{ "best_metric": null, "best_model_checkpoint": null, "epoch": 2.9994017150834273, "eval_steps": 500, "global_step": 2820, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.7699115044247788e-07, "loss": 0.7808, "step": 1 }, { "epoch": 0.0, "learning_rate": 3.5398230088495575e-07, "loss": 0.8643, "step": 2 }, { "epoch": 0.0, "learning_rate": 5.309734513274336e-07, "loss": 0.7932, "step": 3 }, { "epoch": 0.0, "learning_rate": 7.079646017699115e-07, "loss": 0.9994, "step": 4 }, { "epoch": 0.01, "learning_rate": 8.849557522123895e-07, "loss": 0.7348, "step": 5 }, { "epoch": 0.01, "learning_rate": 1.0619469026548673e-06, "loss": 0.7737, "step": 6 }, { "epoch": 0.01, "learning_rate": 1.2389380530973452e-06, "loss": 0.7865, "step": 7 }, { "epoch": 0.01, "learning_rate": 1.415929203539823e-06, "loss": 0.7209, "step": 8 }, { "epoch": 0.01, "learning_rate": 1.592920353982301e-06, "loss": 0.7944, "step": 9 }, { "epoch": 0.01, "learning_rate": 1.769911504424779e-06, "loss": 0.6758, "step": 10 }, { "epoch": 0.01, "learning_rate": 1.9469026548672567e-06, "loss": 0.7082, "step": 11 }, { "epoch": 0.01, "learning_rate": 2.1238938053097345e-06, "loss": 0.7481, "step": 12 }, { "epoch": 0.01, "learning_rate": 2.3008849557522127e-06, "loss": 0.6778, "step": 13 }, { "epoch": 0.01, "learning_rate": 2.4778761061946905e-06, "loss": 0.6822, "step": 14 }, { "epoch": 0.02, "learning_rate": 2.6548672566371687e-06, "loss": 0.6209, "step": 15 }, { "epoch": 0.02, "learning_rate": 2.831858407079646e-06, "loss": 0.7884, "step": 16 }, { "epoch": 0.02, "learning_rate": 3.0088495575221242e-06, "loss": 0.7034, "step": 17 }, { "epoch": 0.02, "learning_rate": 3.185840707964602e-06, "loss": 0.6485, "step": 18 }, { "epoch": 0.02, "learning_rate": 3.36283185840708e-06, "loss": 0.6636, "step": 19 }, { "epoch": 0.02, "learning_rate": 3.539823008849558e-06, "loss": 0.5788, "step": 20 }, { "epoch": 0.02, "learning_rate": 3.7168141592920357e-06, "loss": 0.6915, "step": 21 }, { "epoch": 0.02, "learning_rate": 3.8938053097345135e-06, "loss": 0.6731, "step": 22 }, { "epoch": 0.02, "learning_rate": 4.070796460176992e-06, "loss": 0.6312, "step": 23 }, { "epoch": 0.03, "learning_rate": 4.247787610619469e-06, "loss": 0.6335, "step": 24 }, { "epoch": 0.03, "learning_rate": 4.424778761061948e-06, "loss": 0.6479, "step": 25 }, { "epoch": 0.03, "learning_rate": 4.6017699115044254e-06, "loss": 0.9157, "step": 26 }, { "epoch": 0.03, "learning_rate": 4.778761061946903e-06, "loss": 0.6092, "step": 27 }, { "epoch": 0.03, "learning_rate": 4.955752212389381e-06, "loss": 0.6125, "step": 28 }, { "epoch": 0.03, "learning_rate": 5.132743362831859e-06, "loss": 0.58, "step": 29 }, { "epoch": 0.03, "learning_rate": 5.309734513274337e-06, "loss": 0.5975, "step": 30 }, { "epoch": 0.03, "learning_rate": 5.486725663716814e-06, "loss": 0.7494, "step": 31 }, { "epoch": 0.03, "learning_rate": 5.663716814159292e-06, "loss": 0.6441, "step": 32 }, { "epoch": 0.04, "learning_rate": 5.840707964601771e-06, "loss": 0.6515, "step": 33 }, { "epoch": 0.04, "learning_rate": 6.0176991150442484e-06, "loss": 0.6262, "step": 34 }, { "epoch": 0.04, "learning_rate": 6.194690265486726e-06, "loss": 0.6144, "step": 35 }, { "epoch": 0.04, "learning_rate": 6.371681415929204e-06, "loss": 0.6402, "step": 36 }, { "epoch": 0.04, "learning_rate": 6.548672566371682e-06, "loss": 0.5927, "step": 37 }, { "epoch": 0.04, "learning_rate": 6.72566371681416e-06, "loss": 0.5484, "step": 38 }, { "epoch": 0.04, "learning_rate": 6.902654867256637e-06, "loss": 0.6722, "step": 39 }, { "epoch": 0.04, "learning_rate": 7.079646017699116e-06, "loss": 0.6325, "step": 40 }, { "epoch": 0.04, "learning_rate": 7.256637168141594e-06, "loss": 0.624, "step": 41 }, { "epoch": 0.04, "learning_rate": 7.4336283185840714e-06, "loss": 0.6478, "step": 42 }, { "epoch": 0.05, "learning_rate": 7.610619469026549e-06, "loss": 0.629, "step": 43 }, { "epoch": 0.05, "learning_rate": 7.787610619469027e-06, "loss": 0.7436, "step": 44 }, { "epoch": 0.05, "learning_rate": 7.964601769911505e-06, "loss": 0.5842, "step": 45 }, { "epoch": 0.05, "learning_rate": 8.141592920353984e-06, "loss": 0.6283, "step": 46 }, { "epoch": 0.05, "learning_rate": 8.31858407079646e-06, "loss": 0.573, "step": 47 }, { "epoch": 0.05, "learning_rate": 8.495575221238938e-06, "loss": 0.6322, "step": 48 }, { "epoch": 0.05, "learning_rate": 8.672566371681418e-06, "loss": 0.7609, "step": 49 }, { "epoch": 0.05, "learning_rate": 8.849557522123895e-06, "loss": 0.6525, "step": 50 }, { "epoch": 0.05, "learning_rate": 9.026548672566371e-06, "loss": 0.5804, "step": 51 }, { "epoch": 0.06, "learning_rate": 9.203539823008851e-06, "loss": 0.6947, "step": 52 }, { "epoch": 0.06, "learning_rate": 9.380530973451329e-06, "loss": 0.6001, "step": 53 }, { "epoch": 0.06, "learning_rate": 9.557522123893806e-06, "loss": 0.5978, "step": 54 }, { "epoch": 0.06, "learning_rate": 9.734513274336284e-06, "loss": 0.5965, "step": 55 }, { "epoch": 0.06, "learning_rate": 9.911504424778762e-06, "loss": 0.6012, "step": 56 }, { "epoch": 0.06, "learning_rate": 1.008849557522124e-05, "loss": 0.5896, "step": 57 }, { "epoch": 0.06, "learning_rate": 1.0265486725663717e-05, "loss": 0.6001, "step": 58 }, { "epoch": 0.06, "learning_rate": 1.0442477876106197e-05, "loss": 0.587, "step": 59 }, { "epoch": 0.06, "learning_rate": 1.0619469026548675e-05, "loss": 0.5775, "step": 60 }, { "epoch": 0.06, "learning_rate": 1.079646017699115e-05, "loss": 0.6115, "step": 61 }, { "epoch": 0.07, "learning_rate": 1.0973451327433629e-05, "loss": 0.6015, "step": 62 }, { "epoch": 0.07, "learning_rate": 1.1150442477876106e-05, "loss": 0.6553, "step": 63 }, { "epoch": 0.07, "learning_rate": 1.1327433628318584e-05, "loss": 0.6123, "step": 64 }, { "epoch": 0.07, "learning_rate": 1.1504424778761064e-05, "loss": 0.5653, "step": 65 }, { "epoch": 0.07, "learning_rate": 1.1681415929203541e-05, "loss": 0.6356, "step": 66 }, { "epoch": 0.07, "learning_rate": 1.1858407079646019e-05, "loss": 0.6294, "step": 67 }, { "epoch": 0.07, "learning_rate": 1.2035398230088497e-05, "loss": 0.5604, "step": 68 }, { "epoch": 0.07, "learning_rate": 1.2212389380530973e-05, "loss": 0.5701, "step": 69 }, { "epoch": 0.07, "learning_rate": 1.2389380530973452e-05, "loss": 0.6225, "step": 70 }, { "epoch": 0.08, "learning_rate": 1.256637168141593e-05, "loss": 0.5912, "step": 71 }, { "epoch": 0.08, "learning_rate": 1.2743362831858408e-05, "loss": 0.5864, "step": 72 }, { "epoch": 0.08, "learning_rate": 1.2920353982300886e-05, "loss": 0.6176, "step": 73 }, { "epoch": 0.08, "learning_rate": 1.3097345132743363e-05, "loss": 0.5833, "step": 74 }, { "epoch": 0.08, "learning_rate": 1.3274336283185843e-05, "loss": 0.727, "step": 75 }, { "epoch": 0.08, "learning_rate": 1.345132743362832e-05, "loss": 0.6005, "step": 76 }, { "epoch": 0.08, "learning_rate": 1.3628318584070797e-05, "loss": 0.5827, "step": 77 }, { "epoch": 0.08, "learning_rate": 1.3805309734513275e-05, "loss": 0.4946, "step": 78 }, { "epoch": 0.08, "learning_rate": 1.3982300884955752e-05, "loss": 0.5567, "step": 79 }, { "epoch": 0.09, "learning_rate": 1.4159292035398232e-05, "loss": 0.6404, "step": 80 }, { "epoch": 0.09, "learning_rate": 1.433628318584071e-05, "loss": 0.5769, "step": 81 }, { "epoch": 0.09, "learning_rate": 1.4513274336283187e-05, "loss": 0.6472, "step": 82 }, { "epoch": 0.09, "learning_rate": 1.4690265486725665e-05, "loss": 0.6165, "step": 83 }, { "epoch": 0.09, "learning_rate": 1.4867256637168143e-05, "loss": 0.5793, "step": 84 }, { "epoch": 0.09, "learning_rate": 1.5044247787610619e-05, "loss": 0.5876, "step": 85 }, { "epoch": 0.09, "learning_rate": 1.5221238938053098e-05, "loss": 0.5734, "step": 86 }, { "epoch": 0.09, "learning_rate": 1.5398230088495576e-05, "loss": 0.5643, "step": 87 }, { "epoch": 0.09, "learning_rate": 1.5575221238938054e-05, "loss": 0.5734, "step": 88 }, { "epoch": 0.09, "learning_rate": 1.5752212389380532e-05, "loss": 0.5788, "step": 89 }, { "epoch": 0.1, "learning_rate": 1.592920353982301e-05, "loss": 0.594, "step": 90 }, { "epoch": 0.1, "learning_rate": 1.6106194690265487e-05, "loss": 0.5524, "step": 91 }, { "epoch": 0.1, "learning_rate": 1.628318584070797e-05, "loss": 0.8435, "step": 92 }, { "epoch": 0.1, "learning_rate": 1.6460176991150443e-05, "loss": 0.6331, "step": 93 }, { "epoch": 0.1, "learning_rate": 1.663716814159292e-05, "loss": 0.6384, "step": 94 }, { "epoch": 0.1, "learning_rate": 1.68141592920354e-05, "loss": 0.5448, "step": 95 }, { "epoch": 0.1, "learning_rate": 1.6991150442477876e-05, "loss": 0.6195, "step": 96 }, { "epoch": 0.1, "learning_rate": 1.7168141592920354e-05, "loss": 0.6686, "step": 97 }, { "epoch": 0.1, "learning_rate": 1.7345132743362835e-05, "loss": 0.5842, "step": 98 }, { "epoch": 0.11, "learning_rate": 1.7522123893805313e-05, "loss": 0.6878, "step": 99 }, { "epoch": 0.11, "learning_rate": 1.769911504424779e-05, "loss": 0.5482, "step": 100 }, { "epoch": 0.11, "learning_rate": 1.7876106194690265e-05, "loss": 0.5464, "step": 101 }, { "epoch": 0.11, "learning_rate": 1.8053097345132743e-05, "loss": 0.5854, "step": 102 }, { "epoch": 0.11, "learning_rate": 1.823008849557522e-05, "loss": 0.6363, "step": 103 }, { "epoch": 0.11, "learning_rate": 1.8407079646017702e-05, "loss": 0.619, "step": 104 }, { "epoch": 0.11, "learning_rate": 1.858407079646018e-05, "loss": 0.5756, "step": 105 }, { "epoch": 0.11, "learning_rate": 1.8761061946902657e-05, "loss": 0.5829, "step": 106 }, { "epoch": 0.11, "learning_rate": 1.8938053097345135e-05, "loss": 0.6005, "step": 107 }, { "epoch": 0.11, "learning_rate": 1.9115044247787613e-05, "loss": 0.6197, "step": 108 }, { "epoch": 0.12, "learning_rate": 1.929203539823009e-05, "loss": 0.5932, "step": 109 }, { "epoch": 0.12, "learning_rate": 1.946902654867257e-05, "loss": 0.5853, "step": 110 }, { "epoch": 0.12, "learning_rate": 1.9646017699115046e-05, "loss": 0.5469, "step": 111 }, { "epoch": 0.12, "learning_rate": 1.9823008849557524e-05, "loss": 0.6118, "step": 112 }, { "epoch": 0.12, "learning_rate": 2e-05, "loss": 0.558, "step": 113 }, { "epoch": 0.12, "learning_rate": 1.999999326568868e-05, "loss": 0.5921, "step": 114 }, { "epoch": 0.12, "learning_rate": 1.9999973062763794e-05, "loss": 0.5703, "step": 115 }, { "epoch": 0.12, "learning_rate": 1.999993939125255e-05, "loss": 0.6198, "step": 116 }, { "epoch": 0.12, "learning_rate": 1.99998922512003e-05, "loss": 0.593, "step": 117 }, { "epoch": 0.13, "learning_rate": 1.9999831642670527e-05, "loss": 0.5618, "step": 118 }, { "epoch": 0.13, "learning_rate": 1.9999757565744876e-05, "loss": 0.6126, "step": 119 }, { "epoch": 0.13, "learning_rate": 1.9999670020523113e-05, "loss": 0.6208, "step": 120 }, { "epoch": 0.13, "learning_rate": 1.9999569007123143e-05, "loss": 0.5536, "step": 121 }, { "epoch": 0.13, "learning_rate": 1.9999454525681025e-05, "loss": 0.5842, "step": 122 }, { "epoch": 0.13, "learning_rate": 1.999932657635095e-05, "loss": 0.5699, "step": 123 }, { "epoch": 0.13, "learning_rate": 1.999918515930524e-05, "loss": 0.5531, "step": 124 }, { "epoch": 0.13, "learning_rate": 1.9999030274734372e-05, "loss": 0.5479, "step": 125 }, { "epoch": 0.13, "learning_rate": 1.9998861922846952e-05, "loss": 0.5181, "step": 126 }, { "epoch": 0.14, "learning_rate": 1.9998680103869727e-05, "loss": 0.5729, "step": 127 }, { "epoch": 0.14, "learning_rate": 1.999848481804758e-05, "loss": 0.6215, "step": 128 }, { "epoch": 0.14, "learning_rate": 1.9998276065643538e-05, "loss": 0.5494, "step": 129 }, { "epoch": 0.14, "learning_rate": 1.999805384693876e-05, "loss": 0.5663, "step": 130 }, { "epoch": 0.14, "learning_rate": 1.999781816223254e-05, "loss": 0.5157, "step": 131 }, { "epoch": 0.14, "learning_rate": 1.9997569011842322e-05, "loss": 0.5382, "step": 132 }, { "epoch": 0.14, "learning_rate": 1.9997306396103667e-05, "loss": 0.5426, "step": 133 }, { "epoch": 0.14, "learning_rate": 1.999703031537029e-05, "loss": 0.5909, "step": 134 }, { "epoch": 0.14, "learning_rate": 1.999674077001403e-05, "loss": 0.5476, "step": 135 }, { "epoch": 0.14, "learning_rate": 1.9996437760424864e-05, "loss": 0.5108, "step": 136 }, { "epoch": 0.15, "learning_rate": 1.9996121287010904e-05, "loss": 0.642, "step": 137 }, { "epoch": 0.15, "learning_rate": 1.99957913501984e-05, "loss": 0.5847, "step": 138 }, { "epoch": 0.15, "learning_rate": 1.9995447950431726e-05, "loss": 0.5888, "step": 139 }, { "epoch": 0.15, "learning_rate": 1.9995091088173402e-05, "loss": 0.575, "step": 140 }, { "epoch": 0.15, "learning_rate": 1.9994720763904065e-05, "loss": 0.617, "step": 141 }, { "epoch": 0.15, "learning_rate": 1.999433697812249e-05, "loss": 0.5358, "step": 142 }, { "epoch": 0.15, "learning_rate": 1.9993939731345592e-05, "loss": 0.6511, "step": 143 }, { "epoch": 0.15, "learning_rate": 1.99935290241084e-05, "loss": 0.6212, "step": 144 }, { "epoch": 0.15, "learning_rate": 1.9993104856964084e-05, "loss": 0.6152, "step": 145 }, { "epoch": 0.16, "learning_rate": 1.999266723048394e-05, "loss": 0.6275, "step": 146 }, { "epoch": 0.16, "learning_rate": 1.9992216145257384e-05, "loss": 0.6541, "step": 147 }, { "epoch": 0.16, "learning_rate": 1.999175160189197e-05, "loss": 0.6064, "step": 148 }, { "epoch": 0.16, "learning_rate": 1.9991273601013375e-05, "loss": 0.6264, "step": 149 }, { "epoch": 0.16, "learning_rate": 1.9990782143265397e-05, "loss": 0.6104, "step": 150 }, { "epoch": 0.16, "learning_rate": 1.9990277229309963e-05, "loss": 0.6429, "step": 151 }, { "epoch": 0.16, "learning_rate": 1.9989758859827127e-05, "loss": 0.5782, "step": 152 }, { "epoch": 0.16, "learning_rate": 1.9989227035515057e-05, "loss": 0.5212, "step": 153 }, { "epoch": 0.16, "learning_rate": 1.9988681757090048e-05, "loss": 0.8335, "step": 154 }, { "epoch": 0.16, "learning_rate": 1.998812302528651e-05, "loss": 0.5317, "step": 155 }, { "epoch": 0.17, "learning_rate": 1.9987550840856988e-05, "loss": 0.6349, "step": 156 }, { "epoch": 0.17, "learning_rate": 1.998696520457213e-05, "loss": 0.5783, "step": 157 }, { "epoch": 0.17, "learning_rate": 1.9986366117220702e-05, "loss": 0.6168, "step": 158 }, { "epoch": 0.17, "learning_rate": 1.9985753579609605e-05, "loss": 0.5732, "step": 159 }, { "epoch": 0.17, "learning_rate": 1.998512759256383e-05, "loss": 0.6825, "step": 160 }, { "epoch": 0.17, "learning_rate": 1.9984488156926503e-05, "loss": 0.543, "step": 161 }, { "epoch": 0.17, "learning_rate": 1.998383527355885e-05, "loss": 0.6207, "step": 162 }, { "epoch": 0.17, "learning_rate": 1.9983168943340222e-05, "loss": 0.756, "step": 163 }, { "epoch": 0.17, "learning_rate": 1.998248916716807e-05, "loss": 0.6961, "step": 164 }, { "epoch": 0.18, "learning_rate": 1.998179594595796e-05, "loss": 0.5441, "step": 165 }, { "epoch": 0.18, "learning_rate": 1.9981089280643565e-05, "loss": 0.5703, "step": 166 }, { "epoch": 0.18, "learning_rate": 1.9980369172176663e-05, "loss": 0.5544, "step": 167 }, { "epoch": 0.18, "learning_rate": 1.9979635621527145e-05, "loss": 0.5722, "step": 168 }, { "epoch": 0.18, "learning_rate": 1.9978888629683005e-05, "loss": 0.6244, "step": 169 }, { "epoch": 0.18, "learning_rate": 1.997812819765033e-05, "loss": 0.5422, "step": 170 }, { "epoch": 0.18, "learning_rate": 1.9977354326453322e-05, "loss": 0.685, "step": 171 }, { "epoch": 0.18, "learning_rate": 1.997656701713428e-05, "loss": 0.6206, "step": 172 }, { "epoch": 0.18, "learning_rate": 1.99757662707536e-05, "loss": 0.7347, "step": 173 }, { "epoch": 0.19, "learning_rate": 1.9974952088389775e-05, "loss": 0.6214, "step": 174 }, { "epoch": 0.19, "learning_rate": 1.99741244711394e-05, "loss": 0.6097, "step": 175 }, { "epoch": 0.19, "learning_rate": 1.997328342011716e-05, "loss": 0.5521, "step": 176 }, { "epoch": 0.19, "learning_rate": 1.9972428936455834e-05, "loss": 0.6302, "step": 177 }, { "epoch": 0.19, "learning_rate": 1.9971561021306298e-05, "loss": 0.5898, "step": 178 }, { "epoch": 0.19, "learning_rate": 1.9970679675837507e-05, "loss": 0.6419, "step": 179 }, { "epoch": 0.19, "learning_rate": 1.9969784901236516e-05, "loss": 0.607, "step": 180 }, { "epoch": 0.19, "learning_rate": 1.996887669870846e-05, "loss": 0.4798, "step": 181 }, { "epoch": 0.19, "learning_rate": 1.996795506947657e-05, "loss": 0.492, "step": 182 }, { "epoch": 0.19, "learning_rate": 1.9967020014782146e-05, "loss": 0.624, "step": 183 }, { "epoch": 0.2, "learning_rate": 1.9966071535884582e-05, "loss": 0.6998, "step": 184 }, { "epoch": 0.2, "learning_rate": 1.9965109634061347e-05, "loss": 0.5572, "step": 185 }, { "epoch": 0.2, "learning_rate": 1.9964134310607992e-05, "loss": 0.6213, "step": 186 }, { "epoch": 0.2, "learning_rate": 1.9963145566838143e-05, "loss": 0.578, "step": 187 }, { "epoch": 0.2, "learning_rate": 1.99621434040835e-05, "loss": 0.5927, "step": 188 }, { "epoch": 0.2, "learning_rate": 1.9961127823693837e-05, "loss": 0.5975, "step": 189 }, { "epoch": 0.2, "learning_rate": 1.9960098827037003e-05, "loss": 0.5894, "step": 190 }, { "epoch": 0.2, "learning_rate": 1.9959056415498913e-05, "loss": 0.8204, "step": 191 }, { "epoch": 0.2, "learning_rate": 1.995800059048356e-05, "loss": 0.5493, "step": 192 }, { "epoch": 0.21, "learning_rate": 1.995693135341298e-05, "loss": 0.565, "step": 193 }, { "epoch": 0.21, "learning_rate": 1.99558487057273e-05, "loss": 0.5844, "step": 194 }, { "epoch": 0.21, "learning_rate": 1.9954752648884693e-05, "loss": 0.536, "step": 195 }, { "epoch": 0.21, "learning_rate": 1.99536431843614e-05, "loss": 0.6027, "step": 196 }, { "epoch": 0.21, "learning_rate": 1.9952520313651713e-05, "loss": 0.54, "step": 197 }, { "epoch": 0.21, "learning_rate": 1.9951384038267983e-05, "loss": 0.5783, "step": 198 }, { "epoch": 0.21, "learning_rate": 1.9950234359740623e-05, "loss": 0.5531, "step": 199 }, { "epoch": 0.21, "learning_rate": 1.994907127961808e-05, "loss": 0.5593, "step": 200 }, { "epoch": 0.21, "learning_rate": 1.9947894799466876e-05, "loss": 0.6141, "step": 201 }, { "epoch": 0.21, "learning_rate": 1.994670492087156e-05, "loss": 0.5435, "step": 202 }, { "epoch": 0.22, "learning_rate": 1.994550164543474e-05, "loss": 0.5868, "step": 203 }, { "epoch": 0.22, "learning_rate": 1.9944284974777053e-05, "loss": 0.5372, "step": 204 }, { "epoch": 0.22, "learning_rate": 1.9943054910537192e-05, "loss": 0.5889, "step": 205 }, { "epoch": 0.22, "learning_rate": 1.9941811454371888e-05, "loss": 0.5772, "step": 206 }, { "epoch": 0.22, "learning_rate": 1.9940554607955903e-05, "loss": 0.5353, "step": 207 }, { "epoch": 0.22, "learning_rate": 1.993928437298203e-05, "loss": 0.757, "step": 208 }, { "epoch": 0.22, "learning_rate": 1.993800075116111e-05, "loss": 0.6408, "step": 209 }, { "epoch": 0.22, "learning_rate": 1.9936703744222e-05, "loss": 0.5439, "step": 210 }, { "epoch": 0.22, "learning_rate": 1.993539335391159e-05, "loss": 0.5665, "step": 211 }, { "epoch": 0.23, "learning_rate": 1.9934069581994788e-05, "loss": 0.6081, "step": 212 }, { "epoch": 0.23, "learning_rate": 1.9932732430254543e-05, "loss": 0.5427, "step": 213 }, { "epoch": 0.23, "learning_rate": 1.9931381900491814e-05, "loss": 0.7853, "step": 214 }, { "epoch": 0.23, "learning_rate": 1.9930017994525575e-05, "loss": 0.5514, "step": 215 }, { "epoch": 0.23, "learning_rate": 1.9928640714192818e-05, "loss": 0.5694, "step": 216 }, { "epoch": 0.23, "learning_rate": 1.992725006134855e-05, "loss": 0.605, "step": 217 }, { "epoch": 0.23, "learning_rate": 1.9925846037865795e-05, "loss": 0.9187, "step": 218 }, { "epoch": 0.23, "learning_rate": 1.992442864563557e-05, "loss": 0.5502, "step": 219 }, { "epoch": 0.23, "learning_rate": 1.9922997886566913e-05, "loss": 0.5708, "step": 220 }, { "epoch": 0.24, "learning_rate": 1.992155376258686e-05, "loss": 0.5587, "step": 221 }, { "epoch": 0.24, "learning_rate": 1.9920096275640444e-05, "loss": 0.5351, "step": 222 }, { "epoch": 0.24, "learning_rate": 1.99186254276907e-05, "loss": 0.5726, "step": 223 }, { "epoch": 0.24, "learning_rate": 1.991714122071866e-05, "loss": 0.5739, "step": 224 }, { "epoch": 0.24, "learning_rate": 1.9915643656723344e-05, "loss": 0.5878, "step": 225 }, { "epoch": 0.24, "learning_rate": 1.9914132737721764e-05, "loss": 0.5652, "step": 226 }, { "epoch": 0.24, "learning_rate": 1.991260846574892e-05, "loss": 0.5843, "step": 227 }, { "epoch": 0.24, "learning_rate": 1.99110708428578e-05, "loss": 0.6123, "step": 228 }, { "epoch": 0.24, "learning_rate": 1.9909519871119368e-05, "loss": 0.5072, "step": 229 }, { "epoch": 0.24, "learning_rate": 1.9907955552622564e-05, "loss": 0.5509, "step": 230 }, { "epoch": 0.25, "learning_rate": 1.990637788947432e-05, "loss": 0.5438, "step": 231 }, { "epoch": 0.25, "learning_rate": 1.9904786883799518e-05, "loss": 0.613, "step": 232 }, { "epoch": 0.25, "learning_rate": 1.9903182537741035e-05, "loss": 0.538, "step": 233 }, { "epoch": 0.25, "learning_rate": 1.9901564853459702e-05, "loss": 0.769, "step": 234 }, { "epoch": 0.25, "learning_rate": 1.989993383313431e-05, "loss": 0.6034, "step": 235 }, { "epoch": 0.25, "learning_rate": 1.9898289478961623e-05, "loss": 0.5761, "step": 236 }, { "epoch": 0.25, "learning_rate": 1.9896631793156363e-05, "loss": 0.7734, "step": 237 }, { "epoch": 0.25, "learning_rate": 1.9894960777951202e-05, "loss": 0.7259, "step": 238 }, { "epoch": 0.25, "learning_rate": 1.9893276435596765e-05, "loss": 0.5889, "step": 239 }, { "epoch": 0.26, "learning_rate": 1.9891578768361633e-05, "loss": 0.6636, "step": 240 }, { "epoch": 0.26, "learning_rate": 1.988986777853233e-05, "loss": 0.5285, "step": 241 }, { "epoch": 0.26, "learning_rate": 1.9888143468413314e-05, "loss": 0.6156, "step": 242 }, { "epoch": 0.26, "learning_rate": 1.9886405840327005e-05, "loss": 0.5996, "step": 243 }, { "epoch": 0.26, "learning_rate": 1.9884654896613743e-05, "loss": 0.575, "step": 244 }, { "epoch": 0.26, "learning_rate": 1.9882890639631812e-05, "loss": 0.7417, "step": 245 }, { "epoch": 0.26, "learning_rate": 1.988111307175742e-05, "loss": 0.6623, "step": 246 }, { "epoch": 0.26, "learning_rate": 1.987932219538471e-05, "loss": 0.6135, "step": 247 }, { "epoch": 0.26, "learning_rate": 1.9877518012925736e-05, "loss": 0.7071, "step": 248 }, { "epoch": 0.26, "learning_rate": 1.987570052681049e-05, "loss": 0.7295, "step": 249 }, { "epoch": 0.27, "learning_rate": 1.9873869739486883e-05, "loss": 0.7431, "step": 250 }, { "epoch": 0.27, "learning_rate": 1.9872025653420718e-05, "loss": 0.5272, "step": 251 }, { "epoch": 0.27, "learning_rate": 1.9870168271095735e-05, "loss": 0.7295, "step": 252 }, { "epoch": 0.27, "learning_rate": 1.9868297595013574e-05, "loss": 0.5371, "step": 253 }, { "epoch": 0.27, "learning_rate": 1.9866413627693768e-05, "loss": 0.557, "step": 254 }, { "epoch": 0.27, "learning_rate": 1.986451637167377e-05, "loss": 0.5482, "step": 255 }, { "epoch": 0.27, "learning_rate": 1.986260582950892e-05, "loss": 0.6929, "step": 256 }, { "epoch": 0.27, "learning_rate": 1.9860682003772453e-05, "loss": 0.622, "step": 257 }, { "epoch": 0.27, "learning_rate": 1.9858744897055498e-05, "loss": 0.5472, "step": 258 }, { "epoch": 0.28, "learning_rate": 1.9856794511967076e-05, "loss": 0.5392, "step": 259 }, { "epoch": 0.28, "learning_rate": 1.985483085113408e-05, "loss": 0.6551, "step": 260 }, { "epoch": 0.28, "learning_rate": 1.9852853917201295e-05, "loss": 0.634, "step": 261 }, { "epoch": 0.28, "learning_rate": 1.985086371283138e-05, "loss": 0.5573, "step": 262 }, { "epoch": 0.28, "learning_rate": 1.9848860240704862e-05, "loss": 0.5285, "step": 263 }, { "epoch": 0.28, "learning_rate": 1.9846843503520144e-05, "loss": 0.5761, "step": 264 }, { "epoch": 0.28, "learning_rate": 1.9844813503993493e-05, "loss": 0.5594, "step": 265 }, { "epoch": 0.28, "learning_rate": 1.9842770244859038e-05, "loss": 0.5405, "step": 266 }, { "epoch": 0.28, "learning_rate": 1.9840713728868768e-05, "loss": 0.5327, "step": 267 }, { "epoch": 0.29, "learning_rate": 1.983864395879253e-05, "loss": 0.5862, "step": 268 }, { "epoch": 0.29, "learning_rate": 1.9836560937418013e-05, "loss": 0.5556, "step": 269 }, { "epoch": 0.29, "learning_rate": 1.9834464667550765e-05, "loss": 0.6056, "step": 270 }, { "epoch": 0.29, "learning_rate": 1.9832355152014167e-05, "loss": 0.6107, "step": 271 }, { "epoch": 0.29, "learning_rate": 1.9830232393649454e-05, "loss": 0.5519, "step": 272 }, { "epoch": 0.29, "learning_rate": 1.9828096395315687e-05, "loss": 0.5765, "step": 273 }, { "epoch": 0.29, "learning_rate": 1.982594715988976e-05, "loss": 0.4871, "step": 274 }, { "epoch": 0.29, "learning_rate": 1.982378469026639e-05, "loss": 0.559, "step": 275 }, { "epoch": 0.29, "learning_rate": 1.982160898935814e-05, "loss": 0.504, "step": 276 }, { "epoch": 0.29, "learning_rate": 1.9819420060095368e-05, "loss": 0.5212, "step": 277 }, { "epoch": 0.3, "learning_rate": 1.9817217905426264e-05, "loss": 0.58, "step": 278 }, { "epoch": 0.3, "learning_rate": 1.9815002528316826e-05, "loss": 0.5671, "step": 279 }, { "epoch": 0.3, "learning_rate": 1.9812773931750862e-05, "loss": 0.5402, "step": 280 }, { "epoch": 0.3, "learning_rate": 1.981053211872999e-05, "loss": 0.654, "step": 281 }, { "epoch": 0.3, "learning_rate": 1.9808277092273616e-05, "loss": 0.5989, "step": 282 }, { "epoch": 0.3, "learning_rate": 1.9806008855418955e-05, "loss": 0.5915, "step": 283 }, { "epoch": 0.3, "learning_rate": 1.9803727411221006e-05, "loss": 0.5856, "step": 284 }, { "epoch": 0.3, "learning_rate": 1.980143276275256e-05, "loss": 0.5707, "step": 285 }, { "epoch": 0.3, "learning_rate": 1.97991249131042e-05, "loss": 0.5737, "step": 286 }, { "epoch": 0.31, "learning_rate": 1.9796803865384273e-05, "loss": 0.5895, "step": 287 }, { "epoch": 0.31, "learning_rate": 1.979446962271891e-05, "loss": 0.5093, "step": 288 }, { "epoch": 0.31, "learning_rate": 1.9792122188252022e-05, "loss": 0.6135, "step": 289 }, { "epoch": 0.31, "learning_rate": 1.978976156514527e-05, "loss": 0.5506, "step": 290 }, { "epoch": 0.31, "learning_rate": 1.97873877565781e-05, "loss": 0.5674, "step": 291 }, { "epoch": 0.31, "learning_rate": 1.9785000765747696e-05, "loss": 0.6109, "step": 292 }, { "epoch": 0.31, "learning_rate": 1.978260059586901e-05, "loss": 0.6727, "step": 293 }, { "epoch": 0.31, "learning_rate": 1.9780187250174737e-05, "loss": 0.6052, "step": 294 }, { "epoch": 0.31, "learning_rate": 1.9777760731915325e-05, "loss": 0.5422, "step": 295 }, { "epoch": 0.31, "learning_rate": 1.9775321044358957e-05, "loss": 0.5446, "step": 296 }, { "epoch": 0.32, "learning_rate": 1.977286819079156e-05, "loss": 0.505, "step": 297 }, { "epoch": 0.32, "learning_rate": 1.977040217451678e-05, "loss": 0.5927, "step": 298 }, { "epoch": 0.32, "learning_rate": 1.9767922998856015e-05, "loss": 0.5778, "step": 299 }, { "epoch": 0.32, "learning_rate": 1.9765430667148368e-05, "loss": 0.5707, "step": 300 }, { "epoch": 0.32, "learning_rate": 1.976292518275066e-05, "loss": 0.5305, "step": 301 }, { "epoch": 0.32, "learning_rate": 1.976040654903744e-05, "loss": 0.519, "step": 302 }, { "epoch": 0.32, "learning_rate": 1.975787476940096e-05, "loss": 0.5436, "step": 303 }, { "epoch": 0.32, "learning_rate": 1.975532984725118e-05, "loss": 0.7989, "step": 304 }, { "epoch": 0.32, "learning_rate": 1.9752771786015756e-05, "loss": 0.5648, "step": 305 }, { "epoch": 0.33, "learning_rate": 1.9750200589140044e-05, "loss": 0.599, "step": 306 }, { "epoch": 0.33, "learning_rate": 1.974761626008709e-05, "loss": 0.5322, "step": 307 }, { "epoch": 0.33, "learning_rate": 1.974501880233764e-05, "loss": 0.6081, "step": 308 }, { "epoch": 0.33, "learning_rate": 1.97424082193901e-05, "loss": 0.5676, "step": 309 }, { "epoch": 0.33, "learning_rate": 1.973978451476057e-05, "loss": 0.5656, "step": 310 }, { "epoch": 0.33, "learning_rate": 1.9737147691982817e-05, "loss": 0.5802, "step": 311 }, { "epoch": 0.33, "learning_rate": 1.9734497754608287e-05, "loss": 0.7008, "step": 312 }, { "epoch": 0.33, "learning_rate": 1.973183470620607e-05, "loss": 0.6082, "step": 313 }, { "epoch": 0.33, "learning_rate": 1.972915855036293e-05, "loss": 0.5717, "step": 314 }, { "epoch": 0.34, "learning_rate": 1.9726469290683276e-05, "loss": 0.529, "step": 315 }, { "epoch": 0.34, "learning_rate": 1.9723766930789177e-05, "loss": 0.7472, "step": 316 }, { "epoch": 0.34, "learning_rate": 1.9721051474320337e-05, "loss": 0.7192, "step": 317 }, { "epoch": 0.34, "learning_rate": 1.97183229249341e-05, "loss": 0.5621, "step": 318 }, { "epoch": 0.34, "learning_rate": 1.9715581286305447e-05, "loss": 0.6221, "step": 319 }, { "epoch": 0.34, "learning_rate": 1.9712826562126988e-05, "loss": 0.5628, "step": 320 }, { "epoch": 0.34, "learning_rate": 1.971005875610896e-05, "loss": 0.5276, "step": 321 }, { "epoch": 0.34, "learning_rate": 1.970727787197921e-05, "loss": 0.5506, "step": 322 }, { "epoch": 0.34, "learning_rate": 1.9704483913483208e-05, "loss": 0.5618, "step": 323 }, { "epoch": 0.34, "learning_rate": 1.9701676884384036e-05, "loss": 0.5, "step": 324 }, { "epoch": 0.35, "learning_rate": 1.9698856788462372e-05, "loss": 0.5138, "step": 325 }, { "epoch": 0.35, "learning_rate": 1.9696023629516498e-05, "loss": 0.5337, "step": 326 }, { "epoch": 0.35, "learning_rate": 1.9693177411362283e-05, "loss": 0.5481, "step": 327 }, { "epoch": 0.35, "learning_rate": 1.9690318137833202e-05, "loss": 0.5296, "step": 328 }, { "epoch": 0.35, "learning_rate": 1.9687445812780294e-05, "loss": 0.6868, "step": 329 }, { "epoch": 0.35, "learning_rate": 1.968456044007219e-05, "loss": 0.5867, "step": 330 }, { "epoch": 0.35, "learning_rate": 1.968166202359508e-05, "loss": 0.5437, "step": 331 }, { "epoch": 0.35, "learning_rate": 1.9678750567252742e-05, "loss": 0.6034, "step": 332 }, { "epoch": 0.35, "learning_rate": 1.9675826074966505e-05, "loss": 0.5028, "step": 333 }, { "epoch": 0.36, "learning_rate": 1.967288855067526e-05, "loss": 0.5512, "step": 334 }, { "epoch": 0.36, "learning_rate": 1.9669937998335438e-05, "loss": 0.5936, "step": 335 }, { "epoch": 0.36, "learning_rate": 1.9666974421921035e-05, "loss": 0.5825, "step": 336 }, { "epoch": 0.36, "learning_rate": 1.9663997825423577e-05, "loss": 0.5814, "step": 337 }, { "epoch": 0.36, "learning_rate": 1.9661008212852128e-05, "loss": 0.5212, "step": 338 }, { "epoch": 0.36, "learning_rate": 1.965800558823329e-05, "loss": 0.5946, "step": 339 }, { "epoch": 0.36, "learning_rate": 1.9654989955611177e-05, "loss": 0.5596, "step": 340 }, { "epoch": 0.36, "learning_rate": 1.9651961319047436e-05, "loss": 0.5694, "step": 341 }, { "epoch": 0.36, "learning_rate": 1.9648919682621223e-05, "loss": 0.4794, "step": 342 }, { "epoch": 0.36, "learning_rate": 1.9645865050429203e-05, "loss": 0.5756, "step": 343 }, { "epoch": 0.37, "learning_rate": 1.964279742658554e-05, "loss": 0.6045, "step": 344 }, { "epoch": 0.37, "learning_rate": 1.963971681522191e-05, "loss": 0.6946, "step": 345 }, { "epoch": 0.37, "learning_rate": 1.9636623220487468e-05, "loss": 0.5623, "step": 346 }, { "epoch": 0.37, "learning_rate": 1.963351664654886e-05, "loss": 0.6787, "step": 347 }, { "epoch": 0.37, "learning_rate": 1.963039709759021e-05, "loss": 0.5414, "step": 348 }, { "epoch": 0.37, "learning_rate": 1.9627264577813123e-05, "loss": 0.5316, "step": 349 }, { "epoch": 0.37, "learning_rate": 1.962411909143667e-05, "loss": 0.5403, "step": 350 }, { "epoch": 0.37, "learning_rate": 1.9620960642697394e-05, "loss": 0.5355, "step": 351 }, { "epoch": 0.37, "learning_rate": 1.9617789235849284e-05, "loss": 0.4921, "step": 352 }, { "epoch": 0.38, "learning_rate": 1.961460487516379e-05, "loss": 0.5815, "step": 353 }, { "epoch": 0.38, "learning_rate": 1.961140756492981e-05, "loss": 0.6341, "step": 354 }, { "epoch": 0.38, "learning_rate": 1.9608197309453673e-05, "loss": 0.5236, "step": 355 }, { "epoch": 0.38, "learning_rate": 