 + }, + { + "epoch": 2.49, + "learning_rate": 3.409930465015211e-06, + "loss": 0.1317, + "step": 30539 + }, + { + "epoch": 2.49, + "learning_rate": 3.4093872229465453e-06, + "loss": 0.1866, + "step": 30540 + }, + { + "epoch": 2.49, + "learning_rate": 3.4088439808778795e-06, + "loss": 0.4714, + "step": 30541 + }, + { + "epoch": 2.49, + "learning_rate": 3.4083007388092137e-06, + "loss": 0.1304, + "step": 30542 + }, + { + "epoch": 2.49, + "learning_rate": 3.407757496740548e-06, + "loss": 0.2971, + "step": 30543 + }, + { + "epoch": 2.49, + "learning_rate": 3.407214254671882e-06, + "loss": 0.2022, + "step": 30544 + }, + { + "epoch": 2.49, + "learning_rate": 3.4066710126032164e-06, + "loss": 0.2213, + "step": 30545 + }, + { + "epoch": 2.49, + "learning_rate": 3.4061277705345502e-06, + "loss": 0.1285, + "step": 30546 + }, + { + "epoch": 2.49, + "learning_rate": 3.4055845284658845e-06, + "loss": 0.3094, + "step": 30547 + }, + { + "epoch": 2.49, + "learning_rate": 3.4050412863972187e-06, + "loss": 0.0998, + "step": 30548 + }, + { + "epoch": 2.49, + "learning_rate": 3.404498044328553e-06, + "loss": 0.249, + "step": 30549 + }, + { + "epoch": 2.49, + "learning_rate": 3.403954802259887e-06, + "loss": 0.3518, + "step": 30550 + }, + { + "epoch": 2.49, + "learning_rate": 3.4034115601912214e-06, + "loss": 0.4318, + "step": 30551 + }, + { + "epoch": 2.49, + "learning_rate": 3.4028683181225556e-06, + "loss": 0.1964, + "step": 30552 + }, + { + "epoch": 2.49, + "learning_rate": 3.40232507605389e-06, + "loss": 0.2225, + "step": 30553 + }, + { + "epoch": 2.49, + "learning_rate": 3.4017818339852245e-06, + "loss": 0.2102, + "step": 30554 + }, + { + "epoch": 2.49, + "learning_rate": 3.401238591916558e-06, + "loss": 0.3299, + "step": 30555 + }, + { + "epoch": 2.49, + "learning_rate": 3.400695349847892e-06, + "loss": 0.3737, + "step": 30556 + }, + { + "epoch": 2.49, + "learning_rate": 3.4001521077792264e-06, + "loss": 0.1928, + "step": 30557 + }, + { + "epoch": 2.49, + "learning_rate": 3.399608865710561e-06, + "loss": 0.2316, + "step": 30558 + }, + { + "epoch": 2.49, + "learning_rate": 3.3990656236418952e-06, + "loss": 0.1684, + "step": 30559 + }, + { + "epoch": 2.49, + "learning_rate": 3.3985223815732295e-06, + "loss": 0.1254, + "step": 30560 + }, + { + "epoch": 2.49, + "learning_rate": 3.3979791395045637e-06, + "loss": 0.0335, + "step": 30561 + }, + { + "epoch": 2.49, + "learning_rate": 3.397435897435898e-06, + "loss": 0.1113, + "step": 30562 + }, + { + "epoch": 2.49, + "learning_rate": 3.396892655367232e-06, + "loss": 0.1213, + "step": 30563 + }, + { + "epoch": 2.49, + "learning_rate": 3.3963494132985664e-06, + "loss": 0.2891, + "step": 30564 + }, + { + "epoch": 2.49, + "learning_rate": 3.3958061712299e-06, + "loss": 0.1877, + "step": 30565 + }, + { + "epoch": 2.49, + "learning_rate": 3.3952629291612344e-06, + "loss": 0.146, + "step": 30566 + }, + { + "epoch": 2.49, + "learning_rate": 3.3947196870925687e-06, + "loss": 0.3106, + "step": 30567 + }, + { + "epoch": 2.49, + "learning_rate": 3.394176445023903e-06, + "loss": 0.2548, + "step": 30568 + }, + { + "epoch": 2.49, + "learning_rate": 3.393633202955237e-06, + "loss": 0.2402, + "step": 30569 + }, + { + "epoch": 2.49, + "learning_rate": 3.3930899608865714e-06, + "loss": 0.1848, + "step": 30570 + }, + { + "epoch": 2.49, + "learning_rate": 3.3925467188179056e-06, + "loss": 0.1555, + "step": 30571 + }, + { + "epoch": 2.49, + "learning_rate": 3.39200347674924e-06, + "loss": 0.3311, + "step": 30572 + }, + { + "epoch": 2.49, + "learning_rate": 3.391460234680574e-06, + "loss": 0.3091, + "step": 30573 + }, + { + "epoch": 2.49, + "learning_rate": 3.390916992611908e-06, + "loss": 0.2316, + "step": 30574 + }, + { + "epoch": 2.49, + "learning_rate": 3.390373750543242e-06, + "loss": 0.3889, + "step": 30575 + }, + { + "epoch": 2.49, + "learning_rate": 3.3898305084745763e-06, + "loss": 0.145, + "step": 30576 + }, + { + "epoch": 2.49, + "learning_rate": 3.3892872664059105e-06, + "loss": 0.2155, + "step": 30577 + }, + { + "epoch": 2.49, + "learning_rate": 3.3887440243372448e-06, + "loss": 0.1958, + "step": 30578 + }, + { + "epoch": 2.49, + "learning_rate": 3.388200782268579e-06, + "loss": 0.1723, + "step": 30579 + }, + { + "epoch": 2.49, + "learning_rate": 3.3876575401999132e-06, + "loss": 0.3432, + "step": 30580 + }, + { + "epoch": 2.49, + "learning_rate": 3.387114298131248e-06, + "loss": 0.1407, + "step": 30581 + }, + { + "epoch": 2.49, + "learning_rate": 3.386571056062582e-06, + "loss": 0.244, + "step": 30582 + }, + { + "epoch": 2.49, + "learning_rate": 3.3860278139939163e-06, + "loss": 0.1841, + "step": 30583 + }, + { + "epoch": 2.49, + "learning_rate": 3.3854845719252497e-06, + "loss": 0.1618, + "step": 30584 + }, + { + "epoch": 2.49, + "learning_rate": 3.3849413298565844e-06, + "loss": 0.1429, + "step": 30585 + }, + { + "epoch": 2.49, + "learning_rate": 3.3843980877879186e-06, + "loss": 0.154, + "step": 30586 + }, + { + "epoch": 2.49, + "learning_rate": 3.383854845719253e-06, + "loss": 0.3587, + "step": 30587 + }, + { + "epoch": 2.49, + "learning_rate": 3.383311603650587e-06, + "loss": 0.2426, + "step": 30588 + }, + { + "epoch": 2.49, + "learning_rate": 3.3827683615819213e-06, + "loss": 0.2588, + "step": 30589 + }, + { + "epoch": 2.49, + "learning_rate": 3.3822251195132555e-06, + "loss": 0.3766, + "step": 30590 + }, + { + "epoch": 2.49, + "learning_rate": 3.3816818774445898e-06, + "loss": 0.2301, + "step": 30591 + }, + { + "epoch": 2.49, + "learning_rate": 3.381138635375924e-06, + "loss": 0.1506, + "step": 30592 + }, + { + "epoch": 2.49, + "learning_rate": 3.380595393307258e-06, + "loss": 0.2286, + "step": 30593 + }, + { + "epoch": 2.49, + "learning_rate": 3.380052151238592e-06, + "loss": 0.1725, + "step": 30594 + }, + { + "epoch": 2.49, + "learning_rate": 3.3795089091699263e-06, + "loss": 0.0324, + "step": 30595 + }, + { + "epoch": 2.49, + "learning_rate": 3.3789656671012605e-06, + "loss": 0.3386, + "step": 30596 + }, + { + "epoch": 2.49, + "learning_rate": 3.3784224250325947e-06, + "loss": 0.1238, + "step": 30597 + }, + { + "epoch": 2.49, + "learning_rate": 3.377879182963929e-06, + "loss": 0.1691, + "step": 30598 + }, + { + "epoch": 2.49, + "learning_rate": 3.377335940895263e-06, + "loss": 0.2448, + "step": 30599 + }, + { + "epoch": 2.49, + "learning_rate": 3.3767926988265974e-06, + "loss": 0.0681, + "step": 30600 + }, + { + "epoch": 2.49, + "learning_rate": 3.3762494567579317e-06, + "loss": 0.1737, + "step": 30601 + }, + { + "epoch": 2.49, + "learning_rate": 3.375706214689266e-06, + "loss": 0.0566, + "step": 30602 + }, + { + "epoch": 2.49, + "learning_rate": 3.3751629726205997e-06, + "loss": 0.1801, + "step": 30603 + }, + { + "epoch": 2.49, + "learning_rate": 3.374619730551934e-06, + "loss": 0.1433, + "step": 30604 + }, + { + "epoch": 2.49, + "learning_rate": 3.374076488483268e-06, + "loss": 0.3038, + "step": 30605 + }, + { + "epoch": 2.49, + "learning_rate": 3.3735332464146024e-06, + "loss": 0.1281, + "step": 30606 + }, + { + "epoch": 2.49, + "learning_rate": 3.3729900043459366e-06, + "loss": 0.3927, + "step": 30607 + }, + { + "epoch": 2.49, + "learning_rate": 3.3724467622772713e-06, + "loss": 0.2998, + "step": 30608 + }, + { + "epoch": 2.49, + "learning_rate": 3.3719035202086055e-06, + "loss": 0.1548, + "step": 30609 + }, + { + "epoch": 2.49, + "learning_rate": 3.3713602781399397e-06, + "loss": 0.5361, + "step": 30610 + }, + { + "epoch": 2.49, + "learning_rate": 3.370817036071274e-06, + "loss": 0.1752, + "step": 30611 + }, + { + "epoch": 2.49, + "learning_rate": 3.3702737940026078e-06, + "loss": 0.1139, + "step": 30612 + }, + { + "epoch": 2.49, + "learning_rate": 3.369730551933942e-06, + "loss": 0.2982, + "step": 30613 + }, + { + "epoch": 2.49, + "learning_rate": 3.3691873098652762e-06, + "loss": 0.2065, + "step": 30614 + }, + { + "epoch": 2.49, + "learning_rate": 3.3686440677966105e-06, + "loss": 0.1545, + "step": 30615 + }, + { + "epoch": 2.49, + "learning_rate": 3.3681008257279447e-06, + "loss": 0.4554, + "step": 30616 + }, + { + "epoch": 2.49, + "learning_rate": 3.367557583659279e-06, + "loss": 0.1928, + "step": 30617 + }, + { + "epoch": 2.49, + "learning_rate": 3.367014341590613e-06, + "loss": 0.3785, + "step": 30618 + }, + { + "epoch": 2.5, + "learning_rate": 3.3664710995219474e-06, + "loss": 0.1884, + "step": 30619 + }, + { + "epoch": 2.5, + "learning_rate": 3.3659278574532816e-06, + "loss": 0.2884, + "step": 30620 + }, + { + "epoch": 2.5, + "learning_rate": 3.365384615384616e-06, + "loss": 0.3933, + "step": 30621 + }, + { + "epoch": 2.5, + "learning_rate": 3.3648413733159496e-06, + "loss": 0.2247, + "step": 30622 + }, + { + "epoch": 2.5, + "learning_rate": 3.364298131247284e-06, + "loss": 0.1481, + "step": 30623 + }, + { + "epoch": 2.5, + "learning_rate": 3.363754889178618e-06, + "loss": 0.0962, + "step": 30624 + }, + { + "epoch": 2.5, + "learning_rate": 3.3632116471099523e-06, + "loss": 0.3538, + "step": 30625 + }, + { + "epoch": 2.5, + "learning_rate": 3.3626684050412866e-06, + "loss": 0.4088, + "step": 30626 + }, + { + "epoch": 2.5, + "learning_rate": 3.362125162972621e-06, + "loss": 0.1231, + "step": 30627 + }, + { + "epoch": 2.5, + "learning_rate": 3.361581920903955e-06, + "loss": 0.4168, + "step": 30628 + }, + { + "epoch": 2.5, + "learning_rate": 3.3610386788352893e-06, + "loss": 0.1784, + "step": 30629 + }, + { + "epoch": 2.5, + "learning_rate": 3.360495436766624e-06, + "loss": 0.1344, + "step": 30630 + }, + { + "epoch": 2.5, + "learning_rate": 3.3599521946979573e-06, + "loss": 0.1841, + "step": 30631 + }, + { + "epoch": 2.5, + "learning_rate": 3.3594089526292915e-06, + "loss": 0.6193, + "step": 30632 + }, + { + "epoch": 2.5, + "learning_rate": 3.3588657105606258e-06, + "loss": 0.164, + "step": 30633 + }, + { + "epoch": 2.5, + "learning_rate": 3.35832246849196e-06, + "loss": 0.0693, + "step": 30634 + }, + { + "epoch": 2.5, + "learning_rate": 3.3577792264232946e-06, + "loss": 0.1103, + "step": 30635 + }, + { + "epoch": 2.5, + "learning_rate": 3.357235984354629e-06, + "loss": 0.1398, + "step": 30636 + }, + { + "epoch": 2.5, + "learning_rate": 3.356692742285963e-06, + "loss": 0.3905, + "step": 30637 + }, + { + "epoch": 2.5, + "learning_rate": 3.3561495002172973e-06, + "loss": 0.1486, + "step": 30638 + }, + { + "epoch": 2.5, + "learning_rate": 3.3556062581486316e-06, + "loss": 0.0756, + "step": 30639 + }, + { + "epoch": 2.5, + "learning_rate": 3.355063016079966e-06, + "loss": 0.0798, + "step": 30640 + }, + { + "epoch": 2.5, + "learning_rate": 3.3545197740112996e-06, + "loss": 0.1064, + "step": 30641 + }, + { + "epoch": 2.5, + "learning_rate": 3.353976531942634e-06, + "loss": 0.1014, + "step": 30642 + }, + { + "epoch": 2.5, + "learning_rate": 3.353433289873968e-06, + "loss": 0.2529, + "step": 30643 + }, + { + "epoch": 2.5, + "learning_rate": 3.3528900478053023e-06, + "loss": 0.2571, + "step": 30644 + }, + { + "epoch": 2.5, + "learning_rate": 3.3523468057366365e-06, + "loss": 0.0655, + "step": 30645 + }, + { + "epoch": 2.5, + "learning_rate": 3.3518035636679708e-06, + "loss": 0.0917, + "step": 30646 + }, + { + "epoch": 2.5, + "learning_rate": 3.351260321599305e-06, + "loss": 0.5091, + "step": 30647 + }, + { + "epoch": 2.5, + "learning_rate": 3.3507170795306392e-06, + "loss": 0.173, + "step": 30648 + }, + { + "epoch": 2.5, + "learning_rate": 3.3501738374619734e-06, + "loss": 0.1923, + "step": 30649 + }, + { + "epoch": 2.5, + "learning_rate": 3.3496305953933073e-06, + "loss": 0.138, + "step": 30650 + }, + { + "epoch": 2.5, + "learning_rate": 3.3490873533246415e-06, + "loss": 0.1833, + "step": 30651 + }, + { + "epoch": 2.5, + "learning_rate": 3.3485441112559757e-06, + "loss": 0.2499, + "step": 30652 + }, + { + "epoch": 2.5, + "learning_rate": 3.34800086918731e-06, + "loss": 0.1235, + "step": 30653 + }, + { + "epoch": 2.5, + "learning_rate": 3.347457627118644e-06, + "loss": 0.3604, + "step": 30654 + }, + { + "epoch": 2.5, + "learning_rate": 3.3469143850499784e-06, + "loss": 0.2603, + "step": 30655 + }, + { + "epoch": 2.5, + "learning_rate": 3.3463711429813126e-06, + "loss": 0.3979, + "step": 30656 + }, + { + "epoch": 2.5, + "learning_rate": 3.3458279009126473e-06, + "loss": 0.2424, + "step": 30657 + }, + { + "epoch": 2.5, + "learning_rate": 3.3452846588439815e-06, + "loss": 0.0762, + "step": 30658 + }, + { + "epoch": 2.5, + "learning_rate": 3.3447414167753158e-06, + "loss": 0.1603, + "step": 30659 + }, + { + "epoch": 2.5, + "learning_rate": 3.344198174706649e-06, + "loss": 0.0519, + "step": 30660 + }, + { + "epoch": 2.5, + "learning_rate": 3.3436549326379834e-06, + "loss": 0.2681, + "step": 30661 + }, + { + "epoch": 2.5, + "learning_rate": 3.343111690569318e-06, + "loss": 0.0331, + "step": 30662 + }, + { + "epoch": 2.5, + "learning_rate": 3.3425684485006523e-06, + "loss": 0.0796, + "step": 30663 + }, + { + "epoch": 2.5, + "learning_rate": 3.3420252064319865e-06, + "loss": 0.2186, + "step": 30664 + }, + { + "epoch": 2.5, + "learning_rate": 3.3414819643633207e-06, + "loss": 0.3762, + "step": 30665 + }, + { + "epoch": 2.5, + "learning_rate": 3.340938722294655e-06, + "loss": 0.1646, + "step": 30666 + }, + { + "epoch": 2.5, + "learning_rate": 3.340395480225989e-06, + "loss": 0.3351, + "step": 30667 + }, + { + "epoch": 2.5, + "learning_rate": 3.3398522381573234e-06, + "loss": 0.3129, + "step": 30668 + }, + { + "epoch": 2.5, + "learning_rate": 3.339308996088657e-06, + "loss": 0.1098, + "step": 30669 + }, + { + "epoch": 2.5, + "learning_rate": 3.3387657540199914e-06, + "loss": 0.2722, + "step": 30670 + }, + { + "epoch": 2.5, + "learning_rate": 3.3382225119513257e-06, + "loss": 0.2198, + "step": 30671 + }, + { + "epoch": 2.5, + "learning_rate": 3.33767926988266e-06, + "loss": 0.1239, + "step": 30672 + }, + { + "epoch": 2.5, + "learning_rate": 3.337136027813994e-06, + "loss": 0.2222, + "step": 30673 + }, + { + "epoch": 2.5, + "learning_rate": 3.3365927857453284e-06, + "loss": 0.4329, + "step": 30674 + }, + { + "epoch": 2.5, + "learning_rate": 3.3360495436766626e-06, + "loss": 0.3381, + "step": 30675 + }, + { + "epoch": 2.5, + "learning_rate": 3.335506301607997e-06, + "loss": 0.5052, + "step": 30676 + }, + { + "epoch": 2.5, + "learning_rate": 3.334963059539331e-06, + "loss": 0.1067, + "step": 30677 + }, + { + "epoch": 2.5, + "learning_rate": 3.3344198174706653e-06, + "loss": 0.1035, + "step": 30678 + }, + { + "epoch": 2.5, + "learning_rate": 3.333876575401999e-06, + "loss": 0.0847, + "step": 30679 + }, + { + "epoch": 2.5, + "learning_rate": 3.3333333333333333e-06, + "loss": 0.4739, + "step": 30680 + }, + { + "epoch": 2.5, + "learning_rate": 3.3327900912646676e-06, + "loss": 0.1987, + "step": 30681 + }, + { + "epoch": 2.5, + "learning_rate": 3.3322468491960018e-06, + "loss": 0.3657, + "step": 30682 + }, + { + "epoch": 2.5, + "learning_rate": 3.331703607127336e-06, + "loss": 0.125, + "step": 30683 + }, + { + "epoch": 2.5, + "learning_rate": 3.3311603650586707e-06, + "loss": 0.1339, + "step": 30684 + }, + { + "epoch": 2.5, + "learning_rate": 3.330617122990005e-06, + "loss": 0.474, + "step": 30685 + }, + { + "epoch": 2.5, + "learning_rate": 3.330073880921339e-06, + "loss": 0.1571, + "step": 30686 + }, + { + "epoch": 2.5, + "learning_rate": 3.3295306388526734e-06, + "loss": 0.3625, + "step": 30687 + }, + { + "epoch": 2.5, + "learning_rate": 3.3289873967840067e-06, + "loss": 0.0925, + "step": 30688 + }, + { + "epoch": 2.5, + "learning_rate": 3.3284441547153414e-06, + "loss": 0.3526, + "step": 30689 + }, + { + "epoch": 2.5, + "learning_rate": 3.3279009126466756e-06, + "loss": 0.275, + "step": 30690 + }, + { + "epoch": 2.5, + "learning_rate": 3.32735767057801e-06, + "loss": 0.2228, + "step": 30691 + }, + { + "epoch": 2.5, + "learning_rate": 3.326814428509344e-06, + "loss": 0.2898, + "step": 30692 + }, + { + "epoch": 2.5, + "learning_rate": 3.3262711864406783e-06, + "loss": 0.1117, + "step": 30693 + }, + { + "epoch": 2.5, + "learning_rate": 3.3257279443720126e-06, + "loss": 0.1319, + "step": 30694 + }, + { + "epoch": 2.5, + "learning_rate": 3.3251847023033468e-06, + "loss": 0.2077, + "step": 30695 + }, + { + "epoch": 2.5, + "learning_rate": 3.324641460234681e-06, + "loss": 0.1031, + "step": 30696 + }, + { + "epoch": 2.5, + "learning_rate": 3.3240982181660152e-06, + "loss": 0.2584, + "step": 30697 + }, + { + "epoch": 2.5, + "learning_rate": 3.323554976097349e-06, + "loss": 0.116, + "step": 30698 + }, + { + "epoch": 2.5, + "learning_rate": 3.3230117340286833e-06, + "loss": 0.2472, + "step": 30699 + }, + { + "epoch": 2.5, + "learning_rate": 3.3224684919600175e-06, + "loss": 0.1191, + "step": 30700 + }, + { + "epoch": 2.5, + "learning_rate": 3.3219252498913517e-06, + "loss": 0.3137, + "step": 30701 + }, + { + "epoch": 2.5, + "learning_rate": 3.321382007822686e-06, + "loss": 0.2729, + "step": 30702 + }, + { + "epoch": 2.5, + "learning_rate": 3.32083876575402e-06, + "loss": 0.4066, + "step": 30703 + }, + { + "epoch": 2.5, + "learning_rate": 3.3202955236853544e-06, + "loss": 0.191, + "step": 30704 + }, + { + "epoch": 2.5, + "learning_rate": 3.3197522816166887e-06, + "loss": 0.3032, + "step": 30705 + }, + { + "epoch": 2.5, + "learning_rate": 3.319209039548023e-06, + "loss": 0.0951, + "step": 30706 + }, + { + "epoch": 2.5, + "learning_rate": 3.3186657974793567e-06, + "loss": 0.1472, + "step": 30707 + }, + { + "epoch": 2.5, + "learning_rate": 3.318122555410691e-06, + "loss": 0.3402, + "step": 30708 + }, + { + "epoch": 2.5, + "learning_rate": 3.317579313342025e-06, + "loss": 0.1037, + "step": 30709 + }, + { + "epoch": 2.5, + "learning_rate": 3.3170360712733594e-06, + "loss": 0.228, + "step": 30710 + }, + { + "epoch": 2.5, + "learning_rate": 3.316492829204694e-06, + "loss": 0.244, + "step": 30711 + }, + { + "epoch": 2.5, + "learning_rate": 3.3159495871360283e-06, + "loss": 0.7551, + "step": 30712 + }, + { + "epoch": 2.5, + "learning_rate": 3.3154063450673625e-06, + "loss": 0.2401, + "step": 30713 + }, + { + "epoch": 2.5, + "learning_rate": 3.3148631029986967e-06, + "loss": 0.1516, + "step": 30714 + }, + { + "epoch": 2.5, + "learning_rate": 3.314319860930031e-06, + "loss": 0.2381, + "step": 30715 + }, + { + "epoch": 2.5, + "learning_rate": 3.313776618861365e-06, + "loss": 0.1902, + "step": 30716 + }, + { + "epoch": 2.5, + "learning_rate": 3.313233376792699e-06, + "loss": 0.2393, + "step": 30717 + }, + { + "epoch": 2.5, + "learning_rate": 3.3126901347240332e-06, + "loss": 0.2178, + "step": 30718 + }, + { + "epoch": 2.5, + "learning_rate": 3.3121468926553675e-06, + "loss": 0.2358, + "step": 30719 + }, + { + "epoch": 2.5, + "learning_rate": 3.3116036505867017e-06, + "loss": 0.3833, + "step": 30720 + }, + { + "epoch": 2.5, + "learning_rate": 3.311060408518036e-06, + "loss": 0.4377, + "step": 30721 + }, + { + "epoch": 2.5, + "learning_rate": 3.31051716644937e-06, + "loss": 0.1762, + "step": 30722 + }, + { + "epoch": 2.5, + "learning_rate": 3.3099739243807044e-06, + "loss": 0.2509, + "step": 30723 + }, + { + "epoch": 2.5, + "learning_rate": 3.3094306823120386e-06, + "loss": 0.2735, + "step": 30724 + }, + { + "epoch": 2.5, + "learning_rate": 3.308887440243373e-06, + "loss": 0.1038, + "step": 30725 + }, + { + "epoch": 2.5, + "learning_rate": 3.3083441981747067e-06, + "loss": 0.3677, + "step": 30726 + }, + { + "epoch": 2.5, + "learning_rate": 3.307800956106041e-06, + "loss": 0.2256, + "step": 30727 + }, + { + "epoch": 2.5, + "learning_rate": 3.307257714037375e-06, + "loss": 0.2488, + "step": 30728 + }, + { + "epoch": 2.5, + "learning_rate": 3.3067144719687093e-06, + "loss": 0.069, + "step": 30729 + }, + { + "epoch": 2.5, + "learning_rate": 3.3061712299000436e-06, + "loss": 0.0974, + "step": 30730 + }, + { + "epoch": 2.5, + "learning_rate": 3.305627987831378e-06, + "loss": 0.1395, + "step": 30731 + }, + { + "epoch": 2.5, + "learning_rate": 3.305084745762712e-06, + "loss": 0.0874, + "step": 30732 + }, + { + "epoch": 2.5, + "learning_rate": 3.3045415036940463e-06, + "loss": 0.2922, + "step": 30733 + }, + { + "epoch": 2.5, + "learning_rate": 3.303998261625381e-06, + "loss": 0.3102, + "step": 30734 + }, + { + "epoch": 2.5, + "learning_rate": 3.303455019556715e-06, + "loss": 0.0977, + "step": 30735 + }, + { + "epoch": 2.5, + "learning_rate": 3.3029117774880485e-06, + "loss": 0.1599, + "step": 30736 + }, + { + "epoch": 2.5, + "learning_rate": 3.3023685354193828e-06, + "loss": 0.3289, + "step": 30737 + }, + { + "epoch": 2.5, + "learning_rate": 3.3018252933507174e-06, + "loss": 0.3509, + "step": 30738 + }, + { + "epoch": 2.5, + "learning_rate": 3.3012820512820517e-06, + "loss": 0.0935, + "step": 30739 + }, + { + "epoch": 2.5, + "learning_rate": 3.300738809213386e-06, + "loss": 0.122, + "step": 30740 + }, + { + "epoch": 2.5, + "learning_rate": 3.30019556714472e-06, + "loss": 0.1861, + "step": 30741 + }, + { + "epoch": 2.51, + "learning_rate": 3.2996523250760543e-06, + "loss": 0.2146, + "step": 30742 + }, + { + "epoch": 2.51, + "learning_rate": 3.2991090830073886e-06, + "loss": 0.1919, + "step": 30743 + }, + { + "epoch": 2.51, + "learning_rate": 3.298565840938723e-06, + "loss": 0.2914, + "step": 30744 + }, + { + "epoch": 2.51, + "learning_rate": 3.2980225988700566e-06, + "loss": 0.3578, + "step": 30745 + }, + { + "epoch": 2.51, + "learning_rate": 3.297479356801391e-06, + "loss": 0.1033, + "step": 30746 + }, + { + "epoch": 2.51, + "learning_rate": 3.296936114732725e-06, + "loss": 0.1781, + "step": 30747 + }, + { + "epoch": 2.51, + "learning_rate": 3.2963928726640593e-06, + "loss": 0.1461, + "step": 30748 + }, + { + "epoch": 2.51, + "learning_rate": 3.2958496305953935e-06, + "loss": 0.097, + "step": 30749 + }, + { + "epoch": 2.51, + "learning_rate": 3.2953063885267278e-06, + "loss": 0.4043, + "step": 30750 + }, + { + "epoch": 2.51, + "eval_accuracy": 0.8398369842078451, + "eval_loss": 0.5076714158058167, + "eval_runtime": 22.196, + "eval_samples_per_second": 442.197, + "eval_steps_per_second": 3.469, + "step": 30750 + }, + { + "epoch": 2.51, + "learning_rate": 3.294763146458062e-06, + "loss": 0.3505, + "step": 30751 + }, + { + "epoch": 2.51, + "learning_rate": 3.2942199043893962e-06, + "loss": 0.2223, + "step": 30752 + }, + { + "epoch": 2.51, + "learning_rate": 3.2936766623207305e-06, + "loss": 0.2649, + "step": 30753 + }, + { + "epoch": 2.51, + "learning_rate": 3.2931334202520647e-06, + "loss": 0.1645, + "step": 30754 + }, + { + "epoch": 2.51, + "learning_rate": 3.2925901781833985e-06, + "loss": 0.4247, + "step": 30755 + }, + { + "epoch": 2.51, + "learning_rate": 3.2920469361147327e-06, + "loss": 0.2014, + "step": 30756 + }, + { + "epoch": 2.51, + "learning_rate": 3.291503694046067e-06, + "loss": 0.1708, + "step": 30757 + }, + { + "epoch": 2.51, + "learning_rate": 3.290960451977401e-06, + "loss": 0.3884, + "step": 30758 + }, + { + "epoch": 2.51, + "learning_rate": 3.2904172099087354e-06, + "loss": 0.3662, + "step": 30759 + }, + { + "epoch": 2.51, + "learning_rate": 3.2898739678400696e-06, + "loss": 0.2049, + "step": 30760 + }, + { + "epoch": 2.51, + "learning_rate": 3.2893307257714043e-06, + "loss": 0.1571, + "step": 30761 + }, + { + "epoch": 2.51, + "learning_rate": 3.2887874837027385e-06, + "loss": 0.1148, + "step": 30762 + }, + { + "epoch": 2.51, + "learning_rate": 3.2882442416340728e-06, + "loss": 0.1026, + "step": 30763 + }, + { + "epoch": 2.51, + "learning_rate": 3.287700999565406e-06, + "loss": 0.1206, + "step": 30764 + }, + { + "epoch": 2.51, + "learning_rate": 3.287157757496741e-06, + "loss": 0.1307, + "step": 30765 + }, + { + "epoch": 2.51, + "learning_rate": 3.286614515428075e-06, + "loss": 0.1924, + "step": 30766 + }, + { + "epoch": 2.51, + "learning_rate": 3.2860712733594093e-06, + "loss": 0.4167, + "step": 30767 + }, + { + "epoch": 2.51, + "learning_rate": 3.2855280312907435e-06, + "loss": 0.141, + "step": 30768 + }, + { + "epoch": 2.51, + "learning_rate": 3.2849847892220777e-06, + "loss": 0.1096, + "step": 30769 + }, + { + "epoch": 2.51, + "learning_rate": 3.284441547153412e-06, + "loss": 0.0973, + "step": 30770 + }, + { + "epoch": 2.51, + "learning_rate": 3.283898305084746e-06, + "loss": 0.1555, + "step": 30771 + }, + { + "epoch": 2.51, + "learning_rate": 3.2833550630160804e-06, + "loss": 0.2015, + "step": 30772 + }, + { + "epoch": 2.51, + "learning_rate": 3.2828118209474146e-06, + "loss": 0.3175, + "step": 30773 + }, + { + "epoch": 2.51, + "learning_rate": 3.2822685788787485e-06, + "loss": 0.283, + "step": 30774 + }, + { + "epoch": 2.51, + "learning_rate": 3.2817253368100827e-06, + "loss": 0.0305, + "step": 30775 + }, + { + "epoch": 2.51, + "learning_rate": 3.281182094741417e-06, + "loss": 0.3488, + "step": 30776 + }, + { + "epoch": 2.51, + "learning_rate": 3.280638852672751e-06, + "loss": 0.3173, + "step": 30777 + }, + { + "epoch": 2.51, + "learning_rate": 3.2800956106040854e-06, + "loss": 0.4895, + "step": 30778 + }, + { + "epoch": 2.51, + "learning_rate": 3.2795523685354196e-06, + "loss": 0.2049, + "step": 30779 + }, + { + "epoch": 2.51, + "learning_rate": 3.279009126466754e-06, + "loss": 0.2004, + "step": 30780 + }, + { + "epoch": 2.51, + "learning_rate": 3.278465884398088e-06, + "loss": 0.1559, + "step": 30781 + }, + { + "epoch": 2.51, + "learning_rate": 3.2779226423294223e-06, + "loss": 0.2682, + "step": 30782 + }, + { + "epoch": 2.51, + "learning_rate": 3.2773794002607565e-06, + "loss": 0.2154, + "step": 30783 + }, + { + "epoch": 2.51, + "learning_rate": 3.2768361581920903e-06, + "loss": 0.1702, + "step": 30784 + }, + { + "epoch": 2.51, + "learning_rate": 3.2762929161234246e-06, + "loss": 0.1064, + "step": 30785 + }, + { + "epoch": 2.51, + "learning_rate": 3.275749674054759e-06, + "loss": 0.188, + "step": 30786 + }, + { + "epoch": 2.51, + "learning_rate": 3.275206431986093e-06, + "loss": 0.3965, + "step": 30787 + }, + { + "epoch": 2.51, + "learning_rate": 3.2746631899174277e-06, + "loss": 0.1571, + "step": 30788 + }, + { + "epoch": 2.51, + "learning_rate": 3.274119947848762e-06, + "loss": 0.3902, + "step": 30789 + }, + { + "epoch": 2.51, + "learning_rate": 3.273576705780096e-06, + "loss": 0.0935, + "step": 30790 + }, + { + "epoch": 2.51, + "learning_rate": 3.2730334637114304e-06, + "loss": 0.3141, + "step": 30791 + }, + { + "epoch": 2.51, + "learning_rate": 3.2724902216427646e-06, + "loss": 0.1296, + "step": 30792 + }, + { + "epoch": 2.51, + "learning_rate": 3.2719469795740984e-06, + "loss": 0.1647, + "step": 30793 + }, + { + "epoch": 2.51, + "learning_rate": 3.2714037375054326e-06, + "loss": 0.2, + "step": 30794 + }, + { + "epoch": 2.51, + "learning_rate": 3.270860495436767e-06, + "loss": 0.2784, + "step": 30795 + }, + { + "epoch": 2.51, + "learning_rate": 3.270317253368101e-06, + "loss": 0.191, + "step": 30796 + }, + { + "epoch": 2.51, + "learning_rate": 3.2697740112994353e-06, + "loss": 0.5628, + "step": 30797 + }, + { + "epoch": 2.51, + "learning_rate": 3.2692307692307696e-06, + "loss": 0.2657, + "step": 30798 + }, + { + "epoch": 2.51, + "learning_rate": 3.268687527162104e-06, + "loss": 0.118, + "step": 30799 + }, + { + "epoch": 2.51, + "learning_rate": 3.268144285093438e-06, + "loss": 0.1999, + "step": 30800 + }, + { + "epoch": 2.51, + "learning_rate": 3.2676010430247723e-06, + "loss": 0.3315, + "step": 30801 + }, + { + "epoch": 2.51, + "learning_rate": 3.2670578009561065e-06, + "loss": 0.0735, + "step": 30802 + }, + { + "epoch": 2.51, + "learning_rate": 3.2665145588874403e-06, + "loss": 0.1243, + "step": 30803 + }, + { + "epoch": 2.51, + "learning_rate": 3.2659713168187745e-06, + "loss": 0.1813, + "step": 30804 + }, + { + "epoch": 2.51, + "learning_rate": 3.2654280747501088e-06, + "loss": 0.1934, + "step": 30805 + }, + { + "epoch": 2.51, + "learning_rate": 3.264884832681443e-06, + "loss": 0.3774, + "step": 30806 + }, + { + "epoch": 2.51, + "learning_rate": 3.2643415906127772e-06, + "loss": 0.2997, + "step": 30807 + }, + { + "epoch": 2.51, + "learning_rate": 3.2637983485441114e-06, + "loss": 0.1904, + "step": 30808 + }, + { + "epoch": 2.51, + "learning_rate": 3.2632551064754457e-06, + "loss": 0.1002, + "step": 30809 + }, + { + "epoch": 2.51, + "learning_rate": 3.26271186440678e-06, + "loss": 0.3354, + "step": 30810 + }, + { + "epoch": 2.51, + "learning_rate": 3.2621686223381146e-06, + "loss": 0.4722, + "step": 30811 + }, + { + "epoch": 2.51, + "learning_rate": 3.261625380269448e-06, + "loss": 0.2828, + "step": 30812 + }, + { + "epoch": 2.51, + "learning_rate": 3.261082138200782e-06, + "loss": 0.1906, + "step": 30813 + }, + { + "epoch": 2.51, + "learning_rate": 3.2605388961321164e-06, + "loss": 0.1237, + "step": 30814 + }, + { + "epoch": 2.51, + "learning_rate": 3.259995654063451e-06, + "loss": 0.2656, + "step": 30815 + }, + { + "epoch": 2.51, + "learning_rate": 3.2594524119947853e-06, + "loss": 0.1178, + "step": 30816 + }, + { + "epoch": 2.51, + "learning_rate": 3.2589091699261195e-06, + "loss": 0.0968, + "step": 30817 + }, + { + "epoch": 2.51, + "learning_rate": 3.2583659278574538e-06, + "loss": 0.2054, + "step": 30818 + }, + { + "epoch": 2.51, + "learning_rate": 3.257822685788788e-06, + "loss": 0.2113, + "step": 30819 + }, + { + "epoch": 2.51, + "learning_rate": 3.2572794437201222e-06, + "loss": 0.1684, + "step": 30820 + }, + { + "epoch": 2.51, + "learning_rate": 3.2567362016514564e-06, + "loss": 0.1733, + "step": 30821 + }, + { + "epoch": 2.51, + "learning_rate": 3.2561929595827902e-06, + "loss": 0.1856, + "step": 30822 + }, + { + "epoch": 2.51, + "learning_rate": 3.2556497175141245e-06, + "loss": 0.5569, + "step": 30823 + }, + { + "epoch": 2.51, + "learning_rate": 3.2551064754454587e-06, + "loss": 0.1792, + "step": 30824 + }, + { + "epoch": 2.51, + "learning_rate": 3.254563233376793e-06, + "loss": 0.2709, + "step": 30825 + }, + { + "epoch": 2.51, + "learning_rate": 3.254019991308127e-06, + "loss": 0.1773, + "step": 30826 + }, + { + "epoch": 2.51, + "learning_rate": 3.2534767492394614e-06, + "loss": 0.1934, + "step": 30827 + }, + { + "epoch": 2.51, + "learning_rate": 3.2529335071707956e-06, + "loss": 0.1749, + "step": 30828 + }, + { + "epoch": 2.51, + "learning_rate": 3.25239026510213e-06, + "loss": 0.1045, + "step": 30829 + }, + { + "epoch": 2.51, + "learning_rate": 3.251847023033464e-06, + "loss": 0.0318, + "step": 30830 + }, + { + "epoch": 2.51, + "learning_rate": 3.251303780964798e-06, + "loss": 0.1919, + "step": 30831 + }, + { + "epoch": 2.51, + "learning_rate": 3.250760538896132e-06, + "loss": 0.3048, + "step": 30832 + }, + { + "epoch": 2.51, + "learning_rate": 3.2502172968274664e-06, + "loss": 0.1999, + "step": 30833 + }, + { + "epoch": 2.51, + "learning_rate": 3.2496740547588006e-06, + "loss": 0.0664, + "step": 30834 + }, + { + "epoch": 2.51, + "learning_rate": 3.249130812690135e-06, + "loss": 0.1645, + "step": 30835 + }, + { + "epoch": 2.51, + "learning_rate": 3.248587570621469e-06, + "loss": 0.322, + "step": 30836 + }, + { + "epoch": 2.51, + "learning_rate": 3.2480443285528033e-06, + "loss": 0.0934, + "step": 30837 + }, + { + "epoch": 2.51, + "learning_rate": 3.247501086484138e-06, + "loss": 0.3442, + "step": 30838 + }, + { + "epoch": 2.51, + "learning_rate": 3.246957844415472e-06, + "loss": 0.2463, + "step": 30839 + }, + { + "epoch": 2.51, + "learning_rate": 3.2464146023468064e-06, + "loss": 0.1945, + "step": 30840 + }, + { + "epoch": 2.51, + "learning_rate": 3.2458713602781398e-06, + "loss": 0.1766, + "step": 30841 + }, + { + "epoch": 2.51, + "learning_rate": 3.2453281182094744e-06, + "loss": 0.3141, + "step": 30842 + }, + { + "epoch": 2.51, + "learning_rate": 3.2447848761408087e-06, + "loss": 0.1844, + "step": 30843 + }, + { + "epoch": 2.51, + "learning_rate": 3.244241634072143e-06, + "loss": 0.0693, + "step": 30844 + }, + { + "epoch": 2.51, + "learning_rate": 3.243698392003477e-06, + "loss": 0.2269, + "step": 30845 + }, + { + "epoch": 2.51, + "learning_rate": 3.2431551499348114e-06, + "loss": 0.1676, + "step": 30846 + }, + { + "epoch": 2.51, + "learning_rate": 3.2426119078661456e-06, + "loss": 0.2543, + "step": 30847 + }, + { + "epoch": 2.51, + "learning_rate": 3.24206866579748e-06, + "loss": 0.1844, + "step": 30848 + }, + { + "epoch": 2.51, + "learning_rate": 3.241525423728814e-06, + "loss": 0.2043, + "step": 30849 + }, + { + "epoch": 2.51, + "learning_rate": 3.240982181660148e-06, + "loss": 0.3942, + "step": 30850 + }, + { + "epoch": 2.51, + "learning_rate": 3.240438939591482e-06, + "loss": 0.3152, + "step": 30851 + }, + { + "epoch": 2.51, + "learning_rate": 3.2398956975228163e-06, + "loss": 0.2411, + "step": 30852 + }, + { + "epoch": 2.51, + "learning_rate": 3.2393524554541505e-06, + "loss": 0.2461, + "step": 30853 + }, + { + "epoch": 2.51, + "learning_rate": 3.2388092133854848e-06, + "loss": 0.1083, + "step": 30854 + }, + { + "epoch": 2.51, + "learning_rate": 3.238265971316819e-06, + "loss": 0.0724, + "step": 30855 + }, + { + "epoch": 2.51, + "learning_rate": 3.2377227292481532e-06, + "loss": 0.0982, + "step": 30856 + }, + { + "epoch": 2.51, + "learning_rate": 3.2371794871794875e-06, + "loss": 0.1756, + "step": 30857 + }, + { + "epoch": 2.51, + "learning_rate": 3.2366362451108217e-06, + "loss": 0.1301, + "step": 30858 + }, + { + "epoch": 2.51, + "learning_rate": 3.236093003042156e-06, + "loss": 0.293, + "step": 30859 + }, + { + "epoch": 2.51, + "learning_rate": 3.2355497609734897e-06, + "loss": 0.2811, + "step": 30860 + }, + { + "epoch": 2.51, + "learning_rate": 3.235006518904824e-06, + "loss": 0.1621, + "step": 30861 + }, + { + "epoch": 2.51, + "learning_rate": 3.234463276836158e-06, + "loss": 0.3298, + "step": 30862 + }, + { + "epoch": 2.51, + "learning_rate": 3.2339200347674924e-06, + "loss": 0.1612, + "step": 30863 + }, + { + "epoch": 2.51, + "learning_rate": 3.2333767926988267e-06, + "loss": 0.3752, + "step": 30864 + }, + { + "epoch": 2.52, + "learning_rate": 3.2328335506301613e-06, + "loss": 0.434, + "step": 30865 + }, + { + "epoch": 2.52, + "learning_rate": 3.2322903085614955e-06, + "loss": 0.2624, + "step": 30866 + }, + { + "epoch": 2.52, + "learning_rate": 3.2317470664928298e-06, + "loss": 0.4076, + "step": 30867 + }, + { + "epoch": 2.52, + "learning_rate": 3.231203824424164e-06, + "loss": 0.1549, + "step": 30868 + }, + { + "epoch": 2.52, + "learning_rate": 3.230660582355498e-06, + "loss": 0.1143, + "step": 30869 + }, + { + "epoch": 2.52, + "learning_rate": 3.230117340286832e-06, + "loss": 0.1383, + "step": 30870 + }, + { + "epoch": 2.52, + "learning_rate": 3.2295740982181663e-06, + "loss": 0.1865, + "step": 30871 + }, + { + "epoch": 2.52, + "learning_rate": 3.2290308561495005e-06, + "loss": 0.3136, + "step": 30872 + }, + { + "epoch": 2.52, + "learning_rate": 3.2284876140808347e-06, + "loss": 0.1922, + "step": 30873 + }, + { + "epoch": 2.52, + "learning_rate": 3.227944372012169e-06, + "loss": 0.1146, + "step": 30874 + }, + { + "epoch": 2.52, + "learning_rate": 3.227401129943503e-06, + "loss": 0.2919, + "step": 30875 + }, + { + "epoch": 2.52, + "learning_rate": 3.2268578878748374e-06, + "loss": 0.5198, + "step": 30876 + }, + { + "epoch": 2.52, + "learning_rate": 3.2263146458061717e-06, + "loss": 0.2824, + "step": 30877 + }, + { + "epoch": 2.52, + "learning_rate": 3.225771403737506e-06, + "loss": 0.3208, + "step": 30878 + }, + { + "epoch": 2.52, + "learning_rate": 3.2252281616688397e-06, + "loss": 0.2619, + "step": 30879 + }, + { + "epoch": 2.52, + "learning_rate": 3.224684919600174e-06, + "loss": 0.1762, + "step": 30880 + }, + { + "epoch": 2.52, + "learning_rate": 3.224141677531508e-06, + "loss": 0.1653, + "step": 30881 + }, + { + "epoch": 2.52, + "learning_rate": 3.2235984354628424e-06, + "loss": 0.1597, + "step": 30882 + }, + { + "epoch": 2.52, + "learning_rate": 3.2230551933941766e-06, + "loss": 0.0637, + "step": 30883 + }, + { + "epoch": 2.52, + "learning_rate": 3.222511951325511e-06, + "loss": 0.2992, + "step": 30884 + }, + { + "epoch": 2.52, + "learning_rate": 3.221968709256845e-06, + "loss": 0.1051, + "step": 30885 + }, + { + "epoch": 2.52, + "learning_rate": 3.2214254671881793e-06, + "loss": 0.2237, + "step": 30886 + }, + { + "epoch": 2.52, + "learning_rate": 3.220882225119514e-06, + "loss": 0.0655, + "step": 30887 + }, + { + "epoch": 2.52, + "learning_rate": 3.2203389830508473e-06, + "loss": 0.3279, + "step": 30888 + }, + { + "epoch": 2.52, + "learning_rate": 3.2197957409821816e-06, + "loss": 0.0483, + "step": 30889 + }, + { + "epoch": 2.52, + "learning_rate": 3.219252498913516e-06, + "loss": 0.0687, + "step": 30890 + }, + { + "epoch": 2.52, + "learning_rate": 3.21870925684485e-06, + "loss": 0.1323, + "step": 30891 + }, + { + "epoch": 2.52, + "learning_rate": 3.2181660147761847e-06, + "loss": 0.2682, + "step": 30892 + }, + { + "epoch": 2.52, + "learning_rate": 3.217622772707519e-06, + "loss": 0.3581, + "step": 30893 + }, + { + "epoch": 2.52, + "learning_rate": 3.217079530638853e-06, + "loss": 0.1788, + "step": 30894 + }, + { + "epoch": 2.52, + "learning_rate": 3.2165362885701874e-06, + "loss": 0.3897, + "step": 30895 + }, + { + "epoch": 2.52, + "learning_rate": 3.2159930465015216e-06, + "loss": 0.3887, + "step": 30896 + }, + { + "epoch": 2.52, + "learning_rate": 3.215449804432856e-06, + "loss": 0.2561, + "step": 30897 + }, + { + "epoch": 2.52, + "learning_rate": 3.2149065623641897e-06, + "loss": 0.1857, + "step": 30898 + }, + { + "epoch": 2.52, + "learning_rate": 3.214363320295524e-06, + "loss": 0.2653, + "step": 30899 + }, + { + "epoch": 2.52, + "learning_rate": 3.213820078226858e-06, + "loss": 0.1809, + "step": 30900 + }, + { + "epoch": 2.52, + "learning_rate": 3.2132768361581923e-06, + "loss": 0.4375, + "step": 30901 + }, + { + "epoch": 2.52, + "learning_rate": 3.2127335940895266e-06, + "loss": 0.1893, + "step": 30902 + }, + { + "epoch": 2.52, + "learning_rate": 3.212190352020861e-06, + "loss": 0.3812, + "step": 30903 + }, + { + "epoch": 2.52, + "learning_rate": 3.211647109952195e-06, + "loss": 0.0542, + "step": 30904 + }, + { + "epoch": 2.52, + "learning_rate": 3.2111038678835293e-06, + "loss": 0.0246, + "step": 30905 + }, + { + "epoch": 2.52, + "learning_rate": 3.2105606258148635e-06, + "loss": 0.2866, + "step": 30906 + }, + { + "epoch": 2.52, + "learning_rate": 3.2100173837461973e-06, + "loss": 0.1223, + "step": 30907 + }, + { + "epoch": 2.52, + "learning_rate": 3.2094741416775315e-06, + "loss": 0.3951, + "step": 30908 + }, + { + "epoch": 2.52, + "learning_rate": 3.2089308996088658e-06, + "loss": 0.1138, + "step": 30909 + }, + { + "epoch": 2.52, + "learning_rate": 3.2083876575402e-06, + "loss": 0.1563, + "step": 30910 + }, + { + "epoch": 2.52, + "learning_rate": 3.2078444154715342e-06, + "loss": 0.4907, + "step": 30911 + }, + { + "epoch": 2.52, + "learning_rate": 3.2073011734028685e-06, + "loss": 0.1314, + "step": 30912 + }, + { + "epoch": 2.52, + "learning_rate": 3.2067579313342027e-06, + "loss": 0.3764, + "step": 30913 + }, + { + "epoch": 2.52, + "learning_rate": 3.2062146892655373e-06, + "loss": 0.0773, + "step": 30914 + }, + { + "epoch": 2.52, + "learning_rate": 3.2056714471968716e-06, + "loss": 0.3027, + "step": 30915 + }, + { + "epoch": 2.52, + "learning_rate": 3.205128205128206e-06, + "loss": 0.1925, + "step": 30916 + }, + { + "epoch": 2.52, + "learning_rate": 3.204584963059539e-06, + "loss": 0.3413, + "step": 30917 + }, + { + "epoch": 2.52, + "learning_rate": 3.2040417209908734e-06, + "loss": 0.2406, + "step": 30918 + }, + { + "epoch": 2.52, + "learning_rate": 3.203498478922208e-06, + "loss": 0.2852, + "step": 30919 + }, + { + "epoch": 2.52, + "learning_rate": 3.2029552368535423e-06, + "loss": 0.2304, + "step": 30920 + }, + { + "epoch": 2.52, + "learning_rate": 3.2024119947848765e-06, + "loss": 0.2336, + "step": 30921 + }, + { + "epoch": 2.52, + "learning_rate": 3.2018687527162108e-06, + "loss": 0.1781, + "step": 30922 + }, + { + "epoch": 2.52, + "learning_rate": 3.201325510647545e-06, + "loss": 0.2482, + "step": 30923 + }, + { + "epoch": 2.52, + "learning_rate": 3.2007822685788792e-06, + "loss": 0.0905, + "step": 30924 + }, + { + "epoch": 2.52, + "learning_rate": 3.2002390265102135e-06, + "loss": 0.1494, + "step": 30925 + }, + { + "epoch": 2.52, + "learning_rate": 3.1996957844415473e-06, + "loss": 0.3025, + "step": 30926 + }, + { + "epoch": 2.52, + "learning_rate": 3.1991525423728815e-06, + "loss": 0.2756, + "step": 30927 + }, + { + "epoch": 2.52, + "learning_rate": 3.1986093003042157e-06, + "loss": 0.5086, + "step": 30928 + }, + { + "epoch": 2.52, + "learning_rate": 3.19806605823555e-06, + "loss": 0.1915, + "step": 30929 + }, + { + "epoch": 2.52, + "learning_rate": 3.197522816166884e-06, + "loss": 0.2033, + "step": 30930 + }, + { + "epoch": 2.52, + "learning_rate": 3.1969795740982184e-06, + "loss": 0.3138, + "step": 30931 + }, + { + "epoch": 2.52, + "learning_rate": 3.1964363320295526e-06, + "loss": 0.2608, + "step": 30932 + }, + { + "epoch": 2.52, + "learning_rate": 3.195893089960887e-06, + "loss": 0.171, + "step": 30933 + }, + { + "epoch": 2.52, + "learning_rate": 3.195349847892221e-06, + "loss": 0.0571, + "step": 30934 + }, + { + "epoch": 2.52, + "learning_rate": 3.1948066058235553e-06, + "loss": 0.0676, + "step": 30935 + }, + { + "epoch": 2.52, + "learning_rate": 3.194263363754889e-06, + "loss": 0.7054, + "step": 30936 + }, + { + "epoch": 2.52, + "learning_rate": 3.1937201216862234e-06, + "loss": 0.1928, + "step": 30937 + }, + { + "epoch": 2.52, + "learning_rate": 3.1931768796175576e-06, + "loss": 0.1399, + "step": 30938 + }, + { + "epoch": 2.52, + "learning_rate": 3.192633637548892e-06, + "loss": 0.245, + "step": 30939 + }, + { + "epoch": 2.52, + "learning_rate": 3.192090395480226e-06, + "loss": 0.2891, + "step": 30940 + }, + { + "epoch": 2.52, + "learning_rate": 3.1915471534115607e-06, + "loss": 0.3745, + "step": 30941 + }, + { + "epoch": 2.52, + "learning_rate": 3.191003911342895e-06, + "loss": 0.5475, + "step": 30942 + }, + { + "epoch": 2.52, + "learning_rate": 3.190460669274229e-06, + "loss": 0.306, + "step": 30943 + }, + { + "epoch": 2.52, + "learning_rate": 3.1899174272055634e-06, + "loss": 0.326, + "step": 30944 + }, + { + "epoch": 2.52, + "learning_rate": 3.189374185136897e-06, + "loss": 0.292, + "step": 30945 + }, + { + "epoch": 2.52, + "learning_rate": 3.1888309430682314e-06, + "loss": 0.3291, + "step": 30946 + }, + { + "epoch": 2.52, + "learning_rate": 3.1882877009995657e-06, + "loss": 0.201, + "step": 30947 + }, + { + "epoch": 2.52, + "learning_rate": 3.1877444589309e-06, + "loss": 0.1626, + "step": 30948 + }, + { + "epoch": 2.52, + "learning_rate": 3.187201216862234e-06, + "loss": 0.1269, + "step": 30949 + }, + { + "epoch": 2.52, + "learning_rate": 3.1866579747935684e-06, + "loss": 0.2022, + "step": 30950 + }, + { + "epoch": 2.52, + "learning_rate": 3.1861147327249026e-06, + "loss": 0.4393, + "step": 30951 + }, + { + "epoch": 2.52, + "learning_rate": 3.185571490656237e-06, + "loss": 0.2661, + "step": 30952 + }, + { + "epoch": 2.52, + "learning_rate": 3.185028248587571e-06, + "loss": 0.0795, + "step": 30953 + }, + { + "epoch": 2.52, + "learning_rate": 3.1844850065189053e-06, + "loss": 0.532, + "step": 30954 + }, + { + "epoch": 2.52, + "learning_rate": 3.183941764450239e-06, + "loss": 0.2733, + "step": 30955 + }, + { + "epoch": 2.52, + "learning_rate": 3.1833985223815733e-06, + "loss": 0.0557, + "step": 30956 + }, + { + "epoch": 2.52, + "learning_rate": 3.1828552803129076e-06, + "loss": 0.33, + "step": 30957 + }, + { + "epoch": 2.52, + "learning_rate": 3.182312038244242e-06, + "loss": 0.1396, + "step": 30958 + }, + { + "epoch": 2.52, + "learning_rate": 3.181768796175576e-06, + "loss": 0.1594, + "step": 30959 + }, + { + "epoch": 2.52, + "learning_rate": 3.1812255541069103e-06, + "loss": 0.5197, + "step": 30960 + }, + { + "epoch": 2.52, + "learning_rate": 3.1806823120382445e-06, + "loss": 0.165, + "step": 30961 + }, + { + "epoch": 2.52, + "learning_rate": 3.1801390699695787e-06, + "loss": 0.1792, + "step": 30962 + }, + { + "epoch": 2.52, + "learning_rate": 3.179595827900913e-06, + "loss": 0.1563, + "step": 30963 + }, + { + "epoch": 2.52, + "learning_rate": 3.1790525858322468e-06, + "loss": 0.1922, + "step": 30964 + }, + { + "epoch": 2.52, + "learning_rate": 3.178509343763581e-06, + "loss": 0.4142, + "step": 30965 + }, + { + "epoch": 2.52, + "learning_rate": 3.1779661016949152e-06, + "loss": 0.0561, + "step": 30966 + }, + { + "epoch": 2.52, + "learning_rate": 3.1774228596262494e-06, + "loss": 0.0752, + "step": 30967 + }, + { + "epoch": 2.52, + "learning_rate": 3.176879617557584e-06, + "loss": 0.1297, + "step": 30968 + }, + { + "epoch": 2.52, + "learning_rate": 3.1763363754889183e-06, + "loss": 0.2943, + "step": 30969 + }, + { + "epoch": 2.52, + "learning_rate": 3.1757931334202526e-06, + "loss": 0.1137, + "step": 30970 + }, + { + "epoch": 2.52, + "learning_rate": 3.175249891351587e-06, + "loss": 0.3364, + "step": 30971 + }, + { + "epoch": 2.52, + "learning_rate": 3.174706649282921e-06, + "loss": 0.2769, + "step": 30972 + }, + { + "epoch": 2.52, + "learning_rate": 3.1741634072142553e-06, + "loss": 0.2014, + "step": 30973 + }, + { + "epoch": 2.52, + "learning_rate": 3.173620165145589e-06, + "loss": 0.2849, + "step": 30974 + }, + { + "epoch": 2.52, + "learning_rate": 3.1730769230769233e-06, + "loss": 0.5714, + "step": 30975 + }, + { + "epoch": 2.52, + "learning_rate": 3.1725336810082575e-06, + "loss": 0.3581, + "step": 30976 + }, + { + "epoch": 2.52, + "learning_rate": 3.1719904389395917e-06, + "loss": 0.1433, + "step": 30977 + }, + { + "epoch": 2.52, + "learning_rate": 3.171447196870926e-06, + "loss": 0.2014, + "step": 30978 + }, + { + "epoch": 2.52, + "learning_rate": 3.17090395480226e-06, + "loss": 0.1282, + "step": 30979 + }, + { + "epoch": 2.52, + "learning_rate": 3.1703607127335944e-06, + "loss": 0.1974, + "step": 30980 + }, + { + "epoch": 2.52, + "learning_rate": 3.1698174706649287e-06, + "loss": 0.0882, + "step": 30981 + }, + { + "epoch": 2.52, + "learning_rate": 3.169274228596263e-06, + "loss": 0.1123, + "step": 30982 + }, + { + "epoch": 2.52, + "learning_rate": 3.1687309865275967e-06, + "loss": 0.3031, + "step": 30983 + }, + { + "epoch": 2.52, + "learning_rate": 3.168187744458931e-06, + "loss": 0.1122, + "step": 30984 + }, + { + "epoch": 2.52, + "learning_rate": 3.167644502390265e-06, + "loss": 0.2699, + "step": 30985 + }, + { + "epoch": 2.52, + "learning_rate": 3.1671012603215994e-06, + "loss": 0.3949, + "step": 30986 + }, + { + "epoch": 2.53, + "learning_rate": 3.1665580182529336e-06, + "loss": 0.092, + "step": 30987 + }, + { + "epoch": 2.53, + "learning_rate": 3.166014776184268e-06, + "loss": 0.0921, + "step": 30988 + }, + { + "epoch": 2.53, + "learning_rate": 3.165471534115602e-06, + "loss": 0.3169, + "step": 30989 + }, + { + "epoch": 2.53, + "learning_rate": 3.1649282920469363e-06, + "loss": 0.3445, + "step": 30990 + }, + { + "epoch": 2.53, + "learning_rate": 3.164385049978271e-06, + "loss": 0.1888, + "step": 30991 + }, + { + "epoch": 2.53, + "learning_rate": 3.163841807909605e-06, + "loss": 0.4055, + "step": 30992 + }, + { + "epoch": 2.53, + "learning_rate": 3.1632985658409386e-06, + "loss": 0.2744, + "step": 30993 + }, + { + "epoch": 2.53, + "learning_rate": 3.162755323772273e-06, + "loss": 0.1055, + "step": 30994 + }, + { + "epoch": 2.53, + "learning_rate": 3.1622120817036075e-06, + "loss": 0.155, + "step": 30995 + }, + { + "epoch": 2.53, + "learning_rate": 3.1616688396349417e-06, + "loss": 0.6411, + "step": 30996 + }, + { + "epoch": 2.53, + "learning_rate": 3.161125597566276e-06, + "loss": 0.3014, + "step": 30997 + }, + { + "epoch": 2.53, + "learning_rate": 3.16058235549761e-06, + "loss": 0.2517, + "step": 30998 + }, + { + "epoch": 2.53, + "learning_rate": 3.1600391134289444e-06, + "loss": 0.1208, + "step": 30999 + }, + { + "epoch": 2.53, + "learning_rate": 3.1594958713602786e-06, + "loss": 0.3543, + "step": 31000 + }, + { + "epoch": 2.53, + "eval_accuracy": 0.8440142638818136, + "eval_loss": 0.48775994777679443, + "eval_runtime": 22.2408, + "eval_samples_per_second": 441.306, + "eval_steps_per_second": 3.462, + "step": 31000 + }, + { + "epoch": 2.53, + "learning_rate": 3.158952629291613e-06, + "loss": 0.1011, + "step": 31001 + }, + { + "epoch": 2.53, + "learning_rate": 3.1584093872229467e-06, + "loss": 0.1506, + "step": 31002 + }, + { + "epoch": 2.53, + "learning_rate": 3.157866145154281e-06, + "loss": 0.3257, + "step": 31003 + }, + { + "epoch": 2.53, + "learning_rate": 3.157322903085615e-06, + "loss": 0.3377, + "step": 31004 + }, + { + "epoch": 2.53, + "learning_rate": 3.1567796610169494e-06, + "loss": 0.3473, + "step": 31005 + }, + { + "epoch": 2.53, + "learning_rate": 3.1562364189482836e-06, + "loss": 0.2804, + "step": 31006 + }, + { + "epoch": 2.53, + "learning_rate": 3.155693176879618e-06, + "loss": 0.2036, + "step": 31007 + }, + { + "epoch": 2.53, + "learning_rate": 3.155149934810952e-06, + "loss": 0.171, + "step": 31008 + }, + { + "epoch": 2.53, + "learning_rate": 3.1546066927422863e-06, + "loss": 0.0589, + "step": 31009 + }, + { + "epoch": 2.53, + "learning_rate": 3.1540634506736205e-06, + "loss": 0.1942, + "step": 31010 + }, + { + "epoch": 2.53, + "learning_rate": 3.1535202086049547e-06, + "loss": 0.1613, + "step": 31011 + }, + { + "epoch": 2.53, + "learning_rate": 3.1529769665362885e-06, + "loss": 0.3616, + "step": 31012 + }, + { + "epoch": 2.53, + "learning_rate": 3.1524337244676228e-06, + "loss": 0.5593, + "step": 31013 + }, + { + "epoch": 2.53, + "learning_rate": 3.151890482398957e-06, + "loss": 0.2823, + "step": 31014 + }, + { + "epoch": 2.53, + "learning_rate": 3.1513472403302912e-06, + "loss": 0.2781, + "step": 31015 + }, + { + "epoch": 2.53, + "learning_rate": 3.1508039982616255e-06, + "loss": 0.4903, + "step": 31016 + }, + { + "epoch": 2.53, + "learning_rate": 3.1502607561929597e-06, + "loss": 0.3339, + "step": 31017 + }, + { + "epoch": 2.53, + "learning_rate": 3.1497175141242944e-06, + "loss": 0.3241, + "step": 31018 + }, + { + "epoch": 2.53, + "learning_rate": 3.1491742720556286e-06, + "loss": 0.1648, + "step": 31019 + }, + { + "epoch": 2.53, + "learning_rate": 3.148631029986963e-06, + "loss": 0.0697, + "step": 31020 + }, + { + "epoch": 2.53, + "learning_rate": 3.148087787918296e-06, + "loss": 0.1865, + "step": 31021 + }, + { + "epoch": 2.53, + "learning_rate": 3.147544545849631e-06, + "loss": 0.2154, + "step": 31022 + }, + { + "epoch": 2.53, + "learning_rate": 3.147001303780965e-06, + "loss": 0.1171, + "step": 31023 + }, + { + "epoch": 2.53, + "learning_rate": 3.1464580617122993e-06, + "loss": 0.0878, + "step": 31024 + }, + { + "epoch": 2.53, + "learning_rate": 3.1459148196436335e-06, + "loss": 0.491, + "step": 31025 + }, + { + "epoch": 2.53, + "learning_rate": 3.1453715775749678e-06, + "loss": 0.0603, + "step": 31026 + }, + { + "epoch": 2.53, + "learning_rate": 3.144828335506302e-06, + "loss": 0.1461, + "step": 31027 + }, + { + "epoch": 2.53, + "learning_rate": 3.1442850934376362e-06, + "loss": 0.1757, + "step": 31028 + }, + { + "epoch": 2.53, + "learning_rate": 3.1437418513689705e-06, + "loss": 0.3191, + "step": 31029 + }, + { + "epoch": 2.53, + "learning_rate": 3.1431986093003047e-06, + "loss": 0.5009, + "step": 31030 + }, + { + "epoch": 2.53, + "learning_rate": 3.1426553672316385e-06, + "loss": 0.1269, + "step": 31031 + }, + { + "epoch": 2.53, + "learning_rate": 3.1421121251629727e-06, + "loss": 0.1803, + "step": 31032 + }, + { + "epoch": 2.53, + "learning_rate": 3.141568883094307e-06, + "loss": 0.1991, + "step": 31033 + }, + { + "epoch": 2.53, + "learning_rate": 3.141025641025641e-06, + "loss": 0.1343, + "step": 31034 + }, + { + "epoch": 2.53, + "learning_rate": 3.1404823989569754e-06, + "loss": 0.0664, + "step": 31035 + }, + { + "epoch": 2.53, + "learning_rate": 3.1399391568883097e-06, + "loss": 0.1677, + "step": 31036 + }, + { + "epoch": 2.53, + "learning_rate": 3.139395914819644e-06, + "loss": 0.3358, + "step": 31037 + }, + { + "epoch": 2.53, + "learning_rate": 3.138852672750978e-06, + "loss": 0.1567, + "step": 31038 + }, + { + "epoch": 2.53, + "learning_rate": 3.1383094306823123e-06, + "loss": 0.1984, + "step": 31039 + }, + { + "epoch": 2.53, + "learning_rate": 3.137766188613646e-06, + "loss": 0.1199, + "step": 31040 + }, + { + "epoch": 2.53, + "learning_rate": 3.1372229465449804e-06, + "loss": 0.3818, + "step": 31041 + }, + { + "epoch": 2.53, + "learning_rate": 3.1366797044763146e-06, + "loss": 0.1803, + "step": 31042 + }, + { + "epoch": 2.53, + "learning_rate": 3.136136462407649e-06, + "loss": 0.2455, + "step": 31043 + }, + { + "epoch": 2.53, + "learning_rate": 3.135593220338983e-06, + "loss": 0.2402, + "step": 31044 + }, + { + "epoch": 2.53, + "learning_rate": 3.1350499782703177e-06, + "loss": 0.0824, + "step": 31045 + }, + { + "epoch": 2.53, + "learning_rate": 3.134506736201652e-06, + "loss": 0.3851, + "step": 31046 + }, + { + "epoch": 2.53, + "learning_rate": 3.133963494132986e-06, + "loss": 0.4327, + "step": 31047 + }, + { + "epoch": 2.53, + "learning_rate": 3.1334202520643204e-06, + "loss": 0.1968, + "step": 31048 + }, + { + "epoch": 2.53, + "learning_rate": 3.1328770099956547e-06, + "loss": 0.3744, + "step": 31049 + }, + { + "epoch": 2.53, + "learning_rate": 3.1323337679269885e-06, + "loss": 0.1474, + "step": 31050 + }, + { + "epoch": 2.53, + "learning_rate": 3.1317905258583227e-06, + "loss": 0.3161, + "step": 31051 + }, + { + "epoch": 2.53, + "learning_rate": 3.131247283789657e-06, + "loss": 0.2554, + "step": 31052 + }, + { + "epoch": 2.53, + "learning_rate": 3.130704041720991e-06, + "loss": 0.4784, + "step": 31053 + }, + { + "epoch": 2.53, + "learning_rate": 3.1301607996523254e-06, + "loss": 0.1806, + "step": 31054 + }, + { + "epoch": 2.53, + "learning_rate": 3.1296175575836596e-06, + "loss": 0.3742, + "step": 31055 + }, + { + "epoch": 2.53, + "learning_rate": 3.129074315514994e-06, + "loss": 0.1784, + "step": 31056 + }, + { + "epoch": 2.53, + "learning_rate": 3.128531073446328e-06, + "loss": 0.188, + "step": 31057 + }, + { + "epoch": 2.53, + "learning_rate": 3.1279878313776623e-06, + "loss": 0.2423, + "step": 31058 + }, + { + "epoch": 2.53, + "learning_rate": 3.127444589308996e-06, + "loss": 0.2408, + "step": 31059 + }, + { + "epoch": 2.53, + "learning_rate": 3.1269013472403303e-06, + "loss": 0.1026, + "step": 31060 + }, + { + "epoch": 2.53, + "learning_rate": 3.1263581051716646e-06, + "loss": 0.14, + "step": 31061 + }, + { + "epoch": 2.53, + "learning_rate": 3.125814863102999e-06, + "loss": 0.1667, + "step": 31062 + }, + { + "epoch": 2.53, + "learning_rate": 3.125271621034333e-06, + "loss": 0.2071, + "step": 31063 + }, + { + "epoch": 2.53, + "learning_rate": 3.1247283789656673e-06, + "loss": 0.0962, + "step": 31064 + }, + { + "epoch": 2.53, + "learning_rate": 3.1241851368970015e-06, + "loss": 0.1871, + "step": 31065 + }, + { + "epoch": 2.53, + "learning_rate": 3.1236418948283357e-06, + "loss": 0.1721, + "step": 31066 + }, + { + "epoch": 2.53, + "learning_rate": 3.1230986527596704e-06, + "loss": 0.1794, + "step": 31067 + }, + { + "epoch": 2.53, + "learning_rate": 3.1225554106910046e-06, + "loss": 0.0945, + "step": 31068 + }, + { + "epoch": 2.53, + "learning_rate": 3.122012168622338e-06, + "loss": 0.3429, + "step": 31069 + }, + { + "epoch": 2.53, + "learning_rate": 3.1214689265536722e-06, + "loss": 0.2176, + "step": 31070 + }, + { + "epoch": 2.53, + "learning_rate": 3.1209256844850065e-06, + "loss": 0.3319, + "step": 31071 + }, + { + "epoch": 2.53, + "learning_rate": 3.120382442416341e-06, + "loss": 0.3068, + "step": 31072 + }, + { + "epoch": 2.53, + "learning_rate": 3.1198392003476753e-06, + "loss": 0.3927, + "step": 31073 + }, + { + "epoch": 2.53, + "learning_rate": 3.1192959582790096e-06, + "loss": 0.1849, + "step": 31074 + }, + { + "epoch": 2.53, + "learning_rate": 3.118752716210344e-06, + "loss": 0.1817, + "step": 31075 + }, + { + "epoch": 2.53, + "learning_rate": 3.118209474141678e-06, + "loss": 0.1716, + "step": 31076 + }, + { + "epoch": 2.53, + "learning_rate": 3.1176662320730123e-06, + "loss": 0.2775, + "step": 31077 + }, + { + "epoch": 2.53, + "learning_rate": 3.117122990004346e-06, + "loss": 0.278, + "step": 31078 + }, + { + "epoch": 2.53, + "learning_rate": 3.1165797479356803e-06, + "loss": 0.6119, + "step": 31079 + }, + { + "epoch": 2.53, + "learning_rate": 3.1160365058670145e-06, + "loss": 0.303, + "step": 31080 + }, + { + "epoch": 2.53, + "learning_rate": 3.1154932637983488e-06, + "loss": 0.3736, + "step": 31081 + }, + { + "epoch": 2.53, + "learning_rate": 3.114950021729683e-06, + "loss": 0.1759, + "step": 31082 + }, + { + "epoch": 2.53, + "learning_rate": 3.1144067796610172e-06, + "loss": 0.2387, + "step": 31083 + }, + { + "epoch": 2.53, + "learning_rate": 3.1138635375923515e-06, + "loss": 0.1662, + "step": 31084 + }, + { + "epoch": 2.53, + "learning_rate": 3.1133202955236857e-06, + "loss": 0.3624, + "step": 31085 + }, + { + "epoch": 2.53, + "learning_rate": 3.11277705345502e-06, + "loss": 0.3555, + "step": 31086 + }, + { + "epoch": 2.53, + "learning_rate": 3.112233811386354e-06, + "loss": 0.2564, + "step": 31087 + }, + { + "epoch": 2.53, + "learning_rate": 3.111690569317688e-06, + "loss": 0.2046, + "step": 31088 + }, + { + "epoch": 2.53, + "learning_rate": 3.111147327249022e-06, + "loss": 0.1781, + "step": 31089 + }, + { + "epoch": 2.53, + "learning_rate": 3.1106040851803564e-06, + "loss": 0.1756, + "step": 31090 + }, + { + "epoch": 2.53, + "learning_rate": 3.1100608431116906e-06, + "loss": 0.3509, + "step": 31091 + }, + { + "epoch": 2.53, + "learning_rate": 3.109517601043025e-06, + "loss": 0.1844, + "step": 31092 + }, + { + "epoch": 2.53, + "learning_rate": 3.108974358974359e-06, + "loss": 0.5507, + "step": 31093 + }, + { + "epoch": 2.53, + "learning_rate": 3.1084311169056938e-06, + "loss": 0.1698, + "step": 31094 + }, + { + "epoch": 2.53, + "learning_rate": 3.107887874837028e-06, + "loss": 0.2407, + "step": 31095 + }, + { + "epoch": 2.53, + "learning_rate": 3.1073446327683622e-06, + "loss": 0.2206, + "step": 31096 + }, + { + "epoch": 2.53, + "learning_rate": 3.1068013906996956e-06, + "loss": 0.2017, + "step": 31097 + }, + { + "epoch": 2.53, + "learning_rate": 3.10625814863103e-06, + "loss": 0.1232, + "step": 31098 + }, + { + "epoch": 2.53, + "learning_rate": 3.1057149065623645e-06, + "loss": 0.2235, + "step": 31099 + }, + { + "epoch": 2.53, + "learning_rate": 3.1051716644936987e-06, + "loss": 0.2591, + "step": 31100 + }, + { + "epoch": 2.53, + "learning_rate": 3.104628422425033e-06, + "loss": 0.1598, + "step": 31101 + }, + { + "epoch": 2.53, + "learning_rate": 3.104085180356367e-06, + "loss": 0.1101, + "step": 31102 + }, + { + "epoch": 2.53, + "learning_rate": 3.1035419382877014e-06, + "loss": 0.2569, + "step": 31103 + }, + { + "epoch": 2.53, + "learning_rate": 3.1029986962190356e-06, + "loss": 0.1338, + "step": 31104 + }, + { + "epoch": 2.53, + "learning_rate": 3.10245545415037e-06, + "loss": 0.1588, + "step": 31105 + }, + { + "epoch": 2.53, + "learning_rate": 3.101912212081704e-06, + "loss": 0.2772, + "step": 31106 + }, + { + "epoch": 2.53, + "learning_rate": 3.101368970013038e-06, + "loss": 0.2586, + "step": 31107 + }, + { + "epoch": 2.53, + "learning_rate": 3.100825727944372e-06, + "loss": 0.3138, + "step": 31108 + }, + { + "epoch": 2.53, + "learning_rate": 3.1002824858757064e-06, + "loss": 0.1004, + "step": 31109 + }, + { + "epoch": 2.54, + "learning_rate": 3.0997392438070406e-06, + "loss": 0.0953, + "step": 31110 + }, + { + "epoch": 2.54, + "learning_rate": 3.099196001738375e-06, + "loss": 0.3169, + "step": 31111 + }, + { + "epoch": 2.54, + "learning_rate": 3.098652759669709e-06, + "loss": 0.151, + "step": 31112 + }, + { + "epoch": 2.54, + "learning_rate": 3.0981095176010433e-06, + "loss": 0.2753, + "step": 31113 + }, + { + "epoch": 2.54, + "learning_rate": 3.0975662755323775e-06, + "loss": 0.1589, + "step": 31114 + }, + { + "epoch": 2.54, + "learning_rate": 3.0970230334637118e-06, + "loss": 0.3811, + "step": 31115 + }, + { + "epoch": 2.54, + "learning_rate": 3.0964797913950456e-06, + "loss": 0.2838, + "step": 31116 + }, + { + "epoch": 2.54, + "learning_rate": 3.09593654932638e-06, + "loss": 0.1496, + "step": 31117 + }, + { + "epoch": 2.54, + "learning_rate": 3.095393307257714e-06, + "loss": 0.1756, + "step": 31118 + }, + { + "epoch": 2.54, + "learning_rate": 3.0948500651890483e-06, + "loss": 0.4636, + "step": 31119 + }, + { + "epoch": 2.54, + "learning_rate": 3.0943068231203825e-06, + "loss": 0.2395, + "step": 31120 + }, + { + "epoch": 2.54, + "learning_rate": 3.093763581051717e-06, + "loss": 0.3058, + "step": 31121 + }, + { + "epoch": 2.54, + "learning_rate": 3.0932203389830514e-06, + "loss": 0.0642, + "step": 31122 + }, + { + "epoch": 2.54, + "learning_rate": 3.0926770969143856e-06, + "loss": 0.1484, + "step": 31123 + }, + { + "epoch": 2.54, + "learning_rate": 3.09213385484572e-06, + "loss": 0.1261, + "step": 31124 + }, + { + "epoch": 2.54, + "learning_rate": 3.091590612777054e-06, + "loss": 0.1976, + "step": 31125 + }, + { + "epoch": 2.54, + "learning_rate": 3.091047370708388e-06, + "loss": 0.2642, + "step": 31126 + }, + { + "epoch": 2.54, + "learning_rate": 3.090504128639722e-06, + "loss": 0.1479, + "step": 31127 + }, + { + "epoch": 2.54, + "learning_rate": 3.0899608865710563e-06, + "loss": 0.4532, + "step": 31128 + }, + { + "epoch": 2.54, + "learning_rate": 3.0894176445023906e-06, + "loss": 0.2147, + "step": 31129 + }, + { + "epoch": 2.54, + "learning_rate": 3.0888744024337248e-06, + "loss": 0.2414, + "step": 31130 + }, + { + "epoch": 2.54, + "learning_rate": 3.088331160365059e-06, + "loss": 0.1172, + "step": 31131 + }, + { + "epoch": 2.54, + "learning_rate": 3.0877879182963932e-06, + "loss": 0.0722, + "step": 31132 + }, + { + "epoch": 2.54, + "learning_rate": 3.0872446762277275e-06, + "loss": 0.3586, + "step": 31133 + }, + { + "epoch": 2.54, + "learning_rate": 3.0867014341590617e-06, + "loss": 0.2054, + "step": 31134 + }, + { + "epoch": 2.54, + "learning_rate": 3.0861581920903955e-06, + "loss": 0.1375, + "step": 31135 + }, + { + "epoch": 2.54, + "learning_rate": 3.0856149500217297e-06, + "loss": 0.4777, + "step": 31136 + }, + { + "epoch": 2.54, + "learning_rate": 3.085071707953064e-06, + "loss": 0.1074, + "step": 31137 + }, + { + "epoch": 2.54, + "learning_rate": 3.084528465884398e-06, + "loss": 0.0497, + "step": 31138 + }, + { + "epoch": 2.54, + "learning_rate": 3.0839852238157324e-06, + "loss": 0.1541, + "step": 31139 + }, + { + "epoch": 2.54, + "learning_rate": 3.0834419817470667e-06, + "loss": 0.2158, + "step": 31140 + }, + { + "epoch": 2.54, + "learning_rate": 3.082898739678401e-06, + "loss": 0.2379, + "step": 31141 + }, + { + "epoch": 2.54, + "learning_rate": 3.082355497609735e-06, + "loss": 0.3461, + "step": 31142 + }, + { + "epoch": 2.54, + "learning_rate": 3.0818122555410694e-06, + "loss": 0.1567, + "step": 31143 + }, + { + "epoch": 2.54, + "learning_rate": 3.081269013472404e-06, + "loss": 0.0722, + "step": 31144 + }, + { + "epoch": 2.54, + "learning_rate": 3.0807257714037374e-06, + "loss": 0.157, + "step": 31145 + }, + { + "epoch": 2.54, + "learning_rate": 3.0801825293350716e-06, + "loss": 0.5954, + "step": 31146 + }, + { + "epoch": 2.54, + "learning_rate": 3.079639287266406e-06, + "loss": 0.0766, + "step": 31147 + }, + { + "epoch": 2.54, + "learning_rate": 3.0790960451977405e-06, + "loss": 0.1702, + "step": 31148 + }, + { + "epoch": 2.54, + "learning_rate": 3.0785528031290747e-06, + "loss": 0.4984, + "step": 31149 + }, + { + "epoch": 2.54, + "learning_rate": 3.078009561060409e-06, + "loss": 0.0765, + "step": 31150 + }, + { + "epoch": 2.54, + "learning_rate": 3.077466318991743e-06, + "loss": 0.2007, + "step": 31151 + }, + { + "epoch": 2.54, + "learning_rate": 3.0769230769230774e-06, + "loss": 0.2053, + "step": 31152 + }, + { + "epoch": 2.54, + "learning_rate": 3.0763798348544117e-06, + "loss": 0.1882, + "step": 31153 + }, + { + "epoch": 2.54, + "learning_rate": 3.0758365927857455e-06, + "loss": 0.135, + "step": 31154 + }, + { + "epoch": 2.54, + "learning_rate": 3.0752933507170797e-06, + "loss": 0.5118, + "step": 31155 + }, + { + "epoch": 2.54, + "learning_rate": 3.074750108648414e-06, + "loss": 0.1475, + "step": 31156 + }, + { + "epoch": 2.54, + "learning_rate": 3.074206866579748e-06, + "loss": 0.0988, + "step": 31157 + }, + { + "epoch": 2.54, + "learning_rate": 3.0736636245110824e-06, + "loss": 0.0768, + "step": 31158 + }, + { + "epoch": 2.54, + "learning_rate": 3.0731203824424166e-06, + "loss": 0.3707, + "step": 31159 + }, + { + "epoch": 2.54, + "learning_rate": 3.072577140373751e-06, + "loss": 0.3524, + "step": 31160 + }, + { + "epoch": 2.54, + "learning_rate": 3.072033898305085e-06, + "loss": 0.3982, + "step": 31161 + }, + { + "epoch": 2.54, + "learning_rate": 3.0714906562364193e-06, + "loss": 0.394, + "step": 31162 + }, + { + "epoch": 2.54, + "learning_rate": 3.0709474141677535e-06, + "loss": 0.2741, + "step": 31163 + }, + { + "epoch": 2.54, + "learning_rate": 3.0704041720990874e-06, + "loss": 0.1539, + "step": 31164 + }, + { + "epoch": 2.54, + "learning_rate": 3.0698609300304216e-06, + "loss": 0.2385, + "step": 31165 + }, + { + "epoch": 2.54, + "learning_rate": 3.069317687961756e-06, + "loss": 0.1455, + "step": 31166 + }, + { + "epoch": 2.54, + "learning_rate": 3.06877444589309e-06, + "loss": 0.1742, + "step": 31167 + }, + { + "epoch": 2.54, + "learning_rate": 3.0682312038244243e-06, + "loss": 0.2984, + "step": 31168 + }, + { + "epoch": 2.54, + "learning_rate": 3.0676879617557585e-06, + "loss": 0.2822, + "step": 31169 + }, + { + "epoch": 2.54, + "learning_rate": 3.0671447196870927e-06, + "loss": 0.1387, + "step": 31170 + }, + { + "epoch": 2.54, + "learning_rate": 3.0666014776184274e-06, + "loss": 0.3915, + "step": 31171 + }, + { + "epoch": 2.54, + "learning_rate": 3.0660582355497616e-06, + "loss": 0.1591, + "step": 31172 + }, + { + "epoch": 2.54, + "learning_rate": 3.065514993481095e-06, + "loss": 0.2372, + "step": 31173 + }, + { + "epoch": 2.54, + "learning_rate": 3.0649717514124292e-06, + "loss": 0.2672, + "step": 31174 + }, + { + "epoch": 2.54, + "learning_rate": 3.064428509343764e-06, + "loss": 0.2285, + "step": 31175 + }, + { + "epoch": 2.54, + "learning_rate": 3.063885267275098e-06, + "loss": 0.1837, + "step": 31176 + }, + { + "epoch": 2.54, + "learning_rate": 3.0633420252064324e-06, + "loss": 0.2746, + "step": 31177 + }, + { + "epoch": 2.54, + "learning_rate": 3.0627987831377666e-06, + "loss": 0.2684, + "step": 31178 + }, + { + "epoch": 2.54, + "learning_rate": 3.062255541069101e-06, + "loss": 0.0747, + "step": 31179 + }, + { + "epoch": 2.54, + "learning_rate": 3.061712299000435e-06, + "loss": 0.0949, + "step": 31180 + }, + { + "epoch": 2.54, + "learning_rate": 3.0611690569317693e-06, + "loss": 0.6285, + "step": 31181 + }, + { + "epoch": 2.54, + "learning_rate": 3.0606258148631035e-06, + "loss": 0.2365, + "step": 31182 + }, + { + "epoch": 2.54, + "learning_rate": 3.0600825727944373e-06, + "loss": 0.2739, + "step": 31183 + }, + { + "epoch": 2.54, + "learning_rate": 3.0595393307257715e-06, + "loss": 0.099, + "step": 31184 + }, + { + "epoch": 2.54, + "learning_rate": 3.0589960886571058e-06, + "loss": 0.1913, + "step": 31185 + }, + { + "epoch": 2.54, + "learning_rate": 3.05845284658844e-06, + "loss": 0.1243, + "step": 31186 + }, + { + "epoch": 2.54, + "learning_rate": 3.0579096045197742e-06, + "loss": 0.3093, + "step": 31187 + }, + { + "epoch": 2.54, + "learning_rate": 3.0573663624511085e-06, + "loss": 0.2377, + "step": 31188 + }, + { + "epoch": 2.54, + "learning_rate": 3.0568231203824427e-06, + "loss": 0.1417, + "step": 31189 + }, + { + "epoch": 2.54, + "learning_rate": 3.056279878313777e-06, + "loss": 0.2967, + "step": 31190 + }, + { + "epoch": 2.54, + "learning_rate": 3.055736636245111e-06, + "loss": 0.3638, + "step": 31191 + }, + { + "epoch": 2.54, + "learning_rate": 3.055193394176445e-06, + "loss": 0.4768, + "step": 31192 + }, + { + "epoch": 2.54, + "learning_rate": 3.054650152107779e-06, + "loss": 0.1435, + "step": 31193 + }, + { + "epoch": 2.54, + "learning_rate": 3.0541069100391134e-06, + "loss": 0.2827, + "step": 31194 + }, + { + "epoch": 2.54, + "learning_rate": 3.0535636679704477e-06, + "loss": 0.1393, + "step": 31195 + }, + { + "epoch": 2.54, + "learning_rate": 3.053020425901782e-06, + "loss": 0.213, + "step": 31196 + }, + { + "epoch": 2.54, + "learning_rate": 3.052477183833116e-06, + "loss": 0.1158, + "step": 31197 + }, + { + "epoch": 2.54, + "learning_rate": 3.0519339417644508e-06, + "loss": 0.2524, + "step": 31198 + }, + { + "epoch": 2.54, + "learning_rate": 3.051390699695785e-06, + "loss": 0.322, + "step": 31199 + }, + { + "epoch": 2.54, + "learning_rate": 3.0508474576271192e-06, + "loss": 0.255, + "step": 31200 + }, + { + "epoch": 2.54, + "learning_rate": 3.0503042155584535e-06, + "loss": 0.2219, + "step": 31201 + }, + { + "epoch": 2.54, + "learning_rate": 3.0497609734897873e-06, + "loss": 0.1581, + "step": 31202 + }, + { + "epoch": 2.54, + "learning_rate": 3.0492177314211215e-06, + "loss": 0.3281, + "step": 31203 + }, + { + "epoch": 2.54, + "learning_rate": 3.0486744893524557e-06, + "loss": 0.3432, + "step": 31204 + }, + { + "epoch": 2.54, + "learning_rate": 3.04813124728379e-06, + "loss": 0.2148, + "step": 31205 + }, + { + "epoch": 2.54, + "learning_rate": 3.047588005215124e-06, + "loss": 0.1185, + "step": 31206 + }, + { + "epoch": 2.54, + "learning_rate": 3.0470447631464584e-06, + "loss": 0.1013, + "step": 31207 + }, + { + "epoch": 2.54, + "learning_rate": 3.0465015210777927e-06, + "loss": 0.1525, + "step": 31208 + }, + { + "epoch": 2.54, + "learning_rate": 3.045958279009127e-06, + "loss": 0.2869, + "step": 31209 + }, + { + "epoch": 2.54, + "learning_rate": 3.045415036940461e-06, + "loss": 0.1924, + "step": 31210 + }, + { + "epoch": 2.54, + "learning_rate": 3.044871794871795e-06, + "loss": 0.3914, + "step": 31211 + }, + { + "epoch": 2.54, + "learning_rate": 3.044328552803129e-06, + "loss": 0.291, + "step": 31212 + }, + { + "epoch": 2.54, + "learning_rate": 3.0437853107344634e-06, + "loss": 0.1672, + "step": 31213 + }, + { + "epoch": 2.54, + "learning_rate": 3.0432420686657976e-06, + "loss": 0.2652, + "step": 31214 + }, + { + "epoch": 2.54, + "learning_rate": 3.042698826597132e-06, + "loss": 0.4491, + "step": 31215 + }, + { + "epoch": 2.54, + "learning_rate": 3.042155584528466e-06, + "loss": 0.1455, + "step": 31216 + }, + { + "epoch": 2.54, + "learning_rate": 3.0416123424598003e-06, + "loss": 0.2091, + "step": 31217 + }, + { + "epoch": 2.54, + "learning_rate": 3.0410691003911345e-06, + "loss": 0.3448, + "step": 31218 + }, + { + "epoch": 2.54, + "learning_rate": 3.0405258583224688e-06, + "loss": 0.2736, + "step": 31219 + }, + { + "epoch": 2.54, + "learning_rate": 3.039982616253803e-06, + "loss": 0.2113, + "step": 31220 + }, + { + "epoch": 2.54, + "learning_rate": 3.039439374185137e-06, + "loss": 0.0989, + "step": 31221 + }, + { + "epoch": 2.54, + "learning_rate": 3.038896132116471e-06, + "loss": 0.1995, + "step": 31222 + }, + { + "epoch": 2.54, + "learning_rate": 3.0383528900478053e-06, + "loss": 0.0877, + "step": 31223 + }, + { + "epoch": 2.54, + "learning_rate": 3.0378096479791395e-06, + "loss": 0.272, + "step": 31224 + }, + { + "epoch": 2.54, + "learning_rate": 3.037266405910474e-06, + "loss": 0.1036, + "step": 31225 + }, + { + "epoch": 2.54, + "learning_rate": 3.0367231638418084e-06, + "loss": 0.3117, + "step": 31226 + }, + { + "epoch": 2.54, + "learning_rate": 3.0361799217731426e-06, + "loss": 0.3471, + "step": 31227 + }, + { + "epoch": 2.54, + "learning_rate": 3.035636679704477e-06, + "loss": 0.1516, + "step": 31228 + }, + { + "epoch": 2.54, + "learning_rate": 3.035093437635811e-06, + "loss": 0.3574, + "step": 31229 + }, + { + "epoch": 2.54, + "learning_rate": 3.034550195567145e-06, + "loss": 0.1823, + "step": 31230 + }, + { + "epoch": 2.54, + "learning_rate": 3.034006953498479e-06, + "loss": 0.1716, + "step": 31231 + }, + { + "epoch": 2.54, + "learning_rate": 3.0334637114298133e-06, + "loss": 0.1688, + "step": 31232 + }, + { + "epoch": 2.55, + "learning_rate": 3.0329204693611476e-06, + "loss": 0.097, + "step": 31233 + }, + { + "epoch": 2.55, + "learning_rate": 3.032377227292482e-06, + "loss": 0.1312, + "step": 31234 + }, + { + "epoch": 2.55, + "learning_rate": 3.031833985223816e-06, + "loss": 0.1467, + "step": 31235 + }, + { + "epoch": 2.55, + "learning_rate": 3.0312907431551503e-06, + "loss": 0.3529, + "step": 31236 + }, + { + "epoch": 2.55, + "learning_rate": 3.0307475010864845e-06, + "loss": 0.4036, + "step": 31237 + }, + { + "epoch": 2.55, + "learning_rate": 3.0302042590178187e-06, + "loss": 0.2886, + "step": 31238 + }, + { + "epoch": 2.55, + "learning_rate": 3.029661016949153e-06, + "loss": 0.17, + "step": 31239 + }, + { + "epoch": 2.55, + "learning_rate": 3.0291177748804868e-06, + "loss": 0.1327, + "step": 31240 + }, + { + "epoch": 2.55, + "learning_rate": 3.028574532811821e-06, + "loss": 0.4388, + "step": 31241 + }, + { + "epoch": 2.55, + "learning_rate": 3.0280312907431552e-06, + "loss": 0.1425, + "step": 31242 + }, + { + "epoch": 2.55, + "learning_rate": 3.0274880486744895e-06, + "loss": 0.277, + "step": 31243 + }, + { + "epoch": 2.55, + "learning_rate": 3.0269448066058237e-06, + "loss": 0.2439, + "step": 31244 + }, + { + "epoch": 2.55, + "learning_rate": 3.026401564537158e-06, + "loss": 0.2152, + "step": 31245 + }, + { + "epoch": 2.55, + "learning_rate": 3.025858322468492e-06, + "loss": 0.1361, + "step": 31246 + }, + { + "epoch": 2.55, + "learning_rate": 3.0253150803998264e-06, + "loss": 0.2736, + "step": 31247 + }, + { + "epoch": 2.55, + "learning_rate": 3.024771838331161e-06, + "loss": 0.2287, + "step": 31248 + }, + { + "epoch": 2.55, + "learning_rate": 3.0242285962624944e-06, + "loss": 0.2326, + "step": 31249 + }, + { + "epoch": 2.55, + "learning_rate": 3.0236853541938286e-06, + "loss": 0.4973, + "step": 31250 + }, + { + "epoch": 2.55, + "eval_accuracy": 0.8381049414161997, + "eval_loss": 0.5005374550819397, + "eval_runtime": 22.3228, + "eval_samples_per_second": 439.685, + "eval_steps_per_second": 3.449, + "step": 31250 + }, + { + "epoch": 2.55, + "learning_rate": 3.023142112125163e-06, + "loss": 0.1587, + "step": 31251 + }, + { + "epoch": 2.55, + "learning_rate": 3.0225988700564975e-06, + "loss": 0.3534, + "step": 31252 + }, + { + "epoch": 2.55, + "learning_rate": 3.0220556279878318e-06, + "loss": 0.0986, + "step": 31253 + }, + { + "epoch": 2.55, + "learning_rate": 3.021512385919166e-06, + "loss": 0.1309, + "step": 31254 + }, + { + "epoch": 2.55, + "learning_rate": 3.0209691438505002e-06, + "loss": 0.3542, + "step": 31255 + }, + { + "epoch": 2.55, + "learning_rate": 3.0204259017818344e-06, + "loss": 0.0918, + "step": 31256 + }, + { + "epoch": 2.55, + "learning_rate": 3.0198826597131687e-06, + "loss": 0.144, + "step": 31257 + }, + { + "epoch": 2.55, + "learning_rate": 3.019339417644503e-06, + "loss": 0.249, + "step": 31258 + }, + { + "epoch": 2.55, + "learning_rate": 3.0187961755758367e-06, + "loss": 0.0945, + "step": 31259 + }, + { + "epoch": 2.55, + "learning_rate": 3.018252933507171e-06, + "loss": 0.1856, + "step": 31260 + }, + { + "epoch": 2.55, + "learning_rate": 3.017709691438505e-06, + "loss": 0.1719, + "step": 31261 + }, + { + "epoch": 2.55, + "learning_rate": 3.0171664493698394e-06, + "loss": 0.1549, + "step": 31262 + }, + { + "epoch": 2.55, + "learning_rate": 3.0166232073011736e-06, + "loss": 0.1886, + "step": 31263 + }, + { + "epoch": 2.55, + "learning_rate": 3.016079965232508e-06, + "loss": 0.1192, + "step": 31264 + }, + { + "epoch": 2.55, + "learning_rate": 3.015536723163842e-06, + "loss": 0.3854, + "step": 31265 + }, + { + "epoch": 2.55, + "learning_rate": 3.0149934810951763e-06, + "loss": 0.0561, + "step": 31266 + }, + { + "epoch": 2.55, + "learning_rate": 3.0144502390265106e-06, + "loss": 0.1203, + "step": 31267 + }, + { + "epoch": 2.55, + "learning_rate": 3.0139069969578444e-06, + "loss": 0.3334, + "step": 31268 + }, + { + "epoch": 2.55, + "learning_rate": 3.0133637548891786e-06, + "loss": 0.1133, + "step": 31269 + }, + { + "epoch": 2.55, + "learning_rate": 3.012820512820513e-06, + "loss": 0.502, + "step": 31270 + }, + { + "epoch": 2.55, + "learning_rate": 3.012277270751847e-06, + "loss": 0.1493, + "step": 31271 + }, + { + "epoch": 2.55, + "learning_rate": 3.0117340286831813e-06, + "loss": 0.0617, + "step": 31272 + }, + { + "epoch": 2.55, + "learning_rate": 3.0111907866145155e-06, + "loss": 0.2782, + "step": 31273 + }, + { + "epoch": 2.55, + "learning_rate": 3.0106475445458498e-06, + "loss": 0.3366, + "step": 31274 + }, + { + "epoch": 2.55, + "learning_rate": 3.0101043024771844e-06, + "loss": 0.2673, + "step": 31275 + }, + { + "epoch": 2.55, + "learning_rate": 3.0095610604085186e-06, + "loss": 0.4456, + "step": 31276 + }, + { + "epoch": 2.55, + "learning_rate": 3.009017818339853e-06, + "loss": 0.3255, + "step": 31277 + }, + { + "epoch": 2.55, + "learning_rate": 3.0084745762711862e-06, + "loss": 0.2746, + "step": 31278 + }, + { + "epoch": 2.55, + "learning_rate": 3.007931334202521e-06, + "loss": 0.2543, + "step": 31279 + }, + { + "epoch": 2.55, + "learning_rate": 3.007388092133855e-06, + "loss": 0.3312, + "step": 31280 + }, + { + "epoch": 2.55, + "learning_rate": 3.0068448500651894e-06, + "loss": 0.4529, + "step": 31281 + }, + { + "epoch": 2.55, + "learning_rate": 3.0063016079965236e-06, + "loss": 0.1472, + "step": 31282 + }, + { + "epoch": 2.55, + "learning_rate": 3.005758365927858e-06, + "loss": 0.2966, + "step": 31283 + }, + { + "epoch": 2.55, + "learning_rate": 3.005215123859192e-06, + "loss": 0.1514, + "step": 31284 + }, + { + "epoch": 2.55, + "learning_rate": 3.0046718817905263e-06, + "loss": 0.283, + "step": 31285 + }, + { + "epoch": 2.55, + "learning_rate": 3.0041286397218605e-06, + "loss": 0.0435, + "step": 31286 + }, + { + "epoch": 2.55, + "learning_rate": 3.0035853976531943e-06, + "loss": 0.2704, + "step": 31287 + }, + { + "epoch": 2.55, + "learning_rate": 3.0030421555845286e-06, + "loss": 0.1765, + "step": 31288 + }, + { + "epoch": 2.55, + "learning_rate": 3.0024989135158628e-06, + "loss": 0.369, + "step": 31289 + }, + { + "epoch": 2.55, + "learning_rate": 3.001955671447197e-06, + "loss": 0.2505, + "step": 31290 + }, + { + "epoch": 2.55, + "learning_rate": 3.0014124293785312e-06, + "loss": 0.0819, + "step": 31291 + }, + { + "epoch": 2.55, + "learning_rate": 3.0008691873098655e-06, + "loss": 0.4104, + "step": 31292 + }, + { + "epoch": 2.55, + "learning_rate": 3.0003259452411997e-06, + "loss": 0.1136, + "step": 31293 + }, + { + "epoch": 2.55, + "learning_rate": 2.999782703172534e-06, + "loss": 0.2076, + "step": 31294 + }, + { + "epoch": 2.55, + "learning_rate": 2.999239461103868e-06, + "loss": 0.184, + "step": 31295 + }, + { + "epoch": 2.55, + "learning_rate": 2.9986962190352024e-06, + "loss": 0.1396, + "step": 31296 + }, + { + "epoch": 2.55, + "learning_rate": 2.998152976966536e-06, + "loss": 0.3613, + "step": 31297 + }, + { + "epoch": 2.55, + "learning_rate": 2.9976097348978704e-06, + "loss": 0.3403, + "step": 31298 + }, + { + "epoch": 2.55, + "learning_rate": 2.9970664928292047e-06, + "loss": 0.1031, + "step": 31299 + }, + { + "epoch": 2.55, + "learning_rate": 2.996523250760539e-06, + "loss": 0.0862, + "step": 31300 + }, + { + "epoch": 2.55, + "learning_rate": 2.995980008691873e-06, + "loss": 0.1004, + "step": 31301 + }, + { + "epoch": 2.55, + "learning_rate": 2.9954367666232078e-06, + "loss": 0.2086, + "step": 31302 + }, + { + "epoch": 2.55, + "learning_rate": 2.994893524554542e-06, + "loss": 0.179, + "step": 31303 + }, + { + "epoch": 2.55, + "learning_rate": 2.9943502824858762e-06, + "loss": 0.1605, + "step": 31304 + }, + { + "epoch": 2.55, + "learning_rate": 2.9938070404172105e-06, + "loss": 0.1964, + "step": 31305 + }, + { + "epoch": 2.55, + "learning_rate": 2.9932637983485443e-06, + "loss": 0.0704, + "step": 31306 + }, + { + "epoch": 2.55, + "learning_rate": 2.9927205562798785e-06, + "loss": 0.3409, + "step": 31307 + }, + { + "epoch": 2.55, + "learning_rate": 2.9921773142112127e-06, + "loss": 0.092, + "step": 31308 + }, + { + "epoch": 2.55, + "learning_rate": 2.991634072142547e-06, + "loss": 0.1271, + "step": 31309 + }, + { + "epoch": 2.55, + "learning_rate": 2.991090830073881e-06, + "loss": 0.1304, + "step": 31310 + }, + { + "epoch": 2.55, + "learning_rate": 2.9905475880052154e-06, + "loss": 0.1415, + "step": 31311 + }, + { + "epoch": 2.55, + "learning_rate": 2.9900043459365497e-06, + "loss": 0.25, + "step": 31312 + }, + { + "epoch": 2.55, + "learning_rate": 2.989461103867884e-06, + "loss": 0.423, + "step": 31313 + }, + { + "epoch": 2.55, + "learning_rate": 2.988917861799218e-06, + "loss": 0.0826, + "step": 31314 + }, + { + "epoch": 2.55, + "learning_rate": 2.9883746197305524e-06, + "loss": 0.4491, + "step": 31315 + }, + { + "epoch": 2.55, + "learning_rate": 2.987831377661886e-06, + "loss": 0.1219, + "step": 31316 + }, + { + "epoch": 2.55, + "learning_rate": 2.9872881355932204e-06, + "loss": 0.1715, + "step": 31317 + }, + { + "epoch": 2.55, + "learning_rate": 2.9867448935245546e-06, + "loss": 0.2396, + "step": 31318 + }, + { + "epoch": 2.55, + "learning_rate": 2.986201651455889e-06, + "loss": 0.4125, + "step": 31319 + }, + { + "epoch": 2.55, + "learning_rate": 2.985658409387223e-06, + "loss": 0.1237, + "step": 31320 + }, + { + "epoch": 2.55, + "learning_rate": 2.9851151673185573e-06, + "loss": 0.2901, + "step": 31321 + }, + { + "epoch": 2.55, + "learning_rate": 2.9845719252498915e-06, + "loss": 0.2117, + "step": 31322 + }, + { + "epoch": 2.55, + "learning_rate": 2.9840286831812258e-06, + "loss": 0.13, + "step": 31323 + }, + { + "epoch": 