{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9998615533711754, "eval_steps": 500, "global_step": 3611, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.8348623853211012e-07, "loss": 0.8538, "step": 1 }, { "epoch": 0.0, "learning_rate": 3.6697247706422023e-07, "loss": 0.8406, "step": 2 }, { "epoch": 0.0, "learning_rate": 5.504587155963304e-07, "loss": 0.8607, "step": 3 }, { "epoch": 0.0, "learning_rate": 7.339449541284405e-07, "loss": 0.8335, "step": 4 }, { "epoch": 0.0, "learning_rate": 9.174311926605506e-07, "loss": 0.8386, "step": 5 }, { "epoch": 0.0, "learning_rate": 1.1009174311926608e-06, "loss": 0.8565, "step": 6 }, { "epoch": 0.0, "learning_rate": 1.2844036697247707e-06, "loss": 0.8189, "step": 7 }, { "epoch": 0.0, "learning_rate": 1.467889908256881e-06, "loss": 0.849, "step": 8 }, { "epoch": 0.0, "learning_rate": 1.6513761467889911e-06, "loss": 0.8089, "step": 9 }, { "epoch": 0.0, "learning_rate": 1.8348623853211011e-06, "loss": 0.8235, "step": 10 }, { "epoch": 0.0, "learning_rate": 2.0183486238532113e-06, "loss": 0.7863, "step": 11 }, { "epoch": 0.0, "learning_rate": 2.2018348623853215e-06, "loss": 0.7906, "step": 12 }, { "epoch": 0.0, "learning_rate": 2.3853211009174317e-06, "loss": 0.7831, "step": 13 }, { "epoch": 0.0, "learning_rate": 2.5688073394495415e-06, "loss": 0.7698, "step": 14 }, { "epoch": 0.0, "learning_rate": 2.7522935779816517e-06, "loss": 0.7402, "step": 15 }, { "epoch": 0.0, "learning_rate": 2.935779816513762e-06, "loss": 0.7185, "step": 16 }, { "epoch": 0.0, "learning_rate": 3.119266055045872e-06, "loss": 0.7355, "step": 17 }, { "epoch": 0.0, "learning_rate": 3.3027522935779823e-06, "loss": 0.7269, "step": 18 }, { "epoch": 0.01, "learning_rate": 3.486238532110092e-06, "loss": 0.7281, "step": 19 }, { "epoch": 0.01, "learning_rate": 3.6697247706422022e-06, "loss": 0.7262, "step": 20 }, { "epoch": 0.01, "learning_rate": 3.853211009174313e-06, "loss": 0.7266, "step": 21 }, { "epoch": 0.01, "learning_rate": 4.036697247706423e-06, "loss": 0.6901, "step": 22 }, { "epoch": 0.01, "learning_rate": 4.220183486238532e-06, "loss": 0.7132, "step": 23 }, { "epoch": 0.01, "learning_rate": 4.403669724770643e-06, "loss": 0.7125, "step": 24 }, { "epoch": 0.01, "learning_rate": 4.587155963302753e-06, "loss": 0.7128, "step": 25 }, { "epoch": 0.01, "learning_rate": 4.770642201834863e-06, "loss": 0.7021, "step": 26 }, { "epoch": 0.01, "learning_rate": 4.954128440366973e-06, "loss": 0.7004, "step": 27 }, { "epoch": 0.01, "learning_rate": 5.137614678899083e-06, "loss": 0.7139, "step": 28 }, { "epoch": 0.01, "learning_rate": 5.3211009174311936e-06, "loss": 0.6965, "step": 29 }, { "epoch": 0.01, "learning_rate": 5.504587155963303e-06, "loss": 0.6924, "step": 30 }, { "epoch": 0.01, "learning_rate": 5.688073394495414e-06, "loss": 0.684, "step": 31 }, { "epoch": 0.01, "learning_rate": 5.871559633027524e-06, "loss": 0.6784, "step": 32 }, { "epoch": 0.01, "learning_rate": 6.0550458715596335e-06, "loss": 0.6813, "step": 33 }, { "epoch": 0.01, "learning_rate": 6.238532110091744e-06, "loss": 0.6756, "step": 34 }, { "epoch": 0.01, "learning_rate": 6.422018348623854e-06, "loss": 0.6651, "step": 35 }, { "epoch": 0.01, "learning_rate": 6.6055045871559645e-06, "loss": 0.6808, "step": 36 }, { "epoch": 0.01, "learning_rate": 6.788990825688074e-06, "loss": 0.6674, "step": 37 }, { "epoch": 0.01, "learning_rate": 6.972477064220184e-06, "loss": 0.6702, "step": 38 }, { "epoch": 0.01, "learning_rate": 7.155963302752295e-06, "loss": 0.6813, "step": 39 }, { "epoch": 0.01, "learning_rate": 7.3394495412844045e-06, "loss": 0.6479, "step": 40 }, { "epoch": 0.01, "learning_rate": 7.522935779816515e-06, "loss": 0.6748, "step": 41 }, { "epoch": 0.01, "learning_rate": 7.706422018348626e-06, "loss": 0.6569, "step": 42 }, { "epoch": 0.01, "learning_rate": 7.889908256880735e-06, "loss": 0.665, "step": 43 }, { "epoch": 0.01, "learning_rate": 8.073394495412845e-06, "loss": 0.6637, "step": 44 }, { "epoch": 0.01, "learning_rate": 8.256880733944956e-06, "loss": 0.6662, "step": 45 }, { "epoch": 0.01, "learning_rate": 8.440366972477065e-06, "loss": 0.6549, "step": 46 }, { "epoch": 0.01, "learning_rate": 8.623853211009175e-06, "loss": 0.656, "step": 47 }, { "epoch": 0.01, "learning_rate": 8.807339449541286e-06, "loss": 0.6433, "step": 48 }, { "epoch": 0.01, "learning_rate": 8.990825688073395e-06, "loss": 0.65, "step": 49 }, { "epoch": 0.01, "learning_rate": 9.174311926605506e-06, "loss": 0.6581, "step": 50 }, { "epoch": 0.01, "learning_rate": 9.357798165137616e-06, "loss": 0.6504, "step": 51 }, { "epoch": 0.01, "learning_rate": 9.541284403669727e-06, "loss": 0.6566, "step": 52 }, { "epoch": 0.01, "learning_rate": 9.724770642201836e-06, "loss": 0.6339, "step": 53 }, { "epoch": 0.01, "learning_rate": 9.908256880733946e-06, "loss": 0.6575, "step": 54 }, { "epoch": 0.02, "learning_rate": 1.0091743119266055e-05, "loss": 0.6612, "step": 55 }, { "epoch": 0.02, "learning_rate": 1.0275229357798166e-05, "loss": 0.6613, "step": 56 }, { "epoch": 0.02, "learning_rate": 1.0458715596330275e-05, "loss": 0.6266, "step": 57 }, { "epoch": 0.02, "learning_rate": 1.0642201834862387e-05, "loss": 0.6495, "step": 58 }, { "epoch": 0.02, "learning_rate": 1.0825688073394496e-05, "loss": 0.6643, "step": 59 }, { "epoch": 0.02, "learning_rate": 1.1009174311926607e-05, "loss": 0.656, "step": 60 }, { "epoch": 0.02, "learning_rate": 1.1192660550458716e-05, "loss": 0.6416, "step": 61 }, { "epoch": 0.02, "learning_rate": 1.1376146788990828e-05, "loss": 0.6536, "step": 62 }, { "epoch": 0.02, "learning_rate": 1.1559633027522937e-05, "loss": 0.6431, "step": 63 }, { "epoch": 0.02, "learning_rate": 1.1743119266055047e-05, "loss": 0.6419, "step": 64 }, { "epoch": 0.02, "learning_rate": 1.1926605504587156e-05, "loss": 0.6408, "step": 65 }, { "epoch": 0.02, "learning_rate": 1.2110091743119267e-05, "loss": 0.6468, "step": 66 }, { "epoch": 0.02, "learning_rate": 1.2293577981651376e-05, "loss": 0.6254, "step": 67 }, { "epoch": 0.02, "learning_rate": 1.2477064220183488e-05, "loss": 0.6397, "step": 68 }, { "epoch": 0.02, "learning_rate": 1.2660550458715597e-05, "loss": 0.6343, "step": 69 }, { "epoch": 0.02, "learning_rate": 1.2844036697247708e-05, "loss": 0.6285, "step": 70 }, { "epoch": 0.02, "learning_rate": 1.3027522935779817e-05, "loss": 0.6541, "step": 71 }, { "epoch": 0.02, "learning_rate": 1.3211009174311929e-05, "loss": 0.6347, "step": 72 }, { "epoch": 0.02, "learning_rate": 1.3394495412844038e-05, "loss": 0.6345, "step": 73 }, { "epoch": 0.02, "learning_rate": 1.3577981651376149e-05, "loss": 0.6391, "step": 74 }, { "epoch": 0.02, "learning_rate": 1.3761467889908258e-05, "loss": 0.6271, "step": 75 }, { "epoch": 0.02, "learning_rate": 1.3944954128440368e-05, "loss": 0.6351, "step": 76 }, { "epoch": 0.02, "learning_rate": 1.4128440366972477e-05, "loss": 0.6287, "step": 77 }, { "epoch": 0.02, "learning_rate": 1.431192660550459e-05, "loss": 0.6311, "step": 78 }, { "epoch": 0.02, "learning_rate": 1.4495412844036698e-05, "loss": 0.6202, "step": 79 }, { "epoch": 0.02, "learning_rate": 