{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "global_step": 2248, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 2.9411764705882356e-07, "loss": 2.209, "step": 1 }, { "epoch": 0.0, "learning_rate": 5.882352941176471e-07, "loss": 2.2207, "step": 2 }, { "epoch": 0.0, "learning_rate": 8.823529411764707e-07, "loss": 2.1719, "step": 3 }, { "epoch": 0.0, "learning_rate": 1.1764705882352942e-06, "loss": 2.2617, "step": 4 }, { "epoch": 0.0, "learning_rate": 1.4705882352941177e-06, "loss": 2.1123, "step": 5 }, { "epoch": 0.01, "learning_rate": 1.7647058823529414e-06, "loss": 2.0459, "step": 6 }, { "epoch": 0.01, "learning_rate": 2.058823529411765e-06, "loss": 1.7021, "step": 7 }, { "epoch": 0.01, "learning_rate": 2.3529411764705885e-06, "loss": 1.5352, "step": 8 }, { "epoch": 0.01, "learning_rate": 2.647058823529412e-06, "loss": 0.7798, "step": 9 }, { "epoch": 0.01, "learning_rate": 2.9411764705882355e-06, "loss": 0.7393, "step": 10 }, { "epoch": 0.01, "learning_rate": 3.2352941176470594e-06, "loss": 0.6343, "step": 11 }, { "epoch": 0.01, "learning_rate": 3.529411764705883e-06, "loss": 0.2388, "step": 12 }, { "epoch": 0.01, "learning_rate": 3.8235294117647055e-06, "loss": 0.2211, "step": 13 }, { "epoch": 0.01, "learning_rate": 4.11764705882353e-06, "loss": 0.218, "step": 14 }, { "epoch": 0.01, "learning_rate": 4.411764705882353e-06, "loss": 0.1643, "step": 15 }, { "epoch": 0.01, "learning_rate": 4.705882352941177e-06, "loss": 0.1376, "step": 16 }, { "epoch": 0.02, "learning_rate": 5e-06, "loss": 0.1738, "step": 17 }, { "epoch": 0.02, "learning_rate": 5.294117647058824e-06, "loss": 0.1418, "step": 18 }, { "epoch": 0.02, "learning_rate": 5.588235294117647e-06, "loss": 0.1196, "step": 19 }, { "epoch": 0.02, "learning_rate": 5.882352941176471e-06, "loss": 0.1174, "step": 20 }, { "epoch": 0.02, "learning_rate": 6.176470588235295e-06, "loss": 0.1146, "step": 21 }, { "epoch": 0.02, "learning_rate": 6.470588235294119e-06, "loss": 0.1084, "step": 22 }, { "epoch": 0.02, "learning_rate": 6.764705882352942e-06, "loss": 0.1042, "step": 23 }, { "epoch": 0.02, "learning_rate": 7.058823529411766e-06, "loss": 0.1096, "step": 24 }, { "epoch": 0.02, "learning_rate": 7.352941176470589e-06, "loss": 0.1025, "step": 25 }, { "epoch": 0.02, "learning_rate": 7.647058823529411e-06, "loss": 0.1082, "step": 26 }, { "epoch": 0.02, "learning_rate": 7.941176470588236e-06, "loss": 0.1086, "step": 27 }, { "epoch": 0.02, "learning_rate": 8.23529411764706e-06, "loss": 0.1094, "step": 28 }, { "epoch": 0.03, "learning_rate": 8.529411764705883e-06, "loss": 0.1119, "step": 29 }, { "epoch": 0.03, "learning_rate": 8.823529411764707e-06, "loss": 0.1038, "step": 30 }, { "epoch": 0.03, "learning_rate": 9.11764705882353e-06, "loss": 0.1091, "step": 31 }, { "epoch": 0.03, "learning_rate": 9.411764705882354e-06, "loss": 0.1021, "step": 32 }, { "epoch": 0.03, "learning_rate": 9.705882352941177e-06, "loss": 0.0986, "step": 33 }, { "epoch": 0.03, "learning_rate": 1e-05, "loss": 0.1065, "step": 34 }, { "epoch": 0.03, "learning_rate": 1.0294117647058823e-05, "loss": 0.1106, "step": 35 }, { "epoch": 0.03, "learning_rate": 1.0588235294117648e-05, "loss": 0.0999, "step": 36 }, { "epoch": 0.03, "learning_rate": 1.0882352941176471e-05, "loss": 0.103, "step": 37 }, { "epoch": 0.03, "learning_rate": 1.1176470588235295e-05, "loss": 0.105, "step": 38 }, { "epoch": 0.03, "learning_rate": 1.1470588235294118e-05, "loss": 0.1061, "step": 39 }, { "epoch": 0.04, "learning_rate": 1.1764705882352942e-05, "loss": 0.1032, "step": 40 }, { "epoch": 0.04, "learning_rate": 1.2058823529411765e-05, "loss": 0.1042, "step": 41 }, { "epoch": 0.04, "learning_rate": 1.235294117647059e-05, "loss": 0.1024, "step": 42 }, { "epoch": 0.04, "learning_rate": 1.2647058823529412e-05, "loss": 0.0997, "step": 43 }, { "epoch": 0.04, "learning_rate": 1.2941176470588238e-05, "loss": 0.1009, "step": 44 }, { "epoch": 0.04, "learning_rate": 1.323529411764706e-05, "loss": 0.0997, "step": 45 }, { "epoch": 0.04, "learning_rate": 1.3529411764705885e-05, "loss": 0.0977, "step": 46 }, { "epoch": 0.04, "learning_rate": 1.3823529411764706e-05, "loss": 0.0945, "step": 47 }, { "epoch": 0.04, "learning_rate": 1.4117647058823532e-05, "loss": 0.0966, "step": 48 }, { "epoch": 0.04, "learning_rate": 1.4411764705882353e-05, "loss": 0.1016, "step": 49 }, { "epoch": 0.04, "learning_rate": 1.4705882352941179e-05, "loss": 0.0961, "step": 50 }, { "epoch": 0.05, "learning_rate": 1.5000000000000002e-05, "loss": 0.0974, "step": 51 }, { "epoch": 0.05, "learning_rate": 1.5294117647058822e-05, "loss": 0.0951, "step": 52 }, { "epoch": 0.05, "learning_rate": 1.558823529411765e-05, "loss": 0.0933, "step": 53 }, { "epoch": 0.05, "learning_rate": 1.5882352941176473e-05, "loss": 0.1035, "step": 54 }, { "epoch": 0.05, "learning_rate": 1.6176470588235296e-05, "loss": 0.1048, "step": 55 }, { "epoch": 0.05, "learning_rate": 1.647058823529412e-05, "loss": 0.0922, "step": 56 }, { "epoch": 0.05, "learning_rate": 1.6764705882352943e-05, "loss": 0.0945, "step": 57 }, { "epoch": 0.05, "learning_rate": 1.7058823529411767e-05, "loss": 0.0891, "step": 58 }, { "epoch": 0.05, "learning_rate": 1.735294117647059e-05, "loss": 0.0906, "step": 59 }, { "epoch": 0.05, "learning_rate": 1.7647058823529414e-05, "loss": 0.096, "step": 60 }, { "epoch": 0.05, "learning_rate": 1.7941176470588237e-05, "loss": 0.1047, "step": 61 }, { "epoch": 0.06, "learning_rate": 1.823529411764706e-05, "loss": 0.0898, "step": 62 }, { "epoch": 0.06, "learning_rate": 1.8529411764705884e-05, "loss": 0.1042, "step": 63 }, { "epoch": 0.06, "learning_rate": 1.8823529411764708e-05, "loss": 0.0801, "step": 64 }, { "epoch": 0.06, "learning_rate": 1.911764705882353e-05, "loss": 0.1061, "step": 65 }, { "epoch": 0.06, "learning_rate": 1.9411764705882355e-05, "loss": 0.1001, "step": 66 }, { "epoch": 0.06, "learning_rate": 1.9705882352941178e-05, "loss": 0.0955, "step": 67 }, { "epoch": 0.06, "learning_rate": 2e-05, "loss": 0.101, "step": 68 }, { "epoch": 0.06, "learning_rate": 1.999998961619109e-05, "loss": 0.0948, "step": 69 }, { "epoch": 0.06, "learning_rate": 1.9999958464785925e-05, "loss": 0.0911, "step": 70 }, { "epoch": 0.06, "learning_rate": 1.9999906545849198e-05, "loss": 0.0957, "step": 71 }, { "epoch": 0.06, "learning_rate": 1.999983385948873e-05, "loss": 0.0978, "step": 72 }, { "epoch": 0.06, "learning_rate": 1.9999740405855478e-05, "loss": 0.1, "step": 73 }, { "epoch": 0.07, "learning_rate": 1.9999626185143518e-05, "loss": 0.0947, "step": 74 }, { "epoch": 0.07, "learning_rate": 1.9999491197590065e-05, "loss": 0.0925, "step": 75 }, { "epoch": 0.07, "learning_rate": 1.9999335443475452e-05, "loss": 0.0963, "step": 76 }, { "epoch": 0.07, "learning_rate": 1.9999158923123145e-05, "loss": 0.0875, "step": 77 }, { "epoch": 0.07, "learning_rate": 1.9998961636899736e-05, "loss": 0.0927, "step": 78 }, { "epoch": 0.07, "learning_rate": 1.999874358521493e-05, "loss": 0.0789, "step": 79 }, { "epoch": 0.07, "learning_rate": 1.9998504768521588e-05, "loss": 0.092, "step": 80 }, { "epoch": 0.07, "learning_rate": 1.9998245187315662e-05, "loss": 0.0927, "step": 81 }, { "epoch": 0.07, "learning_rate": 1.999796484213624e-05, "loss": 0.0853, "step": 82 }, { "epoch": 0.07, "learning_rate": 1.9997663733565537e-05, "loss": 0.0809, "step": 83 }, { "epoch": 0.07, "learning_rate": 1.9997341862228886e-05, "loss": 0.0835, "step": 84 }, { "epoch": 0.08, "learning_rate": 1.9996999228794728e-05, "loss": 0.0848, "step": 85 }, { "epoch": 0.08, "learning_rate": 1.9996635833974637e-05, "loss": 0.078, "step": 86 }, { "epoch": 0.08, "learning_rate": 1.99962516785233e-05, "loss": 0.0886, "step": 87 }, { "epoch": 0.08, "learning_rate": 1.9995846763238514e-05, "loss": 0.0837, "step": 88 }, { "epoch": 0.08, "learning_rate": 1.999542108896119e-05, "loss": 0.0878, "step": 89 }, { "epoch": 0.08, "learning_rate": 1.999497465657535e-05, "loss": 0.0775, "step": 90 }, { "epoch": 0.08, "learning_rate": 1.999450746700813e-05, "loss": 0.0845, "step": 91 }, { "epoch": 0.08, "learning_rate": 1.999401952122978e-05, "loss": 0.0834, "step": 92 }, { "epoch": 0.08, "learning_rate": 1.999351082025363e-05, "loss": 0.0858, "step": 93 }, { "epoch": 0.08, "learning_rate": 1.9992981365136145e-05, "loss": 0.0856, "step": 94 }, { "epoch": 0.08, "learning_rate": 1.999243115697687e-05, "loss": 0.0789, "step": 95 }, { "epoch": 0.09, "learning_rate": 1.999186019691846e-05, "loss": 0.0775, "step": 96 }, { "epoch": 0.09, "learning_rate": 1.999126848614666e-05, "loss": 0.085, "step": 97 }, { "epoch": 0.09, "learning_rate": 1.9990656025890315e-05, "loss": 0.0858, "step": 98 }, { "epoch": 0.09, "learning_rate": 1.999002281742136e-05, "loss": 0.0811, "step": 99 }, { "epoch": 0.09, "learning_rate": 1.9989368862054814e-05, "loss": 0.0873, "step": 100 }, { "epoch": 0.09, "learning_rate": 1.9988694161148788e-05, "loss": 0.0928, "step": 101 }, { "epoch": 0.09, "learning_rate": 1.9987998716104473e-05, "loss": 0.0996, "step": 102 }, { "epoch": 0.09, "learning_rate": 1.9987282528366147e-05, "loss": 0.0844, "step": 103 }, { "epoch": 0.09, "learning_rate": 1.998654559942116e-05, "loss": 0.0871, "step": 104 }, { "epoch": 0.09, "learning_rate": 1.998578793079994e-05, "loss": 0.0959, "step": 105 }, { "epoch": 0.09, "learning_rate": 1.998500952407598e-05, "loss": 0.0894, "step": 106 }, { "epoch": 0.1, "learning_rate": 1.9984210380865842e-05, "loss": 0.0869, "step": 107 }, { "epoch": 0.1, "learning_rate": 1.9983390502829168e-05, "loss": 0.0837, "step": 108 }, { "epoch": 0.1, "learning_rate": 1.998254989166864e-05, "loss": 0.0839, "step": 109 }, { "epoch": 0.1, "learning_rate": 1.998168854913001e-05, "loss": 0.0934, "step": 110 }, { "epoch": 0.1, "learning_rate": 1.9980806477002078e-05, "loss": 0.0813, "step": 111 }, { "epoch": 0.1, "learning_rate": 1.9979903677116705e-05, "loss": 0.0813, "step": 112 }, { "epoch": 0.1, "learning_rate": 1.997898015134878e-05, "loss": 0.0837, "step": 113 }, { "epoch": 0.1, "learning_rate": 1.997803590161626e-05, "loss": 0.0819, "step": 114 }, { "epoch": 0.1, "learning_rate": 1.997707092988012e-05, "loss": 0.0778, "step": 115 }, { "epoch": 0.1, "learning_rate": 1.997608523814437e-05, "loss": 0.0899, "step": 116 }, { "epoch": 0.1, "learning_rate": 1.9975078828456066e-05, "loss": 0.0741, "step": 117 }, { "epoch": 0.1, "learning_rate": 1.997405170290528e-05, "loss": 0.088, "step": 118 }, { "epoch": 0.11, "learning_rate": 1.99730038636251e-05, "loss": 0.0782, "step": 119 }, { "epoch": 0.11, "learning_rate": 1.9971935312791646e-05, "loss": 0.0839, "step": 120 }, { "epoch": 0.11, "learning_rate": 1.9970846052624044e-05, "loss": 0.0984, "step": 121 }, { "epoch": 0.11, "learning_rate": 1.9969736085384422e-05, "loss": 0.0819, "step": 122 }, { "epoch": 0.11, "learning_rate": 1.9968605413377924e-05, "loss": 0.0826, "step": 123 }, { "epoch": 0.11, "learning_rate": 1.996745403895268e-05, "loss": 0.0945, "step": 124 }, { "epoch": 0.11, "learning_rate": 1.9966281964499826e-05, "loss": 0.0816, "step": 125 }, { "epoch": 0.11, "learning_rate": 1.9965089192453475e-05, "loss": 0.0823, "step": 126 }, { "epoch": 0.11, "learning_rate": 1.9963875725290737e-05, "loss": 0.0767, "step": 127 }, { "epoch": 0.11, "learning_rate": 1.9962641565531694e-05, "loss": 0.0822, "step": 128 }, { "epoch": 0.11, "learning_rate": 1.9961386715739395e-05, "loss": 0.0786, "step": 129 }, { "epoch": 0.12, "learning_rate": 1.9960111178519873e-05, "loss": 0.0777, "step": 130 }, { "epoch": 0.12, "learning_rate": 1.9958814956522108e-05, "loss": 0.0797, "step": 131 }, { "epoch": 0.12, "learning_rate": 1.9957498052438046e-05, "loss": 0.0758, "step": 132 }, { "epoch": 0.12, "learning_rate": 1.9956160469002584e-05, "loss": 0.0798, "step": 133 }, { "epoch": 0.12, "learning_rate": 1.9954802208993565e-05, "loss": 0.0721, "step": 134 }, { "epoch": 0.12, "learning_rate": 1.9953423275231773e-05, "loss": 0.08, "step": 135 }, { "epoch": 0.12, "learning_rate": 1.9952023670580915e-05, "loss": 0.0846, "step": 136 }, { "epoch": 0.12, "learning_rate": 1.995060339794765e-05, "loss": 0.0742, "step": 137 }, { "epoch": 0.12, "learning_rate": 1.994916246028154e-05, "loss": 0.0792, "step": 138 }, { "epoch": 0.12, "learning_rate": 1.9947700860575065e-05, "loss": 0.079, "step": 139 }, { "epoch": 0.12, "learning_rate": 1.9946218601863626e-05, "loss": 0.0713, "step": 140 }, { "epoch": 0.13, "learning_rate": 1.994471568722552e-05, "loss": 0.0784, "step": 141 }, { "epoch": 0.13, "learning_rate": 1.994319211978194e-05, "loss": 0.08, "step": 142 }, { "epoch": 0.13, "learning_rate": 1.9941647902696975e-05, "loss": 0.0925, "step": 143 }, { "epoch": 0.13, "learning_rate": 1.9940083039177594e-05, "loss": 0.0636, "step": 144 }, { "epoch": 0.13, "learning_rate": 1.9938497532473646e-05, "loss": 0.0805, "step": 145 }, { "epoch": 0.13, "learning_rate": 1.9936891385877854e-05, "loss": 0.0741, "step": 146 }, { "epoch": 0.13, "learning_rate": 1.9935264602725796e-05, "loss": 0.0726, "step": 147 }, { "epoch": 0.13, "learning_rate": 1.9933617186395917e-05, "loss": 0.0762, "step": 148 }, { "epoch": 0.13, "learning_rate": 1.993194914030951e-05, "loss": 0.0709, "step": 149 }, { "epoch": 0.13, "learning_rate": 1.9930260467930706e-05, "loss": 0.0804, "step": 150 }, { "epoch": 0.13, "learning_rate": 1.9928551172766478e-05, "loss": 0.0815, "step": 151 }, { "epoch": 0.14, "learning_rate": 1.9926821258366622e-05, "loss": 0.0789, "step": 152 }, { "epoch": 0.14, "learning_rate": 1.9925070728323758e-05, "loss": 0.081, "step": 153 }, { "epoch": 0.14, "learning_rate": 1.9923299586273323e-05, "loss": 0.0797, "step": 154 }, { "epoch": 0.14, "learning_rate": 1.9921507835893554e-05, "loss": 0.0789, "step": 155 }, { "epoch": 0.14, "learning_rate": 1.991969548090549e-05, "loss": 0.0758, "step": 156 }, { "epoch": 0.14, "learning_rate": 1.991786252507297e-05, "loss": 0.0717, "step": 157 }, { "epoch": 0.14, "learning_rate": 1.9916008972202586e-05, "loss": 0.0759, "step": 158 }, { "epoch": 0.14, "learning_rate": 1.991413482614375e-05, "loss": 0.0785, "step": 159 }, { "epoch": 0.14, "learning_rate": 1.9912240090788595e-05, "loss": 0.079, "step": 160 }, { "epoch": 0.14, "learning_rate": 1.991032477007205e-05, "loss": 0.0701, "step": 161 }, { "epoch": 0.14, "learning_rate": 1.9908388867971772e-05, "loss": 0.0717, "step": 162 }, { "epoch": 0.15, "learning_rate": 1.9906432388508176e-05, "loss": 0.076, "step": 163 }, { "epoch": 0.15, "learning_rate": 1.9904455335744395e-05, "loss": 0.0775, "step": 164 }, { "epoch": 0.15, "learning_rate": 1.9902457713786303e-05, "loss": 0.0797, "step": 165 }, { "epoch": 0.15, "learning_rate": 1.990043952678248e-05, "loss": 0.0777, "step": 166 }, { "epoch": 0.15, "learning_rate": 1.9898400778924223e-05, "loss": 0.0807, "step": 167 }, { "epoch": 0.15, "learning_rate": 1.9896341474445526e-05, "loss": 0.0856, "step": 168 }, { "epoch": 0.15, "learning_rate": 1.9894261617623073e-05, "loss": 0.0941, "step": 169 }, { "epoch": 0.15, "learning_rate": 1.989216121277623e-05, "loss": 0.0855, "step": 170 }, { "epoch": 0.15, "learning_rate": 1.9890040264267036e-05, "loss": 0.075, "step": 171 }, { "epoch": 0.15, "learning_rate": 1.9887898776500203e-05, "loss": 0.0867, "step": 172 }, { "epoch": 0.15, "learning_rate": 1.9885736753923084e-05, "loss": 0.0826, "step": 173 }, { "epoch": 0.15, "learning_rate": 1.9883554201025687e-05, "loss": 0.0851, "step": 174 }, { "epoch": 0.16, "learning_rate": 1.9881351122340657e-05, "loss": 0.0829, "step": 175 }, { "epoch": 0.16, "learning_rate": 1.9879127522443255e-05, "loss": 0.0781, "step": 176 }, { "epoch": 0.16, "learning_rate": 1.9876883405951378e-05, "loss": 0.0757, "step": 177 }, { "epoch": 0.16, "learning_rate": 1.987461877752552e-05, "loss": 0.0848, "step": 178 }, { "epoch": 0.16, "learning_rate": 1.9872333641868767e-05, "loss": 0.0786, "step": 179 }, { "epoch": 0.16, "learning_rate": 1.987002800372681e-05, "loss": 0.0836, "step": 180 }, { "epoch": 0.16, "learning_rate": 1.986770186788791e-05, "loss": 0.0826, "step": 181 }, { "epoch": 0.16, "learning_rate": 1.9865355239182892e-05, "loss": 0.0818, "step": 182 }, { "epoch": 0.16, "learning_rate": 1.9862988122485145e-05, "loss": 0.0864, "step": 183 }, { "epoch": 0.16, "learning_rate": 1.986060052271061e-05, "loss": 0.0787, "step": 184 }, { "epoch": 0.16, "learning_rate": 1.985819244481776e-05, "loss": 0.0806, "step": 185 }, { "epoch": 0.17, "learning_rate": 1.9855763893807603e-05, "loss": 0.0742, "step": 186 }, { "epoch": 0.17, "learning_rate": 1.9853314874723657e-05, "loss": 0.0742, "step": 187 }, { "epoch": 0.17, "learning_rate": 1.985084539265195e-05, "loss": 0.0809, "step": 188 }, { "epoch": 0.17, "learning_rate": 1.9848355452721012e-05, "loss": 0.0757, "step": 189 }, { "epoch": 0.17, "learning_rate": 1.984584506010186e-05, "loss": 0.0745, "step": 190 }, { "epoch": 0.17, "learning_rate": 1.9843314220007967e-05, "loss": 0.0793, "step": 191 }, { "epoch": 0.17, "learning_rate": 1.9840762937695296e-05, "loss": 0.0768, "step": 192 }, { "epoch": 0.17, "learning_rate": 1.983819121846225e-05, "loss": 0.0803, "step": 193 }, { "epoch": 0.17, "learning_rate": 1.9835599067649676e-05, "loss": 0.0707, "step": 194 }, { "epoch": 0.17, "learning_rate": 1.9832986490640856e-05, "loss": 0.0746, "step": 195 }, { "epoch": 0.17, "learning_rate": 1.9830353492861493e-05, "loss": 0.0831, "step": 196 }, { "epoch": 0.18, "learning_rate": 1.9827700079779685e-05, "loss": 0.0737, "step": 197 }, { "epoch": 0.18, "learning_rate": 1.982502625690595e-05, "loss": 0.0779, "step": 198 }, { "epoch": 0.18, "learning_rate": 1.9822332029793173e-05, "loss": 0.073, "step": 199 }, { "epoch": 0.18, "learning_rate": 1.981961740403663e-05, "loss": 0.0789, "step": 200 }, { "epoch": 0.18, "learning_rate": 1.9816882385273946e-05, "loss": 0.0772, "step": 201 }, { "epoch": 0.18, "learning_rate": 1.9814126979185105e-05, "loss": 0.0685, "step": 202 }, { "epoch": 0.18, "learning_rate": 1.981135119149243e-05, "loss": 0.0778, "step": 203 }, { "epoch": 0.18, "learning_rate": 1.980855502796057e-05, "loss": 0.0737, "step": 204 }, { "epoch": 0.18, "learning_rate": 1.9805738494396492e-05, "loss": 0.077, "step": 205 }, { "epoch": 0.18, "learning_rate": 1.9802901596649462e-05, "loss": 0.0637, "step": 206 }, { "epoch": 0.18, "learning_rate": 1.980004434061104e-05, "loss": 0.072, "step": 207 }, { "epoch": 0.19, "learning_rate": 1.9797166732215078e-05, "loss": 0.087, "step": 208 }, { "epoch": 0.19, "learning_rate": 1.9794268777437668e-05, "loss": 0.0749, "step": 209 }, { "epoch": 0.19, "learning_rate": 1.9791350482297177e-05, "loss": 0.0793, "step": 210 }, { "epoch": 0.19, "learning_rate": 1.9788411852854214e-05, "loss": 0.0734, "step": 211 }, { "epoch": 0.19, "learning_rate": 1.9785452895211606e-05, "loss": 0.0714, "step": 212 }, { "epoch": 0.19, "learning_rate": 1.9782473615514403e-05, "loss": 0.0742, "step": 213 }, { "epoch": 0.19, "learning_rate": 1.9779474019949864e-05, "loss": 0.0771, "step": 214 }, { "epoch": 0.19, "learning_rate": 1.9776454114747432e-05, "loss": 0.0733, "step": 215 }, { "epoch": 0.19, "learning_rate": 1.977341390617873e-05, "loss": 0.0739, "step": 216 }, { "epoch": 0.19, "learning_rate": 1.977035340055755e-05, "loss": 0.0705, "step": 217 }, { "epoch": 0.19, "learning_rate": 1.9767272604239823e-05, "loss": 0.077, "step": 218 }, { "epoch": 0.19, "learning_rate": 1.9764171523623642e-05, "loss": 0.0755, "step": 219 }, { "epoch": 0.2, "learning_rate": 1.9761050165149208e-05, "loss": 0.075, "step": 220 }, { "epoch": 0.2, "learning_rate": 1.9757908535298834e-05, "loss": 0.0717, "step": 221 }, { "epoch": 0.2, "learning_rate": 1.9754746640596945e-05, "loss": 0.0739, "step": 222 }, { "epoch": 0.2, "learning_rate": 1.9751564487610038e-05, "loss": 0.0787, "step": 223 }, { "epoch": 0.2, "learning_rate": 1.974836208294669e-05, "loss": 0.0749, "step": 224 }, { "epoch": 0.2, "learning_rate": 1.9745139433257527e-05, "loss": 0.0736, "step": 225 }, { "epoch": 0.2, "learning_rate": 1.974189654523523e-05, "loss": 0.0765, "step": 226 }, { "epoch": 0.2, "learning_rate": 1.97386334256145e-05, "loss": 0.0681, "step": 227 }, { "epoch": 0.2, "learning_rate": 1.973535008117207e-05, "loss": 0.0707, "step": 228 }, { "epoch": 0.2, "learning_rate": 1.9732046518726652e-05, "loss": 0.0795, "step": 229 }, { "epoch": 0.2, "learning_rate": 1.972872274513896e-05, "loss": 0.0743, "step": 230 }, { "epoch": 0.21, "learning_rate": 1.9725378767311686e-05, "loss": 0.075, "step": 231 }, { "epoch": 0.21, "learning_rate": 1.9722014592189472e-05, "loss": 0.0714, "step": 232 }, { "epoch": 0.21, "learning_rate": 1.971863022675891e-05, "loss": 0.0742, "step": 233 }, { "epoch": 0.21, "learning_rate": 1.9715225678048515e-05, "loss": 0.0698, "step": 234 }, { "epoch": 0.21, "learning_rate": 1.971180095312873e-05, "loss": 0.0676, "step": 235 }, { "epoch": 0.21, "learning_rate": 1.970835605911189e-05, "loss": 0.0744, "step": 236 }, { "epoch": 0.21, "learning_rate": 1.9704891003152223e-05, "loss": 0.0758, "step": 237 }, { "epoch": 0.21, "learning_rate": 1.9701405792445815e-05, "loss": 0.0753, "step": 238 }, { "epoch": 0.21, "learning_rate": 1.9697900434230634e-05, "loss": 0.0735, "step": 239 }, { "epoch": 0.21, "learning_rate": 1.9694374935786457e-05, "loss": 0.0723, "step": 240 }, { "epoch": 0.21, "learning_rate": 1.9690829304434914e-05, "loss": 0.0714, "step": 241 }, { "epoch": 0.22, "learning_rate": 1.968726354753944e-05, "loss": 0.0687, "step": 242 }, { "epoch": 0.22, "learning_rate": 1.9683677672505254e-05, "loss": 0.0715, "step": 243 }, { "epoch": 0.22, "learning_rate": 1.9680071686779368e-05, "loss": 0.0721, "step": 244 }, { "epoch": 0.22, "learning_rate": 1.967644559785056e-05, "loss": 0.0742, "step": 245 }, { "epoch": 0.22, "learning_rate": 1.9672799413249343e-05, "loss": 0.0693, "step": 246 }, { "epoch": 0.22, "learning_rate": 1.966913314054798e-05, "loss": 0.0862, "step": 247 }, { "epoch": 0.22, "learning_rate": 1.9665446787360444e-05, "loss": 0.0694, "step": 248 }, { "epoch": 0.22, "learning_rate": 1.9661740361342417e-05, "loss": 0.0788, "step": 249 }, { "epoch": 0.22, "learning_rate": 1.9658013870191258e-05, "loss": 0.0732, "step": 250 }, { "epoch": 0.22, "learning_rate": 1.9654267321646002e-05, "loss": 0.0762, "step": 251 }, { "epoch": 0.22, "learning_rate": 1.9650500723487335e-05, "loss": 0.0723, "step": 252 }, { "epoch": 0.23, "learning_rate": 1.9646714083537596e-05, "loss": 0.0734, "step": 253 }, { "epoch": 0.23, "learning_rate": 1.964290740966072e-05, "loss": 0.0757, "step": 254 }, { "epoch": 0.23, "learning_rate": 1.963908070976227e-05, "loss": 0.076, "step": 255 }, { "epoch": 0.23, "learning_rate": 1.963523399178939e-05, "loss": 0.0768, "step": 256 }, { "epoch": 0.23, "learning_rate": 1.963136726373079e-05, "loss": 0.0815, "step": 257 }, { "epoch": 0.23, "learning_rate": 1.962748053361675e-05, "loss": 0.0801, "step": 258 }, { "epoch": 0.23, "learning_rate": 1.962357380951908e-05, "loss": 0.0824, "step": 259 }, { "epoch": 0.23, "learning_rate": 1.9619647099551118e-05, "loss": 0.0691, "step": 260 }, { "epoch": 0.23, "learning_rate": 1.96157004118677e-05, "loss": 0.0742, "step": 261 }, { "epoch": 0.23, "learning_rate": 1.9611733754665157e-05, "loss": 0.0706, "step": 262 }, { "epoch": 0.23, "learning_rate": 1.96077471361813e-05, "loss": 0.0732, "step": 263 }, { "epoch": 0.23, "learning_rate": 1.960374056469537e-05, "loss": 0.0734, "step": 264 }, { "epoch": 0.24, "learning_rate": 1.959971404852808e-05, "loss": 0.0703, "step": 265 }, { "epoch": 0.24, "learning_rate": 1.959566759604153e-05, "loss": 0.0708, "step": 266 }, { "epoch": 0.24, "learning_rate": 1.9591601215639244e-05, "loss": 0.0771, "step": 267 }, { "epoch": 0.24, "learning_rate": 1.9587514915766124e-05, "loss": 0.0754, "step": 268 }, { "epoch": 0.24, "learning_rate": 1.9583408704908443e-05, "loss": 0.0711, "step": 269 }, { "epoch": 0.24, "learning_rate": 1.957928259159382e-05, "loss": 0.0711, "step": 270 }, { "epoch": 0.24, "learning_rate": 1.9575136584391215e-05, "loss": 0.081, "step": 271 }, { "epoch": 0.24, "learning_rate": 1.957097069191089e-05, "loss": 0.0772, "step": 272 }, { "epoch": 0.24, "learning_rate": 1.9566784922804415e-05, "loss": 0.0773, "step": 273 }, { "epoch": 0.24, "learning_rate": 1.9562579285764638e-05, "loss": 0.0797, "step": 274 }, { "epoch": 0.24, "learning_rate": 1.9558353789525665e-05, "loss": 0.069, "step": 275 }, { "epoch": 0.25, "learning_rate": 1.9554108442862836e-05, "loss": 0.0681, "step": 276 }, { "epoch": 0.25, "learning_rate": 1.9549843254592735e-05, "loss": 0.0779, "step": 277 }, { "epoch": 0.25, "learning_rate": 1.9545558233573136e-05, "loss": 0.0762, "step": 278 }, { "epoch": 0.25, "learning_rate": 1.9541253388703013e-05, "loss": 0.0772, "step": 279 }, { "epoch": 0.25, "learning_rate": 1.9536928728922496e-05, "loss": 0.0745, "step": 280 }, { "epoch": 0.25, "learning_rate": 1.9532584263212876e-05, "loss": 0.0716, "step": 281 }, { "epoch": 0.25, "learning_rate": 1.9528220000596577e-05, "loss": 0.0663, "step": 282 }, { "epoch": 0.25, "learning_rate": 1.9523835950137128e-05, "loss": 0.078, "step": 283 }, { "epoch": 0.25, "learning_rate": 