2.55, + "learning_rate": 2.9834854411125604e-06, + "loss": 0.1473, + "step": 31324 + }, + { + "epoch": 2.55, + "learning_rate": 2.982942199043894e-06, + "loss": 0.0771, + "step": 31325 + }, + { + "epoch": 2.55, + "learning_rate": 2.982398956975228e-06, + "loss": 0.2693, + "step": 31326 + }, + { + "epoch": 2.55, + "learning_rate": 2.9818557149065623e-06, + "loss": 0.2566, + "step": 31327 + }, + { + "epoch": 2.55, + "learning_rate": 2.9813124728378965e-06, + "loss": 0.1234, + "step": 31328 + }, + { + "epoch": 2.55, + "learning_rate": 2.980769230769231e-06, + "loss": 0.0688, + "step": 31329 + }, + { + "epoch": 2.55, + "learning_rate": 2.9802259887005654e-06, + "loss": 0.2059, + "step": 31330 + }, + { + "epoch": 2.55, + "learning_rate": 2.9796827466318996e-06, + "loss": 0.294, + "step": 31331 + }, + { + "epoch": 2.55, + "learning_rate": 2.979139504563234e-06, + "loss": 0.1137, + "step": 31332 + }, + { + "epoch": 2.55, + "learning_rate": 2.978596262494568e-06, + "loss": 0.145, + "step": 31333 + }, + { + "epoch": 2.55, + "learning_rate": 2.9780530204259023e-06, + "loss": 0.3451, + "step": 31334 + }, + { + "epoch": 2.55, + "learning_rate": 2.977509778357236e-06, + "loss": 0.3238, + "step": 31335 + }, + { + "epoch": 2.55, + "learning_rate": 2.9769665362885703e-06, + "loss": 0.2789, + "step": 31336 + }, + { + "epoch": 2.55, + "learning_rate": 2.9764232942199046e-06, + "loss": 0.1576, + "step": 31337 + }, + { + "epoch": 2.55, + "learning_rate": 2.975880052151239e-06, + "loss": 0.2656, + "step": 31338 + }, + { + "epoch": 2.55, + "learning_rate": 2.975336810082573e-06, + "loss": 0.3917, + "step": 31339 + }, + { + "epoch": 2.55, + "learning_rate": 2.9747935680139073e-06, + "loss": 0.1316, + "step": 31340 + }, + { + "epoch": 2.55, + "learning_rate": 2.9742503259452415e-06, + "loss": 0.2083, + "step": 31341 + }, + { + "epoch": 2.55, + "learning_rate": 2.9737070838765757e-06, + "loss": 0.3401, + "step": 31342 + }, + { + "epoch": 2.55, + "learning_rate": 2.97316384180791e-06, + "loss": 0.3152, + "step": 31343 + }, + { + "epoch": 2.55, + "learning_rate": 2.9726205997392438e-06, + "loss": 0.429, + "step": 31344 + }, + { + "epoch": 2.55, + "learning_rate": 2.972077357670578e-06, + "loss": 0.3452, + "step": 31345 + }, + { + "epoch": 2.55, + "learning_rate": 2.9715341156019122e-06, + "loss": 0.1226, + "step": 31346 + }, + { + "epoch": 2.55, + "learning_rate": 2.9709908735332465e-06, + "loss": 0.2817, + "step": 31347 + }, + { + "epoch": 2.55, + "learning_rate": 2.9704476314645807e-06, + "loss": 0.1474, + "step": 31348 + }, + { + "epoch": 2.55, + "learning_rate": 2.969904389395915e-06, + "loss": 0.1277, + "step": 31349 + }, + { + "epoch": 2.55, + "learning_rate": 2.969361147327249e-06, + "loss": 0.0475, + "step": 31350 + }, + { + "epoch": 2.55, + "learning_rate": 2.968817905258584e-06, + "loss": 0.164, + "step": 31351 + }, + { + "epoch": 2.55, + "learning_rate": 2.968274663189918e-06, + "loss": 0.3093, + "step": 31352 + }, + { + "epoch": 2.55, + "learning_rate": 2.9677314211212523e-06, + "loss": 0.1419, + "step": 31353 + }, + { + "epoch": 2.55, + "learning_rate": 2.9671881790525857e-06, + "loss": 0.6555, + "step": 31354 + }, + { + "epoch": 2.56, + "learning_rate": 2.96664493698392e-06, + "loss": 0.2085, + "step": 31355 + }, + { + "epoch": 2.56, + "learning_rate": 2.9661016949152545e-06, + "loss": 0.1325, + "step": 31356 + }, + { + "epoch": 2.56, + "learning_rate": 2.9655584528465888e-06, + "loss": 0.2834, + "step": 31357 + }, + { + "epoch": 2.56, + "learning_rate": 2.965015210777923e-06, + "loss": 0.5327, + "step": 31358 + }, + { + "epoch": 2.56, + "learning_rate": 2.9644719687092572e-06, + "loss": 0.0808, + "step": 31359 + }, + { + "epoch": 2.56, + "learning_rate": 2.9639287266405915e-06, + "loss": 0.0894, + "step": 31360 + }, + { + "epoch": 2.56, + "learning_rate": 2.9633854845719257e-06, + "loss": 0.2573, + "step": 31361 + }, + { + "epoch": 2.56, + "learning_rate": 2.96284224250326e-06, + "loss": 0.3475, + "step": 31362 + }, + { + "epoch": 2.56, + "learning_rate": 2.962299000434594e-06, + "loss": 0.058, + "step": 31363 + }, + { + "epoch": 2.56, + "learning_rate": 2.961755758365928e-06, + "loss": 0.0335, + "step": 31364 + }, + { + "epoch": 2.56, + "learning_rate": 2.961212516297262e-06, + "loss": 0.1468, + "step": 31365 + }, + { + "epoch": 2.56, + "learning_rate": 2.9606692742285964e-06, + "loss": 0.3188, + "step": 31366 + }, + { + "epoch": 2.56, + "learning_rate": 2.9601260321599306e-06, + "loss": 0.2772, + "step": 31367 + }, + { + "epoch": 2.56, + "learning_rate": 2.959582790091265e-06, + "loss": 0.187, + "step": 31368 + }, + { + "epoch": 2.56, + "learning_rate": 2.959039548022599e-06, + "loss": 0.2994, + "step": 31369 + }, + { + "epoch": 2.56, + "learning_rate": 2.9584963059539333e-06, + "loss": 0.2335, + "step": 31370 + }, + { + "epoch": 2.56, + "learning_rate": 2.9579530638852676e-06, + "loss": 0.0599, + "step": 31371 + }, + { + "epoch": 2.56, + "learning_rate": 2.957409821816602e-06, + "loss": 0.3119, + "step": 31372 + }, + { + "epoch": 2.56, + "learning_rate": 2.9568665797479356e-06, + "loss": 0.2099, + "step": 31373 + }, + { + "epoch": 2.56, + "learning_rate": 2.95632333767927e-06, + "loss": 0.0487, + "step": 31374 + }, + { + "epoch": 2.56, + "learning_rate": 2.955780095610604e-06, + "loss": 0.2055, + "step": 31375 + }, + { + "epoch": 2.56, + "learning_rate": 2.9552368535419383e-06, + "loss": 0.0755, + "step": 31376 + }, + { + "epoch": 2.56, + "learning_rate": 2.9546936114732725e-06, + "loss": 0.1526, + "step": 31377 + }, + { + "epoch": 2.56, + "learning_rate": 2.954150369404607e-06, + "loss": 0.3216, + "step": 31378 + }, + { + "epoch": 2.56, + "learning_rate": 2.9536071273359414e-06, + "loss": 0.1854, + "step": 31379 + }, + { + "epoch": 2.56, + "learning_rate": 2.9530638852672756e-06, + "loss": 0.1152, + "step": 31380 + }, + { + "epoch": 2.56, + "learning_rate": 2.95252064319861e-06, + "loss": 0.0687, + "step": 31381 + }, + { + "epoch": 2.56, + "learning_rate": 2.951977401129944e-06, + "loss": 0.0795, + "step": 31382 + }, + { + "epoch": 2.56, + "learning_rate": 2.951434159061278e-06, + "loss": 0.3802, + "step": 31383 + }, + { + "epoch": 2.56, + "learning_rate": 2.950890916992612e-06, + "loss": 0.1883, + "step": 31384 + }, + { + "epoch": 2.56, + "learning_rate": 2.9503476749239464e-06, + "loss": 0.179, + "step": 31385 + }, + { + "epoch": 2.56, + "learning_rate": 2.9498044328552806e-06, + "loss": 0.2181, + "step": 31386 + }, + { + "epoch": 2.56, + "learning_rate": 2.949261190786615e-06, + "loss": 0.1115, + "step": 31387 + }, + { + "epoch": 2.56, + "learning_rate": 2.948717948717949e-06, + "loss": 0.3103, + "step": 31388 + }, + { + "epoch": 2.56, + "learning_rate": 2.9481747066492833e-06, + "loss": 0.2484, + "step": 31389 + }, + { + "epoch": 2.56, + "learning_rate": 2.9476314645806175e-06, + "loss": 0.1588, + "step": 31390 + }, + { + "epoch": 2.56, + "learning_rate": 2.9470882225119518e-06, + "loss": 0.1348, + "step": 31391 + }, + { + "epoch": 2.56, + "learning_rate": 2.9465449804432856e-06, + "loss": 0.3132, + "step": 31392 + }, + { + "epoch": 2.56, + "learning_rate": 2.94600173837462e-06, + "loss": 0.1043, + "step": 31393 + }, + { + "epoch": 2.56, + "learning_rate": 2.945458496305954e-06, + "loss": 0.246, + "step": 31394 + }, + { + "epoch": 2.56, + "learning_rate": 2.9449152542372883e-06, + "loss": 0.2926, + "step": 31395 + }, + { + "epoch": 2.56, + "learning_rate": 2.9443720121686225e-06, + "loss": 0.3799, + "step": 31396 + }, + { + "epoch": 2.56, + "learning_rate": 2.9438287700999567e-06, + "loss": 0.2254, + "step": 31397 + }, + { + "epoch": 2.56, + "learning_rate": 2.943285528031291e-06, + "loss": 0.2163, + "step": 31398 + }, + { + "epoch": 2.56, + "learning_rate": 2.942742285962625e-06, + "loss": 0.179, + "step": 31399 + }, + { + "epoch": 2.56, + "learning_rate": 2.9421990438939594e-06, + "loss": 0.2112, + "step": 31400 + }, + { + "epoch": 2.56, + "learning_rate": 2.941655801825294e-06, + "loss": 0.3205, + "step": 31401 + }, + { + "epoch": 2.56, + "learning_rate": 2.9411125597566274e-06, + "loss": 0.1698, + "step": 31402 + }, + { + "epoch": 2.56, + "learning_rate": 2.9405693176879617e-06, + "loss": 0.1572, + "step": 31403 + }, + { + "epoch": 2.56, + "learning_rate": 2.940026075619296e-06, + "loss": 0.4049, + "step": 31404 + }, + { + "epoch": 2.56, + "learning_rate": 2.9394828335506306e-06, + "loss": 0.3261, + "step": 31405 + }, + { + "epoch": 2.56, + "learning_rate": 2.938939591481965e-06, + "loss": 0.3584, + "step": 31406 + }, + { + "epoch": 2.56, + "learning_rate": 2.938396349413299e-06, + "loss": 0.166, + "step": 31407 + }, + { + "epoch": 2.56, + "learning_rate": 2.9378531073446333e-06, + "loss": 0.1616, + "step": 31408 + }, + { + "epoch": 2.56, + "learning_rate": 2.9373098652759675e-06, + "loss": 0.2081, + "step": 31409 + }, + { + "epoch": 2.56, + "learning_rate": 2.9367666232073017e-06, + "loss": 0.0425, + "step": 31410 + }, + { + "epoch": 2.56, + "learning_rate": 2.9362233811386355e-06, + "loss": 0.1209, + "step": 31411 + }, + { + "epoch": 2.56, + "learning_rate": 2.9356801390699698e-06, + "loss": 0.089, + "step": 31412 + }, + { + "epoch": 2.56, + "learning_rate": 2.935136897001304e-06, + "loss": 0.3815, + "step": 31413 + }, + { + "epoch": 2.56, + "learning_rate": 2.9345936549326382e-06, + "loss": 0.0901, + "step": 31414 + }, + { + "epoch": 2.56, + "learning_rate": 2.9340504128639724e-06, + "loss": 0.2492, + "step": 31415 + }, + { + "epoch": 2.56, + "learning_rate": 2.9335071707953067e-06, + "loss": 0.1121, + "step": 31416 + }, + { + "epoch": 2.56, + "learning_rate": 2.932963928726641e-06, + "loss": 0.2409, + "step": 31417 + }, + { + "epoch": 2.56, + "learning_rate": 2.932420686657975e-06, + "loss": 0.1326, + "step": 31418 + }, + { + "epoch": 2.56, + "learning_rate": 2.9318774445893094e-06, + "loss": 0.5255, + "step": 31419 + }, + { + "epoch": 2.56, + "learning_rate": 2.9313342025206436e-06, + "loss": 0.0366, + "step": 31420 + }, + { + "epoch": 2.56, + "learning_rate": 2.9307909604519774e-06, + "loss": 0.1795, + "step": 31421 + }, + { + "epoch": 2.56, + "learning_rate": 2.9302477183833116e-06, + "loss": 0.3164, + "step": 31422 + }, + { + "epoch": 2.56, + "learning_rate": 2.929704476314646e-06, + "loss": 0.3362, + "step": 31423 + }, + { + "epoch": 2.56, + "learning_rate": 2.92916123424598e-06, + "loss": 0.2368, + "step": 31424 + }, + { + "epoch": 2.56, + "learning_rate": 2.9286179921773143e-06, + "loss": 0.2068, + "step": 31425 + }, + { + "epoch": 2.56, + "learning_rate": 2.9280747501086486e-06, + "loss": 0.214, + "step": 31426 + }, + { + "epoch": 2.56, + "learning_rate": 2.927531508039983e-06, + "loss": 0.4054, + "step": 31427 + }, + { + "epoch": 2.56, + "learning_rate": 2.9269882659713174e-06, + "loss": 0.1015, + "step": 31428 + }, + { + "epoch": 2.56, + "learning_rate": 2.9264450239026517e-06, + "loss": 0.111, + "step": 31429 + }, + { + "epoch": 2.56, + "learning_rate": 2.925901781833985e-06, + "loss": 0.1328, + "step": 31430 + }, + { + "epoch": 2.56, + "learning_rate": 2.9253585397653193e-06, + "loss": 0.2263, + "step": 31431 + }, + { + "epoch": 2.56, + "learning_rate": 2.924815297696654e-06, + "loss": 0.2189, + "step": 31432 + }, + { + "epoch": 2.56, + "learning_rate": 2.924272055627988e-06, + "loss": 0.2658, + "step": 31433 + }, + { + "epoch": 2.56, + "learning_rate": 2.9237288135593224e-06, + "loss": 0.3487, + "step": 31434 + }, + { + "epoch": 2.56, + "learning_rate": 2.9231855714906566e-06, + "loss": 0.2891, + "step": 31435 + }, + { + "epoch": 2.56, + "learning_rate": 2.922642329421991e-06, + "loss": 0.3594, + "step": 31436 + }, + { + "epoch": 2.56, + "learning_rate": 2.922099087353325e-06, + "loss": 0.4509, + "step": 31437 + }, + { + "epoch": 2.56, + "learning_rate": 2.9215558452846593e-06, + "loss": 0.0631, + "step": 31438 + }, + { + "epoch": 2.56, + "learning_rate": 2.9210126032159936e-06, + "loss": 0.3202, + "step": 31439 + }, + { + "epoch": 2.56, + "learning_rate": 2.9204693611473274e-06, + "loss": 0.3256, + "step": 31440 + }, + { + "epoch": 2.56, + "learning_rate": 2.9199261190786616e-06, + "loss": 0.1227, + "step": 31441 + }, + { + "epoch": 2.56, + "learning_rate": 2.919382877009996e-06, + "loss": 0.274, + "step": 31442 + }, + { + "epoch": 2.56, + "learning_rate": 2.91883963494133e-06, + "loss": 0.1391, + "step": 31443 + }, + { + "epoch": 2.56, + "learning_rate": 2.9182963928726643e-06, + "loss": 0.5355, + "step": 31444 + }, + { + "epoch": 2.56, + "learning_rate": 2.9177531508039985e-06, + "loss": 0.2284, + "step": 31445 + }, + { + "epoch": 2.56, + "learning_rate": 2.9172099087353327e-06, + "loss": 0.1727, + "step": 31446 + }, + { + "epoch": 2.56, + "learning_rate": 2.916666666666667e-06, + "loss": 0.1981, + "step": 31447 + }, + { + "epoch": 2.56, + "learning_rate": 2.916123424598001e-06, + "loss": 0.4452, + "step": 31448 + }, + { + "epoch": 2.56, + "learning_rate": 2.915580182529335e-06, + "loss": 0.141, + "step": 31449 + }, + { + "epoch": 2.56, + "learning_rate": 2.9150369404606692e-06, + "loss": 0.1254, + "step": 31450 + }, + { + "epoch": 2.56, + "learning_rate": 2.9144936983920035e-06, + "loss": 0.2314, + "step": 31451 + }, + { + "epoch": 2.56, + "learning_rate": 2.9139504563233377e-06, + "loss": 0.4116, + "step": 31452 + }, + { + "epoch": 2.56, + "learning_rate": 2.913407214254672e-06, + "loss": 0.2146, + "step": 31453 + }, + { + "epoch": 2.56, + "learning_rate": 2.912863972186006e-06, + "loss": 0.1526, + "step": 31454 + }, + { + "epoch": 2.56, + "learning_rate": 2.912320730117341e-06, + "loss": 0.2025, + "step": 31455 + }, + { + "epoch": 2.56, + "learning_rate": 2.911777488048675e-06, + "loss": 0.2785, + "step": 31456 + }, + { + "epoch": 2.56, + "learning_rate": 2.9112342459800093e-06, + "loss": 0.1769, + "step": 31457 + }, + { + "epoch": 2.56, + "learning_rate": 2.9106910039113435e-06, + "loss": 0.3003, + "step": 31458 + }, + { + "epoch": 2.56, + "learning_rate": 2.9101477618426773e-06, + "loss": 0.3065, + "step": 31459 + }, + { + "epoch": 2.56, + "learning_rate": 2.9096045197740115e-06, + "loss": 0.2168, + "step": 31460 + }, + { + "epoch": 2.56, + "learning_rate": 2.9090612777053458e-06, + "loss": 0.1748, + "step": 31461 + }, + { + "epoch": 2.56, + "learning_rate": 2.90851803563668e-06, + "loss": 0.2429, + "step": 31462 + }, + { + "epoch": 2.56, + "learning_rate": 2.9079747935680142e-06, + "loss": 0.2505, + "step": 31463 + }, + { + "epoch": 2.56, + "learning_rate": 2.9074315514993485e-06, + "loss": 0.2671, + "step": 31464 + }, + { + "epoch": 2.56, + "learning_rate": 2.9068883094306827e-06, + "loss": 0.1056, + "step": 31465 + }, + { + "epoch": 2.56, + "learning_rate": 2.906345067362017e-06, + "loss": 0.3184, + "step": 31466 + }, + { + "epoch": 2.56, + "learning_rate": 2.905801825293351e-06, + "loss": 0.0703, + "step": 31467 + }, + { + "epoch": 2.56, + "learning_rate": 2.905258583224685e-06, + "loss": 0.1038, + "step": 31468 + }, + { + "epoch": 2.56, + "learning_rate": 2.904715341156019e-06, + "loss": 0.1348, + "step": 31469 + }, + { + "epoch": 2.56, + "learning_rate": 2.9041720990873534e-06, + "loss": 0.3426, + "step": 31470 + }, + { + "epoch": 2.56, + "learning_rate": 2.9036288570186877e-06, + "loss": 0.2766, + "step": 31471 + }, + { + "epoch": 2.56, + "learning_rate": 2.903085614950022e-06, + "loss": 0.2616, + "step": 31472 + }, + { + "epoch": 2.56, + "learning_rate": 2.902542372881356e-06, + "loss": 0.4291, + "step": 31473 + }, + { + "epoch": 2.56, + "learning_rate": 2.9019991308126904e-06, + "loss": 0.3411, + "step": 31474 + }, + { + "epoch": 2.56, + "learning_rate": 2.9014558887440246e-06, + "loss": 0.2335, + "step": 31475 + }, + { + "epoch": 2.56, + "learning_rate": 2.900912646675359e-06, + "loss": 0.0878, + "step": 31476 + }, + { + "epoch": 2.56, + "learning_rate": 2.900369404606693e-06, + "loss": 0.3312, + "step": 31477 + }, + { + "epoch": 2.57, + "learning_rate": 2.899826162538027e-06, + "loss": 0.1089, + "step": 31478 + }, + { + "epoch": 2.57, + "learning_rate": 2.899282920469361e-06, + "loss": 0.1724, + "step": 31479 + }, + { + "epoch": 2.57, + "learning_rate": 2.8987396784006953e-06, + "loss": 0.0506, + "step": 31480 + }, + { + "epoch": 2.57, + "learning_rate": 2.8981964363320295e-06, + "loss": 0.3535, + "step": 31481 + }, + { + "epoch": 2.57, + "learning_rate": 2.897653194263364e-06, + "loss": 0.1699, + "step": 31482 + }, + { + "epoch": 2.57, + "learning_rate": 2.8971099521946984e-06, + "loss": 0.4906, + "step": 31483 + }, + { + "epoch": 2.57, + "learning_rate": 2.8965667101260327e-06, + "loss": 0.2009, + "step": 31484 + }, + { + "epoch": 2.57, + "learning_rate": 2.896023468057367e-06, + "loss": 0.3358, + "step": 31485 + }, + { + "epoch": 2.57, + "learning_rate": 2.895480225988701e-06, + "loss": 0.4594, + "step": 31486 + }, + { + "epoch": 2.57, + "learning_rate": 2.894936983920035e-06, + "loss": 0.4208, + "step": 31487 + }, + { + "epoch": 2.57, + "learning_rate": 2.894393741851369e-06, + "loss": 0.1626, + "step": 31488 + }, + { + "epoch": 2.57, + "learning_rate": 2.8938504997827034e-06, + "loss": 0.1166, + "step": 31489 + }, + { + "epoch": 2.57, + "learning_rate": 2.8933072577140376e-06, + "loss": 0.1983, + "step": 31490 + }, + { + "epoch": 2.57, + "learning_rate": 2.892764015645372e-06, + "loss": 0.0875, + "step": 31491 + }, + { + "epoch": 2.57, + "learning_rate": 2.892220773576706e-06, + "loss": 0.168, + "step": 31492 + }, + { + "epoch": 2.57, + "learning_rate": 2.8916775315080403e-06, + "loss": 0.2277, + "step": 31493 + }, + { + "epoch": 2.57, + "learning_rate": 2.8911342894393745e-06, + "loss": 0.1046, + "step": 31494 + }, + { + "epoch": 2.57, + "learning_rate": 2.8905910473707088e-06, + "loss": 0.3761, + "step": 31495 + }, + { + "epoch": 2.57, + "learning_rate": 2.890047805302043e-06, + "loss": 0.3936, + "step": 31496 + }, + { + "epoch": 2.57, + "learning_rate": 2.889504563233377e-06, + "loss": 0.1475, + "step": 31497 + }, + { + "epoch": 2.57, + "learning_rate": 2.888961321164711e-06, + "loss": 0.1294, + "step": 31498 + }, + { + "epoch": 2.57, + "learning_rate": 2.8884180790960453e-06, + "loss": 0.3068, + "step": 31499 + }, + { + "epoch": 2.57, + "learning_rate": 2.8878748370273795e-06, + "loss": 0.0886, + "step": 31500 + }, + { + "epoch": 2.57, + "eval_accuracy": 0.8415690269994905, + "eval_loss": 0.5020298361778259, + "eval_runtime": 22.2281, + "eval_samples_per_second": 441.558, + "eval_steps_per_second": 3.464, + "step": 31500 + }, + { + "epoch": 2.57, + "learning_rate": 2.8873315949587137e-06, + "loss": 0.1842, + "step": 31501 + }, + { + "epoch": 2.57, + "learning_rate": 2.886788352890048e-06, + "loss": 0.1342, + "step": 31502 + }, + { + "epoch": 2.57, + "learning_rate": 2.886245110821382e-06, + "loss": 0.4239, + "step": 31503 + }, + { + "epoch": 2.57, + "learning_rate": 2.8857018687527164e-06, + "loss": 0.2188, + "step": 31504 + }, + { + "epoch": 2.57, + "learning_rate": 2.885158626684051e-06, + "loss": 0.0512, + "step": 31505 + }, + { + "epoch": 2.57, + "learning_rate": 2.8846153846153845e-06, + "loss": 0.1977, + "step": 31506 + }, + { + "epoch": 2.57, + "learning_rate": 2.8840721425467187e-06, + "loss": 0.4314, + "step": 31507 + }, + { + "epoch": 2.57, + "learning_rate": 2.883528900478053e-06, + "loss": 0.2625, + "step": 31508 + }, + { + "epoch": 2.57, + "learning_rate": 2.8829856584093876e-06, + "loss": 0.1873, + "step": 31509 + }, + { + "epoch": 2.57, + "learning_rate": 2.882442416340722e-06, + "loss": 0.518, + "step": 31510 + }, + { + "epoch": 2.57, + "learning_rate": 2.881899174272056e-06, + "loss": 0.1765, + "step": 31511 + }, + { + "epoch": 2.57, + "learning_rate": 2.8813559322033903e-06, + "loss": 0.2805, + "step": 31512 + }, + { + "epoch": 2.57, + "learning_rate": 2.8808126901347245e-06, + "loss": 0.1271, + "step": 31513 + }, + { + "epoch": 2.57, + "learning_rate": 2.8802694480660587e-06, + "loss": 0.2879, + "step": 31514 + }, + { + "epoch": 2.57, + "learning_rate": 2.879726205997393e-06, + "loss": 0.242, + "step": 31515 + }, + { + "epoch": 2.57, + "learning_rate": 2.8791829639287268e-06, + "loss": 0.1152, + "step": 31516 + }, + { + "epoch": 2.57, + "learning_rate": 2.878639721860061e-06, + "loss": 0.192, + "step": 31517 + }, + { + "epoch": 2.57, + "learning_rate": 2.8780964797913952e-06, + "loss": 0.5904, + "step": 31518 + }, + { + "epoch": 2.57, + "learning_rate": 2.8775532377227295e-06, + "loss": 0.1858, + "step": 31519 + }, + { + "epoch": 2.57, + "learning_rate": 2.8770099956540637e-06, + "loss": 0.0945, + "step": 31520 + }, + { + "epoch": 2.57, + "learning_rate": 2.876466753585398e-06, + "loss": 0.3463, + "step": 31521 + }, + { + "epoch": 2.57, + "learning_rate": 2.875923511516732e-06, + "loss": 0.4827, + "step": 31522 + }, + { + "epoch": 2.57, + "learning_rate": 2.8753802694480664e-06, + "loss": 0.2555, + "step": 31523 + }, + { + "epoch": 2.57, + "learning_rate": 2.8748370273794006e-06, + "loss": 0.4414, + "step": 31524 + }, + { + "epoch": 2.57, + "learning_rate": 2.8742937853107344e-06, + "loss": 0.1854, + "step": 31525 + }, + { + "epoch": 2.57, + "learning_rate": 2.8737505432420686e-06, + "loss": 0.1328, + "step": 31526 + }, + { + "epoch": 2.57, + "learning_rate": 2.873207301173403e-06, + "loss": 0.3456, + "step": 31527 + }, + { + "epoch": 2.57, + "learning_rate": 2.872664059104737e-06, + "loss": 0.3488, + "step": 31528 + }, + { + "epoch": 2.57, + "learning_rate": 2.8721208170360713e-06, + "loss": 0.1485, + "step": 31529 + }, + { + "epoch": 2.57, + "learning_rate": 2.8715775749674056e-06, + "loss": 0.2373, + "step": 31530 + }, + { + "epoch": 2.57, + "learning_rate": 2.87103433289874e-06, + "loss": 0.3389, + "step": 31531 + }, + { + "epoch": 2.57, + "learning_rate": 2.8704910908300745e-06, + "loss": 0.2283, + "step": 31532 + }, + { + "epoch": 2.57, + "learning_rate": 2.8699478487614087e-06, + "loss": 0.1061, + "step": 31533 + }, + { + "epoch": 2.57, + "learning_rate": 2.869404606692743e-06, + "loss": 0.4044, + "step": 31534 + }, + { + "epoch": 2.57, + "learning_rate": 2.8688613646240763e-06, + "loss": 0.3232, + "step": 31535 + }, + { + "epoch": 2.57, + "learning_rate": 2.868318122555411e-06, + "loss": 0.5257, + "step": 31536 + }, + { + "epoch": 2.57, + "learning_rate": 2.867774880486745e-06, + "loss": 0.4315, + "step": 31537 + }, + { + "epoch": 2.57, + "learning_rate": 2.8672316384180794e-06, + "loss": 0.3459, + "step": 31538 + }, + { + "epoch": 2.57, + "learning_rate": 2.8666883963494136e-06, + "loss": 0.3661, + "step": 31539 + }, + { + "epoch": 2.57, + "learning_rate": 2.866145154280748e-06, + "loss": 0.444, + "step": 31540 + }, + { + "epoch": 2.57, + "learning_rate": 2.865601912212082e-06, + "loss": 0.1214, + "step": 31541 + }, + { + "epoch": 2.57, + "learning_rate": 2.8650586701434163e-06, + "loss": 0.0734, + "step": 31542 + }, + { + "epoch": 2.57, + "learning_rate": 2.8645154280747506e-06, + "loss": 0.118, + "step": 31543 + }, + { + "epoch": 2.57, + "learning_rate": 2.8639721860060844e-06, + "loss": 0.4409, + "step": 31544 + }, + { + "epoch": 2.57, + "learning_rate": 2.8634289439374186e-06, + "loss": 0.23, + "step": 31545 + }, + { + "epoch": 2.57, + "learning_rate": 2.862885701868753e-06, + "loss": 0.3609, + "step": 31546 + }, + { + "epoch": 2.57, + "learning_rate": 2.862342459800087e-06, + "loss": 0.4807, + "step": 31547 + }, + { + "epoch": 2.57, + "learning_rate": 2.8617992177314213e-06, + "loss": 0.0945, + "step": 31548 + }, + { + "epoch": 2.57, + "learning_rate": 2.8612559756627555e-06, + "loss": 0.133, + "step": 31549 + }, + { + "epoch": 2.57, + "learning_rate": 2.8607127335940898e-06, + "loss": 0.2607, + "step": 31550 + }, + { + "epoch": 2.57, + "learning_rate": 2.860169491525424e-06, + "loss": 0.1945, + "step": 31551 + }, + { + "epoch": 2.57, + "learning_rate": 2.8596262494567582e-06, + "loss": 0.2781, + "step": 31552 + }, + { + "epoch": 2.57, + "learning_rate": 2.8590830073880924e-06, + "loss": 0.2436, + "step": 31553 + }, + { + "epoch": 2.57, + "learning_rate": 2.8585397653194263e-06, + "loss": 0.374, + "step": 31554 + }, + { + "epoch": 2.57, + "learning_rate": 2.8579965232507605e-06, + "loss": 0.1109, + "step": 31555 + }, + { + "epoch": 2.57, + "learning_rate": 2.8574532811820947e-06, + "loss": 0.3559, + "step": 31556 + }, + { + "epoch": 2.57, + "learning_rate": 2.856910039113429e-06, + "loss": 0.0804, + "step": 31557 + }, + { + "epoch": 2.57, + "learning_rate": 2.856366797044763e-06, + "loss": 0.222, + "step": 31558 + }, + { + "epoch": 2.57, + "learning_rate": 2.855823554976098e-06, + "loss": 0.2596, + "step": 31559 + }, + { + "epoch": 2.57, + "learning_rate": 2.855280312907432e-06, + "loss": 0.0509, + "step": 31560 + }, + { + "epoch": 2.57, + "learning_rate": 2.8547370708387663e-06, + "loss": 0.1326, + "step": 31561 + }, + { + "epoch": 2.57, + "learning_rate": 2.8541938287701005e-06, + "loss": 0.1571, + "step": 31562 + }, + { + "epoch": 2.57, + "learning_rate": 2.8536505867014343e-06, + "loss": 0.0846, + "step": 31563 + }, + { + "epoch": 2.57, + "learning_rate": 2.8531073446327686e-06, + "loss": 0.3221, + "step": 31564 + }, + { + "epoch": 2.57, + "learning_rate": 2.852564102564103e-06, + "loss": 0.535, + "step": 31565 + }, + { + "epoch": 2.57, + "learning_rate": 2.852020860495437e-06, + "loss": 0.2294, + "step": 31566 + }, + { + "epoch": 2.57, + "learning_rate": 2.8514776184267713e-06, + "loss": 0.493, + "step": 31567 + }, + { + "epoch": 2.57, + "learning_rate": 2.8509343763581055e-06, + "loss": 0.3007, + "step": 31568 + }, + { + "epoch": 2.57, + "learning_rate": 2.8503911342894397e-06, + "loss": 0.0734, + "step": 31569 + }, + { + "epoch": 2.57, + "learning_rate": 2.849847892220774e-06, + "loss": 0.1775, + "step": 31570 + }, + { + "epoch": 2.57, + "learning_rate": 2.849304650152108e-06, + "loss": 0.3861, + "step": 31571 + }, + { + "epoch": 2.57, + "learning_rate": 2.8487614080834424e-06, + "loss": 0.2559, + "step": 31572 + }, + { + "epoch": 2.57, + "learning_rate": 2.8482181660147762e-06, + "loss": 0.1842, + "step": 31573 + }, + { + "epoch": 2.57, + "learning_rate": 2.8476749239461104e-06, + "loss": 0.0569, + "step": 31574 + }, + { + "epoch": 2.57, + "learning_rate": 2.8471316818774447e-06, + "loss": 0.1236, + "step": 31575 + }, + { + "epoch": 2.57, + "learning_rate": 2.846588439808779e-06, + "loss": 0.4085, + "step": 31576 + }, + { + "epoch": 2.57, + "learning_rate": 2.846045197740113e-06, + "loss": 0.3291, + "step": 31577 + }, + { + "epoch": 2.57, + "learning_rate": 2.8455019556714474e-06, + "loss": 0.3481, + "step": 31578 + }, + { + "epoch": 2.57, + "learning_rate": 2.8449587136027816e-06, + "loss": 0.3362, + "step": 31579 + }, + { + "epoch": 2.57, + "learning_rate": 2.844415471534116e-06, + "loss": 0.3939, + "step": 31580 + }, + { + "epoch": 2.57, + "learning_rate": 2.8438722294654505e-06, + "loss": 0.1184, + "step": 31581 + }, + { + "epoch": 2.57, + "learning_rate": 2.843328987396784e-06, + "loss": 0.2302, + "step": 31582 + }, + { + "epoch": 2.57, + "learning_rate": 2.842785745328118e-06, + "loss": 0.1867, + "step": 31583 + }, + { + "epoch": 2.57, + "learning_rate": 2.8422425032594523e-06, + "loss": 0.3351, + "step": 31584 + }, + { + "epoch": 2.57, + "learning_rate": 2.8416992611907866e-06, + "loss": 0.2901, + "step": 31585 + }, + { + "epoch": 2.57, + "learning_rate": 2.841156019122121e-06, + "loss": 0.1274, + "step": 31586 + }, + { + "epoch": 2.57, + "learning_rate": 2.8406127770534554e-06, + "loss": 0.2574, + "step": 31587 + }, + { + "epoch": 2.57, + "learning_rate": 2.8400695349847897e-06, + "loss": 0.1298, + "step": 31588 + }, + { + "epoch": 2.57, + "learning_rate": 2.839526292916124e-06, + "loss": 0.444, + "step": 31589 + }, + { + "epoch": 2.57, + "learning_rate": 2.838983050847458e-06, + "loss": 0.2094, + "step": 31590 + }, + { + "epoch": 2.57, + "learning_rate": 2.8384398087787924e-06, + "loss": 0.1547, + "step": 31591 + }, + { + "epoch": 2.57, + "learning_rate": 2.837896566710126e-06, + "loss": 0.1039, + "step": 31592 + }, + { + "epoch": 2.57, + "learning_rate": 2.8373533246414604e-06, + "loss": 0.1654, + "step": 31593 + }, + { + "epoch": 2.57, + "learning_rate": 2.8368100825727946e-06, + "loss": 0.3897, + "step": 31594 + }, + { + "epoch": 2.57, + "learning_rate": 2.836266840504129e-06, + "loss": 0.1202, + "step": 31595 + }, + { + "epoch": 2.57, + "learning_rate": 2.835723598435463e-06, + "loss": 0.1415, + "step": 31596 + }, + { + "epoch": 2.57, + "learning_rate": 2.8351803563667973e-06, + "loss": 0.2067, + "step": 31597 + }, + { + "epoch": 2.57, + "learning_rate": 2.8346371142981316e-06, + "loss": 0.1107, + "step": 31598 + }, + { + "epoch": 2.57, + "learning_rate": 2.8340938722294658e-06, + "loss": 0.2093, + "step": 31599 + }, + { + "epoch": 2.57, + "learning_rate": 2.8335506301608e-06, + "loss": 0.0648, + "step": 31600 + }, + { + "epoch": 2.58, + "learning_rate": 2.833007388092134e-06, + "loss": 0.5554, + "step": 31601 + }, + { + "epoch": 2.58, + "learning_rate": 2.832464146023468e-06, + "loss": 0.1714, + "step": 31602 + }, + { + "epoch": 2.58, + "learning_rate": 2.8319209039548023e-06, + "loss": 0.2154, + "step": 31603 + }, + { + "epoch": 2.58, + "learning_rate": 2.8313776618861365e-06, + "loss": 0.1323, + "step": 31604 + }, + { + "epoch": 2.58, + "learning_rate": 2.8308344198174707e-06, + "loss": 0.2399, + "step": 31605 + }, + { + "epoch": 2.58, + "learning_rate": 2.830291177748805e-06, + "loss": 0.0731, + "step": 31606 + }, + { + "epoch": 2.58, + "learning_rate": 2.829747935680139e-06, + "loss": 0.1043, + "step": 31607 + }, + { + "epoch": 2.58, + "learning_rate": 2.829204693611474e-06, + "loss": 0.1853, + "step": 31608 + }, + { + "epoch": 2.58, + "learning_rate": 2.828661451542808e-06, + "loss": 0.0858, + "step": 31609 + }, + { + "epoch": 2.58, + "learning_rate": 2.8281182094741423e-06, + "loss": 0.3216, + "step": 31610 + }, + { + "epoch": 2.58, + "learning_rate": 2.8275749674054757e-06, + "loss": 0.1156, + "step": 31611 + }, + { + "epoch": 2.58, + "learning_rate": 2.82703172533681e-06, + "loss": 0.3451, + "step": 31612 + }, + { + "epoch": 2.58, + "learning_rate": 2.8264884832681446e-06, + "loss": 0.093, + "step": 31613 + }, + { + "epoch": 2.58, + "learning_rate": 2.825945241199479e-06, + "loss": 0.1423, + "step": 31614 + }, + { + "epoch": 2.58, + "learning_rate": 2.825401999130813e-06, + "loss": 0.0879, + "step": 31615 + }, + { + "epoch": 2.58, + "learning_rate": 2.8248587570621473e-06, + "loss": 0.5353, + "step": 31616 + }, + { + "epoch": 2.58, + "learning_rate": 2.8243155149934815e-06, + "loss": 0.2482, + "step": 31617 + }, + { + "epoch": 2.58, + "learning_rate": 2.8237722729248157e-06, + "loss": 0.3268, + "step": 31618 + }, + { + "epoch": 2.58, + "learning_rate": 2.82322903085615e-06, + "loss": 0.0492, + "step": 31619 + }, + { + "epoch": 2.58, + "learning_rate": 2.8226857887874838e-06, + "loss": 0.426, + "step": 31620 + }, + { + "epoch": 2.58, + "learning_rate": 2.822142546718818e-06, + "loss": 0.3192, + "step": 31621 + }, + { + "epoch": 2.58, + "learning_rate": 2.8215993046501522e-06, + "loss": 0.1087, + "step": 31622 + }, + { + "epoch": 2.58, + "learning_rate": 2.8210560625814865e-06, + "loss": 0.2501, + "step": 31623 + }, + { + "epoch": 2.58, + "learning_rate": 2.8205128205128207e-06, + "loss": 0.0846, + "step": 31624 + }, + { + "epoch": 2.58, + "learning_rate": 2.819969578444155e-06, + "loss": 0.1768, + "step": 31625 + }, + { + "epoch": 2.58, + "learning_rate": 2.819426336375489e-06, + "loss": 0.429, + "step": 31626 + }, + { + "epoch": 2.58, + "learning_rate": 2.8188830943068234e-06, + "loss": 0.2647, + "step": 31627 + }, + { + "epoch": 2.58, + "learning_rate": 2.8183398522381576e-06, + "loss": 0.0464, + "step": 31628 + }, + { + "epoch": 2.58, + "learning_rate": 2.817796610169492e-06, + "loss": 0.1653, + "step": 31629 + }, + { + "epoch": 2.58, + "learning_rate": 2.8172533681008257e-06, + "loss": 0.2756, + "step": 31630 + }, + { + "epoch": 2.58, + "learning_rate": 2.81671012603216e-06, + "loss": 0.0364, + "step": 31631 + }, + { + "epoch": 2.58, + "learning_rate": 2.816166883963494e-06, + "loss": 0.2326, + "step": 31632 + }, + { + "epoch": 2.58, + "learning_rate": 2.8156236418948284e-06, + "loss": 0.1926, + "step": 31633 + }, + { + "epoch": 2.58, + "learning_rate": 2.8150803998261626e-06, + "loss": 0.1038, + "step": 31634 + }, + { + "epoch": 2.58, + "learning_rate": 2.8145371577574972e-06, + "loss": 0.524, + "step": 31635 + }, + { + "epoch": 2.58, + "learning_rate": 2.8139939156888315e-06, + "loss": 0.2874, + "step": 31636 + }, + { + "epoch": 2.58, + "learning_rate": 2.8134506736201657e-06, + "loss": 0.1316, + "step": 31637 + }, + { + "epoch": 2.58, + "learning_rate": 2.8129074315515e-06, + "loss": 0.2123, + "step": 31638 + }, + { + "epoch": 2.58, + "learning_rate": 2.8123641894828333e-06, + "loss": 0.2284, + "step": 31639 + }, + { + "epoch": 2.58, + "learning_rate": 2.811820947414168e-06, + "loss": 0.1726, + "step": 31640 + }, + { + "epoch": 2.58, + "learning_rate": 2.811277705345502e-06, + "loss": 0.1881, + "step": 31641 + }, + { + "epoch": 2.58, + "learning_rate": 2.8107344632768364e-06, + "loss": 0.3713, + "step": 31642 + }, + { + "epoch": 2.58, + "learning_rate": 2.8101912212081707e-06, + "loss": 0.0582, + "step": 31643 + }, + { + "epoch": 2.58, + "learning_rate": 2.809647979139505e-06, + "loss": 0.0424, + "step": 31644 + }, + { + "epoch": 2.58, + "learning_rate": 2.809104737070839e-06, + "loss": 0.5043, + "step": 31645 + }, + { + "epoch": 2.58, + "learning_rate": 2.8085614950021733e-06, + "loss": 0.309, + "step": 31646 + }, + { + "epoch": 2.58, + "learning_rate": 2.8080182529335076e-06, + "loss": 0.0686, + "step": 31647 + }, + { + "epoch": 2.58, + "learning_rate": 2.807475010864842e-06, + "loss": 0.1082, + "step": 31648 + }, + { + "epoch": 2.58, + "learning_rate": 2.8069317687961756e-06, + "loss": 0.3103, + "step": 31649 + }, + { + "epoch": 2.58, + "learning_rate": 2.80638852672751e-06, + "loss": 0.2653, + "step": 31650 + }, + { + "epoch": 2.58, + "learning_rate": 2.805845284658844e-06, + "loss": 0.2812, + "step": 31651 + }, + { + "epoch": 2.58, + "learning_rate": 2.8053020425901783e-06, + "loss": 0.1623, + "step": 31652 + }, + { + "epoch": 2.58, + "learning_rate": 2.8047588005215125e-06, + "loss": 0.2982, + "step": 31653 + }, + { + "epoch": 2.58, + "learning_rate": 2.8042155584528468e-06, + "loss": 0.1059, + "step": 31654 + }, + { + "epoch": 2.58, + "learning_rate": 2.803672316384181e-06, + "loss": 0.4076, + "step": 31655 + }, + { + "epoch": 2.58, + "learning_rate": 2.8031290743155152e-06, + "loss": 0.2248, + "step": 31656 + }, + { + "epoch": 2.58, + "learning_rate": 2.8025858322468495e-06, + "loss": 0.3825, + "step": 31657 + }, + { + "epoch": 2.58, + "learning_rate": 2.8020425901781833e-06, + "loss": 0.3191, + "step": 31658 + }, + { + "epoch": 2.58, + "learning_rate": 2.8014993481095175e-06, + "loss": 0.2514, + "step": 31659 + }, + { + "epoch": 2.58, + "learning_rate": 2.8009561060408517e-06, + "loss": 0.3282, + "step": 31660 + }, + { + "epoch": 2.58, + "learning_rate": 2.800412863972186e-06, + "loss": 0.2155, + "step": 31661 + }, + { + "epoch": 2.58, + "learning_rate": 2.7998696219035206e-06, + "loss": 0.2711, + "step": 31662 + }, + { + "epoch": 2.58, + "learning_rate": 2.799326379834855e-06, + "loss": 0.1094, + "step": 31663 + }, + { + "epoch": 2.58, + "learning_rate": 2.798783137766189e-06, + "loss": 0.1814, + "step": 31664 + }, + { + "epoch": 2.58, + "learning_rate": 2.7982398956975233e-06, + "loss": 0.2542, + "step": 31665 + }, + { + "epoch": 2.58, + "learning_rate": 2.7976966536288575e-06, + "loss": 0.1256, + "step": 31666 + }, + { + "epoch": 2.58, + "learning_rate": 2.7971534115601918e-06, + "loss": 0.1461, + "step": 31667 + }, + { + "epoch": 2.58, + "learning_rate": 2.7966101694915256e-06, + "loss": 0.378, + "step": 31668 + }, + { + "epoch": 2.58, + "learning_rate": 2.79606692742286e-06, + "loss": 0.2261, + "step": 31669 + }, + { + "epoch": 2.58, + "learning_rate": 2.795523685354194e-06, + "loss": 0.0557, + "step": 31670 + }, + { + "epoch": 2.58, + "learning_rate": 2.7949804432855283e-06, + "loss": 0.0934, + "step": 31671 + }, + { + "epoch": 2.58, + "learning_rate": 2.7944372012168625e-06, + "loss": 0.228, + "step": 31672 + }, + { + "epoch": 2.58, + "learning_rate": 2.7938939591481967e-06, + "loss": 0.2318, + "step": 31673 + }, + { + "epoch": 2.58, + "learning_rate": 2.793350717079531e-06, + "loss": 0.0925, + "step": 31674 + }, + { + "epoch": 2.58, + "learning_rate": 2.792807475010865e-06, + "loss": 0.1703, + "step": 31675 + }, + { + "epoch": 2.58, + "learning_rate": 2.7922642329421994e-06, + "loss": 0.3326, + "step": 31676 + }, + { + "epoch": 2.58, + "learning_rate": 2.7917209908735332e-06, + "loss": 0.0971, + "step": 31677 + }, + { + "epoch": 2.58, + "learning_rate": 2.7911777488048675e-06, + "loss": 0.2964, + "step": 31678 + }, + { + "epoch": 2.58, + "learning_rate": 2.7906345067362017e-06, + "loss": 0.1642, + "step": 31679 + }, + { + "epoch": 2.58, + "learning_rate": 2.790091264667536e-06, + "loss": 0.386, + "step": 31680 + }, + { + "epoch": 2.58, + "learning_rate": 2.78954802259887e-06, + "loss": 0.2174, + "step": 31681 + }, + { + "epoch": 2.58, + "learning_rate": 2.7890047805302044e-06, + "loss": 0.0701, + "step": 31682 + }, + { + "epoch": 2.58, + "learning_rate": 2.7884615384615386e-06, + "loss": 0.1561, + "step": 31683 + }, + { + "epoch": 2.58, + "learning_rate": 2.787918296392873e-06, + "loss": 0.3169, + "step": 31684 + }, + { + "epoch": 2.58, + "learning_rate": 2.7873750543242075e-06, + "loss": 0.3359, + "step": 31685 + }, + { + "epoch": 2.58, + "learning_rate": 2.7868318122555417e-06, + "loss": 0.4328, + "step": 31686 + }, + { + "epoch": 2.58, + "learning_rate": 2.786288570186875e-06, + "loss": 0.313, + "step": 31687 + }, + { + "epoch": 2.58, + "learning_rate": 2.7857453281182093e-06, + "loss": 0.3305, + "step": 31688 + }, + { + "epoch": 2.58, + "learning_rate": 2.785202086049544e-06, + "loss": 0.2512, + "step": 31689 + }, + { + "epoch": 2.58, + "learning_rate": 2.7846588439808782e-06, + "loss": 0.1058, + "step": 31690 + }, + { + "epoch": 2.58, + "learning_rate": 2.7841156019122125e-06, + "loss": 0.3887, + "step": 31691 + }, + { + "epoch": 2.58, + "learning_rate": 2.7835723598435467e-06, + "loss": 0.3632, + "step": 31692 + }, + { + "epoch": 2.58, + "learning_rate": 2.783029117774881e-06, + "loss": 0.411, + "step": 31693 + }, + { + "epoch": 2.58, + "learning_rate": 2.782485875706215e-06, + "loss": 0.3555, + "step": 31694 + }, + { + "epoch": 2.58, + "learning_rate": 2.7819426336375494e-06, + "loss": 0.236, + "step": 31695 + }, + { + "epoch": 2.58, + "learning_rate": 2.781399391568883e-06, + "loss": 0.4723, + "step": 31696 + }, + { + "epoch": 2.58, + "learning_rate": 2.7808561495002174e-06, + "loss": 0.2311, + "step": 31697 + }, + { + "epoch": 2.58, + "learning_rate": 2.7803129074315516e-06, + "loss": 0.4336, + "step": 31698 + }, + { + "epoch": 2.58, + "learning_rate": 2.779769665362886e-06, + "loss": 0.1535, + "step": 31699 + }, + { + "epoch": 2.58, + "learning_rate": 2.77922642329422e-06, + "loss": 0.3562, + "step": 31700 + }, + { + "epoch": 2.58, + "learning_rate": 2.7786831812255543e-06, + "loss": 0.3645, + "step": 31701 + }, + { + "epoch": 2.58, + "learning_rate": 2.7781399391568886e-06, + "loss": 0.1228, + "step": 31702 + }, + { + "epoch": 2.58, + "learning_rate": 2.777596697088223e-06, + "loss": 0.0844, + "step": 31703 + }, + { + "epoch": 2.58, + "learning_rate": 2.777053455019557e-06, + "loss": 0.292, + "step": 31704 + }, + { + "epoch": 2.58, + "learning_rate": 2.7765102129508913e-06, + "loss": 0.4462, + "step": 31705 + }, + { + "epoch": 2.58, + "learning_rate": 2.775966970882225e-06, + "loss": 0.1889, + "step": 31706 + }, + { + "epoch": 2.58, + "learning_rate": 2.7754237288135593e-06, + "loss": 0.2084, + "step": 31707 + }, + { + "epoch": 2.58, + "learning_rate": 2.7748804867448935e-06, + "loss": 0.2615, + "step": 31708 + }, + { + "epoch": 2.58, + "learning_rate": 2.7743372446762278e-06, + "loss": 0.4151, + "step": 31709 + }, + { + "epoch": 2.58, + "learning_rate": 2.773794002607562e-06, + "loss": 0.3509, + "step": 31710 + }, + { + "epoch": 2.58, + "learning_rate": 2.7732507605388962e-06, + "loss": 0.1086, + "step": 31711 + }, + { + "epoch": 2.58, + "learning_rate": 2.772707518470231e-06, + "loss": 0.1362, + "step": 31712 + }, + { + "epoch": 2.58, + "learning_rate": 2.772164276401565e-06, + "loss": 0.2291, + "step": 31713 + }, + { + "epoch": 2.58, + "learning_rate": 2.7716210343328993e-06, + "loss": 0.28, + "step": 31714 + }, + { + "epoch": 2.58, + "learning_rate": 2.7710777922642327e-06, + "loss": 0.124, + "step": 31715 + }, + { + "epoch": 2.58, + "learning_rate": 2.7705345501955674e-06, + "loss": 0.3757, + "step": 31716 + }, + { + "epoch": 2.58, + "learning_rate": 2.7699913081269016e-06, + "loss": 0.2627, + "step": 31717 + }, + { + "epoch": 2.58, + "learning_rate": 2.769448066058236e-06, + "loss": 0.1176, + "step": 31718 + }, + { + "epoch": 2.58, + "learning_rate": 2.76890482398957e-06, + "loss": 0.2692, + "step": 31719 + }, + { + "epoch": 2.58, + "learning_rate": 2.7683615819209043e-06, + "loss": 0.1477, + "step": 31720 + }, + { + "epoch": 2.58, + "learning_rate": 2.7678183398522385e-06, + "loss": 0.1962, + "step": 31721 + }, + { + "epoch": 2.58, + "learning_rate": 2.7672750977835728e-06, + "loss": 0.2584, + "step": 31722 + }, + { + "epoch": 2.58, + "learning_rate": 2.766731855714907e-06, + "loss": 0.3452, + "step": 31723 + }, + { + "epoch": 2.59, + "learning_rate": 2.7661886136462412e-06, + "loss": 0.0911, + "step": 31724 + }, + { + "epoch": 2.59, + "learning_rate": 2.765645371577575e-06, + "loss": 0.3098, + "step": 31725 + }, + { + "epoch": 2.59, + "learning_rate": 2.7651021295089093e-06, + "loss": 0.3549, + "step": 31726 + }, + { + "epoch": 2.59, + "learning_rate": 2.7645588874402435e-06, + "loss": 0.1413, + "step": 31727 + }, + { + "epoch": 2.59, + "learning_rate": 2.7640156453715777e-06, + "loss": 0.2151, + "step": 31728 + }, + { + "epoch": 2.59, + "learning_rate": 2.763472403302912e-06, + "loss": 0.1172, + "step": 31729 + }, + { + "epoch": 2.59, + "learning_rate": 2.762929161234246e-06, + "loss": 0.2686, + "step": 31730 + }, + { + "epoch": 2.59, + "learning_rate": 2.7623859191655804e-06, + "loss": 0.1821, + "step": 31731 + }, + { + "epoch": 2.59, + "learning_rate": 2.7618426770969146e-06, + "loss": 0.2191, + "step": 31732 + }, + { + "epoch": 2.59, + "learning_rate": 2.761299435028249e-06, + "loss": 0.3339, + "step": 31733 + }, + { + "epoch": 2.59, + "learning_rate": 2.7607561929595827e-06, + "loss": 0.2288, + "step": 31734 + }, + { + "epoch": 2.59, + "learning_rate": 2.760212950890917e-06, + "loss": 0.2695, + "step": 31735 + }, + { + "epoch": 2.59, + "learning_rate": 2.759669708822251e-06, + "loss": 0.2469, + "step": 31736 + }, + { + "epoch": 2.59, + "learning_rate": 2.7591264667535854e-06, + "loss": 0.0864, + "step": 31737 + }, + { + "epoch": 2.59, + "learning_rate": 2.7585832246849196e-06, + "loss": 0.339, + "step": 31738 + }, + { + "epoch": 2.59, + "learning_rate": 2.7580399826162542e-06, + "loss": 0.1866, + "step": 31739 + }, + { + "epoch": 2.59, + "learning_rate": 2.7574967405475885e-06, + "loss": 0.1036, + "step": 31740 + }, + { + "epoch": 2.59, + "learning_rate": 2.7569534984789227e-06, + "loss": 0.3077, + "step": 31741 + }, + { + "epoch": 2.59, + "learning_rate": 2.756410256410257e-06, + "loss": 0.1813, + "step": 31742 + }, + { + "epoch": 2.59, + "learning_rate": 2.755867014341591e-06, + "loss": 0.5241, + "step": 31743 + }, + { + "epoch": 2.59, + "learning_rate": 2.755323772272925e-06, + "loss": 0.5654, + "step": 31744 + }, + { + "epoch": 2.59, + "learning_rate": 2.754780530204259e-06, + "loss": 0.2446, + "step": 31745 + }, + { + "epoch": 2.59, + "learning_rate": 2.7542372881355934e-06, + "loss": 0.0826, + "step": 31746 + }, + { + "epoch": 2.59, + "learning_rate": 2.7536940460669277e-06, + "loss": 0.3151, + "step": 31747 + }, + { + "epoch": 2.59, + "learning_rate": 2.753150803998262e-06, + "loss": 0.2567, + "step": 31748 + }, + { + "epoch": 2.59, + "learning_rate": 2.752607561929596e-06, + "loss": 0.2563, + "step": 31749 + }, + { + "epoch": 2.59, + "learning_rate": 2.7520643198609304e-06, + "loss": 0.3416, + "step": 31750 + }, + { + "epoch": 2.59, + "eval_accuracy": 0.8435048395313296, + "eval_loss": 0.488090455532074, + "eval_runtime": 22.2773, + "eval_samples_per_second": 440.583, + "eval_steps_per_second": 3.456, + "step": 31750 + }, + { + "epoch": 2.59, + "learning_rate": 2.7515210777922646e-06, + "loss": 0.4272, + "step": 31751 + }, + { + "epoch": 2.59, + "learning_rate": 2.750977835723599e-06, + "loss": 0.0199, + "step": 31752 + }, + { + "epoch": 2.59, + "learning_rate": 2.7504345936549326e-06, + "loss": 0.1777, + "step": 31753 + }, + { + "epoch": 2.59, + "learning_rate": 2.749891351586267e-06, + "loss": 0.1052, + "step": 31754 + }, + { + "epoch": 2.59, + "learning_rate": 2.749348109517601e-06, + "loss": 0.1118, + "step": 31755 + }, + { + "epoch": 2.59, + "learning_rate": 2.7488048674489353e-06, + "loss": 0.1159, + "step": 31756 + }, + { + "epoch": 2.59, + "learning_rate": 2.7482616253802696e-06, + "loss": 0.2275, + "step": 31757 + }, + { + "epoch": 2.59, + "learning_rate": 2.7477183833116038e-06, + "loss": 0.1959, + "step": 31758 + }, + { + "epoch": 2.59, + "learning_rate": 2.747175141242938e-06, + "loss": 0.4609, + "step": 31759 + }, + { + "epoch": 2.59, + "learning_rate": 2.7466318991742722e-06, + "loss": 0.2285, + "step": 31760 + }, + { + "epoch": 2.59, + "learning_rate": 2.7460886571056065e-06, + "loss": 0.3606, + "step": 31761 + }, + { + "epoch": 2.59, + "learning_rate": 2.745545415036941e-06, + "loss": 0.2934, + "step": 31762 + }, + { + "epoch": 2.59, + "learning_rate": 2.7450021729682745e-06, + "loss": 0.2154, + "step": 31763 + }, + { + "epoch": 2.59, + "learning_rate": 2.7444589308996087e-06, + "loss": 0.2354, + "step": 31764 + }, + { + "epoch": 2.59, + "learning_rate": 2.743915688830943e-06, + "loss": 0.1522, + "step": 31765 + }, + { + "epoch": 2.59, + "learning_rate": 2.7433724467622776e-06, + "loss": 0.4415, + "step": 31766 + }, + { + "epoch": 2.59, + "learning_rate": 2.742829204693612e-06, + "loss": 0.1579, + "step": 31767 + }, + { + "epoch": 2.59, + "learning_rate": 2.742285962624946e-06, + "loss": 0.16, + "step": 31768 + }, + { + "epoch": 2.59, + "learning_rate": 2.7417427205562803e-06, + "loss": 0.2069, + "step": 31769 + }, + { + "epoch": 2.59, + "learning_rate": 2.7411994784876145e-06, + "loss": 0.4048, + "step": 31770 + }, + { + "epoch": 2.59, + "learning_rate": 2.7406562364189488e-06, + "loss": 0.1052, + "step": 31771 + }, + { + "epoch": 2.59, + "learning_rate": 2.7401129943502826e-06, + "loss": 0.2231, + "step": 31772 + }, + { + "epoch": 2.59, + "learning_rate": 2.739569752281617e-06, + "loss": 0.1728, + "step": 31773 + }, + { + "epoch": 2.59, + "learning_rate": 2.739026510212951e-06, + "loss": 0.0498, + "step": 31774 + }, + { + "epoch": 2.59, + "learning_rate": 2.7384832681442853e-06, + "loss": 0.2312, + "step": 31775 + }, + { + "epoch": 2.59, + "learning_rate": 2.7379400260756195e-06, + "loss": 0.2196, + "step": 31776 + }, + { + "epoch": 2.59, + "learning_rate": 2.7373967840069537e-06, + "loss": 0.0755, + "step": 31777 + }, + { + "epoch": 2.59, + "learning_rate": 2.736853541938288e-06, + "loss": 0.2272, + "step": 31778 + }, + { + "epoch": 2.59, + "learning_rate": 2.736310299869622e-06, + "loss": 0.156, + "step": 31779 + }, + { + "epoch": 2.59, + "learning_rate": 2.7357670578009564e-06, + "loss": 0.5197, + "step": 31780 + }, + { + "epoch": 2.59, + "learning_rate": 2.7352238157322907e-06, + "loss": 0.3551, + "step": 31781 + }, + { + "epoch": 2.59, + "learning_rate": 2.7346805736636245e-06, + "loss": 0.1417, + "step": 31782 + }, + { + "epoch": 2.59, + "learning_rate": 2.7341373315949587e-06, + "loss": 0.1081, + "step": 31783 + }, + { + "epoch": 2.59, + "learning_rate": 2.733594089526293e-06, + "loss": 0.3195, + "step": 31784 + }, + { + "epoch": 2.59, + "learning_rate": 2.733050847457627e-06, + "loss": 0.182, + "step": 31785 + }, + { + "epoch": 2.59, + "learning_rate": 2.7325076053889614e-06, + "loss": 0.0949, + "step": 31786 + }, + { + "epoch": 2.59, + "learning_rate": 2.7319643633202956e-06, + "loss": 0.538, + "step": 31787 + }, + { + "epoch": 2.59, + "learning_rate": 2.73142112125163e-06, + "loss": 0.3224, + "step": 31788 + }, + { + "epoch": 2.59, + "learning_rate": 2.7308778791829645e-06, + "loss": 0.8355, + "step": 31789 + }, + { + "epoch": 2.59, + "learning_rate": 2.7303346371142987e-06, + "loss": 0.0822, + "step": 31790 + }, + { + "epoch": 2.59, + "learning_rate": 2.729791395045632e-06, + "loss": 0.3288, + "step": 31791 + }, + { + "epoch": 2.59, + "learning_rate": 2.7292481529769663e-06, + "loss": 0.2149, + "step": 31792 + }, + { + "epoch": 2.59, + "learning_rate": 2.728704910908301e-06, + "loss": 0.2443, + "step": 31793 + }, + { + "epoch": 2.59, + "learning_rate": 2.7281616688396352e-06, + "loss": 0.2032, + "step": 31794 + }, + { + "epoch": 2.59, + "learning_rate": 2.7276184267709695e-06, + "loss": 0.3827, + "step": 31795 + }, + { + "epoch": 2.59, + "learning_rate": 2.7270751847023037e-06, + "loss": 0.1002, + "step": 31796 + }, + { + "epoch": 2.59, + "learning_rate": 2.726531942633638e-06, + "loss": 0.261, + "step": 31797 + }, + { + "epoch": 2.59, + "learning_rate": 2.725988700564972e-06, + "loss": 0.1354, + "step": 31798 + }, + { + "epoch": 2.59, + "learning_rate": 2.7254454584963064e-06, + "loss": 0.2077, + "step": 31799 + }, + { + "epoch": 2.59, + "learning_rate": 2.7249022164276406e-06, + "loss": 0.3489, + "step": 31800 + }, + { + "epoch": 2.59, + "learning_rate": 2.7243589743589744e-06, + "loss": 0.2609, + "step": 31801 + }, + { + "epoch": 2.59, + "learning_rate": 2.7238157322903087e-06, + "loss": 0.1965, + "step": 31802 + }, + { + "epoch": 2.59, + "learning_rate": 2.723272490221643e-06, + "loss": 0.3627, + "step": 31803 + }, + { + "epoch": 2.59, + "learning_rate": 2.722729248152977e-06, + "loss": 0.2398, + "step": 31804 + }, + { + "epoch": 2.59, + "learning_rate": 2.7221860060843113e-06, + "loss": 0.4343, + "step": 31805 + }, + { + "epoch": 2.59, + "learning_rate": 2.7216427640156456e-06, + "loss": 0.0856, + "step": 31806 + }, + { + "epoch": 2.59, + "learning_rate": 2.72109952194698e-06, + "loss": 0.0795, + "step": 31807 + }, + { + "epoch": 2.59, + "learning_rate": 2.720556279878314e-06, + "loss": 0.0944, + "step": 31808 + }, + { + "epoch": 2.59, + "learning_rate": 2.7200130378096483e-06, + "loss": 0.1383, + "step": 31809 + }, + { + "epoch": 2.59, + "learning_rate": 2.719469795740982e-06, + "loss": 0.2364, + "step": 31810 + }, + { + "epoch": 2.59, + "learning_rate": 2.7189265536723163e-06, + "loss": 0.1529, + "step": 31811 + }, + { + "epoch": 2.59, + "learning_rate": 2.7183833116036505e-06, + "loss": 0.2743, + "step": 31812 + }, + { + "epoch": 2.59, + "learning_rate": 2.7178400695349848e-06, + "loss": 0.1266, + "step": 31813 + }, + { + "epoch": 2.59, + "learning_rate": 2.717296827466319e-06, + "loss": 0.1264, + "step": 31814 + }, + { + "epoch": 2.59, + "learning_rate": 2.7167535853976532e-06, + "loss": 0.3487, + "step": 31815 + }, + { + "epoch": 2.59, + "learning_rate": 2.716210343328988e-06, + "loss": 0.4133, + "step": 31816 + }, + { + "epoch": 2.59, + "learning_rate": 2.715667101260322e-06, + "loss": 0.37, + "step": 31817 + }, + { + "epoch": 2.59, + "learning_rate": 2.7151238591916563e-06, + "loss": 0.0819, + "step": 31818 + }, + { + "epoch": 2.59, + "learning_rate": 2.7145806171229906e-06, + "loss": 0.4029, + "step": 31819 + }, + { + "epoch": 2.59, + "learning_rate": 2.7140373750543244e-06, + "loss": 0.3034, + "step": 31820 + }, + { + "epoch": 2.59, + "learning_rate": 2.7134941329856586e-06, + "loss": 0.1611, + "step": 31821 + }, + { + "epoch": 2.59, + "learning_rate": 2.712950890916993e-06, + "loss": 0.1659, + "step": 31822 + }, + { + "epoch": 2.59, + "learning_rate": 2.712407648848327e-06, + "loss": 0.1333, + "step": 31823 + }, + { + "epoch": 2.59, + "learning_rate": 2.7118644067796613e-06, + "loss": 0.1266, + "step": 31824 + }, + { + "epoch": 2.59, + "learning_rate": 2.7113211647109955e-06, + "loss": 0.2174, + "step": 31825 + }, + { + "epoch": 2.59, + "learning_rate": 2.7107779226423298e-06, + "loss": 0.4808, + "step": 31826 + }, + { + "epoch": 2.59, + "learning_rate": 2.710234680573664e-06, + "loss": 0.4836, + "step": 31827 + }, + { + "epoch": 2.59, + "learning_rate": 2.7096914385049982e-06, + "loss": 0.07, + "step": 31828 + }, + { + "epoch": 2.59, + "learning_rate": 2.709148196436332e-06, + "loss": 0.097, + "step": 31829 + }, + { + "epoch": 2.59, + "learning_rate": 2.7086049543676663e-06, + "loss": 0.2649, + "step": 31830 + }, + { + "epoch": 2.59, + "learning_rate": 2.7080617122990005e-06, + "loss": 0.1446, + "step": 31831 + }, + { + "epoch": 2.59, + "learning_rate": 2.7075184702303347e-06, + "loss": 0.5957, + "step": 31832 + }, + { + "epoch": 2.59, + "learning_rate": 2.706975228161669e-06, + "loss": 0.5952, + "step": 31833 + }, + { + "epoch": 2.59, + "learning_rate": 2.706431986093003e-06, + "loss": 0.1535, + "step": 31834 + }, + { + "epoch": 2.59, + "learning_rate": 2.7058887440243374e-06, + "loss": 0.4729, + "step": 31835 + }, + { + "epoch": 2.59, + "learning_rate": 2.7053455019556716e-06, + "loss": 0.3146, + "step": 31836 + }, + { + "epoch": 2.59, + "learning_rate": 2.704802259887006e-06, + "loss": 0.5085, + "step": 31837 + }, + { + "epoch": 2.59, + "learning_rate": 2.7042590178183405e-06, + "loss": 0.256, + "step": 31838 + }, + { + "epoch": 2.59, + "learning_rate": 2.703715775749674e-06, + "loss": 0.4123, + "step": 31839 + }, + { + "epoch": 2.59, + "learning_rate": 2.703172533681008e-06, + "loss": 0.141, + "step": 31840 + }, + { + "epoch": 2.59, + "learning_rate": 2.7026292916123424e-06, + "loss": 0.1282, + "step": 31841 + }, + { + "epoch": 2.59, + "learning_rate": 2.7020860495436766e-06, + "loss": 0.2716, + "step": 31842 + }, + { + "epoch": 2.59, + "learning_rate": 2.7015428074750113e-06, + "loss": 0.2757, + "step": 31843 + }, + { + "epoch": 2.59, + "learning_rate": 2.7009995654063455e-06, + "loss": 0.2572, + "step": 31844 + }, + { + "epoch": 2.59, + "learning_rate": 2.7004563233376797e-06, + "loss": 0.1078, + "step": 31845 + }, + { + "epoch": 2.6, + "learning_rate": 2.699913081269014e-06, + "loss": 0.2109, + "step": 31846 + }, + { + "epoch": 2.6, + "learning_rate": 2.699369839200348e-06, + "loss": 0.1701, + "step": 31847 + }, + { + "epoch": 2.6, + "learning_rate": 2.698826597131682e-06, + "loss": 0.1865, + "step": 31848 + }, + { + "epoch": 2.6, + "learning_rate": 2.6982833550630162e-06, + "loss": 0.1889, + "step": 31849 + }, + { + "epoch": 2.6, + "learning_rate": 2.6977401129943505e-06, + "loss": 0.3549, + "step": 31850 + }, + { + "epoch": 2.6, + "learning_rate": 2.6971968709256847e-06, + "loss": 0.1831, + "step": 31851 + }, + { + "epoch": 2.6, + "learning_rate": 2.696653628857019e-06, + "loss": 0.1591, + "step": 31852 + }, + { + "epoch": 2.6, + "learning_rate": 2.696110386788353e-06, + "loss": 0.2194, + "step": 31853 + }, + { + "epoch": 2.6, + "learning_rate": 2.6955671447196874e-06, + "loss": 0.1875, + "step": 31854 + }, + { + "epoch": 2.6, + "learning_rate": 2.6950239026510216e-06, + "loss": 0.1329, + "step": 31855 + }, + { + "epoch": 2.6, + "learning_rate": 2.694480660582356e-06, + "loss": 0.0718, + "step": 31856 + }, + { + "epoch": 2.6, + "learning_rate": 2.69393741851369e-06, + "loss": 0.1517, + "step": 31857 + }, + { + "epoch": 2.6, + "learning_rate": 2.693394176445024e-06, + "loss": 0.0994, + "step": 31858 + }, + { + "epoch": 2.6, + "learning_rate": 2.692850934376358e-06, + "loss": 0.1467, + "step": 31859 + }, + { + "epoch": 2.6, + "learning_rate": 2.6923076923076923e-06, + "loss": 0.1064, + "step": 31860 + }, + { + "epoch": 2.6, + "learning_rate": 2.6917644502390266e-06, + "loss": 0.3718, + "step": 31861 + }, + { + "epoch": 2.6, + "learning_rate": 2.691221208170361e-06, + "loss": 0.2269, + "step": 31862 + }, + { + "epoch": 2.6, + "learning_rate": 2.690677966101695e-06, + "loss": 0.1463, + "step": 31863 + }, + { + "epoch": 2.6, + "learning_rate": 2.6901347240330293e-06, + "loss": 0.3369, + "step": 31864 + }, + { + "epoch": 2.6, + "learning_rate": 2.689591481964364e-06, + "loss": 0.4008, + "step": 31865 + }, + { + "epoch": 2.6, + "learning_rate": 2.689048239895698e-06, + "loss": 0.3347, + "step": 31866 + }, + { + "epoch": 2.6, + "learning_rate": 2.6885049978270315e-06, + "loss": 0.2107, + "step": 31867 + }, + { + "epoch": 2.6, + "learning_rate": 2.6879617557583658e-06, + "loss": 0.129, + "step": 31868 + }, + { + "epoch": 2.6, + "learning_rate": 2.6874185136897e-06, + "loss": 0.119, + "step": 31869 + }, + { + "epoch": 2.6, + "learning_rate": 2.6868752716210346e-06, + "loss": 0.1599, + "step": 31870 + }, + { + "epoch": 2.6, + "learning_rate": 2.686332029552369e-06, + "loss": 0.2658, + "step": 31871 + }, + { + "epoch": 2.6, + "learning_rate": 2.685788787483703e-06, + "loss": 0.071, + "step": 31872 + }, + { + "epoch": 2.6, + "learning_rate": 2.6852455454150373e-06, + "loss": 0.3465, + "step": 31873 + }, + { + "epoch": 2.6, + "learning_rate": 2.6847023033463716e-06, + "loss": 0.2494, + "step": 31874 + }, + { + "epoch": 2.6, + "learning_rate": 2.684159061277706e-06, + "loss": 0.4172, + "step": 31875 + }, + { + "epoch": 2.6, + "learning_rate": 2.68361581920904e-06, + "loss": 0.2708, + "step": 31876 + }, + { + "epoch": 2.6, + "learning_rate": 2.683072577140374e-06, + "loss": 0.2793, + "step": 31877 + }, + { + "epoch": 2.6, + "learning_rate": 2.682529335071708e-06, + "loss": 0.6232, + "step": 31878 + }, + { + "epoch": 2.6, + "learning_rate": 2.6819860930030423e-06, + "loss": 0.311, + "step": 31879 + }, + { + "epoch": 2.6, + "learning_rate": 2.6814428509343765e-06, + "loss": 0.1902, + "step": 31880 + }, + { + "epoch": 2.6, + "learning_rate": 2.6808996088657108e-06, + "loss": 0.2175, + "step": 31881 + }, + { + "epoch": 2.6, + "learning_rate": 2.680356366797045e-06, + "loss": 0.0256, + "step": 31882 + }, + { + "epoch": 2.6, + "learning_rate": 2.679813124728379e-06, + "loss": 0.0411, + "step": 31883 + }, + { + "epoch": 2.6, + "learning_rate": 2.6792698826597134e-06, + "loss": 0.1288, + "step": 31884 + }, + { + "epoch": 2.6, + "learning_rate": 2.6787266405910477e-06, + "loss": 0.2798, + "step": 31885 + }, + { + "epoch": 2.6, + "learning_rate": 2.6781833985223815e-06, + "loss": 0.3543, + "step": 31886 + }, + { + "epoch": 2.6, + "learning_rate": 2.6776401564537157e-06, + "loss": 0.289, + "step": 31887 + }, + { + "epoch": 2.6, + "learning_rate": 2.67709691438505e-06, + "loss": 0.6328, + "step": 31888 + }, + { + "epoch": 2.6, + "learning_rate": 2.676553672316384e-06, + "loss": 0.2142, + "step": 31889 + }, + { + "epoch": 2.6, + "learning_rate": 2.6760104302477184e-06, + "loss": 0.3162, + "step": 31890 + }, + { + "epoch": 2.6, + "learning_rate": 2.6754671881790526e-06, + "loss": 0.3713, + "step": 31891 + }, + { + "epoch": 2.6, + "learning_rate": 2.6749239461103873e-06, + "loss": 0.1509, + "step": 31892 + }, + { + "epoch": 2.6, + "learning_rate": 2.6743807040417215e-06, + "loss": 0.1692, + "step": 31893 + }, + { + "epoch": 2.6, + "learning_rate": 2.6738374619730557e-06, + "loss": 0.4308, + "step": 31894 + }, + { + "epoch": 2.6, + "learning_rate": 2.67329421990439e-06, + "loss": 0.2188, + "step": 31895 + }, + { + "epoch": 2.6, + "learning_rate": 2.6727509778357234e-06, + "loss": 0.1515, + "step": 31896 + }, + { + "epoch": 2.6, + "learning_rate": 2.672207735767058e-06, + "loss": 0.1646, + "step": 31897 + }, + { + "epoch": 2.6, + "learning_rate": 2.6716644936983922e-06, + "loss": 0.0971, + "step": 31898 + }, + { + "epoch": 2.6, + "learning_rate": 2.6711212516297265e-06, + "loss": 0.2691, + "step": 31899 + }, + { + "epoch": 2.6, + "learning_rate": 2.6705780095610607e-06, + "loss": 0.3786, + "step": 31900 + }, + { + "epoch": 2.6, + "learning_rate": 2.670034767492395e-06, + "loss": 0.2674, + "step": 31901 + }, + { + "epoch": 2.6, + "learning_rate": 2.669491525423729e-06, + "loss": 0.1194, + "step": 31902 + }, + { + "epoch": 2.6, + "learning_rate": 2.6689482833550634e-06, + "loss": 0.2842, + "step": 31903 + }, + { + "epoch": 2.6, + "learning_rate": 2.6684050412863976e-06, + "loss": 0.1593, + "step": 31904 + }, + { + "epoch": 2.6, + "learning_rate": 2.6678617992177314e-06, + "loss": 0.0713, + "step": 31905 + }, + { + "epoch": 2.6, + "learning_rate": 2.6673185571490657e-06, + "loss": 0.0961, + "step": 31906 + }, + { + "epoch": 2.6, + "learning_rate": 2.6667753150804e-06, + "loss": 0.2409, + "step": 31907 + }, + { + "epoch": 2.6, + "learning_rate": 2.666232073011734e-06, + "loss": 0.1762, + "step": 31908 + }, + { + "epoch": 2.6, + "learning_rate": 2.6656888309430684e-06, + "loss": 0.1214, + "step": 31909 + }, + { + "epoch": 2.6, + "learning_rate": 2.6651455888744026e-06, + "loss": 0.1491, + "step": 31910 + }, + { + "epoch": 2.6, + "learning_rate": 2.664602346805737e-06, + "loss": 0.1841, + "step": 31911 + }, + { + "epoch": 2.6, + "learning_rate": 2.664059104737071e-06, + "loss": 0.0929, + "step": 31912 + }, + { + "epoch": 2.6, + "learning_rate": 2.6635158626684053e-06, + "loss": 0.0566, + "step": 31913 + }, + { + "epoch": 2.6, + "learning_rate": 2.6629726205997395e-06, + "loss": 0.143, + "step": 31914 + }, + { + "epoch": 2.6, + "learning_rate": 2.6624293785310733e-06, + "loss": 0.1862, + "step": 31915 + }, + { + "epoch": 2.6, + "learning_rate": 2.6618861364624075e-06, + "loss": 0.1916, + "step": 31916 + }, + { + "epoch": 2.6, + "learning_rate": 2.6613428943937418e-06, + "loss": 0.3807, + "step": 31917 + }, + { + "epoch": 2.6, + "learning_rate": 2.660799652325076e-06, + "loss": 0.1969, + "step": 31918 + }, + { + "epoch": 2.6, + "learning_rate": 2.6602564102564107e-06, + "loss": 0.2675, + "step": 31919 + }, + { + "epoch": 2.6, + "learning_rate": 2.659713168187745e-06, + "loss": 0.4974, + "step": 31920 + }, + { + "epoch": 2.6, + "learning_rate": 2.659169926119079e-06, + "loss": 0.2097, + "step": 31921 + }, + { + "epoch": 2.6, + "learning_rate": 2.6586266840504134e-06, + "loss": 0.1435, + "step": 31922 + }, + { + "epoch": 2.6, + "learning_rate": 2.6580834419817476e-06, + "loss": 0.3999, + "step": 31923 + }, + { + "epoch": 2.6, + "learning_rate": 2.6575401999130814e-06, + "loss": 0.1152, + "step": 31924 + }, + { + "epoch": 2.6, + "learning_rate": 2.6569969578444156e-06, + "loss": 0.3049, + "step": 31925 + }, + { + "epoch": 2.6, + "learning_rate": 2.65645371577575e-06, + "loss": 0.0821, + "step": 31926 + }, + { + "epoch": 2.6, + "learning_rate": 2.655910473707084e-06, + "loss": 0.3976, + "step": 31927 + }, + { + "epoch": 2.6, + "learning_rate": 2.6553672316384183e-06, + "loss": 0.3741, + "step": 31928 + }, + { + "epoch": 2.6, + "learning_rate": 2.6548239895697525e-06, + "loss": 0.2921, + "step": 31929 + }, + { + "epoch": 2.6, + "learning_rate": 2.6542807475010868e-06, + "loss": 0.2392, + "step": 31930 + }, + { + "epoch": 2.6, + "learning_rate": 2.653737505432421e-06, + "loss": 0.4071, + "step": 31931 + }, + { + "epoch": 2.6, + "learning_rate": 2.6531942633637552e-06, + "loss": 0.2411, + "step": 31932 + }, + { + "epoch": 2.6, + "learning_rate": 2.6526510212950895e-06, + "loss": 0.1444, + "step": 31933 + }, + { + "epoch": 2.6, + "learning_rate": 2.6521077792264233e-06, + "loss": 0.1671, + "step": 31934 + }, + { + "epoch": 2.6, + "learning_rate": 2.6515645371577575e-06, + "loss": 0.2343, + "step": 31935 + }, + { + "epoch": 2.6, + "learning_rate": 2.6510212950890917e-06, + "loss": 0.0975, + "step": 31936 + }, + { + "epoch": 2.6, + "learning_rate": 2.650478053020426e-06, + "loss": 0.2141, + "step": 31937 + }, + { + "epoch": 2.6, + "learning_rate": 2.64993481095176e-06, + "loss": 0.2504, + "step": 31938 + }, + { + "epoch": 2.6, + "learning_rate": 2.6493915688830944e-06, + "loss": 0.2998, + "step": 31939 + }, + { + "epoch": 2.6, + "learning_rate": 2.6488483268144287e-06, + "loss": 0.072, + "step": 31940 + }, + { + "epoch": 2.6, + "learning_rate": 2.648305084745763e-06, + "loss": 0.1473, + "step": 31941 + }, + { + "epoch": 2.6, + "learning_rate": 2.6477618426770975e-06, + "loss": 0.1377, + "step": 31942 + }, + { + "epoch": 2.6, + "learning_rate": 2.6472186006084318e-06, + "loss": 0.1962, + "step": 31943 + }, + { + "epoch": 2.6, + "learning_rate": 2.646675358539765e-06, + "loss": 0.0931, + "step": 31944 + }, + { + "epoch": 2.6, + "learning_rate": 2.6461321164710994e-06, + "loss": 0.191, + "step": 31945 + }, + { + "epoch": 2.6, + "learning_rate": 2.645588874402434e-06, + "loss": 0.0859, + "step": 31946 + }, + { + "epoch": 2.6, + "learning_rate": 2.6450456323337683e-06, + "loss": 0.2716, + "step": 31947 + }, + { + "epoch": 2.6, + "learning_rate": 2.6445023902651025e-06, + "loss": 0.1186, + "step": 31948 + }, + { + "epoch": 2.6, + "learning_rate": 2.6439591481964367e-06, + "loss": 0.16, + "step": 31949 + }, + { + "epoch": 2.6, + "learning_rate": 2.643415906127771e-06, + "loss": 0.1299, + "step": 31950 + }, + { + "epoch": 2.6, + "learning_rate": 2.642872664059105e-06, + "loss": 0.1247, + "step": 31951 + }, + { + "epoch": 2.6, + "learning_rate": 2.6423294219904394e-06, + "loss": 0.449, + "step": 31952 + }, + { + "epoch": 2.6, + "learning_rate": 2.6417861799217732e-06, + "loss": 0.3167, + "step": 31953 + }, + { + "epoch": 2.6, + "learning_rate": 2.6412429378531075e-06, + "loss": 0.2529, + "step": 31954 + }, + { + "epoch": 2.6, + "learning_rate": 2.6406996957844417e-06, + "loss": 0.2353, + "step": 31955 + }, + { + "epoch": 2.6, + "learning_rate": 2.640156453715776e-06, + "loss": 0.4574, + "step": 31956 + }, + { + "epoch": 2.6, + "learning_rate": 2.63961321164711e-06, + "loss": 0.4476, + "step": 31957 + }, + { + "epoch": 2.6, + "learning_rate": 2.6390699695784444e-06, + "loss": 0.0745, + "step": 31958 + }, + { + "epoch": 2.6, + "learning_rate": 2.6385267275097786e-06, + "loss": 0.1626, + "step": 31959 + }, + { + "epoch": 2.6, + "learning_rate": 2.637983485441113e-06, + "loss": 0.2732, + "step": 31960 + }, + { + "epoch": 2.6, + "learning_rate": 2.637440243372447e-06, + "loss": 0.2831, + "step": 31961 + }, + { + "epoch": 2.6, + "learning_rate": 2.6368970013037813e-06, + "loss": 0.2598, + "step": 31962 + }, + { + "epoch": 2.6, + "learning_rate": 2.636353759235115e-06, + "loss": 0.1301, + "step": 31963 + }, + { + "epoch": 2.6, + "learning_rate": 2.6358105171664493e-06, + "loss": 0.0628, + "step": 31964 + }, + { + "epoch": 2.6, + "learning_rate": 2.6352672750977836e-06, + "loss": 0.3068, + "step": 31965 + }, + { + "epoch": 2.6, + "learning_rate": 2.634724033029118e-06, + "loss": 0.0709, + "step": 31966 + }, + { + "epoch": 2.6, + "learning_rate": 2.634180790960452e-06, + "loss": 0.1232, + "step": 31967 + }, + { + "epoch": 2.6, + "learning_rate": 2.6336375488917863e-06, + "loss": 0.1981, + "step": 31968 + }, + { + "epoch": 2.61, + "learning_rate": 2.633094306823121e-06, + "loss": 0.2271, + "step": 31969 + }, + { + "epoch": 2.61, + "learning_rate": 2.632551064754455e-06, + "loss": 0.4545, + "step": 31970 + }, + { + "epoch": 2.61, + "learning_rate": 2.6320078226857894e-06, + "loss": 0.1006, + "step": 31971 + }, + { + "epoch": 2.61, + "learning_rate": 2.6314645806171228e-06, + "loss": 0.1563, + "step": 31972 + }, + { + "epoch": 2.61, + "learning_rate": 2.6309213385484574e-06, + "loss": 0.1567, + "step": 31973 + }, + { + "epoch": 2.61, + "learning_rate": 2.6303780964797916e-06, + "loss": 0.119, + "step": 31974 + }, + { + "epoch": 2.61, + "learning_rate": 2.629834854411126e-06, + "loss": 0.1438, + "step": 31975 + }, + { + "epoch": 2.61, + "learning_rate": 2.62929161234246e-06, + "loss": 0.2241, + "step": 31976 + }, + { + "epoch": 2.61, + "learning_rate": 2.6287483702737943e-06, + "loss": 0.1847, + "step": 31977 + }, + { + "epoch": 2.61, + "learning_rate": 2.6282051282051286e-06, + "loss": 0.2268, + "step": 31978 + }, + { + "epoch": 2.61, + "learning_rate": 2.627661886136463e-06, + "loss": 0.3603, + "step": 31979 + }, + { + "epoch": 2.61, + "learning_rate": 2.627118644067797e-06, + "loss": 0.2863, + "step": 31980 + }, + { + "epoch": 2.61, + "learning_rate": 2.6265754019991313e-06, + "loss": 0.3684, + "step": 31981 + }, + { + "epoch": 2.61, + "learning_rate": 2.626032159930465e-06, + "loss": 0.241, + "step": 31982 + }, + { + "epoch": 2.61, + "learning_rate": 2.6254889178617993e-06, + "loss": 0.1731, + "step": 31983 + }, + { + "epoch": 2.61, + "learning_rate": 2.6249456757931335e-06, + "loss": 0.2957, + "step": 31984 + }, + { + "epoch": 2.61, + "learning_rate": 2.6244024337244678e-06, + "loss": 0.1524, + "step": 31985 + }, + { + "epoch": 2.61, + "learning_rate": 2.623859191655802e-06, + "loss": 0.1341, + "step": 31986 + }, + { + "epoch": 2.61, + "learning_rate": 2.6233159495871362e-06, + "loss": 0.3238, + "step": 31987 + }, + { + "epoch": 2.61, + "learning_rate": 2.6227727075184705e-06, + "loss": 0.0701, + "step": 31988 + }, + { + "epoch": 2.61, + "learning_rate": 2.6222294654498047e-06, + "loss": 0.2771, + "step": 31989 + }, + { + "epoch": 2.61, + "learning_rate": 2.621686223381139e-06, + "loss": 0.2584, + "step": 31990 + }, + { + "epoch": 2.61, + "learning_rate": 2.6211429813124727e-06, + "loss": 0.3571, + "step": 31991 + }, + { + "epoch": 2.61, + "learning_rate": 2.620599739243807e-06, + "loss": 0.269, + "step": 31992 + }, + { + "epoch": 2.61, + "learning_rate": 2.620056497175141e-06, + "loss": 0.4443, + "step": 31993 + }, + { + "epoch": 2.61, + "learning_rate": 2.6195132551064754e-06, + "loss": 0.2369, + "step": 31994 + }, + { + "epoch": 2.61, + "learning_rate": 2.6189700130378096e-06, + "loss": 0.2557, + "step": 31995 + }, + { + "epoch": 2.61, + "learning_rate": 2.6184267709691443e-06, + "loss": 0.4028, + "step": 31996 + }, + { + "epoch": 2.61, + "learning_rate": 2.6178835289004785e-06, + "loss": 0.3383, + "step": 31997 + }, + { + "epoch": 2.61, + "learning_rate": 2.6173402868318128e-06, + "loss": 0.1515, + "step": 31998 + }, + { + "epoch": 2.61, + "learning_rate": 2.616797044763147e-06, + "loss": 0.1825, + "step": 31999 + }, + { + "epoch": 2.61, + "learning_rate": 2.6162538026944812e-06, + "loss": 0.381, + "step": 32000 + }, + { + "epoch": 2.61, + "eval_accuracy": 0.8439123790117168, + "eval_loss": 0.4818579852581024, + "eval_runtime": 22.3088, + "eval_samples_per_second": 439.96, + "eval_steps_per_second": 3.452, + "step": 32000 + }, + { + "epoch": 2.61, + "learning_rate": 2.615710560625815e-06, + "loss": 0.2467, + "step": 32001 + }, + { + "epoch": 2.61, + "learning_rate": 2.6151673185571493e-06, + "loss": 0.1299, + "step": 32002 + }, + { + "epoch": 2.61, + "learning_rate": 2.6146240764884835e-06, + "loss": 0.2286, + "step": 32003 + }, + { + "epoch": 2.61, + "learning_rate": 2.6140808344198177e-06, + "loss": 0.501, + "step": 32004 + }, + { + "epoch": 2.61, + "learning_rate": 2.613537592351152e-06, + "loss": 0.0798, + "step": 32005 + }, + { + "epoch": 2.61, + "learning_rate": 2.612994350282486e-06, + "loss": 0.2101, + "step": 32006 + }, + { + "epoch": 2.61, + "learning_rate": 2.6124511082138204e-06, + "loss": 0.0757, + "step": 32007 + }, + { + "epoch": 2.61, + "learning_rate": 2.6119078661451546e-06, + "loss": 0.3965, + "step": 32008 + }, + { + "epoch": 2.61, + "learning_rate": 2.611364624076489e-06, + "loss": 0.2535, + "step": 32009 + }, + { + "epoch": 2.61, + "learning_rate": 2.6108213820078227e-06, + "loss": 0.0274, + "step": 32010 + }, + { + "epoch": 2.61, + "learning_rate": 2.610278139939157e-06, + "loss": 0.2341, + "step": 32011 + }, + { + "epoch": 2.61, + "learning_rate": 2.609734897870491e-06, + "loss": 0.3058, + "step": 32012 + }, + { + "epoch": 2.61, + "learning_rate": 2.6091916558018254e-06, + "loss": 0.1745, + "step": 32013 + }, + { + "epoch": 2.61, + "learning_rate": 2.6086484137331596e-06, + "loss": 0.2187, + "step": 32014 + }, + { + "epoch": 2.61, + "learning_rate": 2.608105171664494e-06, + "loss": 0.1514, + "step": 32015 + }, + { + "epoch": 2.61, + "learning_rate": 2.607561929595828e-06, + "loss": 0.1617, + "step": 32016 + }, + { + "epoch": 2.61, + "learning_rate": 2.6070186875271623e-06, + "loss": 0.3231, + "step": 32017 + }, + { + "epoch": 2.61, + "learning_rate": 2.6064754454584965e-06, + "loss": 0.3201, + "step": 32018 + }, + { + "epoch": 2.61, + "learning_rate": 2.605932203389831e-06, + "loss": 0.5955, + "step": 32019 + }, + { + "epoch": 2.61, + "learning_rate": 2.6053889613211646e-06, + "loss": 0.3171, + "step": 32020 + }, + { + "epoch": 2.61, + "learning_rate": 2.604845719252499e-06, + "loss": 0.1807, + "step": 32021 + }, + { + "epoch": 2.61, + "learning_rate": 2.604302477183833e-06, + "loss": 0.3405, + "step": 32022 + }, + { + "epoch": 2.61, + "learning_rate": 2.6037592351151677e-06, + "loss": 0.0762, + "step": 32023 + }, + { + "epoch": 2.61, + "learning_rate": 2.603215993046502e-06, + "loss": 0.4432, + "step": 32024 + }, + { + "epoch": 2.61, + "learning_rate": 2.602672750977836e-06, + "loss": 0.2822, + "step": 32025 + }, + { + "epoch": 2.61, + "learning_rate": 2.6021295089091704e-06, + "loss": 0.3965, + "step": 32026 + }, + { + "epoch": 2.61, + "learning_rate": 2.6015862668405046e-06, + "loss": 0.1716, + "step": 32027 + }, + { + "epoch": 2.61, + "learning_rate": 2.601043024771839e-06, + "loss": 0.136, + "step": 32028 + }, + { + "epoch": 2.61, + "learning_rate": 2.6004997827031726e-06, + "loss": 0.5342, + "step": 32029 + }, + { + "epoch": 2.61, + "learning_rate": 2.599956540634507e-06, + "loss": 0.2021, + "step": 32030 + }, + { + "epoch": 2.61, + "learning_rate": 2.599413298565841e-06, + "loss": 0.0703, + "step": 32031 + }, + { + "epoch": 2.61, + "learning_rate": 2.5988700564971753e-06, + "loss": 0.2037, + "step": 32032 + }, + { + "epoch": 2.61, + "learning_rate": 2.5983268144285096e-06, + "loss": 0.2247, + "step": 32033 + }, + { + "epoch": 2.61, + "learning_rate": 2.597783572359844e-06, + "loss": 0.1405, + "step": 32034 + }, + { + "epoch": 2.61, + "learning_rate": 2.597240330291178e-06, + "loss": 0.0845, + "step": 32035 + }, + { + "epoch": 2.61, + "learning_rate": 2.5966970882225122e-06, + "loss": 0.1109, + "step": 32036 + }, + { + "epoch": 2.61, + "learning_rate": 2.5961538461538465e-06, + "loss": 0.4373, + "step": 32037 + }, + { + "epoch": 2.61, + "learning_rate": 2.5956106040851807e-06, + "loss": 0.1911, + "step": 32038 + }, + { + "epoch": 2.61, + "learning_rate": 2.5950673620165145e-06, + "loss": 0.1565, + "step": 32039 + }, + { + "epoch": 2.61, + "learning_rate": 2.5945241199478487e-06, + "loss": 0.1165, + "step": 32040 + }, + { + "epoch": 2.61, + "learning_rate": 2.593980877879183e-06, + "loss": 0.4457, + "step": 32041 + }, + { + "epoch": 2.61, + "learning_rate": 2.593437635810517e-06, + "loss": 0.2951, + "step": 32042 + }, + { + "epoch": 2.61, + "learning_rate": 2.5928943937418514e-06, + "loss": 0.1007, + "step": 32043 + }, + { + "epoch": 2.61, + "learning_rate": 2.5923511516731857e-06, + "loss": 0.5246, + "step": 32044 + }, + { + "epoch": 2.61, + "learning_rate": 2.59180790960452e-06, + "loss": 0.0998, + "step": 32045 + }, + { + "epoch": 2.61, + "learning_rate": 2.5912646675358546e-06, + "loss": 0.188, + "step": 32046 + }, + { + "epoch": 2.61, + "learning_rate": 2.5907214254671888e-06, + "loss": 0.2169, + "step": 32047 + }, + { + "epoch": 2.61, + "learning_rate": 2.590178183398522e-06, + "loss": 0.1574, + "step": 32048 + }, + { + "epoch": 2.61, + "learning_rate": 2.5896349413298564e-06, + "loss": 0.3413, + "step": 32049 + }, + { + "epoch": 2.61, + "learning_rate": 2.589091699261191e-06, + "loss": 0.2067, + "step": 32050 + }, + { + "epoch": 2.61, + "learning_rate": 2.5885484571925253e-06, + "loss": 0.1708, + "step": 32051 + }, + { + "epoch": 2.61, + "learning_rate": 2.5880052151238595e-06, + "loss": 0.3727, + "step": 32052 + }, + { + "epoch": 2.61, + "learning_rate": 2.5874619730551937e-06, + "loss": 0.0677, + "step": 32053 + }, + { + "epoch": 2.61, + "learning_rate": 2.586918730986528e-06, + "loss": 0.2797, + "step": 32054 + }, + { + "epoch": 2.61, + "learning_rate": 2.586375488917862e-06, + "loss": 0.1323, + "step": 32055 + }, + { + "epoch": 2.61, + "learning_rate": 2.5858322468491964e-06, + "loss": 0.1505, + "step": 32056 + }, + { + "epoch": 2.61, + "learning_rate": 2.5852890047805307e-06, + "loss": 0.3153, + "step": 32057 + }, + { + "epoch": 2.61, + "learning_rate": 2.5847457627118645e-06, + "loss": 0.3596, + "step": 32058 + }, + { + "epoch": 2.61, + "learning_rate": 2.5842025206431987e-06, + "loss": 0.2146, + "step": 32059 + }, + { + "epoch": 2.61, + "learning_rate": 2.583659278574533e-06, + "loss": 0.2939, + "step": 32060 + }, + { + "epoch": 2.61, + "learning_rate": 2.583116036505867e-06, + "loss": 0.1293, + "step": 32061 + }, + { + "epoch": 2.61, + "learning_rate": 2.5825727944372014e-06, + "loss": 0.3402, + "step": 32062 + }, + { + "epoch": 2.61, + "learning_rate": 2.5820295523685356e-06, + "loss": 0.2989, + "step": 32063 + }, + { + "epoch": 2.61, + "learning_rate": 2.58148631029987e-06, + "loss": 0.4975, + "step": 32064 + }, + { + "epoch": 2.61, + "learning_rate": 2.580943068231204e-06, + "loss": 0.3424, + "step": 32065 + }, + { + "epoch": 2.61, + "learning_rate": 2.5803998261625383e-06, + "loss": 0.1512, + "step": 32066 + }, + { + "epoch": 2.61, + "learning_rate": 2.579856584093872e-06, + "loss": 0.2754, + "step": 32067 + }, + { + "epoch": 2.61, + "learning_rate": 2.5793133420252064e-06, + "loss": 0.0948, + "step": 32068 + }, + { + "epoch": 2.61, + "learning_rate": 2.5787700999565406e-06, + "loss": 0.221, + "step": 32069 + }, + { + "epoch": 2.61, + "learning_rate": 2.578226857887875e-06, + "loss": 0.3609, + "step": 32070 + }, + { + "epoch": 2.61, + "learning_rate": 2.577683615819209e-06, + "loss": 0.2949, + "step": 32071 + }, + { + "epoch": 2.61, + "learning_rate": 2.5771403737505433e-06, + "loss": 0.1617, + "step": 32072 + }, + { + "epoch": 2.61, + "learning_rate": 2.576597131681878e-06, + "loss": 0.1394, + "step": 32073 + }, + { + "epoch": 2.61, + "learning_rate": 2.576053889613212e-06, + "loss": 0.2583, + "step": 32074 + }, + { + "epoch": 2.61, + "learning_rate": 2.5755106475445464e-06, + "loss": 0.1652, + "step": 32075 + }, + { + "epoch": 2.61, + "learning_rate": 2.5749674054758806e-06, + "loss": 0.5006, + "step": 32076 + }, + { + "epoch": 2.61, + "learning_rate": 2.5744241634072144e-06, + "loss": 0.2984, + "step": 32077 + }, + { + "epoch": 2.61, + "learning_rate": 2.5738809213385487e-06, + "loss": 0.1382, + "step": 32078 + }, + { + "epoch": 2.61, + "learning_rate": 2.573337679269883e-06, + "loss": 0.483, + "step": 32079 + }, + { + "epoch": 2.61, + "learning_rate": 2.572794437201217e-06, + "loss": 0.2078, + "step": 32080 + }, + { + "epoch": 2.61, + "learning_rate": 2.5722511951325514e-06, + "loss": 0.4593, + "step": 32081 + }, + { + "epoch": 2.61, + "learning_rate": 2.5717079530638856e-06, + "loss": 0.0537, + "step": 32082 + }, + { + "epoch": 2.61, + "learning_rate": 2.57116471099522e-06, + "loss": 0.3407, + "step": 32083 + }, + { + "epoch": 2.61, + "learning_rate": 2.570621468926554e-06, + "loss": 0.4099, + "step": 32084 + }, + { + "epoch": 2.61, + "learning_rate": 2.5700782268578883e-06, + "loss": 0.1246, + "step": 32085 + }, + { + "epoch": 2.61, + "learning_rate": 2.569534984789222e-06, + "loss": 0.2221, + "step": 32086 + }, + { + "epoch": 2.61, + "learning_rate": 2.5689917427205563e-06, + "loss": 0.244, + "step": 32087 + }, + { + "epoch": 2.61, + "learning_rate": 2.5684485006518905e-06, + "loss": 0.4213, + "step": 32088 + }, + { + "epoch": 2.61, + "learning_rate": 2.5679052585832248e-06, + "loss": 0.1791, + "step": 32089 + }, + { + "epoch": 2.61, + "learning_rate": 2.567362016514559e-06, + "loss": 0.2264, + "step": 32090 + }, + { + "epoch": 2.61, + "learning_rate": 2.5668187744458932e-06, + "loss": 0.1126, + "step": 32091 + }, + { + "epoch": 2.62, + "learning_rate": 2.5662755323772275e-06, + "loss": 0.1277, + "step": 32092 + }, + { + "epoch": 2.62, + "learning_rate": 2.5657322903085617e-06, + "loss": 0.1584, + "step": 32093 + }, + { + "epoch": 2.62, + "learning_rate": 2.565189048239896e-06, + "loss": 0.2031, + "step": 32094 + }, + { + "epoch": 2.62, + "learning_rate": 2.5646458061712306e-06, + "loss": 0.1499, + "step": 32095 + }, + { + "epoch": 2.62, + "learning_rate": 2.564102564102564e-06, + "loss": 0.1337, + "step": 32096 + }, + { + "epoch": 2.62, + "learning_rate": 2.563559322033898e-06, + "loss": 0.1512, + "step": 32097 + }, + { + "epoch": 2.62, + "learning_rate": 2.5630160799652324e-06, + "loss": 0.1795, + "step": 32098 + }, + { + "epoch": 2.62, + "learning_rate": 2.5624728378965667e-06, + "loss": 0.2175, + "step": 32099 + }, + { + "epoch": 2.62, + "learning_rate": 2.5619295958279013e-06, + "loss": 0.3033, + "step": 32100 + }, + { + "epoch": 2.62, + "learning_rate": 2.5613863537592355e-06, + "loss": 0.175, + "step": 32101 + }, + { + "epoch": 2.62, + "learning_rate": 2.5608431116905698e-06, + "loss": 0.2395, + "step": 32102 + }, + { + "epoch": 2.62, + "learning_rate": 2.560299869621904e-06, + "loss": 0.3348, + "step": 32103 + }, + { + "epoch": 2.62, + "learning_rate": 2.5597566275532382e-06, + "loss": 0.3347, + "step": 32104 + }, + { + "epoch": 2.62, + "learning_rate": 2.559213385484572e-06, + "loss": 0.2619, + "step": 32105 + }, + { + "epoch": 2.62, + "learning_rate": 2.5586701434159063e-06, + "loss": 0.1242, + "step": 32106 + }, + { + "epoch": 2.62, + "learning_rate": 2.5581269013472405e-06, + "loss": 0.2486, + "step": 32107 + }, + { + "epoch": 2.62, + "learning_rate": 2.5575836592785747e-06, + "loss": 0.0683, + "step": 32108 + }, + { + "epoch": 2.62, + "learning_rate": 2.557040417209909e-06, + "loss": 