1.4678899082568809e-05, "loss": 0.6375, "step": 80 }, { "epoch": 0.02, "learning_rate": 1.4862385321100918e-05, "loss": 0.6365, "step": 81 }, { "epoch": 0.02, "learning_rate": 1.504587155963303e-05, "loss": 0.637, "step": 82 }, { "epoch": 0.02, "learning_rate": 1.5229357798165139e-05, "loss": 0.615, "step": 83 }, { "epoch": 0.02, "learning_rate": 1.541284403669725e-05, "loss": 0.6175, "step": 84 }, { "epoch": 0.02, "learning_rate": 1.559633027522936e-05, "loss": 0.6222, "step": 85 }, { "epoch": 0.02, "learning_rate": 1.577981651376147e-05, "loss": 0.6321, "step": 86 }, { "epoch": 0.02, "learning_rate": 1.5963302752293578e-05, "loss": 0.6017, "step": 87 }, { "epoch": 0.02, "learning_rate": 1.614678899082569e-05, "loss": 0.6159, "step": 88 }, { "epoch": 0.02, "learning_rate": 1.63302752293578e-05, "loss": 0.6293, "step": 89 }, { "epoch": 0.02, "learning_rate": 1.6513761467889912e-05, "loss": 0.6133, "step": 90 }, { "epoch": 0.03, "learning_rate": 1.669724770642202e-05, "loss": 0.6063, "step": 91 }, { "epoch": 0.03, "learning_rate": 1.688073394495413e-05, "loss": 0.6129, "step": 92 }, { "epoch": 0.03, "learning_rate": 1.706422018348624e-05, "loss": 0.6145, "step": 93 }, { "epoch": 0.03, "learning_rate": 1.724770642201835e-05, "loss": 0.6188, "step": 94 }, { "epoch": 0.03, "learning_rate": 1.743119266055046e-05, "loss": 0.6184, "step": 95 }, { "epoch": 0.03, "learning_rate": 1.7614678899082572e-05, "loss": 0.608, "step": 96 }, { "epoch": 0.03, "learning_rate": 1.779816513761468e-05, "loss": 0.6048, "step": 97 }, { "epoch": 0.03, "learning_rate": 1.798165137614679e-05, "loss": 0.6105, "step": 98 }, { "epoch": 0.03, "learning_rate": 1.81651376146789e-05, "loss": 0.6114, "step": 99 }, { "epoch": 0.03, "learning_rate": 1.834862385321101e-05, "loss": 0.6154, "step": 100 }, { "epoch": 0.03, "learning_rate": 1.853211009174312e-05, "loss": 0.611, "step": 101 }, { "epoch": 0.03, "learning_rate": 1.8715596330275232e-05, "loss": 0.6176, "step": 102 }, { "epoch": 0.03, "learning_rate": 1.889908256880734e-05, "loss": 0.6081, "step": 103 }, { "epoch": 0.03, "learning_rate": 1.9082568807339454e-05, "loss": 0.5987, "step": 104 }, { "epoch": 0.03, "learning_rate": 1.9266055045871563e-05, "loss": 0.5943, "step": 105 }, { "epoch": 0.03, "learning_rate": 1.944954128440367e-05, "loss": 0.6101, "step": 106 }, { "epoch": 0.03, "learning_rate": 1.963302752293578e-05, "loss": 0.6121, "step": 107 }, { "epoch": 0.03, "learning_rate": 1.9816513761467893e-05, "loss": 0.6166, "step": 108 }, { "epoch": 0.03, "learning_rate": 2e-05, "loss": 0.6025, "step": 109 }, { "epoch": 0.03, "learning_rate": 1.9999995976190267e-05, "loss": 0.6082, "step": 110 }, { "epoch": 0.03, "learning_rate": 1.99999839047643e-05, "loss": 0.6119, "step": 111 }, { "epoch": 0.03, "learning_rate": 1.9999963785731808e-05, "loss": 0.6139, "step": 112 }, { "epoch": 0.03, "learning_rate": 1.9999935619108992e-05, "loss": 0.5914, "step": 113 }, { "epoch": 0.03, "learning_rate": 1.9999899404918515e-05, "loss": 0.607, "step": 114 }, { "epoch": 0.03, "learning_rate": 1.9999855143189522e-05, "loss": 0.6062, "step": 115 }, { "epoch": 0.03, "learning_rate": 1.999980283395763e-05, "loss": 0.6026, "step": 116 }, { "epoch": 0.03, "learning_rate": 1.999974247726494e-05, "loss": 0.6071, "step": 117 }, { "epoch": 0.03, "learning_rate": 1.9999674073160024e-05, "loss": 0.5949, "step": 118 }, { "epoch": 0.03, "learning_rate": 1.9999597621697927e-05, "loss": 0.6043, "step": 119 }, { "epoch": 0.03, "learning_rate": 1.999951312294018e-05, "loss": 0.6051, "step": 120 }, { "epoch": 0.03, "learning_rate": 1.9999420576954783e-05, "loss": 0.6144, "step": 121 }, { "epoch": 0.03, "learning_rate": 1.9999319983816207e-05, "loss": 0.6116, "step": 122 }, { "epoch": 0.03, "learning_rate": 1.999921134360541e-05, "loss": 0.6003, "step": 123 }, { "epoch": 0.03, "learning_rate": 1.9999094656409826e-05, "loss": 0.5926, "step": 124 }, { "epoch": 0.03, "learning_rate": 1.9998969922323356e-05, "loss": 0.599, "step": 125 }, { "epoch": 0.03, "learning_rate": 1.9998837141446378e-05, "loss": 0.598, "step": 126 }, { "epoch": 0.04, "learning_rate": 1.9998696313885756e-05, "loss": 0.6038, "step": 127 }, { "epoch": 0.04, "learning_rate": 1.9998547439754817e-05, "loss": 0.6008, "step": 128 }, { "epoch": 0.04, "learning_rate": 1.9998390519173376e-05, "loss": 0.6035, "step": 129 }, { "epoch": 0.04, "learning_rate": 1.9998225552267704e-05, "loss": 0.5945, "step": 130 }, { "epoch": 0.04, "learning_rate": 1.9998052539170575e-05, "loss": 0.579, "step": 131 }, { "epoch": 0.04, "learning_rate": 1.9997871480021213e-05, "loss": 0.5988, "step": 132 }, { "epoch": 0.04, "learning_rate": 1.9997682374965332e-05, "loss": 0.6245, "step": 133 }, { "epoch": 0.04, "learning_rate": 1.9997485224155118e-05, "loss": 0.6213, "step": 134 }, { "epoch": 0.04, "learning_rate": 1.9997280027749227e-05, "loss": 0.6047, "step": 135 }, { "epoch": 0.04, "learning_rate": 1.9997066785912797e-05, "loss": 0.5983, "step": 136 }, { "epoch": 0.04, "learning_rate": 1.9996845498817426e-05, "loss": 0.6123, "step": 137 }, { "epoch": 0.04, "learning_rate": 1.9996616166641215e-05, "loss": 0.5923, "step": 138 }, { "epoch": 0.04, "learning_rate": 1.9996378789568708e-05, "loss": 0.5972, "step": 139 }, { "epoch": 0.04, "learning_rate": 1.9996133367790942e-05, "loss": 0.5838, "step": 140 }, { "epoch": 0.04, "learning_rate": 1.999587990150542e-05, "loss": 0.611, "step": 141 }, { "epoch": 0.04, "learning_rate": 1.999561839091613e-05, "loss": 0.5969, "step": 142 }, { "epoch": 0.04, "learning_rate": 1.9995348836233517e-05, "loss": 0.5991, "step": 143 }, { "epoch": 0.04, "learning_rate": 1.9995071237674513e-05, "loss": 0.5798, "step": 144 }, { "epoch": 0.04, "learning_rate": 1.9994785595462518e-05, "loss": 0.5966, "step": 145 }, { "epoch": 0.04, "learning_rate": 1.9994491909827405e-05, "loss": 0.594, "step": 146 }, { "epoch": 0.04, "learning_rate": 1.999419018100552e-05, "loss": 0.5909, "step": 147 }, { "epoch": 0.04, "learning_rate": 1.9993880409239686e-05, "loss": 0.5882, "step": 148 }, { "epoch": 0.04, "learning_rate": 1.9993562594779197e-05, "loss": 0.5998, "step": 149 }, { "epoch": 0.04, "learning_rate": 1.999323673787981e-05, "loss": 0.612, "step": 150 }, { "epoch": 0.04, "learning_rate": 1.9992902838803773e-05, "loss": 0.5838, "step": 151 }, { "epoch": 0.04, "learning_rate": 1.9992560897819785e-05, "loss": 0.5908, "step": 152 }, { "epoch": 0.04, "learning_rate": 1.9992210915203032e-05, "loss": 0.5727, "step": 153 }, { "epoch": 0.04, "learning_rate": 1.9991852891235165e-05, "loss": 0.5902, "step": 154 }, { "epoch": 0.04, "learning_rate": 1.9991486826204314e-05, "loss": 0.6073, "step": 155 }, { "epoch": 0.04, "learning_rate": 1.9991112720405068e-05, "loss": 0.5879, "step": 156 }, { "epoch": 0.04, "learning_rate": 1.999073057413849e-05, "loss": 0.5844, "step": 157 }, { "epoch": 0.04, "learning_rate": 1.9990340387712127e-05, "loss": 0.6071, "step": 158 }, { "epoch": 0.04, "learning_rate": 1.998994216143998e-05, "loss": 0.59, "step": 159 }, { "epoch": 0.04, "learning_rate": 1.9989535895642523e-05, "loss": 