{ "best_metric": null, "best_model_checkpoint": null, "epoch": 10.0, "global_step": 1730, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 2.890173410404624e-07, "loss": 3.8145, "step": 1 }, { "epoch": 0.01, "learning_rate": 5.780346820809248e-07, "loss": 3.7852, "step": 2 }, { "epoch": 0.02, "learning_rate": 8.670520231213873e-07, "loss": 3.8008, "step": 3 }, { "epoch": 0.02, "learning_rate": 1.1560693641618497e-06, "loss": 3.7793, "step": 4 }, { "epoch": 0.03, "learning_rate": 1.4450867052023122e-06, "loss": 3.8008, "step": 5 }, { "epoch": 0.03, "learning_rate": 1.7341040462427746e-06, "loss": 3.7832, "step": 6 }, { "epoch": 0.04, "learning_rate": 2.023121387283237e-06, "loss": 3.832, "step": 7 }, { "epoch": 0.05, "learning_rate": 2.3121387283236993e-06, "loss": 3.7871, "step": 8 }, { "epoch": 0.05, "learning_rate": 2.601156069364162e-06, "loss": 3.8164, "step": 9 }, { "epoch": 0.06, "learning_rate": 2.8901734104046244e-06, "loss": 3.8027, "step": 10 }, { "epoch": 0.06, "learning_rate": 3.1791907514450866e-06, "loss": 3.7695, "step": 11 }, { "epoch": 0.07, "learning_rate": 3.468208092485549e-06, "loss": 3.8301, "step": 12 }, { "epoch": 0.08, "learning_rate": 3.757225433526012e-06, "loss": 3.8301, "step": 13 }, { "epoch": 0.08, "learning_rate": 4.046242774566474e-06, "loss": 3.8066, "step": 14 }, { "epoch": 0.09, "learning_rate": 4.3352601156069365e-06, "loss": 3.7871, "step": 15 }, { "epoch": 0.09, "learning_rate": 4.624277456647399e-06, "loss": 3.7988, "step": 16 }, { "epoch": 0.1, "learning_rate": 4.913294797687862e-06, "loss": 3.8184, "step": 17 }, { "epoch": 0.1, "learning_rate": 5.202312138728324e-06, "loss": 3.793, "step": 18 }, { "epoch": 0.11, "learning_rate": 5.491329479768787e-06, "loss": 3.8008, "step": 19 }, { "epoch": 0.12, "learning_rate": 5.780346820809249e-06, "loss": 3.7988, "step": 20 }, { "epoch": 0.12, "learning_rate": 6.069364161849711e-06, "loss": 3.7754, "step": 21 }, { "epoch": 0.13, "learning_rate": 6.358381502890173e-06, "loss": 3.7793, "step": 22 }, { "epoch": 0.13, "learning_rate": 6.647398843930635e-06, "loss": 3.7871, "step": 23 }, { "epoch": 0.14, "learning_rate": 6.936416184971098e-06, "loss": 3.7812, "step": 24 }, { "epoch": 0.14, "learning_rate": 7.225433526011561e-06, "loss": 3.832, "step": 25 }, { "epoch": 0.15, "learning_rate": 7.514450867052024e-06, "loss": 3.7852, "step": 26 }, { "epoch": 0.16, "learning_rate": 7.803468208092486e-06, "loss": 3.8125, "step": 27 }, { "epoch": 0.16, "learning_rate": 8.092485549132949e-06, "loss": 3.8398, "step": 28 }, { "epoch": 0.17, "learning_rate": 8.38150289017341e-06, "loss": 3.791, "step": 29 }, { "epoch": 0.17, "learning_rate": 8.670520231213873e-06, "loss": 3.7734, "step": 30 }, { "epoch": 0.18, "learning_rate": 8.959537572254335e-06, "loss": 3.8105, "step": 31 }, { "epoch": 0.18, "learning_rate": 9.248554913294797e-06, "loss": 3.8574, "step": 32 }, { "epoch": 0.19, "learning_rate": 9.53757225433526e-06, "loss": 3.793, "step": 33 }, { "epoch": 0.2, "learning_rate": 9.826589595375723e-06, "loss": 3.7852, "step": 34 }, { "epoch": 0.2, "learning_rate": 1.0115606936416185e-05, "loss": 3.7988, "step": 35 }, { "epoch": 0.21, "learning_rate": 1.0404624277456647e-05, "loss": 3.8301, "step": 36 }, { "epoch": 0.21, "learning_rate": 1.0693641618497111e-05, "loss": 3.8105, "step": 37 }, { "epoch": 0.22, "learning_rate": 1.0982658959537573e-05, "loss": 3.7656, "step": 38 }, { "epoch": 0.23, "learning_rate": 1.1271676300578036e-05, "loss": 3.8262, "step": 39 }, { "epoch": 0.23, "learning_rate": 1.1560693641618498e-05, "loss": 3.8164, "step": 40 }, { "epoch": 0.24, "learning_rate": 1.184971098265896e-05, "loss": 3.7441, "step": 41 }, { "epoch": 0.24, "learning_rate": 1.2138728323699422e-05, "loss": 3.6875, "step": 42 }, { "epoch": 0.25, "learning_rate": 1.2427745664739884e-05, "loss": 3.6914, "step": 43 }, { "epoch": 0.25, "learning_rate": 1.2716763005780346e-05, "loss": 3.6641, "step": 44 }, { "epoch": 0.26, "learning_rate": 1.3005780346820809e-05, "loss": 3.8535, "step": 45 }, { "epoch": 0.27, "learning_rate": 1.329479768786127e-05, "loss": 3.6719, "step": 46 }, { "epoch": 0.27, "learning_rate": 1.3583815028901733e-05, "loss": 3.8555, "step": 47 }, { "epoch": 0.28, "learning_rate": 1.3872832369942197e-05, "loss": 3.8047, "step": 48 }, { "epoch": 0.28, "learning_rate": 1.416184971098266e-05, "loss": 3.7461, "step": 49 }, { "epoch": 0.29, "learning_rate": 1.4450867052023123e-05, "loss": 3.8848, "step": 50 }, { "epoch": 0.29, "learning_rate": 1.4739884393063585e-05, "loss": 3.707, "step": 51 }, { "epoch": 0.3, "learning_rate": 1.5028901734104049e-05, "loss": 3.8203, "step": 52 }, { "epoch": 0.31, "learning_rate": 1.531791907514451e-05, "loss": 3.6758, "step": 53 }, { "epoch": 0.31, "learning_rate": 1.5606936416184973e-05, "loss": 3.8066, "step": 54 }, { "epoch": 0.32, "learning_rate": 1.5895953757225435e-05, "loss": 3.8438, "step": 55 }, { "epoch": 0.32, "learning_rate": 1.6184971098265897e-05, "loss": 3.8008, "step": 56 }, { "epoch": 0.33, "learning_rate": 1.647398843930636e-05, "loss": 3.7988, "step": 57 }, { "epoch": 0.34, "learning_rate": 1.676300578034682e-05, "loss": 3.6484, "step": 58 }, { "epoch": 0.34, "learning_rate": 1.7052023121387284e-05, "loss": 3.7012, "step": 59 }, { "epoch": 0.35, "learning_rate": 1.7341040462427746e-05, "loss": 3.6719, "step": 60 }, { "epoch": 0.35, "learning_rate": 1.7630057803468208e-05, "loss": 3.7695, "step": 61 }, { "epoch": 0.36, "learning_rate": 1.791907514450867e-05, "loss": 3.7656, "step": 62 }, { "epoch": 0.36, "learning_rate": 1.8208092485549132e-05, "loss": 3.7539, "step": 63 }, { "epoch": 0.37, "learning_rate": 1.8497109826589594e-05, "loss": 3.7148, "step": 64 }, { "epoch": 0.38, "learning_rate": 1.8786127167630057e-05, "loss": 3.7559, "step": 65 }, { "epoch": 0.38, "learning_rate": 1.907514450867052e-05, "loss": 3.748, "step": 66 }, { "epoch": 0.39, "learning_rate": 1.936416184971098e-05, "loss": 3.832, "step": 67 }, { "epoch": 0.39, "learning_rate": 1.9653179190751446e-05, "loss": 3.8457, "step": 68 }, { "epoch": 0.4, "learning_rate": 1.994219653179191e-05, "loss": 3.7754, "step": 69 }, { "epoch": 0.4, "learning_rate": 2.023121387283237e-05, "loss": 3.6875, "step": 70 }, { "epoch": 0.41, "learning_rate": 2.0520231213872833e-05, "loss": 3.7578, "step": 71 }, { "epoch": 0.42, "learning_rate": 2.0809248554913295e-05, "loss": 3.6797, "step": 72 }, { "epoch": 0.42, "learning_rate": 2.1098265895953757e-05, "loss": 3.6953, "step": 73 }, { "epoch": 0.43, "learning_rate": 2.1387283236994223e-05, "loss": 3.6074, "step": 74 }, { "epoch": 0.43, "learning_rate": 2.1676300578034685e-05, "loss": 3.7793, "step": 75 }, { "epoch": 0.44, "learning_rate": 2.1965317919075147e-05, "loss": 3.8164, "step": 76 }, { "epoch": 0.45, "learning_rate": 2.225433526011561e-05, "loss": 3.7832, "step": 77 }, { "epoch": 0.45, "learning_rate": 2.254335260115607e-05, "loss": 3.7988, "step": 78 }, { "epoch": 0.46, "learning_rate": 2.2832369942196533e-05, "loss": 3.4785, "step": 79 }, { "epoch": 0.46, "learning_rate": 2.3121387283236996e-05, "loss": 3.6484, "step": 80 }, { "epoch": 0.47, "learning_rate": 2.3410404624277458e-05, "loss": 3.8516, "step": 81 }, { "epoch": 0.47, "learning_rate": 2.369942196531792e-05, "loss": 3.8262, "step": 82 }, { "epoch": 0.48, "learning_rate": 2.3988439306358382e-05, "loss": 3.7285, "step": 83 }, { "epoch": 0.49, "learning_rate": 2.4277456647398844e-05, "loss": 3.7773, "step": 84 }, { "epoch": 0.49, "learning_rate": 2.4566473988439306e-05, "loss": 3.5781, "step": 85 }, { "epoch": 0.5, "learning_rate": 2.485549132947977e-05, "loss": 3.7598, "step": 86 }, { "epoch": 0.5, "learning_rate": 2.5144508670520234e-05, "loss": 3.9316, "step": 87 }, { "epoch": 0.51, "learning_rate": 2.5433526011560693e-05, "loss": 3.5234, "step": 88 }, { "epoch": 0.51, "learning_rate": 2.5722543352601158e-05, "loss": 3.6504, "step": 89 }, { "epoch": 0.52, "learning_rate": 2.6011560693641617e-05, "loss": 3.7988, "step": 90 }, { "epoch": 0.53, "learning_rate": 2.6300578034682083e-05, "loss": 3.6309, "step": 91 }, { "epoch": 0.53, "learning_rate": 2.658959537572254e-05, "loss": 3.4141, "step": 92 }, { "epoch": 0.54, "learning_rate": 2.6878612716763007e-05, "loss": 3.8125, "step": 93 }, { "epoch": 0.54, "learning_rate": 2.7167630057803466e-05, "loss": 3.4297, "step": 94 }, { "epoch": 0.55, "learning_rate": 2.745664739884393e-05, "loss": 4.0391, "step": 95 }, { "epoch": 0.55, "learning_rate": 2.7745664739884393e-05, "loss": 3.7617, "step": 96 }, { "epoch": 0.56, "learning_rate": 2.8034682080924855e-05, "loss": 3.6523, "step": 97 }, { "epoch": 0.57, "learning_rate": 2.832369942196532e-05, "loss": 3.5996, "step": 98 }, { "epoch": 0.57, "learning_rate": 2.861271676300578e-05, "loss": 3.7695, "step": 99 }, { "epoch": 0.58, "learning_rate": 2.8901734104046245e-05, "loss": 3.6758, "step": 100 }, { "epoch": 0.58, "learning_rate": 2.9190751445086707e-05, "loss": 3.6582, "step": 101 }, { "epoch": 0.59, "learning_rate": 2.947976878612717e-05, "loss": 3.7969, "step": 102 }, { "epoch": 0.6, "learning_rate": 2.9768786127167632e-05, "loss": 3.7559, "step": 103 }, { "epoch": 0.6, "learning_rate": 3.0057803468208097e-05, "loss": 3.5879, "step": 104 }, { "epoch": 0.61, "learning_rate": 3.0346820809248556e-05, "loss": 3.7832, "step": 105 }, { "epoch": 0.61, "learning_rate": 3.063583815028902e-05, "loss": 3.6191, "step": 106 }, { "epoch": 0.62, "learning_rate": 3.092485549132948e-05, "loss": 3.6992, "step": 107 }, { "epoch": 0.62, "learning_rate": 3.1213872832369946e-05, "loss": 3.625, "step": 108 }, { "epoch": 0.63, "learning_rate": 3.1502890173410405e-05, "loss": 3.7461, "step": 109 }, { "epoch": 0.64, "learning_rate": 3.179190751445087e-05, "loss": 3.7793, "step": 110 }, { "epoch": 0.64, "learning_rate": 3.208092485549133e-05, "loss": 3.8594, "step": 111 }, { "epoch": 0.65, "learning_rate": 3.2369942196531794e-05, "loss": 3.7559, "step": 112 }, { "epoch": 0.65, "learning_rate": 3.265895953757225e-05, "loss": 3.6875, "step": 113 }, { "epoch": 0.66, "learning_rate": 3.294797687861272e-05, "loss": 3.791, "step": 114 }, { "epoch": 0.66, "learning_rate": 3.323699421965318e-05, "loss": 3.6172, "step": 115 }, { "epoch": 0.67, "learning_rate": 3.352601156069364e-05, "loss": 3.5801, "step": 116 }, { "epoch": 0.68, "learning_rate": 3.381502890173411e-05, "loss": 3.6484, "step": 117 }, { "epoch": 0.68, "learning_rate": 3.410404624277457e-05, "loss": 3.5664, "step": 118 }, { "epoch": 0.69, "learning_rate": 3.439306358381503e-05, "loss": 3.5938, "step": 119 }, { "epoch": 0.69, "learning_rate": 3.468208092485549e-05, "loss": 3.6289, "step": 120 }, { "epoch": 0.7, "learning_rate": 3.497109826589596e-05, "loss": 3.8945, "step": 121 }, { "epoch": 0.71, "learning_rate": 3.5260115606936416e-05, "loss": 3.7188, "step": 122 }, { "epoch": 0.71, "learning_rate": 3.554913294797688e-05, "loss": 3.2852, "step": 123 }, { "epoch": 0.72, "learning_rate": 3.583815028901734e-05, "loss": 3.7109, "step": 124 }, { "epoch": 0.72, "learning_rate": 3.6127167630057806e-05, "loss": 3.791, "step": 125 }, { "epoch": 0.73, "learning_rate": 3.6416184971098265e-05, "loss": 3.4883, "step": 126 }, { "epoch": 0.73, "learning_rate": 3.670520231213873e-05, "loss": 3.8301, "step": 127 }, { "epoch": 0.74, "learning_rate": 3.699421965317919e-05, "loss": 3.6797, "step": 128 }, { "epoch": 0.75, "learning_rate": 3.7283236994219654e-05, "loss": 4.0547, "step": 129 }, { "epoch": 0.75, "learning_rate": 3.757225433526011e-05, "loss": 3.5664, "step": 130 }, { "epoch": 0.76, "learning_rate": 3.786127167630058e-05, "loss": 3.3965, "step": 131 }, { "epoch": 0.76, "learning_rate": 3.815028901734104e-05, "loss": 3.5488, "step": 132 }, { "epoch": 0.77, "learning_rate": 3.84393063583815e-05, "loss": 3.6367, "step": 133 }, { "epoch": 0.77, "learning_rate": 3.872832369942196e-05, "loss": 3.5117, "step": 134 }, { "epoch": 0.78, "learning_rate": 3.901734104046243e-05, "loss": 3.4551, "step": 135 }, { "epoch": 0.79, "learning_rate": 3.930635838150289e-05, "loss": 3.7344, "step": 136 }, { "epoch": 0.79, "learning_rate": 3.959537572254335e-05, "loss": 3.5859, "step": 137 }, { "epoch": 0.8, "learning_rate": 3.988439306358382e-05, "loss": 3.4102, "step": 138 }, { "epoch": 0.8, "learning_rate": 4.0173410404624276e-05, "loss": 3.9043, "step": 139 }, { "epoch": 0.81, "learning_rate": 4.046242774566474e-05, "loss": 3.6445, "step": 140 }, { "epoch": 0.82, "learning_rate": 4.07514450867052e-05, "loss": 3.3105, "step": 141 }, { "epoch": 0.82, "learning_rate": 4.1040462427745666e-05, "loss": 3.8223, "step": 142 }, { "epoch": 0.83, "learning_rate": 4.132947976878613e-05, "loss": 3.7578, "step": 143 }, { "epoch": 0.83, "learning_rate": 4.161849710982659e-05, "loss": 3.957, "step": 144 }, { "epoch": 0.84, "learning_rate": 4.1907514450867055e-05, "loss": 3.8027, "step": 145 }, { "epoch": 0.84, "learning_rate": 4.2196531791907514e-05, "loss": 3.4688, "step": 146 }, { "epoch": 0.85, "learning_rate": 4.248554913294798e-05, "loss": 3.3691, "step": 147 }, { "epoch": 0.86, "learning_rate": 4.2774566473988445e-05, "loss": 3.7266, "step": 148 }, { "epoch": 0.86, "learning_rate": 4.3063583815028904e-05, "loss": 3.5117, "step": 149 }, { "epoch": 0.87, "learning_rate": 4.335260115606937e-05, "loss": 3.7031, "step": 150 }, { "epoch": 0.87, "learning_rate": 4.364161849710983e-05, "loss": 3.6777, "step": 151 }, { "epoch": 0.88, "learning_rate": 4.3930635838150294e-05, "loss": 3.5352, "step": 152 }, { "epoch": 0.88, "learning_rate": 4.421965317919075e-05, "loss": 3.6387, "step": 153 }, { "epoch": 0.89, "learning_rate": 4.450867052023122e-05, "loss": 3.5117, "step": 154 }, { "epoch": 0.9, "learning_rate": 4.4797687861271684e-05, "loss": 3.5586, "step": 155 }, { "epoch": 0.9, "learning_rate": 4.508670520231214e-05, "loss": 3.6445, "step": 156 }, { "epoch": 0.91, "learning_rate": 4.537572254335261e-05, "loss": 3.7578, "step": 157 }, { "epoch": 0.91, "learning_rate": 4.566473988439307e-05, "loss": 3.4922, "step": 158 }, { "epoch": 0.92, "learning_rate": 4.595375722543353e-05, "loss": 3.1094, "step": 159 }, { "epoch": 0.92, "learning_rate": 4.624277456647399e-05, "loss": 3.3203, "step": 160 }, { "epoch": 0.93, "learning_rate": 4.653179190751446e-05, "loss": 3.5625, "step": 161 }, { "epoch": 0.94, "learning_rate": 4.6820809248554915e-05, "loss": 3.8477, "step": 162 }, { "epoch": 0.94, "learning_rate": 4.710982658959538e-05, "loss": 3.4609, "step": 163 }, { "epoch": 0.95, "learning_rate": 4.739884393063584e-05, "loss": 3.3984, "step": 164 }, { "epoch": 0.95, "learning_rate": 4.7687861271676305e-05, "loss": 3.291, "step": 165 }, { "epoch": 0.96, "learning_rate": 4.7976878612716764e-05, "loss": 3.4043, "step": 166 }, { "epoch": 0.97, "learning_rate": 4.826589595375723e-05, "loss": 3.2461, "step": 167 }, { "epoch": 0.97, "learning_rate": 4.855491329479769e-05, "loss": 3.3008, "step": 168 }, { "epoch": 0.98, "learning_rate": 4.8843930635838154e-05, "loss": 3.2188, "step": 169 }, { "epoch": 0.98, "learning_rate": 4.913294797687861e-05, "loss": 3.6191, "step": 170 }, { "epoch": 0.99, "learning_rate": 4.942196531791908e-05, "loss": 3.3047, "step": 171 }, { "epoch": 0.99, "learning_rate": 4.971098265895954e-05, "loss": 3.6602, "step": 172 }, { "epoch": 1.0, "learning_rate": 5e-05, "loss": 3.6875, "step": 173 }, { "epoch": 1.01, "learning_rate": 5.028901734104047e-05, "loss": 3.7637, "step": 174 }, { "epoch": 1.01, "learning_rate": 5.0578034682080933e-05, "loss": 3.3535, "step": 175 }, { "epoch": 1.02, "learning_rate": 5.0867052023121385e-05, "loss": 3.3828, "step": 176 }, { "epoch": 1.02, "learning_rate": 5.115606936416185e-05, "loss": 3.8594, "step": 177 }, { "epoch": 1.03, "learning_rate": 5.1445086705202317e-05, "loss": 3.2793, "step": 178 }, { "epoch": 1.03, "learning_rate": 5.173410404624278e-05, "loss": 2.8145, "step": 179 }, { "epoch": 1.04, "learning_rate": 5.2023121387283234e-05, "loss": 3.5508, "step": 180 }, { "epoch": 1.05, "learning_rate": 5.23121387283237e-05, "loss": 3.8457, "step": 181 }, { "epoch": 1.05, "learning_rate": 5.2601156069364165e-05, "loss": 3.291, "step": 182 }, { "epoch": 1.06, "learning_rate": 5.289017341040463e-05, "loss": 3.418, "step": 183 }, { "epoch": 1.06, "learning_rate": 5.317919075144508e-05, "loss": 3.3281, "step": 184 }, { "epoch": 1.07, "learning_rate": 5.346820809248555e-05, "loss": 3.1738, "step": 185 }, { "epoch": 1.08, "learning_rate": 5.3757225433526014e-05, "loss": 3.7246, "step": 186 }, { "epoch": 1.08, "learning_rate": 5.404624277456648e-05, "loss": 3.6602, "step": 187 }, { "epoch": 1.09, "learning_rate": 5.433526011560693e-05, "loss": 3.5723, "step": 188 }, { "epoch": 1.09, "learning_rate": 5.46242774566474e-05, "loss": 3.666, "step": 189 }, { "epoch": 1.1, "learning_rate": 5.491329479768786e-05, "loss": 3.6445, "step": 190 }, { "epoch": 1.1, "learning_rate": 5.520231213872833e-05, "loss": 3.2383, "step": 191 }, { "epoch": 1.11, "learning_rate": 5.5491329479768787e-05, "loss": 3.6875, "step": 192 }, { "epoch": 1.12, "learning_rate": 5.5780346820809245e-05, "loss": 3.7266, "step": 193 }, { "epoch": 1.12, "learning_rate": 5.606936416184971e-05, "loss": 3.4688, "step": 194 }, { "epoch": 1.13, "learning_rate": 5.6358381502890176e-05, "loss": 3.5273, "step": 195 }, { "epoch": 1.13, "learning_rate": 5.664739884393064e-05, "loss": 3.7109, "step": 196 }, { "epoch": 1.14, "learning_rate": 5.69364161849711e-05, "loss": 3.2871, "step": 197 }, { "epoch": 1.14, "learning_rate": 5.722543352601156e-05, "loss": 3.4297, "step": 198 }, { "epoch": 1.15, "learning_rate": 5.7514450867052025e-05, "loss": 3.3496, "step": 199 }, { "epoch": 1.16, "learning_rate": 5.780346820809249e-05, "loss": 3.2344, "step": 200 }, { "epoch": 1.16, "learning_rate": 5.809248554913295e-05, "loss": 2.9121, "step": 201 }, { "epoch": 1.17, "learning_rate": 5.8381502890173415e-05, "loss": 3.9609, "step": 202 }, { "epoch": 1.17, "learning_rate": 5.8670520231213874e-05, "loss": 3.6348, "step": 203 }, { "epoch": 1.18, "learning_rate": 5.895953757225434e-05, "loss": 3.5859, "step": 204 }, { "epoch": 1.18, "learning_rate": 5.92485549132948e-05, "loss": 2.9785, "step": 205 }, { "epoch": 1.19, "learning_rate": 5.9537572254335263e-05, "loss": 3.4844, "step": 206 }, { "epoch": 1.2, "learning_rate": 5.982658959537573e-05, "loss": 3.166, "step": 207 }, { "epoch": 1.2, "learning_rate": 6.0115606936416195e-05, "loss": 3.3711, "step": 208 }, { "epoch": 1.21, "learning_rate": 6.0404624277456646e-05, "loss": 2.8223, "step": 209 }, { "epoch": 1.21, "learning_rate": 6.069364161849711e-05, "loss": 4.2969, "step": 210 }, { "epoch": 1.22, "learning_rate": 6.098265895953758e-05, "loss": 3.0547, "step": 211 }, { "epoch": 1.23, "learning_rate": 6.127167630057804e-05, "loss": 3.5566, "step": 212 }, { "epoch": 1.23, "learning_rate": 6.156069364161851e-05, "loss": 3.8164, "step": 213 }, { "epoch": 1.24, "learning_rate": 6.184971098265896e-05, "loss": 3.5566, "step": 214 }, { "epoch": 1.24, "learning_rate": 6.213872832369943e-05, "loss": 2.6309, "step": 215 }, { "epoch": 1.25, "learning_rate": 6.242774566473989e-05, "loss": 3.291, "step": 216 }, { "epoch": 1.25, "learning_rate": 6.271676300578036e-05, "loss": 3.4062, "step": 217 }, { "epoch": 