1.951943212093916e-05, "loss": 0.0765, "step": 284 }, { "epoch": 0.25, "learning_rate": 1.951500852214838e-05, "loss": 0.0645, "step": 285 }, { "epoch": 0.25, "learning_rate": 1.9510565162951538e-05, "loss": 0.0688, "step": 286 }, { "epoch": 0.26, "learning_rate": 1.950610205257644e-05, "loss": 0.0782, "step": 287 }, { "epoch": 0.26, "learning_rate": 1.950161920029191e-05, "loss": 0.0755, "step": 288 }, { "epoch": 0.26, "learning_rate": 1.9497116615407753e-05, "loss": 0.08, "step": 289 }, { "epoch": 0.26, "learning_rate": 1.9492594307274772e-05, "loss": 0.0688, "step": 290 }, { "epoch": 0.26, "learning_rate": 1.9488052285284714e-05, "loss": 0.0684, "step": 291 }, { "epoch": 0.26, "learning_rate": 1.948349055887029e-05, "loss": 0.0693, "step": 292 }, { "epoch": 0.26, "learning_rate": 1.947890913750511e-05, "loss": 0.0708, "step": 293 }, { "epoch": 0.26, "learning_rate": 1.94743080307037e-05, "loss": 0.067, "step": 294 }, { "epoch": 0.26, "learning_rate": 1.946968724802146e-05, "loss": 0.0734, "step": 295 }, { "epoch": 0.26, "learning_rate": 1.9465046799054657e-05, "loss": 0.0694, "step": 296 }, { "epoch": 0.26, "learning_rate": 1.9460386693440394e-05, "loss": 0.0791, "step": 297 }, { "epoch": 0.27, "learning_rate": 1.9455706940856602e-05, "loss": 0.0771, "step": 298 }, { "epoch": 0.27, "learning_rate": 1.9451007551022013e-05, "loss": 0.066, "step": 299 }, { "epoch": 0.27, "learning_rate": 1.9446288533696145e-05, "loss": 0.0671, "step": 300 }, { "epoch": 0.27, "learning_rate": 1.944154989867926e-05, "loss": 0.0811, "step": 301 }, { "epoch": 0.27, "learning_rate": 1.9436791655812392e-05, "loss": 0.08, "step": 302 }, { "epoch": 0.27, "learning_rate": 1.9432013814977258e-05, "loss": 0.0741, "step": 303 }, { "epoch": 0.27, "learning_rate": 1.9427216386096313e-05, "loss": 0.0765, "step": 304 }, { "epoch": 0.27, "learning_rate": 1.942239937913266e-05, "loss": 0.0683, "step": 305 }, { "epoch": 0.27, "learning_rate": 1.9417562804090086e-05, "loss": 0.0752, "step": 306 }, { "epoch": 0.27, "learning_rate": 1.9412706671012997e-05, "loss": 0.0696, "step": 307 }, { "epoch": 0.27, "learning_rate": 1.940783098998643e-05, "loss": 0.071, "step": 308 }, { "epoch": 0.27, "learning_rate": 1.9402935771136013e-05, "loss": 0.0785, "step": 309 }, { "epoch": 0.28, "learning_rate": 1.939802102462794e-05, "loss": 0.0754, "step": 310 }, { "epoch": 0.28, "learning_rate": 1.939308676066898e-05, "loss": 0.0794, "step": 311 }, { "epoch": 0.28, "learning_rate": 1.9388132989506422e-05, "loss": 0.0763, "step": 312 }, { "epoch": 0.28, "learning_rate": 1.9383159721428067e-05, "loss": 0.0666, "step": 313 }, { "epoch": 0.28, "learning_rate": 1.9378166966762207e-05, "loss": 0.082, "step": 314 }, { "epoch": 0.28, "learning_rate": 1.9373154735877603e-05, "loss": 0.0681, "step": 315 }, { "epoch": 0.28, "learning_rate": 1.9368123039183468e-05, "loss": 0.0692, "step": 316 }, { "epoch": 0.28, "learning_rate": 1.9363071887129435e-05, "loss": 0.0753, "step": 317 }, { "epoch": 0.28, "learning_rate": 1.9358001290205542e-05, "loss": 0.0742, "step": 318 }, { "epoch": 0.28, "learning_rate": 1.9352911258942216e-05, "loss": 0.0823, "step": 319 }, { "epoch": 0.28, "learning_rate": 1.9347801803910236e-05, "loss": 0.0749, "step": 320 }, { "epoch": 0.29, "learning_rate": 1.9342672935720723e-05, "loss": 0.0683, "step": 321 }, { "epoch": 0.29, "learning_rate": 1.9337524665025114e-05, "loss": 0.0726, "step": 322 }, { "epoch": 0.29, "learning_rate": 1.9332357002515146e-05, "loss": 0.0769, "step": 323 }, { "epoch": 0.29, "learning_rate": 1.9327169958922813e-05, "loss": 0.0729, "step": 324 }, { "epoch": 0.29, "learning_rate": 1.932196354502038e-05, "loss": 0.0659, "step": 325 }, { "epoch": 0.29, "learning_rate": 1.931673777162032e-05, "loss": 0.0675, "step": 326 }, { "epoch": 0.29, "learning_rate": 1.931149264957532e-05, "loss": 0.0754, "step": 327 }, { "epoch": 0.29, "learning_rate": 1.9306228189778255e-05, "loss": 0.081, "step": 328 }, { "epoch": 0.29, "learning_rate": 1.930094440316215e-05, "loss": 0.0638, "step": 329 }, { "epoch": 0.29, "learning_rate": 1.9295641300700173e-05, "loss": 0.0708, "step": 330 }, { "epoch": 0.29, "learning_rate": 1.92903188934056e-05, "loss": 0.0746, "step": 331 }, { "epoch": 0.3, "learning_rate": 1.9284977192331807e-05, "loss": 0.0682, "step": 332 }, { "epoch": 0.3, "learning_rate": 1.9279616208572236e-05, "loss": 0.0795, "step": 333 }, { "epoch": 0.3, "learning_rate": 1.9274235953260367e-05, "loss": 0.0695, "step": 334 }, { "epoch": 0.3, "learning_rate": 1.9268836437569712e-05, "loss": 0.077, "step": 335 }, { "epoch": 0.3, "learning_rate": 1.9263417672713786e-05, "loss": 0.0836, "step": 336 }, { "epoch": 0.3, "learning_rate": 1.925797966994606e-05, "loss": 0.0685, "step": 337 }, { "epoch": 0.3, "learning_rate": 1.925252244055998e-05, "loss": 0.0786, "step": 338 }, { "epoch": 0.3, "learning_rate": 1.9247045995888905e-05, "loss": 0.0692, "step": 339 }, { "epoch": 0.3, "learning_rate": 1.924155034730611e-05, "loss": 0.0702, "step": 340 }, { "epoch": 0.3, "learning_rate": 1.9236035506224747e-05, "loss": 0.074, "step": 341 }, { "epoch": 0.3, "learning_rate": 1.9230501484097826e-05, "loss": 0.0765, "step": 342 }, { "epoch": 0.31, "learning_rate": 1.9224948292418194e-05, "loss": 0.0699, "step": 343 }, { "epoch": 0.31, "learning_rate": 1.9219375942718508e-05, "loss": 0.0661, "step": 344 }, { "epoch": 0.31, "learning_rate": 1.9213784446571208e-05, "loss": 0.0705, "step": 345 }, { "epoch": 0.31, "learning_rate": 1.9208173815588506e-05, "loss": 0.073, "step": 346 }, { "epoch": 0.31, "learning_rate": 1.9202544061422338e-05, "loss": 0.0732, "step": 347 }, { "epoch": 0.31, "learning_rate": 1.9196895195764363e-05, "loss": 0.0719, "step": 348 }, { "epoch": 0.31, "learning_rate": 1.9191227230345935e-05, "loss": 0.0691, "step": 349 }, { "epoch": 0.31, "learning_rate": 1.9185540176938065e-05, "loss": 0.0753, "step": 350 }, { "epoch": 0.31, "learning_rate": 1.9179834047351407e-05, "loss": 0.0793, "step": 351 }, { "epoch": 0.31, "learning_rate": 1.9174108853436234e-05, "loss": 0.0756, "step": 352 }, { "epoch": 0.31, "learning_rate": 1.916836460708241e-05, "loss": 0.0722, "step": 353 }, { "epoch": 0.31, "learning_rate": 1.9162601320219364e-05, "loss": 0.0755, "step": 354 }, { "epoch": 0.32, "learning_rate": 1.9156819004816075e-05, "loss": 0.0669, "step": 355 }, { "epoch": 0.32, "learning_rate": 1.9151017672881032e-05, "loss": 0.0641, "step": 356 }, { "epoch": 0.32, "learning_rate": 1.9145197336462215e-05, "loss": 0.0761, "step": 357 }, { "epoch": 0.32, "learning_rate": 1.9139358007647085e-05, "loss": 0.0786, "step": 358 }, { "epoch": 0.32, "learning_rate": 1.913349969856253e-05, "loss": 0.0642, "step": 359 }, { "epoch": 0.32, "learning_rate": 1.9127622421374866e-05, "loss": 0.0708, "step": 360 }, { "epoch": 0.32, "learning_rate": 1.9121726188289794e-05, "loss": 0.0769, "step": 361 }, { "epoch": 0.32, "learning_rate": 1.911581101155239e-05, "loss": 0.0767, "step": 362 }, { "epoch": 0.32, "learning_rate": 1.9109876903447065e-05, "loss": 0.0765, "step": 363 }, { "epoch": 0.32, "learning_rate": 1.9103923876297544e-05, "loss": 0.0719, "step": 364 }, { "epoch": 0.32, "learning_rate": 1.9097951942466854e-05, "loss": 0.0752, "step": 365 }, { "epoch": 0.33, "learning_rate": 1.9091961114357274e-05, "loss": 0.0726, "step": 366 }, { "epoch": 0.33, "learning_rate": 1.9085951404410327e-05, "loss": 0.0705, "step": 367 }, { "epoch": 0.33, "learning_rate": 1.907992282510675e-05, "loss": 0.0735, "step": 368 }, { "epoch": 0.33, "learning_rate": 1.9073875388966466e-05, "loss": 0.069, "step": 369 }, { "epoch": 0.33, "learning_rate": 1.906780910854856e-05, "loss": 0.069, "step": 370 }, { "epoch": 0.33, "learning_rate": 1.906172399645125e-05, "loss": 0.0712, "step": 371 }, { "epoch": 0.33, "learning_rate": 1.905562006531186e-05, "loss": 0.066, "step": 372 }, { "epoch": 0.33, "learning_rate": 1.9049497327806815e-05, "loss": 0.0803, "step": 373 }, { "epoch": 0.33, "learning_rate": 1.9043355796651565e-05, "loss": 0.0744, "step": 374 }, { "epoch": 0.33, "learning_rate": 1.9037195484600618e-05, "loss": 0.0734, "step": 375 }, { "epoch": 0.33, "learning_rate": 1.903101640444747e-05, "loss": 0.0702, "step": 376 }, { "epoch": 0.34, "learning_rate": 1.90248185690246e-05, "loss": 0.0732, "step": 377 }, { "epoch": 0.34, "learning_rate": 1.901860199120344e-05, "loss": 0.0789, "step": 378 }, { "epoch": 0.34, "learning_rate": 1.9012366683894335e-05, "loss": 0.0724, "step": 379 }, { "epoch": 0.34, "learning_rate": 1.9006112660046535e-05, "loss": 0.0706, "step": 380 }, { "epoch": 0.34, "learning_rate": 1.8999839932648155e-05, "loss": 0.0881, "step": 381 }, { "epoch": 0.34, "learning_rate": 1.8993548514726162e-05, "loss": 0.07, "step": 382 }, { "epoch": 0.34, "learning_rate": 1.8987238419346328e-05, "loss": 0.0714, "step": 383 }, { "epoch": 0.34, "learning_rate": 1.8980909659613217e-05, "loss": 0.0685, "step": 384 }, { "epoch": 0.34, "learning_rate": 1.897456224867016e-05, "loss": 0.0688, "step": 385 }, { "epoch": 0.34, "learning_rate": 1.896819619969921e-05, "loss": 0.0646, "step": 386 }, { "epoch": 0.34, "learning_rate": 1.896181152592114e-05, "loss": 0.0736, "step": 387 }, { "epoch": 0.35, "learning_rate": 1.8955408240595396e-05, "loss": 0.0756, "step": 388 }, { "epoch": 0.35, "learning_rate": 1.8948986357020074e-05, "loss": 0.0783, "step": 389 }, { "epoch": 0.35, "learning_rate": 1.8942545888531897e-05, "loss": 0.0685, "step": 390 }, { "epoch": 0.35, "learning_rate": 1.8936086848506186e-05, "loss": 0.0688, "step": 391 }, { "epoch": 0.35, "learning_rate": 1.8929609250356827e-05, "loss": 0.0674, "step": 392 }, { "epoch": 0.35, "learning_rate": 1.8923113107536248e-05, "loss": 0.0724, "step": 393 }, { "epoch": 0.35, "learning_rate": 1.891659843353539e-05, "loss": 0.0724, "step": 394 }, { "epoch": 0.35, "learning_rate": 1.891006524188368e-05, "loss": 0.0744, "step": 395 }, { "epoch": 0.35, "learning_rate": 1.8903513546149e-05, "loss": 0.0712, "step": 396 }, { "epoch": 0.35, "learning_rate": 1.8896943359937662e-05, "loss": 0.0733, "step": 397 }, { "epoch": 0.35, "learning_rate": 1.8890354696894374e-05, "loss": 0.0772, "step": 398 }, { "epoch": 0.35, "learning_rate": 1.8883747570702223e-05, "loss": 0.0736, "step": 399 }, { "epoch": 0.36, "learning_rate": 1.8877121995082638e-05, "loss": 0.0758, "step": 400 }, { "epoch": 0.36, "learning_rate": 1.887047798379536e-05, "loss": 0.0722, "step": 401 }, { "epoch": 0.36, "learning_rate": 1.8863815550638414e-05, "loss": 0.0737, "step": 402 }, { "epoch": 0.36, "learning_rate": 1.8857134709448094e-05, "loss": 0.0723, "step": 403 }, { "epoch": 0.36, "learning_rate": 1.8850435474098903e-05, "loss": 0.0761, "step": 404 }, { "epoch": 0.36, "learning_rate": 1.8843717858503573e-05, "loss": 0.0733, "step": 405 }, { "epoch": 0.36, "learning_rate": 1.883698187661298e-05, "loss": 0.0809, "step": 406 }, { "epoch": 0.36, "learning_rate": 1.8830227542416154e-05, "loss": 0.0773, "step": 407 }, { "epoch": 0.36, "learning_rate": 1.8823454869940243e-05, "loss": 0.0713, "step": 408 }, { "epoch": 0.36, "learning_rate": 1.8816663873250475e-05, "loss": 0.073, "step": 409 }, { "epoch": 0.36, "learning_rate": 1.8809854566450128e-05, "loss": 0.0768, "step": 410 }, { "epoch": 0.37, "learning_rate": 1.880302696368051e-05, "loss": 0.0648, "step": 411 }, { "epoch": 0.37, "learning_rate": 1.879618107912093e-05, "loss": 0.0754, "step": 412 }, { "epoch": 0.37, "learning_rate": 1.8789316926988656e-05, "loss": 0.0722, "step": 413 }, { "epoch": 0.37, "learning_rate": 1.87824345215389e-05, "loss": 0.0703, "step": 414 }, { "epoch": 0.37, "learning_rate": 1.8775533877064772e-05, "loss": 0.074, "step": 415 }, { "epoch": 0.37, "learning_rate": 1.8768615007897274e-05, "loss": 0.0751, "step": 416 }, { "epoch": 0.37, "learning_rate": 1.8761677928405245e-05, "loss": 0.07, "step": 417 }, { "epoch": 0.37, "learning_rate": 1.8754722652995346e-05, "loss": 0.0706, "step": 418 }, { "epoch": 0.37, "learning_rate": 1.874774919611203e-05, "loss": 0.068, "step": 419 }, { "epoch": 0.37, "learning_rate": 1.874075757223751e-05, "loss": 0.0782, "step": 420 }, { "epoch": 0.37, "learning_rate": 1.873374779589171e-05, "loss": 0.0713, "step": 421 }, { "epoch": 0.38, "learning_rate": 1.8726719881632278e-05, "loss": 0.0719, "step": 422 }, { "epoch": 0.38, "learning_rate": 1.871967384405451e-05, "loss": 0.07, "step": 423 }, { "epoch": 0.38, "learning_rate": 1.871260969779135e-05, "loss": 0.0695, "step": 424 }, { "epoch": 0.38, "learning_rate": 1.8705527457513353e-05, "loss": 0.0764, "step": 425 }, { "epoch": 0.38, "learning_rate": 1.8698427137928637e-05, "loss": 0.0721, "step": 426 }, { "epoch": 0.38, "learning_rate": 1.8691308753782874e-05, "loss": 0.0681, "step": 427 }, { "epoch": 0.38, "learning_rate": 1.8684172319859258e-05, "loss": 0.0743, "step": 428 }, { "epoch": 0.38, "learning_rate": 1.867701785097846e-05, "loss": 0.0753, "step": 429 }, { "epoch": 0.38, "learning_rate": 1.8669845361998607e-05, "loss": 0.0715, "step": 430 }, { "epoch": 0.38, "learning_rate": 1.8662654867815247e-05, "loss": 0.0658, "step": 431 }, { "epoch": 0.38, "learning_rate": 1.8655446383361332e-05, "loss": 0.0753, "step": 432 }, { "epoch": 0.39, "learning_rate": 1.8648219923607156e-05, "loss": 0.0711, "step": 433 }, { "epoch": 0.39, "learning_rate": 1.864097550356036e-05, "loss": 0.0695, "step": 434 }, { "epoch": 0.39, "learning_rate": 1.8633713138265884e-05, "loss": 0.0757, "step": 435 }, { "epoch": 0.39, "learning_rate": 1.862643284280592e-05, "loss": 0.0725, "step": 436 }, { "epoch": 0.39, "learning_rate": 1.8619134632299913e-05, "loss": 0.066, "step": 437 }, { "epoch": 0.39, "learning_rate": 1.861181852190451e-05, "loss": 0.0736, "step": 438 }, { "epoch": 0.39, "learning_rate": 1.8604484526813525e-05, "loss": 0.0718, "step": 439 }, { "epoch": 0.39, "learning_rate": 1.859713266225792e-05, "loss": 0.0706, "step": 440 }, { "epoch": 0.39, "learning_rate": 1.8589762943505767e-05, "loss": 0.0684, "step": 441 }, { "epoch": 0.39, "learning_rate": 1.8582375385862215e-05, "loss": 0.0678, "step": 442 }, { "epoch": 0.39, "learning_rate": 1.8574970004669464e-05, "loss": 0.0656, "step": 443 }, { "epoch": 0.4, "learning_rate": 1.8567546815306726e-05, "loss": 0.0702, "step": 444 }, { "epoch": 0.4, "learning_rate": 1.8560105833190195e-05, "loss": 0.0812, "step": 445 }, { "epoch": 0.4, "learning_rate": 1.855264707377302e-05, "loss": 0.0772, "step": 446 }, { "epoch": 0.4, "learning_rate": 1.8545170552545268e-05, "loss": 0.084, "step": 447 }, { "epoch": 0.4, "learning_rate": 1.8537676285033886e-05, "loss": 0.0724, "step": 448 }, { "epoch": 0.4, "learning_rate": 1.8530164286802695e-05, "loss": 0.0682, "step": 449 }, { "epoch": 0.4, "learning_rate": 1.8522634573452314e-05, "loss": 0.0781, "step": 450 }, { "epoch": 0.4, "learning_rate": 1.851508716062017e-05, "loss": 0.0758, "step": 451 }, { "epoch": 0.4, "learning_rate": 1.8507522063980436e-05, "loss": 0.074, "step": 452 }, { "epoch": 0.4, "learning_rate": 1.8499939299244027e-05, "loss": 0.0703, "step": 453 }, { "epoch": 0.4, "learning_rate": 1.8492338882158526e-05, "loss": 0.0668, "step": 454 }, { "epoch": 0.4, "learning_rate": 1.8484720828508195e-05, "loss": 0.0807, "step": 455 }, { "epoch": 0.41, "learning_rate": 1.8477085154113913e-05, "loss": 0.0659, "step": 456 }, { "epoch": 0.41, "learning_rate": 1.8469431874833166e-05, "loss": 0.0753, "step": 457 }, { "epoch": 0.41, "learning_rate": 1.8461761006559982e-05, "loss": 0.078, "step": 458 }, { "epoch": 0.41, "learning_rate": 1.8454072565224933e-05, "loss": 0.0728, "step": 459 }, { "epoch": 0.41, "learning_rate": 1.8446366566795075e-05, "loss": 0.0722, "step": 460 }, { "epoch": 0.41, "learning_rate": 1.8438643027273937e-05, "loss": 0.0742, "step": 461 }, { "epoch": 0.41, "learning_rate": 1.8430901962701465e-05, "loss": 0.0729, "step": 462 }, { "epoch": 0.41, "learning_rate": 1.842314338915401e-05, "loss": 0.0635, "step": 463 }, { "epoch": 0.41, "learning_rate": 1.841536732274428e-05, "loss": 0.0721, "step": 464 }, { "epoch": 0.41, "learning_rate": 1.840757377962131e-05, "loss": 0.0812, "step": 465 }, { "epoch": 0.41, "learning_rate": 1.839976277597044e-05, "loss": 0.0776, "step": 466 }, { "epoch": 0.42, "learning_rate": 1.8391934328013254e-05, "loss": 0.0756, "step": 467 }, { "epoch": 0.42, "learning_rate": 1.838408845200758e-05, "loss": 0.0726, "step": 468 }, { "epoch": 0.42, "learning_rate": 1.8376225164247427e-05, "loss": 0.066, "step": 469 }, { "epoch": 0.42, "learning_rate": 1.836834448106298e-05, "loss": 0.0649, "step": 470 }, { "epoch": 0.42, "learning_rate": 1.8360446418820534e-05, "loss": 0.0758, "step": 471 }, { "epoch": 0.42, "learning_rate": 1.8352530993922483e-05, "loss": 0.0768, "step": 472 }, { "epoch": 0.42, "learning_rate": 1.8344598222807285e-05, "loss": 0.0692, "step": 473 }, { "epoch": 0.42, "learning_rate": 1.8336648121949405e-05, "loss": 0.0715, "step": 474 }, { "epoch": 0.42, "learning_rate": 1.832868070785932e-05, "loss": 0.0695, "step": 475 }, { "epoch": 0.42, "learning_rate": 1.8320695997083443e-05, "loss": 0.0695, "step": 476 }, { "epoch": 0.42, "learning_rate": 1.8312694006204122e-05, "loss": 0.0692, "step": 477 }, { "epoch": 0.43, "learning_rate": 1.8304674751839583e-05, "loss": 0.078, "step": 478 }, { "epoch": 0.43, "learning_rate": 1.8296638250643904e-05, "loss": 0.074, "step": 479 }, { "epoch": 0.43, "learning_rate": 1.8288584519306985e-05, "loss": 0.0701, "step": 480 }, { "epoch": 0.43, "learning_rate": 1.8280513574554514e-05, "loss": 0.0854, "step": 481 }, { "epoch": 0.43, "learning_rate": 1.8272425433147916e-05, "loss": 0.0735, "step": 482 }, { "epoch": 0.43, "learning_rate": 1.826432011188433e-05, "loss": 0.07, "step": 483 }, { "epoch": 0.43, "learning_rate": 1.8256197627596582e-05, "loss": 0.0659, "step": 484 }, { "epoch": 0.43, "learning_rate": 1.8248057997153137e-05, "loss": 0.0803, "step": 485 }, { "epoch": 0.43, "learning_rate": 1.8239901237458064e-05, "loss": 0.0751, "step": 486 }, { "epoch": 0.43, "learning_rate": 1.8231727365451017e-05, "loss": 0.0694, "step": 487 }, { "epoch": 0.43, "learning_rate": 1.8223536398107177e-05, "loss": 0.0844, "step": 488 }, { "epoch": 0.44, "learning_rate": 1.821532835243723e-05, "loss": 0.0719, "step": 489 }, { "epoch": 0.44, "learning_rate": 1.8207103245487335e-05, "loss": 0.0654, "step": 490 }, { "epoch": 0.44, "learning_rate": 1.8198861094339077e-05, "loss": 0.0799, "step": 491 }, { "epoch": 0.44, "learning_rate": 1.8190601916109444e-05, "loss": 0.0676, "step": 492 }, { "epoch": 0.44, "learning_rate": 1.818232572795078e-05, "loss": 0.0785, "step": 493 }, { "epoch": 0.44, "learning_rate": 1.8174032547050754e-05, "loss": 0.074, "step": 494 }, { "epoch": 0.44, "learning_rate": 1.816572239063233e-05, "loss": 0.0713, "step": 495 }, { "epoch": 0.44, "learning_rate": 1.8157395275953722e-05, "loss": 0.0666, "step": 496 }, { "epoch": 0.44, "learning_rate": 1.814905122030836e-05, "loss": 0.073, "step": 497 }, { "epoch": 0.44, "learning_rate": 1.8140690241024872e-05, "loss": 0.0741, "step": 498 }, { "epoch": 0.44, "learning_rate": 1.8132312355467004e-05, "loss": 0.0739, "step": 499 }, { "epoch": 0.44, "learning_rate": 1.8123917581033642e-05, "loss": 0.0718, "step": 500 }, { "epoch": 0.45, "learning_rate": 1.8115505935158726e-05, "loss": 0.0723, "step": 501 }, { "epoch": 0.45, "learning_rate": 1.810707743531124e-05, "loss": 0.0692, "step": 502 }, { "epoch": 0.45, "learning_rate": 1.8098632098995174e-05, "loss": 0.0745, "step": 503 }, { "epoch": 0.45, "learning_rate": 1.8090169943749477e-05, "loss": 0.0738, "step": 504 }, { "epoch": 0.45, "learning_rate": 1.8081690987148032e-05, "loss": 0.076, "step": 505 }, { "epoch": 0.45, "learning_rate": 1.8073195246799605e-05, "loss": 0.0637, "step": 506 }, { "epoch": 0.45, "learning_rate": 1.8064682740347837e-05, "loss": 0.0748, "step": 507 }, { "epoch": 0.45, "learning_rate": 1.8056153485471167e-05, "loss": 0.0684, "step": 508 }, { "epoch": 0.45, "learning_rate": 1.8047607499882825e-05, "loss": 0.0721, "step": 509 }, { "epoch": 0.45, "learning_rate": 1.8039044801330795e-05, "loss": 0.0734, "step": 510 }, { "epoch": 0.45, "learning_rate": 1.8030465407597754e-05, "loss": 0.0677, "step": 511 }, { "epoch": 0.46, "learning_rate": 1.8021869336501066e-05, "loss": 0.0632, "step": 512 }, { "epoch": 0.46, "learning_rate": 1.801325660589272e-05, "loss": 0.0665, "step": 513 }, { "epoch": 0.46, "learning_rate": 1.80046272336593e-05, "loss": 0.073, "step": 514 }, { "epoch": 0.46, "learning_rate": 1.799598123772196e-05, "loss": 0.0784, "step": 515 }, { "epoch": 0.46, "learning_rate": 1.7987318636036382e-05, "loss": 0.0695, "step": 516 }, { "epoch": 0.46, "learning_rate": 1.797863944659272e-05, "loss": 0.074, "step": 517 }, { "epoch": 0.46, "learning_rate": 1.7969943687415575e-05, "loss": 0.0735, "step": 518 }, { "epoch": 0.46, "learning_rate": 1.7961231376563982e-05, "loss": 0.0623, "step": 519 }, { "epoch": 0.46, "learning_rate": 1.7952502532131326e-05, "loss": 0.0669, "step": 520 }, { "epoch": 0.46, "learning_rate": 1.794375717224534e-05, "loss": 0.0701, "step": 521 }, { "epoch": 0.46, "learning_rate": 1.793499531506805e-05, "loss": 0.0665, "step": 522 }, { "epoch": 0.47, "learning_rate": 1.792621697879575e-05, "loss": 0.0731, "step": 523 }, { "epoch": 0.47, "learning_rate": 1.7917422181658954e-05, "loss": 0.0744, "step": 524 }, { "epoch": 0.47, "learning_rate": 1.790861094192236e-05, "loss": 0.0731, "step": 525 }, { "epoch": 0.47, "learning_rate": 1.789978327788481e-05, "loss": 0.0645, "step": 526 }, { "epoch": 0.47, "learning_rate": 1.7890939207879265e-05, "loss": 0.0739, "step": 527 }, { "epoch": 0.47, "learning_rate": 1.788207875027274e-05, "loss": 0.077, "step": 528 }, { "epoch": 0.47, "learning_rate": 1.7873201923466313e-05, "loss": 0.0686, "step": 529 }, { "epoch": 0.47, "learning_rate": 1.7864308745895024e-05, "loss": 0.0679, "step": 530 }, { "epoch": 0.47, "learning_rate": 1.785539923602789e-05, "loss": 0.0713, "step": 531 }, { "epoch": 0.47, "learning_rate": 1.7846473412367845e-05, "loss": 0.0734, "step": 532 }, { "epoch": 0.47, "learning_rate": 1.783753129345169e-05, "loss": 0.067, "step": 533 }, { "epoch": 0.48, "learning_rate": 1.7828572897850076e-05, "loss": 0.0739, "step": 534 }, { "epoch": 0.48, "learning_rate": 1.781959824416746e-05, "loss": 0.0683, "step": 535 }, { "epoch": 0.48, "learning_rate": 1.7810607351042062e-05, "loss": 0.0712, "step": 536 }, { "epoch": 0.48, "learning_rate": 1.7801600237145823e-05, "loss": 0.0722, "step": 537 }, { "epoch": 0.48, "learning_rate": 1.7792576921184374e-05, "loss": 0.0718, "step": 538 }, { "epoch": 0.48, "learning_rate": 1.778353742189699e-05, "loss": 0.0703, "step": 539 }, { "epoch": 0.48, "learning_rate": 1.7774481758056553e-05, "loss": 0.0657, "step": 540 }, { "epoch": 0.48, "learning_rate": 1.7765409948469533e-05, "loss": 0.0681, "step": 541 }, { "epoch": 0.48, "learning_rate": 1.7756322011975906e-05, "loss": 0.0743, "step": 542 }, { "epoch": 0.48, "learning_rate": 1.774721796744916e-05, "loss": 0.0693, "step": 543 }, { "epoch": 0.48, "learning_rate": 1.7738097833796218e-05, "loss": 0.0696, "step": 544 }, { "epoch": 0.48, "learning_rate": 1.772896162995743e-05, "loss": 0.0637, "step": 545 }, { "epoch": 0.49, "learning_rate": 1.771980937490651e-05, "loss": 0.0748, "step": 546 }, { "epoch": 0.49, "learning_rate": 1.771064108765052e-05, "loss": 0.0737, "step": 547 }, { "epoch": 0.49, "learning_rate": 1.7701456787229805e-05, "loss": 0.0706, "step": 548 }, { "epoch": 0.49, "learning_rate": 1.769225649271797e-05, "loss": 0.0677, "step": 549 }, { "epoch": 0.49, "learning_rate": 1.7683040223221828e-05, "loss": 0.0638, "step": 550 }, { "epoch": 0.49, "learning_rate": 1.7673807997881383e-05, "loss": 0.0707, "step": 551 }, { "epoch": 0.49, "learning_rate": 1.7664559835869763e-05, "loss": 0.0725, "step": 552 }, { "epoch": 0.49, "learning_rate": 1.76552957563932e-05, "loss": 0.0766, "step": 553 }, { "epoch": 0.49, "learning_rate": 1.7646015778690983e-05, "loss": 0.0738, "step": 554 }, { "epoch": 0.49, "learning_rate": 1.763671992203541e-05, "loss": 0.0756, "step": 555 }, { "epoch": 0.49, "learning_rate": 1.7627408205731762e-05, "loss": 0.0769, "step": 556 }, { "epoch": 0.5, "learning_rate": 1.7618080649118256e-05, "loss": 0.0715, "step": 557 }, { "epoch": 0.5, "learning_rate": 1.7608737271566004e-05, "loss": 0.0744, "step": 558 }, { "epoch": 0.5, "learning_rate": 1.759937809247898e-05, "loss": 0.0752, "step": 559 }, { "epoch": 0.5, "learning_rate": 1.7590003131293967e-05, "loss": 0.074, "step": 560 }, { "epoch": 0.5, "learning_rate": 1.7580612407480526e-05, "loss": 0.0772, "step": 561 }, { "epoch": 0.5, "learning_rate": 1.7571205940540945e-05, "loss": 0.0723, "step": 562 }, { "epoch": 0.5, "learning_rate": 1.756178375001023e-05, "loss": 0.0684, "step": 563 }, { "epoch": 0.5, "learning_rate": 1.7552345855456017e-05, "loss": 0.0646, "step": 564 }, { "epoch": 0.5, "learning_rate": 1.7542892276478563e-05, "loss": 0.0667, "step": 565 }, { "epoch": 0.5, "learning_rate": 1.7533423032710705e-05, "loss": 0.0724, "step": 566 }, { "epoch": 0.5, "learning_rate": 1.752393814381781e-05, "loss": 0.0691, "step": 567 }, { "epoch": 0.51, "learning_rate": 1.751443762949772e-05, "loss": 0.0662, "step": 568 }, { "epoch": 0.51, "learning_rate": 1.750492150948075e-05, "loss": 0.0748, "step": 569 }, { "epoch": 0.51, "learning_rate": 1.7495389803529615e-05, "loss": 0.0736, "step": 570 }, { "epoch": 0.51, "learning_rate": 1.748584253143939e-05, "loss": 0.0713, "step": 571 }, { "epoch": 0.51, "learning_rate": 1.747627971303749e-05, "loss": 0.0705, "step": 572 }, { "epoch": 0.51, "learning_rate": 1.7466701368183612e-05, "loss": 0.0684, "step": 573 }, { "epoch": 0.51, "learning_rate": 1.7457107516769697e-05, "loss": 0.0673, "step": 574 }, { "epoch": 0.51, "learning_rate": 1.7447498178719882e-05, "loss": 0.0754, "step": 575 }, { "epoch": 0.51, "learning_rate": 1.7437873373990478e-05, "loss": 0.0662, "step": 576 }, { "epoch": 0.51, "learning_rate": 1.742823312256991e-05, "loss": 0.0633, "step": 577 }, { "epoch": 0.51, "learning_rate": 1.741857744447869e-05, "loss": 0.0748, "step": 578 }, { "epoch": 0.52, "learning_rate": 1.7408906359769352e-05, "loss": 0.0727, "step": 579 }, { "epoch": 0.52, "learning_rate": 1.7399219888526438e-05, "loss": 0.0661, "step": 580 }, { "epoch": 0.52, "learning_rate": 1.7389518050866445e-05, "loss": 0.0697, "step": 581 }, { "epoch": 0.52, "learning_rate": 1.7379800866937773e-05, "loss": 0.0625, "step": 582 }, { "epoch": 0.52, "learning_rate": 1.7370068356920708e-05, "loss": 0.0688, "step": 583 }, { "epoch": 0.52, "learning_rate": 1.7360320541027342e-05, "loss": 0.0671, "step": 584 }, { "epoch": 0.52, "learning_rate": 1.7350557439501576e-05, "loss": 0.0686, "step": 585 }, { "epoch": 0.52, "learning_rate": 1.7340779072619043e-05, "loss": 0.0713, "step": 586 }, { "epoch": 0.52, "learning_rate": 1.733098546068708e-05, "loss": 0.0777, "step": 587 }, { "epoch": 0.52, "learning_rate": 1.732117662404469e-05, "loss": 0.069, "step": 588 }, { "epoch": 0.52, "learning_rate": 1.7311352583062485e-05, "loss": 0.0773, "step": 589 }, { "epoch": 0.52, "learning_rate": 1.730151335814266e-05, "loss": 0.0714, "step": 590 }, { "epoch": 0.53, "learning_rate": 1.7291658969718942e-05, "loss": 0.0685, "step": 591 }, { "epoch": 0.53, "learning_rate": 1.728178943825655e-05, "loss": 0.0744, "step": 592 }, { "epoch": 0.53, "learning_rate": 1.7271904784252143e-05, "loss": 0.0741, "step": 593 }, { "epoch": 0.53, "learning_rate": 1.7262005028233802e-05, "loss": 0.0725, "step": 594 }, { "epoch": 0.53, "learning_rate": 1.7252090190760954e-05, "loss": 0.0707, "step": 595 }, { "epoch": 0.53, "learning_rate": 1.7242160292424362e-05, "loss": 0.0684, "step": 596 }, { "epoch": 0.53, "learning_rate": 1.7232215353846054e-05, "loss": 0.0717, "step": 597 }, { "epoch": 0.53, "learning_rate": 1.7222255395679298e-05, "loss": 0.064, "step": 598 }, { "epoch": 0.53, "learning_rate": 1.7212280438608554e-05, "loss": 0.0727, "step": 599 }, { "epoch": 0.53, "learning_rate": 1.7202290503349436e-05, "loss": 0.0611, "step": 600 }, { "epoch": 0.53, "learning_rate": 1.719228561064866e-05, "loss": 0.0724, "step": 601 }, { "epoch": 0.54, "learning_rate": 1.7182265781284e-05, "loss": 0.0718, "step": 602 }, { "epoch": 0.54, "learning_rate": 1.7172231036064257e-05, "loss": 0.0695, "step": 603 }, { "epoch": 0.54, "learning_rate": 1.7162181395829204e-05, "loss": 0.0616, "step": 604 }, { "epoch": 0.54, "learning_rate": 1.7152116881449554e-05, "loss": 0.0743, "step": 605 }, { "epoch": 0.54, "learning_rate": 1.7142037513826904e-05, "loss": 0.0703, "step": 606 }, { "epoch": 0.54, "learning_rate": 1.71319433138937e-05, "loss": 0.067, "step": 607 }, { "epoch": 0.54, "learning_rate": 1.712183430261319e-05, "loss": 0.0681, "step": 608 }, { "epoch": 0.54, "learning_rate": 1.711171050097938e-05, "loss": 0.0692, "step": 609 }, { "epoch": 0.54, "learning_rate": 1.7101571930017e-05, "loss": 0.0726, "step": 610 }, { "epoch": 0.54, "learning_rate": 1.7091418610781438e-05, "loss": 0.0722, "step": 611 }, { "epoch": 0.54, "learning_rate": 1.708125056435873e-05, "loss": 0.068, "step": 612 }, { "epoch": 0.55, "learning_rate": 1.7071067811865477e-05, "loss": 0.0644, "step": 613 }, { "epoch": 0.55, "learning_rate": 1.7060870374448833e-05, "loss": 0.0702, "step": 614 }, { "epoch": 0.55, "learning_rate": 1.7050658273286454e-05, "loss": 0.0696, "step": 615 }, { "epoch": 0.55, "learning_rate": 1.7040431529586427e-05, "loss": 0.0706, "step": 616 }, { "epoch": 0.55, "learning_rate": 1.7030190164587278e-05, "loss": 0.0624, "step": 617 }, { "epoch": 0.55, "learning_rate": 1.7019934199557868e-05, "loss": 0.0728, "step": 618 }, { "epoch": 0.55, "learning_rate": 1.70096636557974e-05, "loss": 0.0678, "step": 619 }, { "epoch": 0.55, "learning_rate": 1.699937855463535e-05, "loss": 0.0732, "step": 620 }, { "epoch": 0.55, "learning_rate": 1.6989078917431417e-05, "loss": 0.0747, "step": 621 }, { "epoch": 0.55, "learning_rate": 1.69787647655755e-05, "loss": 0.0687, "step": 622 }, { "epoch": 0.55, "learning_rate": 1.696843612048763e-05, "loss": 0.0738, "step": 623 }, { "epoch": 0.56, "learning_rate": 1.6958093003617942e-05, "loss": 0.0693, "step": 624 }, { "epoch": 0.56, "learning_rate": 1.6947735436446634e-05, "loss": 0.065, "step": 625 }, { "epoch": 0.56, "learning_rate": 1.6937363440483892e-05, "loss": 0.0833, "step": 626 }, { "epoch": 0.56, "learning_rate": 1.6926977037269896e-05, "loss": 0.0695, "step": 627 }, { "epoch": 0.56, "learning_rate": 1.691657624837472e-05, "loss": 0.0668, "step": 628 }, { "epoch": 0.56, "learning_rate": 1.690616109539833e-05, "loss": 0.0723, "step": 629 }, { "epoch": 0.56, "learning_rate": 1.6895731599970516e-05, "loss": 0.0725, "step": 630 }, { "epoch": 0.56, "learning_rate": 1.6885287783750855e-05, "loss": 0.0697, "step": 631 }, { "epoch": 0.56, "learning_rate": 1.6874829668428667e-05, "loss": 0.074, "step": 632 }, { "epoch": 0.56, "learning_rate": 1.6864357275722966e-05, "loss": 0.0711, "step": 633 }, { "epoch": 0.56, "learning_rate": 1.6853870627382416e-05, "loss": 0.0811, "step": 634 }, { "epoch": 0.56, "learning_rate": 1.6843369745185286e-05, "loss": 0.0749, "step": 635 }, { "epoch": 0.57, "learning_rate": 1.683285465093941e-05, "loss": 0.0746, "step": 636 }, { "epoch": 0.57, "learning_rate": 1.6822325366482135e-05, "loss": 0.0689, "step": 637 }, { "epoch": 0.57, "learning_rate": 1.6811781913680273e-05, "loss": 0.0683, "step": 638 }, { "epoch": 0.57, "learning_rate": 1.680122431443006e-05, "loss": 0.0634, "step": 639 }, { "epoch": 0.57, "learning_rate": 1.6790652590657125e-05, "loss": 0.072, "step": 640 }, { "epoch": 0.57, "learning_rate": 1.6780066764316415e-05, "loss": 0.0707, "step": 641 }, { "epoch": 0.57, "learning_rate": 1.6769466857392167e-05, "loss": 0.0811, "step": 642 }, { "epoch": 0.57, "learning_rate": 1.6758852891897865e-05, "loss": 0.0691, "step": 643 }, { "epoch": 0.57, "learning_rate": 1.6748224889876188e-05, "loss": 0.0688, "step": 644 }, { "epoch": 0.57, "learning_rate": 1.6737582873398963e-05, "loss": 0.07, "step": 645 }, { "epoch": 0.57, "learning_rate": 1.672692686456712e-05, "loss": 0.0718, "step": 646 }, { "epoch": 0.58, "learning_rate": 1.6716256885510656e-05, "loss": 0.0701, "step": 647 }, { "epoch": 0.58, "learning_rate": 1.6705572958388576e-05, "loss": 0.0675, "step": 648 }, { "epoch": 0.58, "learning_rate": 1.6694875105388846e-05, "loss": 0.0638, "step": 649 }, { "epoch": 0.58, "learning_rate": 1.6684163348728364e-05, "loss": 0.0655, "step": 650 }, { "epoch": 0.58, "learning_rate": 1.6673437710652894e-05, "loss": 0.0718, "step": 651 }, { "epoch": 0.58, "learning_rate": 1.666269821343703e-05, "loss": 0.0652, "step": 652 }, { "epoch": 0.58, "learning_rate": 1.665194487938415e-05, "loss": 0.0707, "step": 653 }, { "epoch": 0.58, "learning_rate": 1.664117773082637e-05, "loss": 0.0724, "step": 654 }, { "epoch": 0.58, "learning_rate": 1.663039679012449e-05, "loss": 0.0636, "step": 655 }, { "epoch": 0.58, "learning_rate": 1.6619602079667956e-05, "loss": 0.0693, "step": 656 }, { "epoch": 0.58, "learning_rate": 1.6608793621874812e-05, "loss": 0.0849, "step": 657 }, { "epoch": 0.59, "learning_rate": 1.659797143919165e-05, "loss": 0.0645, "step": 658 }, { "epoch": 0.59, "learning_rate": 1.658713555409356e-05, "loss": 0.0692, "step": 659 }, { "epoch": 0.59, "learning_rate": 1.65762859890841e-05, "loss": 0.0623, "step": 660 }, { "epoch": 0.59, "learning_rate": 1.6565422766695232e-05, "loss": 0.0735, "step": 661 }, { "epoch": 0.59, "learning_rate": 1.6554545909487277e-05, "loss": 0.0724, "step": 662 }, { "epoch": 0.59, "learning_rate": 1.654365544004888e-05, "loss": 0.0713, "step": 663 }, { "epoch": 0.59, "learning_rate": 1.653275138099695e-05, "loss": 0.0799, "step": 664 }, { "epoch": 0.59, "learning_rate": 1.6521833754976616e-05, "loss": 0.0652, "step": 665 }, { "epoch": 0.59, "learning_rate": 1.6510902584661195e-05, "loss": 0.0839, "step": 666 }, { "epoch": 0.59, "learning_rate": 1.649995789275212e-05, "loss": 0.0738, "step": 667 }, { "epoch": 0.59, "learning_rate": 1.6488999701978905e-05, "loss": 0.066, "step": 668 }, { "epoch": 0.6, "learning_rate": 1.6478028035099108e-05, "loss": 0.0684, "step": 669 }, { "epoch": 0.6, "learning_rate": 1.6467042914898262e-05, "loss": 0.0738, "step": 670 }, { "epoch": 0.6, "learning_rate": 1.6456044364189852e-05, "loss": 0.0802, "step": 671 }, { "epoch": 0.6, "learning_rate": 1.644503240581524e-05, "loss": 0.0735, "step": 672 }, { "epoch": 0.6, "learning_rate": 1.643400706264364e-05, "loss": 0.0726, "step": 673 }, { "epoch": 0.6, "learning_rate": 1.6422968357572076e-05, "loss": 0.0673, "step": 674 }, { "epoch": 0.6, "learning_rate": 1.6411916313525293e-05, "loss": 0.0687, "step": 675 }, { "epoch": 0.6, "learning_rate": 1.640085095345576e-05, "loss": 0.07, "step": 676 }, { "epoch": 0.6, "learning_rate": 1.63897723003436e-05, "loss": 0.0687, "step": 677 }, { "epoch": 0.6, "learning_rate": 1.6378680377196526e-05, "loss": 0.0707, "step": 678 }, { "epoch": 0.6, "learning_rate": 1.6367575207049825e-05, "loss": 0.0671, "step": 679 }, { "epoch": 0.6, "learning_rate": 1.635645681296629e-05, "loss": 0.07, "step": 680 }, { "epoch": 0.61, "learning_rate": 1.6345325218036173e-05, "loss": 0.0739, "step": 681 }, { "epoch": 0.61, "learning_rate": 1.6334180445377156e-05, "loss": 0.0707, "step": 682 }, { "epoch": 0.61, "learning_rate": 1.6323022518134265e-05, "loss": 0.0764, "step": 683 }, { "epoch": 0.61, "learning_rate": 1.631185145947986e-05, "loss": 0.0705, "step": 684 }, { "epoch": 0.61, "learning_rate": 1.6300667292613574e-05, "loss": 0.0696, "step": 685 }, { "epoch": 0.61, "learning_rate": 1.628947004076225e-05, "loss": 0.0751, "step": 686 }, { "epoch": 0.61, "learning_rate": 1.627825972717992e-05, "loss": 0.0681, "step": 687 }, { "epoch": 0.61, "learning_rate": 1.6267036375147728e-05, "loss": 0.0636, "step": 688 }, { "epoch": 0.61, "learning_rate": 1.62558000079739e-05, "loss": 0.0681, "step": 689 }, { "epoch": 0.61, "learning_rate": 1.624455064899371e-05, "loss": 0.0759, "step": 690 }, { "epoch": 0.61, "learning_rate": 1.623328832156938e-05, "loss": 0.0696, "step": 691 }, { "epoch": 0.62, "learning_rate": 1.6222013049090086e-05, "loss": 0.0746, "step": 692 }, { "epoch": 0.62, "learning_rate": 1.6210724854971885e-05, "loss": 0.0754, "step": 693 }, { "epoch": 0.62, "learning_rate": 1.619942376265767e-05, "loss": 0.0738, "step": 694 }, { "epoch": 0.62, "learning_rate": 1.6188109795617112e-05, "loss": 0.0683, "step": 695 }, { "epoch": 0.62, "learning_rate": 1.6176782977346626e-05, "loss": 0.0745, "step": 696 }, { "epoch": 0.62, "learning_rate": 1.6165443331369318e-05, "loss": 0.076, "step": 697 }, { "epoch": 0.62, "learning_rate": 1.615409088123493e-05, "loss": 0.0737, "step": 698 }, { "epoch": 0.62, "learning_rate": 1.6142725650519798e-05, "loss": 0.077, "step": 699 }, { "epoch": 0.62, "learning_rate": 1.6131347662826793e-05, "loss": 0.0784, "step": 700 }, { "epoch": 0.62, "learning_rate": 1.611995694178529e-05, "loss": 0.0676, "step": 701 }, { "epoch": 0.62, "learning_rate": 1.6108553511051106e-05, "loss": 0.0694, "step": 702 }, { "epoch": 0.63, "learning_rate": 1.6097137394306444e-05, "loss": 0.0721, "step": 703 }, { "epoch": 0.63, "learning_rate": 1.6085708615259863e-05, "loss": 0.0677, "step": 704 }, { "epoch": 0.63, "learning_rate": 1.6074267197646213e-05, "loss": 0.0648, "step": 705 }, { "epoch": 0.63, "learning_rate": 1.6062813165226594e-05, "loss": 0.0799, "step": 706 }, { "epoch": 0.63, "learning_rate": 1.60513465417883e-05, "loss": 0.0745, "step": 707 }, { "epoch": 0.63, "learning_rate": 1.6039867351144778e-05, "loss": 0.0603, "step": 708 }, { "epoch": 0.63, "learning_rate": 1.6028375617135573e-05, "loss": 0.0686, "step": 709 }, { "epoch": 0.63, "learning_rate": 1.6016871363626277e-05, "loss": 0.0687, "step": 710 }, { "epoch": 0.63, "learning_rate": 1.6005354614508487e-05, "loss": 0.0689, "step": 711 }, { "epoch": 0.63, "learning_rate": 1.5993825393699746e-05, "loss": 0.0736, "step": 712 }, { "epoch": 0.63, "learning_rate": 1.5982283725143498e-05, "loss": 0.0679, "step": 713 }, { "epoch": 0.64, "learning_rate": 1.5970729632809044e-05, "loss": 0.0691, "step": 714 }, { "epoch": 0.64, "learning_rate": 1.5959163140691475e-05, "loss": 0.0712, "step": 715 }, { "epoch": 0.64, "learning_rate": 1.594758427281164e-05, "loss": 0.0767, "step": 716 }, { "epoch": 0.64, "learning_rate": 1.5935993053216094e-05, "loss": 0.0695, "step": 717 }, { "epoch": 0.64, "learning_rate": 1.5924389505977038e-05, "loss": 0.0655, "step": 718 }, { "epoch": 0.64, "learning_rate": 1.5912773655192274e-05, "loss": 0.0728, "step": 719 }, { "epoch": 0.64, "learning_rate": 1.5901145524985155e-05, "loss": 0.0726, "step": 720 }, { "epoch": 0.64, "learning_rate": 1.5889505139504535e-05, "loss": 0.0713, "step": 721 }, { "epoch": 0.64, "learning_rate": 1.5877852522924733e-05, "loss": 0.0716, "step": 722 }, { "epoch": 0.64, "learning_rate": 1.5866187699445447e-05, "loss": 0.0789, "step": 723 }, { "epoch": 0.64, "learning_rate": 1.5854510693291744e-05, "loss": 0.0707, "step": 724 }, { "epoch": 0.65, "learning_rate": 1.584282152871398e-05, "loss": 0.0782, "step": 725 }, { "epoch": 0.65, "learning_rate": 1.583112022998776e-05, "loss": 0.0764, "step": 726 }, { "epoch": 0.65, "learning_rate": 1.5819406821413907e-05, "loss": 0.0725, "step": 727 }, { "epoch": 0.65, "learning_rate": 1.5807681327318372e-05, "loss": 0.0763, "step": 728 }, { "epoch": 0.65, "learning_rate": 1.5795943772052212e-05, "loss": 0.0755, "step": 729 }, { "epoch": 0.65, "learning_rate": 1.5784194179991534e-05, "loss": 0.0743, "step": 730 }, { "epoch": 0.65, "learning_rate": 1.5772432575537447e-05, "loss": 0.0778, "step": 731 }, { "epoch": 0.65, "learning_rate": 1.576065898311599e-05, "loss": 0.0695, "step": 732 }, { "epoch": 0.65, "learning_rate": 1.574887342717813e-05, "loss": 0.0784, "step": 733 }, { "epoch": 0.65, "learning_rate": 1.5737075932199637e-05, "loss": 0.0672, "step": 734 }, { "epoch": 0.65, "learning_rate": 1.572526652268111e-05, "loss": 0.0737, "step": 735 }, { "epoch": 0.65, "learning_rate": 1.5713445223147876e-05, "loss": 0.0859, "step": 736 }, { "epoch": 0.66, "learning_rate": 1.570161205814996e-05, "loss": 0.0691, "step": 737 }, { "epoch": 0.66, "learning_rate": 1.5689767052262028e-05, "loss": 0.0684, "step": 738 }, { "epoch": 0.66, "learning_rate": 1.5677910230083325e-05, "loss": 0.0743, "step": 739 }, { "epoch": 0.66, "learning_rate": 1.566604161623766e-05, "loss": 0.0689, "step": 740 }, { "epoch": 0.66, "learning_rate": 1.5654161235373312e-05, "loss": 0.0792, "step": 741 }, { "epoch": 0.66, "learning_rate": 1.5642269112162998e-05, "loss": 0.0722, "step": 742 }, { "epoch": 0.66, "learning_rate": 1.5630365271303826e-05, "loss": 0.0726, "step": 743 }, { "epoch": 0.66, "learning_rate": 1.5618449737517242e-05, "loss": 0.0765, "step": 744 }, { "epoch": 0.66, "learning_rate": 1.560652253554897e-05, "loss": 0.0676, "step": 745 }, { "epoch": 0.66, "learning_rate": 1.5594583690168966e-05, "loss": 0.0635, "step": 746 }, { "epoch": 0.66, "learning_rate": 1.5582633226171365e-05, "loss": 0.0753, "step": 747 }, { "epoch": 0.67, "learning_rate": 1.557067116837444e-05, "loss": 0.0617, "step": 748 }, { "epoch": 0.67, "learning_rate": 1.555869754162053e-05, "loss": 0.0789, "step": 749 }, { "epoch": 0.67, "learning_rate": 1.5546712370776005e-05, "loss": 0.0701, "step": 750 }, { "epoch": 0.67, "learning_rate": 1.5534715680731218e-05, "loss": 0.0781, "step": 751 }, { "epoch": 0.67, "learning_rate": 1.5522707496400425e-05, "loss": 0.0644, "step": 752 }, { "epoch": 0.67, "learning_rate": 1.5510687842721775e-05, "loss": 0.0648, "step": 753 }, { "epoch": 0.67, "learning_rate": 1.5498656744657222e-05, "loss": 0.065, "step": 754 }, { "epoch": 0.67, "learning_rate": 1.548661422719248e-05, "loss": 0.0718, "step": 755 }, { "epoch": 0.67, "learning_rate": 1.5474560315337007e-05, "loss": 0.0625, "step": 756 }, { "epoch": 0.67, "learning_rate": 1.546249503412389e-05, "loss": 0.0675, "step": 757 }, { "epoch": 0.67, "learning_rate": 1.545041840860986e-05, "loss": 0.076, "step": 758 }, { "epoch": 0.68, "learning_rate": 1.543833046387518e-05, "loss": 0.059, "step": 759 }, { "epoch": 0.68, "learning_rate": 1.542623122502363e-05, "loss": 0.0602, "step": 760 }, { "epoch": 0.68, "learning_rate": 1.5414120717182454e-05, "loss": 0.069, "step": 761 }, { "epoch": 0.68, "learning_rate": 1.5401998965502293e-05, "loss": 0.0692, "step": 762 }, { "epoch": 0.68, "learning_rate": 1.538986599515713e-05, "loss": 0.0669, "step": 763 }, { "epoch": 0.68, "learning_rate": 1.5377721831344258e-05, "loss": 0.0736, "step": 764 }, { "epoch": 0.68, "learning_rate": 1.536556649928421e-05, "loss": 0.075, "step": 765 }, { "epoch": 0.68, "learning_rate": 1.535340002422072e-05, "loss": 0.0789, "step": 766 }, { "epoch": 0.68, "learning_rate": 1.5341222431420658e-05, "loss": 0.069, "step": 767 }, { "epoch": 0.68, "learning_rate": 1.5329033746173975e-05, "loss": 0.0685, "step": 768 }, { "epoch": 0.68, "learning_rate": 1.5316833993793676e-05, "loss": 0.0751, "step": 769 }, { "epoch": 0.69, "learning_rate": 1.5304623199615737e-05, "loss": 0.0651, "step": 770 }, { "epoch": 0.69, "learning_rate": 1.529240138899907e-05, "loss": 0.0616, "step": 771 }, { "epoch": 0.69, "learning_rate": 1.5280168587325462e-05, "loss": 0.0674, "step": 772 }, { "epoch": 0.69, "learning_rate": 1.526792481999953e-05, "loss": 0.0675, "step": 773 }, { "epoch": 0.69, "learning_rate": 1.5255670112448657e-05, "loss": 0.0652, "step": 774 }, { "epoch": 0.69, "learning_rate": 1.524340449012296e-05, "loss": 0.0693, "step": 775 }, { "epoch": 0.69, "learning_rate": 1.5231127978495208e-05, "loss": 0.0701, "step": 776 }, { "epoch": 0.69, "learning_rate": 1.5218840603060794e-05, "loss": 0.0647, "step": 777 }, { "epoch": 0.69, "learning_rate": 1.520654238933767e-05, "loss": 0.0677, "step": 778 }, { "epoch": 0.69, "learning_rate": 1.5194233362866293e-05, "loss": 0.0702, "step": 779 }, { "epoch": 0.69, "learning_rate": 1.5181913549209582e-05, "loss": 0.0651, "step": 780 }, { "epoch": 0.69, "learning_rate": 1.5169582973952852e-05, "loss": 0.0738, "step": 781 }, { "epoch": 0.7, "learning_rate": 1.5157241662703777e-05, "loss": 0.0667, "step": 782 }, { "epoch": 0.7, "learning_rate": 1.5144889641092314e-05, "loss": 0.0676, "step": 783 }, { "epoch": 0.7, "learning_rate": 1.513252693477067e-05, "loss": 0.0676, "step": 784 }, { "epoch": 0.7, "learning_rate": 1.5120153569413243e-05, "loss": 0.0691, "step": 785 }, { "epoch": 0.7, "learning_rate": 1.5107769570716566e-05, "loss": 0.0736, "step": 786 }, { "epoch": 0.7, "learning_rate": 1.5095374964399252e-05, "loss": 0.0684, "step": 787 }, { "epoch": 0.7, "learning_rate": 1.5082969776201948e-05, "loss": 0.0711, "step": 788 }, { "epoch": 0.7, "learning_rate": 1.5070554031887272e-05, "loss": 0.0663, "step": 789 }, { "epoch": 0.7, "learning_rate": 1.5058127757239772e-05, "loss": 0.077, "step": 790 }, { "epoch": 0.7, "learning_rate": 1.5045690978065852e-05, "loss": 0.0717, "step": 791 }, { "epoch": 0.7, "learning_rate": 1.5033243720193746e-05, "loss": 0.0753, "step": 792 }, { "epoch": 0.71, "learning_rate": 1.5020786009473445e-05, "loss": 0.064, "step": 793 }, { "epoch": 0.71, "learning_rate": 1.5008317871776643e-05, "loss": 0.0766, "step": 794 }, { "epoch": 0.71, "learning_rate": 1.4995839332996691e-05, "loss": 0.0682, "step": 795 }, { "epoch": 0.71, "learning_rate": 1.4983350419048544e-05, "loss": 0.0747, "step": 796 }, { "epoch": 0.71, "learning_rate": 1.4970851155868698e-05, "loss": 0.0697, "step": 797 }, { "epoch": 0.71, "learning_rate": 1.4958341569415149e-05, "loss": 0.0624, "step": 798 }, { "epoch": 0.71, "learning_rate": 1.4945821685667325e-05, "loss": 0.0767, "step": 799 }, { "epoch": 0.71, "learning_rate": 1.4933291530626047e-05, "loss": 0.0655, "step": 800 }, { "epoch": 0.71, "learning_rate": 1.4920751130313453e-05, "loss": 0.0691, "step": 801 }, { "epoch": 0.71, "learning_rate": 1.4908200510772979e-05, "loss": 0.0681, "step": 802 }, { "epoch": 0.71, "learning_rate": 1.489563969806926e-05, "loss": 0.0641, "step": 803 }, { "epoch": 0.72, "learning_rate": 1.4883068718288121e-05, "loss": 0.0774, "step": 804 }, { "epoch": 0.72, "learning_rate": 1.4870487597536484e-05, "loss": 0.0711, "step": 805 }, { "epoch": 0.72, "learning_rate": 1.485789636194235e-05, "loss": 0.0707, "step": 806 }, { "epoch": 0.72, "learning_rate": 1.4845295037654707e-05, "loss": 0.0682, "step": 807 }, { "epoch": 0.72, "learning_rate": 1.483268365084351e-05, "loss": 0.0676, "step": 808 }, { "epoch": 0.72, "learning_rate": 1.4820062227699598e-05, "loss": 0.0664, "step": 809 }, { "epoch": 0.72, "learning_rate": 1.480743079443467e-05, "loss": 0.0745, "step": 810 }, { "epoch": 0.72, "learning_rate": 1.4794789377281193e-05, "loss": 0.0682, "step": 811 }, { "epoch": 0.72, "learning_rate": 1.4782138002492385e-05, "loss": 0.0655, "step": 812 }, { "epoch": 0.72, "learning_rate": 1.4769476696342138e-05, "loss": 0.0694, "step": 813 }, { "epoch": 0.72, "learning_rate": 1.475680548512497e-05, "loss": 0.0623, "step": 814 }, { "epoch": 0.73, "learning_rate": 1.4744124395155963e-05, "loss": 0.065, "step": 815 }, { "epoch": 0.73, "learning_rate": 1.4731433452770723e-05, "loss": 0.075, "step": 816 }, { "epoch": 0.73, "learning_rate": 1.4718732684325314e-05, "loss": 0.0646, "step": 817 }, { "epoch": 0.73, "learning_rate": 1.4706022116196208e-05, "loss": 0.0704, "step": 818 }, { "epoch": 0.73, "learning_rate": 1.4693301774780224e-05, "loss": 0.0641, "step": 819 }, { "epoch": 0.73, "learning_rate": 1.4680571686494483e-05, "loss": 0.0764, "step": 820 }, { "epoch": 0.73, "learning_rate": 1.4667831877776344e-05, "loss": 0.0658, "step": 821 }, { "epoch": 0.73, "learning_rate": 1.465508237508336e-05, "loss": 0.065, "step": 822 }, { "epoch": 0.73, "learning_rate": 1.4642323204893202e-05, "loss": 0.0656, "step": 823 }, { "epoch": 0.73, "learning_rate": 1.4629554393703635e-05, "loss": 0.072, "step": 824 }, { "epoch": 0.73, "learning_rate": 1.4616775968032434e-05, "loss": 0.0686, "step": 825 }, { "epoch": 0.73, "learning_rate": 1.4603987954417349e-05, "loss": 0.0699, "step": 826 }, { "epoch": 0.74, "learning_rate": 1.4591190379416033e-05, "loss": 0.0693, "step": 827 }, { "epoch": 0.74, "learning_rate": 1.4578383269606004e-05, "loss": 0.0735, "step": 828 }, { "epoch": 0.74, "learning_rate": 1.4565566651584577e-05, "loss": 0.0677, "step": 829 }, { "epoch": 0.74, "learning_rate": 1.4552740551968817e-05, "loss": 0.0715, "step": 830 }, { "epoch": 0.74, "learning_rate": 1.4539904997395468e-05, "loss": 0.0682, "step": 831 }, { "epoch": 0.74, "learning_rate": 1.4527060014520932e-05, "loss": 0.0632, "step": 832 }, { "epoch": 0.74, "learning_rate": 1.451420563002117e-05, "loss": 0.071, "step": 833 }, { "epoch": 0.74, "learning_rate": 1.4501341870591683e-05, "loss": 0.0636, "step": 834 }, { "epoch": 0.74, "learning_rate": 1.4488468762947427e-05, "loss": 0.0695, "step": 835 }, { "epoch": 0.74, "learning_rate": 1.4475586333822787e-05, "loss": 0.0648, "step": 836 }, { "epoch": 0.74, "learning_rate": 1.4462694609971495e-05, "loss": 0.0675, "step": 837 }, { "epoch": 0.75, "learning_rate": 1.4449793618166594e-05, "loss": 0.0663, "step": 838 }, { "epoch": 0.75, "learning_rate": 1.4436883385200366e-05, "loss": 0.0647, "step": 839 }, { "epoch": 0.75, "learning_rate": 1.4423963937884293e-05, "loss": 0.0632, "step": 840 }, { "epoch": 0.75, "learning_rate": 1.4411035303048989e-05, "loss": 0.0705, "step": 841 }, { "epoch": 0.75, "learning_rate": 1.4398097507544152e-05, "loss": 0.0591, "step": 842 }, { "epoch": 0.75, "learning_rate": 1.4385150578238492e-05, "loss": 0.0642, "step": 843 }, { "epoch": 0.75, "learning_rate": 1.4372194542019705e-05, "loss": 0.0702, "step": 844 }, { "epoch": 0.75, "learning_rate": 1.435922942579439e-05, "loss": 0.0711, "step": 845 }, { "epoch": 0.75, "learning_rate": 1.4346255256488002e-05, "loss": 0.0699, "step": 846 }, { "epoch": 0.75, "learning_rate": 1.4333272061044803e-05, "loss": 0.0713, "step": 847 }, { "epoch": 0.75, "learning_rate": 1.4320279866427798e-05, "loss": 0.0641, "step": 848 }, { "epoch": 0.76, "learning_rate": 