0.6036, "step": 160 }, { "epoch": 0.04, "learning_rate": 1.9989121590646712e-05, "loss": 0.5786, "step": 161 }, { "epoch": 0.04, "learning_rate": 1.9988699246785957e-05, "loss": 0.6024, "step": 162 }, { "epoch": 0.05, "learning_rate": 1.9988268864400147e-05, "loss": 0.5971, "step": 163 }, { "epoch": 0.05, "learning_rate": 1.9987830443835636e-05, "loss": 0.6067, "step": 164 }, { "epoch": 0.05, "learning_rate": 1.998738398544525e-05, "loss": 0.6008, "step": 165 }, { "epoch": 0.05, "learning_rate": 1.998692948958828e-05, "loss": 0.595, "step": 166 }, { "epoch": 0.05, "learning_rate": 1.9986466956630486e-05, "loss": 0.5987, "step": 167 }, { "epoch": 0.05, "learning_rate": 1.99859963869441e-05, "loss": 0.5893, "step": 168 }, { "epoch": 0.05, "learning_rate": 1.9985517780907816e-05, "loss": 0.5991, "step": 169 }, { "epoch": 0.05, "learning_rate": 1.9985031138906804e-05, "loss": 0.6033, "step": 170 }, { "epoch": 0.05, "learning_rate": 1.9984536461332683e-05, "loss": 0.5821, "step": 171 }, { "epoch": 0.05, "learning_rate": 1.9984033748583562e-05, "loss": 0.597, "step": 172 }, { "epoch": 0.05, "learning_rate": 1.9983523001064e-05, "loss": 0.579, "step": 173 }, { "epoch": 0.05, "learning_rate": 1.9983004219185028e-05, "loss": 0.5809, "step": 174 }, { "epoch": 0.05, "learning_rate": 1.998247740336414e-05, "loss": 0.5957, "step": 175 }, { "epoch": 0.05, "learning_rate": 1.9981942554025305e-05, "loss": 0.5979, "step": 176 }, { "epoch": 0.05, "learning_rate": 1.998139967159894e-05, "loss": 0.5973, "step": 177 }, { "epoch": 0.05, "learning_rate": 1.998084875652194e-05, "loss": 0.6009, "step": 178 }, { "epoch": 0.05, "learning_rate": 1.9980289809237662e-05, "loss": 0.5839, "step": 179 }, { "epoch": 0.05, "learning_rate": 1.997972283019592e-05, "loss": 0.5969, "step": 180 }, { "epoch": 0.05, "learning_rate": 1.9979147819853003e-05, "loss": 0.5867, "step": 181 }, { "epoch": 0.05, "learning_rate": 1.9978564778671653e-05, "loss": 0.5971, "step": 182 }, { "epoch": 0.05, "learning_rate": 1.9977973707121085e-05, "loss": 0.5803, "step": 183 }, { "epoch": 0.05, "learning_rate": 1.9977374605676965e-05, "loss": 0.5765, "step": 184 }, { "epoch": 0.05, "learning_rate": 1.9976767474821433e-05, "loss": 0.5921, "step": 185 }, { "epoch": 0.05, "learning_rate": 1.997615231504308e-05, "loss": 0.5839, "step": 186 }, { "epoch": 0.05, "learning_rate": 1.997552912683696e-05, "loss": 0.5786, "step": 187 }, { "epoch": 0.05, "learning_rate": 1.9974897910704603e-05, "loss": 0.5768, "step": 188 }, { "epoch": 0.05, "learning_rate": 1.9974258667153976e-05, "loss": 0.586, "step": 189 }, { "epoch": 0.05, "learning_rate": 1.9973611396699524e-05, "loss": 0.5996, "step": 190 }, { "epoch": 0.05, "learning_rate": 1.9972956099862145e-05, "loss": 0.5935, "step": 191 }, { "epoch": 0.05, "learning_rate": 1.9972292777169192e-05, "loss": 0.5807, "step": 192 }, { "epoch": 0.05, "learning_rate": 1.997162142915449e-05, "loss": 0.5962, "step": 193 }, { "epoch": 0.05, "learning_rate": 1.997094205635831e-05, "loss": 0.5896, "step": 194 }, { "epoch": 0.05, "learning_rate": 1.997025465932738e-05, "loss": 0.5843, "step": 195 }, { "epoch": 0.05, "learning_rate": 1.9969559238614904e-05, "loss": 0.5983, "step": 196 }, { "epoch": 0.05, "learning_rate": 1.9968855794780516e-05, "loss": 0.5939, "step": 197 }, { "epoch": 0.05, "learning_rate": 1.9968144328390333e-05, "loss": 0.5877, "step": 198 }, { "epoch": 0.06, "learning_rate": 1.996742484001691e-05, "loss": 0.5973, "step": 199 }, { "epoch": 0.06, "learning_rate": 1.9966697330239262e-05, "loss": 0.5935, "step": 200 }, { "epoch": 0.06, "learning_rate": 1.9965961799642865e-05, "loss": 0.6048, "step": 201 }, { "epoch": 0.06, "learning_rate": 1.996521824881964e-05, "loss": 0.6044, "step": 202 }, { "epoch": 0.06, "learning_rate": 1.996446667836798e-05, "loss": 0.5907, "step": 203 }, { "epoch": 0.06, "learning_rate": 1.9963707088892712e-05, "loss": 0.5898, "step": 204 }, { "epoch": 0.06, "learning_rate": 1.9962939481005123e-05, "loss": 0.585, "step": 205 }, { "epoch": 0.06, "learning_rate": 1.996216385532296e-05, "loss": 0.5822, "step": 206 }, { "epoch": 0.06, "learning_rate": 1.9961380212470412e-05, "loss": 0.5843, "step": 207 }, { "epoch": 0.06, "learning_rate": 1.9960588553078132e-05, "loss": 0.5817, "step": 208 }, { "epoch": 0.06, "learning_rate": 1.995978887778321e-05, "loss": 0.5804, "step": 209 }, { "epoch": 0.06, "learning_rate": 1.9958981187229197e-05, "loss": 0.5848, "step": 210 }, { "epoch": 0.06, "learning_rate": 1.9958165482066094e-05, "loss": 0.5872, "step": 211 }, { "epoch": 0.06, "learning_rate": 1.9957341762950346e-05, "loss": 0.5819, "step": 212 }, { "epoch": 0.06, "learning_rate": 1.9956510030544854e-05, "loss": 0.5896, "step": 213 }, { "epoch": 0.06, "learning_rate": 1.995567028551896e-05, "loss": 0.5897, "step": 214 }, { "epoch": 0.06, "learning_rate": 1.9954822528548462e-05, "loss": 0.5915, "step": 215 }, { "epoch": 0.06, "learning_rate": 1.9953966760315604e-05, "loss": 0.5848, "step": 216 }, { "epoch": 0.06, "learning_rate": 1.9953102981509073e-05, "loss": 0.5954, "step": 217 }, { "epoch": 0.06, "learning_rate": 1.9952231192824008e-05, "loss": 0.5805, "step": 218 }, { "epoch": 0.06, "learning_rate": 1.9951351394961986e-05, "loss": 0.5941, "step": 219 }, { "epoch": 0.06, "learning_rate": 1.995046358863104e-05, "loss": 0.5807, "step": 220 }, { "epoch": 0.06, "learning_rate": 1.9949567774545642e-05, "loss": 0.5855, "step": 221 }, { "epoch": 0.06, "learning_rate": 1.9948663953426706e-05, "loss": 0.5702, "step": 222 }, { "epoch": 0.06, "learning_rate": 1.9947752126001597e-05, "loss": 0.5882, "step": 223 }, { "epoch": 0.06, "learning_rate": 1.9946832293004114e-05, "loss": 0.5939, "step": 224 }, { "epoch": 0.06, "learning_rate": 1.994590445517451e-05, "loss": 0.5963, "step": 225 }, { "epoch": 0.06, "learning_rate": 1.994496861325947e-05, "loss": 0.5864, "step": 226 }, { "epoch": 0.06, "learning_rate": 1.9944024768012122e-05, "loss": 0.5816, "step": 227 }, { "epoch": 0.06, "learning_rate": 1.9943072920192042e-05, "loss": 0.5905, "step": 228 }, { "epoch": 0.06, "learning_rate": 1.9942113070565233e-05, "loss": 0.5811, "step": 229 }, { "epoch": 0.06, "learning_rate": 1.9941145219904157e-05, "loss": 0.586, "step": 230 }, { "epoch": 0.06, "learning_rate": 1.9940169368987692e-05, "loss": 0.581, "step": 231 }, { "epoch": 0.06, "learning_rate": 1.9939185518601173e-05, "loss": 0.5797, "step": 232 }, { "epoch": 0.06, "learning_rate": 1.993819366953636e-05, "loss": 0.5945, "step": 233 }, { "epoch": 0.06, "learning_rate": 1.993719382259146e-05, "loss": 0.5823, "step": 234 }, { "epoch": 0.07, "learning_rate": 1.993618597857111e-05, "loss": 0.5726, "step": 235 }, { "epoch": 0.07, "learning_rate": 1.9935170138286382e-05, "loss": 0.5738, "step": 236 }, { "epoch": 0.07, "learning_rate": 1.993414630255479e-05, "loss": 0.5908, "step": 237 }, { "epoch": 0.07, "learning_rate": 1.9933114472200274e-05, "loss": 0.5845, "step": 238 }, { "epoch": 0.07, "learning_rate": 1.9932074648053216e-05, "loss": 0.5765, "step": 239 }, { "epoch": 0.07, "learning_rate": 