1.26, "learning_rate": 6.300578034682081e-05, "loss": 3.7715, "step": 218 }, { "epoch": 1.27, "learning_rate": 6.329479768786127e-05, "loss": 2.6523, "step": 219 }, { "epoch": 1.27, "learning_rate": 6.358381502890174e-05, "loss": 3.3418, "step": 220 }, { "epoch": 1.28, "learning_rate": 6.38728323699422e-05, "loss": 3.0469, "step": 221 }, { "epoch": 1.28, "learning_rate": 6.416184971098266e-05, "loss": 3.5352, "step": 222 }, { "epoch": 1.29, "learning_rate": 6.445086705202312e-05, "loss": 2.959, "step": 223 }, { "epoch": 1.29, "learning_rate": 6.473988439306359e-05, "loss": 2.5117, "step": 224 }, { "epoch": 1.3, "learning_rate": 6.502890173410405e-05, "loss": 2.832, "step": 225 }, { "epoch": 1.31, "learning_rate": 6.53179190751445e-05, "loss": 2.9121, "step": 226 }, { "epoch": 1.31, "learning_rate": 6.560693641618497e-05, "loss": 3.4961, "step": 227 }, { "epoch": 1.32, "learning_rate": 6.589595375722544e-05, "loss": 3.3203, "step": 228 }, { "epoch": 1.32, "learning_rate": 6.61849710982659e-05, "loss": 3.1758, "step": 229 }, { "epoch": 1.33, "learning_rate": 6.647398843930635e-05, "loss": 3.0273, "step": 230 }, { "epoch": 1.34, "learning_rate": 6.676300578034682e-05, "loss": 2.543, "step": 231 }, { "epoch": 1.34, "learning_rate": 6.705202312138729e-05, "loss": 2.9844, "step": 232 }, { "epoch": 1.35, "learning_rate": 6.734104046242775e-05, "loss": 3.0137, "step": 233 }, { "epoch": 1.35, "learning_rate": 6.763005780346822e-05, "loss": 2.709, "step": 234 }, { "epoch": 1.36, "learning_rate": 6.791907514450867e-05, "loss": 3.4805, "step": 235 }, { "epoch": 1.36, "learning_rate": 6.820809248554913e-05, "loss": 3.8672, "step": 236 }, { "epoch": 1.37, "learning_rate": 6.84971098265896e-05, "loss": 3.3477, "step": 237 }, { "epoch": 1.38, "learning_rate": 6.878612716763007e-05, "loss": 3.0762, "step": 238 }, { "epoch": 1.38, "learning_rate": 6.907514450867052e-05, "loss": 2.5781, "step": 239 }, { "epoch": 1.39, "learning_rate": 6.936416184971098e-05, "loss": 3.6328, "step": 240 }, { "epoch": 1.39, "learning_rate": 6.965317919075145e-05, "loss": 3.2188, "step": 241 }, { "epoch": 1.4, "learning_rate": 6.994219653179191e-05, "loss": 3.6328, "step": 242 }, { "epoch": 1.4, "learning_rate": 7.023121387283237e-05, "loss": 3.4766, "step": 243 }, { "epoch": 1.41, "learning_rate": 7.052023121387283e-05, "loss": 3.373, "step": 244 }, { "epoch": 1.42, "learning_rate": 7.08092485549133e-05, "loss": 3.0312, "step": 245 }, { "epoch": 1.42, "learning_rate": 7.109826589595376e-05, "loss": 4.2695, "step": 246 }, { "epoch": 1.43, "learning_rate": 7.138728323699421e-05, "loss": 3.0273, "step": 247 }, { "epoch": 1.43, "learning_rate": 7.167630057803468e-05, "loss": 3.709, "step": 248 }, { "epoch": 1.44, "learning_rate": 7.196531791907515e-05, "loss": 3.1328, "step": 249 }, { "epoch": 1.45, "learning_rate": 7.225433526011561e-05, "loss": 3.3145, "step": 250 }, { "epoch": 1.45, "learning_rate": 7.254335260115608e-05, "loss": 3.4922, "step": 251 }, { "epoch": 1.46, "learning_rate": 7.283236994219653e-05, "loss": 3.0547, "step": 252 }, { "epoch": 1.46, "learning_rate": 7.3121387283237e-05, "loss": 2.0879, "step": 253 }, { "epoch": 1.47, "learning_rate": 7.341040462427746e-05, "loss": 3.2148, "step": 254 }, { "epoch": 1.47, "learning_rate": 7.369942196531793e-05, "loss": 3.3164, "step": 255 }, { "epoch": 1.48, "learning_rate": 7.398843930635838e-05, "loss": 3.291, "step": 256 }, { "epoch": 1.49, "learning_rate": 7.427745664739884e-05, "loss": 3.2148, "step": 257 }, { "epoch": 1.49, "learning_rate": 7.456647398843931e-05, "loss": 2.6348, "step": 258 }, { "epoch": 1.5, "learning_rate": 7.485549132947977e-05, "loss": 3.3555, "step": 259 }, { "epoch": 1.5, "learning_rate": 7.514450867052023e-05, "loss": 3.2227, "step": 260 }, { "epoch": 1.51, "learning_rate": 7.543352601156069e-05, "loss": 3.1035, "step": 261 }, { "epoch": 1.51, "learning_rate": 7.572254335260116e-05, "loss": 3.6172, "step": 262 }, { "epoch": 1.52, "learning_rate": 7.601156069364162e-05, "loss": 3.207, "step": 263 }, { "epoch": 1.53, "learning_rate": 7.630057803468207e-05, "loss": 3.0391, "step": 264 }, { "epoch": 1.53, "learning_rate": 7.658959537572254e-05, "loss": 3.1328, "step": 265 }, { "epoch": 1.54, "learning_rate": 7.6878612716763e-05, "loss": 2.3301, "step": 266 }, { "epoch": 1.54, "learning_rate": 7.716763005780347e-05, "loss": 4.0, "step": 267 }, { "epoch": 1.55, "learning_rate": 7.745664739884392e-05, "loss": 2.5586, "step": 268 }, { "epoch": 1.55, "learning_rate": 7.774566473988439e-05, "loss": 2.7559, "step": 269 }, { "epoch": 1.56, "learning_rate": 7.803468208092485e-05, "loss": 3.0293, "step": 270 }, { "epoch": 1.57, "learning_rate": 7.832369942196532e-05, "loss": 3.459, "step": 271 }, { "epoch": 1.57, "learning_rate": 7.861271676300579e-05, "loss": 2.1367, "step": 272 }, { "epoch": 1.58, "learning_rate": 7.890173410404624e-05, "loss": 2.9531, "step": 273 }, { "epoch": 1.58, "learning_rate": 7.91907514450867e-05, "loss": 3.207, "step": 274 }, { "epoch": 1.59, "learning_rate": 7.947976878612717e-05, "loss": 2.8477, "step": 275 }, { "epoch": 1.6, "learning_rate": 7.976878612716763e-05, "loss": 3.0352, "step": 276 }, { "epoch": 1.6, "learning_rate": 8.005780346820809e-05, "loss": 3.2246, "step": 277 }, { "epoch": 1.61, "learning_rate": 8.034682080924855e-05, "loss": 2.8008, "step": 278 }, { "epoch": 1.61, "learning_rate": 8.063583815028902e-05, "loss": 3.0918, "step": 279 }, { "epoch": 1.62, "learning_rate": 8.092485549132948e-05, "loss": 2.8828, "step": 280 }, { "epoch": 1.62, "learning_rate": 8.121387283236995e-05, "loss": 3.0664, "step": 281 }, { "epoch": 1.63, "learning_rate": 8.15028901734104e-05, "loss": 3.0762, "step": 282 }, { "epoch": 1.64, "learning_rate": 8.179190751445087e-05, "loss": 2.3008, "step": 283 }, { "epoch": 1.64, "learning_rate": 8.208092485549133e-05, "loss": 3.5859, "step": 284 }, { "epoch": 1.65, "learning_rate": 8.23699421965318e-05, "loss": 2.4805, "step": 285 }, { "epoch": 1.65, "learning_rate": 8.265895953757226e-05, "loss": 2.6543, "step": 286 }, { "epoch": 1.66, "learning_rate": 8.294797687861271e-05, "loss": 2.9824, "step": 287 }, { "epoch": 1.66, "learning_rate": 8.323699421965318e-05, "loss": 2.1426, "step": 288 }, { "epoch": 1.67, "learning_rate": 8.352601156069365e-05, "loss": 3.3086, "step": 289 }, { "epoch": 1.68, "learning_rate": 8.381502890173411e-05, "loss": 2.4414, "step": 290 }, { "epoch": 1.68, "learning_rate": 8.410404624277458e-05, "loss": 2.3789, "step": 291 }, { "epoch": 1.69, "learning_rate": 8.439306358381503e-05, "loss": 2.6992, "step": 292 }, { "epoch": 1.69, "learning_rate": 8.46820809248555e-05, "loss": 1.8965, "step": 293 }, { "epoch": 1.7, "learning_rate": 8.497109826589596e-05, "loss": 3.5527, "step": 294 }, { "epoch": 1.71, "learning_rate": 8.526011560693643e-05, "loss": 2.875, "step": 295 }, { "epoch": 1.71, "learning_rate": 8.554913294797689e-05, "loss": 2.1914, "step": 296 }, { "epoch": 1.72, "learning_rate": 8.583815028901736e-05, "loss": 2.4492, "step": 297 }, { "epoch": 1.72, "learning_rate": 8.612716763005781e-05, "loss": 2.7461, "step": 298 }, { "epoch": 1.73, "learning_rate": 8.641618497109827e-05, "loss": 2.3281, "step": 299 }, { "epoch": 1.73, "learning_rate": 8.670520231213874e-05, "loss": 2.8887, "step": 300 }, { "epoch": 1.74, "learning_rate": 8.69942196531792e-05, "loss": 2.625, "step": 301 }, { "epoch": 1.75, "learning_rate": 8.728323699421966e-05, "loss": 2.7031, "step": 302 }, { "epoch": 1.75, "learning_rate": 8.757225433526012e-05, "loss": 1.4668, "step": 303 }, { "epoch": 1.76, "learning_rate": 8.786127167630059e-05, "loss": 2.6074, "step": 304 }, { "epoch": 1.76, "learning_rate": 8.815028901734105e-05, "loss": 2.1035, "step": 305 }, { "epoch": 1.77, "learning_rate": 8.84393063583815e-05, "loss": 2.3281, "step": 306 }, { "epoch": 1.77, "learning_rate": 8.872832369942197e-05, "loss": 3.4531, "step": 307 }, { "epoch": 1.78, "learning_rate": 8.901734104046244e-05, "loss": 2.1699, "step": 308 }, { "epoch": 1.79, "learning_rate": 8.93063583815029e-05, "loss": 2.5996, "step": 309 }, { "epoch": 1.79, "learning_rate": 8.959537572254337e-05, "loss": 2.3086, "step": 310 }, { "epoch": 1.8, "learning_rate": 8.988439306358382e-05, "loss": 3.748, "step": 311 }, { "epoch": 1.8, "learning_rate": 9.017341040462428e-05, "loss": 2.9141, "step": 312 }, { "epoch": 1.81, "learning_rate": 9.046242774566475e-05, "loss": 2.7031, "step": 313 }, { "epoch": 1.82, "learning_rate": 9.075144508670522e-05, "loss": 2.082, "step": 314 }, { "epoch": 1.82, "learning_rate": 9.104046242774567e-05, "loss": 3.7324, "step": 315 }, { "epoch": 1.83, "learning_rate": 9.132947976878613e-05, "loss": 2.4766, "step": 316 }, { "epoch": 1.83, "learning_rate": 9.16184971098266e-05, "loss": 2.7109, "step": 317 }, { "epoch": 1.84, "learning_rate": 9.190751445086706e-05, "loss": 2.834, "step": 318 }, { "epoch": 1.84, "learning_rate": 9.219653179190752e-05, "loss": 3.127, "step": 319 }, { "epoch": 1.85, "learning_rate": 9.248554913294798e-05, "loss": 2.293, "step": 320 }, { "epoch": 1.86, "learning_rate": 9.277456647398845e-05, "loss": 2.6465, "step": 321 }, { "epoch": 1.86, "learning_rate": 9.306358381502891e-05, "loss": 2.166, "step": 322 }, { "epoch": 1.87, "learning_rate": 9.335260115606937e-05, "loss": 1.9834, "step": 323 }, { "epoch": 1.87, "learning_rate": 9.364161849710983e-05, "loss": 3.2656, "step": 324 }, { "epoch": 1.88, "learning_rate": 9.39306358381503e-05, "loss": 2.5859, "step": 325 }, { "epoch": 1.88, "learning_rate": 9.421965317919076e-05, "loss": 2.5938, "step": 326 }, { "epoch": 1.89, "learning_rate": 9.450867052023123e-05, "loss": 2.2461, "step": 327 }, { "epoch": 1.9, "learning_rate": 9.479768786127168e-05, "loss": 2.6406, "step": 328 }, { "epoch": 1.9, "learning_rate": 9.508670520231214e-05, "loss": 2.9961, "step": 329 }, { "epoch": 1.91, "learning_rate": 9.537572254335261e-05, "loss": 2.541, "step": 330 }, { "epoch": 1.91, "learning_rate": 9.566473988439308e-05, "loss": 2.0059, "step": 331 }, { "epoch": 1.92, "learning_rate": 9.595375722543353e-05, "loss": 3.9473, "step": 332 }, { "epoch": 1.92, "learning_rate": 9.6242774566474e-05, "loss": 2.6875, "step": 333 }, { "epoch": 1.93, "learning_rate": 9.653179190751446e-05, "loss": 2.5527, "step": 334 }, { "epoch": 1.94, "learning_rate": 9.682080924855492e-05, "loss": 2.1738, "step": 335 }, { "epoch": 1.94, "learning_rate": 9.710982658959538e-05, "loss": 3.1914, "step": 336 }, { "epoch": 1.95, "learning_rate": 9.739884393063584e-05, "loss": 4.4922, "step": 337 }, { "epoch": 1.95, "learning_rate": 9.768786127167631e-05, "loss": 1.8311, "step": 338 }, { "epoch": 1.96, "learning_rate": 9.797687861271677e-05, "loss": 3.0078, "step": 339 }, { "epoch": 1.97, "learning_rate": 9.826589595375723e-05, "loss": 1.9141, "step": 340 }, { "epoch": 1.97, "learning_rate": 9.855491329479769e-05, "loss": 1.8818, "step": 341 }, { "epoch": 1.98, "learning_rate": 9.884393063583816e-05, "loss": 3.1504, "step": 342 }, { "epoch": 1.98, "learning_rate": 9.913294797687862e-05, "loss": 1.9385, "step": 343 }, { "epoch": 1.99, "learning_rate": 9.942196531791907e-05, "loss": 2.8203, "step": 344 }, { "epoch": 1.99, "learning_rate": 9.971098265895954e-05, "loss": 2.3594, "step": 345 }, { "epoch": 2.0, "learning_rate": 0.0001, "loss": 2.9375, "step": 346 }, { "epoch": 2.01, "learning_rate": 9.99277456647399e-05, "loss": 1.8301, "step": 347 }, { "epoch": 2.01, "learning_rate": 9.985549132947977e-05, "loss": 2.127, "step": 348 }, { "epoch": 2.02, "learning_rate": 9.978323699421965e-05, "loss": 2.0527, "step": 349 }, { "epoch": 2.02, "learning_rate": 9.971098265895954e-05, "loss": 1.7529, "step": 350 }, { "epoch": 2.03, "learning_rate": 9.963872832369943e-05, "loss": 1.9395, "step": 351 }, { "epoch": 2.03, "learning_rate": 9.95664739884393e-05, "loss": 2.873, "step": 352 }, { "epoch": 2.04, "learning_rate": 9.94942196531792e-05, "loss": 2.0312, "step": 353 }, { "epoch": 2.05, "learning_rate": 9.942196531791907e-05, "loss": 1.7881, "step": 354 }, { "epoch": 2.05, "learning_rate": 9.934971098265896e-05, "loss": 1.7637, "step": 355 }, { "epoch": 2.06, "learning_rate": 9.927745664739884e-05, "loss": 3.1562, "step": 356 }, { "epoch": 2.06, "learning_rate": 9.920520231213873e-05, "loss": 2.0059, "step": 357 }, { "epoch": 2.07, "learning_rate": 9.913294797687862e-05, "loss": 2.7695, "step": 358 }, { "epoch": 2.08, "learning_rate": 9.906069364161851e-05, "loss": 1.2988, "step": 359 }, { "epoch": 2.08, "learning_rate": 9.898843930635839e-05, "loss": 1.9062, "step": 360 }, { "epoch": 2.09, "learning_rate": 9.891618497109827e-05, "loss": 2.748, "step": 361 }, { "epoch": 2.09, "learning_rate": 9.884393063583816e-05, "loss": 1.0225, "step": 362 }, { "epoch": 2.1, "learning_rate": 9.877167630057805e-05, "loss": 2.0723, "step": 363 }, { "epoch": 2.1, "learning_rate": 9.869942196531792e-05, "loss": 2.6523, "step": 364 }, { "epoch": 2.11, "learning_rate": 9.86271676300578e-05, "loss": 2.5371, "step": 365 }, { "epoch": 2.12, "learning_rate": 9.855491329479769e-05, "loss": 1.8691, "step": 366 }, { "epoch": 2.12, "learning_rate": 9.848265895953758e-05, "loss": 2.0273, "step": 367 }, { "epoch": 2.13, "learning_rate": 9.841040462427746e-05, "loss": 1.7139, "step": 368 }, { "epoch": 2.13, "learning_rate": 9.833815028901735e-05, "loss": 2.4238, "step": 369 }, { "epoch": 2.14, "learning_rate": 9.826589595375723e-05, "loss": 1.499, "step": 370 }, { "epoch": 2.14, "learning_rate": 9.819364161849712e-05, "loss": 1.6475, "step": 371 }, { "epoch": 2.15, "learning_rate": 9.812138728323699e-05, "loss": 1.7852, "step": 372 }, { "epoch": 2.16, "learning_rate": 9.804913294797688e-05, "loss": 2.0703, "step": 373 }, { "epoch": 2.16, "learning_rate": 9.797687861271677e-05, "loss": 1.4629, "step": 374 }, { "epoch": 2.17, "learning_rate": 9.790462427745665e-05, "loss": 3.1895, "step": 375 }, { "epoch": 2.17, "learning_rate": 9.783236994219653e-05, "loss": 3.0273, "step": 376 }, { "epoch": 2.18, "learning_rate": 9.776011560693642e-05, "loss": 2.4062, "step": 377 }, { "epoch": 2.18, "learning_rate": 9.768786127167631e-05, "loss": 0.98, "step": 378 }, { "epoch": 2.19, "learning_rate": 9.76156069364162e-05, "loss": 1.3408, "step": 379 }, { "epoch": 2.2, "learning_rate": 9.754335260115607e-05, "loss": 2.043, "step": 380 }, { "epoch": 2.2, "learning_rate": 9.747109826589595e-05, "loss": 1.6006, "step": 381 }, { "epoch": 2.21, "learning_rate": 9.739884393063584e-05, "loss": 2.209, "step": 382 }, { "epoch": 2.21, "learning_rate": 9.732658959537573e-05, "loss": 3.5352, "step": 383 }, { "epoch": 2.22, "learning_rate": 9.725433526011561e-05, "loss": 1.4072, "step": 384 }, { "epoch": 2.23, "learning_rate": 9.71820809248555e-05, "loss": 2.2773, "step": 385 }, { "epoch": 2.23, "learning_rate": 9.710982658959538e-05, "loss": 1.9326, "step": 386 }, { "epoch": 2.24, "learning_rate": 9.703757225433527e-05, "loss": 1.8008, "step": 387 }, { "epoch": 2.24, "learning_rate": 9.696531791907514e-05, "loss": 2.6582, "step": 388 }, { "epoch": 2.25, "learning_rate": 9.689306358381503e-05, "loss": 2.9941, "step": 389 }, { "epoch": 2.25, "learning_rate": 9.682080924855492e-05, "loss": 2.1348, "step": 390 }, { "epoch": 2.26, "learning_rate": 9.67485549132948e-05, "loss": 1.9922, "step": 391 }, { "epoch": 2.27, "learning_rate": 9.667630057803468e-05, "loss": 1.8955, "step": 392 }, { "epoch": 2.27, "learning_rate": 9.660404624277457e-05, "loss": 3.209, "step": 393 }, { "epoch": 2.28, "learning_rate": 9.653179190751446e-05, "loss": 2.3867, "step": 394 }, { "epoch": 2.28, "learning_rate": 9.645953757225435e-05, "loss": 2.252, "step": 395 }, { "epoch": 2.29, "learning_rate": 9.638728323699421e-05, "loss": 1.5752, "step": 396 }, { "epoch": 2.29, "learning_rate": 9.63150289017341e-05, "loss": 2.6055, "step": 397 }, { "epoch": 2.3, "learning_rate": 9.6242774566474e-05, "loss": 2.1348, "step": 398 }, { "epoch": 2.31, "learning_rate": 9.617052023121388e-05, "loss": 2.4121, "step": 399 }, { "epoch": 2.31, "learning_rate": 9.609826589595376e-05, "loss": 3.168, "step": 400 }, { "epoch": 2.32, "learning_rate": 9.602601156069365e-05, "loss": 2.459, "step": 401 }, { "epoch": 2.32, "learning_rate": 9.595375722543353e-05, "loss": 2.0488, "step": 402 }, { "epoch": 2.33, "learning_rate": 9.588150289017342e-05, "loss": 1.5723, "step": 403 }, { "epoch": 2.34, "learning_rate": 9.58092485549133e-05, "loss": 0.7979, "step": 404 }, { "epoch": 2.34, "learning_rate": 9.573699421965319e-05, "loss": 2.0664, "step": 405 }, { "epoch": 2.35, "learning_rate": 9.566473988439308e-05, "loss": 2.8223, "step": 406 }, { "epoch": 2.35, "learning_rate": 9.559248554913295e-05, "loss": 2.0898, "step": 407 }, { "epoch": 2.36, "learning_rate": 9.552023121387283e-05, "loss": 2.709, "step": 408 }, { "epoch": 2.36, "learning_rate": 9.544797687861272e-05, "loss": 2.6562, "step": 409 }, { "epoch": 2.37, "learning_rate": 9.537572254335261e-05, "loss": 1.4248, "step": 410 }, { "epoch": 2.38, "learning_rate": 9.53034682080925e-05, "loss": 2.5039, "step": 411 }, { "epoch": 2.38, "learning_rate": 9.523121387283236e-05, "loss": 1.709, "step": 412 }, { "epoch": 2.39, "learning_rate": 9.515895953757225e-05, "loss": 1.4287, "step": 413 }, { "epoch": 2.39, "learning_rate": 9.508670520231214e-05, "loss": 1.5596, "step": 414 }, { "epoch": 2.4, "learning_rate": 9.501445086705204e-05, "loss": 3.4746, "step": 415 }, { "epoch": 2.4, "learning_rate": 9.494219653179191e-05, "loss": 2.2285, "step": 416 }, { "epoch": 2.41, "learning_rate": 9.486994219653179e-05, "loss": 1.7188, "step": 417 }, { "epoch": 2.42, "learning_rate": 9.479768786127168e-05, "loss": 3.0742, "step": 418 }, { "epoch": 2.42, "learning_rate": 9.472543352601157e-05, "loss": 1.6416, "step": 419 }, { "epoch": 2.43, "learning_rate": 9.465317919075145e-05, "loss": 2.2012, "step": 420 }, { "epoch": 2.43, "learning_rate": 9.458092485549134e-05, "loss": 2.1211, "step": 421 }, { "epoch": 2.44, "learning_rate": 9.450867052023123e-05, "loss": 1.4551, "step": 422 }, { "epoch": 2.45, "learning_rate": 9.44364161849711e-05, "loss": 2.6055, "step": 423 }, { "epoch": 2.45, "learning_rate": 9.436416184971098e-05, "loss": 1.0186, "step": 424 }, { "epoch": 2.46, "learning_rate": 9.429190751445087e-05, "loss": 2.0977, "step": 425 }, { "epoch": 2.46, "learning_rate": 9.421965317919076e-05, "loss": 1.7656, "step": 426 }, { "epoch": 2.47, "learning_rate": 9.414739884393064e-05, "loss": 3.1582, "step": 427 }, { "epoch": 2.47, "learning_rate": 9.407514450867052e-05, "loss": 0.9648, "step": 428 }, { "epoch": 2.48, "learning_rate": 9.40028901734104e-05, "loss": 2.6426, "step": 429 }, { "epoch": 2.49, "learning_rate": 9.39306358381503e-05, "loss": 2.1328, "step": 430 }, { "epoch": 2.49, "learning_rate": 9.385838150289019e-05, "loss": 1.8848, "step": 431 }, { "epoch": 2.5, "learning_rate": 9.378612716763006e-05, "loss": 2.1133, "step": 432 }, { "epoch": 2.5, "learning_rate": 9.371387283236994e-05, "loss": 2.0391, "step": 433 }, { "epoch": 2.51, "learning_rate": 9.364161849710983e-05, "loss": 1.4375, "step": 434 }, { "epoch": 2.51, "learning_rate": 9.356936416184972e-05, "loss": 1.7705, "step": 435 }, { "epoch": 2.52, "learning_rate": 9.34971098265896e-05, "loss": 1.7529, "step": 