1.9604974113059164e-05, "loss": 0.5679, "step": 356 }, { "epoch": 0.38, "learning_rate": 1.9601737980087468e-05, "loss": 0.5791, "step": 357 }, { "epoch": 0.38, "learning_rate": 1.9598488914897226e-05, "loss": 0.5494, "step": 358 }, { "epoch": 0.38, "learning_rate": 1.9595226921864472e-05, "loss": 0.565, "step": 359 }, { "epoch": 0.38, "learning_rate": 1.9591952005382668e-05, "loss": 0.5852, "step": 360 }, { "epoch": 0.38, "learning_rate": 1.9588664169862665e-05, "loss": 0.6202, "step": 361 }, { "epoch": 0.39, "learning_rate": 1.9585363419732736e-05, "loss": 0.571, "step": 362 }, { "epoch": 0.39, "learning_rate": 1.958204975943853e-05, "loss": 0.5526, "step": 363 }, { "epoch": 0.39, "learning_rate": 1.957872319344309e-05, "loss": 0.7049, "step": 364 }, { "epoch": 0.39, "learning_rate": 1.9575383726226844e-05, "loss": 0.6912, "step": 365 }, { "epoch": 0.39, "learning_rate": 1.95720313622876e-05, "loss": 0.5521, "step": 366 }, { "epoch": 0.39, "learning_rate": 1.956866610614052e-05, "loss": 0.5597, "step": 367 }, { "epoch": 0.39, "learning_rate": 1.956528796231815e-05, "loss": 0.5584, "step": 368 }, { "epoch": 0.39, "learning_rate": 1.9561896935370385e-05, "loss": 0.5019, "step": 369 }, { "epoch": 0.39, "learning_rate": 1.955849302986446e-05, "loss": 0.4866, "step": 370 }, { "epoch": 0.39, "learning_rate": 1.9555076250384975e-05, "loss": 0.5616, "step": 371 }, { "epoch": 0.4, "learning_rate": 1.955164660153386e-05, "loss": 0.5691, "step": 372 }, { "epoch": 0.4, "learning_rate": 1.954820408793038e-05, "loss": 0.5969, "step": 373 }, { "epoch": 0.4, "learning_rate": 1.9544748714211128e-05, "loss": 0.5884, "step": 374 }, { "epoch": 0.4, "learning_rate": 1.9541280485030013e-05, "loss": 0.6357, "step": 375 }, { "epoch": 0.4, "learning_rate": 1.9537799405058266e-05, "loss": 0.57, "step": 376 }, { "epoch": 0.4, "learning_rate": 1.953430547898442e-05, "loss": 0.5722, "step": 377 }, { "epoch": 0.4, "learning_rate": 1.953079871151431e-05, "loss": 0.6698, "step": 378 }, { "epoch": 0.4, "learning_rate": 1.952727910737107e-05, "loss": 0.5427, "step": 379 }, { "epoch": 0.4, "learning_rate": 1.9523746671295125e-05, "loss": 0.5256, "step": 380 }, { "epoch": 0.41, "learning_rate": 1.952020140804418e-05, "loss": 0.489, "step": 381 }, { "epoch": 0.41, "learning_rate": 1.951664332239321e-05, "loss": 0.5765, "step": 382 }, { "epoch": 0.41, "learning_rate": 1.9513072419134475e-05, "loss": 0.5888, "step": 383 }, { "epoch": 0.41, "learning_rate": 1.9509488703077483e-05, "loss": 0.4835, "step": 384 }, { "epoch": 0.41, "learning_rate": 1.950589217904901e-05, "loss": 0.5605, "step": 385 }, { "epoch": 0.41, "learning_rate": 1.9502282851893072e-05, "loss": 0.7391, "step": 386 }, { "epoch": 0.41, "learning_rate": 1.9498660726470944e-05, "loss": 0.57, "step": 387 }, { "epoch": 0.41, "learning_rate": 1.9495025807661125e-05, "loss": 0.724, "step": 388 }, { "epoch": 0.41, "learning_rate": 1.949137810035935e-05, "loss": 0.5892, "step": 389 }, { "epoch": 0.41, "learning_rate": 1.9487717609478586e-05, "loss": 0.5535, "step": 390 }, { "epoch": 0.42, "learning_rate": 1.9484044339948998e-05, "loss": 0.5777, "step": 391 }, { "epoch": 0.42, "learning_rate": 1.9480358296717982e-05, "loss": 0.6756, "step": 392 }, { "epoch": 0.42, "learning_rate": 1.9476659484750126e-05, "loss": 0.6383, "step": 393 }, { "epoch": 0.42, "learning_rate": 1.9472947909027224e-05, "loss": 0.5455, "step": 394 }, { "epoch": 0.42, "learning_rate": 1.9469223574548255e-05, "loss": 0.5407, "step": 395 }, { "epoch": 0.42, "learning_rate": 1.9465486486329385e-05, "loss": 0.577, "step": 396 }, { "epoch": 0.42, "learning_rate": 1.946173664940396e-05, "loss": 0.5759, "step": 397 }, { "epoch": 0.42, "learning_rate": 1.9457974068822492e-05, "loss": 0.6076, "step": 398 }, { "epoch": 0.42, "learning_rate": 1.9454198749652655e-05, "loss": 0.5805, "step": 399 }, { "epoch": 0.43, "learning_rate": 1.945041069697929e-05, "loss": 0.6478, "step": 400 }, { "epoch": 0.43, "learning_rate": 1.9446609915904375e-05, "loss": 0.5789, "step": 401 }, { "epoch": 0.43, "learning_rate": 1.9442796411547046e-05, "loss": 0.582, "step": 402 }, { "epoch": 0.43, "learning_rate": 1.9438970189043564e-05, "loss": 0.5772, "step": 403 }, { "epoch": 0.43, "learning_rate": 1.9435131253547327e-05, "loss": 0.5764, "step": 404 }, { "epoch": 0.43, "learning_rate": 1.9431279610228845e-05, "loss": 0.52, "step": 405 }, { "epoch": 0.43, "learning_rate": 1.942741526427576e-05, "loss": 0.4357, "step": 406 }, { "epoch": 0.43, "learning_rate": 1.942353822089281e-05, "loss": 0.6089, "step": 407 }, { "epoch": 0.43, "learning_rate": 1.941964848530184e-05, "loss": 0.5429, "step": 408 }, { "epoch": 0.44, "learning_rate": 1.9415746062741784e-05, "loss": 0.586, "step": 409 }, { "epoch": 0.44, "learning_rate": 1.9411830958468668e-05, "loss": 0.6796, "step": 410 }, { "epoch": 0.44, "learning_rate": 1.94079031777556e-05, "loss": 0.7836, "step": 411 }, { "epoch": 0.44, "learning_rate": 1.9403962725892764e-05, "loss": 0.5262, "step": 412 }, { "epoch": 0.44, "learning_rate": 1.94000096081874e-05, "loss": 0.5616, "step": 413 }, { "epoch": 0.44, "learning_rate": 1.9396043829963817e-05, "loss": 0.5955, "step": 414 }, { "epoch": 0.44, "learning_rate": 1.9392065396563368e-05, "loss": 0.5699, "step": 415 }, { "epoch": 0.44, "learning_rate": 1.9388074313344454e-05, "loss": 0.6338, "step": 416 }, { "epoch": 0.44, "learning_rate": 1.9384070585682518e-05, "loss": 0.6416, "step": 417 }, { "epoch": 0.44, "learning_rate": 1.938005421897003e-05, "loss": 0.605, "step": 418 }, { "epoch": 0.45, "learning_rate": 1.9376025218616484e-05, "loss": 0.5573, "step": 419 }, { "epoch": 0.45, "learning_rate": 1.9371983590048383e-05, "loss": 0.6306, "step": 420 }, { "epoch": 0.45, "learning_rate": 1.9367929338709245e-05, "loss": 0.5353, "step": 421 }, { "epoch": 0.45, "learning_rate": 1.9363862470059595e-05, "loss": 0.5477, "step": 422 }, { "epoch": 0.45, "learning_rate": 1.935978298957694e-05, "loss": 0.5254, "step": 423 }, { "epoch": 0.45, "learning_rate": 1.9355690902755776e-05, "loss": 0.5814, "step": 424 }, { "epoch": 0.45, "learning_rate": 1.935158621510758e-05, "loss": 0.6357, "step": 425 }, { "epoch": 0.45, "learning_rate": 1.934746893216081e-05, "loss": 0.5962, "step": 426 }, { "epoch": 0.45, "learning_rate": 1.9343339059460868e-05, "loss": 0.5125, "step": 427 }, { "epoch": 0.46, "learning_rate": 1.9339196602570133e-05, "loss": 0.6385, "step": 428 }, { "epoch": 0.46, "learning_rate": 1.9335041567067913e-05, "loss": 0.5218, "step": 429 }, { "epoch": 0.46, "learning_rate": 1.933087395855048e-05, "loss": 0.6623, "step": 430 }, { "epoch": 0.46, "learning_rate": 1.932669378263102e-05, "loss": 0.5815, "step": 431 }, { "epoch": 0.46, "learning_rate": 1.9322501044939658e-05, "loss": 0.7636, "step": 432 }, { "epoch": 0.46, "learning_rate": 1.9318295751123438e-05, "loss": 0.5605, "step": 433 }, { "epoch": 0.46, "learning_rate": 1.9314077906846303e-05, "loss": 0.6314, "step": 434 }, { "epoch": 0.46, "learning_rate": 1.9309847517789114e-05, "loss": 0.538, "step": 435 }, { "epoch": 0.46, "learning_rate": 1.930560458964962e-05, "loss": 0.539, "step": 436 }, { "epoch": 0.46, "learning_rate": 1.9301349128142463e-05, "loss": 0.5496, "step": 437 }, { "epoch": 0.47, "learning_rate": 1.9297081138999164e-05, "loss": 0.5005, "step": 438 }, { "epoch": 0.47, "learning_rate": 1.9292800627968112e-05, "loss": 0.5309, "step": 439 }, { "epoch": 0.47, "learning_rate": 1.928850760081457e-05, "loss": 0.5553, "step": 440 }, { "epoch": 0.47, "learning_rate": 1.9284202063320652e-05, "loss": 0.6578, "step": 441 }, { "epoch": 0.47, "learning_rate": 1.9279884021285326e-05, "loss": 0.5801, "step": 442 }, { "epoch": 0.47, "learning_rate": 1.9275553480524397e-05, "loss": 0.5568, "step": 443 }, { "epoch": 0.47, "learning_rate": 1.927121044687051e-05, "loss": 0.5163, "step": 444 }, { "epoch": 0.47, "learning_rate": 1.9266854926173134e-05, "loss": 0.4926, "step": 445 }, { "epoch": 0.47, "learning_rate": 1.926248692429855e-05, "loss": 0.5818, "step": 446 }, { "epoch": 0.48, "learning_rate": 1.925810644712986e-05, "loss": 0.5065, "step": 447 }, { "epoch": 0.48, "learning_rate": 1.925371350056696e-05, "loss": 0.5259, "step": 448 }, { "epoch": 0.48, "learning_rate": 1.9249308090526545e-05, "loss": 0.4826, "step": 449 }, { "epoch": 0.48, "learning_rate": 1.92448902229421e-05, "loss": 0.558, "step": 450 }, { "epoch": 0.48, "learning_rate": 1.9240459903763878e-05, "loss": 0.5017, "step": 451 }, { "epoch": 0.48, "learning_rate": 1.9236017138958913e-05, "loss": 0.568, "step": 452 }, { "epoch": 0.48, "learning_rate": 1.923156193451099e-05, "loss": 0.4871, "step": 453 }, { "epoch": 0.48, "learning_rate": 1.9227094296420662e-05, "loss": 0.5557, "step": 454 }, { "epoch": 0.48, "learning_rate": 1.9222614230705225e-05, "loss": 0.5703, "step": 455 }, { "epoch": 0.49, "learning_rate": 1.9218121743398702e-05, "loss": 0.5318, "step": 456 }, { "epoch": 0.49, "learning_rate": 1.9213616840551867e-05, "loss": 0.5605, "step": 457 }, { "epoch": 0.49, "learning_rate": 1.9209099528232188e-05, "loss": 0.6088, "step": 458 }, { "epoch": 0.49, "learning_rate": 1.9204569812523874e-05, "loss": 0.5307, "step": 459 }, { "epoch": 0.49, "learning_rate": 1.9200027699527824e-05, "loss": 0.5064, "step": 460 }, { "epoch": 0.49, "learning_rate": 1.9195473195361636e-05, "loss": 0.5764, "step": 461 }, { "epoch": 0.49, "learning_rate": 1.9190906306159607e-05, "loss": 0.5125, "step": 462 }, { "epoch": 0.49, "learning_rate": 1.91863270380727e-05, "loss": 0.5612, "step": 463 }, { "epoch": 0.49, "learning_rate": 1.9181735397268565e-05, "loss": 0.5108, "step": 464 }, { "epoch": 0.49, "learning_rate": 1.9177131389931503e-05, "loss": 0.7011, "step": 465 }, { "epoch": 0.5, "learning_rate": 1.9172515022262487e-05, "loss": 0.5749, "step": 466 }, { "epoch": 0.5, "learning_rate": 1.9167886300479115e-05, "loss": 0.6166, "step": 467 }, { "epoch": 0.5, "learning_rate": 1.916324523081565e-05, "loss": 0.5728, "step": 468 }, { "epoch": 0.5, "learning_rate": 1.9158591819522972e-05, "loss": 0.5026, "step": 469 }, { "epoch": 0.5, "learning_rate": 1.9153926072868582e-05, "loss": 0.725, "step": 470 }, { "epoch": 0.5, "learning_rate": 1.9149247997136596e-05, "loss": 0.6488, "step": 471 }, { "epoch": 0.5, "learning_rate": 1.914455759862774e-05, "loss": 0.6037, "step": 472 }, { "epoch": 0.5, "learning_rate": 1.9139854883659333e-05, "loss": 0.6748, "step": 473 }, { "epoch": 0.5, "learning_rate": 1.913513985856529e-05, "loss": 0.5451, "step": 474 }, { "epoch": 0.51, "learning_rate": 1.913041252969609e-05, "loss": 0.5559, "step": 475 }, { "epoch": 0.51, "learning_rate": 1.9125672903418808e-05, "loss": 0.56, "step": 476 }, { "epoch": 0.51, "learning_rate": 1.9120920986117058e-05, "loss": 0.5613, "step": 477 }, { "epoch": 0.51, "learning_rate": 1.911615678419102e-05, "loss": 0.5112, "step": 478 }, { "epoch": 0.51, "learning_rate": 1.9111380304057415e-05, "loss": 0.5742, "step": 479 }, { "epoch": 0.51, "learning_rate": 1.9106591552149506e-05, "loss": 0.5243, "step": 480 }, { "epoch": 0.51, "learning_rate": 1.9101790534917088e-05, "loss": 0.545, "step": 481 }, { "epoch": 0.51, "learning_rate": 1.9096977258826462e-05, "loss": 0.5596, "step": 482 }, { "epoch": 0.51, "learning_rate": 1.9092151730360453e-05, "loss": 0.5366, "step": 483 }, { "epoch": 0.51, "learning_rate": 1.908731395601838e-05, "loss": 0.5246, "step": 484 }, { "epoch": 0.52, "learning_rate": 1.9082463942316057e-05, "loss": 0.5587, "step": 485 }, { "epoch": 0.52, "learning_rate": 1.9077601695785793e-05, "loss": 0.5454, "step": 486 }, { "epoch": 0.52, "learning_rate": 1.9072727222976356e-05, "loss": 0.6544, "step": 487 }, { "epoch": 0.52, "learning_rate": 1.906784053045299e-05, "loss": 0.5867, "step": 488 }, { "epoch": 0.52, "learning_rate": 1.90629416247974e-05, "loss": 0.5448, "step": 489 }, { "epoch": 0.52, "learning_rate": 1.9058030512607736e-05, "loss": 0.635, "step": 490 }, { "epoch": 0.52, "learning_rate": 1.9053107200498592e-05, "loss": 0.6514, "step": 491 }, { "epoch": 0.52, "learning_rate": 1.9048171695100985e-05, "loss": 0.5645, "step": 492 }, { "epoch": 0.52, "learning_rate": 1.904322400306237e-05, "loss": 0.5524, "step": 493 }, { "epoch": 0.53, "learning_rate": 1.9038264131046597e-05, "loss": 0.5112, "step": 494 }, { "epoch": 0.53, "learning_rate": 1.9033292085733935e-05, "loss": 0.5325, "step": 495 }, { "epoch": 0.53, "learning_rate": 1.9028307873821046e-05, "loss": 0.5719, "step": 496 }, { "epoch": 0.53, "learning_rate": 1.902331150202098e-05, "loss": 0.5301, "step": 497 }, { "epoch": 0.53, "learning_rate": 1.9018302977063153e-05, "loss": 0.6145, "step": 498 }, { "epoch": 0.53, "learning_rate": 1.9013282305693358e-05, "loss": 0.5598, "step": 499 }, { "epoch": 0.53, "learning_rate": 1.9008249494673756e-05, "loss": 0.5553, "step": 500 }, { "epoch": 0.53, "learning_rate": 1.9003204550782848e-05, "loss": 0.5852, "step": 501 }, { "epoch": 0.53, "learning_rate": 1.8998147480815473e-05, "loss": 0.5253, "step": 502 }, { "epoch": 0.53, "learning_rate": 1.8993078291582814e-05, "loss": 0.5553, "step": 503 }, { "epoch": 0.54, "learning_rate": 1.8987996989912366e-05, "loss": 0.7983, "step": 504 }, { "epoch": 0.54, "learning_rate": 1.8982903582647946e-05, "loss": 0.6, "step": 505 }, { "epoch": 0.54, "learning_rate": 1.8977798076649673e-05, "loss": 0.6008, "step": 506 }, { "epoch": 0.54, "learning_rate": 1.8972680478793953e-05, "loss": 0.5003, "step": 507 }, { "epoch": 0.54, "learning_rate": 1.8967550795973494e-05, "loss": 0.7798, "step": 508 }, { "epoch": 0.54, "learning_rate": 1.896240903509727e-05, "loss": 0.5888, "step": 509 }, { "epoch": 0.54, "learning_rate": 1.8957255203090517e-05, "loss": 0.5803, "step": 510 }, { "epoch": 0.54, "learning_rate": 1.895208930689475e-05, "loss": 0.7172, "step": 511 }, { "epoch": 0.54, "learning_rate": 1.894691135346771e-05, "loss": 0.5658, "step": 512 }, { "epoch": 0.55, "learning_rate": 1.894172134978339e-05, "loss": 0.692, "step": 513 }, { "epoch": 0.55, "learning_rate": 1.893651930283201e-05, "loss": 0.5369, "step": 514 }, { "epoch": 0.55, "learning_rate": 1.893130521962001e-05, "loss": 0.5601, "step": 515 }, { "epoch": 0.55, "learning_rate": 1.8926079107170045e-05, "loss": 0.4975, "step": 516 }, { "epoch": 0.55, "learning_rate": 1.8920840972520963e-05, "loss": 0.5545, "step": 517 }, { "epoch": 0.55, "learning_rate": 1.8915590822727816e-05, "loss": 0.6945, "step": 518 }, { "epoch": 0.55, "learning_rate": 1.891032866486183e-05, "loss": 0.6718, "step": 519 }, { "epoch": 0.55, "learning_rate": 1.890505450601041e-05, "loss": 0.597, "step": 520 }, { "epoch": 0.55, "learning_rate": 1.889976835327711e-05, "loss": 0.6008, "step": 521 }, { "epoch": 0.56, "learning_rate": 1.889447021378166e-05, "loss": 0.5419, "step": 522 }, { "epoch": 0.56, "learning_rate": 1.8889160094659926e-05, "loss": 0.5746, "step": 523 }, { "epoch": 0.56, "learning_rate": 1.8883838003063902e-05, "loss": 0.5448, "step": 524 }, { "epoch": 0.56, "learning_rate": 1.887850394616171e-05, "loss": 0.6543, "step": 525 }, { "epoch": 0.56, "learning_rate": 1.8873157931137596e-05, "loss": 0.5508, "step": 526 }, { "epoch": 0.56, "learning_rate": 1.8867799965191905e-05, "loss": 0.5241, "step": 527 }, { "epoch": 0.56, "learning_rate": 1.8862430055541078e-05, "loss": 0.5327, "step": 528 }, { "epoch": 0.56, "learning_rate": 1.885704820941764e-05, "loss": 0.563, "step": 529 }, { "epoch": 0.56, "learning_rate": 1.88516544340702e-05, "loss": 0.5388, "step": 530 }, { "epoch": 0.56, "learning_rate": 1.884624873676343e-05, "loss": 0.4725, "step": 531 }, { "epoch": 0.57, "learning_rate": 1.8840831124778062e-05, "loss": 0.5919, "step": 532 }, { "epoch": 0.57, "learning_rate": 1.883540160541087e-05, "loss": 0.5094, "step": 533 }, { "epoch": 0.57, "learning_rate": 1.8829960185974667e-05, "loss": 0.5297, "step": 534 }, { "epoch": 0.57, "learning_rate": 1.88245068737983e-05, "loss": 0.5323, "step": 535 }, { "epoch": 0.57, "learning_rate": 1.8819041676226632e-05, "loss": 0.5349, "step": 536 }, { "epoch": 0.57, "learning_rate": 1.881356460062052e-05, "loss": 0.5802, "step": 537 }, { "epoch": 0.57, "learning_rate": 1.880807565435684e-05, "loss": 0.5231, "step": 538 }, { "epoch": 0.57, "learning_rate": 1.8802574844828446e-05, "loss": 0.8007, "step": 539 }, { "epoch": 0.57, "learning_rate": 1.8797062179444166e-05, "loss": 0.5602, "step": 540 }, { "epoch": 0.58, "learning_rate": 1.8791537665628803e-05, "loss": 0.5707, "step": 541 }, { "epoch": 0.58, "learning_rate": 1.878600131082312e-05, "loss": 0.5158, "step": 542 }, { "epoch": 0.58, "learning_rate": 1.8780453122483816e-05, "loss": 0.5667, "step": 543 }, { "epoch": 0.58, "learning_rate": 1.877489310808355e-05, "loss": 0.5918, "step": 544 }, { "epoch": 0.58, "learning_rate": 1.8769321275110878e-05, "loss": 0.5782, "step": 545 }, { "epoch": 0.58, "learning_rate": 1.8763737631070306e-05, "loss": 0.5636, "step": 546 }, { "epoch": 0.58, "learning_rate": 1.8758142183482228e-05, "loss": 0.6314, "step": 547 }, { "epoch": 0.58, "learning_rate": 1.8752534939882944e-05, "loss": 0.575, "step": 548 }, { "epoch": 0.58, "learning_rate": 1.8746915907824633e-05, "loss": 0.6748, "step": 549 }, { "epoch": 0.58, "learning_rate": 1.874128509487536e-05, "loss": 0.5735, "step": 550 }, { "epoch": 0.59, "learning_rate": 1.8735642508619055e-05, "loss": 0.5533, "step": 551 }, { "epoch": 0.59, "learning_rate": 1.8729988156655507e-05, "loss": 0.5361, "step": 552 }, { "epoch": 0.59, "learning_rate": 1.8724322046600347e-05, "loss": 0.5474, "step": 553 }, { "epoch": 0.59, "learning_rate": 1.8718644186085045e-05, "loss": 0.5302, "step": 554 }, { "epoch": 0.59, "learning_rate": 1.8712954582756895e-05, "loss": 0.5572, "step": 555 }, { "epoch": 0.59, "learning_rate": 1.870725324427901e-05, "loss": 0.5514, "step": 556 }, { "epoch": 0.59, "learning_rate": 1.8701540178330312e-05, "loss": 0.5048, "step": 557 }, { "epoch": 0.59, "learning_rate": 1.8695815392605506e-05, "loss": 0.4938, "step": 558 }, { "epoch": 0.59, "learning_rate": 1.8690078894815098e-05, "loss": 0.5509, "step": 559 }, { "epoch": 0.6, "learning_rate": 1.8684330692685355e-05, "loss": 0.5673, "step": 560 }, { "epoch": 0.6, "learning_rate": 1.8678570793958312e-05, "loss": 0.5249, "step": 561 }, { "epoch": 0.6, "learning_rate": 1.867279920639177e-05, "loss": 0.5297, "step": 562 }, { "epoch": 0.6, "learning_rate": 1.866701593775925e-05, "loss": 0.6632, "step": 563 }, { "epoch": 0.6, "learning_rate": 1.8661220995850024e-05, "loss": 0.6173, "step": 564 }, { "epoch": 0.6, "learning_rate": 1.865541438846908e-05, "loss": 0.5582, "step": 565 }, { "epoch": 0.6, "learning_rate": 1.8649596123437116e-05, "loss": 0.5437, "step": 566 }, { "epoch": 0.6, "learning_rate": 1.8643766208590536e-05, "loss": 0.5194, "step": 567 }, { "epoch": 0.6, "learning_rate": 1.8637924651781433e-05, "loss": 0.5522, "step": 568 }, { "epoch": 0.61, "learning_rate": 1.863207146087758e-05, "loss": 0.5676, "step": 569 }, { "epoch": 0.61, "learning_rate": 1.8626206643762415e-05, "loss": 0.5626, "step": 570 }, { "epoch": 0.61, "learning_rate": 1.8620330208335042e-05, "loss": 0.5481, "step": 571 }, { "epoch": 0.61, "learning_rate": 1.861444216251021e-05, "loss": 0.5044, "step": 572 }, { "epoch": 0.61, "learning_rate": 1.8608542514218308e-05, "loss": 0.6179, "step": 573 }, { "epoch": 0.61, "learning_rate": 1.8602631271405343e-05, "loss": 0.5461, "step": 574 }, { "epoch": 0.61, "learning_rate": 1.859670844203295e-05, "loss": 0.6747, "step": 575 }, { "epoch": 0.61, "learning_rate": 1.8590774034078362e-05, "loss": 0.4699, "step": 576 }, { "epoch": 0.61, "learning_rate": 1.858482805553441e-05, "loss": 0.5541, "step": 577 }, { "epoch": 0.61, "learning_rate": 1.857887051440951e-05, "loss": 0.5674, "step": 578 }, { "epoch": 0.62, "learning_rate": 1.8572901418727647e-05, "loss": 0.5853, "step": 579 }, { "epoch": 0.62, "learning_rate": 1.856692077652837e-05, "loss": 0.5609, "step": 580 }, { "epoch": 0.62, "learning_rate": 1.8560928595866784e-05, "loss": 0.4885, "step": 581 }, { "epoch": 0.62, "learning_rate": 1.8554924884813527e-05, "loss": 0.5463, "step": 582 }, { "epoch": 0.62, "learning_rate": 1.854890965145477e-05, "loss": 0.5552, "step": 583 }, { "epoch": 0.62, "learning_rate": 1.854288290389221e-05, "loss": 0.5674, "step": 584 }, { "epoch": 0.62, "learning_rate": 1.8536844650243045e-05, "loss": 0.4766, "step": 585 }, { "epoch": 0.62, "learning_rate": 1.8530794898639963e-05, "loss": 0.5947, "step": 586 }, { "epoch": 0.62, "learning_rate": 1.8524733657231152e-05, "loss": 0.6068, "step": 587 }, { "epoch": 0.63, "learning_rate": 1.851866093418027e-05, "loss": 0.5383, "step": 588 }, { "epoch": 0.63, "learning_rate": 1.851257673766644e-05, "loss": 0.5502, "step": 589 }, { "epoch": 0.63, "learning_rate": 1.850648107588423e-05, "loss": 0.6178, "step": 590 }, { "epoch": 0.63, "learning_rate": 1.8500373957043658e-05, "loss": 0.5512, "step": 591 }, { "epoch": 0.63, "learning_rate": 1.849425538937018e-05, "loss": 0.5911, "step": 592 }, { "epoch": 0.63, "learning_rate": 1.8488125381104655e-05, "loss": 0.5721, "step": 593 }, { "epoch": 0.63, "learning_rate": 1.8481983940503365e-05, "loss": 0.5035, "step": 594 }, { "epoch": 0.63, "learning_rate": 1.8475831075837982e-05, "loss": 0.5514, "step": 595 }, { "epoch": 0.63, "learning_rate": 1.846966679539557e-05, "loss": 0.5754, "step": 596 }, { "epoch": 0.63, "learning_rate": 1.8463491107478563e-05, "loss": 0.5284, "step": 597 }, { "epoch": 0.64, "learning_rate": 1.8457304020404764e-05, "loss": 0.5674, "step": 598 }, { "epoch": 0.64, "learning_rate": 1.845110554250732e-05, "loss": 0.6311, "step": 599 }, { "epoch": 0.64, "learning_rate": 1.844489568213474e-05, "loss": 0.4969, "step": 600 }, { "epoch": 0.64, "learning_rate": 1.843867444765084e-05, "loss": 0.501, "step": 601 }, { "epoch": 0.64, "learning_rate": 1.843244184743477e-05, "loss": 0.5425, "step": 602 }, { "epoch": 0.64, "learning_rate": 1.8426197889880985e-05, "loss": 0.5288, "step": 603 }, { "epoch": 0.64, "learning_rate": 1.841994258339923e-05, "loss": 0.5319, "step": 604 }, { "epoch": 0.64, "learning_rate": 1.8413675936414552e-05, "loss": 0.4963, "step": 605 }, { "epoch": 0.64, "learning_rate": 1.8407397957367253e-05, "loss": 0.51, "step": 606 }, { "epoch": 0.65, "learning_rate": 1.8401108654712905e-05, "loss": 0.4349, "step": 607 }, { "epoch": 0.65, "learning_rate": 1.839480803692234e-05, "loss": 0.5715, "step": 608 }, { "epoch": 0.65, "learning_rate": 1.8388496112481612e-05, "loss": 0.5008, "step": 609 }, { "epoch": 0.65, "learning_rate": 1.8382172889892023e-05, "loss": 0.5718, "step": 610 }, { "epoch": 0.65, "learning_rate": 1.837583837767008e-05, "loss": 0.5405, "step": 611 }, { "epoch": 0.65, "learning_rate": 1.8369492584347494e-05, "loss": 0.5324, "step": 612 }, { "epoch": 0.65, "learning_rate": 1.8363135518471184e-05, "loss": 0.5039, "step": 613 }, { "epoch": 0.65, "learning_rate": 1.8356767188603232e-05, "loss": 0.5275, "step": 614 }, { "epoch": 0.65, "learning_rate": 1.8350387603320908e-05, "loss": 0.4663, "step": 615 }, { "epoch": 0.66, "learning_rate": 1.8343996771216632e-05, "loss": 0.5298, "step": 616 }, { "epoch": 0.66, "learning_rate": 1.8337594700897977e-05, "loss": 0.4961, "step": 617 }, { "epoch": 0.66, "learning_rate": 1.8331181400987647e-05, "loss": 0.5859, "step": 618 }, { "epoch": 0.66, "learning_rate": 1.8324756880123473e-05, "loss": 0.5618, "step": 619 }, { "epoch": 0.66, "learning_rate": 1.83183211469584e-05, "loss": 0.5728, "step": 620 }, { "epoch": 0.66, "learning_rate": 1.8311874210160477e-05, "loss": 0.5873, "step": 621 }, { "epoch": 0.66, "learning_rate": 1.830541607841284e-05, "loss": 0.6861, "step": 622 }, { "epoch": 0.66, "learning_rate": 1.8298946760413702e-05, "loss": 0.5562, "step": 623 }, { "epoch": 0.66, "learning_rate": 1.8292466264876342e-05, "loss": 0.4596, "step": 624 }, { "epoch": 0.66, "learning_rate": 1.8285974600529097e-05, "loss": 0.5202, "step": 625 }, { "epoch": 0.67, "learning_rate": 1.827947177611534e-05, "loss": 0.6236, "step": 626 }, { "epoch": 0.67, "learning_rate": 1.8272957800393485e-05, "loss": 0.631, "step": 627 }, { "epoch": 0.67, "learning_rate": 1.8266432682136957e-05, "loss": 0.5634, "step": 628 }, { "epoch": 0.67, "learning_rate": 1.8259896430134193e-05, "loss": 0.4891, "step": 629 }, { "epoch": 0.67, "learning_rate": 1.8253349053188625e-05, "loss": 0.5266, "step": 630 }, { "epoch": 0.67, "learning_rate": 1.8246790560118665e-05, "loss": 0.5149, "step": 631 }, { "epoch": 0.67, "learning_rate": 1.8240220959757705e-05, "loss": 0.611, "step": 632 }, { "epoch": 0.67, "learning_rate": 1.8233640260954084e-05, "loss": 0.5316, "step": 633 }, { "epoch": 0.67, "learning_rate": 1.8227048472571104e-05, "loss": 0.5912, "step": 634 }, { "epoch": 0.68, "learning_rate": 1.8220445603486993e-05, "loss": 0.4879, "step": 635 }, { "epoch": 0.68, "learning_rate": 1.8213831662594904e-05, "loss": 0.6622, "step": 636 }, { "epoch": 0.68, "learning_rate": 1.820720665880291e-05, "loss": 0.6376, "step": 637 }, { "epoch": 0.68, "learning_rate": 1.8200570601033977e-05, "loss": 0.6333, "step": 638 }, { "epoch": 0.68, "learning_rate": 1.8193923498225957e-05, "loss": 0.5388, "step": 639 }, { "epoch": 0.68, "learning_rate": 1.8187265359331582e-05, "loss": 0.5463, "step": 640 }, { "epoch": 0.68, "learning_rate": 1.8180596193318454e-05, "loss": 0.7462, "step": 641 }, { "epoch": 0.68, "learning_rate": 1.817391600916902e-05, "loss": 0.5276, "step": 642 }, { "epoch": 0.68, "learning_rate": 1.816722481588056e-05, "loss": 0.4865, "step": 643 }, { "epoch": 0.68, "learning_rate": 1.8160522622465194e-05, "loss": 0.5656, "step": 644 }, { "epoch": 0.69, "learning_rate": 1.815380943794986e-05, "loss": 0.579, "step": 645 }, { "epoch": 0.69, "learning_rate": 1.8147085271376285e-05, "loss": 0.552, "step": 646 }, { "epoch": 0.69, "learning_rate": 1.8140350131800993e-05, "loss": 0.6841, "step": 647 }, { "epoch": 0.69, "learning_rate": 1.81336040282953e-05, "loss": 0.5228, "step": 648 }, { "epoch": 0.69, "learning_rate": 1.812684696994527e-05, "loss": 0.5023, "step": 649 }, { "epoch": 0.69, "learning_rate": 1.8120078965851733e-05, "loss": 0.7443, "step": 650 }, { "epoch": 0.69, "learning_rate": 1.811330002513026e-05, "loss": 0.6585, "step": 651 }, { "epoch": 0.69, "learning_rate": 1.810651015691114e-05, "loss": 0.5395, "step": 652 }, { "epoch": 0.69, "learning_rate": 1.8099709370339403e-05, "loss": 0.5343, "step": 653 }, { "epoch": 0.7, "learning_rate": 1.8092897674574765e-05, "loss": 0.5461, "step": 654 }, { "epoch": 0.7, "learning_rate": 1.8086075078791646e-05, "loss": 0.5259, "step": 655 }, { "epoch": 0.7, "learning_rate": 1.807924159217914e-05, "loss": 0.557, "step": 656 }, { "epoch": 0.7, "learning_rate": 1.8072397223941015e-05, "loss": 0.5099, "step": 657 }, { "epoch": 0.7, "learning_rate": 1.8065541983295687e-05, "loss": 0.5523, "step": 658 }, { "epoch": 0.7, "learning_rate": 1.8058675879476225e-05, "loss": 0.6623, "step": 659 }, { "epoch": 0.7, "learning_rate": 1.8051798921730323e-05, "loss": 0.5299, "step": 660 }, { "epoch": 0.7, "learning_rate": 1.8044911119320302e-05, "loss": 0.5968, "step": 661 }, { "epoch": 0.7, "learning_rate": 1.8038012481523074e-05, "loss": 0.544, "step": 662 }, { "epoch": 0.71, "learning_rate": 1.803110301763016e-05, "loss": 0.6423, "step": 663 }, { "epoch": 0.71, "learning_rate": 1.802418273694765e-05, "loss": 0.553, "step": 664 }, { "epoch": 0.71, "learning_rate": 1.8017251648796216e-05, "loss": 0.5324, "step": 665 }, { "epoch": 0.71, "learning_rate": 1.801030976251108e-05, "loss": 0.538, "step": 666 }, { "epoch": 0.71, "learning_rate": 1.8003357087442e-05, "loss": 0.5288, "step": 667 }, { "epoch": 0.71, "learning_rate": 1.7996393632953275e-05, "loss": 0.5491, "step": 668 }, { "epoch": 0.71, "learning_rate": 1.7989419408423718e-05, "loss": 0.5286, "step": 669 }, { "epoch": 0.71, "learning_rate": 1.798243442324665e-05, "loss": 0.5763, "step": 670 }, { "epoch": 0.71, "learning_rate": 1.7975438686829884e-05, "loss": 0.4663, "step": 671 }, { "epoch": 0.71, "learning_rate": 1.796843220859571e-05, "loss": 0.5575, "step": 672 }, { "epoch": 0.72, "learning_rate": 1.79614149979809e-05, "loss": 0.5519, "step": 673 }, { "epoch": 0.72, "learning_rate": 1.795438706443666e-05, "loss": 0.6785, "step": 674 }, { "epoch": 0.72, "learning_rate": 1.7947348417428646e-05, "loss": 0.4597, "step": 675 }, { "epoch": 0.72, "learning_rate": 1.7940299066436954e-05, "loss": 0.5359, "step": 676 }, { "epoch": 0.72, "learning_rate": 1.7933239020956083e-05, "loss": 0.5468, "step": 677 }, { "epoch": 0.72, "learning_rate": 1.7926168290494947e-05, "loss": 0.5721, "step": 678 }, { "epoch": 0.72, "learning_rate": 1.7919086884576843e-05, "loss": 0.5516, "step": 679 }, { "epoch": 0.72, "learning_rate": 1.791199481273945e-05, "loss": 0.6756, "step": 680 }, { "epoch": 0.72, "learning_rate": 1.7904892084534813e-05, "loss": 0.5565, "step": 681 }, { "epoch": 0.73, "learning_rate": 1.7897778709529325e-05, "loss": 0.561, "step": 682 }, { "epoch": 0.73, "learning_rate": 1.7890654697303725e-05, "loss": 0.5118, "step": 683 }, { "epoch": 0.73, "learning_rate": 1.788352005745308e-05, "loss": 0.5508, "step": 684 }, { "epoch": 0.73, "learning_rate": 1.787637479958676e-05, "loss": 0.5366, "step": 685 }, { "epoch": 0.73, "learning_rate": 1.7869218933328448e-05, "loss": 0.533, "step": 686 }, { "epoch": 0.73, "learning_rate": 1.7862052468316105e-05, "loss": 0.5621, "step": 687 }, { "epoch": 0.73, "learning_rate": 1.785487541420198e-05, "loss": 0.5343, "step": 688 }, { "epoch": 0.73, "learning_rate": 1.784768778065257e-05, "loss": 0.5993, "step": 689 }, { "epoch": 0.73, "learning_rate": 1.784048957734863e-05, "loss": 0.5823, "step": 690 }, { "epoch": 0.73, "learning_rate": 1.7833280813985147e-05, "loss": 0.5251, "step": 691 }, { "epoch": 0.74, "learning_rate": 1.782606150027134e-05, "loss": 0.4876, "step": 692 }, { "epoch": 0.74, "learning_rate": 1.7818831645930616e-05, "loss": 0.5391, "step": 693 }, { "epoch": 0.74, "learning_rate": 1.7811591260700606e-05, "loss": 0.5439, "step": 694 }, { "epoch": 0.74, "learning_rate": 1.78043403543331e-05, "loss": 0.5697, "step": 695 }, { "epoch": 0.74, "learning_rate": 1.779707893659408e-05, "loss": 0.4911, "step": 696 }, { "epoch": 0.74, "learning_rate": 1.7789807017263673e-05, "loss": 0.5209, "step": 697 }, { "epoch": 0.74, "learning_rate": 1.778252460613615e-05, "loss": 0.6469, "step": 698 }, { "epoch": 0.74, "learning_rate": 1.777523171301992e-05, "loss": 0.5589, "step": 699 }, { "epoch": 0.74, "learning_rate": 1.77679283477375e-05, "loss": 0.5021, "step": 700 }, { "epoch": 0.75, "learning_rate": 1.7760614520125523e-05, "loss": 0.5335, "step": 701 }, { "epoch": 0.75, "learning_rate": 1.77532902400347e-05, "loss": 0.6373, "step": 702 }, { "epoch": 0.75, "learning_rate": 1.7745955517329837e-05, "loss": 0.5524, "step": 703 }, { "epoch": 0.75, "learning_rate": 1.773861036188979e-05, "loss": 0.5466, "step": 704 }, { "epoch": 0.75, "learning_rate": 1.773125478360747e-05, "loss": 0.5246, "step": 705 }, { "epoch": 0.75, "learning_rate": 1.772388879238983e-05, "loss": 0.5911, "step": 706 }, { "epoch": 0.75, "learning_rate": 1.7716512398157847e-05, "loss": 0.523, "step": 707 }, { "epoch": 0.75, "learning_rate": 1.7709125610846502e-05, "loss": 0.5273, "step": 708 }, { "epoch": 0.75, "learning_rate": 1.7701728440404786e-05, "loss": 0.5156, "step": 709 }, { "epoch": 0.76, "learning_rate": 1.7694320896795668e-05, "loss": 0.4983, "step": 710 }, { "epoch": 0.76, "learning_rate": 