1.9931026830950425e-05, "loss": 0.5837, "step": 240 }, { "epoch": 0.07, "learning_rate": 1.992997102173514e-05, "loss": 0.5855, "step": 241 }, { "epoch": 0.07, "learning_rate": 1.9928907221257048e-05, "loss": 0.5939, "step": 242 }, { "epoch": 0.07, "learning_rate": 1.992783543037224e-05, "loss": 0.578, "step": 243 }, { "epoch": 0.07, "learning_rate": 1.9926755649943265e-05, "loss": 0.5844, "step": 244 }, { "epoch": 0.07, "learning_rate": 1.992566788083908e-05, "loss": 0.5909, "step": 245 }, { "epoch": 0.07, "learning_rate": 1.9924572123935085e-05, "loss": 0.5762, "step": 246 }, { "epoch": 0.07, "learning_rate": 1.9923468380113105e-05, "loss": 0.594, "step": 247 }, { "epoch": 0.07, "learning_rate": 1.9922356650261387e-05, "loss": 0.581, "step": 248 }, { "epoch": 0.07, "learning_rate": 1.992123693527461e-05, "loss": 0.5894, "step": 249 }, { "epoch": 0.07, "learning_rate": 1.992010923605388e-05, "loss": 0.5889, "step": 250 }, { "epoch": 0.07, "learning_rate": 1.9918973553506723e-05, "loss": 0.5701, "step": 251 }, { "epoch": 0.07, "learning_rate": 1.9917829888547096e-05, "loss": 0.5728, "step": 252 }, { "epoch": 0.07, "learning_rate": 1.9916678242095377e-05, "loss": 0.5782, "step": 253 }, { "epoch": 0.07, "learning_rate": 1.9915518615078367e-05, "loss": 0.5869, "step": 254 }, { "epoch": 0.07, "learning_rate": 1.991435100842929e-05, "loss": 0.5911, "step": 255 }, { "epoch": 0.07, "learning_rate": 1.9913175423087786e-05, "loss": 0.5782, "step": 256 }, { "epoch": 0.07, "learning_rate": 1.9911991859999928e-05, "loss": 0.5819, "step": 257 }, { "epoch": 0.07, "learning_rate": 1.9910800320118202e-05, "loss": 0.593, "step": 258 }, { "epoch": 0.07, "learning_rate": 1.990960080440151e-05, "loss": 0.5726, "step": 259 }, { "epoch": 0.07, "learning_rate": 1.990839331381518e-05, "loss": 0.6004, "step": 260 }, { "epoch": 0.07, "learning_rate": 1.9907177849330956e-05, "loss": 0.5922, "step": 261 }, { "epoch": 0.07, "learning_rate": 1.9905954411926992e-05, "loss": 0.5843, "step": 262 }, { "epoch": 0.07, "learning_rate": 1.9904723002587868e-05, "loss": 0.5801, "step": 263 }, { "epoch": 0.07, "learning_rate": 1.9903483622304573e-05, "loss": 0.5875, "step": 264 }, { "epoch": 0.07, "learning_rate": 1.9902236272074514e-05, "loss": 0.572, "step": 265 }, { "epoch": 0.07, "learning_rate": 1.990098095290151e-05, "loss": 0.5828, "step": 266 }, { "epoch": 0.07, "learning_rate": 1.98997176657958e-05, "loss": 0.5821, "step": 267 }, { "epoch": 0.07, "learning_rate": 1.989844641177402e-05, "loss": 0.5821, "step": 268 }, { "epoch": 0.07, "learning_rate": 1.9897167191859234e-05, "loss": 0.5737, "step": 269 }, { "epoch": 0.07, "learning_rate": 1.989588000708091e-05, "loss": 0.5862, "step": 270 }, { "epoch": 0.08, "learning_rate": 1.9894584858474916e-05, "loss": 0.5896, "step": 271 }, { "epoch": 0.08, "learning_rate": 1.989328174708355e-05, "loss": 0.5863, "step": 272 }, { "epoch": 0.08, "learning_rate": 1.98919706739555e-05, "loss": 0.5917, "step": 273 }, { "epoch": 0.08, "learning_rate": 1.9890651640145867e-05, "loss": 0.572, "step": 274 }, { "epoch": 0.08, "learning_rate": 1.9889324646716166e-05, "loss": 0.5786, "step": 275 }, { "epoch": 0.08, "learning_rate": 1.9887989694734302e-05, "loss": 0.5784, "step": 276 }, { "epoch": 0.08, "learning_rate": 1.9886646785274595e-05, "loss": 0.5746, "step": 277 }, { "epoch": 0.08, "learning_rate": 1.9885295919417778e-05, "loss": 0.5686, "step": 278 }, { "epoch": 0.08, "learning_rate": 1.9883937098250962e-05, "loss": 0.5871, "step": 279 }, { "epoch": 0.08, "learning_rate": 1.9882570322867685e-05, "loss": 0.5801, "step": 280 }, { "epoch": 0.08, "learning_rate": 1.988119559436787e-05, "loss": 0.6008, "step": 281 }, { "epoch": 0.08, "learning_rate": 1.9879812913857848e-05, "loss": 0.587, "step": 282 }, { "epoch": 0.08, "learning_rate": 1.9878422282450346e-05, "loss": 0.5728, "step": 283 }, { "epoch": 0.08, "learning_rate": 1.98770237012645e-05, "loss": 0.5957, "step": 284 }, { "epoch": 0.08, "learning_rate": 1.9875617171425817e-05, "loss": 0.5782, "step": 285 }, { "epoch": 0.08, "learning_rate": 1.9874202694066236e-05, "loss": 0.5767, "step": 286 }, { "epoch": 0.08, "learning_rate": 1.987278027032407e-05, "loss": 0.5908, "step": 287 }, { "epoch": 0.08, "learning_rate": 1.9871349901344027e-05, "loss": 0.5877, "step": 288 }, { "epoch": 0.08, "learning_rate": 1.9869911588277214e-05, "loss": 0.587, "step": 289 }, { "epoch": 0.08, "learning_rate": 1.9868465332281134e-05, "loss": 0.5756, "step": 290 }, { "epoch": 0.08, "learning_rate": 1.986701113451968e-05, "loss": 0.5856, "step": 291 }, { "epoch": 0.08, "learning_rate": 1.986554899616313e-05, "loss": 0.574, "step": 292 }, { "epoch": 0.08, "learning_rate": 1.986407891838816e-05, "loss": 0.5762, "step": 293 }, { "epoch": 0.08, "learning_rate": 1.9862600902377835e-05, "loss": 0.5901, "step": 294 }, { "epoch": 0.08, "learning_rate": 1.98611149493216e-05, "loss": 0.5846, "step": 295 }, { "epoch": 0.08, "learning_rate": 1.9859621060415302e-05, "loss": 0.5542, "step": 296 }, { "epoch": 0.08, "learning_rate": 1.9858119236861157e-05, "loss": 0.5735, "step": 297 }, { "epoch": 0.08, "learning_rate": 1.9856609479867784e-05, "loss": 0.5746, "step": 298 }, { "epoch": 0.08, "learning_rate": 1.9855091790650166e-05, "loss": 0.5867, "step": 299 }, { "epoch": 0.08, "learning_rate": 1.9853566170429696e-05, "loss": 0.5697, "step": 300 }, { "epoch": 0.08, "learning_rate": 1.9852032620434124e-05, "loss": 0.5827, "step": 301 }, { "epoch": 0.08, "learning_rate": 1.9850491141897596e-05, "loss": 0.5825, "step": 302 }, { "epoch": 0.08, "learning_rate": 1.984894173606064e-05, "loss": 0.5875, "step": 303 }, { "epoch": 0.08, "learning_rate": 1.984738440417015e-05, "loss": 0.5785, "step": 304 }, { "epoch": 0.08, "learning_rate": 1.9845819147479418e-05, "loss": 0.579, "step": 305 }, { "epoch": 0.08, "learning_rate": 1.9844245967248093e-05, "loss": 0.5768, "step": 306 }, { "epoch": 0.09, "learning_rate": 1.9842664864742218e-05, "loss": 0.5883, "step": 307 }, { "epoch": 0.09, "learning_rate": 1.9841075841234197e-05, "loss": 0.5909, "step": 308 }, { "epoch": 0.09, "learning_rate": 1.9839478898002825e-05, "loss": 0.574, "step": 309 }, { "epoch": 0.09, "learning_rate": 1.9837874036333252e-05, "loss": 0.5938, "step": 310 }, { "epoch": 0.09, "learning_rate": 1.9836261257517015e-05, "loss": 0.5741, "step": 311 }, { "epoch": 0.09, "learning_rate": 1.9834640562852015e-05, "loss": 0.5839, "step": 312 }, { "epoch": 0.09, "learning_rate": 1.9833011953642525e-05, "loss": 0.5618, "step": 313 }, { "epoch": 0.09, "learning_rate": 1.983137543119919e-05, "loss": 0.5808, "step": 314 }, { "epoch": 0.09, "learning_rate": 1.982973099683902e-05, "loss": 0.5871, "step": 315 }, { "epoch": 0.09, "learning_rate": 1.982807865188539e-05, "loss": 0.5833, "step": 316 }, { "epoch": 0.09, "learning_rate": 1.982641839766805e-05, "loss": 0.5874, "step": 317 }, { "epoch": 0.09, "learning_rate": 1.9824750235523105e-05, "loss": 0.5755, "step": 318 }, { "epoch": 0.09, "learning_rate": 1.9823074166793034e-05, "loss": 0.5763, "step": 319 }, { "epoch": 0.09, "learning_rate": 