436 }, { "epoch": 2.53, "learning_rate": 9.342485549132949e-05, "loss": 2.875, "step": 437 }, { "epoch": 2.53, "learning_rate": 9.335260115606937e-05, "loss": 2.4785, "step": 438 }, { "epoch": 2.54, "learning_rate": 9.328034682080926e-05, "loss": 2.4375, "step": 439 }, { "epoch": 2.54, "learning_rate": 9.320809248554913e-05, "loss": 1.959, "step": 440 }, { "epoch": 2.55, "learning_rate": 9.313583815028902e-05, "loss": 2.4629, "step": 441 }, { "epoch": 2.55, "learning_rate": 9.306358381502891e-05, "loss": 2.1309, "step": 442 }, { "epoch": 2.56, "learning_rate": 9.299132947976879e-05, "loss": 1.25, "step": 443 }, { "epoch": 2.57, "learning_rate": 9.291907514450867e-05, "loss": 2.8906, "step": 444 }, { "epoch": 2.57, "learning_rate": 9.284682080924856e-05, "loss": 1.8184, "step": 445 }, { "epoch": 2.58, "learning_rate": 9.277456647398845e-05, "loss": 3.1348, "step": 446 }, { "epoch": 2.58, "learning_rate": 9.270231213872832e-05, "loss": 1.6465, "step": 447 }, { "epoch": 2.59, "learning_rate": 9.263005780346821e-05, "loss": 3.2148, "step": 448 }, { "epoch": 2.6, "learning_rate": 9.255780346820809e-05, "loss": 2.3438, "step": 449 }, { "epoch": 2.6, "learning_rate": 9.248554913294798e-05, "loss": 2.0488, "step": 450 }, { "epoch": 2.61, "learning_rate": 9.241329479768787e-05, "loss": 2.375, "step": 451 }, { "epoch": 2.61, "learning_rate": 9.234104046242775e-05, "loss": 2.9824, "step": 452 }, { "epoch": 2.62, "learning_rate": 9.226878612716764e-05, "loss": 2.0176, "step": 453 }, { "epoch": 2.62, "learning_rate": 9.219653179190752e-05, "loss": 0.6484, "step": 454 }, { "epoch": 2.63, "learning_rate": 9.212427745664741e-05, "loss": 1.8838, "step": 455 }, { "epoch": 2.64, "learning_rate": 9.205202312138728e-05, "loss": 1.4443, "step": 456 }, { "epoch": 2.64, "learning_rate": 9.197976878612717e-05, "loss": 2.127, "step": 457 }, { "epoch": 2.65, "learning_rate": 9.190751445086706e-05, "loss": 1.957, "step": 458 }, { "epoch": 2.65, "learning_rate": 9.183526011560694e-05, "loss": 2.3984, "step": 459 }, { "epoch": 2.66, "learning_rate": 9.176300578034682e-05, "loss": 1.1777, "step": 460 }, { "epoch": 2.66, "learning_rate": 9.169075144508671e-05, "loss": 1.5605, "step": 461 }, { "epoch": 2.67, "learning_rate": 9.16184971098266e-05, "loss": 1.6924, "step": 462 }, { "epoch": 2.68, "learning_rate": 9.154624277456648e-05, "loss": 1.915, "step": 463 }, { "epoch": 2.68, "learning_rate": 9.147398843930635e-05, "loss": 2.2949, "step": 464 }, { "epoch": 2.69, "learning_rate": 9.140173410404624e-05, "loss": 2.8555, "step": 465 }, { "epoch": 2.69, "learning_rate": 9.132947976878613e-05, "loss": 2.4082, "step": 466 }, { "epoch": 2.7, "learning_rate": 9.125722543352601e-05, "loss": 1.4141, "step": 467 }, { "epoch": 2.71, "learning_rate": 9.11849710982659e-05, "loss": 3.4844, "step": 468 }, { "epoch": 2.71, "learning_rate": 9.111271676300579e-05, "loss": 0.6567, "step": 469 }, { "epoch": 2.72, "learning_rate": 9.104046242774567e-05, "loss": 1.0703, "step": 470 }, { "epoch": 2.72, "learning_rate": 9.096820809248556e-05, "loss": 1.584, "step": 471 }, { "epoch": 2.73, "learning_rate": 9.089595375722544e-05, "loss": 1.6572, "step": 472 }, { "epoch": 2.73, "learning_rate": 9.082369942196533e-05, "loss": 2.7852, "step": 473 }, { "epoch": 2.74, "learning_rate": 9.075144508670522e-05, "loss": 1.6104, "step": 474 }, { "epoch": 2.75, "learning_rate": 9.067919075144509e-05, "loss": 1.7295, "step": 475 }, { "epoch": 2.75, "learning_rate": 9.060693641618497e-05, "loss": 1.2539, "step": 476 }, { "epoch": 2.76, "learning_rate": 9.053468208092486e-05, "loss": 2.0, "step": 477 }, { "epoch": 2.76, "learning_rate": 9.046242774566475e-05, "loss": 3.1328, "step": 478 }, { "epoch": 2.77, "learning_rate": 9.039017341040463e-05, "loss": 1.7354, "step": 479 }, { "epoch": 2.77, "learning_rate": 9.03179190751445e-05, "loss": 2.2734, "step": 480 }, { "epoch": 2.78, "learning_rate": 9.02456647398844e-05, "loss": 1.6748, "step": 481 }, { "epoch": 2.79, "learning_rate": 9.017341040462428e-05, "loss": 2.3848, "step": 482 }, { "epoch": 2.79, "learning_rate": 9.010115606936416e-05, "loss": 2.2539, "step": 483 }, { "epoch": 2.8, "learning_rate": 9.002890173410405e-05, "loss": 1.8789, "step": 484 }, { "epoch": 2.8, "learning_rate": 8.995664739884393e-05, "loss": 1.1904, "step": 485 }, { "epoch": 2.81, "learning_rate": 8.988439306358382e-05, "loss": 3.0625, "step": 486 }, { "epoch": 2.82, "learning_rate": 8.98121387283237e-05, "loss": 1.4922, "step": 487 }, { "epoch": 2.82, "learning_rate": 8.973988439306359e-05, "loss": 1.3135, "step": 488 }, { "epoch": 2.83, "learning_rate": 8.966763005780348e-05, "loss": 1.332, "step": 489 }, { "epoch": 2.83, "learning_rate": 8.959537572254337e-05, "loss": 1.8145, "step": 490 }, { "epoch": 2.84, "learning_rate": 8.952312138728323e-05, "loss": 2.957, "step": 491 }, { "epoch": 2.84, "learning_rate": 8.945086705202312e-05, "loss": 0.8486, "step": 492 }, { "epoch": 2.85, "learning_rate": 8.937861271676301e-05, "loss": 2.1836, "step": 493 }, { "epoch": 2.86, "learning_rate": 8.93063583815029e-05, "loss": 2.207, "step": 494 }, { "epoch": 2.86, "learning_rate": 8.923410404624278e-05, "loss": 1.2178, "step": 495 }, { "epoch": 2.87, "learning_rate": 8.916184971098266e-05, "loss": 2.7207, "step": 496 }, { "epoch": 2.87, "learning_rate": 8.908959537572255e-05, "loss": 2.2285, "step": 497 }, { "epoch": 2.88, "learning_rate": 8.901734104046244e-05, "loss": 1.5977, "step": 498 }, { "epoch": 2.88, "learning_rate": 8.894508670520231e-05, "loss": 1.0723, "step": 499 }, { "epoch": 2.89, "learning_rate": 8.88728323699422e-05, "loss": 2.0098, "step": 500 }, { "epoch": 2.9, "learning_rate": 8.880057803468208e-05, "loss": 3.8672, "step": 501 }, { "epoch": 2.9, "learning_rate": 8.872832369942197e-05, "loss": 1.8477, "step": 502 }, { "epoch": 2.91, "learning_rate": 8.865606936416185e-05, "loss": 1.9775, "step": 503 }, { "epoch": 2.91, "learning_rate": 8.858381502890174e-05, "loss": 2.502, "step": 504 }, { "epoch": 2.92, "learning_rate": 8.851156069364163e-05, "loss": 2.2969, "step": 505 }, { "epoch": 2.92, "learning_rate": 8.84393063583815e-05, "loss": 1.0859, "step": 506 }, { "epoch": 2.93, "learning_rate": 8.836705202312138e-05, "loss": 2.1113, "step": 507 }, { "epoch": 2.94, "learning_rate": 8.829479768786127e-05, "loss": 2.5781, "step": 508 }, { "epoch": 2.94, "learning_rate": 8.822254335260116e-05, "loss": 0.7017, "step": 509 }, { "epoch": 2.95, "learning_rate": 8.815028901734105e-05, "loss": 0.915, "step": 510 }, { "epoch": 2.95, "learning_rate": 8.807803468208093e-05, "loss": 2.8047, "step": 511 }, { "epoch": 2.96, "learning_rate": 8.800578034682081e-05, "loss": 1.0518, "step": 512 }, { "epoch": 2.97, "learning_rate": 8.79335260115607e-05, "loss": 2.2129, "step": 513 }, { "epoch": 2.97, "learning_rate": 8.786127167630059e-05, "loss": 1.6592, "step": 514 }, { "epoch": 2.98, "learning_rate": 8.778901734104046e-05, "loss": 0.7651, "step": 515 }, { "epoch": 2.98, "learning_rate": 8.771676300578036e-05, "loss": 1.3008, "step": 516 }, { "epoch": 2.99, "learning_rate": 8.764450867052023e-05, "loss": 1.8633, "step": 517 }, { "epoch": 2.99, "learning_rate": 8.757225433526012e-05, "loss": 1.1982, "step": 518 }, { "epoch": 3.0, "learning_rate": 8.75e-05, "loss": 1.5439, "step": 519 }, { "epoch": 3.01, "learning_rate": 8.742774566473989e-05, "loss": 2.0391, "step": 520 }, { "epoch": 3.01, "learning_rate": 8.735549132947978e-05, "loss": 0.2642, "step": 521 }, { "epoch": 3.02, "learning_rate": 8.728323699421966e-05, "loss": 1.2285, "step": 522 }, { "epoch": 3.02, "learning_rate": 8.721098265895953e-05, "loss": 0.647, "step": 523 }, { "epoch": 3.03, "learning_rate": 8.713872832369942e-05, "loss": 0.9629, "step": 524 }, { "epoch": 3.03, "learning_rate": 8.706647398843931e-05, "loss": 0.77, "step": 525 }, { "epoch": 3.04, "learning_rate": 8.69942196531792e-05, "loss": 0.8516, "step": 526 }, { "epoch": 3.05, "learning_rate": 8.692196531791907e-05, "loss": 3.4238, "step": 527 }, { "epoch": 3.05, "learning_rate": 8.684971098265896e-05, "loss": 1.3691, "step": 528 }, { "epoch": 3.06, "learning_rate": 8.677745664739885e-05, "loss": 0.771, "step": 529 }, { "epoch": 3.06, "learning_rate": 8.670520231213874e-05, "loss": 1.542, "step": 530 }, { "epoch": 3.07, "learning_rate": 8.663294797687862e-05, "loss": 1.8145, "step": 531 }, { "epoch": 3.08, "learning_rate": 8.65606936416185e-05, "loss": 2.127, "step": 532 }, { "epoch": 3.08, "learning_rate": 8.648843930635838e-05, "loss": 1.8428, "step": 533 }, { "epoch": 3.09, "learning_rate": 8.641618497109827e-05, "loss": 1.2607, "step": 534 }, { "epoch": 3.09, "learning_rate": 8.634393063583815e-05, "loss": 0.8179, "step": 535 }, { "epoch": 3.1, "learning_rate": 8.627167630057804e-05, "loss": 2.1562, "step": 536 }, { "epoch": 3.1, "learning_rate": 8.619942196531793e-05, "loss": 0.6484, "step": 537 }, { "epoch": 3.11, "learning_rate": 8.612716763005781e-05, "loss": 1.251, "step": 538 }, { "epoch": 3.12, "learning_rate": 8.605491329479768e-05, "loss": 0.9678, "step": 539 }, { "epoch": 3.12, "learning_rate": 8.598265895953758e-05, "loss": 2.209, "step": 540 }, { "epoch": 3.13, "learning_rate": 8.591040462427747e-05, "loss": 0.7319, "step": 541 }, { "epoch": 3.13, "learning_rate": 8.583815028901736e-05, "loss": 1.3066, "step": 542 }, { "epoch": 3.14, "learning_rate": 8.576589595375722e-05, "loss": 2.2129, "step": 543 }, { "epoch": 3.14, "learning_rate": 8.569364161849711e-05, "loss": 2.1289, "step": 544 }, { "epoch": 3.15, "learning_rate": 8.5621387283237e-05, "loss": 2.1406, "step": 545 }, { "epoch": 3.16, "learning_rate": 8.554913294797689e-05, "loss": 0.7563, "step": 546 }, { "epoch": 3.16, "learning_rate": 8.547687861271677e-05, "loss": 0.7163, "step": 547 }, { "epoch": 3.17, "learning_rate": 8.540462427745664e-05, "loss": 1.7539, "step": 548 }, { "epoch": 3.17, "learning_rate": 8.533236994219653e-05, "loss": 1.0635, "step": 549 }, { "epoch": 3.18, "learning_rate": 8.526011560693643e-05, "loss": 2.2539, "step": 550 }, { "epoch": 3.18, "learning_rate": 8.51878612716763e-05, "loss": 1.1982, "step": 551 }, { "epoch": 3.19, "learning_rate": 8.511560693641619e-05, "loss": 0.2034, "step": 552 }, { "epoch": 3.2, "learning_rate": 8.504335260115608e-05, "loss": 1.2529, "step": 553 }, { "epoch": 3.2, "learning_rate": 8.497109826589596e-05, "loss": 1.2021, "step": 554 }, { "epoch": 3.21, "learning_rate": 8.489884393063584e-05, "loss": 1.3154, "step": 555 }, { "epoch": 3.21, "learning_rate": 8.482658959537573e-05, "loss": 0.5991, "step": 556 }, { "epoch": 3.22, "learning_rate": 8.475433526011562e-05, "loss": 1.1367, "step": 557 }, { "epoch": 3.23, "learning_rate": 8.46820809248555e-05, "loss": 1.4717, "step": 558 }, { "epoch": 3.23, "learning_rate": 8.460982658959537e-05, "loss": 1.9199, "step": 559 }, { "epoch": 3.24, "learning_rate": 8.453757225433526e-05, "loss": 0.96, "step": 560 }, { "epoch": 3.24, "learning_rate": 8.446531791907515e-05, "loss": 1.4648, "step": 561 }, { "epoch": 3.25, "learning_rate": 8.439306358381503e-05, "loss": 1.2793, "step": 562 }, { "epoch": 3.25, "learning_rate": 8.432080924855492e-05, "loss": 2.1484, "step": 563 }, { "epoch": 3.26, "learning_rate": 8.42485549132948e-05, "loss": 0.3433, "step": 564 }, { "epoch": 3.27, "learning_rate": 8.417630057803469e-05, "loss": 0.6904, "step": 565 }, { "epoch": 3.27, "learning_rate": 8.410404624277458e-05, "loss": 1.1885, "step": 566 }, { "epoch": 3.28, "learning_rate": 8.403179190751445e-05, "loss": 0.8369, "step": 567 }, { "epoch": 3.28, "learning_rate": 8.395953757225434e-05, "loss": 0.8232, "step": 568 }, { "epoch": 3.29, "learning_rate": 8.388728323699422e-05, "loss": 0.7954, "step": 569 }, { "epoch": 3.29, "learning_rate": 8.381502890173411e-05, "loss": 0.7241, "step": 570 }, { "epoch": 3.3, "learning_rate": 8.374277456647399e-05, "loss": 0.7163, "step": 571 }, { "epoch": 3.31, "learning_rate": 8.367052023121388e-05, "loss": 0.6465, "step": 572 }, { "epoch": 3.31, "learning_rate": 8.359826589595377e-05, "loss": 0.4871, "step": 573 }, { "epoch": 3.32, "learning_rate": 8.352601156069365e-05, "loss": 0.8379, "step": 574 }, { "epoch": 3.32, "learning_rate": 8.345375722543352e-05, "loss": 1.5342, "step": 575 }, { "epoch": 3.33, "learning_rate": 8.338150289017341e-05, "loss": 1.4932, "step": 576 }, { "epoch": 3.34, "learning_rate": 8.33092485549133e-05, "loss": 1.0342, "step": 577 }, { "epoch": 3.34, "learning_rate": 8.323699421965318e-05, "loss": 2.0918, "step": 578 }, { "epoch": 3.35, "learning_rate": 8.316473988439307e-05, "loss": 2.8633, "step": 579 }, { "epoch": 3.35, "learning_rate": 8.309248554913295e-05, "loss": 1.1895, "step": 580 }, { "epoch": 3.36, "learning_rate": 8.302023121387284e-05, "loss": 1.4795, "step": 581 }, { "epoch": 3.36, "learning_rate": 8.294797687861271e-05, "loss": 0.9106, "step": 582 }, { "epoch": 3.37, "learning_rate": 8.28757225433526e-05, "loss": 0.9492, "step": 583 }, { "epoch": 3.38, "learning_rate": 8.28034682080925e-05, "loss": 1.3086, "step": 584 }, { "epoch": 3.38, "learning_rate": 8.273121387283237e-05, "loss": 0.5005, "step": 585 }, { "epoch": 3.39, "learning_rate": 8.265895953757226e-05, "loss": 1.166, "step": 586 }, { "epoch": 3.39, "learning_rate": 8.258670520231214e-05, "loss": 0.8462, "step": 587 }, { "epoch": 3.4, "learning_rate": 8.251445086705203e-05, "loss": 0.9277, "step": 588 }, { "epoch": 3.4, "learning_rate": 8.244219653179192e-05, "loss": 1.0859, "step": 589 }, { "epoch": 3.41, "learning_rate": 8.23699421965318e-05, "loss": 1.167, "step": 590 }, { "epoch": 3.42, "learning_rate": 8.229768786127167e-05, "loss": 0.8462, "step": 591 }, { "epoch": 3.42, "learning_rate": 8.222543352601156e-05, "loss": 1.1865, "step": 592 }, { "epoch": 3.43, "learning_rate": 8.215317919075145e-05, "loss": 1.2061, "step": 593 }, { "epoch": 3.43, "learning_rate": 8.208092485549133e-05, "loss": 0.6431, "step": 594 }, { "epoch": 3.44, "learning_rate": 8.200867052023122e-05, "loss": 0.7578, "step": 595 }, { "epoch": 3.45, "learning_rate": 8.19364161849711e-05, "loss": 2.7637, "step": 596 }, { "epoch": 3.45, "learning_rate": 8.186416184971099e-05, "loss": 0.5347, "step": 597 }, { "epoch": 3.46, "learning_rate": 8.179190751445087e-05, "loss": 0.6401, "step": 598 }, { "epoch": 3.46, "learning_rate": 8.171965317919076e-05, "loss": 0.6567, "step": 599 }, { "epoch": 3.47, "learning_rate": 8.164739884393065e-05, "loss": 1.0566, "step": 600 }, { "epoch": 3.47, "learning_rate": 8.157514450867052e-05, "loss": 1.0703, "step": 601 }, { "epoch": 3.48, "learning_rate": 8.15028901734104e-05, "loss": 0.9473, "step": 602 }, { "epoch": 3.49, "learning_rate": 8.143063583815029e-05, "loss": 1.3223, "step": 603 }, { "epoch": 3.49, "learning_rate": 8.135838150289018e-05, "loss": 1.4961, "step": 604 }, { "epoch": 3.5, "learning_rate": 8.128612716763007e-05, "loss": 1.9814, "step": 605 }, { "epoch": 3.5, "learning_rate": 8.121387283236995e-05, "loss": 1.2295, "step": 606 }, { "epoch": 3.51, "learning_rate": 8.114161849710983e-05, "loss": 1.6816, "step": 607 }, { "epoch": 3.51, "learning_rate": 8.106936416184972e-05, "loss": 1.6738, "step": 608 }, { "epoch": 3.52, "learning_rate": 8.09971098265896e-05, "loss": 0.978, "step": 609 }, { "epoch": 3.53, "learning_rate": 8.092485549132948e-05, "loss": 1.21, "step": 610 }, { "epoch": 3.53, "learning_rate": 8.085260115606936e-05, "loss": 0.6855, "step": 611 }, { "epoch": 3.54, "learning_rate": 8.078034682080925e-05, "loss": 1.6504, "step": 612 }, { "epoch": 3.54, "learning_rate": 8.070809248554914e-05, "loss": 1.7666, "step": 613 }, { "epoch": 3.55, "learning_rate": 8.063583815028902e-05, "loss": 0.5835, "step": 614 }, { "epoch": 3.55, "learning_rate": 8.056358381502891e-05, "loss": 1.1113, "step": 615 }, { "epoch": 3.56, "learning_rate": 8.049132947976878e-05, "loss": 0.793, "step": 616 }, { "epoch": 3.57, "learning_rate": 8.041907514450867e-05, "loss": 1.6406, "step": 617 }, { "epoch": 3.57, "learning_rate": 8.034682080924855e-05, "loss": 0.6562, "step": 618 }, { "epoch": 3.58, "learning_rate": 8.027456647398844e-05, "loss": 0.6675, "step": 619 }, { "epoch": 3.58, "learning_rate": 8.020231213872833e-05, "loss": 0.3252, "step": 620 }, { "epoch": 3.59, "learning_rate": 8.013005780346822e-05, "loss": 0.8599, "step": 621 }, { "epoch": 3.6, "learning_rate": 8.005780346820809e-05, "loss": 1.0771, "step": 622 }, { "epoch": 3.6, "learning_rate": 7.998554913294798e-05, "loss": 0.6504, "step": 623 }, { "epoch": 3.61, "learning_rate": 7.991329479768787e-05, "loss": 2.4629, "step": 624 }, { "epoch": 3.61, "learning_rate": 7.984104046242776e-05, "loss": 0.5884, "step": 625 }, { "epoch": 3.62, "learning_rate": 7.976878612716763e-05, "loss": 0.6709, "step": 626 }, { "epoch": 3.62, "learning_rate": 7.969653179190751e-05, "loss": 1.2275, "step": 627 }, { "epoch": 3.63, "learning_rate": 7.96242774566474e-05, "loss": 0.9023, "step": 628 }, { "epoch": 3.64, "learning_rate": 7.955202312138729e-05, "loss": 0.8711, "step": 629 }, { "epoch": 3.64, "learning_rate": 7.947976878612717e-05, "loss": 2.6641, "step": 630 }, { "epoch": 3.65, "learning_rate": 7.940751445086706e-05, "loss": 1.0176, "step": 631 }, { "epoch": 3.65, "learning_rate": 7.933526011560694e-05, "loss": 0.645, "step": 632 }, { "epoch": 3.66, "learning_rate": 7.926300578034683e-05, "loss": 1.4189, "step": 633 }, { "epoch": 3.66, "learning_rate": 7.91907514450867e-05, "loss": 0.7056, "step": 634 }, { "epoch": 3.67, "learning_rate": 7.91184971098266e-05, "loss": 1.7725, "step": 635 }, { "epoch": 3.68, "learning_rate": 7.904624277456648e-05, "loss": 0.6953, "step": 636 }, { "epoch": 3.68, "learning_rate": 7.897398843930636e-05, "loss": 1.1865, "step": 637 }, { "epoch": 3.69, "learning_rate": 7.890173410404624e-05, "loss": 1.3799, "step": 638 }, { "epoch": 3.69, "learning_rate": 7.882947976878613e-05, "loss": 0.4417, "step": 639 }, { "epoch": 3.7, "learning_rate": 7.875722543352602e-05, "loss": 0.5322, "step": 640 }, { "epoch": 3.71, "learning_rate": 7.868497109826591e-05, "loss": 0.957, "step": 641 }, { "epoch": 3.71, "learning_rate": 7.861271676300579e-05, "loss": 0.3308, "step": 642 }, { "epoch": 3.72, "learning_rate": 7.854046242774566e-05, "loss": 0.8237, "step": 643 }, { "epoch": 3.72, "learning_rate": 7.846820809248555e-05, "loss": 0.8208, "step": 644 }, { "epoch": 3.73, "learning_rate": 7.839595375722544e-05, "loss": 0.3904, "step": 645 }, { "epoch": 3.73, "learning_rate": 7.832369942196532e-05, "loss": 1.6475, "step": 646 }, { "epoch": 3.74, "learning_rate": 7.825144508670521e-05, "loss": 0.5352, "step": 647 }, { "epoch": 3.75, "learning_rate": 7.817919075144509e-05, "loss": 0.9473, "step": 648 }, { "epoch": 3.75, "learning_rate": 7.810693641618498e-05, "loss": 1.3525, "step": 649 }, { "epoch": 3.76, "learning_rate": 7.803468208092485e-05, "loss": 1.5947, "step": 650 }, { "epoch": 3.76, "learning_rate": 7.796242774566474e-05, "loss": 0.8428, "step": 651 }, { "epoch": 3.77, "learning_rate": 7.789017341040464e-05, "loss": 0.6968, "step": 652 }, { "epoch": 3.77, "learning_rate": 7.781791907514451e-05, "loss": 1.5352, "step": 653 }, { "epoch": 3.78, "learning_rate": 7.774566473988439e-05, "loss": 1.1396, "step": 654 }, { "epoch": 3.79, "learning_rate": 