0.1334, + "step": 32109 + }, + { + "epoch": 2.62, + "learning_rate": 2.556497175141243e-06, + "loss": 0.3864, + "step": 32110 + }, + { + "epoch": 2.62, + "learning_rate": 2.5559539330725774e-06, + "loss": 0.3479, + "step": 32111 + }, + { + "epoch": 2.62, + "learning_rate": 2.5554106910039117e-06, + "loss": 0.3458, + "step": 32112 + }, + { + "epoch": 2.62, + "learning_rate": 2.554867448935246e-06, + "loss": 0.2687, + "step": 32113 + }, + { + "epoch": 2.62, + "learning_rate": 2.55432420686658e-06, + "loss": 0.5105, + "step": 32114 + }, + { + "epoch": 2.62, + "learning_rate": 2.553780964797914e-06, + "loss": 0.093, + "step": 32115 + }, + { + "epoch": 2.62, + "learning_rate": 2.553237722729248e-06, + "loss": 0.2871, + "step": 32116 + }, + { + "epoch": 2.62, + "learning_rate": 2.5526944806605824e-06, + "loss": 0.4394, + "step": 32117 + }, + { + "epoch": 2.62, + "learning_rate": 2.5521512385919166e-06, + "loss": 0.215, + "step": 32118 + }, + { + "epoch": 2.62, + "learning_rate": 2.551607996523251e-06, + "loss": 0.1363, + "step": 32119 + }, + { + "epoch": 2.62, + "learning_rate": 2.551064754454585e-06, + "loss": 0.1003, + "step": 32120 + }, + { + "epoch": 2.62, + "learning_rate": 2.5505215123859193e-06, + "loss": 0.3083, + "step": 32121 + }, + { + "epoch": 2.62, + "learning_rate": 2.549978270317254e-06, + "loss": 0.2829, + "step": 32122 + }, + { + "epoch": 2.62, + "learning_rate": 2.549435028248588e-06, + "loss": 0.1655, + "step": 32123 + }, + { + "epoch": 2.62, + "learning_rate": 2.5488917861799216e-06, + "loss": 0.2198, + "step": 32124 + }, + { + "epoch": 2.62, + "learning_rate": 2.548348544111256e-06, + "loss": 0.2565, + "step": 32125 + }, + { + "epoch": 2.62, + "learning_rate": 2.54780530204259e-06, + "loss": 0.2745, + "step": 32126 + }, + { + "epoch": 2.62, + "learning_rate": 2.5472620599739247e-06, + "loss": 0.4546, + "step": 32127 + }, + { + "epoch": 2.62, + "learning_rate": 2.546718817905259e-06, + "loss": 0.3665, + "step": 32128 + }, + { + "epoch": 2.62, + "learning_rate": 2.546175575836593e-06, + "loss": 0.1639, + "step": 32129 + }, + { + "epoch": 2.62, + "learning_rate": 2.5456323337679274e-06, + "loss": 0.2556, + "step": 32130 + }, + { + "epoch": 2.62, + "learning_rate": 2.5450890916992616e-06, + "loss": 0.1573, + "step": 32131 + }, + { + "epoch": 2.62, + "learning_rate": 2.544545849630596e-06, + "loss": 0.1512, + "step": 32132 + }, + { + "epoch": 2.62, + "learning_rate": 2.54400260756193e-06, + "loss": 0.3445, + "step": 32133 + }, + { + "epoch": 2.62, + "learning_rate": 2.543459365493264e-06, + "loss": 0.2361, + "step": 32134 + }, + { + "epoch": 2.62, + "learning_rate": 2.542916123424598e-06, + "loss": 0.191, + "step": 32135 + }, + { + "epoch": 2.62, + "learning_rate": 2.5423728813559323e-06, + "loss": 0.2681, + "step": 32136 + }, + { + "epoch": 2.62, + "learning_rate": 2.5418296392872666e-06, + "loss": 0.1117, + "step": 32137 + }, + { + "epoch": 2.62, + "learning_rate": 2.541286397218601e-06, + "loss": 0.2698, + "step": 32138 + }, + { + "epoch": 2.62, + "learning_rate": 2.540743155149935e-06, + "loss": 0.0818, + "step": 32139 + }, + { + "epoch": 2.62, + "learning_rate": 2.5401999130812693e-06, + "loss": 0.4751, + "step": 32140 + }, + { + "epoch": 2.62, + "learning_rate": 2.5396566710126035e-06, + "loss": 0.1635, + "step": 32141 + }, + { + "epoch": 2.62, + "learning_rate": 2.5391134289439377e-06, + "loss": 0.1969, + "step": 32142 + }, + { + "epoch": 2.62, + "learning_rate": 2.5385701868752715e-06, + "loss": 0.2131, + "step": 32143 + }, + { + "epoch": 2.62, + "learning_rate": 2.5380269448066058e-06, + "loss": 0.1809, + "step": 32144 + }, + { + "epoch": 2.62, + "learning_rate": 2.53748370273794e-06, + "loss": 0.212, + "step": 32145 + }, + { + "epoch": 2.62, + "learning_rate": 2.5369404606692742e-06, + "loss": 0.1867, + "step": 32146 + }, + { + "epoch": 2.62, + "learning_rate": 2.5363972186006085e-06, + "loss": 0.0828, + "step": 32147 + }, + { + "epoch": 2.62, + "learning_rate": 2.5358539765319427e-06, + "loss": 0.1913, + "step": 32148 + }, + { + "epoch": 2.62, + "learning_rate": 2.5353107344632773e-06, + "loss": 0.1216, + "step": 32149 + }, + { + "epoch": 2.62, + "learning_rate": 2.5347674923946116e-06, + "loss": 0.1733, + "step": 32150 + }, + { + "epoch": 2.62, + "learning_rate": 2.534224250325946e-06, + "loss": 0.2691, + "step": 32151 + }, + { + "epoch": 2.62, + "learning_rate": 2.53368100825728e-06, + "loss": 0.3179, + "step": 32152 + }, + { + "epoch": 2.62, + "learning_rate": 2.5331377661886134e-06, + "loss": 0.4283, + "step": 32153 + }, + { + "epoch": 2.62, + "learning_rate": 2.532594524119948e-06, + "loss": 0.1818, + "step": 32154 + }, + { + "epoch": 2.62, + "learning_rate": 2.5320512820512823e-06, + "loss": 0.3402, + "step": 32155 + }, + { + "epoch": 2.62, + "learning_rate": 2.5315080399826165e-06, + "loss": 0.1582, + "step": 32156 + }, + { + "epoch": 2.62, + "learning_rate": 2.5309647979139508e-06, + "loss": 0.2161, + "step": 32157 + }, + { + "epoch": 2.62, + "learning_rate": 2.530421555845285e-06, + "loss": 0.1859, + "step": 32158 + }, + { + "epoch": 2.62, + "learning_rate": 2.5298783137766192e-06, + "loss": 0.1737, + "step": 32159 + }, + { + "epoch": 2.62, + "learning_rate": 2.5293350717079534e-06, + "loss": 0.3457, + "step": 32160 + }, + { + "epoch": 2.62, + "learning_rate": 2.5287918296392877e-06, + "loss": 0.1005, + "step": 32161 + }, + { + "epoch": 2.62, + "learning_rate": 2.5282485875706215e-06, + "loss": 0.1897, + "step": 32162 + }, + { + "epoch": 2.62, + "learning_rate": 2.5277053455019557e-06, + "loss": 0.3333, + "step": 32163 + }, + { + "epoch": 2.62, + "learning_rate": 2.52716210343329e-06, + "loss": 0.3933, + "step": 32164 + }, + { + "epoch": 2.62, + "learning_rate": 2.526618861364624e-06, + "loss": 0.322, + "step": 32165 + }, + { + "epoch": 2.62, + "learning_rate": 2.5260756192959584e-06, + "loss": 0.3815, + "step": 32166 + }, + { + "epoch": 2.62, + "learning_rate": 2.5255323772272926e-06, + "loss": 0.1507, + "step": 32167 + }, + { + "epoch": 2.62, + "learning_rate": 2.524989135158627e-06, + "loss": 0.1898, + "step": 32168 + }, + { + "epoch": 2.62, + "learning_rate": 2.524445893089961e-06, + "loss": 0.1928, + "step": 32169 + }, + { + "epoch": 2.62, + "learning_rate": 2.5239026510212953e-06, + "loss": 0.2583, + "step": 32170 + }, + { + "epoch": 2.62, + "learning_rate": 2.5233594089526296e-06, + "loss": 0.1231, + "step": 32171 + }, + { + "epoch": 2.62, + "learning_rate": 2.5228161668839634e-06, + "loss": 0.2024, + "step": 32172 + }, + { + "epoch": 2.62, + "learning_rate": 2.5222729248152976e-06, + "loss": 0.4898, + "step": 32173 + }, + { + "epoch": 2.62, + "learning_rate": 2.521729682746632e-06, + "loss": 0.4135, + "step": 32174 + }, + { + "epoch": 2.62, + "learning_rate": 2.521186440677966e-06, + "loss": 0.2645, + "step": 32175 + }, + { + "epoch": 2.62, + "learning_rate": 2.5206431986093007e-06, + "loss": 0.3174, + "step": 32176 + }, + { + "epoch": 2.62, + "learning_rate": 2.520099956540635e-06, + "loss": 0.3393, + "step": 32177 + }, + { + "epoch": 2.62, + "learning_rate": 2.519556714471969e-06, + "loss": 0.2701, + "step": 32178 + }, + { + "epoch": 2.62, + "learning_rate": 2.5190134724033034e-06, + "loss": 0.0784, + "step": 32179 + }, + { + "epoch": 2.62, + "learning_rate": 2.5184702303346376e-06, + "loss": 0.267, + "step": 32180 + }, + { + "epoch": 2.62, + "learning_rate": 2.5179269882659714e-06, + "loss": 0.2339, + "step": 32181 + }, + { + "epoch": 2.62, + "learning_rate": 2.5173837461973057e-06, + "loss": 0.4208, + "step": 32182 + }, + { + "epoch": 2.62, + "learning_rate": 2.51684050412864e-06, + "loss": 0.4963, + "step": 32183 + }, + { + "epoch": 2.62, + "learning_rate": 2.516297262059974e-06, + "loss": 0.2291, + "step": 32184 + }, + { + "epoch": 2.62, + "learning_rate": 2.5157540199913084e-06, + "loss": 0.4743, + "step": 32185 + }, + { + "epoch": 2.62, + "learning_rate": 2.5152107779226426e-06, + "loss": 0.3771, + "step": 32186 + }, + { + "epoch": 2.62, + "learning_rate": 2.514667535853977e-06, + "loss": 0.4482, + "step": 32187 + }, + { + "epoch": 2.62, + "learning_rate": 2.514124293785311e-06, + "loss": 0.1981, + "step": 32188 + }, + { + "epoch": 2.62, + "learning_rate": 2.5135810517166453e-06, + "loss": 0.533, + "step": 32189 + }, + { + "epoch": 2.62, + "learning_rate": 2.5130378096479795e-06, + "loss": 0.3317, + "step": 32190 + }, + { + "epoch": 2.62, + "learning_rate": 2.5124945675793133e-06, + "loss": 0.3542, + "step": 32191 + }, + { + "epoch": 2.62, + "learning_rate": 2.5119513255106476e-06, + "loss": 0.1347, + "step": 32192 + }, + { + "epoch": 2.62, + "learning_rate": 2.5114080834419818e-06, + "loss": 0.2541, + "step": 32193 + }, + { + "epoch": 2.62, + "learning_rate": 2.510864841373316e-06, + "loss": 0.0301, + "step": 32194 + }, + { + "epoch": 2.62, + "learning_rate": 2.5103215993046502e-06, + "loss": 0.4, + "step": 32195 + }, + { + "epoch": 2.62, + "learning_rate": 2.5097783572359845e-06, + "loss": 0.1666, + "step": 32196 + }, + { + "epoch": 2.62, + "learning_rate": 2.5092351151673187e-06, + "loss": 0.1145, + "step": 32197 + }, + { + "epoch": 2.62, + "learning_rate": 2.508691873098653e-06, + "loss": 0.2156, + "step": 32198 + }, + { + "epoch": 2.62, + "learning_rate": 2.5081486310299876e-06, + "loss": 0.209, + "step": 32199 + }, + { + "epoch": 2.62, + "learning_rate": 2.507605388961321e-06, + "loss": 0.148, + "step": 32200 + }, + { + "epoch": 2.62, + "learning_rate": 2.507062146892655e-06, + "loss": 0.2491, + "step": 32201 + }, + { + "epoch": 2.62, + "learning_rate": 2.5065189048239894e-06, + "loss": 0.2375, + "step": 32202 + }, + { + "epoch": 2.62, + "learning_rate": 2.505975662755324e-06, + "loss": 0.2371, + "step": 32203 + }, + { + "epoch": 2.62, + "learning_rate": 2.5054324206866583e-06, + "loss": 0.1802, + "step": 32204 + }, + { + "epoch": 2.62, + "learning_rate": 2.5048891786179926e-06, + "loss": 0.4564, + "step": 32205 + }, + { + "epoch": 2.62, + "learning_rate": 2.5043459365493268e-06, + "loss": 0.2472, + "step": 32206 + }, + { + "epoch": 2.62, + "learning_rate": 2.503802694480661e-06, + "loss": 0.3327, + "step": 32207 + }, + { + "epoch": 2.62, + "learning_rate": 2.5032594524119952e-06, + "loss": 0.2379, + "step": 32208 + }, + { + "epoch": 2.62, + "learning_rate": 2.5027162103433295e-06, + "loss": 0.4336, + "step": 32209 + }, + { + "epoch": 2.62, + "learning_rate": 2.5021729682746633e-06, + "loss": 0.1074, + "step": 32210 + }, + { + "epoch": 2.62, + "learning_rate": 2.5016297262059975e-06, + "loss": 0.2614, + "step": 32211 + }, + { + "epoch": 2.62, + "learning_rate": 2.5010864841373317e-06, + "loss": 0.1653, + "step": 32212 + }, + { + "epoch": 2.62, + "learning_rate": 2.500543242068666e-06, + "loss": 0.1738, + "step": 32213 + }, + { + "epoch": 2.62, + "learning_rate": 2.5e-06, + "loss": 0.2742, + "step": 32214 + }, + { + "epoch": 2.63, + "learning_rate": 2.4994567579313344e-06, + "loss": 0.4059, + "step": 32215 + }, + { + "epoch": 2.63, + "learning_rate": 2.4989135158626687e-06, + "loss": 0.2444, + "step": 32216 + }, + { + "epoch": 2.63, + "learning_rate": 2.498370273794003e-06, + "loss": 0.4705, + "step": 32217 + }, + { + "epoch": 2.63, + "learning_rate": 2.497827031725337e-06, + "loss": 0.1755, + "step": 32218 + }, + { + "epoch": 2.63, + "learning_rate": 2.4972837896566714e-06, + "loss": 0.1353, + "step": 32219 + }, + { + "epoch": 2.63, + "learning_rate": 2.4967405475880056e-06, + "loss": 0.2561, + "step": 32220 + }, + { + "epoch": 2.63, + "learning_rate": 2.49619730551934e-06, + "loss": 0.2843, + "step": 32221 + }, + { + "epoch": 2.63, + "learning_rate": 2.4956540634506736e-06, + "loss": 0.1077, + "step": 32222 + }, + { + "epoch": 2.63, + "learning_rate": 2.495110821382008e-06, + "loss": 0.0894, + "step": 32223 + }, + { + "epoch": 2.63, + "learning_rate": 2.494567579313342e-06, + "loss": 0.4118, + "step": 32224 + }, + { + "epoch": 2.63, + "learning_rate": 2.4940243372446763e-06, + "loss": 0.1359, + "step": 32225 + }, + { + "epoch": 2.63, + "learning_rate": 2.4934810951760105e-06, + "loss": 0.1931, + "step": 32226 + }, + { + "epoch": 2.63, + "learning_rate": 2.4929378531073448e-06, + "loss": 0.4575, + "step": 32227 + }, + { + "epoch": 2.63, + "learning_rate": 2.492394611038679e-06, + "loss": 0.4237, + "step": 32228 + }, + { + "epoch": 2.63, + "learning_rate": 2.4918513689700132e-06, + "loss": 0.4784, + "step": 32229 + }, + { + "epoch": 2.63, + "learning_rate": 2.4913081269013475e-06, + "loss": 0.206, + "step": 32230 + }, + { + "epoch": 2.63, + "learning_rate": 2.4907648848326817e-06, + "loss": 0.2903, + "step": 32231 + }, + { + "epoch": 2.63, + "learning_rate": 2.490221642764016e-06, + "loss": 0.1613, + "step": 32232 + }, + { + "epoch": 2.63, + "learning_rate": 2.48967840069535e-06, + "loss": 0.3555, + "step": 32233 + }, + { + "epoch": 2.63, + "learning_rate": 2.4891351586266844e-06, + "loss": 0.1102, + "step": 32234 + }, + { + "epoch": 2.63, + "learning_rate": 2.4885919165580186e-06, + "loss": 0.179, + "step": 32235 + }, + { + "epoch": 2.63, + "learning_rate": 2.4880486744893524e-06, + "loss": 0.175, + "step": 32236 + }, + { + "epoch": 2.63, + "learning_rate": 2.4875054324206867e-06, + "loss": 0.1178, + "step": 32237 + }, + { + "epoch": 2.63, + "learning_rate": 2.486962190352021e-06, + "loss": 0.1128, + "step": 32238 + }, + { + "epoch": 2.63, + "learning_rate": 2.4864189482833555e-06, + "loss": 0.0604, + "step": 32239 + }, + { + "epoch": 2.63, + "learning_rate": 2.4858757062146898e-06, + "loss": 0.2267, + "step": 32240 + }, + { + "epoch": 2.63, + "learning_rate": 2.4853324641460236e-06, + "loss": 0.1768, + "step": 32241 + }, + { + "epoch": 2.63, + "learning_rate": 2.484789222077358e-06, + "loss": 0.2686, + "step": 32242 + }, + { + "epoch": 2.63, + "learning_rate": 2.484245980008692e-06, + "loss": 0.5773, + "step": 32243 + }, + { + "epoch": 2.63, + "learning_rate": 2.4837027379400263e-06, + "loss": 0.1453, + "step": 32244 + }, + { + "epoch": 2.63, + "learning_rate": 2.4831594958713605e-06, + "loss": 0.3954, + "step": 32245 + }, + { + "epoch": 2.63, + "learning_rate": 2.4826162538026947e-06, + "loss": 0.1565, + "step": 32246 + }, + { + "epoch": 2.63, + "learning_rate": 2.482073011734029e-06, + "loss": 0.0735, + "step": 32247 + }, + { + "epoch": 2.63, + "learning_rate": 2.481529769665363e-06, + "loss": 0.3593, + "step": 32248 + }, + { + "epoch": 2.63, + "learning_rate": 2.4809865275966974e-06, + "loss": 0.0829, + "step": 32249 + }, + { + "epoch": 2.63, + "learning_rate": 2.4804432855280312e-06, + "loss": 0.0583, + "step": 32250 + }, + { + "epoch": 2.63, + "eval_accuracy": 0.8424859908303617, + "eval_loss": 0.4833948612213135, + "eval_runtime": 22.3477, + "eval_samples_per_second": 439.196, + "eval_steps_per_second": 3.446, + "step": 32250 + }, + { + "epoch": 2.63, + "learning_rate": 2.4799000434593655e-06, + "loss": 0.109, + "step": 32251 + }, + { + "epoch": 2.63, + "learning_rate": 2.4793568013906997e-06, + "loss": 0.1618, + "step": 32252 + }, + { + "epoch": 2.63, + "learning_rate": 2.4788135593220343e-06, + "loss": 0.2026, + "step": 32253 + }, + { + "epoch": 2.63, + "learning_rate": 2.4782703172533686e-06, + "loss": 0.272, + "step": 32254 + }, + { + "epoch": 2.63, + "learning_rate": 2.4777270751847024e-06, + "loss": 0.1989, + "step": 32255 + }, + { + "epoch": 2.63, + "learning_rate": 2.4771838331160366e-06, + "loss": 0.2173, + "step": 32256 + }, + { + "epoch": 2.63, + "learning_rate": 2.476640591047371e-06, + "loss": 0.1789, + "step": 32257 + }, + { + "epoch": 2.63, + "learning_rate": 2.476097348978705e-06, + "loss": 0.1177, + "step": 32258 + }, + { + "epoch": 2.63, + "learning_rate": 2.4755541069100393e-06, + "loss": 0.1042, + "step": 32259 + }, + { + "epoch": 2.63, + "learning_rate": 2.4750108648413735e-06, + "loss": 0.1289, + "step": 32260 + }, + { + "epoch": 2.63, + "learning_rate": 2.4744676227727078e-06, + "loss": 0.4249, + "step": 32261 + }, + { + "epoch": 2.63, + "learning_rate": 2.473924380704042e-06, + "loss": 0.1525, + "step": 32262 + }, + { + "epoch": 2.63, + "learning_rate": 2.4733811386353762e-06, + "loss": 0.3713, + "step": 32263 + }, + { + "epoch": 2.63, + "learning_rate": 2.47283789656671e-06, + "loss": 0.1144, + "step": 32264 + }, + { + "epoch": 2.63, + "learning_rate": 2.4722946544980443e-06, + "loss": 0.2148, + "step": 32265 + }, + { + "epoch": 2.63, + "learning_rate": 2.471751412429379e-06, + "loss": 0.2713, + "step": 32266 + }, + { + "epoch": 2.63, + "learning_rate": 2.471208170360713e-06, + "loss": 0.2356, + "step": 32267 + }, + { + "epoch": 2.63, + "learning_rate": 2.4706649282920474e-06, + "loss": 0.2356, + "step": 32268 + }, + { + "epoch": 2.63, + "learning_rate": 2.470121686223381e-06, + "loss": 0.1045, + "step": 32269 + }, + { + "epoch": 2.63, + "learning_rate": 2.4695784441547154e-06, + "loss": 0.25, + "step": 32270 + }, + { + "epoch": 2.63, + "learning_rate": 2.4690352020860497e-06, + "loss": 0.2608, + "step": 32271 + }, + { + "epoch": 2.63, + "learning_rate": 2.468491960017384e-06, + "loss": 0.3969, + "step": 32272 + }, + { + "epoch": 2.63, + "learning_rate": 2.467948717948718e-06, + "loss": 0.2467, + "step": 32273 + }, + { + "epoch": 2.63, + "learning_rate": 2.4674054758800523e-06, + "loss": 0.4792, + "step": 32274 + }, + { + "epoch": 2.63, + "learning_rate": 2.4668622338113866e-06, + "loss": 0.1218, + "step": 32275 + }, + { + "epoch": 2.63, + "learning_rate": 2.466318991742721e-06, + "loss": 0.4886, + "step": 32276 + }, + { + "epoch": 2.63, + "learning_rate": 2.465775749674055e-06, + "loss": 0.1834, + "step": 32277 + }, + { + "epoch": 2.63, + "learning_rate": 2.4652325076053893e-06, + "loss": 0.1516, + "step": 32278 + }, + { + "epoch": 2.63, + "learning_rate": 2.464689265536723e-06, + "loss": 0.2297, + "step": 32279 + }, + { + "epoch": 2.63, + "learning_rate": 2.4641460234680577e-06, + "loss": 0.1765, + "step": 32280 + }, + { + "epoch": 2.63, + "learning_rate": 2.463602781399392e-06, + "loss": 0.2368, + "step": 32281 + }, + { + "epoch": 2.63, + "learning_rate": 2.463059539330726e-06, + "loss": 0.1618, + "step": 32282 + }, + { + "epoch": 2.63, + "learning_rate": 2.46251629726206e-06, + "loss": 0.195, + "step": 32283 + }, + { + "epoch": 2.63, + "learning_rate": 2.4619730551933942e-06, + "loss": 0.1341, + "step": 32284 + }, + { + "epoch": 2.63, + "learning_rate": 2.4614298131247285e-06, + "loss": 0.239, + "step": 32285 + }, + { + "epoch": 2.63, + "learning_rate": 2.4608865710560627e-06, + "loss": 0.2108, + "step": 32286 + }, + { + "epoch": 2.63, + "learning_rate": 2.460343328987397e-06, + "loss": 0.2792, + "step": 32287 + }, + { + "epoch": 2.63, + "learning_rate": 2.459800086918731e-06, + "loss": 0.1859, + "step": 32288 + }, + { + "epoch": 2.63, + "learning_rate": 2.4592568448500654e-06, + "loss": 0.1909, + "step": 32289 + }, + { + "epoch": 2.63, + "learning_rate": 2.4587136027813996e-06, + "loss": 0.2698, + "step": 32290 + }, + { + "epoch": 2.63, + "learning_rate": 2.458170360712734e-06, + "loss": 0.2676, + "step": 32291 + }, + { + "epoch": 2.63, + "learning_rate": 2.457627118644068e-06, + "loss": 0.1157, + "step": 32292 + }, + { + "epoch": 2.63, + "learning_rate": 2.4570838765754023e-06, + "loss": 0.3345, + "step": 32293 + }, + { + "epoch": 2.63, + "learning_rate": 2.4565406345067365e-06, + "loss": 0.2503, + "step": 32294 + }, + { + "epoch": 2.63, + "learning_rate": 2.4559973924380708e-06, + "loss": 0.1305, + "step": 32295 + }, + { + "epoch": 2.63, + "learning_rate": 2.455454150369405e-06, + "loss": 0.1546, + "step": 32296 + }, + { + "epoch": 2.63, + "learning_rate": 2.4549109083007392e-06, + "loss": 0.3498, + "step": 32297 + }, + { + "epoch": 2.63, + "learning_rate": 2.454367666232073e-06, + "loss": 0.1997, + "step": 32298 + }, + { + "epoch": 2.63, + "learning_rate": 2.4538244241634073e-06, + "loss": 0.1511, + "step": 32299 + }, + { + "epoch": 2.63, + "learning_rate": 2.4532811820947415e-06, + "loss": 0.0546, + "step": 32300 + }, + { + "epoch": 2.63, + "learning_rate": 2.4527379400260757e-06, + "loss": 0.3198, + "step": 32301 + }, + { + "epoch": 2.63, + "learning_rate": 2.45219469795741e-06, + "loss": 0.1734, + "step": 32302 + }, + { + "epoch": 2.63, + "learning_rate": 2.451651455888744e-06, + "loss": 0.2241, + "step": 32303 + }, + { + "epoch": 2.63, + "learning_rate": 2.4511082138200784e-06, + "loss": 0.2471, + "step": 32304 + }, + { + "epoch": 2.63, + "learning_rate": 2.4505649717514126e-06, + "loss": 0.1792, + "step": 32305 + }, + { + "epoch": 2.63, + "learning_rate": 2.450021729682747e-06, + "loss": 0.0684, + "step": 32306 + }, + { + "epoch": 2.63, + "learning_rate": 2.449478487614081e-06, + "loss": 0.2447, + "step": 32307 + }, + { + "epoch": 2.63, + "learning_rate": 2.4489352455454153e-06, + "loss": 0.2002, + "step": 32308 + }, + { + "epoch": 2.63, + "learning_rate": 2.4483920034767496e-06, + "loss": 0.3656, + "step": 32309 + }, + { + "epoch": 2.63, + "learning_rate": 2.447848761408084e-06, + "loss": 0.1657, + "step": 32310 + }, + { + "epoch": 2.63, + "learning_rate": 2.447305519339418e-06, + "loss": 0.2982, + "step": 32311 + }, + { + "epoch": 2.63, + "learning_rate": 2.446762277270752e-06, + "loss": 0.6753, + "step": 32312 + }, + { + "epoch": 2.63, + "learning_rate": 2.446219035202086e-06, + "loss": 0.1614, + "step": 32313 + }, + { + "epoch": 2.63, + "learning_rate": 2.4456757931334203e-06, + "loss": 0.1222, + "step": 32314 + }, + { + "epoch": 2.63, + "learning_rate": 2.4451325510647545e-06, + "loss": 0.238, + "step": 32315 + }, + { + "epoch": 2.63, + "learning_rate": 2.444589308996089e-06, + "loss": 0.2991, + "step": 32316 + }, + { + "epoch": 2.63, + "learning_rate": 2.444046066927423e-06, + "loss": 0.2192, + "step": 32317 + }, + { + "epoch": 2.63, + "learning_rate": 2.4435028248587572e-06, + "loss": 0.3103, + "step": 32318 + }, + { + "epoch": 2.63, + "learning_rate": 2.4429595827900914e-06, + "loss": 0.0795, + "step": 32319 + }, + { + "epoch": 2.63, + "learning_rate": 2.4424163407214257e-06, + "loss": 0.159, + "step": 32320 + }, + { + "epoch": 2.63, + "learning_rate": 2.44187309865276e-06, + "loss": 0.0866, + "step": 32321 + }, + { + "epoch": 2.63, + "learning_rate": 2.441329856584094e-06, + "loss": 0.2326, + "step": 32322 + }, + { + "epoch": 2.63, + "learning_rate": 2.4407866145154284e-06, + "loss": 0.1498, + "step": 32323 + }, + { + "epoch": 2.63, + "learning_rate": 2.4402433724467626e-06, + "loss": 0.3129, + "step": 32324 + }, + { + "epoch": 2.63, + "learning_rate": 2.439700130378097e-06, + "loss": 0.1499, + "step": 32325 + }, + { + "epoch": 2.63, + "learning_rate": 2.4391568883094306e-06, + "loss": 0.2647, + "step": 32326 + }, + { + "epoch": 2.63, + "learning_rate": 2.438613646240765e-06, + "loss": 0.2495, + "step": 32327 + }, + { + "epoch": 2.63, + "learning_rate": 2.438070404172099e-06, + "loss": 0.1351, + "step": 32328 + }, + { + "epoch": 2.63, + "learning_rate": 2.4375271621034338e-06, + "loss": 0.2592, + "step": 32329 + }, + { + "epoch": 2.63, + "learning_rate": 2.436983920034768e-06, + "loss": 0.1634, + "step": 32330 + }, + { + "epoch": 2.63, + "learning_rate": 2.436440677966102e-06, + "loss": 0.1694, + "step": 32331 + }, + { + "epoch": 2.63, + "learning_rate": 2.435897435897436e-06, + "loss": 0.3575, + "step": 32332 + }, + { + "epoch": 2.63, + "learning_rate": 2.4353541938287703e-06, + "loss": 0.2072, + "step": 32333 + }, + { + "epoch": 2.63, + "learning_rate": 2.4348109517601045e-06, + "loss": 0.7674, + "step": 32334 + }, + { + "epoch": 2.63, + "learning_rate": 2.4342677096914387e-06, + "loss": 0.1717, + "step": 32335 + }, + { + "epoch": 2.63, + "learning_rate": 2.433724467622773e-06, + "loss": 0.1923, + "step": 32336 + }, + { + "epoch": 2.64, + "learning_rate": 2.433181225554107e-06, + "loss": 0.2052, + "step": 32337 + }, + { + "epoch": 2.64, + "learning_rate": 2.4326379834854414e-06, + "loss": 0.2178, + "step": 32338 + }, + { + "epoch": 2.64, + "learning_rate": 2.4320947414167756e-06, + "loss": 0.4683, + "step": 32339 + }, + { + "epoch": 2.64, + "learning_rate": 2.4315514993481094e-06, + "loss": 0.2078, + "step": 32340 + }, + { + "epoch": 2.64, + "learning_rate": 2.4310082572794437e-06, + "loss": 0.2325, + "step": 32341 + }, + { + "epoch": 2.64, + "learning_rate": 2.430465015210778e-06, + "loss": 0.3977, + "step": 32342 + }, + { + "epoch": 2.64, + "learning_rate": 2.4299217731421126e-06, + "loss": 0.1035, + "step": 32343 + }, + { + "epoch": 2.64, + "learning_rate": 2.4293785310734468e-06, + "loss": 0.1864, + "step": 32344 + }, + { + "epoch": 2.64, + "learning_rate": 2.4288352890047806e-06, + "loss": 0.2488, + "step": 32345 + }, + { + "epoch": 2.64, + "learning_rate": 2.428292046936115e-06, + "loss": 0.5381, + "step": 32346 + }, + { + "epoch": 2.64, + "learning_rate": 2.427748804867449e-06, + "loss": 0.1151, + "step": 32347 + }, + { + "epoch": 2.64, + "learning_rate": 2.4272055627987833e-06, + "loss": 0.0974, + "step": 32348 + }, + { + "epoch": 2.64, + "learning_rate": 2.4266623207301175e-06, + "loss": 0.3817, + "step": 32349 + }, + { + "epoch": 2.64, + "learning_rate": 2.4261190786614517e-06, + "loss": 0.178, + "step": 32350 + }, + { + "epoch": 2.64, + "learning_rate": 2.425575836592786e-06, + "loss": 0.0806, + "step": 32351 + }, + { + "epoch": 2.64, + "learning_rate": 2.42503259452412e-06, + "loss": 0.2784, + "step": 32352 + }, + { + "epoch": 2.64, + "learning_rate": 2.4244893524554544e-06, + "loss": 0.2195, + "step": 32353 + }, + { + "epoch": 2.64, + "learning_rate": 2.4239461103867887e-06, + "loss": 0.154, + "step": 32354 + }, + { + "epoch": 2.64, + "learning_rate": 2.4234028683181225e-06, + "loss": 0.1874, + "step": 32355 + }, + { + "epoch": 2.64, + "learning_rate": 2.422859626249457e-06, + "loss": 0.4452, + "step": 32356 + }, + { + "epoch": 2.64, + "learning_rate": 2.4223163841807914e-06, + "loss": 0.3604, + "step": 32357 + }, + { + "epoch": 2.64, + "learning_rate": 2.4217731421121256e-06, + "loss": 0.1499, + "step": 32358 + }, + { + "epoch": 2.64, + "learning_rate": 2.42122990004346e-06, + "loss": 0.168, + "step": 32359 + }, + { + "epoch": 2.64, + "learning_rate": 2.4206866579747936e-06, + "loss": 0.2044, + "step": 32360 + }, + { + "epoch": 2.64, + "learning_rate": 2.420143415906128e-06, + "loss": 0.1925, + "step": 32361 + }, + { + "epoch": 2.64, + "learning_rate": 2.419600173837462e-06, + "loss": 0.3168, + "step": 32362 + }, + { + "epoch": 2.64, + "learning_rate": 2.4190569317687963e-06, + "loss": 0.1474, + "step": 32363 + }, + { + "epoch": 2.64, + "learning_rate": 2.4185136897001306e-06, + "loss": 0.2009, + "step": 32364 + }, + { + "epoch": 2.64, + "learning_rate": 2.4179704476314648e-06, + "loss": 0.4832, + "step": 32365 + }, + { + "epoch": 2.64, + "learning_rate": 2.417427205562799e-06, + "loss": 0.3988, + "step": 32366 + }, + { + "epoch": 2.64, + "learning_rate": 2.4168839634941332e-06, + "loss": 0.2111, + "step": 32367 + }, + { + "epoch": 2.64, + "learning_rate": 2.4163407214254675e-06, + "loss": 0.1844, + "step": 32368 + }, + { + "epoch": 2.64, + "learning_rate": 2.4157974793568013e-06, + "loss": 0.3874, + "step": 32369 + }, + { + "epoch": 2.64, + "learning_rate": 2.415254237288136e-06, + "loss": 0.2339, + "step": 32370 + }, + { + "epoch": 2.64, + "learning_rate": 2.41471099521947e-06, + "loss": 0.1783, + "step": 32371 + }, + { + "epoch": 2.64, + "learning_rate": 2.4141677531508044e-06, + "loss": 0.302, + "step": 32372 + }, + { + "epoch": 2.64, + "learning_rate": 2.4136245110821386e-06, + "loss": 0.2562, + "step": 32373 + }, + { + "epoch": 2.64, + "learning_rate": 2.4130812690134724e-06, + "loss": 0.2771, + "step": 32374 + }, + { + "epoch": 2.64, + "learning_rate": 2.4125380269448067e-06, + "loss": 0.2516, + "step": 32375 + }, + { + "epoch": 2.64, + "learning_rate": 2.411994784876141e-06, + "loss": 0.1923, + "step": 32376 + }, + { + "epoch": 2.64, + "learning_rate": 2.411451542807475e-06, + "loss": 0.2569, + "step": 32377 + }, + { + "epoch": 2.64, + "learning_rate": 2.4109083007388094e-06, + "loss": 0.2258, + "step": 32378 + }, + { + "epoch": 2.64, + "learning_rate": 2.4103650586701436e-06, + "loss": 0.2608, + "step": 32379 + }, + { + "epoch": 2.64, + "learning_rate": 2.409821816601478e-06, + "loss": 0.5109, + "step": 32380 + }, + { + "epoch": 2.64, + "learning_rate": 2.409278574532812e-06, + "loss": 0.0668, + "step": 32381 + }, + { + "epoch": 2.64, + "learning_rate": 2.4087353324641463e-06, + "loss": 0.0894, + "step": 32382 + }, + { + "epoch": 2.64, + "learning_rate": 2.4081920903954805e-06, + "loss": 0.6045, + "step": 32383 + }, + { + "epoch": 2.64, + "learning_rate": 2.4076488483268147e-06, + "loss": 0.1949, + "step": 32384 + }, + { + "epoch": 2.64, + "learning_rate": 2.407105606258149e-06, + "loss": 0.1352, + "step": 32385 + }, + { + "epoch": 2.64, + "learning_rate": 2.406562364189483e-06, + "loss": 0.4169, + "step": 32386 + }, + { + "epoch": 2.64, + "learning_rate": 2.4060191221208174e-06, + "loss": 0.0759, + "step": 32387 + }, + { + "epoch": 2.64, + "learning_rate": 2.4054758800521512e-06, + "loss": 0.1705, + "step": 32388 + }, + { + "epoch": 2.64, + "learning_rate": 2.4049326379834855e-06, + "loss": 0.1387, + "step": 32389 + }, + { + "epoch": 2.64, + "learning_rate": 2.4043893959148197e-06, + "loss": 0.3817, + "step": 32390 + }, + { + "epoch": 2.64, + "learning_rate": 2.403846153846154e-06, + "loss": 0.2721, + "step": 32391 + }, + { + "epoch": 2.64, + "learning_rate": 2.403302911777488e-06, + "loss": 0.3695, + "step": 32392 + }, + { + "epoch": 2.64, + "learning_rate": 2.4027596697088224e-06, + "loss": 0.071, + "step": 32393 + }, + { + "epoch": 2.64, + "learning_rate": 2.4022164276401566e-06, + "loss": 0.0622, + "step": 32394 + }, + { + "epoch": 2.64, + "learning_rate": 2.401673185571491e-06, + "loss": 0.1588, + "step": 32395 + }, + { + "epoch": 2.64, + "learning_rate": 2.401129943502825e-06, + "loss": 0.1602, + "step": 32396 + }, + { + "epoch": 2.64, + "learning_rate": 2.4005867014341593e-06, + "loss": 0.2806, + "step": 32397 + }, + { + "epoch": 2.64, + "learning_rate": 2.4000434593654935e-06, + "loss": 0.1552, + "step": 32398 + }, + { + "epoch": 2.64, + "learning_rate": 2.3995002172968278e-06, + "loss": 0.252, + "step": 32399 + }, + { + "epoch": 2.64, + "learning_rate": 2.398956975228162e-06, + "loss": 0.1236, + "step": 32400 + }, + { + "epoch": 2.64, + "learning_rate": 2.3984137331594962e-06, + "loss": 0.3022, + "step": 32401 + }, + { + "epoch": 2.64, + "learning_rate": 2.39787049109083e-06, + "loss": 0.3017, + "step": 32402 + }, + { + "epoch": 2.64, + "learning_rate": 2.3973272490221643e-06, + "loss": 0.0884, + "step": 32403 + }, + { + "epoch": 2.64, + "learning_rate": 2.3967840069534985e-06, + "loss": 0.342, + "step": 32404 + }, + { + "epoch": 2.64, + "learning_rate": 2.3962407648848327e-06, + "loss": 0.2432, + "step": 32405 + }, + { + "epoch": 2.64, + "learning_rate": 2.3956975228161674e-06, + "loss": 0.2708, + "step": 32406 + }, + { + "epoch": 2.64, + "learning_rate": 2.395154280747501e-06, + "loss": 0.2998, + "step": 32407 + }, + { + "epoch": 2.64, + "learning_rate": 2.3946110386788354e-06, + "loss": 0.3179, + "step": 32408 + }, + { + "epoch": 2.64, + "learning_rate": 2.3940677966101697e-06, + "loss": 0.2739, + "step": 32409 + }, + { + "epoch": 2.64, + "learning_rate": 2.393524554541504e-06, + "loss": 0.2796, + "step": 32410 + }, + { + "epoch": 2.64, + "learning_rate": 2.392981312472838e-06, + "loss": 0.3233, + "step": 32411 + }, + { + "epoch": 2.64, + "learning_rate": 2.3924380704041723e-06, + "loss": 0.3324, + "step": 32412 + }, + { + "epoch": 2.64, + "learning_rate": 2.3918948283355066e-06, + "loss": 0.2372, + "step": 32413 + }, + { + "epoch": 2.64, + "learning_rate": 2.391351586266841e-06, + "loss": 0.2353, + "step": 32414 + }, + { + "epoch": 2.64, + "learning_rate": 2.390808344198175e-06, + "loss": 0.1526, + "step": 32415 + }, + { + "epoch": 2.64, + "learning_rate": 2.3902651021295093e-06, + "loss": 0.2233, + "step": 32416 + }, + { + "epoch": 2.64, + "learning_rate": 2.389721860060843e-06, + "loss": 0.4982, + "step": 32417 + }, + { + "epoch": 2.64, + "learning_rate": 2.3891786179921773e-06, + "loss": 0.2946, + "step": 32418 + }, + { + "epoch": 2.64, + "learning_rate": 2.3886353759235115e-06, + "loss": 0.2773, + "step": 32419 + }, + { + "epoch": 2.64, + "learning_rate": 2.388092133854846e-06, + "loss": 0.2217, + "step": 32420 + }, + { + "epoch": 2.64, + "learning_rate": 2.38754889178618e-06, + "loss": 0.2323, + "step": 32421 + }, + { + "epoch": 2.64, + "learning_rate": 2.3870056497175142e-06, + "loss": 0.2452, + "step": 32422 + }, + { + "epoch": 2.64, + "learning_rate": 2.3864624076488485e-06, + "loss": 0.395, + "step": 32423 + }, + { + "epoch": 2.64, + "learning_rate": 2.3859191655801827e-06, + "loss": 0.1968, + "step": 32424 + }, + { + "epoch": 2.64, + "learning_rate": 2.385375923511517e-06, + "loss": 0.4491, + "step": 32425 + }, + { + "epoch": 2.64, + "learning_rate": 2.384832681442851e-06, + "loss": 0.3685, + "step": 32426 + }, + { + "epoch": 2.64, + "learning_rate": 2.3842894393741854e-06, + "loss": 0.1459, + "step": 32427 + }, + { + "epoch": 2.64, + "learning_rate": 2.3837461973055196e-06, + "loss": 0.3876, + "step": 32428 + }, + { + "epoch": 2.64, + "learning_rate": 2.383202955236854e-06, + "loss": 0.2827, + "step": 32429 + }, + { + "epoch": 2.64, + "learning_rate": 2.382659713168188e-06, + "loss": 0.2662, + "step": 32430 + }, + { + "epoch": 2.64, + "learning_rate": 2.382116471099522e-06, + "loss": 0.2356, + "step": 32431 + }, + { + "epoch": 2.64, + "learning_rate": 2.381573229030856e-06, + "loss": 0.3152, + "step": 32432 + }, + { + "epoch": 2.64, + "learning_rate": 2.3810299869621908e-06, + "loss": 0.1612, + "step": 32433 + }, + { + "epoch": 2.64, + "learning_rate": 2.380486744893525e-06, + "loss": 0.392, + "step": 32434 + }, + { + "epoch": 2.64, + "learning_rate": 2.3799435028248592e-06, + "loss": 0.3651, + "step": 32435 + }, + { + "epoch": 2.64, + "learning_rate": 2.379400260756193e-06, + "loss": 0.4449, + "step": 32436 + }, + { + "epoch": 2.64, + "learning_rate": 2.3788570186875273e-06, + "loss": 0.2989, + "step": 32437 + }, + { + "epoch": 2.64, + "learning_rate": 2.3783137766188615e-06, + "loss": 0.2812, + "step": 32438 + }, + { + "epoch": 2.64, + "learning_rate": 2.3777705345501957e-06, + "loss": 0.1419, + "step": 32439 + }, + { + "epoch": 2.64, + "learning_rate": 2.37722729248153e-06, + "loss": 0.1733, + "step": 32440 + }, + { + "epoch": 2.64, + "learning_rate": 2.376684050412864e-06, + "loss": 0.4706, + "step": 32441 + }, + { + "epoch": 2.64, + "learning_rate": 2.3761408083441984e-06, + "loss": 0.2373, + "step": 32442 + }, + { + "epoch": 2.64, + "learning_rate": 2.3755975662755326e-06, + "loss": 0.1293, + "step": 32443 + }, + { + "epoch": 2.64, + "learning_rate": 2.375054324206867e-06, + "loss": 0.2595, + "step": 32444 + }, + { + "epoch": 2.64, + "learning_rate": 2.3745110821382007e-06, + "loss": 0.1373, + "step": 32445 + }, + { + "epoch": 2.64, + "learning_rate": 2.373967840069535e-06, + "loss": 0.0709, + "step": 32446 + }, + { + "epoch": 2.64, + "learning_rate": 2.3734245980008696e-06, + "loss": 0.3109, + "step": 32447 + }, + { + "epoch": 2.64, + "learning_rate": 2.372881355932204e-06, + "loss": 0.4555, + "step": 32448 + }, + { + "epoch": 2.64, + "learning_rate": 2.372338113863538e-06, + "loss": 0.0878, + "step": 32449 + }, + { + "epoch": 2.64, + "learning_rate": 2.371794871794872e-06, + "loss": 0.1113, + "step": 32450 + }, + { + "epoch": 2.64, + "learning_rate": 2.371251629726206e-06, + "loss": 0.1498, + "step": 32451 + }, + { + "epoch": 2.64, + "learning_rate": 2.3707083876575403e-06, + "loss": 0.3042, + "step": 32452 + }, + { + "epoch": 2.64, + "learning_rate": 2.3701651455888745e-06, + "loss": 0.5451, + "step": 32453 + }, + { + "epoch": 2.64, + "learning_rate": 2.3696219035202088e-06, + "loss": 0.149, + "step": 32454 + }, + { + "epoch": 2.64, + "learning_rate": 2.369078661451543e-06, + "loss": 0.1866, + "step": 32455 + }, + { + "epoch": 2.64, + "learning_rate": 2.3685354193828772e-06, + "loss": 0.0851, + "step": 32456 + }, + { + "epoch": 2.64, + "learning_rate": 2.3679921773142115e-06, + "loss": 0.1243, + "step": 32457 + }, + { + "epoch": 2.64, + "learning_rate": 2.3674489352455457e-06, + "loss": 0.379, + "step": 32458 + }, + { + "epoch": 2.64, + "learning_rate": 2.3669056931768795e-06, + "loss": 0.2392, + "step": 32459 + }, + { + "epoch": 2.65, + "learning_rate": 2.366362451108214e-06, + "loss": 0.3972, + "step": 32460 + }, + { + "epoch": 2.65, + "learning_rate": 2.3658192090395484e-06, + "loss": 0.2257, + "step": 32461 + }, + { + "epoch": 2.65, + "learning_rate": 2.3652759669708826e-06, + "loss": 0.491, + "step": 32462 + }, + { + "epoch": 2.65, + "learning_rate": 2.364732724902217e-06, + "loss": 0.4326, + "step": 32463 + }, + { + "epoch": 2.65, + "learning_rate": 2.3641894828335506e-06, + "loss": 0.197, + "step": 32464 + }, + { + "epoch": 2.65, + "learning_rate": 2.363646240764885e-06, + "loss": 0.2453, + "step": 32465 + }, + { + "epoch": 2.65, + "learning_rate": 2.363102998696219e-06, + "loss": 0.2186, + "step": 32466 + }, + { + "epoch": 2.65, + "learning_rate": 2.3625597566275533e-06, + "loss": 0.2487, + "step": 32467 + }, + { + "epoch": 2.65, + "learning_rate": 2.3620165145588876e-06, + "loss": 0.2066, + "step": 32468 + }, + { + "epoch": 2.65, + "learning_rate": 2.361473272490222e-06, + "loss": 0.1809, + "step": 32469 + }, + { + "epoch": 2.65, + "learning_rate": 2.360930030421556e-06, + "loss": 0.2378, + "step": 32470 + }, + { + "epoch": 2.65, + "learning_rate": 2.3603867883528903e-06, + "loss": 0.179, + "step": 32471 + }, + { + "epoch": 2.65, + "learning_rate": 2.3598435462842245e-06, + "loss": 0.0917, + "step": 32472 + }, + { + "epoch": 2.65, + "learning_rate": 2.3593003042155587e-06, + "loss": 0.0819, + "step": 32473 + }, + { + "epoch": 2.65, + "learning_rate": 2.358757062146893e-06, + "loss": 0.194, + "step": 32474 + }, + { + "epoch": 2.65, + "learning_rate": 2.358213820078227e-06, + "loss": 0.2073, + "step": 32475 + }, + { + "epoch": 2.65, + "learning_rate": 2.3576705780095614e-06, + "loss": 0.1577, + "step": 32476 + }, + { + "epoch": 2.65, + "learning_rate": 2.3571273359408956e-06, + "loss": 0.1751, + "step": 32477 + }, + { + "epoch": 2.65, + "learning_rate": 2.3565840938722294e-06, + "loss": 0.1773, + "step": 32478 + }, + { + "epoch": 2.65, + "learning_rate": 2.3560408518035637e-06, + "loss": 0.2294, + "step": 32479 + }, + { + "epoch": 2.65, + "learning_rate": 2.355497609734898e-06, + "loss": 0.1176, + "step": 32480 + }, + { + "epoch": 2.65, + "learning_rate": 2.354954367666232e-06, + "loss": 0.1484, + "step": 32481 + }, + { + "epoch": 2.65, + "learning_rate": 2.3544111255975664e-06, + "loss": 0.4514, + "step": 32482 + }, + { + "epoch": 2.65, + "learning_rate": 2.3538678835289006e-06, + "loss": 0.1663, + "step": 32483 + }, + { + "epoch": 2.65, + "learning_rate": 2.353324641460235e-06, + "loss": 0.2875, + "step": 32484 + }, + { + "epoch": 2.65, + "learning_rate": 2.352781399391569e-06, + "loss": 0.1764, + "step": 32485 + }, + { + "epoch": 2.65, + "learning_rate": 2.3522381573229033e-06, + "loss": 0.2607, + "step": 32486 + }, + { + "epoch": 2.65, + "learning_rate": 2.3516949152542375e-06, + "loss": 0.1211, + "step": 32487 + }, + { + "epoch": 2.65, + "learning_rate": 2.3511516731855718e-06, + "loss": 0.1358, + "step": 32488 + }, + { + "epoch": 2.65, + "learning_rate": 2.350608431116906e-06, + "loss": 0.1656, + "step": 32489 + }, + { + "epoch": 2.65, + "learning_rate": 2.35006518904824e-06, + "loss": 0.0377, + "step": 32490 + }, + { + "epoch": 2.65, + "learning_rate": 2.3495219469795744e-06, + "loss": 0.0759, + "step": 32491 + }, + { + "epoch": 2.65, + "learning_rate": 2.3489787049109087e-06, + "loss": 0.1592, + "step": 32492 + }, + { + "epoch": 2.65, + "learning_rate": 2.3484354628422425e-06, + "loss": 0.095, + "step": 32493 + }, + { + "epoch": 2.65, + "learning_rate": 2.3478922207735767e-06, + "loss": 0.3827, + "step": 32494 + }, + { + "epoch": 2.65, + "learning_rate": 2.347348978704911e-06, + "loss": 0.3807, + "step": 32495 + }, + { + "epoch": 2.65, + "learning_rate": 2.3468057366362456e-06, + "loss": 0.0798, + "step": 32496 + }, + { + "epoch": 2.65, + "learning_rate": 2.3462624945675794e-06, + "loss": 0.1511, + "step": 32497 + }, + { + "epoch": 2.65, + "learning_rate": 2.3457192524989136e-06, + "loss": 0.1035, + "step": 32498 + }, + { + "epoch": 2.65, + "learning_rate": 2.345176010430248e-06, + "loss": 0.0474, + "step": 32499 + }, + { + "epoch": 2.65, + "learning_rate": 2.344632768361582e-06, + "loss": 0.1271, + "step": 32500 + }, + { + "epoch": 2.65, + "eval_accuracy": 0.8445236882322975, + "eval_loss": 0.47894003987312317, + "eval_runtime": 22.274, + "eval_samples_per_second": 440.648, + "eval_steps_per_second": 3.457, + "step": 32500 + }, + { + "epoch": 2.65, + "learning_rate": 2.3440895262929163e-06, + "loss": 0.3119, + "step": 32501 + }, + { + "epoch": 2.65, + "learning_rate": 2.3435462842242506e-06, + "loss": 0.2421, + "step": 32502 + }, + { + "epoch": 2.65, + "learning_rate": 2.3430030421555848e-06, + "loss": 0.1986, + "step": 32503 + }, + { + "epoch": 2.65, + "learning_rate": 2.342459800086919e-06, + "loss": 0.2416, + "step": 32504 + }, + { + "epoch": 2.65, + "learning_rate": 2.3419165580182532e-06, + "loss": 0.2158, + "step": 32505 + }, + { + "epoch": 2.65, + "learning_rate": 2.3413733159495875e-06, + "loss": 0.0796, + "step": 32506 + }, + { + "epoch": 2.65, + "learning_rate": 2.3408300738809213e-06, + "loss": 0.4405, + "step": 32507 + }, + { + "epoch": 2.65, + "learning_rate": 2.3402868318122555e-06, + "loss": 0.2622, + "step": 32508 + }, + { + "epoch": 2.65, + "learning_rate": 2.3397435897435897e-06, + "loss": 0.0544, + "step": 32509 + }, + { + "epoch": 2.65, + "learning_rate": 2.3392003476749244e-06, + "loss": 0.2464, + "step": 32510 + }, + { + "epoch": 2.65, + "learning_rate": 2.3386571056062586e-06, + "loss": 0.1682, + "step": 32511 + }, + { + "epoch": 2.65, + "learning_rate": 2.3381138635375924e-06, + "loss": 0.1588, + "step": 32512 + }, + { + "epoch": 2.65, + "learning_rate": 2.3375706214689267e-06, + "loss": 0.1809, + "step": 32513 + }, + { + "epoch": 2.65, + "learning_rate": 2.337027379400261e-06, + "loss": 0.0359, + "step": 32514 + }, + { + "epoch": 2.65, + "learning_rate": 2.336484137331595e-06, + "loss": 0.1902, + "step": 32515 + }, + { + "epoch": 2.65, + "learning_rate": 2.3359408952629294e-06, + "loss": 0.1066, + "step": 32516 + }, + { + "epoch": 2.65, + "learning_rate": 2.3353976531942636e-06, + "loss": 0.415, + "step": 32517 + }, + { + "epoch": 2.65, + "learning_rate": 2.334854411125598e-06, + "loss": 0.2702, + "step": 32518 + }, + { + "epoch": 2.65, + "learning_rate": 2.334311169056932e-06, + "loss": 0.4537, + "step": 32519 + }, + { + "epoch": 2.65, + "learning_rate": 2.3337679269882663e-06, + "loss": 0.5308, + "step": 32520 + }, + { + "epoch": 2.65, + "learning_rate": 2.3332246849196e-06, + "loss": 0.2788, + "step": 32521 + }, + { + "epoch": 2.65, + "learning_rate": 2.3326814428509343e-06, + "loss": 0.5549, + "step": 32522 + }, + { + "epoch": 2.65, + "learning_rate": 2.332138200782269e-06, + "loss": 0.2523, + "step": 32523 + }, + { + "epoch": 2.65, + "learning_rate": 2.331594958713603e-06, + "loss": 0.3998, + "step": 32524 + }, + { + "epoch": 2.65, + "learning_rate": 2.3310517166449374e-06, + "loss": 0.116, + "step": 32525 + }, + { + "epoch": 2.65, + "learning_rate": 2.3305084745762712e-06, + "loss": 0.4171, + "step": 32526 + }, + { + "epoch": 2.65, + "learning_rate": 2.3299652325076055e-06, + "loss": 0.1712, + "step": 32527 + }, + { + "epoch": 2.65, + "learning_rate": 2.3294219904389397e-06, + "loss": 0.1436, + "step": 32528 + }, + { + "epoch": 2.65, + "learning_rate": 2.328878748370274e-06, + "loss": 0.1686, + "step": 32529 + }, + { + "epoch": 2.65, + "learning_rate": 2.328335506301608e-06, + "loss": 0.2571, + "step": 32530 + }, + { + "epoch": 2.65, + "learning_rate": 2.3277922642329424e-06, + "loss": 0.0556, + "step": 32531 + }, + { + "epoch": 2.65, + "learning_rate": 2.3272490221642766e-06, + "loss": 0.2736, + "step": 32532 + }, + { + "epoch": 2.65, + "learning_rate": 2.326705780095611e-06, + "loss": 0.2087, + "step": 32533 + }, + { + "epoch": 2.65, + "learning_rate": 2.326162538026945e-06, + "loss": 0.2345, + "step": 32534 + }, + { + "epoch": 2.65, + "learning_rate": 2.325619295958279e-06, + "loss": 0.1131, + "step": 32535 + }, + { + "epoch": 2.65, + "learning_rate": 2.325076053889613e-06, + "loss": 0.5527, + "step": 32536 + }, + { + "epoch": 2.65, + "learning_rate": 2.3245328118209478e-06, + "loss": 0.034, + "step": 32537 + }, + { + "epoch": 2.65, + "learning_rate": 2.323989569752282e-06, + "loss": 0.1107, + "step": 32538 + }, + { + "epoch": 2.65, + "learning_rate": 2.3234463276836162e-06, + "loss": 0.1688, + "step": 32539 + }, + { + "epoch": 2.65, + "learning_rate": 2.32290308561495e-06, + "loss": 0.2792, + "step": 32540 + }, + { + "epoch": 2.65, + "learning_rate": 2.3223598435462843e-06, + "loss": 0.2225, + "step": 32541 + }, + { + "epoch": 2.65, + "learning_rate": 2.3218166014776185e-06, + "loss": 0.1557, + "step": 32542 + }, + { + "epoch": 2.65, + "learning_rate": 2.3212733594089527e-06, + "loss": 0.0749, + "step": 32543 + }, + { + "epoch": 2.65, + "learning_rate": 2.320730117340287e-06, + "loss": 0.0863, + "step": 32544 + }, + { + "epoch": 2.65, + "learning_rate": 2.320186875271621e-06, + "loss": 0.3077, + "step": 32545 + }, + { + "epoch": 2.65, + "learning_rate": 2.3196436332029554e-06, + "loss": 0.1451, + "step": 32546 + }, + { + "epoch": 2.65, + "learning_rate": 2.3191003911342897e-06, + "loss": 0.0394, + "step": 32547 + }, + { + "epoch": 2.65, + "learning_rate": 2.318557149065624e-06, + "loss": 0.0953, + "step": 32548 + }, + { + "epoch": 2.65, + "learning_rate": 2.318013906996958e-06, + "loss": 0.3046, + "step": 32549 + }, + { + "epoch": 2.65, + "learning_rate": 2.3174706649282924e-06, + "loss": 0.077, + "step": 32550 + }, + { + "epoch": 2.65, + "learning_rate": 2.3169274228596266e-06, + "loss": 0.2911, + "step": 32551 + }, + { + "epoch": 2.65, + "learning_rate": 2.316384180790961e-06, + "loss": 0.3921, + "step": 32552 + }, + { + "epoch": 2.65, + "learning_rate": 2.315840938722295e-06, + "loss": 0.2093, + "step": 32553 + }, + { + "epoch": 2.65, + "learning_rate": 2.315297696653629e-06, + "loss": 0.2257, + "step": 32554 + }, + { + "epoch": 2.65, + "learning_rate": 2.314754454584963e-06, + "loss": 0.0719, + "step": 32555 + }, + { + "epoch": 2.65, + "learning_rate": 2.3142112125162973e-06, + "loss": 0.1479, + "step": 32556 + }, + { + "epoch": 2.65, + "learning_rate": 2.3136679704476315e-06, + "loss": 0.4743, + "step": 32557 + }, + { + "epoch": 2.65, + "learning_rate": 2.3131247283789658e-06, + "loss": 0.4697, + "step": 32558 + }, + { + "epoch": 2.65, + "learning_rate": 2.3125814863103e-06, + "loss": 0.5356, + "step": 32559 + }, + { + "epoch": 2.65, + "learning_rate": 2.3120382442416342e-06, + "loss": 0.1721, + "step": 32560 + }, + { + "epoch": 2.65, + "learning_rate": 2.3114950021729685e-06, + "loss": 0.2932, + "step": 32561 + }, + { + "epoch": 2.65, + "learning_rate": 2.3109517601043027e-06, + "loss": 0.2336, + "step": 32562 + }, + { + "epoch": 2.65, + "learning_rate": 2.310408518035637e-06, + "loss": 0.2416, + "step": 32563 + }, + { + "epoch": 2.65, + "learning_rate": 2.309865275966971e-06, + "loss": 0.2686, + "step": 32564 + }, + { + "epoch": 2.65, + "learning_rate": 2.3093220338983054e-06, + "loss": 0.1007, + "step": 32565 + }, + { + "epoch": 2.65, + "learning_rate": 2.3087787918296396e-06, + "loss": 0.1465, + "step": 32566 + }, + { + "epoch": 2.65, + "learning_rate": 2.308235549760974e-06, + "loss": 0.2816, + "step": 32567 + }, + { + "epoch": 2.65, + "learning_rate": 2.307692307692308e-06, + "loss": 0.2079, + "step": 32568 + }, + { + "epoch": 2.65, + "learning_rate": 2.307149065623642e-06, + "loss": 0.2967, + "step": 32569 + }, + { + "epoch": 2.65, + "learning_rate": 2.306605823554976e-06, + "loss": 0.368, + "step": 32570 + }, + { + "epoch": 2.65, + "learning_rate": 2.3060625814863103e-06, + "loss": 0.1452, + "step": 32571 + }, + { + "epoch": 2.65, + "learning_rate": 2.3055193394176446e-06, + "loss": 0.1728, + "step": 32572 + }, + { + "epoch": 2.65, + "learning_rate": 2.304976097348979e-06, + "loss": 0.1665, + "step": 32573 + }, + { + "epoch": 2.65, + "learning_rate": 2.304432855280313e-06, + "loss": 0.2767, + "step": 32574 + }, + { + "epoch": 2.65, + "learning_rate": 2.3038896132116473e-06, + "loss": 0.1539, + "step": 32575 + }, + { + "epoch": 2.65, + "learning_rate": 2.3033463711429815e-06, + "loss": 0.1973, + "step": 32576 + }, + { + "epoch": 2.65, + "learning_rate": 2.3028031290743157e-06, + "loss": 0.1486, + "step": 32577 + }, + { + "epoch": 2.65, + "learning_rate": 2.30225988700565e-06, + "loss": 0.0987, + "step": 32578 + }, + { + "epoch": 2.65, + "learning_rate": 2.301716644936984e-06, + "loss": 0.1493, + "step": 32579 + }, + { + "epoch": 2.65, + "learning_rate": 2.3011734028683184e-06, + "loss": 0.1732, + "step": 32580 + }, + { + "epoch": 2.65, + "learning_rate": 2.3006301607996527e-06, + "loss": 0.4954, + "step": 32581 + }, + { + "epoch": 2.65, + "learning_rate": 2.300086918730987e-06, + "loss": 0.1307, + "step": 32582 + }, + { + "epoch": 2.66, + "learning_rate": 2.2995436766623207e-06, + "loss": 0.4292, + "step": 32583 + }, + { + "epoch": 2.66, + "learning_rate": 2.299000434593655e-06, + "loss": 0.1605, + "step": 32584 + }, + { + "epoch": 2.66, + "learning_rate": 2.298457192524989e-06, + "loss": 0.2996, + "step": 32585 + }, + { + "epoch": 2.66, + "learning_rate": 2.297913950456324e-06, + "loss": 0.3458, + "step": 32586 + }, + { + "epoch": 2.66, + "learning_rate": 2.297370708387658e-06, + "loss": 0.2612, + "step": 32587 + }, + { + "epoch": 2.66, + "learning_rate": 2.296827466318992e-06, + "loss": 0.2378, + "step": 32588 + }, + { + "epoch": 2.66, + "learning_rate": 2.296284224250326e-06, + "loss": 0.1234, + "step": 32589 + }, + { + "epoch": 2.66, + "learning_rate": 2.2957409821816603e-06, + "loss": 0.203, + "step": 32590 + }, + { + "epoch": 2.66, + "learning_rate": 2.2951977401129945e-06, + "loss": 0.1295, + "step": 32591 + }, + { + "epoch": 2.66, + "learning_rate": 2.2946544980443288e-06, + "loss": 0.3937, + "step": 32592 + }, + { + "epoch": 2.66, + "learning_rate": 2.294111255975663e-06, + "loss": 0.2711, + "step": 32593 + }, + { + "epoch": 2.66, + "learning_rate": 2.2935680139069972e-06, + "loss": 0.2853, + "step": 32594 + }, + { + "epoch": 2.66, + "learning_rate": 2.2930247718383315e-06, + "loss": 0.0375, + "step": 32595 + }, + { + "epoch": 2.66, + "learning_rate": 2.2924815297696657e-06, + "loss": 0.331, + "step": 32596 + }, + { + "epoch": 2.66, + "learning_rate": 2.2919382877009995e-06, + "loss": 0.2391, + "step": 32597 + }, + { + "epoch": 2.66, + "learning_rate": 2.2913950456323337e-06, + "loss": 0.3782, + "step": 32598 + }, + { + "epoch": 2.66, + "learning_rate": 2.290851803563668e-06, + "loss": 0.2669, + "step": 32599 + }, + { + "epoch": 2.66, + "learning_rate": 2.2903085614950026e-06, + "loss": 0.2043, + "step": 32600 + }, + { + "epoch": 2.66, + "learning_rate": 2.289765319426337e-06, + "loss": 0.0542, + "step": 32601 + }, + { + "epoch": 2.66, + "learning_rate": 2.2892220773576706e-06, + "loss": 0.2463, + "step": 32602 + }, + { + "epoch": 2.66, + "learning_rate": 2.288678835289005e-06, + "loss": 0.1119, + "step": 32603 + }, + { + "epoch": 2.66, + "learning_rate": 2.288135593220339e-06, + "loss": 0.3898, + "step": 32604 + }, + { + "epoch": 2.66, + "learning_rate": 2.2875923511516733e-06, + "loss": 0.1186, + "step": 32605 + }, + { + "epoch": 2.66, + "learning_rate": 2.2870491090830076e-06, + "loss": 0.5261, + "step": 32606 + }, + { + "epoch": 2.66, + "learning_rate": 2.286505867014342e-06, + "loss": 0.217, + "step": 32607 + }, + { + "epoch": 2.66, + "learning_rate": 2.285962624945676e-06, + "loss": 0.0761, + "step": 32608 + }, + { + "epoch": 2.66, + "learning_rate": 2.2854193828770103e-06, + "loss": 0.3787, + "step": 32609 + }, + { + "epoch": 2.66, + "learning_rate": 2.2848761408083445e-06, + "loss": 0.3743, + "step": 32610 + }, + { + "epoch": 2.66, + "learning_rate": 2.2843328987396783e-06, + "loss": 0.1312, + "step": 32611 + }, + { + "epoch": 2.66, + "learning_rate": 2.2837896566710125e-06, + "loss": 0.4268, + "step": 32612 + }, + { + "epoch": 2.66, + "learning_rate": 2.283246414602347e-06, + "loss": 0.4442, + "step": 32613 + }, + { + "epoch": 2.66, + "learning_rate": 2.2827031725336814e-06, + "loss": 0.1808, + "step": 32614 + }, + { + "epoch": 2.66, + "learning_rate": 2.2821599304650156e-06, + "loss": 0.2905, + "step": 32615 + }, + { + "epoch": 2.66, + "learning_rate": 2.2816166883963494e-06, + "loss": 0.0773, + "step": 32616 + }, + { + "epoch": 2.66, + "learning_rate": 2.2810734463276837e-06, + "loss": 0.1306, + "step": 32617 + }, + { + "epoch": 2.66, + "learning_rate": 2.280530204259018e-06, + "loss": 0.4019, + "step": 32618 + }, + { + "epoch": 2.66, + "learning_rate": 2.279986962190352e-06, + "loss": 0.1896, + "step": 32619 + }, + { + "epoch": 2.66, + "learning_rate": 2.2794437201216864e-06, + "loss": 0.1688, + "step": 32620 + }, + { + "epoch": 2.66, + "learning_rate": 2.2789004780530206e-06, + "loss": 0.1095, + "step": 32621 + }, + { + "epoch": 2.66, + "learning_rate": 2.278357235984355e-06, + "loss": 0.0744, + "step": 32622 + }, + { + "epoch": 2.66, + "learning_rate": 2.277813993915689e-06, + "loss": 0.177, + "step": 32623 + }, + { + "epoch": 2.66, + "learning_rate": 2.2772707518470233e-06, + "loss": 0.2836, + "step": 32624 + }, + { + "epoch": 2.66, + "learning_rate": 2.2767275097783575e-06, + "loss": 0.1523, + "step": 32625 + }, + { + "epoch": 2.66, + "learning_rate": 2.2761842677096913e-06, + "loss": 0.274, + "step": 32626 + }, + { + "epoch": 2.66, + "learning_rate": 2.275641025641026e-06, + "loss": 0.0699, + "step": 32627 + }, + { + "epoch": 2.66, + "learning_rate": 2.2750977835723602e-06, + "loss": 0.1491, + "step": 32628 + }, + { + "epoch": 2.66, + "learning_rate": 2.2745545415036944e-06, + "loss": 0.2049, + "step": 32629 + }, + { + "epoch": 2.66, + "learning_rate": 2.2740112994350283e-06, + "loss": 0.2933, + "step": 32630 + }, + { + "epoch": 2.66, + "learning_rate": 2.2734680573663625e-06, + "loss": 0.057, + "step": 32631 + }, + { + "epoch": 2.66, + "learning_rate": 2.2729248152976967e-06, + "loss": 0.1727, + "step": 32632 + }, + { + "epoch": 2.66, + "learning_rate": 2.272381573229031e-06, + "loss": 0.2528, + "step": 32633 + }, + { + "epoch": 2.66, + "learning_rate": 2.271838331160365e-06, + "loss": 0.2164, + "step": 32634 + }, + { + "epoch": 2.66, + "learning_rate": 2.2712950890916994e-06, + "loss": 0.3697, + "step": 32635 + }, + { + "epoch": 2.66, + "learning_rate": 2.2707518470230336e-06, + "loss": 0.1176, + "step": 32636 + }, + { + "epoch": 2.66, + "learning_rate": 2.270208604954368e-06, + "loss": 0.2231, + "step": 32637 + }, + { + "epoch": 2.66, + "learning_rate": 2.269665362885702e-06, + "loss": 0.2802, + "step": 32638 + }, + { + "epoch": 2.66, + "learning_rate": 2.2691221208170363e-06, + "loss": 0.218, + "step": 32639 + }, + { + "epoch": 2.66, + "learning_rate": 2.2685788787483706e-06, + "loss": 0.2502, + "step": 32640 + }, + { + "epoch": 2.66, + "learning_rate": 2.268035636679705e-06, + "loss": 0.0688, + "step": 32641 + }, + { + "epoch": 2.66, + "learning_rate": 2.267492394611039e-06, + "loss": 0.1254, + "step": 32642 + }, + { + "epoch": 2.66, + "learning_rate": 2.2669491525423732e-06, + "loss": 0.4084, + "step": 32643 + }, + { + "epoch": 2.66, + "learning_rate": 2.2664059104737075e-06, + "loss": 0.1103, + "step": 32644 + }, + { + "epoch": 2.66, + "learning_rate": 2.2658626684050413e-06, + "loss": 0.1776, + "step": 32645 + }, + { + "epoch": 2.66, + "learning_rate": 2.2653194263363755e-06, + "loss": 0.3044, + "step": 32646 + }, + { + "epoch": 2.66, + "learning_rate": 2.2647761842677097e-06, + "loss": 0.2228, + "step": 32647 + }, + { + "epoch": 2.66, + "learning_rate": 2.264232942199044e-06, + "loss": 0.13, + "step": 32648 + }, + { + "epoch": 2.66, + "learning_rate": 2.263689700130378e-06, + "loss": 0.158, + "step": 32649 + }, + { + "epoch": 2.66, + "learning_rate": 2.2631464580617124e-06, + "loss": 0.3073, + "step": 32650 + }, + { + "epoch": 2.66, + "learning_rate": 2.2626032159930467e-06, + "loss": 0.1489, + "step": 32651 + }, + { + "epoch": 2.66, + "learning_rate": 2.262059973924381e-06, + "loss": 0.0509, + "step": 32652 + }, + { + "epoch": 2.66, + "learning_rate": 2.261516731855715e-06, + "loss": 0.2632, + "step": 32653 + }, + { + "epoch": 2.66, + "learning_rate": 2.2609734897870494e-06, + "loss": 0.2933, + "step": 32654 + }, + { + "epoch": 2.66, + "learning_rate": 2.2604302477183836e-06, + "loss": 0.1724, + "step": 32655 + }, + { + "epoch": 2.66, + "learning_rate": 2.259887005649718e-06, + "loss": 0.4924, + "step": 32656 + }, + { + "epoch": 2.66, + "learning_rate": 2.259343763581052e-06, + "loss": 0.1976, + "step": 32657 + }, + { + "epoch": 2.66, + "learning_rate": 2.2588005215123863e-06, + "loss": 0.095, + "step": 32658 + }, + { + "epoch": 2.66, + "learning_rate": 2.25825727944372e-06, + "loss": 0.3719, + "step": 32659 + }, + { + "epoch": 2.66, + "learning_rate": 2.2577140373750543e-06, + "loss": 0.2614, + "step": 32660 + }, + { + "epoch": 2.66, + "learning_rate": 2.2571707953063886e-06, + "loss": 0.2216, + "step": 32661 + }, + { + "epoch": 2.66, + "learning_rate": 2.2566275532377228e-06, + "loss": 0.2358, + "step": 32662 + }, + { + "epoch": 2.66, + "learning_rate": 2.2560843111690574e-06, + "loss": 0.4075, + "step": 32663 + }, + { + "epoch": 2.66, + "learning_rate": 2.2555410691003912e-06, + "loss": 0.1345, + "step": 32664 + }, + { + "epoch": 2.66, + "learning_rate": 2.2549978270317255e-06, + "loss": 0.1795, + "step": 32665 + }, + { + "epoch": 2.66, + "learning_rate": 2.2544545849630597e-06, + "loss": 0.3712, + "step": 32666 + }, + { + "epoch": 2.66, + "learning_rate": 2.253911342894394e-06, + "loss": 0.5006, + "step": 32667 + }, + { + "epoch": 2.66, + "learning_rate": 2.253368100825728e-06, + "loss": 0.1853, + "step": 32668 + }, + { + "epoch": 2.66, + "learning_rate": 2.2528248587570624e-06, + "loss": 0.5425, + "step": 32669 + }, + { + "epoch": 2.66, + "learning_rate": 2.2522816166883966e-06, + "loss": 0.1528, + "step": 32670 + }, + { + "epoch": 2.66, + "learning_rate": 2.251738374619731e-06, + "loss": 0.2788, + "step": 32671 + }, + { + "epoch": 2.66, + "learning_rate": 2.251195132551065e-06, + "loss": 0.1745, + "step": 32672 + }, + { + "epoch": 2.66, + "learning_rate": 2.250651890482399e-06, + "loss": 0.2901, + "step": 32673 + }, + { + "epoch": 2.66, + "learning_rate": 2.250108648413733e-06, + "loss": 0.2266, + "step": 32674 + }, + { + "epoch": 2.66, + "learning_rate": 2.2495654063450674e-06, + "loss": 0.2188, + "step": 32675 + }, + { + "epoch": 2.66, + "learning_rate": 2.2490221642764016e-06, + "loss": 0.1882, + "step": 32676 + }, + { + "epoch": 2.66, + "learning_rate": 2.2484789222077362e-06, + "loss": 0.0234, + "step": 32677 + }, + { + "epoch": 2.66, + "learning_rate": 2.24793568013907e-06, + "loss": 0.3384, + "step": 32678 + }, + { + "epoch": 2.66, + "learning_rate": 2.2473924380704043e-06, + "loss": 0.0972, + "step": 32679 + }, + { + "epoch": 2.66, + "learning_rate": 2.2468491960017385e-06, + "loss": 0.2435, + "step": 32680 + }, + { + "epoch": 2.66, + "learning_rate": 2.2463059539330727e-06, + "loss": 0.3789, + "step": 32681 + }, + { + "epoch": 2.66, + "learning_rate": 2.245762711864407e-06, + "loss": 0.2382, + "step": 32682 + }, + { + "epoch": 2.66, + "learning_rate": 2.245219469795741e-06, + "loss": 0.1851, + "step": 32683 + }, + { + "epoch": 2.66, + "learning_rate": 2.2446762277270754e-06, + "loss": 0.3299, + "step": 32684 + }, + { + "epoch": 2.66, + "learning_rate": 2.2441329856584097e-06, + "loss": 0.0673, + "step": 32685 + }, + { + "epoch": 2.66, + "learning_rate": 2.243589743589744e-06, + "loss": 0.1242, + "step": 32686 + }, + { + "epoch": 2.66, + "learning_rate": 2.243046501521078e-06, + "loss": 0.1273, + "step": 32687 + }, + { + "epoch": 2.66, + "learning_rate": 2.242503259452412e-06, + "loss": 0.2154, + "step": 32688 + }, + { + "epoch": 2.66, + "learning_rate": 2.241960017383746e-06, + "loss": 0.6715, + "step": 32689 + }, + { + "epoch": 2.66, + "learning_rate": 2.241416775315081e-06, + "loss": 0.3863, + "step": 32690 + }, + { + "epoch": 2.66, + "learning_rate": 2.240873533246415e-06, + "loss": 0.2678, + "step": 32691 + }, + { + "epoch": 2.66, + "learning_rate": 2.240330291177749e-06, + "loss": 0.1752, + "step": 32692 + }, + { + "epoch": 2.66, + "learning_rate": 2.239787049109083e-06, + "loss": 0.1608, + "step": 32693 + }, + { + "epoch": 2.66, + "learning_rate": 2.2392438070404173e-06, + "loss": 0.14, + "step": 32694 + }, + { + "epoch": 2.66, + "learning_rate": 2.2387005649717515e-06, + "loss": 0.2316, + "step": 32695 + }, + { + "epoch": 2.66, + "learning_rate": 2.2381573229030858e-06, + "loss": 0.2503, + "step": 32696 + }, + { + "epoch": 2.66, + "learning_rate": 2.23761408083442e-06, + "loss": 0.115, + "step": 32697 + }, + { + "epoch": 2.66, + "learning_rate": 2.2370708387657542e-06, + "loss": 0.2119, + "step": 32698 + }, + { + "epoch": 2.66, + "learning_rate": 2.2365275966970885e-06, + "loss": 0.0339, + "step": 32699 + }, + { + "epoch": 2.66, + "learning_rate": 2.2359843546284227e-06, + "loss": 0.0959, + "step": 32700 + }, + { + "epoch": 2.66, + "learning_rate": 2.235441112559757e-06, + "loss": 0.109, + "step": 32701 + }, + { + "epoch": 2.66, + "learning_rate": 2.2348978704910907e-06, + "loss": 0.2536, + "step": 32702 + }, + { + "epoch": 2.66, + "learning_rate": 2.234354628422425e-06, + "loss": 0.1443, + "step": 32703 + }, + { + "epoch": 2.66, + "learning_rate": 2.2338113863537596e-06, + "loss": 0.3217, + "step": 32704 + }, + { + "epoch": 2.67, + "learning_rate": 2.233268144285094e-06, + "loss": 0.0846, + "step": 32705 + }, + { + "epoch": 2.67, + "learning_rate": 2.232724902216428e-06, + "loss": 0.1921, + "step": 32706 + }, + { + "epoch": 2.67, + "learning_rate": 2.232181660147762e-06, + "loss": 0.3839, + "step": 32707 + }, + { + "epoch": 2.67, + "learning_rate": 2.231638418079096e-06, + "loss": 0.1175, + "step": 32708 + }, + { + "epoch": 2.67, + "learning_rate": 2.2310951760104303e-06, + "loss": 0.055, + "step": 32709 + }, + { + "epoch": 2.67, + "learning_rate": 2.2305519339417646e-06, + "loss": 0.119, + "step": 32710 + }, + { + "epoch": 2.67, + "learning_rate": 2.230008691873099e-06, + "loss": 0.2036, + "step": 32711 + }, + { + "epoch": 2.67, + "learning_rate": 2.229465449804433e-06, + "loss": 0.2626, + "step": 32712 + }, + { + "epoch": 2.67, + "learning_rate": 2.2289222077357673e-06, + "loss": 0.1318, + "step": 32713 + }, + { + "epoch": 2.67, + "learning_rate": 2.2283789656671015e-06, + "loss": 0.3039, + "step": 32714 + }, + { + "epoch": 2.67, + "learning_rate": 2.2278357235984357e-06, + "loss": 0.4342, + "step": 32715 + }, + { + "epoch": 2.67, + "learning_rate": 2.2272924815297695e-06, + "loss": 0.2159, + "step": 32716 + }, + { + "epoch": 2.67, + "learning_rate": 2.226749239461104e-06, + "loss": 0.2117, + "step": 32717 + }, + { + "epoch": 2.67, + "learning_rate": 2.2262059973924384e-06, + "loss": 0.2348, + "step": 32718 + }, + { + "epoch": 2.67, + "learning_rate": 2.2256627553237727e-06, + "loss": 0.1875, + "step": 32719 + }, + { + "epoch": 2.67, + "learning_rate": 2.225119513255107e-06, + "loss": 0.4642, + "step": 32720 + }, + { + "epoch": 2.67, + "learning_rate": 2.2245762711864407e-06, + "loss": 0.337, + "step": 32721 + }, + { + "epoch": 2.67, + "learning_rate": 2.224033029117775e-06, + "loss": 0.1288, + "step": 32722 + }, + { + "epoch": 2.67, + "learning_rate": 2.223489787049109e-06, + "loss": 0.2976, + "step": 32723 + }, + { + "epoch": 2.67, + "learning_rate": 2.2229465449804434e-06, + "loss": 0.1977, + "step": 32724 + }, + { + "epoch": 2.67, + "learning_rate": 2.2224033029117776e-06, + "loss": 0.3465, + "step": 32725 + }, + { + "epoch": 2.67, + "learning_rate": 2.221860060843112e-06, + "loss": 0.059, + "step": 32726 + }, + { + "epoch": 2.67, + "learning_rate": 2.221316818774446e-06, + "loss": 0.3286, + "step": 32727 + }, + { + "epoch": 2.67, + "learning_rate": 2.2207735767057803e-06, + "loss": 0.2118, + "step": 32728 + }, + { + "epoch": 2.67, + "learning_rate": 2.2202303346371145e-06, + "loss": 0.361, + "step": 32729 + }, + { + "epoch": 2.67, + "learning_rate": 2.2196870925684483e-06, + "loss": 0.4859, + "step": 32730 + }, + { + "epoch": 2.67, + "learning_rate": 2.219143850499783e-06, + "loss": 0.4086, + "step": 32731 + }, + { + "epoch": 2.67, + "learning_rate": 2.2186006084311172e-06, + "loss": 0.2689, + "step": 32732 + }, + { + "epoch": 2.67, + "learning_rate": 2.2180573663624515e-06, + "loss": 0.3266, + "step": 32733 + }, + { + "epoch": 2.67, + "learning_rate": 2.2175141242937857e-06, + "loss": 0.1382, + "step": 32734 + }, + { + "epoch": 2.67, + "learning_rate": 2.2169708822251195e-06, + "loss": 0.0426, + "step": 32735 + }, + { + "epoch": 2.67, + "learning_rate": 2.2164276401564537e-06, + "loss": 0.3586, + "step": 32736 + }, + { + "epoch": 2.67, + "learning_rate": 2.215884398087788e-06, + "loss": 0.0578, + "step": 32737 + }, + { + "epoch": 2.67, + "learning_rate": 2.215341156019122e-06, + "loss": 0.2699, + "step": 32738 + }, + { + "epoch": 2.67, + "learning_rate": 2.2147979139504564e-06, + "loss": 0.4177, + "step": 32739 + }, + { + "epoch": 2.67, + "learning_rate": 2.2142546718817906e-06, + "loss": 0.2478, + "step": 32740 + }, + { + "epoch": 2.67, + "learning_rate": 2.213711429813125e-06, + "loss": 0.5428, + "step": 32741 + }, + { + "epoch": 2.67, + "learning_rate": 2.213168187744459e-06, + "loss": 0.3127, + "step": 32742 + }, + { + "epoch": 2.67, + "learning_rate": 2.2126249456757933e-06, + "loss": 0.3741, + "step": 32743 + }, + { + "epoch": 2.67, + "learning_rate": 2.2120817036071276e-06, + "loss": 0.05, + "step": 32744 + }, + { + "epoch": 2.67, + "learning_rate": 2.211538461538462e-06, + "loss": 0.2456, + "step": 32745 + }, + { + "epoch": 2.67, + "learning_rate": 2.210995219469796e-06, + "loss": 0.1895, + "step": 32746 + }, + { + "epoch": 2.67, + "learning_rate": 2.2104519774011303e-06, + "loss": 0.2947, + "step": 32747 + }, + { + "epoch": 2.67, + "learning_rate": 2.2099087353324645e-06, + "loss": 0.3329, + "step": 32748 + }, + { + "epoch": 2.67, + "learning_rate": 2.2093654932637983e-06, + "loss": 0.1868, + "step": 32749 + }, + { + "epoch": 2.67, + "learning_rate": 2.2088222511951325e-06, + "loss": 0.1384, + "step": 32750 + }, + { + "epoch": 2.67, + "eval_accuracy": 0.8431991849210392, + "eval_loss": 0.4931495487689972, + "eval_runtime": 22.3141, + "eval_samples_per_second": 439.856, + "eval_steps_per_second": 3.451, + "step": 32750 + }, + { + "epoch": 2.67, + "learning_rate": 2.2082790091264668e-06, + "loss": 0.141, + "step": 32751 + }, + { + "epoch": 2.67, + "learning_rate": 2.207735767057801e-06, + "loss": 0.341, + "step": 32752 + }, + { + "epoch": 2.67, + "learning_rate": 2.2071925249891356e-06, + "loss": 0.3166, + "step": 32753 + }, + { + "epoch": 2.67, + "learning_rate": 2.2066492829204695e-06, + "loss": 0.1756, + "step": 32754 + }, + { + "epoch": 2.67, + "learning_rate": 2.2061060408518037e-06, + "loss": 0.0889, + "step": 32755 + }, + { + "epoch": 2.67, + "learning_rate": 2.205562798783138e-06, + "loss": 0.0579, + "step": 32756 + }, + { + "epoch": 2.67, + "learning_rate": 2.205019556714472e-06, + "loss": 0.2481, + "step": 32757 + }, + { + "epoch": 2.67, + "learning_rate": 2.2044763146458064e-06, + "loss": 0.1979, + "step": 32758 + }, + { + "epoch": 2.67, + "learning_rate": 2.2039330725771406e-06, + "loss": 0.2632, + "step": 32759 + }, + { + "epoch": 2.67, + "learning_rate": 2.203389830508475e-06, + "loss": 0.0669, + "step": 32760 + }, + { + "epoch": 2.67, + "learning_rate": 2.202846588439809e-06, + "loss": 0.2081, + "step": 32761 + }, + { + "epoch": 2.67, + "learning_rate": 2.2023033463711433e-06, + "loss": 0.1202, + "step": 32762 + }, + { + "epoch": 2.67, + "learning_rate": 2.2017601043024775e-06, + "loss": 0.0579, + "step": 32763 + }, + { + "epoch": 2.67, + "learning_rate": 2.2012168622338113e-06, + "loss": 0.0637, + "step": 32764 + }, + { + "epoch": 2.67, + "learning_rate": 2.2006736201651456e-06, + "loss": 0.2749, + "step": 32765 + }, + { + "epoch": 2.67, + "learning_rate": 2.20013037809648e-06, + "loss": 0.086, + "step": 32766 + }, + { + "epoch": 2.67, + "learning_rate": 2.1995871360278144e-06, + "loss": 0.5804, + "step": 32767 + }, + { + "epoch": 2.67, + "learning_rate": 2.1990438939591483e-06, + "loss": 0.0521, + "step": 32768 + }, + { + "epoch": 2.67, + "learning_rate": 2.1985006518904825e-06, + "loss": 0.3387, + "step": 32769 + }, + { + "epoch": 2.67, + "learning_rate": 2.1979574098218167e-06, + "loss": 0.1152, + "step": 32770 + }, + { + "epoch": 2.67, + "learning_rate": 2.197414167753151e-06, + "loss": 0.1936, + "step": 32771 + }, + { + "epoch": 2.67, + "learning_rate": 2.196870925684485e-06, + "loss": 0.2507, + "step": 32772 + }, + { + "epoch": 2.67, + "learning_rate": 2.1963276836158194e-06, + "loss": 0.4705, + "step": 32773 + }, + { + "epoch": 2.67, + "learning_rate": 2.1957844415471536e-06, + "loss": 0.1037, + "step": 32774 + }, + { + "epoch": 2.67, + "learning_rate": 2.195241199478488e-06, + "loss": 0.187, + "step": 32775 + }, + { + "epoch": 2.67, + "learning_rate": 2.194697957409822e-06, + "loss": 0.4964, + "step": 32776 + }, + { + "epoch": 2.67, + "learning_rate": 2.1941547153411563e-06, + "loss": 0.455, + "step": 32777 + }, + { + "epoch": 2.67, + "learning_rate": 2.19361147327249e-06, + "loss": 0.1191, + "step": 32778 + }, + { + "epoch": 2.67, + "learning_rate": 2.1930682312038244e-06, + "loss": 0.0751, + "step": 32779 + }, + { + "epoch": 2.67, + "learning_rate": 2.192524989135159e-06, + "loss": 0.107, + "step": 32780 + }, + { + "epoch": 2.67, + "learning_rate": 2.1919817470664933e-06, + "loss": 0.2171, + "step": 32781 + }, + { + "epoch": 2.67, + "learning_rate": 2.1914385049978275e-06, + "loss": 0.449, + "step": 32782 + }, + { + "epoch": 2.67, + "learning_rate": 2.1908952629291613e-06, + "loss": 0.478, + "step": 32783 + }, + { + "epoch": 2.67, + "learning_rate": 2.1903520208604955e-06, + "loss": 0.0846, + "step": 32784 + }, + { + "epoch": 2.67, + "learning_rate": 2.1898087787918298e-06, + "loss": 0.5625, + "step": 32785 + }, + { + "epoch": 2.67, + "learning_rate": 2.189265536723164e-06, + "loss": 0.331, + "step": 32786 + }, + { + "epoch": 2.67, + "learning_rate": 2.1887222946544982e-06, + "loss": 0.1478, + "step": 32787 + }, + { + "epoch": 2.67, + "learning_rate": 2.1881790525858324e-06, + "loss": 0.0973, + "step": 32788 + }, + { + "epoch": 2.67, + "learning_rate": 2.1876358105171667e-06, + "loss": 0.1016, + "step": 32789 + }, + { + "epoch": 2.67, + "learning_rate": 2.187092568448501e-06, + "loss": 0.1808, + "step": 32790 + }, + { + "epoch": 2.67, + "learning_rate": 2.186549326379835e-06, + "loss": 0.5156, + "step": 32791 + }, + { + "epoch": 2.67, + "learning_rate": 2.186006084311169e-06, + "loss": 0.2886, + "step": 32792 + }, + { + "epoch": 2.67, + "learning_rate": 2.185462842242503e-06, + "loss": 0.3665, + "step": 32793 + }, + { + "epoch": 2.67, + "learning_rate": 2.184919600173838e-06, + "loss": 0.2791, + "step": 32794 + }, + { + "epoch": 2.67, + "learning_rate": 2.184376358105172e-06, + "loss": 0.1439, + "step": 32795 + }, + { + "epoch": 2.67, + "learning_rate": 2.1838331160365063e-06, + "loss": 0.0546, + "step": 32796 + }, + { + "epoch": 2.67, + "learning_rate": 2.18328987396784e-06, + "loss": 0.3793, + "step": 32797 + }, + { + "epoch": 2.67, + "learning_rate": 2.1827466318991743e-06, + "loss": 0.1387, + "step": 32798 + }, + { + "epoch": 2.67, + "learning_rate": 2.1822033898305086e-06, + "loss": 0.1364, + "step": 32799 + }, + { + "epoch": 2.67, + "learning_rate": 2.1816601477618428e-06, + "loss": 0.1601, + "step": 32800 + }, + { + "epoch": 2.67, + "learning_rate": 2.181116905693177e-06, + "loss": 0.2979, + "step": 32801 + }, + { + "epoch": 2.67, + "learning_rate": 2.1805736636245112e-06, + "loss": 0.183, + "step": 32802 + }, + { + "epoch": 2.67, + "learning_rate": 2.1800304215558455e-06, + "loss": 0.1314, + "step": 32803 + }, + { + "epoch": 2.67, + "learning_rate": 2.1794871794871797e-06, + "loss": 0.1691, + "step": 32804 + }, + { + "epoch": 2.67, + "learning_rate": 2.178943937418514e-06, + "loss": 0.2506, + "step": 32805 + }, + { + "epoch": 2.67, + "learning_rate": 2.1784006953498477e-06, + "loss": 0.3026, + "step": 32806 + }, + { + "epoch": 2.67, + "learning_rate": 2.1778574532811824e-06, + "loss": 0.2436, + "step": 32807 + }, + { + "epoch": 2.67, + "learning_rate": 2.1773142112125166e-06, + "loss": 0.3214, + "step": 32808 + }, + { + "epoch": 2.67, + "learning_rate": 2.176770969143851e-06, + "loss": 0.2246, + "step": 32809 + }, + { + "epoch": 2.67, + "learning_rate": 2.176227727075185e-06, + "loss": 0.3075, + "step": 32810 + }, + { + "epoch": 2.67, + "learning_rate": 2.175684485006519e-06, + "loss": 0.3688, + "step": 32811 + }, + { + "epoch": 2.67, + "learning_rate": 2.175141242937853e-06, + "loss": 0.17, + "step": 32812 + }, + { + "epoch": 2.67, + "learning_rate": 2.1745980008691874e-06, + "loss": 0.24, + "step": 32813 + }, + { + "epoch": 2.67, + "learning_rate": 2.1740547588005216e-06, + "loss": 0.1387, + "step": 32814 + }, + { + "epoch": 2.67, + "learning_rate": 2.173511516731856e-06, + "loss": 0.5266, + "step": 32815 + }, + { + "epoch": 2.67, + "learning_rate": 2.17296827466319e-06, + "loss": 0.2602, + "step": 32816 + }, + { + "epoch": 2.67, + "learning_rate": 2.1724250325945243e-06, + "loss": 0.2974, + "step": 32817 + }, + { + "epoch": 2.67, + "learning_rate": 2.1718817905258585e-06, + "loss": 0.1706, + "step": 32818 + }, + { + "epoch": 2.67, + "learning_rate": 2.1713385484571927e-06, + "loss": 0.2103, + "step": 32819 + }, + { + "epoch": 2.67, + "learning_rate": 2.170795306388527e-06, + "loss": 0.0424, + "step": 32820 + }, + { + "epoch": 2.67, + "learning_rate": 2.170252064319861e-06, + "loss": 0.2581, + "step": 32821 + }, + { + "epoch": 2.67, + "learning_rate": 2.1697088222511954e-06, + "loss": 0.6049, + "step": 32822 + }, + { + "epoch": 2.67, + "learning_rate": 2.1691655801825297e-06, + "loss": 0.3339, + "step": 32823 + }, + { + "epoch": 2.67, + "learning_rate": 2.168622338113864e-06, + "loss": 0.161, + "step": 32824 + }, + { + "epoch": 2.67, + "learning_rate": 2.1680790960451977e-06, + "loss": 0.0798, + "step": 32825 + }, + { + "epoch": 2.67, + "learning_rate": 2.167535853976532e-06, + "loss": 0.1295, + "step": 32826 + }, + { + "epoch": 2.67, + "learning_rate": 2.166992611907866e-06, + "loss": 0.3154, + "step": 32827 + }, + { + "epoch": 2.68, + "learning_rate": 2.1664493698392004e-06, + "loss": 0.2763, + "step": 32828 + }, + { + "epoch": 2.68, + "learning_rate": 2.1659061277705346e-06, + "loss": 0.6, + "step": 32829 + }, + { + "epoch": 2.68, + "learning_rate": 2.165362885701869e-06, + "loss": 0.0917, + "step": 32830 + }, + { + "epoch": 2.68, + "learning_rate": 2.164819643633203e-06, + "loss": 0.2362, + "step": 32831 + }, + { + "epoch": 2.68, + "learning_rate": 2.1642764015645373e-06, + "loss": 0.3928, + "step": 32832 + }, + { + "epoch": 2.68, + "learning_rate": 2.1637331594958715e-06, + "loss": 0.2928, + "step": 32833 + }, + { + "epoch": 2.68, + "learning_rate": 2.1631899174272058e-06, + "loss": 0.2831, + "step": 32834 + }, + { + "epoch": 2.68, + "learning_rate": 2.16264667535854e-06, + "loss": 0.0869, + "step": 32835 + }, + { + "epoch": 2.68, + "learning_rate": 2.1621034332898742e-06, + "loss": 0.4265, + "step": 32836 + }, + { + "epoch": 2.68, + "learning_rate": 2.1615601912212085e-06, + "loss": 0.2692, + "step": 32837 + }, + { + "epoch": 2.68, + "learning_rate": 2.1610169491525427e-06, + "loss": 0.2285, + "step": 32838 + }, + { + "epoch": 2.68, + "learning_rate": 2.160473707083877e-06, + "loss": 0.3445, + "step": 32839 + }, + { + "epoch": 2.68, + "learning_rate": 2.1599304650152107e-06, + "loss": 0.3322, + "step": 32840 + }, + { + "epoch": 2.68, + "learning_rate": 2.159387222946545e-06, + "loss": 0.1094, + "step": 32841 + }, + { + "epoch": 2.68, + "learning_rate": 2.158843980877879e-06, + "loss": 0.0991, + "step": 32842 + }, + { + "epoch": 2.68, + "learning_rate": 2.158300738809214e-06, + "loss": 0.4325, + "step": 32843 + }, + { + "epoch": 2.68, + "learning_rate": 2.1577574967405477e-06, + "loss": 0.0545, + "step": 32844 + }, + { + "epoch": 2.68, + "learning_rate": 2.157214254671882e-06, + "loss": 0.2617, + "step": 32845 + }, + { + "epoch": 2.68, + "learning_rate": 2.156671012603216e-06, + "loss": 0.4573, + "step": 32846 + }, + { + "epoch": 2.68, + "learning_rate": 2.1561277705345504e-06, + "loss": 0.0722, + "step": 32847 + }, + { + "epoch": 2.68, + "learning_rate": 2.1555845284658846e-06, + "loss": 0.242, + "step": 32848 + }, + { + "epoch": 2.68, + "learning_rate": 2.155041286397219e-06, + "loss": 0.1056, + "step": 32849 + }, + { + "epoch": 2.68, + "learning_rate": 2.154498044328553e-06, + "loss": 0.1486, + "step": 32850 + }, + { + "epoch": 2.68, + "learning_rate": 2.1539548022598873e-06, + "loss": 0.2369, + "step": 32851 + }, + { + "epoch": 2.68, + "learning_rate": 2.1534115601912215e-06, + "loss": 0.4074, + "step": 32852 + }, + { + "epoch": 2.68, + "learning_rate": 2.1528683181225557e-06, + "loss": 0.5107, + "step": 32853 + }, + { + "epoch": 2.68, + "learning_rate": 2.1523250760538895e-06, + "loss": 0.2376, + "step": 32854 + }, + { + "epoch": 2.68, + "learning_rate": 2.1517818339852238e-06, + "loss": 0.166, + "step": 32855 + }, + { + "epoch": 2.68, + "learning_rate": 2.151238591916558e-06, + "loss": 0.4331, + "step": 32856 + }, + { + "epoch": 2.68, + "learning_rate": 2.1506953498478927e-06, + "loss": 0.2106, + "step": 32857 + }, + { + "epoch": 2.68, + "learning_rate": 2.150152107779227e-06, + "loss": 0.0986, + "step": 32858 + }, + { + "epoch": 2.68, + "learning_rate": 2.1496088657105607e-06, + "loss": 0.1371, + "step": 32859 + }, + { + "epoch": 2.68, + "learning_rate": 2.149065623641895e-06, + "loss": 0.263, + "step": 32860 + }, + { + "epoch": 2.68, + "learning_rate": 2.148522381573229e-06, + "loss": 0.184, + "step": 32861 + }, + { + "epoch": 2.68, + "learning_rate": 2.1479791395045634e-06, + "loss": 0.4101, + "step": 32862 + }, + { + "epoch": 2.68, + "learning_rate": 2.1474358974358976e-06, + "loss": 0.1725, + "step": 32863 + }, + { + "epoch": 2.68, + "learning_rate": 2.146892655367232e-06, + "loss": 0.1629, + "step": 32864 + }, + { + "epoch": 2.68, + "learning_rate": 2.146349413298566e-06, + "loss": 0.3782, + "step": 32865 + }, + { + "epoch": 2.68, + "learning_rate": 2.1458061712299003e-06, + "loss": 0.1296, + "step": 32866 + }, + { + "epoch": 2.68, + "learning_rate": 2.1452629291612345e-06, + "loss": 0.1386, + "step": 32867 + }, + { + "epoch": 2.68, + "learning_rate": 2.1447196870925683e-06, + "loss": 0.1799, + "step": 32868 + }, + { + "epoch": 2.68, + "learning_rate": 2.1441764450239026e-06, + "loss": 0.1052, + "step": 32869 + }, + { + "epoch": 2.68, + "learning_rate": 2.1436332029552372e-06, + "loss": 0.2196, + "step": 32870 + }, + { + "epoch": 2.68, + "learning_rate": 2.1430899608865715e-06, + "loss": 0.2072, + "step": 32871 + }, + { + "epoch": 2.68, + "learning_rate": 2.1425467188179057e-06, + "loss": 0.1592, + "step": 32872 + }, + { + "epoch": 2.68, + "learning_rate": 2.1420034767492395e-06, + "loss": 0.2102, + "step": 32873 + }, + { + "epoch": 2.68, + "learning_rate": 2.1414602346805737e-06, + "loss": 0.1929, + "step": 32874 + }, + { + "epoch": 2.68, + "learning_rate": 2.140916992611908e-06, + "loss": 0.3416, + "step": 32875 + }, + { + "epoch": 2.68, + "learning_rate": 2.140373750543242e-06, + "loss": 0.2243, + "step": 32876 + }, + { + "epoch": 2.68, + "learning_rate": 2.1398305084745764e-06, + "loss": 0.3047, + "step": 32877 + }, + { + "epoch": 2.68, + "learning_rate": 2.1392872664059107e-06, + "loss": 0.1831, + "step": 32878 + }, + { + "epoch": 2.68, + "learning_rate": 2.138744024337245e-06, + "loss": 0.2856, + "step": 32879 + }, + { + "epoch": 2.68, + "learning_rate": 2.138200782268579e-06, + "loss": 0.2459, + "step": 32880 + }, + { + "epoch": 2.68, + "learning_rate": 2.1376575401999133e-06, + "loss": 0.2236, + "step": 32881 + }, + { + "epoch": 2.68, + "learning_rate": 2.137114298131247e-06, + "loss": 0.4334, + "step": 32882 + }, + { + "epoch": 2.68, + "learning_rate": 2.1365710560625814e-06, + "loss": 0.4482, + "step": 32883 + }, + { + "epoch": 2.68, + "learning_rate": 2.136027813993916e-06, + "loss": 0.2444, + "step": 32884 + }, + { + "epoch": 2.68, + "learning_rate": 2.1354845719252503e-06, + "loss": 0.2963, + "step": 32885 + }, + { + "epoch": 2.68, + "learning_rate": 2.1349413298565845e-06, + "loss": 0.0541, + "step": 32886 + }, + { + "epoch": 2.68, + "learning_rate": 2.1343980877879183e-06, + "loss": 0.1356, + "step": 32887 + }, + { + "epoch": 2.68, + "learning_rate": 2.1338548457192525e-06, + "loss": 0.193, + "step": 32888 + }, + { + "epoch": 2.68, + "learning_rate": 2.1333116036505868e-06, + "loss": 0.1125, + "step": 32889 + }, + { + "epoch": 2.68, + "learning_rate": 2.132768361581921e-06, + "loss": 0.149, + "step": 32890 + }, + { + "epoch": 2.68, + "learning_rate": 2.1322251195132552e-06, + "loss": 0.1375, + "step": 32891 + }, + { + "epoch": 2.68, + "learning_rate": 2.1316818774445895e-06, + "loss": 0.1139, + "step": 32892 + }, + { + "epoch": 2.68, + "learning_rate": 2.1311386353759237e-06, + "loss": 0.3451, + "step": 32893 + }, + { + "epoch": 2.68, + "learning_rate": 2.130595393307258e-06, + "loss": 0.1888, + "step": 32894 + }, + { + "epoch": 2.68, + "learning_rate": 2.130052151238592e-06, + "loss": 0.1316, + "step": 32895 + }, + { + "epoch": 2.68, + "learning_rate": 2.1295089091699264e-06, + "loss": 0.3099, + "step": 32896 + }, + { + "epoch": 2.68, + "learning_rate": 2.1289656671012606e-06, + "loss": 0.1924, + "step": 32897 + }, + { + "epoch": 2.68, + "learning_rate": 2.128422425032595e-06, + "loss": 0.4318, + "step": 32898 + }, + { + "epoch": 2.68, + "learning_rate": 2.127879182963929e-06, + "loss": 0.2275, + "step": 32899 + }, + { + "epoch": 2.68, + "learning_rate": 2.1273359408952633e-06, + "loss": 0.3197, + "step": 32900 + }, + { + "epoch": 2.68, + "learning_rate": 2.126792698826597e-06, + "loss": 0.2093, + "step": 32901 + }, + { + "epoch": 2.68, + "learning_rate": 2.1262494567579313e-06, + "loss": 0.2646, + "step": 32902 + }, + { + "epoch": 2.68, + "learning_rate": 2.1257062146892656e-06, + "loss": 0.0503, + "step": 32903 + }, + { + "epoch": 2.68, + "learning_rate": 2.1251629726206e-06, + "loss": 0.2898, + "step": 32904 + }, + { + "epoch": 2.68, + "learning_rate": 2.124619730551934e-06, + "loss": 0.0713, + "step": 32905 + }, + { + "epoch": 2.68, + "learning_rate": 2.1240764884832683e-06, + "loss": 0.268, + "step": 32906 + }, + { + "epoch": 2.68, + "learning_rate": 2.1235332464146025e-06, + "loss": 0.3475, + "step": 32907 + }, + { + "epoch": 2.68, + "learning_rate": 2.1229900043459367e-06, + "loss": 0.1844, + "step": 32908 + }, + { + "epoch": 2.68, + "learning_rate": 2.122446762277271e-06, + "loss": 0.2778, + "step": 32909 + }, + { + "epoch": 2.68, + "learning_rate": 2.121903520208605e-06, + "loss": 0.1276, + "step": 32910 + }, + { + "epoch": 2.68, + "learning_rate": 2.1213602781399394e-06, + "loss": 0.1911, + "step": 32911 + }, + { + "epoch": 2.68, + "learning_rate": 2.1208170360712736e-06, + "loss": 0.394, + "step": 32912 + }, + { + "epoch": 2.68, + "learning_rate": 2.120273794002608e-06, + "loss": 0.109, + "step": 32913 + }, + { + "epoch": 2.68, + "learning_rate": 2.119730551933942e-06, + "loss": 0.2544, + "step": 32914 + }, + { + "epoch": 2.68, + "learning_rate": 2.1191873098652763e-06, + "loss": 0.2701, + "step": 32915 + }, + { + "epoch": 2.68, + "learning_rate": 2.11864406779661e-06, + "loss": 0.1675, + "step": 32916 + }, + { + "epoch": 2.68, + "learning_rate": 2.1181008257279444e-06, + "loss": 0.3615, + "step": 32917 + }, + { + "epoch": 2.68, + "learning_rate": 2.1175575836592786e-06, + "loss": 0.2893, + "step": 32918 + }, + { + "epoch": 2.68, + "learning_rate": 2.117014341590613e-06, + "loss": 0.3005, + "step": 32919 + }, + { + "epoch": 2.68, + "learning_rate": 2.116471099521947e-06, + "loss": 0.3721, + "step": 32920 + }, + { + "epoch": 2.68, + "learning_rate": 2.1159278574532813e-06, + "loss": 0.2772, + "step": 32921 + }, + { + "epoch": 2.68, + "learning_rate": 2.1153846153846155e-06, + "loss": 0.1739, + "step": 32922 + }, + { + "epoch": 2.68, + "learning_rate": 2.1148413733159498e-06, + "loss": 0.2145, + "step": 32923 + }, + { + "epoch": 2.68, + "learning_rate": 2.114298131247284e-06, + "loss": 0.3465, + "step": 32924 + }, + { + "epoch": 2.68, + "learning_rate": 2.1137548891786182e-06, + "loss": 0.1116, + "step": 32925 + }, + { + "epoch": 2.68, + "learning_rate": 2.1132116471099524e-06, + "loss": 0.047, + "step": 32926 + }, + { + "epoch": 2.68, + "learning_rate": 2.1126684050412867e-06, + "loss": 0.092, + "step": 32927 + }, + { + "epoch": 2.68, + "learning_rate": 2.112125162972621e-06, + "loss": 0.3903, + "step": 32928 + }, + { + "epoch": 2.68, + "learning_rate": 2.111581920903955e-06, + "loss": 0.1865, + "step": 32929 + }, + { + "epoch": 2.68, + "learning_rate": 2.111038678835289e-06, + "loss": 0.4883, + "step": 32930 + }, + { + "epoch": 2.68, + "learning_rate": 2.110495436766623e-06, + "loss": 0.3682, + "step": 32931 + }, + { + "epoch": 2.68, + "learning_rate": 2.1099521946979574e-06, + "loss": 0.2343, + "step": 32932 + }, + { + "epoch": 2.68, + "learning_rate": 2.109408952629292e-06, + "loss": 0.1316, + "step": 32933 + }, + { + "epoch": 2.68, + "learning_rate": 2.1088657105606263e-06, + "loss": 0.1081, + "step": 32934 + }, + { + "epoch": 2.68, + "learning_rate": 2.10832246849196e-06, + "loss": 0.1209, + "step": 32935 + }, + { + "epoch": 2.68, + "learning_rate": 2.1077792264232943e-06, + "loss": 0.3624, + "step": 32936 + }, + { + "epoch": 2.68, + "learning_rate": 2.1072359843546286e-06, + "loss": 0.1055, + "step": 32937 + }, + { + "epoch": 2.68, + "learning_rate": 2.106692742285963e-06, + "loss": 0.2565, + "step": 32938 + }, + { + "epoch": 2.68, + "learning_rate": 2.106149500217297e-06, + "loss": 0.447, + "step": 32939 + }, + { + "epoch": 2.68, + "learning_rate": 2.1056062581486313e-06, + "loss": 0.2863, + "step": 32940 + }, + { + "epoch": 2.68, + "learning_rate": 2.1050630160799655e-06, + "loss": 0.1641, + "step": 32941 + }, + { + "epoch": 2.68, + "learning_rate": 2.1045197740112997e-06, + "loss": 0.2, + "step": 32942 + }, + { + "epoch": 2.68, + "learning_rate": 2.103976531942634e-06, + "loss": 0.3886, + "step": 32943 + }, + { + "epoch": 2.68, + "learning_rate": 2.1034332898739678e-06, + "loss": 0.2325, + "step": 32944 + }, + { + "epoch": 2.68, + "learning_rate": 2.102890047805302e-06, + "loss": 0.2202, + "step": 32945 + }, + { + "epoch": 2.68, + "learning_rate": 2.102346805736636e-06, + "loss": 0.1829, + "step": 32946 + }, + { + "epoch": 2.68, + "learning_rate": 2.101803563667971e-06, + "loss": 0.0403, + "step": 32947 + }, + { + "epoch": 2.68, + "learning_rate": 2.101260321599305e-06, + "loss": 0.1048, + "step": 32948 + }, + { + "epoch": 2.68, + "learning_rate": 2.100717079530639e-06, + "loss": 0.1479, + "step": 32949 + }, + { + "epoch": 2.68, + "learning_rate": 2.100173837461973e-06, + "loss": 0.1123, + "step": 32950 + }, + { + "epoch": 2.69, + "learning_rate": 2.0996305953933074e-06, + "loss": 0.1023, + "step": 32951 + }, + { + "epoch": 2.69, + "learning_rate": 2.0990873533246416e-06, + "loss": 0.1212, + "step": 32952 + }, + { + "epoch": 2.69, + "learning_rate": 2.098544111255976e-06, + "loss": 0.1713, + "step": 32953 + }, + { + "epoch": 2.69, + "learning_rate": 2.09800086918731e-06, + "loss": 0.3462, + "step": 32954 + }, + { + "epoch": 2.69, + "learning_rate": 2.0974576271186443e-06, + "loss": 0.125, + "step": 32955 + }, + { + "epoch": 2.69, + "learning_rate": 2.0969143850499785e-06, + "loss": 0.0886, + "step": 32956 + }, + { + "epoch": 2.69, + "learning_rate": 2.0963711429813127e-06, + "loss": 0.1389, + "step": 32957 + }, + { + "epoch": 2.69, + "learning_rate": 2.095827900912647e-06, + "loss": 0.3585, + "step": 32958 + }, + { + "epoch": 2.69, + "learning_rate": 2.0952846588439808e-06, + "loss": 0.1924, + "step": 32959 + }, + { + "epoch": 2.69, + "learning_rate": 2.0947414167753154e-06, + "loss": 0.2398, + "step": 32960 + }, + { + "epoch": 2.69, + "learning_rate": 2.0941981747066497e-06, + "loss": 0.2309, + "step": 32961 + }, + { + "epoch": 2.69, + "learning_rate": 2.093654932637984e-06, + "loss": 0.2168, + "step": 32962 + }, + { + "epoch": 2.69, + "learning_rate": 2.0931116905693177e-06, + "loss": 0.2004, + "step": 32963 + }, + { + "epoch": 2.69, + "learning_rate": 2.092568448500652e-06, + "loss": 0.2641, + "step": 32964 + }, + { + "epoch": 2.69, + "learning_rate": 2.092025206431986e-06, + "loss": 0.0748, + "step": 32965 + }, + { + "epoch": 2.69, + "learning_rate": 2.0914819643633204e-06, + "loss": 0.2358, + "step": 32966 + }, + { + "epoch": 2.69, + "learning_rate": 2.0909387222946546e-06, + "loss": 0.2031, + "step": 32967 + }, + { + "epoch": 2.69, + "learning_rate": 2.090395480225989e-06, + "loss": 0.1357, + "step": 32968 + }, + { + "epoch": 2.69, + "learning_rate": 2.089852238157323e-06, + "loss": 0.2038, + "step": 32969 + }, + { + "epoch": 2.69, + "learning_rate": 2.0893089960886573e-06, + "loss": 0.4274, + "step": 32970 + }, + { + "epoch": 2.69, + "learning_rate": 2.0887657540199916e-06, + "loss": 0.3218, + "step": 32971 + }, + { + "epoch": 2.69, + "learning_rate": 2.0882225119513258e-06, + "loss": 0.1736, + "step": 32972 + }, + { + "epoch": 2.69, + "learning_rate": 2.0876792698826596e-06, + "loss": 0.2635, + "step": 32973 + }, + { + "epoch": 2.69, + "learning_rate": 2.0871360278139942e-06, + "loss": 0.09, + "step": 32974 + }, + { + "epoch": 2.69, + "learning_rate": 2.0865927857453285e-06, + "loss": 0.0991, + "step": 32975 + }, + { + "epoch": 2.69, + "learning_rate": 2.0860495436766627e-06, + "loss": 0.0727, + "step": 32976 + }, + { + "epoch": 2.69, + "learning_rate": 2.085506301607997e-06, + "loss": 0.2198, + "step": 32977 + }, + { + "epoch": 2.69, + "learning_rate": 2.0849630595393307e-06, + "loss": 0.1391, + "step": 32978 + }, + { + "epoch": 2.69, + "learning_rate": 2.084419817470665e-06, + "loss": 0.3029, + "step": 32979 + }, + { + "epoch": 2.69, + "learning_rate": 2.083876575401999e-06, + "loss": 0.1376, + "step": 32980 + }, + { + "epoch": 2.69, + "learning_rate": 2.0833333333333334e-06, + "loss": 0.0815, + "step": 32981 + }, + { + "epoch": 2.69, + "learning_rate": 2.0827900912646677e-06, + "loss": 0.1054, + "step": 32982 + }, + { + "epoch": 2.69, + "learning_rate": 2.082246849196002e-06, + "loss": 0.5068, + "step": 32983 + }, + { + "epoch": 2.69, + "learning_rate": 2.081703607127336e-06, + "loss": 0.2588, + "step": 32984 + }, + { + "epoch": 2.69, + "learning_rate": 2.0811603650586704e-06, + "loss": 0.3923, + "step": 32985 + }, + { + "epoch": 2.69, + "learning_rate": 2.0806171229900046e-06, + "loss": 0.292, + "step": 32986 + }, + { + "epoch": 2.69, + "learning_rate": 2.080073880921339e-06, + "loss": 0.1004, + "step": 32987 + }, + { + "epoch": 2.69, + "learning_rate": 2.079530638852673e-06, + "loss": 0.2793, + "step": 32988 + }, + { + "epoch": 2.69, + "learning_rate": 2.0789873967840073e-06, + "loss": 0.0903, + "step": 32989 + }, + { + "epoch": 2.69, + "learning_rate": 2.0784441547153415e-06, + "loss": 0.083, + "step": 32990 + }, + { + "epoch": 2.69, + "learning_rate": 2.0779009126466757e-06, + "loss": 0.3496, + "step": 32991 + }, + { + "epoch": 2.69, + "learning_rate": 2.0773576705780095e-06, + "loss": 0.1839, + "step": 32992 + }, + { + "epoch": 2.69, + "learning_rate": 2.0768144285093438e-06, + "loss": 0.2514, + "step": 32993 + }, + { + "epoch": 2.69, + "learning_rate": 2.076271186440678e-06, + "loss": 0.4144, + "step": 32994 + }, + { + "epoch": 2.69, + "learning_rate": 2.0757279443720122e-06, + "loss": 0.5569, + "step": 32995 + }, + { + "epoch": 2.69, + "learning_rate": 2.0751847023033465e-06, + "loss": 0.0913, + "step": 32996 + }, + { + "epoch": 2.69, + "learning_rate": 2.0746414602346807e-06, + "loss": 0.2567, + "step": 32997 + }, + { + "epoch": 2.69, + "learning_rate": 2.074098218166015e-06, + "loss": 0.2104, + "step": 32998 + }, + { + "epoch": 2.69, + "learning_rate": 2.073554976097349e-06, + "loss": 0.1419, + "step": 32999 + }, + { + "epoch": 2.69, + "learning_rate": 2.0730117340286834e-06, + "loss": 0.1612, + "step": 33000 + }, + { + "epoch": 2.69, + "eval_accuracy": 0.8442180336220071, + "eval_loss": 0.4930252730846405, + "eval_runtime": 22.222, + "eval_samples_per_second": 441.68, + "eval_steps_per_second": 3.465, + "step": 33000 + }, + { + "epoch": 2.69, + "learning_rate": 2.0724684919600176e-06, + "loss": 0.3087, + "step": 33001 + }, + { + "epoch": 2.69, + "learning_rate": 2.071925249891352e-06, + "loss": 0.2067, + "step": 33002 + }, + { + "epoch": 2.69, + "learning_rate": 2.071382007822686e-06, + "loss": 0.1817, + "step": 33003 + }, + { + "epoch": 2.69, + "learning_rate": 2.0708387657540203e-06, + "loss": 0.1932, + "step": 33004 + }, + { + "epoch": 2.69, + "learning_rate": 2.0702955236853545e-06, + "loss": 0.1913, + "step": 33005 + }, + { + "epoch": 2.69, + "learning_rate": 2.0697522816166883e-06, + "loss": 0.2354, + "step": 33006 + }, + { + "epoch": 2.69, + "learning_rate": 2.0692090395480226e-06, + "loss": 0.192, + "step": 33007 + }, + { + "epoch": 2.69, + "learning_rate": 2.068665797479357e-06, + "loss": 0.1864, + "step": 33008 + }, + { + "epoch": 2.69, + "learning_rate": 2.068122555410691e-06, + "loss": 0.2783, + "step": 33009 + }, + { + "epoch": 2.69, + "learning_rate": 2.0675793133420257e-06, + "loss": 0.0977, + "step": 33010 + }, + { + "epoch": 2.69, + "learning_rate": 2.0670360712733595e-06, + "loss": 0.1923, + "step": 33011 + }, + { + "epoch": 2.69, + "learning_rate": 2.0664928292046937e-06, + "loss": 0.1264, + "step": 33012 + }, + { + "epoch": 2.69, + "learning_rate": 2.065949587136028e-06, + "loss": 0.0322, + "step": 33013 + }, + { + "epoch": 2.69, + "learning_rate": 2.065406345067362e-06, + "loss": 0.2045, + "step": 33014 + }, + { + "epoch": 2.69, + "learning_rate": 2.0648631029986964e-06, + "loss": 0.244, + "step": 33015 + }, + { + "epoch": 2.69, + "learning_rate": 2.0643198609300307e-06, + "loss": 0.2209, + "step": 33016 + }, + { + "epoch": 2.69, + "learning_rate": 2.063776618861365e-06, + "loss": 0.2613, + "step": 33017 + }, + { + "epoch": 2.69, + "learning_rate": 2.063233376792699e-06, + "loss": 0.1781, + "step": 33018 + }, + { + "epoch": 2.69, + "learning_rate": 2.0626901347240333e-06, + "loss": 0.138, + "step": 33019 + }, + { + "epoch": 2.69, + "learning_rate": 2.062146892655367e-06, + "loss": 0.1312, + "step": 33020 + }, + { + "epoch": 2.69, + "learning_rate": 2.0616036505867014e-06, + "loss": 0.1654, + "step": 33021 + }, + { + "epoch": 2.69, + "learning_rate": 2.0610604085180356e-06, + "loss": 0.237, + "step": 33022 + }, + { + "epoch": 2.69, + "learning_rate": 2.06051716644937e-06, + "loss": 0.2033, + "step": 33023 + }, + { + "epoch": 2.69, + "learning_rate": 2.0599739243807045e-06, + "loss": 0.435, + "step": 33024 + }, + { + "epoch": 2.69, + "learning_rate": 2.0594306823120383e-06, + "loss": 0.3137, + "step": 33025 + }, + { + "epoch": 2.69, + "learning_rate": 2.0588874402433725e-06, + "loss": 0.0479, + "step": 33026 + }, + { + "epoch": 2.69, + "learning_rate": 2.0583441981747068e-06, + "loss": 0.1364, + "step": 33027 + }, + { + "epoch": 2.69, + "learning_rate": 2.057800956106041e-06, + "loss": 0.2101, + "step": 33028 + }, + { + "epoch": 2.69, + "learning_rate": 2.0572577140373752e-06, + "loss": 0.2135, + "step": 33029 + }, + { + "epoch": 2.69, + "learning_rate": 2.0567144719687095e-06, + "loss": 0.2157, + "step": 33030 + }, + { + "epoch": 2.69, + "learning_rate": 2.0561712299000437e-06, + "loss": 0.0945, + "step": 33031 + }, + { + "epoch": 2.69, + "learning_rate": 2.055627987831378e-06, + "loss": 0.1547, + "step": 33032 + }, + { + "epoch": 2.69, + "learning_rate": 2.055084745762712e-06, + "loss": 0.4244, + "step": 33033 + }, + { + "epoch": 2.69, + "learning_rate": 2.0545415036940464e-06, + "loss": 0.1148, + "step": 33034 + }, + { + "epoch": 2.69, + "learning_rate": 2.05399826162538e-06, + "loss": 0.3533, + "step": 33035 + }, + { + "epoch": 2.69, + "learning_rate": 2.0534550195567144e-06, + "loss": 0.1078, + "step": 33036 + }, + { + "epoch": 2.69, + "learning_rate": 2.052911777488049e-06, + "loss": 0.2139, + "step": 33037 + }, + { + "epoch": 2.69, + "learning_rate": 2.0523685354193833e-06, + "loss": 0.1608, + "step": 33038 + }, + { + "epoch": 2.69, + "learning_rate": 2.051825293350717e-06, + "loss": 0.272, + "step": 33039 + }, + { + "epoch": 2.69, + "learning_rate": 2.0512820512820513e-06, + "loss": 0.1036, + "step": 33040 + }, + { + "epoch": 2.69, + "learning_rate": 2.0507388092133856e-06, + "loss": 0.2464, + "step": 33041 + }, + { + "epoch": 2.69, + "learning_rate": 2.05019556714472e-06, + "loss": 0.5135, + "step": 33042 + }, + { + "epoch": 2.69, + "learning_rate": 2.049652325076054e-06, + "loss": 0.2526, + "step": 33043 + }, + { + "epoch": 2.69, + "learning_rate": 2.0491090830073883e-06, + "loss": 0.3622, + "step": 33044 + }, + { + "epoch": 2.69, + "learning_rate": 2.0485658409387225e-06, + "loss": 0.1837, + "step": 33045 + }, + { + "epoch": 2.69, + "learning_rate": 2.0480225988700567e-06, + "loss": 0.0519, + "step": 33046 + }, + { + "epoch": 2.69, + "learning_rate": 2.047479356801391e-06, + "loss": 0.266, + "step": 33047 + }, + { + "epoch": 2.69, + "learning_rate": 2.046936114732725e-06, + "loss": 0.3856, + "step": 33048 + }, + { + "epoch": 2.69, + "learning_rate": 2.046392872664059e-06, + "loss": 0.2145, + "step": 33049 + }, + { + "epoch": 2.69, + "learning_rate": 2.0458496305953932e-06, + "loss": 0.1892, + "step": 33050 + }, + { + "epoch": 2.69, + "learning_rate": 2.045306388526728e-06, + "loss": 0.1121, + "step": 33051 + }, + { + "epoch": 2.69, + "learning_rate": 2.044763146458062e-06, + "loss": 0.135, + "step": 33052 + }, + { + "epoch": 2.69, + "learning_rate": 2.0442199043893963e-06, + "loss": 0.1801, + "step": 33053 + }, + { + "epoch": 2.69, + "learning_rate": 2.04367666232073e-06, + "loss": 0.2568, + "step": 33054 + }, + { + "epoch": 2.69, + "learning_rate": 2.0431334202520644e-06, + "loss": 0.1167, + "step": 33055 + }, + { + "epoch": 2.69, + "learning_rate": 2.0425901781833986e-06, + "loss": 0.5096, + "step": 33056 + }, + { + "epoch": 2.69, + "learning_rate": 2.042046936114733e-06, + "loss": 0.1765, + "step": 33057 + }, + { + "epoch": 2.69, + "learning_rate": 2.041503694046067e-06, + "loss": 0.5672, + "step": 33058 + }, + { + "epoch": 2.69, + "learning_rate": 2.0409604519774013e-06, + "loss": 0.2602, + "step": 33059 + }, + { + "epoch": 2.69, + "learning_rate": 2.0404172099087355e-06, + "loss": 0.1847, + "step": 33060 + }, + { + "epoch": 2.69, + "learning_rate": 2.0398739678400698e-06, + "loss": 0.2159, + "step": 33061 + }, + { + "epoch": 2.69, + "learning_rate": 2.039330725771404e-06, + "loss": 0.1846, + "step": 33062 + }, + { + "epoch": 2.69, + "learning_rate": 2.038787483702738e-06, + "loss": 0.2675, + "step": 33063 + }, + { + "epoch": 2.69, + "learning_rate": 2.0382442416340725e-06, + "loss": 0.303, + "step": 33064 + }, + { + "epoch": 2.69, + "learning_rate": 2.0377009995654067e-06, + "loss": 0.4896, + "step": 33065 + }, + { + "epoch": 2.69, + "learning_rate": 2.037157757496741e-06, + "loss": 0.5306, + "step": 33066 + }, + { + "epoch": 2.69, + "learning_rate": 2.036614515428075e-06, + "loss": 0.3492, + "step": 33067 + }, + { + "epoch": 2.69, + "learning_rate": 2.036071273359409e-06, + "loss": 0.1388, + "step": 33068 + }, + { + "epoch": 2.69, + "learning_rate": 2.035528031290743e-06, + "loss": 0.3037, + "step": 33069 + }, + { + "epoch": 2.69, + "learning_rate": 2.0349847892220774e-06, + "loss": 0.2914, + "step": 33070 + }, + { + "epoch": 2.69, + "learning_rate": 2.0344415471534116e-06, + "loss": 0.1016, + "step": 33071 + }, + { + "epoch": 2.69, + "learning_rate": 2.033898305084746e-06, + "loss": 0.1975, + "step": 33072 + }, + { + "epoch": 2.69, + "learning_rate": 2.03335506301608e-06, + "loss": 0.3301, + "step": 33073 + }, + { + "epoch": 2.7, + "learning_rate": 2.0328118209474143e-06, + "loss": 0.2735, + "step": 33074 + }, + { + "epoch": 2.7, + "learning_rate": 2.0322685788787486e-06, + "loss": 0.0805, + "step": 33075 + }, + { + "epoch": 2.7, + "learning_rate": 2.031725336810083e-06, + "loss": 0.1787, + "step": 33076 + }, + { + "epoch": 2.7, + "learning_rate": 2.0311820947414166e-06, + "loss": 0.1801, + "step": 33077 + }, + { + "epoch": 2.7, + "learning_rate": 2.0306388526727513e-06, + "loss": 0.3137, + "step": 33078 + }, + { + "epoch": 2.7, + "learning_rate": 2.0300956106040855e-06, + "loss": 0.3296, + "step": 33079 + }, + { + "epoch": 2.7, + "learning_rate": 2.0295523685354197e-06, + "loss": 0.1316, + "step": 33080 + }, + { + "epoch": 2.7, + "learning_rate": 2.029009126466754e-06, + "loss": 0.1638, + "step": 33081 + }, + { + "epoch": 2.7, + "learning_rate": 2.0284658843980878e-06, + "loss": 0.0723, + "step": 33082 + }, + { + "epoch": 2.7, + "learning_rate": 2.027922642329422e-06, + "loss": 0.2451, + "step": 33083 + }, + { + "epoch": 2.7, + "learning_rate": 2.0273794002607562e-06, + "loss": 0.0944, + "step": 33084 + }, + { + "epoch": 2.7, + "learning_rate": 2.0268361581920904e-06, + "loss": 0.1587, + "step": 33085 + }, + { + "epoch": 2.7, + "learning_rate": 2.0262929161234247e-06, + "loss": 0.3707, + "step": 33086 + }, + { + "epoch": 2.7, + "learning_rate": 2.025749674054759e-06, + "loss": 0.1325, + "step": 33087 + }, + { + "epoch": 2.7, + "learning_rate": 2.025206431986093e-06, + "loss": 0.3332, + "step": 33088 + }, + { + "epoch": 2.7, + "learning_rate": 2.0246631899174274e-06, + "loss": 0.0959, + "step": 33089 + }, + { + "epoch": 2.7, + "learning_rate": 2.0241199478487616e-06, + "loss": 0.1999, + "step": 33090 + }, + { + "epoch": 2.7, + "learning_rate": 2.023576705780096e-06, + "loss": 0.0602, + "step": 33091 + }, + { + "epoch": 2.7, + "learning_rate": 2.02303346371143e-06, + "loss": 0.3085, + "step": 33092 + }, + { + "epoch": 2.7, + "learning_rate": 2.0224902216427643e-06, + "loss": 0.2793, + "step": 33093 + }, + { + "epoch": 2.7, + "learning_rate": 2.0219469795740985e-06, + "loss": 0.2903, + "step": 33094 + }, + { + "epoch": 2.7, + "learning_rate": 2.0214037375054328e-06, + "loss": 0.2587, + "step": 33095 + }, + { + "epoch": 2.7, + "learning_rate": 2.0208604954367666e-06, + "loss": 0.0891, + "step": 33096 + }, + { + "epoch": 2.7, + "learning_rate": 2.020317253368101e-06, + "loss": 0.076, + "step": 33097 + }, + { + "epoch": 2.7, + "learning_rate": 2.019774011299435e-06, + "loss": 0.2119, + "step": 33098 + }, + { + "epoch": 2.7, + "learning_rate": 2.0192307692307692e-06, + "loss": 0.102, + "step": 33099 + }, + { + "epoch": 2.7, + "learning_rate": 2.018687527162104e-06, + "loss": 0.0854, + "step": 33100 + }, + { + "epoch": 2.7, + "learning_rate": 2.0181442850934377e-06, + "loss": 0.0722, + "step": 33101 + }, + { + "epoch": 2.7, + "learning_rate": 2.017601043024772e-06, + "loss": 0.0923, + "step": 33102 + }, + { + "epoch": 2.7, + "learning_rate": 2.017057800956106e-06, + "loss": 0.1513, + "step": 33103 + }, + { + "epoch": 2.7, + "learning_rate": 2.0165145588874404e-06, + "loss": 0.1226, + "step": 33104 + }, + { + "epoch": 2.7, + "learning_rate": 2.0159713168187746e-06, + "loss": 0.0693, + "step": 33105 + }, + { + "epoch": 2.7, + "learning_rate": 2.015428074750109e-06, + "loss": 0.3642, + "step": 33106 + }, + { + "epoch": 2.7, + "learning_rate": 2.014884832681443e-06, + "loss": 0.1588, + "step": 33107 + }, + { + "epoch": 2.7, + "learning_rate": 2.0143415906127773e-06, + "loss": 0.2038, + "step": 33108 + }, + { + "epoch": 2.7, + "learning_rate": 2.0137983485441116e-06, + "loss": 0.089, + "step": 33109 + }, + { + "epoch": 2.7, + "learning_rate": 2.0132551064754458e-06, + "loss": 0.1885, + "step": 33110 + }, + { + "epoch": 2.7, + "learning_rate": 2.0127118644067796e-06, + "loss": 0.3617, + "step": 33111 + }, + { + "epoch": 2.7, + "learning_rate": 2.012168622338114e-06, + "loss": 0.1126, + "step": 33112 + }, + { + "epoch": 2.7, + "learning_rate": 2.011625380269448e-06, + "loss": 0.322, + "step": 33113 + }, + { + "epoch": 2.7, + "learning_rate": 2.0110821382007827e-06, + "loss": 0.3385, + "step": 33114 + }, + { + "epoch": 2.7, + "learning_rate": 2.0105388961321165e-06, + "loss": 0.3691, + "step": 33115 + }, + { + "epoch": 2.7, + "learning_rate": 2.0099956540634507e-06, + "loss": 0.1897, + "step": 33116 + }, + { + "epoch": 2.7, + "learning_rate": 2.009452411994785e-06, + "loss": 0.1395, + "step": 33117 + }, + { + "epoch": 2.7, + "learning_rate": 2.008909169926119e-06, + "loss": 0.4007, + "step": 33118 + }, + { + "epoch": 2.7, + "learning_rate": 2.0083659278574534e-06, + "loss": 0.1469, + "step": 33119 + }, + { + "epoch": 2.7, + "learning_rate": 2.0078226857887877e-06, + "loss": 0.1584, + "step": 33120 + }, + { + "epoch": 2.7, + "learning_rate": 2.007279443720122e-06, + "loss": 0.3382, + "step": 33121 + }, + { + "epoch": 2.7, + "learning_rate": 2.006736201651456e-06, + "loss": 0.1809, + "step": 33122 + }, + { + "epoch": 2.7, + "learning_rate": 2.0061929595827904e-06, + "loss": 0.1434, + "step": 33123 + }, + { + "epoch": 2.7, + "learning_rate": 2.0056497175141246e-06, + "loss": 0.1012, + "step": 33124 + }, + { + "epoch": 2.7, + "learning_rate": 2.0051064754454584e-06, + "loss": 0.1184, + "step": 33125 + }, + { + "epoch": 2.7, + "learning_rate": 2.0045632333767926e-06, + "loss": 0.1028, + "step": 33126 + }, + { + "epoch": 2.7, + "learning_rate": 2.0040199913081273e-06, + "loss": 0.3217, + "step": 33127 + }, + { + "epoch": 2.7, + "learning_rate": 2.0034767492394615e-06, + "loss": 0.2358, + "step": 33128 + }, + { + "epoch": 2.7, + "learning_rate": 2.0029335071707957e-06, + "loss": 0.2723, + "step": 33129 + }, + { + "epoch": 2.7, + "learning_rate": 2.0023902651021295e-06, + "loss": 0.3428, + "step": 33130 + }, + { + "epoch": 2.7, + "learning_rate": 2.0018470230334638e-06, + "loss": 0.1564, + "step": 33131 + }, + { + "epoch": 2.7, + "learning_rate": 2.001303780964798e-06, + "loss": 0.117, + "step": 33132 + }, + { + "epoch": 2.7, + "learning_rate": 2.0007605388961322e-06, + "loss": 0.2384, + "step": 33133 + }, + { + "epoch": 2.7, + "learning_rate": 2.0002172968274665e-06, + "loss": 0.2756, + "step": 33134 + }, + { + "epoch": 2.7, + "learning_rate": 1.9996740547588007e-06, + "loss": 0.2436, + "step": 33135 + }, + { + "epoch": 2.7, + "learning_rate": 1.999130812690135e-06, + "loss": 0.3637, + "step": 33136 + }, + { + "epoch": 2.7, + "learning_rate": 1.998587570621469e-06, + "loss": 0.3604, + "step": 33137 + }, + { + "epoch": 2.7, + "learning_rate": 1.9980443285528034e-06, + "loss": 0.11, + "step": 33138 + }, + { + "epoch": 2.7, + "learning_rate": 1.997501086484137e-06, + "loss": 0.4947, + "step": 33139 + }, + { + "epoch": 2.7, + "learning_rate": 1.9969578444154714e-06, + "loss": 0.5113, + "step": 33140 + }, + { + "epoch": 2.7, + "learning_rate": 1.996414602346806e-06, + "loss": 0.2122, + "step": 33141 + }, + { + "epoch": 2.7, + "learning_rate": 1.9958713602781403e-06, + "loss": 0.2015, + "step": 33142 + }, + { + "epoch": 2.7, + "learning_rate": 1.9953281182094745e-06, + "loss": 0.1311, + "step": 33143 + }, + { + "epoch": 2.7, + "learning_rate": 1.9947848761408084e-06, + "loss": 0.3969, + "step": 33144 + }, + { + "epoch": 2.7, + "learning_rate": 1.9942416340721426e-06, + "loss": 0.2132, + "step": 33145 + }, + { + "epoch": 2.7, + "learning_rate": 1.993698392003477e-06, + "loss": 0.2763, + "step": 33146 + }, + { + "epoch": 2.7, + "learning_rate": 1.993155149934811e-06, + "loss": 0.2319, + "step": 33147 + }, + { + "epoch": 2.7, + "learning_rate": 1.9926119078661453e-06, + "loss": 0.1999, + "step": 33148 + }, + { + "epoch": 2.7, + "learning_rate": 1.9920686657974795e-06, + "loss": 0.0547, + "step": 33149 + }, + { + "epoch": 2.7, + "learning_rate": 1.9915254237288137e-06, + "loss": 0.1699, + "step": 33150 + }, + { + "epoch": 2.7, + "learning_rate": 1.990982181660148e-06, + "loss": 0.1531, + "step": 33151 + }, + { + "epoch": 2.7, + "learning_rate": 1.990438939591482e-06, + "loss": 0.3278, + "step": 33152 + }, + { + "epoch": 2.7, + "learning_rate": 1.989895697522816e-06, + "loss": 0.2552, + "step": 33153 + }, + { + "epoch": 2.7, + "learning_rate": 1.9893524554541507e-06, + "loss": 0.2632, + "step": 33154 + }, + { + "epoch": 2.7, + "learning_rate": 1.988809213385485e-06, + "loss": 0.3781, + "step": 33155 + }, + { + "epoch": 2.7, + "learning_rate": 1.988265971316819e-06, + "loss": 0.1578, + "step": 33156 + }, + { + "epoch": 2.7, + "learning_rate": 1.9877227292481534e-06, + "loss": 0.301, + "step": 33157 + }, + { + "epoch": 2.7, + "learning_rate": 1.987179487179487e-06, + "loss": 0.2601, + "step": 33158 + }, + { + "epoch": 2.7, + "learning_rate": 1.9866362451108214e-06, + "loss": 0.2048, + "step": 33159 + }, + { + "epoch": 2.7, + "learning_rate": 1.9860930030421556e-06, + "loss": 0.2299, + "step": 33160 + }, + { + "epoch": 2.7, + "learning_rate": 1.98554976097349e-06, + "loss": 0.2506, + "step": 33161 + }, + { + "epoch": 2.7, + "learning_rate": 1.985006518904824e-06, + "loss": 0.1857, + "step": 33162 + }, + { + "epoch": 2.7, + "learning_rate": 1.9844632768361583e-06, + "loss": 0.2002, + "step": 33163 + }, + { + "epoch": 2.7, + "learning_rate": 1.9839200347674925e-06, + "loss": 0.0571, + "step": 33164 + }, + { + "epoch": 2.7, + "learning_rate": 1.9833767926988268e-06, + "loss": 0.2366, + "step": 33165 + }, + { + "epoch": 2.7, + "learning_rate": 1.982833550630161e-06, + "loss": 0.3268, + "step": 33166 + }, + { + "epoch": 2.7, + "learning_rate": 1.9822903085614952e-06, + "loss": 0.2004, + "step": 33167 + }, + { + "epoch": 2.7, + "learning_rate": 1.9817470664928295e-06, + "loss": 0.0953, + "step": 33168 + }, + { + "epoch": 2.7, + "learning_rate": 1.9812038244241637e-06, + "loss": 0.2407, + "step": 33169 + }, + { + "epoch": 2.7, + "learning_rate": 1.980660582355498e-06, + "loss": 0.2391, + "step": 33170 + }, + { + "epoch": 2.7, + "learning_rate": 1.980117340286832e-06, + "loss": 0.3105, + "step": 33171 + }, + { + "epoch": 2.7, + "learning_rate": 1.979574098218166e-06, + "loss": 0.3496, + "step": 33172 + }, + { + "epoch": 2.7, + "learning_rate": 1.9790308561495e-06, + "loss": 0.3128, + "step": 33173 + }, + { + "epoch": 2.7, + "learning_rate": 1.9784876140808344e-06, + "loss": 0.2476, + "step": 33174 + }, + { + "epoch": 2.7, + "learning_rate": 1.9779443720121687e-06, + "loss": 0.2179, + "step": 33175 + }, + { + "epoch": 2.7, + "learning_rate": 1.977401129943503e-06, + "loss": 0.2027, + "step": 33176 + }, + { + "epoch": 2.7, + "learning_rate": 1.976857887874837e-06, + "loss": 0.305, + "step": 33177 + }, + { + "epoch": 2.7, + "learning_rate": 1.9763146458061713e-06, + "loss": 0.1974, + "step": 33178 + }, + { + "epoch": 2.7, + "learning_rate": 1.9757714037375056e-06, + "loss": 0.1218, + "step": 33179 + }, + { + "epoch": 2.7, + "learning_rate": 1.97522816166884e-06, + "loss": 0.1192, + "step": 33180 + }, + { + "epoch": 2.7, + "learning_rate": 1.974684919600174e-06, + "loss": 0.2253, + "step": 33181 + }, + { + "epoch": 2.7, + "learning_rate": 1.9741416775315083e-06, + "loss": 0.1115, + "step": 33182 + }, + { + "epoch": 2.7, + "learning_rate": 1.9735984354628425e-06, + "loss": 0.1048, + "step": 33183 + }, + { + "epoch": 2.7, + "learning_rate": 1.9730551933941767e-06, + "loss": 0.3291, + "step": 33184 + }, + { + "epoch": 2.7, + "learning_rate": 1.972511951325511e-06, + "loss": 0.1846, + "step": 33185 + }, + { + "epoch": 2.7, + "learning_rate": 1.971968709256845e-06, + "loss": 0.3435, + "step": 33186 + }, + { + "epoch": 2.7, + "learning_rate": 1.971425467188179e-06, + "loss": 0.2858, + "step": 33187 + }, + { + "epoch": 2.7, + "learning_rate": 1.9708822251195132e-06, + "loss": 0.1247, + "step": 33188 + }, + { + "epoch": 2.7, + "learning_rate": 1.9703389830508475e-06, + "loss": 0.2858, + "step": 33189 + }, + { + "epoch": 2.7, + "learning_rate": 1.969795740982182e-06, + "loss": 0.2168, + "step": 33190 + }, + { + "epoch": 2.7, + "learning_rate": 1.969252498913516e-06, + "loss": 0.5045, + "step": 33191 + }, + { + "epoch": 2.7, + "learning_rate": 1.96870925684485e-06, + "loss": 0.2033, + "step": 33192 + }, + { + "epoch": 2.7, + "learning_rate": 1.9681660147761844e-06, + "loss": 0.3482, + "step": 33193 + }, + { + "epoch": 2.7, + "learning_rate": 1.9676227727075186e-06, + "loss": 0.2157, + "step": 33194 + }, + { + "epoch": 2.7, + "learning_rate": 1.967079530638853e-06, + "loss": 0.269, + "step": 33195 + }, + { + "epoch": 2.71, + "learning_rate": 1.966536288570187e-06, + "loss": 0.3497, + "step": 33196 + }, + { + "epoch": 2.71, + "learning_rate": 1.9659930465015213e-06, + "loss": 0.1621, + "step": 33197 + }, + { + "epoch": 2.71, + "learning_rate": 1.9654498044328555e-06, + "loss": 0.1963, + "step": 33198 + }, + { + "epoch": 2.71, + "learning_rate": 1.9649065623641898e-06, + "loss": 0.3059, + "step": 33199 + }, + { + "epoch": 2.71, + "learning_rate": 1.964363320295524e-06, + "loss": 0.184, + "step": 33200 + }, + { + "epoch": 2.71, + "learning_rate": 1.963820078226858e-06, + "loss": 0.0535, + "step": 33201 + }, + { + "epoch": 2.71, + "learning_rate": 1.963276836158192e-06, + "loss": 0.0395, + "step": 33202 + }, + { + "epoch": 2.71, + "learning_rate": 1.9627335940895263e-06, + "loss": 0.1973, + "step": 33203 + }, + { + "epoch": 2.71, + "learning_rate": 1.962190352020861e-06, + "loss": 0.4344, + "step": 33204 + }, + { + "epoch": 2.71, + "learning_rate": 1.961647109952195e-06, + "loss": 0.1621, + "step": 33205 + }, + { + "epoch": 2.71, + "learning_rate": 1.961103867883529e-06, + "loss": 0.1617, + "step": 33206 + }, + { + "epoch": 2.71, + "learning_rate": 1.960560625814863e-06, + "loss": 0.1206, + "step": 33207 + }, + { + "epoch": 2.71, + "learning_rate": 1.9600173837461974e-06, + "loss": 0.3831, + "step": 33208 + }, + { + "epoch": 2.71, + "learning_rate": 1.9594741416775316e-06, + "loss": 0.1428, + "step": 33209 + }, + { + "epoch": 2.71, + "learning_rate": 1.958930899608866e-06, + "loss": 0.1774, + "step": 33210 + }, + { + "epoch": 2.71, + "learning_rate": 1.9583876575402e-06, + "loss": 0.1626, + "step": 33211 + }, + { + "epoch": 2.71, + "learning_rate": 1.9578444154715343e-06, + "loss": 0.2437, + "step": 33212 + }, + { + "epoch": 2.71, + "learning_rate": 1.9573011734028686e-06, + "loss": 0.1693, + "step": 33213 + }, + { + "epoch": 2.71, + "learning_rate": 1.956757931334203e-06, + "loss": 0.1787, + "step": 33214 + }, + { + "epoch": 2.71, + "learning_rate": 1.9562146892655366e-06, + "loss": 0.1148, + "step": 33215 + }, + { + "epoch": 2.71, + "learning_rate": 1.955671447196871e-06, + "loss": 0.3835, + "step": 33216 + }, + { + "epoch": 2.71, + "learning_rate": 1.9551282051282055e-06, + "loss": 0.1317, + "step": 33217 + }, + { + "epoch": 2.71, + "learning_rate": 1.9545849630595397e-06, + "loss": 0.4585, + "step": 33218 + }, + { + "epoch": 2.71, + "learning_rate": 1.954041720990874e-06, + "loss": 0.1164, + "step": 33219 + }, + { + "epoch": 2.71, + "learning_rate": 1.9534984789222078e-06, + "loss": 0.1915, + "step": 33220 + }, + { + "epoch": 2.71, + "learning_rate": 1.952955236853542e-06, + "loss": 0.2913, + "step": 33221 + }, + { + "epoch": 2.71, + "learning_rate": 1.9524119947848762e-06, + "loss": 0.1779, + "step": 33222 + }, + { + "epoch": 2.71, + "learning_rate": 1.9518687527162104e-06, + "loss": 0.0716, + "step": 33223 + }, + { + "epoch": 2.71, + "learning_rate": 1.9513255106475447e-06, + "loss": 0.3134, + "step": 33224 + }, + { + "epoch": 2.71, + "learning_rate": 1.950782268578879e-06, + "loss": 0.3146, + "step": 33225 + }, + { + "epoch": 2.71, + "learning_rate": 1.950239026510213e-06, + "loss": 0.4389, + "step": 33226 + }, + { + "epoch": 2.71, + "learning_rate": 1.9496957844415474e-06, + "loss": 0.1719, + "step": 33227 + }, + { + "epoch": 2.71, + "learning_rate": 1.9491525423728816e-06, + "loss": 0.1823, + "step": 33228 + }, + { + "epoch": 2.71, + "learning_rate": 1.948609300304216e-06, + "loss": 0.1699, + "step": 33229 + }, + { + "epoch": 2.71, + "learning_rate": 1.9480660582355496e-06, + "loss": 0.0784, + "step": 33230 + }, + { + "epoch": 2.71, + "learning_rate": 1.9475228161668843e-06, + "loss": 0.2526, + "step": 33231 + }, + { + "epoch": 2.71, + "learning_rate": 1.9469795740982185e-06, + "loss": 0.4769, + "step": 33232 + }, + { + "epoch": 2.71, + "learning_rate": 1.9464363320295528e-06, + "loss": 0.5085, + "step": 33233 + }, + { + "epoch": 2.71, + "learning_rate": 1.9458930899608866e-06, + "loss": 0.363, + "step": 33234 + }, + { + "epoch": 2.71, + "learning_rate": 1.945349847892221e-06, + "loss": 0.1192, + "step": 33235 + }, + { + "epoch": 2.71, + "learning_rate": 1.944806605823555e-06, + "loss": 0.3334, + "step": 33236 + }, + { + "epoch": 2.71, + "learning_rate": 1.9442633637548893e-06, + "loss": 0.2181, + "step": 33237 + }, + { + "epoch": 2.71, + "learning_rate": 1.9437201216862235e-06, + "loss": 0.1166, + "step": 33238 + }, + { + "epoch": 2.71, + "learning_rate": 1.9431768796175577e-06, + "loss": 0.0814, + "step": 33239 + }, + { + "epoch": 2.71, + "learning_rate": 1.942633637548892e-06, + "loss": 0.1156, + "step": 33240 + }, + { + "epoch": 2.71, + "learning_rate": 1.942090395480226e-06, + "loss": 0.151, + "step": 33241 + }, + { + "epoch": 2.71, + "learning_rate": 1.9415471534115604e-06, + "loss": 0.1045, + "step": 33242 + }, + { + "epoch": 2.71, + "learning_rate": 1.9410039113428946e-06, + "loss": 0.4735, + "step": 33243 + }, + { + "epoch": 2.71, + "learning_rate": 1.940460669274229e-06, + "loss": 0.3305, + "step": 33244 + }, + { + "epoch": 2.71, + "learning_rate": 1.939917427205563e-06, + "loss": 0.1071, + "step": 33245 + }, + { + "epoch": 2.71, + "learning_rate": 1.9393741851368973e-06, + "loss": 0.3275, + "step": 33246 + }, + { + "epoch": 2.71, + "learning_rate": 1.9388309430682316e-06, + "loss": 0.1828, + "step": 33247 + }, + { + "epoch": 2.71, + "learning_rate": 1.938287700999566e-06, + "loss": 0.3945, + "step": 33248 + }, + { + "epoch": 2.71, + "learning_rate": 1.9377444589308996e-06, + "loss": 0.3766, + "step": 33249 + }, + { + "epoch": 2.71, + "learning_rate": 1.937201216862234e-06, + "loss": 0.4564, + "step": 33250 + }, + { + "epoch": 2.71, + "eval_accuracy": 0.8434029546612328, + "eval_loss": 0.4937683045864105, + "eval_runtime": 22.2374, + "eval_samples_per_second": 441.374, + "eval_steps_per_second": 3.463, + "step": 33250 + }, + { + "epoch": 2.71, + "learning_rate": 1.936657974793568e-06, + "loss": 0.4069, + "step": 33251 + }, + { + "epoch": 2.71, + "learning_rate": 1.9361147327249023e-06, + "loss": 0.2046, + "step": 33252 + }, + { + "epoch": 2.71, + "learning_rate": 1.9355714906562365e-06, + "loss": 0.0916, + "step": 33253 + }, + { + "epoch": 2.71, + "learning_rate": 1.9350282485875707e-06, + "loss": 0.2514, + "step": 33254 + }, + { + "epoch": 2.71, + "learning_rate": 1.934485006518905e-06, + "loss": 0.3793, + "step": 33255 + }, + { + "epoch": 2.71, + "learning_rate": 1.933941764450239e-06, + "loss": 0.1779, + "step": 33256 + }, + { + "epoch": 2.71, + "learning_rate": 1.9333985223815734e-06, + "loss": 0.2854, + "step": 33257 + }, + { + "epoch": 2.71, + "learning_rate": 1.9328552803129077e-06, + "loss": 0.2577, + "step": 33258 + }, + { + "epoch": 2.71, + "learning_rate": 1.932312038244242e-06, + "loss": 0.1628, + "step": 33259 + }, + { + "epoch": 2.71, + "learning_rate": 1.931768796175576e-06, + "loss": 0.2748, + "step": 33260 + }, + { + "epoch": 2.71, + "learning_rate": 1.9312255541069104e-06, + "loss": 0.237, + "step": 33261 + }, + { + "epoch": 2.71, + "learning_rate": 1.9306823120382446e-06, + "loss": 0.1451, + "step": 33262 + }, + { + "epoch": 2.71, + "learning_rate": 1.9301390699695784e-06, + "loss": 0.1479, + "step": 33263 + }, + { + "epoch": 2.71, + "learning_rate": 1.9295958279009126e-06, + "loss": 0.2298, + "step": 33264 + }, + { + "epoch": 2.71, + "learning_rate": 1.929052585832247e-06, + "loss": 0.1334, + "step": 33265 + }, + { + "epoch": 2.71, + "learning_rate": 1.928509343763581e-06, + "loss": 0.1762, + "step": 33266 + }, + { + "epoch": 2.71, + "learning_rate": 1.9279661016949157e-06, + "loss": 0.1171, + "step": 33267 + }, + { + "epoch": 2.71, + "learning_rate": 1.9274228596262496e-06, + "loss": 0.3611, + "step": 33268 + }, + { + "epoch": 2.71, + "learning_rate": 1.9268796175575838e-06, + "loss": 0.1191, + "step": 33269 + }, + { + "epoch": 2.71, + "learning_rate": 1.926336375488918e-06, + "loss": 0.0729, + "step": 33270 + }, + { + "epoch": 2.71, + "learning_rate": 1.9257931334202522e-06, + "loss": 0.1557, + "step": 33271 + }, + { + "epoch": 2.71, + "learning_rate": 1.9252498913515865e-06, + "loss": 0.2116, + "step": 33272 + }, + { + "epoch": 2.71, + "learning_rate": 1.9247066492829207e-06, + "loss": 0.4034, + "step": 33273 + }, + { + "epoch": 2.71, + "learning_rate": 1.924163407214255e-06, + "loss": 0.102, + "step": 33274 + }, + { + "epoch": 2.71, + "learning_rate": 1.923620165145589e-06, + "loss": 0.2322, + "step": 33275 + }, + { + "epoch": 2.71, + "learning_rate": 1.9230769230769234e-06, + "loss": 0.1753, + "step": 33276 + }, + { + "epoch": 2.71, + "learning_rate": 1.922533681008257e-06, + "loss": 0.4172, + "step": 33277 + }, + { + "epoch": 2.71, + "learning_rate": 1.9219904389395914e-06, + "loss": 0.0927, + "step": 33278 + }, + { + "epoch": 2.71, + "learning_rate": 1.9214471968709257e-06, + "loss": 0.1258, + "step": 33279 + }, + { + "epoch": 2.71, + "learning_rate": 1.92090395480226e-06, + "loss": 0.0821, + "step": 33280 + }, + { + "epoch": 2.71, + "learning_rate": 1.9203607127335945e-06, + "loss": 0.0963, + "step": 33281 + }, + { + "epoch": 2.71, + "learning_rate": 1.9198174706649284e-06, + "loss": 0.0791, + "step": 33282 + }, + { + "epoch": 2.71, + "learning_rate": 1.9192742285962626e-06, + "loss": 0.2482, + "step": 33283 + }, + { + "epoch": 2.71, + "learning_rate": 1.918730986527597e-06, + "loss": 0.3261, + "step": 33284 + }, + { + "epoch": 2.71, + "learning_rate": 1.918187744458931e-06, + "loss": 0.0437, + "step": 33285 + }, + { + "epoch": 2.71, + "learning_rate": 1.9176445023902653e-06, + "loss": 0.1546, + "step": 33286 + }, + { + "epoch": 2.71, + "learning_rate": 1.9171012603215995e-06, + "loss": 0.2755, + "step": 33287 + }, + { + "epoch": 2.71, + "learning_rate": 1.9165580182529337e-06, + "loss": 0.1039, + "step": 33288 + }, + { + "epoch": 2.71, + "learning_rate": 1.916014776184268e-06, + "loss": 0.3909, + "step": 33289 + }, + { + "epoch": 2.71, + "learning_rate": 1.915471534115602e-06, + "loss": 0.3891, + "step": 33290 + }, + { + "epoch": 2.71, + "learning_rate": 1.914928292046936e-06, + "loss": 0.3619, + "step": 33291 + }, + { + "epoch": 2.71, + "learning_rate": 1.9143850499782702e-06, + "loss": 0.3164, + "step": 33292 + }, + { + "epoch": 2.71, + "learning_rate": 1.9138418079096045e-06, + "loss": 0.2165, + "step": 33293 + }, + { + "epoch": 2.71, + "learning_rate": 1.913298565840939e-06, + "loss": 0.063, + "step": 33294 + }, + { + "epoch": 2.71, + "learning_rate": 1.9127553237722734e-06, + "loss": 0.3656, + "step": 33295 + }, + { + "epoch": 2.71, + "learning_rate": 1.912212081703607e-06, + "loss": 0.1067, + "step": 33296 + }, + { + "epoch": 2.71, + "learning_rate": 1.9116688396349414e-06, + "loss": 0.5096, + "step": 33297 + }, + { + "epoch": 2.71, + "learning_rate": 1.9111255975662756e-06, + "loss": 0.2321, + "step": 33298 + }, + { + "epoch": 2.71, + "learning_rate": 1.91058235549761e-06, + "loss": 0.2468, + "step": 33299 + }, + { + "epoch": 2.71, + "learning_rate": 1.910039113428944e-06, + "loss": 0.0444, + "step": 33300 + }, + { + "epoch": 2.71, + "learning_rate": 1.9094958713602783e-06, + "loss": 0.1117, + "step": 33301 + }, + { + "epoch": 2.71, + "learning_rate": 1.9089526292916125e-06, + "loss": 0.3237, + "step": 33302 + }, + { + "epoch": 2.71, + "learning_rate": 1.9084093872229468e-06, + "loss": 0.3534, + "step": 33303 + }, + { + "epoch": 2.71, + "learning_rate": 1.907866145154281e-06, + "loss": 0.2962, + "step": 33304 + }, + { + "epoch": 2.71, + "learning_rate": 1.9073229030856152e-06, + "loss": 0.2187, + "step": 33305 + }, + { + "epoch": 2.71, + "learning_rate": 1.9067796610169493e-06, + "loss": 0.2113, + "step": 33306 + }, + { + "epoch": 2.71, + "learning_rate": 1.9062364189482835e-06, + "loss": 0.2335, + "step": 33307 + }, + { + "epoch": 2.71, + "learning_rate": 1.9056931768796177e-06, + "loss": 0.245, + "step": 33308 + }, + { + "epoch": 2.71, + "learning_rate": 1.905149934810952e-06, + "loss": 0.1788, + "step": 33309 + }, + { + "epoch": 2.71, + "learning_rate": 1.904606692742286e-06, + "loss": 0.1949, + "step": 33310 + }, + { + "epoch": 2.71, + "learning_rate": 1.9040634506736202e-06, + "loss": 0.0848, + "step": 33311 + }, + { + "epoch": 2.71, + "learning_rate": 1.9035202086049544e-06, + "loss": 0.3503, + "step": 33312 + }, + { + "epoch": 2.71, + "learning_rate": 1.9029769665362889e-06, + "loss": 0.2246, + "step": 33313 + }, + { + "epoch": 2.71, + "learning_rate": 1.902433724467623e-06, + "loss": 0.4576, + "step": 33314 + }, + { + "epoch": 2.71, + "learning_rate": 1.9018904823989571e-06, + "loss": 0.2171, + "step": 33315 + }, + { + "epoch": 2.71, + "learning_rate": 1.9013472403302913e-06, + "loss": 0.3899, + "step": 33316 + }, + { + "epoch": 2.71, + "learning_rate": 1.9008039982616256e-06, + "loss": 0.1397, + "step": 33317 + }, + { + "epoch": 2.71, + "learning_rate": 1.9002607561929598e-06, + "loss": 0.2231, + "step": 33318 + }, + { + "epoch": 2.72, + "learning_rate": 1.899717514124294e-06, + "loss": 0.3268, + "step": 33319 + }, + { + "epoch": 2.72, + "learning_rate": 1.899174272055628e-06, + "loss": 0.2804, + "step": 33320 + }, + { + "epoch": 2.72, + "learning_rate": 1.8986310299869623e-06, + "loss": 0.168, + "step": 33321 + }, + { + "epoch": 2.72, + "learning_rate": 1.8980877879182965e-06, + "loss": 0.1701, + "step": 33322 + }, + { + "epoch": 2.72, + "learning_rate": 1.8975445458496308e-06, + "loss": 0.3554, + "step": 33323 + }, + { + "epoch": 2.72, + "learning_rate": 1.897001303780965e-06, + "loss": 0.1827, + "step": 33324 + }, + { + "epoch": 2.72, + "learning_rate": 1.896458061712299e-06, + "loss": 0.2441, + "step": 33325 + }, + { + "epoch": 2.72, + "learning_rate": 1.8959148196436332e-06, + "loss": 0.3815, + "step": 33326 + }, + { + "epoch": 2.72, + "learning_rate": 1.8953715775749677e-06, + "loss": 0.3101, + "step": 33327 + }, + { + "epoch": 2.72, + "learning_rate": 1.894828335506302e-06, + "loss": 0.4048, + "step": 33328 + }, + { + "epoch": 2.72, + "learning_rate": 1.894285093437636e-06, + "loss": 0.3608, + "step": 33329 + }, + { + "epoch": 2.72, + "learning_rate": 1.8937418513689702e-06, + "loss": 0.1926, + "step": 33330 + }, + { + "epoch": 2.72, + "learning_rate": 1.8931986093003044e-06, + "loss": 0.1422, + "step": 33331 + }, + { + "epoch": 2.72, + "learning_rate": 1.8926553672316386e-06, + "loss": 0.5802, + "step": 33332 + }, + { + "epoch": 2.72, + "learning_rate": 1.8921121251629728e-06, + "loss": 0.1505, + "step": 33333 + }, + { + "epoch": 2.72, + "learning_rate": 1.8915688830943069e-06, + "loss": 0.3838, + "step": 33334 + }, + { + "epoch": 2.72, + "learning_rate": 1.891025641025641e-06, + "loss": 0.3569, + "step": 33335 + }, + { + "epoch": 2.72, + "learning_rate": 1.8904823989569753e-06, + "loss": 0.141, + "step": 33336 + }, + { + "epoch": 2.72, + "learning_rate": 1.8899391568883096e-06, + "loss": 0.3997, + "step": 33337 + }, + { + "epoch": 2.72, + "learning_rate": 1.889395914819644e-06, + "loss": 0.1283, + "step": 33338 + }, + { + "epoch": 2.72, + "learning_rate": 1.8888526727509778e-06, + "loss": 0.2285, + "step": 33339 + }, + { + "epoch": 2.72, + "learning_rate": 1.8883094306823122e-06, + "loss": 0.1837, + "step": 33340 + }, + { + "epoch": 2.72, + "learning_rate": 1.8877661886136465e-06, + "loss": 0.1217, + "step": 33341 + }, + { + "epoch": 2.72, + "learning_rate": 1.8872229465449807e-06, + "loss": 0.2798, + "step": 33342 + }, + { + "epoch": 2.72, + "learning_rate": 1.886679704476315e-06, + "loss": 0.0562, + "step": 33343 + }, + { + "epoch": 2.72, + "learning_rate": 1.886136462407649e-06, + "loss": 0.1302, + "step": 33344 + }, + { + "epoch": 2.72, + "learning_rate": 1.8855932203389832e-06, + "loss": 0.1425, + "step": 33345 + }, + { + "epoch": 2.72, + "learning_rate": 1.8850499782703174e-06, + "loss": 0.2767, + "step": 33346 + }, + { + "epoch": 2.72, + "learning_rate": 1.8845067362016516e-06, + "loss": 0.274, + "step": 33347 + }, + { + "epoch": 2.72, + "learning_rate": 1.8839634941329857e-06, + "loss": 0.2084, + "step": 33348 + }, + { + "epoch": 2.72, + "learning_rate": 1.88342025206432e-06, + "loss": 0.0839, + "step": 33349 + }, + { + "epoch": 2.72, + "learning_rate": 1.8828770099956541e-06, + "loss": 0.1286, + "step": 33350 + }, + { + "epoch": 2.72, + "learning_rate": 1.8823337679269884e-06, + "loss": 0.3139, + "step": 33351 + }, + { + "epoch": 2.72, + "learning_rate": 1.8817905258583228e-06, + "loss": 0.222, + "step": 33352 + }, + { + "epoch": 2.72, + "learning_rate": 1.8812472837896566e-06, + "loss": 0.1412, + "step": 33353 + }, + { + "epoch": 2.72, + "learning_rate": 1.880704041720991e-06, + "loss": 0.1516, + "step": 33354 + }, + { + "epoch": 2.72, + "learning_rate": 1.8801607996523253e-06, + "loss": 0.2834, + "step": 33355 + }, + { + "epoch": 2.72, + "learning_rate": 1.8796175575836595e-06, + "loss": 0.2965, + "step": 33356 + }, + { + "epoch": 2.72, + "learning_rate": 1.8790743155149937e-06, + "loss": 0.2991, + "step": 33357 + }, + { + "epoch": 2.72, + "learning_rate": 1.8785310734463278e-06, + "loss": 0.1165, + "step": 33358 + }, + { + "epoch": 2.72, + "learning_rate": 1.877987831377662e-06, + "loss": 0.1359, + "step": 33359 + }, + { + "epoch": 2.72, + "learning_rate": 1.8774445893089962e-06, + "loss": 0.0558, + "step": 33360 + }, + { + "epoch": 2.72, + "learning_rate": 1.8769013472403305e-06, + "loss": 0.4919, + "step": 33361 + }, + { + "epoch": 2.72, + "learning_rate": 1.8763581051716647e-06, + "loss": 0.2123, + "step": 33362 + }, + { + "epoch": 2.72, + "learning_rate": 1.8758148631029987e-06, + "loss": 0.1634, + "step": 33363 + }, + { + "epoch": 2.72, + "learning_rate": 1.875271621034333e-06, + "loss": 0.3652, + "step": 33364 + }, + { + "epoch": 2.72, + "learning_rate": 1.8747283789656674e-06, + "loss": 0.0831, + "step": 33365 + }, + { + "epoch": 2.72, + "learning_rate": 1.8741851368970016e-06, + "loss": 0.1779, + "step": 33366 + }, + { + "epoch": 2.72, + "learning_rate": 1.8736418948283356e-06, + "loss": 0.1155, + "step": 33367 + }, + { + "epoch": 2.72, + "learning_rate": 1.8730986527596699e-06, + "loss": 0.2661, + "step": 33368 + }, + { + "epoch": 2.72, + "learning_rate": 1.872555410691004e-06, + "loss": 0.2754, + "step": 33369 + }, + { + "epoch": 2.72, + "learning_rate": 1.8720121686223383e-06, + "loss": 0.3209, + "step": 33370 + }, + { + "epoch": 2.72, + "learning_rate": 1.8714689265536725e-06, + "loss": 0.2108, + "step": 33371 + }, + { + "epoch": 2.72, + "learning_rate": 1.8709256844850066e-06, + "loss": 0.2911, + "step": 33372 + }, + { + "epoch": 2.72, + "learning_rate": 1.8703824424163408e-06, + "loss": 0.1755, + "step": 33373 + }, + { + "epoch": 2.72, + "learning_rate": 1.869839200347675e-06, + "loss": 0.1667, + "step": 33374 + }, + { + "epoch": 2.72, + "learning_rate": 1.8692959582790093e-06, + "loss": 0.059, + "step": 33375 + }, + { + "epoch": 2.72, + "learning_rate": 1.8687527162103437e-06, + "loss": 0.4115, + "step": 33376 + }, + { + "epoch": 2.72, + "learning_rate": 1.8682094741416775e-06, + "loss": 0.112, + "step": 33377 + }, + { + "epoch": 2.72, + "learning_rate": 1.867666232073012e-06, + "loss": 0.1607, + "step": 33378 + }, + { + "epoch": 2.72, + "learning_rate": 1.8671229900043462e-06, + "loss": 0.295, + "step": 33379 + }, + { + "epoch": 2.72, + "learning_rate": 1.8665797479356804e-06, + "loss": 0.0839, + "step": 33380 + }, + { + "epoch": 2.72, + "learning_rate": 1.8660365058670146e-06, + "loss": 0.2348, + "step": 33381 + }, + { + "epoch": 2.72, + "learning_rate": 1.8654932637983487e-06, + "loss": 0.1573, + "step": 33382 + }, + { + "epoch": 2.72, + "learning_rate": 1.8649500217296829e-06, + "loss": 0.186, + "step": 33383 + }, + { + "epoch": 2.72, + "learning_rate": 1.8644067796610171e-06, + "loss": 0.2015, + "step": 33384 + }, + { + "epoch": 2.72, + "learning_rate": 1.8638635375923514e-06, + "loss": 0.2376, + "step": 33385 + }, + { + "epoch": 2.72, + "learning_rate": 1.8633202955236854e-06, + "loss": 0.0956, + "step": 33386 + }, + { + "epoch": 2.72, + "learning_rate": 1.8627770534550196e-06, + "loss": 0.2852, + "step": 33387 + }, + { + "epoch": 2.72, + "learning_rate": 1.8622338113863538e-06, + "loss": 0.077, + "step": 33388 + }, + { + "epoch": 2.72, + "learning_rate": 1.861690569317688e-06, + "loss": 0.3678, + "step": 33389 + }, + { + "epoch": 2.72, + "learning_rate": 1.8611473272490225e-06, + "loss": 0.3743, + "step": 33390 + }, + { + "epoch": 2.72, + "learning_rate": 1.8606040851803563e-06, + "loss": 0.4084, + "step": 33391 + }, + { + "epoch": 2.72, + "learning_rate": 1.8600608431116908e-06, + "loss": 0.1307, + "step": 33392 + }, + { + "epoch": 2.72, + "learning_rate": 1.859517601043025e-06, + "loss": 0.2371, + "step": 33393 + }, + { + "epoch": 2.72, + "learning_rate": 1.8589743589743592e-06, + "loss": 0.1434, + "step": 33394 + }, + { + "epoch": 2.72, + "learning_rate": 1.8584311169056934e-06, + "loss": 0.2495, + "step": 33395 + }, + { + "epoch": 2.72, + "learning_rate": 1.8578878748370275e-06, + "loss": 0.3346, + "step": 33396 + }, + { + "epoch": 2.72, + "learning_rate": 1.8573446327683617e-06, + "loss": 0.1046, + "step": 33397 + }, + { + "epoch": 2.72, + "learning_rate": 1.856801390699696e-06, + "loss": 0.1077, + "step": 33398 + }, + { + "epoch": 2.72, + "learning_rate": 1.8562581486310302e-06, + "loss": 0.0784, + "step": 33399 + }, + { + "epoch": 2.72, + "learning_rate": 1.8557149065623644e-06, + "loss": 0.2498, + "step": 33400 + }, + { + "epoch": 2.72, + "learning_rate": 1.8551716644936984e-06, + "loss": 0.1792, + "step": 33401 + }, + { + "epoch": 2.72, + "learning_rate": 1.8546284224250326e-06, + "loss": 0.2973, + "step": 33402 + }, + { + "epoch": 2.72, + "learning_rate": 1.854085180356367e-06, + "loss": 0.1068, + "step": 33403 + }, + { + "epoch": 2.72, + "learning_rate": 1.8535419382877013e-06, + "loss": 0.2023, + "step": 33404 + }, + { + "epoch": 2.72, + "learning_rate": 1.8529986962190353e-06, + "loss": 0.1827, + "step": 33405 + }, + { + "epoch": 2.72, + "learning_rate": 1.8524554541503696e-06, + "loss": 0.1597, + "step": 33406 + }, + { + "epoch": 2.72, + "learning_rate": 1.8519122120817038e-06, + "loss": 0.4483, + "step": 33407 + }, + { + "epoch": 2.72, + "learning_rate": 1.851368970013038e-06, + "loss": 0.3911, + "step": 33408 + }, + { + "epoch": 2.72, + "learning_rate": 1.8508257279443722e-06, + "loss": 0.1866, + "step": 33409 + }, + { + "epoch": 2.72, + "learning_rate": 1.8502824858757063e-06, + "loss": 0.1522, + "step": 33410 + }, + { + "epoch": 2.72, + "learning_rate": 1.8497392438070405e-06, + "loss": 0.0783, + "step": 33411 + }, + { + "epoch": 2.72, + "learning_rate": 1.8491960017383747e-06, + "loss": 0.1345, + "step": 33412 + }, + { + "epoch": 2.72, + "learning_rate": 1.848652759669709e-06, + "loss": 0.1205, + "step": 33413 + }, + { + "epoch": 2.72, + "learning_rate": 1.8481095176010432e-06, + "loss": 0.0338, + "step": 33414 + }, + { + "epoch": 2.72, + "learning_rate": 1.8475662755323772e-06, + "loss": 0.2139, + "step": 33415 + }, + { + "epoch": 2.72, + "learning_rate": 1.8470230334637114e-06, + "loss": 0.3153, + "step": 33416 + }, + { + "epoch": 2.72, + "learning_rate": 1.8464797913950459e-06, + "loss": 0.2554, + "step": 33417 + }, + { + "epoch": 2.72, + "learning_rate": 1.8459365493263801e-06, + "loss": 0.0535, + "step": 33418 + }, + { + "epoch": 2.72, + "learning_rate": 1.8453933072577143e-06, + "loss": 0.1007, + "step": 33419 + }, + { + "epoch": 2.72, + "learning_rate": 1.8448500651890484e-06, + "loss": 0.3125, + "step": 33420 + }, + { + "epoch": 2.72, + "learning_rate": 1.8443068231203826e-06, + "loss": 0.1864, + "step": 33421 + }, + { + "epoch": 2.72, + "learning_rate": 1.8437635810517168e-06, + "loss": 0.2778, + "step": 33422 + }, + { + "epoch": 2.72, + "learning_rate": 1.843220338983051e-06, + "loss": 0.0603, + "step": 33423 + }, + { + "epoch": 2.72, + "learning_rate": 1.842677096914385e-06, + "loss": 0.3701, + "step": 33424 + }, + { + "epoch": 2.72, + "learning_rate": 1.8421338548457193e-06, + "loss": 0.2226, + "step": 33425 + }, + { + "epoch": 2.72, + "learning_rate": 1.8415906127770535e-06, + "loss": 0.2133, + "step": 33426 + }, + { + "epoch": 2.72, + "learning_rate": 1.8410473707083878e-06, + "loss": 0.3452, + "step": 33427 + }, + { + "epoch": 2.72, + "learning_rate": 1.8405041286397222e-06, + "loss": 0.2051, + "step": 33428 + }, + { + "epoch": 2.72, + "learning_rate": 1.839960886571056e-06, + "loss": 0.1435, + "step": 33429 + }, + { + "epoch": 2.72, + "learning_rate": 1.8394176445023905e-06, + "loss": 0.1038, + "step": 33430 + }, + { + "epoch": 2.72, + "learning_rate": 1.8388744024337247e-06, + "loss": 0.153, + "step": 33431 + }, + { + "epoch": 2.72, + "learning_rate": 1.838331160365059e-06, + "loss": 0.2662, + "step": 33432 + }, + { + "epoch": 2.72, + "learning_rate": 1.8377879182963931e-06, + "loss": 0.0654, + "step": 33433 + }, + { + "epoch": 2.72, + "learning_rate": 1.8372446762277272e-06, + "loss": 0.221, + "step": 33434 + }, + { + "epoch": 2.72, + "learning_rate": 1.8367014341590614e-06, + "loss": 0.3045, + "step": 33435 + }, + { + "epoch": 2.72, + "learning_rate": 1.8361581920903956e-06, + "loss": 0.1749, + "step": 33436 + }, + { + "epoch": 2.72, + "learning_rate": 1.8356149500217299e-06, + "loss": 0.1831, + "step": 33437 + }, + { + "epoch": 2.72, + "learning_rate": 1.835071707953064e-06, + "loss": 0.3028, + "step": 33438 + }, + { + "epoch": 2.72, + "learning_rate": 1.834528465884398e-06, + "loss": 0.2045, + "step": 33439 + }, + { + "epoch": 2.72, + "learning_rate": 1.8339852238157323e-06, + "loss": 0.2216, + "step": 33440 + }, + { + "epoch": 2.72, + "learning_rate": 1.8334419817470666e-06, + "loss": 0.2698, + "step": 33441 + }, + { + "epoch": 2.73, + "learning_rate": 1.832898739678401e-06, + "loss": 0.1701, + "step": 33442 + }, + { + "epoch": 2.73, + "learning_rate": 1.8323554976097348e-06, + "loss": 0.1808, + "step": 33443 + }, + { + "epoch": 2.73, + "learning_rate": 1.8318122555410693e-06, + "loss": 0.3245, + "step": 33444 + }, + { + "epoch": 2.73, + "learning_rate": 1.8312690134724035e-06, + "loss": 0.0358, + "step": 33445 + }, + { + "epoch": 2.73, + "learning_rate": 1.8307257714037377e-06, + "loss": 0.0765, + "step": 33446 + }, + { + "epoch": 2.73, + "learning_rate": 1.830182529335072e-06, + "loss": 0.2191, + "step": 33447 + }, + { + "epoch": 2.73, + "learning_rate": 1.829639287266406e-06, + "loss": 0.2236, + "step": 33448 + }, + { + "epoch": 2.73, + "learning_rate": 1.8290960451977402e-06, + "loss": 0.4016, + "step": 33449 + }, + { + "epoch": 2.73, + "learning_rate": 1.8285528031290744e-06, + "loss": 0.1651, + "step": 33450 + }, + { + "epoch": 2.73, + "learning_rate": 1.8280095610604087e-06, + "loss": 0.0907, + "step": 33451 + }, + { + "epoch": 2.73, + "learning_rate": 1.8274663189917429e-06, + "loss": 0.3502, + "step": 33452 + }, + { + "epoch": 2.73, + "learning_rate": 1.826923076923077e-06, + "loss": 0.1966, + "step": 33453 + }, + { + "epoch": 2.73, + "learning_rate": 1.8263798348544111e-06, + "loss": 0.1838, + "step": 33454 + }, + { + "epoch": 2.73, + "learning_rate": 1.8258365927857456e-06, + "loss": 0.2107, + "step": 33455 + }, + { + "epoch": 2.73, + "learning_rate": 1.8252933507170798e-06, + "loss": 0.5682, + "step": 33456 + }, + { + "epoch": 2.73, + "learning_rate": 1.824750108648414e-06, + "loss": 0.2311, + "step": 33457 + }, + { + "epoch": 2.73, + "learning_rate": 1.824206866579748e-06, + "loss": 0.3245, + "step": 33458 + }, + { + "epoch": 2.73, + "learning_rate": 1.8236636245110823e-06, + "loss": 0.297, + "step": 33459 + }, + { + "epoch": 2.73, + "learning_rate": 1.8231203824424165e-06, + "loss": 0.0604, + "step": 33460 + }, + { + "epoch": 2.73, + "learning_rate": 1.8225771403737508e-06, + "loss": 0.2279, + "step": 33461 + }, + { + "epoch": 2.73, + "learning_rate": 1.8220338983050848e-06, + "loss": 0.1214, + "step": 33462 + }, + { + "epoch": 2.73, + "learning_rate": 1.821490656236419e-06, + "loss": 0.1536, + "step": 33463 + }, + { + "epoch": 2.73, + "learning_rate": 1.8209474141677532e-06, + "loss": 0.5403, + "step": 33464 + }, + { + "epoch": 2.73, + "learning_rate": 1.8204041720990875e-06, + "loss": 0.4263, + "step": 33465 + }, + { + "epoch": 2.73, + "learning_rate": 1.819860930030422e-06, + "loss": 0.1201, + "step": 33466 + }, + { + "epoch": 2.73, + "learning_rate": 1.8193176879617557e-06, + "loss": 0.5184, + "step": 33467 + }, + { + "epoch": 2.73, + "learning_rate": 1.81877444589309e-06, + "loss": 0.1008, + "step": 33468 + }, + { + "epoch": 2.73, + "learning_rate": 1.8182312038244244e-06, + "loss": 0.0933, + "step": 33469 + }, + { + "epoch": 2.73, + "learning_rate": 1.8176879617557586e-06, + "loss": 0.1079, + "step": 33470 + }, + { + "epoch": 2.73, + "learning_rate": 1.8171447196870928e-06, + "loss": 0.2258, + "step": 33471 + }, + { + "epoch": 2.73, + "learning_rate": 1.8166014776184269e-06, + "loss": 0.3968, + "step": 33472 + }, + { + "epoch": 2.73, + "learning_rate": 1.816058235549761e-06, + "loss": 0.2987, + "step": 33473 + }, + { + "epoch": 2.73, + "learning_rate": 1.8155149934810953e-06, + "loss": 0.0807, + "step": 33474 + }, + { + "epoch": 2.73, + "learning_rate": 1.8149717514124296e-06, + "loss": 0.1758, + "step": 33475 + }, + { + "epoch": 2.73, + "learning_rate": 1.8144285093437638e-06, + "loss": 0.384, + "step": 33476 + }, + { + "epoch": 2.73, + "learning_rate": 1.8138852672750978e-06, + "loss": 0.1747, + "step": 33477 + }, + { + "epoch": 2.73, + "learning_rate": 1.813342025206432e-06, + "loss": 0.205, + "step": 33478 + }, + { + "epoch": 2.73, + "learning_rate": 1.8127987831377663e-06, + "loss": 0.2672, + "step": 33479 + }, + { + "epoch": 2.73, + "learning_rate": 1.8122555410691007e-06, + "loss": 0.1596, + "step": 33480 + }, + { + "epoch": 2.73, + "learning_rate": 1.8117122990004345e-06, + "loss": 0.4745, + "step": 33481 + }, + { + "epoch": 2.73, + "learning_rate": 1.811169056931769e-06, + "loss": 0.2015, + "step": 33482 + }, + { + "epoch": 2.73, + "learning_rate": 1.8106258148631032e-06, + "loss": 0.1457, + "step": 33483 + }, + { + "epoch": 2.73, + "learning_rate": 1.8100825727944374e-06, + "loss": 0.248, + "step": 33484 + }, + { + "epoch": 2.73, + "learning_rate": 1.8095393307257717e-06, + "loss": 0.1255, + "step": 33485 + }, + { + "epoch": 2.73, + "learning_rate": 1.8089960886571057e-06, + "loss": 0.2672, + "step": 33486 + }, + { + "epoch": 2.73, + "learning_rate": 1.80845284658844e-06, + "loss": 0.4497, + "step": 33487 + }, + { + "epoch": 2.73, + "learning_rate": 1.8079096045197741e-06, + "loss": 0.4711, + "step": 33488 + }, + { + "epoch": 2.73, + "learning_rate": 1.8073663624511084e-06, + "loss": 0.2489, + "step": 33489 + }, + { + "epoch": 2.73, + "learning_rate": 1.8068231203824426e-06, + "loss": 0.2861, + "step": 33490 + }, + { + "epoch": 2.73, + "learning_rate": 1.8062798783137766e-06, + "loss": 0.1922, + "step": 33491 + }, + { + "epoch": 2.73, + "learning_rate": 1.8057366362451108e-06, + "loss": 0.1011, + "step": 33492 + }, + { + "epoch": 2.73, + "learning_rate": 1.8051933941764453e-06, + "loss": 0.2118, + "step": 33493 + }, + { + "epoch": 2.73, + "learning_rate": 1.8046501521077795e-06, + "loss": 0.4629, + "step": 33494 + }, + { + "epoch": 2.73, + "learning_rate": 1.8041069100391137e-06, + "loss": 0.1213, + "step": 33495 + }, + { + "epoch": 2.73, + "learning_rate": 1.8035636679704478e-06, + "loss": 0.2253, + "step": 33496 + }, + { + "epoch": 2.73, + "learning_rate": 1.803020425901782e-06, + "loss": 0.124, + "step": 33497 + }, + { + "epoch": 2.73, + "learning_rate": 1.8024771838331162e-06, + "loss": 0.1313, + "step": 33498 + }, + { + "epoch": 2.73, + "learning_rate": 1.8019339417644505e-06, + "loss": 0.1317, + "step": 33499 + }, + { + "epoch": 2.73, + "learning_rate": 1.8013906996957845e-06, + "loss": 0.136, + "step": 33500 + }, + { + "epoch": 2.73, + "eval_accuracy": 0.8437086092715231, + "eval_loss": 0.4965471625328064, + "eval_runtime": 22.3142, + "eval_samples_per_second": 439.855, + "eval_steps_per_second": 3.451, + "step": 33500 + }, + { + "epoch": 2.73, + "learning_rate": 1.8008474576271187e-06, + "loss": 0.3741, + "step": 33501 + }, + { + "epoch": 2.73, + "learning_rate": 1.800304215558453e-06, + "loss": 0.1517, + "step": 33502 + }, + { + "epoch": 2.73, + "learning_rate": 1.7997609734897872e-06, + "loss": 0.212, + "step": 33503 + }, + { + "epoch": 2.73, + "learning_rate": 1.7992177314211214e-06, + "loss": 0.1216, + "step": 33504 + }, + { + "epoch": 2.73, + "learning_rate": 1.7986744893524554e-06, + "loss": 0.1664, + "step": 33505 + }, + { + "epoch": 2.73, + "learning_rate": 1.7981312472837896e-06, + "loss": 0.3496, + "step": 33506 + }, + { + "epoch": 2.73, + "learning_rate": 1.797588005215124e-06, + "loss": 0.0854, + "step": 33507 + }, + { + "epoch": 2.73, + "learning_rate": 1.7970447631464583e-06, + "loss": 0.1978, + "step": 33508 + }, + { + "epoch": 2.73, + "learning_rate": 1.7965015210777925e-06, + "loss": 0.1427, + "step": 33509 + }, + { + "epoch": 2.73, + "learning_rate": 1.7959582790091266e-06, + "loss": 0.5064, + "step": 33510 + }, + { + "epoch": 2.73, + "learning_rate": 1.7954150369404608e-06, + "loss": 0.1446, + "step": 33511 + }, + { + "epoch": 2.73, + "learning_rate": 1.794871794871795e-06, + "loss": 0.2252, + "step": 33512 + }, + { + "epoch": 2.73, + "learning_rate": 1.7943285528031293e-06, + "loss": 0.4942, + "step": 33513 + }, + { + "epoch": 2.73, + "learning_rate": 1.7937853107344635e-06, + "loss": 0.1744, + "step": 33514 + }, + { + "epoch": 2.73, + "learning_rate": 1.7932420686657975e-06, + "loss": 0.0469, + "step": 33515 + }, + { + "epoch": 2.73, + "learning_rate": 1.7926988265971317e-06, + "loss": 0.1108, + "step": 33516 + }, + { + "epoch": 2.73, + "learning_rate": 1.792155584528466e-06, + "loss": 0.199, + "step": 33517 + }, + { + "epoch": 2.73, + "learning_rate": 1.7916123424598004e-06, + "loss": 0.4116, + "step": 33518 + }, + { + "epoch": 2.73, + "learning_rate": 1.7910691003911346e-06, + "loss": 0.1414, + "step": 33519 + }, + { + "epoch": 2.73, + "learning_rate": 1.7905258583224687e-06, + "loss": 0.1977, + "step": 33520 + }, + { + "epoch": 2.73, + "learning_rate": 1.7899826162538029e-06, + "loss": 0.3356, + "step": 33521 + }, + { + "epoch": 2.73, + "learning_rate": 1.7894393741851371e-06, + "loss": 0.2587, + "step": 33522 + }, + { + "epoch": 2.73, + "learning_rate": 1.7888961321164714e-06, + "loss": 0.0723, + "step": 33523 + }, + { + "epoch": 2.73, + "learning_rate": 1.7883528900478054e-06, + "loss": 0.2914, + "step": 33524 + }, + { + "epoch": 2.73, + "learning_rate": 1.7878096479791396e-06, + "loss": 0.2319, + "step": 33525 + }, + { + "epoch": 2.73, + "learning_rate": 1.7872664059104738e-06, + "loss": 0.3337, + "step": 33526 + }, + { + "epoch": 2.73, + "learning_rate": 1.786723163841808e-06, + "loss": 0.3992, + "step": 33527 + }, + { + "epoch": 2.73, + "learning_rate": 1.7861799217731423e-06, + "loss": 0.2907, + "step": 33528 + }, + { + "epoch": 2.73, + "learning_rate": 1.7856366797044763e-06, + "loss": 0.3459, + "step": 33529 + }, + { + "epoch": 2.73, + "learning_rate": 1.7850934376358105e-06, + "loss": 0.3128, + "step": 33530 + }, + { + "epoch": 2.73, + "learning_rate": 1.7845501955671448e-06, + "loss": 0.3094, + "step": 33531 + }, + { + "epoch": 2.73, + "learning_rate": 1.7840069534984792e-06, + "loss": 0.1265, + "step": 33532 + }, + { + "epoch": 2.73, + "learning_rate": 1.7834637114298134e-06, + "loss": 0.2767, + "step": 33533 + }, + { + "epoch": 2.73, + "learning_rate": 1.7829204693611475e-06, + "loss": 0.3523, + "step": 33534 + }, + { + "epoch": 2.73, + "learning_rate": 1.7823772272924817e-06, + "loss": 0.2344, + "step": 33535 + }, + { + "epoch": 2.73, + "learning_rate": 1.781833985223816e-06, + "loss": 0.152, + "step": 33536 + }, + { + "epoch": 2.73, + "learning_rate": 1.7812907431551502e-06, + "loss": 0.106, + "step": 33537 + }, + { + "epoch": 2.73, + "learning_rate": 1.7807475010864844e-06, + "loss": 0.1597, + "step": 33538 + }, + { + "epoch": 2.73, + "learning_rate": 1.7802042590178184e-06, + "loss": 0.1844, + "step": 33539 + }, + { + "epoch": 2.73, + "learning_rate": 1.7796610169491526e-06, + "loss": 0.3135, + "step": 33540 + }, + { + "epoch": 2.73, + "learning_rate": 1.7791177748804869e-06, + "loss": 0.2132, + "step": 33541 + }, + { + "epoch": 2.73, + "learning_rate": 1.778574532811821e-06, + "loss": 0.1483, + "step": 33542 + }, + { + "epoch": 2.73, + "learning_rate": 1.7780312907431551e-06, + "loss": 0.1147, + "step": 33543 + }, + { + "epoch": 2.73, + "learning_rate": 1.7774880486744893e-06, + "loss": 0.2748, + "step": 33544 + }, + { + "epoch": 2.73, + "learning_rate": 1.7769448066058238e-06, + "loss": 0.2162, + "step": 33545 + }, + { + "epoch": 2.73, + "learning_rate": 1.776401564537158e-06, + "loss": 0.1135, + "step": 33546 + }, + { + "epoch": 2.73, + "learning_rate": 1.7758583224684923e-06, + "loss": 0.095, + "step": 33547 + }, + { + "epoch": 2.73, + "learning_rate": 1.7753150803998263e-06, + "loss": 0.2195, + "step": 33548 + }, + { + "epoch": 2.73, + "learning_rate": 1.7747718383311605e-06, + "loss": 0.2926, + "step": 33549 + }, + { + "epoch": 2.73, + "learning_rate": 1.7742285962624947e-06, + "loss": 0.1954, + "step": 33550 + }, + { + "epoch": 2.73, + "learning_rate": 1.773685354193829e-06, + "loss": 0.1749, + "step": 33551 + }, + { + "epoch": 2.73, + "learning_rate": 1.7731421121251632e-06, + "loss": 0.1031, + "step": 33552 + }, + { + "epoch": 2.73, + "learning_rate": 1.7725988700564972e-06, + "loss": 0.1211, + "step": 33553 + }, + { + "epoch": 2.73, + "learning_rate": 1.7720556279878314e-06, + "loss": 0.2306, + "step": 33554 + }, + { + "epoch": 2.73, + "learning_rate": 1.7715123859191657e-06, + "loss": 0.3763, + "step": 33555 + }, + { + "epoch": 2.73, + "learning_rate": 1.7709691438505e-06, + "loss": 0.2884, + "step": 33556 + }, + { + "epoch": 2.73, + "learning_rate": 1.7704259017818343e-06, + "loss": 0.2101, + "step": 33557 + }, + { + "epoch": 2.73, + "learning_rate": 1.7698826597131682e-06, + "loss": 0.4147, + "step": 33558 + }, + { + "epoch": 2.73, + "learning_rate": 1.7693394176445026e-06, + "loss": 0.2903, + "step": 33559 + }, + { + "epoch": 2.73, + "learning_rate": 1.7687961755758368e-06, + "loss": 0.2187, + "step": 33560 + }, + { + "epoch": 2.73, + "learning_rate": 1.768252933507171e-06, + "loss": 0.0847, + "step": 33561 + }, + { + "epoch": 2.73, + "learning_rate": 1.767709691438505e-06, + "loss": 0.2878, + "step": 33562 + }, + { + "epoch": 2.73, + "learning_rate": 1.7671664493698393e-06, + "loss": 0.236, + "step": 33563 + }, + { + "epoch": 2.74, + "learning_rate": 1.7666232073011735e-06, + "loss": 0.2448, + "step": 33564 + }, + { + "epoch": 2.74, + "learning_rate": 1.7660799652325078e-06, + "loss": 0.3054, + "step": 33565 + }, + { + "epoch": 2.74, + "learning_rate": 1.765536723163842e-06, + "loss": 0.3135, + "step": 33566 + }, + { + "epoch": 2.74, + "learning_rate": 1.764993481095176e-06, + "loss": 0.0535, + "step": 33567 + }, + { + "epoch": 2.74, + "learning_rate": 1.7644502390265102e-06, + "loss": 0.1145, + "step": 33568 + }, + { + "epoch": 2.74, + "learning_rate": 1.7639069969578445e-06, + "loss": 0.3235, + "step": 33569 + }, + { + "epoch": 2.74, + "learning_rate": 1.763363754889179e-06, + "loss": 0.1126, + "step": 33570 + }, + { + "epoch": 2.74, + "learning_rate": 1.7628205128205131e-06, + "loss": 0.1823, + "step": 33571 + }, + { + "epoch": 2.74, + "learning_rate": 1.7622772707518472e-06, + "loss": 0.0387, + "step": 33572 + }, + { + "epoch": 2.74, + "learning_rate": 1.7617340286831814e-06, + "loss": 0.3152, + "step": 33573 + }, + { + "epoch": 2.74, + "learning_rate": 1.7611907866145156e-06, + "loss": 0.3502, + "step": 33574 + }, + { + "epoch": 2.74, + "learning_rate": 1.7606475445458499e-06, + "loss": 0.3169, + "step": 33575 + }, + { + "epoch": 2.74, + "learning_rate": 1.760104302477184e-06, + "loss": 0.2333, + "step": 33576 + }, + { + "epoch": 2.74, + "learning_rate": 1.7595610604085181e-06, + "loss": 0.1695, + "step": 33577 + }, + { + "epoch": 2.74, + "learning_rate": 1.7590178183398523e-06, + "loss": 0.1374, + "step": 33578 + }, + { + "epoch": 2.74, + "learning_rate": 1.7584745762711866e-06, + "loss": 0.3758, + "step": 33579 + }, + { + "epoch": 2.74, + "learning_rate": 1.7579313342025208e-06, + "loss": 0.1572, + "step": 33580 + }, + { + "epoch": 2.74, + "learning_rate": 1.7573880921338548e-06, + "loss": 0.2701, + "step": 33581 + }, + { + "epoch": 2.74, + "learning_rate": 1.756844850065189e-06, + "loss": 0.2581, + "step": 33582 + }, + { + "epoch": 2.74, + "learning_rate": 1.7563016079965233e-06, + "loss": 0.3369, + "step": 33583 + }, + { + "epoch": 2.74, + "learning_rate": 1.7557583659278577e-06, + "loss": 0.2514, + "step": 33584 + }, + { + "epoch": 2.74, + "learning_rate": 1.755215123859192e-06, + "loss": 0.1835, + "step": 33585 + }, + { + "epoch": 2.74, + "learning_rate": 1.754671881790526e-06, + "loss": 0.0798, + "step": 33586 + }, + { + "epoch": 2.74, + "learning_rate": 1.7541286397218602e-06, + "loss": 0.5012, + "step": 33587 + }, + { + "epoch": 2.74, + "learning_rate": 1.7535853976531944e-06, + "loss": 0.3836, + "step": 33588 + }, + { + "epoch": 2.74, + "learning_rate": 1.7530421555845287e-06, + "loss": 0.1418, + "step": 33589 + }, + { + "epoch": 2.74, + "learning_rate": 1.752498913515863e-06, + "loss": 0.1618, + "step": 33590 + }, + { + "epoch": 2.74, + "learning_rate": 1.751955671447197e-06, + "loss": 0.135, + "step": 33591 + }, + { + "epoch": 2.74, + "learning_rate": 1.7514124293785311e-06, + "loss": 0.1857, + "step": 33592 + }, + { + "epoch": 2.74, + "learning_rate": 1.7508691873098654e-06, + "loss": 0.3094, + "step": 33593 + }, + { + "epoch": 2.74, + "learning_rate": 1.7503259452411996e-06, + "loss": 0.0851, + "step": 33594 + }, + { + "epoch": 2.74, + "learning_rate": 1.749782703172534e-06, + "loss": 0.2129, + "step": 33595 + }, + { + "epoch": 2.74, + "learning_rate": 1.7492394611038679e-06, + "loss": 0.3622, + "step": 33596 + }, + { + "epoch": 2.74, + "learning_rate": 1.7486962190352023e-06, + "loss": 0.1623, + "step": 33597 + }, + { + "epoch": 2.74, + "learning_rate": 1.7481529769665365e-06, + "loss": 0.1947, + "step": 33598 + }, + { + "epoch": 2.74, + "learning_rate": 1.7476097348978708e-06, + "loss": 0.4619, + "step": 33599 + }, + { + "epoch": 2.74, + "learning_rate": 1.7470664928292048e-06, + "loss": 0.1821, + "step": 33600 + }, + { + "epoch": 2.74, + "learning_rate": 1.746523250760539e-06, + "loss": 0.1397, + "step": 33601 + }, + { + "epoch": 2.74, + "learning_rate": 1.7459800086918732e-06, + "loss": 0.1837, + "step": 33602 + }, + { + "epoch": 2.74, + "learning_rate": 1.7454367666232075e-06, + "loss": 0.282, + "step": 33603 + }, + { + "epoch": 2.74, + "learning_rate": 1.7448935245545417e-06, + "loss": 0.3455, + "step": 33604 + }, + { + "epoch": 2.74, + "learning_rate": 1.7443502824858757e-06, + "loss": 0.3164, + "step": 33605 + }, + { + "epoch": 2.74, + "learning_rate": 1.74380704041721e-06, + "loss": 0.317, + "step": 33606 + }, + { + "epoch": 2.74, + "learning_rate": 1.7432637983485442e-06, + "loss": 0.2225, + "step": 33607 + }, + { + "epoch": 2.74, + "learning_rate": 1.7427205562798786e-06, + "loss": 0.2318, + "step": 33608 + }, + { + "epoch": 2.74, + "learning_rate": 1.7421773142112129e-06, + "loss": 0.0747, + "step": 33609 + }, + { + "epoch": 2.74, + "learning_rate": 1.7416340721425467e-06, + "loss": 0.1306, + "step": 33610 + }, + { + "epoch": 2.74, + "learning_rate": 1.741090830073881e-06, + "loss": 0.1631, + "step": 33611 + }, + { + "epoch": 2.74, + "learning_rate": 1.7405475880052153e-06, + "loss": 0.4396, + "step": 33612 + }, + { + "epoch": 2.74, + "learning_rate": 1.7400043459365496e-06, + "loss": 0.3605, + "step": 33613 + }, + { + "epoch": 2.74, + "learning_rate": 1.7394611038678838e-06, + "loss": 0.2535, + "step": 33614 + }, + { + "epoch": 2.74, + "learning_rate": 1.7389178617992178e-06, + "loss": 0.266, + "step": 33615 + }, + { + "epoch": 2.74, + "learning_rate": 1.738374619730552e-06, + "loss": 0.1929, + "step": 33616 + }, + { + "epoch": 2.74, + "learning_rate": 1.7378313776618863e-06, + "loss": 0.2762, + "step": 33617 + }, + { + "epoch": 2.74, + "learning_rate": 1.7372881355932205e-06, + "loss": 0.1175, + "step": 33618 + }, + { + "epoch": 2.74, + "learning_rate": 1.7367448935245545e-06, + "loss": 0.1029, + "step": 33619 + }, + { + "epoch": 2.74, + "learning_rate": 1.7362016514558888e-06, + "loss": 0.1356, + "step": 33620 + }, + { + "epoch": 2.74, + "learning_rate": 1.735658409387223e-06, + "loss": 0.1517, + "step": 33621 + }, + { + "epoch": 2.74, + "learning_rate": 1.7351151673185574e-06, + "loss": 0.3762, + "step": 33622 + }, + { + "epoch": 2.74, + "learning_rate": 1.7345719252498917e-06, + "loss": 0.0754, + "step": 33623 + }, + { + "epoch": 2.74, + "learning_rate": 1.7340286831812257e-06, + "loss": 0.2561, + "step": 33624 + }, + { + "epoch": 2.74, + "learning_rate": 1.73348544111256e-06, + "loss": 0.2, + "step": 33625 + }, + { + "epoch": 2.74, + "learning_rate": 1.7329421990438941e-06, + "loss": 0.0815, + "step": 33626 + }, + { + "epoch": 2.74, + "learning_rate": 1.7323989569752284e-06, + "loss": 0.0951, + "step": 33627 + }, + { + "epoch": 2.74, + "learning_rate": 1.7318557149065626e-06, + "loss": 0.1725, + "step": 33628 + }, + { + "epoch": 2.74, + "learning_rate": 1.7313124728378966e-06, + "loss": 0.5191, + "step": 33629 + }, + { + "epoch": 2.74, + "learning_rate": 1.7307692307692308e-06, + "loss": 0.2406, + "step": 33630 + }, + { + "epoch": 2.74, + "learning_rate": 1.730225988700565e-06, + "loss": 0.1046, + "step": 33631 + }, + { + "epoch": 2.74, + "learning_rate": 1.7296827466318993e-06, + "loss": 0.0801, + "step": 33632 + }, + { + "epoch": 2.74, + "learning_rate": 1.7291395045632337e-06, + "loss": 0.0615, + "step": 33633 + }, + { + "epoch": 2.74, + "learning_rate": 1.7285962624945676e-06, + "loss": 0.2155, + "step": 33634 + }, + { + "epoch": 2.74, + "learning_rate": 1.728053020425902e-06, + "loss": 0.2652, + "step": 33635 + }, + { + "epoch": 2.74, + "learning_rate": 1.7275097783572362e-06, + "loss": 0.2805, + "step": 33636 + }, + { + "epoch": 2.74, + "learning_rate": 1.7269665362885705e-06, + "loss": 0.2235, + "step": 33637 + }, + { + "epoch": 2.74, + "learning_rate": 1.7264232942199045e-06, + "loss": 0.3185, + "step": 33638 + }, + { + "epoch": 2.74, + "learning_rate": 1.7258800521512387e-06, + "loss": 0.1263, + "step": 33639 + }, + { + "epoch": 2.74, + "learning_rate": 1.725336810082573e-06, + "loss": 0.2795, + "step": 33640 + }, + { + "epoch": 2.74, + "learning_rate": 1.7247935680139072e-06, + "loss": 0.2422, + "step": 33641 + }, + { + "epoch": 2.74, + "learning_rate": 1.7242503259452414e-06, + "loss": 0.1592, + "step": 33642 + }, + { + "epoch": 2.74, + "learning_rate": 1.7237070838765754e-06, + "loss": 0.2027, + "step": 33643 + }, + { + "epoch": 2.74, + "learning_rate": 1.7231638418079096e-06, + "loss": 0.1965, + "step": 33644 + }, + { + "epoch": 2.74, + "learning_rate": 1.7226205997392439e-06, + "loss": 0.2175, + "step": 33645 + }, + { + "epoch": 2.74, + "learning_rate": 1.7220773576705781e-06, + "loss": 0.2431, + "step": 33646 + }, + { + "epoch": 2.74, + "learning_rate": 1.7215341156019126e-06, + "loss": 0.3605, + "step": 33647 + }, + { + "epoch": 2.74, + "learning_rate": 1.7209908735332464e-06, + "loss": 0.3381, + "step": 33648 + }, + { + "epoch": 2.74, + "learning_rate": 1.7204476314645808e-06, + "loss": 0.091, + "step": 33649 + }, + { + "epoch": 2.74, + "learning_rate": 1.719904389395915e-06, + "loss": 0.1024, + "step": 33650 + }, + { + "epoch": 2.74, + "learning_rate": 1.7193611473272493e-06, + "loss": 0.289, + "step": 33651 + }, + { + "epoch": 2.74, + "learning_rate": 1.7188179052585835e-06, + "loss": 0.0814, + "step": 33652 + }, + { + "epoch": 2.74, + "learning_rate": 1.7182746631899175e-06, + "loss": 0.4142, + "step": 33653 + }, + { + "epoch": 2.74, + "learning_rate": 1.7177314211212517e-06, + "loss": 0.2914, + "step": 33654 + }, + { + "epoch": 2.74, + "learning_rate": 1.717188179052586e-06, + "loss": 0.1995, + "step": 33655 + }, + { + "epoch": 2.74, + "learning_rate": 1.7166449369839202e-06, + "loss": 0.1397, + "step": 33656 + }, + { + "epoch": 2.74, + "learning_rate": 1.7161016949152542e-06, + "loss": 0.2715, + "step": 33657 + }, + { + "epoch": 2.74, + "learning_rate": 1.7155584528465885e-06, + "loss": 0.3232, + "step": 33658 + }, + { + "epoch": 2.74, + "learning_rate": 1.7150152107779227e-06, + "loss": 0.2783, + "step": 33659 + }, + { + "epoch": 2.74, + "learning_rate": 1.7144719687092571e-06, + "loss": 0.4023, + "step": 33660 + }, + { + "epoch": 2.74, + "learning_rate": 1.7139287266405914e-06, + "loss": 0.6183, + "step": 33661 + }, + { + "epoch": 2.74, + "learning_rate": 1.7133854845719254e-06, + "loss": 0.1062, + "step": 33662 + }, + { + "epoch": 2.74, + "learning_rate": 1.7128422425032596e-06, + "loss": 0.0808, + "step": 33663 + }, + { + "epoch": 2.74, + "learning_rate": 1.7122990004345938e-06, + "loss": 0.1785, + "step": 33664 + }, + { + "epoch": 2.74, + "learning_rate": 1.711755758365928e-06, + "loss": 0.121, + "step": 33665 + }, + { + "epoch": 2.74, + "learning_rate": 1.7112125162972623e-06, + "loss": 0.2117, + "step": 33666 + }, + { + "epoch": 2.74, + "learning_rate": 1.7106692742285963e-06, + "loss": 0.065, + "step": 33667 + }, + { + "epoch": 2.74, + "learning_rate": 1.7101260321599305e-06, + "loss": 0.1729, + "step": 33668 + }, + { + "epoch": 2.74, + "learning_rate": 1.7095827900912648e-06, + "loss": 0.3804, + "step": 33669 + }, + { + "epoch": 2.74, + "learning_rate": 1.709039548022599e-06, + "loss": 0.0804, + "step": 33670 + }, + { + "epoch": 2.74, + "learning_rate": 1.7084963059539332e-06, + "loss": 0.1785, + "step": 33671 + }, + { + "epoch": 2.74, + "learning_rate": 1.7079530638852673e-06, + "loss": 0.222, + "step": 33672 + }, + { + "epoch": 2.74, + "learning_rate": 1.7074098218166015e-06, + "loss": 0.2206, + "step": 33673 + }, + { + "epoch": 2.74, + "learning_rate": 1.706866579747936e-06, + "loss": 0.1382, + "step": 33674 + }, + { + "epoch": 2.74, + "learning_rate": 1.7063233376792702e-06, + "loss": 0.3043, + "step": 33675 + }, + { + "epoch": 2.74, + "learning_rate": 1.7057800956106042e-06, + "loss": 0.4469, + "step": 33676 + }, + { + "epoch": 2.74, + "learning_rate": 1.7052368535419384e-06, + "loss": 0.2353, + "step": 33677 + }, + { + "epoch": 2.74, + "learning_rate": 1.7046936114732726e-06, + "loss": 