1.9821390192826663e-05, "loss": 0.5729, "step": 320 }, { "epoch": 0.09, "learning_rate": 1.98196983149792e-05, "loss": 0.5746, "step": 321 }, { "epoch": 0.09, "learning_rate": 1.9817998534612197e-05, "loss": 0.5883, "step": 322 }, { "epoch": 0.09, "learning_rate": 1.981629085309358e-05, "loss": 0.5949, "step": 323 }, { "epoch": 0.09, "learning_rate": 1.981457527179762e-05, "loss": 0.5763, "step": 324 }, { "epoch": 0.09, "learning_rate": 1.9812851792104955e-05, "loss": 0.5751, "step": 325 }, { "epoch": 0.09, "learning_rate": 1.981112041540257e-05, "loss": 0.5738, "step": 326 }, { "epoch": 0.09, "learning_rate": 1.9809381143083823e-05, "loss": 0.5789, "step": 327 }, { "epoch": 0.09, "learning_rate": 1.98076339765484e-05, "loss": 0.57, "step": 328 }, { "epoch": 0.09, "learning_rate": 1.9805878917202366e-05, "loss": 0.5871, "step": 329 }, { "epoch": 0.09, "learning_rate": 1.9804115966458118e-05, "loss": 0.5879, "step": 330 }, { "epoch": 0.09, "learning_rate": 1.9802345125734416e-05, "loss": 0.566, "step": 331 }, { "epoch": 0.09, "learning_rate": 1.980056639645636e-05, "loss": 0.5755, "step": 332 }, { "epoch": 0.09, "learning_rate": 1.9798779780055413e-05, "loss": 0.5746, "step": 333 }, { "epoch": 0.09, "learning_rate": 1.9796985277969365e-05, "loss": 0.5687, "step": 334 }, { "epoch": 0.09, "learning_rate": 1.979518289164237e-05, "loss": 0.5805, "step": 335 }, { "epoch": 0.09, "learning_rate": 1.979337262252492e-05, "loss": 0.581, "step": 336 }, { "epoch": 0.09, "learning_rate": 1.979155447207385e-05, "loss": 0.591, "step": 337 }, { "epoch": 0.09, "learning_rate": 1.9789728441752332e-05, "loss": 0.5842, "step": 338 }, { "epoch": 0.09, "learning_rate": 1.9787894533029893e-05, "loss": 0.5662, "step": 339 }, { "epoch": 0.09, "learning_rate": 1.9786052747382393e-05, "loss": 0.595, "step": 340 }, { "epoch": 0.09, "learning_rate": 1.9784203086292028e-05, "loss": 0.5743, "step": 341 }, { "epoch": 0.09, "learning_rate": 1.9782345551247336e-05, "loss": 0.5715, "step": 342 }, { "epoch": 0.09, "learning_rate": 1.978048014374319e-05, "loss": 0.5864, "step": 343 }, { "epoch": 0.1, "learning_rate": 1.9778606865280795e-05, "loss": 0.5704, "step": 344 }, { "epoch": 0.1, "learning_rate": 1.9776725717367705e-05, "loss": 0.5728, "step": 345 }, { "epoch": 0.1, "learning_rate": 1.9774836701517787e-05, "loss": 0.5798, "step": 346 }, { "epoch": 0.1, "learning_rate": 1.9772939819251247e-05, "loss": 0.5781, "step": 347 }, { "epoch": 0.1, "learning_rate": 1.9771035072094637e-05, "loss": 0.5701, "step": 348 }, { "epoch": 0.1, "learning_rate": 1.9769122461580813e-05, "loss": 0.5876, "step": 349 }, { "epoch": 0.1, "learning_rate": 1.9767201989248975e-05, "loss": 0.5952, "step": 350 }, { "epoch": 0.1, "learning_rate": 1.9765273656644645e-05, "loss": 0.5697, "step": 351 }, { "epoch": 0.1, "learning_rate": 1.976333746531967e-05, "loss": 0.5596, "step": 352 }, { "epoch": 0.1, "learning_rate": 1.9761393416832226e-05, "loss": 0.574, "step": 353 }, { "epoch": 0.1, "learning_rate": 1.9759441512746812e-05, "loss": 0.572, "step": 354 }, { "epoch": 0.1, "learning_rate": 1.9757481754634243e-05, "loss": 0.5825, "step": 355 }, { "epoch": 0.1, "learning_rate": 1.9755514144071654e-05, "loss": 0.5779, "step": 356 }, { "epoch": 0.1, "learning_rate": 1.975353868264251e-05, "loss": 0.5559, "step": 357 }, { "epoch": 0.1, "learning_rate": 1.975155537193658e-05, "loss": 0.5731, "step": 358 }, { "epoch": 0.1, "learning_rate": 1.9749564213549965e-05, "loss": 0.5815, "step": 359 }, { "epoch": 0.1, "learning_rate": 1.974756520908507e-05, "loss": 0.5802, "step": 360 }, { "epoch": 0.1, "learning_rate": 1.9745558360150614e-05, "loss": 0.5665, "step": 361 }, { "epoch": 0.1, "learning_rate": 1.9743543668361636e-05, "loss": 0.5769, "step": 362 }, { "epoch": 0.1, "learning_rate": 1.9741521135339485e-05, "loss": 0.5876, "step": 363 }, { "epoch": 0.1, "learning_rate": 1.9739490762711812e-05, "loss": 0.5701, "step": 364 }, { "epoch": 0.1, "learning_rate": 1.9737452552112596e-05, "loss": 0.5608, "step": 365 }, { "epoch": 0.1, "learning_rate": 1.9735406505182095e-05, "loss": 0.5861, "step": 366 }, { "epoch": 0.1, "learning_rate": 1.9733352623566904e-05, "loss": 0.5924, "step": 367 }, { "epoch": 0.1, "learning_rate": 1.9731290908919903e-05, "loss": 0.5814, "step": 368 }, { "epoch": 0.1, "learning_rate": 1.972922136290028e-05, "loss": 0.5942, "step": 369 }, { "epoch": 0.1, "learning_rate": 1.972714398717353e-05, "loss": 0.574, "step": 370 }, { "epoch": 0.1, "learning_rate": 1.9725058783411442e-05, "loss": 0.5752, "step": 371 }, { "epoch": 0.1, "learning_rate": 1.972296575329211e-05, "loss": 0.5645, "step": 372 }, { "epoch": 0.1, "learning_rate": 1.972086489849993e-05, "loss": 0.5765, "step": 373 }, { "epoch": 0.1, "learning_rate": 1.9718756220725586e-05, "loss": 0.5752, "step": 374 }, { "epoch": 0.1, "learning_rate": 1.971663972166606e-05, "loss": 0.574, "step": 375 }, { "epoch": 0.1, "learning_rate": 1.9714515403024633e-05, "loss": 0.5868, "step": 376 }, { "epoch": 0.1, "learning_rate": 1.971238326651087e-05, "loss": 0.5735, "step": 377 }, { "epoch": 0.1, "learning_rate": 1.9710243313840643e-05, "loss": 0.5671, "step": 378 }, { "epoch": 0.1, "learning_rate": 1.97080955467361e-05, "loss": 0.586, "step": 379 }, { "epoch": 0.11, "learning_rate": 1.9705939966925677e-05, "loss": 0.5589, "step": 380 }, { "epoch": 0.11, "learning_rate": 1.9703776576144106e-05, "loss": 0.5702, "step": 381 }, { "epoch": 0.11, "learning_rate": 1.9701605376132405e-05, "loss": 0.5709, "step": 382 }, { "epoch": 0.11, "learning_rate": 1.9699426368637874e-05, "loss": 0.5581, "step": 383 }, { "epoch": 0.11, "learning_rate": 1.9697239555414088e-05, "loss": 0.592, "step": 384 }, { "epoch": 0.11, "learning_rate": 1.9695044938220917e-05, "loss": 0.5834, "step": 385 }, { "epoch": 0.11, "learning_rate": 1.9692842518824503e-05, "loss": 0.5721, "step": 386 }, { "epoch": 0.11, "learning_rate": 1.9690632298997272e-05, "loss": 0.5717, "step": 387 }, { "epoch": 0.11, "learning_rate": 1.968841428051792e-05, "loss": 0.5856, "step": 388 }, { "epoch": 0.11, "learning_rate": 1.9686188465171425e-05, "loss": 0.5725, "step": 389 }, { "epoch": 0.11, "learning_rate": 1.9683954854749042e-05, "loss": 0.5949, "step": 390 }, { "epoch": 0.11, "learning_rate": 1.9681713451048298e-05, "loss": 0.5754, "step": 391 }, { "epoch": 0.11, "learning_rate": 1.9679464255872978e-05, "loss": 0.5604, "step": 392 }, { "epoch": 0.11, "learning_rate": 1.967720727103316e-05, "loss": 0.5803, "step": 393 }, { "epoch": 0.11, "learning_rate": 1.9674942498345175e-05, "loss": 0.5677, "step": 394 }, { "epoch": 0.11, "learning_rate": 1.9672669939631627e-05, "loss": 0.5712, "step": 395 }, { "epoch": 0.11, "learning_rate": 1.967038959672138e-05, "loss": 0.5666, "step": 396 }, { "epoch": 0.11, "learning_rate": 1.9668101471449575e-05, "loss": 0.5759, "step": 397 }, { "epoch": 0.11, "learning_rate": 1.9665805565657602e-05, "loss": 0.5694, "step": 398 }, { "epoch": 0.11, "learning_rate": 1.966350188119312e-05, "loss": 0.5855, "step": 399 }, { "epoch": 0.11, "learning_rate": 