7.767341040462428e-05, "loss": 1.7617, "step": 655 }, { "epoch": 3.79, "learning_rate": 7.760115606936417e-05, "loss": 1.1445, "step": 656 }, { "epoch": 3.8, "learning_rate": 7.752890173410406e-05, "loss": 1.9502, "step": 657 }, { "epoch": 3.8, "learning_rate": 7.745664739884392e-05, "loss": 0.9048, "step": 658 }, { "epoch": 3.81, "learning_rate": 7.738439306358381e-05, "loss": 1.7373, "step": 659 }, { "epoch": 3.82, "learning_rate": 7.73121387283237e-05, "loss": 0.2493, "step": 660 }, { "epoch": 3.82, "learning_rate": 7.72398843930636e-05, "loss": 0.5571, "step": 661 }, { "epoch": 3.83, "learning_rate": 7.716763005780347e-05, "loss": 0.9624, "step": 662 }, { "epoch": 3.83, "learning_rate": 7.709537572254336e-05, "loss": 1.0078, "step": 663 }, { "epoch": 3.84, "learning_rate": 7.702312138728324e-05, "loss": 0.543, "step": 664 }, { "epoch": 3.84, "learning_rate": 7.695086705202313e-05, "loss": 0.6665, "step": 665 }, { "epoch": 3.85, "learning_rate": 7.6878612716763e-05, "loss": 0.5049, "step": 666 }, { "epoch": 3.86, "learning_rate": 7.68063583815029e-05, "loss": 0.9136, "step": 667 }, { "epoch": 3.86, "learning_rate": 7.673410404624279e-05, "loss": 1.6494, "step": 668 }, { "epoch": 3.87, "learning_rate": 7.666184971098266e-05, "loss": 1.6484, "step": 669 }, { "epoch": 3.87, "learning_rate": 7.658959537572254e-05, "loss": 2.1992, "step": 670 }, { "epoch": 3.88, "learning_rate": 7.651734104046243e-05, "loss": 0.7026, "step": 671 }, { "epoch": 3.88, "learning_rate": 7.644508670520232e-05, "loss": 1.8701, "step": 672 }, { "epoch": 3.89, "learning_rate": 7.63728323699422e-05, "loss": 1.2461, "step": 673 }, { "epoch": 3.9, "learning_rate": 7.630057803468207e-05, "loss": 1.8457, "step": 674 }, { "epoch": 3.9, "learning_rate": 7.622832369942197e-05, "loss": 1.3818, "step": 675 }, { "epoch": 3.91, "learning_rate": 7.615606936416186e-05, "loss": 1.3438, "step": 676 }, { "epoch": 3.91, "learning_rate": 7.608381502890175e-05, "loss": 0.5293, "step": 677 }, { "epoch": 3.92, "learning_rate": 7.601156069364162e-05, "loss": 1.4971, "step": 678 }, { "epoch": 3.92, "learning_rate": 7.59393063583815e-05, "loss": 0.7163, "step": 679 }, { "epoch": 3.93, "learning_rate": 7.586705202312139e-05, "loss": 1.1074, "step": 680 }, { "epoch": 3.94, "learning_rate": 7.579479768786128e-05, "loss": 0.7866, "step": 681 }, { "epoch": 3.94, "learning_rate": 7.572254335260116e-05, "loss": 3.1758, "step": 682 }, { "epoch": 3.95, "learning_rate": 7.565028901734105e-05, "loss": 0.8877, "step": 683 }, { "epoch": 3.95, "learning_rate": 7.557803468208094e-05, "loss": 0.8252, "step": 684 }, { "epoch": 3.96, "learning_rate": 7.550578034682081e-05, "loss": 0.874, "step": 685 }, { "epoch": 3.97, "learning_rate": 7.543352601156069e-05, "loss": 0.2052, "step": 686 }, { "epoch": 3.97, "learning_rate": 7.536127167630058e-05, "loss": 0.5786, "step": 687 }, { "epoch": 3.98, "learning_rate": 7.528901734104047e-05, "loss": 0.5962, "step": 688 }, { "epoch": 3.98, "learning_rate": 7.521676300578035e-05, "loss": 1.3105, "step": 689 }, { "epoch": 3.99, "learning_rate": 7.514450867052023e-05, "loss": 0.9766, "step": 690 }, { "epoch": 3.99, "learning_rate": 7.507225433526012e-05, "loss": 0.6572, "step": 691 }, { "epoch": 4.0, "learning_rate": 7.500000000000001e-05, "loss": 0.4854, "step": 692 }, { "epoch": 4.01, "learning_rate": 7.492774566473988e-05, "loss": 0.7168, "step": 693 }, { "epoch": 4.01, "learning_rate": 7.485549132947977e-05, "loss": 0.8154, "step": 694 }, { "epoch": 4.02, "learning_rate": 7.478323699421965e-05, "loss": 0.1877, "step": 695 }, { "epoch": 4.02, "learning_rate": 7.471098265895954e-05, "loss": 0.2507, "step": 696 }, { "epoch": 4.03, "learning_rate": 7.463872832369942e-05, "loss": 0.7983, "step": 697 }, { "epoch": 4.03, "learning_rate": 7.456647398843931e-05, "loss": 0.7524, "step": 698 }, { "epoch": 4.04, "learning_rate": 7.44942196531792e-05, "loss": 0.7378, "step": 699 }, { "epoch": 4.05, "learning_rate": 7.442196531791908e-05, "loss": 0.5991, "step": 700 }, { "epoch": 4.05, "learning_rate": 7.434971098265897e-05, "loss": 0.5728, "step": 701 }, { "epoch": 4.06, "learning_rate": 7.427745664739884e-05, "loss": 0.9297, "step": 702 }, { "epoch": 4.06, "learning_rate": 7.420520231213873e-05, "loss": 0.4419, "step": 703 }, { "epoch": 4.07, "learning_rate": 7.413294797687862e-05, "loss": 0.7456, "step": 704 }, { "epoch": 4.08, "learning_rate": 7.40606936416185e-05, "loss": 0.2932, "step": 705 }, { "epoch": 4.08, "learning_rate": 7.398843930635838e-05, "loss": 1.54, "step": 706 }, { "epoch": 4.09, "learning_rate": 7.391618497109827e-05, "loss": 1.5947, "step": 707 }, { "epoch": 4.09, "learning_rate": 7.384393063583816e-05, "loss": 0.936, "step": 708 }, { "epoch": 4.1, "learning_rate": 7.377167630057804e-05, "loss": 0.9072, "step": 709 }, { "epoch": 4.1, "learning_rate": 7.369942196531793e-05, "loss": 0.9575, "step": 710 }, { "epoch": 4.11, "learning_rate": 7.36271676300578e-05, "loss": 0.0718, "step": 711 }, { "epoch": 4.12, "learning_rate": 7.355491329479769e-05, "loss": 0.3481, "step": 712 }, { "epoch": 4.12, "learning_rate": 7.348265895953757e-05, "loss": 0.7949, "step": 713 }, { "epoch": 4.13, "learning_rate": 7.341040462427746e-05, "loss": 0.8638, "step": 714 }, { "epoch": 4.13, "learning_rate": 7.333815028901735e-05, "loss": 0.7446, "step": 715 }, { "epoch": 4.14, "learning_rate": 7.326589595375723e-05, "loss": 0.3567, "step": 716 }, { "epoch": 4.14, "learning_rate": 7.31936416184971e-05, "loss": 0.2634, "step": 717 }, { "epoch": 4.15, "learning_rate": 7.3121387283237e-05, "loss": 0.9561, "step": 718 }, { "epoch": 4.16, "learning_rate": 7.304913294797688e-05, "loss": 0.4019, "step": 719 }, { "epoch": 4.16, "learning_rate": 7.297687861271678e-05, "loss": 0.1997, "step": 720 }, { "epoch": 4.17, "learning_rate": 7.290462427745665e-05, "loss": 0.2766, "step": 721 }, { "epoch": 4.17, "learning_rate": 7.283236994219653e-05, "loss": 1.3291, "step": 722 }, { "epoch": 4.18, "learning_rate": 7.276011560693642e-05, "loss": 0.9097, "step": 723 }, { "epoch": 4.18, "learning_rate": 7.268786127167631e-05, "loss": 0.3206, "step": 724 }, { "epoch": 4.19, "learning_rate": 7.261560693641619e-05, "loss": 0.79, "step": 725 }, { "epoch": 4.2, "learning_rate": 7.254335260115608e-05, "loss": 1.4492, "step": 726 }, { "epoch": 4.2, "learning_rate": 7.247109826589595e-05, "loss": 0.4182, "step": 727 }, { "epoch": 4.21, "learning_rate": 7.239884393063584e-05, "loss": 0.6021, "step": 728 }, { "epoch": 4.21, "learning_rate": 7.232658959537572e-05, "loss": 1.6348, "step": 729 }, { "epoch": 4.22, "learning_rate": 7.225433526011561e-05, "loss": 2.4414, "step": 730 }, { "epoch": 4.23, "learning_rate": 7.21820809248555e-05, "loss": 1.3262, "step": 731 }, { "epoch": 4.23, "learning_rate": 7.210982658959538e-05, "loss": 0.0728, "step": 732 }, { "epoch": 4.24, "learning_rate": 7.203757225433526e-05, "loss": 1.4277, "step": 733 }, { "epoch": 4.24, "learning_rate": 7.196531791907515e-05, "loss": 0.978, "step": 734 }, { "epoch": 4.25, "learning_rate": 7.189306358381504e-05, "loss": 0.6304, "step": 735 }, { "epoch": 4.25, "learning_rate": 7.182080924855493e-05, "loss": 0.2275, "step": 736 }, { "epoch": 4.26, "learning_rate": 7.174855491329479e-05, "loss": 0.3618, "step": 737 }, { "epoch": 4.27, "learning_rate": 7.167630057803468e-05, "loss": 2.9316, "step": 738 }, { "epoch": 4.27, "learning_rate": 7.160404624277457e-05, "loss": 0.3352, "step": 739 }, { "epoch": 4.28, "learning_rate": 7.153179190751446e-05, "loss": 1.3799, "step": 740 }, { "epoch": 4.28, "learning_rate": 7.145953757225434e-05, "loss": 0.3552, "step": 741 }, { "epoch": 4.29, "learning_rate": 7.138728323699421e-05, "loss": 1.5254, "step": 742 }, { "epoch": 4.29, "learning_rate": 7.13150289017341e-05, "loss": 1.5742, "step": 743 }, { "epoch": 4.3, "learning_rate": 7.1242774566474e-05, "loss": 0.8462, "step": 744 }, { "epoch": 4.31, "learning_rate": 7.117052023121387e-05, "loss": 1.2773, "step": 745 }, { "epoch": 4.31, "learning_rate": 7.109826589595376e-05, "loss": 0.3086, "step": 746 }, { "epoch": 4.32, "learning_rate": 7.102601156069365e-05, "loss": 0.3745, "step": 747 }, { "epoch": 4.32, "learning_rate": 7.095375722543353e-05, "loss": 1.3057, "step": 748 }, { "epoch": 4.33, "learning_rate": 7.088150289017341e-05, "loss": 0.5737, "step": 749 }, { "epoch": 4.34, "learning_rate": 7.08092485549133e-05, "loss": 1.208, "step": 750 }, { "epoch": 4.34, "learning_rate": 7.073699421965319e-05, "loss": 1.082, "step": 751 }, { "epoch": 4.35, "learning_rate": 7.066473988439308e-05, "loss": 0.5708, "step": 752 }, { "epoch": 4.35, "learning_rate": 7.059248554913294e-05, "loss": 0.8008, "step": 753 }, { "epoch": 4.36, "learning_rate": 7.052023121387283e-05, "loss": 3.1895, "step": 754 }, { "epoch": 4.36, "learning_rate": 7.044797687861272e-05, "loss": 0.7192, "step": 755 }, { "epoch": 4.37, "learning_rate": 7.037572254335261e-05, "loss": 0.246, "step": 756 }, { "epoch": 4.38, "learning_rate": 7.030346820809249e-05, "loss": 1.1982, "step": 757 }, { "epoch": 4.38, "learning_rate": 7.023121387283237e-05, "loss": 0.3928, "step": 758 }, { "epoch": 4.39, "learning_rate": 7.015895953757226e-05, "loss": 0.1206, "step": 759 }, { "epoch": 4.39, "learning_rate": 7.008670520231215e-05, "loss": 0.5464, "step": 760 }, { "epoch": 4.4, "learning_rate": 7.001445086705202e-05, "loss": 0.4485, "step": 761 }, { "epoch": 4.4, "learning_rate": 6.994219653179191e-05, "loss": 0.3047, "step": 762 }, { "epoch": 4.41, "learning_rate": 6.986994219653179e-05, "loss": 1.0312, "step": 763 }, { "epoch": 4.42, "learning_rate": 6.979768786127168e-05, "loss": 0.3481, "step": 764 }, { "epoch": 4.42, "learning_rate": 6.972543352601156e-05, "loss": 0.5161, "step": 765 }, { "epoch": 4.43, "learning_rate": 6.965317919075145e-05, "loss": 0.6694, "step": 766 }, { "epoch": 4.43, "learning_rate": 6.958092485549134e-05, "loss": 0.5723, "step": 767 }, { "epoch": 4.44, "learning_rate": 6.950867052023122e-05, "loss": 0.5503, "step": 768 }, { "epoch": 4.45, "learning_rate": 6.943641618497109e-05, "loss": 0.2603, "step": 769 }, { "epoch": 4.45, "learning_rate": 6.936416184971098e-05, "loss": 0.1652, "step": 770 }, { "epoch": 4.46, "learning_rate": 6.929190751445087e-05, "loss": 0.7349, "step": 771 }, { "epoch": 4.46, "learning_rate": 6.921965317919076e-05, "loss": 0.9585, "step": 772 }, { "epoch": 4.47, "learning_rate": 6.914739884393064e-05, "loss": 0.5176, "step": 773 }, { "epoch": 4.47, "learning_rate": 6.907514450867052e-05, "loss": 0.6919, "step": 774 }, { "epoch": 4.48, "learning_rate": 6.900289017341041e-05, "loss": 0.3958, "step": 775 }, { "epoch": 4.49, "learning_rate": 6.89306358381503e-05, "loss": 0.915, "step": 776 }, { "epoch": 4.49, "learning_rate": 6.885838150289018e-05, "loss": 0.2267, "step": 777 }, { "epoch": 4.5, "learning_rate": 6.878612716763007e-05, "loss": 0.2448, "step": 778 }, { "epoch": 4.5, "learning_rate": 6.871387283236994e-05, "loss": 2.1348, "step": 779 }, { "epoch": 4.51, "learning_rate": 6.864161849710983e-05, "loss": 0.1556, "step": 780 }, { "epoch": 4.51, "learning_rate": 6.856936416184971e-05, "loss": 0.604, "step": 781 }, { "epoch": 4.52, "learning_rate": 6.84971098265896e-05, "loss": 0.447, "step": 782 }, { "epoch": 4.53, "learning_rate": 6.842485549132949e-05, "loss": 1.1621, "step": 783 }, { "epoch": 4.53, "learning_rate": 6.835260115606937e-05, "loss": 1.0186, "step": 784 }, { "epoch": 4.54, "learning_rate": 6.828034682080924e-05, "loss": 1.3984, "step": 785 }, { "epoch": 4.54, "learning_rate": 6.820809248554913e-05, "loss": 0.2722, "step": 786 }, { "epoch": 4.55, "learning_rate": 6.813583815028903e-05, "loss": 0.3308, "step": 787 }, { "epoch": 4.55, "learning_rate": 6.80635838150289e-05, "loss": 1.0127, "step": 788 }, { "epoch": 4.56, "learning_rate": 6.799132947976878e-05, "loss": 0.3582, "step": 789 }, { "epoch": 4.57, "learning_rate": 6.791907514450867e-05, "loss": 0.9277, "step": 790 }, { "epoch": 4.57, "learning_rate": 6.784682080924856e-05, "loss": 0.1014, "step": 791 }, { "epoch": 4.58, "learning_rate": 6.777456647398845e-05, "loss": 0.0942, "step": 792 }, { "epoch": 4.58, "learning_rate": 6.770231213872833e-05, "loss": 0.0748, "step": 793 }, { "epoch": 4.59, "learning_rate": 6.763005780346822e-05, "loss": 1.7529, "step": 794 }, { "epoch": 4.6, "learning_rate": 6.75578034682081e-05, "loss": 0.1633, "step": 795 }, { "epoch": 4.6, "learning_rate": 6.748554913294798e-05, "loss": 0.3679, "step": 796 }, { "epoch": 4.61, "learning_rate": 6.741329479768786e-05, "loss": 0.3796, "step": 797 }, { "epoch": 4.61, "learning_rate": 6.734104046242775e-05, "loss": 0.3879, "step": 798 }, { "epoch": 4.62, "learning_rate": 6.726878612716764e-05, "loss": 0.1392, "step": 799 }, { "epoch": 4.62, "learning_rate": 6.719653179190752e-05, "loss": 0.6958, "step": 800 }, { "epoch": 4.63, "learning_rate": 6.71242774566474e-05, "loss": 0.7627, "step": 801 }, { "epoch": 4.64, "learning_rate": 6.705202312138729e-05, "loss": 1.3213, "step": 802 }, { "epoch": 4.64, "learning_rate": 6.697976878612718e-05, "loss": 0.7412, "step": 803 }, { "epoch": 4.65, "learning_rate": 6.690751445086705e-05, "loss": 1.9873, "step": 804 }, { "epoch": 4.65, "learning_rate": 6.683526011560693e-05, "loss": 2.0957, "step": 805 }, { "epoch": 4.66, "learning_rate": 6.676300578034682e-05, "loss": 0.645, "step": 806 }, { "epoch": 4.66, "learning_rate": 6.669075144508671e-05, "loss": 0.1798, "step": 807 }, { "epoch": 4.67, "learning_rate": 6.661849710982659e-05, "loss": 0.2683, "step": 808 }, { "epoch": 4.68, "learning_rate": 6.654624277456648e-05, "loss": 0.0817, "step": 809 }, { "epoch": 4.68, "learning_rate": 6.647398843930635e-05, "loss": 2.6328, "step": 810 }, { "epoch": 4.69, "learning_rate": 6.640173410404625e-05, "loss": 0.1882, "step": 811 }, { "epoch": 4.69, "learning_rate": 6.632947976878614e-05, "loss": 0.4387, "step": 812 }, { "epoch": 4.7, "learning_rate": 6.625722543352601e-05, "loss": 0.179, "step": 813 }, { "epoch": 4.71, "learning_rate": 6.61849710982659e-05, "loss": 1.6758, "step": 814 }, { "epoch": 4.71, "learning_rate": 6.61127167630058e-05, "loss": 1.0859, "step": 815 }, { "epoch": 4.72, "learning_rate": 6.604046242774567e-05, "loss": 0.2534, "step": 816 }, { "epoch": 4.72, "learning_rate": 6.596820809248555e-05, "loss": 0.282, "step": 817 }, { "epoch": 4.73, "learning_rate": 6.589595375722544e-05, "loss": 1.0127, "step": 818 }, { "epoch": 4.73, "learning_rate": 6.582369942196533e-05, "loss": 1.1582, "step": 819 }, { "epoch": 4.74, "learning_rate": 6.57514450867052e-05, "loss": 0.1227, "step": 820 }, { "epoch": 4.75, "learning_rate": 6.567919075144508e-05, "loss": 0.132, "step": 821 }, { "epoch": 4.75, "learning_rate": 6.560693641618497e-05, "loss": 0.0927, "step": 822 }, { "epoch": 4.76, "learning_rate": 6.553468208092486e-05, "loss": 0.8086, "step": 823 }, { "epoch": 4.76, "learning_rate": 6.546242774566474e-05, "loss": 0.3208, "step": 824 }, { "epoch": 4.77, "learning_rate": 6.539017341040463e-05, "loss": 0.3301, "step": 825 }, { "epoch": 4.77, "learning_rate": 6.53179190751445e-05, "loss": 0.9961, "step": 826 }, { "epoch": 4.78, "learning_rate": 6.52456647398844e-05, "loss": 0.135, "step": 827 }, { "epoch": 4.79, "learning_rate": 6.517341040462427e-05, "loss": 0.7505, "step": 828 }, { "epoch": 4.79, "learning_rate": 6.510115606936416e-05, "loss": 0.707, "step": 829 }, { "epoch": 4.8, "learning_rate": 6.502890173410405e-05, "loss": 0.2096, "step": 830 }, { "epoch": 4.8, "learning_rate": 6.495664739884393e-05, "loss": 0.313, "step": 831 }, { "epoch": 4.81, "learning_rate": 6.488439306358381e-05, "loss": 0.3015, "step": 832 }, { "epoch": 4.82, "learning_rate": 6.48121387283237e-05, "loss": 0.3948, "step": 833 }, { "epoch": 4.82, "learning_rate": 6.473988439306359e-05, "loss": 0.1351, "step": 834 }, { "epoch": 4.83, "learning_rate": 6.466763005780348e-05, "loss": 0.397, "step": 835 }, { "epoch": 4.83, "learning_rate": 6.459537572254336e-05, "loss": 0.7754, "step": 836 }, { "epoch": 4.84, "learning_rate": 6.452312138728323e-05, "loss": 0.4358, "step": 837 }, { "epoch": 4.84, "learning_rate": 6.445086705202312e-05, "loss": 0.3955, "step": 838 }, { "epoch": 4.85, "learning_rate": 6.437861271676301e-05, "loss": 0.3838, "step": 839 }, { "epoch": 4.86, "learning_rate": 6.430635838150289e-05, "loss": 0.5825, "step": 840 }, { "epoch": 4.86, "learning_rate": 6.423410404624278e-05, "loss": 0.1262, "step": 841 }, { "epoch": 4.87, "learning_rate": 6.416184971098266e-05, "loss": 1.1172, "step": 842 }, { "epoch": 4.87, "learning_rate": 6.408959537572255e-05, "loss": 0.5957, "step": 843 }, { "epoch": 4.88, "learning_rate": 6.401734104046243e-05, "loss": 0.126, "step": 844 }, { "epoch": 4.88, "learning_rate": 6.394508670520232e-05, "loss": 1.1279, "step": 845 }, { "epoch": 4.89, "learning_rate": 6.38728323699422e-05, "loss": 0.2252, "step": 846 }, { "epoch": 4.9, "learning_rate": 6.380057803468208e-05, "loss": 1.0674, "step": 847 }, { "epoch": 4.9, "learning_rate": 6.372832369942196e-05, "loss": 0.8145, "step": 848 }, { "epoch": 4.91, "learning_rate": 6.365606936416185e-05, "loss": 0.3667, "step": 849 }, { "epoch": 4.91, "learning_rate": 6.358381502890174e-05, "loss": 0.4365, "step": 850 }, { "epoch": 4.92, "learning_rate": 6.351156069364163e-05, "loss": 0.6084, "step": 851 }, { "epoch": 4.92, "learning_rate": 6.34393063583815e-05, "loss": 0.343, "step": 852 }, { "epoch": 4.93, "learning_rate": 6.336705202312138e-05, "loss": 1.5518, "step": 853 }, { "epoch": 4.94, "learning_rate": 6.329479768786127e-05, "loss": 2.1113, "step": 854 }, { "epoch": 4.94, "learning_rate": 6.322254335260117e-05, "loss": 1.542, "step": 855 }, { "epoch": 4.95, "learning_rate": 6.315028901734104e-05, "loss": 2.2168, "step": 856 }, { "epoch": 4.95, "learning_rate": 6.307803468208093e-05, "loss": 0.4385, "step": 857 }, { "epoch": 4.96, "learning_rate": 6.300578034682081e-05, "loss": 1.1543, "step": 858 }, { "epoch": 4.97, "learning_rate": 6.29335260115607e-05, "loss": 0.1339, "step": 859 }, { "epoch": 4.97, "learning_rate": 6.286127167630058e-05, "loss": 0.1678, "step": 860 }, { "epoch": 4.98, "learning_rate": 6.278901734104047e-05, "loss": 2.0801, "step": 861 }, { "epoch": 4.98, "learning_rate": 6.271676300578036e-05, "loss": 1.417, "step": 862 }, { "epoch": 4.99, "learning_rate": 6.264450867052023e-05, "loss": 0.793, "step": 863 }, { "epoch": 4.99, "learning_rate": 6.257225433526011e-05, "loss": 0.1017, "step": 864 }, { "epoch": 5.0, "learning_rate": 6.25e-05, "loss": 0.9209, "step": 865 }, { "epoch": 5.01, "learning_rate": 6.242774566473989e-05, "loss": 0.6675, "step": 866 }, { "epoch": 5.01, "learning_rate": 6.235549132947978e-05, "loss": 0.5308, "step": 867 }, { "epoch": 5.02, "learning_rate": 6.228323699421965e-05, "loss": 0.1527, "step": 868 }, { "epoch": 5.02, "learning_rate": 6.221098265895954e-05, "loss": 1.4238, "step": 869 }, { "epoch": 5.03, "learning_rate": 6.213872832369943e-05, "loss": 0.1262, "step": 870 }, { "epoch": 5.03, "learning_rate": 6.206647398843932e-05, "loss": 0.1543, "step": 871 }, { "epoch": 5.04, "learning_rate": 6.19942196531792e-05, "loss": 1.1572, "step": 872 }, { "epoch": 5.05, "learning_rate": 6.192196531791907e-05, "loss": 0.2355, "step": 873 }, { "epoch": 5.05, "learning_rate": 6.184971098265896e-05, "loss": 0.2046, "step": 874 }, { "epoch": 5.06, "learning_rate": 6.177745664739885e-05, "loss": 0.1271, "step": 875 }, { "epoch": 5.06, "learning_rate": 6.170520231213873e-05, "loss": 0.2119, "step": 876 }, { "epoch": 5.07, "learning_rate": 6.163294797687862e-05, "loss": 0.2289, "step": 877 }, { "epoch": 5.08, "learning_rate": 6.156069364161851e-05, "loss": 0.1641, "step": 878 }, { "epoch": 5.08, "learning_rate": 6.148843930635839e-05, "loss": 0.0983, "step": 879 }, { "epoch": 5.09, "learning_rate": 6.141618497109826e-05, "loss": 0.6348, "step": 880 }, { "epoch": 5.09, "learning_rate": 6.134393063583815e-05, "loss": 0.1884, "step": 881 }, { "epoch": 5.1, "learning_rate": 6.127167630057804e-05, "loss": 1.1025, "step": 882 }, { "epoch": 5.1, "learning_rate": 6.119942196531793e-05, "loss": 0.1639, "step": 883 }, { "epoch": 5.11, "learning_rate": 6.11271676300578e-05, "loss": 0.3169, "step": 884 }, { "epoch": 5.12, "learning_rate": 6.105491329479769e-05, "loss": 0.0669, "step": 885 }, { "epoch": 5.12, "learning_rate": 6.098265895953758e-05, "loss": 0.4001, "step": 886 }, { "epoch": 5.13, "learning_rate": 6.091040462427746e-05, "loss": 0.1901, "step": 887 }, { "epoch": 5.13, "learning_rate": 6.083815028901735e-05, "loss": 0.7515, "step": 888 }, { "epoch": 5.14, "learning_rate": 6.076589595375722e-05, "loss": 1.0029, "step": 889 }, { "epoch": 5.14, "learning_rate": 6.069364161849711e-05, "loss": 1.4229, "step": 890 }, { "epoch": 5.15, "learning_rate": 6.0621387283236996e-05, "loss": 0.405, "step": 891 }, { "epoch": 5.16, "learning_rate": 6.0549132947976886e-05, "loss": 0.0482, "step": 892 }, { "epoch": 5.16, "learning_rate": 6.047687861271677e-05, "loss": 0.1689, "step": 893 }, { "epoch": 5.17, "learning_rate": 6.0404624277456646e-05, "loss": 0.1427, "step": 894 }, { "epoch": 5.17, "learning_rate": 6.033236994219653e-05, "loss": 0.2035, "step": 895 }, { "epoch": 5.18, "learning_rate": 6.026011560693642e-05, "loss": 0.2183, "step": 896 }, { "epoch": 5.18, "learning_rate": 6.0187861271676304e-05, "loss": 0.2076, "step": 897 }, { "epoch": 5.19, "learning_rate": 6.0115606936416195e-05, "loss": 0.0494, "step": 898 }, { "epoch": 5.2, "learning_rate": 6.004335260115608e-05, "loss": 0.4253, "step": 899 }, { "epoch": 5.2, "learning_rate": 5.9971098265895955e-05, "loss": 0.1998, "step": 900 }, { "epoch": 5.21, "learning_rate": 5.989884393063584e-05, "loss": 0.0816, "step": 901 }, { "epoch": 5.21, "learning_rate": 5.982658959537573e-05, "loss": 0.119, "step": 902 }, { "epoch": 5.22, "learning_rate": 5.975433526011561e-05, "loss": 0.4331, "step": 903 }, { "epoch": 5.23, "learning_rate": 5.9682080924855496e-05, "loss": 1.5527, "step": 904 }, { "epoch": 5.23, "learning_rate": 5.960982658959537e-05, "loss": 0.4216, "step": 905 }, { "epoch": 5.24, "learning_rate": 5.9537572254335263e-05, "loss": 0.5083, "step": 906 }, { "epoch": 5.24, "learning_rate": 5.946531791907515e-05, "loss": 0.6611, "step": 907 }, { "epoch": 5.25, "learning_rate": 5.939306358381503e-05, "loss": 0.4089, "step": 908 }, { "epoch": 5.25, "learning_rate": 5.932080924855492e-05, "loss": 0.2084, "step": 909 }, { "epoch": 5.26, "learning_rate": 5.92485549132948e-05, "loss": 0.0862, "step": 910 }, { "epoch": 5.27, "learning_rate": 5.917630057803468e-05, "loss": 0.0308, "step": 911 }, { "epoch": 5.27, "learning_rate": 5.910404624277457e-05, "loss": 1.04, "step": 912 }, { "epoch": 5.28, "learning_rate": 5.9031791907514456e-05, "loss": 0.5933, "step": 913 }, { "epoch": 5.28, "learning_rate": 5.895953757225434e-05, "loss": 0.3857, "step": 914 }, { "epoch": 5.29, "learning_rate": 5.8887283236994216e-05, "loss": 0.3113, "step": 915 }, { "epoch": 5.29, "learning_rate": 5.8815028901734106e-05, "loss": 1.0283, "step": 916 }, { "epoch": 5.3, "learning_rate": 5.874277456647399e-05, "loss": 0.1606, "step": 917 }, { "epoch": 5.31, "learning_rate": 5.8670520231213874e-05, "loss": 0.1316, "step": 918 }, { "epoch": 5.31, "learning_rate": 5.8598265895953764e-05, "loss": 0.1326, "step": 919 }, { "epoch": 5.32, "learning_rate": 5.852601156069365e-05, "loss": 0.1426, "step": 920 }, { "epoch": 5.32, "learning_rate": 5.8453757225433524e-05, "loss": 0.0912, "step": 921 }, { "epoch": 5.33, "learning_rate": 5.8381502890173415e-05, "loss": 0.1223, "step": 922 }, { "epoch": 5.34, "learning_rate": 5.83092485549133e-05, "loss": 0.4419, "step": 923 }, { "epoch": 5.34, "learning_rate": 5.823699421965318e-05, "loss": 0.0721, "step": 924 }, { "epoch": 5.35, "learning_rate": 5.816473988439307e-05, "loss": 0.087, "step": 925 }, { "epoch": 5.35, "learning_rate": 5.809248554913295e-05, "loss": 1.0381, "step": 926 }, { "epoch": 5.36, "learning_rate": 5.802023121387283e-05, "loss": 0.0871, "step": 927 }, { "epoch": 5.36, "learning_rate": 5.7947976878612717e-05, "loss": 0.2406, "step": 928 }, { "epoch": 5.37, "learning_rate": 5.787572254335261e-05, "loss": 0.0811, "step": 929 }, { "epoch": 5.38, "learning_rate": 5.780346820809249e-05, "loss": 0.1663, "step": 930 }, { "epoch": 5.38, "learning_rate": 5.773121387283237e-05, "loss": 0.4058, "step": 931 }, { "epoch": 5.39, "learning_rate": 5.765895953757226e-05, "loss": 0.0524, "step": 932 }, { "epoch": 5.39, "learning_rate": 5.758670520231214e-05, "loss": 0.3625, "step": 933 }, { "epoch": 5.4, "learning_rate": 5.7514450867052025e-05, "loss": 0.4182, "step": 934 }, { "epoch": 5.4, "learning_rate": 5.7442196531791915e-05, "loss": 0.1842, "step": 935 }, { "epoch": 5.41, "learning_rate": 5.736994219653179e-05, "loss": 0.2188, "step": 936 }, { "epoch": 5.42, "learning_rate": 5.7297687861271676e-05, "loss": 0.0976, "step": 937 }, { "epoch": 5.42, "learning_rate": 5.722543352601156e-05, "loss": 0.4324, "step": 938 }, { "epoch": 5.43, "learning_rate": 5.715317919075145e-05, "loss": 0.6494, "step": 939 }, { "epoch": 5.43, "learning_rate": 5.7080924855491333e-05, "loss": 1.0283, "step": 940 }, { "epoch": 5.44, "learning_rate": 5.7008670520231224e-05, "loss": 0.1549, "step": 941 }, { "epoch": 5.45, "learning_rate": 5.69364161849711e-05, "loss": 0.0479, "step": 942 }, { "epoch": 5.45, "learning_rate": 5.6864161849710984e-05, "loss": 0.6104, "step": 943 }, { "epoch": 5.46, "learning_rate": 5.679190751445087e-05, "loss": 0.1044, "step": 944 }, { "epoch": 5.46, "learning_rate": 5.671965317919076e-05, "loss": 1.0371, "step": 945 }, { "epoch": 5.47, "learning_rate": 5.664739884393064e-05, "loss": 0.0698, "step": 946 }, { "epoch": 5.47, "learning_rate": 5.657514450867052e-05, "loss": 1.0039, "step": 947 }, { "epoch": 5.48, "learning_rate": 5.65028901734104e-05, "loss": 0.665, "step": 948 }, { "epoch": 5.49, "learning_rate": 5.643063583815029e-05, "loss": 1.8359, "step": 949 }, { "epoch": 5.49, "learning_rate": 5.6358381502890176e-05, "loss": 0.1306, "step": 950 }, { "epoch": 5.5, "learning_rate": 5.628612716763007e-05, "loss": 0.2312, "step": 951 }, { "epoch": 5.5, "learning_rate": 5.6213872832369944e-05, "loss": 0.5083, "step": 952 }, { "epoch": 5.51, "learning_rate": 5.614161849710983e-05, "loss": 0.1721, "step": 953 }, { "epoch": 5.51, "learning_rate": 5.606936416184971e-05, "loss": 0.1969, "step": 954 }, { "epoch": 5.52, "learning_rate": 5.59971098265896e-05, "loss": 0.2544, "step": 955 }, { "epoch": 5.53, "learning_rate": 5.5924855491329485e-05, "loss": 0.5366, "step": 956 }, { "epoch": 5.53, "learning_rate": 5.585260115606936e-05, "loss": 0.1372, "step": 957 }, { "epoch": 5.54, "learning_rate": 5.5780346820809245e-05, "loss": 0.3704, "step": 958 }, { "epoch": 5.54, "learning_rate": 5.5708092485549136e-05, "loss": 0.9263, "step": 959 }, { "epoch": 5.55, "learning_rate": 5.563583815028902e-05, "loss": 0.7959, "step": 960 }, { "epoch": 5.55, "learning_rate": 5.556358381502891e-05, "loss": 0.2479, "step": 961 }, { "epoch": 5.56, "learning_rate": 5.5491329479768787e-05, "loss": 0.752, "step": 962 }, { "epoch": 5.57, "learning_rate": 5.541907514450867e-05, "loss": 0.5405, "step": 963 }, { "epoch": 5.57, "learning_rate": 5.5346820809248554e-05, "loss": 0.5664, "step": 964 }, { "epoch": 5.58, "learning_rate": 5.5274566473988444e-05, "loss": 0.1226, "step": 965 }, { "epoch": 5.58, "learning_rate": 5.520231213872833e-05, "loss": 0.1069, "step": 966 }, { "epoch": 5.59, "learning_rate": 5.513005780346822e-05, "loss": 0.1293, "step": 967 }, { "epoch": 5.6, "learning_rate": 5.505780346820809e-05, "loss": 0.5967, "step": 968 }, { "epoch": 5.6, "learning_rate": 5.498554913294798e-05, "loss": 1.249, "step": 969 }, { "epoch": 5.61, "learning_rate": 5.491329479768786e-05, "loss": 0.1059, "step": 970 }, { "epoch": 5.61, "learning_rate": 5.484104046242775e-05, "loss": 0.0981, "step": 971 }, { "epoch": 5.62, "learning_rate": 5.4768786127167636e-05, "loss": 0.2263, "step": 972 }, { "epoch": 5.62, "learning_rate": 5.469653179190751e-05, "loss": 0.0743, "step": 973 }, { "epoch": 5.63, "learning_rate": 5.46242774566474e-05, "loss": 0.6899, "step": 974 }, { "epoch": 5.64, "learning_rate": 5.455202312138729e-05, "loss": 0.5317, "step": 975 }, { "epoch": 5.64, "learning_rate": 5.447976878612717e-05, "loss": 0.0978, "step": 976 }, { "epoch": 5.65, "learning_rate": 5.440751445086706e-05, "loss": 0.6572, "step": 977 }, { "epoch": 5.65, "learning_rate": 5.433526011560693e-05, "loss": 0.0288, "step": 978 }, { "epoch": 5.66, "learning_rate": 5.426300578034682e-05, "loss": 0.1472, "step": 979 }, { "epoch": 5.66, "learning_rate": 5.4190751445086705e-05, "loss": 0.0677, "step": 980 }, { "epoch": 5.67, "learning_rate": 5.4118497109826596e-05, "loss": 0.1234, "step": 981 }, { "epoch": 5.68, "learning_rate": 5.404624277456648e-05, "loss": 0.2278, "step": 982 }, { "epoch": 5.68, "learning_rate": 5.3973988439306356e-05, "loss": 0.0499, "step": 983 }, { "epoch": 5.69, "learning_rate": 5.390173410404624e-05, "loss": 0.3049, "step": 984 }, { "epoch": 5.69, "learning_rate": 5.382947976878613e-05, "loss": 0.118, "step": 985 }, { "epoch": 5.7, "learning_rate": 5.3757225433526014e-05, "loss": 1.0068, "step": 986 }, { "epoch": 5.71, "learning_rate": 5.3684971098265904e-05, "loss": 0.5439, "step": 987 }, { "epoch": 5.71, "learning_rate": 5.361271676300579e-05, "loss": 0.7544, "step": 988 }, { "epoch": 5.72, "learning_rate": 5.3540462427745665e-05, "loss": 0.1864, "step": 989 }, { "epoch": 5.72, "learning_rate": 5.346820809248555e-05, "loss": 0.0692, "step": 990 }, { "epoch": 5.73, "learning_rate": 5.339595375722544e-05, "loss": 0.1442, "step": 991 }, { "epoch": 5.73, "learning_rate": 5.332369942196532e-05, "loss": 0.3025, "step": 992 }, { "epoch": 5.74, "learning_rate": 5.325144508670521e-05, "loss": 1.2441, "step": 993 }, { "epoch": 5.75, "learning_rate": 5.317919075144508e-05, "loss": 0.3381, "step": 994 }, { "epoch": 5.75, "learning_rate": 5.310693641618497e-05, "loss": 1.0391, "step": 995 }, { "epoch": 5.76, "learning_rate": 5.303468208092486e-05, "loss": 0.2793, "step": 996 }, { "epoch": 5.76, "learning_rate": 5.296242774566475e-05, "loss": 0.051, "step": 997 }, { "epoch": 5.77, "learning_rate": 5.289017341040463e-05, "loss": 0.0452, "step": 998 }, { "epoch": 5.77, "learning_rate": 5.281791907514451e-05, "loss": 0.0527, "step": 999 }, { "epoch": 5.78, "learning_rate": 5.274566473988439e-05, "loss": 0.0787, "step": 1000 }, { "epoch": 5.79, "learning_rate": 5.267341040462428e-05, "loss": 0.2859, "step": 1001 }, { "epoch": 5.79, "learning_rate": 5.2601156069364165e-05, "loss": 0.1048, "step": 1002 }, { "epoch": 5.8, "learning_rate": 5.2528901734104056e-05, "loss": 0.3464, "step": 1003 }, { "epoch": 5.8, "learning_rate": 5.2456647398843926e-05, "loss": 0.0637, "step": 1004 }, { "epoch": 5.81, "learning_rate": 5.2384393063583816e-05, "loss": 0.468, "step": 1005 }, { "epoch": 5.82, "learning_rate": 5.23121387283237e-05, "loss": 0.8721, "step": 1006 }, { "epoch": 5.82, "learning_rate": 5.223988439306359e-05, "loss": 0.248, "step": 1007 }, { "epoch": 5.83, "learning_rate": 5.2167630057803474e-05, "loss": 1.4512, "step": 1008 }, { "epoch": 5.83, "learning_rate": 5.209537572254336e-05, "loss": 0.2844, "step": 1009 }, { "epoch": 5.84, "learning_rate": 5.2023121387283234e-05, "loss": 0.0779, "step": 1010 }, { "epoch": 5.84, "learning_rate": 5.1950867052023124e-05, "loss": 0.8091, "step": 1011 }, { "epoch": 5.85, "learning_rate": 5.187861271676301e-05, "loss": 0.3804, "step": 1012 }, { "epoch": 5.86, "learning_rate": 5.18063583815029e-05, "loss": 0.498, "step": 1013 }, { "epoch": 5.86, "learning_rate": 5.173410404624278e-05, "loss": 0.29, "step": 1014 }, { "epoch": 5.87, "learning_rate": 5.166184971098266e-05, "loss": 0.4446, "step": 1015 }, { "epoch": 5.87, "learning_rate": 5.158959537572254e-05, "loss": 0.2842, "step": 1016 }, { "epoch": 5.88, "learning_rate": 5.151734104046243e-05, "loss": 0.2937, "step": 1017 }, { "epoch": 5.88, "learning_rate": 5.1445086705202317e-05, "loss": 0.0732, "step": 1018 }, { "epoch": 5.89, "learning_rate": 5.13728323699422e-05, "loss": 0.0523, "step": 1019 }, { "epoch": 5.9, "learning_rate": 5.130057803468208e-05, "loss": 0.283, "step": 1020 }, { "epoch": 5.9, "learning_rate": 5.122832369942197e-05, "loss": 0.0865, "step": 1021 }, { "epoch": 5.91, "learning_rate": 5.115606936416185e-05, "loss": 0.71, "step": 1022 }, { "epoch": 5.91, "learning_rate": 5.108381502890174e-05, "loss": 0.4834, "step": 1023 }, { "epoch": 5.92, "learning_rate": 5.1011560693641625e-05, "loss": 0.5327, "step": 1024 }, { "epoch": 5.92, "learning_rate": 5.09393063583815e-05, "loss": 0.583, "step": 1025 }, { "epoch": 5.93, "learning_rate": 5.0867052023121385e-05, "loss": 0.6245, "step": 1026 }, { "epoch": 5.94, "learning_rate": 5.0794797687861276e-05, "loss": 0.1218, "step": 1027 }, { "epoch": 5.94, "learning_rate": 5.072254335260116e-05, "loss": 0.3779, "step": 1028 }, { "epoch": 5.95, "learning_rate": 5.065028901734104e-05, "loss": 0.0681, "step": 1029 }, { "epoch": 5.95, "learning_rate": 5.0578034682080933e-05, "loss": 0.5293, "step": 1030 }, { "epoch": 5.96, "learning_rate": 5.050578034682081e-05, "loss": 0.2615, "step": 1031 }, { "epoch": 5.97, "learning_rate": 5.0433526011560694e-05, "loss": 0.1216, "step": 1032 }, { "epoch": 5.97, "learning_rate": 5.0361271676300584e-05, "loss": 0.1024, "step": 1033 }, { "epoch": 5.98, "learning_rate": 5.028901734104047e-05, "loss": 0.4194, "step": 1034 }, { "epoch": 5.98, "learning_rate": 5.021676300578035e-05, "loss": 0.0668, "step": 1035 }, { "epoch": 5.99, "learning_rate": 5.014450867052023e-05, "loss": 0.2603, "step": 1036 }, { "epoch": 5.99, "learning_rate": 5.007225433526012e-05, "loss": 0.236, "step": 1037 }, { "epoch": 6.0, "learning_rate": 5e-05, "loss": 0.1864, "step": 1038 }, { "epoch": 6.01, "learning_rate": 4.9927745664739886e-05, "loss": 0.5059, "step": 1039 }, { "epoch": 6.01, "learning_rate": 4.985549132947977e-05, "loss": 0.1103, "step": 1040 }, { "epoch": 6.02, "learning_rate": 4.978323699421965e-05, "loss": 1.1426, "step": 1041 }, { "epoch": 6.02, "learning_rate": 4.971098265895954e-05, "loss": 0.0718, "step": 1042 }, { "epoch": 6.03, "learning_rate": 4.963872832369942e-05, "loss": 0.0851, "step": 1043 }, { "epoch": 6.03, "learning_rate": 4.956647398843931e-05, "loss": 0.1479, "step": 1044 }, { "epoch": 6.04, "learning_rate": 4.9494219653179194e-05, "loss": 0.3003, "step": 1045 }, { "epoch": 6.05, "learning_rate": 4.942196531791908e-05, "loss": 1.4795, "step": 1046 }, { "epoch": 6.05, "learning_rate": 4.934971098265896e-05, "loss": 0.4636, "step": 1047 }, { "epoch": 6.06, "learning_rate": 4.9277456647398845e-05, "loss": 0.2698, "step": 1048 }, { "epoch": 6.06, "learning_rate": 4.920520231213873e-05, "loss": 0.4043, "step": 1049 }, { "epoch": 6.07, "learning_rate": 4.913294797687861e-05, "loss": 0.0864, "step": 1050 }, { "epoch": 6.08, "learning_rate": 4.9060693641618496e-05, "loss": 0.3259, "step": 1051 }, { "epoch": 6.08, "learning_rate": 4.8988439306358387e-05, "loss": 0.4578, "step": 1052 }, { "epoch": 6.09, "learning_rate": 4.8916184971098263e-05, "loss": 0.7275, "step": 1053 }, { "epoch": 6.09, "learning_rate": 4.8843930635838154e-05, "loss": 0.1146, "step": 1054 }, { "epoch": 6.1, "learning_rate": 4.877167630057804e-05, "loss": 0.0964, "step": 1055 }, { "epoch": 6.1, "learning_rate": 4.869942196531792e-05, "loss": 1.2549, "step": 1056 }, { "epoch": 6.11, "learning_rate": 4.8627167630057805e-05, "loss": 0.1674, "step": 1057 }, { "epoch": 6.12, "learning_rate": 4.855491329479769e-05, "loss": 0.5093, "step": 1058 }, { "epoch": 6.12, "learning_rate": 4.848265895953757e-05, "loss": 0.0292, "step": 1059 }, { "epoch": 6.13, "learning_rate": 4.841040462427746e-05, "loss": 0.2324, "step": 1060 }, { "epoch": 6.13, "learning_rate": 4.833815028901734e-05, "loss": 0.0645, "step": 1061 }, { "epoch": 6.14, "learning_rate": 4.826589595375723e-05, "loss": 0.1932, "step": 1062 }, { "epoch": 6.14, "learning_rate": 4.8193641618497106e-05, "loss": 0.5078, "step": 1063 }, { "epoch": 6.15, "learning_rate": 4.8121387283237e-05, "loss": 0.1044, "step": 1064 }, { "epoch": 6.16, "learning_rate": 4.804913294797688e-05, "loss": 0.0692, "step": 1065 }, { "epoch": 6.16, "learning_rate": 4.7976878612716764e-05, "loss": 0.1609, "step": 1066 }, { "epoch": 6.17, "learning_rate": 4.790462427745665e-05, "loss": 0.2805, "step": 1067 }, { "epoch": 6.17, "learning_rate": 4.783236994219654e-05, "loss": 0.0351, "step": 1068 }, { "epoch": 6.18, "learning_rate": 4.7760115606936415e-05, "loss": 0.0269, "step": 1069 }, { "epoch": 6.18, "learning_rate": 4.7687861271676305e-05, "loss": 0.0909, "step": 1070 }, { "epoch": 6.19, "learning_rate": 4.761560693641618e-05, "loss": 0.3835, "step": 1071 }, { "epoch": 6.2, "learning_rate": 4.754335260115607e-05, "loss": 0.1043, "step": 1072 }, { "epoch": 6.2, "learning_rate": 4.7471098265895956e-05, "loss": 0.1198, "step": 1073 }, { "epoch": 6.21, "learning_rate": 4.739884393063584e-05, "loss": 0.0962, "step": 1074 }, { "epoch": 6.21, "learning_rate": 4.732658959537572e-05, "loss": 0.0391, "step": 1075 }, { "epoch": 6.22, "learning_rate": 4.7254335260115614e-05, "loss": 0.0626, "step": 1076 }, { "epoch": 6.23, "learning_rate": 4.718208092485549e-05, "loss": 0.2886, "step": 1077 }, { "epoch": 6.23, "learning_rate": 4.710982658959538e-05, "loss": 0.3933, "step": 1078 }, { "epoch": 6.24, "learning_rate": 4.703757225433526e-05, "loss": 0.0483, "step": 1079 }, { "epoch": 6.24, "learning_rate": 4.696531791907515e-05, "loss": 0.5444, "step": 1080 }, { "epoch": 6.25, "learning_rate": 4.689306358381503e-05, "loss": 0.2971, "step": 1081 }, { "epoch": 6.25, "learning_rate": 4.6820809248554915e-05, "loss": 0.0339, "step": 1082 }, { "epoch": 6.26, "learning_rate": 4.67485549132948e-05, "loss": 0.1923, "step": 1083 }, { "epoch": 6.27, "learning_rate": 4.667630057803468e-05, "loss": 0.3647, "step": 1084 }, { "epoch": 6.27, "learning_rate": 4.6604046242774566e-05, "loss": 0.261, "step": 1085 }, { "epoch": 6.28, "learning_rate": 4.653179190751446e-05, "loss": 0.5928, "step": 1086 }, { "epoch": 6.28, "learning_rate": 4.6459537572254333e-05, "loss": 0.2321, "step": 1087 }, { "epoch": 6.29, "learning_rate": 4.6387283236994224e-05, "loss": 0.4026, "step": 1088 }, { "epoch": 6.29, "learning_rate": 4.631502890173411e-05, "loss": 0.1016, "step": 1089 }, { "epoch": 6.3, "learning_rate": 