1.4307278699618678e-05, "loss": 0.0708, "step": 849 }, { "epoch": 0.76, "learning_rate": 1.429426858761777e-05, "loss": 0.0699, "step": 850 }, { "epoch": 0.76, "learning_rate": 1.4281249557443977e-05, "loss": 0.0643, "step": 851 }, { "epoch": 0.76, "learning_rate": 1.4268221636134722e-05, "loss": 0.0674, "step": 852 }, { "epoch": 0.76, "learning_rate": 1.42551848507459e-05, "loss": 0.0655, "step": 853 }, { "epoch": 0.76, "learning_rate": 1.42421392283518e-05, "loss": 0.0719, "step": 854 }, { "epoch": 0.76, "learning_rate": 1.4229084796045078e-05, "loss": 0.0652, "step": 855 }, { "epoch": 0.76, "learning_rate": 1.4216021580936681e-05, "loss": 0.0656, "step": 856 }, { "epoch": 0.76, "learning_rate": 1.4202949610155789e-05, "loss": 0.0681, "step": 857 }, { "epoch": 0.76, "learning_rate": 1.4189868910849779e-05, "loss": 0.0714, "step": 858 }, { "epoch": 0.76, "learning_rate": 1.4176779510184138e-05, "loss": 0.0685, "step": 859 }, { "epoch": 0.77, "learning_rate": 1.416368143534244e-05, "loss": 0.072, "step": 860 }, { "epoch": 0.77, "learning_rate": 1.4150574713526266e-05, "loss": 0.075, "step": 861 }, { "epoch": 0.77, "learning_rate": 1.4137459371955151e-05, "loss": 0.062, "step": 862 }, { "epoch": 0.77, "learning_rate": 1.412433543786654e-05, "loss": 0.067, "step": 863 }, { "epoch": 0.77, "learning_rate": 1.4111202938515711e-05, "loss": 0.0626, "step": 864 }, { "epoch": 0.77, "learning_rate": 1.4098061901175749e-05, "loss": 0.0671, "step": 865 }, { "epoch": 0.77, "learning_rate": 1.4084912353137444e-05, "loss": 0.065, "step": 866 }, { "epoch": 0.77, "learning_rate": 1.4071754321709284e-05, "loss": 0.0646, "step": 867 }, { "epoch": 0.77, "learning_rate": 1.4058587834217356e-05, "loss": 0.0697, "step": 868 }, { "epoch": 0.77, "learning_rate": 1.4045412918005332e-05, "loss": 0.0721, "step": 869 }, { "epoch": 0.77, "learning_rate": 1.4032229600434363e-05, "loss": 0.0732, "step": 870 }, { "epoch": 0.77, "learning_rate": 1.4019037908883068e-05, "loss": 0.068, "step": 871 }, { "epoch": 0.78, "learning_rate": 1.4005837870747439e-05, "loss": 0.0706, "step": 872 }, { "epoch": 0.78, "learning_rate": 1.3992629513440818e-05, "loss": 0.0736, "step": 873 }, { "epoch": 0.78, "learning_rate": 1.397941286439381e-05, "loss": 0.0685, "step": 874 }, { "epoch": 0.78, "learning_rate": 1.3966187951054256e-05, "loss": 0.0771, "step": 875 }, { "epoch": 0.78, "learning_rate": 1.3952954800887137e-05, "loss": 0.0751, "step": 876 }, { "epoch": 0.78, "learning_rate": 1.393971344137457e-05, "loss": 0.0702, "step": 877 }, { "epoch": 0.78, "learning_rate": 1.392646390001569e-05, "loss": 0.0671, "step": 878 }, { "epoch": 0.78, "learning_rate": 1.3913206204326647e-05, "loss": 0.0659, "step": 879 }, { "epoch": 0.78, "learning_rate": 1.389994038184051e-05, "loss": 0.0668, "step": 880 }, { "epoch": 0.78, "learning_rate": 1.3886666460107237e-05, "loss": 0.0678, "step": 881 }, { "epoch": 0.78, "learning_rate": 1.38733844666936e-05, "loss": 0.068, "step": 882 }, { "epoch": 0.79, "learning_rate": 1.3860094429183138e-05, "loss": 0.064, "step": 883 }, { "epoch": 0.79, "learning_rate": 1.3846796375176083e-05, "loss": 0.0705, "step": 884 }, { "epoch": 0.79, "learning_rate": 1.3833490332289341e-05, "loss": 0.0651, "step": 885 }, { "epoch": 0.79, "learning_rate": 1.3820176328156381e-05, "loss": 0.0604, "step": 886 }, { "epoch": 0.79, "learning_rate": 1.3806854390427224e-05, "loss": 0.0749, "step": 887 }, { "epoch": 0.79, "learning_rate": 1.3793524546768358e-05, "loss": 0.0755, "step": 888 }, { "epoch": 0.79, "learning_rate": 1.3780186824862694e-05, "loss": 0.0621, "step": 889 }, { "epoch": 0.79, "learning_rate": 1.3766841252409502e-05, "loss": 0.0777, "step": 890 }, { "epoch": 0.79, "learning_rate": 1.3753487857124361e-05, "loss": 0.0704, "step": 891 }, { "epoch": 0.79, "learning_rate": 1.3740126666739086e-05, "loss": 0.074, "step": 892 }, { "epoch": 0.79, "learning_rate": 1.3726757709001693e-05, "loss": 0.0656, "step": 893 }, { "epoch": 0.8, "learning_rate": 1.3713381011676315e-05, "loss": 0.0701, "step": 894 }, { "epoch": 0.8, "learning_rate": 1.369999660254317e-05, "loss": 0.0667, "step": 895 }, { "epoch": 0.8, "learning_rate": 1.3686604509398489e-05, "loss": 0.0678, "step": 896 }, { "epoch": 0.8, "learning_rate": 1.3673204760054457e-05, "loss": 0.0689, "step": 897 }, { "epoch": 0.8, "learning_rate": 1.3659797382339162e-05, "loss": 0.076, "step": 898 }, { "epoch": 0.8, "learning_rate": 1.3646382404096533e-05, "loss": 0.0647, "step": 899 }, { "epoch": 0.8, "learning_rate": 1.363295985318628e-05, "loss": 0.0724, "step": 900 }, { "epoch": 0.8, "learning_rate": 1.3619529757483857e-05, "loss": 0.0675, "step": 901 }, { "epoch": 0.8, "learning_rate": 1.3606092144880359e-05, "loss": 0.0601, "step": 902 }, { "epoch": 0.8, "learning_rate": 1.3592647043282514e-05, "loss": 0.0691, "step": 903 }, { "epoch": 0.8, "learning_rate": 1.357919448061259e-05, "loss": 0.0738, "step": 904 }, { "epoch": 0.81, "learning_rate": 1.3565734484808361e-05, "loss": 0.0667, "step": 905 }, { "epoch": 0.81, "learning_rate": 1.3552267083823028e-05, "loss": 0.0725, "step": 906 }, { "epoch": 0.81, "learning_rate": 1.3538792305625177e-05, "loss": 0.0648, "step": 907 }, { "epoch": 0.81, "learning_rate": 1.3525310178198707e-05, "loss": 0.0703, "step": 908 }, { "epoch": 0.81, "learning_rate": 1.3511820729542792e-05, "loss": 0.0646, "step": 909 }, { "epoch": 0.81, "learning_rate": 1.3498323987671801e-05, "loss": 0.0751, "step": 910 }, { "epoch": 0.81, "learning_rate": 1.3484819980615251e-05, "loss": 0.0689, "step": 911 }, { "epoch": 0.81, "learning_rate": 1.347130873641775e-05, "loss": 0.0688, "step": 912 }, { "epoch": 0.81, "learning_rate": 1.3457790283138928e-05, "loss": 0.0686, "step": 913 }, { "epoch": 0.81, "learning_rate": 1.3444264648853395e-05, "loss": 0.0724, "step": 914 }, { "epoch": 0.81, "learning_rate": 1.3430731861650674e-05, "loss": 0.0664, "step": 915 }, { "epoch": 0.81, "learning_rate": 1.3417191949635137e-05, "loss": 0.0709, "step": 916 }, { "epoch": 0.82, "learning_rate": 1.340364494092596e-05, "loss": 0.0723, "step": 917 }, { "epoch": 0.82, "learning_rate": 1.3390090863657048e-05, "loss": 0.0641, "step": 918 }, { "epoch": 0.82, "learning_rate": 1.3376529745976994e-05, "loss": 0.0793, "step": 919 }, { "epoch": 0.82, "learning_rate": 1.3362961616049006e-05, "loss": 0.0691, "step": 920 }, { "epoch": 0.82, "learning_rate": 1.334938650205086e-05, "loss": 0.0659, "step": 921 }, { "epoch": 0.82, "learning_rate": 1.333580443217483e-05, "loss": 0.0658, "step": 922 }, { "epoch": 0.82, "learning_rate": 1.3322215434627647e-05, "loss": 0.0684, "step": 923 }, { "epoch": 0.82, "learning_rate": 1.3308619537630416e-05, "loss": 0.0768, "step": 924 }, { "epoch": 0.82, "learning_rate": 1.3295016769418579e-05, "loss": 0.0609, "step": 925 }, { "epoch": 0.82, "learning_rate": 1.3281407158241842e-05, "loss": 0.0691, "step": 926 }, { "epoch": 0.82, "learning_rate": 1.326779073236413e-05, "loss": 0.0711, "step": 927 }, { "epoch": 0.83, "learning_rate": 1.325416752006351e-05, "loss": 0.0797, "step": 928 }, { "epoch": 0.83, "learning_rate": 1.3240537549632154e-05, "loss": 0.0615, "step": 929 }, { "epoch": 0.83, "learning_rate": 1.3226900849376263e-05, "loss": 0.0738, "step": 930 }, { "epoch": 0.83, "learning_rate": 1.3213257447616013e-05, "loss": 0.0655, "step": 931 }, { "epoch": 0.83, "learning_rate": 1.3199607372685497e-05, "loss": 0.0678, "step": 932 }, { "epoch": 0.83, "learning_rate": 1.3185950652932673e-05, "loss": 0.0706, "step": 933 }, { "epoch": 0.83, "learning_rate": 1.3172287316719297e-05, "loss": 0.0709, "step": 934 }, { "epoch": 0.83, "learning_rate": 1.3158617392420855e-05, "loss": 0.071, "step": 935 }, { "epoch": 0.83, "learning_rate": 1.3144940908426532e-05, "loss": 0.0632, "step": 936 }, { "epoch": 0.83, "learning_rate": 1.313125789313912e-05, "loss": 0.071, "step": 937 }, { "epoch": 0.83, "learning_rate": 1.311756837497499e-05, "loss": 0.074, "step": 938 }, { "epoch": 0.84, "learning_rate": 1.3103872382364003e-05, "loss": 0.0642, "step": 939 }, { "epoch": 0.84, "learning_rate": 1.3090169943749475e-05, "loss": 0.0742, "step": 940 }, { "epoch": 0.84, "learning_rate": 1.307646108758811e-05, "loss": 0.0743, "step": 941 }, { "epoch": 0.84, "learning_rate": 1.3062745842349935e-05, "loss": 0.0649, "step": 942 }, { "epoch": 0.84, "learning_rate": 1.3049024236518244e-05, "loss": 0.0659, "step": 943 }, { "epoch": 0.84, "learning_rate": 1.3035296298589549e-05, "loss": 0.0702, "step": 944 }, { "epoch": 0.84, "learning_rate": 1.30215620570735e-05, "loss": 0.0664, "step": 945 }, { "epoch": 0.84, "learning_rate": 1.3007821540492854e-05, "loss": 0.0709, "step": 946 }, { "epoch": 0.84, "learning_rate": 1.2994074777383382e-05, "loss": 0.0706, "step": 947 }, { "epoch": 0.84, "learning_rate": 1.2980321796293838e-05, "loss": 0.067, "step": 948 }, { "epoch": 0.84, "learning_rate": 1.2966562625785891e-05, "loss": 0.0661, "step": 949 }, { "epoch": 0.85, "learning_rate": 1.295279729443406e-05, "loss": 0.0682, "step": 950 }, { "epoch": 0.85, "learning_rate": 1.2939025830825657e-05, "loss": 0.0658, "step": 951 }, { "epoch": 0.85, "learning_rate": 1.2925248263560733e-05, "loss": 0.0618, "step": 952 }, { "epoch": 0.85, "learning_rate": 1.291146462125201e-05, "loss": 0.0765, "step": 953 }, { "epoch": 0.85, "learning_rate": 1.2897674932524832e-05, "loss": 0.0681, "step": 954 }, { "epoch": 0.85, "learning_rate": 1.28838792260171e-05, "loss": 0.0738, "step": 955 }, { "epoch": 0.85, "learning_rate": 1.2870077530379205e-05, "loss": 0.0697, "step": 956 }, { "epoch": 0.85, "learning_rate": 1.2856269874273984e-05, "loss": 0.0617, "step": 957 }, { "epoch": 0.85, "learning_rate": 1.284245628637665e-05, "loss": 0.0716, "step": 958 }, { "epoch": 0.85, "learning_rate": 1.2828636795374732e-05, "loss": 0.0634, "step": 959 }, { "epoch": 0.85, "learning_rate": 1.2814811429968022e-05, "loss": 0.0688, "step": 960 }, { "epoch": 0.85, "learning_rate": 1.2800980218868508e-05, "loss": 0.0636, "step": 961 }, { "epoch": 0.86, "learning_rate": 1.278714319080033e-05, "loss": 0.0657, "step": 962 }, { "epoch": 0.86, "learning_rate": 1.2773300374499687e-05, "loss": 0.0685, "step": 963 }, { "epoch": 0.86, "learning_rate": 1.2759451798714816e-05, "loss": 0.066, "step": 964 }, { "epoch": 0.86, "learning_rate": 1.2745597492205913e-05, "loss": 0.0683, "step": 965 }, { "epoch": 0.86, "learning_rate": 1.2731737483745068e-05, "loss": 0.0648, "step": 966 }, { "epoch": 0.86, "learning_rate": 1.2717871802116218e-05, "loss": 0.0676, "step": 967 }, { "epoch": 0.86, "learning_rate": 1.2704000476115079e-05, "loss": 0.0719, "step": 968 }, { "epoch": 0.86, "learning_rate": 1.2690123534549095e-05, "loss": 0.0663, "step": 969 }, { "epoch": 0.86, "learning_rate": 1.2676241006237367e-05, "loss": 0.0733, "step": 970 }, { "epoch": 0.86, "learning_rate": 1.2662352920010595e-05, "loss": 0.0674, "step": 971 }, { "epoch": 0.86, "learning_rate": 1.2648459304711026e-05, "loss": 0.0642, "step": 972 }, { "epoch": 0.87, "learning_rate": 1.2634560189192395e-05, "loss": 0.0656, "step": 973 }, { "epoch": 0.87, "learning_rate": 1.2620655602319851e-05, "loss": 0.0681, "step": 974 }, { "epoch": 0.87, "learning_rate": 1.2606745572969907e-05, "loss": 0.0695, "step": 975 }, { "epoch": 0.87, "learning_rate": 1.259283013003038e-05, "loss": 0.0574, "step": 976 }, { "epoch": 0.87, "learning_rate": 1.2578909302400332e-05, "loss": 0.0682, "step": 977 }, { "epoch": 0.87, "learning_rate": 1.256498311899001e-05, "loss": 0.0626, "step": 978 }, { "epoch": 0.87, "learning_rate": 1.255105160872077e-05, "loss": 0.0678, "step": 979 }, { "epoch": 0.87, "learning_rate": 1.2537114800525047e-05, "loss": 0.0747, "step": 980 }, { "epoch": 0.87, "learning_rate": 1.2523172723346268e-05, "loss": 0.0656, "step": 981 }, { "epoch": 0.87, "learning_rate": 1.2509225406138809e-05, "loss": 0.0663, "step": 982 }, { "epoch": 0.87, "learning_rate": 1.2495272877867925e-05, "loss": 0.075, "step": 983 }, { "epoch": 0.88, "learning_rate": 1.2481315167509691e-05, "loss": 0.0659, "step": 984 }, { "epoch": 0.88, "learning_rate": 1.2467352304050947e-05, "loss": 0.065, "step": 985 }, { "epoch": 0.88, "learning_rate": 1.2453384316489239e-05, "loss": 0.0648, "step": 986 }, { "epoch": 0.88, "learning_rate": 1.243941123383274e-05, "loss": 0.0663, "step": 987 }, { "epoch": 0.88, "learning_rate": 1.2425433085100224e-05, "loss": 0.0689, "step": 988 }, { "epoch": 0.88, "learning_rate": 1.241144989932097e-05, "loss": 0.0644, "step": 989 }, { "epoch": 0.88, "learning_rate": 1.2397461705534727e-05, "loss": 0.0705, "step": 990 }, { "epoch": 0.88, "learning_rate": 1.238346853279164e-05, "loss": 0.0634, "step": 991 }, { "epoch": 0.88, "learning_rate": 1.2369470410152195e-05, "loss": 0.0698, "step": 992 }, { "epoch": 0.88, "learning_rate": 1.2355467366687156e-05, "loss": 0.063, "step": 993 }, { "epoch": 0.88, "learning_rate": 1.2341459431477516e-05, "loss": 0.0629, "step": 994 }, { "epoch": 0.89, "learning_rate": 1.2327446633614413e-05, "loss": 0.0619, "step": 995 }, { "epoch": 0.89, "learning_rate": 1.2313429002199088e-05, "loss": 0.0667, "step": 996 }, { "epoch": 0.89, "learning_rate": 1.2299406566342831e-05, "loss": 0.0613, "step": 997 }, { "epoch": 0.89, "learning_rate": 1.2285379355166893e-05, "loss": 0.0682, "step": 998 }, { "epoch": 0.89, "learning_rate": 1.2271347397802452e-05, "loss": 0.0688, "step": 999 }, { "epoch": 0.89, "learning_rate": 1.2257310723390541e-05, "loss": 0.071, "step": 1000 }, { "epoch": 0.89, "learning_rate": 1.2243269361081992e-05, "loss": 0.0642, "step": 1001 }, { "epoch": 0.89, "learning_rate": 1.2229223340037364e-05, "loss": 0.0721, "step": 1002 }, { "epoch": 0.89, "learning_rate": 1.2215172689426902e-05, "loss": 0.0716, "step": 1003 }, { "epoch": 0.89, "learning_rate": 1.2201117438430456e-05, "loss": 0.072, "step": 1004 }, { "epoch": 0.89, "learning_rate": 1.218705761623744e-05, "loss": 0.0693, "step": 1005 }, { "epoch": 0.9, "learning_rate": 1.2172993252046747e-05, "loss": 0.077, "step": 1006 }, { "epoch": 0.9, "learning_rate": 1.2158924375066716e-05, "loss": 0.0691, "step": 1007 }, { "epoch": 0.9, "learning_rate": 1.2144851014515055e-05, "loss": 0.0653, "step": 1008 }, { "epoch": 0.9, "learning_rate": 1.213077319961878e-05, "loss": 0.0678, "step": 1009 }, { "epoch": 0.9, "learning_rate": 1.2116690959614154e-05, "loss": 0.0704, "step": 1010 }, { "epoch": 0.9, "learning_rate": 1.210260432374664e-05, "loss": 0.0709, "step": 1011 }, { "epoch": 0.9, "learning_rate": 1.2088513321270823e-05, "loss": 0.0691, "step": 1012 }, { "epoch": 0.9, "learning_rate": 1.2074417981450361e-05, "loss": 0.0711, "step": 1013 }, { "epoch": 0.9, "learning_rate": 1.2060318333557915e-05, "loss": 0.0741, "step": 1014 }, { "epoch": 0.9, "learning_rate": 1.2046214406875093e-05, "loss": 0.0694, "step": 1015 }, { "epoch": 0.9, "learning_rate": 1.2032106230692394e-05, "loss": 0.0695, "step": 1016 }, { "epoch": 0.9, "learning_rate": 1.2017993834309138e-05, "loss": 0.0632, "step": 1017 }, { "epoch": 0.91, "learning_rate": 1.2003877247033411e-05, "loss": 0.0742, "step": 1018 }, { "epoch": 0.91, "learning_rate": 1.1989756498182e-05, "loss": 0.0714, "step": 1019 }, { "epoch": 0.91, "learning_rate": 1.1975631617080339e-05, "loss": 0.0656, "step": 1020 }, { "epoch": 0.91, "learning_rate": 1.1961502633062441e-05, "loss": 0.0637, "step": 1021 }, { "epoch": 0.91, "learning_rate": 1.1947369575470837e-05, "loss": 0.0719, "step": 1022 }, { "epoch": 0.91, "learning_rate": 1.1933232473656527e-05, "loss": 0.0709, "step": 1023 }, { "epoch": 0.91, "learning_rate": 1.1919091356978894e-05, "loss": 0.0623, "step": 1024 }, { "epoch": 0.91, "learning_rate": 1.190494625480568e-05, "loss": 0.0634, "step": 1025 }, { "epoch": 0.91, "learning_rate": 1.1890797196512884e-05, "loss": 0.074, "step": 1026 }, { "epoch": 0.91, "learning_rate": 1.1876644211484736e-05, "loss": 0.0642, "step": 1027 }, { "epoch": 0.91, "learning_rate": 1.1862487329113606e-05, "loss": 0.0699, "step": 1028 }, { "epoch": 0.92, "learning_rate": 1.1848326578799975e-05, "loss": 0.0694, "step": 1029 }, { "epoch": 0.92, "learning_rate": 1.1834161989952345e-05, "loss": 0.0721, "step": 1030 }, { "epoch": 0.92, "learning_rate": 1.1819993591987191e-05, "loss": 0.0684, "step": 1031 }, { "epoch": 0.92, "learning_rate": 1.1805821414328897e-05, "loss": 0.0723, "step": 1032 }, { "epoch": 0.92, "learning_rate": 1.179164548640971e-05, "loss": 0.0647, "step": 1033 }, { "epoch": 0.92, "learning_rate": 1.177746583766965e-05, "loss": 0.0719, "step": 1034 }, { "epoch": 0.92, "learning_rate": 1.176328249755647e-05, "loss": 0.0665, "step": 1035 }, { "epoch": 0.92, "learning_rate": 1.1749095495525584e-05, "loss": 0.0685, "step": 1036 }, { "epoch": 0.92, "learning_rate": 1.1734904861040022e-05, "loss": 0.0711, "step": 1037 }, { "epoch": 0.92, "learning_rate": 1.172071062357035e-05, "loss": 0.0757, "step": 1038 }, { "epoch": 0.92, "learning_rate": 1.1706512812594617e-05, "loss": 0.0702, "step": 1039 }, { "epoch": 0.93, "learning_rate": 1.1692311457598291e-05, "loss": 0.0737, "step": 1040 }, { "epoch": 0.93, "learning_rate": 1.167810658807421e-05, "loss": 0.0698, "step": 1041 }, { "epoch": 0.93, "learning_rate": 1.1663898233522499e-05, "loss": 0.0687, "step": 1042 }, { "epoch": 0.93, "learning_rate": 1.164968642345053e-05, "loss": 0.0724, "step": 1043 }, { "epoch": 0.93, "learning_rate": 1.163547118737284e-05, "loss": 0.0672, "step": 1044 }, { "epoch": 0.93, "learning_rate": 1.1621252554811096e-05, "loss": 0.0611, "step": 1045 }, { "epoch": 0.93, "learning_rate": 1.1607030555294005e-05, "loss": 0.0664, "step": 1046 }, { "epoch": 0.93, "learning_rate": 1.1592805218357276e-05, "loss": 0.0674, "step": 1047 }, { "epoch": 0.93, "learning_rate": 1.1578576573543541e-05, "loss": 0.0668, "step": 1048 }, { "epoch": 0.93, "learning_rate": 1.156434465040231e-05, "loss": 0.0604, "step": 1049 }, { "epoch": 0.93, "learning_rate": 1.1550109478489896e-05, "loss": 0.0669, "step": 1050 }, { "epoch": 0.94, "learning_rate": 1.1535871087369356e-05, "loss": 0.07, "step": 1051 }, { "epoch": 0.94, "learning_rate": 1.1521629506610439e-05, "loss": 0.0693, "step": 1052 }, { "epoch": 0.94, "learning_rate": 1.150738476578952e-05, "loss": 0.0695, "step": 1053 }, { "epoch": 0.94, "learning_rate": 1.1493136894489527e-05, "loss": 0.0681, "step": 1054 }, { "epoch": 0.94, "learning_rate": 1.1478885922299899e-05, "loss": 0.072, "step": 1055 }, { "epoch": 0.94, "learning_rate": 1.1464631878816502e-05, "loss": 0.0709, "step": 1056 }, { "epoch": 0.94, "learning_rate": 1.1450374793641596e-05, "loss": 0.0616, "step": 1057 }, { "epoch": 0.94, "learning_rate": 1.1436114696383749e-05, "loss": 0.0752, "step": 1058 }, { "epoch": 0.94, "learning_rate": 1.142185161665779e-05, "loss": 0.0619, "step": 1059 }, { "epoch": 0.94, "learning_rate": 1.1407585584084726e-05, "loss": 0.0756, "step": 1060 }, { "epoch": 0.94, "learning_rate": 1.1393316628291724e-05, "loss": 0.0671, "step": 1061 }, { "epoch": 0.94, "learning_rate": 1.1379044778911994e-05, "loss": 0.0673, "step": 1062 }, { "epoch": 0.95, "learning_rate": 1.1364770065584771e-05, "loss": 0.066, "step": 1063 }, { "epoch": 0.95, "learning_rate": 1.1350492517955234e-05, "loss": 0.0666, "step": 1064 }, { "epoch": 0.95, "learning_rate": 1.1336212165674452e-05, "loss": 0.0683, "step": 1065 }, { "epoch": 0.95, "learning_rate": 1.1321929038399309e-05, "loss": 0.0686, "step": 1066 }, { "epoch": 0.95, "learning_rate": 1.1307643165792463e-05, "loss": 0.0735, "step": 1067 }, { "epoch": 0.95, "learning_rate": 1.1293354577522264e-05, "loss": 0.076, "step": 1068 }, { "epoch": 0.95, "learning_rate": 1.1279063303262707e-05, "loss": 0.0607, "step": 1069 }, { "epoch": 0.95, "learning_rate": 1.1264769372693365e-05, "loss": 0.0663, "step": 1070 }, { "epoch": 0.95, "learning_rate": 1.1250472815499329e-05, "loss": 0.0673, "step": 1071 }, { "epoch": 0.95, "learning_rate": 1.1236173661371139e-05, "loss": 0.0675, "step": 1072 }, { "epoch": 0.95, "learning_rate": 1.1221871940004731e-05, "loss": 0.0646, "step": 1073 }, { "epoch": 0.96, "learning_rate": 1.1207567681101377e-05, "loss": 0.0742, "step": 1074 }, { "epoch": 0.96, "learning_rate": 1.1193260914367617e-05, "loss": 0.0674, "step": 1075 }, { "epoch": 0.96, "learning_rate": 1.117895166951519e-05, "loss": 0.0742, "step": 1076 }, { "epoch": 0.96, "learning_rate": 1.1164639976260993e-05, "loss": 0.0724, "step": 1077 }, { "epoch": 0.96, "learning_rate": 1.1150325864327003e-05, "loss": 0.0627, "step": 1078 }, { "epoch": 0.96, "learning_rate": 1.1136009363440224e-05, "loss": 0.0645, "step": 1079 }, { "epoch": 0.96, "learning_rate": 1.1121690503332613e-05, "loss": 0.0717, "step": 1080 }, { "epoch": 0.96, "learning_rate": 1.1107369313741032e-05, "loss": 0.0648, "step": 1081 }, { "epoch": 0.96, "learning_rate": 1.1093045824407186e-05, "loss": 0.068, "step": 1082 }, { "epoch": 0.96, "learning_rate": 1.1078720065077542e-05, "loss": 0.0688, "step": 1083 }, { "epoch": 0.96, "learning_rate": 1.1064392065503294e-05, "loss": 0.0704, "step": 1084 }, { "epoch": 0.97, "learning_rate": 1.1050061855440284e-05, "loss": 0.0718, "step": 1085 }, { "epoch": 0.97, "learning_rate": 1.1035729464648945e-05, "loss": 0.0769, "step": 1086 }, { "epoch": 0.97, "learning_rate": 1.1021394922894236e-05, "loss": 0.0678, "step": 1087 }, { "epoch": 0.97, "learning_rate": 1.1007058259945584e-05, "loss": 0.0712, "step": 1088 }, { "epoch": 0.97, "learning_rate": 1.0992719505576828e-05, "loss": 0.0733, "step": 1089 }, { "epoch": 0.97, "learning_rate": 1.0978378689566144e-05, "loss": 0.0646, "step": 1090 }, { "epoch": 0.97, "learning_rate": 1.0964035841695989e-05, "loss": 0.0758, "step": 1091 }, { "epoch": 0.97, "learning_rate": 1.0949690991753036e-05, "loss": 0.0704, "step": 1092 }, { "epoch": 0.97, "learning_rate": 1.0935344169528132e-05, "loss": 0.0666, "step": 1093 }, { "epoch": 0.97, "learning_rate": 1.0920995404816204e-05, "loss": 0.0701, "step": 1094 }, { "epoch": 0.97, "learning_rate": 1.0906644727416215e-05, "loss": 0.0659, "step": 1095 }, { "epoch": 0.98, "learning_rate": 1.0892292167131107e-05, "loss": 0.0697, "step": 1096 }, { "epoch": 0.98, "learning_rate": 1.0877937753767727e-05, "loss": 0.0637, "step": 1097 }, { "epoch": 0.98, "learning_rate": 1.0863581517136776e-05, "loss": 0.0688, "step": 1098 }, { "epoch": 0.98, "learning_rate": 1.0849223487052734e-05, "loss": 0.0699, "step": 1099 }, { "epoch": 0.98, "learning_rate": 1.0834863693333805e-05, "loss": 0.07, "step": 1100 }, { "epoch": 0.98, "learning_rate": 1.082050216580187e-05, "loss": 0.0721, "step": 1101 }, { "epoch": 0.98, "learning_rate": 1.0806138934282393e-05, "loss": 0.0707, "step": 1102 }, { "epoch": 0.98, "learning_rate": 1.0791774028604385e-05, "loss": 0.0726, "step": 1103 }, { "epoch": 0.98, "learning_rate": 1.0777407478600334e-05, "loss": 0.0757, "step": 1104 }, { "epoch": 0.98, "learning_rate": 1.0763039314106144e-05, "loss": 0.0739, "step": 1105 }, { "epoch": 0.98, "learning_rate": 1.074866956496107e-05, "loss": 0.068, "step": 1106 }, { "epoch": 0.98, "learning_rate": 1.0734298261007654e-05, "loss": 0.0653, "step": 1107 }, { "epoch": 0.99, "learning_rate": 1.0719925432091671e-05, "loss": 0.0694, "step": 1108 }, { "epoch": 0.99, "learning_rate": 1.0705551108062067e-05, "loss": 0.0611, "step": 1109 }, { "epoch": 0.99, "learning_rate": 1.0691175318770887e-05, "loss": 0.0644, "step": 1110 }, { "epoch": 0.99, "learning_rate": 1.067679809407322e-05, "loss": 0.066, "step": 1111 }, { "epoch": 0.99, "learning_rate": 1.0662419463827136e-05, "loss": 0.065, "step": 1112 }, { "epoch": 0.99, "learning_rate": 1.0648039457893626e-05, "loss": 0.0725, "step": 1113 }, { "epoch": 0.99, "learning_rate": 1.0633658106136538e-05, "loss": 0.071, "step": 1114 }, { "epoch": 0.99, "learning_rate": 1.0619275438422512e-05, "loss": 0.0674, "step": 1115 }, { "epoch": 0.99, "learning_rate": 1.060489148462092e-05, "loss": 0.0687, "step": 1116 }, { "epoch": 0.99, "learning_rate": 1.0590506274603814e-05, "loss": 0.0666, "step": 1117 }, { "epoch": 0.99, "learning_rate": 1.0576119838245843e-05, "loss": 0.0698, "step": 1118 }, { "epoch": 1.0, "learning_rate": 1.0561732205424211e-05, "loss": 0.0659, "step": 1119 }, { "epoch": 1.0, "learning_rate": 1.0547343406018602e-05, "loss": 0.0689, "step": 1120 }, { "epoch": 1.0, "learning_rate": 1.0532953469911127e-05, "loss": 0.0645, "step": 1121 }, { "epoch": 1.0, "learning_rate": 1.0518562426986253e-05, "loss": 0.0724, "step": 1122 }, { "epoch": 1.0, "learning_rate": 1.050417030713075e-05, "loss": 0.0636, "step": 1123 }, { "epoch": 1.0, "learning_rate": 1.0489777140233619e-05, "loss": 0.0666, "step": 1124 }, { "epoch": 1.0, "learning_rate": 1.0475382956186045e-05, "loss": 0.0517, "step": 1125 }, { "epoch": 1.0, "learning_rate": 1.0460987784881313e-05, "loss": 0.0605, "step": 1126 }, { "epoch": 1.0, "learning_rate": 1.0446591656214769e-05, "loss": 0.0628, "step": 1127 }, { "epoch": 1.0, "learning_rate": 1.043219460008374e-05, "loss": 0.0547, "step": 1128 }, { "epoch": 1.0, "learning_rate": 1.0417796646387484e-05, "loss": 0.0559, "step": 1129 }, { "epoch": 1.01, "learning_rate": 1.0403397825027122e-05, "loss": 0.0552, "step": 1130 }, { "epoch": 1.01, "learning_rate": 1.038899816590557e-05, "loss": 0.0586, "step": 1131 }, { "epoch": 1.01, "learning_rate": 1.0374597698927496e-05, "loss": 0.0576, "step": 1132 }, { "epoch": 1.01, "learning_rate": 1.0360196453999236e-05, "loss": 0.0652, "step": 1133 }, { "epoch": 1.01, "learning_rate": 1.034579446102875e-05, "loss": 0.0648, "step": 1134 }, { "epoch": 1.01, "learning_rate": 1.0331391749925539e-05, "loss": 0.0469, "step": 1135 }, { "epoch": 1.01, "learning_rate": 1.0316988350600608e-05, "loss": 0.0651, "step": 1136 }, { "epoch": 1.01, "learning_rate": 1.0302584292966384e-05, "loss": 0.0504, "step": 1137 }, { "epoch": 1.01, "learning_rate": 1.0288179606936666e-05, "loss": 0.0549, "step": 1138 }, { "epoch": 1.01, "learning_rate": 1.0273774322426553e-05, "loss": 0.0527, "step": 1139 }, { "epoch": 1.01, "learning_rate": 1.025936846935239e-05, "loss": 0.059, "step": 1140 }, { "epoch": 1.02, "learning_rate": 1.0244962077631703e-05, "loss": 0.0585, "step": 1141 }, { "epoch": 1.02, "learning_rate": 1.0230555177183136e-05, "loss": 0.0608, "step": 1142 }, { "epoch": 1.02, "learning_rate": 1.0216147797926387e-05, "loss": 0.0564, "step": 1143 }, { "epoch": 1.02, "learning_rate": 1.0201739969782154e-05, "loss": 0.0506, "step": 1144 }, { "epoch": 1.02, "learning_rate": 1.0187331722672061e-05, "loss": 0.0558, "step": 1145 }, { "epoch": 1.02, "learning_rate": 1.0172923086518607e-05, "loss": 0.0539, "step": 1146 }, { "epoch": 1.02, "learning_rate": 1.0158514091245094e-05, "loss": 0.0591, "step": 1147 }, { "epoch": 1.02, "learning_rate": 1.0144104766775574e-05, "loss": 0.0644, "step": 1148 }, { "epoch": 1.02, "learning_rate": 1.012969514303478e-05, "loss": 0.0523, "step": 1149 }, { "epoch": 1.02, "learning_rate": 1.0115285249948073e-05, "loss": 0.0499, "step": 1150 }, { "epoch": 1.02, "learning_rate": 1.0100875117441364e-05, "loss": 0.0592, "step": 1151 }, { "epoch": 1.02, "learning_rate": 1.0086464775441064e-05, "loss": 0.0572, "step": 1152 }, { "epoch": 1.03, "learning_rate": 1.0072054253874027e-05, "loss": 0.0564, "step": 1153 }, { "epoch": 1.03, "learning_rate": 1.0057643582667467e-05, "loss": 0.0568, "step": 1154 }, { "epoch": 1.03, "learning_rate": 1.0043232791748918e-05, "loss": 0.0571, "step": 1155 }, { "epoch": 1.03, "learning_rate": 1.0028821911046158e-05, "loss": 0.0581, "step": 1156 }, { "epoch": 1.03, "learning_rate": 1.0014410970487157e-05, "loss": 0.0568, "step": 1157 }, { "epoch": 1.03, "learning_rate": 1e-05, "loss": 0.0503, "step": 1158 }, { "epoch": 1.03, "learning_rate": 9.985589029512845e-06, "loss": 0.0546, "step": 1159 }, { "epoch": 1.03, "learning_rate": 9.971178088953845e-06, "loss": 0.054, "step": 1160 }, { "epoch": 1.03, "learning_rate": 9.956767208251086e-06, "loss": 0.0623, "step": 1161 }, { "epoch": 1.03, "learning_rate": 9.942356417332538e-06, "loss": 0.0536, "step": 1162 }, { "epoch": 1.03, "learning_rate": 9.927945746125975e-06, "loss": 0.0588, "step": 1163 }, { "epoch": 1.04, "learning_rate": 9.913535224558936e-06, "loss": 0.0564, "step": 1164 }, { "epoch": 1.04, "learning_rate": 9.89912488255864e-06, "loss": 0.0508, "step": 1165 }, { "epoch": 1.04, "learning_rate": 9.884714750051929e-06, "loss": 0.0493, "step": 1166 }, { "epoch": 1.04, "learning_rate": 9.870304856965222e-06, "loss": 0.0567, "step": 1167 }, { "epoch": 1.04, "learning_rate": 9.855895233224431e-06, "loss": 0.0509, "step": 1168 }, { "epoch": 1.04, "learning_rate": 9.841485908754911e-06, "loss": 0.0586, "step": 1169 }, { "epoch": 1.04, "learning_rate": 9.8270769134814e-06, "loss": 0.0555, "step": 1170 }, { "epoch": 1.04, "learning_rate": 9.81266827732794e-06, "loss": 0.055, "step": 1171 }, { "epoch": 1.04, "learning_rate": 9.798260030217846e-06, "loss": 0.0611, "step": 1172 }, { "epoch": 1.04, "learning_rate": 9.783852202073614e-06, "loss": 0.0522, "step": 1173 }, { "epoch": 1.04, "learning_rate": 9.769444822816865e-06, "loss": 0.0591, "step": 1174 }, { "epoch": 1.05, "learning_rate": 9.755037922368298e-06, "loss": 0.0541, "step": 1175 }, { "epoch": 1.05, "learning_rate": 9.740631530647611e-06, "loss": 0.0643, "step": 1176 }, { "epoch": 1.05, "learning_rate": 9.726225677573449e-06, "loss": 0.0561, "step": 1177 }, { "epoch": 1.05, "learning_rate": 9.711820393063337e-06, "loss": 0.0565, "step": 1178 }, { "epoch": 1.05, "learning_rate": 9.697415707033618e-06, "loss": 0.0623, "step": 1179 }, { "epoch": 1.05, "learning_rate": 9.683011649399393e-06, "loss": 0.0615, "step": 1180 }, { "epoch": 1.05, "learning_rate": 9.668608250074464e-06, "loss": 0.0612, "step": 1181 }, { "epoch": 1.05, "learning_rate": 9.654205538971254e-06, "loss": 0.0621, "step": 1182 }, { "epoch": 1.05, "learning_rate": 9.639803546000767e-06, "loss": 0.0653, "step": 1183 }, { "epoch": 1.05, "learning_rate": 9.625402301072508e-06, "loss": 0.0566, "step": 1184 }, { "epoch": 1.05, "learning_rate": 9.611001834094434e-06, "loss": 0.0613, "step": 1185 }, { "epoch": 1.06, "learning_rate": 9.596602174972883e-06, "loss": 0.056, "step": 1186 }, { "epoch": 1.06, "learning_rate": 9.582203353612518e-06, "loss": 0.0603, "step": 1187 }, { "epoch": 1.06, "learning_rate": 9.56780539991626e-06, "loss": 0.0599, "step": 1188 }, { "epoch": 1.06, "learning_rate": 9.553408343785233e-06, "loss": 0.0571, "step": 1189 }, { "epoch": 1.06, "learning_rate": 9.539012215118688e-06, "loss": 0.0584, "step": 1190 }, { "epoch": 1.06, "learning_rate": 9.52461704381396e-06, "loss": 0.062, "step": 1191 }, { "epoch": 1.06, "learning_rate": 9.510222859766383e-06, "loss": 0.057, "step": 1192 }, { "epoch": 1.06, "learning_rate": 9.495829692869255e-06, "loss": 0.0524, "step": 1193 }, { "epoch": 1.06, "learning_rate": 9.48143757301375e-06, "loss": 0.0539, "step": 1194 }, { "epoch": 1.06, "learning_rate": 9.467046530088875e-06, "loss": 0.0543, "step": 1195 }, { "epoch": 1.06, "learning_rate": 9.452656593981398e-06, "loss": 0.0588, "step": 1196 }, { "epoch": 1.06, "learning_rate": 9.438267794575792e-06, "loss": 0.0506, "step": 1197 }, { "epoch": 1.07, "learning_rate": 9.423880161754158e-06, "loss": 0.0644, "step": 1198 }, { "epoch": 1.07, "learning_rate": 9.40949372539619e-06, "loss": 0.0562, "step": 1199 }, { "epoch": 1.07, "learning_rate": 9.395108515379082e-06, "loss": 0.0529, "step": 1200 }, { "epoch": 1.07, "learning_rate": 9.380724561577495e-06, "loss": 0.0552, "step": 1201 }, { "epoch": 1.07, "learning_rate": 9.366341893863467e-06, "loss": 0.0558, "step": 1202 }, { "epoch": 1.07, "learning_rate": 9.351960542106375e-06, "loss": 0.0597, "step": 1203 }, { "epoch": 1.07, "learning_rate": 9.337580536172864e-06, "loss": 0.0538, "step": 1204 }, { "epoch": 1.07, "learning_rate": 9.323201905926782e-06, "loss": 0.0659, "step": 1205 }, { "epoch": 1.07, "learning_rate": 9.308824681229115e-06, "loss": 0.0477, "step": 1206 }, { "epoch": 1.07, "learning_rate": 9.294448891937936e-06, "loss": 0.0562, "step": 1207 }, { "epoch": 1.07, "learning_rate": 9.28007456790833e-06, "loss": 0.0531, "step": 1208 }, { "epoch": 1.08, "learning_rate": 9.265701738992353e-06, "loss": 0.0644, "step": 1209 }, { "epoch": 1.08, "learning_rate": 9.251330435038935e-06, "loss": 0.0527, "step": 1210 }, { "epoch": 1.08, "learning_rate": 9.236960685893857e-06, "loss": 0.0461, "step": 1211 }, { "epoch": 1.08, "learning_rate": 9.222592521399666e-06, "loss": 0.0556, "step": 1212 }, { "epoch": 1.08, "learning_rate": 9.208225971395618e-06, "loss": 0.0561, "step": 1213 }, { "epoch": 1.08, "learning_rate": 9.19386106571761e-06, "loss": 0.0484, "step": 1214 }, { "epoch": 1.08, "learning_rate": 9.179497834198134e-06, "loss": 0.0541, "step": 1215 }, { "epoch": 1.08, "learning_rate": 9.165136306666196e-06, "loss": 0.0516, "step": 1216 }, { "epoch": 1.08, "learning_rate": 9.150776512947273e-06, "loss": 0.0489, "step": 1217 }, { "epoch": 1.08, "learning_rate": 9.13641848286323e-06, "loss": 0.0562, "step": 1218 }, { "epoch": 1.08, "learning_rate": 9.122062246232272e-06, "loss": 0.0515, "step": 1219 }, { "epoch": 1.09, "learning_rate": 9.107707832868896e-06, "loss": 0.0586, "step": 1220 }, { "epoch": 1.09, "learning_rate": 9.093355272583788e-06, "loss": 0.0478, "step": 1221 }, { "epoch": 1.09, "learning_rate": 9.079004595183799e-06, "loss": 0.0548, "step": 1222 }, { "epoch": 1.09, "learning_rate": 9.064655830471871e-06, "loss": 0.0657, "step": 1223 }, { "epoch": 1.09, "learning_rate": 9.050309008246965e-06, "loss": 0.0561, "step": 1224 }, { "epoch": 1.09, "learning_rate": 9.035964158304018e-06, "loss": 0.0527, "step": 1225 }, { "epoch": 1.09, "learning_rate": 9.021621310433861e-06, "loss": 0.0606, "step": 1226 }, { "epoch": 1.09, "learning_rate": 9.007280494423173e-06, "loss": 0.0594, "step": 1227 }, { "epoch": 1.09, "learning_rate": 8.992941740054418e-06, "loss": 0.0552, "step": 1228 }, { "epoch": 1.09, "learning_rate": 8.97860507710577e-06, "loss": 0.0641, "step": 1229 }, { "epoch": 1.09, "learning_rate": 8.964270535351058e-06, "loss": 0.0583, "step": 1230 }, { "epoch": 1.1, "learning_rate": 8.94993814455972e-06, "loss": 0.0551, "step": 1231 }, { "epoch": 1.1, "learning_rate": 8.935607934496708e-06, "loss": 0.0574, "step": 1232 }, { "epoch": 1.1, "learning_rate": 8.921279934922463e-06, "loss": 0.0513, "step": 1233 }, { "epoch": 1.1, "learning_rate": 8.906954175592819e-06, "loss": 0.0548, "step": 1234 }, { "epoch": 1.1, "learning_rate": 8.892630686258968e-06, "loss": 0.0584, "step": 1235 }, { "epoch": 1.1, "learning_rate": 8.87830949666739e-06, "loss": 0.0558, "step": 1236 }, { "epoch": 1.1, "learning_rate": 8.863990636559777e-06, "loss": 0.0564, "step": 1237 }, { "epoch": 1.1, "learning_rate": 8.849674135672999e-06, "loss": 0.0646, "step": 1238 }, { "epoch": 1.1, "learning_rate": 8.83536002373901e-06, "loss": 0.0479, "step": 1239 }, { "epoch": 1.1, "learning_rate": 8.821048330484814e-06, "loss": 0.0566, "step": 1240 }, { "epoch": 1.1, "learning_rate": 8.806739085632388e-06, "loss": 0.0501, "step": 1241 }, { "epoch": 1.1, "learning_rate": 8.792432318898624e-06, "loss": 0.0622, "step": 1242 }, { "epoch": 1.11, "learning_rate": 8.778128059995269e-06, "loss": 0.056, "step": 1243 }, { "epoch": 1.11, "learning_rate": 8.763826338628865e-06, "loss": 0.0503, "step": 1244 }, { "epoch": 1.11, "learning_rate": 8.749527184500673e-06, "loss": 0.0535, "step": 1245 }, { "epoch": 1.11, "learning_rate": 8.735230627306637e-06, "loss": 0.0497, "step": 1246 }, { "epoch": 1.11, "learning_rate": 8.720936696737295e-06, "loss": 0.0513, "step": 1247 }, { "epoch": 1.11, "learning_rate": 8.706645422477739e-06, "loss": 0.0518, "step": 1248 }, { "epoch": 1.11, "learning_rate": 8.692356834207542e-06, "loss": 0.0589, "step": 1249 }, { "epoch": 1.11, "learning_rate": 8.678070961600693e-06, "loss": 0.061, "step": 1250 }, { "epoch": 1.11, "learning_rate": 8.663787834325548e-06, "loss": 0.0587, "step": 1251 }, { "epoch": 1.11, "learning_rate": 8.649507482044766e-06, "loss": 0.0584, "step": 1252 }, { "epoch": 1.11, "learning_rate": 8.63522993441523e-06, "loss": 0.0528, "step": 1253 }, { "epoch": 1.12, "learning_rate": 8.62095522108801e-06, "loss": 0.0627, "step": 1254 }, { "epoch": 1.12, "learning_rate": 8.60668337170828e-06, "loss": 0.0514, "step": 1255 }, { "epoch": 1.12, "learning_rate": 8.592414415915275e-06, "loss": 0.0592, "step": 1256 }, { "epoch": 1.12, "learning_rate": 8.578148383342216e-06, "loss": 0.0543, "step": 1257 }, { "epoch": 1.12, "learning_rate": 8.563885303616253e-06, "loss": 0.0554, "step": 1258 }, { "epoch": 1.12, "learning_rate": 8.549625206358404e-06, "loss": 0.0528, "step": 1259 }, { "epoch": 1.12, "learning_rate": 8.5353681211835e-06, "loss": 0.0572, "step": 1260 }, { "epoch": 1.12, "learning_rate": 8.521114077700106e-06, "loss": 0.0478, "step": 1261 }, { "epoch": 1.12, "learning_rate": 8.506863105510476e-06, "loss": 0.046, "step": 1262 }, { "epoch": 1.12, "learning_rate": 8.492615234210483e-06, "loss": 0.0509, "step": 1263 }, { "epoch": 1.12, "learning_rate": 8.478370493389563e-06, "loss": 0.0528, "step": 1264 }, { "epoch": 1.13, "learning_rate": 8.464128912630649e-06, "loss": 0.058, "step": 1265 }, { "epoch": 1.13, "learning_rate": 8.44989052151011e-06, "loss": 0.0483, "step": 1266 }, { "epoch": 1.13, "learning_rate": 8.43565534959769e-06, "loss": 0.0524, "step": 1267 }, { "epoch": 1.13, "learning_rate": 8.42142342645646e-06, "loss": 0.0581, "step": 1268 }, { "epoch": 1.13, "learning_rate": 8.407194781642727e-06, "loss": 0.0648, "step": 1269 }, { "epoch": 1.13, "learning_rate": 8.392969444705998e-06, "loss": 0.0542, "step": 1270 }, { "epoch": 1.13, "learning_rate": 8.378747445188908e-06, "loss": 0.0601, "step": 1271 }, { "epoch": 1.13, "learning_rate": 8.364528812627164e-06, "loss": 0.06, "step": 1272 }, { "epoch": 1.13, "learning_rate": 8.350313576549477e-06, "loss": 0.0597, "step": 1273 }, { "epoch": 1.13, "learning_rate": 8.336101766477506e-06, "loss": 0.0674, "step": 1274 }, { "epoch": 1.13, "learning_rate": 8.32189341192579e-06, "loss": 0.0552, "step": 1275 }, { "epoch": 1.14, "learning_rate": 8.307688542401709e-06, "loss": 0.0533, "step": 1276 }, { "epoch": 1.14, "learning_rate": 8.293487187405386e-06, "loss": 0.0494, "step": 1277 }, { "epoch": 1.14, "learning_rate": 8.279289376429653e-06, "loss": 0.0578, "step": 1278 }, { "epoch": 1.14, "learning_rate": 8.26509513895998e-06, "loss": 0.0571, "step": 1279 }, { "epoch": 1.14, "learning_rate": 8.25090450447442e-06, "loss": 0.0576, "step": 1280 }, { "epoch": 1.14, "learning_rate": 8.236717502443536e-06, "loss": 0.0553, "step": 1281 }, { "epoch": 1.14, "learning_rate": 8.222534162330355e-06, "loss": 0.051, "step": 1282 }, { "epoch": 1.14, "learning_rate": 8.20835451359029e-06, "loss": 0.0525, "step": 1283 }, { "epoch": 1.14, "learning_rate": 8.194178585671102e-06, "loss": 0.0596, "step": 1284 }, { "epoch": 1.14, "learning_rate": 8.180006408012812e-06, "loss": 0.0534, "step": 1285 }, { "epoch": 1.14, "learning_rate": 8.16583801004766e-06, "loss": 0.0604, "step": 1286 }, { "epoch": 1.15, "learning_rate": 8.151673421200026e-06, "loss": 0.056, "step": 1287 }, { "epoch": 1.15, "learning_rate": 8.137512670886397e-06, "loss": 0.0559, "step": 1288 }, { "epoch": 1.15, "learning_rate": 8.123355788515269e-06, "loss": 0.0551, "step": 1289 }, { "epoch": 1.15, "learning_rate": 8.109202803487121e-06, "loss": 0.057, "step": 1290 }, { "epoch": 1.15, "learning_rate": 8.095053745194323e-06, "loss": 0.0557, "step": 1291 }, { "epoch": 1.15, "learning_rate": 8.080908643021107e-06, "loss": 0.0544, "step": 1292 }, { "epoch": 1.15, "learning_rate": 8.066767526343477e-06, "loss": 0.0546, "step": 1293 }, { "epoch": 1.15, "learning_rate": 8.052630424529166e-06, "loss": 0.0602, "step": 1294 }, { "epoch": 1.15, "learning_rate": 8.038497366937562e-06, "loss": 0.0586, "step": 1295 }, { "epoch": 1.15, "learning_rate": 8.024368382919665e-06, "loss": 0.058, "step": 1296 }, { "epoch": 1.15, "learning_rate": 8.010243501818004e-06, "loss": 0.0555, "step": 1297 }, { "epoch": 1.15, "learning_rate": 7.996122752966596e-06, "loss": 0.0588, "step": 1298 }, { "epoch": 1.16, "learning_rate": 7.982006165690865e-06, "loss": 0.0592, "step": 1299 }, { "epoch": 1.16, "learning_rate": 7.967893769307608e-06, "loss": 0.0626, "step": 1300 }, { "epoch": 1.16, "learning_rate": 7.953785593124908e-06, "loss": 0.054, "step": 1301 }, { "epoch": 1.16, "learning_rate": 7.93968166644209e-06, "loss": 0.0635, "step": 1302 }, { "epoch": 1.16, "learning_rate": 7.925582018549642e-06, "loss": 0.0579, "step": 1303 }, { "epoch": 1.16, "learning_rate": 7.91148667872918e-06, "loss": 0.0629, "step": 1304 }, { "epoch": 1.16, "learning_rate": 7.897395676253363e-06, "loss": 0.0551, "step": 1305 }, { "epoch": 1.16, "learning_rate": 7.88330904038585e-06, "loss": 0.0526, "step": 1306 }, { "epoch": 1.16, "learning_rate": 7.869226800381224e-06, "loss": 0.0562, "step": 1307 }, { "epoch": 1.16, "learning_rate": 7.855148985484946e-06, "loss": 0.0711, "step": 1308 }, { "epoch": 1.16, "learning_rate": 7.841075624933285e-06, "loss": 0.063, "step": 1309 }, { "epoch": 1.17, "learning_rate": 7.827006747953255e-06, "loss": 0.0506, "step": 1310 }, { "epoch": 1.17, "learning_rate": 7.812942383762562e-06, "loss": 0.0573, "step": 1311 }, { "epoch": 1.17, "learning_rate": 7.798882561569546e-06, "loss": 0.0624, "step": 1312 }, { "epoch": 1.17, "learning_rate": 7.784827310573101e-06, "loss": 0.0612, "step": 1313 }, { "epoch": 1.17, "learning_rate": 7.77077665996264e-06, "loss": 0.054, "step": 1314 }, { "epoch": 1.17, "learning_rate": 7.756730638918011e-06, "loss": 0.0541, "step": 1315 }, { "epoch": 1.17, "learning_rate": 7.742689276609459e-06, "loss": 0.0613, "step": 1316 }, { "epoch": 1.17, "learning_rate": 7.728652602197552e-06, "loss": 0.0581, "step": 1317 }, { "epoch": 1.17, "learning_rate": 7.71462064483311e-06, "loss": 0.0534, "step": 1318 }, { "epoch": 1.17, "learning_rate": 7.700593433657172e-06, "loss": 0.0633, "step": 1319 }, { "epoch": 1.17, "learning_rate": 7.686570997800914e-06, "loss": 0.0563, "step": 1320 }, { "epoch": 1.18, "learning_rate": 7.672553366385592e-06, "loss": 0.0593, "step": 1321 }, { "epoch": 1.18, "learning_rate": 7.658540568522487e-06, "loss": 0.0516, "step": 1322 }, { "epoch": 1.18, "learning_rate": 7.644532633312842e-06, "loss": 0.0563, "step": 1323 }, { "epoch": 1.18, "learning_rate": 7.630529589847807e-06, "loss": 0.0542, "step": 1324 }, { "epoch": 1.18, "learning_rate": 7.616531467208362e-06, "loss": 0.0544, "step": 1325 }, { "epoch": 1.18, "learning_rate": 7.602538294465273e-06, "loss": 0.0552, "step": 1326 }, { "epoch": 1.18, "learning_rate": 7.588550100679033e-06, "loss": 0.0515, "step": 1327 }, { "epoch": 1.18, "learning_rate": 7.574566914899779e-06, "loss": 0.0592, "step": 1328 }, { "epoch": 1.18, "learning_rate": 7.56058876616726e-06, "loss": 0.062, "step": 1329 }, { "epoch": 1.18, "learning_rate": 7.546615683510767e-06, "loss": 0.0585, "step": 1330 }, { "epoch": 1.18, "learning_rate": 7.532647695949053e-06, "loss": 0.0606, "step": 1331 }, { "epoch": 1.19, "learning_rate": 7.518684832490311e-06, "loss": 0.0507, "step": 1332 }, { "epoch": 1.19, "learning_rate": 7.504727122132078e-06, "loss": 0.0547, "step": 1333 }, { "epoch": 1.19, "learning_rate": 7.490774593861192e-06, "loss": 0.0543, "step": 1334 }, { "epoch": 1.19, "learning_rate": 7.4768272766537345e-06, "loss": 0.0543, "step": 1335 }, { "epoch": 1.19, "learning_rate": 7.462885199474956e-06, "loss": 0.0508, "step": 1336 }, { "epoch": 1.19, "learning_rate": 7.4489483912792336e-06, "loss": 0.049, "step": 1337 }, { "epoch": 1.19, "learning_rate": 7.4350168810099955e-06, "loss": 0.0594, "step": 1338 }, { "epoch": 1.19, "learning_rate": 7.421090697599667e-06, "loss": 0.0511, "step": 1339 }, { "epoch": 1.19, "learning_rate": 7.40716986996962e-06, "loss": 0.0516, "step": 1340 }, { "epoch": 1.19, "learning_rate": 7.393254427030097e-06, "loss": 0.0575, "step": 1341 }, { "epoch": 1.19, "learning_rate": 7.379344397680151e-06, "loss": 0.0554, "step": 1342 }, { "epoch": 1.19, "learning_rate": 7.365439810807609e-06, "loss": 0.0586, "step": 1343 }, { "epoch": 1.2, "learning_rate": 7.351540695288977e-06, "loss": 0.0611, "step": 1344 }, { "epoch": 1.2, "learning_rate": 7.337647079989412e-06, "loss": 0.0522, "step": 1345 }, { "epoch": 1.2, "learning_rate": 7.3237589937626395e-06, "loss": 0.0552, "step": 1346 }, { "epoch": 1.2, "learning_rate": 7.309876465450907e-06, "loss": 0.057, "step": 1347 }, { "epoch": 1.2, "learning_rate": 7.295999523884921e-06, "loss": 0.0577, "step": 1348 }, { "epoch": 1.2, "learning_rate": 7.2821281978837855e-06, "loss": 0.0568, "step": 1349 }, { "epoch": 1.2, "learning_rate": 7.268262516254934e-06, "loss": 0.0534, "step": 1350 }, { "epoch": 1.2, "learning_rate": 7.254402507794092e-06, "loss": 0.0486, "step": 1351 }, { "epoch": 1.2, "learning_rate": 7.240548201285186e-06, "loss": 0.057, "step": 1352 }, { "epoch": 1.2, "learning_rate": 7.226699625500317e-06, "loss": 0.0537, "step": 1353 }, { "epoch": 1.2, "learning_rate": 7.212856809199676e-06, "loss": 0.0568, "step": 1354 }, { "epoch": 1.21, "learning_rate": 7.199019781131491e-06, "loss": 0.054, "step": 1355 }, { "epoch": 1.21, "learning_rate": 7.185188570031979e-06, "loss": 0.052, "step": 1356 }, { "epoch": 1.21, "learning_rate": 7.171363204625271e-06, "loss": 0.0492, "step": 1357 }, { "epoch": 1.21, "learning_rate": 7.157543713623353e-06, "loss": 0.0586, "step": 1358 }, { "epoch": 1.21, "learning_rate": 7.14373012572602e-06, "loss": 0.0585, "step": 1359 }, { "epoch": 1.21, "learning_rate": 7.129922469620798e-06, "loss": 0.0521, "step": 1360 }, { "epoch": 1.21, "learning_rate": 7.116120773982905e-06, "loss": 0.052, "step": 1361 }, { "epoch": 1.21, "learning_rate": 7.102325067475171e-06, "loss": 0.0526, "step": 1362 }, { "epoch": 1.21, "learning_rate": 7.088535378747991e-06, "loss": 0.062, "step": 1363 }, { "epoch": 1.21, "learning_rate": 7.0747517364392694e-06, "loss": 0.0516, "step": 1364 }, { "epoch": 1.21, "learning_rate": 7.060974169174346e-06, "loss": 0.0482, "step": 1365 }, { "epoch": 1.22, "learning_rate": 7.047202705565942e-06, "loss": 0.0537, "step": 1366 }, { "epoch": 1.22, "learning_rate": 7.033437374214112e-06, "loss": 0.0583, "step": 1367 }, { "epoch": 1.22, "learning_rate": 7.019678203706164e-06, "loss": 0.0529, "step": 1368 }, { "epoch": 1.22, "learning_rate": 7.005925222616624e-06, "loss": 0.0562, "step": 1369 }, { "epoch": 1.22, "learning_rate": 6.992178459507153e-06, "loss": 0.0596, "step": 1370 }, { "epoch": 1.22, "learning_rate": 6.9784379429265005e-06, "loss": 0.0546, "step": 1371 }, { "epoch": 1.22, "learning_rate": 6.964703701410455e-06, "loss": 0.0497, "step": 1372 }, { "epoch": 1.22, "learning_rate": 6.950975763481758e-06, "loss": 0.0592, "step": 1373 }, { "epoch": 1.22, "learning_rate": 6.937254157650068e-06, "loss": 0.0528, "step": 1374 }, { "epoch": 1.22, "learning_rate": 6.923538912411893e-06, "loss": 0.0528, "step": 1375 }, { "epoch": 1.22, "learning_rate": 6.909830056250527e-06, "loss": 0.0516, "step": 1376 }, { "epoch": 1.23, "learning_rate": 6.896127617636001e-06, "loss": 0.0587, "step": 1377 }, { "epoch": 1.23, "learning_rate": 6.882431625025016e-06, "loss": 0.0494, "step": 1378 }, { "epoch": 1.23, "learning_rate": 6.86874210686088e-06, "loss": 0.0484, "step": 1379 }, { "epoch": 1.23, "learning_rate": 6.855059091573472e-06, "loss": 0.0538, "step": 1380 }, { "epoch": 1.23, "learning_rate": 6.841382607579148e-06, "loss": 0.0499, "step": 1381 }, { "epoch": 1.23, "learning_rate": 6.827712683280707e-06, "loss": 0.0555, "step": 1382 }, { "epoch": 1.23, "learning_rate": 6.81404934706733e-06, "loss": 0.0555, "step": 1383 }, { "epoch": 1.23, "learning_rate": 6.800392627314506e-06, "loss": 0.0623, "step": 1384 }, { "epoch": 1.23, "learning_rate": 6.786742552383994e-06, "loss": 0.056, "step": 1385 }, { "epoch": 1.23, "learning_rate": 6.773099150623742e-06, "loss": 0.0493, "step": 1386 }, { "epoch": 1.23, "learning_rate": 6.759462450367846e-06, "loss": 0.0556, "step": 1387 }, { "epoch": 1.23, "learning_rate": 6.745832479936492e-06, "loss": 0.0509, "step": 1388 }, { "epoch": 1.24, "learning_rate": 6.732209267635874e-06, "loss": 0.0523, "step": 1389 }, { "epoch": 1.24, "learning_rate": 6.7185928417581615e-06, "loss": 0.0582, "step": 1390 }, { "epoch": 1.24, "learning_rate": 6.704983230581425e-06, "loss": 0.0594, "step": 1391 }, { "epoch": 1.24, "learning_rate": 6.691380462369588e-06, "loss": 0.0556, "step": 1392 }, { "epoch": 1.24, "learning_rate": 6.677784565372359e-06, "loss": 0.0661, "step": 1393 }, { "epoch": 1.24, "learning_rate": 6.664195567825174e-06, "loss": 0.0654, "step": 1394 }, { "epoch": 1.24, "learning_rate": 6.650613497949143e-06, "loss": 0.0497, "step": 1395 }, { "epoch": 1.24, "learning_rate": 6.637038383950998e-06, "loss": 0.0514, "step": 1396 }, { "epoch": 1.24, "learning_rate": 6.62347025402301e-06, "loss": 0.054, "step": 1397 }, { "epoch": 1.24, "learning_rate": 6.609909136342956e-06, "loss": 0.0472, "step": 1398 }, { "epoch": 1.24, "learning_rate": 6.596355059074043e-06, "loss": 0.0602, "step": 1399 }, { "epoch": 1.25, "learning_rate": 6.582808050364864e-06, "loss": 0.056, "step": 1400 }, { "epoch": 1.25, "learning_rate": 6.569268138349329e-06, "loss": 0.0544, "step": 1401 }, { "epoch": 1.25, "learning_rate": 6.5557353511466085e-06, "loss": 0.0618, "step": 1402 }, { "epoch": 1.25, "learning_rate": 6.542209716861074e-06, "loss": 0.0559, "step": 1403 }, { "epoch": 1.25, "learning_rate": 6.528691263582254e-06, "loss": 0.0526, "step": 1404 }, { "epoch": 1.25, "learning_rate": 6.515180019384751e-06, "loss": 0.0561, "step": 1405 }, { "epoch": 1.25, "learning_rate": 6.501676012328202e-06, "loss": 0.0498, "step": 1406 }, { "epoch": 1.25, "learning_rate": 6.4881792704572084e-06, "loss": 0.0553, "step": 1407 }, { "epoch": 1.25, "learning_rate": 6.474689821801295e-06, "loss": 0.0542, "step": 1408 }, { "epoch": 1.25, "learning_rate": 6.461207694374828e-06, "loss": 0.053, "step": 1409 }, { "epoch": 1.25, "learning_rate": 6.447732916176975e-06, "loss": 0.0508, "step": 1410 }, { "epoch": 1.26, "learning_rate": 