1.768690298999609e-05, "loss": 0.5558, "step": 711 }, { "epoch": 0.76, "learning_rate": 1.7679474729996946e-05, "loss": 0.6352, "step": 712 }, { "epoch": 0.76, "learning_rate": 1.7672036126803083e-05, "loss": 0.4626, "step": 713 }, { "epoch": 0.76, "learning_rate": 1.7664587190433272e-05, "loss": 0.5393, "step": 714 }, { "epoch": 0.76, "learning_rate": 1.765712793092021e-05, "loss": 0.5035, "step": 715 }, { "epoch": 0.76, "learning_rate": 1.7649658358310485e-05, "loss": 0.5397, "step": 716 }, { "epoch": 0.76, "learning_rate": 1.7642178482664586e-05, "loss": 0.5219, "step": 717 }, { "epoch": 0.76, "learning_rate": 1.7634688314056875e-05, "loss": 0.5129, "step": 718 }, { "epoch": 0.76, "learning_rate": 1.762718786257558e-05, "loss": 0.5436, "step": 719 }, { "epoch": 0.77, "learning_rate": 1.761967713832277e-05, "loss": 0.5219, "step": 720 }, { "epoch": 0.77, "learning_rate": 1.7612156151414366e-05, "loss": 0.5693, "step": 721 }, { "epoch": 0.77, "learning_rate": 1.760462491198009e-05, "loss": 0.5331, "step": 722 }, { "epoch": 0.77, "learning_rate": 1.7597083430163488e-05, "loss": 0.504, "step": 723 }, { "epoch": 0.77, "learning_rate": 1.75895317161219e-05, "loss": 0.5474, "step": 724 }, { "epoch": 0.77, "learning_rate": 1.7581969780026448e-05, "loss": 0.5332, "step": 725 }, { "epoch": 0.77, "learning_rate": 1.7574397632062007e-05, "loss": 0.5075, "step": 726 }, { "epoch": 0.77, "learning_rate": 1.7566815282427226e-05, "loss": 0.5698, "step": 727 }, { "epoch": 0.77, "learning_rate": 1.7559222741334484e-05, "loss": 0.4927, "step": 728 }, { "epoch": 0.78, "learning_rate": 1.7551620019009887e-05, "loss": 0.5693, "step": 729 }, { "epoch": 0.78, "learning_rate": 1.7544007125693258e-05, "loss": 0.5734, "step": 730 }, { "epoch": 0.78, "learning_rate": 1.753638407163811e-05, "loss": 0.5202, "step": 731 }, { "epoch": 0.78, "learning_rate": 1.752875086711165e-05, "loss": 0.6264, "step": 732 }, { "epoch": 0.78, "learning_rate": 1.7521107522394753e-05, "loss": 0.5399, "step": 733 }, { "epoch": 0.78, "learning_rate": 1.7513454047781954e-05, "loss": 0.6222, "step": 734 }, { "epoch": 0.78, "learning_rate": 1.7505790453581427e-05, "loss": 0.6028, "step": 735 }, { "epoch": 0.78, "learning_rate": 1.7498116750114975e-05, "loss": 0.572, "step": 736 }, { "epoch": 0.78, "learning_rate": 1.7490432947718024e-05, "loss": 0.4958, "step": 737 }, { "epoch": 0.78, "learning_rate": 1.7482739056739594e-05, "loss": 0.5231, "step": 738 }, { "epoch": 0.79, "learning_rate": 1.74750350875423e-05, "loss": 0.5709, "step": 739 }, { "epoch": 0.79, "learning_rate": 1.7467321050502322e-05, "loss": 0.5125, "step": 740 }, { "epoch": 0.79, "learning_rate": 1.7459596956009415e-05, "loss": 0.5324, "step": 741 }, { "epoch": 0.79, "learning_rate": 1.745186281446686e-05, "loss": 0.4944, "step": 742 }, { "epoch": 0.79, "learning_rate": 1.7444118636291486e-05, "loss": 0.5172, "step": 743 }, { "epoch": 0.79, "learning_rate": 1.7436364431913636e-05, "loss": 0.5628, "step": 744 }, { "epoch": 0.79, "learning_rate": 1.742860021177715e-05, "loss": 0.5164, "step": 745 }, { "epoch": 0.79, "learning_rate": 1.7420825986339363e-05, "loss": 0.5173, "step": 746 }, { "epoch": 0.79, "learning_rate": 1.741304176607109e-05, "loss": 0.4799, "step": 747 }, { "epoch": 0.8, "learning_rate": 1.7405247561456605e-05, "loss": 0.5249, "step": 748 }, { "epoch": 0.8, "learning_rate": 1.7397443382993623e-05, "loss": 0.4909, "step": 749 }, { "epoch": 0.8, "learning_rate": 1.7389629241193295e-05, "loss": 0.5928, "step": 750 }, { "epoch": 0.8, "learning_rate": 1.7381805146580204e-05, "loss": 0.5239, "step": 751 }, { "epoch": 0.8, "learning_rate": 1.737397110969232e-05, "loss": 0.7112, "step": 752 }, { "epoch": 0.8, "learning_rate": 1.736612714108101e-05, "loss": 0.521, "step": 753 }, { "epoch": 0.8, "learning_rate": 1.7358273251311032e-05, "loss": 0.4943, "step": 754 }, { "epoch": 0.8, "learning_rate": 1.7350409450960474e-05, "loss": 0.5338, "step": 755 }, { "epoch": 0.8, "learning_rate": 1.734253575062081e-05, "loss": 0.5677, "step": 756 }, { "epoch": 0.81, "learning_rate": 1.733465216089682e-05, "loss": 0.5656, "step": 757 }, { "epoch": 0.81, "learning_rate": 1.732675869240662e-05, "loss": 0.5542, "step": 758 }, { "epoch": 0.81, "learning_rate": 1.7318855355781612e-05, "loss": 0.495, "step": 759 }, { "epoch": 0.81, "learning_rate": 1.7310942161666516e-05, "loss": 0.5221, "step": 760 }, { "epoch": 0.81, "learning_rate": 1.7303019120719307e-05, "loss": 0.5112, "step": 761 }, { "epoch": 0.81, "learning_rate": 1.7295086243611238e-05, "loss": 0.5231, "step": 762 }, { "epoch": 0.81, "learning_rate": 1.728714354102679e-05, "loss": 0.6536, "step": 763 }, { "epoch": 0.81, "learning_rate": 1.7279191023663696e-05, "loss": 0.5366, "step": 764 }, { "epoch": 0.81, "learning_rate": 1.72712287022329e-05, "loss": 0.6253, "step": 765 }, { "epoch": 0.81, "learning_rate": 1.726325658745856e-05, "loss": 0.6108, "step": 766 }, { "epoch": 0.82, "learning_rate": 1.7255274690078002e-05, "loss": 0.5274, "step": 767 }, { "epoch": 0.82, "learning_rate": 1.724728302084175e-05, "loss": 0.5868, "step": 768 }, { "epoch": 0.82, "learning_rate": 1.7239281590513486e-05, "loss": 0.7547, "step": 769 }, { "epoch": 0.82, "learning_rate": 1.723127040987003e-05, "loss": 0.5382, "step": 770 }, { "epoch": 0.82, "learning_rate": 1.7223249489701336e-05, "loss": 0.5589, "step": 771 }, { "epoch": 0.82, "learning_rate": 1.7215218840810487e-05, "loss": 0.5189, "step": 772 }, { "epoch": 0.82, "learning_rate": 1.720717847401365e-05, "loss": 0.497, "step": 773 }, { "epoch": 0.82, "learning_rate": 1.7199128400140098e-05, "loss": 0.5329, "step": 774 }, { "epoch": 0.82, "learning_rate": 1.7191068630032174e-05, "loss": 0.4992, "step": 775 }, { "epoch": 0.83, "learning_rate": 1.7182999174545276e-05, "loss": 0.5549, "step": 776 }, { "epoch": 0.83, "learning_rate": 1.7174920044547846e-05, "loss": 0.6635, "step": 777 }, { "epoch": 0.83, "learning_rate": 1.7166831250921365e-05, "loss": 0.5251, "step": 778 }, { "epoch": 0.83, "learning_rate": 1.715873280456032e-05, "loss": 0.5408, "step": 779 }, { "epoch": 0.83, "learning_rate": 1.7150624716372203e-05, "loss": 0.5483, "step": 780 }, { "epoch": 0.83, "learning_rate": 1.714250699727749e-05, "loss": 0.5384, "step": 781 }, { "epoch": 0.83, "learning_rate": 1.7134379658209634e-05, "loss": 0.6286, "step": 782 }, { "epoch": 0.83, "learning_rate": 1.712624271011504e-05, "loss": 0.4468, "step": 783 }, { "epoch": 0.83, "learning_rate": 1.7118096163953056e-05, "loss": 0.5625, "step": 784 }, { "epoch": 0.83, "learning_rate": 1.7109940030695962e-05, "loss": 0.5226, "step": 785 }, { "epoch": 0.84, "learning_rate": 1.710177432132894e-05, "loss": 0.5835, "step": 786 }, { "epoch": 0.84, "learning_rate": 1.709359904685008e-05, "loss": 0.709, "step": 787 }, { "epoch": 0.84, "learning_rate": 1.7085414218270347e-05, "loss": 0.5222, "step": 788 }, { "epoch": 0.84, "learning_rate": 1.707721984661358e-05, "loss": 0.4774, "step": 789 }, { "epoch": 0.84, "learning_rate": 1.706901594291647e-05, "loss": 0.5568, "step": 790 }, { "epoch": 0.84, "learning_rate": 1.706080251822854e-05, "loss": 0.5069, "step": 791 }, { "epoch": 0.84, "learning_rate": 1.7052579583612147e-05, "loss": 0.5838, "step": 792 }, { "epoch": 0.84, "learning_rate": 1.7044347150142452e-05, "loss": 0.4521, "step": 793 }, { "epoch": 0.84, "learning_rate": 1.7036105228907406e-05, "loss": 0.5641, "step": 794 }, { "epoch": 0.85, "learning_rate": 1.7027853831007743e-05, "loss": 0.5685, "step": 795 }, { "epoch": 0.85, "learning_rate": 1.701959296755696e-05, "loss": 0.4648, "step": 796 }, { "epoch": 0.85, "learning_rate": 1.7011322649681302e-05, "loss": 0.536, "step": 797 }, { "epoch": 0.85, "learning_rate": 1.7003042888519745e-05, "loss": 0.538, "step": 798 }, { "epoch": 0.85, "learning_rate": 1.699475369522399e-05, "loss": 0.5402, "step": 799 }, { "epoch": 0.85, "learning_rate": 1.6986455080958438e-05, "loss": 0.6973, "step": 800 }, { "epoch": 0.85, "learning_rate": 1.6978147056900178e-05, "loss": 0.7187, "step": 801 }, { "epoch": 0.85, "learning_rate": 1.6969829634238976e-05, "loss": 0.5279, "step": 802 }, { "epoch": 0.85, "learning_rate": 1.6961502824177256e-05, "loss": 0.6427, "step": 803 }, { "epoch": 0.86, "learning_rate": 1.695316663793008e-05, "loss": 0.5382, "step": 804 }, { "epoch": 0.86, "learning_rate": 1.6944821086725144e-05, "loss": 0.5261, "step": 805 }, { "epoch": 0.86, "learning_rate": 1.693646618180276e-05, "loss": 0.5526, "step": 806 }, { "epoch": 0.86, "learning_rate": 1.692810193441583e-05, "loss": 0.5581, "step": 807 }, { "epoch": 0.86, "learning_rate": 1.6919728355829844e-05, "loss": 0.6219, "step": 808 }, { "epoch": 0.86, "learning_rate": 1.6911345457322865e-05, "loss": 0.556, "step": 809 }, { "epoch": 0.86, "learning_rate": 1.690295325018549e-05, "loss": 0.5438, "step": 810 }, { "epoch": 0.86, "learning_rate": 1.6894551745720876e-05, "loss": 0.5924, "step": 811 }, { "epoch": 0.86, "learning_rate": 1.688614095524469e-05, "loss": 0.5244, "step": 812 }, { "epoch": 0.86, "learning_rate": 1.6877720890085105e-05, "loss": 0.5166, "step": 813 }, { "epoch": 0.87, "learning_rate": 1.6869291561582793e-05, "loss": 0.5085, "step": 814 }, { "epoch": 0.87, "learning_rate": 1.68608529810909e-05, "loss": 0.5495, "step": 815 }, { "epoch": 0.87, "learning_rate": 1.6852405159975025e-05, "loss": 0.4965, "step": 816 }, { "epoch": 0.87, "learning_rate": 1.6843948109613227e-05, "loss": 0.4956, "step": 817 }, { "epoch": 0.87, "learning_rate": 1.683548184139598e-05, "loss": 0.5225, "step": 818 }, { "epoch": 0.87, "learning_rate": 1.6827006366726187e-05, "loss": 0.5458, "step": 819 }, { "epoch": 0.87, "learning_rate": 1.6818521697019146e-05, "loss": 0.4848, "step": 820 }, { "epoch": 0.87, "learning_rate": 1.6810027843702533e-05, "loss": 0.4675, "step": 821 }, { "epoch": 0.87, "learning_rate": 1.6801524818216406e-05, "loss": 0.5848, "step": 822 }, { "epoch": 0.88, "learning_rate": 1.6793012632013162e-05, "loss": 0.5484, "step": 823 }, { "epoch": 0.88, "learning_rate": 1.6784491296557545e-05, "loss": 0.5318, "step": 824 }, { "epoch": 0.88, "learning_rate": 1.677596082332662e-05, "loss": 0.5077, "step": 825 }, { "epoch": 0.88, "learning_rate": 1.6767421223809766e-05, "loss": 0.7089, "step": 826 }, { "epoch": 0.88, "learning_rate": 1.6758872509508637e-05, "loss": 0.5203, "step": 827 }, { "epoch": 0.88, "learning_rate": 1.675031469193718e-05, "loss": 0.5663, "step": 828 }, { "epoch": 0.88, "learning_rate": 1.6741747782621595e-05, "loss": 0.5469, "step": 829 }, { "epoch": 0.88, "learning_rate": 1.673317179310033e-05, "loss": 0.5367, "step": 830 }, { "epoch": 0.88, "learning_rate": 1.672458673492406e-05, "loss": 0.5745, "step": 831 }, { "epoch": 0.88, "learning_rate": 1.671599261965568e-05, "loss": 0.5192, "step": 832 }, { "epoch": 0.89, "learning_rate": 1.6707389458870272e-05, "loss": 0.6867, "step": 833 }, { "epoch": 0.89, "learning_rate": 1.6698777264155116e-05, "loss": 0.6172, "step": 834 }, { "epoch": 0.89, "learning_rate": 1.6690156047109646e-05, "loss": 0.5296, "step": 835 }, { "epoch": 0.89, "learning_rate": 1.6681525819345457e-05, "loss": 0.4904, "step": 836 }, { "epoch": 0.89, "learning_rate": 1.6672886592486278e-05, "loss": 0.5134, "step": 837 }, { "epoch": 0.89, "learning_rate": 1.666423837816796e-05, "loss": 0.5938, "step": 838 }, { "epoch": 0.89, "learning_rate": 1.6655581188038446e-05, "loss": 0.4842, "step": 839 }, { "epoch": 0.89, "learning_rate": 1.664691503375779e-05, "loss": 0.5007, "step": 840 }, { "epoch": 0.89, "learning_rate": 1.6638239926998105e-05, "loss": 0.4913, "step": 841 }, { "epoch": 0.9, "learning_rate": 1.6629555879443563e-05, "loss": 0.5448, "step": 842 }, { "epoch": 0.9, "learning_rate": 1.662086290279038e-05, "loss": 0.5035, "step": 843 }, { "epoch": 0.9, "learning_rate": 1.6612161008746798e-05, "loss": 0.4952, "step": 844 }, { "epoch": 0.9, "learning_rate": 1.6603450209033072e-05, "loss": 0.5286, "step": 845 }, { "epoch": 0.9, "learning_rate": 1.6594730515381446e-05, "loss": 0.4992, "step": 846 }, { "epoch": 0.9, "learning_rate": 1.6586001939536155e-05, "loss": 0.6832, "step": 847 }, { "epoch": 0.9, "learning_rate": 1.6577264493253377e-05, "loss": 0.4658, "step": 848 }, { "epoch": 0.9, "learning_rate": 1.6568518188301253e-05, "loss": 0.4912, "step": 849 }, { "epoch": 0.9, "learning_rate": 1.6559763036459855e-05, "loss": 0.6174, "step": 850 }, { "epoch": 0.91, "learning_rate": 1.6550999049521163e-05, "loss": 0.5091, "step": 851 }, { "epoch": 0.91, "learning_rate": 1.6542226239289057e-05, "loss": 0.7002, "step": 852 }, { "epoch": 0.91, "learning_rate": 1.653344461757931e-05, "loss": 0.5327, "step": 853 }, { "epoch": 0.91, "learning_rate": 1.6524654196219555e-05, "loss": 0.4974, "step": 854 }, { "epoch": 0.91, "learning_rate": 1.651585498704928e-05, "loss": 0.5408, "step": 855 }, { "epoch": 0.91, "learning_rate": 1.6507047001919802e-05, "loss": 0.568, "step": 856 }, { "epoch": 0.91, "learning_rate": 1.6498230252694268e-05, "loss": 0.5481, "step": 857 }, { "epoch": 0.91, "learning_rate": 1.648940475124763e-05, "loss": 0.5671, "step": 858 }, { "epoch": 0.91, "learning_rate": 1.6480570509466615e-05, "loss": 0.5193, "step": 859 }, { "epoch": 0.91, "learning_rate": 1.647172753924973e-05, "loss": 0.5885, "step": 860 }, { "epoch": 0.92, "learning_rate": 1.646287585250724e-05, "loss": 0.5629, "step": 861 }, { "epoch": 0.92, "learning_rate": 1.6454015461161152e-05, "loss": 0.5337, "step": 862 }, { "epoch": 0.92, "learning_rate": 1.644514637714519e-05, "loss": 0.544, "step": 863 }, { "epoch": 0.92, "learning_rate": 1.6436268612404783e-05, "loss": 0.5489, "step": 864 }, { "epoch": 0.92, "learning_rate": 1.6427382178897064e-05, "loss": 0.4853, "step": 865 }, { "epoch": 0.92, "learning_rate": 1.6418487088590834e-05, "loss": 0.6271, "step": 866 }, { "epoch": 0.92, "learning_rate": 1.6409583353466554e-05, "loss": 0.4912, "step": 867 }, { "epoch": 0.92, "learning_rate": 1.6400670985516324e-05, "loss": 0.5272, "step": 868 }, { "epoch": 0.92, "learning_rate": 1.6391749996743884e-05, "loss": 0.5627, "step": 869 }, { "epoch": 0.93, "learning_rate": 1.638282039916457e-05, "loss": 0.5611, "step": 870 }, { "epoch": 0.93, "learning_rate": 1.6373882204805326e-05, "loss": 0.5757, "step": 871 }, { "epoch": 0.93, "learning_rate": 1.6364935425704667e-05, "loss": 0.5608, "step": 872 }, { "epoch": 0.93, "learning_rate": 1.635598007391267e-05, "loss": 0.519, "step": 873 }, { "epoch": 0.93, "learning_rate": 1.634701616149096e-05, "loss": 0.5568, "step": 874 }, { "epoch": 0.93, "learning_rate": 1.63380437005127e-05, "loss": 0.434, "step": 875 }, { "epoch": 0.93, "learning_rate": 1.6329062703062546e-05, "loss": 0.4801, "step": 876 }, { "epoch": 0.93, "learning_rate": 1.6320073181236674e-05, "loss": 0.5309, "step": 877 }, { "epoch": 0.93, "learning_rate": 1.631107514714273e-05, "loss": 0.5528, "step": 878 }, { "epoch": 0.93, "learning_rate": 1.6302068612899827e-05, "loss": 0.4957, "step": 879 }, { "epoch": 0.94, "learning_rate": 1.629305359063852e-05, "loss": 0.5037, "step": 880 }, { "epoch": 0.94, "learning_rate": 1.6284030092500813e-05, "loss": 0.5498, "step": 881 }, { "epoch": 0.94, "learning_rate": 1.6274998130640108e-05, "loss": 0.5129, "step": 882 }, { "epoch": 0.94, "learning_rate": 1.6265957717221213e-05, "loss": 0.5202, "step": 883 }, { "epoch": 0.94, "learning_rate": 1.6256908864420323e-05, "loss": 0.5177, "step": 884 }, { "epoch": 0.94, "learning_rate": 1.6247851584424995e-05, "loss": 0.4835, "step": 885 }, { "epoch": 0.94, "learning_rate": 1.623878588943414e-05, "loss": 0.5914, "step": 886 }, { "epoch": 0.94, "learning_rate": 1.6229711791657997e-05, "loss": 0.5489, "step": 887 }, { "epoch": 0.94, "learning_rate": 1.622062930331813e-05, "loss": 0.5761, "step": 888 }, { "epoch": 0.95, "learning_rate": 1.6211538436647388e-05, "loss": 0.5076, "step": 889 }, { "epoch": 0.95, "learning_rate": 1.620243920388993e-05, "loss": 0.4796, "step": 890 }, { "epoch": 0.95, "learning_rate": 1.6193331617301167e-05, "loss": 0.5646, "step": 891 }, { "epoch": 0.95, "learning_rate": 1.618421568914776e-05, "loss": 0.6006, "step": 892 }, { "epoch": 0.95, "learning_rate": 1.6175091431707607e-05, "loss": 0.5087, "step": 893 }, { "epoch": 0.95, "learning_rate": 1.616595885726983e-05, "loss": 0.5521, "step": 894 }, { "epoch": 0.95, "learning_rate": 1.615681797813475e-05, "loss": 0.4847, "step": 895 }, { "epoch": 0.95, "learning_rate": 1.614766880661387e-05, "loss": 0.5311, "step": 896 }, { "epoch": 0.95, "learning_rate": 1.6138511355029857e-05, "loss": 0.6208, "step": 897 }, { "epoch": 0.96, "learning_rate": 1.6129345635716555e-05, "loss": 0.5463, "step": 898 }, { "epoch": 0.96, "learning_rate": 1.6120171661018904e-05, "loss": 0.4958, "step": 899 }, { "epoch": 0.96, "learning_rate": 1.6110989443292998e-05, "loss": 0.5406, "step": 900 }, { "epoch": 0.96, "learning_rate": 1.6101798994906018e-05, "loss": 0.4674, "step": 901 }, { "epoch": 0.96, "learning_rate": 1.6092600328236227e-05, "loss": 0.4756, "step": 902 }, { "epoch": 0.96, "learning_rate": 1.6083393455672965e-05, "loss": 0.5513, "step": 903 }, { "epoch": 0.96, "learning_rate": 1.6074178389616625e-05, "loss": 0.6024, "step": 904 }, { "epoch": 0.96, "learning_rate": 1.6064955142478626e-05, "loss": 0.5512, "step": 905 }, { "epoch": 0.96, "learning_rate": 1.6055723726681413e-05, "loss": 0.6124, "step": 906 }, { "epoch": 0.96, "learning_rate": 1.604648415465843e-05, "loss": 0.5203, "step": 907 }, { "epoch": 0.97, "learning_rate": 1.6037236438854114e-05, "loss": 0.5789, "step": 908 }, { "epoch": 0.97, "learning_rate": 1.6027980591723856e-05, "loss": 0.5147, "step": 909 }, { "epoch": 0.97, "learning_rate": 1.6018716625734016e-05, "loss": 0.5192, "step": 910 }, { "epoch": 0.97, "learning_rate": 1.6009444553361878e-05, "loss": 0.4505, "step": 911 }, { "epoch": 0.97, "learning_rate": 1.600016438709564e-05, "loss": 0.5322, "step": 912 }, { "epoch": 0.97, "learning_rate": 1.5990876139434414e-05, "loss": 0.5092, "step": 913 }, { "epoch": 0.97, "learning_rate": 1.5981579822888187e-05, "loss": 0.5077, "step": 914 }, { "epoch": 0.97, "learning_rate": 1.5972275449977818e-05, "loss": 0.4966, "step": 915 }, { "epoch": 0.97, "learning_rate": 1.5962963033235016e-05, "loss": 0.4785, "step": 916 }, { "epoch": 0.98, "learning_rate": 1.5953642585202325e-05, "loss": 0.5444, "step": 917 }, { "epoch": 0.98, "learning_rate": 1.5944314118433103e-05, "loss": 0.4847, "step": 918 }, { "epoch": 0.98, "learning_rate": 1.5934977645491513e-05, "loss": 0.5098, "step": 919 }, { "epoch": 0.98, "learning_rate": 1.592563317895249e-05, "loss": 0.4987, "step": 920 }, { "epoch": 0.98, "learning_rate": 1.5916280731401753e-05, "loss": 0.5476, "step": 921 }, { "epoch": 0.98, "learning_rate": 1.5906920315435757e-05, "loss": 0.5363, "step": 922 }, { "epoch": 0.98, "learning_rate": 1.589755194366169e-05, "loss": 0.4571, "step": 923 }, { "epoch": 0.98, "learning_rate": 1.5888175628697462e-05, "loss": 0.5176, "step": 924 }, { "epoch": 0.98, "learning_rate": 1.5878791383171678e-05, "loss": 0.548, "step": 925 }, { "epoch": 0.98, "learning_rate": 1.586939921972362e-05, "loss": 0.5262, "step": 926 }, { "epoch": 0.99, "learning_rate": 1.5859999151003245e-05, "loss": 0.593, "step": 927 }, { "epoch": 0.99, "learning_rate": 1.5850591189671144e-05, "loss": 0.5034, "step": 928 }, { "epoch": 0.99, "learning_rate": 1.584117534839855e-05, "loss": 0.5248, "step": 929 }, { "epoch": 0.99, "learning_rate": 1.5831751639867302e-05, "loss": 0.5514, "step": 930 }, { "epoch": 0.99, "learning_rate": 1.582232007676984e-05, "loss": 0.5488, "step": 931 }, { "epoch": 0.99, "learning_rate": 1.5812880671809177e-05, "loss": 0.5551, "step": 932 }, { "epoch": 0.99, "learning_rate": 1.580343343769889e-05, "loss": 0.6783, "step": 933 }, { "epoch": 0.99, "learning_rate": 1.579397838716311e-05, "loss": 0.5302, "step": 934 }, { "epoch": 0.99, "learning_rate": 1.578451553293648e-05, "loss": 0.5156, "step": 935 }, { "epoch": 1.0, "learning_rate": 1.577504488776416e-05, "loss": 0.5165, "step": 936 }, { "epoch": 1.0, "learning_rate": 1.5765566464401816e-05, "loss": 0.5112, "step": 937 }, { "epoch": 1.0, "learning_rate": 1.575608027561557e-05, "loss": 0.6636, "step": 938 }, { "epoch": 1.0, "learning_rate": 1.574658633418201e-05, "loss": 0.5325, "step": 939 }, { "epoch": 1.0, "learning_rate": 1.5737084652888173e-05, "loss": 0.5981, "step": 940 }, { "epoch": 1.0, "learning_rate": 1.572757524453151e-05, "loss": 0.4923, "step": 941 }, { "epoch": 1.0, "learning_rate": 1.571805812191989e-05, "loss": 0.3966, "step": 942 }, { "epoch": 1.0, "learning_rate": 1.570853329787156e-05, "loss": 0.4132, "step": 943 }, { "epoch": 1.0, "learning_rate": 1.569900078521515e-05, "loss": 0.428, "step": 944 }, { "epoch": 1.01, "learning_rate": 1.568946059678964e-05, "loss": 0.3906, "step": 945 }, { "epoch": 1.01, "learning_rate": 1.5679912745444354e-05, "loss": 0.4032, "step": 946 }, { "epoch": 1.01, "learning_rate": 1.5670357244038924e-05, "loss": 0.4191, "step": 947 }, { "epoch": 1.01, "learning_rate": 1.56607941054433e-05, "loss": 0.389, "step": 948 }, { "epoch": 1.01, "learning_rate": 1.5651223342537718e-05, "loss": 0.5675, "step": 949 }, { "epoch": 1.01, "learning_rate": 1.564164496821267e-05, "loss": 0.504, "step": 950 }, { "epoch": 1.01, "learning_rate": 1.5632058995368905e-05, "loss": 0.3884, "step": 951 }, { "epoch": 1.01, "learning_rate": 1.5622465436917408e-05, "loss": 0.4324, "step": 952 }, { "epoch": 1.01, "learning_rate": 1.5612864305779388e-05, "loss": 0.4445, "step": 953 }, { "epoch": 1.01, "learning_rate": 1.5603255614886245e-05, "loss": 0.3858, "step": 954 }, { "epoch": 1.02, "learning_rate": 1.5593639377179556e-05, "loss": 0.4127, "step": 955 }, { "epoch": 1.02, "learning_rate": 1.5584015605611074e-05, "loss": 0.4207, "step": 956 }, { "epoch": 1.02, "learning_rate": 1.557438431314269e-05, "loss": 0.4546, "step": 957 }, { "epoch": 1.02, "learning_rate": 1.556474551274643e-05, "loss": 0.3792, "step": 958 }, { "epoch": 1.02, "learning_rate": 1.5555099217404433e-05, "loss": 0.4031, "step": 959 }, { "epoch": 1.02, "learning_rate": 1.554544544010893e-05, "loss": 0.5332, "step": 960 }, { "epoch": 1.02, "learning_rate": 1.5535784193862224e-05, "loss": 0.4203, "step": 961 }, { "epoch": 1.02, "learning_rate": 1.5526115491676688e-05, "loss": 0.4272, "step": 962 }, { "epoch": 1.02, "learning_rate": 1.551643934657473e-05, "loss": 0.398, "step": 963 }, { "epoch": 1.03, "learning_rate": 1.5506755771588785e-05, "loss": 0.398, "step": 964 }, { "epoch": 1.03, "learning_rate": 1.5497064779761295e-05, "loss": 0.444, "step": 965 }, { "epoch": 1.03, "learning_rate": 1.5487366384144692e-05, "loss": 0.393, "step": 966 }, { "epoch": 1.03, "learning_rate": 1.5477660597801376e-05, "loss": 0.4155, "step": 967 }, { "epoch": 1.03, "learning_rate": 1.546794743380371e-05, "loss": 0.4606, "step": 968 }, { "epoch": 1.03, "learning_rate": 1.5458226905233985e-05, "loss": 0.5266, "step": 969 }, { "epoch": 1.03, "learning_rate": 1.544849902518441e-05, "loss": 0.4408, "step": 970 }, { "epoch": 1.03, "learning_rate": 1.5438763806757107e-05, "loss": 0.4237, "step": 971 }, { "epoch": 1.03, "learning_rate": 1.5429021263064064e-05, "loss": 0.3957, "step": 972 }, { "epoch": 1.03, "learning_rate": 1.541927140722716e-05, "loss": 0.4377, "step": 973 }, { "epoch": 1.04, "learning_rate": 1.54095142523781e-05, "loss": 0.4108, "step": 974 }, { "epoch": 1.04, "learning_rate": 1.539974981165842e-05, "loss": 0.4406, "step": 975 }, { "epoch": 1.04, "learning_rate": 1.538997809821949e-05, "loss": 0.3846, "step": 976 }, { "epoch": 1.04, "learning_rate": 1.5380199125222454e-05, "loss": 0.4138, "step": 977 }, { "epoch": 1.04, "learning_rate": 1.5370412905838244e-05, "loss": 0.5289, "step": 978 }, { "epoch": 1.04, "learning_rate": 1.5360619453247556e-05, "loss": 0.4356, "step": 979 }, { "epoch": 1.04, "learning_rate": 1.535081878064081e-05, "loss": 0.4061, "step": 980 }, { "epoch": 1.04, "learning_rate": 1.534101090121817e-05, "loss": 0.4284, "step": 981 }, { "epoch": 1.04, "learning_rate": 1.5331195828189493e-05, "loss": 0.4583, "step": 982 }, { "epoch": 1.05, "learning_rate": 1.5321373574774337e-05, "loss": 0.3998, "step": 983 }, { "epoch": 1.05, "learning_rate": 1.531154415420192e-05, "loss": 0.4348, "step": 984 }, { "epoch": 1.05, "learning_rate": 1.530170757971112e-05, "loss": 0.4586, "step": 985 }, { "epoch": 1.05, "learning_rate": 1.5291863864550443e-05, "loss": 0.4363, "step": 986 }, { "epoch": 1.05, "learning_rate": 1.5282013021978028e-05, "loss": 0.3806, "step": 987 }, { "epoch": 1.05, "learning_rate": 1.5272155065261588e-05, "loss": 0.4248, "step": 988 }, { "epoch": 1.05, "learning_rate": 1.5262290007678446e-05, "loss": 0.4397, "step": 989 }, { "epoch": 1.05, "learning_rate": 1.5252417862515473e-05, "loss": 0.4238, "step": 990 }, { "epoch": 1.05, "learning_rate": 1.5242538643069085e-05, "loss": 0.4447, "step": 991 }, { "epoch": 1.06, "learning_rate": 1.5232652362645231e-05, "loss": 0.5165, "step": 992 }, { "epoch": 1.06, "learning_rate": 1.5222759034559368e-05, "loss": 0.435, "step": 993 }, { "epoch": 1.06, "learning_rate": 1.5212858672136452e-05, "loss": 0.4133, "step": 994 }, { "epoch": 1.06, "learning_rate": 1.5202951288710903e-05, "loss": 0.4049, "step": 995 }, { "epoch": 1.06, "learning_rate": 1.5193036897626603e-05, "loss": 0.3693, "step": 996 }, { "epoch": 1.06, "learning_rate": 1.518311551223687e-05, "loss": 0.3908, "step": 997 }, { "epoch": 1.06, "learning_rate": 1.5173187145904444e-05, "loss": 0.4375, "step": 998 }, { "epoch": 1.06, "learning_rate": 1.516325181200147e-05, "loss": 0.4131, "step": 999 }, { "epoch": 1.06, "learning_rate": 1.5153309523909467e-05, "loss": 0.49, "step": 1000 }, { "epoch": 1.06, "learning_rate": 1.5143360295019333e-05, "loss": 0.4173, "step": 1001 }, { "epoch": 1.07, "learning_rate": 1.5133404138731314e-05, "loss": 0.415, "step": 1002 }, { "epoch": 1.07, "learning_rate": 1.5123441068454967e-05, "loss": 0.4337, "step": 1003 }, { "epoch": 1.07, "learning_rate": 1.511347109760919e-05, "loss": 0.4433, "step": 1004 }, { "epoch": 1.07, "learning_rate": 1.5103494239622154e-05, "loss": 0.4171, "step": 1005 }, { "epoch": 1.07, "learning_rate": 1.5093510507931309e-05, "loss": 0.3792, "step": 1006 }, { "epoch": 1.07, "learning_rate": 1.5083519915983373e-05, "loss": 0.4252, "step": 1007 }, { "epoch": 1.07, "learning_rate": 1.5073522477234294e-05, "loss": 0.4432, "step": 1008 }, { "epoch": 1.07, "learning_rate": 1.5063518205149245e-05, "loss": 0.4348, "step": 1009 }, { "epoch": 1.07, "learning_rate": 1.5053507113202606e-05, "loss": 0.4285, "step": 1010 }, { "epoch": 1.08, "learning_rate": 1.5043489214877933e-05, "loss": 0.41, "step": 1011 }, { "epoch": 1.08, "learning_rate": 1.5033464523667958e-05, "loss": 0.4361, "step": 1012 }, { "epoch": 1.08, "learning_rate": 1.502343305307456e-05, "loss": 0.3979, "step": 1013 }, { "epoch": 1.08, "learning_rate": 1.501339481660875e-05, "loss": 0.4028, "step": 1014 }, { "epoch": 1.08, "learning_rate": 1.5003349827790646e-05, "loss": 0.5147, "step": 1015 }, { "epoch": 1.08, "learning_rate": 1.4993298100149468e-05, "loss": 0.4364, "step": 1016 }, { "epoch": 1.08, "learning_rate": 1.4983239647223504e-05, "loss": 0.3967, "step": 1017 }, { "epoch": 1.08, "learning_rate": 1.4973174482560106e-05, "loss": 0.552, "step": 1018 }, { "epoch": 1.08, "learning_rate": 1.496310261971567e-05, "loss": 0.3922, "step": 1019 }, { "epoch": 1.08, "learning_rate": 1.4953024072255601e-05, "loss": 0.4248, "step": 1020 }, { "epoch": 1.09, "learning_rate": 1.4942938853754321e-05, "loss": 0.3769, "step": 1021 }, { "epoch": 1.09, "learning_rate": 1.4932846977795223e-05, "loss": 0.5364, "step": 1022 }, { "epoch": 1.09, "learning_rate": 1.4922748457970679e-05, "loss": 0.3814, "step": 1023 }, { "epoch": 1.09, "learning_rate": 1.4912643307882e-05, "loss": 0.4517, "step": 1024 }, { "epoch": 1.09, "learning_rate": 1.4902531541139436e-05, "loss": 0.3848, "step": 1025 }, { "epoch": 1.09, "learning_rate": 1.4892413171362142e-05, "loss": 0.4025, "step": 1026 }, { "epoch": 1.09, "learning_rate": 1.4882288212178167e-05, "loss": 0.4945, "step": 1027 }, { "epoch": 1.09, "learning_rate": 1.4872156677224437e-05, "loss": 0.3878, "step": 1028 }, { "epoch": 1.09, "learning_rate": 1.4862018580146735e-05, "loss": 0.3879, "step": 1029 }, { "epoch": 1.1, "learning_rate": 1.4851873934599683e-05, "loss": 0.4477, "step": 1030 }, { "epoch": 1.1, "learning_rate": 1.484172275424672e-05, "loss": 0.4324, "step": 1031 }, { "epoch": 1.1, "learning_rate": 1.4831565052760084e-05, "loss": 0.3965, "step": 1032 }, { "epoch": 1.1, "learning_rate": 1.4821400843820805e-05, "loss": 0.4032, "step": 1033 }, { "epoch": 1.1, "learning_rate": 1.481123014111867e-05, "loss": 0.4317, "step": 1034 }, { "epoch": 1.1, "learning_rate": 1.4801052958352218e-05, "loss": 0.423, "step": 1035 }, { "epoch": 1.1, "learning_rate": 1.4790869309228706e-05, "loss": 0.3985, "step": 1036 }, { "epoch": 1.1, "learning_rate": 1.4780679207464113e-05, "loss": 0.3973, "step": 1037 }, { "epoch": 1.1, "learning_rate": 1.4770482666783097e-05, "loss": 0.4571, "step": 1038 }, { "epoch": 1.11, "learning_rate": 1.4760279700918997e-05, "loss": 0.5185, "step": 1039 }, { "epoch": 1.11, "learning_rate": 1.4750070323613807e-05, "loss": 0.462, "step": 1040 }, { "epoch": 1.11, "learning_rate": 1.4739854548618143e-05, "loss": 0.3822, "step": 1041 }, { "epoch": 1.11, "learning_rate": 1.4729632389691253e-05, "loss": 0.4602, "step": 1042 }, { "epoch": 1.11, "learning_rate": 1.4719403860600973e-05, "loss": 0.4142, "step": 1043 }, { "epoch": 1.11, "learning_rate": 1.4709168975123726e-05, "loss": 0.3875, "step": 1044 }, { "epoch": 1.11, "learning_rate": 1.4698927747044499e-05, "loss": 0.4049, "step": 1045 }, { "epoch": 1.11, "learning_rate": 1.4688680190156799e-05, "loss": 0.4243, "step": 1046 }, { "epoch": 1.11, "learning_rate": 1.4678426318262689e-05, "loss": 0.4449, "step": 1047 }, { "epoch": 1.11, "learning_rate": 1.4668166145172716e-05, "loss": 0.4267, "step": 1048 }, { "epoch": 1.12, "learning_rate": 1.4657899684705918e-05, "loss": 0.5222, "step": 1049 }, { "epoch": 1.12, "learning_rate": 1.464762695068981e-05, "loss": 0.4836, "step": 1050 }, { "epoch": 1.12, "learning_rate": 1.4637347956960344e-05, "loss": 0.3886, "step": 1051 }, { "epoch": 1.12, "learning_rate": 1.4627062717361909e-05, "loss": 0.445, "step": 1052 }, { "epoch": 1.12, "learning_rate": 1.461677124574731e-05, "loss": 0.4068, "step": 1053 }, { "epoch": 1.12, "learning_rate": 1.4606473555977737e-05, "loss": 0.4153, "step": 1054 }, { "epoch": 1.12, "learning_rate": 1.4596169661922761e-05, "loss": 0.4198, "step": 1055 }, { "epoch": 1.12, "learning_rate": 1.4585859577460312e-05, "loss": 0.4111, "step": 1056 }, { "epoch": 1.12, "learning_rate": 1.457554331647665e-05, "loss": 0.4712, "step": 1057 }, { "epoch": 1.13, "learning_rate": 1.4565220892866358e-05, "loss": 0.5762, "step": 1058 }, { "epoch": 1.13, "learning_rate": 1.4554892320532319e-05, "loss": 0.4183, "step": 1059 }, { "epoch": 1.13, "learning_rate": 1.4544557613385699e-05, "loss": 0.4252, "step": 1060 }, { "epoch": 1.13, "learning_rate": 1.4534216785345922e-05, "loss": 0.5408, "step": 1061 }, { "epoch": 1.13, "learning_rate": 1.4523869850340662e-05, "loss": 0.4369, "step": 1062 }, { "epoch": 1.13, "learning_rate": 1.4513516822305814e-05, "loss": 0.3915, "step": 1063 }, { "epoch": 1.13, "learning_rate": 1.4503157715185479e-05, "loss": 0.3785, "step": 1064 }, { "epoch": 1.13, "learning_rate": 1.4492792542931949e-05, "loss": 