0.1337, + "step": 33678 + }, + { + "epoch": 2.74, + "learning_rate": 1.7041503694046069e-06, + "loss": 0.3373, + "step": 33679 + }, + { + "epoch": 2.74, + "learning_rate": 1.703607127335941e-06, + "loss": 0.0559, + "step": 33680 + }, + { + "epoch": 2.74, + "learning_rate": 1.7030638852672751e-06, + "loss": 0.2917, + "step": 33681 + }, + { + "epoch": 2.74, + "learning_rate": 1.7025206431986094e-06, + "loss": 0.1657, + "step": 33682 + }, + { + "epoch": 2.74, + "learning_rate": 1.7019774011299436e-06, + "loss": 0.1266, + "step": 33683 + }, + { + "epoch": 2.74, + "learning_rate": 1.7014341590612778e-06, + "loss": 0.1048, + "step": 33684 + }, + { + "epoch": 2.74, + "learning_rate": 1.7008909169926123e-06, + "loss": 0.0429, + "step": 33685 + }, + { + "epoch": 2.74, + "learning_rate": 1.700347674923946e-06, + "loss": 0.1895, + "step": 33686 + }, + { + "epoch": 2.75, + "learning_rate": 1.6998044328552805e-06, + "loss": 0.3509, + "step": 33687 + }, + { + "epoch": 2.75, + "learning_rate": 1.6992611907866147e-06, + "loss": 0.2643, + "step": 33688 + }, + { + "epoch": 2.75, + "learning_rate": 1.698717948717949e-06, + "loss": 0.27, + "step": 33689 + }, + { + "epoch": 2.75, + "learning_rate": 1.6981747066492832e-06, + "loss": 0.263, + "step": 33690 + }, + { + "epoch": 2.75, + "learning_rate": 1.6976314645806172e-06, + "loss": 0.2515, + "step": 33691 + }, + { + "epoch": 2.75, + "learning_rate": 1.6970882225119514e-06, + "loss": 0.4319, + "step": 33692 + }, + { + "epoch": 2.75, + "learning_rate": 1.6965449804432857e-06, + "loss": 0.1739, + "step": 33693 + }, + { + "epoch": 2.75, + "learning_rate": 1.69600173837462e-06, + "loss": 0.0441, + "step": 33694 + }, + { + "epoch": 2.75, + "learning_rate": 1.695458496305954e-06, + "loss": 0.3495, + "step": 33695 + }, + { + "epoch": 2.75, + "learning_rate": 1.6949152542372882e-06, + "loss": 0.3277, + "step": 33696 + }, + { + "epoch": 2.75, + "learning_rate": 1.6943720121686224e-06, + "loss": 0.0908, + "step": 33697 + }, + { + "epoch": 2.75, + "learning_rate": 1.6938287700999566e-06, + "loss": 0.2791, + "step": 33698 + }, + { + "epoch": 2.75, + "learning_rate": 1.693285528031291e-06, + "loss": 0.168, + "step": 33699 + }, + { + "epoch": 2.75, + "learning_rate": 1.6927422859626249e-06, + "loss": 0.136, + "step": 33700 + }, + { + "epoch": 2.75, + "learning_rate": 1.6921990438939593e-06, + "loss": 0.3519, + "step": 33701 + }, + { + "epoch": 2.75, + "learning_rate": 1.6916558018252935e-06, + "loss": 0.1646, + "step": 33702 + }, + { + "epoch": 2.75, + "learning_rate": 1.6911125597566278e-06, + "loss": 0.1021, + "step": 33703 + }, + { + "epoch": 2.75, + "learning_rate": 1.690569317687962e-06, + "loss": 0.0939, + "step": 33704 + }, + { + "epoch": 2.75, + "learning_rate": 1.690026075619296e-06, + "loss": 0.4941, + "step": 33705 + }, + { + "epoch": 2.75, + "learning_rate": 1.6894828335506302e-06, + "loss": 0.4911, + "step": 33706 + }, + { + "epoch": 2.75, + "learning_rate": 1.6889395914819645e-06, + "loss": 0.3275, + "step": 33707 + }, + { + "epoch": 2.75, + "learning_rate": 1.6883963494132987e-06, + "loss": 0.1369, + "step": 33708 + }, + { + "epoch": 2.75, + "learning_rate": 1.687853107344633e-06, + "loss": 0.2167, + "step": 33709 + }, + { + "epoch": 2.75, + "learning_rate": 1.687309865275967e-06, + "loss": 0.4715, + "step": 33710 + }, + { + "epoch": 2.75, + "learning_rate": 1.6867666232073012e-06, + "loss": 0.1057, + "step": 33711 + }, + { + "epoch": 2.75, + "learning_rate": 1.6862233811386356e-06, + "loss": 0.1046, + "step": 33712 + }, + { + "epoch": 2.75, + "learning_rate": 1.6856801390699699e-06, + "loss": 0.0629, + "step": 33713 + }, + { + "epoch": 2.75, + "learning_rate": 1.6851368970013039e-06, + "loss": 0.2488, + "step": 33714 + }, + { + "epoch": 2.75, + "learning_rate": 1.6845936549326381e-06, + "loss": 0.3018, + "step": 33715 + }, + { + "epoch": 2.75, + "learning_rate": 1.6840504128639723e-06, + "loss": 0.091, + "step": 33716 + }, + { + "epoch": 2.75, + "learning_rate": 1.6835071707953066e-06, + "loss": 0.1708, + "step": 33717 + }, + { + "epoch": 2.75, + "learning_rate": 1.6829639287266408e-06, + "loss": 0.0912, + "step": 33718 + }, + { + "epoch": 2.75, + "learning_rate": 1.6824206866579748e-06, + "loss": 0.1195, + "step": 33719 + }, + { + "epoch": 2.75, + "learning_rate": 1.681877444589309e-06, + "loss": 0.0937, + "step": 33720 + }, + { + "epoch": 2.75, + "learning_rate": 1.6813342025206433e-06, + "loss": 0.1549, + "step": 33721 + }, + { + "epoch": 2.75, + "learning_rate": 1.6807909604519775e-06, + "loss": 0.1977, + "step": 33722 + }, + { + "epoch": 2.75, + "learning_rate": 1.680247718383312e-06, + "loss": 0.101, + "step": 33723 + }, + { + "epoch": 2.75, + "learning_rate": 1.6797044763146458e-06, + "loss": 0.4002, + "step": 33724 + }, + { + "epoch": 2.75, + "learning_rate": 1.67916123424598e-06, + "loss": 0.4095, + "step": 33725 + }, + { + "epoch": 2.75, + "learning_rate": 1.6786179921773144e-06, + "loss": 0.168, + "step": 33726 + }, + { + "epoch": 2.75, + "learning_rate": 1.6780747501086487e-06, + "loss": 0.1086, + "step": 33727 + }, + { + "epoch": 2.75, + "learning_rate": 1.677531508039983e-06, + "loss": 0.2351, + "step": 33728 + }, + { + "epoch": 2.75, + "learning_rate": 1.676988265971317e-06, + "loss": 0.1731, + "step": 33729 + }, + { + "epoch": 2.75, + "learning_rate": 1.6764450239026511e-06, + "loss": 0.3157, + "step": 33730 + }, + { + "epoch": 2.75, + "learning_rate": 1.6759017818339854e-06, + "loss": 0.2923, + "step": 33731 + }, + { + "epoch": 2.75, + "learning_rate": 1.6753585397653196e-06, + "loss": 0.2624, + "step": 33732 + }, + { + "epoch": 2.75, + "learning_rate": 1.6748152976966536e-06, + "loss": 0.6223, + "step": 33733 + }, + { + "epoch": 2.75, + "learning_rate": 1.6742720556279879e-06, + "loss": 0.1388, + "step": 33734 + }, + { + "epoch": 2.75, + "learning_rate": 1.673728813559322e-06, + "loss": 0.1788, + "step": 33735 + }, + { + "epoch": 2.75, + "learning_rate": 1.6731855714906563e-06, + "loss": 0.1229, + "step": 33736 + }, + { + "epoch": 2.75, + "learning_rate": 1.6726423294219908e-06, + "loss": 0.0899, + "step": 33737 + }, + { + "epoch": 2.75, + "learning_rate": 1.6720990873533246e-06, + "loss": 0.3691, + "step": 33738 + }, + { + "epoch": 2.75, + "learning_rate": 1.671555845284659e-06, + "loss": 0.0996, + "step": 33739 + }, + { + "epoch": 2.75, + "learning_rate": 1.6710126032159932e-06, + "loss": 0.3695, + "step": 33740 + }, + { + "epoch": 2.75, + "learning_rate": 1.6704693611473275e-06, + "loss": 0.2671, + "step": 33741 + }, + { + "epoch": 2.75, + "learning_rate": 1.6699261190786617e-06, + "loss": 0.1572, + "step": 33742 + }, + { + "epoch": 2.75, + "learning_rate": 1.6693828770099957e-06, + "loss": 0.3202, + "step": 33743 + }, + { + "epoch": 2.75, + "learning_rate": 1.66883963494133e-06, + "loss": 0.0695, + "step": 33744 + }, + { + "epoch": 2.75, + "learning_rate": 1.6682963928726642e-06, + "loss": 0.3915, + "step": 33745 + }, + { + "epoch": 2.75, + "learning_rate": 1.6677531508039984e-06, + "loss": 0.1923, + "step": 33746 + }, + { + "epoch": 2.75, + "learning_rate": 1.6672099087353326e-06, + "loss": 0.1549, + "step": 33747 + }, + { + "epoch": 2.75, + "learning_rate": 1.6666666666666667e-06, + "loss": 0.2734, + "step": 33748 + }, + { + "epoch": 2.75, + "learning_rate": 1.6661234245980009e-06, + "loss": 0.1192, + "step": 33749 + }, + { + "epoch": 2.75, + "learning_rate": 1.6655801825293353e-06, + "loss": 0.4061, + "step": 33750 + }, + { + "epoch": 2.75, + "eval_accuracy": 0.8433010697911361, + "eval_loss": 0.4938463270664215, + "eval_runtime": 22.2906, + "eval_samples_per_second": 440.32, + "eval_steps_per_second": 3.454, + "step": 33750 + }, + { + "epoch": 2.75, + "learning_rate": 1.6650369404606696e-06, + "loss": 0.4309, + "step": 33751 + }, + { + "epoch": 2.75, + "learning_rate": 1.6644936983920034e-06, + "loss": 0.2611, + "step": 33752 + }, + { + "epoch": 2.75, + "learning_rate": 1.6639504563233378e-06, + "loss": 0.1288, + "step": 33753 + }, + { + "epoch": 2.75, + "learning_rate": 1.663407214254672e-06, + "loss": 0.4694, + "step": 33754 + }, + { + "epoch": 2.75, + "learning_rate": 1.6628639721860063e-06, + "loss": 0.3332, + "step": 33755 + }, + { + "epoch": 2.75, + "learning_rate": 1.6623207301173405e-06, + "loss": 0.1575, + "step": 33756 + }, + { + "epoch": 2.75, + "learning_rate": 1.6617774880486745e-06, + "loss": 0.2865, + "step": 33757 + }, + { + "epoch": 2.75, + "learning_rate": 1.6612342459800088e-06, + "loss": 0.2162, + "step": 33758 + }, + { + "epoch": 2.75, + "learning_rate": 1.660691003911343e-06, + "loss": 0.1586, + "step": 33759 + }, + { + "epoch": 2.75, + "learning_rate": 1.6601477618426772e-06, + "loss": 0.2364, + "step": 33760 + }, + { + "epoch": 2.75, + "learning_rate": 1.6596045197740114e-06, + "loss": 0.2986, + "step": 33761 + }, + { + "epoch": 2.75, + "learning_rate": 1.6590612777053455e-06, + "loss": 0.2893, + "step": 33762 + }, + { + "epoch": 2.75, + "learning_rate": 1.6585180356366797e-06, + "loss": 0.1892, + "step": 33763 + }, + { + "epoch": 2.75, + "learning_rate": 1.6579747935680141e-06, + "loss": 0.1643, + "step": 33764 + }, + { + "epoch": 2.75, + "learning_rate": 1.6574315514993484e-06, + "loss": 0.1477, + "step": 33765 + }, + { + "epoch": 2.75, + "learning_rate": 1.6568883094306826e-06, + "loss": 0.2015, + "step": 33766 + }, + { + "epoch": 2.75, + "learning_rate": 1.6563450673620166e-06, + "loss": 0.163, + "step": 33767 + }, + { + "epoch": 2.75, + "learning_rate": 1.6558018252933508e-06, + "loss": 0.2292, + "step": 33768 + }, + { + "epoch": 2.75, + "learning_rate": 1.655258583224685e-06, + "loss": 0.1579, + "step": 33769 + }, + { + "epoch": 2.75, + "learning_rate": 1.6547153411560193e-06, + "loss": 0.1828, + "step": 33770 + }, + { + "epoch": 2.75, + "learning_rate": 1.6541720990873533e-06, + "loss": 0.1754, + "step": 33771 + }, + { + "epoch": 2.75, + "learning_rate": 1.6536288570186876e-06, + "loss": 0.384, + "step": 33772 + }, + { + "epoch": 2.75, + "learning_rate": 1.6530856149500218e-06, + "loss": 0.1448, + "step": 33773 + }, + { + "epoch": 2.75, + "learning_rate": 1.652542372881356e-06, + "loss": 0.0317, + "step": 33774 + }, + { + "epoch": 2.75, + "learning_rate": 1.6519991308126905e-06, + "loss": 0.1988, + "step": 33775 + }, + { + "epoch": 2.75, + "learning_rate": 1.6514558887440243e-06, + "loss": 0.3602, + "step": 33776 + }, + { + "epoch": 2.75, + "learning_rate": 1.6509126466753587e-06, + "loss": 0.4737, + "step": 33777 + }, + { + "epoch": 2.75, + "learning_rate": 1.650369404606693e-06, + "loss": 0.2501, + "step": 33778 + }, + { + "epoch": 2.75, + "learning_rate": 1.6498261625380272e-06, + "loss": 0.3456, + "step": 33779 + }, + { + "epoch": 2.75, + "learning_rate": 1.6492829204693614e-06, + "loss": 0.2134, + "step": 33780 + }, + { + "epoch": 2.75, + "learning_rate": 1.6487396784006954e-06, + "loss": 0.1435, + "step": 33781 + }, + { + "epoch": 2.75, + "learning_rate": 1.6481964363320297e-06, + "loss": 0.1587, + "step": 33782 + }, + { + "epoch": 2.75, + "learning_rate": 1.6476531942633639e-06, + "loss": 0.0838, + "step": 33783 + }, + { + "epoch": 2.75, + "learning_rate": 1.6471099521946981e-06, + "loss": 0.0992, + "step": 33784 + }, + { + "epoch": 2.75, + "learning_rate": 1.6465667101260323e-06, + "loss": 0.1839, + "step": 33785 + }, + { + "epoch": 2.75, + "learning_rate": 1.6460234680573664e-06, + "loss": 0.3349, + "step": 33786 + }, + { + "epoch": 2.75, + "learning_rate": 1.6454802259887006e-06, + "loss": 0.1318, + "step": 33787 + }, + { + "epoch": 2.75, + "learning_rate": 1.6449369839200348e-06, + "loss": 0.1978, + "step": 33788 + }, + { + "epoch": 2.75, + "learning_rate": 1.6443937418513693e-06, + "loss": 0.1472, + "step": 33789 + }, + { + "epoch": 2.75, + "learning_rate": 1.643850499782703e-06, + "loss": 0.4009, + "step": 33790 + }, + { + "epoch": 2.75, + "learning_rate": 1.6433072577140375e-06, + "loss": 0.0866, + "step": 33791 + }, + { + "epoch": 2.75, + "learning_rate": 1.6427640156453717e-06, + "loss": 0.2441, + "step": 33792 + }, + { + "epoch": 2.75, + "learning_rate": 1.642220773576706e-06, + "loss": 0.3195, + "step": 33793 + }, + { + "epoch": 2.75, + "learning_rate": 1.6416775315080402e-06, + "loss": 0.2627, + "step": 33794 + }, + { + "epoch": 2.75, + "learning_rate": 1.6411342894393742e-06, + "loss": 0.2699, + "step": 33795 + }, + { + "epoch": 2.75, + "learning_rate": 1.6405910473707085e-06, + "loss": 0.3498, + "step": 33796 + }, + { + "epoch": 2.75, + "learning_rate": 1.6400478053020427e-06, + "loss": 0.3379, + "step": 33797 + }, + { + "epoch": 2.75, + "learning_rate": 1.639504563233377e-06, + "loss": 0.2661, + "step": 33798 + }, + { + "epoch": 2.75, + "learning_rate": 1.6389613211647111e-06, + "loss": 0.1543, + "step": 33799 + }, + { + "epoch": 2.75, + "learning_rate": 1.6384180790960452e-06, + "loss": 0.1027, + "step": 33800 + }, + { + "epoch": 2.75, + "learning_rate": 1.6378748370273794e-06, + "loss": 0.2604, + "step": 33801 + }, + { + "epoch": 2.75, + "learning_rate": 1.6373315949587138e-06, + "loss": 0.0584, + "step": 33802 + }, + { + "epoch": 2.75, + "learning_rate": 1.636788352890048e-06, + "loss": 0.2567, + "step": 33803 + }, + { + "epoch": 2.75, + "learning_rate": 1.6362451108213823e-06, + "loss": 0.5266, + "step": 33804 + }, + { + "epoch": 2.75, + "learning_rate": 1.6357018687527163e-06, + "loss": 0.2218, + "step": 33805 + }, + { + "epoch": 2.75, + "learning_rate": 1.6351586266840506e-06, + "loss": 0.2664, + "step": 33806 + }, + { + "epoch": 2.75, + "learning_rate": 1.6346153846153848e-06, + "loss": 0.3215, + "step": 33807 + }, + { + "epoch": 2.75, + "learning_rate": 1.634072142546719e-06, + "loss": 0.2683, + "step": 33808 + }, + { + "epoch": 2.75, + "learning_rate": 1.6335289004780532e-06, + "loss": 0.2246, + "step": 33809 + }, + { + "epoch": 2.76, + "learning_rate": 1.6329856584093873e-06, + "loss": 0.4168, + "step": 33810 + }, + { + "epoch": 2.76, + "learning_rate": 1.6324424163407215e-06, + "loss": 0.2394, + "step": 33811 + }, + { + "epoch": 2.76, + "learning_rate": 1.6318991742720557e-06, + "loss": 0.3483, + "step": 33812 + }, + { + "epoch": 2.76, + "learning_rate": 1.63135593220339e-06, + "loss": 0.2793, + "step": 33813 + }, + { + "epoch": 2.76, + "learning_rate": 1.630812690134724e-06, + "loss": 0.1638, + "step": 33814 + }, + { + "epoch": 2.76, + "learning_rate": 1.6302694480660582e-06, + "loss": 0.1252, + "step": 33815 + }, + { + "epoch": 2.76, + "learning_rate": 1.6297262059973926e-06, + "loss": 0.1805, + "step": 33816 + }, + { + "epoch": 2.76, + "learning_rate": 1.6291829639287269e-06, + "loss": 0.1589, + "step": 33817 + }, + { + "epoch": 2.76, + "learning_rate": 1.6286397218600611e-06, + "loss": 0.2155, + "step": 33818 + }, + { + "epoch": 2.76, + "learning_rate": 1.6280964797913951e-06, + "loss": 0.3405, + "step": 33819 + }, + { + "epoch": 2.76, + "learning_rate": 1.6275532377227294e-06, + "loss": 0.237, + "step": 33820 + }, + { + "epoch": 2.76, + "learning_rate": 1.6270099956540636e-06, + "loss": 0.3106, + "step": 33821 + }, + { + "epoch": 2.76, + "learning_rate": 1.6264667535853978e-06, + "loss": 0.2134, + "step": 33822 + }, + { + "epoch": 2.76, + "learning_rate": 1.625923511516732e-06, + "loss": 0.3558, + "step": 33823 + }, + { + "epoch": 2.76, + "learning_rate": 1.625380269448066e-06, + "loss": 0.2058, + "step": 33824 + }, + { + "epoch": 2.76, + "learning_rate": 1.6248370273794003e-06, + "loss": 0.0881, + "step": 33825 + }, + { + "epoch": 2.76, + "learning_rate": 1.6242937853107345e-06, + "loss": 0.0421, + "step": 33826 + }, + { + "epoch": 2.76, + "learning_rate": 1.623750543242069e-06, + "loss": 0.2045, + "step": 33827 + }, + { + "epoch": 2.76, + "learning_rate": 1.6232073011734032e-06, + "loss": 0.3877, + "step": 33828 + }, + { + "epoch": 2.76, + "learning_rate": 1.6226640591047372e-06, + "loss": 0.1024, + "step": 33829 + }, + { + "epoch": 2.76, + "learning_rate": 1.6221208170360714e-06, + "loss": 0.0881, + "step": 33830 + }, + { + "epoch": 2.76, + "learning_rate": 1.6215775749674057e-06, + "loss": 0.2351, + "step": 33831 + }, + { + "epoch": 2.76, + "learning_rate": 1.62103433289874e-06, + "loss": 0.121, + "step": 33832 + }, + { + "epoch": 2.76, + "learning_rate": 1.620491090830074e-06, + "loss": 0.2528, + "step": 33833 + }, + { + "epoch": 2.76, + "learning_rate": 1.6199478487614082e-06, + "loss": 0.2587, + "step": 33834 + }, + { + "epoch": 2.76, + "learning_rate": 1.6194046066927424e-06, + "loss": 0.3132, + "step": 33835 + }, + { + "epoch": 2.76, + "learning_rate": 1.6188613646240766e-06, + "loss": 0.3164, + "step": 33836 + }, + { + "epoch": 2.76, + "learning_rate": 1.6183181225554109e-06, + "loss": 0.3584, + "step": 33837 + }, + { + "epoch": 2.76, + "learning_rate": 1.6177748804867449e-06, + "loss": 0.1653, + "step": 33838 + }, + { + "epoch": 2.76, + "learning_rate": 1.617231638418079e-06, + "loss": 0.2755, + "step": 33839 + }, + { + "epoch": 2.76, + "learning_rate": 1.6166883963494133e-06, + "loss": 0.2017, + "step": 33840 + }, + { + "epoch": 2.76, + "learning_rate": 1.6161451542807478e-06, + "loss": 0.0518, + "step": 33841 + }, + { + "epoch": 2.76, + "learning_rate": 1.615601912212082e-06, + "loss": 0.3429, + "step": 33842 + }, + { + "epoch": 2.76, + "learning_rate": 1.615058670143416e-06, + "loss": 0.1262, + "step": 33843 + }, + { + "epoch": 2.76, + "learning_rate": 1.6145154280747503e-06, + "loss": 0.4547, + "step": 33844 + }, + { + "epoch": 2.76, + "learning_rate": 1.6139721860060845e-06, + "loss": 0.1956, + "step": 33845 + }, + { + "epoch": 2.76, + "learning_rate": 1.6134289439374187e-06, + "loss": 0.3467, + "step": 33846 + }, + { + "epoch": 2.76, + "learning_rate": 1.612885701868753e-06, + "loss": 0.2342, + "step": 33847 + }, + { + "epoch": 2.76, + "learning_rate": 1.612342459800087e-06, + "loss": 0.3345, + "step": 33848 + }, + { + "epoch": 2.76, + "learning_rate": 1.6117992177314212e-06, + "loss": 0.0894, + "step": 33849 + }, + { + "epoch": 2.76, + "learning_rate": 1.6112559756627554e-06, + "loss": 0.1705, + "step": 33850 + }, + { + "epoch": 2.76, + "learning_rate": 1.6107127335940897e-06, + "loss": 0.3436, + "step": 33851 + }, + { + "epoch": 2.76, + "learning_rate": 1.6101694915254237e-06, + "loss": 0.1966, + "step": 33852 + }, + { + "epoch": 2.76, + "learning_rate": 1.609626249456758e-06, + "loss": 0.1346, + "step": 33853 + }, + { + "epoch": 2.76, + "learning_rate": 1.6090830073880923e-06, + "loss": 0.202, + "step": 33854 + }, + { + "epoch": 2.76, + "learning_rate": 1.6085397653194266e-06, + "loss": 0.0512, + "step": 33855 + }, + { + "epoch": 2.76, + "learning_rate": 1.6079965232507608e-06, + "loss": 0.0672, + "step": 33856 + }, + { + "epoch": 2.76, + "learning_rate": 1.6074532811820948e-06, + "loss": 0.2747, + "step": 33857 + }, + { + "epoch": 2.76, + "learning_rate": 1.606910039113429e-06, + "loss": 0.3151, + "step": 33858 + }, + { + "epoch": 2.76, + "learning_rate": 1.6063667970447633e-06, + "loss": 0.3098, + "step": 33859 + }, + { + "epoch": 2.76, + "learning_rate": 1.6058235549760975e-06, + "loss": 0.1231, + "step": 33860 + }, + { + "epoch": 2.76, + "learning_rate": 1.6052803129074317e-06, + "loss": 0.2402, + "step": 33861 + }, + { + "epoch": 2.76, + "learning_rate": 1.6047370708387658e-06, + "loss": 0.0538, + "step": 33862 + }, + { + "epoch": 2.76, + "learning_rate": 1.6041938287701e-06, + "loss": 0.5293, + "step": 33863 + }, + { + "epoch": 2.76, + "learning_rate": 1.6036505867014342e-06, + "loss": 0.239, + "step": 33864 + }, + { + "epoch": 2.76, + "learning_rate": 1.6031073446327687e-06, + "loss": 0.1969, + "step": 33865 + }, + { + "epoch": 2.76, + "learning_rate": 1.602564102564103e-06, + "loss": 0.0694, + "step": 33866 + }, + { + "epoch": 2.76, + "learning_rate": 1.6020208604954367e-06, + "loss": 0.3281, + "step": 33867 + }, + { + "epoch": 2.76, + "learning_rate": 1.6014776184267712e-06, + "loss": 0.4334, + "step": 33868 + }, + { + "epoch": 2.76, + "learning_rate": 1.6009343763581054e-06, + "loss": 0.3013, + "step": 33869 + }, + { + "epoch": 2.76, + "learning_rate": 1.6003911342894396e-06, + "loss": 0.2475, + "step": 33870 + }, + { + "epoch": 2.76, + "learning_rate": 1.5998478922207736e-06, + "loss": 0.2512, + "step": 33871 + }, + { + "epoch": 2.76, + "learning_rate": 1.5993046501521079e-06, + "loss": 0.2831, + "step": 33872 + }, + { + "epoch": 2.76, + "learning_rate": 1.598761408083442e-06, + "loss": 0.2689, + "step": 33873 + }, + { + "epoch": 2.76, + "learning_rate": 1.5982181660147763e-06, + "loss": 0.1126, + "step": 33874 + }, + { + "epoch": 2.76, + "learning_rate": 1.5976749239461106e-06, + "loss": 0.1624, + "step": 33875 + }, + { + "epoch": 2.76, + "learning_rate": 1.5971316818774446e-06, + "loss": 0.1188, + "step": 33876 + }, + { + "epoch": 2.76, + "learning_rate": 1.5965884398087788e-06, + "loss": 0.3397, + "step": 33877 + }, + { + "epoch": 2.76, + "learning_rate": 1.596045197740113e-06, + "loss": 0.1973, + "step": 33878 + }, + { + "epoch": 2.76, + "learning_rate": 1.5955019556714475e-06, + "loss": 0.2038, + "step": 33879 + }, + { + "epoch": 2.76, + "learning_rate": 1.5949587136027817e-06, + "loss": 0.1316, + "step": 33880 + }, + { + "epoch": 2.76, + "learning_rate": 1.5944154715341157e-06, + "loss": 0.0949, + "step": 33881 + }, + { + "epoch": 2.76, + "learning_rate": 1.59387222946545e-06, + "loss": 0.1396, + "step": 33882 + }, + { + "epoch": 2.76, + "learning_rate": 1.5933289873967842e-06, + "loss": 0.2474, + "step": 33883 + }, + { + "epoch": 2.76, + "learning_rate": 1.5927857453281184e-06, + "loss": 0.3388, + "step": 33884 + }, + { + "epoch": 2.76, + "learning_rate": 1.5922425032594526e-06, + "loss": 0.2116, + "step": 33885 + }, + { + "epoch": 2.76, + "learning_rate": 1.5916992611907867e-06, + "loss": 0.0858, + "step": 33886 + }, + { + "epoch": 2.76, + "learning_rate": 1.591156019122121e-06, + "loss": 0.2953, + "step": 33887 + }, + { + "epoch": 2.76, + "learning_rate": 1.5906127770534551e-06, + "loss": 0.1882, + "step": 33888 + }, + { + "epoch": 2.76, + "learning_rate": 1.5900695349847894e-06, + "loss": 0.1054, + "step": 33889 + }, + { + "epoch": 2.76, + "learning_rate": 1.5895262929161234e-06, + "loss": 0.2876, + "step": 33890 + }, + { + "epoch": 2.76, + "learning_rate": 1.5889830508474576e-06, + "loss": 0.2674, + "step": 33891 + }, + { + "epoch": 2.76, + "learning_rate": 1.588439808778792e-06, + "loss": 0.2521, + "step": 33892 + }, + { + "epoch": 2.76, + "learning_rate": 1.5878965667101263e-06, + "loss": 0.3243, + "step": 33893 + }, + { + "epoch": 2.76, + "learning_rate": 1.5873533246414605e-06, + "loss": 0.1515, + "step": 33894 + }, + { + "epoch": 2.76, + "learning_rate": 1.5868100825727945e-06, + "loss": 0.2277, + "step": 33895 + }, + { + "epoch": 2.76, + "learning_rate": 1.5862668405041288e-06, + "loss": 0.204, + "step": 33896 + }, + { + "epoch": 2.76, + "learning_rate": 1.585723598435463e-06, + "loss": 0.1617, + "step": 33897 + }, + { + "epoch": 2.76, + "learning_rate": 1.5851803563667972e-06, + "loss": 0.2848, + "step": 33898 + }, + { + "epoch": 2.76, + "learning_rate": 1.5846371142981315e-06, + "loss": 0.2262, + "step": 33899 + }, + { + "epoch": 2.76, + "learning_rate": 1.5840938722294655e-06, + "loss": 0.2759, + "step": 33900 + }, + { + "epoch": 2.76, + "learning_rate": 1.5835506301607997e-06, + "loss": 0.1907, + "step": 33901 + }, + { + "epoch": 2.76, + "learning_rate": 1.583007388092134e-06, + "loss": 0.221, + "step": 33902 + }, + { + "epoch": 2.76, + "learning_rate": 1.5824641460234682e-06, + "loss": 0.3006, + "step": 33903 + }, + { + "epoch": 2.76, + "learning_rate": 1.5819209039548026e-06, + "loss": 0.1891, + "step": 33904 + }, + { + "epoch": 2.76, + "learning_rate": 1.5813776618861364e-06, + "loss": 0.2482, + "step": 33905 + }, + { + "epoch": 2.76, + "learning_rate": 1.5808344198174709e-06, + "loss": 0.1434, + "step": 33906 + }, + { + "epoch": 2.76, + "learning_rate": 1.580291177748805e-06, + "loss": 0.3377, + "step": 33907 + }, + { + "epoch": 2.76, + "learning_rate": 1.5797479356801393e-06, + "loss": 0.263, + "step": 33908 + }, + { + "epoch": 2.76, + "learning_rate": 1.5792046936114733e-06, + "loss": 0.3853, + "step": 33909 + }, + { + "epoch": 2.76, + "learning_rate": 1.5786614515428076e-06, + "loss": 0.31, + "step": 33910 + }, + { + "epoch": 2.76, + "learning_rate": 1.5781182094741418e-06, + "loss": 0.2238, + "step": 33911 + }, + { + "epoch": 2.76, + "learning_rate": 1.577574967405476e-06, + "loss": 0.1944, + "step": 33912 + }, + { + "epoch": 2.76, + "learning_rate": 1.5770317253368103e-06, + "loss": 0.1155, + "step": 33913 + }, + { + "epoch": 2.76, + "learning_rate": 1.5764884832681443e-06, + "loss": 0.0557, + "step": 33914 + }, + { + "epoch": 2.76, + "learning_rate": 1.5759452411994785e-06, + "loss": 0.2658, + "step": 33915 + }, + { + "epoch": 2.76, + "learning_rate": 1.5754019991308127e-06, + "loss": 0.5089, + "step": 33916 + }, + { + "epoch": 2.76, + "learning_rate": 1.5748587570621472e-06, + "loss": 0.1608, + "step": 33917 + }, + { + "epoch": 2.76, + "learning_rate": 1.5743155149934814e-06, + "loss": 0.1845, + "step": 33918 + }, + { + "epoch": 2.76, + "learning_rate": 1.5737722729248154e-06, + "loss": 0.1215, + "step": 33919 + }, + { + "epoch": 2.76, + "learning_rate": 1.5732290308561497e-06, + "loss": 0.4208, + "step": 33920 + }, + { + "epoch": 2.76, + "learning_rate": 1.5726857887874839e-06, + "loss": 0.5255, + "step": 33921 + }, + { + "epoch": 2.76, + "learning_rate": 1.5721425467188181e-06, + "loss": 0.1294, + "step": 33922 + }, + { + "epoch": 2.76, + "learning_rate": 1.5715993046501523e-06, + "loss": 0.1177, + "step": 33923 + }, + { + "epoch": 2.76, + "learning_rate": 1.5710560625814864e-06, + "loss": 0.3366, + "step": 33924 + }, + { + "epoch": 2.76, + "learning_rate": 1.5705128205128206e-06, + "loss": 0.1755, + "step": 33925 + }, + { + "epoch": 2.76, + "learning_rate": 1.5699695784441548e-06, + "loss": 0.205, + "step": 33926 + }, + { + "epoch": 2.76, + "learning_rate": 1.569426336375489e-06, + "loss": 0.2202, + "step": 33927 + }, + { + "epoch": 2.76, + "learning_rate": 1.568883094306823e-06, + "loss": 0.3543, + "step": 33928 + }, + { + "epoch": 2.76, + "learning_rate": 1.5683398522381573e-06, + "loss": 0.1222, + "step": 33929 + }, + { + "epoch": 2.76, + "learning_rate": 1.5677966101694915e-06, + "loss": 0.0514, + "step": 33930 + }, + { + "epoch": 2.76, + "learning_rate": 1.567253368100826e-06, + "loss": 0.3307, + "step": 33931 + }, + { + "epoch": 2.76, + "learning_rate": 1.5667101260321602e-06, + "loss": 0.0722, + "step": 33932 + }, + { + "epoch": 2.77, + "learning_rate": 1.5661668839634942e-06, + "loss": 0.445, + "step": 33933 + }, + { + "epoch": 2.77, + "learning_rate": 1.5656236418948285e-06, + "loss": 0.2325, + "step": 33934 + }, + { + "epoch": 2.77, + "learning_rate": 1.5650803998261627e-06, + "loss": 0.1225, + "step": 33935 + }, + { + "epoch": 2.77, + "learning_rate": 1.564537157757497e-06, + "loss": 0.215, + "step": 33936 + }, + { + "epoch": 2.77, + "learning_rate": 1.5639939156888312e-06, + "loss": 0.0935, + "step": 33937 + }, + { + "epoch": 2.77, + "learning_rate": 1.5634506736201652e-06, + "loss": 0.3726, + "step": 33938 + }, + { + "epoch": 2.77, + "learning_rate": 1.5629074315514994e-06, + "loss": 0.3182, + "step": 33939 + }, + { + "epoch": 2.77, + "learning_rate": 1.5623641894828336e-06, + "loss": 0.319, + "step": 33940 + }, + { + "epoch": 2.77, + "learning_rate": 1.5618209474141679e-06, + "loss": 0.3895, + "step": 33941 + }, + { + "epoch": 2.77, + "learning_rate": 1.5612777053455023e-06, + "loss": 0.1373, + "step": 33942 + }, + { + "epoch": 2.77, + "learning_rate": 1.5607344632768361e-06, + "loss": 0.2293, + "step": 33943 + }, + { + "epoch": 2.77, + "learning_rate": 1.5601912212081706e-06, + "loss": 0.1126, + "step": 33944 + }, + { + "epoch": 2.77, + "learning_rate": 1.5596479791395048e-06, + "loss": 0.2711, + "step": 33945 + }, + { + "epoch": 2.77, + "learning_rate": 1.559104737070839e-06, + "loss": 0.0832, + "step": 33946 + }, + { + "epoch": 2.77, + "learning_rate": 1.558561495002173e-06, + "loss": 0.1397, + "step": 33947 + }, + { + "epoch": 2.77, + "learning_rate": 1.5580182529335073e-06, + "loss": 0.1945, + "step": 33948 + }, + { + "epoch": 2.77, + "learning_rate": 1.5574750108648415e-06, + "loss": 0.2709, + "step": 33949 + }, + { + "epoch": 2.77, + "learning_rate": 1.5569317687961757e-06, + "loss": 0.142, + "step": 33950 + }, + { + "epoch": 2.77, + "learning_rate": 1.55638852672751e-06, + "loss": 0.3421, + "step": 33951 + }, + { + "epoch": 2.77, + "learning_rate": 1.555845284658844e-06, + "loss": 0.1624, + "step": 33952 + }, + { + "epoch": 2.77, + "learning_rate": 1.5553020425901782e-06, + "loss": 0.1154, + "step": 33953 + }, + { + "epoch": 2.77, + "learning_rate": 1.5547588005215124e-06, + "loss": 0.1869, + "step": 33954 + }, + { + "epoch": 2.77, + "learning_rate": 1.5542155584528469e-06, + "loss": 0.2793, + "step": 33955 + }, + { + "epoch": 2.77, + "learning_rate": 1.5536723163841811e-06, + "loss": 0.0517, + "step": 33956 + }, + { + "epoch": 2.77, + "learning_rate": 1.553129074315515e-06, + "loss": 0.1672, + "step": 33957 + }, + { + "epoch": 2.77, + "learning_rate": 1.5525858322468494e-06, + "loss": 0.1156, + "step": 33958 + }, + { + "epoch": 2.77, + "learning_rate": 1.5520425901781836e-06, + "loss": 0.312, + "step": 33959 + }, + { + "epoch": 2.77, + "learning_rate": 1.5514993481095178e-06, + "loss": 0.1614, + "step": 33960 + }, + { + "epoch": 2.77, + "learning_rate": 1.550956106040852e-06, + "loss": 0.2944, + "step": 33961 + }, + { + "epoch": 2.77, + "learning_rate": 1.550412863972186e-06, + "loss": 0.4127, + "step": 33962 + }, + { + "epoch": 2.77, + "learning_rate": 1.5498696219035203e-06, + "loss": 0.5206, + "step": 33963 + }, + { + "epoch": 2.77, + "learning_rate": 1.5493263798348545e-06, + "loss": 0.095, + "step": 33964 + }, + { + "epoch": 2.77, + "learning_rate": 1.5487831377661888e-06, + "loss": 0.1124, + "step": 33965 + }, + { + "epoch": 2.77, + "learning_rate": 1.5482398956975228e-06, + "loss": 0.2232, + "step": 33966 + }, + { + "epoch": 2.77, + "learning_rate": 1.547696653628857e-06, + "loss": 0.3649, + "step": 33967 + }, + { + "epoch": 2.77, + "learning_rate": 1.5471534115601912e-06, + "loss": 0.2653, + "step": 33968 + }, + { + "epoch": 2.77, + "learning_rate": 1.5466101694915257e-06, + "loss": 0.2771, + "step": 33969 + }, + { + "epoch": 2.77, + "learning_rate": 1.54606692742286e-06, + "loss": 0.5683, + "step": 33970 + }, + { + "epoch": 2.77, + "learning_rate": 1.545523685354194e-06, + "loss": 0.3757, + "step": 33971 + }, + { + "epoch": 2.77, + "learning_rate": 1.5449804432855282e-06, + "loss": 0.2065, + "step": 33972 + }, + { + "epoch": 2.77, + "learning_rate": 1.5444372012168624e-06, + "loss": 0.3101, + "step": 33973 + }, + { + "epoch": 2.77, + "learning_rate": 1.5438939591481966e-06, + "loss": 0.2414, + "step": 33974 + }, + { + "epoch": 2.77, + "learning_rate": 1.5433507170795309e-06, + "loss": 0.1199, + "step": 33975 + }, + { + "epoch": 2.77, + "learning_rate": 1.5428074750108649e-06, + "loss": 0.3448, + "step": 33976 + }, + { + "epoch": 2.77, + "learning_rate": 1.542264232942199e-06, + "loss": 0.1955, + "step": 33977 + }, + { + "epoch": 2.77, + "learning_rate": 1.5417209908735333e-06, + "loss": 0.236, + "step": 33978 + }, + { + "epoch": 2.77, + "learning_rate": 1.5411777488048676e-06, + "loss": 0.2052, + "step": 33979 + }, + { + "epoch": 2.77, + "learning_rate": 1.540634506736202e-06, + "loss": 0.4084, + "step": 33980 + }, + { + "epoch": 2.77, + "learning_rate": 1.5400912646675358e-06, + "loss": 0.1919, + "step": 33981 + }, + { + "epoch": 2.77, + "learning_rate": 1.5395480225988703e-06, + "loss": 0.1912, + "step": 33982 + }, + { + "epoch": 2.77, + "learning_rate": 1.5390047805302045e-06, + "loss": 0.2405, + "step": 33983 + }, + { + "epoch": 2.77, + "learning_rate": 1.5384615384615387e-06, + "loss": 0.3713, + "step": 33984 + }, + { + "epoch": 2.77, + "learning_rate": 1.5379182963928727e-06, + "loss": 0.4447, + "step": 33985 + }, + { + "epoch": 2.77, + "learning_rate": 1.537375054324207e-06, + "loss": 0.19, + "step": 33986 + }, + { + "epoch": 2.77, + "learning_rate": 1.5368318122555412e-06, + "loss": 0.0825, + "step": 33987 + }, + { + "epoch": 2.77, + "learning_rate": 1.5362885701868754e-06, + "loss": 0.1855, + "step": 33988 + }, + { + "epoch": 2.77, + "learning_rate": 1.5357453281182097e-06, + "loss": 0.0646, + "step": 33989 + }, + { + "epoch": 2.77, + "learning_rate": 1.5352020860495437e-06, + "loss": 0.1197, + "step": 33990 + }, + { + "epoch": 2.77, + "learning_rate": 1.534658843980878e-06, + "loss": 0.0994, + "step": 33991 + }, + { + "epoch": 2.77, + "learning_rate": 1.5341156019122121e-06, + "loss": 0.1953, + "step": 33992 + }, + { + "epoch": 2.77, + "learning_rate": 1.5335723598435464e-06, + "loss": 0.1087, + "step": 33993 + }, + { + "epoch": 2.77, + "learning_rate": 1.5330291177748808e-06, + "loss": 0.1726, + "step": 33994 + }, + { + "epoch": 2.77, + "learning_rate": 1.5324858757062146e-06, + "loss": 0.1128, + "step": 33995 + }, + { + "epoch": 2.77, + "learning_rate": 1.531942633637549e-06, + "loss": 0.2718, + "step": 33996 + }, + { + "epoch": 2.77, + "learning_rate": 1.5313993915688833e-06, + "loss": 0.3113, + "step": 33997 + }, + { + "epoch": 2.77, + "learning_rate": 1.5308561495002175e-06, + "loss": 0.0974, + "step": 33998 + }, + { + "epoch": 2.77, + "learning_rate": 1.5303129074315518e-06, + "loss": 0.0905, + "step": 33999 + }, + { + "epoch": 2.77, + "learning_rate": 1.5297696653628858e-06, + "loss": 0.108, + "step": 34000 + }, + { + "epoch": 2.77, + "eval_accuracy": 0.8427916454406521, + "eval_loss": 0.49588096141815186, + "eval_runtime": 22.4231, + "eval_samples_per_second": 437.718, + "eval_steps_per_second": 3.434, + "step": 34000 + }, + { + "epoch": 2.77, + "learning_rate": 1.52922642329422e-06, + "loss": 0.2994, + "step": 34001 + }, + { + "epoch": 2.77, + "learning_rate": 1.5286831812255542e-06, + "loss": 0.4389, + "step": 34002 + }, + { + "epoch": 2.77, + "learning_rate": 1.5281399391568885e-06, + "loss": 0.3104, + "step": 34003 + }, + { + "epoch": 2.77, + "learning_rate": 1.5275966970882225e-06, + "loss": 0.0604, + "step": 34004 + }, + { + "epoch": 2.77, + "learning_rate": 1.5270534550195567e-06, + "loss": 0.1429, + "step": 34005 + }, + { + "epoch": 2.77, + "learning_rate": 1.526510212950891e-06, + "loss": 0.3307, + "step": 34006 + }, + { + "epoch": 2.77, + "learning_rate": 1.5259669708822254e-06, + "loss": 0.3045, + "step": 34007 + }, + { + "epoch": 2.77, + "learning_rate": 1.5254237288135596e-06, + "loss": 0.3163, + "step": 34008 + }, + { + "epoch": 2.77, + "learning_rate": 1.5248804867448936e-06, + "loss": 0.253, + "step": 34009 + }, + { + "epoch": 2.77, + "learning_rate": 1.5243372446762279e-06, + "loss": 0.2835, + "step": 34010 + }, + { + "epoch": 2.77, + "learning_rate": 1.523794002607562e-06, + "loss": 0.1745, + "step": 34011 + }, + { + "epoch": 2.77, + "learning_rate": 1.5232507605388963e-06, + "loss": 0.1702, + "step": 34012 + }, + { + "epoch": 2.77, + "learning_rate": 1.5227075184702306e-06, + "loss": 0.1398, + "step": 34013 + }, + { + "epoch": 2.77, + "learning_rate": 1.5221642764015646e-06, + "loss": 0.118, + "step": 34014 + }, + { + "epoch": 2.77, + "learning_rate": 1.5216210343328988e-06, + "loss": 0.2834, + "step": 34015 + }, + { + "epoch": 2.77, + "learning_rate": 1.521077792264233e-06, + "loss": 0.1247, + "step": 34016 + }, + { + "epoch": 2.77, + "learning_rate": 1.5205345501955673e-06, + "loss": 0.274, + "step": 34017 + }, + { + "epoch": 2.77, + "learning_rate": 1.5199913081269015e-06, + "loss": 0.1277, + "step": 34018 + }, + { + "epoch": 2.77, + "learning_rate": 1.5194480660582355e-06, + "loss": 0.2202, + "step": 34019 + }, + { + "epoch": 2.77, + "learning_rate": 1.5189048239895697e-06, + "loss": 0.2075, + "step": 34020 + }, + { + "epoch": 2.77, + "learning_rate": 1.5183615819209042e-06, + "loss": 0.303, + "step": 34021 + }, + { + "epoch": 2.77, + "learning_rate": 1.5178183398522384e-06, + "loss": 0.1533, + "step": 34022 + }, + { + "epoch": 2.77, + "learning_rate": 1.5172750977835724e-06, + "loss": 0.4652, + "step": 34023 + }, + { + "epoch": 2.77, + "learning_rate": 1.5167318557149067e-06, + "loss": 0.1684, + "step": 34024 + }, + { + "epoch": 2.77, + "learning_rate": 1.516188613646241e-06, + "loss": 0.1423, + "step": 34025 + }, + { + "epoch": 2.77, + "learning_rate": 1.5156453715775751e-06, + "loss": 0.229, + "step": 34026 + }, + { + "epoch": 2.77, + "learning_rate": 1.5151021295089094e-06, + "loss": 0.1022, + "step": 34027 + }, + { + "epoch": 2.77, + "learning_rate": 1.5145588874402434e-06, + "loss": 0.2515, + "step": 34028 + }, + { + "epoch": 2.77, + "learning_rate": 1.5140156453715776e-06, + "loss": 0.3744, + "step": 34029 + }, + { + "epoch": 2.77, + "learning_rate": 1.5134724033029118e-06, + "loss": 0.1895, + "step": 34030 + }, + { + "epoch": 2.77, + "learning_rate": 1.512929161234246e-06, + "loss": 0.0917, + "step": 34031 + }, + { + "epoch": 2.77, + "learning_rate": 1.5123859191655805e-06, + "loss": 0.1426, + "step": 34032 + }, + { + "epoch": 2.77, + "learning_rate": 1.5118426770969143e-06, + "loss": 0.2667, + "step": 34033 + }, + { + "epoch": 2.77, + "learning_rate": 1.5112994350282488e-06, + "loss": 0.0612, + "step": 34034 + }, + { + "epoch": 2.77, + "learning_rate": 1.510756192959583e-06, + "loss": 0.3368, + "step": 34035 + }, + { + "epoch": 2.77, + "learning_rate": 1.5102129508909172e-06, + "loss": 0.0458, + "step": 34036 + }, + { + "epoch": 2.77, + "learning_rate": 1.5096697088222515e-06, + "loss": 0.0759, + "step": 34037 + }, + { + "epoch": 2.77, + "learning_rate": 1.5091264667535855e-06, + "loss": 0.4098, + "step": 34038 + }, + { + "epoch": 2.77, + "learning_rate": 1.5085832246849197e-06, + "loss": 0.2584, + "step": 34039 + }, + { + "epoch": 2.77, + "learning_rate": 1.508039982616254e-06, + "loss": 0.0854, + "step": 34040 + }, + { + "epoch": 2.77, + "learning_rate": 1.5074967405475882e-06, + "loss": 0.2155, + "step": 34041 + }, + { + "epoch": 2.77, + "learning_rate": 1.5069534984789222e-06, + "loss": 0.1196, + "step": 34042 + }, + { + "epoch": 2.77, + "learning_rate": 1.5064102564102564e-06, + "loss": 0.0811, + "step": 34043 + }, + { + "epoch": 2.77, + "learning_rate": 1.5058670143415906e-06, + "loss": 0.1937, + "step": 34044 + }, + { + "epoch": 2.77, + "learning_rate": 1.5053237722729249e-06, + "loss": 0.2201, + "step": 34045 + }, + { + "epoch": 2.77, + "learning_rate": 1.5047805302042593e-06, + "loss": 0.1225, + "step": 34046 + }, + { + "epoch": 2.77, + "learning_rate": 1.5042372881355931e-06, + "loss": 0.1358, + "step": 34047 + }, + { + "epoch": 2.77, + "learning_rate": 1.5036940460669276e-06, + "loss": 0.3198, + "step": 34048 + }, + { + "epoch": 2.77, + "learning_rate": 1.5031508039982618e-06, + "loss": 0.1682, + "step": 34049 + }, + { + "epoch": 2.77, + "learning_rate": 1.502607561929596e-06, + "loss": 0.2418, + "step": 34050 + }, + { + "epoch": 2.77, + "learning_rate": 1.5020643198609303e-06, + "loss": 0.11, + "step": 34051 + }, + { + "epoch": 2.77, + "learning_rate": 1.5015210777922643e-06, + "loss": 0.1686, + "step": 34052 + }, + { + "epoch": 2.77, + "learning_rate": 1.5009778357235985e-06, + "loss": 0.0387, + "step": 34053 + }, + { + "epoch": 2.77, + "learning_rate": 1.5004345936549327e-06, + "loss": 0.3081, + "step": 34054 + }, + { + "epoch": 2.78, + "learning_rate": 1.499891351586267e-06, + "loss": 0.0775, + "step": 34055 + }, + { + "epoch": 2.78, + "learning_rate": 1.4993481095176012e-06, + "loss": 0.3511, + "step": 34056 + }, + { + "epoch": 2.78, + "learning_rate": 1.4988048674489352e-06, + "loss": 0.1796, + "step": 34057 + }, + { + "epoch": 2.78, + "learning_rate": 1.4982616253802694e-06, + "loss": 0.5473, + "step": 34058 + }, + { + "epoch": 2.78, + "learning_rate": 1.4977183833116039e-06, + "loss": 0.3166, + "step": 34059 + }, + { + "epoch": 2.78, + "learning_rate": 1.4971751412429381e-06, + "loss": 0.2905, + "step": 34060 + }, + { + "epoch": 2.78, + "learning_rate": 1.4966318991742721e-06, + "loss": 0.1286, + "step": 34061 + }, + { + "epoch": 2.78, + "learning_rate": 1.4960886571056064e-06, + "loss": 0.1183, + "step": 34062 + }, + { + "epoch": 2.78, + "learning_rate": 1.4955454150369406e-06, + "loss": 0.2205, + "step": 34063 + }, + { + "epoch": 2.78, + "learning_rate": 1.4950021729682748e-06, + "loss": 0.1907, + "step": 34064 + }, + { + "epoch": 2.78, + "learning_rate": 1.494458930899609e-06, + "loss": 0.2795, + "step": 34065 + }, + { + "epoch": 2.78, + "learning_rate": 1.493915688830943e-06, + "loss": 0.2208, + "step": 34066 + }, + { + "epoch": 2.78, + "learning_rate": 1.4933724467622773e-06, + "loss": 0.2551, + "step": 34067 + }, + { + "epoch": 2.78, + "learning_rate": 1.4928292046936115e-06, + "loss": 0.2852, + "step": 34068 + }, + { + "epoch": 2.78, + "learning_rate": 1.4922859626249458e-06, + "loss": 0.2592, + "step": 34069 + }, + { + "epoch": 2.78, + "learning_rate": 1.4917427205562802e-06, + "loss": 0.3464, + "step": 34070 + }, + { + "epoch": 2.78, + "learning_rate": 1.491199478487614e-06, + "loss": 0.1953, + "step": 34071 + }, + { + "epoch": 2.78, + "learning_rate": 1.4906562364189483e-06, + "loss": 0.5166, + "step": 34072 + }, + { + "epoch": 2.78, + "learning_rate": 1.4901129943502827e-06, + "loss": 0.5376, + "step": 34073 + }, + { + "epoch": 2.78, + "learning_rate": 1.489569752281617e-06, + "loss": 0.2631, + "step": 34074 + }, + { + "epoch": 2.78, + "learning_rate": 1.4890265102129512e-06, + "loss": 0.1337, + "step": 34075 + }, + { + "epoch": 2.78, + "learning_rate": 1.4884832681442852e-06, + "loss": 0.3806, + "step": 34076 + }, + { + "epoch": 2.78, + "learning_rate": 1.4879400260756194e-06, + "loss": 0.1035, + "step": 34077 + }, + { + "epoch": 2.78, + "learning_rate": 1.4873967840069536e-06, + "loss": 0.2265, + "step": 34078 + }, + { + "epoch": 2.78, + "learning_rate": 1.4868535419382879e-06, + "loss": 0.1326, + "step": 34079 + }, + { + "epoch": 2.78, + "learning_rate": 1.4863102998696219e-06, + "loss": 0.5031, + "step": 34080 + }, + { + "epoch": 2.78, + "learning_rate": 1.4857670578009561e-06, + "loss": 0.4211, + "step": 34081 + }, + { + "epoch": 2.78, + "learning_rate": 1.4852238157322903e-06, + "loss": 0.2068, + "step": 34082 + }, + { + "epoch": 2.78, + "learning_rate": 1.4846805736636246e-06, + "loss": 0.0389, + "step": 34083 + }, + { + "epoch": 2.78, + "learning_rate": 1.484137331594959e-06, + "loss": 0.3031, + "step": 34084 + }, + { + "epoch": 2.78, + "learning_rate": 1.4835940895262928e-06, + "loss": 0.1922, + "step": 34085 + }, + { + "epoch": 2.78, + "learning_rate": 1.4830508474576273e-06, + "loss": 0.2752, + "step": 34086 + }, + { + "epoch": 2.78, + "learning_rate": 1.4825076053889615e-06, + "loss": 0.2276, + "step": 34087 + }, + { + "epoch": 2.78, + "learning_rate": 1.4819643633202957e-06, + "loss": 0.176, + "step": 34088 + }, + { + "epoch": 2.78, + "learning_rate": 1.48142112125163e-06, + "loss": 0.2923, + "step": 34089 + }, + { + "epoch": 2.78, + "learning_rate": 1.480877879182964e-06, + "loss": 0.1854, + "step": 34090 + }, + { + "epoch": 2.78, + "learning_rate": 1.4803346371142982e-06, + "loss": 0.1203, + "step": 34091 + }, + { + "epoch": 2.78, + "learning_rate": 1.4797913950456324e-06, + "loss": 0.1587, + "step": 34092 + }, + { + "epoch": 2.78, + "learning_rate": 1.4792481529769667e-06, + "loss": 0.3647, + "step": 34093 + }, + { + "epoch": 2.78, + "learning_rate": 1.478704910908301e-06, + "loss": 0.1997, + "step": 34094 + }, + { + "epoch": 2.78, + "learning_rate": 1.478161668839635e-06, + "loss": 0.1954, + "step": 34095 + }, + { + "epoch": 2.78, + "learning_rate": 1.4776184267709692e-06, + "loss": 0.2636, + "step": 34096 + }, + { + "epoch": 2.78, + "learning_rate": 1.4770751847023036e-06, + "loss": 0.4041, + "step": 34097 + }, + { + "epoch": 2.78, + "learning_rate": 1.4765319426336378e-06, + "loss": 0.183, + "step": 34098 + }, + { + "epoch": 2.78, + "learning_rate": 1.475988700564972e-06, + "loss": 0.2137, + "step": 34099 + }, + { + "epoch": 2.78, + "learning_rate": 1.475445458496306e-06, + "loss": 0.3977, + "step": 34100 + }, + { + "epoch": 2.78, + "learning_rate": 1.4749022164276403e-06, + "loss": 0.2376, + "step": 34101 + }, + { + "epoch": 2.78, + "learning_rate": 1.4743589743589745e-06, + "loss": 0.1028, + "step": 34102 + }, + { + "epoch": 2.78, + "learning_rate": 1.4738157322903088e-06, + "loss": 0.0657, + "step": 34103 + }, + { + "epoch": 2.78, + "learning_rate": 1.4732724902216428e-06, + "loss": 0.0843, + "step": 34104 + }, + { + "epoch": 2.78, + "learning_rate": 1.472729248152977e-06, + "loss": 0.0966, + "step": 34105 + }, + { + "epoch": 2.78, + "learning_rate": 1.4721860060843112e-06, + "loss": 0.1529, + "step": 34106 + }, + { + "epoch": 2.78, + "learning_rate": 1.4716427640156455e-06, + "loss": 0.2438, + "step": 34107 + }, + { + "epoch": 2.78, + "learning_rate": 1.4710995219469797e-06, + "loss": 0.2069, + "step": 34108 + }, + { + "epoch": 2.78, + "learning_rate": 1.4705562798783137e-06, + "loss": 0.1997, + "step": 34109 + }, + { + "epoch": 2.78, + "learning_rate": 1.470013037809648e-06, + "loss": 0.2676, + "step": 34110 + }, + { + "epoch": 2.78, + "learning_rate": 1.4694697957409824e-06, + "loss": 0.4088, + "step": 34111 + }, + { + "epoch": 2.78, + "learning_rate": 1.4689265536723166e-06, + "loss": 0.2307, + "step": 34112 + }, + { + "epoch": 2.78, + "learning_rate": 1.4683833116036509e-06, + "loss": 0.1755, + "step": 34113 + }, + { + "epoch": 2.78, + "learning_rate": 1.4678400695349849e-06, + "loss": 0.2749, + "step": 34114 + }, + { + "epoch": 2.78, + "learning_rate": 1.4672968274663191e-06, + "loss": 0.3256, + "step": 34115 + }, + { + "epoch": 2.78, + "learning_rate": 1.4667535853976533e-06, + "loss": 0.5668, + "step": 34116 + }, + { + "epoch": 2.78, + "learning_rate": 1.4662103433289876e-06, + "loss": 0.1557, + "step": 34117 + }, + { + "epoch": 2.78, + "learning_rate": 1.4656671012603218e-06, + "loss": 0.2882, + "step": 34118 + }, + { + "epoch": 2.78, + "learning_rate": 1.4651238591916558e-06, + "loss": 0.0849, + "step": 34119 + }, + { + "epoch": 2.78, + "learning_rate": 1.46458061712299e-06, + "loss": 0.1386, + "step": 34120 + }, + { + "epoch": 2.78, + "learning_rate": 1.4640373750543243e-06, + "loss": 0.4393, + "step": 34121 + }, + { + "epoch": 2.78, + "learning_rate": 1.4634941329856587e-06, + "loss": 0.4264, + "step": 34122 + }, + { + "epoch": 2.78, + "learning_rate": 1.4629508909169925e-06, + "loss": 0.1191, + "step": 34123 + }, + { + "epoch": 2.78, + "learning_rate": 1.462407648848327e-06, + "loss": 0.3444, + "step": 34124 + }, + { + "epoch": 2.78, + "learning_rate": 1.4618644067796612e-06, + "loss": 0.2115, + "step": 34125 + }, + { + "epoch": 2.78, + "learning_rate": 1.4613211647109954e-06, + "loss": 0.2737, + "step": 34126 + }, + { + "epoch": 2.78, + "learning_rate": 1.4607779226423297e-06, + "loss": 0.1919, + "step": 34127 + }, + { + "epoch": 2.78, + "learning_rate": 1.4602346805736637e-06, + "loss": 0.1431, + "step": 34128 + }, + { + "epoch": 2.78, + "learning_rate": 1.459691438504998e-06, + "loss": 0.2691, + "step": 34129 + }, + { + "epoch": 2.78, + "learning_rate": 1.4591481964363321e-06, + "loss": 0.1269, + "step": 34130 + }, + { + "epoch": 2.78, + "learning_rate": 1.4586049543676664e-06, + "loss": 0.351, + "step": 34131 + }, + { + "epoch": 2.78, + "learning_rate": 1.4580617122990006e-06, + "loss": 0.2533, + "step": 34132 + }, + { + "epoch": 2.78, + "learning_rate": 1.4575184702303346e-06, + "loss": 0.1242, + "step": 34133 + }, + { + "epoch": 2.78, + "learning_rate": 1.4569752281616689e-06, + "loss": 0.049, + "step": 34134 + }, + { + "epoch": 2.78, + "learning_rate": 1.456431986093003e-06, + "loss": 0.2847, + "step": 34135 + }, + { + "epoch": 2.78, + "learning_rate": 1.4558887440243375e-06, + "loss": 0.3178, + "step": 34136 + }, + { + "epoch": 2.78, + "learning_rate": 1.4553455019556718e-06, + "loss": 0.3749, + "step": 34137 + }, + { + "epoch": 2.78, + "learning_rate": 1.4548022598870058e-06, + "loss": 0.4079, + "step": 34138 + }, + { + "epoch": 2.78, + "learning_rate": 1.45425901781834e-06, + "loss": 0.2101, + "step": 34139 + }, + { + "epoch": 2.78, + "learning_rate": 1.4537157757496742e-06, + "loss": 0.1662, + "step": 34140 + }, + { + "epoch": 2.78, + "learning_rate": 1.4531725336810085e-06, + "loss": 0.2664, + "step": 34141 + }, + { + "epoch": 2.78, + "learning_rate": 1.4526292916123425e-06, + "loss": 0.332, + "step": 34142 + }, + { + "epoch": 2.78, + "learning_rate": 1.4520860495436767e-06, + "loss": 0.2412, + "step": 34143 + }, + { + "epoch": 2.78, + "learning_rate": 1.451542807475011e-06, + "loss": 0.0989, + "step": 34144 + }, + { + "epoch": 2.78, + "learning_rate": 1.4509995654063452e-06, + "loss": 0.4031, + "step": 34145 + }, + { + "epoch": 2.78, + "learning_rate": 1.4504563233376794e-06, + "loss": 0.1869, + "step": 34146 + }, + { + "epoch": 2.78, + "learning_rate": 1.4499130812690134e-06, + "loss": 0.4408, + "step": 34147 + }, + { + "epoch": 2.78, + "learning_rate": 1.4493698392003477e-06, + "loss": 0.2535, + "step": 34148 + }, + { + "epoch": 2.78, + "learning_rate": 1.448826597131682e-06, + "loss": 0.2674, + "step": 34149 + }, + { + "epoch": 2.78, + "learning_rate": 1.4482833550630163e-06, + "loss": 0.0858, + "step": 34150 + }, + { + "epoch": 2.78, + "learning_rate": 1.4477401129943506e-06, + "loss": 0.2256, + "step": 34151 + }, + { + "epoch": 2.78, + "learning_rate": 1.4471968709256846e-06, + "loss": 0.0867, + "step": 34152 + }, + { + "epoch": 2.78, + "learning_rate": 1.4466536288570188e-06, + "loss": 0.2782, + "step": 34153 + }, + { + "epoch": 2.78, + "learning_rate": 1.446110386788353e-06, + "loss": 0.1303, + "step": 34154 + }, + { + "epoch": 2.78, + "learning_rate": 1.4455671447196873e-06, + "loss": 0.2058, + "step": 34155 + }, + { + "epoch": 2.78, + "learning_rate": 1.4450239026510215e-06, + "loss": 0.1752, + "step": 34156 + }, + { + "epoch": 2.78, + "learning_rate": 1.4444806605823555e-06, + "loss": 0.2011, + "step": 34157 + }, + { + "epoch": 2.78, + "learning_rate": 1.4439374185136898e-06, + "loss": 0.226, + "step": 34158 + }, + { + "epoch": 2.78, + "learning_rate": 1.443394176445024e-06, + "loss": 0.3575, + "step": 34159 + }, + { + "epoch": 2.78, + "learning_rate": 1.4428509343763582e-06, + "loss": 0.4949, + "step": 34160 + }, + { + "epoch": 2.78, + "learning_rate": 1.4423076923076922e-06, + "loss": 0.3364, + "step": 34161 + }, + { + "epoch": 2.78, + "learning_rate": 1.4417644502390265e-06, + "loss": 0.0417, + "step": 34162 + }, + { + "epoch": 2.78, + "learning_rate": 1.441221208170361e-06, + "loss": 0.2998, + "step": 34163 + }, + { + "epoch": 2.78, + "learning_rate": 1.4406779661016951e-06, + "loss": 0.343, + "step": 34164 + }, + { + "epoch": 2.78, + "learning_rate": 1.4401347240330294e-06, + "loss": 0.1084, + "step": 34165 + }, + { + "epoch": 2.78, + "learning_rate": 1.4395914819643634e-06, + "loss": 0.1903, + "step": 34166 + }, + { + "epoch": 2.78, + "learning_rate": 1.4390482398956976e-06, + "loss": 0.1745, + "step": 34167 + }, + { + "epoch": 2.78, + "learning_rate": 1.4385049978270318e-06, + "loss": 0.247, + "step": 34168 + }, + { + "epoch": 2.78, + "learning_rate": 1.437961755758366e-06, + "loss": 0.1759, + "step": 34169 + }, + { + "epoch": 2.78, + "learning_rate": 1.4374185136897003e-06, + "loss": 0.1305, + "step": 34170 + }, + { + "epoch": 2.78, + "learning_rate": 1.4368752716210343e-06, + "loss": 0.1501, + "step": 34171 + }, + { + "epoch": 2.78, + "learning_rate": 1.4363320295523686e-06, + "loss": 0.1334, + "step": 34172 + }, + { + "epoch": 2.78, + "learning_rate": 1.4357887874837028e-06, + "loss": 0.297, + "step": 34173 + }, + { + "epoch": 2.78, + "learning_rate": 1.4352455454150372e-06, + "loss": 0.3966, + "step": 34174 + }, + { + "epoch": 2.78, + "learning_rate": 1.4347023033463715e-06, + "loss": 0.0267, + "step": 34175 + }, + { + "epoch": 2.78, + "learning_rate": 1.4341590612777055e-06, + "loss": 0.2587, + "step": 34176 + }, + { + "epoch": 2.78, + "learning_rate": 1.4336158192090397e-06, + "loss": 0.1732, + "step": 34177 + }, + { + "epoch": 2.79, + "learning_rate": 1.433072577140374e-06, + "loss": 0.239, + "step": 34178 + }, + { + "epoch": 2.79, + "learning_rate": 1.4325293350717082e-06, + "loss": 0.3256, + "step": 34179 + }, + { + "epoch": 2.79, + "learning_rate": 1.4319860930030422e-06, + "loss": 0.1882, + "step": 34180 + }, + { + "epoch": 2.79, + "learning_rate": 1.4314428509343764e-06, + "loss": 0.2859, + "step": 34181 + }, + { + "epoch": 2.79, + "learning_rate": 1.4308996088657106e-06, + "loss": 0.2992, + "step": 34182 + }, + { + "epoch": 2.79, + "learning_rate": 1.4303563667970449e-06, + "loss": 0.3253, + "step": 34183 + }, + { + "epoch": 2.79, + "learning_rate": 1.4298131247283791e-06, + "loss": 0.2547, + "step": 34184 + }, + { + "epoch": 2.79, + "learning_rate": 1.4292698826597131e-06, + "loss": 0.5275, + "step": 34185 + }, + { + "epoch": 2.79, + "learning_rate": 1.4287266405910474e-06, + "loss": 0.1622, + "step": 34186 + }, + { + "epoch": 2.79, + "learning_rate": 1.4281833985223816e-06, + "loss": 0.0485, + "step": 34187 + }, + { + "epoch": 2.79, + "learning_rate": 1.427640156453716e-06, + "loss": 0.278, + "step": 34188 + }, + { + "epoch": 2.79, + "learning_rate": 1.4270969143850503e-06, + "loss": 0.2057, + "step": 34189 + }, + { + "epoch": 2.79, + "learning_rate": 1.4265536723163843e-06, + "loss": 0.1624, + "step": 34190 + }, + { + "epoch": 2.79, + "learning_rate": 1.4260104302477185e-06, + "loss": 0.0824, + "step": 34191 + }, + { + "epoch": 2.79, + "learning_rate": 1.4254671881790527e-06, + "loss": 0.1997, + "step": 34192 + }, + { + "epoch": 2.79, + "learning_rate": 1.424923946110387e-06, + "loss": 0.6653, + "step": 34193 + }, + { + "epoch": 2.79, + "learning_rate": 1.4243807040417212e-06, + "loss": 0.2529, + "step": 34194 + }, + { + "epoch": 2.79, + "learning_rate": 1.4238374619730552e-06, + "loss": 0.2003, + "step": 34195 + }, + { + "epoch": 2.79, + "learning_rate": 1.4232942199043895e-06, + "loss": 0.2857, + "step": 34196 + }, + { + "epoch": 2.79, + "learning_rate": 1.4227509778357237e-06, + "loss": 0.2794, + "step": 34197 + }, + { + "epoch": 2.79, + "learning_rate": 1.422207735767058e-06, + "loss": 0.1914, + "step": 34198 + }, + { + "epoch": 2.79, + "learning_rate": 1.421664493698392e-06, + "loss": 0.3866, + "step": 34199 + }, + { + "epoch": 2.79, + "learning_rate": 1.4211212516297262e-06, + "loss": 0.284, + "step": 34200 + }, + { + "epoch": 2.79, + "learning_rate": 1.4205780095610606e-06, + "loss": 0.054, + "step": 34201 + }, + { + "epoch": 2.79, + "learning_rate": 1.4200347674923948e-06, + "loss": 0.3248, + "step": 34202 + }, + { + "epoch": 2.79, + "learning_rate": 1.419491525423729e-06, + "loss": 0.1668, + "step": 34203 + }, + { + "epoch": 2.79, + "learning_rate": 1.418948283355063e-06, + "loss": 0.0493, + "step": 34204 + }, + { + "epoch": 2.79, + "learning_rate": 1.4184050412863973e-06, + "loss": 0.3143, + "step": 34205 + }, + { + "epoch": 2.79, + "learning_rate": 1.4178617992177315e-06, + "loss": 0.1515, + "step": 34206 + }, + { + "epoch": 2.79, + "learning_rate": 1.4173185571490658e-06, + "loss": 0.3628, + "step": 34207 + }, + { + "epoch": 2.79, + "learning_rate": 1.4167753150804e-06, + "loss": 0.3171, + "step": 34208 + }, + { + "epoch": 2.79, + "learning_rate": 1.416232073011734e-06, + "loss": 0.4135, + "step": 34209 + }, + { + "epoch": 2.79, + "learning_rate": 1.4156888309430683e-06, + "loss": 0.3862, + "step": 34210 + }, + { + "epoch": 2.79, + "learning_rate": 1.4151455888744025e-06, + "loss": 0.3477, + "step": 34211 + }, + { + "epoch": 2.79, + "learning_rate": 1.414602346805737e-06, + "loss": 0.138, + "step": 34212 + }, + { + "epoch": 2.79, + "learning_rate": 1.4140591047370712e-06, + "loss": 0.2325, + "step": 34213 + }, + { + "epoch": 2.79, + "learning_rate": 1.413515862668405e-06, + "loss": 0.248, + "step": 34214 + }, + { + "epoch": 2.79, + "learning_rate": 1.4129726205997394e-06, + "loss": 0.0254, + "step": 34215 + }, + { + "epoch": 2.79, + "learning_rate": 1.4124293785310736e-06, + "loss": 0.2822, + "step": 34216 + }, + { + "epoch": 2.79, + "learning_rate": 1.4118861364624079e-06, + "loss": 0.3121, + "step": 34217 + }, + { + "epoch": 2.79, + "learning_rate": 1.4113428943937419e-06, + "loss": 0.2031, + "step": 34218 + }, + { + "epoch": 2.79, + "learning_rate": 1.4107996523250761e-06, + "loss": 0.0783, + "step": 34219 + }, + { + "epoch": 2.79, + "learning_rate": 1.4102564102564104e-06, + "loss": 0.2819, + "step": 34220 + }, + { + "epoch": 2.79, + "learning_rate": 1.4097131681877446e-06, + "loss": 0.1911, + "step": 34221 + }, + { + "epoch": 2.79, + "learning_rate": 1.4091699261190788e-06, + "loss": 0.3141, + "step": 34222 + }, + { + "epoch": 2.79, + "learning_rate": 1.4086266840504128e-06, + "loss": 0.1413, + "step": 34223 + }, + { + "epoch": 2.79, + "learning_rate": 1.408083441981747e-06, + "loss": 0.1125, + "step": 34224 + }, + { + "epoch": 2.79, + "learning_rate": 1.4075401999130813e-06, + "loss": 0.3021, + "step": 34225 + }, + { + "epoch": 2.79, + "learning_rate": 1.4069969578444157e-06, + "loss": 0.4962, + "step": 34226 + }, + { + "epoch": 2.79, + "learning_rate": 1.40645371577575e-06, + "loss": 0.2182, + "step": 34227 + }, + { + "epoch": 2.79, + "learning_rate": 1.405910473707084e-06, + "loss": 0.555, + "step": 34228 + }, + { + "epoch": 2.79, + "learning_rate": 1.4053672316384182e-06, + "loss": 0.0538, + "step": 34229 + }, + { + "epoch": 2.79, + "learning_rate": 1.4048239895697524e-06, + "loss": 0.2591, + "step": 34230 + }, + { + "epoch": 2.79, + "learning_rate": 1.4042807475010867e-06, + "loss": 0.4593, + "step": 34231 + }, + { + "epoch": 2.79, + "learning_rate": 1.403737505432421e-06, + "loss": 0.1815, + "step": 34232 + }, + { + "epoch": 2.79, + "learning_rate": 1.403194263363755e-06, + "loss": 0.1132, + "step": 34233 + }, + { + "epoch": 2.79, + "learning_rate": 1.4026510212950892e-06, + "loss": 0.335, + "step": 34234 + }, + { + "epoch": 2.79, + "learning_rate": 1.4021077792264234e-06, + "loss": 0.0678, + "step": 34235 + }, + { + "epoch": 2.79, + "learning_rate": 1.4015645371577576e-06, + "loss": 0.2612, + "step": 34236 + }, + { + "epoch": 2.79, + "learning_rate": 1.4010212950890916e-06, + "loss": 0.1192, + "step": 34237 + }, + { + "epoch": 2.79, + "learning_rate": 1.4004780530204259e-06, + "loss": 0.3579, + "step": 34238 + }, + { + "epoch": 2.79, + "learning_rate": 1.3999348109517603e-06, + "loss": 0.1603, + "step": 34239 + }, + { + "epoch": 2.79, + "learning_rate": 1.3993915688830945e-06, + "loss": 0.2298, + "step": 34240 + }, + { + "epoch": 2.79, + "learning_rate": 1.3988483268144288e-06, + "loss": 0.2366, + "step": 34241 + }, + { + "epoch": 2.79, + "learning_rate": 1.3983050847457628e-06, + "loss": 0.3008, + "step": 34242 + }, + { + "epoch": 2.79, + "learning_rate": 1.397761842677097e-06, + "loss": 0.2239, + "step": 34243 + }, + { + "epoch": 2.79, + "learning_rate": 1.3972186006084312e-06, + "loss": 0.0719, + "step": 34244 + }, + { + "epoch": 2.79, + "learning_rate": 1.3966753585397655e-06, + "loss": 0.2341, + "step": 34245 + }, + { + "epoch": 2.79, + "learning_rate": 1.3961321164710997e-06, + "loss": 0.1531, + "step": 34246 + }, + { + "epoch": 2.79, + "learning_rate": 1.3955888744024337e-06, + "loss": 0.2429, + "step": 34247 + }, + { + "epoch": 2.79, + "learning_rate": 1.395045632333768e-06, + "loss": 0.0961, + "step": 34248 + }, + { + "epoch": 2.79, + "learning_rate": 1.3945023902651022e-06, + "loss": 0.1481, + "step": 34249 + }, + { + "epoch": 2.79, + "learning_rate": 1.3939591481964364e-06, + "loss": 0.1643, + "step": 34250 + }, + { + "epoch": 2.79, + "eval_accuracy": 0.8424859908303617, + "eval_loss": 0.4935804009437561, + "eval_runtime": 22.289, + "eval_samples_per_second": 440.352, + "eval_steps_per_second": 3.455, + "step": 34250 + }, + { + "epoch": 2.79, + "learning_rate": 1.3934159061277709e-06, + "loss": 0.2413, + "step": 34251 + }, + { + "epoch": 2.79, + "learning_rate": 1.3928726640591047e-06, + "loss": 0.0807, + "step": 34252 + }, + { + "epoch": 2.79, + "learning_rate": 1.3923294219904391e-06, + "loss": 0.2442, + "step": 34253 + }, + { + "epoch": 2.79, + "learning_rate": 1.3917861799217733e-06, + "loss": 0.1106, + "step": 34254 + }, + { + "epoch": 2.79, + "learning_rate": 1.3912429378531076e-06, + "loss": 0.1873, + "step": 34255 + }, + { + "epoch": 2.79, + "learning_rate": 1.3906996957844416e-06, + "loss": 0.1097, + "step": 34256 + }, + { + "epoch": 2.79, + "learning_rate": 1.3901564537157758e-06, + "loss": 0.043, + "step": 34257 + }, + { + "epoch": 2.79, + "learning_rate": 1.38961321164711e-06, + "loss": 0.1598, + "step": 34258 + }, + { + "epoch": 2.79, + "learning_rate": 1.3890699695784443e-06, + "loss": 0.1047, + "step": 34259 + }, + { + "epoch": 2.79, + "learning_rate": 1.3885267275097785e-06, + "loss": 0.2445, + "step": 34260 + }, + { + "epoch": 2.79, + "learning_rate": 1.3879834854411125e-06, + "loss": 0.0934, + "step": 34261 + }, + { + "epoch": 2.79, + "learning_rate": 1.3874402433724468e-06, + "loss": 0.1827, + "step": 34262 + }, + { + "epoch": 2.79, + "learning_rate": 1.386897001303781e-06, + "loss": 0.3193, + "step": 34263 + }, + { + "epoch": 2.79, + "learning_rate": 1.3863537592351154e-06, + "loss": 0.2375, + "step": 34264 + }, + { + "epoch": 2.79, + "learning_rate": 1.3858105171664497e-06, + "loss": 0.3263, + "step": 34265 + }, + { + "epoch": 2.79, + "learning_rate": 1.3852672750977837e-06, + "loss": 0.2556, + "step": 34266 + }, + { + "epoch": 2.79, + "learning_rate": 1.384724033029118e-06, + "loss": 0.4152, + "step": 34267 + }, + { + "epoch": 2.79, + "learning_rate": 1.3841807909604521e-06, + "loss": 0.1505, + "step": 34268 + }, + { + "epoch": 2.79, + "learning_rate": 1.3836375488917864e-06, + "loss": 0.3807, + "step": 34269 + }, + { + "epoch": 2.79, + "learning_rate": 1.3830943068231206e-06, + "loss": 0.233, + "step": 34270 + }, + { + "epoch": 2.79, + "learning_rate": 1.3825510647544546e-06, + "loss": 0.2486, + "step": 34271 + }, + { + "epoch": 2.79, + "learning_rate": 1.3820078226857889e-06, + "loss": 0.2542, + "step": 34272 + }, + { + "epoch": 2.79, + "learning_rate": 1.381464580617123e-06, + "loss": 0.4511, + "step": 34273 + }, + { + "epoch": 2.79, + "learning_rate": 1.3809213385484573e-06, + "loss": 0.26, + "step": 34274 + }, + { + "epoch": 2.79, + "learning_rate": 1.3803780964797913e-06, + "loss": 0.1601, + "step": 34275 + }, + { + "epoch": 2.79, + "learning_rate": 1.3798348544111256e-06, + "loss": 0.1457, + "step": 34276 + }, + { + "epoch": 2.79, + "learning_rate": 1.3792916123424598e-06, + "loss": 0.1134, + "step": 34277 + }, + { + "epoch": 2.79, + "learning_rate": 1.3787483702737942e-06, + "loss": 0.202, + "step": 34278 + }, + { + "epoch": 2.79, + "learning_rate": 1.3782051282051285e-06, + "loss": 0.1778, + "step": 34279 + }, + { + "epoch": 2.79, + "learning_rate": 1.3776618861364625e-06, + "loss": 0.166, + "step": 34280 + }, + { + "epoch": 2.79, + "learning_rate": 1.3771186440677967e-06, + "loss": 0.4112, + "step": 34281 + }, + { + "epoch": 2.79, + "learning_rate": 1.376575401999131e-06, + "loss": 0.1476, + "step": 34282 + }, + { + "epoch": 2.79, + "learning_rate": 1.3760321599304652e-06, + "loss": 0.1867, + "step": 34283 + }, + { + "epoch": 2.79, + "learning_rate": 1.3754889178617994e-06, + "loss": 0.2481, + "step": 34284 + }, + { + "epoch": 2.79, + "learning_rate": 1.3749456757931334e-06, + "loss": 0.0566, + "step": 34285 + }, + { + "epoch": 2.79, + "learning_rate": 1.3744024337244677e-06, + "loss": 0.3058, + "step": 34286 + }, + { + "epoch": 2.79, + "learning_rate": 1.3738591916558019e-06, + "loss": 0.2594, + "step": 34287 + }, + { + "epoch": 2.79, + "learning_rate": 1.3733159495871361e-06, + "loss": 0.3166, + "step": 34288 + }, + { + "epoch": 2.79, + "learning_rate": 1.3727727075184706e-06, + "loss": 0.0748, + "step": 34289 + }, + { + "epoch": 2.79, + "learning_rate": 1.3722294654498044e-06, + "loss": 0.2152, + "step": 34290 + }, + { + "epoch": 2.79, + "learning_rate": 1.3716862233811388e-06, + "loss": 0.1462, + "step": 34291 + }, + { + "epoch": 2.79, + "learning_rate": 1.371142981312473e-06, + "loss": 0.0682, + "step": 34292 + }, + { + "epoch": 2.79, + "learning_rate": 1.3705997392438073e-06, + "loss": 0.2239, + "step": 34293 + }, + { + "epoch": 2.79, + "learning_rate": 1.3700564971751413e-06, + "loss": 0.3756, + "step": 34294 + }, + { + "epoch": 2.79, + "learning_rate": 1.3695132551064755e-06, + "loss": 0.1181, + "step": 34295 + }, + { + "epoch": 2.79, + "learning_rate": 1.3689700130378098e-06, + "loss": 0.3826, + "step": 34296 + }, + { + "epoch": 2.79, + "learning_rate": 1.368426770969144e-06, + "loss": 0.1763, + "step": 34297 + }, + { + "epoch": 2.79, + "learning_rate": 1.3678835289004782e-06, + "loss": 0.2793, + "step": 34298 + }, + { + "epoch": 2.79, + "learning_rate": 1.3673402868318122e-06, + "loss": 0.232, + "step": 34299 + }, + { + "epoch": 2.79, + "learning_rate": 1.3667970447631465e-06, + "loss": 0.2506, + "step": 34300 + }, + { + "epoch": 2.8, + "learning_rate": 1.3662538026944807e-06, + "loss": 0.2616, + "step": 34301 + }, + { + "epoch": 2.8, + "learning_rate": 1.365710560625815e-06, + "loss": 0.417, + "step": 34302 + }, + { + "epoch": 2.8, + "learning_rate": 1.3651673185571494e-06, + "loss": 0.173, + "step": 34303 + }, + { + "epoch": 2.8, + "learning_rate": 1.3646240764884832e-06, + "loss": 0.5229, + "step": 34304 + }, + { + "epoch": 2.8, + "learning_rate": 1.3640808344198176e-06, + "loss": 0.0639, + "step": 34305 + }, + { + "epoch": 2.8, + "learning_rate": 1.3635375923511518e-06, + "loss": 0.2487, + "step": 34306 + }, + { + "epoch": 2.8, + "learning_rate": 1.362994350282486e-06, + "loss": 0.2942, + "step": 34307 + }, + { + "epoch": 2.8, + "learning_rate": 1.3624511082138203e-06, + "loss": 0.0621, + "step": 34308 + }, + { + "epoch": 2.8, + "learning_rate": 1.3619078661451543e-06, + "loss": 0.1833, + "step": 34309 + }, + { + "epoch": 2.8, + "learning_rate": 1.3613646240764886e-06, + "loss": 0.0831, + "step": 34310 + }, + { + "epoch": 2.8, + "learning_rate": 1.3608213820078228e-06, + "loss": 0.4114, + "step": 34311 + }, + { + "epoch": 2.8, + "learning_rate": 1.360278139939157e-06, + "loss": 0.1683, + "step": 34312 + }, + { + "epoch": 2.8, + "learning_rate": 1.359734897870491e-06, + "loss": 0.1084, + "step": 34313 + }, + { + "epoch": 2.8, + "learning_rate": 1.3591916558018253e-06, + "loss": 0.2939, + "step": 34314 + }, + { + "epoch": 2.8, + "learning_rate": 1.3586484137331595e-06, + "loss": 0.6709, + "step": 34315 + }, + { + "epoch": 2.8, + "learning_rate": 1.358105171664494e-06, + "loss": 0.3323, + "step": 34316 + }, + { + "epoch": 2.8, + "learning_rate": 1.3575619295958282e-06, + "loss": 0.1929, + "step": 34317 + }, + { + "epoch": 2.8, + "learning_rate": 1.3570186875271622e-06, + "loss": 0.3722, + "step": 34318 + }, + { + "epoch": 2.8, + "learning_rate": 1.3564754454584964e-06, + "loss": 0.2701, + "step": 34319 + }, + { + "epoch": 2.8, + "learning_rate": 1.3559322033898307e-06, + "loss": 0.167, + "step": 34320 + }, + { + "epoch": 2.8, + "learning_rate": 1.3553889613211649e-06, + "loss": 0.4042, + "step": 34321 + }, + { + "epoch": 2.8, + "learning_rate": 1.3548457192524991e-06, + "loss": 0.2223, + "step": 34322 + }, + { + "epoch": 2.8, + "learning_rate": 1.3543024771838331e-06, + "loss": 0.5462, + "step": 34323 + }, + { + "epoch": 2.8, + "learning_rate": 1.3537592351151674e-06, + "loss": 0.1892, + "step": 34324 + }, + { + "epoch": 2.8, + "learning_rate": 1.3532159930465016e-06, + "loss": 0.1612, + "step": 34325 + }, + { + "epoch": 2.8, + "learning_rate": 1.3526727509778358e-06, + "loss": 0.3108, + "step": 34326 + }, + { + "epoch": 2.8, + "learning_rate": 1.3521295089091703e-06, + "loss": 0.3046, + "step": 34327 + }, + { + "epoch": 2.8, + "learning_rate": 1.351586266840504e-06, + "loss": 0.2177, + "step": 34328 + }, + { + "epoch": 2.8, + "learning_rate": 1.3510430247718383e-06, + "loss": 0.1988, + "step": 34329 + }, + { + "epoch": 2.8, + "learning_rate": 1.3504997827031727e-06, + "loss": 0.1909, + "step": 34330 + }, + { + "epoch": 2.8, + "learning_rate": 1.349956540634507e-06, + "loss": 0.4218, + "step": 34331 + }, + { + "epoch": 2.8, + "learning_rate": 1.349413298565841e-06, + "loss": 0.2919, + "step": 34332 + }, + { + "epoch": 2.8, + "learning_rate": 1.3488700564971752e-06, + "loss": 0.0342, + "step": 34333 + }, + { + "epoch": 2.8, + "learning_rate": 1.3483268144285095e-06, + "loss": 0.1806, + "step": 34334 + }, + { + "epoch": 2.8, + "learning_rate": 1.3477835723598437e-06, + "loss": 0.0377, + "step": 34335 + }, + { + "epoch": 2.8, + "learning_rate": 1.347240330291178e-06, + "loss": 0.1735, + "step": 34336 + }, + { + "epoch": 2.8, + "learning_rate": 1.346697088222512e-06, + "loss": 0.215, + "step": 34337 + }, + { + "epoch": 2.8, + "learning_rate": 1.3461538461538462e-06, + "loss": 0.305, + "step": 34338 + }, + { + "epoch": 2.8, + "learning_rate": 1.3456106040851804e-06, + "loss": 0.0857, + "step": 34339 + }, + { + "epoch": 2.8, + "learning_rate": 1.3450673620165146e-06, + "loss": 0.0911, + "step": 34340 + }, + { + "epoch": 2.8, + "learning_rate": 1.344524119947849e-06, + "loss": 0.3884, + "step": 34341 + }, + { + "epoch": 2.8, + "learning_rate": 1.3439808778791829e-06, + "loss": 0.2186, + "step": 34342 + }, + { + "epoch": 2.8, + "learning_rate": 1.3434376358105173e-06, + "loss": 0.0975, + "step": 34343 + }, + { + "epoch": 2.8, + "learning_rate": 1.3428943937418515e-06, + "loss": 0.3754, + "step": 34344 + }, + { + "epoch": 2.8, + "learning_rate": 1.3423511516731858e-06, + "loss": 0.0656, + "step": 34345 + }, + { + "epoch": 2.8, + "learning_rate": 1.34180790960452e-06, + "loss": 0.2454, + "step": 34346 + }, + { + "epoch": 2.8, + "learning_rate": 1.341264667535854e-06, + "loss": 0.2618, + "step": 34347 + }, + { + "epoch": 2.8, + "learning_rate": 1.3407214254671883e-06, + "loss": 0.1596, + "step": 34348 + }, + { + "epoch": 2.8, + "learning_rate": 1.3401781833985225e-06, + "loss": 0.4438, + "step": 34349 + }, + { + "epoch": 2.8, + "learning_rate": 1.3396349413298567e-06, + "loss": 0.1359, + "step": 34350 + }, + { + "epoch": 2.8, + "learning_rate": 1.3390916992611907e-06, + "loss": 0.2127, + "step": 34351 + }, + { + "epoch": 2.8, + "learning_rate": 1.338548457192525e-06, + "loss": 0.1558, + "step": 34352 + }, + { + "epoch": 2.8, + "learning_rate": 1.3380052151238592e-06, + "loss": 0.2021, + "step": 34353 + }, + { + "epoch": 2.8, + "learning_rate": 1.3374619730551936e-06, + "loss": 0.0886, + "step": 34354 + }, + { + "epoch": 2.8, + "learning_rate": 1.3369187309865279e-06, + "loss": 0.1662, + "step": 34355 + }, + { + "epoch": 2.8, + "learning_rate": 1.3363754889178617e-06, + "loss": 0.3121, + "step": 34356 + }, + { + "epoch": 2.8, + "learning_rate": 1.3358322468491961e-06, + "loss": 0.2603, + "step": 34357 + }, + { + "epoch": 2.8, + "learning_rate": 1.3352890047805304e-06, + "loss": 0.2245, + "step": 34358 + }, + { + "epoch": 2.8, + "learning_rate": 1.3347457627118646e-06, + "loss": 0.4855, + "step": 34359 + }, + { + "epoch": 2.8, + "learning_rate": 1.3342025206431988e-06, + "loss": 0.2235, + "step": 34360 + }, + { + "epoch": 2.8, + "learning_rate": 1.3336592785745328e-06, + "loss": 0.2543, + "step": 34361 + }, + { + "epoch": 2.8, + "learning_rate": 1.333116036505867e-06, + "loss": 0.5399, + "step": 34362 + }, + { + "epoch": 2.8, + "learning_rate": 1.3325727944372013e-06, + "loss": 0.1573, + "step": 34363 + }, + { + "epoch": 2.8, + "learning_rate": 1.3320295523685355e-06, + "loss": 0.2206, + "step": 34364 + }, + { + "epoch": 2.8, + "learning_rate": 1.3314863102998698e-06, + "loss": 0.1829, + "step": 34365 + }, + { + "epoch": 2.8, + "learning_rate": 1.3309430682312038e-06, + "loss": 0.0379, + "step": 34366 + }, + { + "epoch": 2.8, + "learning_rate": 1.330399826162538e-06, + "loss": 0.4621, + "step": 34367 + }, + { + "epoch": 2.8, + "learning_rate": 1.3298565840938724e-06, + "loss": 0.3677, + "step": 34368 + }, + { + "epoch": 2.8, + "learning_rate": 1.3293133420252067e-06, + "loss": 0.4274, + "step": 34369 + }, + { + "epoch": 2.8, + "learning_rate": 1.3287700999565407e-06, + "loss": 0.2952, + "step": 34370 + }, + { + "epoch": 2.8, + "learning_rate": 1.328226857887875e-06, + "loss": 0.1504, + "step": 34371 + }, + { + "epoch": 2.8, + "learning_rate": 1.3276836158192092e-06, + "loss": 0.1996, + "step": 34372 + }, + { + "epoch": 2.8, + "learning_rate": 1.3271403737505434e-06, + "loss": 0.0957, + "step": 34373 + }, + { + "epoch": 2.8, + "learning_rate": 1.3265971316818776e-06, + "loss": 0.2137, + "step": 34374 + }, + { + "epoch": 2.8, + "learning_rate": 1.3260538896132116e-06, + "loss": 0.2814, + "step": 34375 + }, + { + "epoch": 2.8, + "learning_rate": 1.3255106475445459e-06, + "loss": 0.2374, + "step": 34376 + }, + { + "epoch": 2.8, + "learning_rate": 1.32496740547588e-06, + "loss": 0.363, + "step": 34377 + }, + { + "epoch": 2.8, + "learning_rate": 1.3244241634072143e-06, + "loss": 0.1161, + "step": 34378 + }, + { + "epoch": 2.8, + "learning_rate": 1.3238809213385488e-06, + "loss": 0.186, + "step": 34379 + }, + { + "epoch": 2.8, + "learning_rate": 1.3233376792698826e-06, + "loss": 0.1323, + "step": 34380 + }, + { + "epoch": 2.8, + "learning_rate": 1.322794437201217e-06, + "loss": 0.2834, + "step": 34381 + }, + { + "epoch": 2.8, + "learning_rate": 1.3222511951325513e-06, + "loss": 0.1781, + "step": 34382 + }, + { + "epoch": 2.8, + "learning_rate": 1.3217079530638855e-06, + "loss": 0.4638, + "step": 34383 + }, + { + "epoch": 2.8, + "learning_rate": 1.3211647109952197e-06, + "loss": 0.3667, + "step": 34384 + }, + { + "epoch": 2.8, + "learning_rate": 1.3206214689265537e-06, + "loss": 0.1763, + "step": 34385 + }, + { + "epoch": 2.8, + "learning_rate": 1.320078226857888e-06, + "loss": 0.2298, + "step": 34386 + }, + { + "epoch": 2.8, + "learning_rate": 1.3195349847892222e-06, + "loss": 0.2604, + "step": 34387 + }, + { + "epoch": 2.8, + "learning_rate": 1.3189917427205564e-06, + "loss": 0.2191, + "step": 34388 + }, + { + "epoch": 2.8, + "learning_rate": 1.3184485006518907e-06, + "loss": 0.4268, + "step": 34389 + }, + { + "epoch": 2.8, + "learning_rate": 1.3179052585832247e-06, + "loss": 0.202, + "step": 34390 + }, + { + "epoch": 2.8, + "learning_rate": 1.317362016514559e-06, + "loss": 0.2735, + "step": 34391 + }, + { + "epoch": 2.8, + "learning_rate": 1.3168187744458931e-06, + "loss": 0.2008, + "step": 34392 + }, + { + "epoch": 2.8, + "learning_rate": 1.3162755323772276e-06, + "loss": 0.0584, + "step": 34393 + }, + { + "epoch": 2.8, + "learning_rate": 1.3157322903085614e-06, + "loss": 0.1247, + "step": 34394 + }, + { + "epoch": 2.8, + "learning_rate": 1.3151890482398958e-06, + "loss": 0.1343, + "step": 34395 + }, + { + "epoch": 2.8, + "learning_rate": 1.31464580617123e-06, + "loss": 0.3462, + "step": 34396 + }, + { + "epoch": 2.8, + "learning_rate": 1.3141025641025643e-06, + "loss": 0.0887, + "step": 34397 + }, + { + "epoch": 2.8, + "learning_rate": 1.3135593220338985e-06, + "loss": 0.1936, + "step": 34398 + }, + { + "epoch": 2.8, + "learning_rate": 1.3130160799652325e-06, + "loss": 0.3778, + "step": 34399 + }, + { + "epoch": 2.8, + "learning_rate": 1.3124728378965668e-06, + "loss": 0.2885, + "step": 34400 + }, + { + "epoch": 2.8, + "learning_rate": 1.311929595827901e-06, + "loss": 0.2081, + "step": 34401 + }, + { + "epoch": 2.8, + "learning_rate": 1.3113863537592352e-06, + "loss": 0.2238, + "step": 34402 + }, + { + "epoch": 2.8, + "learning_rate": 1.3108431116905695e-06, + "loss": 0.4, + "step": 34403 + }, + { + "epoch": 2.8, + "learning_rate": 1.3102998696219035e-06, + "loss": 0.2117, + "step": 34404 + }, + { + "epoch": 2.8, + "learning_rate": 1.3097566275532377e-06, + "loss": 0.2874, + "step": 34405 + }, + { + "epoch": 2.8, + "learning_rate": 1.3092133854845721e-06, + "loss": 0.3426, + "step": 34406 + }, + { + "epoch": 2.8, + "learning_rate": 1.3086701434159064e-06, + "loss": 0.2417, + "step": 34407 + }, + { + "epoch": 2.8, + "learning_rate": 1.3081269013472406e-06, + "loss": 0.1144, + "step": 34408 + }, + { + "epoch": 2.8, + "learning_rate": 1.3075836592785746e-06, + "loss": 0.1972, + "step": 34409 + }, + { + "epoch": 2.8, + "learning_rate": 1.3070404172099089e-06, + "loss": 0.3179, + "step": 34410 + }, + { + "epoch": 2.8, + "learning_rate": 1.306497175141243e-06, + "loss": 0.1043, + "step": 34411 + }, + { + "epoch": 2.8, + "learning_rate": 1.3059539330725773e-06, + "loss": 0.1183, + "step": 34412 + }, + { + "epoch": 2.8, + "learning_rate": 1.3054106910039113e-06, + "loss": 0.1907, + "step": 34413 + }, + { + "epoch": 2.8, + "learning_rate": 1.3048674489352456e-06, + "loss": 0.123, + "step": 34414 + }, + { + "epoch": 2.8, + "learning_rate": 1.3043242068665798e-06, + "loss": 0.0832, + "step": 34415 + }, + { + "epoch": 2.8, + "learning_rate": 1.303780964797914e-06, + "loss": 0.3531, + "step": 34416 + }, + { + "epoch": 2.8, + "learning_rate": 1.3032377227292483e-06, + "loss": 0.2589, + "step": 34417 + }, + { + "epoch": 2.8, + "learning_rate": 1.3026944806605823e-06, + "loss": 0.2454, + "step": 34418 + }, + { + "epoch": 2.8, + "learning_rate": 1.3021512385919165e-06, + "loss": 0.1448, + "step": 34419 + }, + { + "epoch": 2.8, + "learning_rate": 1.301607996523251e-06, + "loss": 0.2012, + "step": 34420 + }, + { + "epoch": 2.8, + "learning_rate": 1.3010647544545852e-06, + "loss": 0.0783, + "step": 34421 + }, + { + "epoch": 2.8, + "learning_rate": 1.3005215123859194e-06, + "loss": 0.2717, + "step": 34422 + }, + { + "epoch": 2.81, + "learning_rate": 1.2999782703172534e-06, + "loss": 0.1726, + "step": 34423 + }, + { + "epoch": 2.81, + "learning_rate": 1.2994350282485877e-06, + "loss": 0.1649, + "step": 34424 + }, + { + "epoch": 2.81, + "learning_rate": 1.298891786179922e-06, + "loss": 0.2249, + "step": 34425 + }, + { + "epoch": 2.81, + "learning_rate": 1.2983485441112561e-06, + "loss": 0.4266, + "step": 34426 + }, + { + "epoch": 2.81, + "learning_rate": 1.2978053020425904e-06, + "loss": 0.1896, + "step": 34427 + }, + { + "epoch": 2.81, + "learning_rate": 1.2972620599739244e-06, + "loss": 0.259, + "step": 34428 + }, + { + "epoch": 2.81, + "learning_rate": 1.2967188179052586e-06, + "loss": 0.2365, + "step": 34429 + }, + { + "epoch": 2.81, + "learning_rate": 1.2961755758365928e-06, + "loss": 0.0867, + "step": 34430 + }, + { + "epoch": 2.81, + "learning_rate": 1.2956323337679273e-06, + "loss": 0.1372, + "step": 34431 + }, + { + "epoch": 2.81, + "learning_rate": 1.295089091699261e-06, + "loss": 0.2202, + "step": 34432 + }, + { + "epoch": 2.81, + "learning_rate": 1.2945458496305955e-06, + "loss": 0.1695, + "step": 34433 + }, + { + "epoch": 2.81, + "learning_rate": 1.2940026075619298e-06, + "loss": 0.076, + "step": 34434 + }, + { + "epoch": 2.81, + "learning_rate": 1.293459365493264e-06, + "loss": 0.4064, + "step": 34435 + }, + { + "epoch": 2.81, + "learning_rate": 1.2929161234245982e-06, + "loss": 0.4369, + "step": 34436 + }, + { + "epoch": 2.81, + "learning_rate": 1.2923728813559322e-06, + "loss": 0.2328, + "step": 34437 + }, + { + "epoch": 2.81, + "learning_rate": 1.2918296392872665e-06, + "loss": 0.1721, + "step": 34438 + }, + { + "epoch": 2.81, + "learning_rate": 1.2912863972186007e-06, + "loss": 0.3388, + "step": 34439 + }, + { + "epoch": 2.81, + "learning_rate": 1.290743155149935e-06, + "loss": 0.5854, + "step": 34440 + }, + { + "epoch": 2.81, + "learning_rate": 1.2901999130812692e-06, + "loss": 0.1951, + "step": 34441 + }, + { + "epoch": 2.81, + "learning_rate": 1.2896566710126032e-06, + "loss": 0.2737, + "step": 34442 + }, + { + "epoch": 2.81, + "learning_rate": 1.2891134289439374e-06, + "loss": 0.1786, + "step": 34443 + }, + { + "epoch": 2.81, + "learning_rate": 1.2885701868752716e-06, + "loss": 0.4027, + "step": 34444 + }, + { + "epoch": 2.81, + "learning_rate": 1.288026944806606e-06, + "loss": 0.2058, + "step": 34445 + }, + { + "epoch": 2.81, + "learning_rate": 1.2874837027379403e-06, + "loss": 0.2385, + "step": 34446 + }, + { + "epoch": 2.81, + "learning_rate": 1.2869404606692743e-06, + "loss": 0.2541, + "step": 34447 + }, + { + "epoch": 2.81, + "learning_rate": 1.2863972186006086e-06, + "loss": 0.1796, + "step": 34448 + }, + { + "epoch": 2.81, + "learning_rate": 1.2858539765319428e-06, + "loss": 0.1817, + "step": 34449 + }, + { + "epoch": 2.81, + "learning_rate": 1.285310734463277e-06, + "loss": 0.0253, + "step": 34450 + }, + { + "epoch": 2.81, + "learning_rate": 1.284767492394611e-06, + "loss": 0.14, + "step": 34451 + }, + { + "epoch": 2.81, + "learning_rate": 1.2842242503259453e-06, + "loss": 0.2762, + "step": 34452 + }, + { + "epoch": 2.81, + "learning_rate": 1.2836810082572795e-06, + "loss": 0.2238, + "step": 34453 + }, + { + "epoch": 2.81, + "learning_rate": 1.2831377661886137e-06, + "loss": 0.3904, + "step": 34454 + }, + { + "epoch": 2.81, + "learning_rate": 1.282594524119948e-06, + "loss": 0.378, + "step": 34455 + }, + { + "epoch": 2.81, + "learning_rate": 1.282051282051282e-06, + "loss": 0.0661, + "step": 34456 + }, + { + "epoch": 2.81, + "learning_rate": 1.2815080399826162e-06, + "loss": 0.2499, + "step": 34457 + }, + { + "epoch": 2.81, + "learning_rate": 1.2809647979139507e-06, + "loss": 0.4776, + "step": 34458 + }, + { + "epoch": 2.81, + "learning_rate": 1.2804215558452849e-06, + "loss": 0.2781, + "step": 34459 + }, + { + "epoch": 2.81, + "learning_rate": 1.2798783137766191e-06, + "loss": 0.1376, + "step": 34460 + }, + { + "epoch": 2.81, + "learning_rate": 1.2793350717079531e-06, + "loss": 0.1819, + "step": 34461 + }, + { + "epoch": 