6.43426551519164e-06, "loss": 0.0518, "step": 1411 }, { "epoch": 1.26, "learning_rate": 6.420805519387412e-06, "loss": 0.0486, "step": 1412 }, { "epoch": 1.26, "learning_rate": 6.407352956717489e-06, "loss": 0.0701, "step": 1413 }, { "epoch": 1.26, "learning_rate": 6.393907855119645e-06, "loss": 0.0613, "step": 1414 }, { "epoch": 1.26, "learning_rate": 6.380470242516147e-06, "loss": 0.0502, "step": 1415 }, { "epoch": 1.26, "learning_rate": 6.367040146813721e-06, "loss": 0.0566, "step": 1416 }, { "epoch": 1.26, "learning_rate": 6.353617595903472e-06, "loss": 0.0536, "step": 1417 }, { "epoch": 1.26, "learning_rate": 6.340202617660842e-06, "loss": 0.0484, "step": 1418 }, { "epoch": 1.26, "learning_rate": 6.326795239945543e-06, "loss": 0.0583, "step": 1419 }, { "epoch": 1.26, "learning_rate": 6.313395490601513e-06, "loss": 0.0549, "step": 1420 }, { "epoch": 1.26, "learning_rate": 6.3000033974568305e-06, "loss": 0.0552, "step": 1421 }, { "epoch": 1.27, "learning_rate": 6.2866189883236885e-06, "loss": 0.0507, "step": 1422 }, { "epoch": 1.27, "learning_rate": 6.2732422909983116e-06, "loss": 0.0543, "step": 1423 }, { "epoch": 1.27, "learning_rate": 6.259873333260917e-06, "loss": 0.0511, "step": 1424 }, { "epoch": 1.27, "learning_rate": 6.246512142875643e-06, "loss": 0.0512, "step": 1425 }, { "epoch": 1.27, "learning_rate": 6.233158747590502e-06, "loss": 0.0478, "step": 1426 }, { "epoch": 1.27, "learning_rate": 6.219813175137306e-06, "loss": 0.0582, "step": 1427 }, { "epoch": 1.27, "learning_rate": 6.206475453231644e-06, "loss": 0.0553, "step": 1428 }, { "epoch": 1.27, "learning_rate": 6.193145609572777e-06, "loss": 0.0551, "step": 1429 }, { "epoch": 1.27, "learning_rate": 6.179823671843621e-06, "loss": 0.0493, "step": 1430 }, { "epoch": 1.27, "learning_rate": 6.16650966771066e-06, "loss": 0.0543, "step": 1431 }, { "epoch": 1.27, "learning_rate": 6.153203624823918e-06, "loss": 0.0583, "step": 1432 }, { "epoch": 1.27, "learning_rate": 6.1399055708168675e-06, "loss": 0.0555, "step": 1433 }, { "epoch": 1.28, "learning_rate": 6.126615533306405e-06, "loss": 0.0584, "step": 1434 }, { "epoch": 1.28, "learning_rate": 6.113333539892764e-06, "loss": 0.0574, "step": 1435 }, { "epoch": 1.28, "learning_rate": 6.100059618159493e-06, "loss": 0.0543, "step": 1436 }, { "epoch": 1.28, "learning_rate": 6.086793795673357e-06, "loss": 0.0533, "step": 1437 }, { "epoch": 1.28, "learning_rate": 6.073536099984314e-06, "loss": 0.0571, "step": 1438 }, { "epoch": 1.28, "learning_rate": 6.060286558625435e-06, "loss": 0.0533, "step": 1439 }, { "epoch": 1.28, "learning_rate": 6.047045199112865e-06, "loss": 0.0527, "step": 1440 }, { "epoch": 1.28, "learning_rate": 6.033812048945749e-06, "loss": 0.049, "step": 1441 }, { "epoch": 1.28, "learning_rate": 6.020587135606193e-06, "loss": 0.0618, "step": 1442 }, { "epoch": 1.28, "learning_rate": 6.007370486559185e-06, "loss": 0.0582, "step": 1443 }, { "epoch": 1.28, "learning_rate": 5.994162129252561e-06, "loss": 0.0523, "step": 1444 }, { "epoch": 1.29, "learning_rate": 5.980962091116933e-06, "loss": 0.0533, "step": 1445 }, { "epoch": 1.29, "learning_rate": 5.967770399565638e-06, "loss": 0.052, "step": 1446 }, { "epoch": 1.29, "learning_rate": 5.9545870819946705e-06, "loss": 0.0557, "step": 1447 }, { "epoch": 1.29, "learning_rate": 5.941412165782645e-06, "loss": 0.0582, "step": 1448 }, { "epoch": 1.29, "learning_rate": 5.928245678290723e-06, "loss": 0.0463, "step": 1449 }, { "epoch": 1.29, "learning_rate": 5.915087646862561e-06, "loss": 0.0589, "step": 1450 }, { "epoch": 1.29, "learning_rate": 5.9019380988242555e-06, "loss": 0.0429, "step": 1451 }, { "epoch": 1.29, "learning_rate": 5.888797061484288e-06, "loss": 0.0532, "step": 1452 }, { "epoch": 1.29, "learning_rate": 5.875664562133462e-06, "loss": 0.0493, "step": 1453 }, { "epoch": 1.29, "learning_rate": 5.86254062804485e-06, "loss": 0.0519, "step": 1454 }, { "epoch": 1.29, "learning_rate": 5.849425286473737e-06, "loss": 0.0563, "step": 1455 }, { "epoch": 1.3, "learning_rate": 5.836318564657561e-06, "loss": 0.0595, "step": 1456 }, { "epoch": 1.3, "learning_rate": 5.823220489815867e-06, "loss": 0.0489, "step": 1457 }, { "epoch": 1.3, "learning_rate": 5.810131089150228e-06, "loss": 0.0576, "step": 1458 }, { "epoch": 1.3, "learning_rate": 5.79705038984421e-06, "loss": 0.0511, "step": 1459 }, { "epoch": 1.3, "learning_rate": 5.783978419063323e-06, "loss": 0.06, "step": 1460 }, { "epoch": 1.3, "learning_rate": 5.770915203954923e-06, "loss": 0.0552, "step": 1461 }, { "epoch": 1.3, "learning_rate": 5.757860771648202e-06, "loss": 0.0514, "step": 1462 }, { "epoch": 1.3, "learning_rate": 5.7448151492541025e-06, "loss": 0.0586, "step": 1463 }, { "epoch": 1.3, "learning_rate": 5.731778363865278e-06, "loss": 0.0581, "step": 1464 }, { "epoch": 1.3, "learning_rate": 5.718750442556028e-06, "loss": 0.0585, "step": 1465 }, { "epoch": 1.3, "learning_rate": 5.705731412382235e-06, "loss": 0.0558, "step": 1466 }, { "epoch": 1.31, "learning_rate": 5.692721300381322e-06, "loss": 0.0589, "step": 1467 }, { "epoch": 1.31, "learning_rate": 5.6797201335722064e-06, "loss": 0.0529, "step": 1468 }, { "epoch": 1.31, "learning_rate": 5.666727938955199e-06, "loss": 0.0582, "step": 1469 }, { "epoch": 1.31, "learning_rate": 5.653744743512e-06, "loss": 0.0493, "step": 1470 }, { "epoch": 1.31, "learning_rate": 5.640770574205614e-06, "loss": 0.058, "step": 1471 }, { "epoch": 1.31, "learning_rate": 5.627805457980298e-06, "loss": 0.0504, "step": 1472 }, { "epoch": 1.31, "learning_rate": 5.6148494217615136e-06, "loss": 0.0522, "step": 1473 }, { "epoch": 1.31, "learning_rate": 5.601902492455855e-06, "loss": 0.0544, "step": 1474 }, { "epoch": 1.31, "learning_rate": 5.5889646969510105e-06, "loss": 0.0566, "step": 1475 }, { "epoch": 1.31, "learning_rate": 5.576036062115709e-06, "loss": 0.055, "step": 1476 }, { "epoch": 1.31, "learning_rate": 5.563116614799638e-06, "loss": 0.049, "step": 1477 }, { "epoch": 1.31, "learning_rate": 5.550206381833409e-06, "loss": 0.0481, "step": 1478 }, { "epoch": 1.32, "learning_rate": 5.537305390028507e-06, "loss": 0.0536, "step": 1479 }, { "epoch": 1.32, "learning_rate": 5.524413666177216e-06, "loss": 0.0564, "step": 1480 }, { "epoch": 1.32, "learning_rate": 5.511531237052576e-06, "loss": 0.0589, "step": 1481 }, { "epoch": 1.32, "learning_rate": 5.498658129408323e-06, "loss": 0.058, "step": 1482 }, { "epoch": 1.32, "learning_rate": 5.485794369978828e-06, "loss": 0.055, "step": 1483 }, { "epoch": 1.32, "learning_rate": 5.472939985479071e-06, "loss": 0.0573, "step": 1484 }, { "epoch": 1.32, "learning_rate": 5.460095002604533e-06, "loss": 0.0497, "step": 1485 }, { "epoch": 1.32, "learning_rate": 5.447259448031188e-06, "loss": 0.0568, "step": 1486 }, { "epoch": 1.32, "learning_rate": 5.434433348415424e-06, "loss": 0.0569, "step": 1487 }, { "epoch": 1.32, "learning_rate": 5.421616730394e-06, "loss": 0.0562, "step": 1488 }, { "epoch": 1.32, "learning_rate": 5.40880962058397e-06, "loss": 0.0604, "step": 1489 }, { "epoch": 1.33, "learning_rate": 5.3960120455826545e-06, "loss": 0.0558, "step": 1490 }, { "epoch": 1.33, "learning_rate": 5.383224031967564e-06, "loss": 0.0521, "step": 1491 }, { "epoch": 1.33, "learning_rate": 5.3704456062963674e-06, "loss": 0.0592, "step": 1492 }, { "epoch": 1.33, "learning_rate": 5.357676795106798e-06, "loss": 0.0574, "step": 1493 }, { "epoch": 1.33, "learning_rate": 5.344917624916644e-06, "loss": 0.0526, "step": 1494 }, { "epoch": 1.33, "learning_rate": 5.332168122223656e-06, "loss": 0.0561, "step": 1495 }, { "epoch": 1.33, "learning_rate": 5.319428313505523e-06, "loss": 0.0484, "step": 1496 }, { "epoch": 1.33, "learning_rate": 5.306698225219781e-06, "loss": 0.0511, "step": 1497 }, { "epoch": 1.33, "learning_rate": 5.293977883803797e-06, "loss": 0.0529, "step": 1498 }, { "epoch": 1.33, "learning_rate": 5.281267315674685e-06, "loss": 0.049, "step": 1499 }, { "epoch": 1.33, "learning_rate": 5.2685665472292805e-06, "loss": 0.0524, "step": 1500 }, { "epoch": 1.34, "learning_rate": 5.25587560484404e-06, "loss": 0.0523, "step": 1501 }, { "epoch": 1.34, "learning_rate": 5.243194514875033e-06, "loss": 0.0517, "step": 1502 }, { "epoch": 1.34, "learning_rate": 5.230523303657861e-06, "loss": 0.0468, "step": 1503 }, { "epoch": 1.34, "learning_rate": 5.217861997507618e-06, "loss": 0.0483, "step": 1504 }, { "epoch": 1.34, "learning_rate": 5.205210622718811e-06, "loss": 0.0533, "step": 1505 }, { "epoch": 1.34, "learning_rate": 5.192569205565336e-06, "loss": 0.047, "step": 1506 }, { "epoch": 1.34, "learning_rate": 5.179937772300401e-06, "loss": 0.0506, "step": 1507 }, { "epoch": 1.34, "learning_rate": 5.167316349156495e-06, "loss": 0.0571, "step": 1508 }, { "epoch": 1.34, "learning_rate": 5.154704962345294e-06, "loss": 0.0629, "step": 1509 }, { "epoch": 1.34, "learning_rate": 5.142103638057652e-06, "loss": 0.0487, "step": 1510 }, { "epoch": 1.34, "learning_rate": 5.129512402463515e-06, "loss": 0.0578, "step": 1511 }, { "epoch": 1.35, "learning_rate": 5.116931281711886e-06, "loss": 0.0601, "step": 1512 }, { "epoch": 1.35, "learning_rate": 5.104360301930744e-06, "loss": 0.0557, "step": 1513 }, { "epoch": 1.35, "learning_rate": 5.091799489227027e-06, "loss": 0.0497, "step": 1514 }, { "epoch": 1.35, "learning_rate": 5.079248869686544e-06, "loss": 0.0545, "step": 1515 }, { "epoch": 1.35, "learning_rate": 5.066708469373958e-06, "loss": 0.048, "step": 1516 }, { "epoch": 1.35, "learning_rate": 5.054178314332676e-06, "loss": 0.053, "step": 1517 }, { "epoch": 1.35, "learning_rate": 5.041658430584852e-06, "loss": 0.054, "step": 1518 }, { "epoch": 1.35, "learning_rate": 5.029148844131303e-06, "loss": 0.0577, "step": 1519 }, { "epoch": 1.35, "learning_rate": 5.016649580951462e-06, "loss": 0.0527, "step": 1520 }, { "epoch": 1.35, "learning_rate": 5.004160667003314e-06, "loss": 0.062, "step": 1521 }, { "epoch": 1.35, "learning_rate": 4.991682128223362e-06, "loss": 0.0479, "step": 1522 }, { "epoch": 1.35, "learning_rate": 4.979213990526558e-06, "loss": 0.0571, "step": 1523 }, { "epoch": 1.36, "learning_rate": 4.966756279806255e-06, "loss": 0.0542, "step": 1524 }, { "epoch": 1.36, "learning_rate": 4.954309021934149e-06, "loss": 0.0537, "step": 1525 }, { "epoch": 1.36, "learning_rate": 4.9418722427602315e-06, "loss": 0.0515, "step": 1526 }, { "epoch": 1.36, "learning_rate": 4.929445968112728e-06, "loss": 0.0556, "step": 1527 }, { "epoch": 1.36, "learning_rate": 4.917030223798057e-06, "loss": 0.0488, "step": 1528 }, { "epoch": 1.36, "learning_rate": 4.904625035600752e-06, "loss": 0.0555, "step": 1529 }, { "epoch": 1.36, "learning_rate": 4.892230429283438e-06, "loss": 0.0555, "step": 1530 }, { "epoch": 1.36, "learning_rate": 4.8798464305867596e-06, "loss": 0.0527, "step": 1531 }, { "epoch": 1.36, "learning_rate": 4.867473065229332e-06, "loss": 0.0518, "step": 1532 }, { "epoch": 1.36, "learning_rate": 4.855110358907689e-06, "loss": 0.0529, "step": 1533 }, { "epoch": 1.36, "learning_rate": 4.842758337296225e-06, "loss": 0.0542, "step": 1534 }, { "epoch": 1.37, "learning_rate": 4.830417026047148e-06, "loss": 0.0549, "step": 1535 }, { "epoch": 1.37, "learning_rate": 4.818086450790423e-06, "loss": 0.0531, "step": 1536 }, { "epoch": 1.37, "learning_rate": 4.805766637133711e-06, "loss": 0.0558, "step": 1537 }, { "epoch": 1.37, "learning_rate": 4.793457610662334e-06, "loss": 0.0534, "step": 1538 }, { "epoch": 1.37, "learning_rate": 4.781159396939209e-06, "loss": 0.0488, "step": 1539 }, { "epoch": 1.37, "learning_rate": 4.768872021504795e-06, "loss": 0.0528, "step": 1540 }, { "epoch": 1.37, "learning_rate": 4.7565955098770425e-06, "loss": 0.0485, "step": 1541 }, { "epoch": 1.37, "learning_rate": 4.744329887551343e-06, "loss": 0.0596, "step": 1542 }, { "epoch": 1.37, "learning_rate": 4.732075180000473e-06, "loss": 0.0511, "step": 1543 }, { "epoch": 1.37, "learning_rate": 4.7198314126745424e-06, "loss": 0.0602, "step": 1544 }, { "epoch": 1.37, "learning_rate": 4.707598611000934e-06, "loss": 0.0584, "step": 1545 }, { "epoch": 1.38, "learning_rate": 4.695376800384266e-06, "loss": 0.0473, "step": 1546 }, { "epoch": 1.38, "learning_rate": 4.683166006206326e-06, "loss": 0.0504, "step": 1547 }, { "epoch": 1.38, "learning_rate": 4.670966253826027e-06, "loss": 0.0498, "step": 1548 }, { "epoch": 1.38, "learning_rate": 4.658777568579347e-06, "loss": 0.0533, "step": 1549 }, { "epoch": 1.38, "learning_rate": 4.6465999757792815e-06, "loss": 0.054, "step": 1550 }, { "epoch": 1.38, "learning_rate": 4.634433500715794e-06, "loss": 0.0552, "step": 1551 }, { "epoch": 1.38, "learning_rate": 4.6222781686557485e-06, "loss": 0.0479, "step": 1552 }, { "epoch": 1.38, "learning_rate": 4.610134004842876e-06, "loss": 0.0493, "step": 1553 }, { "epoch": 1.38, "learning_rate": 4.598001034497712e-06, "loss": 0.0565, "step": 1554 }, { "epoch": 1.38, "learning_rate": 4.585879282817547e-06, "loss": 0.0515, "step": 1555 }, { "epoch": 1.38, "learning_rate": 4.573768774976371e-06, "loss": 0.0478, "step": 1556 }, { "epoch": 1.39, "learning_rate": 4.561669536124823e-06, "loss": 0.0561, "step": 1557 }, { "epoch": 1.39, "learning_rate": 4.549581591390142e-06, "loss": 0.0569, "step": 1558 }, { "epoch": 1.39, "learning_rate": 4.53750496587611e-06, "loss": 0.049, "step": 1559 }, { "epoch": 1.39, "learning_rate": 4.5254396846629975e-06, "loss": 0.0481, "step": 1560 }, { "epoch": 1.39, "learning_rate": 4.51338577280752e-06, "loss": 0.0522, "step": 1561 }, { "epoch": 1.39, "learning_rate": 4.5013432553427835e-06, "loss": 0.0508, "step": 1562 }, { "epoch": 1.39, "learning_rate": 4.489312157278227e-06, "loss": 0.0545, "step": 1563 }, { "epoch": 1.39, "learning_rate": 4.477292503599574e-06, "loss": 0.0499, "step": 1564 }, { "epoch": 1.39, "learning_rate": 4.4652843192687845e-06, "loss": 0.051, "step": 1565 }, { "epoch": 1.39, "learning_rate": 4.453287629223994e-06, "loss": 0.0571, "step": 1566 }, { "epoch": 1.39, "learning_rate": 4.441302458379475e-06, "loss": 0.0578, "step": 1567 }, { "epoch": 1.4, "learning_rate": 4.429328831625565e-06, "loss": 0.0573, "step": 1568 }, { "epoch": 1.4, "learning_rate": 4.417366773828638e-06, "loss": 0.0524, "step": 1569 }, { "epoch": 1.4, "learning_rate": 4.4054163098310375e-06, "loss": 0.058, "step": 1570 }, { "epoch": 1.4, "learning_rate": 4.393477464451032e-06, "loss": 0.054, "step": 1571 }, { "epoch": 1.4, "learning_rate": 4.381550262482759e-06, "loss": 0.0527, "step": 1572 }, { "epoch": 1.4, "learning_rate": 4.369634728696175e-06, "loss": 0.0549, "step": 1573 }, { "epoch": 1.4, "learning_rate": 4.357730887837005e-06, "loss": 0.0604, "step": 1574 }, { "epoch": 1.4, "learning_rate": 4.345838764626694e-06, "loss": 0.0505, "step": 1575 }, { "epoch": 1.4, "learning_rate": 4.333958383762345e-06, "loss": 0.0475, "step": 1576 }, { "epoch": 1.4, "learning_rate": 4.322089769916678e-06, "loss": 0.0497, "step": 1577 }, { "epoch": 1.4, "learning_rate": 4.310232947737979e-06, "loss": 0.0508, "step": 1578 }, { "epoch": 1.4, "learning_rate": 4.298387941850043e-06, "loss": 0.0544, "step": 1579 }, { "epoch": 1.41, "learning_rate": 4.286554776852125e-06, "loss": 0.0564, "step": 1580 }, { "epoch": 1.41, "learning_rate": 4.274733477318892e-06, "loss": 0.0481, "step": 1581 }, { "epoch": 1.41, "learning_rate": 4.262924067800364e-06, "loss": 0.0451, "step": 1582 }, { "epoch": 1.41, "learning_rate": 4.251126572821876e-06, "loss": 0.0559, "step": 1583 }, { "epoch": 1.41, "learning_rate": 4.239341016884008e-06, "loss": 0.0501, "step": 1584 }, { "epoch": 1.41, "learning_rate": 4.2275674244625575e-06, "loss": 0.0545, "step": 1585 }, { "epoch": 1.41, "learning_rate": 4.215805820008468e-06, "loss": 0.0505, "step": 1586 }, { "epoch": 1.41, "learning_rate": 4.204056227947792e-06, "loss": 0.0594, "step": 1587 }, { "epoch": 1.41, "learning_rate": 4.192318672681631e-06, "loss": 0.0566, "step": 1588 }, { "epoch": 1.41, "learning_rate": 4.180593178586094e-06, "loss": 0.0488, "step": 1589 }, { "epoch": 1.41, "learning_rate": 4.168879770012237e-06, "loss": 0.0512, "step": 1590 }, { "epoch": 1.42, "learning_rate": 4.157178471286025e-06, "loss": 0.0544, "step": 1591 }, { "epoch": 1.42, "learning_rate": 4.1454893067082605e-06, "loss": 0.0587, "step": 1592 }, { "epoch": 1.42, "learning_rate": 4.133812300554555e-06, "loss": 0.0492, "step": 1593 }, { "epoch": 1.42, "learning_rate": 4.12214747707527e-06, "loss": 0.0472, "step": 1594 }, { "epoch": 1.42, "learning_rate": 4.110494860495465e-06, "loss": 0.0497, "step": 1595 }, { "epoch": 1.42, "learning_rate": 4.098854475014849e-06, "loss": 0.0547, "step": 1596 }, { "epoch": 1.42, "learning_rate": 4.08722634480773e-06, "loss": 0.0495, "step": 1597 }, { "epoch": 1.42, "learning_rate": 4.0756104940229645e-06, "loss": 0.0583, "step": 1598 }, { "epoch": 1.42, "learning_rate": 4.0640069467839095e-06, "loss": 0.0551, "step": 1599 }, { "epoch": 1.42, "learning_rate": 4.0524157271883635e-06, "loss": 0.0516, "step": 1600 }, { "epoch": 1.42, "learning_rate": 4.04083685930853e-06, "loss": 0.0582, "step": 1601 }, { "epoch": 1.43, "learning_rate": 4.0292703671909605e-06, "loss": 0.0527, "step": 1602 }, { "epoch": 1.43, "learning_rate": 4.017716274856503e-06, "loss": 0.0491, "step": 1603 }, { "epoch": 1.43, "learning_rate": 4.006174606300255e-06, "loss": 0.0553, "step": 1604 }, { "epoch": 1.43, "learning_rate": 3.994645385491513e-06, "loss": 0.049, "step": 1605 }, { "epoch": 1.43, "learning_rate": 3.983128636373723e-06, "loss": 0.047, "step": 1606 }, { "epoch": 1.43, "learning_rate": 3.971624382864432e-06, "loss": 0.06, "step": 1607 }, { "epoch": 1.43, "learning_rate": 3.960132648855226e-06, "loss": 0.0521, "step": 1608 }, { "epoch": 1.43, "learning_rate": 3.948653458211704e-06, "loss": 0.0547, "step": 1609 }, { "epoch": 1.43, "learning_rate": 3.93718683477341e-06, "loss": 0.0475, "step": 1610 }, { "epoch": 1.43, "learning_rate": 3.9257328023537884e-06, "loss": 0.0536, "step": 1611 }, { "epoch": 1.43, "learning_rate": 3.914291384740139e-06, "loss": 0.0442, "step": 1612 }, { "epoch": 1.44, "learning_rate": 3.902862605693557e-06, "loss": 0.0526, "step": 1613 }, { "epoch": 1.44, "learning_rate": 3.891446488948894e-06, "loss": 0.0527, "step": 1614 }, { "epoch": 1.44, "learning_rate": 3.880043058214712e-06, "loss": 0.05, "step": 1615 }, { "epoch": 1.44, "learning_rate": 3.868652337173211e-06, "loss": 0.0561, "step": 1616 }, { "epoch": 1.44, "learning_rate": 3.857274349480208e-06, "loss": 0.0565, "step": 1617 }, { "epoch": 1.44, "learning_rate": 3.845909118765073e-06, "loss": 0.0456, "step": 1618 }, { "epoch": 1.44, "learning_rate": 3.834556668630684e-06, "loss": 0.0534, "step": 1619 }, { "epoch": 1.44, "learning_rate": 3.823217022653376e-06, "loss": 0.0602, "step": 1620 }, { "epoch": 1.44, "learning_rate": 3.8118902043828897e-06, "loss": 0.0456, "step": 1621 }, { "epoch": 1.44, "learning_rate": 3.800576237342335e-06, "loss": 0.0615, "step": 1622 }, { "epoch": 1.44, "learning_rate": 3.7892751450281162e-06, "loss": 0.0515, "step": 1623 }, { "epoch": 1.44, "learning_rate": 3.7779869509099166e-06, "loss": 0.0531, "step": 1624 }, { "epoch": 1.45, "learning_rate": 3.7667116784306236e-06, "loss": 0.0514, "step": 1625 }, { "epoch": 1.45, "learning_rate": 3.755449351006294e-06, "loss": 0.0518, "step": 1626 }, { "epoch": 1.45, "learning_rate": 3.7441999920260984e-06, "loss": 0.0564, "step": 1627 }, { "epoch": 1.45, "learning_rate": 3.732963624852275e-06, "loss": 0.0501, "step": 1628 }, { "epoch": 1.45, "learning_rate": 3.7217402728200823e-06, "loss": 0.0462, "step": 1629 }, { "epoch": 1.45, "learning_rate": 3.710529959237753e-06, "loss": 0.0523, "step": 1630 }, { "epoch": 1.45, "learning_rate": 3.699332707386429e-06, "loss": 0.0543, "step": 1631 }, { "epoch": 1.45, "learning_rate": 3.688148540520141e-06, "loss": 0.0553, "step": 1632 }, { "epoch": 1.45, "learning_rate": 3.6769774818657376e-06, "loss": 0.0498, "step": 1633 }, { "epoch": 1.45, "learning_rate": 3.665819554622847e-06, "loss": 0.0559, "step": 1634 }, { "epoch": 1.45, "learning_rate": 3.6546747819638263e-06, "loss": 0.0526, "step": 1635 }, { "epoch": 1.46, "learning_rate": 3.6435431870337123e-06, "loss": 0.0516, "step": 1636 }, { "epoch": 1.46, "learning_rate": 3.6324247929501765e-06, "loss": 0.0564, "step": 1637 }, { "epoch": 1.46, "learning_rate": 3.6213196228034796e-06, "loss": 0.0499, "step": 1638 }, { "epoch": 1.46, "learning_rate": 3.6102276996564056e-06, "loss": 0.0485, "step": 1639 }, { "epoch": 1.46, "learning_rate": 3.5991490465442413e-06, "loss": 0.0482, "step": 1640 }, { "epoch": 1.46, "learning_rate": 3.58808368647471e-06, "loss": 0.0521, "step": 1641 }, { "epoch": 1.46, "learning_rate": 3.5770316424279283e-06, "loss": 0.0557, "step": 1642 }, { "epoch": 1.46, "learning_rate": 3.5659929373563586e-06, "loss": 0.053, "step": 1643 }, { "epoch": 1.46, "learning_rate": 3.554967594184762e-06, "loss": 0.053, "step": 1644 }, { "epoch": 1.46, "learning_rate": 3.54395563581015e-06, "loss": 0.0546, "step": 1645 }, { "epoch": 1.46, "learning_rate": 3.5329570851017405e-06, "loss": 0.0483, "step": 1646 }, { "epoch": 1.47, "learning_rate": 3.5219719649008956e-06, "loss": 0.0549, "step": 1647 }, { "epoch": 1.47, "learning_rate": 3.511000298021098e-06, "loss": 0.0448, "step": 1648 }, { "epoch": 1.47, "learning_rate": 3.500042107247884e-06, "loss": 0.0534, "step": 1649 }, { "epoch": 1.47, "learning_rate": 3.489097415338808e-06, "loss": 0.055, "step": 1650 }, { "epoch": 1.47, "learning_rate": 3.4781662450233856e-06, "loss": 0.0463, "step": 1651 }, { "epoch": 1.47, "learning_rate": 3.4672486190030543e-06, "loss": 0.0547, "step": 1652 }, { "epoch": 1.47, "learning_rate": 3.4563445599511225e-06, "loss": 0.0562, "step": 1653 }, { "epoch": 1.47, "learning_rate": 3.4454540905127277e-06, "loss": 0.0521, "step": 1654 }, { "epoch": 1.47, "learning_rate": 3.434577233304772e-06, "loss": 0.0476, "step": 1655 }, { "epoch": 1.47, "learning_rate": 3.4237140109159015e-06, "loss": 0.0576, "step": 1656 }, { "epoch": 1.47, "learning_rate": 3.4128644459064418e-06, "loss": 0.0478, "step": 1657 }, { "epoch": 1.48, "learning_rate": 3.402028560808357e-06, "loss": 0.0517, "step": 1658 }, { "epoch": 1.48, "learning_rate": 3.3912063781251892e-06, "loss": 0.0519, "step": 1659 }, { "epoch": 1.48, "learning_rate": 3.380397920332045e-06, "loss": 0.0459, "step": 1660 }, { "epoch": 1.48, "learning_rate": 3.3696032098755106e-06, "loss": 0.0501, "step": 1661 }, { "epoch": 1.48, "learning_rate": 3.358822269173634e-06, "loss": 0.049, "step": 1662 }, { "epoch": 1.48, "learning_rate": 3.348055120615854e-06, "loss": 0.0486, "step": 1663 }, { "epoch": 1.48, "learning_rate": 3.3373017865629742e-06, "loss": 0.056, "step": 1664 }, { "epoch": 1.48, "learning_rate": 3.3265622893471107e-06, "loss": 0.0539, "step": 1665 }, { "epoch": 1.48, "learning_rate": 3.3158366512716424e-06, "loss": 0.0514, "step": 1666 }, { "epoch": 1.48, "learning_rate": 3.3051248946111557e-06, "loss": 0.0517, "step": 1667 }, { "epoch": 1.48, "learning_rate": 3.2944270416114256e-06, "loss": 0.0527, "step": 1668 }, { "epoch": 1.48, "learning_rate": 3.2837431144893427e-06, "loss": 0.0519, "step": 1669 }, { "epoch": 1.49, "learning_rate": 3.2730731354328827e-06, "loss": 0.0501, "step": 1670 }, { "epoch": 1.49, "learning_rate": 3.2624171266010406e-06, "loss": 0.0571, "step": 1671 }, { "epoch": 1.49, "learning_rate": 3.251775110123814e-06, "loss": 0.0551, "step": 1672 }, { "epoch": 1.49, "learning_rate": 3.241147108102135e-06, "loss": 0.0609, "step": 1673 }, { "epoch": 1.49, "learning_rate": 3.2305331426078367e-06, "loss": 0.059, "step": 1674 }, { "epoch": 1.49, "learning_rate": 3.2199332356835855e-06, "loss": 0.0505, "step": 1675 }, { "epoch": 1.49, "learning_rate": 3.2093474093428733e-06, "loss": 0.0506, "step": 1676 }, { "epoch": 1.49, "learning_rate": 3.198775685569937e-06, "loss": 0.0508, "step": 1677 }, { "epoch": 1.49, "learning_rate": 3.1882180863197308e-06, "loss": 0.0466, "step": 1678 }, { "epoch": 1.49, "learning_rate": 3.1776746335178678e-06, "loss": 0.0531, "step": 1679 }, { "epoch": 1.49, "learning_rate": 3.1671453490605906e-06, "loss": 0.049, "step": 1680 }, { "epoch": 1.5, "learning_rate": 3.1566302548147155e-06, "loss": 0.0528, "step": 1681 }, { "epoch": 1.5, "learning_rate": 3.146129372617589e-06, "loss": 0.0543, "step": 1682 }, { "epoch": 1.5, "learning_rate": 3.135642724277036e-06, "loss": 0.0494, "step": 1683 }, { "epoch": 1.5, "learning_rate": 3.1251703315713333e-06, "loss": 0.0536, "step": 1684 }, { "epoch": 1.5, "learning_rate": 3.114712216249145e-06, "loss": 0.0507, "step": 1685 }, { "epoch": 1.5, "learning_rate": 3.1042684000294876e-06, "loss": 0.0472, "step": 1686 }, { "epoch": 1.5, "learning_rate": 3.0938389046016725e-06, "loss": 0.0463, "step": 1687 }, { "epoch": 1.5, "learning_rate": 3.0834237516252817e-06, "loss": 0.0616, "step": 1688 }, { "epoch": 1.5, "learning_rate": 3.0730229627301057e-06, "loss": 0.0586, "step": 1689 }, { "epoch": 1.5, "learning_rate": 3.06263655951611e-06, "loss": 0.0571, "step": 1690 }, { "epoch": 1.5, "learning_rate": 3.0522645635533678e-06, "loss": 0.0526, "step": 1691 }, { "epoch": 1.51, "learning_rate": 