1.966119041991005e-05, "loss": 0.5488, "step": 400 }, { "epoch": 0.11, "learning_rate": 1.9658871183668567e-05, "loss": 0.5717, "step": 401 }, { "epoch": 0.11, "learning_rate": 1.96565441743351e-05, "loss": 0.5637, "step": 402 }, { "epoch": 0.11, "learning_rate": 1.965420939378234e-05, "loss": 0.5804, "step": 403 }, { "epoch": 0.11, "learning_rate": 1.9651866843889233e-05, "loss": 0.5599, "step": 404 }, { "epoch": 0.11, "learning_rate": 1.9649516526540968e-05, "loss": 0.5723, "step": 405 }, { "epoch": 0.11, "learning_rate": 1.9647158443629e-05, "loss": 0.5733, "step": 406 }, { "epoch": 0.11, "learning_rate": 1.964479259705101e-05, "loss": 0.5718, "step": 407 }, { "epoch": 0.11, "learning_rate": 1.964241898871095e-05, "loss": 0.5922, "step": 408 }, { "epoch": 0.11, "learning_rate": 1.9640037620519013e-05, "loss": 0.5758, "step": 409 }, { "epoch": 0.11, "learning_rate": 1.9637648494391628e-05, "loss": 0.5788, "step": 410 }, { "epoch": 0.11, "learning_rate": 1.9635251612251475e-05, "loss": 0.5711, "step": 411 }, { "epoch": 0.11, "learning_rate": 1.9632846976027475e-05, "loss": 0.5768, "step": 412 }, { "epoch": 0.11, "learning_rate": 1.963043458765478e-05, "loss": 0.5688, "step": 413 }, { "epoch": 0.11, "learning_rate": 1.96280144490748e-05, "loss": 0.5693, "step": 414 }, { "epoch": 0.11, "learning_rate": 1.962558656223516e-05, "loss": 0.5912, "step": 415 }, { "epoch": 0.12, "learning_rate": 1.9623150929089737e-05, "loss": 0.5754, "step": 416 }, { "epoch": 0.12, "learning_rate": 1.9620707551598635e-05, "loss": 0.5607, "step": 417 }, { "epoch": 0.12, "learning_rate": 1.961825643172819e-05, "loss": 0.5765, "step": 418 }, { "epoch": 0.12, "learning_rate": 1.9615797571450976e-05, "loss": 0.5753, "step": 419 }, { "epoch": 0.12, "learning_rate": 1.9613330972745775e-05, "loss": 0.5723, "step": 420 }, { "epoch": 0.12, "learning_rate": 1.961085663759763e-05, "loss": 0.5697, "step": 421 }, { "epoch": 0.12, "learning_rate": 1.960837456799778e-05, "loss": 0.5635, "step": 422 }, { "epoch": 0.12, "learning_rate": 1.9605884765943703e-05, "loss": 0.5771, "step": 423 }, { "epoch": 0.12, "learning_rate": 1.9603387233439096e-05, "loss": 0.5775, "step": 424 }, { "epoch": 0.12, "learning_rate": 1.960088197249388e-05, "loss": 0.5785, "step": 425 }, { "epoch": 0.12, "learning_rate": 1.9598368985124198e-05, "loss": 0.57, "step": 426 }, { "epoch": 0.12, "learning_rate": 1.9595848273352397e-05, "loss": 0.5746, "step": 427 }, { "epoch": 0.12, "learning_rate": 1.9593319839207057e-05, "loss": 0.5762, "step": 428 }, { "epoch": 0.12, "learning_rate": 1.959078368472296e-05, "loss": 0.5762, "step": 429 }, { "epoch": 0.12, "learning_rate": 1.958823981194111e-05, "loss": 0.5805, "step": 430 }, { "epoch": 0.12, "learning_rate": 1.9585688222908726e-05, "loss": 0.5898, "step": 431 }, { "epoch": 0.12, "learning_rate": 1.9583128919679218e-05, "loss": 0.5789, "step": 432 }, { "epoch": 0.12, "learning_rate": 1.958056190431222e-05, "loss": 0.568, "step": 433 }, { "epoch": 0.12, "learning_rate": 1.9577987178873567e-05, "loss": 0.5799, "step": 434 }, { "epoch": 0.12, "learning_rate": 1.9575404745435306e-05, "loss": 0.5639, "step": 435 }, { "epoch": 0.12, "learning_rate": 1.9572814606075674e-05, "loss": 0.5761, "step": 436 }, { "epoch": 0.12, "learning_rate": 1.957021676287912e-05, "loss": 0.5813, "step": 437 }, { "epoch": 0.12, "learning_rate": 1.956761121793629e-05, "loss": 0.5739, "step": 438 }, { "epoch": 0.12, "learning_rate": 1.9564997973344027e-05, "loss": 0.5757, "step": 439 }, { "epoch": 0.12, "learning_rate": 1.956237703120537e-05, "loss": 0.5875, "step": 440 }, { "epoch": 0.12, "learning_rate": 1.9559748393629553e-05, "loss": 0.5792, "step": 441 }, { "epoch": 0.12, "learning_rate": 1.9557112062732004e-05, "loss": 0.5814, "step": 442 }, { "epoch": 0.12, "learning_rate": 1.9554468040634345e-05, "loss": 0.5798, "step": 443 }, { "epoch": 0.12, "learning_rate": 1.955181632946438e-05, "loss": 0.5665, "step": 444 }, { "epoch": 0.12, "learning_rate": 1.9549156931356106e-05, "loss": 0.5735, "step": 445 }, { "epoch": 0.12, "learning_rate": 1.9546489848449705e-05, "loss": 0.5765, "step": 446 }, { "epoch": 0.12, "learning_rate": 1.9543815082891547e-05, "loss": 0.5817, "step": 447 }, { "epoch": 0.12, "learning_rate": 1.9541132636834175e-05, "loss": 0.5738, "step": 448 }, { "epoch": 0.12, "learning_rate": 1.953844251243633e-05, "loss": 0.5681, "step": 449 }, { "epoch": 0.12, "learning_rate": 1.953574471186291e-05, "loss": 0.5689, "step": 450 }, { "epoch": 0.12, "learning_rate": 1.9533039237285012e-05, "loss": 0.5784, "step": 451 }, { "epoch": 0.13, "learning_rate": 1.9530326090879896e-05, "loss": 0.5601, "step": 452 }, { "epoch": 0.13, "learning_rate": 1.9527605274830993e-05, "loss": 0.5765, "step": 453 }, { "epoch": 0.13, "learning_rate": 1.952487679132792e-05, "loss": 0.5712, "step": 454 }, { "epoch": 0.13, "learning_rate": 1.952214064256645e-05, "loss": 0.5736, "step": 455 }, { "epoch": 0.13, "learning_rate": 1.951939683074854e-05, "loss": 0.5788, "step": 456 }, { "epoch": 0.13, "learning_rate": 1.95166453580823e-05, "loss": 0.5634, "step": 457 }, { "epoch": 0.13, "learning_rate": 1.951388622678201e-05, "loss": 0.5765, "step": 458 }, { "epoch": 0.13, "learning_rate": 1.9511119439068116e-05, "loss": 0.571, "step": 459 }, { "epoch": 0.13, "learning_rate": 1.950834499716722e-05, "loss": 0.561, "step": 460 }, { "epoch": 0.13, "learning_rate": 1.950556290331209e-05, "loss": 0.5587, "step": 461 }, { "epoch": 0.13, "learning_rate": 1.9502773159741654e-05, "loss": 0.5765, "step": 462 }, { "epoch": 0.13, "learning_rate": 1.949997576870098e-05, "loss": 0.5817, "step": 463 }, { "epoch": 0.13, "learning_rate": 1.9497170732441314e-05, "loss": 0.566, "step": 464 }, { "epoch": 0.13, "learning_rate": 1.949435805322003e-05, "loss": 0.5678, "step": 465 }, { "epoch": 0.13, "learning_rate": 1.9491537733300677e-05, "loss": 0.5733, "step": 466 }, { "epoch": 0.13, "learning_rate": 1.9488709774952937e-05, "loss": 0.5689, "step": 467 }, { "epoch": 0.13, "learning_rate": 1.9485874180452636e-05, "loss": 0.5669, "step": 468 }, { "epoch": 0.13, "learning_rate": 1.9483030952081765e-05, "loss": 0.5865, "step": 469 }, { "epoch": 0.13, "learning_rate": 1.948018009212844e-05, "loss": 0.5672, "step": 470 }, { "epoch": 0.13, "learning_rate": 1.947732160288692e-05, "loss": 0.5714, "step": 471 }, { "epoch": 0.13, "learning_rate": 1.9474455486657615e-05, "loss": 0.5846, "step": 472 }, { "epoch": 0.13, "learning_rate": 1.9471581745747065e-05, "loss": 0.5782, "step": 473 }, { "epoch": 0.13, "learning_rate": 1.9468700382467945e-05, "loss": 0.5638, "step": 474 }, { "epoch": 0.13, "learning_rate": 1.9465811399139068e-05, "loss": 0.5659, "step": 475 }, { "epoch": 0.13, "learning_rate": 1.946291479808538e-05, "loss": 0.5745, "step": 476 }, { "epoch": 0.13, "learning_rate": 1.9460010581637952e-05, "loss": 0.5767, "step": 477 }, { "epoch": 0.13, "learning_rate": 1.9457098752133986e-05, "loss": 0.5637, "step": 478 }, { "epoch": 0.13, "learning_rate": 1.9454179311916813e-05, "loss": 0.5792, "step": 479 }, { "epoch": 