0.4709, "step": 1065 }, { "epoch": 1.13, "learning_rate": 1.4482421319505684e-05, "loss": 0.432, "step": 1066 }, { "epoch": 1.13, "learning_rate": 1.4472044058875297e-05, "loss": 0.3963, "step": 1067 }, { "epoch": 1.14, "learning_rate": 1.4461660775017521e-05, "loss": 0.392, "step": 1068 }, { "epoch": 1.14, "learning_rate": 1.4451271481917212e-05, "loss": 0.5089, "step": 1069 }, { "epoch": 1.14, "learning_rate": 1.4440876193567319e-05, "loss": 0.4101, "step": 1070 }, { "epoch": 1.14, "learning_rate": 1.4430474923968862e-05, "loss": 0.4212, "step": 1071 }, { "epoch": 1.14, "learning_rate": 1.442006768713092e-05, "loss": 0.4186, "step": 1072 }, { "epoch": 1.14, "learning_rate": 1.4409654497070609e-05, "loss": 0.4728, "step": 1073 }, { "epoch": 1.14, "learning_rate": 1.4399235367813056e-05, "loss": 0.5061, "step": 1074 }, { "epoch": 1.14, "learning_rate": 1.4388810313391395e-05, "loss": 0.4501, "step": 1075 }, { "epoch": 1.14, "learning_rate": 1.4378379347846743e-05, "loss": 0.3491, "step": 1076 }, { "epoch": 1.15, "learning_rate": 1.4367942485228169e-05, "loss": 0.4214, "step": 1077 }, { "epoch": 1.15, "learning_rate": 1.4357499739592691e-05, "loss": 0.3741, "step": 1078 }, { "epoch": 1.15, "learning_rate": 1.4347051125005249e-05, "loss": 0.4191, "step": 1079 }, { "epoch": 1.15, "learning_rate": 1.4336596655538686e-05, "loss": 0.4109, "step": 1080 }, { "epoch": 1.15, "learning_rate": 1.4326136345273738e-05, "loss": 0.4407, "step": 1081 }, { "epoch": 1.15, "learning_rate": 1.4315670208298995e-05, "loss": 0.4061, "step": 1082 }, { "epoch": 1.15, "learning_rate": 1.4305198258710906e-05, "loss": 0.4287, "step": 1083 }, { "epoch": 1.15, "learning_rate": 1.4294720510613745e-05, "loss": 0.4262, "step": 1084 }, { "epoch": 1.15, "learning_rate": 1.428423697811959e-05, "loss": 0.4874, "step": 1085 }, { "epoch": 1.16, "learning_rate": 1.4273747675348326e-05, "loss": 0.444, "step": 1086 }, { "epoch": 1.16, "learning_rate": 1.426325261642759e-05, "loss": 0.5176, "step": 1087 }, { "epoch": 1.16, "learning_rate": 1.4252751815492782e-05, "loss": 0.3972, "step": 1088 }, { "epoch": 1.16, "learning_rate": 1.424224528668704e-05, "loss": 0.4165, "step": 1089 }, { "epoch": 1.16, "learning_rate": 1.4231733044161203e-05, "loss": 0.3969, "step": 1090 }, { "epoch": 1.16, "learning_rate": 1.4221215102073823e-05, "loss": 0.3912, "step": 1091 }, { "epoch": 1.16, "learning_rate": 1.421069147459111e-05, "loss": 0.3779, "step": 1092 }, { "epoch": 1.16, "learning_rate": 1.4200162175886947e-05, "loss": 0.4422, "step": 1093 }, { "epoch": 1.16, "learning_rate": 1.4189627220142848e-05, "loss": 0.4044, "step": 1094 }, { "epoch": 1.16, "learning_rate": 1.4179086621547945e-05, "loss": 0.4153, "step": 1095 }, { "epoch": 1.17, "learning_rate": 1.4168540394298974e-05, "loss": 0.4164, "step": 1096 }, { "epoch": 1.17, "learning_rate": 1.415798855260025e-05, "loss": 0.4375, "step": 1097 }, { "epoch": 1.17, "learning_rate": 1.4147431110663654e-05, "loss": 0.4309, "step": 1098 }, { "epoch": 1.17, "learning_rate": 1.41368680827086e-05, "loss": 0.4323, "step": 1099 }, { "epoch": 1.17, "learning_rate": 1.4126299482962038e-05, "loss": 0.4217, "step": 1100 }, { "epoch": 1.17, "learning_rate": 1.4115725325658411e-05, "loss": 0.5259, "step": 1101 }, { "epoch": 1.17, "learning_rate": 1.4105145625039654e-05, "loss": 0.4113, "step": 1102 }, { "epoch": 1.17, "learning_rate": 1.4094560395355169e-05, "loss": 0.4583, "step": 1103 }, { "epoch": 1.17, "learning_rate": 1.4083969650861797e-05, "loss": 0.3966, "step": 1104 }, { "epoch": 1.18, "learning_rate": 1.4073373405823818e-05, "loss": 0.3849, "step": 1105 }, { "epoch": 1.18, "learning_rate": 1.406277167451291e-05, "loss": 0.426, "step": 1106 }, { "epoch": 1.18, "learning_rate": 1.405216447120815e-05, "loss": 0.4654, "step": 1107 }, { "epoch": 1.18, "learning_rate": 1.4041551810195974e-05, "loss": 0.3904, "step": 1108 }, { "epoch": 1.18, "learning_rate": 1.403093370577018e-05, "loss": 0.4204, "step": 1109 }, { "epoch": 1.18, "learning_rate": 1.402031017223189e-05, "loss": 0.4225, "step": 1110 }, { "epoch": 1.18, "learning_rate": 1.4009681223889535e-05, "loss": 0.4569, "step": 1111 }, { "epoch": 1.18, "learning_rate": 1.3999046875058857e-05, "loss": 0.5438, "step": 1112 }, { "epoch": 1.18, "learning_rate": 1.3988407140062845e-05, "loss": 0.3913, "step": 1113 }, { "epoch": 1.18, "learning_rate": 1.3977762033231765e-05, "loss": 0.4158, "step": 1114 }, { "epoch": 1.19, "learning_rate": 1.3967111568903108e-05, "loss": 0.5221, "step": 1115 }, { "epoch": 1.19, "learning_rate": 1.3956455761421584e-05, "loss": 0.4451, "step": 1116 }, { "epoch": 1.19, "learning_rate": 1.3945794625139097e-05, "loss": 0.4132, "step": 1117 }, { "epoch": 1.19, "learning_rate": 1.3935128174414726e-05, "loss": 0.4149, "step": 1118 }, { "epoch": 1.19, "learning_rate": 1.3924456423614714e-05, "loss": 0.4272, "step": 1119 }, { "epoch": 1.19, "learning_rate": 1.3913779387112439e-05, "loss": 0.4384, "step": 1120 }, { "epoch": 1.19, "learning_rate": 1.3903097079288397e-05, "loss": 0.3973, "step": 1121 }, { "epoch": 1.19, "learning_rate": 1.389240951453019e-05, "loss": 0.4589, "step": 1122 }, { "epoch": 1.19, "learning_rate": 1.3881716707232489e-05, "loss": 0.3996, "step": 1123 }, { "epoch": 1.2, "learning_rate": 1.3871018671797037e-05, "loss": 0.4065, "step": 1124 }, { "epoch": 1.2, "learning_rate": 1.3860315422632615e-05, "loss": 0.4041, "step": 1125 }, { "epoch": 1.2, "learning_rate": 1.384960697415502e-05, "loss": 0.4044, "step": 1126 }, { "epoch": 1.2, "learning_rate": 1.3838893340787065e-05, "loss": 0.4544, "step": 1127 }, { "epoch": 1.2, "learning_rate": 1.3828174536958532e-05, "loss": 0.4279, "step": 1128 }, { "epoch": 1.2, "learning_rate": 1.3817450577106177e-05, "loss": 0.4088, "step": 1129 }, { "epoch": 1.2, "learning_rate": 1.3806721475673697e-05, "loss": 0.4432, "step": 1130 }, { "epoch": 1.2, "learning_rate": 1.3795987247111706e-05, "loss": 0.4282, "step": 1131 }, { "epoch": 1.2, "learning_rate": 1.3785247905877746e-05, "loss": 0.4256, "step": 1132 }, { "epoch": 1.21, "learning_rate": 1.3774503466436216e-05, "loss": 0.4076, "step": 1133 }, { "epoch": 1.21, "learning_rate": 1.3763753943258404e-05, "loss": 0.4236, "step": 1134 }, { "epoch": 1.21, "learning_rate": 1.3752999350822438e-05, "loss": 0.4411, "step": 1135 }, { "epoch": 1.21, "learning_rate": 1.3742239703613266e-05, "loss": 0.4263, "step": 1136 }, { "epoch": 1.21, "learning_rate": 1.373147501612266e-05, "loss": 0.3788, "step": 1137 }, { "epoch": 1.21, "learning_rate": 1.372070530284916e-05, "loss": 0.4339, "step": 1138 }, { "epoch": 1.21, "learning_rate": 1.3709930578298098e-05, "loss": 0.4138, "step": 1139 }, { "epoch": 1.21, "learning_rate": 1.3699150856981536e-05, "loss": 0.4161, "step": 1140 }, { "epoch": 1.21, "learning_rate": 1.3688366153418278e-05, "loss": 0.4673, "step": 1141 }, { "epoch": 1.21, "learning_rate": 1.3677576482133832e-05, "loss": 0.3907, "step": 1142 }, { "epoch": 1.22, "learning_rate": 1.3666781857660396e-05, "loss": 0.4159, "step": 1143 }, { "epoch": 1.22, "learning_rate": 1.3655982294536851e-05, "loss": 0.4775, "step": 1144 }, { "epoch": 1.22, "learning_rate": 1.3645177807308715e-05, "loss": 0.4521, "step": 1145 }, { "epoch": 1.22, "learning_rate": 1.3634368410528145e-05, "loss": 0.3959, "step": 1146 }, { "epoch": 1.22, "learning_rate": 1.362355411875391e-05, "loss": 0.3861, "step": 1147 }, { "epoch": 1.22, "learning_rate": 1.361273494655137e-05, "loss": 0.4912, "step": 1148 }, { "epoch": 1.22, "learning_rate": 1.3601910908492462e-05, "loss": 0.4065, "step": 1149 }, { "epoch": 1.22, "learning_rate": 1.3591082019155674e-05, "loss": 0.3739, "step": 1150 }, { "epoch": 1.22, "learning_rate": 1.358024829312603e-05, "loss": 0.4168, "step": 1151 }, { "epoch": 1.23, "learning_rate": 1.3569409744995063e-05, "loss": 0.4215, "step": 1152 }, { "epoch": 1.23, "learning_rate": 1.3558566389360805e-05, "loss": 0.4405, "step": 1153 }, { "epoch": 1.23, "learning_rate": 1.3547718240827764e-05, "loss": 0.4294, "step": 1154 }, { "epoch": 1.23, "learning_rate": 1.3536865314006903e-05, "loss": 0.4039, "step": 1155 }, { "epoch": 1.23, "learning_rate": 1.3526007623515618e-05, "loss": 0.4255, "step": 1156 }, { "epoch": 1.23, "learning_rate": 1.351514518397772e-05, "loss": 0.4737, "step": 1157 }, { "epoch": 1.23, "learning_rate": 1.3504278010023426e-05, "loss": 0.4208, "step": 1158 }, { "epoch": 1.23, "learning_rate": 1.3493406116289314e-05, "loss": 0.4458, "step": 1159 }, { "epoch": 1.23, "learning_rate": 1.3482529517418334e-05, "loss": 0.4212, "step": 1160 }, { "epoch": 1.23, "learning_rate": 1.3471648228059767e-05, "loss": 0.4086, "step": 1161 }, { "epoch": 1.24, "learning_rate": 1.3460762262869202e-05, "loss": 0.4139, "step": 1162 }, { "epoch": 1.24, "learning_rate": 1.3449871636508547e-05, "loss": 0.4237, "step": 1163 }, { "epoch": 1.24, "learning_rate": 1.3438976363645966e-05, "loss": 0.4194, "step": 1164 }, { "epoch": 1.24, "learning_rate": 1.3428076458955897e-05, "loss": 0.3903, "step": 1165 }, { "epoch": 1.24, "learning_rate": 1.3417171937119004e-05, "loss": 0.404, "step": 1166 }, { "epoch": 1.24, "learning_rate": 1.3406262812822181e-05, "loss": 0.4408, "step": 1167 }, { "epoch": 1.24, "learning_rate": 1.3395349100758519e-05, "loss": 0.4155, "step": 1168 }, { "epoch": 1.24, "learning_rate": 1.3384430815627277e-05, "loss": 0.4416, "step": 1169 }, { "epoch": 1.24, "learning_rate": 1.3373507972133883e-05, "loss": 0.3836, "step": 1170 }, { "epoch": 1.25, "learning_rate": 1.3362580584989908e-05, "loss": 0.4327, "step": 1171 }, { "epoch": 1.25, "learning_rate": 1.3351648668913034e-05, "loss": 0.3867, "step": 1172 }, { "epoch": 1.25, "learning_rate": 1.3340712238627042e-05, "loss": 0.4064, "step": 1173 }, { "epoch": 1.25, "learning_rate": 1.3329771308861804e-05, "loss": 0.4698, "step": 1174 }, { "epoch": 1.25, "learning_rate": 1.3318825894353244e-05, "loss": 0.3914, "step": 1175 }, { "epoch": 1.25, "learning_rate": 1.3307876009843325e-05, "loss": 0.434, "step": 1176 }, { "epoch": 1.25, "learning_rate": 1.3296921670080037e-05, "loss": 0.4476, "step": 1177 }, { "epoch": 1.25, "learning_rate": 1.3285962889817363e-05, "loss": 0.3904, "step": 1178 }, { "epoch": 1.25, "learning_rate": 1.327499968381527e-05, "loss": 0.3843, "step": 1179 }, { "epoch": 1.26, "learning_rate": 1.3264032066839691e-05, "loss": 0.3798, "step": 1180 }, { "epoch": 1.26, "learning_rate": 1.3253060053662494e-05, "loss": 0.4216, "step": 1181 }, { "epoch": 1.26, "learning_rate": 1.3242083659061469e-05, "loss": 0.4297, "step": 1182 }, { "epoch": 1.26, "learning_rate": 1.3231102897820304e-05, "loss": 0.409, "step": 1183 }, { "epoch": 1.26, "learning_rate": 1.3220117784728577e-05, "loss": 0.4103, "step": 1184 }, { "epoch": 1.26, "learning_rate": 1.3209128334581723e-05, "loss": 0.3496, "step": 1185 }, { "epoch": 1.26, "learning_rate": 1.3198134562181011e-05, "loss": 0.4529, "step": 1186 }, { "epoch": 1.26, "learning_rate": 1.3187136482333547e-05, "loss": 0.3739, "step": 1187 }, { "epoch": 1.26, "learning_rate": 1.3176134109852223e-05, "loss": 0.4109, "step": 1188 }, { "epoch": 1.26, "learning_rate": 1.3165127459555722e-05, "loss": 0.4001, "step": 1189 }, { "epoch": 1.27, "learning_rate": 1.3154116546268482e-05, "loss": 0.3822, "step": 1190 }, { "epoch": 1.27, "learning_rate": 1.3143101384820694e-05, "loss": 0.4214, "step": 1191 }, { "epoch": 1.27, "learning_rate": 1.3132081990048257e-05, "loss": 0.4126, "step": 1192 }, { "epoch": 1.27, "learning_rate": 1.3121058376792783e-05, "loss": 0.4112, "step": 1193 }, { "epoch": 1.27, "learning_rate": 1.3110030559901557e-05, "loss": 0.4257, "step": 1194 }, { "epoch": 1.27, "learning_rate": 1.3098998554227529e-05, "loss": 0.535, "step": 1195 }, { "epoch": 1.27, "learning_rate": 1.3087962374629293e-05, "loss": 0.4231, "step": 1196 }, { "epoch": 1.27, "learning_rate": 1.3076922035971062e-05, "loss": 0.4022, "step": 1197 }, { "epoch": 1.27, "learning_rate": 1.3065877553122654e-05, "loss": 0.3846, "step": 1198 }, { "epoch": 1.28, "learning_rate": 1.3054828940959462e-05, "loss": 0.384, "step": 1199 }, { "epoch": 1.28, "learning_rate": 1.304377621436245e-05, "loss": 0.4543, "step": 1200 }, { "epoch": 1.28, "learning_rate": 1.3032719388218114e-05, "loss": 0.6161, "step": 1201 }, { "epoch": 1.28, "learning_rate": 1.3021658477418475e-05, "loss": 0.3898, "step": 1202 }, { "epoch": 1.28, "learning_rate": 1.301059349686106e-05, "loss": 0.3704, "step": 1203 }, { "epoch": 1.28, "learning_rate": 1.2999524461448871e-05, "loss": 0.4287, "step": 1204 }, { "epoch": 1.28, "learning_rate": 1.2988451386090376e-05, "loss": 0.4331, "step": 1205 }, { "epoch": 1.28, "learning_rate": 1.2977374285699483e-05, "loss": 0.4036, "step": 1206 }, { "epoch": 1.28, "learning_rate": 1.2966293175195517e-05, "loss": 0.424, "step": 1207 }, { "epoch": 1.28, "learning_rate": 1.2955208069503208e-05, "loss": 0.4178, "step": 1208 }, { "epoch": 1.29, "learning_rate": 1.2944118983552674e-05, "loss": 0.4011, "step": 1209 }, { "epoch": 1.29, "learning_rate": 1.2933025932279378e-05, "loss": 0.5028, "step": 1210 }, { "epoch": 1.29, "learning_rate": 1.2921928930624134e-05, "loss": 0.3506, "step": 1211 }, { "epoch": 1.29, "learning_rate": 1.2910827993533078e-05, "loss": 0.4734, "step": 1212 }, { "epoch": 1.29, "learning_rate": 1.289972313595764e-05, "loss": 0.3732, "step": 1213 }, { "epoch": 1.29, "learning_rate": 1.2888614372854536e-05, "loss": 0.3696, "step": 1214 }, { "epoch": 1.29, "learning_rate": 1.2877501719185732e-05, "loss": 0.407, "step": 1215 }, { "epoch": 1.29, "learning_rate": 1.2866385189918456e-05, "loss": 0.4516, "step": 1216 }, { "epoch": 1.29, "learning_rate": 1.285526480002513e-05, "loss": 0.3835, "step": 1217 }, { "epoch": 1.3, "learning_rate": 1.2844140564483392e-05, "loss": 0.4044, "step": 1218 }, { "epoch": 1.3, "learning_rate": 1.2833012498276056e-05, "loss": 0.4075, "step": 1219 }, { "epoch": 1.3, "learning_rate": 1.2821880616391089e-05, "loss": 0.358, "step": 1220 }, { "epoch": 1.3, "learning_rate": 1.2810744933821611e-05, "loss": 0.4081, "step": 1221 }, { "epoch": 1.3, "learning_rate": 1.2799605465565848e-05, "loss": 0.3947, "step": 1222 }, { "epoch": 1.3, "learning_rate": 1.2788462226627127e-05, "loss": 0.38, "step": 1223 }, { "epoch": 1.3, "learning_rate": 1.277731523201386e-05, "loss": 0.3879, "step": 1224 }, { "epoch": 1.3, "learning_rate": 1.2766164496739515e-05, "loss": 0.3831, "step": 1225 }, { "epoch": 1.3, "learning_rate": 1.2755010035822588e-05, "loss": 0.436, "step": 1226 }, { "epoch": 1.31, "learning_rate": 1.2743851864286611e-05, "loss": 0.3824, "step": 1227 }, { "epoch": 1.31, "learning_rate": 1.2732689997160102e-05, "loss": 0.4268, "step": 1228 }, { "epoch": 1.31, "learning_rate": 1.2721524449476554e-05, "loss": 0.4141, "step": 1229 }, { "epoch": 1.31, "learning_rate": 1.2710355236274428e-05, "loss": 0.5252, "step": 1230 }, { "epoch": 1.31, "learning_rate": 1.2699182372597108e-05, "loss": 0.4095, "step": 1231 }, { "epoch": 1.31, "learning_rate": 1.268800587349291e-05, "loss": 0.4019, "step": 1232 }, { "epoch": 1.31, "learning_rate": 1.2676825754015037e-05, "loss": 0.3915, "step": 1233 }, { "epoch": 1.31, "learning_rate": 1.2665642029221565e-05, "loss": 0.4553, "step": 1234 }, { "epoch": 1.31, "learning_rate": 1.265445471417544e-05, "loss": 0.3876, "step": 1235 }, { "epoch": 1.31, "learning_rate": 1.2643263823944425e-05, "loss": 0.4864, "step": 1236 }, { "epoch": 1.32, "learning_rate": 1.2632069373601114e-05, "loss": 0.3978, "step": 1237 }, { "epoch": 1.32, "learning_rate": 1.2620871378222888e-05, "loss": 0.4092, "step": 1238 }, { "epoch": 1.32, "learning_rate": 1.2609669852891904e-05, "loss": 0.4321, "step": 1239 }, { "epoch": 1.32, "learning_rate": 1.2598464812695073e-05, "loss": 0.4097, "step": 1240 }, { "epoch": 1.32, "learning_rate": 1.2587256272724042e-05, "loss": 0.3951, "step": 1241 }, { "epoch": 1.32, "learning_rate": 1.2576044248075174e-05, "loss": 0.4426, "step": 1242 }, { "epoch": 1.32, "learning_rate": 1.2564828753849511e-05, "loss": 0.5182, "step": 1243 }, { "epoch": 1.32, "learning_rate": 1.2553609805152793e-05, "loss": 0.4201, "step": 1244 }, { "epoch": 1.32, "learning_rate": 1.254238741709539e-05, "loss": 0.4322, "step": 1245 }, { "epoch": 1.33, "learning_rate": 1.2531161604792312e-05, "loss": 0.4324, "step": 1246 }, { "epoch": 1.33, "learning_rate": 1.251993238336319e-05, "loss": 0.4526, "step": 1247 }, { "epoch": 1.33, "learning_rate": 1.2508699767932227e-05, "loss": 0.368, "step": 1248 }, { "epoch": 1.33, "learning_rate": 1.249746377362822e-05, "loss": 0.4246, "step": 1249 }, { "epoch": 1.33, "learning_rate": 1.24862244155845e-05, "loss": 0.3403, "step": 1250 }, { "epoch": 1.33, "learning_rate": 1.2474981708938931e-05, "loss": 0.3781, "step": 1251 }, { "epoch": 1.33, "learning_rate": 1.2463735668833903e-05, "loss": 0.3989, "step": 1252 }, { "epoch": 1.33, "learning_rate": 1.2452486310416267e-05, "loss": 0.459, "step": 1253 }, { "epoch": 1.33, "learning_rate": 1.244123364883737e-05, "loss": 0.4024, "step": 1254 }, { "epoch": 1.33, "learning_rate": 1.2429977699252993e-05, "loss": 0.4161, "step": 1255 }, { "epoch": 1.34, "learning_rate": 1.241871847682335e-05, "loss": 0.4275, "step": 1256 }, { "epoch": 1.34, "learning_rate": 1.2407455996713069e-05, "loss": 0.3658, "step": 1257 }, { "epoch": 1.34, "learning_rate": 1.2396190274091147e-05, "loss": 0.3645, "step": 1258 }, { "epoch": 1.34, "learning_rate": 1.2384921324130972e-05, "loss": 0.4237, "step": 1259 }, { "epoch": 1.34, "learning_rate": 1.2373649162010262e-05, "loss": 0.446, "step": 1260 }, { "epoch": 1.34, "learning_rate": 1.236237380291107e-05, "loss": 0.5489, "step": 1261 }, { "epoch": 1.34, "learning_rate": 1.2351095262019746e-05, "loss": 0.4309, "step": 1262 }, { "epoch": 1.34, "learning_rate": 1.2339813554526938e-05, "loss": 0.3738, "step": 1263 }, { "epoch": 1.34, "learning_rate": 1.2328528695627548e-05, "loss": 0.3996, "step": 1264 }, { "epoch": 1.35, "learning_rate": 1.2317240700520727e-05, "loss": 0.5374, "step": 1265 }, { "epoch": 1.35, "learning_rate": 1.2305949584409853e-05, "loss": 0.448, "step": 1266 }, { "epoch": 1.35, "learning_rate": 1.2294655362502496e-05, "loss": 0.4084, "step": 1267 }, { "epoch": 1.35, "learning_rate": 1.2283358050010428e-05, "loss": 0.4737, "step": 1268 }, { "epoch": 1.35, "learning_rate": 1.2272057662149563e-05, "loss": 0.4502, "step": 1269 }, { "epoch": 1.35, "learning_rate": 1.2260754214139975e-05, "loss": 0.4108, "step": 1270 }, { "epoch": 1.35, "learning_rate": 1.2249447721205847e-05, "loss": 0.4326, "step": 1271 }, { "epoch": 1.35, "learning_rate": 1.223813819857547e-05, "loss": 0.4544, "step": 1272 }, { "epoch": 1.35, "learning_rate": 1.2226825661481211e-05, "loss": 0.4344, "step": 1273 }, { "epoch": 1.36, "learning_rate": 1.22155101251595e-05, "loss": 0.4284, "step": 1274 }, { "epoch": 1.36, "learning_rate": 1.2204191604850806e-05, "loss": 0.4412, "step": 1275 }, { "epoch": 1.36, "learning_rate": 1.2192870115799618e-05, "loss": 0.3563, "step": 1276 }, { "epoch": 1.36, "learning_rate": 1.2181545673254421e-05, "loss": 0.3862, "step": 1277 }, { "epoch": 1.36, "learning_rate": 1.2170218292467681e-05, "loss": 0.4239, "step": 1278 }, { "epoch": 1.36, "learning_rate": 1.2158887988695815e-05, "loss": 0.4187, "step": 1279 }, { "epoch": 1.36, "learning_rate": 1.2147554777199188e-05, "loss": 0.4378, "step": 1280 }, { "epoch": 1.36, "learning_rate": 1.2136218673242073e-05, "loss": 0.4141, "step": 1281 }, { "epoch": 1.36, "learning_rate": 1.2124879692092634e-05, "loss": 0.4054, "step": 1282 }, { "epoch": 1.36, "learning_rate": 1.2113537849022932e-05, "loss": 0.4318, "step": 1283 }, { "epoch": 1.37, "learning_rate": 1.210219315930885e-05, "loss": 0.3838, "step": 1284 }, { "epoch": 1.37, "learning_rate": 1.2090845638230133e-05, "loss": 0.3902, "step": 1285 }, { "epoch": 1.37, "learning_rate": 1.2079495301070327e-05, "loss": 0.4098, "step": 1286 }, { "epoch": 1.37, "learning_rate": 1.2068142163116769e-05, "loss": 0.4148, "step": 1287 }, { "epoch": 1.37, "learning_rate": 1.205678623966058e-05, "loss": 0.4306, "step": 1288 }, { "epoch": 1.37, "learning_rate": 1.2045427545996617e-05, "loss": 0.4149, "step": 1289 }, { "epoch": 1.37, "learning_rate": 1.203406609742348e-05, "loss": 0.4207, "step": 1290 }, { "epoch": 1.37, "learning_rate": 1.2022701909243476e-05, "loss": 0.4243, "step": 1291 }, { "epoch": 1.37, "learning_rate": 1.2011334996762593e-05, "loss": 0.4781, "step": 1292 }, { "epoch": 1.38, "learning_rate": 1.199996537529051e-05, "loss": 0.445, "step": 1293 }, { "epoch": 1.38, "learning_rate": 1.198859306014053e-05, "loss": 0.3778, "step": 1294 }, { "epoch": 1.38, "learning_rate": 1.1977218066629599e-05, "loss": 0.3893, "step": 1295 }, { "epoch": 1.38, "learning_rate": 1.1965840410078268e-05, "loss": 0.3834, "step": 1296 }, { "epoch": 1.38, "learning_rate": 1.195446010581067e-05, "loss": 0.4092, "step": 1297 }, { "epoch": 1.38, "learning_rate": 1.1943077169154514e-05, "loss": 0.3705, "step": 1298 }, { "epoch": 1.38, "learning_rate": 1.193169161544104e-05, "loss": 0.3818, "step": 1299 }, { "epoch": 1.38, "learning_rate": 1.1920303460005023e-05, "loss": 0.4016, "step": 1300 }, { "epoch": 1.38, "learning_rate": 1.1908912718184741e-05, "loss": 0.5155, "step": 1301 }, { "epoch": 1.38, "learning_rate": 1.1897519405321956e-05, "loss": 0.3908, "step": 1302 }, { "epoch": 1.39, "learning_rate": 1.1886123536761886e-05, "loss": 0.4256, "step": 1303 }, { "epoch": 1.39, "learning_rate": 1.18747251278532e-05, "loss": 0.4502, "step": 1304 }, { "epoch": 1.39, "learning_rate": 1.1863324193947984e-05, "loss": 0.4115, "step": 1305 }, { "epoch": 1.39, "learning_rate": 1.1851920750401728e-05, "loss": 0.4144, "step": 1306 }, { "epoch": 1.39, "learning_rate": 1.1840514812573297e-05, "loss": 0.3828, "step": 1307 }, { "epoch": 1.39, "learning_rate": 1.1829106395824918e-05, "loss": 0.423, "step": 1308 }, { "epoch": 1.39, "learning_rate": 1.1817695515522156e-05, "loss": 0.5031, "step": 1309 }, { "epoch": 1.39, "learning_rate": 1.1806282187033899e-05, "loss": 0.4381, "step": 1310 }, { "epoch": 1.39, "learning_rate": 1.1794866425732327e-05, "loss": 0.4038, "step": 1311 }, { "epoch": 1.4, "learning_rate": 1.17834482469929e-05, "loss": 0.4161, "step": 1312 }, { "epoch": 1.4, "learning_rate": 1.1772027666194324e-05, "loss": 0.3736, "step": 1313 }, { "epoch": 1.4, "learning_rate": 1.1760604698718559e-05, "loss": 0.3924, "step": 1314 }, { "epoch": 1.4, "learning_rate": 1.174917935995076e-05, "loss": 0.4572, "step": 1315 }, { "epoch": 1.4, "learning_rate": 1.173775166527929e-05, "loss": 0.409, "step": 1316 }, { "epoch": 1.4, "learning_rate": 1.1726321630095676e-05, "loss": 0.4014, "step": 1317 }, { "epoch": 1.4, "learning_rate": 1.1714889269794605e-05, "loss": 0.4241, "step": 1318 }, { "epoch": 1.4, "learning_rate": 1.170345459977389e-05, "loss": 0.3837, "step": 1319 }, { "epoch": 1.4, "learning_rate": 1.1692017635434456e-05, "loss": 0.4291, "step": 1320 }, { "epoch": 1.41, "learning_rate": 1.1680578392180318e-05, "loss": 0.4483, "step": 1321 }, { "epoch": 1.41, "learning_rate": 1.1669136885418564e-05, "loss": 0.4166, "step": 1322 }, { "epoch": 1.41, "learning_rate": 1.1657693130559322e-05, "loss": 0.4143, "step": 1323 }, { "epoch": 1.41, "learning_rate": 1.1646247143015762e-05, "loss": 0.4286, "step": 1324 }, { "epoch": 1.41, "learning_rate": 1.1634798938204045e-05, "loss": 0.4167, "step": 1325 }, { "epoch": 1.41, "learning_rate": 1.1623348531543333e-05, "loss": 0.3517, "step": 1326 }, { "epoch": 1.41, "learning_rate": 1.161189593845574e-05, "loss": 0.4042, "step": 1327 }, { "epoch": 1.41, "learning_rate": 1.1600441174366332e-05, "loss": 0.3929, "step": 1328 }, { "epoch": 1.41, "learning_rate": 1.1588984254703107e-05, "loss": 0.3653, "step": 1329 }, { "epoch": 1.41, "learning_rate": 1.1577525194896945e-05, "loss": 0.3715, "step": 1330 }, { "epoch": 1.42, "learning_rate": 1.1566064010381633e-05, "loss": 0.4174, "step": 1331 }, { "epoch": 1.42, "learning_rate": 1.15546007165938e-05, "loss": 0.4028, "step": 1332 }, { "epoch": 1.42, "learning_rate": 1.1543135328972923e-05, "loss": 0.4381, "step": 1333 }, { "epoch": 1.42, "learning_rate": 1.1531667862961312e-05, "loss": 0.4344, "step": 1334 }, { "epoch": 1.42, "learning_rate": 1.1520198334004047e-05, "loss": 0.5004, "step": 1335 }, { "epoch": 1.42, "learning_rate": 1.1508726757549015e-05, "loss": 0.3852, "step": 1336 }, { "epoch": 1.42, "learning_rate": 1.149725314904685e-05, "loss": 0.4273, "step": 1337 }, { "epoch": 1.42, "learning_rate": 1.1485777523950917e-05, "loss": 0.5577, "step": 1338 }, { "epoch": 1.42, "learning_rate": 1.1474299897717305e-05, "loss": 0.4262, "step": 1339 }, { "epoch": 1.43, "learning_rate": 1.1462820285804793e-05, "loss": 0.3728, "step": 1340 }, { "epoch": 1.43, "learning_rate": 1.145133870367484e-05, "loss": 0.4343, "step": 1341 }, { "epoch": 1.43, "learning_rate": 1.1439855166791559e-05, "loss": 0.3914, "step": 1342 }, { "epoch": 1.43, "learning_rate": 1.1428369690621684e-05, "loss": 0.3925, "step": 1343 }, { "epoch": 1.43, "learning_rate": 1.1416882290634575e-05, "loss": 0.3725, "step": 1344 }, { "epoch": 1.43, "learning_rate": 1.1405392982302175e-05, "loss": 0.4131, "step": 1345 }, { "epoch": 1.43, "learning_rate": 1.1393901781099004e-05, "loss": 0.4325, "step": 1346 }, { "epoch": 1.43, "learning_rate": 1.1382408702502121e-05, "loss": 0.4079, "step": 1347 }, { "epoch": 1.43, "learning_rate": 1.1370913761991128e-05, "loss": 0.3591, "step": 1348 }, { "epoch": 1.43, "learning_rate": 1.1359416975048119e-05, "loss": 0.5679, "step": 1349 }, { "epoch": 1.44, "learning_rate": 1.1347918357157686e-05, "loss": 0.3882, "step": 1350 }, { "epoch": 1.44, "learning_rate": 1.1336417923806882e-05, "loss": 0.4421, "step": 1351 }, { "epoch": 1.44, "learning_rate": 1.1324915690485207e-05, "loss": 0.4361, "step": 1352 }, { "epoch": 1.44, "learning_rate": 1.1313411672684589e-05, "loss": 0.4256, "step": 1353 }, { "epoch": 1.44, "learning_rate": 1.1301905885899352e-05, "loss": 0.5275, "step": 1354 }, { "epoch": 1.44, "learning_rate": 1.1290398345626203e-05, "loss": 0.3999, "step": 1355 }, { "epoch": 1.44, "learning_rate": 1.1278889067364218e-05, "loss": 0.4204, "step": 1356 }, { "epoch": 1.44, "learning_rate": 1.126737806661481e-05, "loss": 0.3573, "step": 1357 }, { "epoch": 1.44, "learning_rate": 1.125586535888171e-05, "loss": 0.4639, "step": 1358 }, { "epoch": 1.45, "learning_rate": 1.1244350959670948e-05, "loss": 0.398, "step": 1359 }, { "epoch": 1.45, "learning_rate": 1.1232834884490838e-05, "loss": 0.4125, "step": 1360 }, { "epoch": 1.45, "learning_rate": 1.122131714885194e-05, "loss": 0.4393, "step": 1361 }, { "epoch": 1.45, "learning_rate": 1.1209797768267068e-05, "loss": 0.3963, "step": 1362 }, { "epoch": 1.45, "learning_rate": 1.119827675825123e-05, "loss": 0.4036, "step": 1363 }, { "epoch": 1.45, "learning_rate": 1.1186754134321645e-05, "loss": 0.3848, "step": 1364 }, { "epoch": 1.45, "learning_rate": 1.1175229911997703e-05, "loss": 0.3786, "step": 1365 }, { "epoch": 1.45, "learning_rate": 1.1163704106800936e-05, "loss": 0.3925, "step": 1366 }, { "epoch": 1.45, "learning_rate": 1.1152176734255027e-05, "loss": 0.3765, "step": 1367 }, { "epoch": 1.46, "learning_rate": 1.1140647809885751e-05, "loss": 0.3971, "step": 1368 }, { "epoch": 1.46, "learning_rate": 1.112911734922098e-05, "loss": 0.496, "step": 1369 }, { "epoch": 1.46, "learning_rate": 1.1117585367790668e-05, "loss": 0.3924, "step": 1370 }, { "epoch": 1.46, "learning_rate": 1.1106051881126792e-05, "loss": 0.4023, "step": 1371 }, { "epoch": 1.46, "learning_rate": 1.1094516904763378e-05, "loss": 0.3501, "step": 1372 }, { "epoch": 1.46, "learning_rate": 1.1082980454236445e-05, "loss": 0.3509, "step": 1373 }, { "epoch": 1.46, "learning_rate": 1.1071442545084008e-05, "loss": 0.3949, "step": 1374 }, { "epoch": 1.46, "learning_rate": 1.1059903192846038e-05, "loss": 0.3679, "step": 1375 }, { "epoch": 1.46, "learning_rate": 1.1048362413064453e-05, "loss": 0.4099, "step": 1376 }, { "epoch": 1.46, "learning_rate": 1.1036820221283096e-05, "loss": 0.5086, "step": 1377 }, { "epoch": 1.47, "learning_rate": 1.102527663304771e-05, "loss": 0.4143, "step": 1378 }, { "epoch": 1.47, "learning_rate": 1.1013731663905916e-05, "loss": 0.3764, "step": 1379 }, { "epoch": 1.47, "learning_rate": 1.1002185329407198e-05, "loss": 0.6181, "step": 1380 }, { "epoch": 1.47, "learning_rate": 1.0990637645102877e-05, "loss": 0.3859, "step": 1381 }, { "epoch": 1.47, "learning_rate": 1.0979088626546097e-05, "loss": 0.4188, "step": 1382 }, { "epoch": 1.47, "learning_rate": 1.0967538289291793e-05, "loss": 0.5372, "step": 1383 }, { "epoch": 1.47, "learning_rate": 1.0955986648896677e-05, "loss": 0.4375, "step": 1384 }, { "epoch": 1.47, "learning_rate": 1.0944433720919218e-05, "loss": 0.4222, "step": 1385 }, { "epoch": 1.47, "learning_rate": 1.0932879520919624e-05, "loss": 0.3952, "step": 1386 }, { "epoch": 1.48, "learning_rate": 1.0921324064459799e-05, "loss": 0.4392, "step": 1387 }, { "epoch": 1.48, "learning_rate": 1.0909767367103366e-05, "loss": 0.3792, "step": 1388 }, { "epoch": 1.48, "learning_rate": 1.0898209444415593e-05, "loss": 0.4097, "step": 1389 }, { "epoch": 1.48, "learning_rate": 1.0886650311963419e-05, "loss": 0.4377, "step": 1390 }, { "epoch": 1.48, "learning_rate": 1.0875089985315394e-05, "loss": 0.393, "step": 1391 }, { "epoch": 1.48, "learning_rate": 1.086352848004169e-05, "loss": 0.4334, "step": 1392 }, { "epoch": 1.48, "learning_rate": 1.0851965811714065e-05, "loss": 0.4381, "step": 1393 }, { "epoch": 1.48, "learning_rate": 1.0840401995905837e-05, "loss": 0.3881, "step": 1394 }, { "epoch": 1.48, "learning_rate": 1.0828837048191875e-05, "loss": 0.4212, "step": 1395 }, { "epoch": 1.48, "learning_rate": 1.0817270984148569e-05, "loss": 0.3965, "step": 1396 }, { "epoch": 1.49, "learning_rate": 1.0805703819353815e-05, "loss": 0.4369, "step": 1397 }, { "epoch": 1.49, "learning_rate": 1.0794135569386994e-05, "loss": 0.3947, "step": 1398 }, { "epoch": 1.49, "learning_rate": 1.0782566249828937e-05, "loss": 0.3937, "step": 1399 }, { "epoch": 1.49, "learning_rate": 1.0770995876261932e-05, "loss": 0.3857, "step": 1400 }, { "epoch": 1.49, "learning_rate": 1.0759424464269676e-05, "loss": 0.4437, "step": 1401 }, { "epoch": 1.49, "learning_rate": 1.0747852029437264e-05, "loss": 0.4503, "step": 1402 }, { "epoch": 1.49, "learning_rate": 1.073627858735118e-05, "loss": 0.3796, "step": 1403 }, { "epoch": 1.49, "learning_rate": 1.0724704153599245e-05, "loss": 0.3973, "step": 1404 }, { "epoch": 1.49, "learning_rate": 1.0713128743770638e-05, "loss": 0.3687, "step": 1405 }, { "epoch": 1.5, "learning_rate": 1.0701552373455835e-05, "loss": 0.3624, "step": 1406 }, { "epoch": 1.5, "learning_rate": 1.0689975058246611e-05, "loss": 0.4147, "step": 1407 }, { "epoch": 1.5, "learning_rate": 1.0678396813736023e-05, "loss": 0.4141, "step": 1408 }, { "epoch": 1.5, "learning_rate": 1.0666817655518362e-05, "loss": 0.4017, "step": 1409 }, { "epoch": 1.5, "learning_rate": 1.0655237599189168e-05, "loss": 0.4236, "step": 1410 }, { "epoch": 1.5, "learning_rate": 1.0643656660345177e-05, "loss": 0.5138, "step": 1411 }, { "epoch": 1.5, "learning_rate": 1.0632074854584315e-05, "loss": 0.4377, "step": 1412 }, { "epoch": 1.5, "learning_rate": 1.062049219750569e-05, "loss": 0.4109, "step": 1413 }, { "epoch": 1.5, "learning_rate": 1.0608908704709535e-05, "loss": 0.421, "step": 1414 }, { "epoch": 1.51, "learning_rate": 1.0597324391797224e-05, "loss": 0.3607, "step": 