4.624277456647399e-05, "loss": 0.1064, "step": 1090 }, { "epoch": 6.31, "learning_rate": 4.6170520231213875e-05, "loss": 0.142, "step": 1091 }, { "epoch": 6.31, "learning_rate": 4.609826589595376e-05, "loss": 0.1277, "step": 1092 }, { "epoch": 6.32, "learning_rate": 4.602601156069364e-05, "loss": 0.129, "step": 1093 }, { "epoch": 6.32, "learning_rate": 4.595375722543353e-05, "loss": 0.3604, "step": 1094 }, { "epoch": 6.33, "learning_rate": 4.588150289017341e-05, "loss": 0.1687, "step": 1095 }, { "epoch": 6.34, "learning_rate": 4.58092485549133e-05, "loss": 0.0752, "step": 1096 }, { "epoch": 6.34, "learning_rate": 4.5736994219653176e-05, "loss": 0.2542, "step": 1097 }, { "epoch": 6.35, "learning_rate": 4.566473988439307e-05, "loss": 0.0568, "step": 1098 }, { "epoch": 6.35, "learning_rate": 4.559248554913295e-05, "loss": 0.4595, "step": 1099 }, { "epoch": 6.36, "learning_rate": 4.5520231213872834e-05, "loss": 0.0514, "step": 1100 }, { "epoch": 6.36, "learning_rate": 4.544797687861272e-05, "loss": 0.1414, "step": 1101 }, { "epoch": 6.37, "learning_rate": 4.537572254335261e-05, "loss": 0.1995, "step": 1102 }, { "epoch": 6.38, "learning_rate": 4.5303468208092485e-05, "loss": 0.7603, "step": 1103 }, { "epoch": 6.38, "learning_rate": 4.5231213872832375e-05, "loss": 0.4648, "step": 1104 }, { "epoch": 6.39, "learning_rate": 4.515895953757225e-05, "loss": 0.0458, "step": 1105 }, { "epoch": 6.39, "learning_rate": 4.508670520231214e-05, "loss": 0.2793, "step": 1106 }, { "epoch": 6.4, "learning_rate": 4.5014450867052026e-05, "loss": 0.0698, "step": 1107 }, { "epoch": 6.4, "learning_rate": 4.494219653179191e-05, "loss": 0.5542, "step": 1108 }, { "epoch": 6.41, "learning_rate": 4.486994219653179e-05, "loss": 0.1351, "step": 1109 }, { "epoch": 6.42, "learning_rate": 4.4797687861271684e-05, "loss": 0.1388, "step": 1110 }, { "epoch": 6.42, "learning_rate": 4.472543352601156e-05, "loss": 0.2688, "step": 1111 }, { "epoch": 6.43, "learning_rate": 4.465317919075145e-05, "loss": 0.2279, "step": 1112 }, { "epoch": 6.43, "learning_rate": 4.458092485549133e-05, "loss": 0.8984, "step": 1113 }, { "epoch": 6.44, "learning_rate": 4.450867052023122e-05, "loss": 0.1462, "step": 1114 }, { "epoch": 6.45, "learning_rate": 4.44364161849711e-05, "loss": 0.1348, "step": 1115 }, { "epoch": 6.45, "learning_rate": 4.4364161849710985e-05, "loss": 0.9751, "step": 1116 }, { "epoch": 6.46, "learning_rate": 4.429190751445087e-05, "loss": 0.8076, "step": 1117 }, { "epoch": 6.46, "learning_rate": 4.421965317919075e-05, "loss": 0.0341, "step": 1118 }, { "epoch": 6.47, "learning_rate": 4.4147398843930636e-05, "loss": 0.0415, "step": 1119 }, { "epoch": 6.47, "learning_rate": 4.407514450867053e-05, "loss": 0.8198, "step": 1120 }, { "epoch": 6.48, "learning_rate": 4.4002890173410404e-05, "loss": 0.0991, "step": 1121 }, { "epoch": 6.49, "learning_rate": 4.3930635838150294e-05, "loss": 0.27, "step": 1122 }, { "epoch": 6.49, "learning_rate": 4.385838150289018e-05, "loss": 0.1782, "step": 1123 }, { "epoch": 6.5, "learning_rate": 4.378612716763006e-05, "loss": 0.0435, "step": 1124 }, { "epoch": 6.5, "learning_rate": 4.3713872832369945e-05, "loss": 1.3643, "step": 1125 }, { "epoch": 6.51, "learning_rate": 4.364161849710983e-05, "loss": 0.1512, "step": 1126 }, { "epoch": 6.51, "learning_rate": 4.356936416184971e-05, "loss": 0.3682, "step": 1127 }, { "epoch": 6.52, "learning_rate": 4.34971098265896e-05, "loss": 0.2361, "step": 1128 }, { "epoch": 6.53, "learning_rate": 4.342485549132948e-05, "loss": 0.1429, "step": 1129 }, { "epoch": 6.53, "learning_rate": 4.335260115606937e-05, "loss": 0.0474, "step": 1130 }, { "epoch": 6.54, "learning_rate": 4.328034682080925e-05, "loss": 0.1757, "step": 1131 }, { "epoch": 6.54, "learning_rate": 4.320809248554914e-05, "loss": 0.1002, "step": 1132 }, { "epoch": 6.55, "learning_rate": 4.313583815028902e-05, "loss": 0.0467, "step": 1133 }, { "epoch": 6.55, "learning_rate": 4.3063583815028904e-05, "loss": 0.3843, "step": 1134 }, { "epoch": 6.56, "learning_rate": 4.299132947976879e-05, "loss": 0.1632, "step": 1135 }, { "epoch": 6.57, "learning_rate": 4.291907514450868e-05, "loss": 0.0807, "step": 1136 }, { "epoch": 6.57, "learning_rate": 4.2846820809248555e-05, "loss": 0.0778, "step": 1137 }, { "epoch": 6.58, "learning_rate": 4.2774566473988445e-05, "loss": 0.0561, "step": 1138 }, { "epoch": 6.58, "learning_rate": 4.270231213872832e-05, "loss": 0.1298, "step": 1139 }, { "epoch": 6.59, "learning_rate": 4.263005780346821e-05, "loss": 0.0257, "step": 1140 }, { "epoch": 6.6, "learning_rate": 4.2557803468208096e-05, "loss": 0.3228, "step": 1141 }, { "epoch": 6.6, "learning_rate": 4.248554913294798e-05, "loss": 0.2866, "step": 1142 }, { "epoch": 6.61, "learning_rate": 4.2413294797687863e-05, "loss": 0.0176, "step": 1143 }, { "epoch": 6.61, "learning_rate": 4.234104046242775e-05, "loss": 0.501, "step": 1144 }, { "epoch": 6.62, "learning_rate": 4.226878612716763e-05, "loss": 0.4587, "step": 1145 }, { "epoch": 6.62, "learning_rate": 4.2196531791907514e-05, "loss": 0.0371, "step": 1146 }, { "epoch": 6.63, "learning_rate": 4.21242774566474e-05, "loss": 0.261, "step": 1147 }, { "epoch": 6.64, "learning_rate": 4.205202312138729e-05, "loss": 0.1233, "step": 1148 }, { "epoch": 6.64, "learning_rate": 4.197976878612717e-05, "loss": 0.1749, "step": 1149 }, { "epoch": 6.65, "learning_rate": 4.1907514450867055e-05, "loss": 0.5347, "step": 1150 }, { "epoch": 6.65, "learning_rate": 4.183526011560694e-05, "loss": 1.168, "step": 1151 }, { "epoch": 6.66, "learning_rate": 4.176300578034682e-05, "loss": 0.0302, "step": 1152 }, { "epoch": 6.66, "learning_rate": 4.1690751445086706e-05, "loss": 1.5771, "step": 1153 }, { "epoch": 6.67, "learning_rate": 4.161849710982659e-05, "loss": 0.0875, "step": 1154 }, { "epoch": 6.68, "learning_rate": 4.1546242774566474e-05, "loss": 0.4185, "step": 1155 }, { "epoch": 6.68, "learning_rate": 4.147398843930636e-05, "loss": 0.0222, "step": 1156 }, { "epoch": 6.69, "learning_rate": 4.140173410404625e-05, "loss": 0.0307, "step": 1157 }, { "epoch": 6.69, "learning_rate": 4.132947976878613e-05, "loss": 0.0816, "step": 1158 }, { "epoch": 6.7, "learning_rate": 4.1257225433526015e-05, "loss": 0.7207, "step": 1159 }, { "epoch": 6.71, "learning_rate": 4.11849710982659e-05, "loss": 0.1414, "step": 1160 }, { "epoch": 6.71, "learning_rate": 4.111271676300578e-05, "loss": 0.4385, "step": 1161 }, { "epoch": 6.72, "learning_rate": 4.1040462427745666e-05, "loss": 0.0222, "step": 1162 }, { "epoch": 6.72, "learning_rate": 4.096820809248555e-05, "loss": 0.1887, "step": 1163 }, { "epoch": 6.73, "learning_rate": 4.089595375722543e-05, "loss": 0.915, "step": 1164 }, { "epoch": 6.73, "learning_rate": 4.082369942196532e-05, "loss": 0.2737, "step": 1165 }, { "epoch": 6.74, "learning_rate": 4.07514450867052e-05, "loss": 0.0715, "step": 1166 }, { "epoch": 6.75, "learning_rate": 4.067919075144509e-05, "loss": 0.0723, "step": 1167 }, { "epoch": 6.75, "learning_rate": 4.0606936416184974e-05, "loss": 0.4812, "step": 1168 }, { "epoch": 6.76, "learning_rate": 4.053468208092486e-05, "loss": 0.0267, "step": 1169 }, { "epoch": 6.76, "learning_rate": 4.046242774566474e-05, "loss": 0.1722, "step": 1170 }, { "epoch": 6.77, "learning_rate": 4.0390173410404625e-05, "loss": 0.2179, "step": 1171 }, { "epoch": 6.77, "learning_rate": 4.031791907514451e-05, "loss": 0.1813, "step": 1172 }, { "epoch": 6.78, "learning_rate": 4.024566473988439e-05, "loss": 0.0319, "step": 1173 }, { "epoch": 6.79, "learning_rate": 4.0173410404624276e-05, "loss": 0.3083, "step": 1174 }, { "epoch": 6.79, "learning_rate": 4.0101156069364166e-05, "loss": 0.1238, "step": 1175 }, { "epoch": 6.8, "learning_rate": 4.002890173410404e-05, "loss": 0.0918, "step": 1176 }, { "epoch": 6.8, "learning_rate": 3.9956647398843933e-05, "loss": 0.1139, "step": 1177 }, { "epoch": 6.81, "learning_rate": 3.988439306358382e-05, "loss": 0.0865, "step": 1178 }, { "epoch": 6.82, "learning_rate": 3.98121387283237e-05, "loss": 0.0482, "step": 1179 }, { "epoch": 6.82, "learning_rate": 3.9739884393063584e-05, "loss": 0.1104, "step": 1180 }, { "epoch": 6.83, "learning_rate": 3.966763005780347e-05, "loss": 0.0356, "step": 1181 }, { "epoch": 6.83, "learning_rate": 3.959537572254335e-05, "loss": 1.3721, "step": 1182 }, { "epoch": 6.84, "learning_rate": 3.952312138728324e-05, "loss": 0.3274, "step": 1183 }, { "epoch": 6.84, "learning_rate": 3.945086705202312e-05, "loss": 1.5762, "step": 1184 }, { "epoch": 6.85, "learning_rate": 3.937861271676301e-05, "loss": 0.8618, "step": 1185 }, { "epoch": 6.86, "learning_rate": 3.930635838150289e-05, "loss": 0.0488, "step": 1186 }, { "epoch": 6.86, "learning_rate": 3.9234104046242776e-05, "loss": 0.0551, "step": 1187 }, { "epoch": 6.87, "learning_rate": 3.916184971098266e-05, "loss": 0.1334, "step": 1188 }, { "epoch": 6.87, "learning_rate": 3.9089595375722544e-05, "loss": 0.0598, "step": 1189 }, { "epoch": 6.88, "learning_rate": 3.901734104046243e-05, "loss": 0.1169, "step": 1190 }, { "epoch": 6.88, "learning_rate": 3.894508670520232e-05, "loss": 0.0349, "step": 1191 }, { "epoch": 6.89, "learning_rate": 3.8872832369942194e-05, "loss": 0.0823, "step": 1192 }, { "epoch": 6.9, "learning_rate": 3.8800578034682085e-05, "loss": 0.1059, "step": 1193 }, { "epoch": 6.9, "learning_rate": 3.872832369942196e-05, "loss": 0.2155, "step": 1194 }, { "epoch": 6.91, "learning_rate": 3.865606936416185e-05, "loss": 0.2937, "step": 1195 }, { "epoch": 6.91, "learning_rate": 3.8583815028901736e-05, "loss": 0.1575, "step": 1196 }, { "epoch": 6.92, "learning_rate": 3.851156069364162e-05, "loss": 0.0522, "step": 1197 }, { "epoch": 6.92, "learning_rate": 3.84393063583815e-05, "loss": 0.0586, "step": 1198 }, { "epoch": 6.93, "learning_rate": 3.836705202312139e-05, "loss": 0.1429, "step": 1199 }, { "epoch": 6.94, "learning_rate": 3.829479768786127e-05, "loss": 0.0614, "step": 1200 }, { "epoch": 6.94, "learning_rate": 3.822254335260116e-05, "loss": 0.1046, "step": 1201 }, { "epoch": 6.95, "learning_rate": 3.815028901734104e-05, "loss": 0.2932, "step": 1202 }, { "epoch": 6.95, "learning_rate": 3.807803468208093e-05, "loss": 0.1882, "step": 1203 }, { "epoch": 6.96, "learning_rate": 3.800578034682081e-05, "loss": 0.335, "step": 1204 }, { "epoch": 6.97, "learning_rate": 3.7933526011560695e-05, "loss": 0.0467, "step": 1205 }, { "epoch": 6.97, "learning_rate": 3.786127167630058e-05, "loss": 0.0432, "step": 1206 }, { "epoch": 6.98, "learning_rate": 3.778901734104047e-05, "loss": 0.0472, "step": 1207 }, { "epoch": 6.98, "learning_rate": 3.7716763005780346e-05, "loss": 0.1842, "step": 1208 }, { "epoch": 6.99, "learning_rate": 3.7644508670520236e-05, "loss": 0.125, "step": 1209 }, { "epoch": 6.99, "learning_rate": 3.757225433526011e-05, "loss": 0.3108, "step": 1210 }, { "epoch": 7.0, "learning_rate": 3.7500000000000003e-05, "loss": 0.0698, "step": 1211 }, { "epoch": 7.01, "learning_rate": 3.742774566473989e-05, "loss": 0.0881, "step": 1212 }, { "epoch": 7.01, "learning_rate": 3.735549132947977e-05, "loss": 0.1825, "step": 1213 }, { "epoch": 7.02, "learning_rate": 3.7283236994219654e-05, "loss": 0.0883, "step": 1214 }, { "epoch": 7.02, "learning_rate": 3.721098265895954e-05, "loss": 0.3293, "step": 1215 }, { "epoch": 7.03, "learning_rate": 3.713872832369942e-05, "loss": 0.0947, "step": 1216 }, { "epoch": 7.03, "learning_rate": 3.706647398843931e-05, "loss": 0.2255, "step": 1217 }, { "epoch": 7.04, "learning_rate": 3.699421965317919e-05, "loss": 0.0228, "step": 1218 }, { "epoch": 7.05, "learning_rate": 3.692196531791908e-05, "loss": 0.1392, "step": 1219 }, { "epoch": 7.05, "learning_rate": 3.684971098265896e-05, "loss": 0.1849, "step": 1220 }, { "epoch": 7.06, "learning_rate": 3.6777456647398846e-05, "loss": 0.1449, "step": 1221 }, { "epoch": 7.06, "learning_rate": 3.670520231213873e-05, "loss": 0.0373, "step": 1222 }, { "epoch": 7.07, "learning_rate": 3.6632947976878614e-05, "loss": 0.3066, "step": 1223 }, { "epoch": 7.08, "learning_rate": 3.65606936416185e-05, "loss": 0.1376, "step": 1224 }, { "epoch": 7.08, "learning_rate": 3.648843930635839e-05, "loss": 0.0597, "step": 1225 }, { "epoch": 7.09, "learning_rate": 3.6416184971098265e-05, "loss": 0.3782, "step": 1226 }, { "epoch": 7.09, "learning_rate": 3.6343930635838155e-05, "loss": 0.3362, "step": 1227 }, { "epoch": 7.1, "learning_rate": 3.627167630057804e-05, "loss": 0.079, "step": 1228 }, { "epoch": 7.1, "learning_rate": 3.619942196531792e-05, "loss": 0.0582, "step": 1229 }, { "epoch": 7.11, "learning_rate": 3.6127167630057806e-05, "loss": 0.0238, "step": 1230 }, { "epoch": 7.12, "learning_rate": 3.605491329479769e-05, "loss": 0.0421, "step": 1231 }, { "epoch": 7.12, "learning_rate": 3.598265895953757e-05, "loss": 0.0196, "step": 1232 }, { "epoch": 7.13, "learning_rate": 3.591040462427746e-05, "loss": 0.0848, "step": 1233 }, { "epoch": 7.13, "learning_rate": 3.583815028901734e-05, "loss": 0.04, "step": 1234 }, { "epoch": 7.14, "learning_rate": 3.576589595375723e-05, "loss": 0.0686, "step": 1235 }, { "epoch": 7.14, "learning_rate": 3.569364161849711e-05, "loss": 0.0565, "step": 1236 }, { "epoch": 7.15, "learning_rate": 3.5621387283237e-05, "loss": 0.0416, "step": 1237 }, { "epoch": 7.16, "learning_rate": 3.554913294797688e-05, "loss": 0.0447, "step": 1238 }, { "epoch": 7.16, "learning_rate": 3.5476878612716765e-05, "loss": 0.3757, "step": 1239 }, { "epoch": 7.17, "learning_rate": 3.540462427745665e-05, "loss": 0.0224, "step": 1240 }, { "epoch": 7.17, "learning_rate": 3.533236994219654e-05, "loss": 0.0817, "step": 1241 }, { "epoch": 7.18, "learning_rate": 3.5260115606936416e-05, "loss": 0.1531, "step": 1242 }, { "epoch": 7.18, "learning_rate": 3.5187861271676306e-05, "loss": 0.0746, "step": 1243 }, { "epoch": 7.19, "learning_rate": 3.511560693641618e-05, "loss": 0.9326, "step": 1244 }, { "epoch": 7.2, "learning_rate": 3.5043352601156074e-05, "loss": 0.2896, "step": 1245 }, { "epoch": 7.2, "learning_rate": 3.497109826589596e-05, "loss": 0.0511, "step": 1246 }, { "epoch": 7.21, "learning_rate": 3.489884393063584e-05, "loss": 0.0388, "step": 1247 }, { "epoch": 7.21, "learning_rate": 3.4826589595375724e-05, "loss": 0.1256, "step": 1248 }, { "epoch": 7.22, "learning_rate": 3.475433526011561e-05, "loss": 0.025, "step": 1249 }, { "epoch": 7.23, "learning_rate": 3.468208092485549e-05, "loss": 0.0149, "step": 1250 }, { "epoch": 7.23, "learning_rate": 3.460982658959538e-05, "loss": 0.1381, "step": 1251 }, { "epoch": 7.24, "learning_rate": 3.453757225433526e-05, "loss": 0.0465, "step": 1252 }, { "epoch": 7.24, "learning_rate": 3.446531791907515e-05, "loss": 0.0399, "step": 1253 }, { "epoch": 7.25, "learning_rate": 3.439306358381503e-05, "loss": 0.082, "step": 1254 }, { "epoch": 7.25, "learning_rate": 3.4320809248554916e-05, "loss": 0.0382, "step": 1255 }, { "epoch": 7.26, "learning_rate": 3.42485549132948e-05, "loss": 0.0133, "step": 1256 }, { "epoch": 7.27, "learning_rate": 3.4176300578034684e-05, "loss": 0.1542, "step": 1257 }, { "epoch": 7.27, "learning_rate": 3.410404624277457e-05, "loss": 0.0593, "step": 1258 }, { "epoch": 7.28, "learning_rate": 3.403179190751445e-05, "loss": 0.0452, "step": 1259 }, { "epoch": 7.28, "learning_rate": 3.3959537572254335e-05, "loss": 0.0316, "step": 1260 }, { "epoch": 7.29, "learning_rate": 3.3887283236994225e-05, "loss": 0.0949, "step": 1261 }, { "epoch": 7.29, "learning_rate": 3.381502890173411e-05, "loss": 0.0709, "step": 1262 }, { "epoch": 7.3, "learning_rate": 3.374277456647399e-05, "loss": 0.0396, "step": 1263 }, { "epoch": 7.31, "learning_rate": 3.3670520231213876e-05, "loss": 0.0512, "step": 1264 }, { "epoch": 7.31, "learning_rate": 3.359826589595376e-05, "loss": 0.4504, "step": 1265 }, { "epoch": 7.32, "learning_rate": 3.352601156069364e-05, "loss": 0.0439, "step": 1266 }, { "epoch": 7.32, "learning_rate": 3.345375722543353e-05, "loss": 0.0438, "step": 1267 }, { "epoch": 7.33, "learning_rate": 3.338150289017341e-05, "loss": 0.0262, "step": 1268 }, { "epoch": 7.34, "learning_rate": 3.3309248554913294e-05, "loss": 0.0635, "step": 1269 }, { "epoch": 7.34, "learning_rate": 3.323699421965318e-05, "loss": 0.0672, "step": 1270 }, { "epoch": 7.35, "learning_rate": 3.316473988439307e-05, "loss": 0.2834, "step": 1271 }, { "epoch": 7.35, "learning_rate": 3.309248554913295e-05, "loss": 0.1714, "step": 1272 }, { "epoch": 7.36, "learning_rate": 3.3020231213872835e-05, "loss": 0.0411, "step": 1273 }, { "epoch": 7.36, "learning_rate": 3.294797687861272e-05, "loss": 0.1542, "step": 1274 }, { "epoch": 7.37, "learning_rate": 3.28757225433526e-05, "loss": 0.0361, "step": 1275 }, { "epoch": 7.38, "learning_rate": 3.2803468208092486e-05, "loss": 0.1713, "step": 1276 }, { "epoch": 7.38, "learning_rate": 3.273121387283237e-05, "loss": 0.0525, "step": 1277 }, { "epoch": 7.39, "learning_rate": 3.265895953757225e-05, "loss": 0.1263, "step": 1278 }, { "epoch": 7.39, "learning_rate": 3.258670520231214e-05, "loss": 0.0382, "step": 1279 }, { "epoch": 7.4, "learning_rate": 3.251445086705203e-05, "loss": 0.0246, "step": 1280 }, { "epoch": 7.4, "learning_rate": 3.2442196531791904e-05, "loss": 0.2162, "step": 1281 }, { "epoch": 7.41, "learning_rate": 3.2369942196531794e-05, "loss": 0.1227, "step": 1282 }, { "epoch": 7.42, "learning_rate": 3.229768786127168e-05, "loss": 0.4153, "step": 1283 }, { "epoch": 7.42, "learning_rate": 3.222543352601156e-05, "loss": 0.0349, "step": 1284 }, { "epoch": 7.43, "learning_rate": 3.2153179190751445e-05, "loss": 0.0902, "step": 1285 }, { "epoch": 7.43, "learning_rate": 3.208092485549133e-05, "loss": 0.0881, "step": 1286 }, { "epoch": 7.44, "learning_rate": 3.200867052023121e-05, "loss": 0.0595, "step": 1287 }, { "epoch": 7.45, "learning_rate": 3.19364161849711e-05, "loss": 0.0819, "step": 1288 }, { "epoch": 7.45, "learning_rate": 3.186416184971098e-05, "loss": 0.03, "step": 1289 }, { "epoch": 7.46, "learning_rate": 3.179190751445087e-05, "loss": 0.7544, "step": 1290 }, { "epoch": 7.46, "learning_rate": 3.171965317919075e-05, "loss": 0.0212, "step": 1291 }, { "epoch": 7.47, "learning_rate": 3.164739884393064e-05, "loss": 0.0339, "step": 1292 }, { "epoch": 7.47, "learning_rate": 3.157514450867052e-05, "loss": 0.0273, "step": 1293 }, { "epoch": 7.48, "learning_rate": 3.1502890173410405e-05, "loss": 0.0856, "step": 1294 }, { "epoch": 7.49, "learning_rate": 3.143063583815029e-05, "loss": 0.124, "step": 1295 }, { "epoch": 7.49, "learning_rate": 3.135838150289018e-05, "loss": 0.0275, "step": 1296 }, { "epoch": 7.5, "learning_rate": 3.1286127167630055e-05, "loss": 0.0222, "step": 1297 }, { "epoch": 7.5, "learning_rate": 3.1213872832369946e-05, "loss": 0.0211, "step": 1298 }, { "epoch": 7.51, "learning_rate": 3.114161849710982e-05, "loss": 0.0296, "step": 1299 }, { "epoch": 7.51, "learning_rate": 3.106936416184971e-05, "loss": 0.1104, "step": 1300 }, { "epoch": 7.52, "learning_rate": 3.09971098265896e-05, "loss": 0.2375, "step": 1301 }, { "epoch": 7.53, "learning_rate": 3.092485549132948e-05, "loss": 0.3435, "step": 1302 }, { "epoch": 7.53, "learning_rate": 3.0852601156069364e-05, "loss": 0.0267, "step": 1303 }, { "epoch": 7.54, "learning_rate": 3.0780346820809254e-05, "loss": 0.9507, "step": 1304 }, { "epoch": 7.54, "learning_rate": 