3.041906996382056e-06, "loss": 0.054, "step": 1692 }, { "epoch": 1.51, "learning_rate": 3.0315638795123726e-06, "loss": 0.05, "step": 1693 }, { "epoch": 1.51, "learning_rate": 3.021235234424502e-06, "loss": 0.0527, "step": 1694 }, { "epoch": 1.51, "learning_rate": 3.010921082568583e-06, "loss": 0.045, "step": 1695 }, { "epoch": 1.51, "learning_rate": 3.000621445364651e-06, "loss": 0.0565, "step": 1696 }, { "epoch": 1.51, "learning_rate": 2.9903363442026002e-06, "loss": 0.0576, "step": 1697 }, { "epoch": 1.51, "learning_rate": 2.980065800442137e-06, "loss": 0.0545, "step": 1698 }, { "epoch": 1.51, "learning_rate": 2.969809835412726e-06, "loss": 0.0564, "step": 1699 }, { "epoch": 1.51, "learning_rate": 2.959568470413572e-06, "loss": 0.049, "step": 1700 }, { "epoch": 1.51, "learning_rate": 2.9493417267135514e-06, "loss": 0.057, "step": 1701 }, { "epoch": 1.51, "learning_rate": 2.9391296255511683e-06, "loss": 0.0465, "step": 1702 }, { "epoch": 1.52, "learning_rate": 2.9289321881345257e-06, "loss": 0.0526, "step": 1703 }, { "epoch": 1.52, "learning_rate": 2.918749435641274e-06, "loss": 0.0559, "step": 1704 }, { "epoch": 1.52, "learning_rate": 2.9085813892185634e-06, "loss": 0.0588, "step": 1705 }, { "epoch": 1.52, "learning_rate": 2.898428069983007e-06, "loss": 0.055, "step": 1706 }, { "epoch": 1.52, "learning_rate": 2.8882894990206245e-06, "loss": 0.0515, "step": 1707 }, { "epoch": 1.52, "learning_rate": 2.878165697386812e-06, "loss": 0.0585, "step": 1708 }, { "epoch": 1.52, "learning_rate": 2.8680566861063042e-06, "loss": 0.0451, "step": 1709 }, { "epoch": 1.52, "learning_rate": 2.857962486173098e-06, "loss": 0.0566, "step": 1710 }, { "epoch": 1.52, "learning_rate": 2.8478831185504476e-06, "loss": 0.0514, "step": 1711 }, { "epoch": 1.52, "learning_rate": 2.8378186041707977e-06, "loss": 0.0522, "step": 1712 }, { "epoch": 1.52, "learning_rate": 2.8277689639357453e-06, "loss": 0.0516, "step": 1713 }, { "epoch": 1.52, "learning_rate": 2.817734218716005e-06, "loss": 0.0595, "step": 1714 }, { "epoch": 1.53, "learning_rate": 2.807714389351345e-06, "loss": 0.0509, "step": 1715 }, { "epoch": 1.53, "learning_rate": 2.7977094966505624e-06, "loss": 0.0539, "step": 1716 }, { "epoch": 1.53, "learning_rate": 2.7877195613914475e-06, "loss": 0.0523, "step": 1717 }, { "epoch": 1.53, "learning_rate": 2.777744604320706e-06, "loss": 0.0475, "step": 1718 }, { "epoch": 1.53, "learning_rate": 2.767784646153949e-06, "loss": 0.0551, "step": 1719 }, { "epoch": 1.53, "learning_rate": 2.7578397075756404e-06, "loss": 0.0523, "step": 1720 }, { "epoch": 1.53, "learning_rate": 2.7479098092390487e-06, "loss": 0.0515, "step": 1721 }, { "epoch": 1.53, "learning_rate": 2.7379949717662014e-06, "loss": 0.0527, "step": 1722 }, { "epoch": 1.53, "learning_rate": 2.7280952157478592e-06, "loss": 0.0556, "step": 1723 }, { "epoch": 1.53, "learning_rate": 2.7182105617434516e-06, "loss": 0.0573, "step": 1724 }, { "epoch": 1.53, "learning_rate": 2.7083410302810607e-06, "loss": 0.0531, "step": 1725 }, { "epoch": 1.54, "learning_rate": 2.698486641857343e-06, "loss": 0.0575, "step": 1726 }, { "epoch": 1.54, "learning_rate": 2.6886474169375185e-06, "loss": 0.0564, "step": 1727 }, { "epoch": 1.54, "learning_rate": 2.678823375955314e-06, "loss": 0.0494, "step": 1728 }, { "epoch": 1.54, "learning_rate": 2.669014539312924e-06, "loss": 0.047, "step": 1729 }, { "epoch": 1.54, "learning_rate": 2.659220927380961e-06, "loss": 0.0521, "step": 1730 }, { "epoch": 1.54, "learning_rate": 2.6494425604984266e-06, "loss": 0.0511, "step": 1731 }, { "epoch": 1.54, "learning_rate": 2.639679458972657e-06, "loss": 0.047, "step": 1732 }, { "epoch": 1.54, "learning_rate": 2.6299316430792955e-06, "loss": 0.0539, "step": 1733 }, { "epoch": 1.54, "learning_rate": 2.620199133062227e-06, "loss": 0.0492, "step": 1734 }, { "epoch": 1.54, "learning_rate": 2.6104819491335567e-06, "loss": 0.0446, "step": 1735 }, { "epoch": 1.54, "learning_rate": 2.600780111473563e-06, "loss": 0.0492, "step": 1736 }, { "epoch": 1.55, "learning_rate": 2.591093640230654e-06, "loss": 0.0551, "step": 1737 }, { "epoch": 1.55, "learning_rate": 2.581422555521316e-06, "loss": 0.055, "step": 1738 }, { "epoch": 1.55, "learning_rate": 2.571766877430092e-06, "loss": 0.0504, "step": 1739 }, { "epoch": 1.55, "learning_rate": 2.562126626009522e-06, "loss": 0.0507, "step": 1740 }, { "epoch": 1.55, "learning_rate": 2.552501821280122e-06, "loss": 0.0567, "step": 1741 }, { "epoch": 1.55, "learning_rate": 2.542892483230308e-06, "loss": 0.0493, "step": 1742 }, { "epoch": 1.55, "learning_rate": 2.5332986318163887e-06, "loss": 0.0527, "step": 1743 }, { "epoch": 1.55, "learning_rate": 2.52372028696251e-06, "loss": 0.0499, "step": 1744 }, { "epoch": 1.55, "learning_rate": 2.514157468560613e-06, "loss": 0.0581, "step": 1745 }, { "epoch": 1.55, "learning_rate": 2.5046101964703894e-06, "loss": 0.0546, "step": 1746 }, { "epoch": 1.55, "learning_rate": 2.4950784905192517e-06, "loss": 0.0627, "step": 1747 }, { "epoch": 1.56, "learning_rate": 2.485562370502279e-06, "loss": 0.0494, "step": 1748 }, { "epoch": 1.56, "learning_rate": 2.4760618561821947e-06, "loss": 0.0482, "step": 1749 }, { "epoch": 1.56, "learning_rate": 2.4665769672892946e-06, "loss": 0.0637, "step": 1750 }, { "epoch": 1.56, "learning_rate": 2.4571077235214368e-06, "loss": 0.06, "step": 1751 }, { "epoch": 1.56, "learning_rate": 2.447654144543986e-06, "loss": 0.0471, "step": 1752 }, { "epoch": 1.56, "learning_rate": 2.4382162499897743e-06, "loss": 0.0562, "step": 1753 }, { "epoch": 1.56, "learning_rate": 2.4287940594590564e-06, "loss": 0.0515, "step": 1754 }, { "epoch": 1.56, "learning_rate": 2.4193875925194798e-06, "loss": 0.0445, "step": 1755 }, { "epoch": 1.56, "learning_rate": 2.409996868706036e-06, "loss": 0.0496, "step": 1756 }, { "epoch": 1.56, "learning_rate": 2.40062190752102e-06, "loss": 0.0518, "step": 1757 }, { "epoch": 1.56, "learning_rate": 2.391262728433995e-06, "loss": 0.0506, "step": 1758 }, { "epoch": 1.56, "learning_rate": 2.381919350881745e-06, "loss": 0.0511, "step": 1759 }, { "epoch": 1.57, "learning_rate": 2.3725917942682397e-06, "loss": 0.0449, "step": 1760 }, { "epoch": 1.57, "learning_rate": 2.363280077964594e-06, "loss": 0.052, "step": 1761 }, { "epoch": 1.57, "learning_rate": 2.35398422130902e-06, "loss": 0.0469, "step": 1762 }, { "epoch": 1.57, "learning_rate": 2.3447042436068013e-06, "loss": 0.055, "step": 1763 }, { "epoch": 1.57, "learning_rate": 2.3354401641302395e-06, "loss": 0.0485, "step": 1764 }, { "epoch": 1.57, "learning_rate": 2.32619200211862e-06, "loss": 0.0541, "step": 1765 }, { "epoch": 1.57, "learning_rate": 2.3169597767781736e-06, "loss": 0.0414, "step": 1766 }, { "epoch": 1.57, "learning_rate": 2.3077435072820343e-06, "loss": 0.0619, "step": 1767 }, { "epoch": 1.57, "learning_rate": 2.2985432127701945e-06, "loss": 0.0481, "step": 1768 }, { "epoch": 1.57, "learning_rate": 2.289358912349481e-06, "loss": 0.0506, "step": 1769 }, { "epoch": 1.57, "learning_rate": 2.2801906250934904e-06, "loss": 0.0532, "step": 1770 }, { "epoch": 1.58, "learning_rate": 2.2710383700425744e-06, "loss": 0.054, "step": 1771 }, { "epoch": 1.58, "learning_rate": 2.2619021662037855e-06, "loss": 0.0511, "step": 1772 }, { "epoch": 1.58, "learning_rate": 2.2527820325508445e-06, "loss": 0.0449, "step": 1773 }, { "epoch": 1.58, "learning_rate": 2.2436779880240943e-06, "loss": 0.0511, "step": 1774 }, { "epoch": 1.58, "learning_rate": 2.23459005153047e-06, "loss": 0.0461, "step": 1775 }, { "epoch": 1.58, "learning_rate": 2.225518241943446e-06, "loss": 0.0435, "step": 1776 }, { "epoch": 1.58, "learning_rate": 2.216462578103017e-06, "loss": 0.0493, "step": 1777 }, { "epoch": 1.58, "learning_rate": 2.2074230788156325e-06, "loss": 0.0532, "step": 1778 }, { "epoch": 1.58, "learning_rate": 2.198399762854181e-06, "loss": 0.0435, "step": 1779 }, { "epoch": 1.58, "learning_rate": 2.18939264895794e-06, "loss": 0.0531, "step": 1780 }, { "epoch": 1.58, "learning_rate": 2.1804017558325407e-06, "loss": 0.0528, "step": 1781 }, { "epoch": 1.59, "learning_rate": 2.171427102149927e-06, "loss": 0.0528, "step": 1782 }, { "epoch": 1.59, "learning_rate": 2.162468706548314e-06, "loss": 0.0558, "step": 1783 }, { "epoch": 1.59, "learning_rate": 2.1535265876321574e-06, "loss": 0.0517, "step": 1784 }, { "epoch": 1.59, "learning_rate": 2.144600763972111e-06, "loss": 0.0505, "step": 1785 }, { "epoch": 1.59, "learning_rate": 2.135691254104977e-06, "loss": 0.0524, "step": 1786 }, { "epoch": 1.59, "learning_rate": 2.126798076533689e-06, "loss": 0.0449, "step": 1787 }, { "epoch": 1.59, "learning_rate": 2.1179212497272582e-06, "loss": 0.0535, "step": 1788 }, { "epoch": 1.59, "learning_rate": 2.1090607921207394e-06, "loss": 0.0438, "step": 1789 }, { "epoch": 1.59, "learning_rate": 2.1002167221151915e-06, "loss": 0.0491, "step": 1790 }, { "epoch": 1.59, "learning_rate": 2.091389058077642e-06, "loss": 0.0542, "step": 1791 }, { "epoch": 1.59, "learning_rate": 2.0825778183410485e-06, "loss": 0.0486, "step": 1792 }, { "epoch": 1.6, "learning_rate": 2.073783021204251e-06, "loss": 0.0535, "step": 1793 }, { "epoch": 1.6, "learning_rate": 2.0650046849319516e-06, "loss": 0.0536, "step": 1794 }, { "epoch": 1.6, "learning_rate": 2.056242827754663e-06, "loss": 0.0468, "step": 1795 }, { "epoch": 1.6, "learning_rate": 2.0474974678686764e-06, "loss": 0.0511, "step": 1796 }, { "epoch": 1.6, "learning_rate": 2.038768623436019e-06, "loss": 0.0518, "step": 1797 }, { "epoch": 1.6, "learning_rate": 2.030056312584424e-06, "loss": 0.0546, "step": 1798 }, { "epoch": 1.6, "learning_rate": 2.0213605534072833e-06, "loss": 0.0524, "step": 1799 }, { "epoch": 1.6, "learning_rate": 2.012681363963621e-06, "loss": 0.0515, "step": 1800 }, { "epoch": 1.6, "learning_rate": 2.0040187622780406e-06, "loss": 0.0529, "step": 1801 }, { "epoch": 1.6, "learning_rate": 1.9953727663407043e-06, "loss": 0.0448, "step": 1802 }, { "epoch": 1.6, "learning_rate": 1.9867433941072857e-06, "loss": 0.0495, "step": 1803 }, { "epoch": 1.6, "learning_rate": 1.9781306634989373e-06, "loss": 0.0538, "step": 1804 }, { "epoch": 1.61, "learning_rate": 1.9695345924022467e-06, "loss": 0.0579, "step": 1805 }, { "epoch": 1.61, "learning_rate": 1.9609551986692067e-06, "loss": 0.0494, "step": 1806 }, { "epoch": 1.61, "learning_rate": 1.952392500117175e-06, "loss": 0.0528, "step": 1807 }, { "epoch": 1.61, "learning_rate": 1.9438465145288377e-06, "loss": 0.0567, "step": 1808 }, { "epoch": 1.61, "learning_rate": 1.9353172596521675e-06, "loss": 0.0517, "step": 1809 }, { "epoch": 1.61, "learning_rate": 1.9268047532003962e-06, "loss": 0.0476, "step": 1810 }, { "epoch": 1.61, "learning_rate": 1.9183090128519733e-06, "loss": 0.0563, "step": 1811 }, { "epoch": 1.61, "learning_rate": 1.9098300562505266e-06, "loss": 0.0484, "step": 1812 }, { "epoch": 1.61, "learning_rate": 1.9013679010048292e-06, "loss": 0.0563, "step": 1813 }, { "epoch": 1.61, "learning_rate": 1.8929225646887617e-06, "loss": 0.0519, "step": 1814 }, { "epoch": 1.61, "learning_rate": 1.884494064841277e-06, "loss": 0.0527, "step": 1815 }, { "epoch": 1.62, "learning_rate": 1.8760824189663618e-06, "loss": 0.0497, "step": 1816 }, { "epoch": 1.62, "learning_rate": 1.8676876445329972e-06, "loss": 0.047, "step": 1817 }, { "epoch": 1.62, "learning_rate": 1.8593097589751318e-06, "loss": 0.0579, "step": 1818 }, { "epoch": 1.62, "learning_rate": 1.8509487796916392e-06, "loss": 0.0549, "step": 1819 }, { "epoch": 1.62, "learning_rate": 1.8426047240462807e-06, "loss": 0.0527, "step": 1820 }, { "epoch": 1.62, "learning_rate": 1.8342776093676717e-06, "loss": 0.0518, "step": 1821 }, { "epoch": 1.62, "learning_rate": 1.8259674529492476e-06, "loss": 0.0534, "step": 1822 }, { "epoch": 1.62, "learning_rate": 1.8176742720492213e-06, "loss": 0.0476, "step": 1823 }, { "epoch": 1.62, "learning_rate": 1.809398083890559e-06, "loss": 0.0502, "step": 1824 }, { "epoch": 1.62, "learning_rate": 1.8011389056609241e-06, "loss": 0.0497, "step": 1825 }, { "epoch": 1.62, "learning_rate": 1.7928967545126674e-06, "loss": 0.062, "step": 1826 }, { "epoch": 1.63, "learning_rate": 1.7846716475627712e-06, "loss": 0.0504, "step": 1827 }, { "epoch": 1.63, "learning_rate": 1.7764636018928249e-06, "loss": 0.0483, "step": 1828 }, { "epoch": 1.63, "learning_rate": 1.7682726345489842e-06, "loss": 0.05, "step": 1829 }, { "epoch": 1.63, "learning_rate": 1.7600987625419353e-06, "loss": 0.05, "step": 1830 }, { "epoch": 1.63, "learning_rate": 1.7519420028468648e-06, "loss": 0.049, "step": 1831 }, { "epoch": 1.63, "learning_rate": 1.7438023724034215e-06, "loss": 0.0494, "step": 1832 }, { "epoch": 1.63, "learning_rate": 1.7356798881156734e-06, "loss": 0.0484, "step": 1833 }, { "epoch": 1.63, "learning_rate": 1.7275745668520883e-06, "loss": 0.0521, "step": 1834 }, { "epoch": 1.63, "learning_rate": 1.7194864254454868e-06, "loss": 0.052, "step": 1835 }, { "epoch": 1.63, "learning_rate": 1.7114154806930138e-06, "loss": 0.0535, "step": 1836 }, { "epoch": 1.63, "learning_rate": 1.7033617493560983e-06, "loss": 0.0513, "step": 1837 }, { "epoch": 1.64, "learning_rate": 1.6953252481604198e-06, "loss": 0.0467, "step": 1838 }, { "epoch": 1.64, "learning_rate": 1.687305993795879e-06, "loss": 0.052, "step": 1839 }, { "epoch": 1.64, "learning_rate": 1.6793040029165596e-06, "loss": 0.0504, "step": 1840 }, { "epoch": 1.64, "learning_rate": 1.671319292140683e-06, "loss": 0.0522, "step": 1841 }, { "epoch": 1.64, "learning_rate": 1.6633518780505964e-06, "loss": 0.0546, "step": 1842 }, { "epoch": 1.64, "learning_rate": 1.655401777192719e-06, "loss": 0.0547, "step": 1843 }, { "epoch": 1.64, "learning_rate": 1.6474690060775178e-06, "loss": 0.0534, "step": 1844 }, { "epoch": 1.64, "learning_rate": 1.6395535811794683e-06, "loss": 0.0522, "step": 1845 }, { "epoch": 1.64, "learning_rate": 1.631655518937022e-06, "loss": 0.0457, "step": 1846 }, { "epoch": 1.64, "learning_rate": 1.623774835752574e-06, "loss": 0.0556, "step": 1847 }, { "epoch": 1.64, "learning_rate": 1.6159115479924259e-06, "loss": 0.0532, "step": 1848 }, { "epoch": 1.65, "learning_rate": 1.6080656719867504e-06, "loss": 0.0462, "step": 1849 }, { "epoch": 1.65, "learning_rate": 1.600237224029565e-06, "loss": 0.0512, "step": 1850 }, { "epoch": 1.65, "learning_rate": 1.592426220378691e-06, "loss": 0.0536, "step": 1851 }, { "epoch": 1.65, "learning_rate": 1.584632677255723e-06, "loss": 0.0576, "step": 1852 }, { "epoch": 1.65, "learning_rate": 1.5768566108459916e-06, "loss": 0.0506, "step": 1853 }, { "epoch": 1.65, "learning_rate": 1.5690980372985354e-06, "loss": 0.0441, "step": 1854 }, { "epoch": 1.65, "learning_rate": 1.5613569727260648e-06, "loss": 0.0446, "step": 1855 }, { "epoch": 1.65, "learning_rate": 1.5536334332049274e-06, "loss": 0.0506, "step": 1856 }, { "epoch": 1.65, "learning_rate": 1.5459274347750708e-06, "loss": 0.0526, "step": 1857 }, { "epoch": 1.65, "learning_rate": 1.5382389934400199e-06, "loss": 0.0565, "step": 1858 }, { "epoch": 1.65, "learning_rate": 1.530568125166837e-06, "loss": 0.0532, "step": 1859 }, { "epoch": 1.65, "learning_rate": 1.5229148458860865e-06, "loss": 0.0524, "step": 1860 }, { "epoch": 1.66, "learning_rate": 1.515279171491808e-06, "loss": 0.0584, "step": 1861 }, { "epoch": 1.66, "learning_rate": 1.507661117841477e-06, "loss": 0.0521, "step": 1862 }, { "epoch": 1.66, "learning_rate": 1.5000607007559797e-06, "loss": 0.0457, "step": 1863 }, { "epoch": 1.66, "learning_rate": 1.4924779360195662e-06, "loss": 0.051, "step": 1864 }, { "epoch": 1.66, "learning_rate": 1.484912839379835e-06, "loss": 0.0499, "step": 1865 }, { "epoch": 1.66, "learning_rate": 1.47736542654769e-06, "loss": 0.0512, "step": 1866 }, { "epoch": 1.66, "learning_rate": 1.4698357131973095e-06, "loss": 0.0529, "step": 1867 }, { "epoch": 1.66, "learning_rate": 1.462323714966114e-06, "loss": 0.0575, "step": 1868 }, { "epoch": 1.66, "learning_rate": 1.4548294474547354e-06, "loss": 0.0574, "step": 1869 }, { "epoch": 1.66, "learning_rate": 1.4473529262269814e-06, "loss": 0.0473, "step": 1870 }, { "epoch": 1.66, "learning_rate": 1.4398941668098077e-06, "loss": 0.0464, "step": 1871 }, { "epoch": 1.67, "learning_rate": 1.4324531846932766e-06, "loss": 0.0532, "step": 1872 }, { "epoch": 1.67, "learning_rate": 1.4250299953305368e-06, "loss": 0.0569, "step": 1873 }, { "epoch": 1.67, "learning_rate": 1.417624614137786e-06, "loss": 0.0504, "step": 1874 }, { "epoch": 1.67, "learning_rate": 1.4102370564942346e-06, "loss": 0.0427, "step": 1875 }, { "epoch": 1.67, "learning_rate": 1.4028673377420821e-06, "loss": 0.0484, "step": 1876 }, { "epoch": 1.67, "learning_rate": 1.3955154731864772e-06, "loss": 0.0513, "step": 1877 }, { "epoch": 1.67, "learning_rate": 1.3881814780954916e-06, "loss": 0.0497, "step": 1878 }, { "epoch": 1.67, "learning_rate": 1.3808653677000895e-06, "loss": 0.0472, "step": 1879 }, { "epoch": 1.67, "learning_rate": 1.3735671571940835e-06, "loss": 0.0483, "step": 1880 }, { "epoch": 1.67, "learning_rate": 1.3662868617341207e-06, "loss": 0.0502, "step": 1881 }, { "epoch": 1.67, "learning_rate": 1.3590244964396403e-06, "loss": 0.0602, "step": 1882 }, { "epoch": 1.68, "learning_rate": 1.3517800763928457e-06, "loss": 0.0578, "step": 1883 }, { "epoch": 1.68, "learning_rate": 1.3445536166386708e-06, "loss": 0.0509, "step": 1884 }, { "epoch": 1.68, "learning_rate": 1.337345132184752e-06, "loss": 0.0526, "step": 1885 }, { "epoch": 1.68, "learning_rate": 1.3301546380013942e-06, "loss": 0.0501, "step": 1886 }, { "epoch": 1.68, "learning_rate": 1.3229821490215422e-06, "loss": 0.0515, "step": 1887 }, { "epoch": 1.68, "learning_rate": 1.3158276801407432e-06, "loss": 0.0541, "step": 1888 }, { "epoch": 1.68, "learning_rate": 1.3086912462171264e-06, "loss": 0.0509, "step": 1889 }, { "epoch": 1.68, "learning_rate": 1.3015728620713653e-06, "loss": 0.0518, "step": 1890 }, { "epoch": 1.68, "learning_rate": 1.2944725424866511e-06, "loss": 0.051, "step": 1891 }, { "epoch": 1.68, "learning_rate": 1.2873903022086487e-06, "loss": 0.0565, "step": 1892 }, { "epoch": 1.68, "learning_rate": 1.2803261559454905e-06, "loss": 0.0444, "step": 1893 }, { "epoch": 1.69, "learning_rate": 1.2732801183677246e-06, "loss": 0.0491, "step": 1894 }, { "epoch": 1.69, "learning_rate": 1.2662522041082924e-06, "loss": 0.0563, "step": 1895 }, { "epoch": 1.69, "learning_rate": 1.2592424277624948e-06, "loss": 0.0459, "step": 1896 }, { "epoch": 1.69, "learning_rate": 1.2522508038879698e-06, "loss": 0.0539, "step": 1897 }, { "epoch": 1.69, "learning_rate": 1.2452773470046543e-06, "loss": 0.0507, "step": 1898 }, { "epoch": 1.69, "learning_rate": 1.2383220715947596e-06, "loss": 0.049, "step": 1899 }, { "epoch": 1.69, "learning_rate": 1.2313849921027277e-06, "loss": 0.0469, "step": 1900 }, { "epoch": 1.69, "learning_rate": 1.2244661229352284e-06, "loss": 0.0516, "step": 1901 }, { "epoch": 1.69, "learning_rate": 1.2175654784611024e-06, "loss": 0.0531, "step": 1902 }, { "epoch": 1.69, "learning_rate": 1.2106830730113462e-06, "loss": 0.0447, "step": 1903 }, { "epoch": 1.69, "learning_rate": 1.2038189208790718e-06, "loss": 0.0534, "step": 1904 }, { "epoch": 1.69, "learning_rate": 1.1969730363194908e-06, "loss": 0.0541, "step": 1905 }, { "epoch": 1.7, "learning_rate": 1.1901454335498752e-06, "loss": 0.0505, "step": 1906 }, { "epoch": 1.7, "learning_rate": 1.1833361267495292e-06, "loss": 0.0491, "step": 1907 }, { "epoch": 1.7, "learning_rate": 1.1765451300597574e-06, "loss": 0.0616, "step": 1908 }, { "epoch": 1.7, "learning_rate": 1.1697724575838464e-06, "loss": 0.0471, "step": 1909 }, { "epoch": 1.7, "learning_rate": 1.163018123387023e-06, "loss": 0.0602, "step": 1910 }, { "epoch": 1.7, "learning_rate": 1.156282141496431e-06, "loss": 0.0501, "step": 1911 }, { "epoch": 1.7, "learning_rate": 1.1495645259010969e-06, "loss": 0.0449, "step": 1912 }, { "epoch": 1.7, "learning_rate": 1.14286529055191e-06, "loss": 0.0553, "step": 1913 }, { "epoch": 1.7, "learning_rate": 1.136184449361586e-06, "loss": 0.0486, "step": 1914 }, { "epoch": 1.7, "learning_rate": 1.1295220162046427e-06, "loss": 0.0514, "step": 1915 }, { "epoch": 1.7, "learning_rate": 1.1228780049173616e-06, "loss": 0.0519, "step": 1916 }, { "epoch": 1.71, "learning_rate": 1.116252429297775e-06, "loss": 0.05, "step": 1917 }, { "epoch": 1.71, "learning_rate": 1.1096453031056265e-06, "loss": 0.052, "step": 1918 }, { "epoch": 1.71, "learning_rate": 1.1030566400623422e-06, "loss": 0.055, "step": 1919 }, { "epoch": 1.71, "learning_rate": 1.0964864538510022e-06, "loss": 0.0513, "step": 1920 }, { "epoch": 1.71, "learning_rate": 1.0899347581163222e-06, "loss": 0.0464, "step": 1921 }, { "epoch": 1.71, "learning_rate": 1.0834015664646114e-06, "loss": 0.0527, "step": 1922 }, { "epoch": 1.71, "learning_rate": 1.0768868924637555e-06, "loss": 0.0483, "step": 1923 }, { "epoch": 1.71, "learning_rate": 1.0703907496431743e-06, "loss": 0.0471, "step": 1924 }, { "epoch": 1.71, "learning_rate": 1.063913151493814e-06, "loss": 0.0519, "step": 1925 }, { "epoch": 1.71, "learning_rate": 1.0574541114681046e-06, "loss": 0.05, "step": 1926 }, { "epoch": 1.71, "learning_rate": 1.051013642979929e-06, "loss": 0.0595, "step": 1927 }, { "epoch": 1.72, "learning_rate": 1.0445917594046073e-06, "loss": 0.0468, "step": 1928 }, { "epoch": 1.72, "learning_rate": 1.0381884740788628e-06, "loss": 0.044, "step": 1929 }, { "epoch": 1.72, "learning_rate": 1.0318038003007924e-06, "loss": 0.0463, "step": 1930 }, { "epoch": 1.72, "learning_rate": 1.0254377513298463e-06, "loss": 0.0473, "step": 1931 }, { "epoch": 1.72, "learning_rate": 1.0190903403867847e-06, "loss": 0.0512, "step": 1932 }, { "epoch": 1.72, "learning_rate": 1.012761580653674e-06, "loss": 0.0529, "step": 1933 }, { "epoch": 1.72, "learning_rate": 1.0064514852738406e-06, "loss": 0.054, "step": 1934 }, { "epoch": 1.72, "learning_rate": 1.0001600673518463e-06, "loss": 0.0513, "step": 1935 }, { "epoch": 1.72, "learning_rate": 9.938873399534688e-07, "loss": 0.049, "step": 1936 }, { "epoch": 1.72, "learning_rate": 9.876333161056672e-07, "loss": 0.0512, "step": 1937 }, { "epoch": 1.72, "learning_rate": 9.813980087965625e-07, "loss": 0.0582, "step": 1938 }, { "epoch": 1.73, "learning_rate": 9.751814309754003e-07, "loss": 0.053, "step": 1939 }, { "epoch": 1.73, "learning_rate": 9.689835955525307e-07, "loss": 0.0529, "step": 1940 }, { "epoch": 1.73, "learning_rate": 9.628045153993837e-07, "loss": 0.0453, "step": 1941 }, { "epoch": 1.73, "learning_rate": 9.56644203348438e-07, "loss": 0.0558, "step": 1942 }, { "epoch": 1.73, "learning_rate": 9.505026721931898e-07, "loss": 0.0494, "step": 1943 }, { "epoch": 1.73, "learning_rate": 9.443799346881388e-07, "loss": 0.0516, "step": 1944 }, { "epoch": 1.73, "learning_rate": 9.382760035487538e-07, "loss": 0.0614, "step": 1945 }, { "epoch": 1.73, "learning_rate": 9.321908914514421e-07, "loss": 0.0562, "step": 1946 }, { "epoch": 1.73, "learning_rate": 9.261246110335376e-07, "loss": 0.0461, "step": 1947 }, { "epoch": 1.73, "learning_rate": 9.200771748932513e-07, "loss": 0.0502, "step": 1948 }, { "epoch": 1.73, "learning_rate": 9.140485955896739e-07, "loss": 0.0543, "step": 1949 }, { "epoch": 1.73, "learning_rate": 9.080388856427291e-07, "loss": 0.0477, "step": 1950 }, { "epoch": 1.74, "learning_rate": 9.020480575331481e-07, "loss": 0.0486, "step": 1951 }, { "epoch": 1.74, "learning_rate": 8.960761237024573e-07, "loss": 0.0461, "step": 1952 }, { "epoch": 1.74, "learning_rate": 8.901230965529383e-07, "loss": 0.0529, "step": 1953 }, { "epoch": 1.74, "learning_rate": 8.841889884476118e-07, "loss": 0.0521, "step": 1954 }, { "epoch": 1.74, "learning_rate": 8.782738117102085e-07, "loss": 0.0437, "step": 1955 }, { "epoch": 1.74, "learning_rate": 8.723775786251354e-07, "loss": 0.0515, "step": 1956 }, { "epoch": 1.74, "learning_rate": 8.665003014374706e-07, "loss": 0.0456, "step": 1957 }, { "epoch": 1.74, "learning_rate": 8.606419923529175e-07, "loss": 0.054, "step": 1958 }, { "epoch": 1.74, "learning_rate": 8.548026635377849e-07, "loss": 0.0506, "step": 1959 }, { "epoch": 1.74, "learning_rate": 8.489823271189712e-07, "loss": 0.0548, "step": 1960 }, { "epoch": 1.74, "learning_rate": 8.431809951839264e-07, "loss": 0.0436, "step": 1961 }, { "epoch": 1.75, "learning_rate": 8.373986797806377e-07, "loss": 0.0512, "step": 1962 }, { "epoch": 1.75, "learning_rate": 8.316353929175935e-07, "loss": 0.0503, "step": 1963 }, { "epoch": 1.75, "learning_rate": 8.258911465637675e-07, "loss": 0.057, "step": 1964 }, { "epoch": 1.75, "learning_rate": 8.20165952648595e-07, "loss": 0.0386, "step": 1965 }, { "epoch": 1.75, "learning_rate": 8.144598230619383e-07, "loss": 0.0472, "step": 1966 }, { "epoch": 1.75, "learning_rate": 8.087727696540681e-07, "loss": 0.0544, "step": 1967 }, { "epoch": 1.75, "learning_rate": 8.031048042356393e-07, "loss": 0.0483, "step": 1968 }, { "epoch": 1.75, "learning_rate": 7.974559385776659e-07, "loss": 0.052, "step": 1969 }, { "epoch": 1.75, "learning_rate": 7.918261844114994e-07, "loss": 0.06, "step": 1970 }, { "epoch": 1.75, "learning_rate": 7.862155534287941e-07, "loss": 0.0545, "step": 1971 }, { "epoch": 1.75, "learning_rate": 7.806240572814927e-07, "loss": 0.0437, "step": 1972 }, { "epoch": 1.76, "learning_rate": 7.750517075818064e-07, "loss": 0.0487, "step": 1973 }, { "epoch": 1.76, "learning_rate": 7.694985159021762e-07, "loss": 0.0506, "step": 1974 }, { "epoch": 1.76, "learning_rate": 7.639644937752566e-07, "loss": 0.0518, "step": 1975 }, { "epoch": 1.76, "learning_rate": 7.584496526938933e-07, "loss": 0.0538, "step": 1976 }, { "epoch": 1.76, "learning_rate": 7.529540041110983e-07, "loss": 0.0519, "step": 1977 }, { "epoch": 1.76, "learning_rate": 7.474775594400252e-07, "loss": 0.0522, "step": 1978 }, { "epoch": 1.76, "learning_rate": 7.420203300539441e-07, "loss": 0.0587, "step": 1979 }, { "epoch": 1.76, "learning_rate": 7.365823272862183e-07, "loss": 0.0496, "step": 1980 }, { "epoch": 1.76, "learning_rate": 7.311635624302871e-07, "loss": 0.0541, "step": 1981 }, { "epoch": 1.76, "learning_rate": 7.257640467396365e-07, "loss": 0.0494, "step": 1982 }, { "epoch": 1.76, "learning_rate": 7.203837914277689e-07, "loss": 0.049, "step": 1983 }, { "epoch": 1.77, "learning_rate": 7.150228076681954e-07, "loss": 0.0472, "step": 1984 }, { "epoch": 1.77, "learning_rate": 7.096811065944032e-07, "loss": 0.0543, "step": 1985 }, { "epoch": 1.77, "learning_rate": 7.04358699299832e-07, "loss": 0.0605, "step": 1986 }, { "epoch": 1.77, "learning_rate": 6.990555968378532e-07, "loss": 0.056, "step": 1987 }, { "epoch": 1.77, "learning_rate": 6.937718102217461e-07, "loss": 0.0551, "step": 1988 }, { "epoch": 1.77, "learning_rate": 6.885073504246798e-07, "loss": 0.0511, "step": 1989 }, { "epoch": 1.77, "learning_rate": 6.832622283796842e-07, "loss": 0.0497, "step": 1990 }, { "epoch": 1.77, "learning_rate": 6.780364549796237e-07, "loss": 0.0541, "step": 1991 }, { "epoch": 1.77, "learning_rate": 6.728300410771871e-07, "loss": 0.0542, "step": 1992 }, { "epoch": 1.77, "learning_rate": 6.676429974848564e-07, "loss": 0.0515, "step": 1993 }, { "epoch": 1.77, "learning_rate": 6.62475334974887e-07, "loss": 0.0518, "step": 1994 }, { "epoch": 1.77, "learning_rate": 6.573270642792784e-07, "loss": 0.0522, "step": 1995 }, { "epoch": 1.78, "learning_rate": 6.521981960897639e-07, "loss": 0.0544, "step": 1996 }, { "epoch": 1.78, "learning_rate": 6.470887410577853e-07, "loss": 0.0481, "step": 1997 }, { "epoch": 1.78, "learning_rate": 6.41998709794458e-07, "loss": 0.0484, "step": 1998 }, { "epoch": 1.78, "learning_rate": 6.369281128705673e-07, "loss": 0.0466, "step": 1999 }, { "epoch": 1.78, "learning_rate": 6.318769608165332e-07, "loss": 0.055, "step": 2000 }, { "epoch": 1.78, "learning_rate": 6.268452641223977e-07, "loss": 0.0532, "step": 2001 }, { "epoch": 1.78, "learning_rate": 6.218330332377953e-07, "loss": 0.0486, "step": 2002 }, { "epoch": 1.78, "learning_rate": 6.168402785719351e-07, "loss": 0.0522, "step": 2003 }, { "epoch": 1.78, "learning_rate": 6.118670104935765e-07, "loss": 0.0485, "step": 2004 }, { "epoch": 1.78, "learning_rate": 6.069132393310184e-07, "loss": 0.0537, "step": 2005 }, { "epoch": 1.78, "learning_rate": 6.019789753720595e-07, "loss": 0.0565, "step": 2006 }, { "epoch": 1.79, "learning_rate": 5.970642288639916e-07, "loss": 0.0473, "step": 2007 }, { "epoch": 1.79, "learning_rate": 5.921690100135713e-07, "loss": 0.0487, "step": 2008 }, { "epoch": 1.79, "learning_rate": 5.872933289870042e-07, "loss": 0.0547, "step": 2009 }, { "epoch": 1.79, "learning_rate": 5.824371959099174e-07, "loss": 0.0451, "step": 2010 }, { "epoch": 1.79, "learning_rate": 5.776006208673412e-07, "loss": 0.0499, "step": 2011 }, { "epoch": 1.79, "learning_rate": 5.727836139036902e-07, "loss": 0.0478, "step": 2012 }, { "epoch": 1.79, "learning_rate": 5.67986185022743e-07, "loss": 0.0576, "step": 2013 }, { "epoch": 1.79, "learning_rate": 5.632083441876123e-07, "loss": 0.0506, "step": 2014 }, { "epoch": 1.79, "learning_rate": 5.584501013207388e-07, "loss": 0.0451, "step": 2015 }, { "epoch": 1.79, "learning_rate": 5.537114663038579e-07, "loss": 0.0464, "step": 2016 }, { "epoch": 1.79, "learning_rate": 5.489924489779863e-07, "loss": 0.0516, "step": 2017 }, { "epoch": 1.8, "learning_rate": 5.442930591433992e-07, "loss": 0.0548, "step": 2018 }, { "epoch": 1.8, "learning_rate": 5.396133065596087e-07, "loss": 0.0518, "step": 2019 }, { "epoch": 1.8, "learning_rate": 5.34953200945344e-07, "loss": 0.0543, "step": 2020 }, { "epoch": 1.8, "learning_rate": 5.303127519785412e-07, "loss": 0.0488, "step": 2021 }, { "epoch": 1.8, "learning_rate": 5.256919692963003e-07, "loss": 0.0473, "step": 2022 }, { "epoch": 1.8, "learning_rate": 5.210908624948896e-07, "loss": 0.053, "step": 2023 }, { "epoch": 1.8, "learning_rate": 5.165094411297111e-07, "loss": 0.053, "step": 2024 }, { "epoch": 1.8, "learning_rate": 5.119477147152851e-07, "loss": 0.0505, "step": 2025 }, { "epoch": 1.8, "learning_rate": 5.074056927252335e-07, "loss": 0.053, "step": 2026 }, { "epoch": 1.8, "learning_rate": 5.028833845922509e-07, "loss": 0.0601, "step": 2027 }, { "epoch": 1.8, "learning_rate": 4.983807997080925e-07, "loss": 0.0469, "step": 2028 }, { "epoch": 1.81, "learning_rate": 4.938979474235595e-07, "loss": 0.0547, "step": 2029 }, { "epoch": 1.81, "learning_rate": 4.894348370484648e-07, "loss": 0.0435, "step": 2030 }, { "epoch": 1.81, "learning_rate": 4.849914778516262e-07, "loss": 0.0528, "step": 2031 }, { "epoch": 1.81, "learning_rate": 4.805678790608415e-07, "loss": 0.0472, "step": 2032 }, { "epoch": 1.81, "learning_rate": 4.76164049862875e-07, "loss": 0.0532, "step": 2033 }, { "epoch": 1.81, "learning_rate": 4.7177999940342554e-07, "loss": 0.0592, "step": 2034 }, { "epoch": 1.81, "learning_rate": 4.674157367871257e-07, "loss": 0.0553, "step": 2035 }, { "epoch": 1.81, "learning_rate": 4.630712710775054e-07, "loss": 0.0498, "step": 2036 }, { "epoch": 1.81, "learning_rate": 4.587466112969907e-07, "loss": 0.057, "step": 2037 }, { "epoch": 1.81, "learning_rate": 4.544417664268652e-07, "loss": 0.0581, "step": 2038 }, { "epoch": 1.81, "learning_rate": 4.501567454072675e-07, "loss": 0.0477, "step": 2039 }, { "epoch": 1.81, "learning_rate": 4.458915571371647e-07, "loss": 0.0574, "step": 2040 }, { "epoch": 1.82, "learning_rate": 4.416462104743402e-07, "loss": 0.0519, "step": 2041 }, { "epoch": 1.82, "learning_rate": 4.3742071423536256e-07, "loss": 0.0545, "step": 2042 }, { "epoch": 1.82, "learning_rate": 4.332150771955845e-07, "loss": 0.0485, "step": 2043 }, { "epoch": 1.82, "learning_rate": 4.2902930808910946e-07, "loss": 0.0541, "step": 2044 }, { "epoch": 1.82, "learning_rate": 4.248634156087872e-07, "loss": 0.0535, "step": 2045 }, { "epoch": 1.82, "learning_rate": 4.2071740840618045e-07, "loss": 0.0541, "step": 2046 }, { "epoch": 1.82, "learning_rate": 4.165912950915585e-07, "loss": 0.0531, "step": 2047 }, { "epoch": 1.82, "learning_rate": 4.124850842338779e-07, "loss": 0.0556, "step": 2048 }, { "epoch": 1.82, "learning_rate": 4.0839878436075955e-07, "loss": 0.0547, "step": 2049 }, { "epoch": 1.82, "learning_rate": 4.0433240395847284e-07, "loss": 0.0507, "step": 2050 }, { "epoch": 1.82, "learning_rate": 4.0028595147192374e-07, "loss": 0.0513, "step": 2051 }, { "epoch": 1.83, "learning_rate": 3.9625943530462787e-07, "loss": 0.0556, "step": 2052 }, { "epoch": 1.83, "learning_rate": 3.92252863818704e-07, "loss": 0.0584, "step": 2053 }, { "epoch": 1.83, "learning_rate": 3.8826624533484293e-07, "loss": 0.0517, "step": 2054 }, { "epoch": 1.83, "learning_rate": 3.8429958813230195e-07, "loss": 0.0569, "step": 2055 }, { "epoch": 1.83, "learning_rate": 3.803529004488848e-07, "loss": 0.0548, "step": 2056 }, { "epoch": 1.83, "learning_rate": 3.764261904809219e-07, "loss": 0.0428, "step": 2057 }, { "epoch": 1.83, "learning_rate": 3.725194663832521e-07, "loss": 0.0449, "step": 2058 }, { "epoch": 1.83, "learning_rate": 3.686327362692121e-07, "loss": 0.0441, "step": 2059 }, { "epoch": 1.83, "learning_rate": 3.64766008210613e-07, "loss": 0.0479, "step": 2060 }, { "epoch": 1.83, "learning_rate": 3.609192902377323e-07, "loss": 0.0559, "step": 2061 }, { "epoch": 1.83, "learning_rate": 3.570925903392819e-07, "loss": 0.0491, "step": 2062 }, { "epoch": 1.84, "learning_rate": 3.5328591646240695e-07, "loss": 0.0537, "step": 2063 }, { "epoch": 1.84, "learning_rate": 3.494992765126637e-07, "loss": 0.0566, "step": 2064 }, { "epoch": 1.84, "learning_rate": 3.457326783540027e-07, "loss": 0.0518, "step": 2065 }, { "epoch": 1.84, "learning_rate": 3.419861298087468e-07, "loss": 0.0511, "step": 2066 }, { "epoch": 1.84, "learning_rate": 3.382596386575876e-07, "loss": 0.0514, "step": 2067 }, { "epoch": 1.84, "learning_rate": 3.345532126395579e-07, "loss": 0.0516, "step": 2068 }, { "epoch": 1.84, "learning_rate": 3.3086685945202367e-07, "loss": 0.049, "step": 2069 }, { "epoch": 1.84, "learning_rate": 3.272005867506611e-07, "loss": 0.0526, "step": 2070 }, { "epoch": 1.84, "learning_rate": 3.2355440214944524e-07, "loss": 0.0552, "step": 2071 }, { "epoch": 1.84, "learning_rate": 3.1992831322063324e-07, "loss": 0.0546, "step": 2072 }, { "epoch": 1.84, "learning_rate": 3.163223274947491e-07, "loss": 0.0592, "step": 2073 }, { "epoch": 1.85, "learning_rate": 3.127364524605636e-07, "loss": 0.0541, "step": 2074 }, { "epoch": 1.85, "learning_rate": 3.0917069556508637e-07, "loss": 0.0538, "step": 2075 }, { "epoch": 1.85, "learning_rate": 3.05625064213545e-07, "loss": 0.0504, "step": 2076 }, { "epoch": 1.85, "learning_rate": 3.020995657693715e-07, "loss": 0.0506, "step": 2077 }, { "epoch": 1.85, "learning_rate": 2.985942075541848e-07, "loss": 0.0491, "step": 2078 }, { "epoch": 1.85, "learning_rate": 2.951089968477805e-07, "loss": 0.043, "step": 2079 }, { "epoch": 1.85, "learning_rate": 2.916439408881111e-07, "loss": 0.056, "step": 2080 }, { "epoch": 1.85, "learning_rate": 2.881990468712725e-07, "loss": 0.0518, "step": 2081 }, { "epoch": 1.85, "learning_rate": 2.847743219514876e-07, "loss": 0.054, "step": 2082 }, { "epoch": 1.85, "learning_rate": 2.813697732410947e-07, "loss": 0.0513, "step": 2083 }, { "epoch": 1.85, "learning_rate": 2.779854078105304e-07, "loss": 0.0513, "step": 2084 }, { "epoch": 1.85, "learning_rate": 2.7462123268831573e-07, "loss": 0.0445, "step": 2085 }, { "epoch": 1.86, "learning_rate": 2.7127725486104094e-07, "loss": 0.0436, "step": 2086 }, { "epoch": 1.86, "learning_rate": 2.6795348127335086e-07, "loss": 0.0484, "step": 2087 }, { "epoch": 1.86, "learning_rate": 2.646499188279328e-07, "loss": 0.0419, "step": 2088 }, { "epoch": 1.86, "learning_rate": 2.613665743854998e-07, "loss": 0.0522, "step": 2089 }, { "epoch": 1.86, "learning_rate": 2.5810345476477207e-07, "loss": 0.0498, "step": 2090 }, { "epoch": 1.86, "learning_rate": 2.548605667424753e-07, "loss": 0.0508, "step": 2091 }, { "epoch": 1.86, "learning_rate": 2.5163791705331343e-07, "loss": 0.047, "step": 2092 }, { "epoch": 1.86, "learning_rate": 2.48435512389964e-07, "loss": 0.0531, "step": 2093 }, { "epoch": 1.86, "learning_rate": 2.4525335940305704e-07, "loss": 0.0525, "step": 2094 }, { "epoch": 1.86, "learning_rate": 2.420914647011663e-07, "loss": 0.0453, "step": 2095 }, { "epoch": 1.86, "learning_rate": 2.3894983485079683e-07, "loss": 0.0506, "step": 2096 }, { "epoch": 1.87, "learning_rate": 2.3582847637636074e-07, "loss": 0.0477, "step": 2097 }, { "epoch": 1.87, "learning_rate": 2.3272739576017945e-07, "loss": 0.0545, "step": 2098 }, { "epoch": 1.87, "learning_rate": 2.296465994424568e-07, "loss": 0.0484, "step": 2099 }, { "epoch": 1.87, "learning_rate": 2.2658609382127384e-07, "loss": 0.0604, "step": 2100 }, { "epoch": 1.87, "learning_rate": 2.235458852525707e-07, "loss": 0.0556, "step": 2101 }, { "epoch": 1.87, "learning_rate": 2.2052598005013803e-07, "loss": 0.0496, "step": 2102 }, { "epoch": 1.87, "learning_rate": 2.1752638448559793e-07, "loss": 0.0495, "step": 2103 }, { "epoch": 1.87, "learning_rate": 2.1454710478839736e-07, "loss": 0.0481, "step": 2104 }, { "epoch": 1.87, "learning_rate": 2.1158814714578923e-07, "loss": 0.0523, "step": 2105 }, { "epoch": 1.87, "learning_rate": 2.086495177028236e-07, "loss": 0.0499, "step": 2106 }, { "epoch": 1.87, "learning_rate": 2.0573122256233423e-07, "loss": 0.0444, "step": 2107 }, { "epoch": 1.88, "learning_rate": 2.028332677849254e-07, "loss": 0.0508, "step": 2108 }, { "epoch": 1.88, "learning_rate": 1.9995565938895846e-07, "loss": 0.0498, "step": 2109 }, { "epoch": 1.88, "learning_rate": 1.9709840335053965e-07, "loss": 0.0523, "step": 2110 }, { "epoch": 1.88, "learning_rate": 1.9426150560351132e-07, "loss": 0.0491, "step": 2111 }, { "epoch": 1.88, "learning_rate": 1.914449720394329e-07, "loss": 0.0515, "step": 2112 }, { "epoch": 1.88, "learning_rate": 1.8864880850757327e-07, "loss": 0.0494, "step": 2113 }, { "epoch": 1.88, "learning_rate": 1.8587302081489734e-07, "loss": 0.0534, "step": 2114 }, { "epoch": 1.88, "learning_rate": 1.8311761472605715e-07, "loss": 0.0486, "step": 2115 }, { "epoch": 1.88, "learning_rate": 1.8038259596337316e-07, "loss": 0.0545, "step": 2116 }, { "epoch": 1.88, "learning_rate": 1.7766797020682848e-07, "loss": 0.0469, "step": 2117 }, { "epoch": 1.88, "learning_rate": 1.7497374309405346e-07, "loss": 0.0465, "step": 2118 }, { "epoch": 1.89, "learning_rate": 1.7229992022031682e-07, "loss": 0.0454, "step": 2119 }, { "epoch": 1.89, "learning_rate": 1.6964650713851228e-07, "loss": 0.0541, "step": 2120 }, { "epoch": 1.89, "learning_rate": 1.6701350935914518e-07, "loss": 0.048, "step": 2121 }, { "epoch": 1.89, "learning_rate": 1.6440093235032484e-07, "loss": 0.0503, "step": 2122 }, { "epoch": 1.89, "learning_rate": 1.6180878153775114e-07, "loss": 0.0504, "step": 2123 }, { "epoch": 1.89, "learning_rate": 1.592370623047046e-07, "loss": 0.0578, "step": 2124 }, { "epoch": 1.89, "learning_rate": 1.5668577999203405e-07, "loss": 0.0493, "step": 2125 }, { "epoch": 1.89, "learning_rate": 1.5415493989814457e-07, "loss": 0.0498, "step": 2126 }, { "epoch": 1.89, "learning_rate": 1.5164454727898735e-07, "loss": 0.0554, "step": 2127 }, { "epoch": 1.89, "learning_rate": 1.49154607348051e-07, "loss": 0.0573, "step": 2128 }, { "epoch": 1.89, "learning_rate": 1.4668512527634682e-07, "loss": 0.0495, "step": 2129 }, { "epoch": 1.9, "learning_rate": 1.4423610619240026e-07, "loss": 0.0495, "step": 2130 }, { "epoch": 1.9, "learning_rate": 1.4180755518224175e-07, "loss": 0.0522, "step": 2131 }, { "epoch": 1.9, "learning_rate": 1.393994772893925e-07, "loss": 0.0487, "step": 2132 }, { "epoch": 1.9, "learning_rate": 1.3701187751485655e-07, "loss": 0.0529, "step": 2133 }, { "epoch": 1.9, "learning_rate": 1.3464476081711088e-07, "loss": 0.0564, "step": 2134 }, { "epoch": 1.9, "learning_rate": 1.3229813211209196e-07, "loss": 0.051, "step": 2135 }, { "epoch": 1.9, "learning_rate": 1.2997199627319047e-07, "loss": 0.0479, "step": 2136 }, { "epoch": 1.9, "learning_rate": 1.2766635813123317e-07, "loss": 0.0457, "step": 2137 }, { "epoch": 1.9, "learning_rate": 1.2538122247448325e-07, "loss": 0.0483, "step": 2138 }, { "epoch": 1.9, "learning_rate": 1.231165940486234e-07, "loss": 0.0559, "step": 2139 }, { "epoch": 1.9, "learning_rate": 1.2087247755674603e-07, "loss": 0.0417, "step": 2140 }, { "epoch": 1.9, "learning_rate": 1.1864887765934752e-07, "loss": 0.0515, "step": 2141 }, { "epoch": 1.91, "learning_rate": 1.1644579897431507e-07, "loss": 0.0464, "step": 2142 }, { "epoch": 1.91, "learning_rate": 1.1426324607691774e-07, "loss": 0.0503, "step": 2143 }, { "epoch": 1.91, "learning_rate": 1.1210122349979979e-07, "loss": 0.0528, "step": 2144 }, { "epoch": 1.91, "learning_rate": 1.0995973573296403e-07, "loss": 0.0578, "step": 2145 }, { "epoch": 1.91, "learning_rate": 1.0783878722377295e-07, "loss": 0.0541, "step": 2146 }, { "epoch": 1.91, "learning_rate": 1.057383823769298e-07, "loss": 0.0523, "step": 2147 }, { "epoch": 1.91, "learning_rate": 1.0365852555447642e-07, "loss": 0.0473, "step": 2148 }, { "epoch": 1.91, "learning_rate": 1.015992210757788e-07, "loss": 0.0481, "step": 2149 }, { "epoch": 1.91, "learning_rate": 9.95604732175215e-08, "loss": 0.0443, "step": 2150 }, { "epoch": 1.91, "learning_rate": 9.754228621369988e-08, "loss": 0.0528, "step": 2151 }, { "epoch": 1.91, "learning_rate": 9.554466425560793e-08, "loss": 0.0467, "step": 2152 }, { "epoch": 1.92, "learning_rate": 9.356761149182714e-08, "loss": 0.0551, "step": 2153 }, { "epoch": 1.92, "learning_rate": 9.161113202822868e-08, "loss": 0.0438, "step": 2154 }, { "epoch": 1.92, "learning_rate": 8.967522992795241e-08, "loss": 0.0445, "step": 2155 }, { "epoch": 1.92, "learning_rate": 8.775990921140565e-08, "loss": 0.0494, "step": 2156 }, { "epoch": 1.92, "learning_rate": 8.586517385625437e-08, "loss": 0.0494, "step": 2157 }, { "epoch": 1.92, "learning_rate": 8.39910277974132e-08, "loss": 0.0476, "step": 2158 }, { "epoch": 1.92, "learning_rate": 8.213747492703427e-08, "loss": 0.0501, "step": 2159 }, { "epoch": 1.92, "learning_rate": 8.030451909450842e-08, "loss": 0.0451, "step": 2160 }, { "epoch": 1.92, "learning_rate": 7.849216410644622e-08, "loss": 0.0455, "step": 2161 }, { "epoch": 1.92, "learning_rate": 7.670041372667803e-08, "loss": 0.0492, "step": 2162 }, { "epoch": 1.92, "learning_rate": 7.492927167624286e-08, "loss": 0.0558, "step": 2163 }, { "epoch": 1.93, "learning_rate": 7.317874163338068e-08, "loss": 0.0501, "step": 2164 }, { "epoch": 1.93, "learning_rate": 7.144882723352342e-08, "loss": 0.0473, "step": 2165 }, { "epoch": 1.93, "learning_rate": 6.973953206929507e-08, "loss": 0.0463, "step": 2166 }, { "epoch": 1.93, "learning_rate": 6.805085969049163e-08, "loss": 0.0568, "step": 2167 }, { "epoch": 1.93, "learning_rate": 6.638281360408339e-08, "loss": 0.0489, "step": 2168 }, { "epoch": 1.93, "learning_rate": 6.473539727420597e-08, "loss": 0.0526, "step": 2169 }, { "epoch": 1.93, "learning_rate": 6.31086141221493e-08, "loss": 0.0443, "step": 2170 }, { "epoch": 1.93, "learning_rate": 6.150246752635536e-08, "loss": 0.0624, "step": 2171 }, { "epoch": 1.93, "learning_rate": 5.991696082240817e-08, "loss": 0.0522, "step": 2172 }, { "epoch": 1.93, "learning_rate": 5.8352097303027155e-08, "loss": 0.0527, "step": 2173 }, { "epoch": 1.93, "learning_rate": 5.680788021806161e-08, "loss": 0.0502, "step": 2174 }, { "epoch": 1.94, "learning_rate": 5.5284312774481764e-08, "loss": 0.0609, "step": 2175 }, { "epoch": 1.94, "learning_rate": 5.3781398136374394e-08, "loss": 0.0504, "step": 2176 }, { "epoch": 1.94, "learning_rate": 5.229913942493503e-08, "loss": 0.0545, "step": 2177 }, { "epoch": 1.94, "learning_rate": 5.083753971846239e-08, "loss": 0.0501, "step": 2178 }, { "epoch": 1.94, "learning_rate": 4.939660205235064e-08, "loss": 0.0534, "step": 2179 }, { "epoch": 1.94, "learning_rate": 4.7976329419084924e-08, "loss": 0.0488, "step": 2180 }, { "epoch": 1.94, "learning_rate": 4.6576724768231386e-08, "loss": 0.0475, "step": 2181 }, { "epoch": 1.94, "learning_rate": 4.519779100643606e-08, "loss": 0.05, "step": 2182 }, { "epoch": 1.94, "learning_rate": 4.383953099741711e-08, "loss": 0.0528, "step": 2183 }, { "epoch": 1.94, "learning_rate": 4.2501947561955914e-08, "loss": 0.0566, "step": 2184 }, { "epoch": 1.94, "learning_rate": 4.118504347789487e-08, "loss": 0.0473, "step": 2185 }, { "epoch": 1.94, "learning_rate": 3.988882148012963e-08, "loss": 0.0517, "step": 2186 }, { "epoch": 1.95, "learning_rate": 3.8613284260605734e-08, "loss": 0.0432, "step": 2187 }, { "epoch": 1.95, "learning_rate": 3.735843446830867e-08, "loss": 0.061, "step": 2188 }, { "epoch": 1.95, "learning_rate": 3.612427470926383e-08, "loss": 0.0475, "step": 2189 }, { "epoch": 1.95, "learning_rate": 3.4910807546525426e-08, "loss": 0.0511, "step": 2190 }, { "epoch": 1.95, "learning_rate": 3.3718035500177607e-08, "loss": 0.0501, "step": 2191 }, { "epoch": 1.95, "learning_rate": 3.254596104732222e-08, "loss": 0.0525, "step": 2192 }, { "epoch": 1.95, "learning_rate": 3.139458662207995e-08, "loss": 0.0456, "step": 2193 }, { "epoch": 1.95, "learning_rate": 3.026391461557921e-08, "loss": 0.054, "step": 2194 }, { "epoch": 1.95, "learning_rate": 2.9153947375958337e-08, "loss": 0.0503, "step": 2195 }, { "epoch": 1.95, "learning_rate": 2.8064687208354534e-08, "loss": 0.0459, "step": 2196 }, { "epoch": 1.95, "learning_rate": 2.6996136374901616e-08, "loss": 0.0502, "step": 2197 }, { "epoch": 1.96, "learning_rate": 2.5948297094724463e-08, "loss": 0.0478, "step": 2198 }, { "epoch": 1.96, "learning_rate": 2.4921171543936805e-08, "loss": 0.0493, "step": 2199 }, { "epoch": 1.96, "learning_rate": 2.3914761855632353e-08, "loss": 0.0512, "step": 2200 }, { "epoch": 1.96, "learning_rate": 2.2929070119884767e-08, "loss": 0.0486, "step": 2201 }, { "epoch": 1.96, "learning_rate": 2.1964098383742138e-08, "loss": 0.0486, "step": 2202 }, { "epoch": 1.96, "learning_rate": 2.10198486512192e-08, "loss": 0.0559, "step": 2203 }, { "epoch": 1.96, "learning_rate": 2.0096322883298435e-08, "loss": 0.0543, "step": 2204 }, { "epoch": 1.96, "learning_rate": 1.919352299792343e-08, "loss": 0.0473, "step": 2205 }, { "epoch": 1.96, "learning_rate": 1.831145086999331e-08, "loss": 0.0489, "step": 2206 }, { "epoch": 1.96, "learning_rate": 1.7450108331362735e-08, "loss": 0.0522, "step": 2207 }, { "epoch": 1.96, "learning_rate": 1.6609497170834154e-08, "loss": 0.049, "step": 2208 }, { "epoch": 1.97, "learning_rate": 1.5789619134157775e-08, "loss": 0.0499, "step": 2209 }, { "epoch": 1.97, "learning_rate": 1.4990475924023805e-08, "loss": 0.0536, "step": 2210 }, { "epoch": 1.97, "learning_rate": 1.4212069200063571e-08, "loss": 0.0517, "step": 2211 }, { "epoch": 1.97, "learning_rate": 1.345440057884062e-08, "loss": 0.0563, "step": 2212 }, { "epoch": 1.97, "learning_rate": 1.2717471633852951e-08, "loss": 0.0499, "step": 2213 }, { "epoch": 1.97, "learning_rate": 1.200128389552857e-08, "loss": 0.0538, "step": 2214 }, { "epoch": 1.97, "learning_rate": 1.13058388512155e-08, "loss": 0.0436, "step": 2215 }, { "epoch": 1.97, "learning_rate": 1.063113794518955e-08, "loss": 0.0503, "step": 2216 }, { "epoch": 1.97, "learning_rate": 9.977182578643218e-09, "loss": 0.0508, "step": 2217 }, { "epoch": 1.97, "learning_rate": 9.343974109685684e-09, "loss": 0.0419, "step": 2218 }, { "epoch": 1.97, "learning_rate": 8.73151385334059e-09, "loss": 0.0489, "step": 2219 }, { "epoch": 1.98, "learning_rate": 8.139803081540499e-09, "loss": 0.0472, "step": 2220 }, { "epoch": 1.98, "learning_rate": 7.568843023130213e-09, "loss": 0.05, "step": 2221 }, { "epoch": 1.98, "learning_rate": 7.018634863856788e-09, "loss": 0.0509, "step": 2222 }, { "epoch": 1.98, "learning_rate": 6.489179746370644e-09, "loss": 0.0454, "step": 2223 }, { "epoch": 1.98, "learning_rate": 5.980478770224452e-09, "loss": 0.0547, "step": 2224 }, { "epoch": 1.98, "learning_rate": 5.492532991868693e-09, "loss": 0.0538, "step": 2225 }, { "epoch": 1.98, "learning_rate": 5.025343424651663e-09, "loss": 0.0555, "step": 2226 }, { "epoch": 1.98, "learning_rate": 4.5789110388139156e-09, "loss": 0.0542, "step": 2227 }, { "epoch": 1.98, "learning_rate": 4.153236761488266e-09, "loss": 0.0559, "step": 2228 }, { "epoch": 1.98, "learning_rate": 3.7483214767009e-09, "loss": 0.0508, "step": 2229 }, { "epoch": 1.98, "learning_rate": 3.364166025362492e-09, "loss": 0.053, "step": 2230 }, { "epoch": 1.98, "learning_rate": 3.000771205273756e-09, "loss": 0.0597, "step": 2231 }, { "epoch": 1.99, "learning_rate": 2.6581377711176747e-09, "loss": 0.0485, "step": 2232 }, { "epoch": 1.99, "learning_rate": 2.336266434463941e-09, "loss": 0.0518, "step": 2233 }, { "epoch": 1.99, "learning_rate": 2.0351578637611834e-09, "loss": 0.0482, "step": 2234 }, { "epoch": 1.99, "learning_rate": 1.7548126843425216e-09, "loss": 0.0469, "step": 2235 }, { "epoch": 1.99, "learning_rate": 1.4952314784144606e-09, "loss": 0.0507, "step": 2236 }, { "epoch": 1.99, "learning_rate": 1.2564147850679942e-09, "loss": 0.0574, "step": 2237 }, { "epoch": 1.99, "learning_rate": 1.0383631002686133e-09, "loss": 0.0536, "step": 2238 }, { "epoch": 1.99, "learning_rate": 8.41076876856306e-10, "loss": 0.0508, "step": 2239 }, { "epoch": 1.99, "learning_rate": 6.64556524547777e-10, "loss": 0.0481, "step": 2240 }, { "epoch": 1.99, "learning_rate": 5.088024099353384e-10, "loss": 0.054, "step": 2241 }, { "epoch": 1.99, "learning_rate": 3.738148564813582e-10, "loss": 0.0462, "step": 2242 }, { "epoch": 2.0, "learning_rate": 2.5959414452270126e-10, "loss": 0.0508, "step": 2243 }, { "epoch": 2.0, "learning_rate": 1.6614051127072929e-10, "loss": 0.053, "step": 2244 }, { "epoch": 2.0, "learning_rate": 9.345415080463937e-11, "loss": 0.0519, "step": 2245 }, { "epoch": 2.0, "learning_rate": 4.153521407590511e-11, "loss": 0.0487, "step": 2246 }, { "epoch": 2.0, "learning_rate": 1.038380891049684e-11, "loss": 0.0525, "step": 2247 }, { "epoch": 2.0, "learning_rate": 0.0, "loss": 0.0408, "step": 2248 }, { "epoch": 2.0, "step": 2248, "total_flos": 278665338814464.0, "train_loss": 0.07144167754149522, "train_runtime": 27330.9919, "train_samples_per_second": 21.045, "train_steps_per_second": 0.082 } ], "max_steps": 2248, "num_train_epochs": 2, "total_flos": 278665338814464.0, "trial_name": null, "trial_params": null }