2.81, + "learning_rate": 1.2787918296392874e-06, + "loss": 0.3115, + "step": 34462 + }, + { + "epoch": 2.81, + "learning_rate": 1.2782485875706216e-06, + "loss": 0.1103, + "step": 34463 + }, + { + "epoch": 2.81, + "learning_rate": 1.2777053455019558e-06, + "loss": 0.1355, + "step": 34464 + }, + { + "epoch": 2.81, + "learning_rate": 1.27716210343329e-06, + "loss": 0.2319, + "step": 34465 + }, + { + "epoch": 2.81, + "learning_rate": 1.276618861364624e-06, + "loss": 0.3127, + "step": 34466 + }, + { + "epoch": 2.81, + "learning_rate": 1.2760756192959583e-06, + "loss": 0.1963, + "step": 34467 + }, + { + "epoch": 2.81, + "learning_rate": 1.2755323772272925e-06, + "loss": 0.1508, + "step": 34468 + }, + { + "epoch": 2.81, + "learning_rate": 1.274989135158627e-06, + "loss": 0.3982, + "step": 34469 + }, + { + "epoch": 2.81, + "learning_rate": 1.2744458930899608e-06, + "loss": 0.2901, + "step": 34470 + }, + { + "epoch": 2.81, + "learning_rate": 1.273902651021295e-06, + "loss": 0.1376, + "step": 34471 + }, + { + "epoch": 2.81, + "learning_rate": 1.2733594089526295e-06, + "loss": 0.1962, + "step": 34472 + }, + { + "epoch": 2.81, + "learning_rate": 1.2728161668839637e-06, + "loss": 0.093, + "step": 34473 + }, + { + "epoch": 2.81, + "learning_rate": 1.272272924815298e-06, + "loss": 0.4289, + "step": 34474 + }, + { + "epoch": 2.81, + "learning_rate": 1.271729682746632e-06, + "loss": 0.2193, + "step": 34475 + }, + { + "epoch": 2.81, + "learning_rate": 1.2711864406779662e-06, + "loss": 0.3099, + "step": 34476 + }, + { + "epoch": 2.81, + "learning_rate": 1.2706431986093004e-06, + "loss": 0.1813, + "step": 34477 + }, + { + "epoch": 2.81, + "learning_rate": 1.2700999565406346e-06, + "loss": 0.4296, + "step": 34478 + }, + { + "epoch": 2.81, + "learning_rate": 1.2695567144719689e-06, + "loss": 0.1299, + "step": 34479 + }, + { + "epoch": 2.81, + "learning_rate": 1.2690134724033029e-06, + "loss": 0.2128, + "step": 34480 + }, + { + "epoch": 2.81, + "learning_rate": 1.2684702303346371e-06, + "loss": 0.3128, + "step": 34481 + }, + { + "epoch": 2.81, + "learning_rate": 1.2679269882659713e-06, + "loss": 0.2319, + "step": 34482 + }, + { + "epoch": 2.81, + "learning_rate": 1.2673837461973058e-06, + "loss": 0.3478, + "step": 34483 + }, + { + "epoch": 2.81, + "learning_rate": 1.26684050412864e-06, + "loss": 0.247, + "step": 34484 + }, + { + "epoch": 2.81, + "learning_rate": 1.266297262059974e-06, + "loss": 0.1582, + "step": 34485 + }, + { + "epoch": 2.81, + "learning_rate": 1.2657540199913083e-06, + "loss": 0.1553, + "step": 34486 + }, + { + "epoch": 2.81, + "learning_rate": 1.2652107779226425e-06, + "loss": 0.3258, + "step": 34487 + }, + { + "epoch": 2.81, + "learning_rate": 1.2646675358539767e-06, + "loss": 0.2136, + "step": 34488 + }, + { + "epoch": 2.81, + "learning_rate": 1.2641242937853107e-06, + "loss": 0.2692, + "step": 34489 + }, + { + "epoch": 2.81, + "learning_rate": 1.263581051716645e-06, + "loss": 0.37, + "step": 34490 + }, + { + "epoch": 2.81, + "learning_rate": 1.2630378096479792e-06, + "loss": 0.2758, + "step": 34491 + }, + { + "epoch": 2.81, + "learning_rate": 1.2624945675793134e-06, + "loss": 0.1493, + "step": 34492 + }, + { + "epoch": 2.81, + "learning_rate": 1.2619513255106477e-06, + "loss": 0.1408, + "step": 34493 + }, + { + "epoch": 2.81, + "learning_rate": 1.2614080834419817e-06, + "loss": 0.5116, + "step": 34494 + }, + { + "epoch": 2.81, + "learning_rate": 1.260864841373316e-06, + "loss": 0.2121, + "step": 34495 + }, + { + "epoch": 2.81, + "learning_rate": 1.2603215993046504e-06, + "loss": 0.1806, + "step": 34496 + }, + { + "epoch": 2.81, + "learning_rate": 1.2597783572359846e-06, + "loss": 0.2817, + "step": 34497 + }, + { + "epoch": 2.81, + "learning_rate": 1.2592351151673188e-06, + "loss": 0.3107, + "step": 34498 + }, + { + "epoch": 2.81, + "learning_rate": 1.2586918730986528e-06, + "loss": 0.1067, + "step": 34499 + }, + { + "epoch": 2.81, + "learning_rate": 1.258148631029987e-06, + "loss": 0.3067, + "step": 34500 + }, + { + "epoch": 2.81, + "eval_accuracy": 0.84381049414162, + "eval_loss": 0.49146604537963867, + "eval_runtime": 22.2699, + "eval_samples_per_second": 440.73, + "eval_steps_per_second": 3.458, + "step": 34500 + }, + { + "epoch": 2.81, + "learning_rate": 1.2576053889613213e-06, + "loss": 0.1872, + "step": 34501 + }, + { + "epoch": 2.81, + "learning_rate": 1.2570621468926555e-06, + "loss": 0.1155, + "step": 34502 + }, + { + "epoch": 2.81, + "learning_rate": 1.2565189048239898e-06, + "loss": 0.1224, + "step": 34503 + }, + { + "epoch": 2.81, + "learning_rate": 1.2559756627553238e-06, + "loss": 0.1275, + "step": 34504 + }, + { + "epoch": 2.81, + "learning_rate": 1.255432420686658e-06, + "loss": 0.2367, + "step": 34505 + }, + { + "epoch": 2.81, + "learning_rate": 1.2548891786179922e-06, + "loss": 0.1252, + "step": 34506 + }, + { + "epoch": 2.81, + "learning_rate": 1.2543459365493265e-06, + "loss": 0.1931, + "step": 34507 + }, + { + "epoch": 2.81, + "learning_rate": 1.2538026944806605e-06, + "loss": 0.1572, + "step": 34508 + }, + { + "epoch": 2.81, + "learning_rate": 1.2532594524119947e-06, + "loss": 0.2198, + "step": 34509 + }, + { + "epoch": 2.81, + "learning_rate": 1.2527162103433292e-06, + "loss": 0.1486, + "step": 34510 + }, + { + "epoch": 2.81, + "learning_rate": 1.2521729682746634e-06, + "loss": 0.2461, + "step": 34511 + }, + { + "epoch": 2.81, + "learning_rate": 1.2516297262059976e-06, + "loss": 0.1221, + "step": 34512 + }, + { + "epoch": 2.81, + "learning_rate": 1.2510864841373316e-06, + "loss": 0.1426, + "step": 34513 + }, + { + "epoch": 2.81, + "learning_rate": 1.2505432420686659e-06, + "loss": 0.384, + "step": 34514 + }, + { + "epoch": 2.81, + "learning_rate": 1.25e-06, + "loss": 0.2448, + "step": 34515 + }, + { + "epoch": 2.81, + "learning_rate": 1.2494567579313343e-06, + "loss": 0.2119, + "step": 34516 + }, + { + "epoch": 2.81, + "learning_rate": 1.2489135158626686e-06, + "loss": 0.2139, + "step": 34517 + }, + { + "epoch": 2.81, + "learning_rate": 1.2483702737940028e-06, + "loss": 0.3327, + "step": 34518 + }, + { + "epoch": 2.81, + "learning_rate": 1.2478270317253368e-06, + "loss": 0.4274, + "step": 34519 + }, + { + "epoch": 2.81, + "learning_rate": 1.247283789656671e-06, + "loss": 0.4165, + "step": 34520 + }, + { + "epoch": 2.81, + "learning_rate": 1.2467405475880053e-06, + "loss": 0.2452, + "step": 34521 + }, + { + "epoch": 2.81, + "learning_rate": 1.2461973055193395e-06, + "loss": 0.2998, + "step": 34522 + }, + { + "epoch": 2.81, + "learning_rate": 1.2456540634506737e-06, + "loss": 0.1916, + "step": 34523 + }, + { + "epoch": 2.81, + "learning_rate": 1.245110821382008e-06, + "loss": 0.0805, + "step": 34524 + }, + { + "epoch": 2.81, + "learning_rate": 1.2445675793133422e-06, + "loss": 0.0966, + "step": 34525 + }, + { + "epoch": 2.81, + "learning_rate": 1.2440243372446762e-06, + "loss": 0.2449, + "step": 34526 + }, + { + "epoch": 2.81, + "learning_rate": 1.2434810951760104e-06, + "loss": 0.2369, + "step": 34527 + }, + { + "epoch": 2.81, + "learning_rate": 1.2429378531073449e-06, + "loss": 0.2368, + "step": 34528 + }, + { + "epoch": 2.81, + "learning_rate": 1.242394611038679e-06, + "loss": 0.169, + "step": 34529 + }, + { + "epoch": 2.81, + "learning_rate": 1.2418513689700131e-06, + "loss": 0.0782, + "step": 34530 + }, + { + "epoch": 2.81, + "learning_rate": 1.2413081269013474e-06, + "loss": 0.2787, + "step": 34531 + }, + { + "epoch": 2.81, + "learning_rate": 1.2407648848326816e-06, + "loss": 0.3226, + "step": 34532 + }, + { + "epoch": 2.81, + "learning_rate": 1.2402216427640156e-06, + "loss": 0.1488, + "step": 34533 + }, + { + "epoch": 2.81, + "learning_rate": 1.2396784006953498e-06, + "loss": 0.2864, + "step": 34534 + }, + { + "epoch": 2.81, + "learning_rate": 1.2391351586266843e-06, + "loss": 0.1762, + "step": 34535 + }, + { + "epoch": 2.81, + "learning_rate": 1.2385919165580183e-06, + "loss": 0.4555, + "step": 34536 + }, + { + "epoch": 2.81, + "learning_rate": 1.2380486744893525e-06, + "loss": 0.5388, + "step": 34537 + }, + { + "epoch": 2.81, + "learning_rate": 1.2375054324206868e-06, + "loss": 0.354, + "step": 34538 + }, + { + "epoch": 2.81, + "learning_rate": 1.236962190352021e-06, + "loss": 0.203, + "step": 34539 + }, + { + "epoch": 2.81, + "learning_rate": 1.236418948283355e-06, + "loss": 0.2565, + "step": 34540 + }, + { + "epoch": 2.81, + "learning_rate": 1.2358757062146895e-06, + "loss": 0.1299, + "step": 34541 + }, + { + "epoch": 2.81, + "learning_rate": 1.2353324641460237e-06, + "loss": 0.1719, + "step": 34542 + }, + { + "epoch": 2.81, + "learning_rate": 1.2347892220773577e-06, + "loss": 0.0857, + "step": 34543 + }, + { + "epoch": 2.81, + "learning_rate": 1.234245980008692e-06, + "loss": 0.2537, + "step": 34544 + }, + { + "epoch": 2.81, + "learning_rate": 1.2337027379400262e-06, + "loss": 0.2565, + "step": 34545 + }, + { + "epoch": 2.82, + "learning_rate": 1.2331594958713604e-06, + "loss": 0.2049, + "step": 34546 + }, + { + "epoch": 2.82, + "learning_rate": 1.2326162538026946e-06, + "loss": 0.0954, + "step": 34547 + }, + { + "epoch": 2.82, + "learning_rate": 1.2320730117340289e-06, + "loss": 0.1833, + "step": 34548 + }, + { + "epoch": 2.82, + "learning_rate": 1.231529769665363e-06, + "loss": 0.3475, + "step": 34549 + }, + { + "epoch": 2.82, + "learning_rate": 1.2309865275966971e-06, + "loss": 0.2341, + "step": 34550 + }, + { + "epoch": 2.82, + "learning_rate": 1.2304432855280313e-06, + "loss": 0.4347, + "step": 34551 + }, + { + "epoch": 2.82, + "learning_rate": 1.2299000434593656e-06, + "loss": 0.0915, + "step": 34552 + }, + { + "epoch": 2.82, + "learning_rate": 1.2293568013906998e-06, + "loss": 0.3304, + "step": 34553 + }, + { + "epoch": 2.82, + "learning_rate": 1.228813559322034e-06, + "loss": 0.3291, + "step": 34554 + }, + { + "epoch": 2.82, + "learning_rate": 1.2282703172533683e-06, + "loss": 0.2429, + "step": 34555 + }, + { + "epoch": 2.82, + "learning_rate": 1.2277270751847025e-06, + "loss": 0.276, + "step": 34556 + }, + { + "epoch": 2.82, + "learning_rate": 1.2271838331160365e-06, + "loss": 0.2505, + "step": 34557 + }, + { + "epoch": 2.82, + "learning_rate": 1.2266405910473707e-06, + "loss": 0.367, + "step": 34558 + }, + { + "epoch": 2.82, + "learning_rate": 1.226097348978705e-06, + "loss": 0.3106, + "step": 34559 + }, + { + "epoch": 2.82, + "learning_rate": 1.2255541069100392e-06, + "loss": 0.1921, + "step": 34560 + }, + { + "epoch": 2.82, + "learning_rate": 1.2250108648413734e-06, + "loss": 0.2546, + "step": 34561 + }, + { + "epoch": 2.82, + "learning_rate": 1.2244676227727077e-06, + "loss": 0.1424, + "step": 34562 + }, + { + "epoch": 2.82, + "learning_rate": 1.223924380704042e-06, + "loss": 0.2177, + "step": 34563 + }, + { + "epoch": 2.82, + "learning_rate": 1.223381138635376e-06, + "loss": 0.1784, + "step": 34564 + }, + { + "epoch": 2.82, + "learning_rate": 1.2228378965667101e-06, + "loss": 0.2411, + "step": 34565 + }, + { + "epoch": 2.82, + "learning_rate": 1.2222946544980446e-06, + "loss": 0.2551, + "step": 34566 + }, + { + "epoch": 2.82, + "learning_rate": 1.2217514124293786e-06, + "loss": 0.0622, + "step": 34567 + }, + { + "epoch": 2.82, + "learning_rate": 1.2212081703607128e-06, + "loss": 0.0879, + "step": 34568 + }, + { + "epoch": 2.82, + "learning_rate": 1.220664928292047e-06, + "loss": 0.1427, + "step": 34569 + }, + { + "epoch": 2.82, + "learning_rate": 1.2201216862233813e-06, + "loss": 0.4007, + "step": 34570 + }, + { + "epoch": 2.82, + "learning_rate": 1.2195784441547153e-06, + "loss": 0.2842, + "step": 34571 + }, + { + "epoch": 2.82, + "learning_rate": 1.2190352020860495e-06, + "loss": 0.3854, + "step": 34572 + }, + { + "epoch": 2.82, + "learning_rate": 1.218491960017384e-06, + "loss": 0.1388, + "step": 34573 + }, + { + "epoch": 2.82, + "learning_rate": 1.217948717948718e-06, + "loss": 0.2459, + "step": 34574 + }, + { + "epoch": 2.82, + "learning_rate": 1.2174054758800522e-06, + "loss": 0.1523, + "step": 34575 + }, + { + "epoch": 2.82, + "learning_rate": 1.2168622338113865e-06, + "loss": 0.1441, + "step": 34576 + }, + { + "epoch": 2.82, + "learning_rate": 1.2163189917427207e-06, + "loss": 0.1717, + "step": 34577 + }, + { + "epoch": 2.82, + "learning_rate": 1.2157757496740547e-06, + "loss": 0.0989, + "step": 34578 + }, + { + "epoch": 2.82, + "learning_rate": 1.215232507605389e-06, + "loss": 0.2425, + "step": 34579 + }, + { + "epoch": 2.82, + "learning_rate": 1.2146892655367234e-06, + "loss": 0.2276, + "step": 34580 + }, + { + "epoch": 2.82, + "learning_rate": 1.2141460234680574e-06, + "loss": 0.0753, + "step": 34581 + }, + { + "epoch": 2.82, + "learning_rate": 1.2136027813993916e-06, + "loss": 0.2375, + "step": 34582 + }, + { + "epoch": 2.82, + "learning_rate": 1.2130595393307259e-06, + "loss": 0.3883, + "step": 34583 + }, + { + "epoch": 2.82, + "learning_rate": 1.21251629726206e-06, + "loss": 0.1625, + "step": 34584 + }, + { + "epoch": 2.82, + "learning_rate": 1.2119730551933943e-06, + "loss": 0.2882, + "step": 34585 + }, + { + "epoch": 2.82, + "learning_rate": 1.2114298131247286e-06, + "loss": 0.1071, + "step": 34586 + }, + { + "epoch": 2.82, + "learning_rate": 1.2108865710560628e-06, + "loss": 0.1775, + "step": 34587 + }, + { + "epoch": 2.82, + "learning_rate": 1.2103433289873968e-06, + "loss": 0.4663, + "step": 34588 + }, + { + "epoch": 2.82, + "learning_rate": 1.209800086918731e-06, + "loss": 0.3013, + "step": 34589 + }, + { + "epoch": 2.82, + "learning_rate": 1.2092568448500653e-06, + "loss": 0.3158, + "step": 34590 + }, + { + "epoch": 2.82, + "learning_rate": 1.2087136027813995e-06, + "loss": 0.1564, + "step": 34591 + }, + { + "epoch": 2.82, + "learning_rate": 1.2081703607127337e-06, + "loss": 0.0867, + "step": 34592 + }, + { + "epoch": 2.82, + "learning_rate": 1.207627118644068e-06, + "loss": 0.2484, + "step": 34593 + }, + { + "epoch": 2.82, + "learning_rate": 1.2070838765754022e-06, + "loss": 0.1507, + "step": 34594 + }, + { + "epoch": 2.82, + "learning_rate": 1.2065406345067362e-06, + "loss": 0.0755, + "step": 34595 + }, + { + "epoch": 2.82, + "learning_rate": 1.2059973924380704e-06, + "loss": 0.1588, + "step": 34596 + }, + { + "epoch": 2.82, + "learning_rate": 1.2054541503694047e-06, + "loss": 0.0719, + "step": 34597 + }, + { + "epoch": 2.82, + "learning_rate": 1.204910908300739e-06, + "loss": 0.3443, + "step": 34598 + }, + { + "epoch": 2.82, + "learning_rate": 1.2043676662320731e-06, + "loss": 0.2699, + "step": 34599 + }, + { + "epoch": 2.82, + "learning_rate": 1.2038244241634074e-06, + "loss": 0.076, + "step": 34600 + }, + { + "epoch": 2.82, + "learning_rate": 1.2032811820947416e-06, + "loss": 0.152, + "step": 34601 + }, + { + "epoch": 2.82, + "learning_rate": 1.2027379400260756e-06, + "loss": 0.1252, + "step": 34602 + }, + { + "epoch": 2.82, + "learning_rate": 1.2021946979574098e-06, + "loss": 0.0518, + "step": 34603 + }, + { + "epoch": 2.82, + "learning_rate": 1.201651455888744e-06, + "loss": 0.1178, + "step": 34604 + }, + { + "epoch": 2.82, + "learning_rate": 1.2011082138200783e-06, + "loss": 0.2889, + "step": 34605 + }, + { + "epoch": 2.82, + "learning_rate": 1.2005649717514125e-06, + "loss": 0.1613, + "step": 34606 + }, + { + "epoch": 2.82, + "learning_rate": 1.2000217296827468e-06, + "loss": 0.1782, + "step": 34607 + }, + { + "epoch": 2.82, + "learning_rate": 1.199478487614081e-06, + "loss": 0.3389, + "step": 34608 + }, + { + "epoch": 2.82, + "learning_rate": 1.198935245545415e-06, + "loss": 0.1214, + "step": 34609 + }, + { + "epoch": 2.82, + "learning_rate": 1.1983920034767493e-06, + "loss": 0.1514, + "step": 34610 + }, + { + "epoch": 2.82, + "learning_rate": 1.1978487614080837e-06, + "loss": 0.2552, + "step": 34611 + }, + { + "epoch": 2.82, + "learning_rate": 1.1973055193394177e-06, + "loss": 0.2411, + "step": 34612 + }, + { + "epoch": 2.82, + "learning_rate": 1.196762277270752e-06, + "loss": 0.4123, + "step": 34613 + }, + { + "epoch": 2.82, + "learning_rate": 1.1962190352020862e-06, + "loss": 0.4201, + "step": 34614 + }, + { + "epoch": 2.82, + "learning_rate": 1.1956757931334204e-06, + "loss": 0.2129, + "step": 34615 + }, + { + "epoch": 2.82, + "learning_rate": 1.1951325510647546e-06, + "loss": 0.5507, + "step": 34616 + }, + { + "epoch": 2.82, + "learning_rate": 1.1945893089960887e-06, + "loss": 0.0735, + "step": 34617 + }, + { + "epoch": 2.82, + "learning_rate": 1.194046066927423e-06, + "loss": 0.2976, + "step": 34618 + }, + { + "epoch": 2.82, + "learning_rate": 1.1935028248587571e-06, + "loss": 0.2516, + "step": 34619 + }, + { + "epoch": 2.82, + "learning_rate": 1.1929595827900913e-06, + "loss": 0.0751, + "step": 34620 + }, + { + "epoch": 2.82, + "learning_rate": 1.1924163407214256e-06, + "loss": 0.0746, + "step": 34621 + }, + { + "epoch": 2.82, + "learning_rate": 1.1918730986527598e-06, + "loss": 0.4937, + "step": 34622 + }, + { + "epoch": 2.82, + "learning_rate": 1.191329856584094e-06, + "loss": 0.3656, + "step": 34623 + }, + { + "epoch": 2.82, + "learning_rate": 1.190786614515428e-06, + "loss": 0.2087, + "step": 34624 + }, + { + "epoch": 2.82, + "learning_rate": 1.1902433724467625e-06, + "loss": 0.1437, + "step": 34625 + }, + { + "epoch": 2.82, + "learning_rate": 1.1897001303780965e-06, + "loss": 0.1083, + "step": 34626 + }, + { + "epoch": 2.82, + "learning_rate": 1.1891568883094307e-06, + "loss": 0.3644, + "step": 34627 + }, + { + "epoch": 2.82, + "learning_rate": 1.188613646240765e-06, + "loss": 0.2192, + "step": 34628 + }, + { + "epoch": 2.82, + "learning_rate": 1.1880704041720992e-06, + "loss": 0.1622, + "step": 34629 + }, + { + "epoch": 2.82, + "learning_rate": 1.1875271621034334e-06, + "loss": 0.4496, + "step": 34630 + }, + { + "epoch": 2.82, + "learning_rate": 1.1869839200347675e-06, + "loss": 0.0501, + "step": 34631 + }, + { + "epoch": 2.82, + "learning_rate": 1.186440677966102e-06, + "loss": 0.1642, + "step": 34632 + }, + { + "epoch": 2.82, + "learning_rate": 1.185897435897436e-06, + "loss": 0.1912, + "step": 34633 + }, + { + "epoch": 2.82, + "learning_rate": 1.1853541938287701e-06, + "loss": 0.2415, + "step": 34634 + }, + { + "epoch": 2.82, + "learning_rate": 1.1848109517601044e-06, + "loss": 0.0778, + "step": 34635 + }, + { + "epoch": 2.82, + "learning_rate": 1.1842677096914386e-06, + "loss": 0.0664, + "step": 34636 + }, + { + "epoch": 2.82, + "learning_rate": 1.1837244676227728e-06, + "loss": 0.0957, + "step": 34637 + }, + { + "epoch": 2.82, + "learning_rate": 1.183181225554107e-06, + "loss": 0.2407, + "step": 34638 + }, + { + "epoch": 2.82, + "learning_rate": 1.1826379834854413e-06, + "loss": 0.2474, + "step": 34639 + }, + { + "epoch": 2.82, + "learning_rate": 1.1820947414167753e-06, + "loss": 0.0795, + "step": 34640 + }, + { + "epoch": 2.82, + "learning_rate": 1.1815514993481096e-06, + "loss": 0.2635, + "step": 34641 + }, + { + "epoch": 2.82, + "learning_rate": 1.1810082572794438e-06, + "loss": 0.3971, + "step": 34642 + }, + { + "epoch": 2.82, + "learning_rate": 1.180465015210778e-06, + "loss": 0.2035, + "step": 34643 + }, + { + "epoch": 2.82, + "learning_rate": 1.1799217731421122e-06, + "loss": 0.2093, + "step": 34644 + }, + { + "epoch": 2.82, + "learning_rate": 1.1793785310734465e-06, + "loss": 0.0922, + "step": 34645 + }, + { + "epoch": 2.82, + "learning_rate": 1.1788352890047807e-06, + "loss": 0.1728, + "step": 34646 + }, + { + "epoch": 2.82, + "learning_rate": 1.1782920469361147e-06, + "loss": 0.1663, + "step": 34647 + }, + { + "epoch": 2.82, + "learning_rate": 1.177748804867449e-06, + "loss": 0.227, + "step": 34648 + }, + { + "epoch": 2.82, + "learning_rate": 1.1772055627987832e-06, + "loss": 0.1967, + "step": 34649 + }, + { + "epoch": 2.82, + "learning_rate": 1.1766623207301174e-06, + "loss": 0.2082, + "step": 34650 + }, + { + "epoch": 2.82, + "learning_rate": 1.1761190786614516e-06, + "loss": 0.1577, + "step": 34651 + }, + { + "epoch": 2.82, + "learning_rate": 1.1755758365927859e-06, + "loss": 0.2164, + "step": 34652 + }, + { + "epoch": 2.82, + "learning_rate": 1.17503259452412e-06, + "loss": 0.3803, + "step": 34653 + }, + { + "epoch": 2.82, + "learning_rate": 1.1744893524554543e-06, + "loss": 0.1718, + "step": 34654 + }, + { + "epoch": 2.82, + "learning_rate": 1.1739461103867884e-06, + "loss": 0.1917, + "step": 34655 + }, + { + "epoch": 2.82, + "learning_rate": 1.1734028683181228e-06, + "loss": 0.125, + "step": 34656 + }, + { + "epoch": 2.82, + "learning_rate": 1.1728596262494568e-06, + "loss": 0.2144, + "step": 34657 + }, + { + "epoch": 2.82, + "learning_rate": 1.172316384180791e-06, + "loss": 0.2891, + "step": 34658 + }, + { + "epoch": 2.82, + "learning_rate": 1.1717731421121253e-06, + "loss": 0.1904, + "step": 34659 + }, + { + "epoch": 2.82, + "learning_rate": 1.1712299000434595e-06, + "loss": 0.1386, + "step": 34660 + }, + { + "epoch": 2.82, + "learning_rate": 1.1706866579747937e-06, + "loss": 0.1695, + "step": 34661 + }, + { + "epoch": 2.82, + "learning_rate": 1.1701434159061278e-06, + "loss": 0.1966, + "step": 34662 + }, + { + "epoch": 2.82, + "learning_rate": 1.1696001738374622e-06, + "loss": 0.3079, + "step": 34663 + }, + { + "epoch": 2.82, + "learning_rate": 1.1690569317687962e-06, + "loss": 0.4709, + "step": 34664 + }, + { + "epoch": 2.82, + "learning_rate": 1.1685136897001304e-06, + "loss": 0.3086, + "step": 34665 + }, + { + "epoch": 2.82, + "learning_rate": 1.1679704476314647e-06, + "loss": 0.2242, + "step": 34666 + }, + { + "epoch": 2.82, + "learning_rate": 1.167427205562799e-06, + "loss": 0.4707, + "step": 34667 + }, + { + "epoch": 2.82, + "learning_rate": 1.1668839634941331e-06, + "loss": 0.2036, + "step": 34668 + }, + { + "epoch": 2.83, + "learning_rate": 1.1663407214254672e-06, + "loss": 0.3965, + "step": 34669 + }, + { + "epoch": 2.83, + "learning_rate": 1.1657974793568016e-06, + "loss": 0.2487, + "step": 34670 + }, + { + "epoch": 2.83, + "learning_rate": 1.1652542372881356e-06, + "loss": 0.5383, + "step": 34671 + }, + { + "epoch": 2.83, + "learning_rate": 1.1647109952194699e-06, + "loss": 0.1509, + "step": 34672 + }, + { + "epoch": 2.83, + "learning_rate": 1.164167753150804e-06, + "loss": 0.292, + "step": 34673 + }, + { + "epoch": 2.83, + "learning_rate": 1.1636245110821383e-06, + "loss": 0.2729, + "step": 34674 + }, + { + "epoch": 2.83, + "learning_rate": 1.1630812690134725e-06, + "loss": 0.1658, + "step": 34675 + }, + { + "epoch": 2.83, + "learning_rate": 1.1625380269448066e-06, + "loss": 0.0944, + "step": 34676 + }, + { + "epoch": 2.83, + "learning_rate": 1.161994784876141e-06, + "loss": 0.2534, + "step": 34677 + }, + { + "epoch": 2.83, + "learning_rate": 1.161451542807475e-06, + "loss": 0.1353, + "step": 34678 + }, + { + "epoch": 2.83, + "learning_rate": 1.1609083007388093e-06, + "loss": 0.2312, + "step": 34679 + }, + { + "epoch": 2.83, + "learning_rate": 1.1603650586701435e-06, + "loss": 0.1433, + "step": 34680 + }, + { + "epoch": 2.83, + "learning_rate": 1.1598218166014777e-06, + "loss": 0.183, + "step": 34681 + }, + { + "epoch": 2.83, + "learning_rate": 1.159278574532812e-06, + "loss": 0.2325, + "step": 34682 + }, + { + "epoch": 2.83, + "learning_rate": 1.1587353324641462e-06, + "loss": 0.251, + "step": 34683 + }, + { + "epoch": 2.83, + "learning_rate": 1.1581920903954804e-06, + "loss": 0.169, + "step": 34684 + }, + { + "epoch": 2.83, + "learning_rate": 1.1576488483268144e-06, + "loss": 0.3057, + "step": 34685 + }, + { + "epoch": 2.83, + "learning_rate": 1.1571056062581487e-06, + "loss": 0.3179, + "step": 34686 + }, + { + "epoch": 2.83, + "learning_rate": 1.1565623641894829e-06, + "loss": 0.1628, + "step": 34687 + }, + { + "epoch": 2.83, + "learning_rate": 1.1560191221208171e-06, + "loss": 0.3911, + "step": 34688 + }, + { + "epoch": 2.83, + "learning_rate": 1.1554758800521513e-06, + "loss": 0.0937, + "step": 34689 + }, + { + "epoch": 2.83, + "learning_rate": 1.1549326379834856e-06, + "loss": 0.5158, + "step": 34690 + }, + { + "epoch": 2.83, + "learning_rate": 1.1543893959148198e-06, + "loss": 0.1762, + "step": 34691 + }, + { + "epoch": 2.83, + "learning_rate": 1.153846153846154e-06, + "loss": 0.0743, + "step": 34692 + }, + { + "epoch": 2.83, + "learning_rate": 1.153302911777488e-06, + "loss": 0.3147, + "step": 34693 + }, + { + "epoch": 2.83, + "learning_rate": 1.1527596697088223e-06, + "loss": 0.1567, + "step": 34694 + }, + { + "epoch": 2.83, + "learning_rate": 1.1522164276401565e-06, + "loss": 0.2237, + "step": 34695 + }, + { + "epoch": 2.83, + "learning_rate": 1.1516731855714907e-06, + "loss": 0.1052, + "step": 34696 + }, + { + "epoch": 2.83, + "learning_rate": 1.151129943502825e-06, + "loss": 0.408, + "step": 34697 + }, + { + "epoch": 2.83, + "learning_rate": 1.1505867014341592e-06, + "loss": 0.3713, + "step": 34698 + }, + { + "epoch": 2.83, + "learning_rate": 1.1500434593654934e-06, + "loss": 0.1032, + "step": 34699 + }, + { + "epoch": 2.83, + "learning_rate": 1.1495002172968275e-06, + "loss": 0.0776, + "step": 34700 + }, + { + "epoch": 2.83, + "learning_rate": 1.148956975228162e-06, + "loss": 0.1152, + "step": 34701 + }, + { + "epoch": 2.83, + "learning_rate": 1.148413733159496e-06, + "loss": 0.1749, + "step": 34702 + }, + { + "epoch": 2.83, + "learning_rate": 1.1478704910908302e-06, + "loss": 0.1915, + "step": 34703 + }, + { + "epoch": 2.83, + "learning_rate": 1.1473272490221644e-06, + "loss": 0.2403, + "step": 34704 + }, + { + "epoch": 2.83, + "learning_rate": 1.1467840069534986e-06, + "loss": 0.1117, + "step": 34705 + }, + { + "epoch": 2.83, + "learning_rate": 1.1462407648848328e-06, + "loss": 0.2817, + "step": 34706 + }, + { + "epoch": 2.83, + "learning_rate": 1.1456975228161669e-06, + "loss": 0.1531, + "step": 34707 + }, + { + "epoch": 2.83, + "learning_rate": 1.1451542807475013e-06, + "loss": 0.1625, + "step": 34708 + }, + { + "epoch": 2.83, + "learning_rate": 1.1446110386788353e-06, + "loss": 0.0465, + "step": 34709 + }, + { + "epoch": 2.83, + "learning_rate": 1.1440677966101696e-06, + "loss": 0.2254, + "step": 34710 + }, + { + "epoch": 2.83, + "learning_rate": 1.1435245545415038e-06, + "loss": 0.5373, + "step": 34711 + }, + { + "epoch": 2.83, + "learning_rate": 1.142981312472838e-06, + "loss": 0.1447, + "step": 34712 + }, + { + "epoch": 2.83, + "learning_rate": 1.1424380704041722e-06, + "loss": 0.627, + "step": 34713 + }, + { + "epoch": 2.83, + "learning_rate": 1.1418948283355063e-06, + "loss": 0.2999, + "step": 34714 + }, + { + "epoch": 2.83, + "learning_rate": 1.1413515862668407e-06, + "loss": 0.1302, + "step": 34715 + }, + { + "epoch": 2.83, + "learning_rate": 1.1408083441981747e-06, + "loss": 0.1915, + "step": 34716 + }, + { + "epoch": 2.83, + "learning_rate": 1.140265102129509e-06, + "loss": 0.319, + "step": 34717 + }, + { + "epoch": 2.83, + "learning_rate": 1.1397218600608432e-06, + "loss": 0.4032, + "step": 34718 + }, + { + "epoch": 2.83, + "learning_rate": 1.1391786179921774e-06, + "loss": 0.1191, + "step": 34719 + }, + { + "epoch": 2.83, + "learning_rate": 1.1386353759235116e-06, + "loss": 0.2678, + "step": 34720 + }, + { + "epoch": 2.83, + "learning_rate": 1.1380921338548457e-06, + "loss": 0.157, + "step": 34721 + }, + { + "epoch": 2.83, + "learning_rate": 1.1375488917861801e-06, + "loss": 0.2518, + "step": 34722 + }, + { + "epoch": 2.83, + "learning_rate": 1.1370056497175141e-06, + "loss": 0.1699, + "step": 34723 + }, + { + "epoch": 2.83, + "learning_rate": 1.1364624076488484e-06, + "loss": 0.146, + "step": 34724 + }, + { + "epoch": 2.83, + "learning_rate": 1.1359191655801826e-06, + "loss": 0.2166, + "step": 34725 + }, + { + "epoch": 2.83, + "learning_rate": 1.1353759235115168e-06, + "loss": 0.1269, + "step": 34726 + }, + { + "epoch": 2.83, + "learning_rate": 1.134832681442851e-06, + "loss": 0.1464, + "step": 34727 + }, + { + "epoch": 2.83, + "learning_rate": 1.1342894393741853e-06, + "loss": 0.2232, + "step": 34728 + }, + { + "epoch": 2.83, + "learning_rate": 1.1337461973055195e-06, + "loss": 0.0525, + "step": 34729 + }, + { + "epoch": 2.83, + "learning_rate": 1.1332029552368537e-06, + "loss": 0.1653, + "step": 34730 + }, + { + "epoch": 2.83, + "learning_rate": 1.1326597131681878e-06, + "loss": 0.442, + "step": 34731 + }, + { + "epoch": 2.83, + "learning_rate": 1.132116471099522e-06, + "loss": 0.1215, + "step": 34732 + }, + { + "epoch": 2.83, + "learning_rate": 1.1315732290308562e-06, + "loss": 0.2835, + "step": 34733 + }, + { + "epoch": 2.83, + "learning_rate": 1.1310299869621905e-06, + "loss": 0.1659, + "step": 34734 + }, + { + "epoch": 2.83, + "learning_rate": 1.1304867448935247e-06, + "loss": 0.1057, + "step": 34735 + }, + { + "epoch": 2.83, + "learning_rate": 1.129943502824859e-06, + "loss": 0.1776, + "step": 34736 + }, + { + "epoch": 2.83, + "learning_rate": 1.1294002607561931e-06, + "loss": 0.3136, + "step": 34737 + }, + { + "epoch": 2.83, + "learning_rate": 1.1288570186875272e-06, + "loss": 0.1348, + "step": 34738 + }, + { + "epoch": 2.83, + "learning_rate": 1.1283137766188614e-06, + "loss": 0.2256, + "step": 34739 + }, + { + "epoch": 2.83, + "learning_rate": 1.1277705345501956e-06, + "loss": 0.1027, + "step": 34740 + }, + { + "epoch": 2.83, + "learning_rate": 1.1272272924815299e-06, + "loss": 0.1552, + "step": 34741 + }, + { + "epoch": 2.83, + "learning_rate": 1.126684050412864e-06, + "loss": 0.23, + "step": 34742 + }, + { + "epoch": 2.83, + "learning_rate": 1.1261408083441983e-06, + "loss": 0.5452, + "step": 34743 + }, + { + "epoch": 2.83, + "learning_rate": 1.1255975662755325e-06, + "loss": 0.1487, + "step": 34744 + }, + { + "epoch": 2.83, + "learning_rate": 1.1250543242068666e-06, + "loss": 0.0907, + "step": 34745 + }, + { + "epoch": 2.83, + "learning_rate": 1.1245110821382008e-06, + "loss": 0.151, + "step": 34746 + }, + { + "epoch": 2.83, + "learning_rate": 1.123967840069535e-06, + "loss": 0.3045, + "step": 34747 + }, + { + "epoch": 2.83, + "learning_rate": 1.1234245980008693e-06, + "loss": 0.1828, + "step": 34748 + }, + { + "epoch": 2.83, + "learning_rate": 1.1228813559322035e-06, + "loss": 0.1094, + "step": 34749 + }, + { + "epoch": 2.83, + "learning_rate": 1.1223381138635377e-06, + "loss": 0.1945, + "step": 34750 + }, + { + "epoch": 2.83, + "eval_accuracy": 0.8416709118695873, + "eval_loss": 0.49926239252090454, + "eval_runtime": 22.2675, + "eval_samples_per_second": 440.777, + "eval_steps_per_second": 3.458, + "step": 34750 + }, + { + "epoch": 2.83, + "learning_rate": 1.121794871794872e-06, + "loss": 0.3911, + "step": 34751 + }, + { + "epoch": 2.83, + "learning_rate": 1.121251629726206e-06, + "loss": 0.3842, + "step": 34752 + }, + { + "epoch": 2.83, + "learning_rate": 1.1207083876575404e-06, + "loss": 0.3249, + "step": 34753 + }, + { + "epoch": 2.83, + "learning_rate": 1.1201651455888744e-06, + "loss": 0.2323, + "step": 34754 + }, + { + "epoch": 2.83, + "learning_rate": 1.1196219035202087e-06, + "loss": 0.1188, + "step": 34755 + }, + { + "epoch": 2.83, + "learning_rate": 1.1190786614515429e-06, + "loss": 0.1343, + "step": 34756 + }, + { + "epoch": 2.83, + "learning_rate": 1.1185354193828771e-06, + "loss": 0.1864, + "step": 34757 + }, + { + "epoch": 2.83, + "learning_rate": 1.1179921773142113e-06, + "loss": 0.2087, + "step": 34758 + }, + { + "epoch": 2.83, + "learning_rate": 1.1174489352455454e-06, + "loss": 0.3128, + "step": 34759 + }, + { + "epoch": 2.83, + "learning_rate": 1.1169056931768798e-06, + "loss": 0.375, + "step": 34760 + }, + { + "epoch": 2.83, + "learning_rate": 1.116362451108214e-06, + "loss": 0.4146, + "step": 34761 + }, + { + "epoch": 2.83, + "learning_rate": 1.115819209039548e-06, + "loss": 0.357, + "step": 34762 + }, + { + "epoch": 2.83, + "learning_rate": 1.1152759669708823e-06, + "loss": 0.2364, + "step": 34763 + }, + { + "epoch": 2.83, + "learning_rate": 1.1147327249022165e-06, + "loss": 0.1639, + "step": 34764 + }, + { + "epoch": 2.83, + "learning_rate": 1.1141894828335508e-06, + "loss": 0.1515, + "step": 34765 + }, + { + "epoch": 2.83, + "learning_rate": 1.1136462407648848e-06, + "loss": 0.1233, + "step": 34766 + }, + { + "epoch": 2.83, + "learning_rate": 1.1131029986962192e-06, + "loss": 0.1942, + "step": 34767 + }, + { + "epoch": 2.83, + "learning_rate": 1.1125597566275534e-06, + "loss": 0.3728, + "step": 34768 + }, + { + "epoch": 2.83, + "learning_rate": 1.1120165145588875e-06, + "loss": 0.2284, + "step": 34769 + }, + { + "epoch": 2.83, + "learning_rate": 1.1114732724902217e-06, + "loss": 0.2681, + "step": 34770 + }, + { + "epoch": 2.83, + "learning_rate": 1.110930030421556e-06, + "loss": 0.4258, + "step": 34771 + }, + { + "epoch": 2.83, + "learning_rate": 1.1103867883528902e-06, + "loss": 0.3354, + "step": 34772 + }, + { + "epoch": 2.83, + "learning_rate": 1.1098435462842242e-06, + "loss": 0.1923, + "step": 34773 + }, + { + "epoch": 2.83, + "learning_rate": 1.1093003042155586e-06, + "loss": 0.3754, + "step": 34774 + }, + { + "epoch": 2.83, + "learning_rate": 1.1087570621468928e-06, + "loss": 0.4091, + "step": 34775 + }, + { + "epoch": 2.83, + "learning_rate": 1.1082138200782269e-06, + "loss": 0.098, + "step": 34776 + }, + { + "epoch": 2.83, + "learning_rate": 1.107670578009561e-06, + "loss": 0.5071, + "step": 34777 + }, + { + "epoch": 2.83, + "learning_rate": 1.1071273359408953e-06, + "loss": 0.1523, + "step": 34778 + }, + { + "epoch": 2.83, + "learning_rate": 1.1065840938722296e-06, + "loss": 0.4222, + "step": 34779 + }, + { + "epoch": 2.83, + "learning_rate": 1.1060408518035638e-06, + "loss": 0.3608, + "step": 34780 + }, + { + "epoch": 2.83, + "learning_rate": 1.105497609734898e-06, + "loss": 0.3422, + "step": 34781 + }, + { + "epoch": 2.83, + "learning_rate": 1.1049543676662322e-06, + "loss": 0.0488, + "step": 34782 + }, + { + "epoch": 2.83, + "learning_rate": 1.1044111255975663e-06, + "loss": 0.239, + "step": 34783 + }, + { + "epoch": 2.83, + "learning_rate": 1.1038678835289005e-06, + "loss": 0.1796, + "step": 34784 + }, + { + "epoch": 2.83, + "learning_rate": 1.1033246414602347e-06, + "loss": 0.215, + "step": 34785 + }, + { + "epoch": 2.83, + "learning_rate": 1.102781399391569e-06, + "loss": 0.3103, + "step": 34786 + }, + { + "epoch": 2.83, + "learning_rate": 1.1022381573229032e-06, + "loss": 0.2435, + "step": 34787 + }, + { + "epoch": 2.83, + "learning_rate": 1.1016949152542374e-06, + "loss": 0.3308, + "step": 34788 + }, + { + "epoch": 2.83, + "learning_rate": 1.1011516731855716e-06, + "loss": 0.1649, + "step": 34789 + }, + { + "epoch": 2.83, + "learning_rate": 1.1006084311169057e-06, + "loss": 0.0519, + "step": 34790 + }, + { + "epoch": 2.83, + "learning_rate": 1.10006518904824e-06, + "loss": 0.2093, + "step": 34791 + }, + { + "epoch": 2.84, + "learning_rate": 1.0995219469795741e-06, + "loss": 0.0597, + "step": 34792 + }, + { + "epoch": 2.84, + "learning_rate": 1.0989787049109084e-06, + "loss": 0.2355, + "step": 34793 + }, + { + "epoch": 2.84, + "learning_rate": 1.0984354628422426e-06, + "loss": 0.207, + "step": 34794 + }, + { + "epoch": 2.84, + "learning_rate": 1.0978922207735768e-06, + "loss": 0.1756, + "step": 34795 + }, + { + "epoch": 2.84, + "learning_rate": 1.097348978704911e-06, + "loss": 0.3397, + "step": 34796 + }, + { + "epoch": 2.84, + "learning_rate": 1.096805736636245e-06, + "loss": 0.2079, + "step": 34797 + }, + { + "epoch": 2.84, + "learning_rate": 1.0962624945675795e-06, + "loss": 0.1401, + "step": 34798 + }, + { + "epoch": 2.84, + "learning_rate": 1.0957192524989137e-06, + "loss": 0.0774, + "step": 34799 + }, + { + "epoch": 2.84, + "learning_rate": 1.0951760104302478e-06, + "loss": 0.2517, + "step": 34800 + }, + { + "epoch": 2.84, + "learning_rate": 1.094632768361582e-06, + "loss": 0.2271, + "step": 34801 + }, + { + "epoch": 2.84, + "learning_rate": 1.0940895262929162e-06, + "loss": 0.3628, + "step": 34802 + }, + { + "epoch": 2.84, + "learning_rate": 1.0935462842242505e-06, + "loss": 0.5293, + "step": 34803 + }, + { + "epoch": 2.84, + "learning_rate": 1.0930030421555845e-06, + "loss": 0.1814, + "step": 34804 + }, + { + "epoch": 2.84, + "learning_rate": 1.092459800086919e-06, + "loss": 0.1345, + "step": 34805 + }, + { + "epoch": 2.84, + "learning_rate": 1.0919165580182531e-06, + "loss": 0.1087, + "step": 34806 + }, + { + "epoch": 2.84, + "learning_rate": 1.0913733159495872e-06, + "loss": 0.2476, + "step": 34807 + }, + { + "epoch": 2.84, + "learning_rate": 1.0908300738809214e-06, + "loss": 0.4705, + "step": 34808 + }, + { + "epoch": 2.84, + "learning_rate": 1.0902868318122556e-06, + "loss": 0.2219, + "step": 34809 + }, + { + "epoch": 2.84, + "learning_rate": 1.0897435897435899e-06, + "loss": 0.1611, + "step": 34810 + }, + { + "epoch": 2.84, + "learning_rate": 1.0892003476749239e-06, + "loss": 0.1255, + "step": 34811 + }, + { + "epoch": 2.84, + "learning_rate": 1.0886571056062583e-06, + "loss": 0.2239, + "step": 34812 + }, + { + "epoch": 2.84, + "learning_rate": 1.0881138635375925e-06, + "loss": 0.072, + "step": 34813 + }, + { + "epoch": 2.84, + "learning_rate": 1.0875706214689266e-06, + "loss": 0.4197, + "step": 34814 + }, + { + "epoch": 2.84, + "learning_rate": 1.0870273794002608e-06, + "loss": 0.0522, + "step": 34815 + }, + { + "epoch": 2.84, + "learning_rate": 1.086484137331595e-06, + "loss": 0.0641, + "step": 34816 + }, + { + "epoch": 2.84, + "learning_rate": 1.0859408952629293e-06, + "loss": 0.3094, + "step": 34817 + }, + { + "epoch": 2.84, + "learning_rate": 1.0853976531942635e-06, + "loss": 0.3477, + "step": 34818 + }, + { + "epoch": 2.84, + "learning_rate": 1.0848544111255977e-06, + "loss": 0.1002, + "step": 34819 + }, + { + "epoch": 2.84, + "learning_rate": 1.084311169056932e-06, + "loss": 0.1428, + "step": 34820 + }, + { + "epoch": 2.84, + "learning_rate": 1.083767926988266e-06, + "loss": 0.2582, + "step": 34821 + }, + { + "epoch": 2.84, + "learning_rate": 1.0832246849196002e-06, + "loss": 0.7298, + "step": 34822 + }, + { + "epoch": 2.84, + "learning_rate": 1.0826814428509344e-06, + "loss": 0.0454, + "step": 34823 + }, + { + "epoch": 2.84, + "learning_rate": 1.0821382007822687e-06, + "loss": 0.4628, + "step": 34824 + }, + { + "epoch": 2.84, + "learning_rate": 1.0815949587136029e-06, + "loss": 0.1283, + "step": 34825 + }, + { + "epoch": 2.84, + "learning_rate": 1.0810517166449371e-06, + "loss": 0.2264, + "step": 34826 + }, + { + "epoch": 2.84, + "learning_rate": 1.0805084745762714e-06, + "loss": 0.6501, + "step": 34827 + }, + { + "epoch": 2.84, + "learning_rate": 1.0799652325076054e-06, + "loss": 0.0619, + "step": 34828 + }, + { + "epoch": 2.84, + "learning_rate": 1.0794219904389396e-06, + "loss": 0.1454, + "step": 34829 + }, + { + "epoch": 2.84, + "learning_rate": 1.0788787483702738e-06, + "loss": 0.211, + "step": 34830 + }, + { + "epoch": 2.84, + "learning_rate": 1.078335506301608e-06, + "loss": 0.317, + "step": 34831 + }, + { + "epoch": 2.84, + "learning_rate": 1.0777922642329423e-06, + "loss": 0.2467, + "step": 34832 + }, + { + "epoch": 2.84, + "learning_rate": 1.0772490221642765e-06, + "loss": 0.3826, + "step": 34833 + }, + { + "epoch": 2.84, + "learning_rate": 1.0767057800956108e-06, + "loss": 0.2607, + "step": 34834 + }, + { + "epoch": 2.84, + "learning_rate": 1.0761625380269448e-06, + "loss": 0.1898, + "step": 34835 + }, + { + "epoch": 2.84, + "learning_rate": 1.075619295958279e-06, + "loss": 0.3309, + "step": 34836 + }, + { + "epoch": 2.84, + "learning_rate": 1.0750760538896134e-06, + "loss": 0.2258, + "step": 34837 + }, + { + "epoch": 2.84, + "learning_rate": 1.0745328118209475e-06, + "loss": 0.5556, + "step": 34838 + }, + { + "epoch": 2.84, + "learning_rate": 1.0739895697522817e-06, + "loss": 0.2264, + "step": 34839 + }, + { + "epoch": 2.84, + "learning_rate": 1.073446327683616e-06, + "loss": 0.2562, + "step": 34840 + }, + { + "epoch": 2.84, + "learning_rate": 1.0729030856149502e-06, + "loss": 0.3179, + "step": 34841 + }, + { + "epoch": 2.84, + "learning_rate": 1.0723598435462842e-06, + "loss": 0.3109, + "step": 34842 + }, + { + "epoch": 2.84, + "learning_rate": 1.0718166014776186e-06, + "loss": 0.1941, + "step": 34843 + }, + { + "epoch": 2.84, + "learning_rate": 1.0712733594089528e-06, + "loss": 0.2813, + "step": 34844 + }, + { + "epoch": 2.84, + "learning_rate": 1.0707301173402869e-06, + "loss": 0.2425, + "step": 34845 + }, + { + "epoch": 2.84, + "learning_rate": 1.070186875271621e-06, + "loss": 0.2963, + "step": 34846 + }, + { + "epoch": 2.84, + "learning_rate": 1.0696436332029553e-06, + "loss": 0.1402, + "step": 34847 + }, + { + "epoch": 2.84, + "learning_rate": 1.0691003911342896e-06, + "loss": 0.4319, + "step": 34848 + }, + { + "epoch": 2.84, + "learning_rate": 1.0685571490656236e-06, + "loss": 0.1541, + "step": 34849 + }, + { + "epoch": 2.84, + "learning_rate": 1.068013906996958e-06, + "loss": 0.2789, + "step": 34850 + }, + { + "epoch": 2.84, + "learning_rate": 1.0674706649282922e-06, + "loss": 0.1253, + "step": 34851 + }, + { + "epoch": 2.84, + "learning_rate": 1.0669274228596263e-06, + "loss": 0.1817, + "step": 34852 + }, + { + "epoch": 2.84, + "learning_rate": 1.0663841807909605e-06, + "loss": 0.5782, + "step": 34853 + }, + { + "epoch": 2.84, + "learning_rate": 1.0658409387222947e-06, + "loss": 0.2003, + "step": 34854 + }, + { + "epoch": 2.84, + "learning_rate": 1.065297696653629e-06, + "loss": 0.1919, + "step": 34855 + }, + { + "epoch": 2.84, + "learning_rate": 1.0647544545849632e-06, + "loss": 0.3966, + "step": 34856 + }, + { + "epoch": 2.84, + "learning_rate": 1.0642112125162974e-06, + "loss": 0.3351, + "step": 34857 + }, + { + "epoch": 2.84, + "learning_rate": 1.0636679704476317e-06, + "loss": 0.2681, + "step": 34858 + }, + { + "epoch": 2.84, + "learning_rate": 1.0631247283789657e-06, + "loss": 0.2019, + "step": 34859 + }, + { + "epoch": 2.84, + "learning_rate": 1.0625814863103e-06, + "loss": 0.2076, + "step": 34860 + }, + { + "epoch": 2.84, + "learning_rate": 1.0620382442416341e-06, + "loss": 0.3089, + "step": 34861 + }, + { + "epoch": 2.84, + "learning_rate": 1.0614950021729684e-06, + "loss": 0.0434, + "step": 34862 + }, + { + "epoch": 2.84, + "learning_rate": 1.0609517601043026e-06, + "loss": 0.0869, + "step": 34863 + }, + { + "epoch": 2.84, + "learning_rate": 1.0604085180356368e-06, + "loss": 0.2621, + "step": 34864 + }, + { + "epoch": 2.84, + "learning_rate": 1.059865275966971e-06, + "loss": 0.1569, + "step": 34865 + }, + { + "epoch": 2.84, + "learning_rate": 1.059322033898305e-06, + "loss": 0.5843, + "step": 34866 + }, + { + "epoch": 2.84, + "learning_rate": 1.0587787918296393e-06, + "loss": 0.1915, + "step": 34867 + }, + { + "epoch": 2.84, + "learning_rate": 1.0582355497609735e-06, + "loss": 0.2812, + "step": 34868 + }, + { + "epoch": 2.84, + "learning_rate": 1.0576923076923078e-06, + "loss": 0.2042, + "step": 34869 + }, + { + "epoch": 2.84, + "learning_rate": 1.057149065623642e-06, + "loss": 0.0727, + "step": 34870 + }, + { + "epoch": 2.84, + "learning_rate": 1.0566058235549762e-06, + "loss": 0.2574, + "step": 34871 + }, + { + "epoch": 2.84, + "learning_rate": 1.0560625814863105e-06, + "loss": 0.3399, + "step": 34872 + }, + { + "epoch": 2.84, + "learning_rate": 1.0555193394176445e-06, + "loss": 0.359, + "step": 34873 + }, + { + "epoch": 2.84, + "learning_rate": 1.0549760973489787e-06, + "loss": 0.1692, + "step": 34874 + }, + { + "epoch": 2.84, + "learning_rate": 1.0544328552803131e-06, + "loss": 0.2143, + "step": 34875 + }, + { + "epoch": 2.84, + "learning_rate": 1.0538896132116472e-06, + "loss": 0.1379, + "step": 34876 + }, + { + "epoch": 2.84, + "learning_rate": 1.0533463711429814e-06, + "loss": 0.2477, + "step": 34877 + }, + { + "epoch": 2.84, + "learning_rate": 1.0528031290743156e-06, + "loss": 0.2716, + "step": 34878 + }, + { + "epoch": 2.84, + "learning_rate": 1.0522598870056499e-06, + "loss": 0.6194, + "step": 34879 + }, + { + "epoch": 2.84, + "learning_rate": 1.0517166449369839e-06, + "loss": 0.3996, + "step": 34880 + }, + { + "epoch": 2.84, + "learning_rate": 1.051173402868318e-06, + "loss": 0.2075, + "step": 34881 + }, + { + "epoch": 2.84, + "learning_rate": 1.0506301607996525e-06, + "loss": 0.1289, + "step": 34882 + }, + { + "epoch": 2.84, + "learning_rate": 1.0500869187309866e-06, + "loss": 0.1898, + "step": 34883 + }, + { + "epoch": 2.84, + "learning_rate": 1.0495436766623208e-06, + "loss": 0.4214, + "step": 34884 + }, + { + "epoch": 2.84, + "learning_rate": 1.049000434593655e-06, + "loss": 0.3647, + "step": 34885 + }, + { + "epoch": 2.84, + "learning_rate": 1.0484571925249893e-06, + "loss": 0.2681, + "step": 34886 + }, + { + "epoch": 2.84, + "learning_rate": 1.0479139504563235e-06, + "loss": 0.2159, + "step": 34887 + }, + { + "epoch": 2.84, + "learning_rate": 1.0473707083876577e-06, + "loss": 0.0192, + "step": 34888 + }, + { + "epoch": 2.84, + "learning_rate": 1.046827466318992e-06, + "loss": 0.1102, + "step": 34889 + }, + { + "epoch": 2.84, + "learning_rate": 1.046284224250326e-06, + "loss": 0.2216, + "step": 34890 + }, + { + "epoch": 2.84, + "learning_rate": 1.0457409821816602e-06, + "loss": 0.1102, + "step": 34891 + }, + { + "epoch": 2.84, + "learning_rate": 1.0451977401129944e-06, + "loss": 0.3922, + "step": 34892 + }, + { + "epoch": 2.84, + "learning_rate": 1.0446544980443287e-06, + "loss": 0.1784, + "step": 34893 + }, + { + "epoch": 2.84, + "learning_rate": 1.0441112559756629e-06, + "loss": 0.232, + "step": 34894 + }, + { + "epoch": 2.84, + "learning_rate": 1.0435680139069971e-06, + "loss": 0.2277, + "step": 34895 + }, + { + "epoch": 2.84, + "learning_rate": 1.0430247718383314e-06, + "loss": 0.2949, + "step": 34896 + }, + { + "epoch": 2.84, + "learning_rate": 1.0424815297696654e-06, + "loss": 0.0834, + "step": 34897 + }, + { + "epoch": 2.84, + "learning_rate": 1.0419382877009996e-06, + "loss": 0.3608, + "step": 34898 + }, + { + "epoch": 2.84, + "learning_rate": 1.0413950456323338e-06, + "loss": 0.2028, + "step": 34899 + }, + { + "epoch": 2.84, + "learning_rate": 1.040851803563668e-06, + "loss": 0.285, + "step": 34900 + }, + { + "epoch": 2.84, + "learning_rate": 1.0403085614950023e-06, + "loss": 0.2283, + "step": 34901 + }, + { + "epoch": 2.84, + "learning_rate": 1.0397653194263365e-06, + "loss": 0.2203, + "step": 34902 + }, + { + "epoch": 2.84, + "learning_rate": 1.0392220773576708e-06, + "loss": 0.2197, + "step": 34903 + }, + { + "epoch": 2.84, + "learning_rate": 1.0386788352890048e-06, + "loss": 0.4258, + "step": 34904 + }, + { + "epoch": 2.84, + "learning_rate": 1.038135593220339e-06, + "loss": 0.2319, + "step": 34905 + }, + { + "epoch": 2.84, + "learning_rate": 1.0375923511516732e-06, + "loss": 0.161, + "step": 34906 + }, + { + "epoch": 2.84, + "learning_rate": 1.0370491090830075e-06, + "loss": 0.0846, + "step": 34907 + }, + { + "epoch": 2.84, + "learning_rate": 1.0365058670143417e-06, + "loss": 0.2475, + "step": 34908 + }, + { + "epoch": 2.84, + "learning_rate": 1.035962624945676e-06, + "loss": 0.3568, + "step": 34909 + }, + { + "epoch": 2.84, + "learning_rate": 1.0354193828770102e-06, + "loss": 0.1545, + "step": 34910 + }, + { + "epoch": 2.84, + "learning_rate": 1.0348761408083442e-06, + "loss": 0.195, + "step": 34911 + }, + { + "epoch": 2.84, + "learning_rate": 1.0343328987396784e-06, + "loss": 0.3636, + "step": 34912 + }, + { + "epoch": 2.84, + "learning_rate": 1.0337896566710128e-06, + "loss": 0.0945, + "step": 34913 + }, + { + "epoch": 2.85, + "learning_rate": 1.0332464146023469e-06, + "loss": 0.2982, + "step": 34914 + }, + { + "epoch": 2.85, + "learning_rate": 1.032703172533681e-06, + "loss": 0.4149, + "step": 34915 + }, + { + "epoch": 2.85, + "learning_rate": 1.0321599304650153e-06, + "loss": 0.1438, + "step": 34916 + }, + { + "epoch": 2.85, + "learning_rate": 1.0316166883963496e-06, + "loss": 0.215, + "step": 34917 + }, + { + "epoch": 2.85, + "learning_rate": 1.0310734463276836e-06, + "loss": 0.2232, + "step": 34918 + }, + { + "epoch": 2.85, + "learning_rate": 1.0305302042590178e-06, + "loss": 0.127, + "step": 34919 + }, + { + "epoch": 2.85, + "learning_rate": 1.0299869621903522e-06, + "loss": 0.2628, + "step": 34920 + }, + { + "epoch": 2.85, + "learning_rate": 1.0294437201216863e-06, + "loss": 0.4291, + "step": 34921 + }, + { + "epoch": 2.85, + "learning_rate": 1.0289004780530205e-06, + "loss": 0.3687, + "step": 34922 + }, + { + "epoch": 2.85, + "learning_rate": 1.0283572359843547e-06, + "loss": 0.1954, + "step": 34923 + }, + { + "epoch": 2.85, + "learning_rate": 1.027813993915689e-06, + "loss": 0.1348, + "step": 34924 + }, + { + "epoch": 2.85, + "learning_rate": 1.0272707518470232e-06, + "loss": 0.2343, + "step": 34925 + }, + { + "epoch": 2.85, + "learning_rate": 1.0267275097783572e-06, + "loss": 0.2719, + "step": 34926 + }, + { + "epoch": 2.85, + "learning_rate": 1.0261842677096917e-06, + "loss": 0.1543, + "step": 34927 + }, + { + "epoch": 2.85, + "learning_rate": 1.0256410256410257e-06, + "loss": 0.5709, + "step": 34928 + }, + { + "epoch": 2.85, + "learning_rate": 1.02509778357236e-06, + "loss": 0.0757, + "step": 34929 + }, + { + "epoch": 2.85, + "learning_rate": 1.0245545415036941e-06, + "loss": 0.4095, + "step": 34930 + }, + { + "epoch": 2.85, + "learning_rate": 1.0240112994350284e-06, + "loss": 0.4422, + "step": 34931 + }, + { + "epoch": 2.85, + "learning_rate": 1.0234680573663626e-06, + "loss": 0.1019, + "step": 34932 + }, + { + "epoch": 2.85, + "learning_rate": 1.0229248152976966e-06, + "loss": 0.3296, + "step": 34933 + }, + { + "epoch": 2.85, + "learning_rate": 1.022381573229031e-06, + "loss": 0.4266, + "step": 34934 + }, + { + "epoch": 2.85, + "learning_rate": 1.021838331160365e-06, + "loss": 0.5807, + "step": 34935 + }, + { + "epoch": 2.85, + "learning_rate": 1.0212950890916993e-06, + "loss": 0.2454, + "step": 34936 + }, + { + "epoch": 2.85, + "learning_rate": 1.0207518470230335e-06, + "loss": 0.1109, + "step": 34937 + }, + { + "epoch": 2.85, + "learning_rate": 1.0202086049543678e-06, + "loss": 0.0368, + "step": 34938 + }, + { + "epoch": 2.85, + "learning_rate": 1.019665362885702e-06, + "loss": 0.369, + "step": 34939 + }, + { + "epoch": 2.85, + "learning_rate": 1.0191221208170362e-06, + "loss": 0.3565, + "step": 34940 + }, + { + "epoch": 2.85, + "learning_rate": 1.0185788787483705e-06, + "loss": 0.3042, + "step": 34941 + }, + { + "epoch": 2.85, + "learning_rate": 1.0180356366797045e-06, + "loss": 0.1593, + "step": 34942 + }, + { + "epoch": 2.85, + "learning_rate": 1.0174923946110387e-06, + "loss": 0.0765, + "step": 34943 + }, + { + "epoch": 2.85, + "learning_rate": 1.016949152542373e-06, + "loss": 0.1731, + "step": 34944 + }, + { + "epoch": 2.85, + "learning_rate": 1.0164059104737072e-06, + "loss": 0.1307, + "step": 34945 + }, + { + "epoch": 2.85, + "learning_rate": 1.0158626684050414e-06, + "loss": 0.1033, + "step": 34946 + }, + { + "epoch": 2.85, + "learning_rate": 1.0153194263363756e-06, + "loss": 0.197, + "step": 34947 + }, + { + "epoch": 2.85, + "learning_rate": 1.0147761842677099e-06, + "loss": 0.1537, + "step": 34948 + }, + { + "epoch": 2.85, + "learning_rate": 1.0142329421990439e-06, + "loss": 0.0941, + "step": 34949 + }, + { + "epoch": 2.85, + "learning_rate": 1.0136897001303781e-06, + "loss": 0.1976, + "step": 34950 + }, + { + "epoch": 2.85, + "learning_rate": 1.0131464580617123e-06, + "loss": 0.1324, + "step": 34951 + }, + { + "epoch": 2.85, + "learning_rate": 1.0126032159930466e-06, + "loss": 0.0951, + "step": 34952 + }, + { + "epoch": 2.85, + "learning_rate": 1.0120599739243808e-06, + "loss": 0.06, + "step": 34953 + }, + { + "epoch": 2.85, + "learning_rate": 1.011516731855715e-06, + "loss": 0.2399, + "step": 34954 + }, + { + "epoch": 2.85, + "learning_rate": 1.0109734897870493e-06, + "loss": 0.1393, + "step": 34955 + }, + { + "epoch": 2.85, + "learning_rate": 1.0104302477183833e-06, + "loss": 0.0838, + "step": 34956 + }, + { + "epoch": 2.85, + "learning_rate": 1.0098870056497175e-06, + "loss": 0.1497, + "step": 34957 + }, + { + "epoch": 2.85, + "learning_rate": 1.009343763581052e-06, + "loss": 0.1764, + "step": 34958 + }, + { + "epoch": 2.85, + "learning_rate": 1.008800521512386e-06, + "loss": 0.1585, + "step": 34959 + }, + { + "epoch": 2.85, + "learning_rate": 1.0082572794437202e-06, + "loss": 0.2732, + "step": 34960 + }, + { + "epoch": 2.85, + "learning_rate": 1.0077140373750544e-06, + "loss": 0.0973, + "step": 34961 + }, + { + "epoch": 2.85, + "learning_rate": 1.0071707953063887e-06, + "loss": 0.31, + "step": 34962 + }, + { + "epoch": 2.85, + "learning_rate": 1.0066275532377229e-06, + "loss": 0.0361, + "step": 34963 + }, + { + "epoch": 2.85, + "learning_rate": 1.006084311169057e-06, + "loss": 0.4947, + "step": 34964 + }, + { + "epoch": 2.85, + "learning_rate": 1.0055410691003914e-06, + "loss": 0.0963, + "step": 34965 + }, + { + "epoch": 2.85, + "learning_rate": 1.0049978270317254e-06, + "loss": 0.2804, + "step": 34966 + }, + { + "epoch": 2.85, + "learning_rate": 1.0044545849630596e-06, + "loss": 0.2654, + "step": 34967 + }, + { + "epoch": 2.85, + "learning_rate": 1.0039113428943938e-06, + "loss": 0.2805, + "step": 34968 + }, + { + "epoch": 2.85, + "learning_rate": 1.003368100825728e-06, + "loss": 0.2345, + "step": 34969 + }, + { + "epoch": 2.85, + "learning_rate": 1.0028248587570623e-06, + "loss": 0.1733, + "step": 34970 + }, + { + "epoch": 2.85, + "learning_rate": 1.0022816166883963e-06, + "loss": 0.0909, + "step": 34971 + }, + { + "epoch": 2.85, + "learning_rate": 1.0017383746197308e-06, + "loss": 0.221, + "step": 34972 + }, + { + "epoch": 2.85, + "learning_rate": 1.0011951325510648e-06, + "loss": 0.1294, + "step": 34973 + }, + { + "epoch": 2.85, + "learning_rate": 1.000651890482399e-06, + "loss": 0.0895, + "step": 34974 + }, + { + "epoch": 2.85, + "learning_rate": 1.0001086484137332e-06, + "loss": 0.1258, + "step": 34975 + }, + { + "epoch": 2.85, + "learning_rate": 9.995654063450675e-07, + "loss": 0.3421, + "step": 34976 + }, + { + "epoch": 2.85, + "learning_rate": 9.990221642764017e-07, + "loss": 0.2398, + "step": 34977 + }, + { + "epoch": 2.85, + "learning_rate": 9.984789222077357e-07, + "loss": 0.2979, + "step": 34978 + }, + { + "epoch": 2.85, + "learning_rate": 9.979356801390702e-07, + "loss": 0.2079, + "step": 34979 + }, + { + "epoch": 2.85, + "learning_rate": 9.973924380704042e-07, + "loss": 0.0713, + "step": 34980 + }, + { + "epoch": 2.85, + "learning_rate": 9.968491960017384e-07, + "loss": 0.3729, + "step": 34981 + }, + { + "epoch": 2.85, + "learning_rate": 9.963059539330726e-07, + "loss": 0.2906, + "step": 34982 + }, + { + "epoch": 2.85, + "learning_rate": 9.957627118644069e-07, + "loss": 0.2102, + "step": 34983 + }, + { + "epoch": 2.85, + "learning_rate": 9.95219469795741e-07, + "loss": 0.1297, + "step": 34984 + }, + { + "epoch": 2.85, + "learning_rate": 9.946762277270753e-07, + "loss": 0.2722, + "step": 34985 + }, + { + "epoch": 2.85, + "learning_rate": 9.941329856584096e-07, + "loss": 0.1521, + "step": 34986 + }, + { + "epoch": 2.85, + "learning_rate": 9.935897435897436e-07, + "loss": 0.1039, + "step": 34987 + }, + { + "epoch": 2.85, + "learning_rate": 9.930465015210778e-07, + "loss": 0.3103, + "step": 34988 + }, + { + "epoch": 2.85, + "learning_rate": 9.92503259452412e-07, + "loss": 0.3062, + "step": 34989 + }, + { + "epoch": 2.85, + "learning_rate": 9.919600173837463e-07, + "loss": 0.0599, + "step": 34990 + }, + { + "epoch": 2.85, + "learning_rate": 9.914167753150805e-07, + "loss": 0.1438, + "step": 34991 + }, + { + "epoch": 2.85, + "learning_rate": 9.908735332464147e-07, + "loss": 0.2813, + "step": 34992 + }, + { + "epoch": 2.85, + "learning_rate": 9.90330291177749e-07, + "loss": 0.2075, + "step": 34993 + }, + { + "epoch": 2.85, + "learning_rate": 9.89787049109083e-07, + "loss": 0.3273, + "step": 34994 + }, + { + "epoch": 2.85, + "learning_rate": 9.892438070404172e-07, + "loss": 0.1873, + "step": 34995 + }, + { + "epoch": 2.85, + "learning_rate": 9.887005649717514e-07, + "loss": 0.2077, + "step": 34996 + }, + { + "epoch": 2.85, + "learning_rate": 9.881573229030857e-07, + "loss": 0.2341, + "step": 34997 + }, + { + "epoch": 2.85, + "learning_rate": 9.8761408083442e-07, + "loss": 0.2259, + "step": 34998 + }, + { + "epoch": 2.85, + "learning_rate": 9.870708387657541e-07, + "loss": 0.149, + "step": 34999 + }, + { + "epoch": 2.85, + "learning_rate": 9.865275966970884e-07, + "loss": 0.0864, + "step": 35000 + }, + { + "epoch": 2.85, + "eval_accuracy": 0.8453387671930719, + "eval_loss": 0.49137306213378906, + "eval_runtime": 22.3227, + "eval_samples_per_second": 439.688, + "eval_steps_per_second": 3.449, + "step": 35000 + }, + { + "epoch": 2.85, + "learning_rate": 9.859843546284226e-07, + "loss": 0.2515, + "step": 35001 + }, + { + "epoch": 2.85, + "learning_rate": 9.854411125597566e-07, + "loss": 0.2154, + "step": 35002 + }, + { + "epoch": 2.85, + "learning_rate": 9.84897870491091e-07, + "loss": 0.5192, + "step": 35003 + }, + { + "epoch": 2.85, + "learning_rate": 9.84354628422425e-07, + "loss": 0.4969, + "step": 35004 + }, + { + "epoch": 2.85, + "learning_rate": 9.838113863537593e-07, + "loss": 0.1085, + "step": 35005 + }, + { + "epoch": 2.85, + "learning_rate": 9.832681442850935e-07, + "loss": 0.3992, + "step": 35006 + }, + { + "epoch": 2.85, + "learning_rate": 9.827249022164278e-07, + "loss": 0.1075, + "step": 35007 + }, + { + "epoch": 2.85, + "learning_rate": 9.82181660147762e-07, + "loss": 0.0646, + "step": 35008 + }, + { + "epoch": 2.85, + "learning_rate": 9.81638418079096e-07, + "loss": 0.2152, + "step": 35009 + }, + { + "epoch": 2.85, + "learning_rate": 9.810951760104305e-07, + "loss": 0.2774, + "step": 35010 + }, + { + "epoch": 2.85, + "learning_rate": 9.805519339417645e-07, + "loss": 0.099, + "step": 35011 + }, + { + "epoch": 2.85, + "learning_rate": 9.800086918730987e-07, + "loss": 0.2678, + "step": 35012 + }, + { + "epoch": 2.85, + "learning_rate": 9.79465449804433e-07, + "loss": 0.1046, + "step": 35013 + }, + { + "epoch": 2.85, + "learning_rate": 9.789222077357672e-07, + "loss": 0.4002, + "step": 35014 + }, + { + "epoch": 2.85, + "learning_rate": 9.783789656671014e-07, + "loss": 0.0759, + "step": 35015 + }, + { + "epoch": 2.85, + "learning_rate": 9.778357235984354e-07, + "loss": 0.3065, + "step": 35016 + }, + { + "epoch": 2.85, + "learning_rate": 9.772924815297699e-07, + "loss": 0.3691, + "step": 35017 + }, + { + "epoch": 2.85, + "learning_rate": 9.767492394611039e-07, + "loss": 0.2441, + "step": 35018 + }, + { + "epoch": 2.85, + "learning_rate": 9.762059973924381e-07, + "loss": 0.3959, + "step": 35019 + }, + { + "epoch": 2.85, + "learning_rate": 9.756627553237723e-07, + "loss": 0.3493, + "step": 35020 + }, + { + "epoch": 2.85, + "learning_rate": 9.751195132551066e-07, + "loss": 0.1397, + "step": 35021 + }, + { + "epoch": 2.85, + "learning_rate": 9.745762711864408e-07, + "loss": 0.2144, + "step": 35022 + }, + { + "epoch": 2.85, + "learning_rate": 9.740330291177748e-07, + "loss": 0.2461, + "step": 35023 + }, + { + "epoch": 2.85, + "learning_rate": 9.734897870491093e-07, + "loss": 0.2099, + "step": 35024 + }, + { + "epoch": 2.85, + "learning_rate": 9.729465449804433e-07, + "loss": 0.2628, + "step": 35025 + }, + { + "epoch": 2.85, + "learning_rate": 9.724033029117775e-07, + "loss": 0.185, + "step": 35026 + }, + { + "epoch": 2.85, + "learning_rate": 9.718600608431117e-07, + "loss": 0.4482, + "step": 35027 + }, + { + "epoch": 2.85, + "learning_rate": 9.71316818774446e-07, + "loss": 0.1888, + "step": 35028 + }, + { + "epoch": 2.85, + "learning_rate": 9.707735767057802e-07, + "loss": 0.3247, + "step": 35029 + }, + { + "epoch": 2.85, + "learning_rate": 9.702303346371144e-07, + "loss": 0.301, + "step": 35030 + }, + { + "epoch": 2.85, + "learning_rate": 9.696870925684487e-07, + "loss": 0.2207, + "step": 35031 + }, + { + "epoch": 2.85, + "learning_rate": 9.69143850499783e-07, + "loss": 0.0726, + "step": 35032 + }, + { + "epoch": 2.85, + "learning_rate": 9.68600608431117e-07, + "loss": 0.1971, + "step": 35033 + }, + { + "epoch": 2.85, + "learning_rate": 9.680573663624511e-07, + "loss": 0.3285, + "step": 35034 + }, + { + "epoch": 2.85, + "learning_rate": 9.675141242937854e-07, + "loss": 0.1237, + "step": 35035 + }, + { + "epoch": 2.85, + "learning_rate": 9.669708822251196e-07, + "loss": 0.3284, + "step": 35036 + }, + { + "epoch": 2.86, + "learning_rate": 9.664276401564538e-07, + "loss": 0.233, + "step": 35037 + }, + { + "epoch": 2.86, + "learning_rate": 9.65884398087788e-07, + "loss": 0.2564, + "step": 35038 + }, + { + "epoch": 2.86, + "learning_rate": 9.653411560191223e-07, + "loss": 0.3091, + "step": 35039 + }, + { + "epoch": 2.86, + "learning_rate": 9.647979139504563e-07, + "loss": 0.2678, + "step": 35040 + }, + { + "epoch": 2.86, + "learning_rate": 9.642546718817905e-07, + "loss": 0.2652, + "step": 35041 + }, + { + "epoch": 2.86, + "learning_rate": 9.637114298131248e-07, + "loss": 0.2185, + "step": 35042 + }, + { + "epoch": 2.86, + "learning_rate": 9.63168187744459e-07, + "loss": 0.2088, + "step": 35043 + }, + { + "epoch": 2.86, + "learning_rate": 9.626249456757932e-07, + "loss": 0.3603, + "step": 35044 + }, + { + "epoch": 2.86, + "learning_rate": 9.620817036071275e-07, + "loss": 0.2318, + "step": 35045 + }, + { + "epoch": 2.86, + "learning_rate": 9.615384615384617e-07, + "loss": 0.4294, + "step": 35046 + }, + { + "epoch": 2.86, + "learning_rate": 9.609952194697957e-07, + "loss": 0.4867, + "step": 35047 + }, + { + "epoch": 2.86, + "learning_rate": 9.6045197740113e-07, + "loss": 0.5544, + "step": 35048 + }, + { + "epoch": 2.86, + "learning_rate": 9.599087353324642e-07, + "loss": 0.1336, + "step": 35049 + }, + { + "epoch": 2.86, + "learning_rate": 9.593654932637984e-07, + "loss": 0.2639, + "step": 35050 + }, + { + "epoch": 2.86, + "learning_rate": 9.588222511951326e-07, + "loss": 0.135, + "step": 35051 + }, + { + "epoch": 2.86, + "learning_rate": 9.582790091264669e-07, + "loss": 0.2395, + "step": 35052 + }, + { + "epoch": 2.86, + "learning_rate": 9.57735767057801e-07, + "loss": 0.203, + "step": 35053 + }, + { + "epoch": 2.86, + "learning_rate": 9.571925249891351e-07, + "loss": 0.1916, + "step": 35054 + }, + { + "epoch": 2.86, + "learning_rate": 9.566492829204696e-07, + "loss": 0.1248, + "step": 35055 + }, + { + "epoch": 2.86, + "learning_rate": 9.561060408518036e-07, + "loss": 0.0198, + "step": 35056 + }, + { + "epoch": 2.86, + "learning_rate": 9.555627987831378e-07, + "loss": 0.3108, + "step": 35057 + }, + { + "epoch": 2.86, + "learning_rate": 9.55019556714472e-07, + "loss": 0.2494, + "step": 35058 + }, + { + "epoch": 2.86, + "learning_rate": 9.544763146458063e-07, + "loss": 0.0596, + "step": 35059 + }, + { + "epoch": 2.86, + "learning_rate": 9.539330725771405e-07, + "loss": 0.3141, + "step": 35060 + }, + { + "epoch": 2.86, + "learning_rate": 9.533898305084746e-07, + "loss": 0.1721, + "step": 35061 + }, + { + "epoch": 2.86, + "learning_rate": 9.528465884398089e-07, + "loss": 0.1883, + "step": 35062 + }, + { + "epoch": 2.86, + "learning_rate": 9.52303346371143e-07, + "loss": 0.1538, + "step": 35063 + }, + { + "epoch": 2.86, + "learning_rate": 9.517601043024772e-07, + "loss": 0.0998, + "step": 35064 + }, + { + "epoch": 2.86, + "learning_rate": 9.512168622338115e-07, + "loss": 0.0853, + "step": 35065 + }, + { + "epoch": 2.86, + "learning_rate": 9.506736201651457e-07, + "loss": 0.0687, + "step": 35066 + }, + { + "epoch": 2.86, + "learning_rate": 9.501303780964799e-07, + "loss": 0.1669, + "step": 35067 + }, + { + "epoch": 2.86, + "learning_rate": 9.49587136027814e-07, + "loss": 0.3817, + "step": 35068 + }, + { + "epoch": 2.86, + "learning_rate": 9.490438939591483e-07, + "loss": 0.1777, + "step": 35069 + }, + { + "epoch": 2.86, + "learning_rate": 9.485006518904825e-07, + "loss": 0.1192, + "step": 35070 + }, + { + "epoch": 2.86, + "learning_rate": 9.479574098218166e-07, + "loss": 0.1301, + "step": 35071 + }, + { + "epoch": 2.86, + "learning_rate": 9.47414167753151e-07, + "loss": 0.0743, + "step": 35072 + }, + { + "epoch": 2.86, + "learning_rate": 9.468709256844851e-07, + "loss": 0.2375, + "step": 35073 + }, + { + "epoch": 2.86, + "learning_rate": 9.463276836158193e-07, + "loss": 0.1184, + "step": 35074 + }, + { + "epoch": 2.86, + "learning_rate": 9.457844415471534e-07, + "loss": 0.1176, + "step": 35075 + }, + { + "epoch": 2.86, + "learning_rate": 9.452411994784877e-07, + "loss": 0.3943, + "step": 35076 + }, + { + "epoch": 2.86, + "learning_rate": 9.44697957409822e-07, + "loss": 0.1067, + "step": 35077 + }, + { + "epoch": 2.86, + "learning_rate": 9.441547153411561e-07, + "loss": 0.2345, + "step": 35078 + }, + { + "epoch": 2.86, + "learning_rate": 9.436114732724904e-07, + "loss": 0.3383, + "step": 35079 + }, + { + "epoch": 2.86, + "learning_rate": 9.430682312038245e-07, + "loss": 0.1422, + "step": 35080 + }, + { + "epoch": 2.86, + "learning_rate": 9.425249891351587e-07, + "loss": 0.2224, + "step": 35081 + }, + { + "epoch": 2.86, + "learning_rate": 9.419817470664928e-07, + "loss": 0.3177, + "step": 35082 + }, + { + "epoch": 2.86, + "learning_rate": 9.414385049978271e-07, + "loss": 0.1334, + "step": 35083 + }, + { + "epoch": 2.86, + "learning_rate": 9.408952629291614e-07, + "loss": 0.1635, + "step": 35084 + }, + { + "epoch": 2.86, + "learning_rate": 9.403520208604955e-07, + "loss": 0.3725, + "step": 35085 + }, + { + "epoch": 2.86, + "learning_rate": 9.398087787918298e-07, + "loss": 0.3389, + "step": 35086 + }, + { + "epoch": 2.86, + "learning_rate": 9.392655367231639e-07, + "loss": 0.2862, + "step": 35087 + }, + { + "epoch": 2.86, + "learning_rate": 9.387222946544981e-07, + "loss": 0.0777, + "step": 35088 + }, + { + "epoch": 2.86, + "learning_rate": 9.381790525858323e-07, + "loss": 0.0923, + "step": 35089 + }, + { + "epoch": 2.86, + "learning_rate": 9.376358105171665e-07, + "loss": 0.1138, + "step": 35090 + }, + { + "epoch": 2.86, + "learning_rate": 9.370925684485008e-07, + "loss": 0.3186, + "step": 35091 + }, + { + "epoch": 2.86, + "learning_rate": 9.365493263798349e-07, + "loss": 0.3386, + "step": 35092 + }, + { + "epoch": 2.86, + "learning_rate": 9.360060843111692e-07, + "loss": 0.3035, + "step": 35093 + }, + { + "epoch": 2.86, + "learning_rate": 9.354628422425033e-07, + "loss": 0.1006, + "step": 35094 + }, + { + "epoch": 2.86, + "learning_rate": 9.349196001738375e-07, + "loss": 0.4231, + "step": 35095 + }, + { + "epoch": 2.86, + "learning_rate": 9.343763581051718e-07, + "loss": 0.5467, + "step": 35096 + }, + { + "epoch": 2.86, + "learning_rate": 9.33833116036506e-07, + "loss": 0.4313, + "step": 35097 + }, + { + "epoch": 2.86, + "learning_rate": 9.332898739678402e-07, + "loss": 0.0982, + "step": 35098 + }, + { + "epoch": 2.86, + "learning_rate": 9.327466318991743e-07, + "loss": 0.2825, + "step": 35099 + }, + { + "epoch": 2.86, + "learning_rate": 9.322033898305086e-07, + "loss": 0.3292, + "step": 35100 + }, + { + "epoch": 2.86, + "learning_rate": 9.316601477618427e-07, + "loss": 0.3005, + "step": 35101 + }, + { + "epoch": 2.86, + "learning_rate": 9.311169056931769e-07, + "loss": 0.2004, + "step": 35102 + }, + { + "epoch": 2.86, + "learning_rate": 9.305736636245113e-07, + "loss": 0.2413, + "step": 35103 + }, + { + "epoch": 2.86, + "learning_rate": 9.300304215558454e-07, + "loss": 0.2803, + "step": 35104 + }, + { + "epoch": 2.86, + "learning_rate": 9.294871794871796e-07, + "loss": 0.2755, + "step": 35105 + }, + { + "epoch": 2.86, + "learning_rate": 9.289439374185137e-07, + "loss": 0.1596, + "step": 35106 + }, + { + "epoch": 2.86, + "learning_rate": 9.28400695349848e-07, + "loss": 0.3472, + "step": 35107 + }, + { + "epoch": 2.86, + "learning_rate": 9.278574532811822e-07, + "loss": 0.3605, + "step": 35108 + }, + { + "epoch": 2.86, + "learning_rate": 9.273142112125163e-07, + "loss": 0.1087, + "step": 35109 + }, + { + "epoch": 2.86, + "learning_rate": 9.267709691438507e-07, + "loss": 0.4382, + "step": 35110 + }, + { + "epoch": 2.86, + "learning_rate": 9.262277270751848e-07, + "loss": 0.1475, + "step": 35111 + }, + { + "epoch": 2.86, + "learning_rate": 9.25684485006519e-07, + "loss": 0.0682, + "step": 35112 + }, + { + "epoch": 2.86, + "learning_rate": 9.251412429378531e-07, + "loss": 0.0797, + "step": 35113 + }, + { + "epoch": 2.86, + "learning_rate": 9.245980008691874e-07, + "loss": 0.4732, + "step": 35114 + }, + { + "epoch": 2.86, + "learning_rate": 9.240547588005216e-07, + "loss": 0.2062, + "step": 35115 + }, + { + "epoch": 2.86, + "learning_rate": 9.235115167318557e-07, + "loss": 0.2819, + "step": 35116 + }, + { + "epoch": 2.86, + "learning_rate": 9.229682746631901e-07, + "loss": 0.3444, + "step": 35117 + }, + { + "epoch": 2.86, + "learning_rate": 9.224250325945242e-07, + "loss": 0.4475, + "step": 35118 + }, + { + "epoch": 2.86, + "learning_rate": 9.218817905258584e-07, + "loss": 0.3044, + "step": 35119 + }, + { + "epoch": 2.86, + "learning_rate": 9.213385484571925e-07, + "loss": 0.1694, + "step": 35120 + }, + { + "epoch": 2.86, + "learning_rate": 9.207953063885268e-07, + "loss": 0.2291, + "step": 35121 + }, + { + "epoch": 2.86, + "learning_rate": 9.202520643198611e-07, + "loss": 0.1335, + "step": 35122 + }, + { + "epoch": 2.86, + "learning_rate": 9.197088222511952e-07, + "loss": 0.1944, + "step": 35123 + }, + { + "epoch": 2.86, + "learning_rate": 9.191655801825295e-07, + "loss": 0.0362, + "step": 35124 + }, + { + "epoch": 2.86, + "learning_rate": 9.186223381138636e-07, + "loss": 0.2441, + "step": 35125 + }, + { + "epoch": 2.86, + "learning_rate": 9.180790960451978e-07, + "loss": 0.4672, + "step": 35126 + }, + { + "epoch": 2.86, + "learning_rate": 9.17535853976532e-07, + "loss": 0.0729, + "step": 35127 + }, + { + "epoch": 2.86, + "learning_rate": 9.169926119078662e-07, + "loss": 0.1929, + "step": 35128 + }, + { + "epoch": 2.86, + "learning_rate": 9.164493698392005e-07, + "loss": 0.4144, + "step": 35129 + }, + { + "epoch": 2.86, + "learning_rate": 9.159061277705346e-07, + "loss": 0.1672, + "step": 35130 + }, + { + "epoch": 2.86, + "learning_rate": 9.153628857018689e-07, + "loss": 0.0976, + "step": 35131 + }, + { + "epoch": 2.86, + "learning_rate": 9.14819643633203e-07, + "loss": 0.2685, + "step": 35132 + }, + { + "epoch": 2.86, + "learning_rate": 9.142764015645372e-07, + "loss": 0.2796, + "step": 35133 + }, + { + "epoch": 2.86, + "learning_rate": 9.137331594958714e-07, + "loss": 0.2182, + "step": 35134 + }, + { + "epoch": 2.86, + "learning_rate": 9.131899174272056e-07, + "loss": 0.1471, + "step": 35135 + }, + { + "epoch": 2.86, + "learning_rate": 9.126466753585399e-07, + "loss": 0.0864, + "step": 35136 + }, + { + "epoch": 2.86, + "learning_rate": 9.12103433289874e-07, + "loss": 0.1023, + "step": 35137 + }, + { + "epoch": 2.86, + "learning_rate": 9.115601912212083e-07, + "loss": 0.1749, + "step": 35138 + }, + { + "epoch": 2.86, + "learning_rate": 9.110169491525424e-07, + "loss": 0.2103, + "step": 35139 + }, + { + "epoch": 2.86, + "learning_rate": 9.104737070838766e-07, + "loss": 0.0669, + "step": 35140 + }, + { + "epoch": 2.86, + "learning_rate": 9.09930465015211e-07, + "loss": 0.1879, + "step": 35141 + }, + { + "epoch": 2.86, + "learning_rate": 9.09387222946545e-07, + "loss": 0.3594, + "step": 35142 + }, + { + "epoch": 2.86, + "learning_rate": 9.088439808778793e-07, + "loss": 0.1778, + "step": 35143 + }, + { + "epoch": 2.86, + "learning_rate": 9.083007388092134e-07, + "loss": 0.2881, + "step": 35144 + }, + { + "epoch": 2.86, + "learning_rate": 9.077574967405477e-07, + "loss": 0.082, + "step": 35145 + }, + { + "epoch": 2.86, + "learning_rate": 9.072142546718819e-07, + "loss": 0.0742, + "step": 35146 + }, + { + "epoch": 2.86, + "learning_rate": 9.06671012603216e-07, + "loss": 0.5288, + "step": 35147 + }, + { + "epoch": 2.86, + "learning_rate": 9.061277705345504e-07, + "loss": 0.3222, + "step": 35148 + }, + { + "epoch": 2.86, + "learning_rate": 9.055845284658845e-07, + "loss": 0.5773, + "step": 35149 + }, + { + "epoch": 2.86, + "learning_rate": 9.050412863972187e-07, + "loss": 0.2652, + "step": 35150 + }, + { + "epoch": 2.86, + "learning_rate": 9.044980443285528e-07, + "loss": 0.2171, + "step": 35151 + }, + { + "epoch": 2.86, + "learning_rate": 9.039548022598871e-07, + "loss": 0.1388, + "step": 35152 + }, + { + "epoch": 2.86, + "learning_rate": 9.034115601912213e-07, + "loss": 0.0702, + "step": 35153 + }, + { + "epoch": 2.86, + "learning_rate": 9.028683181225554e-07, + "loss": 0.1092, + "step": 35154 + }, + { + "epoch": 2.86, + "learning_rate": 9.023250760538898e-07, + "loss": 0.1432, + "step": 35155 + }, + { + "epoch": 2.86, + "learning_rate": 9.017818339852239e-07, + "loss": 0.225, + "step": 35156 + }, + { + "epoch": 2.86, + "learning_rate": 9.012385919165581e-07, + "loss": 0.2595, + "step": 35157 + }, + { + "epoch": 2.86, + "learning_rate": 9.006953498478922e-07, + "loss": 0.2283, + "step": 35158 + }, + { + "epoch": 2.86, + "learning_rate": 9.001521077792265e-07, + "loss": 0.2384, + "step": 35159 + }, + { + "epoch": 2.87, + "learning_rate": 8.996088657105607e-07, + "loss": 0.2632, + "step": 35160 + }, + { + "epoch": 2.87, + "learning_rate": 8.990656236418948e-07, + "loss": 0.1689, + "step": 35161 + }, + { + "epoch": 2.87, + "learning_rate": 8.985223815732292e-07, + "loss": 0.472, + "step": 35162 + }, + { + "epoch": 2.87, + "learning_rate": 8.979791395045633e-07, + "loss": 0.2561, + "step": 35163 + }, + { + "epoch": 2.87, + "learning_rate": 8.974358974358975e-07, + "loss": 0.2608, + "step": 35164 + }, + { + "epoch": 2.87, + "learning_rate": 8.968926553672317e-07, + "loss": 0.1839, + "step": 35165 + }, + { + "epoch": 2.87, + "learning_rate": 8.963494132985659e-07, + "loss": 0.2596, + "step": 35166 + }, + { + "epoch": 2.87, + "learning_rate": 8.958061712299002e-07, + "loss": 0.1968, + "step": 35167 + }, + { + "epoch": 2.87, + "learning_rate": 8.952629291612343e-07, + "loss": 0.1957, + "step": 35168 + }, + { + "epoch": 2.87, + "learning_rate": 8.947196870925686e-07, + "loss": 0.0753, + "step": 35169 + }, + { + "epoch": 2.87, + "learning_rate": 8.941764450239027e-07, + "loss": 0.3503, + "step": 35170 + }, + { + "epoch": 2.87, + "learning_rate": 8.936332029552369e-07, + "loss": 0.2979, + "step": 35171 + }, + { + "epoch": 2.87, + "learning_rate": 8.930899608865711e-07, + "loss": 0.1245, + "step": 35172 + }, + { + "epoch": 2.87, + "learning_rate": 8.925467188179053e-07, + "loss": 0.1008, + "step": 35173 + }, + { + "epoch": 2.87, + "learning_rate": 8.920034767492396e-07, + "loss": 0.6764, + "step": 35174 + }, + { + "epoch": 2.87, + "learning_rate": 8.914602346805737e-07, + "loss": 0.2135, + "step": 35175 + }, + { + "epoch": 2.87, + "learning_rate": 8.90916992611908e-07, + "loss": 0.0503, + "step": 35176 + }, + { + "epoch": 2.87, + "learning_rate": 8.903737505432422e-07, + "loss": 0.0887, + "step": 35177 + }, + { + "epoch": 2.87, + "learning_rate": 8.898305084745763e-07, + "loss": 0.305, + "step": 35178 + }, + { + "epoch": 2.87, + "learning_rate": 8.892872664059105e-07, + "loss": 0.1946, + "step": 35179 + }, + { + "epoch": 2.87, + "learning_rate": 8.887440243372447e-07, + "loss": 0.3978, + "step": 35180 + }, + { + "epoch": 2.87, + "learning_rate": 8.88200782268579e-07, + "loss": 0.032, + "step": 35181 + }, + { + "epoch": 2.87, + "learning_rate": 8.876575401999131e-07, + "loss": 0.1289, + "step": 35182 + }, + { + "epoch": 2.87, + "learning_rate": 8.871142981312474e-07, + "loss": 0.2118, + "step": 35183 + }, + { + "epoch": 2.87, + "learning_rate": 8.865710560625816e-07, + "loss": 0.1994, + "step": 35184 + }, + { + "epoch": 2.87, + "learning_rate": 8.860278139939157e-07, + "loss": 0.4622, + "step": 35185 + }, + { + "epoch": 2.87, + "learning_rate": 8.8548457192525e-07, + "loss": 0.4271, + "step": 35186 + }, + { + "epoch": 2.87, + "learning_rate": 8.849413298565841e-07, + "loss": 0.1535, + "step": 35187 + }, + { + "epoch": 2.87, + "learning_rate": 8.843980877879184e-07, + "loss": 0.3821, + "step": 35188 + }, + { + "epoch": 2.87, + "learning_rate": 8.838548457192525e-07, + "loss": 0.1268, + "step": 35189 + }, + { + "epoch": 2.87, + "learning_rate": 8.833116036505868e-07, + "loss": 0.317, + "step": 35190 + }, + { + "epoch": 2.87, + "learning_rate": 8.82768361581921e-07, + "loss": 0.0359, + "step": 35191 + }, + { + "epoch": 2.87, + "learning_rate": 8.822251195132551e-07, + "loss": 0.271, + "step": 35192 + }, + { + "epoch": 2.87, + "learning_rate": 8.816818774445895e-07, + "loss": 0.096, + "step": 35193 + }, + { + "epoch": 2.87, + "learning_rate": 8.811386353759236e-07, + "loss": 0.3482, + "step": 35194 + }, + { + "epoch": 2.87, + "learning_rate": 8.805953933072578e-07, + "loss": 0.5459, + "step": 35195 + }, + { + "epoch": 2.87, + "learning_rate": 8.80052151238592e-07, + "loss": 0.4178, + "step": 35196 + }, + { + "epoch": 2.87, + "learning_rate": 8.795089091699262e-07, + "loss": 0.2875, + "step": 35197 + }, + { + "epoch": 2.87, + "learning_rate": 8.789656671012604e-07, + "loss": 0.3576, + "step": 35198 + }, + { + "epoch": 2.87, + "learning_rate": 8.784224250325945e-07, + "loss": 0.7852, + "step": 35199 + }, + { + "epoch": 2.87, + "learning_rate": 8.778791829639289e-07, + "loss": 0.152, + "step": 35200 + }, + { + "epoch": 2.87, + "learning_rate": 8.77335940895263e-07, + "loss": 0.2137, + "step": 35201 + }, + { + "epoch": 2.87, + "learning_rate": 8.767926988265972e-07, + "loss": 0.438, + "step": 35202 + }, + { + "epoch": 2.87, + "learning_rate": 8.762494567579314e-07, + "loss": 0.1291, + "step": 35203 + }, + { + "epoch": 2.87, + "learning_rate": 8.757062146892656e-07, + "loss": 0.2999, + "step": 35204 + }, + { + "epoch": 2.87, + "learning_rate": 8.751629726205998e-07, + "loss": 0.3617, + "step": 35205 + }, + { + "epoch": 2.87, + "learning_rate": 8.746197305519339e-07, + "loss": 0.2346, + "step": 35206 + }, + { + "epoch": 2.87, + "learning_rate": 8.740764884832683e-07, + "loss": 0.3506, + "step": 35207 + }, + { + "epoch": 2.87, + "learning_rate": 8.735332464146024e-07, + "loss": 0.1476, + "step": 35208 + }, + { + "epoch": 2.87, + "learning_rate": 8.729900043459366e-07, + "loss": 0.1657, + "step": 35209 + }, + { + "epoch": 2.87, + "learning_rate": 8.724467622772708e-07, + "loss": 0.1334, + "step": 35210 + }, + { + "epoch": 2.87, + "learning_rate": 8.71903520208605e-07, + "loss": 0.1588, + "step": 35211 + }, + { + "epoch": 2.87, + "learning_rate": 8.713602781399393e-07, + "loss": 0.0616, + "step": 35212 + }, + { + "epoch": 2.87, + "learning_rate": 8.708170360712733e-07, + "loss": 0.1173, + "step": 35213 + }, + { + "epoch": 2.87, + "learning_rate": 8.702737940026077e-07, + "loss": 0.2268, + "step": 35214 + }, + { + "epoch": 2.87, + "learning_rate": 8.697305519339419e-07, + "loss": 0.2928, + "step": 35215 + }, + { + "epoch": 2.87, + "learning_rate": 8.69187309865276e-07, + "loss": 0.1755, + "step": 35216 + }, + { + "epoch": 2.87, + "learning_rate": 8.686440677966103e-07, + "loss": 0.6462, + "step": 35217 + }, + { + "epoch": 2.87, + "learning_rate": 8.681008257279444e-07, + "loss": 0.2748, + "step": 35218 + }, + { + "epoch": 2.87, + "learning_rate": 8.675575836592787e-07, + "loss": 0.3473, + "step": 35219 + }, + { + "epoch": 2.87, + "learning_rate": 8.670143415906128e-07, + "loss": 0.2459, + "step": 35220 + }, + { + "epoch": 2.87, + "learning_rate": 8.664710995219471e-07, + "loss": 0.2634, + "step": 35221 + }, + { + "epoch": 2.87, + "learning_rate": 8.659278574532813e-07, + "loss": 0.0894, + "step": 35222 + }, + { + "epoch": 2.87, + "learning_rate": 8.653846153846154e-07, + "loss": 0.2631, + "step": 35223 + }, + { + "epoch": 2.87, + "learning_rate": 8.648413733159497e-07, + "loss": 0.2344, + "step": 35224 + }, + { + "epoch": 2.87, + "learning_rate": 8.642981312472838e-07, + "loss": 0.027, + "step": 35225 + }, + { + "epoch": 2.87, + "learning_rate": 8.637548891786181e-07, + "loss": 0.2752, + "step": 35226 + }, + { + "epoch": 2.87, + "learning_rate": 8.632116471099522e-07, + "loss": 0.2375, + "step": 35227 + }, + { + "epoch": 2.87, + "learning_rate": 8.626684050412865e-07, + "loss": 0.3185, + "step": 35228 + }, + { + "epoch": 2.87, + "learning_rate": 8.621251629726207e-07, + "loss": 0.194, + "step": 35229 + }, + { + "epoch": 2.87, + "learning_rate": 8.615819209039548e-07, + "loss": 0.4586, + "step": 35230 + }, + { + "epoch": 2.87, + "learning_rate": 8.610386788352891e-07, + "loss": 0.2702, + "step": 35231 + }, + { + "epoch": 2.87, + "learning_rate": 8.604954367666232e-07, + "loss": 0.1323, + "step": 35232 + }, + { + "epoch": 2.87, + "learning_rate": 8.599521946979575e-07, + "loss": 0.1611, + "step": 35233 + }, + { + "epoch": 2.87, + "learning_rate": 8.594089526292917e-07, + "loss": 0.0904, + "step": 35234 + }, + { + "epoch": 2.87, + "learning_rate": 8.588657105606259e-07, + "loss": 0.253, + "step": 35235 + }, + { + "epoch": 2.87, + "learning_rate": 8.583224684919601e-07, + "loss": 0.1566, + "step": 35236 + }, + { + "epoch": 2.87, + "learning_rate": 8.577792264232942e-07, + "loss": 0.4685, + "step": 35237 + }, + { + "epoch": 2.87, + "learning_rate": 8.572359843546286e-07, + "loss": 0.3698, + "step": 35238 + }, + { + "epoch": 2.87, + "learning_rate": 8.566927422859627e-07, + "loss": 0.1157, + "step": 35239 + }, + { + "epoch": 2.87, + "learning_rate": 8.561495002172969e-07, + "loss": 0.1018, + "step": 35240 + }, + { + "epoch": 2.87, + "learning_rate": 8.556062581486311e-07, + "loss": 0.4552, + "step": 35241 + }, + { + "epoch": 2.87, + "learning_rate": 8.550630160799653e-07, + "loss": 0.1783, + "step": 35242 + }, + { + "epoch": 2.87, + "learning_rate": 8.545197740112995e-07, + "loss": 0.2659, + "step": 35243 + }, + { + "epoch": 2.87, + "learning_rate": 8.539765319426336e-07, + "loss": 0.0462, + "step": 35244 + }, + { + "epoch": 2.87, + "learning_rate": 8.53433289873968e-07, + "loss": 0.4048, + "step": 35245 + }, + { + "epoch": 2.87, + "learning_rate": 8.528900478053021e-07, + "loss": 0.1798, + "step": 35246 + }, + { + "epoch": 2.87, + "learning_rate": 8.523468057366363e-07, + "loss": 0.3011, + "step": 35247 + }, + { + "epoch": 2.87, + "learning_rate": 8.518035636679706e-07, + "loss": 0.5192, + "step": 35248 + }, + { + "epoch": 2.87, + "learning_rate": 8.512603215993047e-07, + "loss": 0.0915, + "step": 35249 + }, + { + "epoch": 2.87, + "learning_rate": 8.507170795306389e-07, + "loss": 0.2843, + "step": 35250 + }, + { + "epoch": 2.87, + "eval_accuracy": 0.8458481915435557, + "eval_loss": 0.49042609333992004, + "eval_runtime": 22.3249, + "eval_samples_per_second": 439.643, + "eval_steps_per_second": 3.449, + "step": 35250 + }, + { + "epoch": 2.87, + "learning_rate": 8.50173837461973e-07, + "loss": 0.1966, + "step": 35251 + }, + { + "epoch": 2.87, + "learning_rate": 8.496305953933074e-07, + "loss": 0.1819, + "step": 35252 + }, + { + "epoch": 2.87, + "learning_rate": 8.490873533246416e-07, + "loss": 0.198, + "step": 35253 + }, + { + "epoch": 2.87, + "learning_rate": 8.485441112559757e-07, + "loss": 0.2053, + "step": 35254 + }, + { + "epoch": 2.87, + "learning_rate": 8.4800086918731e-07, + "loss": 0.2546, + "step": 35255 + }, + { + "epoch": 2.87, + "learning_rate": 8.474576271186441e-07, + "loss": 0.273, + "step": 35256 + }, + { + "epoch": 2.87, + "learning_rate": 8.469143850499783e-07, + "loss": 0.2952, + "step": 35257 + }, + { + "epoch": 2.87, + "learning_rate": 8.463711429813124e-07, + "loss": 0.0639, + "step": 35258 + }, + { + "epoch": 2.87, + "learning_rate": 8.458279009126468e-07, + "loss": 0.2312, + "step": 35259 + }, + { + "epoch": 2.87, + "learning_rate": 8.45284658843981e-07, + "loss": 0.637, + "step": 35260 + }, + { + "epoch": 2.87, + "learning_rate": 8.447414167753151e-07, + "loss": 0.4195, + "step": 35261 + }, + { + "epoch": 2.87, + "learning_rate": 8.441981747066494e-07, + "loss": 0.1114, + "step": 35262 + }, + { + "epoch": 2.87, + "learning_rate": 8.436549326379835e-07, + "loss": 0.2722, + "step": 35263 + }, + { + "epoch": 2.87, + "learning_rate": 8.431116905693178e-07, + "loss": 0.3106, + "step": 35264 + }, + { + "epoch": 2.87, + "learning_rate": 8.425684485006519e-07, + "loss": 0.3868, + "step": 35265 + }, + { + "epoch": 2.87, + "learning_rate": 8.420252064319862e-07, + "loss": 0.0732, + "step": 35266 + }, + { + "epoch": 2.87, + "learning_rate": 8.414819643633204e-07, + "loss": 0.1447, + "step": 35267 + }, + { + "epoch": 2.87, + "learning_rate": 8.409387222946545e-07, + "loss": 0.0969, + "step": 35268 + }, + { + "epoch": 2.87, + "learning_rate": 8.403954802259888e-07, + "loss": 0.0612, + "step": 35269 + }, + { + "epoch": 2.87, + "learning_rate": 8.398522381573229e-07, + "loss": 0.0547, + "step": 35270 + }, + { + "epoch": 2.87, + "learning_rate": 8.393089960886572e-07, + "loss": 0.2472, + "step": 35271 + }, + { + "epoch": 2.87, + "learning_rate": 8.387657540199914e-07, + "loss": 0.2658, + "step": 35272 + }, + { + "epoch": 2.87, + "learning_rate": 8.382225119513256e-07, + "loss": 0.3568, + "step": 35273 + }, + { + "epoch": 2.87, + "learning_rate": 8.376792698826598e-07, + "loss": 0.2058, + "step": 35274 + }, + { + "epoch": 2.87, + "learning_rate": 8.371360278139939e-07, + "loss": 0.0705, + "step": 35275 + }, + { + "epoch": 2.87, + "learning_rate": 8.365927857453282e-07, + "loss": 0.1768, + "step": 35276 + }, + { + "epoch": 2.87, + "learning_rate": 8.360495436766623e-07, + "loss": 0.4513, + "step": 35277 + }, + { + "epoch": 2.87, + "learning_rate": 8.355063016079966e-07, + "loss": 0.1817, + "step": 35278 + }, + { + "epoch": 2.87, + "learning_rate": 8.349630595393309e-07, + "loss": 0.2208, + "step": 35279 + }, + { + "epoch": 2.87, + "learning_rate": 8.34419817470665e-07, + "loss": 0.2585, + "step": 35280 + }, + { + "epoch": 2.87, + "learning_rate": 8.338765754019992e-07, + "loss": 0.165, + "step": 35281 + }, + { + "epoch": 2.88, + "learning_rate": 8.333333333333333e-07, + "loss": 0.1821, + "step": 35282 + }, + { + "epoch": 2.88, + "learning_rate": 8.327900912646677e-07, + "loss": 0.2169, + "step": 35283 + }, + { + "epoch": 2.88, + "learning_rate": 8.322468491960017e-07, + "loss": 0.2494, + "step": 35284 + }, + { + "epoch": 2.88, + "learning_rate": 8.31703607127336e-07, + "loss": 0.1593, + "step": 35285 + }, + { + "epoch": 2.88, + "learning_rate": 8.311603650586703e-07, + "loss": 0.1093, + "step": 35286 + }, + { + "epoch": 2.88, + "learning_rate": 8.306171229900044e-07, + "loss": 0.2307, + "step": 35287 + }, + { + "epoch": 2.88, + "learning_rate": 8.300738809213386e-07, + "loss": 0.1097, + "step": 35288 + }, + { + "epoch": 2.88, + "learning_rate": 8.295306388526727e-07, + "loss": 0.2518, + "step": 35289 + }, + { + "epoch": 2.88, + "learning_rate": 8.289873967840071e-07, + "loss": 0.1149, + "step": 35290 + }, + { + "epoch": 2.88, + "learning_rate": 8.284441547153413e-07, + "loss": 0.5127, + "step": 35291 + }, + { + "epoch": 2.88, + "learning_rate": 8.279009126466754e-07, + "loss": 0.0526, + "step": 35292 + }, + { + "epoch": 2.88, + "learning_rate": 8.273576705780097e-07, + "loss": 0.4605, + "step": 35293 + }, + { + "epoch": 2.88, + "learning_rate": 8.268144285093438e-07, + "loss": 0.2134, + "step": 35294 + }, + { + "epoch": 2.88, + "learning_rate": 8.26271186440678e-07, + "loss": 0.1868, + "step": 35295 + }, + { + "epoch": 2.88, + "learning_rate": 8.257279443720121e-07, + "loss": 0.0749, + "step": 35296 + }, + { + "epoch": 2.88, + "learning_rate": 8.251847023033465e-07, + "loss": 0.216, + "step": 35297 + }, + { + "epoch": 2.88, + "learning_rate": 8.246414602346807e-07, + "loss": 0.176, + "step": 35298 + }, + { + "epoch": 2.88, + "learning_rate": 8.240982181660148e-07, + "loss": 0.2115, + "step": 35299 + }, + { + "epoch": 2.88, + "learning_rate": 8.235549760973491e-07, + "loss": 0.4744, + "step": 35300 + }, + { + "epoch": 2.88, + "learning_rate": 8.230117340286832e-07, + "loss": 0.2671, + "step": 35301 + }, + { + "epoch": 2.88, + "learning_rate": 8.224684919600174e-07, + "loss": 0.1495, + "step": 35302 + }, + { + "epoch": 2.88, + "learning_rate": 8.219252498913515e-07, + "loss": 0.1096, + "step": 35303 + }, + { + "epoch": 2.88, + "learning_rate": 8.213820078226859e-07, + "loss": 0.21, + "step": 35304 + }, + { + "epoch": 2.88, + "learning_rate": 8.208387657540201e-07, + "loss": 0.2824, + "step": 35305 + }, + { + "epoch": 2.88, + "learning_rate": 8.202955236853542e-07, + "loss": 0.2197, + "step": 35306 + }, + { + "epoch": 2.88, + "learning_rate": 8.197522816166885e-07, + "loss": 0.131, + "step": 35307 + }, + { + "epoch": 2.88, + "learning_rate": 8.192090395480226e-07, + "loss": 0.0461, + "step": 35308 + }, + { + "epoch": 2.88, + "learning_rate": 8.186657974793569e-07, + "loss": 0.2909, + "step": 35309 + }, + { + "epoch": 2.88, + "learning_rate": 8.181225554106912e-07, + "loss": 0.1648, + "step": 35310 + }, + { + "epoch": 2.88, + "learning_rate": 8.175793133420253e-07, + "loss": 0.3187, + "step": 35311 + }, + { + "epoch": 2.88, + "learning_rate": 8.170360712733595e-07, + "loss": 0.1937, + "step": 35312 + }, + { + "epoch": 2.88, + "learning_rate": 8.164928292046936e-07, + "loss": 0.1626, + "step": 35313 + }, + { + "epoch": 2.88, + "learning_rate": 8.159495871360279e-07, + "loss": 0.5288, + "step": 35314 + }, + { + "epoch": 2.88, + "learning_rate": 8.15406345067362e-07, + "loss": 0.1448, + "step": 35315 + }, + { + "epoch": 2.88, + "learning_rate": 8.148631029986963e-07, + "loss": 0.0938, + "step": 35316 + }, + { + "epoch": 2.88, + "learning_rate": 8.143198609300306e-07, + "loss": 0.0695, + "step": 35317 + }, + { + "epoch": 2.88, + "learning_rate": 8.137766188613647e-07, + "loss": 0.2634, + "step": 35318 + }, + { + "epoch": 2.88, + "learning_rate": 8.132333767926989e-07, + "loss": 0.2467, + "step": 35319 + }, + { + "epoch": 2.88, + "learning_rate": 8.12690134724033e-07, + "loss": 0.2301, + "step": 35320 + }, + { + "epoch": 2.88, + "learning_rate": 8.121468926553673e-07, + "loss": 0.2861, + "step": 35321 + }, + { + "epoch": 2.88, + "learning_rate": 8.116036505867016e-07, + "loss": 0.3679, + "step": 35322 + }, + { + "epoch": 2.88, + "learning_rate": 8.110604085180357e-07, + "loss": 0.3531, + "step": 35323 + }, + { + "epoch": 2.88, + "learning_rate": 8.1051716644937e-07, + "loss": 0.1263, + "step": 35324 + }, + { + "epoch": 2.88, + "learning_rate": 8.099739243807041e-07, + "loss": 0.6583, + "step": 35325 + }, + { + "epoch": 2.88, + "learning_rate": 8.094306823120383e-07, + "loss": 0.2331, + "step": 35326 + }, + { + "epoch": 2.88, + "learning_rate": 8.088874402433724e-07, + "loss": 0.3702, + "step": 35327 + }, + { + "epoch": 2.88, + "learning_rate": 8.083441981747067e-07, + "loss": 0.2128, + "step": 35328 + }, + { + "epoch": 2.88, + "learning_rate": 8.07800956106041e-07, + "loss": 0.3821, + "step": 35329 + }, + { + "epoch": 2.88, + "learning_rate": 8.072577140373751e-07, + "loss": 0.1475, + "step": 35330 + }, + { + "epoch": 2.88, + "learning_rate": 8.067144719687094e-07, + "loss": 0.2116, + "step": 35331 + }, + { + "epoch": 2.88, + "learning_rate": 8.061712299000435e-07, + "loss": 0.3464, + "step": 35332 + }, + { + "epoch": 2.88, + "learning_rate": 8.056279878313777e-07, + "loss": 0.1037, + "step": 35333 + }, + { + "epoch": 2.88, + "learning_rate": 8.050847457627118e-07, + "loss": 0.297, + "step": 35334 + }, + { + "epoch": 2.88, + "learning_rate": 8.045415036940462e-07, + "loss": 0.1536, + "step": 35335 + }, + { + "epoch": 2.88, + "learning_rate": 8.039982616253804e-07, + "loss": 0.24, + "step": 35336 + }, + { + "epoch": 2.88, + "learning_rate": 8.034550195567145e-07, + "loss": 0.0743, + "step": 35337 + }, + { + "epoch": 2.88, + "learning_rate": 8.029117774880488e-07, + "loss": 0.3695, + "step": 35338 + }, + { + "epoch": 2.88, + "learning_rate": 8.023685354193829e-07, + "loss": 0.3463, + "step": 35339 + }, + { + "epoch": 2.88, + "learning_rate": 8.018252933507171e-07, + "loss": 0.0534, + "step": 35340 + }, + { + "epoch": 2.88, + "learning_rate": 8.012820512820515e-07, + "loss": 0.1918, + "step": 35341 + }, + { + "epoch": 2.88, + "learning_rate": 8.007388092133856e-07, + "loss": 0.0971, + "step": 35342 + }, + { + "epoch": 2.88, + "learning_rate": 8.001955671447198e-07, + "loss": 0.2062, + "step": 35343 + }, + { + "epoch": 2.88, + "learning_rate": 7.996523250760539e-07, + "loss": 0.0525, + "step": 35344 + }, + { + "epoch": 2.88, + "learning_rate": 7.991090830073882e-07, + "loss": 0.1565, + "step": 35345 + }, + { + "epoch": 2.88, + "learning_rate": 7.985658409387223e-07, + "loss": 0.1688, + "step": 35346 + }, + { + "epoch": 2.88, + "learning_rate": 7.980225988700565e-07, + "loss": 0.1163, + "step": 35347 + }, + { + "epoch": 2.88, + "learning_rate": 7.974793568013909e-07, + "loss": 0.0709, + "step": 35348 + }, + { + "epoch": 2.88, + "learning_rate": 7.96936114732725e-07, + "loss": 0.3034, + "step": 35349 + }, + { + "epoch": 2.88, + "learning_rate": 7.963928726640592e-07, + "loss": 0.0633, + "step": 35350 + }, + { + "epoch": 2.88, + "learning_rate": 7.958496305953933e-07, + "loss": 0.119, + "step": 35351 + }, + { + "epoch": 2.88, + "learning_rate": 7.953063885267276e-07, + "loss": 0.1409, + "step": 35352 + }, + { + "epoch": 2.88, + "learning_rate": 7.947631464580617e-07, + "loss": 0.3251, + "step": 35353 + }, + { + "epoch": 2.88, + "learning_rate": 7.94219904389396e-07, + "loss": 0.2746, + "step": 35354 + }, + { + "epoch": 2.88, + "learning_rate": 7.936766623207303e-07, + "loss": 0.4624, + "step": 35355 + }, + { + "epoch": 2.88, + "learning_rate": 7.931334202520644e-07, + "loss": 0.2574, + "step": 35356 + }, + { + "epoch": 2.88, + "learning_rate": 7.925901781833986e-07, + "loss": 0.1243, + "step": 35357 + }, + { + "epoch": 2.88, + "learning_rate": 7.920469361147327e-07, + "loss": 0.1991, + "step": 35358 + }, + { + "epoch": 2.88, + "learning_rate": 7.91503694046067e-07, + "loss": 0.2846, + "step": 35359 + }, + { + "epoch": 2.88, + "learning_rate": 7.909604519774013e-07, + "loss": 0.1988, + "step": 35360 + }, + { + "epoch": 2.88, + "learning_rate": 7.904172099087354e-07, + "loss": 0.0414, + "step": 35361 + }, + { + "epoch": 2.88, + "learning_rate": 7.898739678400697e-07, + "loss": 0.3627, + "step": 35362 + }, + { + "epoch": 2.88, + "learning_rate": 7.893307257714038e-07, + "loss": 0.3509, + "step": 35363 + }, + { + "epoch": 2.88, + "learning_rate": 7.88787483702738e-07, + "loss": 0.29, + "step": 35364 + }, + { + "epoch": 2.88, + "learning_rate": 7.882442416340721e-07, + "loss": 0.1809, + "step": 35365 + }, + { + "epoch": 2.88, + "learning_rate": 7.877009995654064e-07, + "loss": 0.206, + "step": 35366 + }, + { + "epoch": 2.88, + "learning_rate": 7.871577574967407e-07, + "loss": 0.1435, + "step": 35367 + }, + { + "epoch": 2.88, + "learning_rate": 7.866145154280748e-07, + "loss": 0.4254, + "step": 35368 + }, + { + "epoch": 2.88, + "learning_rate": 7.860712733594091e-07, + "loss": 0.1361, + "step": 35369 + }, + { + "epoch": 2.88, + "learning_rate": 7.855280312907432e-07, + "loss": 0.4077, + "step": 35370 + }, + { + "epoch": 2.88, + "learning_rate": 7.849847892220774e-07, + "loss": 0.1074, + "step": 35371 + }, + { + "epoch": 2.88, + "learning_rate": 7.844415471534115e-07, + "loss": 0.3083, + "step": 35372 + }, + { + "epoch": 2.88, + "learning_rate": 7.838983050847458e-07, + "loss": 0.3691, + "step": 35373 + }, + { + "epoch": 2.88, + "learning_rate": 7.833550630160801e-07, + "loss": 0.1806, + "step": 35374 + }, + { + "epoch": 2.88, + "learning_rate": 7.828118209474142e-07, + "loss": 0.0355, + "step": 35375 + }, + { + "epoch": 2.88, + "learning_rate": 7.822685788787485e-07, + "loss": 0.2988, + "step": 35376 + }, + { + "epoch": 2.88, + "learning_rate": 7.817253368100826e-07, + "loss": 0.0651, + "step": 35377 + }, + { + "epoch": 2.88, + "learning_rate": 7.811820947414168e-07, + "loss": 0.36, + "step": 35378 + }, + { + "epoch": 2.88, + "learning_rate": 7.806388526727512e-07, + "loss": 0.3065, + "step": 35379 + }, + { + "epoch": 2.88, + "learning_rate": 7.800956106040853e-07, + "loss": 0.4394, + "step": 35380 + }, + { + "epoch": 2.88, + "learning_rate": 7.795523685354195e-07, + "loss": 0.273, + "step": 35381 + }, + { + "epoch": 2.88, + "learning_rate": 7.790091264667536e-07, + "loss": 0.1841, + "step": 35382 + }, + { + "epoch": 2.88, + "learning_rate": 7.784658843980879e-07, + "loss": 0.1695, + "step": 35383 + }, + { + "epoch": 2.88, + "learning_rate": 7.77922642329422e-07, + "loss": 0.3099, + "step": 35384 + }, + { + "epoch": 2.88, + "learning_rate": 7.773794002607562e-07, + "loss": 0.2445, + "step": 35385 + }, + { + "epoch": 2.88, + "learning_rate": 7.768361581920906e-07, + "loss": 0.0624, + "step": 35386 + }, + { + "epoch": 2.88, + "learning_rate": 7.762929161234247e-07, + "loss": 0.3048, + "step": 35387 + }, + { + "epoch": 2.88, + "learning_rate": 7.757496740547589e-07, + "loss": 0.3893, + "step": 35388 + }, + { + "epoch": 2.88, + "learning_rate": 7.75206431986093e-07, + "loss": 0.0509, + "step": 35389 + }, + { + "epoch": 2.88, + "learning_rate": 7.746631899174273e-07, + "loss": 0.0975, + "step": 35390 + }, + { + "epoch": 2.88, + "learning_rate": 7.741199478487614e-07, + "loss": 0.1385, + "step": 35391 + }, + { + "epoch": 2.88, + "learning_rate": 7.735767057800956e-07, + "loss": 0.1358, + "step": 35392 + }, + { + "epoch": 2.88, + "learning_rate": 7.7303346371143e-07, + "loss": 0.503, + "step": 35393 + }, + { + "epoch": 2.88, + "learning_rate": 7.724902216427641e-07, + "loss": 0.1322, + "step": 35394 + }, + { + "epoch": 2.88, + "learning_rate": 7.719469795740983e-07, + "loss": 0.275, + "step": 35395 + }, + { + "epoch": 2.88, + "learning_rate": 7.714037375054324e-07, + "loss": 0.2624, + "step": 35396 + }, + { + "epoch": 2.88, + "learning_rate": 7.708604954367667e-07, + "loss": 0.2538, + "step": 35397 + }, + { + "epoch": 2.88, + "learning_rate": 7.70317253368101e-07, + "loss": 0.1856, + "step": 35398 + }, + { + "epoch": 2.88, + "learning_rate": 7.697740112994351e-07, + "loss": 0.4017, + "step": 35399 + }, + { + "epoch": 2.88, + "learning_rate": 7.692307692307694e-07, + "loss": 0.1536, + "step": 35400 + }, + { + "epoch": 2.88, + "learning_rate": 7.686875271621035e-07, + "loss": 0.1578, + "step": 35401 + }, + { + "epoch": 2.88, + "learning_rate": 7.681442850934377e-07, + "loss": 0.1511, + "step": 35402 + }, + { + "epoch": 2.88, + "learning_rate": 7.676010430247718e-07, + "loss": 0.1272, + "step": 35403 + }, + { + "epoch": 2.88, + "learning_rate": 7.670578009561061e-07, + "loss": 0.3605, + "step": 35404 + }, + { + "epoch": 2.89, + "learning_rate": 7.665145588874404e-07, + "loss": 0.4375, + "step": 35405 + }, + { + "epoch": 2.89, + "learning_rate": 7.659713168187745e-07, + "loss": 0.2685, + "step": 35406 + }, + { + "epoch": 2.89, + "learning_rate": 7.654280747501088e-07, + "loss": 0.2815, + "step": 35407 + }, + { + "epoch": 2.89, + "learning_rate": 7.648848326814429e-07, + "loss": 0.3141, + "step": 35408 + }, + { + "epoch": 2.89, + "learning_rate": 7.643415906127771e-07, + "loss": 0.1772, + "step": 35409 + }, + { + "epoch": 2.89, + "learning_rate": 7.637983485441112e-07, + "loss": 0.0842, + "step": 35410 + }, + { + "epoch": 2.89, + "learning_rate": 7.632551064754455e-07, + "loss": 0.2058, + "step": 35411 + }, + { + "epoch": 2.89, + "learning_rate": 7.627118644067798e-07, + "loss": 0.1899, + "step": 35412 + }, + { + "epoch": 2.89, + "learning_rate": 7.621686223381139e-07, + "loss": 0.0668, + "step": 35413 + }, + { + "epoch": 2.89, + "learning_rate": 7.616253802694482e-07, + "loss": 0.1679, + "step": 35414 + }, + { + "epoch": 2.89, + "learning_rate": 7.610821382007823e-07, + "loss": 0.4084, + "step": 35415 + }, + { + "epoch": 2.89, + "learning_rate": 7.605388961321165e-07, + "loss": 0.2418, + "step": 35416 + }, + { + "epoch": 2.89, + "learning_rate": 7.599956540634507e-07, + "loss": 0.1114, + "step": 35417 + }, + { + "epoch": 2.89, + "learning_rate": 7.594524119947849e-07, + "loss": 0.1344, + "step": 35418 + }, + { + "epoch": 2.89, + "learning_rate": 7.589091699261192e-07, + "loss": 0.575, + "step": 35419 + }, + { + "epoch": 2.89, + "learning_rate": 7.583659278574533e-07, + "loss": 0.1207, + "step": 35420 + }, + { + "epoch": 2.89, + "learning_rate": 7.578226857887876e-07, + "loss": 0.3146, + "step": 35421 + }, + { + "epoch": 2.89, + "learning_rate": 7.572794437201217e-07, + "loss": 0.1864, + "step": 35422 + }, + { + "epoch": 2.89, + "learning_rate": 7.567362016514559e-07, + "loss": 0.205, + "step": 35423 + }, + { + "epoch": 2.89, + "learning_rate": 7.561929595827903e-07, + "loss": 0.1186, + "step": 35424 + }, + { + "epoch": 2.89, + "learning_rate": 7.556497175141244e-07, + "loss": 0.1764, + "step": 35425 + }, + { + "epoch": 2.89, + "learning_rate": 7.551064754454586e-07, + "loss": 0.0973, + "step": 35426 + }, + { + "epoch": 2.89, + "learning_rate": 7.545632333767927e-07, + "loss": 0.2104, + "step": 35427 + }, + { + "epoch": 2.89, + "learning_rate": 7.54019991308127e-07, + "loss": 0.5531, + "step": 35428 + }, + { + "epoch": 2.89, + "learning_rate": 7.534767492394611e-07, + "loss": 0.2936, + "step": 35429 + }, + { + "epoch": 2.89, + "learning_rate": 7.529335071707953e-07, + "loss": 0.1453, + "step": 35430 + }, + { + "epoch": 2.89, + "learning_rate": 7.523902651021297e-07, + "loss": 0.2223, + "step": 35431 + }, + { + "epoch": 2.89, + "learning_rate": 7.518470230334638e-07, + "loss": 0.0913, + "step": 35432 + }, + { + "epoch": 2.89, + "learning_rate": 7.51303780964798e-07, + "loss": 0.1882, + "step": 35433 + }, + { + "epoch": 2.89, + "learning_rate": 7.507605388961321e-07, + "loss": 0.3743, + "step": 35434 + }, + { + "epoch": 2.89, + "learning_rate": 7.502172968274664e-07, + "loss": 0.1449, + "step": 35435 + }, + { + "epoch": 2.89, + "learning_rate": 7.496740547588006e-07, + "loss": 0.1547, + "step": 35436 + }, + { + "epoch": 2.89, + "learning_rate": 7.491308126901347e-07, + "loss": 0.1145, + "step": 35437 + }, + { + "epoch": 2.89, + "learning_rate": 7.485875706214691e-07, + "loss": 0.2358, + "step": 35438 + }, + { + "epoch": 2.89, + "learning_rate": 7.480443285528032e-07, + "loss": 0.0412, + "step": 35439 + }, + { + "epoch": 2.89, + "learning_rate": 7.475010864841374e-07, + "loss": 0.1294, + "step": 35440 + }, + { + "epoch": 2.89, + "learning_rate": 7.469578444154715e-07, + "loss": 0.2964, + "step": 35441 + }, + { + "epoch": 2.89, + "learning_rate": 7.464146023468058e-07, + "loss": 0.1297, + "step": 35442 + }, + { + "epoch": 2.89, + "learning_rate": 7.458713602781401e-07, + "loss": 0.3534, + "step": 35443 + }, + { + "epoch": 2.89, + "learning_rate": 7.453281182094741e-07, + "loss": 0.1687, + "step": 35444 + }, + { + "epoch": 2.89, + "learning_rate": 7.447848761408085e-07, + "loss": 0.1757, + "step": 35445 + }, + { + "epoch": 2.89, + "learning_rate": 7.442416340721426e-07, + "loss": 0.1856, + "step": 35446 + }, + { + "epoch": 2.89, + "learning_rate": 7.436983920034768e-07, + "loss": 0.1503, + "step": 35447 + }, + { + "epoch": 2.89, + "learning_rate": 7.431551499348109e-07, + "loss": 0.0669, + "step": 35448 + }, + { + "epoch": 2.89, + "learning_rate": 7.426119078661452e-07, + "loss": 0.0422, + "step": 35449 + }, + { + "epoch": 2.89, + "learning_rate": 7.420686657974795e-07, + "loss": 0.2902, + "step": 35450 + }, + { + "epoch": 2.89, + "learning_rate": 7.415254237288136e-07, + "loss": 0.2596, + "step": 35451 + }, + { + "epoch": 2.89, + "learning_rate": 7.409821816601479e-07, + "loss": 0.0898, + "step": 35452 + }, + { + "epoch": 2.89, + "learning_rate": 7.40438939591482e-07, + "loss": 0.204, + "step": 35453 + }, + { + "epoch": 2.89, + "learning_rate": 7.398956975228162e-07, + "loss": 0.0605, + "step": 35454 + }, + { + "epoch": 2.89, + "learning_rate": 7.393524554541505e-07, + "loss": 0.2607, + "step": 35455 + }, + { + "epoch": 2.89, + "learning_rate": 7.388092133854846e-07, + "loss": 0.2556, + "step": 35456 + }, + { + "epoch": 2.89, + "learning_rate": 7.382659713168189e-07, + "loss": 0.0573, + "step": 35457 + }, + { + "epoch": 2.89, + "learning_rate": 7.37722729248153e-07, + "loss": 0.1911, + "step": 35458 + }, + { + "epoch": 2.89, + "learning_rate": 7.371794871794873e-07, + "loss": 0.2803, + "step": 35459 + }, + { + "epoch": 2.89, + "learning_rate": 7.366362451108214e-07, + "loss": 0.2134, + "step": 35460 + }, + { + "epoch": 2.89, + "learning_rate": 7.360930030421556e-07, + "loss": 0.2097, + "step": 35461 + }, + { + "epoch": 2.89, + "learning_rate": 7.355497609734899e-07, + "loss": 0.1777, + "step": 35462 + }, + { + "epoch": 2.89, + "learning_rate": 7.35006518904824e-07, + "loss": 0.2196, + "step": 35463 + }, + { + "epoch": 2.89, + "learning_rate": 7.344632768361583e-07, + "loss": 0.3575, + "step": 35464 + }, + { + "epoch": 2.89, + "learning_rate": 7.339200347674924e-07, + "loss": 0.2398, + "step": 35465 + }, + { + "epoch": 2.89, + "learning_rate": 7.333767926988267e-07, + "loss": 0.0518, + "step": 35466 + }, + { + "epoch": 2.89, + "learning_rate": 7.328335506301609e-07, + "loss": 0.0347, + "step": 35467 + }, + { + "epoch": 2.89, + "learning_rate": 7.32290308561495e-07, + "loss": 0.185, + "step": 35468 + }, + { + "epoch": 2.89, + "learning_rate": 7.317470664928294e-07, + "loss": 0.3015, + "step": 35469 + }, + { + "epoch": 2.89, + "learning_rate": 7.312038244241635e-07, + "loss": 0.4181, + "step": 35470 + }, + { + "epoch": 2.89, + "learning_rate": 7.306605823554977e-07, + "loss": 0.2059, + "step": 35471 + }, + { + "epoch": 2.89, + "learning_rate": 7.301173402868318e-07, + "loss": 0.0417, + "step": 35472 + }, + { + "epoch": 2.89, + "learning_rate": 7.295740982181661e-07, + "loss": 0.2475, + "step": 35473 + }, + { + "epoch": 2.89, + "learning_rate": 7.290308561495003e-07, + "loss": 0.1676, + "step": 35474 + }, + { + "epoch": 2.89, + "learning_rate": 7.284876140808344e-07, + "loss": 0.1599, + "step": 35475 + }, + { + "epoch": 2.89, + "learning_rate": 7.279443720121688e-07, + "loss": 0.1954, + "step": 35476 + }, + { + "epoch": 2.89, + "learning_rate": 7.274011299435029e-07, + "loss": 0.1431, + "step": 35477 + }, + { + "epoch": 2.89, + "learning_rate": 7.268578878748371e-07, + "loss": 0.3755, + "step": 35478 + }, + { + "epoch": 2.89, + "learning_rate": 7.263146458061712e-07, + "loss": 0.2389, + "step": 35479 + }, + { + "epoch": 2.89, + "learning_rate": 7.257714037375055e-07, + "loss": 0.1173, + "step": 35480 + }, + { + "epoch": 2.89, + "learning_rate": 7.252281616688397e-07, + "loss": 0.1967, + "step": 35481 + }, + { + "epoch": 2.89, + "learning_rate": 7.246849196001738e-07, + "loss": 0.369, + "step": 35482 + }, + { + "epoch": 2.89, + "learning_rate": 7.241416775315082e-07, + "loss": 0.1185, + "step": 35483 + }, + { + "epoch": 2.89, + "learning_rate": 7.235984354628423e-07, + "loss": 0.3154, + "step": 35484 + }, + { + "epoch": 2.89, + "learning_rate": 7.230551933941765e-07, + "loss": 0.1505, + "step": 35485 + }, + { + "epoch": 2.89, + "learning_rate": 7.225119513255108e-07, + "loss": 0.2861, + "step": 35486 + }, + { + "epoch": 2.89, + "learning_rate": 7.219687092568449e-07, + "loss": 0.3485, + "step": 35487 + }, + { + "epoch": 2.89, + "learning_rate": 7.214254671881791e-07, + "loss": 0.1265, + "step": 35488 + }, + { + "epoch": 2.89, + "learning_rate": 7.208822251195132e-07, + "loss": 0.2017, + "step": 35489 + }, + { + "epoch": 2.89, + "learning_rate": 7.203389830508476e-07, + "loss": 0.1602, + "step": 35490 + }, + { + "epoch": 2.89, + "learning_rate": 7.197957409821817e-07, + "loss": 0.0709, + "step": 35491 + }, + { + "epoch": 2.89, + "learning_rate": 7.192524989135159e-07, + "loss": 0.1437, + "step": 35492 + }, + { + "epoch": 2.89, + "learning_rate": 7.187092568448502e-07, + "loss": 0.0574, + "step": 35493 + }, + { + "epoch": 2.89, + "learning_rate": 7.181660147761843e-07, + "loss": 0.3981, + "step": 35494 + }, + { + "epoch": 2.89, + "learning_rate": 7.176227727075186e-07, + "loss": 0.2829, + "step": 35495 + }, + { + "epoch": 2.89, + "learning_rate": 7.170795306388527e-07, + "loss": 0.0919, + "step": 35496 + }, + { + "epoch": 2.89, + "learning_rate": 7.16536288570187e-07, + "loss": 0.065, + "step": 35497 + }, + { + "epoch": 2.89, + "learning_rate": 7.159930465015211e-07, + "loss": 0.3168, + "step": 35498 + }, + { + "epoch": 2.89, + "learning_rate": 7.154498044328553e-07, + "loss": 0.3756, + "step": 35499 + }, + { + "epoch": 2.89, + "learning_rate": 7.149065623641896e-07, + "loss": 0.1095, + "step": 35500 + }, + { + "epoch": 2.89, + "eval_accuracy": 0.8442180336220071, + "eval_loss": 0.49290043115615845, + "eval_runtime": 22.3155, + "eval_samples_per_second": 439.829, + "eval_steps_per_second": 3.451, + "step": 35500 + }, + { + "epoch": 2.89, + "learning_rate": 7.143633202955237e-07, + "loss": 0.1203, + "step": 35501 + }, + { + "epoch": 2.89, + "learning_rate": 7.13820078226858e-07, + "loss": 0.2016, + "step": 35502 + }, + { + "epoch": 2.89, + "learning_rate": 7.132768361581921e-07, + "loss": 0.1698, + "step": 35503 + }, + { + "epoch": 2.89, + "learning_rate": 7.127335940895264e-07, + "loss": 0.5194, + "step": 35504 + }, + { + "epoch": 2.89, + "learning_rate": 7.121903520208606e-07, + "loss": 0.2412, + "step": 35505 + }, + { + "epoch": 2.89, + "learning_rate": 7.116471099521947e-07, + "loss": 0.196, + "step": 35506 + }, + { + "epoch": 2.89, + "learning_rate": 7.11103867883529e-07, + "loss": 0.0974, + "step": 35507 + }, + { + "epoch": 2.89, + "learning_rate": 7.105606258148631e-07, + "loss": 0.1265, + "step": 35508 + }, + { + "epoch": 2.89, + "learning_rate": 7.100173837461974e-07, + "loss": 0.0469, + "step": 35509 + }, + { + "epoch": 2.89, + "learning_rate": 7.094741416775315e-07, + "loss": 0.1904, + "step": 35510 + }, + { + "epoch": 2.89, + "learning_rate": 7.089308996088658e-07, + "loss": 0.2513, + "step": 35511 + }, + { + "epoch": 2.89, + "learning_rate": 7.083876575402e-07, + "loss": 0.1534, + "step": 35512 + }, + { + "epoch": 2.89, + "learning_rate": 7.078444154715341e-07, + "loss": 0.17, + "step": 35513 + }, + { + "epoch": 2.89, + "learning_rate": 7.073011734028685e-07, + "loss": 0.1845, + "step": 35514 + }, + { + "epoch": 2.89, + "learning_rate": 7.067579313342025e-07, + "loss": 0.3129, + "step": 35515 + }, + { + "epoch": 2.89, + "learning_rate": 7.062146892655368e-07, + "loss": 0.2247, + "step": 35516 + }, + { + "epoch": 2.89, + "learning_rate": 7.056714471968709e-07, + "loss": 0.6617, + "step": 35517 + }, + { + "epoch": 2.89, + "learning_rate": 7.051282051282052e-07, + "loss": 0.1389, + "step": 35518 + }, + { + "epoch": 2.89, + "learning_rate": 7.045849630595394e-07, + "loss": 0.2271, + "step": 35519 + }, + { + "epoch": 2.89, + "learning_rate": 7.040417209908735e-07, + "loss": 0.1966, + "step": 35520 + }, + { + "epoch": 2.89, + "learning_rate": 7.034984789222079e-07, + "loss": 0.4238, + "step": 35521 + }, + { + "epoch": 2.89, + "learning_rate": 7.02955236853542e-07, + "loss": 0.1957, + "step": 35522 + }, + { + "epoch": 2.89, + "learning_rate": 7.024119947848762e-07, + "loss": 0.0362, + "step": 35523 + }, + { + "epoch": 2.89, + "learning_rate": 7.018687527162105e-07, + "loss": 0.0433, + "step": 35524 + }, + { + "epoch": 2.89, + "learning_rate": 7.013255106475446e-07, + "loss": 0.3138, + "step": 35525 + }, + { + "epoch": 2.89, + "learning_rate": 7.007822685788788e-07, + "loss": 0.258, + "step": 35526 + }, + { + "epoch": 2.89, + "learning_rate": 7.002390265102129e-07, + "loss": 0.1449, + "step": 35527 + }, + { + "epoch": 2.9, + "learning_rate": 6.996957844415473e-07, + "loss": 0.5414, + "step": 35528 + }, + { + "epoch": 2.9, + "learning_rate": 6.991525423728814e-07, + "loss": 0.1002, + "step": 35529 + }, + { + "epoch": 2.9, + "learning_rate": 6.986093003042156e-07, + "loss": 0.1955, + "step": 35530 + }, + { + "epoch": 2.9, + "learning_rate": 6.980660582355499e-07, + "loss": 0.1586, + "step": 35531 + }, + { + "epoch": 2.9, + "learning_rate": 6.97522816166884e-07, + "loss": 0.4037, + "step": 35532 + }, + { + "epoch": 2.9, + "learning_rate": 6.969795740982182e-07, + "loss": 0.1518, + "step": 35533 + }, + { + "epoch": 2.9, + "learning_rate": 6.964363320295523e-07, + "loss": 0.3509, + "step": 35534 + }, + { + "epoch": 2.9, + "learning_rate": 6.958930899608867e-07, + "loss": 0.1405, + "step": 35535 + }, + { + "epoch": 2.9, + "learning_rate": 6.953498478922208e-07, + "loss": 0.0582, + "step": 35536 + }, + { + "epoch": 2.9, + "learning_rate": 6.94806605823555e-07, + "loss": 0.117, + "step": 35537 + }, + { + "epoch": 2.9, + "learning_rate": 6.942633637548893e-07, + "loss": 0.2255, + "step": 35538 + }, + { + "epoch": 2.9, + "learning_rate": 6.937201216862234e-07, + "loss": 0.1116, + "step": 35539 + }, + { + "epoch": 2.9, + "learning_rate": 6.931768796175577e-07, + "loss": 0.2927, + "step": 35540 + }, + { + "epoch": 2.9, + "learning_rate": 6.926336375488918e-07, + "loss": 0.0333, + "step": 35541 + }, + { + "epoch": 2.9, + "learning_rate": 6.920903954802261e-07, + "loss": 0.2376, + "step": 35542 + }, + { + "epoch": 2.9, + "learning_rate": 6.915471534115603e-07, + "loss": 0.0982, + "step": 35543 + }, + { + "epoch": 2.9, + "learning_rate": 6.910039113428944e-07, + "loss": 0.2295, + "step": 35544 + }, + { + "epoch": 2.9, + "learning_rate": 6.904606692742287e-07, + "loss": 0.0809, + "step": 35545 + }, + { + "epoch": 2.9, + "learning_rate": 6.899174272055628e-07, + "loss": 0.196, + "step": 35546 + }, + { + "epoch": 2.9, + "learning_rate": 6.893741851368971e-07, + "loss": 0.0947, + "step": 35547 + }, + { + "epoch": 2.9, + "learning_rate": 6.888309430682312e-07, + "loss": 0.0737, + "step": 35548 + }, + { + "epoch": 2.9, + "learning_rate": 6.882877009995655e-07, + "loss": 0.1126, + "step": 35549 + }, + { + "epoch": 2.9, + "learning_rate": 6.877444589308997e-07, + "loss": 0.1991, + "step": 35550 + }, + { + "epoch": 2.9, + "learning_rate": 6.872012168622338e-07, + "loss": 0.2171, + "step": 35551 + }, + { + "epoch": 2.9, + "learning_rate": 6.866579747935681e-07, + "loss": 0.1532, + "step": 35552 + }, + { + "epoch": 2.9, + "learning_rate": 6.861147327249022e-07, + "loss": 0.1559, + "step": 35553 + }, + { + "epoch": 2.9, + "learning_rate": 6.855714906562365e-07, + "loss": 0.0658, + "step": 35554 + }, + { + "epoch": 2.9, + "learning_rate": 6.850282485875706e-07, + "loss": 0.2142, + "step": 35555 + }, + { + "epoch": 2.9, + "learning_rate": 6.844850065189049e-07, + "loss": 0.0606, + "step": 35556 + }, + { + "epoch": 2.9, + "learning_rate": 6.839417644502391e-07, + "loss": 0.1302, + "step": 35557 + }, + { + "epoch": 2.9, + "learning_rate": 6.833985223815732e-07, + "loss": 0.179, + "step": 35558 + }, + { + "epoch": 2.9, + "learning_rate": 6.828552803129075e-07, + "loss": 0.1283, + "step": 35559 + }, + { + "epoch": 2.9, + "learning_rate": 6.823120382442416e-07, + "loss": 0.1255, + "step": 35560 + }, + { + "epoch": 2.9, + "learning_rate": 6.817687961755759e-07, + "loss": 0.2254, + "step": 35561 + }, + { + "epoch": 2.9, + "learning_rate": 6.812255541069102e-07, + "loss": 0.425, + "step": 35562 + }, + { + "epoch": 2.9, + "learning_rate": 6.806823120382443e-07, + "loss": 0.0892, + "step": 35563 + }, + { + "epoch": 2.9, + "learning_rate": 6.801390699695785e-07, + "loss": 0.1941, + "step": 35564 + }, + { + "epoch": 2.9, + "learning_rate": 6.795958279009126e-07, + "loss": 0.2368, + "step": 35565 + }, + { + "epoch": 2.9, + "learning_rate": 6.79052585832247e-07, + "loss": 0.1481, + "step": 35566 + }, + { + "epoch": 2.9, + "learning_rate": 6.785093437635811e-07, + "loss": 0.1317, + "step": 35567 + }, + { + "epoch": 2.9, + "learning_rate": 6.779661016949153e-07, + "loss": 0.109, + "step": 35568 + }, + { + "epoch": 2.9, + "learning_rate": 6.774228596262496e-07, + "loss": 0.2199, + "step": 35569 + }, + { + "epoch": 2.9, + "learning_rate": 6.768796175575837e-07, + "loss": 0.0978, + "step": 35570 + }, + { + "epoch": 2.9, + "learning_rate": 6.763363754889179e-07, + "loss": 0.1914, + "step": 35571 + }, + { + "epoch": 2.9, + "learning_rate": 6.75793133420252e-07, + "loss": 0.3346, + "step": 35572 + }, + { + "epoch": 2.9, + "learning_rate": 6.752498913515864e-07, + "loss": 0.2744, + "step": 35573 + }, + { + "epoch": 2.9, + "learning_rate": 6.747066492829205e-07, + "loss": 0.2846, + "step": 35574 + }, + { + "epoch": 2.9, + "learning_rate": 6.741634072142547e-07, + "loss": 0.3015, + "step": 35575 + }, + { + "epoch": 2.9, + "learning_rate": 6.73620165145589e-07, + "loss": 0.1259, + "step": 35576 + }, + { + "epoch": 2.9, + "learning_rate": 6.730769230769231e-07, + "loss": 0.1671, + "step": 35577 + }, + { + "epoch": 2.9, + "learning_rate": 6.725336810082573e-07, + "loss": 0.2158, + "step": 35578 + }, + { + "epoch": 2.9, + "learning_rate": 6.719904389395914e-07, + "loss": 0.2962, + "step": 35579 + }, + { + "epoch": 2.9, + "learning_rate": 6.714471968709258e-07, + "loss": 0.446, + "step": 35580 + }, + { + "epoch": 2.9, + "learning_rate": 6.7090395480226e-07, + "loss": 0.2842, + "step": 35581 + }, + { + "epoch": 2.9, + "learning_rate": 6.703607127335941e-07, + "loss": 0.0454, + "step": 35582 + }, + { + "epoch": 2.9, + "learning_rate": 6.698174706649284e-07, + "loss": 0.2699, + "step": 35583 + }, + { + "epoch": 2.9, + "learning_rate": 6.692742285962625e-07, + "loss": 0.2691, + "step": 35584 + }, + { + "epoch": 2.9, + "learning_rate": 6.687309865275968e-07, + "loss": 0.3217, + "step": 35585 + }, + { + "epoch": 2.9, + "learning_rate": 6.681877444589308e-07, + "loss": 0.2228, + "step": 35586 + }, + { + "epoch": 2.9, + "learning_rate": 6.676445023902652e-07, + "loss": 0.299, + "step": 35587 + }, + { + "epoch": 2.9, + "learning_rate": 6.671012603215994e-07, + "loss": 0.0312, + "step": 35588 + }, + { + "epoch": 2.9, + "learning_rate": 6.665580182529335e-07, + "loss": 0.2183, + "step": 35589 + }, + { + "epoch": 2.9, + "learning_rate": 6.660147761842678e-07, + "loss": 0.417, + "step": 35590 + }, + { + "epoch": 2.9, + "learning_rate": 6.654715341156019e-07, + "loss": 0.4524, + "step": 35591 + }, + { + "epoch": 2.9, + "learning_rate": 6.649282920469362e-07, + "loss": 0.1406, + "step": 35592 + }, + { + "epoch": 2.9, + "learning_rate": 6.643850499782703e-07, + "loss": 0.095, + "step": 35593 + }, + { + "epoch": 2.9, + "learning_rate": 6.638418079096046e-07, + "loss": 0.2825, + "step": 35594 + }, + { + "epoch": 2.9, + "learning_rate": 6.632985658409388e-07, + "loss": 0.2448, + "step": 35595 + }, + { + "epoch": 2.9, + "learning_rate": 6.627553237722729e-07, + "loss": 0.2226, + "step": 35596 + }, + { + "epoch": 2.9, + "learning_rate": 6.622120817036072e-07, + "loss": 0.4001, + "step": 35597 + }, + { + "epoch": 2.9, + "learning_rate": 6.616688396349413e-07, + "loss": 0.2207, + "step": 35598 + }, + { + "epoch": 2.9, + "learning_rate": 6.611255975662756e-07, + "loss": 0.2448, + "step": 35599 + }, + { + "epoch": 2.9, + "learning_rate": 6.605823554976099e-07, + "loss": 0.1861, + "step": 35600 + }, + { + "epoch": 2.9, + "learning_rate": 6.60039113428944e-07, + "loss": 0.1032, + "step": 35601 + }, + { + "epoch": 2.9, + "learning_rate": 6.594958713602782e-07, + "loss": 0.256, + "step": 35602 + }, + { + "epoch": 2.9, + "learning_rate": 6.589526292916123e-07, + "loss": 0.2797, + "step": 35603 + }, + { + "epoch": 2.9, + "learning_rate": 6.584093872229466e-07, + "loss": 0.3898, + "step": 35604 + }, + { + "epoch": 2.9, + "learning_rate": 6.578661451542807e-07, + "loss": 0.2941, + "step": 35605 + }, + { + "epoch": 2.9, + "learning_rate": 6.57322903085615e-07, + "loss": 0.1607, + "step": 35606 + }, + { + "epoch": 2.9, + "learning_rate": 6.567796610169493e-07, + "loss": 0.1622, + "step": 35607 + }, + { + "epoch": 2.9, + "learning_rate": 6.562364189482834e-07, + "loss": 0.0523, + "step": 35608 + }, + { + "epoch": 2.9, + "learning_rate": 6.556931768796176e-07, + "loss": 0.2142, + "step": 35609 + }, + { + "epoch": 2.9, + "learning_rate": 6.551499348109517e-07, + "loss": 0.0769, + "step": 35610 + }, + { + "epoch": 2.9, + "learning_rate": 6.546066927422861e-07, + "loss": 0.1405, + "step": 35611 + }, + { + "epoch": 2.9, + "learning_rate": 6.540634506736203e-07, + "loss": 0.3399, + "step": 35612 + }, + { + "epoch": 2.9, + "learning_rate": 6.535202086049544e-07, + "loss": 0.2774, + "step": 35613 + }, + { + "epoch": 2.9, + "learning_rate": 6.529769665362887e-07, + "loss": 0.5114, + "step": 35614 + }, + { + "epoch": 2.9, + "learning_rate": 6.524337244676228e-07, + "loss": 0.1841, + "step": 35615 + }, + { + "epoch": 2.9, + "learning_rate": 6.51890482398957e-07, + "loss": 0.2928, + "step": 35616 + }, + { + "epoch": 2.9, + "learning_rate": 6.513472403302911e-07, + "loss": 0.2798, + "step": 35617 + }, + { + "epoch": 2.9, + "learning_rate": 6.508039982616255e-07, + "loss": 0.0885, + "step": 35618 + }, + { + "epoch": 2.9, + "learning_rate": 6.502607561929597e-07, + "loss": 0.0675, + "step": 35619 + }, + { + "epoch": 2.9, + "learning_rate": 6.497175141242938e-07, + "loss": 0.1853, + "step": 35620 + }, + { + "epoch": 2.9, + "learning_rate": 6.491742720556281e-07, + "loss": 0.087, + "step": 35621 + }, + { + "epoch": 2.9, + "learning_rate": 6.486310299869622e-07, + "loss": 0.3682, + "step": 35622 + }, + { + "epoch": 2.9, + "learning_rate": 6.480877879182964e-07, + "loss": 0.1854, + "step": 35623 + }, + { + "epoch": 2.9, + "learning_rate": 6.475445458496305e-07, + "loss": 0.2058, + "step": 35624 + }, + { + "epoch": 2.9, + "learning_rate": 6.470013037809649e-07, + "loss": 0.1128, + "step": 35625 + }, + { + "epoch": 2.9, + "learning_rate": 6.464580617122991e-07, + "loss": 0.106, + "step": 35626 + }, + { + "epoch": 2.9, + "learning_rate": 6.459148196436332e-07, + "loss": 0.2065, + "step": 35627 + }, + { + "epoch": 2.9, + "learning_rate": 6.453715775749675e-07, + "loss": 0.2175, + "step": 35628 + }, + { + "epoch": 2.9, + "learning_rate": 6.448283355063016e-07, + "loss": 0.2012, + "step": 35629 + }, + { + "epoch": 2.9, + "learning_rate": 6.442850934376358e-07, + "loss": 0.2423, + "step": 35630 + }, + { + "epoch": 2.9, + "learning_rate": 6.437418513689702e-07, + "loss": 0.2988, + "step": 35631 + }, + { + "epoch": 2.9, + "learning_rate": 6.431986093003043e-07, + "loss": 0.2462, + "step": 35632 + }, + { + "epoch": 2.9, + "learning_rate": 6.426553672316385e-07, + "loss": 0.1105, + "step": 35633 + }, + { + "epoch": 2.9, + "learning_rate": 6.421121251629726e-07, + "loss": 0.1484, + "step": 35634 + }, + { + "epoch": 2.9, + "learning_rate": 6.415688830943069e-07, + "loss": 0.1439, + "step": 35635 + }, + { + "epoch": 2.9, + "learning_rate": 6.41025641025641e-07, + "loss": 0.2479, + "step": 35636 + }, + { + "epoch": 2.9, + "learning_rate": 6.404823989569753e-07, + "loss": 0.2268, + "step": 35637 + }, + { + "epoch": 2.9, + "learning_rate": 6.399391568883096e-07, + "loss": 0.1608, + "step": 35638 + }, + { + "epoch": 2.9, + "learning_rate": 6.393959148196437e-07, + "loss": 0.1456, + "step": 35639 + }, + { + "epoch": 2.9, + "learning_rate": 6.388526727509779e-07, + "loss": 0.4513, + "step": 35640 + }, + { + "epoch": 2.9, + "learning_rate": 6.38309430682312e-07, + "loss": 0.357, + "step": 35641 + }, + { + "epoch": 2.9, + "learning_rate": 6.377661886136463e-07, + "loss": 0.1551, + "step": 35642 + }, + { + "epoch": 2.9, + "learning_rate": 6.372229465449804e-07, + "loss": 0.6591, + "step": 35643 + }, + { + "epoch": 2.9, + "learning_rate": 6.366797044763147e-07, + "loss": 0.0601, + "step": 35644 + }, + { + "epoch": 2.9, + "learning_rate": 6.36136462407649e-07, + "loss": 0.2142, + "step": 35645 + }, + { + "epoch": 2.9, + "learning_rate": 6.355932203389831e-07, + "loss": 0.0896, + "step": 35646 + }, + { + "epoch": 2.9, + "learning_rate": 6.350499782703173e-07, + "loss": 0.2715, + "step": 35647 + }, + { + "epoch": 2.9, + "learning_rate": 6.345067362016514e-07, + "loss": 0.1871, + "step": 35648 + }, + { + "epoch": 2.9, + "learning_rate": 6.339634941329857e-07, + "loss": 0.1785, + "step": 35649 + }, + { + "epoch": 2.9, + "learning_rate": 6.3342025206432e-07, + "loss": 0.0801, + "step": 35650 + }, + { + "epoch": 2.91, + "learning_rate": 6.328770099956541e-07, + "loss": 0.4353, + "step": 35651 + }, + { + "epoch": 2.91, + "learning_rate": 6.323337679269884e-07, + "loss": 0.2437, + "step": 35652 + }, + { + "epoch": 2.91, + "learning_rate": 6.317905258583225e-07, + "loss": 0.0448, + "step": 35653 + }, + { + "epoch": 2.91, + "learning_rate": 6.312472837896567e-07, + "loss": 0.0862, + "step": 35654 + }, + { + "epoch": 2.91, + "learning_rate": 6.307040417209908e-07, + "loss": 0.2637, + "step": 35655 + }, + { + "epoch": 2.91, + "learning_rate": 6.301607996523252e-07, + "loss": 0.2008, + "step": 35656 + }, + { + "epoch": 2.91, + "learning_rate": 6.296175575836594e-07, + "loss": 0.2334, + "step": 35657 + }, + { + "epoch": 2.91, + "learning_rate": 6.290743155149935e-07, + "loss": 0.3738, + "step": 35658 + }, + { + "epoch": 2.91, + "learning_rate": 6.285310734463278e-07, + "loss": 0.3756, + "step": 35659 + }, + { + "epoch": 2.91, + "learning_rate": 6.279878313776619e-07, + "loss": 0.2552, + "step": 35660 + }, + { + "epoch": 2.91, + "learning_rate": 6.274445893089961e-07, + "loss": 0.2892, + "step": 35661 + }, + { + "epoch": 2.91, + "learning_rate": 6.269013472403302e-07, + "loss": 0.1831, + "step": 35662 + }, + { + "epoch": 2.91, + "learning_rate": 6.263581051716646e-07, + "loss": 0.1753, + "step": 35663 + }, + { + "epoch": 2.91, + "learning_rate": 6.258148631029988e-07, + "loss": 0.6062, + "step": 35664 + }, + { + "epoch": 2.91, + "learning_rate": 6.252716210343329e-07, + "loss": 0.2967, + "step": 35665 + }, + { + "epoch": 2.91, + "learning_rate": 6.247283789656672e-07, + "loss": 0.1794, + "step": 35666 + }, + { + "epoch": 2.91, + "learning_rate": 6.241851368970014e-07, + "loss": 0.043, + "step": 35667 + }, + { + "epoch": 2.91, + "learning_rate": 6.236418948283355e-07, + "loss": 0.2894, + "step": 35668 + }, + { + "epoch": 2.91, + "learning_rate": 6.230986527596698e-07, + "loss": 0.1087, + "step": 35669 + }, + { + "epoch": 2.91, + "learning_rate": 6.22555410691004e-07, + "loss": 0.2994, + "step": 35670 + }, + { + "epoch": 2.91, + "learning_rate": 6.220121686223381e-07, + "loss": 0.2176, + "step": 35671 + }, + { + "epoch": 2.91, + "learning_rate": 6.214689265536724e-07, + "loss": 0.3049, + "step": 35672 + }, + { + "epoch": 2.91, + "learning_rate": 6.209256844850066e-07, + "loss": 0.1794, + "step": 35673 + }, + { + "epoch": 2.91, + "learning_rate": 6.203824424163408e-07, + "loss": 0.256, + "step": 35674 + }, + { + "epoch": 2.91, + "learning_rate": 6.198392003476749e-07, + "loss": 0.0726, + "step": 35675 + }, + { + "epoch": 2.91, + "learning_rate": 6.192959582790092e-07, + "loss": 0.341, + "step": 35676 + }, + { + "epoch": 2.91, + "learning_rate": 6.187527162103434e-07, + "loss": 0.223, + "step": 35677 + }, + { + "epoch": 2.91, + "learning_rate": 6.182094741416775e-07, + "loss": 0.5465, + "step": 35678 + }, + { + "epoch": 2.91, + "learning_rate": 6.176662320730118e-07, + "loss": 0.0672, + "step": 35679 + }, + { + "epoch": 2.91, + "learning_rate": 6.17122990004346e-07, + "loss": 0.1809, + "step": 35680 + }, + { + "epoch": 2.91, + "learning_rate": 6.165797479356802e-07, + "loss": 0.348, + "step": 35681 + }, + { + "epoch": 2.91, + "learning_rate": 6.160365058670144e-07, + "loss": 0.1692, + "step": 35682 + }, + { + "epoch": 2.91, + "learning_rate": 6.154932637983486e-07, + "loss": 0.2499, + "step": 35683 + }, + { + "epoch": 2.91, + "learning_rate": 6.149500217296828e-07, + "loss": 0.1908, + "step": 35684 + }, + { + "epoch": 2.91, + "learning_rate": 6.14406779661017e-07, + "loss": 0.2176, + "step": 35685 + }, + { + "epoch": 2.91, + "learning_rate": 6.138635375923512e-07, + "loss": 0.2654, + "step": 35686 + }, + { + "epoch": 2.91, + "learning_rate": 6.133202955236854e-07, + "loss": 0.4085, + "step": 35687 + }, + { + "epoch": 2.91, + "learning_rate": 6.127770534550196e-07, + "loss": 0.1149, + "step": 35688 + }, + { + "epoch": 2.91, + "learning_rate": 6.122338113863538e-07, + "loss": 0.1409, + "step": 35689 + }, + { + "epoch": 2.91, + "learning_rate": 6.11690569317688e-07, + "loss": 0.1899, + "step": 35690 + }, + { + "epoch": 2.91, + "learning_rate": 6.111473272490223e-07, + "loss": 0.175, + "step": 35691 + }, + { + "epoch": 2.91, + "learning_rate": 6.106040851803564e-07, + "loss": 0.1365, + "step": 35692 + }, + { + "epoch": 2.91, + "learning_rate": 6.100608431116906e-07, + "loss": 0.223, + "step": 35693 + }, + { + "epoch": 2.91, + "learning_rate": 6.095176010430248e-07, + "loss": 0.5712, + "step": 35694 + }, + { + "epoch": 2.91, + "learning_rate": 6.08974358974359e-07, + "loss": 0.4591, + "step": 35695 + }, + { + "epoch": 2.91, + "learning_rate": 6.084311169056932e-07, + "loss": 0.1954, + "step": 35696 + }, + { + "epoch": 2.91, + "learning_rate": 6.078878748370274e-07, + "loss": 0.0841, + "step": 35697 + }, + { + "epoch": 2.91, + "learning_rate": 6.073446327683617e-07, + "loss": 0.1163, + "step": 35698 + }, + { + "epoch": 2.91, + "learning_rate": 6.068013906996958e-07, + "loss": 0.372, + "step": 35699 + }, + { + "epoch": 2.91, + "learning_rate": 6.0625814863103e-07, + "loss": 0.2222, + "step": 35700 + }, + { + "epoch": 2.91, + "learning_rate": 6.057149065623643e-07, + "loss": 0.1741, + "step": 35701 + }, + { + "epoch": 2.91, + "learning_rate": 6.051716644936984e-07, + "loss": 0.0955, + "step": 35702 + }, + { + "epoch": 2.91, + "learning_rate": 6.046284224250326e-07, + "loss": 0.0328, + "step": 35703 + }, + { + "epoch": 2.91, + "learning_rate": 6.040851803563669e-07, + "loss": 0.2823, + "step": 35704 + }, + { + "epoch": 2.91, + "learning_rate": 6.035419382877011e-07, + "loss": 0.6864, + "step": 35705 + }, + { + "epoch": 2.91, + "learning_rate": 6.029986962190352e-07, + "loss": 0.2179, + "step": 35706 + }, + { + "epoch": 2.91, + "learning_rate": 6.024554541503695e-07, + "loss": 0.1192, + "step": 35707 + }, + { + "epoch": 2.91, + "learning_rate": 6.019122120817037e-07, + "loss": 0.3084, + "step": 35708 + }, + { + "epoch": 2.91, + "learning_rate": 6.013689700130378e-07, + "loss": 0.4345, + "step": 35709 + }, + { + "epoch": 2.91, + "learning_rate": 6.00825727944372e-07, + "loss": 0.1089, + "step": 35710 + }, + { + "epoch": 2.91, + "learning_rate": 6.002824858757063e-07, + "loss": 0.2652, + "step": 35711 + }, + { + "epoch": 2.91, + "learning_rate": 5.997392438070405e-07, + "loss": 0.1619, + "step": 35712 + }, + { + "epoch": 2.91, + "learning_rate": 5.991960017383746e-07, + "loss": 0.1153, + "step": 35713 + }, + { + "epoch": 2.91, + "learning_rate": 5.986527596697089e-07, + "loss": 0.1681, + "step": 35714 + }, + { + "epoch": 2.91, + "learning_rate": 5.981095176010431e-07, + "loss": 0.442, + "step": 35715 + }, + { + "epoch": 2.91, + "learning_rate": 5.975662755323773e-07, + "loss": 0.3216, + "step": 35716 + }, + { + "epoch": 2.91, + "learning_rate": 5.970230334637115e-07, + "loss": 0.1502, + "step": 35717 + }, + { + "epoch": 2.91, + "learning_rate": 5.964797913950457e-07, + "loss": 0.4392, + "step": 35718 + }, + { + "epoch": 2.91, + "learning_rate": 5.959365493263799e-07, + "loss": 0.2109, + "step": 35719 + }, + { + "epoch": 2.91, + "learning_rate": 5.95393307257714e-07, + "loss": 0.297, + "step": 35720 + }, + { + "epoch": 2.91, + "learning_rate": 5.948500651890483e-07, + "loss": 0.0982, + "step": 35721 + }, + { + "epoch": 2.91, + "learning_rate": 5.943068231203825e-07, + "loss": 0.177, + "step": 35722 + }, + { + "epoch": 2.91, + "learning_rate": 5.937635810517167e-07, + "loss": 0.4666, + "step": 35723 + }, + { + "epoch": 2.91, + "learning_rate": 5.93220338983051e-07, + "loss": 0.254, + "step": 35724 + }, + { + "epoch": 2.91, + "learning_rate": 5.926770969143851e-07, + "loss": 0.1906, + "step": 35725 + }, + { + "epoch": 2.91, + "learning_rate": 5.921338548457193e-07, + "loss": 0.3194, + "step": 35726 + }, + { + "epoch": 2.91, + "learning_rate": 5.915906127770535e-07, + "loss": 0.3394, + "step": 35727 + }, + { + "epoch": 2.91, + "learning_rate": 5.910473707083877e-07, + "loss": 0.1416, + "step": 35728 + }, + { + "epoch": 2.91, + "learning_rate": 5.905041286397219e-07, + "loss": 0.123, + "step": 35729 + }, + { + "epoch": 2.91, + "learning_rate": 5.899608865710561e-07, + "loss": 0.1212, + "step": 35730 + }, + { + "epoch": 2.91, + "learning_rate": 5.894176445023904e-07, + "loss": 0.0538, + "step": 35731 + }, + { + "epoch": 2.91, + "learning_rate": 5.888744024337245e-07, + "loss": 0.0797, + "step": 35732 + }, + { + "epoch": 2.91, + "learning_rate": 5.883311603650587e-07, + "loss": 0.3608, + "step": 35733 + }, + { + "epoch": 2.91, + "learning_rate": 5.877879182963929e-07, + "loss": 0.2362, + "step": 35734 + }, + { + "epoch": 2.91, + "learning_rate": 5.872446762277272e-07, + "loss": 0.2438, + "step": 35735 + }, + { + "epoch": 2.91, + "learning_rate": 5.867014341590614e-07, + "loss": 0.477, + "step": 35736 + }, + { + "epoch": 2.91, + "learning_rate": 5.861581920903955e-07, + "loss": 0.178, + "step": 35737 + }, + { + "epoch": 2.91, + "learning_rate": 5.856149500217298e-07, + "loss": 0.2866, + "step": 35738 + }, + { + "epoch": 2.91, + "learning_rate": 5.850717079530639e-07, + "loss": 0.1667, + "step": 35739 + }, + { + "epoch": 2.91, + "learning_rate": 5.845284658843981e-07, + "loss": 0.2248, + "step": 35740 + }, + { + "epoch": 2.91, + "learning_rate": 5.839852238157323e-07, + "loss": 0.3379, + "step": 35741 + }, + { + "epoch": 2.91, + "learning_rate": 5.834419817470666e-07, + "loss": 0.3008, + "step": 35742 + }, + { + "epoch": 2.91, + "learning_rate": 5.828987396784008e-07, + "loss": 0.1829, + "step": 35743 + }, + { + "epoch": 2.91, + "learning_rate": 5.823554976097349e-07, + "loss": 0.4382, + "step": 35744 + }, + { + "epoch": 2.91, + "learning_rate": 5.818122555410692e-07, + "loss": 0.2975, + "step": 35745 + }, + { + "epoch": 2.91, + "learning_rate": 5.812690134724033e-07, + "loss": 0.2121, + "step": 35746 + }, + { + "epoch": 2.91, + "learning_rate": 5.807257714037375e-07, + "loss": 0.101, + "step": 35747 + }, + { + "epoch": 2.91, + "learning_rate": 5.801825293350717e-07, + "loss": 0.0703, + "step": 35748 + }, + { + "epoch": 2.91, + "learning_rate": 5.79639287266406e-07, + "loss": 0.215, + "step": 35749 + }, + { + "epoch": 2.91, + "learning_rate": 5.790960451977402e-07, + "loss": 0.1216, + "step": 35750 + }, + { + "epoch": 2.91, + "eval_accuracy": 0.8435048395313296, + "eval_loss": 0.4968250095844269, + "eval_runtime": 22.1701, + "eval_samples_per_second": 442.714, + "eval_steps_per_second": 3.473, + "step": 35750 + }, + { + "epoch": 2.91, + "learning_rate": 5.785528031290743e-07, + "loss": 0.1626, + "step": 35751 + }, + { + "epoch": 2.91, + "learning_rate": 5.780095610604086e-07, + "loss": 0.1862, + "step": 35752 + }, + { + "epoch": 2.91, + "learning_rate": 5.774663189917428e-07, + "loss": 0.2256, + "step": 35753 + }, + { + "epoch": 2.91, + "learning_rate": 5.76923076923077e-07, + "loss": 0.5867, + "step": 35754 + }, + { + "epoch": 2.91, + "learning_rate": 5.763798348544111e-07, + "loss": 0.0967, + "step": 35755 + }, + { + "epoch": 2.91, + "learning_rate": 5.758365927857454e-07, + "loss": 0.4198, + "step": 35756 + }, + { + "epoch": 2.91, + "learning_rate": 5.752933507170796e-07, + "loss": 0.432, + "step": 35757 + }, + { + "epoch": 2.91, + "learning_rate": 5.747501086484137e-07, + "loss": 0.2134, + "step": 35758 + }, + { + "epoch": 2.91, + "learning_rate": 5.74206866579748e-07, + "loss": 0.1374, + "step": 35759 + }, + { + "epoch": 2.91, + "learning_rate": 5.736636245110822e-07, + "loss": 0.3419, + "step": 35760 + }, + { + "epoch": 2.91, + "learning_rate": 5.731203824424164e-07, + "loss": 0.1621, + "step": 35761 + }, + { + "epoch": 2.91, + "learning_rate": 5.725771403737507e-07, + "loss": 0.1058, + "step": 35762 + }, + { + "epoch": 2.91, + "learning_rate": 5.720338983050848e-07, + "loss": 0.269, + "step": 35763 + }, + { + "epoch": 2.91, + "learning_rate": 5.71490656236419e-07, + "loss": 0.0542, + "step": 35764 + }, + { + "epoch": 2.91, + "learning_rate": 5.709474141677531e-07, + "loss": 0.054, + "step": 35765 + }, + { + "epoch": 2.91, + "learning_rate": 5.704041720990874e-07, + "loss": 0.1984, + "step": 35766 + }, + { + "epoch": 2.91, + "learning_rate": 5.698609300304216e-07, + "loss": 0.1116, + "step": 35767 + }, + { + "epoch": 2.91, + "learning_rate": 5.693176879617558e-07, + "loss": 0.1652, + "step": 35768 + }, + { + "epoch": 2.91, + "learning_rate": 5.687744458930901e-07, + "loss": 0.2551, + "step": 35769 + }, + { + "epoch": 2.91, + "learning_rate": 5.682312038244242e-07, + "loss": 0.2494, + "step": 35770 + }, + { + "epoch": 2.91, + "learning_rate": 5.676879617557584e-07, + "loss": 0.2505, + "step": 35771 + }, + { + "epoch": 2.91, + "learning_rate": 5.671447196870926e-07, + "loss": 0.1653, + "step": 35772 + }, + { + "epoch": 2.92, + "learning_rate": 5.666014776184269e-07, + "loss": 0.2014, + "step": 35773 + }, + { + "epoch": 2.92, + "learning_rate": 5.66058235549761e-07, + "loss": 0.0325, + "step": 35774 + }, + { + "epoch": 2.92, + "learning_rate": 5.655149934810952e-07, + "loss": 0.0788, + "step": 35775 + }, + { + "epoch": 2.92, + "learning_rate": 5.649717514124295e-07, + "loss": 0.1081, + "step": 35776 + }, + { + "epoch": 2.92, + "learning_rate": 5.644285093437636e-07, + "loss": 0.4915, + "step": 35777 + }, + { + "epoch": 2.92, + "learning_rate": 5.638852672750978e-07, + "loss": 0.2889, + "step": 35778 + }, + { + "epoch": 2.92, + "learning_rate": 5.63342025206432e-07, + "loss": 0.2012, + "step": 35779 + }, + { + "epoch": 2.92, + "learning_rate": 5.627987831377663e-07, + "loss": 0.1076, + "step": 35780 + }, + { + "epoch": 2.92, + "learning_rate": 5.622555410691004e-07, + "loss": 0.1614, + "step": 35781 + }, + { + "epoch": 2.92, + "learning_rate": 5.617122990004346e-07, + "loss": 0.0776, + "step": 35782 + }, + { + "epoch": 2.92, + "learning_rate": 5.611690569317689e-07, + "loss": 0.2379, + "step": 35783 + }, + { + "epoch": 2.92, + "learning_rate": 5.60625814863103e-07, + "loss": 0.4426, + "step": 35784 + }, + { + "epoch": 2.92, + "learning_rate": 5.600825727944372e-07, + "loss": 0.1933, + "step": 35785 + }, + { + "epoch": 2.92, + "learning_rate": 5.595393307257714e-07, + "loss": 0.438, + "step": 35786 + }, + { + "epoch": 2.92, + "learning_rate": 5.589960886571057e-07, + "loss": 0.462, + "step": 35787 + }, + { + "epoch": 2.92, + "learning_rate": 5.584528465884399e-07, + "loss": 0.2619, + "step": 35788 + }, + { + "epoch": 2.92, + "learning_rate": 5.57909604519774e-07, + "loss": 0.0851, + "step": 35789 + }, + { + "epoch": 2.92, + "learning_rate": 5.573663624511083e-07, + "loss": 0.1624, + "step": 35790 + }, + { + "epoch": 2.92, + "learning_rate": 5.568231203824424e-07, + "loss": 0.2933, + "step": 35791 + }, + { + "epoch": 2.92, + "learning_rate": 5.562798783137767e-07, + "loss": 0.3327, + "step": 35792 + }, + { + "epoch": 2.92, + "learning_rate": 5.557366362451108e-07, + "loss": 0.0697, + "step": 35793 + }, + { + "epoch": 2.92, + "learning_rate": 5.551933941764451e-07, + "loss": 0.252, + "step": 35794 + }, + { + "epoch": 2.92, + "learning_rate": 5.546501521077793e-07, + "loss": 0.1539, + "step": 35795 + }, + { + "epoch": 2.92, + "learning_rate": 5.541069100391134e-07, + "loss": 0.0575, + "step": 35796 + }, + { + "epoch": 2.92, + "learning_rate": 5.535636679704477e-07, + "loss": 0.3324, + "step": 35797 + }, + { + "epoch": 2.92, + "learning_rate": 5.530204259017819e-07, + "loss": 0.4911, + "step": 35798 + }, + { + "epoch": 2.92, + "learning_rate": 5.524771838331161e-07, + "loss": 0.0829, + "step": 35799 + }, + { + "epoch": 2.92, + "learning_rate": 5.519339417644502e-07, + "loss": 0.2299, + "step": 35800 + }, + { + "epoch": 2.92, + "learning_rate": 5.513906996957845e-07, + "loss": 0.1919, + "step": 35801 + }, + { + "epoch": 2.92, + "learning_rate": 5.508474576271187e-07, + "loss": 0.2442, + "step": 35802 + }, + { + "epoch": 2.92, + "learning_rate": 5.503042155584528e-07, + "loss": 0.2028, + "step": 35803 + }, + { + "epoch": 2.92, + "learning_rate": 5.497609734897871e-07, + "loss": 0.5124, + "step": 35804 + }, + { + "epoch": 2.92, + "learning_rate": 5.492177314211213e-07, + "loss": 0.2992, + "step": 35805 + }, + { + "epoch": 2.92, + "learning_rate": 5.486744893524555e-07, + "loss": 0.2052, + "step": 35806 + }, + { + "epoch": 2.92, + "learning_rate": 5.481312472837898e-07, + "loss": 0.3579, + "step": 35807 + }, + { + "epoch": 2.92, + "learning_rate": 5.475880052151239e-07, + "loss": 0.1629, + "step": 35808 + }, + { + "epoch": 2.92, + "learning_rate": 5.470447631464581e-07, + "loss": 0.4847, + "step": 35809 + }, + { + "epoch": 2.92, + "learning_rate": 5.465015210777922e-07, + "loss": 0.1938, + "step": 35810 + }, + { + "epoch": 2.92, + "learning_rate": 5.459582790091266e-07, + "loss": 0.387, + "step": 35811 + }, + { + "epoch": 2.92, + "learning_rate": 5.454150369404607e-07, + "loss": 0.0422, + "step": 35812 + }, + { + "epoch": 2.92, + "learning_rate": 5.448717948717949e-07, + "loss": 0.3501, + "step": 35813 + }, + { + "epoch": 2.92, + "learning_rate": 5.443285528031292e-07, + "loss": 0.2205, + "step": 35814 + }, + { + "epoch": 2.92, + "learning_rate": 5.437853107344633e-07, + "loss": 0.2374, + "step": 35815 + }, + { + "epoch": 2.92, + "learning_rate": 5.432420686657975e-07, + "loss": 0.2205, + "step": 35816 + }, + { + "epoch": 2.92, + "learning_rate": 5.426988265971317e-07, + "loss": 0.3924, + "step": 35817 + }, + { + "epoch": 2.92, + "learning_rate": 5.42155584528466e-07, + "loss": 0.3206, + "step": 35818 + }, + { + "epoch": 2.92, + "learning_rate": 5.416123424598001e-07, + "loss": 0.1819, + "step": 35819 + }, + { + "epoch": 2.92, + "learning_rate": 5.410691003911343e-07, + "loss": 0.4248, + "step": 35820 + }, + { + "epoch": 2.92, + "learning_rate": 5.405258583224686e-07, + "loss": 0.1288, + "step": 35821 + }, + { + "epoch": 2.92, + "learning_rate": 5.399826162538027e-07, + "loss": 0.18, + "step": 35822 + }, + { + "epoch": 2.92, + "learning_rate": 5.394393741851369e-07, + "loss": 0.1736, + "step": 35823 + }, + { + "epoch": 2.92, + "learning_rate": 5.388961321164711e-07, + "loss": 0.1702, + "step": 35824 + }, + { + "epoch": 2.92, + "learning_rate": 5.383528900478054e-07, + "loss": 0.1963, + "step": 35825 + }, + { + "epoch": 2.92, + "learning_rate": 5.378096479791395e-07, + "loss": 0.4731, + "step": 35826 + }, + { + "epoch": 2.92, + "learning_rate": 5.372664059104737e-07, + "loss": 0.0813, + "step": 35827 + }, + { + "epoch": 2.92, + "learning_rate": 5.36723163841808e-07, + "loss": 0.1625, + "step": 35828 + }, + { + "epoch": 2.92, + "learning_rate": 5.361799217731421e-07, + "loss": 0.0549, + "step": 35829 + }, + { + "epoch": 2.92, + "learning_rate": 5.356366797044764e-07, + "loss": 0.1901, + "step": 35830 + }, + { + "epoch": 2.92, + "learning_rate": 5.350934376358105e-07, + "loss": 0.1196, + "step": 35831 + }, + { + "epoch": 2.92, + "learning_rate": 5.345501955671448e-07, + "loss": 0.1505, + "step": 35832 + }, + { + "epoch": 2.92, + "learning_rate": 5.34006953498479e-07, + "loss": 0.2278, + "step": 35833 + }, + { + "epoch": 2.92, + "learning_rate": 5.334637114298131e-07, + "loss": 0.067, + "step": 35834 + }, + { + "epoch": 2.92, + "learning_rate": 5.329204693611474e-07, + "loss": 0.1037, + "step": 35835 + }, + { + "epoch": 2.92, + "learning_rate": 5.323772272924816e-07, + "loss": 0.1928, + "step": 35836 + }, + { + "epoch": 2.92, + "learning_rate": 5.318339852238158e-07, + "loss": 0.0725, + "step": 35837 + }, + { + "epoch": 2.92, + "learning_rate": 5.3129074315515e-07, + "loss": 0.1123, + "step": 35838 + }, + { + "epoch": 2.92, + "learning_rate": 5.307475010864842e-07, + "loss": 0.164, + "step": 35839 + }, + { + "epoch": 2.92, + "learning_rate": 5.302042590178184e-07, + "loss": 0.1161, + "step": 35840 + }, + { + "epoch": 2.92, + "learning_rate": 5.296610169491525e-07, + "loss": 0.1371, + "step": 35841 + }, + { + "epoch": 2.92, + "learning_rate": 5.291177748804868e-07, + "loss": 0.2526, + "step": 35842 + }, + { + "epoch": 2.92, + "learning_rate": 5.28574532811821e-07, + "loss": 0.2681, + "step": 35843 + }, + { + "epoch": 2.92, + "learning_rate": 5.280312907431552e-07, + "loss": 0.1086, + "step": 35844 + }, + { + "epoch": 2.92, + "learning_rate": 5.274880486744894e-07, + "loss": 0.3449, + "step": 35845 + }, + { + "epoch": 2.92, + "learning_rate": 5.269448066058236e-07, + "loss": 0.1395, + "step": 35846 + }, + { + "epoch": 2.92, + "learning_rate": 5.264015645371578e-07, + "loss": 0.1122, + "step": 35847 + }, + { + "epoch": 2.92, + "learning_rate": 5.258583224684919e-07, + "loss": 0.0856, + "step": 35848 + }, + { + "epoch": 2.92, + "learning_rate": 5.253150803998263e-07, + "loss": 0.2825, + "step": 35849 + }, + { + "epoch": 2.92, + "learning_rate": 5.247718383311604e-07, + "loss": 0.1251, + "step": 35850 + }, + { + "epoch": 2.92, + "learning_rate": 5.242285962624946e-07, + "loss": 0.2118, + "step": 35851 + }, + { + "epoch": 2.92, + "learning_rate": 5.236853541938289e-07, + "loss": 0.1696, + "step": 35852 + }, + { + "epoch": 2.92, + "learning_rate": 5.23142112125163e-07, + "loss": 0.1856, + "step": 35853 + }, + { + "epoch": 2.92, + "learning_rate": 5.225988700564972e-07, + "loss": 0.165, + "step": 35854 + }, + { + "epoch": 2.92, + "learning_rate": 5.220556279878314e-07, + "loss": 0.205, + "step": 35855 + }, + { + "epoch": 2.92, + "learning_rate": 5.215123859191657e-07, + "loss": 0.2245, + "step": 35856 + }, + { + "epoch": 2.92, + "learning_rate": 5.209691438504998e-07, + "loss": 0.1516, + "step": 35857 + }, + { + "epoch": 2.92, + "learning_rate": 5.20425901781834e-07, + "loss": 0.2879, + "step": 35858 + }, + { + "epoch": 2.92, + "learning_rate": 5.198826597131683e-07, + "loss": 0.2933, + "step": 35859 + }, + { + "epoch": 2.92, + "learning_rate": 5.193394176445024e-07, + "loss": 0.3151, + "step": 35860 + }, + { + "epoch": 2.92, + "learning_rate": 5.187961755758366e-07, + "loss": 0.2561, + "step": 35861 + }, + { + "epoch": 2.92, + "learning_rate": 5.182529335071708e-07, + "loss": 0.4563, + "step": 35862 + }, + { + "epoch": 2.92, + "learning_rate": 5.177096914385051e-07, + "loss": 0.3416, + "step": 35863 + }, + { + "epoch": 2.92, + "learning_rate": 5.171664493698392e-07, + "loss": 0.121, + "step": 35864 + }, + { + "epoch": 2.92, + "learning_rate": 5.166232073011734e-07, + "loss": 0.0512, + "step": 35865 + }, + { + "epoch": 2.92, + "learning_rate": 5.160799652325077e-07, + "loss": 0.2126, + "step": 35866 + }, + { + "epoch": 2.92, + "learning_rate": 5.155367231638418e-07, + "loss": 0.2915, + "step": 35867 + }, + { + "epoch": 2.92, + "learning_rate": 5.149934810951761e-07, + "loss": 0.2218, + "step": 35868 + }, + { + "epoch": 2.92, + "learning_rate": 5.144502390265102e-07, + "loss": 0.1299, + "step": 35869 + }, + { + "epoch": 2.92, + "learning_rate": 5.139069969578445e-07, + "loss": 0.3072, + "step": 35870 + }, + { + "epoch": 2.92, + "learning_rate": 5.133637548891786e-07, + "loss": 0.053, + "step": 35871 + }, + { + "epoch": 2.92, + "learning_rate": 5.128205128205128e-07, + "loss": 0.0956, + "step": 35872 + }, + { + "epoch": 2.92, + "learning_rate": 5.122772707518471e-07, + "loss": 0.24, + "step": 35873 + }, + { + "epoch": 2.92, + "learning_rate": 5.117340286831813e-07, + "loss": 0.0755, + "step": 35874 + }, + { + "epoch": 2.92, + "learning_rate": 5.111907866145155e-07, + "loss": 0.2741, + "step": 35875 + }, + { + "epoch": 2.92, + "learning_rate": 5.106475445458497e-07, + "loss": 0.0802, + "step": 35876 + }, + { + "epoch": 2.92, + "learning_rate": 5.101043024771839e-07, + "loss": 0.2389, + "step": 35877 + }, + { + "epoch": 2.92, + "learning_rate": 5.095610604085181e-07, + "loss": 0.1276, + "step": 35878 + }, + { + "epoch": 2.92, + "learning_rate": 5.090178183398522e-07, + "loss": 0.2539, + "step": 35879 + }, + { + "epoch": 2.92, + "learning_rate": 5.084745762711865e-07, + "loss": 0.2009, + "step": 35880 + }, + { + "epoch": 2.92, + "learning_rate": 5.079313342025207e-07, + "loss": 0.1991, + "step": 35881 + }, + { + "epoch": 2.92, + "learning_rate": 5.073880921338549e-07, + "loss": 0.2381, + "step": 35882 + }, + { + "epoch": 2.92, + "learning_rate": 5.068448500651891e-07, + "loss": 0.1532, + "step": 35883 + }, + { + "epoch": 2.92, + "learning_rate": 5.063016079965233e-07, + "loss": 0.2417, + "step": 35884 + }, + { + "epoch": 2.92, + "learning_rate": 5.057583659278575e-07, + "loss": 0.2454, + "step": 35885 + }, + { + "epoch": 2.92, + "learning_rate": 5.052151238591916e-07, + "loss": 0.2349, + "step": 35886 + }, + { + "epoch": 2.92, + "learning_rate": 5.04671881790526e-07, + "loss": 0.2248, + "step": 35887 + }, + { + "epoch": 2.92, + "learning_rate": 5.041286397218601e-07, + "loss": 0.0696, + "step": 35888 + }, + { + "epoch": 2.92, + "learning_rate": 5.035853976531943e-07, + "loss": 0.2902, + "step": 35889 + }, + { + "epoch": 2.92, + "learning_rate": 5.030421555845285e-07, + "loss": 0.4496, + "step": 35890 + }, + { + "epoch": 2.92, + "learning_rate": 5.024989135158627e-07, + "loss": 0.1163, + "step": 35891 + }, + { + "epoch": 2.92, + "learning_rate": 5.019556714471969e-07, + "loss": 0.1937, + "step": 35892 + }, + { + "epoch": 2.92, + "learning_rate": 5.014124293785311e-07, + "loss": 0.1648, + "step": 35893 + }, + { + "epoch": 2.92, + "learning_rate": 5.008691873098654e-07, + "loss": 0.3735, + "step": 35894 + }, + { + "epoch": 2.92, + "learning_rate": 5.003259452411995e-07, + "loss": 0.2345, + "step": 35895 + }, + { + "epoch": 2.93, + "learning_rate": 4.997827031725337e-07, + "loss": 0.0776, + "step": 35896 + }, + { + "epoch": 2.93, + "learning_rate": 4.992394611038679e-07, + "loss": 0.136, + "step": 35897 + }, + { + "epoch": 2.93, + "learning_rate": 4.986962190352021e-07, + "loss": 0.2141, + "step": 35898 + }, + { + "epoch": 2.93, + "learning_rate": 4.981529769665363e-07, + "loss": 0.3032, + "step": 35899 + }, + { + "epoch": 2.93, + "learning_rate": 4.976097348978705e-07, + "loss": 0.4086, + "step": 35900 + }, + { + "epoch": 2.93, + "learning_rate": 4.970664928292048e-07, + "loss": 0.2094, + "step": 35901 + }, + { + "epoch": 2.93, + "learning_rate": 4.965232507605389e-07, + "loss": 0.3661, + "step": 35902 + }, + { + "epoch": 2.93, + "learning_rate": 4.959800086918731e-07, + "loss": 0.111, + "step": 35903 + }, + { + "epoch": 2.93, + "learning_rate": 4.954367666232074e-07, + "loss": 0.2712, + "step": 35904 + }, + { + "epoch": 2.93, + "learning_rate": 4.948935245545415e-07, + "loss": 0.3461, + "step": 35905 + }, + { + "epoch": 2.93, + "learning_rate": 4.943502824858757e-07, + "loss": 0.0996, + "step": 35906 + }, + { + "epoch": 2.93, + "learning_rate": 4.9380704041721e-07, + "loss": 0.0715, + "step": 35907 + }, + { + "epoch": 2.93, + "learning_rate": 4.932637983485442e-07, + "loss": 0.1661, + "step": 35908 + }, + { + "epoch": 2.93, + "learning_rate": 4.927205562798783e-07, + "loss": 0.2162, + "step": 35909 + }, + { + "epoch": 2.93, + "learning_rate": 4.921773142112125e-07, + "loss": 0.3328, + "step": 35910 + }, + { + "epoch": 2.93, + "learning_rate": 4.916340721425468e-07, + "loss": 0.2379, + "step": 35911 + }, + { + "epoch": 2.93, + "learning_rate": 4.91090830073881e-07, + "loss": 0.2524, + "step": 35912 + }, + { + "epoch": 2.93, + "learning_rate": 4.905475880052152e-07, + "loss": 0.0725, + "step": 35913 + }, + { + "epoch": 2.93, + "learning_rate": 4.900043459365494e-07, + "loss": 0.1063, + "step": 35914 + }, + { + "epoch": 2.93, + "learning_rate": 4.894611038678836e-07, + "loss": 0.2666, + "step": 35915 + }, + { + "epoch": 2.93, + "learning_rate": 4.889178617992177e-07, + "loss": 0.2069, + "step": 35916 + }, + { + "epoch": 2.93, + "learning_rate": 4.883746197305519e-07, + "loss": 0.3528, + "step": 35917 + }, + { + "epoch": 2.93, + "learning_rate": 4.878313776618862e-07, + "loss": 0.1754, + "step": 35918 + }, + { + "epoch": 2.93, + "learning_rate": 4.872881355932204e-07, + "loss": 0.0493, + "step": 35919 + }, + { + "epoch": 2.93, + "learning_rate": 4.867448935245546e-07, + "loss": 0.323, + "step": 35920 + }, + { + "epoch": 2.93, + "learning_rate": 4.862016514558888e-07, + "loss": 0.1082, + "step": 35921 + }, + { + "epoch": 2.93, + "learning_rate": 4.85658409387223e-07, + "loss": 0.2018, + "step": 35922 + }, + { + "epoch": 2.93, + "learning_rate": 4.851151673185572e-07, + "loss": 0.3139, + "step": 35923 + }, + { + "epoch": 2.93, + "learning_rate": 4.845719252498914e-07, + "loss": 0.2154, + "step": 35924 + }, + { + "epoch": 2.93, + "learning_rate": 4.840286831812256e-07, + "loss": 0.0793, + "step": 35925 + }, + { + "epoch": 2.93, + "learning_rate": 4.834854411125598e-07, + "loss": 0.4511, + "step": 35926 + }, + { + "epoch": 2.93, + "learning_rate": 4.82942199043894e-07, + "loss": 0.1947, + "step": 35927 + }, + { + "epoch": 2.93, + "learning_rate": 4.823989569752282e-07, + "loss": 0.1335, + "step": 35928 + }, + { + "epoch": 2.93, + "learning_rate": 4.818557149065624e-07, + "loss": 0.1058, + "step": 35929 + }, + { + "epoch": 2.93, + "learning_rate": 4.813124728378966e-07, + "loss": 0.3191, + "step": 35930 + }, + { + "epoch": 2.93, + "learning_rate": 4.807692307692308e-07, + "loss": 0.0597, + "step": 35931 + }, + { + "epoch": 2.93, + "learning_rate": 4.80225988700565e-07, + "loss": 0.37, + "step": 35932 + }, + { + "epoch": 2.93, + "learning_rate": 4.796827466318992e-07, + "loss": 0.1672, + "step": 35933 + }, + { + "epoch": 2.93, + "learning_rate": 4.791395045632334e-07, + "loss": 0.2078, + "step": 35934 + }, + { + "epoch": 2.93, + "learning_rate": 4.785962624945676e-07, + "loss": 0.0957, + "step": 35935 + }, + { + "epoch": 2.93, + "learning_rate": 4.780530204259018e-07, + "loss": 0.5649, + "step": 35936 + }, + { + "epoch": 2.93, + "learning_rate": 4.77509778357236e-07, + "loss": 0.2292, + "step": 35937 + }, + { + "epoch": 2.93, + "learning_rate": 4.769665362885703e-07, + "loss": 0.1812, + "step": 35938 + }, + { + "epoch": 2.93, + "learning_rate": 4.7642329421990443e-07, + "loss": 0.2522, + "step": 35939 + }, + { + "epoch": 2.93, + "learning_rate": 4.758800521512386e-07, + "loss": 0.3271, + "step": 35940 + }, + { + "epoch": 2.93, + "learning_rate": 4.7533681008257284e-07, + "loss": 0.1817, + "step": 35941 + }, + { + "epoch": 2.93, + "learning_rate": 4.74793568013907e-07, + "loss": 0.1508, + "step": 35942 + }, + { + "epoch": 2.93, + "learning_rate": 4.7425032594524125e-07, + "loss": 0.0769, + "step": 35943 + }, + { + "epoch": 2.93, + "learning_rate": 4.737070838765755e-07, + "loss": 0.3615, + "step": 35944 + }, + { + "epoch": 2.93, + "learning_rate": 4.7316384180790965e-07, + "loss": 0.0635, + "step": 35945 + }, + { + "epoch": 2.93, + "learning_rate": 4.7262059973924383e-07, + "loss": 0.2313, + "step": 35946 + }, + { + "epoch": 2.93, + "learning_rate": 4.7207735767057806e-07, + "loss": 0.2701, + "step": 35947 + }, + { + "epoch": 2.93, + "learning_rate": 4.7153411560191224e-07, + "loss": 0.2038, + "step": 35948 + }, + { + "epoch": 2.93, + "learning_rate": 4.709908735332464e-07, + "loss": 0.1341, + "step": 35949 + }, + { + "epoch": 2.93, + "learning_rate": 4.704476314645807e-07, + "loss": 0.0617, + "step": 35950 + }, + { + "epoch": 2.93, + "learning_rate": 4.699043893959149e-07, + "loss": 0.1774, + "step": 35951 + }, + { + "epoch": 2.93, + "learning_rate": 4.6936114732724906e-07, + "loss": 0.1314, + "step": 35952 + }, + { + "epoch": 2.93, + "learning_rate": 4.6881790525858323e-07, + "loss": 0.1879, + "step": 35953 + }, + { + "epoch": 2.93, + "learning_rate": 4.6827466318991746e-07, + "loss": 0.1765, + "step": 35954 + }, + { + "epoch": 2.93, + "learning_rate": 4.6773142112125164e-07, + "loss": 0.1254, + "step": 35955 + }, + { + "epoch": 2.93, + "learning_rate": 4.671881790525859e-07, + "loss": 0.2401, + "step": 35956 + }, + { + "epoch": 2.93, + "learning_rate": 4.666449369839201e-07, + "loss": 0.1273, + "step": 35957 + }, + { + "epoch": 2.93, + "learning_rate": 4.661016949152543e-07, + "loss": 0.4618, + "step": 35958 + }, + { + "epoch": 2.93, + "learning_rate": 4.6555845284658846e-07, + "loss": 0.4851, + "step": 35959 + }, + { + "epoch": 2.93, + "learning_rate": 4.650152107779227e-07, + "loss": 0.3074, + "step": 35960 + }, + { + "epoch": 2.93, + "learning_rate": 4.6447196870925687e-07, + "loss": 0.1215, + "step": 35961 + }, + { + "epoch": 2.93, + "learning_rate": 4.639287266405911e-07, + "loss": 0.145, + "step": 35962 + }, + { + "epoch": 2.93, + "learning_rate": 4.6338548457192533e-07, + "loss": 0.3456, + "step": 35963 + }, + { + "epoch": 2.93, + "learning_rate": 4.628422425032595e-07, + "loss": 0.2512, + "step": 35964 + }, + { + "epoch": 2.93, + "learning_rate": 4.622990004345937e-07, + "loss": 0.1907, + "step": 35965 + }, + { + "epoch": 2.93, + "learning_rate": 4.6175575836592786e-07, + "loss": 0.1426, + "step": 35966 + }, + { + "epoch": 2.93, + "learning_rate": 4.612125162972621e-07, + "loss": 0.0345, + "step": 35967 + }, + { + "epoch": 2.93, + "learning_rate": 4.6066927422859627e-07, + "loss": 0.143, + "step": 35968 + }, + { + "epoch": 2.93, + "learning_rate": 4.6012603215993055e-07, + "loss": 0.0387, + "step": 35969 + }, + { + "epoch": 2.93, + "learning_rate": 4.5958279009126473e-07, + "loss": 0.3208, + "step": 35970 + }, + { + "epoch": 2.93, + "learning_rate": 4.590395480225989e-07, + "loss": 0.4688, + "step": 35971 + }, + { + "epoch": 2.93, + "learning_rate": 4.584963059539331e-07, + "loss": 0.494, + "step": 35972 + }, + { + "epoch": 2.93, + "learning_rate": 4.579530638852673e-07, + "loss": 0.2627, + "step": 35973 + }, + { + "epoch": 2.93, + "learning_rate": 4.574098218166015e-07, + "loss": 0.1716, + "step": 35974 + }, + { + "epoch": 2.93, + "learning_rate": 4.568665797479357e-07, + "loss": 0.1595, + "step": 35975 + }, + { + "epoch": 2.93, + "learning_rate": 4.5632333767926995e-07, + "loss": 0.2834, + "step": 35976 + }, + { + "epoch": 2.93, + "learning_rate": 4.5578009561060413e-07, + "loss": 0.0712, + "step": 35977 + }, + { + "epoch": 2.93, + "learning_rate": 4.552368535419383e-07, + "loss": 0.1783, + "step": 35978 + }, + { + "epoch": 2.93, + "learning_rate": 4.546936114732725e-07, + "loss": 0.3628, + "step": 35979 + }, + { + "epoch": 2.93, + "learning_rate": 4.541503694046067e-07, + "loss": 0.1754, + "step": 35980 + }, + { + "epoch": 2.93, + "learning_rate": 4.5360712733594095e-07, + "loss": 0.3472, + "step": 35981 + }, + { + "epoch": 2.93, + "learning_rate": 4.530638852672752e-07, + "loss": 0.0839, + "step": 35982 + }, + { + "epoch": 2.93, + "learning_rate": 4.5252064319860936e-07, + "loss": 0.1776, + "step": 35983 + }, + { + "epoch": 2.93, + "learning_rate": 4.5197740112994353e-07, + "loss": 0.1472, + "step": 35984 + }, + { + "epoch": 2.93, + "learning_rate": 4.514341590612777e-07, + "loss": 0.2654, + "step": 35985 + }, + { + "epoch": 2.93, + "learning_rate": 4.5089091699261194e-07, + "loss": 0.5341, + "step": 35986 + }, + { + "epoch": 2.93, + "learning_rate": 4.503476749239461e-07, + "loss": 0.4468, + "step": 35987 + }, + { + "epoch": 2.93, + "learning_rate": 4.4980443285528035e-07, + "loss": 0.159, + "step": 35988 + }, + { + "epoch": 2.93, + "learning_rate": 4.492611907866146e-07, + "loss": 0.1765, + "step": 35989 + }, + { + "epoch": 2.93, + "learning_rate": 4.4871794871794876e-07, + "loss": 0.1376, + "step": 35990 + }, + { + "epoch": 2.93, + "learning_rate": 4.4817470664928293e-07, + "loss": 0.4279, + "step": 35991 + }, + { + "epoch": 2.93, + "learning_rate": 4.4763146458061717e-07, + "loss": 0.1442, + "step": 35992 + }, + { + "epoch": 2.93, + "learning_rate": 4.4708822251195134e-07, + "loss": 0.2152, + "step": 35993 + }, + { + "epoch": 2.93, + "learning_rate": 4.465449804432856e-07, + "loss": 0.5532, + "step": 35994 + }, + { + "epoch": 2.93, + "learning_rate": 4.460017383746198e-07, + "loss": 0.2641, + "step": 35995 + }, + { + "epoch": 2.93, + "learning_rate": 4.45458496305954e-07, + "loss": 0.284, + "step": 35996 + }, + { + "epoch": 2.93, + "learning_rate": 4.4491525423728816e-07, + "loss": 0.1113, + "step": 35997 + }, + { + "epoch": 2.93, + "learning_rate": 4.4437201216862234e-07, + "loss": 0.064, + "step": 35998 + }, + { + "epoch": 2.93, + "learning_rate": 4.4382877009995657e-07, + "loss": 0.115, + "step": 35999 + }, + { + "epoch": 2.93, + "learning_rate": 4.432855280312908e-07, + "loss": 0.1823, + "step": 36000 + }, + { + "epoch": 2.93, + "eval_accuracy": 0.845236882322975, + "eval_loss": 0.48998522758483887, + "eval_runtime": 22.2785, + "eval_samples_per_second": 440.56, + "eval_steps_per_second": 3.456, + "step": 36000 + }, + { + "epoch": 2.93, + "learning_rate": 4.42742285962625e-07, + "loss": 0.4058, + "step": 36001 + }, + { + "epoch": 2.93, + "learning_rate": 4.421990438939592e-07, + "loss": 0.4228, + "step": 36002 + }, + { + "epoch": 2.93, + "learning_rate": 4.416558018252934e-07, + "loss": 0.239, + "step": 36003 + }, + { + "epoch": 2.93, + "learning_rate": 4.4111255975662756e-07, + "loss": 0.438, + "step": 36004 + }, + { + "epoch": 2.93, + "learning_rate": 4.405693176879618e-07, + "loss": 0.1009, + "step": 36005 + }, + { + "epoch": 2.93, + "learning_rate": 4.40026075619296e-07, + "loss": 0.2157, + "step": 36006 + }, + { + "epoch": 2.93, + "learning_rate": 4.394828335506302e-07, + "loss": 0.0796, + "step": 36007 + }, + { + "epoch": 2.93, + "learning_rate": 4.3893959148196443e-07, + "loss": 0.0901, + "step": 36008 + }, + { + "epoch": 2.93, + "learning_rate": 4.383963494132986e-07, + "loss": 0.2191, + "step": 36009 + }, + { + "epoch": 2.93, + "learning_rate": 4.378531073446328e-07, + "loss": 0.2971, + "step": 36010 + }, + { + "epoch": 2.93, + "learning_rate": 4.3730986527596696e-07, + "loss": 0.2391, + "step": 36011 + }, + { + "epoch": 2.93, + "learning_rate": 4.367666232073012e-07, + "loss": 0.0786, + "step": 36012 + }, + { + "epoch": 2.93, + "learning_rate": 4.362233811386354e-07, + "loss": 0.1947, + "step": 36013 + }, + { + "epoch": 2.93, + "learning_rate": 4.3568013906996966e-07, + "loss": 0.1795, + "step": 36014 + }, + { + "epoch": 2.93, + "learning_rate": 4.3513689700130383e-07, + "loss": 0.0229, + "step": 36015 + }, + { + "epoch": 2.93, + "learning_rate": 4.34593654932638e-07, + "loss": 0.0889, + "step": 36016 + }, + { + "epoch": 2.93, + "learning_rate": 4.340504128639722e-07, + "loss": 0.5458, + "step": 36017 + }, + { + "epoch": 2.93, + "learning_rate": 4.335071707953064e-07, + "loss": 0.2095, + "step": 36018 + }, + { + "epoch": 2.94, + "learning_rate": 4.3296392872664065e-07, + "loss": 0.2397, + "step": 36019 + }, + { + "epoch": 2.94, + "learning_rate": 4.3242068665797483e-07, + "loss": 0.1376, + "step": 36020 + }, + { + "epoch": 2.94, + "learning_rate": 4.3187744458930906e-07, + "loss": 0.413, + "step": 36021 + }, + { + "epoch": 2.94, + "learning_rate": 4.3133420252064323e-07, + "loss": 0.2694, + "step": 36022 + }, + { + "epoch": 2.94, + "learning_rate": 4.307909604519774e-07, + "loss": 0.2018, + "step": 36023 + }, + { + "epoch": 2.94, + "learning_rate": 4.302477183833116e-07, + "loss": 0.202, + "step": 36024 + }, + { + "epoch": 2.94, + "learning_rate": 4.297044763146459e-07, + "loss": 0.1474, + "step": 36025 + }, + { + "epoch": 2.94, + "learning_rate": 4.2916123424598005e-07, + "loss": 0.3574, + "step": 36026 + }, + { + "epoch": 2.94, + "learning_rate": 4.286179921773143e-07, + "loss": 0.1346, + "step": 36027 + }, + { + "epoch": 2.94, + "learning_rate": 4.2807475010864846e-07, + "loss": 0.0747, + "step": 36028 + }, + { + "epoch": 2.94, + "learning_rate": 4.2753150803998264e-07, + "loss": 0.2153, + "step": 36029 + }, + { + "epoch": 2.94, + "learning_rate": 4.269882659713168e-07, + "loss": 0.45, + "step": 36030 + }, + { + "epoch": 2.94, + "learning_rate": 4.2644502390265105e-07, + "loss": 0.5251, + "step": 36031 + }, + { + "epoch": 2.94, + "learning_rate": 4.259017818339853e-07, + "loss": 0.176, + "step": 36032 + }, + { + "epoch": 2.94, + "learning_rate": 4.2535853976531945e-07, + "loss": 0.1838, + "step": 36033 + }, + { + "epoch": 2.94, + "learning_rate": 4.248152976966537e-07, + "loss": 0.3884, + "step": 36034 + }, + { + "epoch": 2.94, + "learning_rate": 4.2427205562798786e-07, + "loss": 0.2533, + "step": 36035 + }, + { + "epoch": 2.94, + "learning_rate": 4.2372881355932204e-07, + "loss": 0.121, + "step": 36036 + }, + { + "epoch": 2.94, + "learning_rate": 4.231855714906562e-07, + "loss": 0.1989, + "step": 36037 + }, + { + "epoch": 2.94, + "learning_rate": 4.226423294219905e-07, + "loss": 0.1009, + "step": 36038 + }, + { + "epoch": 2.94, + "learning_rate": 4.220990873533247e-07, + "loss": 0.2532, + "step": 36039 + }, + { + "epoch": 2.94, + "learning_rate": 4.215558452846589e-07, + "loss": 0.5004, + "step": 36040 + }, + { + "epoch": 2.94, + "learning_rate": 4.210126032159931e-07, + "loss": 0.2827, + "step": 36041 + }, + { + "epoch": 2.94, + "learning_rate": 4.2046936114732726e-07, + "loss": 0.3453, + "step": 36042 + }, + { + "epoch": 2.94, + "learning_rate": 4.1992611907866144e-07, + "loss": 0.0543, + "step": 36043 + }, + { + "epoch": 2.94, + "learning_rate": 4.193828770099957e-07, + "loss": 0.4067, + "step": 36044 + }, + { + "epoch": 2.94, + "learning_rate": 4.188396349413299e-07, + "loss": 0.1494, + "step": 36045 + }, + { + "epoch": 2.94, + "learning_rate": 4.182963928726641e-07, + "loss": 0.0675, + "step": 36046 + }, + { + "epoch": 2.94, + "learning_rate": 4.177531508039983e-07, + "loss": 0.1827, + "step": 36047 + }, + { + "epoch": 2.94, + "learning_rate": 4.172099087353325e-07, + "loss": 0.2987, + "step": 36048 + }, + { + "epoch": 2.94, + "learning_rate": 4.1666666666666667e-07, + "loss": 0.2071, + "step": 36049 + }, + { + "epoch": 2.94, + "learning_rate": 4.1612342459800084e-07, + "loss": 0.0746, + "step": 36050 + }, + { + "epoch": 2.94, + "learning_rate": 4.1558018252933513e-07, + "loss": 0.1978, + "step": 36051 + }, + { + "epoch": 2.94, + "learning_rate": 4.150369404606693e-07, + "loss": 0.1053, + "step": 36052 + }, + { + "epoch": 2.94, + "learning_rate": 4.1449369839200353e-07, + "loss": 0.5725, + "step": 36053 + }, + { + "epoch": 2.94, + "learning_rate": 4.139504563233377e-07, + "loss": 0.5151, + "step": 36054 + }, + { + "epoch": 2.94, + "learning_rate": 4.134072142546719e-07, + "loss": 0.4054, + "step": 36055 + }, + { + "epoch": 2.94, + "learning_rate": 4.1286397218600607e-07, + "loss": 0.1548, + "step": 36056 + }, + { + "epoch": 2.94, + "learning_rate": 4.1232073011734035e-07, + "loss": 0.4175, + "step": 36057 + }, + { + "epoch": 2.94, + "learning_rate": 4.1177748804867453e-07, + "loss": 0.189, + "step": 36058 + }, + { + "epoch": 2.94, + "learning_rate": 4.112342459800087e-07, + "loss": 0.1805, + "step": 36059 + }, + { + "epoch": 2.94, + "learning_rate": 4.1069100391134294e-07, + "loss": 0.1209, + "step": 36060 + }, + { + "epoch": 2.94, + "learning_rate": 4.101477618426771e-07, + "loss": 0.1244, + "step": 36061 + }, + { + "epoch": 2.94, + "learning_rate": 4.096045197740113e-07, + "loss": 0.4747, + "step": 36062 + }, + { + "epoch": 2.94, + "learning_rate": 4.090612777053456e-07, + "loss": 0.1568, + "step": 36063 + }, + { + "epoch": 2.94, + "learning_rate": 4.0851803563667975e-07, + "loss": 0.0923, + "step": 36064 + }, + { + "epoch": 2.94, + "learning_rate": 4.0797479356801393e-07, + "loss": 0.1679, + "step": 36065 + }, + { + "epoch": 2.94, + "learning_rate": 4.0743155149934816e-07, + "loss": 0.1635, + "step": 36066 + }, + { + "epoch": 2.94, + "learning_rate": 4.0688830943068234e-07, + "loss": 0.0708, + "step": 36067 + }, + { + "epoch": 2.94, + "learning_rate": 4.063450673620165e-07, + "loss": 0.0778, + "step": 36068 + }, + { + "epoch": 2.94, + "learning_rate": 4.058018252933508e-07, + "loss": 0.1904, + "step": 36069 + }, + { + "epoch": 2.94, + "learning_rate": 4.05258583224685e-07, + "loss": 0.3069, + "step": 36070 + }, + { + "epoch": 2.94, + "learning_rate": 4.0471534115601916e-07, + "loss": 0.2315, + "step": 36071 + }, + { + "epoch": 2.94, + "learning_rate": 4.0417209908735333e-07, + "loss": 0.3644, + "step": 36072 + }, + { + "epoch": 2.94, + "learning_rate": 4.0362885701868756e-07, + "loss": 0.278, + "step": 36073 + }, + { + "epoch": 2.94, + "learning_rate": 4.0308561495002174e-07, + "loss": 0.1725, + "step": 36074 + }, + { + "epoch": 2.94, + "learning_rate": 4.025423728813559e-07, + "loss": 0.1842, + "step": 36075 + }, + { + "epoch": 2.94, + "learning_rate": 4.019991308126902e-07, + "loss": 0.4249, + "step": 36076 + }, + { + "epoch": 2.94, + "learning_rate": 4.014558887440244e-07, + "loss": 0.5184, + "step": 36077 + }, + { + "epoch": 2.94, + "learning_rate": 4.0091264667535856e-07, + "loss": 0.2093, + "step": 36078 + }, + { + "epoch": 2.94, + "learning_rate": 4.003694046066928e-07, + "loss": 0.2725, + "step": 36079 + }, + { + "epoch": 2.94, + "learning_rate": 3.9982616253802697e-07, + "loss": 0.3893, + "step": 36080 + }, + { + "epoch": 2.94, + "learning_rate": 3.9928292046936114e-07, + "loss": 0.2378, + "step": 36081 + }, + { + "epoch": 2.94, + "learning_rate": 3.987396784006954e-07, + "loss": 0.2697, + "step": 36082 + }, + { + "epoch": 2.94, + "learning_rate": 3.981964363320296e-07, + "loss": 0.276, + "step": 36083 + }, + { + "epoch": 2.94, + "learning_rate": 3.976531942633638e-07, + "loss": 0.1643, + "step": 36084 + }, + { + "epoch": 2.94, + "learning_rate": 3.97109952194698e-07, + "loss": 0.0839, + "step": 36085 + }, + { + "epoch": 2.94, + "learning_rate": 3.965667101260322e-07, + "loss": 0.3077, + "step": 36086 + }, + { + "epoch": 2.94, + "learning_rate": 3.9602346805736637e-07, + "loss": 0.0938, + "step": 36087 + }, + { + "epoch": 2.94, + "learning_rate": 3.9548022598870065e-07, + "loss": 0.3762, + "step": 36088 + }, + { + "epoch": 2.94, + "learning_rate": 3.9493698392003483e-07, + "loss": 0.2593, + "step": 36089 + }, + { + "epoch": 2.94, + "learning_rate": 3.94393741851369e-07, + "loss": 0.4023, + "step": 36090 + }, + { + "epoch": 2.94, + "learning_rate": 3.938504997827032e-07, + "loss": 0.2175, + "step": 36091 + }, + { + "epoch": 2.94, + "learning_rate": 3.933072577140374e-07, + "loss": 0.1593, + "step": 36092 + }, + { + "epoch": 2.94, + "learning_rate": 3.927640156453716e-07, + "loss": 0.3976, + "step": 36093 + }, + { + "epoch": 2.94, + "learning_rate": 3.9222077357670577e-07, + "loss": 0.2137, + "step": 36094 + }, + { + "epoch": 2.94, + "learning_rate": 3.9167753150804005e-07, + "loss": 0.2094, + "step": 36095 + }, + { + "epoch": 2.94, + "learning_rate": 3.9113428943937423e-07, + "loss": 0.2722, + "step": 36096 + }, + { + "epoch": 2.94, + "learning_rate": 3.905910473707084e-07, + "loss": 0.0613, + "step": 36097 + }, + { + "epoch": 2.94, + "learning_rate": 3.9004780530204264e-07, + "loss": 0.6332, + "step": 36098 + }, + { + "epoch": 2.94, + "learning_rate": 3.895045632333768e-07, + "loss": 0.1433, + "step": 36099 + }, + { + "epoch": 2.94, + "learning_rate": 3.88961321164711e-07, + "loss": 0.0735, + "step": 36100 + }, + { + "epoch": 2.94, + "learning_rate": 3.884180790960453e-07, + "loss": 0.2687, + "step": 36101 + }, + { + "epoch": 2.94, + "learning_rate": 3.8787483702737945e-07, + "loss": 0.4002, + "step": 36102 + }, + { + "epoch": 2.94, + "learning_rate": 3.8733159495871363e-07, + "loss": 0.3993, + "step": 36103 + }, + { + "epoch": 2.94, + "learning_rate": 3.867883528900478e-07, + "loss": 0.3998, + "step": 36104 + }, + { + "epoch": 2.94, + "learning_rate": 3.8624511082138204e-07, + "loss": 0.1668, + "step": 36105 + }, + { + "epoch": 2.94, + "learning_rate": 3.857018687527162e-07, + "loss": 0.1745, + "step": 36106 + }, + { + "epoch": 2.94, + "learning_rate": 3.851586266840505e-07, + "loss": 0.1963, + "step": 36107 + }, + { + "epoch": 2.94, + "learning_rate": 3.846153846153847e-07, + "loss": 0.4122, + "step": 36108 + }, + { + "epoch": 2.94, + "learning_rate": 3.8407214254671886e-07, + "loss": 0.2051, + "step": 36109 + }, + { + "epoch": 2.94, + "learning_rate": 3.8352890047805303e-07, + "loss": 0.2011, + "step": 36110 + }, + { + "epoch": 2.94, + "learning_rate": 3.8298565840938727e-07, + "loss": 0.2834, + "step": 36111 + }, + { + "epoch": 2.94, + "learning_rate": 3.8244241634072144e-07, + "loss": 0.2638, + "step": 36112 + }, + { + "epoch": 2.94, + "learning_rate": 3.818991742720556e-07, + "loss": 0.0789, + "step": 36113 + }, + { + "epoch": 2.94, + "learning_rate": 3.813559322033899e-07, + "loss": 0.1843, + "step": 36114 + }, + { + "epoch": 2.94, + "learning_rate": 3.808126901347241e-07, + "loss": 0.1604, + "step": 36115 + }, + { + "epoch": 2.94, + "learning_rate": 3.8026944806605826e-07, + "loss": 0.2733, + "step": 36116 + }, + { + "epoch": 2.94, + "learning_rate": 3.7972620599739244e-07, + "loss": 0.1753, + "step": 36117 + }, + { + "epoch": 2.94, + "learning_rate": 3.7918296392872667e-07, + "loss": 0.2362, + "step": 36118 + }, + { + "epoch": 2.94, + "learning_rate": 3.7863972186006084e-07, + "loss": 0.3093, + "step": 36119 + }, + { + "epoch": 2.94, + "learning_rate": 3.7809647979139513e-07, + "loss": 0.2241, + "step": 36120 + }, + { + "epoch": 2.94, + "learning_rate": 3.775532377227293e-07, + "loss": 0.1548, + "step": 36121 + }, + { + "epoch": 2.94, + "learning_rate": 3.770099956540635e-07, + "loss": 0.1395, + "step": 36122 + }, + { + "epoch": 2.94, + "learning_rate": 3.7646675358539766e-07, + "loss": 0.3677, + "step": 36123 + }, + { + "epoch": 2.94, + "learning_rate": 3.759235115167319e-07, + "loss": 0.2046, + "step": 36124 + }, + { + "epoch": 2.94, + "learning_rate": 3.7538026944806607e-07, + "loss": 0.0855, + "step": 36125 + }, + { + "epoch": 2.94, + "learning_rate": 3.748370273794003e-07, + "loss": 0.1585, + "step": 36126 + }, + { + "epoch": 2.94, + "learning_rate": 3.7429378531073453e-07, + "loss": 0.1702, + "step": 36127 + }, + { + "epoch": 2.94, + "learning_rate": 3.737505432420687e-07, + "loss": 0.124, + "step": 36128 + }, + { + "epoch": 2.94, + "learning_rate": 3.732073011734029e-07, + "loss": 0.2244, + "step": 36129 + }, + { + "epoch": 2.94, + "learning_rate": 3.7266405910473706e-07, + "loss": 0.1751, + "step": 36130 + }, + { + "epoch": 2.94, + "learning_rate": 3.721208170360713e-07, + "loss": 0.0993, + "step": 36131 + }, + { + "epoch": 2.94, + "learning_rate": 3.7157757496740547e-07, + "loss": 0.1929, + "step": 36132 + }, + { + "epoch": 2.94, + "learning_rate": 3.7103433289873975e-07, + "loss": 0.3122, + "step": 36133 + }, + { + "epoch": 2.94, + "learning_rate": 3.7049109083007393e-07, + "loss": 0.5431, + "step": 36134 + }, + { + "epoch": 2.94, + "learning_rate": 3.699478487614081e-07, + "loss": 0.2479, + "step": 36135 + }, + { + "epoch": 2.94, + "learning_rate": 3.694046066927423e-07, + "loss": 0.2258, + "step": 36136 + }, + { + "epoch": 2.94, + "learning_rate": 3.688613646240765e-07, + "loss": 0.1028, + "step": 36137 + }, + { + "epoch": 2.94, + "learning_rate": 3.683181225554107e-07, + "loss": 0.1472, + "step": 36138 + }, + { + "epoch": 2.94, + "learning_rate": 3.677748804867449e-07, + "loss": 0.2153, + "step": 36139 + }, + { + "epoch": 2.94, + "learning_rate": 3.6723163841807916e-07, + "loss": 0.1088, + "step": 36140 + }, + { + "epoch": 2.94, + "learning_rate": 3.6668839634941333e-07, + "loss": 0.1464, + "step": 36141 + }, + { + "epoch": 2.95, + "learning_rate": 3.661451542807475e-07, + "loss": 0.2224, + "step": 36142 + }, + { + "epoch": 2.95, + "learning_rate": 3.6560191221208174e-07, + "loss": 0.1891, + "step": 36143 + }, + { + "epoch": 2.95, + "learning_rate": 3.650586701434159e-07, + "loss": 0.2662, + "step": 36144 + }, + { + "epoch": 2.95, + "learning_rate": 3.6451542807475015e-07, + "loss": 0.2215, + "step": 36145 + }, + { + "epoch": 2.95, + "learning_rate": 3.639721860060844e-07, + "loss": 0.3867, + "step": 36146 + }, + { + "epoch": 2.95, + "learning_rate": 3.6342894393741856e-07, + "loss": 0.2011, + "step": 36147 + }, + { + "epoch": 2.95, + "learning_rate": 3.6288570186875274e-07, + "loss": 0.1534, + "step": 36148 + }, + { + "epoch": 2.95, + "learning_rate": 3.623424598000869e-07, + "loss": 0.3138, + "step": 36149 + }, + { + "epoch": 2.95, + "learning_rate": 3.6179921773142114e-07, + "loss": 0.3056, + "step": 36150 + }, + { + "epoch": 2.95, + "learning_rate": 3.612559756627554e-07, + "loss": 0.1143, + "step": 36151 + }, + { + "epoch": 2.95, + "learning_rate": 3.6071273359408955e-07, + "loss": 0.3234, + "step": 36152 + }, + { + "epoch": 2.95, + "learning_rate": 3.601694915254238e-07, + "loss": 0.2939, + "step": 36153 + }, + { + "epoch": 2.95, + "learning_rate": 3.5962624945675796e-07, + "loss": 0.1523, + "step": 36154 + }, + { + "epoch": 2.95, + "learning_rate": 3.5908300738809214e-07, + "loss": 0.1457, + "step": 36155 + }, + { + "epoch": 2.95, + "learning_rate": 3.5853976531942637e-07, + "loss": 0.1184, + "step": 36156 + }, + { + "epoch": 2.95, + "learning_rate": 3.5799652325076055e-07, + "loss": 0.2534, + "step": 36157 + }, + { + "epoch": 2.95, + "learning_rate": 3.574532811820948e-07, + "loss": 0.1158, + "step": 36158 + }, + { + "epoch": 2.95, + "learning_rate": 3.56910039113429e-07, + "loss": 0.1631, + "step": 36159 + }, + { + "epoch": 2.95, + "learning_rate": 3.563667970447632e-07, + "loss": 0.0762, + "step": 36160 + }, + { + "epoch": 2.95, + "learning_rate": 3.5582355497609736e-07, + "loss": 0.1137, + "step": 36161 + }, + { + "epoch": 2.95, + "learning_rate": 3.5528031290743154e-07, + "loss": 0.3662, + "step": 36162 + }, + { + "epoch": 2.95, + "learning_rate": 3.5473707083876577e-07, + "loss": 0.2319, + "step": 36163 + }, + { + "epoch": 2.95, + "learning_rate": 3.541938287701e-07, + "loss": 0.2183, + "step": 36164 + }, + { + "epoch": 2.95, + "learning_rate": 3.5365058670143423e-07, + "loss": 0.2229, + "step": 36165 + }, + { + "epoch": 2.95, + "learning_rate": 3.531073446327684e-07, + "loss": 0.2853, + "step": 36166 + }, + { + "epoch": 2.95, + "learning_rate": 3.525641025641026e-07, + "loss": 0.2156, + "step": 36167 + }, + { + "epoch": 2.95, + "learning_rate": 3.5202086049543677e-07, + "loss": 0.1812, + "step": 36168 + }, + { + "epoch": 2.95, + "learning_rate": 3.51477618426771e-07, + "loss": 0.0863, + "step": 36169 + }, + { + "epoch": 2.95, + "learning_rate": 3.509343763581052e-07, + "loss": 0.1557, + "step": 36170 + }, + { + "epoch": 2.95, + "learning_rate": 3.503911342894394e-07, + "loss": 0.1449, + "step": 36171 + }, + { + "epoch": 2.95, + "learning_rate": 3.4984789222077363e-07, + "loss": 0.1025, + "step": 36172 + }, + { + "epoch": 2.95, + "learning_rate": 3.493046501521078e-07, + "loss": 0.239, + "step": 36173 + }, + { + "epoch": 2.95, + "learning_rate": 3.48761408083442e-07, + "loss": 0.2577, + "step": 36174 + }, + { + "epoch": 2.95, + "learning_rate": 3.4821816601477617e-07, + "loss": 0.0758, + "step": 36175 + }, + { + "epoch": 2.95, + "learning_rate": 3.476749239461104e-07, + "loss": 0.165, + "step": 36176 + }, + { + "epoch": 2.95, + "learning_rate": 3.4713168187744463e-07, + "loss": 0.2762, + "step": 36177 + }, + { + "epoch": 2.95, + "learning_rate": 3.4658843980877886e-07, + "loss": 0.3009, + "step": 36178 + }, + { + "epoch": 2.95, + "learning_rate": 3.4604519774011304e-07, + "loss": 0.6723, + "step": 36179 + }, + { + "epoch": 2.95, + "learning_rate": 3.455019556714472e-07, + "loss": 0.2144, + "step": 36180 + }, + { + "epoch": 2.95, + "learning_rate": 3.449587136027814e-07, + "loss": 0.3074, + "step": 36181 + }, + { + "epoch": 2.95, + "learning_rate": 3.444154715341156e-07, + "loss": 0.3965, + "step": 36182 + }, + { + "epoch": 2.95, + "learning_rate": 3.4387222946544985e-07, + "loss": 0.3273, + "step": 36183 + }, + { + "epoch": 2.95, + "learning_rate": 3.4332898739678403e-07, + "loss": 0.3825, + "step": 36184 + }, + { + "epoch": 2.95, + "learning_rate": 3.4278574532811826e-07, + "loss": 0.3225, + "step": 36185 + }, + { + "epoch": 2.95, + "learning_rate": 3.4224250325945244e-07, + "loss": 0.1943, + "step": 36186 + }, + { + "epoch": 2.95, + "learning_rate": 3.416992611907866e-07, + "loss": 0.1551, + "step": 36187 + }, + { + "epoch": 2.95, + "learning_rate": 3.411560191221208e-07, + "loss": 0.4863, + "step": 36188 + }, + { + "epoch": 2.95, + "learning_rate": 3.406127770534551e-07, + "loss": 0.0999, + "step": 36189 + }, + { + "epoch": 2.95, + "learning_rate": 3.4006953498478925e-07, + "loss": 0.1246, + "step": 36190 + }, + { + "epoch": 2.95, + "learning_rate": 3.395262929161235e-07, + "loss": 0.5465, + "step": 36191 + }, + { + "epoch": 2.95, + "learning_rate": 3.3898305084745766e-07, + "loss": 0.2011, + "step": 36192 + }, + { + "epoch": 2.95, + "learning_rate": 3.3843980877879184e-07, + "loss": 0.3016, + "step": 36193 + }, + { + "epoch": 2.95, + "learning_rate": 3.37896566710126e-07, + "loss": 0.1105, + "step": 36194 + }, + { + "epoch": 2.95, + "learning_rate": 3.3735332464146025e-07, + "loss": 0.2212, + "step": 36195 + }, + { + "epoch": 2.95, + "learning_rate": 3.368100825727945e-07, + "loss": 0.0877, + "step": 36196 + }, + { + "epoch": 2.95, + "learning_rate": 3.3626684050412866e-07, + "loss": 0.0403, + "step": 36197 + }, + { + "epoch": 2.95, + "learning_rate": 3.357235984354629e-07, + "loss": 0.4141, + "step": 36198 + }, + { + "epoch": 2.95, + "learning_rate": 3.3518035636679706e-07, + "loss": 0.1435, + "step": 36199 + }, + { + "epoch": 2.95, + "learning_rate": 3.3463711429813124e-07, + "loss": 0.1102, + "step": 36200 + }, + { + "epoch": 2.95, + "learning_rate": 3.340938722294654e-07, + "loss": 0.2504, + "step": 36201 + }, + { + "epoch": 2.95, + "learning_rate": 3.335506301607997e-07, + "loss": 0.0534, + "step": 36202 + }, + { + "epoch": 2.95, + "learning_rate": 3.330073880921339e-07, + "loss": 0.1706, + "step": 36203 + }, + { + "epoch": 2.95, + "learning_rate": 3.324641460234681e-07, + "loss": 0.1028, + "step": 36204 + }, + { + "epoch": 2.95, + "learning_rate": 3.319209039548023e-07, + "loss": 0.521, + "step": 36205 + }, + { + "epoch": 2.95, + "learning_rate": 3.3137766188613647e-07, + "loss": 0.1988, + "step": 36206 + }, + { + "epoch": 2.95, + "learning_rate": 3.3083441981747064e-07, + "loss": 0.1865, + "step": 36207 + }, + { + "epoch": 2.95, + "learning_rate": 3.3029117774880493e-07, + "loss": 0.3872, + "step": 36208 + }, + { + "epoch": 2.95, + "learning_rate": 3.297479356801391e-07, + "loss": 0.3744, + "step": 36209 + }, + { + "epoch": 2.95, + "learning_rate": 3.292046936114733e-07, + "loss": 0.1332, + "step": 36210 + }, + { + "epoch": 2.95, + "learning_rate": 3.286614515428075e-07, + "loss": 0.037, + "step": 36211 + }, + { + "epoch": 2.95, + "learning_rate": 3.281182094741417e-07, + "loss": 0.3439, + "step": 36212 + }, + { + "epoch": 2.95, + "learning_rate": 3.2757496740547587e-07, + "loss": 0.0648, + "step": 36213 + }, + { + "epoch": 2.95, + "learning_rate": 3.2703172533681015e-07, + "loss": 0.231, + "step": 36214 + }, + { + "epoch": 2.95, + "learning_rate": 3.2648848326814433e-07, + "loss": 0.1164, + "step": 36215 + }, + { + "epoch": 2.95, + "learning_rate": 3.259452411994785e-07, + "loss": 0.3646, + "step": 36216 + }, + { + "epoch": 2.95, + "learning_rate": 3.2540199913081274e-07, + "loss": 0.3257, + "step": 36217 + }, + { + "epoch": 2.95, + "learning_rate": 3.248587570621469e-07, + "loss": 0.2466, + "step": 36218 + }, + { + "epoch": 2.95, + "learning_rate": 3.243155149934811e-07, + "loss": 0.12, + "step": 36219 + }, + { + "epoch": 2.95, + "learning_rate": 3.2377227292481527e-07, + "loss": 0.0463, + "step": 36220 + }, + { + "epoch": 2.95, + "learning_rate": 3.2322903085614955e-07, + "loss": 0.0838, + "step": 36221 + }, + { + "epoch": 2.95, + "learning_rate": 3.2268578878748373e-07, + "loss": 0.2499, + "step": 36222 + }, + { + "epoch": 2.95, + "learning_rate": 3.221425467188179e-07, + "loss": 0.1642, + "step": 36223 + }, + { + "epoch": 2.95, + "learning_rate": 3.2159930465015214e-07, + "loss": 0.1426, + "step": 36224 + }, + { + "epoch": 2.95, + "learning_rate": 3.210560625814863e-07, + "loss": 0.2898, + "step": 36225 + }, + { + "epoch": 2.95, + "learning_rate": 3.205128205128205e-07, + "loss": 0.1784, + "step": 36226 + }, + { + "epoch": 2.95, + "learning_rate": 3.199695784441548e-07, + "loss": 0.1831, + "step": 36227 + }, + { + "epoch": 2.95, + "learning_rate": 3.1942633637548896e-07, + "loss": 0.5169, + "step": 36228 + }, + { + "epoch": 2.95, + "learning_rate": 3.1888309430682313e-07, + "loss": 0.3122, + "step": 36229 + }, + { + "epoch": 2.95, + "learning_rate": 3.1833985223815736e-07, + "loss": 0.2454, + "step": 36230 + }, + { + "epoch": 2.95, + "learning_rate": 3.1779661016949154e-07, + "loss": 0.1749, + "step": 36231 + }, + { + "epoch": 2.95, + "learning_rate": 3.172533681008257e-07, + "loss": 0.1501, + "step": 36232 + }, + { + "epoch": 2.95, + "learning_rate": 3.1671012603216e-07, + "loss": 0.505, + "step": 36233 + }, + { + "epoch": 2.95, + "learning_rate": 3.161668839634942e-07, + "loss": 0.0683, + "step": 36234 + }, + { + "epoch": 2.95, + "learning_rate": 3.1562364189482836e-07, + "loss": 0.1496, + "step": 36235 + }, + { + "epoch": 2.95, + "learning_rate": 3.150803998261626e-07, + "loss": 0.2023, + "step": 36236 + }, + { + "epoch": 2.95, + "learning_rate": 3.1453715775749677e-07, + "loss": 0.4717, + "step": 36237 + }, + { + "epoch": 2.95, + "learning_rate": 3.1399391568883094e-07, + "loss": 0.0867, + "step": 36238 + }, + { + "epoch": 2.95, + "learning_rate": 3.134506736201651e-07, + "loss": 0.1481, + "step": 36239 + }, + { + "epoch": 2.95, + "learning_rate": 3.129074315514994e-07, + "loss": 0.1256, + "step": 36240 + }, + { + "epoch": 2.95, + "learning_rate": 3.123641894828336e-07, + "loss": 0.3889, + "step": 36241 + }, + { + "epoch": 2.95, + "learning_rate": 3.1182094741416776e-07, + "loss": 0.1475, + "step": 36242 + }, + { + "epoch": 2.95, + "learning_rate": 3.11277705345502e-07, + "loss": 0.3796, + "step": 36243 + }, + { + "epoch": 2.95, + "learning_rate": 3.107344632768362e-07, + "loss": 0.1138, + "step": 36244 + }, + { + "epoch": 2.95, + "learning_rate": 3.101912212081704e-07, + "loss": 0.4007, + "step": 36245 + }, + { + "epoch": 2.95, + "learning_rate": 3.096479791395046e-07, + "loss": 0.1636, + "step": 36246 + }, + { + "epoch": 2.95, + "learning_rate": 3.0910473707083875e-07, + "loss": 0.211, + "step": 36247 + }, + { + "epoch": 2.95, + "learning_rate": 3.08561495002173e-07, + "loss": 0.4898, + "step": 36248 + }, + { + "epoch": 2.95, + "learning_rate": 3.080182529335072e-07, + "loss": 0.1086, + "step": 36249 + }, + { + "epoch": 2.95, + "learning_rate": 3.074750108648414e-07, + "loss": 0.2004, + "step": 36250 + }, + { + "epoch": 2.95, + "eval_accuracy": 0.8451349974528782, + "eval_loss": 0.4924587905406952, + "eval_runtime": 22.3, + "eval_samples_per_second": 440.135, + "eval_steps_per_second": 3.453, + "step": 36250 + }, + { + "epoch": 2.95, + "learning_rate": 3.069317687961756e-07, + "loss": 0.2569, + "step": 36251 + }, + { + "epoch": 2.95, + "learning_rate": 3.063885267275098e-07, + "loss": 0.1846, + "step": 36252 + }, + { + "epoch": 2.95, + "learning_rate": 3.05845284658844e-07, + "loss": 0.3681, + "step": 36253 + }, + { + "epoch": 2.95, + "learning_rate": 3.053020425901782e-07, + "loss": 0.1382, + "step": 36254 + }, + { + "epoch": 2.95, + "learning_rate": 3.047588005215124e-07, + "loss": 0.3527, + "step": 36255 + }, + { + "epoch": 2.95, + "learning_rate": 3.042155584528466e-07, + "loss": 0.3685, + "step": 36256 + }, + { + "epoch": 2.95, + "learning_rate": 3.0367231638418085e-07, + "loss": 0.1556, + "step": 36257 + }, + { + "epoch": 2.95, + "learning_rate": 3.03129074315515e-07, + "loss": 0.1613, + "step": 36258 + }, + { + "epoch": 2.95, + "learning_rate": 3.025858322468492e-07, + "loss": 0.2205, + "step": 36259 + }, + { + "epoch": 2.95, + "learning_rate": 3.0204259017818343e-07, + "loss": 0.2092, + "step": 36260 + }, + { + "epoch": 2.95, + "learning_rate": 3.014993481095176e-07, + "loss": 0.2534, + "step": 36261 + }, + { + "epoch": 2.95, + "learning_rate": 3.0095610604085184e-07, + "loss": 0.1391, + "step": 36262 + }, + { + "epoch": 2.95, + "learning_rate": 3.00412863972186e-07, + "loss": 0.1421, + "step": 36263 + }, + { + "epoch": 2.96, + "learning_rate": 2.9986962190352025e-07, + "loss": 0.3105, + "step": 36264 + }, + { + "epoch": 2.96, + "learning_rate": 2.9932637983485443e-07, + "loss": 0.1947, + "step": 36265 + }, + { + "epoch": 2.96, + "learning_rate": 2.9878313776618866e-07, + "loss": 0.1987, + "step": 36266 + }, + { + "epoch": 2.96, + "learning_rate": 2.9823989569752284e-07, + "loss": 0.3139, + "step": 36267 + }, + { + "epoch": 2.96, + "learning_rate": 2.97696653628857e-07, + "loss": 0.175, + "step": 36268 + }, + { + "epoch": 2.96, + "learning_rate": 2.9715341156019124e-07, + "loss": 0.2271, + "step": 36269 + }, + { + "epoch": 2.96, + "learning_rate": 2.966101694915255e-07, + "loss": 0.1362, + "step": 36270 + }, + { + "epoch": 2.96, + "learning_rate": 2.9606692742285965e-07, + "loss": 0.2146, + "step": 36271 + }, + { + "epoch": 2.96, + "learning_rate": 2.9552368535419383e-07, + "loss": 0.1818, + "step": 36272 + }, + { + "epoch": 2.96, + "learning_rate": 2.9498044328552806e-07, + "loss": 0.1752, + "step": 36273 + }, + { + "epoch": 2.96, + "learning_rate": 2.9443720121686224e-07, + "loss": 0.1517, + "step": 36274 + }, + { + "epoch": 2.96, + "learning_rate": 2.9389395914819647e-07, + "loss": 0.2007, + "step": 36275 + }, + { + "epoch": 2.96, + "learning_rate": 2.933507170795307e-07, + "loss": 0.345, + "step": 36276 + }, + { + "epoch": 2.96, + "learning_rate": 2.928074750108649e-07, + "loss": 0.5311, + "step": 36277 + }, + { + "epoch": 2.96, + "learning_rate": 2.9226423294219905e-07, + "loss": 0.316, + "step": 36278 + }, + { + "epoch": 2.96, + "learning_rate": 2.917209908735333e-07, + "loss": 0.0449, + "step": 36279 + }, + { + "epoch": 2.96, + "learning_rate": 2.9117774880486746e-07, + "loss": 0.1492, + "step": 36280 + }, + { + "epoch": 2.96, + "learning_rate": 2.9063450673620164e-07, + "loss": 0.4362, + "step": 36281 + }, + { + "epoch": 2.96, + "learning_rate": 2.9009126466753587e-07, + "loss": 0.1902, + "step": 36282 + }, + { + "epoch": 2.96, + "learning_rate": 2.895480225988701e-07, + "loss": 0.0553, + "step": 36283 + }, + { + "epoch": 2.96, + "learning_rate": 2.890047805302043e-07, + "loss": 0.3102, + "step": 36284 + }, + { + "epoch": 2.96, + "learning_rate": 2.884615384615385e-07, + "loss": 0.4649, + "step": 36285 + }, + { + "epoch": 2.96, + "learning_rate": 2.879182963928727e-07, + "loss": 0.2788, + "step": 36286 + }, + { + "epoch": 2.96, + "learning_rate": 2.8737505432420686e-07, + "loss": 0.1822, + "step": 36287 + }, + { + "epoch": 2.96, + "learning_rate": 2.868318122555411e-07, + "loss": 0.2633, + "step": 36288 + }, + { + "epoch": 2.96, + "learning_rate": 2.862885701868753e-07, + "loss": 0.0831, + "step": 36289 + }, + { + "epoch": 2.96, + "learning_rate": 2.857453281182095e-07, + "loss": 0.2148, + "step": 36290 + }, + { + "epoch": 2.96, + "learning_rate": 2.852020860495437e-07, + "loss": 0.1266, + "step": 36291 + }, + { + "epoch": 2.96, + "learning_rate": 2.846588439808779e-07, + "loss": 0.1276, + "step": 36292 + }, + { + "epoch": 2.96, + "learning_rate": 2.841156019122121e-07, + "loss": 0.1518, + "step": 36293 + }, + { + "epoch": 2.96, + "learning_rate": 2.835723598435463e-07, + "loss": 0.1434, + "step": 36294 + }, + { + "epoch": 2.96, + "learning_rate": 2.830291177748805e-07, + "loss": 0.2773, + "step": 36295 + }, + { + "epoch": 2.96, + "learning_rate": 2.8248587570621473e-07, + "loss": 0.1, + "step": 36296 + }, + { + "epoch": 2.96, + "learning_rate": 2.819426336375489e-07, + "loss": 0.1595, + "step": 36297 + }, + { + "epoch": 2.96, + "learning_rate": 2.8139939156888314e-07, + "loss": 0.31, + "step": 36298 + }, + { + "epoch": 2.96, + "learning_rate": 2.808561495002173e-07, + "loss": 0.2369, + "step": 36299 + }, + { + "epoch": 2.96, + "learning_rate": 2.803129074315515e-07, + "loss": 0.2137, + "step": 36300 + }, + { + "epoch": 2.96, + "learning_rate": 2.797696653628857e-07, + "loss": 0.0421, + "step": 36301 + }, + { + "epoch": 2.96, + "learning_rate": 2.7922642329421995e-07, + "loss": 0.1878, + "step": 36302 + }, + { + "epoch": 2.96, + "learning_rate": 2.7868318122555413e-07, + "loss": 0.0733, + "step": 36303 + }, + { + "epoch": 2.96, + "learning_rate": 2.7813993915688836e-07, + "loss": 0.0235, + "step": 36304 + }, + { + "epoch": 2.96, + "learning_rate": 2.7759669708822254e-07, + "loss": 0.2434, + "step": 36305 + }, + { + "epoch": 2.96, + "learning_rate": 2.770534550195567e-07, + "loss": 0.1995, + "step": 36306 + }, + { + "epoch": 2.96, + "learning_rate": 2.7651021295089095e-07, + "loss": 0.4052, + "step": 36307 + }, + { + "epoch": 2.96, + "learning_rate": 2.759669708822251e-07, + "loss": 0.1846, + "step": 36308 + }, + { + "epoch": 2.96, + "learning_rate": 2.7542372881355935e-07, + "loss": 0.0956, + "step": 36309 + }, + { + "epoch": 2.96, + "learning_rate": 2.7488048674489353e-07, + "loss": 0.1619, + "step": 36310 + }, + { + "epoch": 2.96, + "learning_rate": 2.7433724467622776e-07, + "loss": 0.1718, + "step": 36311 + }, + { + "epoch": 2.96, + "learning_rate": 2.7379400260756194e-07, + "loss": 0.093, + "step": 36312 + }, + { + "epoch": 2.96, + "learning_rate": 2.732507605388961e-07, + "loss": 0.1806, + "step": 36313 + }, + { + "epoch": 2.96, + "learning_rate": 2.7270751847023035e-07, + "loss": 0.2077, + "step": 36314 + }, + { + "epoch": 2.96, + "learning_rate": 2.721642764015646e-07, + "loss": 0.5161, + "step": 36315 + }, + { + "epoch": 2.96, + "learning_rate": 2.7162103433289876e-07, + "loss": 0.2662, + "step": 36316 + }, + { + "epoch": 2.96, + "learning_rate": 2.71077792264233e-07, + "loss": 0.1392, + "step": 36317 + }, + { + "epoch": 2.96, + "learning_rate": 2.7053455019556716e-07, + "loss": 0.1176, + "step": 36318 + }, + { + "epoch": 2.96, + "learning_rate": 2.6999130812690134e-07, + "loss": 0.2364, + "step": 36319 + }, + { + "epoch": 2.96, + "learning_rate": 2.6944806605823557e-07, + "loss": 0.4605, + "step": 36320 + }, + { + "epoch": 2.96, + "learning_rate": 2.6890482398956975e-07, + "loss": 0.0728, + "step": 36321 + }, + { + "epoch": 2.96, + "learning_rate": 2.68361581920904e-07, + "loss": 0.0632, + "step": 36322 + }, + { + "epoch": 2.96, + "learning_rate": 2.678183398522382e-07, + "loss": 0.2489, + "step": 36323 + }, + { + "epoch": 2.96, + "learning_rate": 2.672750977835724e-07, + "loss": 0.1532, + "step": 36324 + }, + { + "epoch": 2.96, + "learning_rate": 2.6673185571490657e-07, + "loss": 0.2432, + "step": 36325 + }, + { + "epoch": 2.96, + "learning_rate": 2.661886136462408e-07, + "loss": 0.1191, + "step": 36326 + }, + { + "epoch": 2.96, + "learning_rate": 2.65645371577575e-07, + "loss": 0.1958, + "step": 36327 + }, + { + "epoch": 2.96, + "learning_rate": 2.651021295089092e-07, + "loss": 0.1412, + "step": 36328 + }, + { + "epoch": 2.96, + "learning_rate": 2.645588874402434e-07, + "loss": 0.226, + "step": 36329 + }, + { + "epoch": 2.96, + "learning_rate": 2.640156453715776e-07, + "loss": 0.3228, + "step": 36330 + }, + { + "epoch": 2.96, + "learning_rate": 2.634724033029118e-07, + "loss": 0.2982, + "step": 36331 + }, + { + "epoch": 2.96, + "learning_rate": 2.6292916123424597e-07, + "loss": 0.3679, + "step": 36332 + }, + { + "epoch": 2.96, + "learning_rate": 2.623859191655802e-07, + "loss": 0.2789, + "step": 36333 + }, + { + "epoch": 2.96, + "learning_rate": 2.6184267709691443e-07, + "loss": 0.3452, + "step": 36334 + }, + { + "epoch": 2.96, + "learning_rate": 2.612994350282486e-07, + "loss": 0.1823, + "step": 36335 + }, + { + "epoch": 2.96, + "learning_rate": 2.6075619295958284e-07, + "loss": 0.1996, + "step": 36336 + }, + { + "epoch": 2.96, + "learning_rate": 2.60212950890917e-07, + "loss": 0.1551, + "step": 36337 + }, + { + "epoch": 2.96, + "learning_rate": 2.596697088222512e-07, + "loss": 0.2781, + "step": 36338 + }, + { + "epoch": 2.96, + "learning_rate": 2.591264667535854e-07, + "loss": 0.3326, + "step": 36339 + }, + { + "epoch": 2.96, + "learning_rate": 2.585832246849196e-07, + "loss": 0.0716, + "step": 36340 + }, + { + "epoch": 2.96, + "learning_rate": 2.5803998261625383e-07, + "loss": 0.375, + "step": 36341 + }, + { + "epoch": 2.96, + "learning_rate": 2.5749674054758806e-07, + "loss": 0.1583, + "step": 36342 + }, + { + "epoch": 2.96, + "learning_rate": 2.5695349847892224e-07, + "loss": 0.3533, + "step": 36343 + }, + { + "epoch": 2.96, + "learning_rate": 2.564102564102564e-07, + "loss": 0.4052, + "step": 36344 + }, + { + "epoch": 2.96, + "learning_rate": 2.5586701434159065e-07, + "loss": 0.1478, + "step": 36345 + }, + { + "epoch": 2.96, + "learning_rate": 2.553237722729248e-07, + "loss": 0.0418, + "step": 36346 + }, + { + "epoch": 2.96, + "learning_rate": 2.5478053020425906e-07, + "loss": 0.1066, + "step": 36347 + }, + { + "epoch": 2.96, + "learning_rate": 2.5423728813559323e-07, + "loss": 0.29, + "step": 36348 + }, + { + "epoch": 2.96, + "learning_rate": 2.5369404606692746e-07, + "loss": 0.0984, + "step": 36349 + }, + { + "epoch": 2.96, + "learning_rate": 2.5315080399826164e-07, + "loss": 0.1622, + "step": 36350 + }, + { + "epoch": 2.96, + "learning_rate": 2.526075619295958e-07, + "loss": 0.7767, + "step": 36351 + }, + { + "epoch": 2.96, + "learning_rate": 2.5206431986093005e-07, + "loss": 0.2382, + "step": 36352 + }, + { + "epoch": 2.96, + "learning_rate": 2.5152107779226423e-07, + "loss": 0.187, + "step": 36353 + }, + { + "epoch": 2.96, + "learning_rate": 2.5097783572359846e-07, + "loss": 0.1379, + "step": 36354 + }, + { + "epoch": 2.96, + "learning_rate": 2.504345936549327e-07, + "loss": 0.149, + "step": 36355 + }, + { + "epoch": 2.96, + "learning_rate": 2.4989135158626687e-07, + "loss": 0.2248, + "step": 36356 + }, + { + "epoch": 2.96, + "learning_rate": 2.4934810951760104e-07, + "loss": 0.0542, + "step": 36357 + }, + { + "epoch": 2.96, + "learning_rate": 2.488048674489353e-07, + "loss": 0.2129, + "step": 36358 + }, + { + "epoch": 2.96, + "learning_rate": 2.4826162538026945e-07, + "loss": 0.3166, + "step": 36359 + }, + { + "epoch": 2.96, + "learning_rate": 2.477183833116037e-07, + "loss": 0.483, + "step": 36360 + }, + { + "epoch": 2.96, + "learning_rate": 2.4717514124293786e-07, + "loss": 0.1797, + "step": 36361 + }, + { + "epoch": 2.96, + "learning_rate": 2.466318991742721e-07, + "loss": 0.2774, + "step": 36362 + }, + { + "epoch": 2.96, + "learning_rate": 2.4608865710560627e-07, + "loss": 0.2566, + "step": 36363 + }, + { + "epoch": 2.96, + "learning_rate": 2.455454150369405e-07, + "loss": 0.2242, + "step": 36364 + }, + { + "epoch": 2.96, + "learning_rate": 2.450021729682747e-07, + "loss": 0.3938, + "step": 36365 + }, + { + "epoch": 2.96, + "learning_rate": 2.4445893089960885e-07, + "loss": 0.2797, + "step": 36366 + }, + { + "epoch": 2.96, + "learning_rate": 2.439156888309431e-07, + "loss": 0.151, + "step": 36367 + }, + { + "epoch": 2.96, + "learning_rate": 2.433724467622773e-07, + "loss": 0.2137, + "step": 36368 + }, + { + "epoch": 2.96, + "learning_rate": 2.428292046936115e-07, + "loss": 0.2413, + "step": 36369 + }, + { + "epoch": 2.96, + "learning_rate": 2.422859626249457e-07, + "loss": 0.1766, + "step": 36370 + }, + { + "epoch": 2.96, + "learning_rate": 2.417427205562799e-07, + "loss": 0.0722, + "step": 36371 + }, + { + "epoch": 2.96, + "learning_rate": 2.411994784876141e-07, + "loss": 0.2564, + "step": 36372 + }, + { + "epoch": 2.96, + "learning_rate": 2.406562364189483e-07, + "loss": 0.6447, + "step": 36373 + }, + { + "epoch": 2.96, + "learning_rate": 2.401129943502825e-07, + "loss": 0.2055, + "step": 36374 + }, + { + "epoch": 2.96, + "learning_rate": 2.395697522816167e-07, + "loss": 0.1429, + "step": 36375 + }, + { + "epoch": 2.96, + "learning_rate": 2.390265102129509e-07, + "loss": 0.495, + "step": 36376 + }, + { + "epoch": 2.96, + "learning_rate": 2.384832681442851e-07, + "loss": 0.0875, + "step": 36377 + }, + { + "epoch": 2.96, + "learning_rate": 2.379400260756193e-07, + "loss": 0.0287, + "step": 36378 + }, + { + "epoch": 2.96, + "learning_rate": 2.373967840069535e-07, + "loss": 0.1759, + "step": 36379 + }, + { + "epoch": 2.96, + "learning_rate": 2.3685354193828774e-07, + "loss": 0.3293, + "step": 36380 + }, + { + "epoch": 2.96, + "learning_rate": 2.3631029986962192e-07, + "loss": 0.1558, + "step": 36381 + }, + { + "epoch": 2.96, + "learning_rate": 2.3576705780095612e-07, + "loss": 0.3877, + "step": 36382 + }, + { + "epoch": 2.96, + "learning_rate": 2.3522381573229035e-07, + "loss": 0.4121, + "step": 36383 + }, + { + "epoch": 2.96, + "learning_rate": 2.3468057366362453e-07, + "loss": 0.337, + "step": 36384 + }, + { + "epoch": 2.96, + "learning_rate": 2.3413733159495873e-07, + "loss": 0.462, + "step": 36385 + }, + { + "epoch": 2.96, + "learning_rate": 2.3359408952629296e-07, + "loss": 0.1568, + "step": 36386 + }, + { + "epoch": 2.97, + "learning_rate": 2.3305084745762714e-07, + "loss": 0.3302, + "step": 36387 + }, + { + "epoch": 2.97, + "learning_rate": 2.3250760538896134e-07, + "loss": 0.3386, + "step": 36388 + }, + { + "epoch": 2.97, + "learning_rate": 2.3196436332029555e-07, + "loss": 0.1114, + "step": 36389 + }, + { + "epoch": 2.97, + "learning_rate": 2.3142112125162975e-07, + "loss": 0.4334, + "step": 36390 + }, + { + "epoch": 2.97, + "learning_rate": 2.3087787918296393e-07, + "loss": 0.1843, + "step": 36391 + }, + { + "epoch": 2.97, + "learning_rate": 2.3033463711429813e-07, + "loss": 0.3792, + "step": 36392 + }, + { + "epoch": 2.97, + "learning_rate": 2.2979139504563236e-07, + "loss": 0.0899, + "step": 36393 + }, + { + "epoch": 2.97, + "learning_rate": 2.2924815297696654e-07, + "loss": 0.0733, + "step": 36394 + }, + { + "epoch": 2.97, + "learning_rate": 2.2870491090830075e-07, + "loss": 0.2405, + "step": 36395 + }, + { + "epoch": 2.97, + "learning_rate": 2.2816166883963498e-07, + "loss": 0.1051, + "step": 36396 + }, + { + "epoch": 2.97, + "learning_rate": 2.2761842677096915e-07, + "loss": 0.1973, + "step": 36397 + }, + { + "epoch": 2.97, + "learning_rate": 2.2707518470230336e-07, + "loss": 0.0868, + "step": 36398 + }, + { + "epoch": 2.97, + "learning_rate": 2.265319426336376e-07, + "loss": 0.1189, + "step": 36399 + }, + { + "epoch": 2.97, + "learning_rate": 2.2598870056497177e-07, + "loss": 0.1785, + "step": 36400 + }, + { + "epoch": 2.97, + "learning_rate": 2.2544545849630597e-07, + "loss": 0.1596, + "step": 36401 + }, + { + "epoch": 2.97, + "learning_rate": 2.2490221642764017e-07, + "loss": 0.2209, + "step": 36402 + }, + { + "epoch": 2.97, + "learning_rate": 2.2435897435897438e-07, + "loss": 0.3763, + "step": 36403 + }, + { + "epoch": 2.97, + "learning_rate": 2.2381573229030858e-07, + "loss": 0.1349, + "step": 36404 + }, + { + "epoch": 2.97, + "learning_rate": 2.232724902216428e-07, + "loss": 0.1479, + "step": 36405 + }, + { + "epoch": 2.97, + "learning_rate": 2.22729248152977e-07, + "loss": 0.341, + "step": 36406 + }, + { + "epoch": 2.97, + "learning_rate": 2.2218600608431117e-07, + "loss": 0.5257, + "step": 36407 + }, + { + "epoch": 2.97, + "learning_rate": 2.216427640156454e-07, + "loss": 0.2528, + "step": 36408 + }, + { + "epoch": 2.97, + "learning_rate": 2.210995219469796e-07, + "loss": 0.1356, + "step": 36409 + }, + { + "epoch": 2.97, + "learning_rate": 2.2055627987831378e-07, + "loss": 0.0866, + "step": 36410 + }, + { + "epoch": 2.97, + "learning_rate": 2.20013037809648e-07, + "loss": 0.1392, + "step": 36411 + }, + { + "epoch": 2.97, + "learning_rate": 2.1946979574098222e-07, + "loss": 0.1025, + "step": 36412 + }, + { + "epoch": 2.97, + "learning_rate": 2.189265536723164e-07, + "loss": 0.4031, + "step": 36413 + }, + { + "epoch": 2.97, + "learning_rate": 2.183833116036506e-07, + "loss": 0.2128, + "step": 36414 + }, + { + "epoch": 2.97, + "learning_rate": 2.1784006953498483e-07, + "loss": 0.381, + "step": 36415 + }, + { + "epoch": 2.97, + "learning_rate": 2.17296827466319e-07, + "loss": 0.2145, + "step": 36416 + }, + { + "epoch": 2.97, + "learning_rate": 2.167535853976532e-07, + "loss": 0.0822, + "step": 36417 + }, + { + "epoch": 2.97, + "learning_rate": 2.1621034332898741e-07, + "loss": 0.376, + "step": 36418 + }, + { + "epoch": 2.97, + "learning_rate": 2.1566710126032162e-07, + "loss": 0.4195, + "step": 36419 + }, + { + "epoch": 2.97, + "learning_rate": 2.151238591916558e-07, + "loss": 0.2392, + "step": 36420 + }, + { + "epoch": 2.97, + "learning_rate": 2.1458061712299003e-07, + "loss": 0.2216, + "step": 36421 + }, + { + "epoch": 2.97, + "learning_rate": 2.1403737505432423e-07, + "loss": 0.1448, + "step": 36422 + }, + { + "epoch": 2.97, + "learning_rate": 2.134941329856584e-07, + "loss": 0.2831, + "step": 36423 + }, + { + "epoch": 2.97, + "learning_rate": 2.1295089091699264e-07, + "loss": 0.5303, + "step": 36424 + }, + { + "epoch": 2.97, + "learning_rate": 2.1240764884832684e-07, + "loss": 0.1299, + "step": 36425 + }, + { + "epoch": 2.97, + "learning_rate": 2.1186440677966102e-07, + "loss": 0.2941, + "step": 36426 + }, + { + "epoch": 2.97, + "learning_rate": 2.1132116471099525e-07, + "loss": 0.4155, + "step": 36427 + }, + { + "epoch": 2.97, + "learning_rate": 2.1077792264232945e-07, + "loss": 0.5348, + "step": 36428 + }, + { + "epoch": 2.97, + "learning_rate": 2.1023468057366363e-07, + "loss": 0.3495, + "step": 36429 + }, + { + "epoch": 2.97, + "learning_rate": 2.0969143850499786e-07, + "loss": 0.0815, + "step": 36430 + }, + { + "epoch": 2.97, + "learning_rate": 2.0914819643633204e-07, + "loss": 0.197, + "step": 36431 + }, + { + "epoch": 2.97, + "learning_rate": 2.0860495436766624e-07, + "loss": 0.0793, + "step": 36432 + }, + { + "epoch": 2.97, + "learning_rate": 2.0806171229900042e-07, + "loss": 0.1491, + "step": 36433 + }, + { + "epoch": 2.97, + "learning_rate": 2.0751847023033465e-07, + "loss": 0.1664, + "step": 36434 + }, + { + "epoch": 2.97, + "learning_rate": 2.0697522816166886e-07, + "loss": 0.3917, + "step": 36435 + }, + { + "epoch": 2.97, + "learning_rate": 2.0643198609300303e-07, + "loss": 0.0683, + "step": 36436 + }, + { + "epoch": 2.97, + "learning_rate": 2.0588874402433726e-07, + "loss": 0.2448, + "step": 36437 + }, + { + "epoch": 2.97, + "learning_rate": 2.0534550195567147e-07, + "loss": 0.2521, + "step": 36438 + }, + { + "epoch": 2.97, + "learning_rate": 2.0480225988700565e-07, + "loss": 0.0409, + "step": 36439 + }, + { + "epoch": 2.97, + "learning_rate": 2.0425901781833988e-07, + "loss": 0.279, + "step": 36440 + }, + { + "epoch": 2.97, + "learning_rate": 2.0371577574967408e-07, + "loss": 0.359, + "step": 36441 + }, + { + "epoch": 2.97, + "learning_rate": 2.0317253368100826e-07, + "loss": 0.1279, + "step": 36442 + }, + { + "epoch": 2.97, + "learning_rate": 2.026292916123425e-07, + "loss": 0.5738, + "step": 36443 + }, + { + "epoch": 2.97, + "learning_rate": 2.0208604954367667e-07, + "loss": 0.3213, + "step": 36444 + }, + { + "epoch": 2.97, + "learning_rate": 2.0154280747501087e-07, + "loss": 0.2044, + "step": 36445 + }, + { + "epoch": 2.97, + "learning_rate": 2.009995654063451e-07, + "loss": 0.117, + "step": 36446 + }, + { + "epoch": 2.97, + "learning_rate": 2.0045632333767928e-07, + "loss": 0.0686, + "step": 36447 + }, + { + "epoch": 2.97, + "learning_rate": 1.9991308126901348e-07, + "loss": 0.2674, + "step": 36448 + }, + { + "epoch": 2.97, + "learning_rate": 1.993698392003477e-07, + "loss": 0.2643, + "step": 36449 + }, + { + "epoch": 2.97, + "learning_rate": 1.988265971316819e-07, + "loss": 0.0989, + "step": 36450 + }, + { + "epoch": 2.97, + "learning_rate": 1.982833550630161e-07, + "loss": 0.2135, + "step": 36451 + }, + { + "epoch": 2.97, + "learning_rate": 1.9774011299435033e-07, + "loss": 0.2031, + "step": 36452 + }, + { + "epoch": 2.97, + "learning_rate": 1.971968709256845e-07, + "loss": 0.2021, + "step": 36453 + }, + { + "epoch": 2.97, + "learning_rate": 1.966536288570187e-07, + "loss": 0.3118, + "step": 36454 + }, + { + "epoch": 2.97, + "learning_rate": 1.9611038678835288e-07, + "loss": 0.2072, + "step": 36455 + }, + { + "epoch": 2.97, + "learning_rate": 1.9556714471968712e-07, + "loss": 0.2794, + "step": 36456 + }, + { + "epoch": 2.97, + "learning_rate": 1.9502390265102132e-07, + "loss": 0.2765, + "step": 36457 + }, + { + "epoch": 2.97, + "learning_rate": 1.944806605823555e-07, + "loss": 0.1434, + "step": 36458 + }, + { + "epoch": 2.97, + "learning_rate": 1.9393741851368973e-07, + "loss": 0.3916, + "step": 36459 + }, + { + "epoch": 2.97, + "learning_rate": 1.933941764450239e-07, + "loss": 0.2343, + "step": 36460 + }, + { + "epoch": 2.97, + "learning_rate": 1.928509343763581e-07, + "loss": 0.4827, + "step": 36461 + }, + { + "epoch": 2.97, + "learning_rate": 1.9230769230769234e-07, + "loss": 0.1656, + "step": 36462 + }, + { + "epoch": 2.97, + "learning_rate": 1.9176445023902652e-07, + "loss": 0.3793, + "step": 36463 + }, + { + "epoch": 2.97, + "learning_rate": 1.9122120817036072e-07, + "loss": 0.3072, + "step": 36464 + }, + { + "epoch": 2.97, + "learning_rate": 1.9067796610169495e-07, + "loss": 0.0318, + "step": 36465 + }, + { + "epoch": 2.97, + "learning_rate": 1.9013472403302913e-07, + "loss": 0.1863, + "step": 36466 + }, + { + "epoch": 2.97, + "learning_rate": 1.8959148196436333e-07, + "loss": 0.1432, + "step": 36467 + }, + { + "epoch": 2.97, + "learning_rate": 1.8904823989569756e-07, + "loss": 0.4157, + "step": 36468 + }, + { + "epoch": 2.97, + "learning_rate": 1.8850499782703174e-07, + "loss": 0.0664, + "step": 36469 + }, + { + "epoch": 2.97, + "learning_rate": 1.8796175575836595e-07, + "loss": 0.258, + "step": 36470 + }, + { + "epoch": 2.97, + "learning_rate": 1.8741851368970015e-07, + "loss": 0.3691, + "step": 36471 + }, + { + "epoch": 2.97, + "learning_rate": 1.8687527162103435e-07, + "loss": 0.3059, + "step": 36472 + }, + { + "epoch": 2.97, + "learning_rate": 1.8633202955236853e-07, + "loss": 0.213, + "step": 36473 + }, + { + "epoch": 2.97, + "learning_rate": 1.8578878748370274e-07, + "loss": 0.061, + "step": 36474 + }, + { + "epoch": 2.97, + "learning_rate": 1.8524554541503697e-07, + "loss": 0.289, + "step": 36475 + }, + { + "epoch": 2.97, + "learning_rate": 1.8470230334637114e-07, + "loss": 0.1637, + "step": 36476 + }, + { + "epoch": 2.97, + "learning_rate": 1.8415906127770535e-07, + "loss": 0.3205, + "step": 36477 + }, + { + "epoch": 2.97, + "learning_rate": 1.8361581920903958e-07, + "loss": 0.3485, + "step": 36478 + }, + { + "epoch": 2.97, + "learning_rate": 1.8307257714037376e-07, + "loss": 0.4471, + "step": 36479 + }, + { + "epoch": 2.97, + "learning_rate": 1.8252933507170796e-07, + "loss": 0.0837, + "step": 36480 + }, + { + "epoch": 2.97, + "learning_rate": 1.819860930030422e-07, + "loss": 0.0821, + "step": 36481 + }, + { + "epoch": 2.97, + "learning_rate": 1.8144285093437637e-07, + "loss": 0.0838, + "step": 36482 + }, + { + "epoch": 2.97, + "learning_rate": 1.8089960886571057e-07, + "loss": 0.2655, + "step": 36483 + }, + { + "epoch": 2.97, + "learning_rate": 1.8035636679704478e-07, + "loss": 0.2556, + "step": 36484 + }, + { + "epoch": 2.97, + "learning_rate": 1.7981312472837898e-07, + "loss": 0.1253, + "step": 36485 + }, + { + "epoch": 2.97, + "learning_rate": 1.7926988265971318e-07, + "loss": 0.2358, + "step": 36486 + }, + { + "epoch": 2.97, + "learning_rate": 1.787266405910474e-07, + "loss": 0.3013, + "step": 36487 + }, + { + "epoch": 2.97, + "learning_rate": 1.781833985223816e-07, + "loss": 0.0992, + "step": 36488 + }, + { + "epoch": 2.97, + "learning_rate": 1.7764015645371577e-07, + "loss": 0.1685, + "step": 36489 + }, + { + "epoch": 2.97, + "learning_rate": 1.7709691438505e-07, + "loss": 0.1688, + "step": 36490 + }, + { + "epoch": 2.97, + "learning_rate": 1.765536723163842e-07, + "loss": 0.1122, + "step": 36491 + }, + { + "epoch": 2.97, + "learning_rate": 1.7601043024771838e-07, + "loss": 0.2378, + "step": 36492 + }, + { + "epoch": 2.97, + "learning_rate": 1.754671881790526e-07, + "loss": 0.3833, + "step": 36493 + }, + { + "epoch": 2.97, + "learning_rate": 1.7492394611038682e-07, + "loss": 0.2791, + "step": 36494 + }, + { + "epoch": 2.97, + "learning_rate": 1.74380704041721e-07, + "loss": 0.1237, + "step": 36495 + }, + { + "epoch": 2.97, + "learning_rate": 1.738374619730552e-07, + "loss": 0.0678, + "step": 36496 + }, + { + "epoch": 2.97, + "learning_rate": 1.7329421990438943e-07, + "loss": 0.0478, + "step": 36497 + }, + { + "epoch": 2.97, + "learning_rate": 1.727509778357236e-07, + "loss": 0.2392, + "step": 36498 + }, + { + "epoch": 2.97, + "learning_rate": 1.722077357670578e-07, + "loss": 0.333, + "step": 36499 + }, + { + "epoch": 2.97, + "learning_rate": 1.7166449369839202e-07, + "loss": 0.1974, + "step": 36500 + }, + { + "epoch": 2.97, + "eval_accuracy": 0.8449312277126847, + "eval_loss": 0.492473304271698, + "eval_runtime": 22.2492, + "eval_samples_per_second": 441.14, + "eval_steps_per_second": 3.461, + "step": 36500 + }, + { + "epoch": 2.97, + "learning_rate": 1.7112125162972622e-07, + "loss": 0.2196, + "step": 36501 + }, + { + "epoch": 2.97, + "learning_rate": 1.705780095610604e-07, + "loss": 0.2209, + "step": 36502 + }, + { + "epoch": 2.97, + "learning_rate": 1.7003476749239463e-07, + "loss": 0.1732, + "step": 36503 + }, + { + "epoch": 2.97, + "learning_rate": 1.6949152542372883e-07, + "loss": 0.3321, + "step": 36504 + }, + { + "epoch": 2.97, + "learning_rate": 1.68948283355063e-07, + "loss": 0.1626, + "step": 36505 + }, + { + "epoch": 2.97, + "learning_rate": 1.6840504128639724e-07, + "loss": 0.2199, + "step": 36506 + }, + { + "epoch": 2.97, + "learning_rate": 1.6786179921773144e-07, + "loss": 0.1074, + "step": 36507 + }, + { + "epoch": 2.97, + "learning_rate": 1.6731855714906562e-07, + "loss": 0.2212, + "step": 36508 + }, + { + "epoch": 2.97, + "learning_rate": 1.6677531508039985e-07, + "loss": 0.2159, + "step": 36509 + }, + { + "epoch": 2.98, + "learning_rate": 1.6623207301173406e-07, + "loss": 0.0657, + "step": 36510 + }, + { + "epoch": 2.98, + "learning_rate": 1.6568883094306823e-07, + "loss": 0.0849, + "step": 36511 + }, + { + "epoch": 2.98, + "learning_rate": 1.6514558887440246e-07, + "loss": 0.2347, + "step": 36512 + }, + { + "epoch": 2.98, + "learning_rate": 1.6460234680573664e-07, + "loss": 0.1592, + "step": 36513 + }, + { + "epoch": 2.98, + "learning_rate": 1.6405910473707085e-07, + "loss": 0.3606, + "step": 36514 + }, + { + "epoch": 2.98, + "learning_rate": 1.6351586266840508e-07, + "loss": 0.2592, + "step": 36515 + }, + { + "epoch": 2.98, + "learning_rate": 1.6297262059973925e-07, + "loss": 0.2489, + "step": 36516 + }, + { + "epoch": 2.98, + "learning_rate": 1.6242937853107346e-07, + "loss": 0.386, + "step": 36517 + }, + { + "epoch": 2.98, + "learning_rate": 1.6188613646240764e-07, + "loss": 0.4743, + "step": 36518 + }, + { + "epoch": 2.98, + "learning_rate": 1.6134289439374187e-07, + "loss": 0.3962, + "step": 36519 + }, + { + "epoch": 2.98, + "learning_rate": 1.6079965232507607e-07, + "loss": 0.1913, + "step": 36520 + }, + { + "epoch": 2.98, + "learning_rate": 1.6025641025641025e-07, + "loss": 0.0428, + "step": 36521 + }, + { + "epoch": 2.98, + "learning_rate": 1.5971316818774448e-07, + "loss": 0.4802, + "step": 36522 + }, + { + "epoch": 2.98, + "learning_rate": 1.5916992611907868e-07, + "loss": 0.2396, + "step": 36523 + }, + { + "epoch": 2.98, + "learning_rate": 1.5862668405041286e-07, + "loss": 0.2413, + "step": 36524 + }, + { + "epoch": 2.98, + "learning_rate": 1.580834419817471e-07, + "loss": 0.2578, + "step": 36525 + }, + { + "epoch": 2.98, + "learning_rate": 1.575401999130813e-07, + "loss": 0.4847, + "step": 36526 + }, + { + "epoch": 2.98, + "learning_rate": 1.5699695784441547e-07, + "loss": 0.2969, + "step": 36527 + }, + { + "epoch": 2.98, + "learning_rate": 1.564537157757497e-07, + "loss": 0.1361, + "step": 36528 + }, + { + "epoch": 2.98, + "learning_rate": 1.5591047370708388e-07, + "loss": 0.3337, + "step": 36529 + }, + { + "epoch": 2.98, + "learning_rate": 1.553672316384181e-07, + "loss": 0.1063, + "step": 36530 + }, + { + "epoch": 2.98, + "learning_rate": 1.548239895697523e-07, + "loss": 0.4777, + "step": 36531 + }, + { + "epoch": 2.98, + "learning_rate": 1.542807475010865e-07, + "loss": 0.055, + "step": 36532 + }, + { + "epoch": 2.98, + "learning_rate": 1.537375054324207e-07, + "loss": 0.164, + "step": 36533 + }, + { + "epoch": 2.98, + "learning_rate": 1.531942633637549e-07, + "loss": 0.1939, + "step": 36534 + }, + { + "epoch": 2.98, + "learning_rate": 1.526510212950891e-07, + "loss": 0.1651, + "step": 36535 + }, + { + "epoch": 2.98, + "learning_rate": 1.521077792264233e-07, + "loss": 0.1903, + "step": 36536 + }, + { + "epoch": 2.98, + "learning_rate": 1.515645371577575e-07, + "loss": 0.1673, + "step": 36537 + }, + { + "epoch": 2.98, + "learning_rate": 1.5102129508909172e-07, + "loss": 0.2643, + "step": 36538 + }, + { + "epoch": 2.98, + "learning_rate": 1.5047805302042592e-07, + "loss": 0.2639, + "step": 36539 + }, + { + "epoch": 2.98, + "learning_rate": 1.4993481095176013e-07, + "loss": 0.2484, + "step": 36540 + }, + { + "epoch": 2.98, + "learning_rate": 1.4939156888309433e-07, + "loss": 0.3865, + "step": 36541 + }, + { + "epoch": 2.98, + "learning_rate": 1.488483268144285e-07, + "loss": 0.4639, + "step": 36542 + }, + { + "epoch": 2.98, + "learning_rate": 1.4830508474576274e-07, + "loss": 0.1704, + "step": 36543 + }, + { + "epoch": 2.98, + "learning_rate": 1.4776184267709692e-07, + "loss": 0.2708, + "step": 36544 + }, + { + "epoch": 2.98, + "learning_rate": 1.4721860060843112e-07, + "loss": 0.0768, + "step": 36545 + }, + { + "epoch": 2.98, + "learning_rate": 1.4667535853976535e-07, + "loss": 0.0613, + "step": 36546 + }, + { + "epoch": 2.98, + "learning_rate": 1.4613211647109953e-07, + "loss": 0.2009, + "step": 36547 + }, + { + "epoch": 2.98, + "learning_rate": 1.4558887440243373e-07, + "loss": 0.2401, + "step": 36548 + }, + { + "epoch": 2.98, + "learning_rate": 1.4504563233376794e-07, + "loss": 0.4185, + "step": 36549 + }, + { + "epoch": 2.98, + "learning_rate": 1.4450239026510214e-07, + "loss": 0.1162, + "step": 36550 + }, + { + "epoch": 2.98, + "learning_rate": 1.4395914819643634e-07, + "loss": 0.2669, + "step": 36551 + }, + { + "epoch": 2.98, + "learning_rate": 1.4341590612777055e-07, + "loss": 0.0906, + "step": 36552 + }, + { + "epoch": 2.98, + "learning_rate": 1.4287266405910475e-07, + "loss": 0.3048, + "step": 36553 + }, + { + "epoch": 2.98, + "learning_rate": 1.4232942199043896e-07, + "loss": 0.1785, + "step": 36554 + }, + { + "epoch": 2.98, + "learning_rate": 1.4178617992177316e-07, + "loss": 0.2233, + "step": 36555 + }, + { + "epoch": 2.98, + "learning_rate": 1.4124293785310736e-07, + "loss": 0.252, + "step": 36556 + }, + { + "epoch": 2.98, + "learning_rate": 1.4069969578444157e-07, + "loss": 0.1524, + "step": 36557 + }, + { + "epoch": 2.98, + "learning_rate": 1.4015645371577575e-07, + "loss": 0.3816, + "step": 36558 + }, + { + "epoch": 2.98, + "learning_rate": 1.3961321164710998e-07, + "loss": 0.3186, + "step": 36559 + }, + { + "epoch": 2.98, + "learning_rate": 1.3906996957844418e-07, + "loss": 0.0722, + "step": 36560 + }, + { + "epoch": 2.98, + "learning_rate": 1.3852672750977836e-07, + "loss": 0.4676, + "step": 36561 + }, + { + "epoch": 2.98, + "learning_rate": 1.3798348544111256e-07, + "loss": 0.1667, + "step": 36562 + }, + { + "epoch": 2.98, + "learning_rate": 1.3744024337244677e-07, + "loss": 0.0357, + "step": 36563 + }, + { + "epoch": 2.98, + "learning_rate": 1.3689700130378097e-07, + "loss": 0.6815, + "step": 36564 + }, + { + "epoch": 2.98, + "learning_rate": 1.3635375923511517e-07, + "loss": 0.086, + "step": 36565 + }, + { + "epoch": 2.98, + "learning_rate": 1.3581051716644938e-07, + "loss": 0.2323, + "step": 36566 + }, + { + "epoch": 2.98, + "learning_rate": 1.3526727509778358e-07, + "loss": 0.0675, + "step": 36567 + }, + { + "epoch": 2.98, + "learning_rate": 1.3472403302911779e-07, + "loss": 0.2502, + "step": 36568 + }, + { + "epoch": 2.98, + "learning_rate": 1.34180790960452e-07, + "loss": 0.0452, + "step": 36569 + }, + { + "epoch": 2.98, + "learning_rate": 1.336375488917862e-07, + "loss": 0.25, + "step": 36570 + }, + { + "epoch": 2.98, + "learning_rate": 1.330943068231204e-07, + "loss": 0.0523, + "step": 36571 + }, + { + "epoch": 2.98, + "learning_rate": 1.325510647544546e-07, + "loss": 0.2585, + "step": 36572 + }, + { + "epoch": 2.98, + "learning_rate": 1.320078226857888e-07, + "loss": 0.084, + "step": 36573 + }, + { + "epoch": 2.98, + "learning_rate": 1.3146458061712298e-07, + "loss": 0.1143, + "step": 36574 + }, + { + "epoch": 2.98, + "learning_rate": 1.3092133854845721e-07, + "loss": 0.2418, + "step": 36575 + }, + { + "epoch": 2.98, + "learning_rate": 1.3037809647979142e-07, + "loss": 0.0402, + "step": 36576 + }, + { + "epoch": 2.98, + "learning_rate": 1.298348544111256e-07, + "loss": 0.2757, + "step": 36577 + }, + { + "epoch": 2.98, + "learning_rate": 1.292916123424598e-07, + "loss": 0.0857, + "step": 36578 + }, + { + "epoch": 2.98, + "learning_rate": 1.2874837027379403e-07, + "loss": 0.1877, + "step": 36579 + }, + { + "epoch": 2.98, + "learning_rate": 1.282051282051282e-07, + "loss": 0.0585, + "step": 36580 + }, + { + "epoch": 2.98, + "learning_rate": 1.276618861364624e-07, + "loss": 0.1527, + "step": 36581 + }, + { + "epoch": 2.98, + "learning_rate": 1.2711864406779662e-07, + "loss": 0.2656, + "step": 36582 + }, + { + "epoch": 2.98, + "learning_rate": 1.2657540199913082e-07, + "loss": 0.252, + "step": 36583 + }, + { + "epoch": 2.98, + "learning_rate": 1.2603215993046503e-07, + "loss": 0.4157, + "step": 36584 + }, + { + "epoch": 2.98, + "learning_rate": 1.2548891786179923e-07, + "loss": 0.2772, + "step": 36585 + }, + { + "epoch": 2.98, + "learning_rate": 1.2494567579313343e-07, + "loss": 0.1463, + "step": 36586 + }, + { + "epoch": 2.98, + "learning_rate": 1.2440243372446764e-07, + "loss": 0.1945, + "step": 36587 + }, + { + "epoch": 2.98, + "learning_rate": 1.2385919165580184e-07, + "loss": 0.1011, + "step": 36588 + }, + { + "epoch": 2.98, + "learning_rate": 1.2331594958713605e-07, + "loss": 0.033, + "step": 36589 + }, + { + "epoch": 2.98, + "learning_rate": 1.2277270751847025e-07, + "loss": 0.0708, + "step": 36590 + }, + { + "epoch": 2.98, + "learning_rate": 1.2222946544980443e-07, + "loss": 0.0657, + "step": 36591 + }, + { + "epoch": 2.98, + "learning_rate": 1.2168622338113866e-07, + "loss": 0.2144, + "step": 36592 + }, + { + "epoch": 2.98, + "learning_rate": 1.2114298131247286e-07, + "loss": 0.1059, + "step": 36593 + }, + { + "epoch": 2.98, + "learning_rate": 1.2059973924380704e-07, + "loss": 0.1756, + "step": 36594 + }, + { + "epoch": 2.98, + "learning_rate": 1.2005649717514124e-07, + "loss": 0.1525, + "step": 36595 + }, + { + "epoch": 2.98, + "learning_rate": 1.1951325510647545e-07, + "loss": 0.2653, + "step": 36596 + }, + { + "epoch": 2.98, + "learning_rate": 1.1897001303780965e-07, + "loss": 0.3036, + "step": 36597 + }, + { + "epoch": 2.98, + "learning_rate": 1.1842677096914387e-07, + "loss": 0.0818, + "step": 36598 + }, + { + "epoch": 2.98, + "learning_rate": 1.1788352890047806e-07, + "loss": 0.1253, + "step": 36599 + }, + { + "epoch": 2.98, + "learning_rate": 1.1734028683181226e-07, + "loss": 0.1805, + "step": 36600 + }, + { + "epoch": 2.98, + "learning_rate": 1.1679704476314648e-07, + "loss": 0.308, + "step": 36601 + }, + { + "epoch": 2.98, + "learning_rate": 1.1625380269448067e-07, + "loss": 0.1367, + "step": 36602 + }, + { + "epoch": 2.98, + "learning_rate": 1.1571056062581488e-07, + "loss": 0.283, + "step": 36603 + }, + { + "epoch": 2.98, + "learning_rate": 1.1516731855714907e-07, + "loss": 0.4031, + "step": 36604 + }, + { + "epoch": 2.98, + "learning_rate": 1.1462407648848327e-07, + "loss": 0.1985, + "step": 36605 + }, + { + "epoch": 2.98, + "learning_rate": 1.1408083441981749e-07, + "loss": 0.1297, + "step": 36606 + }, + { + "epoch": 2.98, + "learning_rate": 1.1353759235115168e-07, + "loss": 0.4062, + "step": 36607 + }, + { + "epoch": 2.98, + "learning_rate": 1.1299435028248588e-07, + "loss": 0.3053, + "step": 36608 + }, + { + "epoch": 2.98, + "learning_rate": 1.1245110821382009e-07, + "loss": 0.3994, + "step": 36609 + }, + { + "epoch": 2.98, + "learning_rate": 1.1190786614515429e-07, + "loss": 0.1412, + "step": 36610 + }, + { + "epoch": 2.98, + "learning_rate": 1.113646240764885e-07, + "loss": 0.2649, + "step": 36611 + }, + { + "epoch": 2.98, + "learning_rate": 1.108213820078227e-07, + "loss": 0.3223, + "step": 36612 + }, + { + "epoch": 2.98, + "learning_rate": 1.1027813993915689e-07, + "loss": 0.2461, + "step": 36613 + }, + { + "epoch": 2.98, + "learning_rate": 1.0973489787049111e-07, + "loss": 0.1788, + "step": 36614 + }, + { + "epoch": 2.98, + "learning_rate": 1.091916558018253e-07, + "loss": 0.1032, + "step": 36615 + }, + { + "epoch": 2.98, + "learning_rate": 1.086484137331595e-07, + "loss": 0.1468, + "step": 36616 + }, + { + "epoch": 2.98, + "learning_rate": 1.0810517166449371e-07, + "loss": 0.195, + "step": 36617 + }, + { + "epoch": 2.98, + "learning_rate": 1.075619295958279e-07, + "loss": 0.2512, + "step": 36618 + }, + { + "epoch": 2.98, + "learning_rate": 1.0701868752716211e-07, + "loss": 0.1464, + "step": 36619 + }, + { + "epoch": 2.98, + "learning_rate": 1.0647544545849632e-07, + "loss": 0.2651, + "step": 36620 + }, + { + "epoch": 2.98, + "learning_rate": 1.0593220338983051e-07, + "loss": 0.2728, + "step": 36621 + }, + { + "epoch": 2.98, + "learning_rate": 1.0538896132116473e-07, + "loss": 0.2617, + "step": 36622 + }, + { + "epoch": 2.98, + "learning_rate": 1.0484571925249893e-07, + "loss": 0.2067, + "step": 36623 + }, + { + "epoch": 2.98, + "learning_rate": 1.0430247718383312e-07, + "loss": 0.2283, + "step": 36624 + }, + { + "epoch": 2.98, + "learning_rate": 1.0375923511516733e-07, + "loss": 0.3646, + "step": 36625 + }, + { + "epoch": 2.98, + "learning_rate": 1.0321599304650152e-07, + "loss": 0.1965, + "step": 36626 + }, + { + "epoch": 2.98, + "learning_rate": 1.0267275097783573e-07, + "loss": 0.2613, + "step": 36627 + }, + { + "epoch": 2.98, + "learning_rate": 1.0212950890916994e-07, + "loss": 0.2511, + "step": 36628 + }, + { + "epoch": 2.98, + "learning_rate": 1.0158626684050413e-07, + "loss": 0.1986, + "step": 36629 + }, + { + "epoch": 2.98, + "learning_rate": 1.0104302477183833e-07, + "loss": 0.1754, + "step": 36630 + }, + { + "epoch": 2.98, + "learning_rate": 1.0049978270317255e-07, + "loss": 0.2515, + "step": 36631 + }, + { + "epoch": 2.99, + "learning_rate": 9.995654063450674e-08, + "loss": 0.1454, + "step": 36632 + }, + { + "epoch": 2.99, + "learning_rate": 9.941329856584095e-08, + "loss": 0.2574, + "step": 36633 + }, + { + "epoch": 2.99, + "learning_rate": 9.887005649717516e-08, + "loss": 0.3824, + "step": 36634 + }, + { + "epoch": 2.99, + "learning_rate": 9.832681442850935e-08, + "loss": 0.0927, + "step": 36635 + }, + { + "epoch": 2.99, + "learning_rate": 9.778357235984356e-08, + "loss": 0.2438, + "step": 36636 + }, + { + "epoch": 2.99, + "learning_rate": 9.724033029117775e-08, + "loss": 0.3562, + "step": 36637 + }, + { + "epoch": 2.99, + "learning_rate": 9.669708822251195e-08, + "loss": 0.3135, + "step": 36638 + }, + { + "epoch": 2.99, + "learning_rate": 9.615384615384617e-08, + "loss": 0.3175, + "step": 36639 + }, + { + "epoch": 2.99, + "learning_rate": 9.561060408518036e-08, + "loss": 0.5111, + "step": 36640 + }, + { + "epoch": 2.99, + "learning_rate": 9.506736201651456e-08, + "loss": 0.2043, + "step": 36641 + }, + { + "epoch": 2.99, + "learning_rate": 9.452411994784878e-08, + "loss": 0.1564, + "step": 36642 + }, + { + "epoch": 2.99, + "learning_rate": 9.398087787918297e-08, + "loss": 0.2598, + "step": 36643 + }, + { + "epoch": 2.99, + "learning_rate": 9.343763581051718e-08, + "loss": 0.1266, + "step": 36644 + }, + { + "epoch": 2.99, + "learning_rate": 9.289439374185137e-08, + "loss": 0.3108, + "step": 36645 + }, + { + "epoch": 2.99, + "learning_rate": 9.235115167318557e-08, + "loss": 0.4175, + "step": 36646 + }, + { + "epoch": 2.99, + "learning_rate": 9.180790960451979e-08, + "loss": 0.1368, + "step": 36647 + }, + { + "epoch": 2.99, + "learning_rate": 9.126466753585398e-08, + "loss": 0.1387, + "step": 36648 + }, + { + "epoch": 2.99, + "learning_rate": 9.072142546718818e-08, + "loss": 0.4972, + "step": 36649 + }, + { + "epoch": 2.99, + "learning_rate": 9.017818339852239e-08, + "loss": 0.3033, + "step": 36650 + }, + { + "epoch": 2.99, + "learning_rate": 8.963494132985659e-08, + "loss": 0.2969, + "step": 36651 + }, + { + "epoch": 2.99, + "learning_rate": 8.90916992611908e-08, + "loss": 0.4996, + "step": 36652 + }, + { + "epoch": 2.99, + "learning_rate": 8.8548457192525e-08, + "loss": 0.2262, + "step": 36653 + }, + { + "epoch": 2.99, + "learning_rate": 8.800521512385919e-08, + "loss": 0.4618, + "step": 36654 + }, + { + "epoch": 2.99, + "learning_rate": 8.746197305519341e-08, + "loss": 0.3259, + "step": 36655 + }, + { + "epoch": 2.99, + "learning_rate": 8.69187309865276e-08, + "loss": 0.1141, + "step": 36656 + }, + { + "epoch": 2.99, + "learning_rate": 8.63754889178618e-08, + "loss": 0.5451, + "step": 36657 + }, + { + "epoch": 2.99, + "learning_rate": 8.583224684919601e-08, + "loss": 0.3574, + "step": 36658 + }, + { + "epoch": 2.99, + "learning_rate": 8.52890047805302e-08, + "loss": 0.3493, + "step": 36659 + }, + { + "epoch": 2.99, + "learning_rate": 8.474576271186442e-08, + "loss": 0.2768, + "step": 36660 + }, + { + "epoch": 2.99, + "learning_rate": 8.420252064319862e-08, + "loss": 0.259, + "step": 36661 + }, + { + "epoch": 2.99, + "learning_rate": 8.365927857453281e-08, + "loss": 0.2401, + "step": 36662 + }, + { + "epoch": 2.99, + "learning_rate": 8.311603650586703e-08, + "loss": 0.1358, + "step": 36663 + }, + { + "epoch": 2.99, + "learning_rate": 8.257279443720123e-08, + "loss": 0.2678, + "step": 36664 + }, + { + "epoch": 2.99, + "learning_rate": 8.202955236853542e-08, + "loss": 0.0837, + "step": 36665 + }, + { + "epoch": 2.99, + "learning_rate": 8.148631029986963e-08, + "loss": 0.1152, + "step": 36666 + }, + { + "epoch": 2.99, + "learning_rate": 8.094306823120382e-08, + "loss": 0.1068, + "step": 36667 + }, + { + "epoch": 2.99, + "learning_rate": 8.039982616253804e-08, + "loss": 0.1821, + "step": 36668 + }, + { + "epoch": 2.99, + "learning_rate": 7.985658409387224e-08, + "loss": 0.457, + "step": 36669 + }, + { + "epoch": 2.99, + "learning_rate": 7.931334202520643e-08, + "loss": 0.5604, + "step": 36670 + }, + { + "epoch": 2.99, + "learning_rate": 7.877009995654065e-08, + "loss": 0.0633, + "step": 36671 + }, + { + "epoch": 2.99, + "learning_rate": 7.822685788787485e-08, + "loss": 0.2383, + "step": 36672 + }, + { + "epoch": 2.99, + "learning_rate": 7.768361581920906e-08, + "loss": 0.2503, + "step": 36673 + }, + { + "epoch": 2.99, + "learning_rate": 7.714037375054325e-08, + "loss": 0.4699, + "step": 36674 + }, + { + "epoch": 2.99, + "learning_rate": 7.659713168187745e-08, + "loss": 0.1566, + "step": 36675 + }, + { + "epoch": 2.99, + "learning_rate": 7.605388961321165e-08, + "loss": 0.2983, + "step": 36676 + }, + { + "epoch": 2.99, + "learning_rate": 7.551064754454586e-08, + "loss": 0.379, + "step": 36677 + }, + { + "epoch": 2.99, + "learning_rate": 7.496740547588006e-08, + "loss": 0.0535, + "step": 36678 + }, + { + "epoch": 2.99, + "learning_rate": 7.442416340721425e-08, + "loss": 0.0857, + "step": 36679 + }, + { + "epoch": 2.99, + "learning_rate": 7.388092133854846e-08, + "loss": 0.2123, + "step": 36680 + }, + { + "epoch": 2.99, + "learning_rate": 7.333767926988267e-08, + "loss": 0.5626, + "step": 36681 + }, + { + "epoch": 2.99, + "learning_rate": 7.279443720121687e-08, + "loss": 0.0998, + "step": 36682 + }, + { + "epoch": 2.99, + "learning_rate": 7.225119513255107e-08, + "loss": 0.1335, + "step": 36683 + }, + { + "epoch": 2.99, + "learning_rate": 7.170795306388527e-08, + "loss": 0.0933, + "step": 36684 + }, + { + "epoch": 2.99, + "learning_rate": 7.116471099521948e-08, + "loss": 0.3953, + "step": 36685 + }, + { + "epoch": 2.99, + "learning_rate": 7.062146892655368e-08, + "loss": 0.0899, + "step": 36686 + }, + { + "epoch": 2.99, + "learning_rate": 7.007822685788787e-08, + "loss": 0.1005, + "step": 36687 + }, + { + "epoch": 2.99, + "learning_rate": 6.953498478922209e-08, + "loss": 0.196, + "step": 36688 + }, + { + "epoch": 2.99, + "learning_rate": 6.899174272055628e-08, + "loss": 0.2123, + "step": 36689 + }, + { + "epoch": 2.99, + "learning_rate": 6.844850065189049e-08, + "loss": 0.2618, + "step": 36690 + }, + { + "epoch": 2.99, + "learning_rate": 6.790525858322469e-08, + "loss": 0.4802, + "step": 36691 + }, + { + "epoch": 2.99, + "learning_rate": 6.736201651455889e-08, + "loss": 0.0859, + "step": 36692 + }, + { + "epoch": 2.99, + "learning_rate": 6.68187744458931e-08, + "loss": 0.3114, + "step": 36693 + }, + { + "epoch": 2.99, + "learning_rate": 6.62755323772273e-08, + "loss": 0.141, + "step": 36694 + }, + { + "epoch": 2.99, + "learning_rate": 6.573229030856149e-08, + "loss": 0.2359, + "step": 36695 + }, + { + "epoch": 2.99, + "learning_rate": 6.518904823989571e-08, + "loss": 0.1254, + "step": 36696 + }, + { + "epoch": 2.99, + "learning_rate": 6.46458061712299e-08, + "loss": 0.5827, + "step": 36697 + }, + { + "epoch": 2.99, + "learning_rate": 6.41025641025641e-08, + "loss": 0.2483, + "step": 36698 + }, + { + "epoch": 2.99, + "learning_rate": 6.355932203389831e-08, + "loss": 0.1228, + "step": 36699 + }, + { + "epoch": 2.99, + "learning_rate": 6.301607996523251e-08, + "loss": 0.0576, + "step": 36700 + }, + { + "epoch": 2.99, + "learning_rate": 6.247283789656672e-08, + "loss": 0.2086, + "step": 36701 + }, + { + "epoch": 2.99, + "learning_rate": 6.192959582790092e-08, + "loss": 0.2605, + "step": 36702 + }, + { + "epoch": 2.99, + "learning_rate": 6.138635375923512e-08, + "loss": 0.4049, + "step": 36703 + }, + { + "epoch": 2.99, + "learning_rate": 6.084311169056933e-08, + "loss": 0.1798, + "step": 36704 + }, + { + "epoch": 2.99, + "learning_rate": 6.029986962190352e-08, + "loss": 0.0805, + "step": 36705 + }, + { + "epoch": 2.99, + "learning_rate": 5.975662755323772e-08, + "loss": 0.1774, + "step": 36706 + }, + { + "epoch": 2.99, + "learning_rate": 5.9213385484571934e-08, + "loss": 0.1417, + "step": 36707 + }, + { + "epoch": 2.99, + "learning_rate": 5.867014341590613e-08, + "loss": 0.229, + "step": 36708 + }, + { + "epoch": 2.99, + "learning_rate": 5.8126901347240336e-08, + "loss": 0.1027, + "step": 36709 + }, + { + "epoch": 2.99, + "learning_rate": 5.7583659278574533e-08, + "loss": 0.0512, + "step": 36710 + }, + { + "epoch": 2.99, + "learning_rate": 5.7040417209908744e-08, + "loss": 0.5253, + "step": 36711 + }, + { + "epoch": 2.99, + "learning_rate": 5.649717514124294e-08, + "loss": 0.0973, + "step": 36712 + }, + { + "epoch": 2.99, + "learning_rate": 5.5953933072577146e-08, + "loss": 0.1338, + "step": 36713 + }, + { + "epoch": 2.99, + "learning_rate": 5.541069100391135e-08, + "loss": 0.4151, + "step": 36714 + }, + { + "epoch": 2.99, + "learning_rate": 5.4867448935245554e-08, + "loss": 0.2204, + "step": 36715 + }, + { + "epoch": 2.99, + "learning_rate": 5.432420686657975e-08, + "loss": 0.1924, + "step": 36716 + }, + { + "epoch": 2.99, + "learning_rate": 5.378096479791395e-08, + "loss": 0.2467, + "step": 36717 + }, + { + "epoch": 2.99, + "learning_rate": 5.323772272924816e-08, + "loss": 0.3369, + "step": 36718 + }, + { + "epoch": 2.99, + "learning_rate": 5.2694480660582364e-08, + "loss": 0.1732, + "step": 36719 + }, + { + "epoch": 2.99, + "learning_rate": 5.215123859191656e-08, + "loss": 0.3531, + "step": 36720 + }, + { + "epoch": 2.99, + "learning_rate": 5.160799652325076e-08, + "loss": 0.1637, + "step": 36721 + }, + { + "epoch": 2.99, + "learning_rate": 5.106475445458497e-08, + "loss": 0.1182, + "step": 36722 + }, + { + "epoch": 2.99, + "learning_rate": 5.0521512385919167e-08, + "loss": 0.2414, + "step": 36723 + }, + { + "epoch": 2.99, + "learning_rate": 4.997827031725337e-08, + "loss": 0.0881, + "step": 36724 + }, + { + "epoch": 2.99, + "learning_rate": 4.943502824858758e-08, + "loss": 0.141, + "step": 36725 + }, + { + "epoch": 2.99, + "learning_rate": 4.889178617992178e-08, + "loss": 0.4712, + "step": 36726 + }, + { + "epoch": 2.99, + "learning_rate": 4.8348544111255976e-08, + "loss": 0.0917, + "step": 36727 + }, + { + "epoch": 2.99, + "learning_rate": 4.780530204259018e-08, + "loss": 0.3028, + "step": 36728 + }, + { + "epoch": 2.99, + "learning_rate": 4.726205997392439e-08, + "loss": 0.0498, + "step": 36729 + }, + { + "epoch": 2.99, + "learning_rate": 4.671881790525859e-08, + "loss": 0.3653, + "step": 36730 + }, + { + "epoch": 2.99, + "learning_rate": 4.6175575836592786e-08, + "loss": 0.2393, + "step": 36731 + }, + { + "epoch": 2.99, + "learning_rate": 4.563233376792699e-08, + "loss": 0.2073, + "step": 36732 + }, + { + "epoch": 2.99, + "learning_rate": 4.5089091699261194e-08, + "loss": 0.3334, + "step": 36733 + }, + { + "epoch": 2.99, + "learning_rate": 4.45458496305954e-08, + "loss": 0.1952, + "step": 36734 + }, + { + "epoch": 2.99, + "learning_rate": 4.4002607561929596e-08, + "loss": 0.2191, + "step": 36735 + }, + { + "epoch": 2.99, + "learning_rate": 4.34593654932638e-08, + "loss": 0.0763, + "step": 36736 + }, + { + "epoch": 2.99, + "learning_rate": 4.2916123424598004e-08, + "loss": 0.1638, + "step": 36737 + }, + { + "epoch": 2.99, + "learning_rate": 4.237288135593221e-08, + "loss": 0.1865, + "step": 36738 + }, + { + "epoch": 2.99, + "learning_rate": 4.1829639287266405e-08, + "loss": 0.4738, + "step": 36739 + }, + { + "epoch": 2.99, + "learning_rate": 4.1286397218600616e-08, + "loss": 0.2998, + "step": 36740 + }, + { + "epoch": 2.99, + "learning_rate": 4.0743155149934813e-08, + "loss": 0.1334, + "step": 36741 + }, + { + "epoch": 2.99, + "learning_rate": 4.019991308126902e-08, + "loss": 0.1407, + "step": 36742 + }, + { + "epoch": 2.99, + "learning_rate": 3.9656671012603215e-08, + "loss": 0.0989, + "step": 36743 + }, + { + "epoch": 2.99, + "learning_rate": 3.9113428943937426e-08, + "loss": 0.2742, + "step": 36744 + }, + { + "epoch": 2.99, + "learning_rate": 3.857018687527162e-08, + "loss": 0.168, + "step": 36745 + }, + { + "epoch": 2.99, + "learning_rate": 3.802694480660583e-08, + "loss": 0.2158, + "step": 36746 + }, + { + "epoch": 2.99, + "learning_rate": 3.748370273794003e-08, + "loss": 0.2827, + "step": 36747 + }, + { + "epoch": 2.99, + "learning_rate": 3.694046066927423e-08, + "loss": 0.2181, + "step": 36748 + }, + { + "epoch": 2.99, + "learning_rate": 3.639721860060843e-08, + "loss": 0.3293, + "step": 36749 + }, + { + "epoch": 2.99, + "learning_rate": 3.585397653194264e-08, + "loss": 0.3403, + "step": 36750 + }, + { + "epoch": 2.99, + "eval_accuracy": 0.8444218033622007, + "eval_loss": 0.49250245094299316, + "eval_runtime": 22.2667, + "eval_samples_per_second": 440.792, + "eval_steps_per_second": 3.458, + "step": 36750 + }, + { + "epoch": 2.99, + "learning_rate": 3.531073446327684e-08, + "loss": 0.2693, + "step": 36751 + }, + { + "epoch": 2.99, + "learning_rate": 3.4767492394611045e-08, + "loss": 0.2286, + "step": 36752 + }, + { + "epoch": 2.99, + "learning_rate": 3.422425032594524e-08, + "loss": 0.1742, + "step": 36753 + }, + { + "epoch": 2.99, + "learning_rate": 3.3681008257279447e-08, + "loss": 0.171, + "step": 36754 + }, + { + "epoch": 3.0, + "learning_rate": 3.313776618861365e-08, + "loss": 0.3481, + "step": 36755 + }, + { + "epoch": 3.0, + "learning_rate": 3.2594524119947855e-08, + "loss": 0.2702, + "step": 36756 + }, + { + "epoch": 3.0, + "learning_rate": 3.205128205128205e-08, + "loss": 0.4057, + "step": 36757 + }, + { + "epoch": 3.0, + "learning_rate": 3.1508039982616256e-08, + "loss": 0.3199, + "step": 36758 + }, + { + "epoch": 3.0, + "learning_rate": 3.096479791395046e-08, + "loss": 0.3044, + "step": 36759 + }, + { + "epoch": 3.0, + "learning_rate": 3.0421555845284664e-08, + "loss": 0.1413, + "step": 36760 + }, + { + "epoch": 3.0, + "learning_rate": 2.987831377661886e-08, + "loss": 0.2942, + "step": 36761 + }, + { + "epoch": 3.0, + "learning_rate": 2.9335071707953066e-08, + "loss": 0.4345, + "step": 36762 + }, + { + "epoch": 3.0, + "learning_rate": 2.8791829639287267e-08, + "loss": 0.1586, + "step": 36763 + }, + { + "epoch": 3.0, + "learning_rate": 2.824858757062147e-08, + "loss": 0.1295, + "step": 36764 + }, + { + "epoch": 3.0, + "learning_rate": 2.7705345501955675e-08, + "loss": 0.0929, + "step": 36765 + }, + { + "epoch": 3.0, + "learning_rate": 2.7162103433289876e-08, + "loss": 0.2326, + "step": 36766 + }, + { + "epoch": 3.0, + "learning_rate": 2.661886136462408e-08, + "loss": 0.4836, + "step": 36767 + }, + { + "epoch": 3.0, + "learning_rate": 2.607561929595828e-08, + "loss": 0.1253, + "step": 36768 + }, + { + "epoch": 3.0, + "learning_rate": 2.5532377227292485e-08, + "loss": 0.2885, + "step": 36769 + }, + { + "epoch": 3.0, + "learning_rate": 2.4989135158626685e-08, + "loss": 0.4798, + "step": 36770 + }, + { + "epoch": 3.0, + "learning_rate": 2.444589308996089e-08, + "loss": 0.3357, + "step": 36771 + }, + { + "epoch": 3.0, + "learning_rate": 2.390265102129509e-08, + "loss": 0.1632, + "step": 36772 + }, + { + "epoch": 3.0, + "learning_rate": 2.3359408952629294e-08, + "loss": 0.1896, + "step": 36773 + }, + { + "epoch": 3.0, + "learning_rate": 2.2816166883963495e-08, + "loss": 0.3192, + "step": 36774 + }, + { + "epoch": 3.0, + "learning_rate": 2.22729248152977e-08, + "loss": 0.1565, + "step": 36775 + }, + { + "epoch": 3.0, + "learning_rate": 2.17296827466319e-08, + "loss": 0.4548, + "step": 36776 + }, + { + "epoch": 3.0, + "learning_rate": 2.1186440677966104e-08, + "loss": 0.2392, + "step": 36777 + }, + { + "epoch": 3.0, + "learning_rate": 2.0643198609300308e-08, + "loss": 0.2607, + "step": 36778 + }, + { + "epoch": 3.0, + "learning_rate": 2.009995654063451e-08, + "loss": 0.1914, + "step": 36779 + }, + { + "epoch": 3.0, + "learning_rate": 1.9556714471968713e-08, + "loss": 0.499, + "step": 36780 + }, + { + "epoch": 3.0, + "learning_rate": 1.9013472403302914e-08, + "loss": 0.2096, + "step": 36781 + }, + { + "epoch": 3.0, + "learning_rate": 1.8470230334637114e-08, + "loss": 0.2538, + "step": 36782 + }, + { + "epoch": 3.0, + "learning_rate": 1.792698826597132e-08, + "loss": 0.3097, + "step": 36783 + }, + { + "epoch": 3.0, + "learning_rate": 1.7383746197305523e-08, + "loss": 0.2944, + "step": 36784 + }, + { + "epoch": 3.0, + "learning_rate": 1.6840504128639723e-08, + "loss": 0.3971, + "step": 36785 + }, + { + "epoch": 3.0, + "learning_rate": 1.6297262059973927e-08, + "loss": 0.2735, + "step": 36786 + }, + { + "epoch": 3.0, + "learning_rate": 1.5754019991308128e-08, + "loss": 0.2229, + "step": 36787 + }, + { + "epoch": 3.0, + "learning_rate": 1.5210777922642332e-08, + "loss": 0.2049, + "step": 36788 + }, + { + "epoch": 3.0, + "learning_rate": 1.4667535853976533e-08, + "loss": 0.2773, + "step": 36789 + }, + { + "epoch": 3.0, + "learning_rate": 1.4124293785310735e-08, + "loss": 0.1366, + "step": 36790 + }, + { + "epoch": 3.0, + "learning_rate": 1.3581051716644938e-08, + "loss": 0.1517, + "step": 36791 + }, + { + "epoch": 3.0, + "learning_rate": 1.303780964797914e-08, + "loss": 0.187, + "step": 36792 + }, + { + "epoch": 3.0, + "learning_rate": 1.2494567579313343e-08, + "loss": 0.3836, + "step": 36793 + }, + { + "epoch": 3.0, + "learning_rate": 1.1951325510647545e-08, + "loss": 0.4619, + "step": 36794 + }, + { + "epoch": 3.0, + "learning_rate": 1.1408083441981748e-08, + "loss": 0.168, + "step": 36795 + }, + { + "epoch": 3.0, + "learning_rate": 1.086484137331595e-08, + "loss": 0.2978, + "step": 36796 + }, + { + "epoch": 3.0, + "learning_rate": 1.0321599304650154e-08, + "loss": 0.0996, + "step": 36797 + }, + { + "epoch": 3.0, + "learning_rate": 9.778357235984356e-09, + "loss": 0.5221, + "step": 36798 + }, + { + "epoch": 3.0, + "learning_rate": 9.235115167318557e-09, + "loss": 0.1182, + "step": 36799 + }, + { + "epoch": 3.0, + "learning_rate": 8.691873098652761e-09, + "loss": 0.1842, + "step": 36800 + }, + { + "epoch": 3.0, + "learning_rate": 8.148631029986964e-09, + "loss": 0.332, + "step": 36801 + }, + { + "epoch": 3.0, + "learning_rate": 7.605388961321166e-09, + "loss": 0.115, + "step": 36802 + }, + { + "epoch": 3.0, + "learning_rate": 7.062146892655368e-09, + "loss": 0.1364, + "step": 36803 + }, + { + "epoch": 3.0, + "learning_rate": 6.51890482398957e-09, + "loss": 0.4564, + "step": 36804 + }, + { + "epoch": 3.0, + "learning_rate": 5.9756627553237725e-09, + "loss": 0.2627, + "step": 36805 + }, + { + "epoch": 3.0, + "learning_rate": 5.432420686657975e-09, + "loss": 0.3573, + "step": 36806 + }, + { + "epoch": 3.0, + "learning_rate": 4.889178617992178e-09, + "loss": 0.1261, + "step": 36807 + }, + { + "epoch": 3.0, + "learning_rate": 4.345936549326381e-09, + "loss": 0.3066, + "step": 36808 + }, + { + "epoch": 3.0, + "learning_rate": 3.802694480660583e-09, + "loss": 0.1267, + "step": 36809 + }, + { + "epoch": 3.0, + "learning_rate": 3.259452411994785e-09, + "loss": 0.237, + "step": 36810 + }, + { + "epoch": 3.0, + "learning_rate": 2.7162103433289875e-09, + "loss": 0.3313, + "step": 36811 + }, + { + "epoch": 3.0, + "learning_rate": 2.1729682746631903e-09, + "loss": 0.1673, + "step": 36812 + }, + { + "epoch": 3.0, + "learning_rate": 1.6297262059973925e-09, + "loss": 0.5028, + "step": 36813 + }, + { + "epoch": 3.0, + "learning_rate": 1.0864841373315952e-09, + "loss": 0.1342, + "step": 36814 + }, + { + "epoch": 3.0, + "learning_rate": 5.432420686657976e-10, + "loss": 0.063, + "step": 36815 + }, + { + "epoch": 3.0, + "learning_rate": 0.0, + "loss": 0.3387, + "step": 36816 + }, + { + "epoch": 3.0, + "step": 36816, + "total_flos": 7.74938740264658e+16, + "train_loss": 0.3605867331176782, + "train_runtime": 11742.5051, + "train_samples_per_second": 100.328, + "train_steps_per_second": 3.135 + } + ], + "max_steps": 36816, + "num_train_epochs": 3, + "total_flos": 7.74938740264658e+16, + "trial_name": null, + "trial_params": null +}