3.070809248554913e-05, "loss": 0.0515, "step": 1305 }, { "epoch": 7.55, "learning_rate": 3.063583815028902e-05, "loss": 0.0495, "step": 1306 }, { "epoch": 7.55, "learning_rate": 3.05635838150289e-05, "loss": 0.2415, "step": 1307 }, { "epoch": 7.56, "learning_rate": 3.049132947976879e-05, "loss": 0.0771, "step": 1308 }, { "epoch": 7.57, "learning_rate": 3.0419075144508676e-05, "loss": 0.0344, "step": 1309 }, { "epoch": 7.57, "learning_rate": 3.0346820809248556e-05, "loss": 0.0413, "step": 1310 }, { "epoch": 7.58, "learning_rate": 3.0274566473988443e-05, "loss": 0.1548, "step": 1311 }, { "epoch": 7.58, "learning_rate": 3.0202312138728323e-05, "loss": 0.1913, "step": 1312 }, { "epoch": 7.59, "learning_rate": 3.013005780346821e-05, "loss": 0.0509, "step": 1313 }, { "epoch": 7.6, "learning_rate": 3.0057803468208097e-05, "loss": 0.0396, "step": 1314 }, { "epoch": 7.6, "learning_rate": 2.9985549132947977e-05, "loss": 0.0523, "step": 1315 }, { "epoch": 7.61, "learning_rate": 2.9913294797687864e-05, "loss": 0.9546, "step": 1316 }, { "epoch": 7.61, "learning_rate": 2.9841040462427748e-05, "loss": 0.0198, "step": 1317 }, { "epoch": 7.62, "learning_rate": 2.9768786127167632e-05, "loss": 0.7148, "step": 1318 }, { "epoch": 7.62, "learning_rate": 2.9696531791907515e-05, "loss": 0.4314, "step": 1319 }, { "epoch": 7.63, "learning_rate": 2.96242774566474e-05, "loss": 0.3684, "step": 1320 }, { "epoch": 7.64, "learning_rate": 2.9552023121387286e-05, "loss": 0.439, "step": 1321 }, { "epoch": 7.64, "learning_rate": 2.947976878612717e-05, "loss": 0.1277, "step": 1322 }, { "epoch": 7.65, "learning_rate": 2.9407514450867053e-05, "loss": 0.0875, "step": 1323 }, { "epoch": 7.65, "learning_rate": 2.9335260115606937e-05, "loss": 0.2046, "step": 1324 }, { "epoch": 7.66, "learning_rate": 2.9263005780346824e-05, "loss": 0.046, "step": 1325 }, { "epoch": 7.66, "learning_rate": 2.9190751445086707e-05, "loss": 0.193, "step": 1326 }, { "epoch": 7.67, "learning_rate": 2.911849710982659e-05, "loss": 0.2615, "step": 1327 }, { "epoch": 7.68, "learning_rate": 2.9046242774566475e-05, "loss": 0.0159, "step": 1328 }, { "epoch": 7.68, "learning_rate": 2.8973988439306358e-05, "loss": 0.3022, "step": 1329 }, { "epoch": 7.69, "learning_rate": 2.8901734104046245e-05, "loss": 0.092, "step": 1330 }, { "epoch": 7.69, "learning_rate": 2.882947976878613e-05, "loss": 0.1024, "step": 1331 }, { "epoch": 7.7, "learning_rate": 2.8757225433526013e-05, "loss": 0.0329, "step": 1332 }, { "epoch": 7.71, "learning_rate": 2.8684971098265896e-05, "loss": 0.0205, "step": 1333 }, { "epoch": 7.71, "learning_rate": 2.861271676300578e-05, "loss": 0.1547, "step": 1334 }, { "epoch": 7.72, "learning_rate": 2.8540462427745667e-05, "loss": 0.1194, "step": 1335 }, { "epoch": 7.72, "learning_rate": 2.846820809248555e-05, "loss": 0.0185, "step": 1336 }, { "epoch": 7.73, "learning_rate": 2.8395953757225434e-05, "loss": 0.0756, "step": 1337 }, { "epoch": 7.73, "learning_rate": 2.832369942196532e-05, "loss": 0.1338, "step": 1338 }, { "epoch": 7.74, "learning_rate": 2.82514450867052e-05, "loss": 0.1195, "step": 1339 }, { "epoch": 7.75, "learning_rate": 2.8179190751445088e-05, "loss": 0.0305, "step": 1340 }, { "epoch": 7.75, "learning_rate": 2.8106936416184972e-05, "loss": 0.0224, "step": 1341 }, { "epoch": 7.76, "learning_rate": 2.8034682080924855e-05, "loss": 0.0414, "step": 1342 }, { "epoch": 7.76, "learning_rate": 2.7962427745664742e-05, "loss": 0.1261, "step": 1343 }, { "epoch": 7.77, "learning_rate": 2.7890173410404623e-05, "loss": 0.0228, "step": 1344 }, { "epoch": 7.77, "learning_rate": 2.781791907514451e-05, "loss": 0.0641, "step": 1345 }, { "epoch": 7.78, "learning_rate": 2.7745664739884393e-05, "loss": 0.3105, "step": 1346 }, { "epoch": 7.79, "learning_rate": 2.7673410404624277e-05, "loss": 1.2959, "step": 1347 }, { "epoch": 7.79, "learning_rate": 2.7601156069364164e-05, "loss": 0.0487, "step": 1348 }, { "epoch": 7.8, "learning_rate": 2.7528901734104044e-05, "loss": 0.0652, "step": 1349 }, { "epoch": 7.8, "learning_rate": 2.745664739884393e-05, "loss": 0.0761, "step": 1350 }, { "epoch": 7.81, "learning_rate": 2.7384393063583818e-05, "loss": 0.0232, "step": 1351 }, { "epoch": 7.82, "learning_rate": 2.73121387283237e-05, "loss": 0.0774, "step": 1352 }, { "epoch": 7.82, "learning_rate": 2.7239884393063585e-05, "loss": 0.0276, "step": 1353 }, { "epoch": 7.83, "learning_rate": 2.7167630057803466e-05, "loss": 0.0746, "step": 1354 }, { "epoch": 7.83, "learning_rate": 2.7095375722543353e-05, "loss": 0.688, "step": 1355 }, { "epoch": 7.84, "learning_rate": 2.702312138728324e-05, "loss": 0.8516, "step": 1356 }, { "epoch": 7.84, "learning_rate": 2.695086705202312e-05, "loss": 0.0777, "step": 1357 }, { "epoch": 7.85, "learning_rate": 2.6878612716763007e-05, "loss": 0.1597, "step": 1358 }, { "epoch": 7.86, "learning_rate": 2.6806358381502894e-05, "loss": 0.0302, "step": 1359 }, { "epoch": 7.86, "learning_rate": 2.6734104046242774e-05, "loss": 0.1183, "step": 1360 }, { "epoch": 7.87, "learning_rate": 2.666184971098266e-05, "loss": 0.2192, "step": 1361 }, { "epoch": 7.87, "learning_rate": 2.658959537572254e-05, "loss": 0.1561, "step": 1362 }, { "epoch": 7.88, "learning_rate": 2.651734104046243e-05, "loss": 0.0732, "step": 1363 }, { "epoch": 7.88, "learning_rate": 2.6445086705202315e-05, "loss": 0.1304, "step": 1364 }, { "epoch": 7.89, "learning_rate": 2.6372832369942196e-05, "loss": 0.3911, "step": 1365 }, { "epoch": 7.9, "learning_rate": 2.6300578034682083e-05, "loss": 0.2898, "step": 1366 }, { "epoch": 7.9, "learning_rate": 2.6228323699421963e-05, "loss": 0.2178, "step": 1367 }, { "epoch": 7.91, "learning_rate": 2.615606936416185e-05, "loss": 0.0424, "step": 1368 }, { "epoch": 7.91, "learning_rate": 2.6083815028901737e-05, "loss": 0.0442, "step": 1369 }, { "epoch": 7.92, "learning_rate": 2.6011560693641617e-05, "loss": 0.1331, "step": 1370 }, { "epoch": 7.92, "learning_rate": 2.5939306358381504e-05, "loss": 0.1705, "step": 1371 }, { "epoch": 7.93, "learning_rate": 2.586705202312139e-05, "loss": 0.0554, "step": 1372 }, { "epoch": 7.94, "learning_rate": 2.579479768786127e-05, "loss": 0.0732, "step": 1373 }, { "epoch": 7.94, "learning_rate": 2.5722543352601158e-05, "loss": 0.1725, "step": 1374 }, { "epoch": 7.95, "learning_rate": 2.565028901734104e-05, "loss": 0.0399, "step": 1375 }, { "epoch": 7.95, "learning_rate": 2.5578034682080925e-05, "loss": 0.2034, "step": 1376 }, { "epoch": 7.96, "learning_rate": 2.5505780346820812e-05, "loss": 0.0613, "step": 1377 }, { "epoch": 7.97, "learning_rate": 2.5433526011560693e-05, "loss": 0.1105, "step": 1378 }, { "epoch": 7.97, "learning_rate": 2.536127167630058e-05, "loss": 0.1292, "step": 1379 }, { "epoch": 7.98, "learning_rate": 2.5289017341040467e-05, "loss": 0.0261, "step": 1380 }, { "epoch": 7.98, "learning_rate": 2.5216763005780347e-05, "loss": 0.2015, "step": 1381 }, { "epoch": 7.99, "learning_rate": 2.5144508670520234e-05, "loss": 0.0551, "step": 1382 }, { "epoch": 7.99, "learning_rate": 2.5072254335260114e-05, "loss": 0.0399, "step": 1383 }, { "epoch": 8.0, "learning_rate": 2.5e-05, "loss": 0.0609, "step": 1384 }, { "epoch": 8.01, "learning_rate": 2.4927745664739885e-05, "loss": 0.0462, "step": 1385 }, { "epoch": 8.01, "learning_rate": 2.485549132947977e-05, "loss": 0.0491, "step": 1386 }, { "epoch": 8.02, "learning_rate": 2.4783236994219655e-05, "loss": 0.2063, "step": 1387 }, { "epoch": 8.02, "learning_rate": 2.471098265895954e-05, "loss": 0.0217, "step": 1388 }, { "epoch": 8.03, "learning_rate": 2.4638728323699423e-05, "loss": 0.055, "step": 1389 }, { "epoch": 8.03, "learning_rate": 2.4566473988439306e-05, "loss": 0.5132, "step": 1390 }, { "epoch": 8.04, "learning_rate": 2.4494219653179193e-05, "loss": 0.0756, "step": 1391 }, { "epoch": 8.05, "learning_rate": 2.4421965317919077e-05, "loss": 0.5049, "step": 1392 }, { "epoch": 8.05, "learning_rate": 2.434971098265896e-05, "loss": 0.0509, "step": 1393 }, { "epoch": 8.06, "learning_rate": 2.4277456647398844e-05, "loss": 0.0416, "step": 1394 }, { "epoch": 8.06, "learning_rate": 2.420520231213873e-05, "loss": 0.4929, "step": 1395 }, { "epoch": 8.07, "learning_rate": 2.4132947976878615e-05, "loss": 0.1276, "step": 1396 }, { "epoch": 8.08, "learning_rate": 2.40606936416185e-05, "loss": 0.0826, "step": 1397 }, { "epoch": 8.08, "learning_rate": 2.3988439306358382e-05, "loss": 0.0464, "step": 1398 }, { "epoch": 8.09, "learning_rate": 2.391618497109827e-05, "loss": 0.0181, "step": 1399 }, { "epoch": 8.09, "learning_rate": 2.3843930635838153e-05, "loss": 0.098, "step": 1400 }, { "epoch": 8.1, "learning_rate": 2.3771676300578036e-05, "loss": 0.1777, "step": 1401 }, { "epoch": 8.1, "learning_rate": 2.369942196531792e-05, "loss": 0.0375, "step": 1402 }, { "epoch": 8.11, "learning_rate": 2.3627167630057807e-05, "loss": 0.0615, "step": 1403 }, { "epoch": 8.12, "learning_rate": 2.355491329479769e-05, "loss": 0.027, "step": 1404 }, { "epoch": 8.12, "learning_rate": 2.3482658959537574e-05, "loss": 0.304, "step": 1405 }, { "epoch": 8.13, "learning_rate": 2.3410404624277458e-05, "loss": 0.021, "step": 1406 }, { "epoch": 8.13, "learning_rate": 2.333815028901734e-05, "loss": 0.1176, "step": 1407 }, { "epoch": 8.14, "learning_rate": 2.326589595375723e-05, "loss": 0.0246, "step": 1408 }, { "epoch": 8.14, "learning_rate": 2.3193641618497112e-05, "loss": 0.0887, "step": 1409 }, { "epoch": 8.15, "learning_rate": 2.3121387283236996e-05, "loss": 0.0623, "step": 1410 }, { "epoch": 8.16, "learning_rate": 2.304913294797688e-05, "loss": 0.0132, "step": 1411 }, { "epoch": 8.16, "learning_rate": 2.2976878612716766e-05, "loss": 0.0682, "step": 1412 }, { "epoch": 8.17, "learning_rate": 2.290462427745665e-05, "loss": 0.6489, "step": 1413 }, { "epoch": 8.17, "learning_rate": 2.2832369942196533e-05, "loss": 0.1528, "step": 1414 }, { "epoch": 8.18, "learning_rate": 2.2760115606936417e-05, "loss": 0.0308, "step": 1415 }, { "epoch": 8.18, "learning_rate": 2.2687861271676304e-05, "loss": 0.0777, "step": 1416 }, { "epoch": 8.19, "learning_rate": 2.2615606936416188e-05, "loss": 0.0204, "step": 1417 }, { "epoch": 8.2, "learning_rate": 2.254335260115607e-05, "loss": 0.161, "step": 1418 }, { "epoch": 8.2, "learning_rate": 2.2471098265895955e-05, "loss": 0.1113, "step": 1419 }, { "epoch": 8.21, "learning_rate": 2.2398843930635842e-05, "loss": 0.0415, "step": 1420 }, { "epoch": 8.21, "learning_rate": 2.2326589595375725e-05, "loss": 0.0702, "step": 1421 }, { "epoch": 8.22, "learning_rate": 2.225433526011561e-05, "loss": 0.49, "step": 1422 }, { "epoch": 8.23, "learning_rate": 2.2182080924855493e-05, "loss": 0.2705, "step": 1423 }, { "epoch": 8.23, "learning_rate": 2.2109826589595376e-05, "loss": 0.0251, "step": 1424 }, { "epoch": 8.24, "learning_rate": 2.2037572254335263e-05, "loss": 0.0559, "step": 1425 }, { "epoch": 8.24, "learning_rate": 2.1965317919075147e-05, "loss": 0.1243, "step": 1426 }, { "epoch": 8.25, "learning_rate": 2.189306358381503e-05, "loss": 0.0339, "step": 1427 }, { "epoch": 8.25, "learning_rate": 2.1820809248554914e-05, "loss": 0.0378, "step": 1428 }, { "epoch": 8.26, "learning_rate": 2.17485549132948e-05, "loss": 0.0256, "step": 1429 }, { "epoch": 8.27, "learning_rate": 2.1676300578034685e-05, "loss": 0.0397, "step": 1430 }, { "epoch": 8.27, "learning_rate": 2.160404624277457e-05, "loss": 0.0274, "step": 1431 }, { "epoch": 8.28, "learning_rate": 2.1531791907514452e-05, "loss": 0.1582, "step": 1432 }, { "epoch": 8.28, "learning_rate": 2.145953757225434e-05, "loss": 0.0289, "step": 1433 }, { "epoch": 8.29, "learning_rate": 2.1387283236994223e-05, "loss": 0.0604, "step": 1434 }, { "epoch": 8.29, "learning_rate": 2.1315028901734106e-05, "loss": 0.1317, "step": 1435 }, { "epoch": 8.3, "learning_rate": 2.124277456647399e-05, "loss": 0.0428, "step": 1436 }, { "epoch": 8.31, "learning_rate": 2.1170520231213874e-05, "loss": 0.0729, "step": 1437 }, { "epoch": 8.31, "learning_rate": 2.1098265895953757e-05, "loss": 0.0305, "step": 1438 }, { "epoch": 8.32, "learning_rate": 2.1026011560693644e-05, "loss": 0.0807, "step": 1439 }, { "epoch": 8.32, "learning_rate": 2.0953757225433528e-05, "loss": 0.023, "step": 1440 }, { "epoch": 8.33, "learning_rate": 2.088150289017341e-05, "loss": 0.106, "step": 1441 }, { "epoch": 8.34, "learning_rate": 2.0809248554913295e-05, "loss": 0.0979, "step": 1442 }, { "epoch": 8.34, "learning_rate": 2.073699421965318e-05, "loss": 0.1731, "step": 1443 }, { "epoch": 8.35, "learning_rate": 2.0664739884393066e-05, "loss": 0.3472, "step": 1444 }, { "epoch": 8.35, "learning_rate": 2.059248554913295e-05, "loss": 0.2023, "step": 1445 }, { "epoch": 8.36, "learning_rate": 2.0520231213872833e-05, "loss": 0.0451, "step": 1446 }, { "epoch": 8.36, "learning_rate": 2.0447976878612716e-05, "loss": 0.0191, "step": 1447 }, { "epoch": 8.37, "learning_rate": 2.03757225433526e-05, "loss": 0.0496, "step": 1448 }, { "epoch": 8.38, "learning_rate": 2.0303468208092487e-05, "loss": 0.051, "step": 1449 }, { "epoch": 8.38, "learning_rate": 2.023121387283237e-05, "loss": 0.0271, "step": 1450 }, { "epoch": 8.39, "learning_rate": 2.0158959537572254e-05, "loss": 0.118, "step": 1451 }, { "epoch": 8.39, "learning_rate": 2.0086705202312138e-05, "loss": 0.0345, "step": 1452 }, { "epoch": 8.4, "learning_rate": 2.001445086705202e-05, "loss": 0.0218, "step": 1453 }, { "epoch": 8.4, "learning_rate": 1.994219653179191e-05, "loss": 0.1061, "step": 1454 }, { "epoch": 8.41, "learning_rate": 1.9869942196531792e-05, "loss": 0.0587, "step": 1455 }, { "epoch": 8.42, "learning_rate": 1.9797687861271676e-05, "loss": 0.0661, "step": 1456 }, { "epoch": 8.42, "learning_rate": 1.972543352601156e-05, "loss": 0.0892, "step": 1457 }, { "epoch": 8.43, "learning_rate": 1.9653179190751446e-05, "loss": 0.0189, "step": 1458 }, { "epoch": 8.43, "learning_rate": 1.958092485549133e-05, "loss": 0.0526, "step": 1459 }, { "epoch": 8.44, "learning_rate": 1.9508670520231214e-05, "loss": 0.0432, "step": 1460 }, { "epoch": 8.45, "learning_rate": 1.9436416184971097e-05, "loss": 0.0303, "step": 1461 }, { "epoch": 8.45, "learning_rate": 1.936416184971098e-05, "loss": 0.1111, "step": 1462 }, { "epoch": 8.46, "learning_rate": 1.9291907514450868e-05, "loss": 0.0666, "step": 1463 }, { "epoch": 8.46, "learning_rate": 1.921965317919075e-05, "loss": 0.0798, "step": 1464 }, { "epoch": 8.47, "learning_rate": 1.9147398843930635e-05, "loss": 0.0916, "step": 1465 }, { "epoch": 8.47, "learning_rate": 1.907514450867052e-05, "loss": 0.4644, "step": 1466 }, { "epoch": 8.48, "learning_rate": 1.9002890173410406e-05, "loss": 0.0297, "step": 1467 }, { "epoch": 8.49, "learning_rate": 1.893063583815029e-05, "loss": 0.0386, "step": 1468 }, { "epoch": 8.49, "learning_rate": 1.8858381502890173e-05, "loss": 0.0203, "step": 1469 }, { "epoch": 8.5, "learning_rate": 1.8786127167630057e-05, "loss": 0.0457, "step": 1470 }, { "epoch": 8.5, "learning_rate": 1.8713872832369944e-05, "loss": 0.0369, "step": 1471 }, { "epoch": 8.51, "learning_rate": 1.8641618497109827e-05, "loss": 0.0294, "step": 1472 }, { "epoch": 8.51, "learning_rate": 1.856936416184971e-05, "loss": 0.0279, "step": 1473 }, { "epoch": 8.52, "learning_rate": 1.8497109826589594e-05, "loss": 0.0315, "step": 1474 }, { "epoch": 8.53, "learning_rate": 1.842485549132948e-05, "loss": 0.0154, "step": 1475 }, { "epoch": 8.53, "learning_rate": 1.8352601156069365e-05, "loss": 0.0484, "step": 1476 }, { "epoch": 8.54, "learning_rate": 1.828034682080925e-05, "loss": 0.2974, "step": 1477 }, { "epoch": 8.54, "learning_rate": 1.8208092485549132e-05, "loss": 0.0248, "step": 1478 }, { "epoch": 8.55, "learning_rate": 1.813583815028902e-05, "loss": 0.0406, "step": 1479 }, { "epoch": 8.55, "learning_rate": 1.8063583815028903e-05, "loss": 0.077, "step": 1480 }, { "epoch": 8.56, "learning_rate": 1.7991329479768786e-05, "loss": 0.0266, "step": 1481 }, { "epoch": 8.57, "learning_rate": 1.791907514450867e-05, "loss": 0.0296, "step": 1482 }, { "epoch": 8.57, "learning_rate": 1.7846820809248554e-05, "loss": 0.1115, "step": 1483 }, { "epoch": 8.58, "learning_rate": 1.777456647398844e-05, "loss": 0.074, "step": 1484 }, { "epoch": 8.58, "learning_rate": 1.7702312138728324e-05, "loss": 0.0756, "step": 1485 }, { "epoch": 8.59, "learning_rate": 1.7630057803468208e-05, "loss": 0.0334, "step": 1486 }, { "epoch": 8.6, "learning_rate": 1.755780346820809e-05, "loss": 0.0178, "step": 1487 }, { "epoch": 8.6, "learning_rate": 1.748554913294798e-05, "loss": 0.0671, "step": 1488 }, { "epoch": 8.61, "learning_rate": 1.7413294797687862e-05, "loss": 0.344, "step": 1489 }, { "epoch": 8.61, "learning_rate": 1.7341040462427746e-05, "loss": 0.2012, "step": 1490 }, { "epoch": 8.62, "learning_rate": 1.726878612716763e-05, "loss": 0.0569, "step": 1491 }, { "epoch": 8.62, "learning_rate": 1.7196531791907516e-05, "loss": 0.1346, "step": 1492 }, { "epoch": 8.63, "learning_rate": 1.71242774566474e-05, "loss": 0.1506, "step": 1493 }, { "epoch": 8.64, "learning_rate": 1.7052023121387284e-05, "loss": 0.1271, "step": 1494 }, { "epoch": 8.64, "learning_rate": 1.6979768786127167e-05, "loss": 0.0223, "step": 1495 }, { "epoch": 8.65, "learning_rate": 1.6907514450867054e-05, "loss": 0.2837, "step": 1496 }, { "epoch": 8.65, "learning_rate": 1.6835260115606938e-05, "loss": 0.0215, "step": 1497 }, { "epoch": 8.66, "learning_rate": 1.676300578034682e-05, "loss": 0.1266, "step": 1498 }, { "epoch": 8.66, "learning_rate": 1.6690751445086705e-05, "loss": 0.1578, "step": 1499 }, { "epoch": 8.67, "learning_rate": 1.661849710982659e-05, "loss": 0.036, "step": 1500 }, { "epoch": 8.68, "learning_rate": 1.6546242774566476e-05, "loss": 0.0279, "step": 1501 }, { "epoch": 8.68, "learning_rate": 1.647398843930636e-05, "loss": 0.0256, "step": 1502 }, { "epoch": 8.69, "learning_rate": 1.6401734104046243e-05, "loss": 0.0388, "step": 1503 }, { "epoch": 8.69, "learning_rate": 1.6329479768786127e-05, "loss": 0.0486, "step": 1504 }, { "epoch": 8.7, "learning_rate": 1.6257225433526014e-05, "loss": 0.0488, "step": 1505 }, { "epoch": 8.71, "learning_rate": 1.6184971098265897e-05, "loss": 0.0513, "step": 1506 }, { "epoch": 8.71, "learning_rate": 1.611271676300578e-05, "loss": 0.037, "step": 1507 }, { "epoch": 8.72, "learning_rate": 1.6040462427745664e-05, "loss": 0.1323, "step": 1508 }, { "epoch": 8.72, "learning_rate": 1.596820809248555e-05, "loss": 0.0687, "step": 1509 }, { "epoch": 8.73, "learning_rate": 1.5895953757225435e-05, "loss": 0.0646, "step": 1510 }, { "epoch": 8.73, "learning_rate": 1.582369942196532e-05, "loss": 0.0289, "step": 1511 }, { "epoch": 8.74, "learning_rate": 1.5751445086705202e-05, "loss": 0.0191, "step": 1512 }, { "epoch": 8.75, "learning_rate": 1.567919075144509e-05, "loss": 0.0551, "step": 1513 }, { "epoch": 8.75, "learning_rate": 1.5606936416184973e-05, "loss": 0.0269, "step": 1514 }, { "epoch": 8.76, "learning_rate": 1.5534682080924857e-05, "loss": 0.0853, "step": 1515 }, { "epoch": 8.76, "learning_rate": 1.546242774566474e-05, "loss": 0.0433, "step": 1516 }, { "epoch": 8.77, "learning_rate": 1.5390173410404627e-05, "loss": 0.0286, "step": 1517 }, { "epoch": 8.77, "learning_rate": 1.531791907514451e-05, "loss": 0.0332, "step": 1518 }, { "epoch": 8.78, "learning_rate": 1.5245664739884394e-05, "loss": 