1415 }, { "epoch": 1.51, "learning_rate": 1.0585739274371232e-05, "loss": 0.4195, "step": 1416 }, { "epoch": 1.51, "learning_rate": 1.0574153368035112e-05, "loss": 0.4604, "step": 1417 }, { "epoch": 1.51, "learning_rate": 1.056256668839349e-05, "loss": 0.4368, "step": 1418 }, { "epoch": 1.51, "learning_rate": 1.0550979251052023e-05, "loss": 0.3659, "step": 1419 }, { "epoch": 1.51, "learning_rate": 1.0539391071617394e-05, "loss": 0.4413, "step": 1420 }, { "epoch": 1.51, "learning_rate": 1.0527802165697288e-05, "loss": 0.4309, "step": 1421 }, { "epoch": 1.51, "learning_rate": 1.0516212548900357e-05, "loss": 0.3992, "step": 1422 }, { "epoch": 1.51, "learning_rate": 1.0504622236836229e-05, "loss": 0.383, "step": 1423 }, { "epoch": 1.51, "learning_rate": 1.049303124511545e-05, "loss": 0.4035, "step": 1424 }, { "epoch": 1.52, "learning_rate": 1.0481439589349493e-05, "loss": 0.4543, "step": 1425 }, { "epoch": 1.52, "learning_rate": 1.046984728515072e-05, "loss": 0.3765, "step": 1426 }, { "epoch": 1.52, "learning_rate": 1.0458254348132371e-05, "loss": 0.3965, "step": 1427 }, { "epoch": 1.52, "learning_rate": 1.044666079390853e-05, "loss": 0.3776, "step": 1428 }, { "epoch": 1.52, "learning_rate": 1.0435066638094122e-05, "loss": 0.4235, "step": 1429 }, { "epoch": 1.52, "learning_rate": 1.0423471896304878e-05, "loss": 0.4283, "step": 1430 }, { "epoch": 1.52, "learning_rate": 1.0411876584157316e-05, "loss": 0.3682, "step": 1431 }, { "epoch": 1.52, "learning_rate": 1.0400280717268728e-05, "loss": 0.4292, "step": 1432 }, { "epoch": 1.52, "learning_rate": 1.0388684311257143e-05, "loss": 0.3761, "step": 1433 }, { "epoch": 1.53, "learning_rate": 1.037708738174133e-05, "loss": 0.4254, "step": 1434 }, { "epoch": 1.53, "learning_rate": 1.036548994434075e-05, "loss": 0.3649, "step": 1435 }, { "epoch": 1.53, "learning_rate": 1.0353892014675558e-05, "loss": 0.3724, "step": 1436 }, { "epoch": 1.53, "learning_rate": 1.0342293608366564e-05, "loss": 0.4304, "step": 1437 }, { "epoch": 1.53, "learning_rate": 1.0330694741035225e-05, "loss": 0.371, "step": 1438 }, { "epoch": 1.53, "learning_rate": 1.0319095428303623e-05, "loss": 0.379, "step": 1439 }, { "epoch": 1.53, "learning_rate": 1.0307495685794426e-05, "loss": 0.3985, "step": 1440 }, { "epoch": 1.53, "learning_rate": 1.0295895529130895e-05, "loss": 0.3981, "step": 1441 }, { "epoch": 1.53, "learning_rate": 1.028429497393684e-05, "loss": 0.4119, "step": 1442 }, { "epoch": 1.53, "learning_rate": 1.0272694035836615e-05, "loss": 0.4321, "step": 1443 }, { "epoch": 1.54, "learning_rate": 1.0261092730455085e-05, "loss": 0.3696, "step": 1444 }, { "epoch": 1.54, "learning_rate": 1.0249491073417605e-05, "loss": 0.3663, "step": 1445 }, { "epoch": 1.54, "learning_rate": 1.0237889080350014e-05, "loss": 0.4212, "step": 1446 }, { "epoch": 1.54, "learning_rate": 1.02262867668786e-05, "loss": 0.4396, "step": 1447 }, { "epoch": 1.54, "learning_rate": 1.0214684148630076e-05, "loss": 0.3726, "step": 1448 }, { "epoch": 1.54, "learning_rate": 1.0203081241231579e-05, "loss": 0.3671, "step": 1449 }, { "epoch": 1.54, "learning_rate": 1.0191478060310613e-05, "loss": 0.3991, "step": 1450 }, { "epoch": 1.54, "learning_rate": 1.0179874621495081e-05, "loss": 0.4121, "step": 1451 }, { "epoch": 1.54, "learning_rate": 1.0168270940413205e-05, "loss": 0.4219, "step": 1452 }, { "epoch": 1.55, "learning_rate": 1.0156667032693548e-05, "loss": 0.4792, "step": 1453 }, { "epoch": 1.55, "learning_rate": 1.0145062913964982e-05, "loss": 0.3973, "step": 1454 }, { "epoch": 1.55, "learning_rate": 1.0133458599856647e-05, "loss": 0.4342, "step": 1455 }, { "epoch": 1.55, "learning_rate": 1.0121854105997962e-05, "loss": 0.3838, "step": 1456 }, { "epoch": 1.55, "learning_rate": 1.0110249448018578e-05, "loss": 0.4308, "step": 1457 }, { "epoch": 1.55, "learning_rate": 1.0098644641548372e-05, "loss": 0.3972, "step": 1458 }, { "epoch": 1.55, "learning_rate": 1.0087039702217427e-05, "loss": 0.4204, "step": 1459 }, { "epoch": 1.55, "learning_rate": 1.0075434645655987e-05, "loss": 0.3936, "step": 1460 }, { "epoch": 1.55, "learning_rate": 1.0063829487494467e-05, "loss": 0.422, "step": 1461 }, { "epoch": 1.56, "learning_rate": 1.0052224243363424e-05, "loss": 0.3883, "step": 1462 }, { "epoch": 1.56, "learning_rate": 1.0040618928893516e-05, "loss": 0.4568, "step": 1463 }, { "epoch": 1.56, "learning_rate": 1.0029013559715506e-05, "loss": 0.4024, "step": 1464 }, { "epoch": 1.56, "learning_rate": 1.0017408151460223e-05, "loss": 0.3248, "step": 1465 }, { "epoch": 1.56, "learning_rate": 1.0005802719758563e-05, "loss": 0.3975, "step": 1466 }, { "epoch": 1.56, "learning_rate": 9.994197280241442e-06, "loss": 0.3738, "step": 1467 }, { "epoch": 1.56, "learning_rate": 9.982591848539779e-06, "loss": 0.3694, "step": 1468 }, { "epoch": 1.56, "learning_rate": 9.970986440284497e-06, "loss": 0.4095, "step": 1469 }, { "epoch": 1.56, "learning_rate": 9.959381071106486e-06, "loss": 0.3991, "step": 1470 }, { "epoch": 1.56, "learning_rate": 9.947775756636578e-06, "loss": 0.3664, "step": 1471 }, { "epoch": 1.57, "learning_rate": 9.936170512505536e-06, "loss": 0.405, "step": 1472 }, { "epoch": 1.57, "learning_rate": 9.924565354344018e-06, "loss": 0.4134, "step": 1473 }, { "epoch": 1.57, "learning_rate": 9.912960297782576e-06, "loss": 0.4199, "step": 1474 }, { "epoch": 1.57, "learning_rate": 9.901355358451628e-06, "loss": 0.3507, "step": 1475 }, { "epoch": 1.57, "learning_rate": 9.889750551981422e-06, "loss": 0.4087, "step": 1476 }, { "epoch": 1.57, "learning_rate": 9.878145894002042e-06, "loss": 0.4153, "step": 1477 }, { "epoch": 1.57, "learning_rate": 9.866541400143357e-06, "loss": 0.6435, "step": 1478 }, { "epoch": 1.57, "learning_rate": 9.854937086035021e-06, "loss": 0.4102, "step": 1479 }, { "epoch": 1.57, "learning_rate": 9.843332967306452e-06, "loss": 0.4458, "step": 1480 }, { "epoch": 1.58, "learning_rate": 9.8317290595868e-06, "loss": 0.4125, "step": 1481 }, { "epoch": 1.58, "learning_rate": 9.820125378504924e-06, "loss": 0.5997, "step": 1482 }, { "epoch": 1.58, "learning_rate": 9.808521939689389e-06, "loss": 0.4234, "step": 1483 }, { "epoch": 1.58, "learning_rate": 9.796918758768426e-06, "loss": 0.3685, "step": 1484 }, { "epoch": 1.58, "learning_rate": 9.785315851369926e-06, "loss": 0.4171, "step": 1485 }, { "epoch": 1.58, "learning_rate": 9.773713233121405e-06, "loss": 0.4252, "step": 1486 }, { "epoch": 1.58, "learning_rate": 9.762110919649988e-06, "loss": 0.3578, "step": 1487 }, { "epoch": 1.58, "learning_rate": 9.750508926582398e-06, "loss": 0.4055, "step": 1488 }, { "epoch": 1.58, "learning_rate": 9.738907269544918e-06, "loss": 0.4048, "step": 1489 }, { "epoch": 1.58, "learning_rate": 9.727305964163387e-06, "loss": 0.3891, "step": 1490 }, { "epoch": 1.59, "learning_rate": 9.715705026063164e-06, "loss": 0.4243, "step": 1491 }, { "epoch": 1.59, "learning_rate": 9.704104470869109e-06, "loss": 0.3655, "step": 1492 }, { "epoch": 1.59, "learning_rate": 9.692504314205576e-06, "loss": 0.3804, "step": 1493 }, { "epoch": 1.59, "learning_rate": 9.680904571696378e-06, "loss": 0.4332, "step": 1494 }, { "epoch": 1.59, "learning_rate": 9.669305258964775e-06, "loss": 0.3718, "step": 1495 }, { "epoch": 1.59, "learning_rate": 9.65770639163344e-06, "loss": 0.4759, "step": 1496 }, { "epoch": 1.59, "learning_rate": 9.646107985324445e-06, "loss": 0.3835, "step": 1497 }, { "epoch": 1.59, "learning_rate": 9.634510055659253e-06, "loss": 0.3666, "step": 1498 }, { "epoch": 1.59, "learning_rate": 9.622912618258672e-06, "loss": 0.3963, "step": 1499 }, { "epoch": 1.6, "learning_rate": 9.611315688742859e-06, "loss": 0.3867, "step": 1500 }, { "epoch": 1.6, "learning_rate": 9.599719282731277e-06, "loss": 0.3643, "step": 1501 }, { "epoch": 1.6, "learning_rate": 9.588123415842686e-06, "loss": 0.45, "step": 1502 }, { "epoch": 1.6, "learning_rate": 9.576528103695124e-06, "loss": 0.4005, "step": 1503 }, { "epoch": 1.6, "learning_rate": 9.564933361905878e-06, "loss": 0.4204, "step": 1504 }, { "epoch": 1.6, "learning_rate": 9.553339206091473e-06, "loss": 0.446, "step": 1505 }, { "epoch": 1.6, "learning_rate": 9.541745651867634e-06, "loss": 0.3821, "step": 1506 }, { "epoch": 1.6, "learning_rate": 9.530152714849281e-06, "loss": 0.4088, "step": 1507 }, { "epoch": 1.6, "learning_rate": 9.518560410650509e-06, "loss": 0.3979, "step": 1508 }, { "epoch": 1.6, "learning_rate": 9.50696875488455e-06, "loss": 0.3991, "step": 1509 }, { "epoch": 1.61, "learning_rate": 9.495377763163774e-06, "loss": 0.4775, "step": 1510 }, { "epoch": 1.61, "learning_rate": 9.483787451099646e-06, "loss": 0.412, "step": 1511 }, { "epoch": 1.61, "learning_rate": 9.472197834302715e-06, "loss": 0.4304, "step": 1512 }, { "epoch": 1.61, "learning_rate": 9.460608928382609e-06, "loss": 0.3874, "step": 1513 }, { "epoch": 1.61, "learning_rate": 9.449020748947977e-06, "loss": 0.3946, "step": 1514 }, { "epoch": 1.61, "learning_rate": 9.437433311606514e-06, "loss": 0.3552, "step": 1515 }, { "epoch": 1.61, "learning_rate": 9.425846631964892e-06, "loss": 0.4053, "step": 1516 }, { "epoch": 1.61, "learning_rate": 9.414260725628772e-06, "loss": 0.4315, "step": 1517 }, { "epoch": 1.61, "learning_rate": 9.402675608202777e-06, "loss": 0.3658, "step": 1518 }, { "epoch": 1.62, "learning_rate": 9.391091295290467e-06, "loss": 0.4368, "step": 1519 }, { "epoch": 1.62, "learning_rate": 9.379507802494315e-06, "loss": 0.443, "step": 1520 }, { "epoch": 1.62, "learning_rate": 9.367925145415688e-06, "loss": 0.374, "step": 1521 }, { "epoch": 1.62, "learning_rate": 9.356343339654826e-06, "loss": 0.3892, "step": 1522 }, { "epoch": 1.62, "learning_rate": 9.344762400810836e-06, "loss": 0.5366, "step": 1523 }, { "epoch": 1.62, "learning_rate": 9.333182344481637e-06, "loss": 0.4256, "step": 1524 }, { "epoch": 1.62, "learning_rate": 9.32160318626398e-06, "loss": 0.4665, "step": 1525 }, { "epoch": 1.62, "learning_rate": 9.310024941753392e-06, "loss": 0.3752, "step": 1526 }, { "epoch": 1.62, "learning_rate": 9.298447626544168e-06, "loss": 0.3823, "step": 1527 }, { "epoch": 1.63, "learning_rate": 9.286871256229365e-06, "loss": 0.4131, "step": 1528 }, { "epoch": 1.63, "learning_rate": 9.275295846400754e-06, "loss": 0.4502, "step": 1529 }, { "epoch": 1.63, "learning_rate": 9.263721412648826e-06, "loss": 0.4654, "step": 1530 }, { "epoch": 1.63, "learning_rate": 9.252147970562737e-06, "loss": 0.3939, "step": 1531 }, { "epoch": 1.63, "learning_rate": 9.240575535730327e-06, "loss": 0.3594, "step": 1532 }, { "epoch": 1.63, "learning_rate": 9.22900412373807e-06, "loss": 0.4008, "step": 1533 }, { "epoch": 1.63, "learning_rate": 9.217433750171068e-06, "loss": 0.4022, "step": 1534 }, { "epoch": 1.63, "learning_rate": 9.205864430613011e-06, "loss": 0.5785, "step": 1535 }, { "epoch": 1.63, "learning_rate": 9.194296180646188e-06, "loss": 0.3574, "step": 1536 }, { "epoch": 1.63, "learning_rate": 9.182729015851433e-06, "loss": 0.395, "step": 1537 }, { "epoch": 1.64, "learning_rate": 9.171162951808128e-06, "loss": 0.3734, "step": 1538 }, { "epoch": 1.64, "learning_rate": 9.159598004094168e-06, "loss": 0.3768, "step": 1539 }, { "epoch": 1.64, "learning_rate": 9.148034188285938e-06, "loss": 0.4623, "step": 1540 }, { "epoch": 1.64, "learning_rate": 9.136471519958314e-06, "loss": 0.3155, "step": 1541 }, { "epoch": 1.64, "learning_rate": 9.124910014684609e-06, "loss": 0.4146, "step": 1542 }, { "epoch": 1.64, "learning_rate": 9.113349688036586e-06, "loss": 0.3919, "step": 1543 }, { "epoch": 1.64, "learning_rate": 9.101790555584412e-06, "loss": 0.4093, "step": 1544 }, { "epoch": 1.64, "learning_rate": 9.090232632896639e-06, "loss": 0.3937, "step": 1545 }, { "epoch": 1.64, "learning_rate": 9.078675935540203e-06, "loss": 0.3577, "step": 1546 }, { "epoch": 1.65, "learning_rate": 9.06712047908038e-06, "loss": 0.3993, "step": 1547 }, { "epoch": 1.65, "learning_rate": 9.055566279080784e-06, "loss": 0.3656, "step": 1548 }, { "epoch": 1.65, "learning_rate": 9.044013351103328e-06, "loss": 0.4079, "step": 1549 }, { "epoch": 1.65, "learning_rate": 9.03246171070821e-06, "loss": 0.3731, "step": 1550 }, { "epoch": 1.65, "learning_rate": 9.020911373453906e-06, "loss": 0.4232, "step": 1551 }, { "epoch": 1.65, "learning_rate": 9.009362354897123e-06, "loss": 0.3985, "step": 1552 }, { "epoch": 1.65, "learning_rate": 8.997814670592803e-06, "loss": 0.3465, "step": 1553 }, { "epoch": 1.65, "learning_rate": 8.98626833609409e-06, "loss": 0.4072, "step": 1554 }, { "epoch": 1.65, "learning_rate": 8.974723366952293e-06, "loss": 0.4417, "step": 1555 }, { "epoch": 1.65, "learning_rate": 8.963179778716906e-06, "loss": 0.3934, "step": 1556 }, { "epoch": 1.66, "learning_rate": 8.951637586935548e-06, "loss": 0.4293, "step": 1557 }, { "epoch": 1.66, "learning_rate": 8.940096807153967e-06, "loss": 0.3964, "step": 1558 }, { "epoch": 1.66, "learning_rate": 8.928557454915997e-06, "loss": 0.449, "step": 1559 }, { "epoch": 1.66, "learning_rate": 8.917019545763558e-06, "loss": 0.3582, "step": 1560 }, { "epoch": 1.66, "learning_rate": 8.905483095236627e-06, "loss": 0.3696, "step": 1561 }, { "epoch": 1.66, "learning_rate": 8.89394811887321e-06, "loss": 0.4144, "step": 1562 }, { "epoch": 1.66, "learning_rate": 8.882414632209337e-06, "loss": 0.4558, "step": 1563 }, { "epoch": 1.66, "learning_rate": 8.870882650779021e-06, "loss": 0.3843, "step": 1564 }, { "epoch": 1.66, "learning_rate": 8.859352190114252e-06, "loss": 0.4923, "step": 1565 }, { "epoch": 1.67, "learning_rate": 8.847823265744976e-06, "loss": 0.4109, "step": 1566 }, { "epoch": 1.67, "learning_rate": 8.836295893199064e-06, "loss": 0.4216, "step": 1567 }, { "epoch": 1.67, "learning_rate": 8.824770088002302e-06, "loss": 0.4272, "step": 1568 }, { "epoch": 1.67, "learning_rate": 8.813245865678359e-06, "loss": 0.4517, "step": 1569 }, { "epoch": 1.67, "learning_rate": 8.801723241748774e-06, "loss": 0.3922, "step": 1570 }, { "epoch": 1.67, "learning_rate": 8.790202231732935e-06, "loss": 0.4183, "step": 1571 }, { "epoch": 1.67, "learning_rate": 8.778682851148062e-06, "loss": 0.3685, "step": 1572 }, { "epoch": 1.67, "learning_rate": 8.767165115509169e-06, "loss": 0.5154, "step": 1573 }, { "epoch": 1.67, "learning_rate": 8.755649040329055e-06, "loss": 0.395, "step": 1574 }, { "epoch": 1.68, "learning_rate": 8.744134641118294e-06, "loss": 0.4105, "step": 1575 }, { "epoch": 1.68, "learning_rate": 8.73262193338519e-06, "loss": 0.4191, "step": 1576 }, { "epoch": 1.68, "learning_rate": 8.721110932635782e-06, "loss": 0.3953, "step": 1577 }, { "epoch": 1.68, "learning_rate": 8.7096016543738e-06, "loss": 0.4166, "step": 1578 }, { "epoch": 1.68, "learning_rate": 8.698094114100651e-06, "loss": 0.4031, "step": 1579 }, { "epoch": 1.68, "learning_rate": 8.686588327315414e-06, "loss": 0.5001, "step": 1580 }, { "epoch": 1.68, "learning_rate": 8.675084309514793e-06, "loss": 0.4327, "step": 1581 }, { "epoch": 1.68, "learning_rate": 8.663582076193121e-06, "loss": 0.4129, "step": 1582 }, { "epoch": 1.68, "learning_rate": 8.652081642842319e-06, "loss": 0.4309, "step": 1583 }, { "epoch": 1.68, "learning_rate": 8.640583024951885e-06, "loss": 0.3981, "step": 1584 }, { "epoch": 1.69, "learning_rate": 8.629086238008876e-06, "loss": 0.4121, "step": 1585 }, { "epoch": 1.69, "learning_rate": 8.617591297497879e-06, "loss": 0.3213, "step": 1586 }, { "epoch": 1.69, "learning_rate": 8.606098218901e-06, "loss": 0.3462, "step": 1587 }, { "epoch": 1.69, "learning_rate": 8.594607017697828e-06, "loss": 0.4134, "step": 1588 }, { "epoch": 1.69, "learning_rate": 8.583117709365428e-06, "loss": 0.3704, "step": 1589 }, { "epoch": 1.69, "learning_rate": 8.57163030937832e-06, "loss": 0.3981, "step": 1590 }, { "epoch": 1.69, "learning_rate": 8.560144833208443e-06, "loss": 0.4125, "step": 1591 }, { "epoch": 1.69, "learning_rate": 8.548661296325163e-06, "loss": 0.3802, "step": 1592 }, { "epoch": 1.69, "learning_rate": 8.537179714195209e-06, "loss": 0.3695, "step": 1593 }, { "epoch": 1.7, "learning_rate": 8.525700102282698e-06, "loss": 0.3976, "step": 1594 }, { "epoch": 1.7, "learning_rate": 8.514222476049085e-06, "loss": 0.442, "step": 1595 }, { "epoch": 1.7, "learning_rate": 8.502746850953151e-06, "loss": 0.4405, "step": 1596 }, { "epoch": 1.7, "learning_rate": 8.491273242450986e-06, "loss": 0.3729, "step": 1597 }, { "epoch": 1.7, "learning_rate": 8.479801665995954e-06, "loss": 0.4201, "step": 1598 }, { "epoch": 1.7, "learning_rate": 8.468332137038692e-06, "loss": 0.391, "step": 1599 }, { "epoch": 1.7, "learning_rate": 8.456864671027077e-06, "loss": 0.5689, "step": 1600 }, { "epoch": 1.7, "learning_rate": 8.445399283406202e-06, "loss": 0.4587, "step": 1601 }, { "epoch": 1.7, "learning_rate": 8.433935989618372e-06, "loss": 0.4392, "step": 1602 }, { "epoch": 1.7, "learning_rate": 8.422474805103056e-06, "loss": 0.424, "step": 1603 }, { "epoch": 1.71, "learning_rate": 8.411015745296895e-06, "loss": 0.4064, "step": 1604 }, { "epoch": 1.71, "learning_rate": 8.399558825633666e-06, "loss": 0.3976, "step": 1605 }, { "epoch": 1.71, "learning_rate": 8.388104061544265e-06, "loss": 0.4118, "step": 1606 }, { "epoch": 1.71, "learning_rate": 8.37665146845667e-06, "loss": 0.3831, "step": 1607 }, { "epoch": 1.71, "learning_rate": 8.365201061795956e-06, "loss": 0.4337, "step": 1608 }, { "epoch": 1.71, "learning_rate": 8.35375285698424e-06, "loss": 0.3616, "step": 1609 }, { "epoch": 1.71, "learning_rate": 8.342306869440676e-06, "loss": 0.3672, "step": 1610 }, { "epoch": 1.71, "learning_rate": 8.33086311458144e-06, "loss": 0.414, "step": 1611 }, { "epoch": 1.71, "learning_rate": 8.319421607819684e-06, "loss": 0.4981, "step": 1612 }, { "epoch": 1.72, "learning_rate": 8.307982364565549e-06, "loss": 0.3593, "step": 1613 }, { "epoch": 1.72, "learning_rate": 8.296545400226113e-06, "loss": 0.3986, "step": 1614 }, { "epoch": 1.72, "learning_rate": 8.285110730205396e-06, "loss": 0.3367, "step": 1615 }, { "epoch": 1.72, "learning_rate": 8.273678369904328e-06, "loss": 0.4491, "step": 1616 }, { "epoch": 1.72, "learning_rate": 8.262248334720714e-06, "loss": 0.4242, "step": 1617 }, { "epoch": 1.72, "learning_rate": 8.250820640049244e-06, "loss": 0.3829, "step": 1618 }, { "epoch": 1.72, "learning_rate": 8.239395301281445e-06, "loss": 0.3729, "step": 1619 }, { "epoch": 1.72, "learning_rate": 8.227972333805678e-06, "loss": 0.3949, "step": 1620 }, { "epoch": 1.72, "learning_rate": 8.216551753007107e-06, "loss": 0.4399, "step": 1621 }, { "epoch": 1.73, "learning_rate": 8.205133574267675e-06, "loss": 0.437, "step": 1622 }, { "epoch": 1.73, "learning_rate": 8.193717812966103e-06, "loss": 0.5677, "step": 1623 }, { "epoch": 1.73, "learning_rate": 8.182304484477844e-06, "loss": 0.4193, "step": 1624 }, { "epoch": 1.73, "learning_rate": 8.170893604175083e-06, "loss": 0.5945, "step": 1625 }, { "epoch": 1.73, "learning_rate": 8.159485187426708e-06, "loss": 0.4133, "step": 1626 }, { "epoch": 1.73, "learning_rate": 8.148079249598275e-06, "loss": 0.4011, "step": 1627 }, { "epoch": 1.73, "learning_rate": 8.136675806052017e-06, "loss": 0.419, "step": 1628 }, { "epoch": 1.73, "learning_rate": 8.1252748721468e-06, "loss": 0.3772, "step": 1629 }, { "epoch": 1.73, "learning_rate": 8.113876463238117e-06, "loss": 0.3575, "step": 1630 }, { "epoch": 1.73, "learning_rate": 8.102480594678049e-06, "loss": 0.3526, "step": 1631 }, { "epoch": 1.74, "learning_rate": 8.09108728181526e-06, "loss": 0.4215, "step": 1632 }, { "epoch": 1.74, "learning_rate": 8.07969653999498e-06, "loss": 0.3677, "step": 1633 }, { "epoch": 1.74, "learning_rate": 8.068308384558962e-06, "loss": 0.4227, "step": 1634 }, { "epoch": 1.74, "learning_rate": 8.056922830845491e-06, "loss": 0.3852, "step": 1635 }, { "epoch": 1.74, "learning_rate": 8.045539894189331e-06, "loss": 0.4495, "step": 1636 }, { "epoch": 1.74, "learning_rate": 8.034159589921734e-06, "loss": 0.4284, "step": 1637 }, { "epoch": 1.74, "learning_rate": 8.022781933370403e-06, "loss": 0.3818, "step": 1638 }, { "epoch": 1.74, "learning_rate": 8.011406939859472e-06, "loss": 0.3734, "step": 1639 }, { "epoch": 1.74, "learning_rate": 8.000034624709495e-06, "loss": 0.4209, "step": 1640 }, { "epoch": 1.75, "learning_rate": 7.988665003237409e-06, "loss": 0.4392, "step": 1641 }, { "epoch": 1.75, "learning_rate": 7.97729809075653e-06, "loss": 0.3983, "step": 1642 }, { "epoch": 1.75, "learning_rate": 7.965933902576523e-06, "loss": 0.3648, "step": 1643 }, { "epoch": 1.75, "learning_rate": 7.954572454003385e-06, "loss": 0.3633, "step": 1644 }, { "epoch": 1.75, "learning_rate": 7.943213760339423e-06, "loss": 0.3841, "step": 1645 }, { "epoch": 1.75, "learning_rate": 7.931857836883233e-06, "loss": 0.3748, "step": 1646 }, { "epoch": 1.75, "learning_rate": 7.920504698929676e-06, "loss": 0.3734, "step": 1647 }, { "epoch": 1.75, "learning_rate": 7.90915436176987e-06, "loss": 0.4046, "step": 1648 }, { "epoch": 1.75, "learning_rate": 7.897806840691151e-06, "loss": 0.3737, "step": 1649 }, { "epoch": 1.75, "learning_rate": 7.886462150977074e-06, "loss": 0.3729, "step": 1650 }, { "epoch": 1.76, "learning_rate": 7.875120307907367e-06, "loss": 0.3911, "step": 1651 }, { "epoch": 1.76, "learning_rate": 7.86378132675793e-06, "loss": 0.4151, "step": 1652 }, { "epoch": 1.76, "learning_rate": 7.852445222800815e-06, "loss": 0.3607, "step": 1653 }, { "epoch": 1.76, "learning_rate": 7.841112011304185e-06, "loss": 0.3743, "step": 1654 }, { "epoch": 1.76, "learning_rate": 7.829781707532325e-06, "loss": 0.4929, "step": 1655 }, { "epoch": 1.76, "learning_rate": 7.818454326745584e-06, "loss": 0.4074, "step": 1656 }, { "epoch": 1.76, "learning_rate": 7.807129884200385e-06, "loss": 0.4245, "step": 1657 }, { "epoch": 1.76, "learning_rate": 7.795808395149197e-06, "loss": 0.3998, "step": 1658 }, { "epoch": 1.76, "learning_rate": 7.784489874840507e-06, "loss": 0.365, "step": 1659 }, { "epoch": 1.77, "learning_rate": 7.773174338518794e-06, "loss": 0.3506, "step": 1660 }, { "epoch": 1.77, "learning_rate": 7.761861801424535e-06, "loss": 0.4219, "step": 1661 }, { "epoch": 1.77, "learning_rate": 7.750552278794154e-06, "loss": 0.5015, "step": 1662 }, { "epoch": 1.77, "learning_rate": 7.739245785860028e-06, "loss": 0.7493, "step": 1663 }, { "epoch": 1.77, "learning_rate": 7.72794233785044e-06, "loss": 0.3971, "step": 1664 }, { "epoch": 1.77, "learning_rate": 7.716641949989575e-06, "loss": 0.3744, "step": 1665 }, { "epoch": 1.77, "learning_rate": 7.705344637497507e-06, "loss": 0.4461, "step": 1666 }, { "epoch": 1.77, "learning_rate": 7.69405041559015e-06, "loss": 0.3867, "step": 1667 }, { "epoch": 1.77, "learning_rate": 7.682759299479274e-06, "loss": 0.3687, "step": 1668 }, { "epoch": 1.78, "learning_rate": 7.671471304372457e-06, "loss": 0.4597, "step": 1669 }, { "epoch": 1.78, "learning_rate": 7.660186445473065e-06, "loss": 0.3926, "step": 1670 }, { "epoch": 1.78, "learning_rate": 7.648904737980255e-06, "loss": 0.4063, "step": 1671 }, { "epoch": 1.78, "learning_rate": 7.637626197088933e-06, "loss": 0.4186, "step": 1672 }, { "epoch": 1.78, "learning_rate": 7.6263508379897375e-06, "loss": 0.4038, "step": 1673 }, { "epoch": 1.78, "learning_rate": 7.615078675869033e-06, "loss": 0.4149, "step": 1674 }, { "epoch": 1.78, "learning_rate": 7.603809725908855e-06, "loss": 0.3758, "step": 1675 }, { "epoch": 1.78, "learning_rate": 7.592544003286934e-06, "loss": 0.4899, "step": 1676 }, { "epoch": 1.78, "learning_rate": 7.58128152317665e-06, "loss": 0.4024, "step": 1677 }, { "epoch": 1.78, "learning_rate": 7.570022300747007e-06, "loss": 0.3957, "step": 1678 }, { "epoch": 1.79, "learning_rate": 7.558766351162635e-06, "loss": 0.5176, "step": 1679 }, { "epoch": 1.79, "learning_rate": 7.547513689583736e-06, "loss": 0.3691, "step": 1680 }, { "epoch": 1.79, "learning_rate": 7.536264331166101e-06, "loss": 0.3877, "step": 1681 }, { "epoch": 1.79, "learning_rate": 7.525018291061068e-06, "loss": 0.3905, "step": 1682 }, { "epoch": 1.79, "learning_rate": 7.5137755844155056e-06, "loss": 0.3851, "step": 1683 }, { "epoch": 1.79, "learning_rate": 7.502536226371784e-06, "loss": 0.3651, "step": 1684 }, { "epoch": 1.79, "learning_rate": 7.491300232067775e-06, "loss": 0.3888, "step": 1685 }, { "epoch": 1.79, "learning_rate": 7.480067616636815e-06, "loss": 0.4599, "step": 1686 }, { "epoch": 1.79, "learning_rate": 7.468838395207689e-06, "loss": 0.394, "step": 1687 }, { "epoch": 1.8, "learning_rate": 7.4576125829046164e-06, "loss": 0.3698, "step": 1688 }, { "epoch": 1.8, "learning_rate": 7.446390194847211e-06, "loss": 0.3853, "step": 1689 }, { "epoch": 1.8, "learning_rate": 7.43517124615049e-06, "loss": 0.359, "step": 1690 }, { "epoch": 1.8, "learning_rate": 7.423955751924829e-06, "loss": 0.4154, "step": 1691 }, { "epoch": 1.8, "learning_rate": 7.412743727275959e-06, "loss": 0.4002, "step": 1692 }, { "epoch": 1.8, "learning_rate": 7.401535187304931e-06, "loss": 0.3816, "step": 1693 }, { "epoch": 1.8, "learning_rate": 7.3903301471081004e-06, "loss": 0.3819, "step": 1694 }, { "epoch": 1.8, "learning_rate": 7.379128621777116e-06, "loss": 0.351, "step": 1695 }, { "epoch": 1.8, "learning_rate": 7.367930626398887e-06, "loss": 0.4162, "step": 1696 }, { "epoch": 1.8, "learning_rate": 7.3567361760555765e-06, "loss": 0.4383, "step": 1697 }, { "epoch": 1.81, "learning_rate": 7.345545285824567e-06, "loss": 0.4178, "step": 1698 }, { "epoch": 1.81, "learning_rate": 7.334357970778436e-06, "loss": 0.3948, "step": 1699 }, { "epoch": 1.81, "learning_rate": 7.323174245984967e-06, "loss": 0.4134, "step": 1700 }, { "epoch": 1.81, "learning_rate": 7.311994126507091e-06, "loss": 0.4456, "step": 1701 }, { "epoch": 1.81, "learning_rate": 7.300817627402893e-06, "loss": 0.4065, "step": 1702 }, { "epoch": 1.81, "learning_rate": 7.289644763725579e-06, "loss": 0.3928, "step": 1703 }, { "epoch": 1.81, "learning_rate": 7.278475550523447e-06, "loss": 0.3645, "step": 1704 }, { "epoch": 1.81, "learning_rate": 7.267310002839901e-06, "loss": 0.4244, "step": 1705 }, { "epoch": 1.81, "learning_rate": 7.256148135713388e-06, "loss": 0.3984, "step": 1706 }, { "epoch": 1.82, "learning_rate": 7.244989964177413e-06, "loss": 0.3832, "step": 1707 }, { "epoch": 1.82, "learning_rate": 7.23383550326049e-06, "loss": 0.3998, "step": 1708 }, { "epoch": 1.82, "learning_rate": 7.222684767986141e-06, "loss": 0.38, "step": 1709 }, { "epoch": 1.82, "learning_rate": 7.211537773372874e-06, "loss": 0.3853, "step": 1710 }, { "epoch": 1.82, "learning_rate": 7.200394534434154e-06, "loss": 0.3898, "step": 1711 }, { "epoch": 1.82, "learning_rate": 7.189255066178392e-06, "loss": 0.4657, "step": 1712 }, { "epoch": 1.82, "learning_rate": 7.178119383608912e-06, "loss": 0.373, "step": 1713 }, { "epoch": 1.82, "learning_rate": 7.166987501723948e-06, "loss": 0.413, "step": 1714 }, { "epoch": 1.82, "learning_rate": 7.15585943551661e-06, "loss": 0.4298, "step": 1715 }, { "epoch": 1.83, "learning_rate": 7.144735199974871e-06, "loss": 0.4847, "step": 1716 }, { "epoch": 1.83, "learning_rate": 7.133614810081548e-06, "loss": 0.4318, "step": 1717 }, { "epoch": 1.83, "learning_rate": 7.122498280814269e-06, "loss": 0.4712, "step": 1718 }, { "epoch": 1.83, "learning_rate": 7.1113856271454684e-06, "loss": 0.4714, "step": 1719 }, { "epoch": 1.83, "learning_rate": 7.100276864042364e-06, "loss": 0.374, "step": 1720 }, { "epoch": 1.83, "learning_rate": 7.089172006466922e-06, "loss": 0.3743, "step": 1721 }, { "epoch": 1.83, "learning_rate": 7.078071069375868e-06, "loss": 0.3677, "step": 1722 }, { "epoch": 1.83, "learning_rate": 7.0669740677206255e-06, "loss": 0.4123, "step": 1723 }, { "epoch": 1.83, "learning_rate": 7.055881016447328e-06, "loss": 0.4465, "step": 1724 }, { "epoch": 1.83, "learning_rate": 7.044791930496792e-06, "loss": 0.3625, "step": 1725 }, { "epoch": 1.84, "learning_rate": 7.033706824804483e-06, "loss": 0.3859, "step": 1726 }, { "epoch": 1.84, "learning_rate": 7.0226257143005216e-06, "loss": 0.3752, "step": 1727 }, { "epoch": 1.84, "learning_rate": 7.011548613909628e-06, "loss": 0.3958, "step": 1728 }, { "epoch": 1.84, "learning_rate": 7.0004755385511314e-06, "loss": 0.552, "step": 1729 }, { "epoch": 1.84, "learning_rate": 6.989406503138945e-06, "loss": 0.3852, "step": 1730 }, { "epoch": 1.84, "learning_rate": 6.978341522581531e-06, "loss": 0.3736, "step": 1731 }, { "epoch": 1.84, "learning_rate": 6.967280611781891e-06, "loss": 0.3701, "step": 1732 }, { "epoch": 1.84, "learning_rate": 6.956223785637555e-06, "loss": 0.432, "step": 1733 }, { "epoch": 1.84, "learning_rate": 6.945171059040538e-06, "loss": 0.3947, "step": 1734 }, { "epoch": 1.85, "learning_rate": 6.934122446877348e-06, "loss": 0.428, "step": 1735 }, { "epoch": 1.85, "learning_rate": 6.923077964028941e-06, "loss": 0.4266, "step": 1736 }, { "epoch": 1.85, "learning_rate": 6.912037625370709e-06, "loss": 0.3619, "step": 1737 }, { "epoch": 1.85, "learning_rate": 6.901001445772475e-06, "loss": 0.4066, "step": 1738 }, { "epoch": 1.85, "learning_rate": 6.889969440098445e-06, "loss": 0.3784, "step": 1739 }, { "epoch": 1.85, "learning_rate": 6.87894162320722e-06, "loss": 0.3673, "step": 1740 }, { "epoch": 1.85, "learning_rate": 6.867918009951746e-06, "loss": 0.401, "step": 1741 }, { "epoch": 1.85, "learning_rate": 6.8568986151793085e-06, "loss": 0.3445, "step": 1742 }, { "epoch": 1.85, "learning_rate": 6.84588345373152e-06, "loss": 0.3993, "step": 1743 }, { "epoch": 1.85, "learning_rate": 6.834872540444282e-06, "loss": 0.4273, "step": 1744 }, { "epoch": 1.86, "learning_rate": 6.823865890147781e-06, "loss": 0.405, "step": 1745 }, { "epoch": 1.86, "learning_rate": 6.812863517666459e-06, "loss": 0.3868, "step": 1746 }, { "epoch": 1.86, "learning_rate": 6.801865437818991e-06, "loss": 0.4148, "step": 1747 }, { "epoch": 1.86, "learning_rate": 6.7908716654182815e-06, "loss": 0.3905, "step": 1748 }, { "epoch": 1.86, "learning_rate": 6.779882215271423e-06, "loss": 0.385, "step": 1749 }, { "epoch": 1.86, "learning_rate": 6.768897102179697e-06, "loss": 0.3972, "step": 1750 }, { "epoch": 1.86, "learning_rate": 6.757916340938538e-06, "loss": 0.4024, "step": 1751 }, { "epoch": 1.86, "learning_rate": 6.746939946337509e-06, "loss": 0.4025, "step": 1752 }, { "epoch": 1.86, "learning_rate": 6.735967933160312e-06, "loss": 0.3768, "step": 1753 }, { "epoch": 1.87, "learning_rate": 6.725000316184731e-06, "loss": 0.3968, "step": 1754 }, { "epoch": 1.87, "learning_rate": 6.714037110182643e-06, "loss": 0.4016, "step": 1755 }, { "epoch": 1.87, "learning_rate": 6.703078329919968e-06, "loss": 0.4686, "step": 1756 }, { "epoch": 1.87, "learning_rate": 6.692123990156678e-06, "loss": 0.501, "step": 1757 }, { "epoch": 1.87, "learning_rate": 6.68117410564676e-06, "loss": 0.4072, "step": 1758 }, { "epoch": 1.87, "learning_rate": 6.670228691138196e-06, "loss": 0.3755, "step": 1759 }, { "epoch": 1.87, "learning_rate": 6.659287761372961e-06, "loss": 0.4728, "step": 1760 }, { "epoch": 1.87, "learning_rate": 6.648351331086972e-06, "loss": 0.4108, "step": 1761 }, { "epoch": 1.87, "learning_rate": 6.637419415010095e-06, "loss": 0.3708, "step": 1762 }, { "epoch": 1.88, "learning_rate": 6.626492027866118e-06, "loss": 0.6291, "step": 1763 }, { "epoch": 1.88, "learning_rate": 6.615569184372726e-06, "loss": 0.3672, "step": 1764 }, { "epoch": 1.88, "learning_rate": 6.604650899241486e-06, "loss": 0.4324, "step": 1765 }, { "epoch": 1.88, "learning_rate": 6.593737187177821e-06, "loss": 0.4357, "step": 1766 }, { "epoch": 1.88, "learning_rate": 6.582828062880997e-06, "loss": 0.4658, "step": 1767 }, { "epoch": 1.88, "learning_rate": 6.571923541044107e-06, "loss": 0.3873, "step": 1768 }, { "epoch": 