0.0547, "step": 1519 }, { "epoch": 8.79, "learning_rate": 1.5173410404624278e-05, "loss": 0.0748, "step": 1520 }, { "epoch": 8.79, "learning_rate": 1.5101156069364162e-05, "loss": 0.1246, "step": 1521 }, { "epoch": 8.8, "learning_rate": 1.5028901734104049e-05, "loss": 0.0483, "step": 1522 }, { "epoch": 8.8, "learning_rate": 1.4956647398843932e-05, "loss": 0.0229, "step": 1523 }, { "epoch": 8.81, "learning_rate": 1.4884393063583816e-05, "loss": 0.0593, "step": 1524 }, { "epoch": 8.82, "learning_rate": 1.48121387283237e-05, "loss": 0.5259, "step": 1525 }, { "epoch": 8.82, "learning_rate": 1.4739884393063585e-05, "loss": 0.0922, "step": 1526 }, { "epoch": 8.83, "learning_rate": 1.4667630057803468e-05, "loss": 0.1433, "step": 1527 }, { "epoch": 8.83, "learning_rate": 1.4595375722543354e-05, "loss": 0.0159, "step": 1528 }, { "epoch": 8.84, "learning_rate": 1.4523121387283237e-05, "loss": 0.0137, "step": 1529 }, { "epoch": 8.84, "learning_rate": 1.4450867052023123e-05, "loss": 0.025, "step": 1530 }, { "epoch": 8.85, "learning_rate": 1.4378612716763006e-05, "loss": 0.2031, "step": 1531 }, { "epoch": 8.86, "learning_rate": 1.430635838150289e-05, "loss": 0.0135, "step": 1532 }, { "epoch": 8.86, "learning_rate": 1.4234104046242775e-05, "loss": 0.0573, "step": 1533 }, { "epoch": 8.87, "learning_rate": 1.416184971098266e-05, "loss": 0.0684, "step": 1534 }, { "epoch": 8.87, "learning_rate": 1.4089595375722544e-05, "loss": 0.5547, "step": 1535 }, { "epoch": 8.88, "learning_rate": 1.4017341040462428e-05, "loss": 0.0906, "step": 1536 }, { "epoch": 8.88, "learning_rate": 1.3945086705202311e-05, "loss": 0.0323, "step": 1537 }, { "epoch": 8.89, "learning_rate": 1.3872832369942197e-05, "loss": 0.0905, "step": 1538 }, { "epoch": 8.9, "learning_rate": 1.3800578034682082e-05, "loss": 0.032, "step": 1539 }, { "epoch": 8.9, "learning_rate": 1.3728323699421966e-05, "loss": 0.0259, "step": 1540 }, { "epoch": 8.91, "learning_rate": 1.365606936416185e-05, "loss": 0.4873, "step": 1541 }, { "epoch": 8.91, "learning_rate": 1.3583815028901733e-05, "loss": 0.0556, "step": 1542 }, { "epoch": 8.92, "learning_rate": 1.351156069364162e-05, "loss": 0.0514, "step": 1543 }, { "epoch": 8.92, "learning_rate": 1.3439306358381503e-05, "loss": 0.0388, "step": 1544 }, { "epoch": 8.93, "learning_rate": 1.3367052023121387e-05, "loss": 0.0911, "step": 1545 }, { "epoch": 8.94, "learning_rate": 1.329479768786127e-05, "loss": 0.1078, "step": 1546 }, { "epoch": 8.94, "learning_rate": 1.3222543352601158e-05, "loss": 0.0186, "step": 1547 }, { "epoch": 8.95, "learning_rate": 1.3150289017341041e-05, "loss": 0.0295, "step": 1548 }, { "epoch": 8.95, "learning_rate": 1.3078034682080925e-05, "loss": 0.0221, "step": 1549 }, { "epoch": 8.96, "learning_rate": 1.3005780346820809e-05, "loss": 0.0116, "step": 1550 }, { "epoch": 8.97, "learning_rate": 1.2933526011560696e-05, "loss": 0.02, "step": 1551 }, { "epoch": 8.97, "learning_rate": 1.2861271676300579e-05, "loss": 0.023, "step": 1552 }, { "epoch": 8.98, "learning_rate": 1.2789017341040463e-05, "loss": 0.0559, "step": 1553 }, { "epoch": 8.98, "learning_rate": 1.2716763005780346e-05, "loss": 0.0979, "step": 1554 }, { "epoch": 8.99, "learning_rate": 1.2644508670520233e-05, "loss": 0.1414, "step": 1555 }, { "epoch": 8.99, "learning_rate": 1.2572254335260117e-05, "loss": 0.1943, "step": 1556 }, { "epoch": 9.0, "learning_rate": 1.25e-05, "loss": 0.0967, "step": 1557 }, { "epoch": 9.01, "learning_rate": 1.2427745664739884e-05, "loss": 0.5552, "step": 1558 }, { "epoch": 9.01, "learning_rate": 1.235549132947977e-05, "loss": 0.0372, "step": 1559 }, { "epoch": 9.02, "learning_rate": 1.2283236994219653e-05, "loss": 0.0811, "step": 1560 }, { "epoch": 9.02, "learning_rate": 1.2210982658959538e-05, "loss": 0.0554, "step": 1561 }, { "epoch": 9.03, "learning_rate": 1.2138728323699422e-05, "loss": 0.0517, "step": 1562 }, { "epoch": 9.03, "learning_rate": 1.2066473988439307e-05, "loss": 0.0318, "step": 1563 }, { "epoch": 9.04, "learning_rate": 1.1994219653179191e-05, "loss": 0.0148, "step": 1564 }, { "epoch": 9.05, "learning_rate": 1.1921965317919076e-05, "loss": 0.0638, "step": 1565 }, { "epoch": 9.05, "learning_rate": 1.184971098265896e-05, "loss": 0.0417, "step": 1566 }, { "epoch": 9.06, "learning_rate": 1.1777456647398845e-05, "loss": 0.0251, "step": 1567 }, { "epoch": 9.06, "learning_rate": 1.1705202312138729e-05, "loss": 0.0494, "step": 1568 }, { "epoch": 9.07, "learning_rate": 1.1632947976878614e-05, "loss": 0.0215, "step": 1569 }, { "epoch": 9.08, "learning_rate": 1.1560693641618498e-05, "loss": 0.1754, "step": 1570 }, { "epoch": 9.08, "learning_rate": 1.1488439306358383e-05, "loss": 0.0341, "step": 1571 }, { "epoch": 9.09, "learning_rate": 1.1416184971098267e-05, "loss": 0.0317, "step": 1572 }, { "epoch": 9.09, "learning_rate": 1.1343930635838152e-05, "loss": 0.0346, "step": 1573 }, { "epoch": 9.1, "learning_rate": 1.1271676300578036e-05, "loss": 0.0194, "step": 1574 }, { "epoch": 9.1, "learning_rate": 1.1199421965317921e-05, "loss": 0.2197, "step": 1575 }, { "epoch": 9.11, "learning_rate": 1.1127167630057805e-05, "loss": 0.0927, "step": 1576 }, { "epoch": 9.12, "learning_rate": 1.1054913294797688e-05, "loss": 0.0565, "step": 1577 }, { "epoch": 9.12, "learning_rate": 1.0982658959537573e-05, "loss": 0.0223, "step": 1578 }, { "epoch": 9.13, "learning_rate": 1.0910404624277457e-05, "loss": 0.0334, "step": 1579 }, { "epoch": 9.13, "learning_rate": 1.0838150289017342e-05, "loss": 0.0231, "step": 1580 }, { "epoch": 9.14, "learning_rate": 1.0765895953757226e-05, "loss": 0.0267, "step": 1581 }, { "epoch": 9.14, "learning_rate": 1.0693641618497111e-05, "loss": 0.0388, "step": 1582 }, { "epoch": 9.15, "learning_rate": 1.0621387283236995e-05, "loss": 0.0477, "step": 1583 }, { "epoch": 9.16, "learning_rate": 1.0549132947976879e-05, "loss": 0.0282, "step": 1584 }, { "epoch": 9.16, "learning_rate": 1.0476878612716764e-05, "loss": 0.1819, "step": 1585 }, { "epoch": 9.17, "learning_rate": 1.0404624277456647e-05, "loss": 0.2483, "step": 1586 }, { "epoch": 9.17, "learning_rate": 1.0332369942196533e-05, "loss": 0.0476, "step": 1587 }, { "epoch": 9.18, "learning_rate": 1.0260115606936416e-05, "loss": 0.0494, "step": 1588 }, { "epoch": 9.18, "learning_rate": 1.01878612716763e-05, "loss": 0.0325, "step": 1589 }, { "epoch": 9.19, "learning_rate": 1.0115606936416185e-05, "loss": 0.0222, "step": 1590 }, { "epoch": 9.2, "learning_rate": 1.0043352601156069e-05, "loss": 0.0642, "step": 1591 }, { "epoch": 9.2, "learning_rate": 9.971098265895954e-06, "loss": 0.0204, "step": 1592 }, { "epoch": 9.21, "learning_rate": 9.898843930635838e-06, "loss": 0.0435, "step": 1593 }, { "epoch": 9.21, "learning_rate": 9.826589595375723e-06, "loss": 0.0951, "step": 1594 }, { "epoch": 9.22, "learning_rate": 9.754335260115607e-06, "loss": 0.0222, "step": 1595 }, { "epoch": 9.23, "learning_rate": 9.68208092485549e-06, "loss": 0.095, "step": 1596 }, { "epoch": 9.23, "learning_rate": 9.609826589595376e-06, "loss": 0.018, "step": 1597 }, { "epoch": 9.24, "learning_rate": 9.53757225433526e-06, "loss": 0.03, "step": 1598 }, { "epoch": 9.24, "learning_rate": 9.465317919075145e-06, "loss": 0.0434, "step": 1599 }, { "epoch": 9.25, "learning_rate": 9.393063583815028e-06, "loss": 0.0175, "step": 1600 }, { "epoch": 9.25, "learning_rate": 9.320809248554914e-06, "loss": 0.0804, "step": 1601 }, { "epoch": 9.26, "learning_rate": 9.248554913294797e-06, "loss": 0.0348, "step": 1602 }, { "epoch": 9.27, "learning_rate": 9.176300578034683e-06, "loss": 0.1162, "step": 1603 }, { "epoch": 9.27, "learning_rate": 9.104046242774566e-06, "loss": 0.1036, "step": 1604 }, { "epoch": 9.28, "learning_rate": 9.031791907514451e-06, "loss": 0.0302, "step": 1605 }, { "epoch": 9.28, "learning_rate": 8.959537572254335e-06, "loss": 0.0199, "step": 1606 }, { "epoch": 9.29, "learning_rate": 8.88728323699422e-06, "loss": 0.0276, "step": 1607 }, { "epoch": 9.29, "learning_rate": 8.815028901734104e-06, "loss": 0.0303, "step": 1608 }, { "epoch": 9.3, "learning_rate": 8.74277456647399e-06, "loss": 0.0139, "step": 1609 }, { "epoch": 9.31, "learning_rate": 8.670520231213873e-06, "loss": 0.0318, "step": 1610 }, { "epoch": 9.31, "learning_rate": 8.598265895953758e-06, "loss": 0.0252, "step": 1611 }, { "epoch": 9.32, "learning_rate": 8.526011560693642e-06, "loss": 0.0413, "step": 1612 }, { "epoch": 9.32, "learning_rate": 8.453757225433527e-06, "loss": 0.1241, "step": 1613 }, { "epoch": 9.33, "learning_rate": 8.38150289017341e-06, "loss": 0.0232, "step": 1614 }, { "epoch": 9.34, "learning_rate": 8.309248554913294e-06, "loss": 0.0975, "step": 1615 }, { "epoch": 9.34, "learning_rate": 8.23699421965318e-06, "loss": 0.0437, "step": 1616 }, { "epoch": 9.35, "learning_rate": 8.164739884393063e-06, "loss": 0.0493, "step": 1617 }, { "epoch": 9.35, "learning_rate": 8.092485549132949e-06, "loss": 0.0529, "step": 1618 }, { "epoch": 9.36, "learning_rate": 8.020231213872832e-06, "loss": 0.0148, "step": 1619 }, { "epoch": 9.36, "learning_rate": 7.947976878612718e-06, "loss": 0.0516, "step": 1620 }, { "epoch": 9.37, "learning_rate": 7.875722543352601e-06, "loss": 0.0614, "step": 1621 }, { "epoch": 9.38, "learning_rate": 7.803468208092486e-06, "loss": 0.0579, "step": 1622 }, { "epoch": 9.38, "learning_rate": 7.73121387283237e-06, "loss": 0.1614, "step": 1623 }, { "epoch": 9.39, "learning_rate": 7.658959537572255e-06, "loss": 0.1004, "step": 1624 }, { "epoch": 9.39, "learning_rate": 7.586705202312139e-06, "loss": 0.0403, "step": 1625 }, { "epoch": 9.4, "learning_rate": 7.514450867052024e-06, "loss": 0.1814, "step": 1626 }, { "epoch": 9.4, "learning_rate": 7.442196531791908e-06, "loss": 0.0324, "step": 1627 }, { "epoch": 9.41, "learning_rate": 7.369942196531792e-06, "loss": 0.0259, "step": 1628 }, { "epoch": 9.42, "learning_rate": 7.297687861271677e-06, "loss": 0.0599, "step": 1629 }, { "epoch": 9.42, "learning_rate": 7.225433526011561e-06, "loss": 0.0181, "step": 1630 }, { "epoch": 9.43, "learning_rate": 7.153179190751445e-06, "loss": 0.0489, "step": 1631 }, { "epoch": 9.43, "learning_rate": 7.08092485549133e-06, "loss": 0.0284, "step": 1632 }, { "epoch": 9.44, "learning_rate": 7.008670520231214e-06, "loss": 0.0197, "step": 1633 }, { "epoch": 9.45, "learning_rate": 6.936416184971098e-06, "loss": 0.1008, "step": 1634 }, { "epoch": 9.45, "learning_rate": 6.864161849710983e-06, "loss": 0.0171, "step": 1635 }, { "epoch": 9.46, "learning_rate": 6.791907514450866e-06, "loss": 0.0316, "step": 1636 }, { "epoch": 9.46, "learning_rate": 6.719653179190752e-06, "loss": 0.046, "step": 1637 }, { "epoch": 9.47, "learning_rate": 6.647398843930635e-06, "loss": 0.0383, "step": 1638 }, { "epoch": 9.47, "learning_rate": 6.575144508670521e-06, "loss": 0.2247, "step": 1639 }, { "epoch": 9.48, "learning_rate": 6.502890173410404e-06, "loss": 0.0194, "step": 1640 }, { "epoch": 9.49, "learning_rate": 6.4306358381502896e-06, "loss": 0.0895, "step": 1641 }, { "epoch": 9.49, "learning_rate": 6.358381502890173e-06, "loss": 0.0614, "step": 1642 }, { "epoch": 9.5, "learning_rate": 6.2861271676300585e-06, "loss": 0.0826, "step": 1643 }, { "epoch": 9.5, "learning_rate": 6.213872832369942e-06, "loss": 0.0322, "step": 1644 }, { "epoch": 9.51, "learning_rate": 6.1416184971098266e-06, "loss": 0.1702, "step": 1645 }, { "epoch": 9.51, "learning_rate": 6.069364161849711e-06, "loss": 0.069, "step": 1646 }, { "epoch": 9.52, "learning_rate": 5.9971098265895955e-06, "loss": 0.0471, "step": 1647 }, { "epoch": 9.53, "learning_rate": 5.92485549132948e-06, "loss": 0.0178, "step": 1648 }, { "epoch": 9.53, "learning_rate": 5.852601156069364e-06, "loss": 0.0098, "step": 1649 }, { "epoch": 9.54, "learning_rate": 5.780346820809249e-06, "loss": 0.052, "step": 1650 }, { "epoch": 9.54, "learning_rate": 5.708092485549133e-06, "loss": 0.0398, "step": 1651 }, { "epoch": 9.55, "learning_rate": 5.635838150289018e-06, "loss": 0.0509, "step": 1652 }, { "epoch": 9.55, "learning_rate": 5.563583815028902e-06, "loss": 0.0262, "step": 1653 }, { "epoch": 9.56, "learning_rate": 5.491329479768787e-06, "loss": 0.1782, "step": 1654 }, { "epoch": 9.57, "learning_rate": 5.419075144508671e-06, "loss": 0.0326, "step": 1655 }, { "epoch": 9.57, "learning_rate": 5.346820809248556e-06, "loss": 0.0357, "step": 1656 }, { "epoch": 9.58, "learning_rate": 5.274566473988439e-06, "loss": 0.0235, "step": 1657 }, { "epoch": 9.58, "learning_rate": 5.202312138728324e-06, "loss": 0.0777, "step": 1658 }, { "epoch": 9.59, "learning_rate": 5.130057803468208e-06, "loss": 0.0171, "step": 1659 }, { "epoch": 9.6, "learning_rate": 5.057803468208093e-06, "loss": 0.0195, "step": 1660 }, { "epoch": 9.6, "learning_rate": 4.985549132947977e-06, "loss": 0.0251, "step": 1661 }, { "epoch": 9.61, "learning_rate": 4.913294797687862e-06, "loss": 0.0369, "step": 1662 }, { "epoch": 9.61, "learning_rate": 4.841040462427745e-06, "loss": 0.0529, "step": 1663 }, { "epoch": 9.62, "learning_rate": 4.76878612716763e-06, "loss": 0.0206, "step": 1664 }, { "epoch": 9.62, "learning_rate": 4.696531791907514e-06, "loss": 0.0382, "step": 1665 }, { "epoch": 9.63, "learning_rate": 4.624277456647399e-06, "loss": 0.0623, "step": 1666 }, { "epoch": 9.64, "learning_rate": 4.552023121387283e-06, "loss": 0.3542, "step": 1667 }, { "epoch": 9.64, "learning_rate": 4.4797687861271675e-06, "loss": 0.0281, "step": 1668 }, { "epoch": 9.65, "learning_rate": 4.407514450867052e-06, "loss": 0.1573, "step": 1669 }, { "epoch": 9.65, "learning_rate": 4.3352601156069365e-06, "loss": 0.0541, "step": 1670 }, { "epoch": 9.66, "learning_rate": 4.263005780346821e-06, "loss": 0.0393, "step": 1671 }, { "epoch": 9.66, "learning_rate": 4.190751445086705e-06, "loss": 0.0213, "step": 1672 }, { "epoch": 9.67, "learning_rate": 4.11849710982659e-06, "loss": 0.0591, "step": 1673 }, { "epoch": 9.68, "learning_rate": 4.046242774566474e-06, "loss": 0.0338, "step": 1674 }, { "epoch": 9.68, "learning_rate": 3.973988439306359e-06, "loss": 0.0187, "step": 1675 }, { "epoch": 9.69, "learning_rate": 3.901734104046243e-06, "loss": 0.0185, "step": 1676 }, { "epoch": 9.69, "learning_rate": 3.829479768786128e-06, "loss": 0.1882, "step": 1677 }, { "epoch": 9.7, "learning_rate": 3.757225433526012e-06, "loss": 0.0365, "step": 1678 }, { "epoch": 9.71, "learning_rate": 3.684971098265896e-06, "loss": 0.064, "step": 1679 }, { "epoch": 9.71, "learning_rate": 3.6127167630057807e-06, "loss": 0.1229, "step": 1680 }, { "epoch": 9.72, "learning_rate": 3.540462427745665e-06, "loss": 0.3818, "step": 1681 }, { "epoch": 9.72, "learning_rate": 3.468208092485549e-06, "loss": 0.0607, "step": 1682 }, { "epoch": 9.73, "learning_rate": 3.395953757225433e-06, "loss": 0.0252, "step": 1683 }, { "epoch": 9.73, "learning_rate": 3.3236994219653177e-06, "loss": 0.027, "step": 1684 }, { "epoch": 9.74, "learning_rate": 3.251445086705202e-06, "loss": 0.0225, "step": 1685 }, { "epoch": 9.75, "learning_rate": 3.1791907514450866e-06, "loss": 0.0499, "step": 1686 }, { "epoch": 9.75, "learning_rate": 3.106936416184971e-06, "loss": 0.1255, "step": 1687 }, { "epoch": 9.76, "learning_rate": 3.0346820809248555e-06, "loss": 0.0671, "step": 1688 }, { "epoch": 9.76, "learning_rate": 2.96242774566474e-06, "loss": 0.0345, "step": 1689 }, { "epoch": 9.77, "learning_rate": 2.8901734104046244e-06, "loss": 0.0274, "step": 1690 }, { "epoch": 9.77, "learning_rate": 2.817919075144509e-06, "loss": 0.026, "step": 1691 }, { "epoch": 9.78, "learning_rate": 2.7456647398843934e-06, "loss": 0.177, "step": 1692 }, { "epoch": 9.79, "learning_rate": 2.673410404624278e-06, "loss": 0.0391, "step": 1693 }, { "epoch": 9.79, "learning_rate": 2.601156069364162e-06, "loss": 0.1362, "step": 1694 }, { "epoch": 9.8, "learning_rate": 2.5289017341040463e-06, "loss": 0.0405, "step": 1695 }, { "epoch": 9.8, "learning_rate": 2.456647398843931e-06, "loss": 0.0358, "step": 1696 }, { "epoch": 9.81, "learning_rate": 2.384393063583815e-06, "loss": 0.0383, "step": 1697 }, { "epoch": 9.82, "learning_rate": 2.3121387283236993e-06, "loss": 0.0351, "step": 1698 }, { "epoch": 9.82, "learning_rate": 2.2398843930635838e-06, "loss": 0.1339, "step": 1699 }, { "epoch": 9.83, "learning_rate": 2.1676300578034682e-06, "loss": 0.0235, "step": 1700 }, { "epoch": 9.83, "learning_rate": 2.0953757225433527e-06, "loss": 0.0123, "step": 1701 }, { "epoch": 9.84, "learning_rate": 2.023121387283237e-06, "loss": 0.0562, "step": 1702 }, { "epoch": 9.84, "learning_rate": 1.9508670520231216e-06, "loss": 0.0138, "step": 1703 }, { "epoch": 9.85, "learning_rate": 1.878612716763006e-06, "loss": 0.026, "step": 1704 }, { "epoch": 9.86, "learning_rate": 1.8063583815028903e-06, "loss": 0.1153, "step": 1705 }, { "epoch": 9.86, "learning_rate": 1.7341040462427746e-06, "loss": 0.0261, "step": 1706 }, { "epoch": 9.87, "learning_rate": 1.6618497109826588e-06, "loss": 0.1375, "step": 1707 }, { "epoch": 9.87, "learning_rate": 1.5895953757225433e-06, "loss": 0.0372, "step": 1708 }, { "epoch": 9.88, "learning_rate": 1.5173410404624278e-06, "loss": 0.3872, "step": 1709 }, { "epoch": 9.88, "learning_rate": 1.4450867052023122e-06, "loss": 0.376, "step": 1710 }, { "epoch": 9.89, "learning_rate": 1.3728323699421967e-06, "loss": 0.0347, "step": 1711 }, { "epoch": 9.9, "learning_rate": 1.300578034682081e-06, "loss": 0.0246, "step": 1712 }, { "epoch": 9.9, "learning_rate": 1.2283236994219654e-06, "loss": 0.0294, "step": 1713 }, { "epoch": 9.91, "learning_rate": 1.1560693641618497e-06, "loss": 0.0346, "step": 1714 }, { "epoch": 9.91, "learning_rate": 1.0838150289017341e-06, "loss": 0.04, "step": 1715 }, { "epoch": 9.92, "learning_rate": 1.0115606936416186e-06, "loss": 0.0903, "step": 1716 }, { "epoch": 9.92, "learning_rate": 9.39306358381503e-07, "loss": 0.1242, "step": 1717 }, { "epoch": 9.93, "learning_rate": 8.670520231213873e-07, "loss": 0.0394, "step": 1718 }, { "epoch": 9.94, "learning_rate": 7.947976878612716e-07, "loss": 0.0211, "step": 1719 }, { "epoch": 9.94, "learning_rate": 7.225433526011561e-07, "loss": 0.037, "step": 1720 }, { "epoch": 9.95, "learning_rate": 6.502890173410405e-07, "loss": 0.0667, "step": 1721 }, { "epoch": 9.95, "learning_rate": 5.780346820809248e-07, "loss": 0.0327, "step": 1722 }, { "epoch": 9.96, "learning_rate": 5.057803468208093e-07, "loss": 0.0365, "step": 1723 }, { "epoch": 9.97, "learning_rate": 4.3352601156069365e-07, "loss": 0.0388, "step": 1724 }, { "epoch": 9.97, "learning_rate": 3.6127167630057806e-07, "loss": 0.0814, "step": 1725 }, { "epoch": 9.98, "learning_rate": 2.890173410404624e-07, "loss": 0.0214, "step": 1726 }, { "epoch": 9.98, "learning_rate": 2.1676300578034682e-07, "loss": 0.0443, "step": 1727 }, { "epoch": 9.99, "learning_rate": 1.445086705202312e-07, "loss": 0.0837, "step": 1728 }, { "epoch": 9.99, "learning_rate": 7.22543352601156e-08, "loss": 0.0186, "step": 1729 }, { "epoch": 10.0, "learning_rate": 0.0, "loss": 0.0674, "step": 1730 }, { "epoch": 10.0, "step": 1730, "total_flos": 3.3456234411117773e+21, "train_loss": 1.1614258385807104, "train_runtime": 785.8758, "train_samples_per_second": 282.411, "train_steps_per_second": 2.201 } ], "max_steps": 1730, "num_train_epochs": 10, "total_flos": 3.3456234411117773e+21, "trial_name": null, "trial_params": null }