1.88, "learning_rate": 6.561023636354036e-06, "loss": 0.4099, "step": 1769 }, { "epoch": 1.88, "learning_rate": 6.550128363491457e-06, "loss": 0.3842, "step": 1770 }, { "epoch": 1.88, "learning_rate": 6.5392377371308005e-06, "loss": 0.3812, "step": 1771 }, { "epoch": 1.88, "learning_rate": 6.528351771940238e-06, "loss": 0.397, "step": 1772 }, { "epoch": 1.89, "learning_rate": 6.517470482581667e-06, "loss": 0.3479, "step": 1773 }, { "epoch": 1.89, "learning_rate": 6.506593883710686e-06, "loss": 0.3563, "step": 1774 }, { "epoch": 1.89, "learning_rate": 6.495721989976578e-06, "loss": 0.5706, "step": 1775 }, { "epoch": 1.89, "learning_rate": 6.484854816022284e-06, "loss": 0.4982, "step": 1776 }, { "epoch": 1.89, "learning_rate": 6.473992376484386e-06, "loss": 0.3906, "step": 1777 }, { "epoch": 1.89, "learning_rate": 6.463134685993099e-06, "loss": 0.3954, "step": 1778 }, { "epoch": 1.89, "learning_rate": 6.452281759172236e-06, "loss": 0.3987, "step": 1779 }, { "epoch": 1.89, "learning_rate": 6.4414336106391995e-06, "loss": 0.4065, "step": 1780 }, { "epoch": 1.89, "learning_rate": 6.4305902550049405e-06, "loss": 0.4414, "step": 1781 }, { "epoch": 1.9, "learning_rate": 6.4197517068739735e-06, "loss": 0.3676, "step": 1782 }, { "epoch": 1.9, "learning_rate": 6.408917980844326e-06, "loss": 0.4147, "step": 1783 }, { "epoch": 1.9, "learning_rate": 6.398089091507542e-06, "loss": 0.507, "step": 1784 }, { "epoch": 1.9, "learning_rate": 6.387265053448633e-06, "loss": 0.3752, "step": 1785 }, { "epoch": 1.9, "learning_rate": 6.376445881246093e-06, "loss": 0.3567, "step": 1786 }, { "epoch": 1.9, "learning_rate": 6.365631589471858e-06, "loss": 0.3768, "step": 1787 }, { "epoch": 1.9, "learning_rate": 6.354822192691285e-06, "loss": 0.3832, "step": 1788 }, { "epoch": 1.9, "learning_rate": 6.3440177054631524e-06, "loss": 0.4178, "step": 1789 }, { "epoch": 1.9, "learning_rate": 6.333218142339606e-06, "loss": 0.4075, "step": 1790 }, { "epoch": 1.9, "learning_rate": 6.322423517866172e-06, "loss": 0.3985, "step": 1791 }, { "epoch": 1.91, "learning_rate": 6.311633846581726e-06, "loss": 0.3401, "step": 1792 }, { "epoch": 1.91, "learning_rate": 6.300849143018464e-06, "loss": 0.4236, "step": 1793 }, { "epoch": 1.91, "learning_rate": 6.290069421701906e-06, "loss": 0.4773, "step": 1794 }, { "epoch": 1.91, "learning_rate": 6.279294697150842e-06, "loss": 0.3884, "step": 1795 }, { "epoch": 1.91, "learning_rate": 6.268524983877343e-06, "loss": 0.3954, "step": 1796 }, { "epoch": 1.91, "learning_rate": 6.2577602963867345e-06, "loss": 0.5056, "step": 1797 }, { "epoch": 1.91, "learning_rate": 6.247000649177563e-06, "loss": 0.3819, "step": 1798 }, { "epoch": 1.91, "learning_rate": 6.2362460567415976e-06, "loss": 0.4005, "step": 1799 }, { "epoch": 1.91, "learning_rate": 6.225496533563786e-06, "loss": 0.4053, "step": 1800 }, { "epoch": 1.92, "learning_rate": 6.214752094122258e-06, "loss": 0.3663, "step": 1801 }, { "epoch": 1.92, "learning_rate": 6.2040127528882935e-06, "loss": 0.3738, "step": 1802 }, { "epoch": 1.92, "learning_rate": 6.193278524326305e-06, "loss": 0.387, "step": 1803 }, { "epoch": 1.92, "learning_rate": 6.182549422893827e-06, "loss": 0.4709, "step": 1804 }, { "epoch": 1.92, "learning_rate": 6.1718254630414695e-06, "loss": 0.384, "step": 1805 }, { "epoch": 1.92, "learning_rate": 6.161106659212936e-06, "loss": 0.3972, "step": 1806 }, { "epoch": 1.92, "learning_rate": 6.150393025844981e-06, "loss": 0.4131, "step": 1807 }, { "epoch": 1.92, "learning_rate": 6.1396845773673905e-06, "loss": 0.4214, "step": 1808 }, { "epoch": 1.92, "learning_rate": 6.128981328202965e-06, "loss": 0.3669, "step": 1809 }, { "epoch": 1.93, "learning_rate": 6.118283292767514e-06, "loss": 0.4127, "step": 1810 }, { "epoch": 1.93, "learning_rate": 6.1075904854698135e-06, "loss": 0.3892, "step": 1811 }, { "epoch": 1.93, "learning_rate": 6.096902920711605e-06, "loss": 0.3943, "step": 1812 }, { "epoch": 1.93, "learning_rate": 6.086220612887565e-06, "loss": 0.4307, "step": 1813 }, { "epoch": 1.93, "learning_rate": 6.07554357638529e-06, "loss": 0.3741, "step": 1814 }, { "epoch": 1.93, "learning_rate": 6.064871825585278e-06, "loss": 0.3467, "step": 1815 }, { "epoch": 1.93, "learning_rate": 6.054205374860906e-06, "loss": 0.3746, "step": 1816 }, { "epoch": 1.93, "learning_rate": 6.043544238578418e-06, "loss": 0.3858, "step": 1817 }, { "epoch": 1.93, "learning_rate": 6.032888431096895e-06, "loss": 0.361, "step": 1818 }, { "epoch": 1.93, "learning_rate": 6.0222379667682364e-06, "loss": 0.3993, "step": 1819 }, { "epoch": 1.94, "learning_rate": 6.011592859937158e-06, "loss": 0.5163, "step": 1820 }, { "epoch": 1.94, "learning_rate": 6.000953124941146e-06, "loss": 0.3446, "step": 1821 }, { "epoch": 1.94, "learning_rate": 5.9903187761104645e-06, "loss": 0.3956, "step": 1822 }, { "epoch": 1.94, "learning_rate": 5.979689827768116e-06, "loss": 0.4235, "step": 1823 }, { "epoch": 1.94, "learning_rate": 5.969066294229821e-06, "loss": 0.3119, "step": 1824 }, { "epoch": 1.94, "learning_rate": 5.958448189804027e-06, "loss": 0.4282, "step": 1825 }, { "epoch": 1.94, "learning_rate": 5.947835528791851e-06, "loss": 0.4302, "step": 1826 }, { "epoch": 1.94, "learning_rate": 5.93722832548709e-06, "loss": 0.4691, "step": 1827 }, { "epoch": 1.94, "learning_rate": 5.926626594176186e-06, "loss": 0.4169, "step": 1828 }, { "epoch": 1.95, "learning_rate": 5.916030349138204e-06, "loss": 0.4409, "step": 1829 }, { "epoch": 1.95, "learning_rate": 5.9054396046448355e-06, "loss": 0.402, "step": 1830 }, { "epoch": 1.95, "learning_rate": 5.894854374960348e-06, "loss": 0.4239, "step": 1831 }, { "epoch": 1.95, "learning_rate": 5.884274674341593e-06, "loss": 0.4147, "step": 1832 }, { "epoch": 1.95, "learning_rate": 5.873700517037967e-06, "loss": 0.3977, "step": 1833 }, { "epoch": 1.95, "learning_rate": 5.863131917291402e-06, "loss": 0.3859, "step": 1834 }, { "epoch": 1.95, "learning_rate": 5.85256888933635e-06, "loss": 0.3696, "step": 1835 }, { "epoch": 1.95, "learning_rate": 5.842011447399749e-06, "loss": 0.4333, "step": 1836 }, { "epoch": 1.95, "learning_rate": 5.831459605701029e-06, "loss": 0.5207, "step": 1837 }, { "epoch": 1.95, "learning_rate": 5.82091337845206e-06, "loss": 0.3974, "step": 1838 }, { "epoch": 1.96, "learning_rate": 5.8103727798571575e-06, "loss": 0.4282, "step": 1839 }, { "epoch": 1.96, "learning_rate": 5.799837824113053e-06, "loss": 0.4033, "step": 1840 }, { "epoch": 1.96, "learning_rate": 5.789308525408891e-06, "loss": 0.5006, "step": 1841 }, { "epoch": 1.96, "learning_rate": 5.778784897926184e-06, "loss": 0.3962, "step": 1842 }, { "epoch": 1.96, "learning_rate": 5.768266955838797e-06, "loss": 0.3651, "step": 1843 }, { "epoch": 1.96, "learning_rate": 5.757754713312964e-06, "loss": 0.4089, "step": 1844 }, { "epoch": 1.96, "learning_rate": 5.7472481845072195e-06, "loss": 0.3547, "step": 1845 }, { "epoch": 1.96, "learning_rate": 5.736747383572414e-06, "loss": 0.5006, "step": 1846 }, { "epoch": 1.96, "learning_rate": 5.7262523246516775e-06, "loss": 0.3657, "step": 1847 }, { "epoch": 1.97, "learning_rate": 5.715763021880412e-06, "loss": 0.3932, "step": 1848 }, { "epoch": 1.97, "learning_rate": 5.7052794893862604e-06, "loss": 0.3713, "step": 1849 }, { "epoch": 1.97, "learning_rate": 5.694801741289095e-06, "loss": 0.3964, "step": 1850 }, { "epoch": 1.97, "learning_rate": 5.684329791701006e-06, "loss": 0.3918, "step": 1851 }, { "epoch": 1.97, "learning_rate": 5.6738636547262694e-06, "loss": 0.3977, "step": 1852 }, { "epoch": 1.97, "learning_rate": 5.6634033444613154e-06, "loss": 0.3996, "step": 1853 }, { "epoch": 1.97, "learning_rate": 5.652948874994754e-06, "loss": 0.417, "step": 1854 }, { "epoch": 1.97, "learning_rate": 5.642500260407313e-06, "loss": 0.3816, "step": 1855 }, { "epoch": 1.97, "learning_rate": 5.632057514771835e-06, "loss": 0.4061, "step": 1856 }, { "epoch": 1.98, "learning_rate": 5.621620652153261e-06, "loss": 0.4247, "step": 1857 }, { "epoch": 1.98, "learning_rate": 5.611189686608608e-06, "loss": 0.372, "step": 1858 }, { "epoch": 1.98, "learning_rate": 5.600764632186949e-06, "loss": 0.4207, "step": 1859 }, { "epoch": 1.98, "learning_rate": 5.590345502929393e-06, "loss": 0.3656, "step": 1860 }, { "epoch": 1.98, "learning_rate": 5.579932312869083e-06, "loss": 0.3656, "step": 1861 }, { "epoch": 1.98, "learning_rate": 5.569525076031142e-06, "loss": 0.4933, "step": 1862 }, { "epoch": 1.98, "learning_rate": 5.559123806432682e-06, "loss": 0.3914, "step": 1863 }, { "epoch": 1.98, "learning_rate": 5.54872851808279e-06, "loss": 0.377, "step": 1864 }, { "epoch": 1.98, "learning_rate": 5.538339224982483e-06, "loss": 0.3686, "step": 1865 }, { "epoch": 1.98, "learning_rate": 5.527955941124707e-06, "loss": 0.4917, "step": 1866 }, { "epoch": 1.99, "learning_rate": 5.5175786804943175e-06, "loss": 0.3851, "step": 1867 }, { "epoch": 1.99, "learning_rate": 5.507207457068053e-06, "loss": 0.355, "step": 1868 }, { "epoch": 1.99, "learning_rate": 5.496842284814526e-06, "loss": 0.3692, "step": 1869 }, { "epoch": 1.99, "learning_rate": 5.4864831776941886e-06, "loss": 0.3781, "step": 1870 }, { "epoch": 1.99, "learning_rate": 5.476130149659343e-06, "loss": 0.5138, "step": 1871 }, { "epoch": 1.99, "learning_rate": 5.465783214654084e-06, "loss": 0.3938, "step": 1872 }, { "epoch": 1.99, "learning_rate": 5.455442386614303e-06, "loss": 0.3797, "step": 1873 }, { "epoch": 1.99, "learning_rate": 5.445107679467683e-06, "loss": 0.3646, "step": 1874 }, { "epoch": 1.99, "learning_rate": 5.434779107133643e-06, "loss": 0.4249, "step": 1875 }, { "epoch": 2.0, "learning_rate": 5.424456683523351e-06, "loss": 0.3811, "step": 1876 }, { "epoch": 2.0, "learning_rate": 5.414140422539691e-06, "loss": 0.4416, "step": 1877 }, { "epoch": 2.0, "learning_rate": 5.4038303380772405e-06, "loss": 0.3495, "step": 1878 }, { "epoch": 2.0, "learning_rate": 5.393526444022263e-06, "loss": 0.3926, "step": 1879 }, { "epoch": 2.0, "learning_rate": 5.383228754252691e-06, "loss": 0.384, "step": 1880 }, { "epoch": 2.0, "learning_rate": 5.3729372826380955e-06, "loss": 0.3244, "step": 1881 }, { "epoch": 2.0, "learning_rate": 5.3626520430396624e-06, "loss": 0.3629, "step": 1882 }, { "epoch": 2.0, "learning_rate": 5.352373049310191e-06, "loss": 0.3393, "step": 1883 }, { "epoch": 2.0, "learning_rate": 5.342100315294082e-06, "loss": 0.3033, "step": 1884 }, { "epoch": 2.0, "learning_rate": 5.331833854827291e-06, "loss": 0.3203, "step": 1885 }, { "epoch": 2.01, "learning_rate": 5.321573681737313e-06, "loss": 0.3031, "step": 1886 }, { "epoch": 2.01, "learning_rate": 5.311319809843203e-06, "loss": 0.3245, "step": 1887 }, { "epoch": 2.01, "learning_rate": 5.301072252955508e-06, "loss": 0.4206, "step": 1888 }, { "epoch": 2.01, "learning_rate": 5.290831024876272e-06, "loss": 0.2982, "step": 1889 }, { "epoch": 2.01, "learning_rate": 5.28059613939903e-06, "loss": 0.3203, "step": 1890 }, { "epoch": 2.01, "learning_rate": 5.270367610308753e-06, "loss": 0.3033, "step": 1891 }, { "epoch": 2.01, "learning_rate": 5.260145451381858e-06, "loss": 0.2868, "step": 1892 }, { "epoch": 2.01, "learning_rate": 5.249929676386196e-06, "loss": 0.3404, "step": 1893 }, { "epoch": 2.01, "learning_rate": 5.2397202990810035e-06, "loss": 0.276, "step": 1894 }, { "epoch": 2.02, "learning_rate": 5.2295173332169045e-06, "loss": 0.2948, "step": 1895 }, { "epoch": 2.02, "learning_rate": 5.219320792535892e-06, "loss": 0.2926, "step": 1896 }, { "epoch": 2.02, "learning_rate": 5.2091306907712955e-06, "loss": 0.3313, "step": 1897 }, { "epoch": 2.02, "learning_rate": 5.198947041647786e-06, "loss": 0.2815, "step": 1898 }, { "epoch": 2.02, "learning_rate": 5.188769858881328e-06, "loss": 0.3259, "step": 1899 }, { "epoch": 2.02, "learning_rate": 5.178599156179198e-06, "loss": 0.3367, "step": 1900 }, { "epoch": 2.02, "learning_rate": 5.16843494723992e-06, "loss": 0.2775, "step": 1901 }, { "epoch": 2.02, "learning_rate": 5.158277245753282e-06, "loss": 0.3339, "step": 1902 }, { "epoch": 2.02, "learning_rate": 5.148126065400319e-06, "loss": 0.3421, "step": 1903 }, { "epoch": 2.03, "learning_rate": 5.1379814198532665e-06, "loss": 0.3171, "step": 1904 }, { "epoch": 2.03, "learning_rate": 5.127843322775565e-06, "loss": 0.2943, "step": 1905 }, { "epoch": 2.03, "learning_rate": 5.117711787821836e-06, "loss": 0.3373, "step": 1906 }, { "epoch": 2.03, "learning_rate": 5.1075868286378625e-06, "loss": 0.32, "step": 1907 }, { "epoch": 2.03, "learning_rate": 5.097468458860568e-06, "loss": 0.2568, "step": 1908 }, { "epoch": 2.03, "learning_rate": 5.087356692118004e-06, "loss": 0.2914, "step": 1909 }, { "epoch": 2.03, "learning_rate": 5.077251542029327e-06, "loss": 0.2654, "step": 1910 }, { "epoch": 2.03, "learning_rate": 5.067153022204782e-06, "loss": 0.3217, "step": 1911 }, { "epoch": 2.03, "learning_rate": 5.057061146245681e-06, "loss": 0.4089, "step": 1912 }, { "epoch": 2.03, "learning_rate": 5.046975927744398e-06, "loss": 0.3206, "step": 1913 }, { "epoch": 2.04, "learning_rate": 5.036897380284335e-06, "loss": 0.28, "step": 1914 }, { "epoch": 2.04, "learning_rate": 5.026825517439893e-06, "loss": 0.322, "step": 1915 }, { "epoch": 2.04, "learning_rate": 5.016760352776498e-06, "loss": 0.3042, "step": 1916 }, { "epoch": 2.04, "learning_rate": 5.0067018998505355e-06, "loss": 0.288, "step": 1917 }, { "epoch": 2.04, "learning_rate": 4.996650172209356e-06, "loss": 0.2908, "step": 1918 }, { "epoch": 2.04, "learning_rate": 4.9866051833912535e-06, "loss": 0.2858, "step": 1919 }, { "epoch": 2.04, "learning_rate": 4.976566946925442e-06, "loss": 0.3131, "step": 1920 }, { "epoch": 2.04, "learning_rate": 4.966535476332045e-06, "loss": 0.2817, "step": 1921 }, { "epoch": 2.04, "learning_rate": 4.956510785122068e-06, "loss": 0.2697, "step": 1922 }, { "epoch": 2.05, "learning_rate": 4.946492886797396e-06, "loss": 0.3062, "step": 1923 }, { "epoch": 2.05, "learning_rate": 4.936481794850759e-06, "loss": 0.3667, "step": 1924 }, { "epoch": 2.05, "learning_rate": 4.9264775227657065e-06, "loss": 0.3695, "step": 1925 }, { "epoch": 2.05, "learning_rate": 4.9164800840166286e-06, "loss": 0.275, "step": 1926 }, { "epoch": 2.05, "learning_rate": 4.906489492068693e-06, "loss": 0.3597, "step": 1927 }, { "epoch": 2.05, "learning_rate": 4.89650576037785e-06, "loss": 0.3213, "step": 1928 }, { "epoch": 2.05, "learning_rate": 4.886528902390812e-06, "loss": 0.2947, "step": 1929 }, { "epoch": 2.05, "learning_rate": 4.876558931545035e-06, "loss": 0.2826, "step": 1930 }, { "epoch": 2.05, "learning_rate": 4.866595861268692e-06, "loss": 0.3347, "step": 1931 }, { "epoch": 2.05, "learning_rate": 4.8566397049806645e-06, "loss": 0.3255, "step": 1932 }, { "epoch": 2.06, "learning_rate": 4.846690476090536e-06, "loss": 0.292, "step": 1933 }, { "epoch": 2.06, "learning_rate": 4.836748187998537e-06, "loss": 0.2663, "step": 1934 }, { "epoch": 2.06, "learning_rate": 4.826812854095556e-06, "loss": 0.3411, "step": 1935 }, { "epoch": 2.06, "learning_rate": 4.8168844877631315e-06, "loss": 0.302, "step": 1936 }, { "epoch": 2.06, "learning_rate": 4.8069631023733985e-06, "loss": 0.2953, "step": 1937 }, { "epoch": 2.06, "learning_rate": 4.7970487112890985e-06, "loss": 0.2905, "step": 1938 }, { "epoch": 2.06, "learning_rate": 4.787141327863549e-06, "loss": 0.2677, "step": 1939 }, { "epoch": 2.06, "learning_rate": 4.7772409654406325e-06, "loss": 0.3256, "step": 1940 }, { "epoch": 2.06, "learning_rate": 4.767347637354772e-06, "loss": 0.3312, "step": 1941 }, { "epoch": 2.07, "learning_rate": 4.757461356930916e-06, "loss": 0.2667, "step": 1942 }, { "epoch": 2.07, "learning_rate": 4.7475821374845325e-06, "loss": 0.3079, "step": 1943 }, { "epoch": 2.07, "learning_rate": 4.7377099923215585e-06, "loss": 0.2766, "step": 1944 }, { "epoch": 2.07, "learning_rate": 4.7278449347384124e-06, "loss": 0.3242, "step": 1945 }, { "epoch": 2.07, "learning_rate": 4.7179869780219775e-06, "loss": 0.3116, "step": 1946 }, { "epoch": 2.07, "learning_rate": 4.7081361354495595e-06, "loss": 0.2837, "step": 1947 }, { "epoch": 2.07, "learning_rate": 4.698292420288884e-06, "loss": 0.3869, "step": 1948 }, { "epoch": 2.07, "learning_rate": 4.6884558457980845e-06, "loss": 0.3246, "step": 1949 }, { "epoch": 2.07, "learning_rate": 4.678626425225667e-06, "loss": 0.382, "step": 1950 }, { "epoch": 2.08, "learning_rate": 4.668804171810511e-06, "loss": 0.3053, "step": 1951 }, { "epoch": 2.08, "learning_rate": 4.658989098781832e-06, "loss": 0.253, "step": 1952 }, { "epoch": 2.08, "learning_rate": 4.6491812193591945e-06, "loss": 0.3414, "step": 1953 }, { "epoch": 2.08, "learning_rate": 4.63938054675245e-06, "loss": 0.3258, "step": 1954 }, { "epoch": 2.08, "learning_rate": 4.629587094161754e-06, "loss": 0.3382, "step": 1955 }, { "epoch": 2.08, "learning_rate": 4.6198008747775455e-06, "loss": 0.2686, "step": 1956 }, { "epoch": 2.08, "learning_rate": 4.610021901780516e-06, "loss": 0.3302, "step": 1957 }, { "epoch": 2.08, "learning_rate": 4.60025018834158e-06, "loss": 0.4355, "step": 1958 }, { "epoch": 2.08, "learning_rate": 4.5904857476219056e-06, "loss": 0.2681, "step": 1959 }, { "epoch": 2.08, "learning_rate": 4.580728592772843e-06, "loss": 0.3169, "step": 1960 }, { "epoch": 2.09, "learning_rate": 4.570978736935936e-06, "loss": 0.3064, "step": 1961 }, { "epoch": 2.09, "learning_rate": 4.5612361932428985e-06, "loss": 0.2791, "step": 1962 }, { "epoch": 2.09, "learning_rate": 4.5515009748155935e-06, "loss": 0.2801, "step": 1963 }, { "epoch": 2.09, "learning_rate": 4.541773094766021e-06, "loss": 0.2869, "step": 1964 }, { "epoch": 2.09, "learning_rate": 4.532052566196291e-06, "loss": 0.2925, "step": 1965 }, { "epoch": 2.09, "learning_rate": 4.522339402198624e-06, "loss": 0.3181, "step": 1966 }, { "epoch": 2.09, "learning_rate": 4.512633615855313e-06, "loss": 0.3644, "step": 1967 }, { "epoch": 2.09, "learning_rate": 4.5029352202387066e-06, "loss": 0.2844, "step": 1968 }, { "epoch": 2.09, "learning_rate": 4.493244228411216e-06, "loss": 0.407, "step": 1969 }, { "epoch": 2.1, "learning_rate": 4.483560653425273e-06, "loss": 0.2868, "step": 1970 }, { "epoch": 2.1, "learning_rate": 4.473884508323315e-06, "loss": 0.2782, "step": 1971 }, { "epoch": 2.1, "learning_rate": 4.4642158061377796e-06, "loss": 0.258, "step": 1972 }, { "epoch": 2.1, "learning_rate": 4.454554559891074e-06, "loss": 0.3274, "step": 1973 }, { "epoch": 2.1, "learning_rate": 4.444900782595569e-06, "loss": 0.3038, "step": 1974 }, { "epoch": 2.1, "learning_rate": 4.435254487253569e-06, "loss": 0.3168, "step": 1975 }, { "epoch": 2.1, "learning_rate": 4.425615686857311e-06, "loss": 0.4734, "step": 1976 }, { "epoch": 2.1, "learning_rate": 4.415984394388933e-06, "loss": 0.3, "step": 1977 }, { "epoch": 2.1, "learning_rate": 4.406360622820446e-06, "loss": 0.3142, "step": 1978 }, { "epoch": 2.1, "learning_rate": 4.396744385113758e-06, "loss": 0.332, "step": 1979 }, { "epoch": 2.11, "learning_rate": 4.387135694220613e-06, "loss": 0.4916, "step": 1980 }, { "epoch": 2.11, "learning_rate": 4.3775345630825935e-06, "loss": 0.3353, "step": 1981 }, { "epoch": 2.11, "learning_rate": 4.367941004631101e-06, "loss": 0.3098, "step": 1982 }, { "epoch": 2.11, "learning_rate": 4.358355031787337e-06, "loss": 0.2806, "step": 1983 }, { "epoch": 2.11, "learning_rate": 4.348776657462287e-06, "loss": 0.3306, "step": 1984 }, { "epoch": 2.11, "learning_rate": 4.3392058945566975e-06, "loss": 0.3243, "step": 1985 }, { "epoch": 2.11, "learning_rate": 4.32964275596108e-06, "loss": 0.2825, "step": 1986 }, { "epoch": 2.11, "learning_rate": 4.320087254555653e-06, "loss": 0.3036, "step": 1987 }, { "epoch": 2.11, "learning_rate": 4.310539403210361e-06, "loss": 0.3133, "step": 1988 }, { "epoch": 2.12, "learning_rate": 4.300999214784852e-06, "loss": 0.3244, "step": 1989 }, { "epoch": 2.12, "learning_rate": 4.291466702128443e-06, "loss": 0.3107, "step": 1990 }, { "epoch": 2.12, "learning_rate": 4.281941878080113e-06, "loss": 0.2982, "step": 1991 }, { "epoch": 2.12, "learning_rate": 4.272424755468493e-06, "loss": 0.3318, "step": 1992 }, { "epoch": 2.12, "learning_rate": 4.262915347111831e-06, "loss": 0.2863, "step": 1993 }, { "epoch": 2.12, "learning_rate": 4.2534136658179904e-06, "loss": 0.2842, "step": 1994 }, { "epoch": 2.12, "learning_rate": 4.243919724384432e-06, "loss": 0.2862, "step": 1995 }, { "epoch": 2.12, "learning_rate": 4.234433535598188e-06, "loss": 0.3794, "step": 1996 }, { "epoch": 2.12, "learning_rate": 4.224955112235838e-06, "loss": 0.32, "step": 1997 }, { "epoch": 2.13, "learning_rate": 4.2154844670635235e-06, "loss": 0.3044, "step": 1998 }, { "epoch": 2.13, "learning_rate": 4.206021612836893e-06, "loss": 0.3246, "step": 1999 }, { "epoch": 2.13, "learning_rate": 4.196566562301111e-06, "loss": 0.2769, "step": 2000 }, { "epoch": 2.13, "learning_rate": 4.187119328190827e-06, "loss": 0.3003, "step": 2001 }, { "epoch": 2.13, "learning_rate": 4.177679923230164e-06, "loss": 0.3288, "step": 2002 }, { "epoch": 2.13, "learning_rate": 4.1682483601327015e-06, "loss": 0.2914, "step": 2003 }, { "epoch": 2.13, "learning_rate": 4.158824651601451e-06, "loss": 0.2964, "step": 2004 }, { "epoch": 2.13, "learning_rate": 4.149408810328856e-06, "loss": 0.2982, "step": 2005 }, { "epoch": 2.13, "learning_rate": 4.140000848996761e-06, "loss": 0.3003, "step": 2006 }, { "epoch": 2.13, "learning_rate": 4.130600780276381e-06, "loss": 0.3119, "step": 2007 }, { "epoch": 2.14, "learning_rate": 4.121208616828325e-06, "loss": 0.2856, "step": 2008 }, { "epoch": 2.14, "learning_rate": 4.11182437130254e-06, "loss": 0.2883, "step": 2009 }, { "epoch": 2.14, "learning_rate": 4.1024480563383115e-06, "loss": 0.3374, "step": 2010 }, { "epoch": 2.14, "learning_rate": 4.093079684564246e-06, "loss": 0.3301, "step": 2011 }, { "epoch": 2.14, "learning_rate": 4.083719268598249e-06, "loss": 0.314, "step": 2012 }, { "epoch": 2.14, "learning_rate": 4.074366821047511e-06, "loss": 0.3089, "step": 2013 }, { "epoch": 2.14, "learning_rate": 4.065022354508488e-06, "loss": 0.3111, "step": 2014 }, { "epoch": 2.14, "learning_rate": 4.0556858815668996e-06, "loss": 0.3121, "step": 2015 }, { "epoch": 2.14, "learning_rate": 4.046357414797678e-06, "loss": 0.3118, "step": 2016 }, { "epoch": 2.15, "learning_rate": 4.0370369667649835e-06, "loss": 0.3511, "step": 2017 }, { "epoch": 2.15, "learning_rate": 4.027724550022183e-06, "loss": 0.2948, "step": 2018 }, { "epoch": 2.15, "learning_rate": 4.018420177111816e-06, "loss": 0.2565, "step": 2019 }, { "epoch": 2.15, "learning_rate": 4.009123860565589e-06, "loss": 0.314, "step": 2020 }, { "epoch": 2.15, "learning_rate": 3.999835612904363e-06, "loss": 0.3238, "step": 2021 }, { "epoch": 2.15, "learning_rate": 3.990555446638127e-06, "loss": 0.3392, "step": 2022 }, { "epoch": 2.15, "learning_rate": 3.9812833742659865e-06, "loss": 0.3441, "step": 2023 }, { "epoch": 2.15, "learning_rate": 3.972019408276141e-06, "loss": 0.287, "step": 2024 }, { "epoch": 2.15, "learning_rate": 3.96276356114589e-06, "loss": 0.255, "step": 2025 }, { "epoch": 2.15, "learning_rate": 3.953515845341574e-06, "loss": 0.2904, "step": 2026 }, { "epoch": 2.16, "learning_rate": 3.9442762733185906e-06, "loss": 0.5435, "step": 2027 }, { "epoch": 2.16, "learning_rate": 3.935044857521378e-06, "loss": 0.2596, "step": 2028 }, { "epoch": 2.16, "learning_rate": 3.925821610383379e-06, "loss": 0.2977, "step": 2029 }, { "epoch": 2.16, "learning_rate": 3.916606544327036e-06, "loss": 0.3335, "step": 2030 }, { "epoch": 2.16, "learning_rate": 3.907399671763777e-06, "loss": 0.3144, "step": 2031 }, { "epoch": 2.16, "learning_rate": 3.898201005093986e-06, "loss": 0.3722, "step": 2032 }, { "epoch": 2.16, "learning_rate": 3.889010556707005e-06, "loss": 0.326, "step": 2033 }, { "epoch": 2.16, "learning_rate": 3.879828338981099e-06, "loss": 0.3058, "step": 2034 }, { "epoch": 2.16, "learning_rate": 3.870654364283453e-06, "loss": 0.2929, "step": 2035 }, { "epoch": 2.17, "learning_rate": 3.861488644970144e-06, "loss": 0.2962, "step": 2036 }, { "epoch": 2.17, "learning_rate": 3.852331193386133e-06, "loss": 0.3047, "step": 2037 }, { "epoch": 2.17, "learning_rate": 3.8431820218652516e-06, "loss": 0.328, "step": 2038 }, { "epoch": 2.17, "learning_rate": 3.834041142730174e-06, "loss": 0.28, "step": 2039 }, { "epoch": 2.17, "learning_rate": 3.824908568292393e-06, "loss": 0.3489, "step": 2040 }, { "epoch": 2.17, "learning_rate": 3.815784310852243e-06, "loss": 0.3569, "step": 2041 }, { "epoch": 2.17, "learning_rate": 3.806668382698836e-06, "loss": 0.3186, "step": 2042 }, { "epoch": 2.17, "learning_rate": 3.7975607961100715e-06, "loss": 0.299, "step": 2043 }, { "epoch": 2.17, "learning_rate": 3.7884615633526146e-06, "loss": 0.2934, "step": 2044 }, { "epoch": 2.18, "learning_rate": 3.779370696681878e-06, "loss": 0.2975, "step": 2045 }, { "epoch": 2.18, "learning_rate": 3.770288208342008e-06, "loss": 0.2587, "step": 2046 }, { "epoch": 2.18, "learning_rate": 3.7612141105658606e-06, "loss": 0.2929, "step": 2047 }, { "epoch": 2.18, "learning_rate": 3.7521484155750045e-06, "loss": 0.3596, "step": 2048 }, { "epoch": 2.18, "learning_rate": 3.7430911355796805e-06, "loss": 0.3086, "step": 2049 }, { "epoch": 2.18, "learning_rate": 3.734042282778788e-06, "loss": 0.3117, "step": 2050 }, { "epoch": 2.18, "learning_rate": 3.7250018693598944e-06, "loss": 0.2943, "step": 2051 }, { "epoch": 2.18, "learning_rate": 3.7159699074991894e-06, "loss": 0.3149, "step": 2052 }, { "epoch": 2.18, "learning_rate": 3.7069464093614803e-06, "loss": 0.3168, "step": 2053 }, { "epoch": 2.18, "learning_rate": 3.6979313871001776e-06, "loss": 0.2646, "step": 2054 }, { "epoch": 2.19, "learning_rate": 3.688924852857274e-06, "loss": 0.2945, "step": 2055 }, { "epoch": 2.19, "learning_rate": 3.6799268187633298e-06, "loss": 0.3195, "step": 2056 }, { "epoch": 2.19, "learning_rate": 3.6709372969374546e-06, "loss": 0.3111, "step": 2057 }, { "epoch": 2.19, "learning_rate": 3.661956299487307e-06, "loss": 0.268, "step": 2058 }, { "epoch": 2.19, "learning_rate": 3.652983838509043e-06, "loss": 0.3089, "step": 2059 }, { "epoch": 2.19, "learning_rate": 3.644019926087331e-06, "loss": 0.3031, "step": 2060 }, { "epoch": 2.19, "learning_rate": 3.635064574295335e-06, "loss": 0.3006, "step": 2061 }, { "epoch": 2.19, "learning_rate": 3.6261177951946746e-06, "loss": 0.3012, "step": 2062 }, { "epoch": 2.19, "learning_rate": 3.617179600835431e-06, "loss": 0.352, "step": 2063 }, { "epoch": 2.2, "learning_rate": 3.6082500032561185e-06, "loss": 0.3182, "step": 2064 }, { "epoch": 2.2, "learning_rate": 3.599329014483678e-06, "loss": 0.2917, "step": 2065 }, { "epoch": 2.2, "learning_rate": 3.590416646533451e-06, "loss": 0.2653, "step": 2066 }, { "epoch": 2.2, "learning_rate": 3.5815129114091663e-06, "loss": 0.3833, "step": 2067 }, { "epoch": 2.2, "learning_rate": 3.5726178211029396e-06, "loss": 0.2789, "step": 2068 }, { "epoch": 2.2, "learning_rate": 3.5637313875952205e-06, "loss": 0.2766, "step": 2069 }, { "epoch": 2.2, "learning_rate": 3.5548536228548127e-06, "loss": 0.3206, "step": 2070 }, { "epoch": 2.2, "learning_rate": 3.5459845388388494e-06, "loss": 0.2816, "step": 2071 }, { "epoch": 2.2, "learning_rate": 3.5371241474927597e-06, "loss": 0.2959, "step": 2072 }, { "epoch": 2.2, "learning_rate": 3.5282724607502728e-06, "loss": 0.2701, "step": 2073 }, { "epoch": 2.21, "learning_rate": 3.5194294905333904e-06, "loss": 0.3187, "step": 2074 }, { "epoch": 2.21, "learning_rate": 3.510595248752374e-06, "loss": 0.2902, "step": 2075 }, { "epoch": 2.21, "learning_rate": 3.5017697473057346e-06, "loss": 0.3195, "step": 2076 }, { "epoch": 2.21, "learning_rate": 3.492952998080199e-06, "loss": 0.287, "step": 2077 }, { "epoch": 2.21, "learning_rate": 3.484145012950727e-06, "loss": 0.3141, "step": 2078 }, { "epoch": 2.21, "learning_rate": 3.47534580378045e-06, "loss": 0.3057, "step": 2079 }, { "epoch": 2.21, "learning_rate": 3.466555382420691e-06, "loss": 0.2829, "step": 2080 }, { "epoch": 2.21, "learning_rate": 3.4577737607109442e-06, "loss": 0.3059, "step": 2081 }, { "epoch": 2.21, "learning_rate": 3.4490009504788444e-06, "loss": 0.2781, "step": 2082 }, { "epoch": 2.22, "learning_rate": 3.440236963540148e-06, "loss": 0.3033, "step": 2083 }, { "epoch": 2.22, "learning_rate": 3.4314818116987483e-06, "loss": 0.2977, "step": 2084 }, { "epoch": 2.22, "learning_rate": 3.422735506746626e-06, "loss": 0.4018, "step": 2085 }, { "epoch": 2.22, "learning_rate": 3.413998060463849e-06, "loss": 0.2822, "step": 2086 }, { "epoch": 2.22, "learning_rate": 3.405269484618554e-06, "loss": 0.2765, "step": 2087 }, { "epoch": 2.22, "learning_rate": 3.396549790966931e-06, "loss": 0.2732, "step": 2088 }, { "epoch": 2.22, "learning_rate": 3.387838991253205e-06, "loss": 0.2749, "step": 2089 }, { "epoch": 2.22, "learning_rate": 3.3791370972096218e-06, "loss": 0.2796, "step": 2090 }, { "epoch": 2.22, "learning_rate": 3.3704441205564396e-06, "loss": 0.2624, "step": 2091 }, { "epoch": 2.23, "learning_rate": 3.361760073001901e-06, "loss": 0.32, "step": 2092 }, { "epoch": 2.23, "learning_rate": 3.3530849662422116e-06, "loss": 0.2941, "step": 2093 }, { "epoch": 2.23, "learning_rate": 3.344418811961555e-06, "loss": 0.3291, "step": 2094 }, { "epoch": 2.23, "learning_rate": 3.3357616218320455e-06, "loss": 0.3332, "step": 2095 }, { "epoch": 2.23, "learning_rate": 3.327113407513721e-06, "loss": 0.2972, "step": 2096 }, { "epoch": 2.23, "learning_rate": 3.318474180654545e-06, "loss": 0.2594, "step": 2097 }, { "epoch": 2.23, "learning_rate": 3.309843952890358e-06, "loss": 0.3341, "step": 2098 }, { "epoch": 2.23, "learning_rate": 3.301222735844887e-06, "loss": 0.3077, "step": 2099 }, { "epoch": 2.23, "learning_rate": 3.2926105411297295e-06, "loss": 0.2852, "step": 2100 }, { "epoch": 2.23, "learning_rate": 3.284007380344323e-06, "loss": 0.3049, "step": 2101 }, { "epoch": 2.24, "learning_rate": 3.275413265075941e-06, "loss": 0.3059, "step": 2102 }, { "epoch": 2.24, "learning_rate": 3.2668282068996716e-06, "loss": 0.2875, "step": 2103 }, { "epoch": 2.24, "learning_rate": 3.258252217378407e-06, "loss": 0.3297, "step": 2104 }, { "epoch": 2.24, "learning_rate": 3.2496853080628232e-06, "loss": 0.2819, "step": 2105 }, { "epoch": 2.24, "learning_rate": 3.2411274904913657e-06, "loss": 0.269, "step": 2106 }, { "epoch": 2.24, "learning_rate": 3.2325787761902392e-06, "loss": 0.2598, "step": 2107 }, { "epoch": 2.24, "learning_rate": 3.2240391766733825e-06, "loss": 0.2747, "step": 2108 }, { "epoch": 2.24, "learning_rate": 3.215508703442456e-06, "loss": 0.2863, "step": 2109 }, { "epoch": 2.24, "learning_rate": 3.2069873679868404e-06, "loss": 0.2925, "step": 2110 }, { "epoch": 2.25, "learning_rate": 3.198475181783599e-06, "loss": 0.3084, "step": 2111 }, { "epoch": 2.25, "learning_rate": 3.1899721562974663e-06, "loss": 0.2298, "step": 2112 }, { "epoch": 2.25, "learning_rate": 3.181478302980856e-06, "loss": 0.2615, "step": 2113 }, { "epoch": 2.25, "learning_rate": 3.172993633273813e-06, "loss": 0.2741, "step": 2114 }, { "epoch": 2.25, "learning_rate": 3.1645181586040217e-06, "loss": 0.3128, "step": 2115 }, { "epoch": 2.25, "learning_rate": 3.1560518903867776e-06, "loss": 0.3119, "step": 2116 }, { "epoch": 2.25, "learning_rate": 3.147594840024978e-06, "loss": 0.3201, "step": 2117 }, { "epoch": 2.25, "learning_rate": 3.1391470189091046e-06, "loss": 0.2617, "step": 2118 }, { "epoch": 2.25, "learning_rate": 3.130708438417207e-06, "loss": 0.2742, "step": 2119 }, { "epoch": 2.25, "learning_rate": 3.122279109914895e-06, "loss": 0.2665, "step": 2120 }, { "epoch": 2.26, "learning_rate": 3.113859044755315e-06, "loss": 0.2638, "step": 2121 }, { "epoch": 2.26, "learning_rate": 3.105448254279125e-06, "loss": 0.3105, "step": 2122 }, { "epoch": 2.26, "learning_rate": 3.0970467498145118e-06, "loss": 0.3514, "step": 2123 }, { "epoch": 2.26, "learning_rate": 3.0886545426771387e-06, "loss": 0.2945, "step": 2124 }, { "epoch": 2.26, "learning_rate": 3.0802716441701554e-06, "loss": 0.3043, "step": 2125 }, { "epoch": 2.26, "learning_rate": 3.0718980655841714e-06, "loss": 0.2996, "step": 2126 }, { "epoch": 2.26, "learning_rate": 3.063533818197242e-06, "loss": 0.3216, "step": 2127 }, { "epoch": 2.26, "learning_rate": 3.0551789132748567e-06, "loss": 0.2837, "step": 2128 }, { "epoch": 2.26, "learning_rate": 3.0468333620699208e-06, "loss": 0.3117, "step": 2129 }, { "epoch": 2.27, "learning_rate": 3.0384971758227454e-06, "loss": 0.3086, "step": 2130 }, { "epoch": 2.27, "learning_rate": 3.0301703657610284e-06, "loss": 0.2953, "step": 2131 }, { "epoch": 2.27, "learning_rate": 3.021852943099823e-06, "loss": 0.2924, "step": 2132 }, { "epoch": 2.27, "learning_rate": 3.0135449190415656e-06, "loss": 0.3311, "step": 2133 }, { "epoch": 2.27, "learning_rate": 3.0052463047760138e-06, "loss": 0.2474, "step": 2134 }, { "epoch": 2.27, "learning_rate": 2.9969571114802586e-06, "loss": 0.3193, "step": 2135 }, { "epoch": 2.27, "learning_rate": 2.9886773503187026e-06, "loss": 0.306, "step": 2136 }, { "epoch": 2.27, "learning_rate": 2.9804070324430435e-06, "loss": 0.2995, "step": 2137 }, { "epoch": 2.27, "learning_rate": 2.9721461689922594e-06, "loss": 0.2837, "step": 2138 }, { "epoch": 2.28, "learning_rate": 2.9638947710925937e-06, "loss": 0.3105, "step": 2139 }, { "epoch": 2.28, "learning_rate": 2.955652849857551e-06, "loss": 0.3028, "step": 2140 }, { "epoch": 2.28, "learning_rate": 2.947420416387855e-06, "loss": 0.2463, "step": 2141 }, { "epoch": 2.28, "learning_rate": 2.939197481771461e-06, "loss": 0.2793, "step": 2142 }, { "epoch": 2.28, "learning_rate": 2.9309840570835336e-06, "loss": 0.2675, "step": 2143 }, { "epoch": 2.28, "learning_rate": 2.922780153386422e-06, "loss": 0.263, "step": 2144 }, { "epoch": 2.28, "learning_rate": 2.9145857817296554e-06, "loss": 0.3273, "step": 2145 }, { "epoch": 2.28, "learning_rate": 2.9064009531499225e-06, "loss": 0.3674, "step": 2146 }, { "epoch": 2.28, "learning_rate": 2.8982256786710617e-06, "loss": 0.3001, "step": 2147 }, { "epoch": 2.28, "learning_rate": 2.890059969304041e-06, "loss": 0.3584, "step": 2148 }, { "epoch": 2.29, "learning_rate": 2.881903836046942e-06, "loss": 0.3468, "step": 2149 }, { "epoch": 2.29, "learning_rate": 2.873757289884963e-06, "loss": 0.2666, "step": 2150 }, { "epoch": 2.29, "learning_rate": 2.8656203417903704e-06, "loss": 0.3306, "step": 2151 }, { "epoch": 2.29, "learning_rate": 2.8574930027225123e-06, "loss": 0.2786, "step": 2152 }, { "epoch": 2.29, "learning_rate": 2.849375283627801e-06, "loss": 0.3064, "step": 2153 }, { "epoch": 2.29, "learning_rate": 2.8412671954396833e-06, "loss": 0.3737, "step": 2154 }, { "epoch": 2.29, "learning_rate": 2.8331687490786376e-06, "loss": 0.2806, "step": 2155 }, { "epoch": 2.29, "learning_rate": 2.8250799554521547e-06, "loss": 0.2917, "step": 2156 }, { "epoch": 2.29, "learning_rate": 2.8170008254547265e-06, "loss": 0.3461, "step": 2157 }, { "epoch": 2.3, "learning_rate": 2.8089313699678267e-06, "loss": 0.3096, "step": 2158 }, { "epoch": 2.3, "learning_rate": 2.8008715998599025e-06, "loss": 0.2923, "step": 2159 }, { "epoch": 2.3, "learning_rate": 2.792821525986353e-06, "loss": 0.3149, "step": 2160 }, { "epoch": 2.3, "learning_rate": 2.784781159189519e-06, "loss": 0.3093, "step": 2161 }, { "epoch": 2.3, "learning_rate": 2.7767505102986635e-06, "loss": 0.3262, "step": 2162 }, { "epoch": 2.3, "learning_rate": 2.7687295901299715e-06, "loss": 0.2886, "step": 2163 }, { "epoch": 2.3, "learning_rate": 2.7607184094865182e-06, "loss": 0.2922, "step": 2164 }, { "epoch": 2.3, "learning_rate": 2.7527169791582497e-06, "loss": 0.3167, "step": 2165 }, { "epoch": 2.3, "learning_rate": 2.7447253099220004e-06, "loss": 0.2996, "step": 2166 }, { "epoch": 2.3, "learning_rate": 2.736743412541445e-06, "loss": 0.3229, "step": 2167 }, { "epoch": 2.31, "learning_rate": 2.7287712977671e-06, "loss": 0.2707, "step": 2168 }, { "epoch": 2.31, "learning_rate": 2.7208089763363066e-06, "loss": 0.2861, "step": 2169 }, { "epoch": 2.31, "learning_rate": 2.712856458973213e-06, "loss": 0.2817, "step": 2170 }, { "epoch": 2.31, "learning_rate": 2.7049137563887674e-06, "loss": 0.3495, "step": 2171 }, { "epoch": 2.31, "learning_rate": 2.696980879280692e-06, "loss": 0.3051, "step": 2172 }, { "epoch": 2.31, "learning_rate": 2.6890578383334853e-06, "loss": 0.2836, "step": 2173 }, { "epoch": 2.31, "learning_rate": 2.681144644218392e-06, "loss": 0.3152, "step": 2174 }, { "epoch": 2.31, "learning_rate": 2.673241307593386e-06, "loss": 0.3166, "step": 2175 }, { "epoch": 2.31, "learning_rate": 2.665347839103182e-06, "loss": 0.3129, "step": 2176 }, { "epoch": 2.32, "learning_rate": 2.6574642493791923e-06, "loss": 0.3795, "step": 2177 }, { "epoch": 2.32, "learning_rate": 2.6495905490395267e-06, "loss": 0.2577, "step": 2178 }, { "epoch": 2.32, "learning_rate": 2.641726748688973e-06, "loss": 0.3259, "step": 2179 }, { "epoch": 2.32, "learning_rate": 2.63387285891899e-06, "loss": 0.2893, "step": 2180 }, { "epoch": 2.32, "learning_rate": 2.6260288903076838e-06, "loss": 0.2956, "step": 2181 }, { "epoch": 2.32, "learning_rate": 2.6181948534197964e-06, "loss": 0.306, "step": 2182 }, { "epoch": 2.32, "learning_rate": 2.6103707588067074e-06, "loss": 0.3042, "step": 2183 }, { "epoch": 2.32, "learning_rate": 2.602556617006383e-06, "loss": 0.2827, "step": 2184 }, { "epoch": 2.32, "learning_rate": 2.5947524385433976e-06, "loss": 0.4819, "step": 2185 }, { "epoch": 2.33, "learning_rate": 2.58695823392891e-06, "loss": 0.364, "step": 2186 }, { "epoch": 2.33, "learning_rate": 2.579174013660638e-06, "loss": 0.2992, "step": 2187 }, { "epoch": 2.33, "learning_rate": 2.5713997882228537e-06, "loss": 0.367, "step": 2188 }, { "epoch": 2.33, "learning_rate": 2.563635568086368e-06, "loss": 0.2572, "step": 2189 }, { "epoch": 2.33, "learning_rate": 2.5558813637085158e-06, "loss": 0.3073, "step": 2190 }, { "epoch": 2.33, "learning_rate": 2.5481371855331415e-06, "loss": 0.3207, "step": 2191 }, { "epoch": 2.33, "learning_rate": 2.540403043990586e-06, "loss": 0.2869, "step": 2192 }, { "epoch": 2.33, "learning_rate": 2.532678949497679e-06, "loss": 0.3005, "step": 2193 }, { "epoch": 2.33, "learning_rate": 2.5249649124577037e-06, "loss": 0.2467, "step": 2194 }, { "epoch": 2.33, "learning_rate": 2.5172609432604066e-06, "loss": 0.2653, "step": 2195 }, { "epoch": 2.34, "learning_rate": 2.509567052281978e-06, "loss": 0.2999, "step": 2196 }, { "epoch": 2.34, "learning_rate": 2.5018832498850277e-06, "loss": 0.3073, "step": 2197 }, { "epoch": 2.34, "learning_rate": 2.494209546418577e-06, "loss": 0.3186, "step": 2198 }, { "epoch": 2.34, "learning_rate": 2.4865459522180492e-06, "loss": 0.3247, "step": 2199 }, { "epoch": 2.34, "learning_rate": 2.478892477605248e-06, "loss": 0.277, "step": 2200 }, { "epoch": 2.34, "learning_rate": 2.4712491328883505e-06, "loss": 0.2903, "step": 2201 }, { "epoch": 2.34, "learning_rate": 2.463615928361891e-06, "loss": 0.2842, "step": 2202 }, { "epoch": 2.34, "learning_rate": 2.4559928743067475e-06, "loss": 0.3831, "step": 2203 }, { "epoch": 2.34, "learning_rate": 2.4483799809901133e-06, "loss": 0.2493, "step": 2204 }, { "epoch": 2.35, "learning_rate": 2.4407772586655175e-06, "loss": 0.3968, "step": 2205 }, { "epoch": 2.35, "learning_rate": 2.4331847175727753e-06, "loss": 0.2661, "step": 2206 }, { "epoch": 2.35, "learning_rate": 2.425602367937995e-06, "loss": 0.2514, "step": 2207 }, { "epoch": 2.35, "learning_rate": 2.4180302199735572e-06, "loss": 0.369, "step": 2208 }, { "epoch": 2.35, "learning_rate": 2.410468283878101e-06, "loss": 0.2946, "step": 2209 }, { "epoch": 2.35, "learning_rate": 2.4029165698365142e-06, "loss": 0.2795, "step": 2210 }, { "epoch": 2.35, "learning_rate": 2.395375088019911e-06, "loss": 0.4135, "step": 2211 }, { "epoch": 2.35, "learning_rate": 2.387843848585639e-06, "loss": 0.2988, "step": 2212 }, { "epoch": 2.35, "learning_rate": 2.3803228616772313e-06, "loss": 0.3037, "step": 2213 }, { "epoch": 2.35, "learning_rate": 2.3728121374244205e-06, "loss": 0.2874, "step": 2214 }, { "epoch": 2.36, "learning_rate": 2.3653116859431246e-06, "loss": 0.284, "step": 2215 }, { "epoch": 2.36, "learning_rate": 2.3578215173354146e-06, "loss": 0.3003, "step": 2216 }, { "epoch": 2.36, "learning_rate": 2.3503416416895174e-06, "loss": 0.2916, "step": 2217 }, { "epoch": 2.36, "learning_rate": 2.3428720690797933e-06, "loss": 0.2907, "step": 2218 }, { "epoch": 2.36, "learning_rate": 2.3354128095667293e-06, "loss": 0.311, "step": 2219 }, { "epoch": 2.36, "learning_rate": 2.32796387319692e-06, "loss": 0.2643, "step": 2220 }, { "epoch": 2.36, "learning_rate": 2.3205252700030544e-06, "loss": 0.2931, "step": 2221 }, { "epoch": 2.36, "learning_rate": 2.3130970100039153e-06, "loss": 0.3155, "step": 2222 }, { "epoch": 2.36, "learning_rate": 2.3056791032043356e-06, "loss": 0.2741, "step": 2223 }, { "epoch": 2.37, "learning_rate": 2.2982715595952142e-06, "loss": 0.3198, "step": 2224 }, { "epoch": 2.37, "learning_rate": 2.2908743891535003e-06, "loss": 0.3205, "step": 2225 }, { "epoch": 2.37, "learning_rate": 2.283487601842157e-06, "loss": 0.2795, "step": 2226 }, { "epoch": 2.37, "learning_rate": 2.276111207610173e-06, "loss": 0.269, "step": 2227 }, { "epoch": 2.37, "learning_rate": 2.268745216392533e-06, "loss": 0.2769, "step": 2228 }, { "epoch": 2.37, "learning_rate": 2.261389638110213e-06, "loss": 0.4443, "step": 2229 }, { "epoch": 2.37, "learning_rate": 2.2540444826701646e-06, "loss": 0.2749, "step": 2230 }, { "epoch": 2.37, "learning_rate": 2.2467097599653e-06, "loss": 0.2591, "step": 2231 }, { "epoch": 2.37, "learning_rate": 2.23938547987448e-06, "loss": 0.3168, "step": 2232 }, { "epoch": 2.38, "learning_rate": 2.2320716522625017e-06, "loss": 0.3427, "step": 2233 }, { "epoch": 2.38, "learning_rate": 2.22476828698008e-06, "loss": 0.3391, "step": 2234 }, { "epoch": 2.38, "learning_rate": 2.2174753938638495e-06, "loss": 0.3251, "step": 2235 }, { "epoch": 2.38, "learning_rate": 2.21019298273633e-06, "loss": 0.3094, "step": 2236 }, { "epoch": 2.38, "learning_rate": 2.2029210634059206e-06, "loss": 0.3125, "step": 2237 }, { "epoch": 2.38, "learning_rate": 2.195659645666901e-06, "loss": 0.3186, "step": 2238 }, { "epoch": 2.38, "learning_rate": 2.188408739299399e-06, "loss": 0.307, "step": 2239 }, { "epoch": 2.38, "learning_rate": 2.181168354069386e-06, "loss": 0.317, "step": 2240 }, { "epoch": 2.38, "learning_rate": 2.173938499728666e-06, "loss": 0.2615, "step": 2241 }, { "epoch": 2.38, "learning_rate": 2.166719186014854e-06, "loss": 0.2885, "step": 2242 }, { "epoch": 2.39, "learning_rate": 2.159510422651373e-06, "loss": 0.3175, "step": 2243 }, { "epoch": 2.39, "learning_rate": 2.152312219347431e-06, "loss": 0.3035, "step": 2244 }, { "epoch": 2.39, "learning_rate": 2.1451245857980217e-06, "loss": 0.3513, "step": 2245 }, { "epoch": 2.39, "learning_rate": 2.1379475316838995e-06, "loss": 0.3455, "step": 2246 }, { "epoch": 2.39, "learning_rate": 2.1307810666715567e-06, "loss": 0.2988, "step": 2247 }, { "epoch": 2.39, "learning_rate": 2.123625200413243e-06, "loss": 0.2924, "step": 2248 }, { "epoch": 2.39, "learning_rate": 2.116479942546924e-06, "loss": 0.2768, "step": 2249 }, { "epoch": 2.39, "learning_rate": 2.1093453026962764e-06, "loss": 0.3275, "step": 2250 }, { "epoch": 2.39, "learning_rate": 2.1022212904706783e-06, "loss": 0.2607, "step": 2251 }, { "epoch": 2.4, "learning_rate": 2.0951079154651923e-06, "loss": 0.3241, "step": 2252 }, { "epoch": 2.4, "learning_rate": 2.0880051872605533e-06, "loss": 0.3253, "step": 2253 }, { "epoch": 2.4, "learning_rate": 2.0809131154231587e-06, "loss": 0.3061, "step": 2254 }, { "epoch": 2.4, "learning_rate": 2.073831709505054e-06, "loss": 0.288, "step": 2255 }, { "epoch": 2.4, "learning_rate": 2.0667609790439215e-06, "loss": 0.2806, "step": 2256 }, { "epoch": 2.4, "learning_rate": 2.0597009335630493e-06, "loss": 0.3423, "step": 2257 }, { "epoch": 2.4, "learning_rate": 2.0526515825713565e-06, "loss": 0.2592, "step": 2258 }, { "epoch": 2.4, "learning_rate": 2.045612935563346e-06, "loss": 0.3238, "step": 2259 }, { "epoch": 2.4, "learning_rate": 2.0385850020191034e-06, "loss": 0.3153, "step": 2260 }, { "epoch": 2.4, "learning_rate": 2.0315677914042887e-06, "loss": 0.2614, "step": 2261 }, { "epoch": 2.41, "learning_rate": 2.024561313170118e-06, "loss": 0.2969, "step": 2262 }, { "epoch": 2.41, "learning_rate": 2.0175655767533532e-06, "loss": 0.2992, "step": 2263 }, { "epoch": 2.41, "learning_rate": 2.0105805915762834e-06, "loss": 0.3276, "step": 2264 }, { "epoch": 2.41, "learning_rate": 2.00360636704673e-06, "loss": 0.3055, "step": 2265 }, { "epoch": 2.41, "learning_rate": 1.9966429125580057e-06, "loss": 0.3073, "step": 2266 }, { "epoch": 2.41, "learning_rate": 1.9896902374889225e-06, "loss": 0.3391, "step": 2267 }, { "epoch": 2.41, "learning_rate": 1.982748351203785e-06, "loss": 0.2938, "step": 2268 }, { "epoch": 2.41, "learning_rate": 1.9758172630523507e-06, "loss": 0.3034, "step": 2269 }, { "epoch": 2.41, "learning_rate": 1.9688969823698457e-06, "loss": 0.3253, "step": 2270 }, { "epoch": 2.42, "learning_rate": 1.961987518476931e-06, "loss": 0.3142, "step": 2271 }, { "epoch": 2.42, "learning_rate": 1.955088880679704e-06, "loss": 0.3312, "step": 2272 }, { "epoch": 2.42, "learning_rate": 1.9482010782696793e-06, "loss": 0.2405, "step": 2273 }, { "epoch": 2.42, "learning_rate": 1.9413241205237766e-06, "loss": 0.2999, "step": 2274 }, { "epoch": 2.42, "learning_rate": 1.934458016704317e-06, "loss": 0.2945, "step": 2275 }, { "epoch": 2.42, "learning_rate": 1.927602776058991e-06, "loss": 0.3091, "step": 2276 }, { "epoch": 2.42, "learning_rate": 1.9207584078208608e-06, "loss": 0.3042, "step": 2277 }, { "epoch": 2.42, "learning_rate": 1.9139249212083554e-06, "loss": 0.3118, "step": 2278 }, { "epoch": 2.42, "learning_rate": 1.9071023254252353e-06, "loss": 0.2995, "step": 2279 }, { "epoch": 2.43, "learning_rate": 1.9002906296605993e-06, "loss": 0.2989, "step": 2280 }, { "epoch": 2.43, "learning_rate": 1.8934898430888614e-06, "loss": 0.2901, "step": 2281 }, { "epoch": 2.43, "learning_rate": 1.8866999748697457e-06, "loss": 0.296, "step": 2282 }, { "epoch": 2.43, "learning_rate": 1.8799210341482698e-06, "loss": 0.3037, "step": 2283 }, { "epoch": 2.43, "learning_rate": 1.8731530300547319e-06, "loss": 0.3048, "step": 2284 }, { "epoch": 2.43, "learning_rate": 1.8663959717047032e-06, "loss": 0.3102, "step": 2285 }, { "epoch": 2.43, "learning_rate": 1.8596498681990083e-06, "loss": 0.3011, "step": 2286 }, { "epoch": 2.43, "learning_rate": 1.8529147286237181e-06, "loss": 0.3303, "step": 2287 }, { "epoch": 2.43, "learning_rate": 1.846190562050143e-06, "loss": 0.3031, "step": 2288 }, { "epoch": 2.43, "learning_rate": 1.8394773775348085e-06, "loss": 0.3058, "step": 2289 }, { "epoch": 2.44, "learning_rate": 1.832775184119443e-06, "loss": 0.3682, "step": 2290 }, { "epoch": 2.44, "learning_rate": 1.8260839908309846e-06, "loss": 0.3253, "step": 2291 }, { "epoch": 2.44, "learning_rate": 1.8194038066815478e-06, "loss": 0.282, "step": 2292 }, { "epoch": 2.44, "learning_rate": 1.8127346406684188e-06, "loss": 0.297, "step": 2293 }, { "epoch": 2.44, "learning_rate": 1.8060765017740466e-06, "loss": 0.3124, "step": 2294 }, { "epoch": 2.44, "learning_rate": 1.799429398966027e-06, "loss": 0.3002, "step": 2295 }, { "epoch": 2.44, "learning_rate": 1.7927933411970922e-06, "loss": 0.2805, "step": 2296 }, { "epoch": 2.44, "learning_rate": 1.7861683374050954e-06, "loss": 0.3097, "step": 2297 }, { "epoch": 2.44, "learning_rate": 1.7795543965130091e-06, "loss": 0.274, "step": 2298 }, { "epoch": 2.45, "learning_rate": 1.772951527428901e-06, "loss": 0.2812, "step": 2299 }, { "epoch": 2.45, "learning_rate": 1.7663597390459176e-06, "loss": 0.32, "step": 2300 }, { "epoch": 2.45, "learning_rate": 1.7597790402422987e-06, "loss": 0.3153, "step": 2301 }, { "epoch": 2.45, "learning_rate": 1.753209439881337e-06, "loss": 0.2838, "step": 2302 }, { "epoch": 2.45, "learning_rate": 1.7466509468113757e-06, "loss": 0.2902, "step": 2303 }, { "epoch": 2.45, "learning_rate": 1.7401035698658098e-06, "loss": 0.3265, "step": 2304 }, { "epoch": 2.45, "learning_rate": 1.7335673178630463e-06, "loss": 0.3006, "step": 2305 }, { "epoch": 2.45, "learning_rate": 1.7270421996065167e-06, "loss": 0.2938, "step": 2306 }, { "epoch": 2.45, "learning_rate": 1.720528223884661e-06, "loss": 0.3124, "step": 2307 }, { "epoch": 2.45, "learning_rate": 1.7140253994709077e-06, "loss": 0.2886, "step": 2308 }, { "epoch": 2.46, "learning_rate": 1.7075337351236588e-06, "loss": 0.3439, "step": 2309 }, { "epoch": 2.46, "learning_rate": 1.7010532395862988e-06, "loss": 0.2915, "step": 2310 }, { "epoch": 2.46, "learning_rate": 1.6945839215871595e-06, "loss": 0.3685, "step": 2311 }, { "epoch": 2.46, "learning_rate": 1.688125789839522e-06, "loss": 0.2971, "step": 2312 }, { "epoch": 2.46, "learning_rate": 1.6816788530416005e-06, "loss": 0.3234, "step": 2313 }, { "epoch": 2.46, "learning_rate": 1.6752431198765308e-06, "loss": 0.2854, "step": 2314 }, { "epoch": 2.46, "learning_rate": 1.6688185990123574e-06, "loss": 0.3636, "step": 2315 }, { "epoch": 2.46, "learning_rate": 1.6624052991020245e-06, "loss": 0.2488, "step": 2316 }, { "epoch": 2.46, "learning_rate": 1.6560032287833682e-06, "loss": 0.2604, "step": 2317 }, { "epoch": 2.47, "learning_rate": 1.6496123966790957e-06, "loss": 0.2693, "step": 2318 }, { "epoch": 2.47, "learning_rate": 1.6432328113967698e-06, "loss": 0.2752, "step": 2319 }, { "epoch": 2.47, "learning_rate": 1.6368644815288194e-06, "loss": 0.2741, "step": 2320 }, { "epoch": 2.47, "learning_rate": 1.630507415652507e-06, "loss": 0.3835, "step": 2321 }, { "epoch": 2.47, "learning_rate": 1.624161622329924e-06, "loss": 0.3216, "step": 2322 }, { "epoch": 2.47, "learning_rate": 1.61782711010798e-06, "loss": 0.3373, "step": 2323 }, { "epoch": 2.47, "learning_rate": 1.611503887518391e-06, "loss": 0.2989, "step": 2324 }, { "epoch": 2.47, "learning_rate": 1.6051919630776658e-06, "loss": 0.2922, "step": 2325 }, { "epoch": 2.47, "learning_rate": 1.5988913452870958e-06, "loss": 0.3418, "step": 2326 }, { "epoch": 2.48, "learning_rate": 1.5926020426327503e-06, "loss": 0.2988, "step": 2327 }, { "epoch": 2.48, "learning_rate": 1.5863240635854526e-06, "loss": 0.3174, "step": 2328 }, { "epoch": 2.48, "learning_rate": 1.5800574166007687e-06, "loss": 0.2664, "step": 2329 }, { "epoch": 2.48, "learning_rate": 1.5738021101190171e-06, "loss": 0.2628, "step": 2330 }, { "epoch": 2.48, "learning_rate": 1.5675581525652317e-06, "loss": 0.3845, "step": 2331 }, { "epoch": 2.48, "learning_rate": 1.5613255523491622e-06, "loss": 0.3744, "step": 2332 }, { "epoch": 2.48, "learning_rate": 1.5551043178652624e-06, "loss": 0.3031, "step": 2333 }, { "epoch": 2.48, "learning_rate": 1.5488944574926801e-06, "loss": 0.3547, "step": 2334 }, { "epoch": 2.48, "learning_rate": 1.5426959795952412e-06, "loss": 0.2508, "step": 2335 }, { "epoch": 2.48, "learning_rate": 1.5365088925214389e-06, "loss": 0.2656, "step": 2336 }, { "epoch": 2.49, "learning_rate": 1.530333204604434e-06, "loss": 0.3272, "step": 2337 }, { "epoch": 2.49, "learning_rate": 1.5241689241620206e-06, "loss": 0.2988, "step": 2338 }, { "epoch": 2.49, "learning_rate": 1.5180160594966364e-06, "loss": 0.3144, "step": 2339 }, { "epoch": 2.49, "learning_rate": 1.511874618895346e-06, "loss": 0.2585, "step": 2340 }, { "epoch": 2.49, "learning_rate": 1.5057446106298224e-06, "loss": 0.336, "step": 2341 }, { "epoch": 2.49, "learning_rate": 1.4996260429563426e-06, "loss": 0.3108, "step": 2342 }, { "epoch": 2.49, "learning_rate": 1.4935189241157744e-06, "loss": 0.3236, "step": 2343 }, { "epoch": 2.49, "learning_rate": 1.487423262333565e-06, "loss": 0.2675, "step": 2344 }, { "epoch": 2.49, "learning_rate": 1.4813390658197325e-06, "loss": 0.2807, "step": 2345 }, { "epoch": 2.5, "learning_rate": 1.4752663427688473e-06, "loss": 0.2744, "step": 2346 }, { "epoch": 2.5, "learning_rate": 1.4692051013600394e-06, "loss": 0.3214, "step": 2347 }, { "epoch": 2.5, "learning_rate": 1.4631553497569594e-06, "loss": 0.2798, "step": 2348 }, { "epoch": 2.5, "learning_rate": 1.4571170961077896e-06, "loss": 0.3067, "step": 2349 }, { "epoch": 2.5, "learning_rate": 1.4510903485452289e-06, "loss": 0.3108, "step": 2350 }, { "epoch": 2.5, "learning_rate": 1.4450751151864751e-06, "loss": 0.3076, "step": 2351 }, { "epoch": 2.5, "learning_rate": 1.4390714041332187e-06, "loss": 0.2828, "step": 2352 }, { "epoch": 2.5, "learning_rate": 1.4330792234716318e-06, "loss": 0.325, "step": 2353 }, { "epoch": 2.5, "learning_rate": 1.427098581272356e-06, "loss": 0.3509, "step": 2354 }, { "epoch": 2.5, "learning_rate": 1.4211294855904922e-06, "loss": 0.2735, "step": 2355 }, { "epoch": 2.51, "learning_rate": 1.4151719444655898e-06, "loss": 0.2847, "step": 2356 }, { "epoch": 2.51, "learning_rate": 1.4092259659216411e-06, "loss": 0.3024, "step": 2357 }, { "epoch": 2.51, "learning_rate": 1.4032915579670536e-06, "loss": 0.3058, "step": 2358 }, { "epoch": 2.51, "learning_rate": 1.397368728594658e-06, "loss": 0.2815, "step": 2359 }, { "epoch": 2.51, "learning_rate": 1.3914574857816943e-06, "loss": 0.3021, "step": 2360 }, { "epoch": 2.51, "learning_rate": 1.3855578374897927e-06, "loss": 0.3173, "step": 2361 }, { "epoch": 2.51, "learning_rate": 1.3796697916649582e-06, "loss": 0.3268, "step": 2362 }, { "epoch": 2.51, "learning_rate": 1.373793356237586e-06, "loss": 0.3033, "step": 2363 }, { "epoch": 2.51, "learning_rate": 1.3679285391224229e-06, "loss": 0.3019, "step": 2364 }, { "epoch": 2.52, "learning_rate": 1.362075348218569e-06, "loss": 0.3555, "step": 2365 }, { "epoch": 2.52, "learning_rate": 1.3562337914094658e-06, "loss": 0.2275, "step": 2366 }, { "epoch": 2.52, "learning_rate": 1.350403876562888e-06, "loss": 0.2999, "step": 2367 }, { "epoch": 2.52, "learning_rate": 1.3445856115309253e-06, "loss": 0.2957, "step": 2368 }, { "epoch": 2.52, "learning_rate": 1.3387790041499793e-06, "loss": 0.3076, "step": 2369 }, { "epoch": 2.52, "learning_rate": 1.332984062240753e-06, "loss": 0.3433, "step": 2370 }, { "epoch": 2.52, "learning_rate": 1.3272007936082353e-06, "loss": 0.2742, "step": 2371 }, { "epoch": 2.52, "learning_rate": 1.3214292060416878e-06, "loss": 0.332, "step": 2372 }, { "epoch": 2.52, "learning_rate": 1.3156693073146476e-06, "loss": 0.4268, "step": 2373 }, { "epoch": 2.53, "learning_rate": 1.3099211051849047e-06, "loss": 0.2905, "step": 2374 }, { "epoch": 2.53, "learning_rate": 1.3041846073944953e-06, "loss": 0.3026, "step": 2375 }, { "epoch": 2.53, "learning_rate": 1.298459821669692e-06, "loss": 0.2653, "step": 2376 }, { "epoch": 2.53, "learning_rate": 1.2927467557209917e-06, "loss": 0.2898, "step": 2377 }, { "epoch": 2.53, "learning_rate": 1.287045417243108e-06, "loss": 0.2726, "step": 2378 }, { "epoch": 2.53, "learning_rate": 1.2813558139149574e-06, "loss": 0.2574, "step": 2379 }, { "epoch": 2.53, "learning_rate": 1.2756779533996544e-06, "loss": 0.2728, "step": 2380 }, { "epoch": 2.53, "learning_rate": 1.2700118433444953e-06, "loss": 0.3219, "step": 2381 }, { "epoch": 2.53, "learning_rate": 1.2643574913809442e-06, "loss": 0.3055, "step": 2382 }, { "epoch": 2.53, "learning_rate": 1.2587149051246416e-06, "loss": 0.3, "step": 2383 }, { "epoch": 2.54, "learning_rate": 1.2530840921753706e-06, "loss": 0.2769, "step": 2384 }, { "epoch": 2.54, "learning_rate": 1.2474650601170602e-06, "loss": 0.3123, "step": 2385 }, { "epoch": 2.54, "learning_rate": 1.241857816517774e-06, "loss": 0.2893, "step": 2386 }, { "epoch": 2.54, "learning_rate": 1.236262368929696e-06, "loss": 0.2796, "step": 2387 }, { "epoch": 2.54, "learning_rate": 1.230678724889124e-06, "loss": 0.355, "step": 2388 }, { "epoch": 2.54, "learning_rate": 1.2251068919164543e-06, "loss": 0.3113, "step": 2389 }, { "epoch": 2.54, "learning_rate": 1.2195468775161855e-06, "loss": 0.2818, "step": 2390 }, { "epoch": 2.54, "learning_rate": 1.2139986891768852e-06, "loss": 0.3391, "step": 2391 }, { "epoch": 2.54, "learning_rate": 1.2084623343711987e-06, "loss": 0.2484, "step": 2392 }, { "epoch": 2.55, "learning_rate": 1.2029378205558373e-06, "loss": 0.2969, "step": 2393 }, { "epoch": 2.55, "learning_rate": 1.1974251551715587e-06, "loss": 0.2917, "step": 2394 }, { "epoch": 2.55, "learning_rate": 1.1919243456431628e-06, "loss": 0.2589, "step": 2395 }, { "epoch": 2.55, "learning_rate": 1.186435399379483e-06, "loss": 0.3764, "step": 2396 }, { "epoch": 2.55, "learning_rate": 1.1809583237733736e-06, "loss": 0.2478, "step": 2397 }, { "epoch": 2.55, "learning_rate": 1.175493126201701e-06, "loss": 0.268, "step": 2398 }, { "epoch": 2.55, "learning_rate": 1.1700398140253322e-06, "loss": 0.414, "step": 2399 }, { "epoch": 2.55, "learning_rate": 1.1645983945891338e-06, "loss": 0.3083, "step": 2400 }, { "epoch": 2.55, "learning_rate": 1.159168875221941e-06, "loss": 0.3029, "step": 2401 }, { "epoch": 2.55, "learning_rate": 1.15375126323657e-06, "loss": 0.3799, "step": 2402 }, { "epoch": 2.56, "learning_rate": 1.1483455659298004e-06, "loss": 0.2691, "step": 2403 }, { "epoch": 2.56, "learning_rate": 1.1429517905823618e-06, "loss": 0.2459, "step": 2404 }, { "epoch": 2.56, "learning_rate": 1.137569944458925e-06, "loss": 0.2698, "step": 2405 }, { "epoch": 2.56, "learning_rate": 1.1322000348080964e-06, "loss": 0.3023, "step": 2406 }, { "epoch": 2.56, "learning_rate": 1.1268420688624037e-06, "loss": 0.2782, "step": 2407 }, { "epoch": 2.56, "learning_rate": 1.121496053838288e-06, "loss": 0.3242, "step": 2408 }, { "epoch": 2.56, "learning_rate": 1.1161619969361014e-06, "loss": 0.325, "step": 2409 }, { "epoch": 2.56, "learning_rate": 1.1108399053400766e-06, "loss": 0.2786, "step": 2410 }, { "epoch": 2.56, "learning_rate": 1.105529786218339e-06, "loss": 0.2785, "step": 2411 }, { "epoch": 2.57, "learning_rate": 1.1002316467228913e-06, "loss": 0.3144, "step": 2412 }, { "epoch": 2.57, "learning_rate": 1.0949454939895954e-06, "loss": 0.3147, "step": 2413 }, { "epoch": 2.57, "learning_rate": 1.0896713351381716e-06, "loss": 0.3212, "step": 2414 }, { "epoch": 2.57, "learning_rate": 1.0844091772721854e-06, "loss": 0.3322, "step": 2415 }, { "epoch": 2.57, "learning_rate": 1.0791590274790375e-06, "loss": 0.2754, "step": 2416 }, { "epoch": 2.57, "learning_rate": 1.0739208928299582e-06, "loss": 0.3526, "step": 2417 }, { "epoch": 2.57, "learning_rate": 1.0686947803799897e-06, "loss": 0.2984, "step": 2418 }, { "epoch": 2.57, "learning_rate": 1.0634806971679933e-06, "loss": 0.3032, "step": 2419 }, { "epoch": 2.57, "learning_rate": 1.0582786502166132e-06, "loss": 0.3004, "step": 2420 }, { "epoch": 2.58, "learning_rate": 1.053088646532292e-06, "loss": 0.308, "step": 2421 }, { "epoch": 2.58, "learning_rate": 1.0479106931052518e-06, "loss": 0.2738, "step": 2422 }, { "epoch": 2.58, "learning_rate": 1.0427447969094828e-06, "loss": 0.292, "step": 2423 }, { "epoch": 2.58, "learning_rate": 1.037590964902734e-06, "loss": 0.2864, "step": 2424 }, { "epoch": 2.58, "learning_rate": 1.0324492040265077e-06, "loss": 0.3196, "step": 2425 }, { "epoch": 2.58, "learning_rate": 1.0273195212060483e-06, "loss": 0.3342, "step": 2426 }, { "epoch": 2.58, "learning_rate": 1.0222019233503312e-06, "loss": 0.4013, "step": 2427 }, { "epoch": 2.58, "learning_rate": 1.0170964173520536e-06, "loss": 0.2842, "step": 2428 }, { "epoch": 2.58, "learning_rate": 1.0120030100876354e-06, "loss": 0.2843, "step": 2429 }, { "epoch": 2.58, "learning_rate": 1.006921708417189e-06, "loss": 0.2859, "step": 2430 }, { "epoch": 2.59, "learning_rate": 1.0018525191845273e-06, "loss": 0.2833, "step": 2431 }, { "epoch": 2.59, "learning_rate": 9.967954492171539e-07, "loss": 0.2515, "step": 2432 }, { "epoch": 2.59, "learning_rate": 9.917505053262467e-07, "loss": 0.299, "step": 2433 }, { "epoch": 2.59, "learning_rate": 9.867176943066425e-07, "loss": 0.3133, "step": 2434 }, { "epoch": 2.59, "learning_rate": 9.816970229368505e-07, "loss": 0.2952, "step": 2435 }, { "epoch": 2.59, "learning_rate": 9.766884979790238e-07, "loss": 0.2699, "step": 2436 }, { "epoch": 2.59, "learning_rate": 9.716921261789537e-07, "loss": 0.3072, "step": 2437 }, { "epoch": 2.59, "learning_rate": 9.667079142660652e-07, "loss": 0.3559, "step": 2438 }, { "epoch": 2.59, "learning_rate": 9.617358689534052e-07, "loss": 0.3725, "step": 2439 }, { "epoch": 2.6, "learning_rate": 9.567759969376344e-07, "loss": 0.2518, "step": 2440 }, { "epoch": 2.6, "learning_rate": 9.518283048990152e-07, "loss": 0.2896, "step": 2441 }, { "epoch": 2.6, "learning_rate": 9.468927995014099e-07, "loss": 0.2788, "step": 2442 }, { "epoch": 2.6, "learning_rate": 9.419694873922658e-07, "loss": 0.2873, "step": 2443 }, { "epoch": 2.6, "learning_rate": 9.370583752026008e-07, "loss": 0.2911, "step": 2444 }, { "epoch": 2.6, "learning_rate": 9.321594695470115e-07, "loss": 0.2803, "step": 2445 }, { "epoch": 2.6, "learning_rate": 9.272727770236478e-07, "loss": 0.325, "step": 2446 }, { "epoch": 2.6, "learning_rate": 9.223983042142104e-07, "loss": 0.2883, "step": 2447 }, { "epoch": 2.6, "learning_rate": 9.175360576839431e-07, "loss": 0.3159, "step": 2448 }, { "epoch": 2.6, "learning_rate": 9.126860439816231e-07, "loss": 0.3155, "step": 2449 }, { "epoch": 2.61, "learning_rate": 9.078482696395497e-07, "loss": 0.2805, "step": 2450 }, { "epoch": 2.61, "learning_rate": 9.030227411735382e-07, "loss": 0.2913, "step": 2451 }, { "epoch": 2.61, "learning_rate": 8.982094650829132e-07, "loss": 0.3357, "step": 2452 }, { "epoch": 2.61, "learning_rate": 8.934084478504945e-07, "loss": 0.2975, "step": 2453 }, { "epoch": 2.61, "learning_rate": 8.886196959425875e-07, "loss": 0.2878, "step": 2454 }, { "epoch": 2.61, "learning_rate": 8.838432158089838e-07, "loss": 0.2998, "step": 2455 }, { "epoch": 2.61, "learning_rate": 8.790790138829452e-07, "loss": 0.2893, "step": 2456 }, { "epoch": 2.61, "learning_rate": 8.743270965811945e-07, "loss": 0.3259, "step": 2457 }, { "epoch": 2.61, "learning_rate": 8.695874703039086e-07, "loss": 0.3489, "step": 2458 }, { "epoch": 2.62, "learning_rate": 8.648601414347135e-07, "loss": 0.3085, "step": 2459 }, { "epoch": 2.62, "learning_rate": 8.601451163406682e-07, "loss": 0.3042, "step": 2460 }, { "epoch": 2.62, "learning_rate": 8.554424013722617e-07, "loss": 0.3, "step": 2461 }, { "epoch": 2.62, "learning_rate": 8.507520028634075e-07, "loss": 0.2779, "step": 2462 }, { "epoch": 2.62, "learning_rate": 8.460739271314223e-07, "loss": 0.3916, "step": 2463 }, { "epoch": 2.62, "learning_rate": 8.41408180477028e-07, "loss": 0.2934, "step": 2464 }, { "epoch": 2.62, "learning_rate": 8.36754769184348e-07, "loss": 0.2792, "step": 2465 }, { "epoch": 2.62, "learning_rate": 8.321136995208834e-07, "loss": 0.2642, "step": 2466 }, { "epoch": 2.62, "learning_rate": 8.27484977737516e-07, "loss": 0.2964, "step": 2467 }, { "epoch": 2.63, "learning_rate": 8.228686100684979e-07, "loss": 0.3739, "step": 2468 }, { "epoch": 2.63, "learning_rate": 8.182646027314378e-07, "loss": 0.278, "step": 2469 }, { "epoch": 2.63, "learning_rate": 8.13672961927302e-07, "loss": 0.3288, "step": 2470 }, { "epoch": 2.63, "learning_rate": 8.090936938403959e-07, "loss": 0.3085, "step": 2471 }, { "epoch": 2.63, "learning_rate": 8.045268046383669e-07, "loss": 0.2963, "step": 2472 }, { "epoch": 2.63, "learning_rate": 7.999723004721815e-07, "loss": 0.2832, "step": 2473 }, { "epoch": 2.63, "learning_rate": 7.954301874761295e-07, "loss": 0.2853, "step": 2474 }, { "epoch": 2.63, "learning_rate": 7.909004717678137e-07, "loss": 0.3918, "step": 2475 }, { "epoch": 2.63, "learning_rate": 7.863831594481375e-07, "loss": 0.2837, "step": 2476 }, { "epoch": 2.63, "learning_rate": 7.818782566012983e-07, "loss": 0.3028, "step": 2477 }, { "epoch": 2.64, "learning_rate": 7.773857692947773e-07, "loss": 0.2911, "step": 2478 }, { "epoch": 2.64, "learning_rate": 7.729057035793385e-07, "loss": 0.3425, "step": 2479 }, { "epoch": 2.64, "learning_rate": 7.684380654890123e-07, "loss": 0.2884, "step": 2480 }, { "epoch": 2.64, "learning_rate": 7.639828610410916e-07, "loss": 0.2779, "step": 2481 }, { "epoch": 2.64, "learning_rate": 7.595400962361254e-07, "loss": 0.3213, "step": 2482 }, { "epoch": 2.64, "learning_rate": 7.551097770579041e-07, "loss": 0.2814, "step": 2483 }, { "epoch": 2.64, "learning_rate": 7.506919094734544e-07, "loss": 0.3422, "step": 2484 }, { "epoch": 2.64, "learning_rate": 7.46286499433041e-07, "loss": 0.3082, "step": 2485 }, { "epoch": 2.64, "learning_rate": 7.418935528701443e-07, "loss": 0.2941, "step": 2486 }, { "epoch": 2.65, "learning_rate": 7.375130757014515e-07, "loss": 0.3134, "step": 2487 }, { "epoch": 2.65, "learning_rate": 7.331450738268686e-07, "loss": 0.2955, "step": 2488 }, { "epoch": 2.65, "learning_rate": 7.287895531294908e-07, "loss": 0.326, "step": 2489 }, { "epoch": 2.65, "learning_rate": 7.244465194756045e-07, "loss": 0.3148, "step": 2490 }, { "epoch": 2.65, "learning_rate": 7.201159787146772e-07, "loss": 0.3329, "step": 2491 }, { "epoch": 2.65, "learning_rate": 7.1579793667935e-07, "loss": 0.2952, "step": 2492 }, { "epoch": 2.65, "learning_rate": 7.114923991854328e-07, "loss": 0.3149, "step": 2493 }, { "epoch": 2.65, "learning_rate": 7.071993720318892e-07, "loss": 0.3142, "step": 2494 }, { "epoch": 2.65, "learning_rate": 7.029188610008387e-07, "loss": 0.2773, "step": 2495 }, { "epoch": 2.65, "learning_rate": 6.986508718575402e-07, "loss": 0.224, "step": 2496 }, { "epoch": 2.66, "learning_rate": 6.943954103503814e-07, "loss": 0.2541, "step": 2497 }, { "epoch": 2.66, "learning_rate": 6.901524822108885e-07, "loss": 0.2723, "step": 2498 }, { "epoch": 2.66, "learning_rate": 6.859220931536992e-07, "loss": 0.3165, "step": 2499 }, { "epoch": 2.66, "learning_rate": 6.817042488765657e-07, "loss": 0.2926, "step": 2500 }, { "epoch": 2.66, "learning_rate": 6.774989550603428e-07, "loss": 0.2978, "step": 2501 }, { "epoch": 2.66, "learning_rate": 6.733062173689819e-07, "loss": 0.341, "step": 2502 }, { "epoch": 2.66, "learning_rate": 6.691260414495238e-07, "loss": 0.2969, "step": 2503 }, { "epoch": 2.66, "learning_rate": 6.649584329320879e-07, "loss": 0.2842, "step": 2504 }, { "epoch": 2.66, "learning_rate": 6.60803397429871e-07, "loss": 0.3014, "step": 2505 }, { "epoch": 2.67, "learning_rate": 6.566609405391355e-07, "loss": 0.2675, "step": 2506 }, { "epoch": 2.67, "learning_rate": 6.525310678391938e-07, "loss": 0.3063, "step": 2507 }, { "epoch": 2.67, "learning_rate": 6.48413784892421e-07, "loss": 0.3257, "step": 2508 }, { "epoch": 2.67, "learning_rate": 6.443090972442279e-07, "loss": 0.3353, "step": 2509 }, { "epoch": 2.67, "learning_rate": 6.402170104230643e-07, "loss": 0.2933, "step": 2510 }, { "epoch": 2.67, "learning_rate": 6.361375299404082e-07, "loss": 0.2683, "step": 2511 }, { "epoch": 2.67, "learning_rate": 6.320706612907556e-07, "loss": 0.3029, "step": 2512 }, { "epoch": 2.67, "learning_rate": 6.280164099516195e-07, "loss": 0.2715, "step": 2513 }, { "epoch": 2.67, "learning_rate": 6.239747813835196e-07, "loss": 0.3518, "step": 2514 }, { "epoch": 2.67, "learning_rate": 6.199457810299725e-07, "loss": 0.3221, "step": 2515 }, { "epoch": 2.68, "learning_rate": 6.159294143174832e-07, "loss": 0.3077, "step": 2516 }, { "epoch": 2.68, "learning_rate": 6.11925686655549e-07, "loss": 0.2856, "step": 2517 }, { "epoch": 2.68, "learning_rate": 6.079346034366373e-07, "loss": 0.2817, "step": 2518 }, { "epoch": 2.68, "learning_rate": 6.039561700361874e-07, "loss": 0.2861, "step": 2519 }, { "epoch": 2.68, "learning_rate": 5.999903918126027e-07, "loss": 0.3263, "step": 2520 }, { "epoch": 2.68, "learning_rate": 5.960372741072384e-07, "loss": 0.3356, "step": 2521 }, { "epoch": 2.68, "learning_rate": 5.920968222444002e-07, "loss": 0.3718, "step": 2522 }, { "epoch": 2.68, "learning_rate": 5.881690415313335e-07, "loss": 0.3283, "step": 2523 }, { "epoch": 2.68, "learning_rate": 5.84253937258219e-07, "loss": 0.299, "step": 2524 }, { "epoch": 2.69, "learning_rate": 5.803515146981642e-07, "loss": 0.2975, "step": 2525 }, { "epoch": 2.69, "learning_rate": 5.764617791071913e-07, "loss": 0.2862, "step": 2526 }, { "epoch": 2.69, "learning_rate": 5.725847357242398e-07, "loss": 0.3537, "step": 2527 }, { "epoch": 2.69, "learning_rate": 5.687203897711546e-07, "loss": 0.3135, "step": 2528 }, { "epoch": 2.69, "learning_rate": 5.648687464526759e-07, "loss": 0.2904, "step": 2529 }, { "epoch": 2.69, "learning_rate": 5.610298109564371e-07, "loss": 0.3068, "step": 2530 }, { "epoch": 2.69, "learning_rate": 5.572035884529559e-07, "loss": 0.2833, "step": 2531 }, { "epoch": 2.69, "learning_rate": 5.533900840956275e-07, "loss": 0.3782, "step": 2532 }, { "epoch": 2.69, "learning_rate": 5.495893030207133e-07, "loss": 0.2888, "step": 2533 }, { "epoch": 2.7, "learning_rate": 5.458012503473486e-07, "loss": 0.2719, "step": 2534 }, { "epoch": 2.7, "learning_rate": 5.420259311775123e-07, "loss": 0.3067, "step": 2535 }, { "epoch": 2.7, "learning_rate": 5.38263350596041e-07, "loss": 0.3422, "step": 2536 }, { "epoch": 2.7, "learning_rate": 5.345135136706147e-07, "loss": 0.31, "step": 2537 }, { "epoch": 2.7, "learning_rate": 5.307764254517467e-07, "loss": 0.2722, "step": 2538 }, { "epoch": 2.7, "learning_rate": 5.270520909727783e-07, "loss": 0.4017, "step": 2539 }, { "epoch": 2.7, "learning_rate": 5.23340515249876e-07, "loss": 0.2953, "step": 2540 }, { "epoch": 2.7, "learning_rate": 5.196417032820222e-07, "loss": 0.3061, "step": 2541 }, { "epoch": 2.7, "learning_rate": 5.159556600510051e-07, "loss": 0.2996, "step": 2542 }, { "epoch": 2.7, "learning_rate": 5.122823905214169e-07, "loss": 0.3105, "step": 2543 }, { "epoch": 2.71, "learning_rate": 5.0862189964065e-07, "loss": 0.3055, "step": 2544 }, { "epoch": 2.71, "learning_rate": 5.049741923388774e-07, "loss": 0.3006, "step": 2545 }, { "epoch": 2.71, "learning_rate": 5.013392735290579e-07, "loss": 0.2782, "step": 2546 }, { "epoch": 2.71, "learning_rate": 4.977171481069288e-07, "loss": 0.3181, "step": 2547 }, { "epoch": 2.71, "learning_rate": 4.941078209509942e-07, "loss": 0.2866, "step": 2548 }, { "epoch": 2.71, "learning_rate": 4.905112969225201e-07, "loss": 0.3128, "step": 2549 }, { "epoch": 2.71, "learning_rate": 4.869275808655272e-07, "loss": 0.2778, "step": 2550 }, { "epoch": 2.71, "learning_rate": 4.833566776067899e-07, "loss": 0.2864, "step": 2551 }, { "epoch": 2.71, "learning_rate": 4.797985919558224e-07, "loss": 0.2848, "step": 2552 }, { "epoch": 2.72, "learning_rate": 4.762533287048743e-07, "loss": 0.2813, "step": 2553 }, { "epoch": 2.72, "learning_rate": 4.727208926289306e-07, "loss": 0.306, "step": 2554 }, { "epoch": 2.72, "learning_rate": 4.6920128848569336e-07, "loss": 0.2579, "step": 2555 }, { "epoch": 2.72, "learning_rate": 4.656945210155828e-07, "loss": 0.2738, "step": 2556 }, { "epoch": 2.72, "learning_rate": 4.622005949417363e-07, "loss": 0.2949, "step": 2557 }, { "epoch": 2.72, "learning_rate": 4.5871951496998857e-07, "loss": 0.3185, "step": 2558 }, { "epoch": 2.72, "learning_rate": 4.5525128578887355e-07, "loss": 0.3016, "step": 2559 }, { "epoch": 2.72, "learning_rate": 4.5179591206962023e-07, "loss": 0.3033, "step": 2560 }, { "epoch": 2.72, "learning_rate": 4.4835339846614145e-07, "loss": 0.3962, "step": 2561 }, { "epoch": 2.72, "learning_rate": 4.4492374961502717e-07, "loss": 0.3564, "step": 2562 }, { "epoch": 2.73, "learning_rate": 4.4150697013554344e-07, "loss": 0.3341, "step": 2563 }, { "epoch": 2.73, "learning_rate": 4.3810306462962027e-07, "loss": 0.3578, "step": 2564 }, { "epoch": 2.73, "learning_rate": 4.3471203768185034e-07, "loss": 0.2911, "step": 2565 }, { "epoch": 2.73, "learning_rate": 4.313338938594791e-07, "loss": 0.346, "step": 2566 }, { "epoch": 2.73, "learning_rate": 4.279686377124026e-07, "loss": 0.2989, "step": 2567 }, { "epoch": 2.73, "learning_rate": 4.246162737731574e-07, "loss": 0.3379, "step": 2568 }, { "epoch": 2.73, "learning_rate": 4.212768065569128e-07, "loss": 0.3774, "step": 2569 }, { "epoch": 2.73, "learning_rate": 4.1795024056147435e-07, "loss": 0.2919, "step": 2570 }, { "epoch": 2.73, "learning_rate": 4.1463658026726806e-07, "loss": 0.3267, "step": 2571 }, { "epoch": 2.74, "learning_rate": 4.11335830137336e-07, "loss": 0.2753, "step": 2572 }, { "epoch": 2.74, "learning_rate": 4.080479946173366e-07, "loss": 0.3182, "step": 2573 }, { "epoch": 2.74, "learning_rate": 4.047730781355286e-07, "loss": 0.3183, "step": 2574 }, { "epoch": 2.74, "learning_rate": 4.015110851027759e-07, "loss": 0.3593, "step": 2575 }, { "epoch": 2.74, "learning_rate": 3.9826201991253087e-07, "loss": 0.3056, "step": 2576 }, { "epoch": 2.74, "learning_rate": 3.9502588694083964e-07, "loss": 0.2504, "step": 2577 }, { "epoch": 2.74, "learning_rate": 3.918026905463279e-07, "loss": 0.3247, "step": 2578 }, { "epoch": 2.74, "learning_rate": 3.8859243507019416e-07, "loss": 0.3012, "step": 2579 }, { "epoch": 2.74, "learning_rate": 3.853951248362131e-07, "loss": 0.3815, "step": 2580 }, { "epoch": 2.75, "learning_rate": 3.8221076415072e-07, "loss": 0.2948, "step": 2581 }, { "epoch": 2.75, "learning_rate": 3.7903935730260965e-07, "loss": 0.272, "step": 2582 }, { "epoch": 2.75, "learning_rate": 3.7588090856333193e-07, "loss": 0.3682, "step": 2583 }, { "epoch": 2.75, "learning_rate": 3.7273542218688173e-07, "loss": 0.3021, "step": 2584 }, { "epoch": 2.75, "learning_rate": 3.6960290240979467e-07, "loss": 0.2713, "step": 2585 }, { "epoch": 2.75, "learning_rate": 3.664833534511436e-07, "loss": 0.3311, "step": 2586 }, { "epoch": 2.75, "learning_rate": 3.6337677951253427e-07, "loss": 0.3093, "step": 2587 }, { "epoch": 2.75, "learning_rate": 3.6028318477809077e-07, "loss": 0.3272, "step": 2588 }, { "epoch": 2.75, "learning_rate": 3.5720257341445906e-07, "loss": 0.3477, "step": 2589 }, { "epoch": 2.75, "learning_rate": 3.541349495707991e-07, "loss": 0.3034, "step": 2590 }, { "epoch": 2.76, "learning_rate": 3.5108031737877913e-07, "loss": 0.29, "step": 2591 }, { "epoch": 2.76, "learning_rate": 3.48038680952566e-07, "loss": 0.2961, "step": 2592 }, { "epoch": 2.76, "learning_rate": 3.45010044388826e-07, "loss": 0.3005, "step": 2593 }, { "epoch": 2.76, "learning_rate": 3.4199441176671513e-07, "loss": 0.2571, "step": 2594 }, { "epoch": 2.76, "learning_rate": 3.389917871478743e-07, "loss": 0.3183, "step": 2595 }, { "epoch": 2.76, "learning_rate": 3.3600217457642523e-07, "loss": 0.3107, "step": 2596 }, { "epoch": 2.76, "learning_rate": 3.330255780789682e-07, "loss": 0.2916, "step": 2597 }, { "epoch": 2.76, "learning_rate": 3.3006200166456504e-07, "loss": 0.2799, "step": 2598 }, { "epoch": 2.76, "learning_rate": 3.2711144932474294e-07, "loss": 0.3171, "step": 2599 }, { "epoch": 2.77, "learning_rate": 3.241739250334952e-07, "loss": 0.302, "step": 2600 }, { "epoch": 2.77, "learning_rate": 3.212494327472582e-07, "loss": 0.4394, "step": 2601 }, { "epoch": 2.77, "learning_rate": 3.1833797640492214e-07, "loss": 0.2586, "step": 2602 }, { "epoch": 2.77, "learning_rate": 3.154395599278159e-07, "loss": 0.3034, "step": 2603 }, { "epoch": 2.77, "learning_rate": 3.125541872197102e-07, "loss": 0.2884, "step": 2604 }, { "epoch": 2.77, "learning_rate": 3.0968186216680184e-07, "loss": 0.2895, "step": 2605 }, { "epoch": 2.77, "learning_rate": 3.068225886377163e-07, "loss": 0.2638, "step": 2606 }, { "epoch": 2.77, "learning_rate": 3.039763704835064e-07, "loss": 0.3357, "step": 2607 }, { "epoch": 2.77, "learning_rate": 3.0114321153763114e-07, "loss": 0.2862, "step": 2608 }, { "epoch": 2.77, "learning_rate": 2.983231156159661e-07, "loss": 0.3061, "step": 2609 }, { "epoch": 2.78, "learning_rate": 2.955160865167928e-07, "loss": 0.285, "step": 2610 }, { "epoch": 2.78, "learning_rate": 2.927221280207948e-07, "loss": 0.3008, "step": 2611 }, { "epoch": 2.78, "learning_rate": 2.899412438910454e-07, "loss": 0.3328, "step": 2612 }, { "epoch": 2.78, "learning_rate": 2.87173437873014e-07, "loss": 0.2548, "step": 2613 }, { "epoch": 2.78, "learning_rate": 2.844187136945564e-07, "loss": 0.3113, "step": 2614 }, { "epoch": 2.78, "learning_rate": 2.816770750659026e-07, "loss": 0.2494, "step": 2615 }, { "epoch": 2.78, "learning_rate": 2.789485256796665e-07, "loss": 0.3027, "step": 2616 }, { "epoch": 2.78, "learning_rate": 2.7623306921082507e-07, "loss": 0.3035, "step": 2617 }, { "epoch": 2.78, "learning_rate": 2.7353070931672496e-07, "loss": 0.3753, "step": 2618 }, { "epoch": 2.79, "learning_rate": 2.708414496370726e-07, "loss": 0.2949, "step": 2619 }, { "epoch": 2.79, "learning_rate": 2.6816529379393274e-07, "loss": 0.2928, "step": 2620 }, { "epoch": 2.79, "learning_rate": 2.6550224539171555e-07, "loss": 0.3179, "step": 2621 }, { "epoch": 2.79, "learning_rate": 2.6285230801718186e-07, "loss": 0.3081, "step": 2622 }, { "epoch": 2.79, "learning_rate": 2.602154852394323e-07, "loss": 0.2652, "step": 2623 }, { "epoch": 2.79, "learning_rate": 2.5759178060990265e-07, "loss": 0.3371, "step": 2624 }, { "epoch": 2.79, "learning_rate": 2.5498119766236285e-07, "loss": 0.3114, "step": 2625 }, { "epoch": 2.79, "learning_rate": 2.523837399129103e-07, "loss": 0.2833, "step": 2626 }, { "epoch": 2.79, "learning_rate": 2.4979941085995994e-07, "loss": 0.2797, "step": 2627 }, { "epoch": 2.8, "learning_rate": 2.4722821398424747e-07, "loss": 0.2894, "step": 2628 }, { "epoch": 2.8, "learning_rate": 2.4467015274882266e-07, "loss": 0.2946, "step": 2629 }, { "epoch": 2.8, "learning_rate": 2.4212523059903956e-07, "loss": 0.2936, "step": 2630 }, { "epoch": 2.8, "learning_rate": 2.3959345096255973e-07, "loss": 0.3199, "step": 2631 }, { "epoch": 2.8, "learning_rate": 2.370748172493409e-07, "loss": 0.2993, "step": 2632 }, { "epoch": 2.8, "learning_rate": 2.345693328516352e-07, "loss": 0.3034, "step": 2633 }, { "epoch": 2.8, "learning_rate": 2.3207700114398546e-07, "loss": 0.3149, "step": 2634 }, { "epoch": 2.8, "learning_rate": 2.2959782548321873e-07, "loss": 0.2779, "step": 2635 }, { "epoch": 2.8, "learning_rate": 2.2713180920844403e-07, "loss": 0.2601, "step": 2636 }, { "epoch": 2.8, "learning_rate": 2.2467895564104448e-07, "loss": 0.3507, "step": 2637 }, { "epoch": 2.81, "learning_rate": 2.2223926808467632e-07, "loss": 0.3265, "step": 2638 }, { "epoch": 2.81, "learning_rate": 2.1981274982526447e-07, "loss": 0.3197, "step": 2639 }, { "epoch": 2.81, "learning_rate": 2.1739940413099347e-07, "loss": 0.2611, "step": 2640 }, { "epoch": 2.81, "learning_rate": 2.149992342523055e-07, "loss": 0.3152, "step": 2641 }, { "epoch": 2.81, "learning_rate": 2.1261224342190135e-07, "loss": 0.3011, "step": 2642 }, { "epoch": 2.81, "learning_rate": 2.1023843485472927e-07, "loss": 0.2956, "step": 2643 }, { "epoch": 2.81, "learning_rate": 2.078778117479807e-07, "loss": 0.3147, "step": 2644 }, { "epoch": 2.81, "learning_rate": 2.0553037728109128e-07, "loss": 0.2868, "step": 2645 }, { "epoch": 2.81, "learning_rate": 2.0319613461573072e-07, "loss": 0.2732, "step": 2646 }, { "epoch": 2.82, "learning_rate": 2.0087508689580314e-07, "loss": 0.316, "step": 2647 }, { "epoch": 2.82, "learning_rate": 1.9856723724743788e-07, "loss": 0.303, "step": 2648 }, { "epoch": 2.82, "learning_rate": 1.9627258877899403e-07, "loss": 0.3197, "step": 2649 }, { "epoch": 2.82, "learning_rate": 1.9399114458104718e-07, "loss": 0.2699, "step": 2650 }, { "epoch": 2.82, "learning_rate": 1.917229077263838e-07, "loss": 0.3091, "step": 2651 }, { "epoch": 2.82, "learning_rate": 1.8946788127001126e-07, "loss": 0.2583, "step": 2652 }, { "epoch": 2.82, "learning_rate": 1.8722606824913668e-07, "loss": 0.2883, "step": 2653 }, { "epoch": 2.82, "learning_rate": 1.8499747168317595e-07, "loss": 0.2828, "step": 2654 }, { "epoch": 2.82, "learning_rate": 1.827820945737391e-07, "loss": 0.3233, "step": 2655 }, { "epoch": 2.82, "learning_rate": 1.8057993990463596e-07, "loss": 0.3391, "step": 2656 }, { "epoch": 2.83, "learning_rate": 1.7839101064186403e-07, "loss": 0.3266, "step": 2657 }, { "epoch": 2.83, "learning_rate": 1.7621530973360944e-07, "loss": 0.2685, "step": 2658 }, { "epoch": 2.83, "learning_rate": 1.740528401102448e-07, "loss": 0.3657, "step": 2659 }, { "epoch": 2.83, "learning_rate": 1.7190360468431476e-07, "loss": 0.287, "step": 2660 }, { "epoch": 2.83, "learning_rate": 1.697676063505449e-07, "loss": 0.3705, "step": 2661 }, { "epoch": 2.83, "learning_rate": 1.676448479858317e-07, "loss": 0.3031, "step": 2662 }, { "epoch": 2.83, "learning_rate": 1.6553533244923702e-07, "loss": 0.2771, "step": 2663 }, { "epoch": 2.83, "learning_rate": 1.6343906258198927e-07, "loss": 0.2974, "step": 2664 }, { "epoch": 2.83, "learning_rate": 1.6135604120747328e-07, "loss": 0.395, "step": 2665 }, { "epoch": 2.84, "learning_rate": 1.5928627113123374e-07, "loss": 0.313, "step": 2666 }, { "epoch": 2.84, "learning_rate": 1.5722975514096518e-07, "loss": 0.3081, "step": 2667 }, { "epoch": 2.84, "learning_rate": 1.551864960065097e-07, "loss": 0.2724, "step": 2668 }, { "epoch": 2.84, "learning_rate": 1.531564964798593e-07, "loss": 0.2968, "step": 2669 }, { "epoch": 2.84, "learning_rate": 1.5113975929514025e-07, "loss": 0.2738, "step": 2670 }, { "epoch": 2.84, "learning_rate": 1.4913628716862195e-07, "loss": 0.2812, "step": 2671 }, { "epoch": 2.84, "learning_rate": 1.471460827987048e-07, "loss": 0.281, "step": 2672 }, { "epoch": 2.84, "learning_rate": 1.4516914886592014e-07, "loss": 0.2925, "step": 2673 }, { "epoch": 2.84, "learning_rate": 1.4320548803292588e-07, "loss": 0.3194, "step": 2674 }, { "epoch": 2.85, "learning_rate": 1.4125510294450307e-07, "loss": 0.2505, "step": 2675 }, { "epoch": 2.85, "learning_rate": 1.3931799622754928e-07, "loss": 0.2945, "step": 2676 }, { "epoch": 2.85, "learning_rate": 1.3739417049108416e-07, "loss": 0.2763, "step": 2677 }, { "epoch": 2.85, "learning_rate": 1.3548362832623175e-07, "loss": 0.2737, "step": 2678 }, { "epoch": 2.85, "learning_rate": 1.335863723062336e-07, "loss": 0.3041, "step": 2679 }, { "epoch": 2.85, "learning_rate": 1.3170240498643017e-07, "loss": 0.2876, "step": 2680 }, { "epoch": 2.85, "learning_rate": 1.29831728904265e-07, "loss": 0.2828, "step": 2681 }, { "epoch": 2.85, "learning_rate": 1.2797434657928153e-07, "loss": 0.275, "step": 2682 }, { "epoch": 2.85, "learning_rate": 1.2613026051312093e-07, "loss": 0.3537, "step": 2683 }, { "epoch": 2.85, "learning_rate": 1.2429947318950863e-07, "loss": 0.2986, "step": 2684 }, { "epoch": 2.86, "learning_rate": 1.224819870742655e-07, "loss": 0.2887, "step": 2685 }, { "epoch": 2.86, "learning_rate": 1.2067780461529455e-07, "loss": 0.2669, "step": 2686 }, { "epoch": 2.86, "learning_rate": 1.1888692824258085e-07, "loss": 0.2927, "step": 2687 }, { "epoch": 2.86, "learning_rate": 1.1710936036818832e-07, "loss": 0.2878, "step": 2688 }, { "epoch": 2.86, "learning_rate": 1.1534510338625626e-07, "loss": 0.2832, "step": 2689 }, { "epoch": 2.86, "learning_rate": 1.1359415967299614e-07, "loss": 0.3058, "step": 2690 }, { "epoch": 2.86, "learning_rate": 1.1185653158668707e-07, "loss": 0.3513, "step": 2691 }, { "epoch": 2.86, "learning_rate": 1.1013222146767477e-07, "loss": 0.2912, "step": 2692 }, { "epoch": 2.86, "learning_rate": 1.0842123163836926e-07, "loss": 0.3351, "step": 2693 }, { "epoch": 2.87, "learning_rate": 1.0672356440323606e-07, "loss": 0.3055, "step": 2694 }, { "epoch": 2.87, "learning_rate": 1.0503922204879946e-07, "loss": 0.3464, "step": 2695 }, { "epoch": 2.87, "learning_rate": 1.0336820684363813e-07, "loss": 0.3061, "step": 2696 }, { "epoch": 2.87, "learning_rate": 1.017105210383773e-07, "loss": 0.2973, "step": 2697 }, { "epoch": 2.87, "learning_rate": 1.0006616686569215e-07, "loss": 0.2986, "step": 2698 }, { "epoch": 2.87, "learning_rate": 9.843514654030217e-08, "loss": 0.3149, "step": 2699 }, { "epoch": 2.87, "learning_rate": 9.681746225896682e-08, "loss": 0.304, "step": 2700 }, { "epoch": 2.87, "learning_rate": 9.521311620048213e-08, "loss": 0.3206, "step": 2701 }, { "epoch": 2.87, "learning_rate": 9.362211052568404e-08, "loss": 0.2932, "step": 2702 }, { "epoch": 2.87, "learning_rate": 9.204444737743735e-08, "loss": 0.2863, "step": 2703 }, { "epoch": 2.88, "learning_rate": 9.048012888063562e-08, "loss": 0.3716, "step": 2704 }, { "epoch": 2.88, "learning_rate": 8.89291571422013e-08, "loss": 0.2672, "step": 2705 }, { "epoch": 2.88, "learning_rate": 8.739153425107893e-08, "loss": 0.2962, "step": 2706 }, { "epoch": 2.88, "learning_rate": 8.586726227823638e-08, "loss": 0.2797, "step": 2707 }, { "epoch": 2.88, "learning_rate": 8.435634327665698e-08, "loss": 0.3061, "step": 2708 }, { "epoch": 2.88, "learning_rate": 8.285877928134068e-08, "loss": 0.2951, "step": 2709 }, { "epoch": 2.88, "learning_rate": 8.137457230929957e-08, "loss": 0.3451, "step": 2710 }, { "epoch": 2.88, "learning_rate": 7.990372435955685e-08, "loss": 0.2948, "step": 2711 }, { "epoch": 2.88, "learning_rate": 7.844623741314228e-08, "loss": 0.32, "step": 2712 }, { "epoch": 2.89, "learning_rate": 7.700211343308783e-08, "loss": 0.3308, "step": 2713 }, { "epoch": 2.89, "learning_rate": 7.557135436443097e-08, "loss": 0.3052, "step": 2714 }, { "epoch": 2.89, "learning_rate": 7.4153962134208e-08, "loss": 0.3195, "step": 2715 }, { "epoch": 2.89, "learning_rate": 7.274993865145075e-08, "loss": 0.2934, "step": 2716 }, { "epoch": 2.89, "learning_rate": 7.135928580718432e-08, "loss": 0.2665, "step": 2717 }, { "epoch": 2.89, "learning_rate": 6.998200547442824e-08, "loss": 0.2932, "step": 2718 }, { "epoch": 2.89, "learning_rate": 6.861809950818754e-08, "loss": 0.3022, "step": 2719 }, { "epoch": 2.89, "learning_rate": 6.726756974545612e-08, "loss": 0.2656, "step": 2720 }, { "epoch": 2.89, "learning_rate": 6.593041800521227e-08, "loss": 0.3222, "step": 2721 }, { "epoch": 2.9, "learning_rate": 6.460664608841538e-08, "loss": 0.2997, "step": 2722 }, { "epoch": 2.9, "learning_rate": 6.329625577800369e-08, "loss": 0.2996, "step": 2723 }, { "epoch": 2.9, "learning_rate": 6.199924883889097e-08, "loss": 0.3252, "step": 2724 }, { "epoch": 2.9, "learning_rate": 6.071562701796985e-08, "loss": 0.2804, "step": 2725 }, { "epoch": 2.9, "learning_rate": 5.9445392044099606e-08, "loss": 0.3799, "step": 2726 }, { "epoch": 2.9, "learning_rate": 5.818854562811171e-08, "loss": 0.2898, "step": 2727 }, { "epoch": 2.9, "learning_rate": 5.6945089462807635e-08, "loss": 0.2765, "step": 2728 }, { "epoch": 2.9, "learning_rate": 5.5715025222948804e-08, "loss": 0.3022, "step": 2729 }, { "epoch": 2.9, "learning_rate": 5.449835456526442e-08, "loss": 0.3775, "step": 2730 }, { "epoch": 2.9, "learning_rate": 5.329507912844034e-08, "loss": 0.3107, "step": 2731 }, { "epoch": 2.91, "learning_rate": 5.210520053312573e-08, "loss": 0.2861, "step": 2732 }, { "epoch": 2.91, "learning_rate": 5.092872038191976e-08, "loss": 0.2661, "step": 2733 }, { "epoch": 2.91, "learning_rate": 4.976564025938047e-08, "loss": 0.2929, "step": 2734 }, { "epoch": 2.91, "learning_rate": 4.86159617320181e-08, "loss": 0.3633, "step": 2735 }, { "epoch": 2.91, "learning_rate": 4.747968634828959e-08, "loss": 0.3238, "step": 2736 }, { "epoch": 2.91, "learning_rate": 4.6356815638601836e-08, "loss": 0.3005, "step": 2737 }, { "epoch": 2.91, "learning_rate": 4.52473511153062e-08, "loss": 0.3158, "step": 2738 }, { "epoch": 2.91, "learning_rate": 4.4151294272700706e-08, "loss": 0.301, "step": 2739 }, { "epoch": 2.91, "learning_rate": 4.306864658702004e-08, "loss": 0.271, "step": 2740 }, { "epoch": 2.92, "learning_rate": 4.199940951644443e-08, "loss": 0.2907, "step": 2741 }, { "epoch": 2.92, "learning_rate": 4.0943584501087485e-08, "loss": 0.3382, "step": 2742 }, { "epoch": 2.92, "learning_rate": 3.9901172962999444e-08, "loss": 0.3226, "step": 2743 }, { "epoch": 2.92, "learning_rate": 3.887217630616613e-08, "loss": 0.2898, "step": 2744 }, { "epoch": 2.92, "learning_rate": 3.785659591650448e-08, "loss": 0.3057, "step": 2745 }, { "epoch": 2.92, "learning_rate": 3.685443316186032e-08, "loss": 0.3326, "step": 2746 }, { "epoch": 2.92, "learning_rate": 3.5865689392009517e-08, "loss": 0.2945, "step": 2747 }, { "epoch": 2.92, "learning_rate": 3.489036593865458e-08, "loss": 0.2796, "step": 2748 }, { "epoch": 2.92, "learning_rate": 3.3928464115420276e-08, "loss": 0.3025, "step": 2749 }, { "epoch": 2.92, "learning_rate": 3.2979985217855835e-08, "loss": 0.3093, "step": 2750 }, { "epoch": 2.93, "learning_rate": 3.204493052343383e-08, "loss": 0.2651, "step": 2751 }, { "epoch": 2.93, "learning_rate": 3.112330129154128e-08, "loss": 0.2727, "step": 2752 }, { "epoch": 2.93, "learning_rate": 3.0215098763487495e-08, "loss": 0.3325, "step": 2753 }, { "epoch": 2.93, "learning_rate": 2.9320324162496195e-08, "loss": 0.2797, "step": 2754 }, { "epoch": 2.93, "learning_rate": 2.8438978693705598e-08, "loss": 0.302, "step": 2755 }, { "epoch": 2.93, "learning_rate": 2.7571063544166165e-08, "loss": 0.2774, "step": 2756 }, { "epoch": 2.93, "learning_rate": 2.67165798828406e-08, "loss": 0.2658, "step": 2757 }, { "epoch": 2.93, "learning_rate": 2.5875528860600517e-08, "loss": 0.3011, "step": 2758 }, { "epoch": 2.93, "learning_rate": 2.504791161022535e-08, "loss": 0.2938, "step": 2759 }, { "epoch": 2.94, "learning_rate": 2.4233729246401216e-08, "loss": 0.3132, "step": 2760 }, { "epoch": 2.94, "learning_rate": 2.3432982865720932e-08, "loss": 0.2534, "step": 2761 }, { "epoch": 2.94, "learning_rate": 2.264567354667846e-08, "loss": 0.4272, "step": 2762 }, { "epoch": 2.94, "learning_rate": 2.1871802349671124e-08, "loss": 0.3173, "step": 2763 }, { "epoch": 2.94, "learning_rate": 2.1111370316997394e-08, "loss": 0.3141, "step": 2764 }, { "epoch": 2.94, "learning_rate": 2.036437847285466e-08, "loss": 0.2961, "step": 2765 }, { "epoch": 2.94, "learning_rate": 1.963082782333703e-08, "loss": 0.2811, "step": 2766 }, { "epoch": 2.94, "learning_rate": 1.8910719356436404e-08, "loss": 0.3229, "step": 2767 }, { "epoch": 2.94, "learning_rate": 1.8204054042041398e-08, "loss": 0.3111, "step": 2768 }, { "epoch": 2.95, "learning_rate": 1.7510832831930667e-08, "loss": 0.2793, "step": 2769 }, { "epoch": 2.95, "learning_rate": 1.6831056659778465e-08, "loss": 0.2643, "step": 2770 }, { "epoch": 2.95, "learning_rate": 1.6164726441150192e-08, "loss": 0.3144, "step": 2771 }, { "epoch": 2.95, "learning_rate": 1.5511843073500175e-08, "loss": 0.2987, "step": 2772 }, { "epoch": 2.95, "learning_rate": 1.4872407436171688e-08, "loss": 0.2736, "step": 2773 }, { "epoch": 2.95, "learning_rate": 1.424642039039914e-08, "loss": 0.2695, "step": 2774 }, { "epoch": 2.95, "learning_rate": 1.3633882779298113e-08, "loss": 0.3338, "step": 2775 }, { "epoch": 2.95, "learning_rate": 1.3034795427873115e-08, "loss": 0.2764, "step": 2776 }, { "epoch": 2.95, "learning_rate": 1.2449159143013146e-08, "loss": 0.295, "step": 2777 }, { "epoch": 2.95, "learning_rate": 1.1876974713489476e-08, "loss": 0.2907, "step": 2778 }, { "epoch": 2.96, "learning_rate": 1.1318242909955645e-08, "loss": 0.2725, "step": 2779 }, { "epoch": 2.96, "learning_rate": 1.0772964484945247e-08, "loss": 0.28, "step": 2780 }, { "epoch": 2.96, "learning_rate": 1.0241140172874143e-08, "loss": 0.3486, "step": 2781 }, { "epoch": 2.96, "learning_rate": 9.72277069003602e-09, "loss": 0.3088, "step": 2782 }, { "epoch": 2.96, "learning_rate": 9.217856734603514e-09, "loss": 0.3351, "step": 2783 }, { "epoch": 2.96, "learning_rate": 8.726398986627083e-09, "loss": 0.4554, "step": 2784 }, { "epoch": 2.96, "learning_rate": 8.248398108031686e-09, "loss": 0.2694, "step": 2785 }, { "epoch": 2.96, "learning_rate": 7.78385474261789e-09, "loss": 0.2738, "step": 2786 }, { "epoch": 2.96, "learning_rate": 7.332769516062988e-09, "loss": 0.287, "step": 2787 }, { "epoch": 2.97, "learning_rate": 6.89514303591543e-09, "loss": 0.2593, "step": 2788 }, { "epoch": 2.97, "learning_rate": 6.470975891599285e-09, "loss": 0.2828, "step": 2789 }, { "epoch": 2.97, "learning_rate": 6.060268654408674e-09, "loss": 0.3443, "step": 2790 }, { "epoch": 2.97, "learning_rate": 5.66302187750889e-09, "loss": 0.2903, "step": 2791 }, { "epoch": 2.97, "learning_rate": 5.2792360959375014e-09, "loss": 0.2988, "step": 2792 }, { "epoch": 2.97, "learning_rate": 4.908911826599916e-09, "loss": 0.2877, "step": 2793 }, { "epoch": 2.97, "learning_rate": 4.552049568273819e-09, "loss": 0.2841, "step": 2794 }, { "epoch": 2.97, "learning_rate": 4.208649801602516e-09, "loss": 0.2804, "step": 2795 }, { "epoch": 2.97, "learning_rate": 3.878712989097144e-09, "loss": 0.3343, "step": 2796 }, { "epoch": 2.97, "learning_rate": 3.5622395751389036e-09, "loss": 0.2896, "step": 2797 }, { "epoch": 2.98, "learning_rate": 3.2592299859735e-09, "loss": 0.3307, "step": 2798 }, { "epoch": 2.98, "learning_rate": 2.969684629712255e-09, "loss": 0.3224, "step": 2799 }, { "epoch": 2.98, "learning_rate": 2.693603896333219e-09, "loss": 0.2601, "step": 2800 }, { "epoch": 2.98, "learning_rate": 2.430988157680059e-09, "loss": 0.2963, "step": 2801 }, { "epoch": 2.98, "learning_rate": 2.1818377674587276e-09, "loss": 0.3279, "step": 2802 }, { "epoch": 2.98, "learning_rate": 1.9461530612419066e-09, "loss": 0.2986, "step": 2803 }, { "epoch": 2.98, "learning_rate": 1.7239343564623423e-09, "loss": 0.3518, "step": 2804 }, { "epoch": 2.98, "learning_rate": 1.5151819524195088e-09, "loss": 0.3288, "step": 2805 }, { "epoch": 2.98, "learning_rate": 1.3198961302740564e-09, "loss": 0.2851, "step": 2806 }, { "epoch": 2.99, "learning_rate": 1.1380771530489222e-09, "loss": 0.2918, "step": 2807 }, { "epoch": 2.99, "learning_rate": 9.697252656293288e-10, "loss": 0.3288, "step": 2808 }, { "epoch": 2.99, "learning_rate": 8.148406947616761e-10, "loss": 0.3326, "step": 2809 }, { "epoch": 2.99, "learning_rate": 6.734236490535395e-10, "loss": 0.2612, "step": 2810 }, { "epoch": 2.99, "learning_rate": 5.454743189758916e-10, "loss": 0.3008, "step": 2811 }, { "epoch": 2.99, "learning_rate": 4.309928768586602e-10, "loss": 0.2818, "step": 2812 }, { "epoch": 2.99, "learning_rate": 3.2997947689183963e-10, "loss": 0.2831, "step": 2813 }, { "epoch": 2.99, "learning_rate": 2.424342551254899e-10, "loss": 0.4241, "step": 2814 }, { "epoch": 2.99, "learning_rate": 1.6835732947306783e-10, "loss": 0.3062, "step": 2815 }, { "epoch": 3.0, "learning_rate": 1.0774879970476548e-10, "loss": 0.2845, "step": 2816 }, { "epoch": 3.0, "learning_rate": 6.060874745195123e-11, "loss": 0.3471, "step": 2817 }, { "epoch": 3.0, "learning_rate": 2.693723620716959e-11, "loss": 0.2809, "step": 2818 }, { "epoch": 3.0, "learning_rate": 6.734311319700481e-12, "loss": 0.3166, "step": 2819 }, { "epoch": 3.0, "learning_rate": 0.0, "loss": 0.2655, "step": 2820 }, { "epoch": 3.0, "step": 2820, "total_flos": 7.326679301011538e+18, "train_loss": 0.4328134870698266, "train_runtime": 143996.0196, "train_samples_per_second": 1.88, "train_steps_per_second": 0.02 } ], "logging_steps": 1.0, "max_steps": 2820, "num_input_tokens_seen": 0, "num_train_epochs": 3, "save_steps": 1200, "total_flos": 7.326679301011538e+18, "train_batch_size": 2, "trial_name": null, "trial_params": null }