0.13, "learning_rate": 1.9451252263335892e-05, "loss": 0.569, "step": 480 }, { "epoch": 0.13, "learning_rate": 1.9448317608746795e-05, "loss": 0.5784, "step": 481 }, { "epoch": 0.13, "learning_rate": 1.9445375350511222e-05, "loss": 0.5638, "step": 482 }, { "epoch": 0.13, "learning_rate": 1.9442425490996987e-05, "loss": 0.5663, "step": 483 }, { "epoch": 0.13, "learning_rate": 1.943946803257803e-05, "loss": 0.5701, "step": 484 }, { "epoch": 0.13, "learning_rate": 1.94365029776344e-05, "loss": 0.5653, "step": 485 }, { "epoch": 0.13, "learning_rate": 1.943353032855226e-05, "loss": 0.5699, "step": 486 }, { "epoch": 0.13, "learning_rate": 1.9430550087723882e-05, "loss": 0.5675, "step": 487 }, { "epoch": 0.14, "learning_rate": 1.9427562257547648e-05, "loss": 0.5731, "step": 488 }, { "epoch": 0.14, "learning_rate": 1.942456684042806e-05, "loss": 0.5731, "step": 489 }, { "epoch": 0.14, "learning_rate": 1.942156383877571e-05, "loss": 0.5674, "step": 490 }, { "epoch": 0.14, "learning_rate": 1.94185532550073e-05, "loss": 0.5648, "step": 491 }, { "epoch": 0.14, "learning_rate": 1.9415535091545633e-05, "loss": 0.5799, "step": 492 }, { "epoch": 0.14, "learning_rate": 1.941250935081961e-05, "loss": 0.5835, "step": 493 }, { "epoch": 0.14, "learning_rate": 1.9409476035264237e-05, "loss": 0.5798, "step": 494 }, { "epoch": 0.14, "learning_rate": 1.9406435147320605e-05, "loss": 0.5807, "step": 495 }, { "epoch": 0.14, "learning_rate": 1.940338668943591e-05, "loss": 0.5538, "step": 496 }, { "epoch": 0.14, "learning_rate": 1.940033066406343e-05, "loss": 0.5652, "step": 497 }, { "epoch": 0.14, "learning_rate": 1.9397267073662543e-05, "loss": 0.576, "step": 498 }, { "epoch": 0.14, "learning_rate": 1.9394195920698706e-05, "loss": 0.5821, "step": 499 }, { "epoch": 0.14, "learning_rate": 1.939111720764347e-05, "loss": 0.5615, "step": 500 }, { "epoch": 0.14, "learning_rate": 1.9388030936974463e-05, "loss": 0.5633, "step": 501 }, { "epoch": 0.14, "learning_rate": 1.9384937111175398e-05, "loss": 0.562, "step": 502 }, { "epoch": 0.14, "learning_rate": 1.938183573273607e-05, "loss": 0.5792, "step": 503 }, { "epoch": 0.14, "learning_rate": 1.937872680415235e-05, "loss": 0.5598, "step": 504 }, { "epoch": 0.14, "learning_rate": 1.9375610327926182e-05, "loss": 0.572, "step": 505 }, { "epoch": 0.14, "learning_rate": 1.9372486306565594e-05, "loss": 0.5593, "step": 506 }, { "epoch": 0.14, "learning_rate": 1.9369354742584676e-05, "loss": 0.5821, "step": 507 }, { "epoch": 0.14, "learning_rate": 1.9366215638503592e-05, "loss": 0.561, "step": 508 }, { "epoch": 0.14, "learning_rate": 1.936306899684857e-05, "loss": 0.5554, "step": 509 }, { "epoch": 0.14, "learning_rate": 1.9359914820151915e-05, "loss": 0.5687, "step": 510 }, { "epoch": 0.14, "learning_rate": 1.935675311095198e-05, "loss": 0.5767, "step": 511 }, { "epoch": 0.14, "learning_rate": 1.9353583871793195e-05, "loss": 0.5646, "step": 512 }, { "epoch": 0.14, "learning_rate": 1.935040710522604e-05, "loss": 0.5535, "step": 513 }, { "epoch": 0.14, "learning_rate": 1.9347222813807054e-05, "loss": 0.5697, "step": 514 }, { "epoch": 0.14, "learning_rate": 1.9344031000098836e-05, "loss": 0.5935, "step": 515 }, { "epoch": 0.14, "learning_rate": 1.934083166667004e-05, "loss": 0.5769, "step": 516 }, { "epoch": 0.14, "learning_rate": 1.933762481609536e-05, "loss": 0.5643, "step": 517 }, { "epoch": 0.14, "learning_rate": 1.9334410450955547e-05, "loss": 0.572, "step": 518 }, { "epoch": 0.14, "learning_rate": 1.933118857383741e-05, "loss": 0.564, "step": 519 }, { "epoch": 0.14, "learning_rate": 1.9327959187333784e-05, "loss": 0.5746, "step": 520 }, { "epoch": 0.14, "learning_rate": 1.932472229404356e-05, "loss": 0.58, "step": 521 }, { "epoch": 0.14, "learning_rate": 1.9321477896571664e-05, "loss": 0.5656, "step": 522 }, { "epoch": 0.14, "learning_rate": 1.931822599752907e-05, "loss": 0.5717, "step": 523 }, { "epoch": 0.15, "learning_rate": 1.9314966599532774e-05, "loss": 0.5835, "step": 524 }, { "epoch": 0.15, "learning_rate": 1.931169970520582e-05, "loss": 0.581, "step": 525 }, { "epoch": 0.15, "learning_rate": 1.9308425317177282e-05, "loss": 0.5623, "step": 526 }, { "epoch": 0.15, "learning_rate": 1.930514343808226e-05, "loss": 0.567, "step": 527 }, { "epoch": 0.15, "learning_rate": 1.9301854070561883e-05, "loss": 0.5684, "step": 528 }, { "epoch": 0.15, "learning_rate": 1.9298557217263315e-05, "loss": 0.5729, "step": 529 }, { "epoch": 0.15, "learning_rate": 1.9295252880839733e-05, "loss": 0.5566, "step": 530 }, { "epoch": 0.15, "learning_rate": 1.9291941063950347e-05, "loss": 0.5795, "step": 531 }, { "epoch": 0.15, "learning_rate": 1.9288621769260372e-05, "loss": 0.5773, "step": 532 }, { "epoch": 0.15, "learning_rate": 1.928529499944106e-05, "loss": 0.5764, "step": 533 }, { "epoch": 0.15, "learning_rate": 1.928196075716966e-05, "loss": 0.5682, "step": 534 }, { "epoch": 0.15, "learning_rate": 1.9278619045129452e-05, "loss": 0.5595, "step": 535 }, { "epoch": 0.15, "learning_rate": 1.927526986600971e-05, "loss": 0.5735, "step": 536 }, { "epoch": 0.15, "learning_rate": 1.9271913222505733e-05, "loss": 0.5654, "step": 537 }, { "epoch": 0.15, "learning_rate": 1.9268549117318814e-05, "loss": 0.5636, "step": 538 }, { "epoch": 0.15, "learning_rate": 1.9265177553156262e-05, "loss": 0.5575, "step": 539 }, { "epoch": 0.15, "learning_rate": 1.926179853273138e-05, "loss": 0.5703, "step": 540 }, { "epoch": 0.15, "learning_rate": 1.9258412058763478e-05, "loss": 0.5741, "step": 541 }, { "epoch": 0.15, "learning_rate": 1.9255018133977858e-05, "loss": 0.5755, "step": 542 }, { "epoch": 0.15, "learning_rate": 1.9251616761105826e-05, "loss": 0.5629, "step": 543 }, { "epoch": 0.15, "learning_rate": 1.9248207942884675e-05, "loss": 0.5635, "step": 544 }, { "epoch": 0.15, "learning_rate": 1.924479168205769e-05, "loss": 0.565, "step": 545 }, { "epoch": 0.15, "learning_rate": 1.924136798137415e-05, "loss": 0.564, "step": 546 }, { "epoch": 0.15, "learning_rate": 1.9237936843589317e-05, "loss": 0.5665, "step": 547 }, { "epoch": 0.15, "learning_rate": 1.9234498271464446e-05, "loss": 0.5516, "step": 548 }, { "epoch": 0.15, "learning_rate": 1.9231052267766764e-05, "loss": 0.5791, "step": 549 }, { "epoch": 0.15, "learning_rate": 1.9227598835269482e-05, "loss": 0.5678, "step": 550 }, { "epoch": 0.15, "learning_rate": 1.9224137976751797e-05, "loss": 0.5778, "step": 551 }, { "epoch": 0.15, "learning_rate": 1.9220669694998867e-05, "loss": 0.5616, "step": 552 }, { "epoch": 0.15, "learning_rate": 1.9217193992801843e-05, "loss": 0.5737, "step": 553 }, { "epoch": 0.15, "learning_rate": 1.9213710872957833e-05, "loss": 0.5657, "step": 554 }, { "epoch": 0.15, "learning_rate": 1.921022033826992e-05, "loss": 0.5743, "step": 555 }, { "epoch": 0.15, "learning_rate": 1.9206722391547153e-05, "loss": 0.5621, "step": 556 }, { "epoch": 0.15, "learning_rate": 1.9203217035604555e-05, "loss": 0.5667, "step": 557 }, { "epoch": 0.15, "learning_rate": 1.9199704273263084e-05, "loss": 0.5608, "step": 558 }, { "epoch": 0.15, "learning_rate": 1.9196184107349697e-05, "loss": 0.5609, "step": 559 }, { "epoch": 0.16, "learning_rate": 1.9192656540697275e-05, "loss": 0.5779, "step": 560 }, { "epoch": 0.16, "learning_rate": 1.918912157614468e-05, "loss": 0.5668, "step": 561 }, { "epoch": 0.16, "learning_rate": 1.9185579216536706e-05, "loss": 0.5688, "step": 562 }, { "epoch": 0.16, "learning_rate": 1.918202946472412e-05, "loss": 0.5802, "step": 563 }, { "epoch": 0.16, "learning_rate": 1.9178472323563628e-05, "loss": 0.562, "step": 564 }, { "epoch": 0.16, "learning_rate": 1.917490779591787e-05, "loss": 0.5616, "step": 565 }, { "epoch": 0.16, "learning_rate": 1.917133588465545e-05, "loss": 0.5566, "step": 566 }, { "epoch": 0.16, "learning_rate": 1.9167756592650907e-05, "loss": 0.5839, "step": 567 }, { "epoch": 0.16, "learning_rate": 1.9164169922784717e-05, "loss": 0.565, "step": 568 }, { "epoch": 0.16, "learning_rate": 1.9160575877943296e-05, "loss": 0.5596, "step": 569 }, { "epoch": 0.16, "learning_rate": 1.9156974461018995e-05, "loss": 0.5724, "step": 570 }, { "epoch": 0.16, "learning_rate": 1.9153365674910095e-05, "loss": 0.578, "step": 571 }, { "epoch": 0.16, "learning_rate": 1.914974952252081e-05, "loss": 0.5683, "step": 572 }, { "epoch": 0.16, "learning_rate": 1.9146126006761282e-05, "loss": 0.5654, "step": 573 }, { "epoch": 0.16, "learning_rate": 1.9142495130547582e-05, "loss": 0.5686, "step": 574 }, { "epoch": 0.16, "learning_rate": 1.91388568968017e-05, "loss": 0.5556, "step": 575 }, { "epoch": 0.16, "learning_rate": 1.9135211308451547e-05, "loss": 0.5641, "step": 576 }, { "epoch": 0.16, "learning_rate": 1.913155836843095e-05, "loss": 0.5837, "step": 577 }, { "epoch": 0.16, "learning_rate": 1.9127898079679662e-05, "loss": 0.5651, "step": 578 }, { "epoch": 0.16, "learning_rate": 1.912423044514334e-05, "loss": 0.5775, "step": 579 }, { "epoch": 0.16, "learning_rate": 1.9120555467773564e-05, "loss": 0.5772, "step": 580 }, { "epoch": 0.16, "learning_rate": 1.9116873150527807e-05, "loss": 0.5677, "step": 581 }, { "epoch": 0.16, "learning_rate": 1.9113183496369458e-05, "loss": 0.5727, "step": 582 }, { "epoch": 0.16, "learning_rate": 1.9109486508267818e-05, "loss": 0.5548, "step": 583 }, { "epoch": 0.16, "learning_rate": 1.9105782189198073e-05, "loss": 0.5641, "step": 584 }, { "epoch": 0.16, "learning_rate": 1.910207054214133e-05, "loss": 0.5697, "step": 585 }, { "epoch": 0.16, "learning_rate": 1.9098351570084567e-05, "loss": 0.5749, "step": 586 }, { "epoch": 0.16, "learning_rate": 1.9094625276020685e-05, "loss": 0.5586, "step": 587 }, { "epoch": 0.16, "learning_rate": 1.909089166294845e-05, "loss": 0.574, "step": 588 }, { "epoch": 0.16, "learning_rate": 1.9087150733872546e-05, "loss": 0.5732, "step": 589 }, { "epoch": 0.16, "learning_rate": 1.9083402491803517e-05, "loss": 0.5711, "step": 590 }, { "epoch": 0.16, "learning_rate": 1.9079646939757815e-05, "loss": 0.5633, "step": 591 }, { "epoch": 0.16, "learning_rate": 1.9075884080757762e-05, "loss": 0.5664, "step": 592 }, { "epoch": 0.16, "learning_rate": 1.907211391783156e-05, "loss": 0.5577, "step": 593 }, { "epoch": 0.16, "learning_rate": 1.9068336454013302e-05, "loss": 0.5858, "step": 594 }, { "epoch": 0.16, "learning_rate": 1.906455169234294e-05, "loss": 0.5739, "step": 595 }, { "epoch": 0.17, "learning_rate": 1.9060759635866305e-05, "loss": 0.5626, "step": 596 }, { "epoch": 0.17, "learning_rate": 1.9056960287635107e-05, "loss": 0.5828, "step": 597 }, { "epoch": 0.17, "learning_rate": 1.905315365070691e-05, "loss": 0.5635, "step": 598 }, { "epoch": 0.17, "learning_rate": 1.9049339728145152e-05, "loss": 0.5578, "step": 599 }, { "epoch": 0.17, "learning_rate": 1.9045518523019137e-05, "loss": 0.5669, "step": 600 }, { "epoch": 0.17, "learning_rate": 1.904169003840402e-05, "loss": 0.5614, "step": 601 }, { "epoch": 0.17, "learning_rate": 1.903785427738082e-05, "loss": 0.5802, "step": 602 }, { "epoch": 0.17, "learning_rate": 1.9034011243036414e-05, "loss": 0.5641, "step": 603 }, { "epoch": 0.17, "learning_rate": 1.903016093846353e-05, "loss": 0.5657, "step": 604 }, { "epoch": 0.17, "learning_rate": 1.902630336676075e-05, "loss": 0.5784, "step": 605 }, { "epoch": 0.17, "learning_rate": 1.9022438531032493e-05, "loss": 0.5763, "step": 606 }, { "epoch": 0.17, "learning_rate": 1.9018566434389037e-05, "loss": 0.5624, "step": 607 }, { "epoch": 0.17, "learning_rate": 1.9014687079946494e-05, "loss": 0.5655, "step": 608 }, { "epoch": 0.17, "learning_rate": 1.9010800470826826e-05, "loss": 0.5543, "step": 609 }, { "epoch": 0.17, "learning_rate": 1.900690661015782e-05, "loss": 0.5574, "step": 610 }, { "epoch": 0.17, "learning_rate": 1.900300550107312e-05, "loss": 0.5819, "step": 611 }, { "epoch": 0.17, "learning_rate": 1.899909714671218e-05, "loss": 0.5754, "step": 612 }, { "epoch": 0.17, "learning_rate": 1.8995181550220296e-05, "loss": 0.5525, "step": 613 }, { "epoch": 0.17, "learning_rate": 1.8991258714748594e-05, "loss": 0.5675, "step": 614 }, { "epoch": 0.17, "learning_rate": 1.898732864345402e-05, "loss": 0.5786, "step": 615 }, { "epoch": 0.17, "learning_rate": 1.8983391339499344e-05, "loss": 0.5712, "step": 616 }, { "epoch": 0.17, "learning_rate": 1.8979446806053167e-05, "loss": 0.562, "step": 617 }, { "epoch": 0.17, "learning_rate": 1.897549504628989e-05, "loss": 0.5637, "step": 618 }, { "epoch": 0.17, "learning_rate": 1.8971536063389745e-05, "loss": 0.5782, "step": 619 }, { "epoch": 0.17, "learning_rate": 1.8967569860538765e-05, "loss": 0.5732, "step": 620 }, { "epoch": 0.17, "learning_rate": 1.8963596440928806e-05, "loss": 0.5753, "step": 621 }, { "epoch": 0.17, "learning_rate": 1.8959615807757522e-05, "loss": 0.5602, "step": 622 }, { "epoch": 0.17, "learning_rate": 1.895562796422837e-05, "loss": 0.5725, "step": 623 }, { "epoch": 0.17, "learning_rate": 1.8951632913550625e-05, "loss": 0.5714, "step": 624 }, { "epoch": 0.17, "learning_rate": 1.894763065893934e-05, "loss": 0.5716, "step": 625 }, { "epoch": 0.17, "learning_rate": 1.894362120361539e-05, "loss": 0.5656, "step": 626 }, { "epoch": 0.17, "learning_rate": 1.8939604550805422e-05, "loss": 0.591, "step": 627 }, { "epoch": 0.17, "learning_rate": 1.893558070374189e-05, "loss": 0.5718, "step": 628 }, { "epoch": 0.17, "learning_rate": 1.893154966566303e-05, "loss": 0.591, "step": 629 }, { "epoch": 0.17, "learning_rate": 1.892751143981287e-05, "loss": 0.5735, "step": 630 }, { "epoch": 0.17, "learning_rate": 1.892346602944122e-05, "loss": 0.5541, "step": 631 }, { "epoch": 0.17, "learning_rate": 1.8919413437803676e-05, "loss": 0.5649, "step": 632 }, { "epoch": 0.18, "learning_rate": 1.8915353668161605e-05, "loss": 0.5661, "step": 633 }, { "epoch": 0.18, "learning_rate": 1.891128672378215e-05, "loss": 0.5651, "step": 634 }, { "epoch": 0.18, "learning_rate": 1.8907212607938247e-05, "loss": 0.5649, "step": 635 }, { "epoch": 0.18, "learning_rate": 1.890313132390858e-05, "loss": 0.5624, "step": 636 }, { "epoch": 0.18, "learning_rate": 1.8899042874977613e-05, "loss": 0.5616, "step": 637 }, { "epoch": 0.18, "learning_rate": 1.889494726443557e-05, "loss": 0.5729, "step": 638 }, { "epoch": 0.18, "learning_rate": 1.8890844495578448e-05, "loss": 0.5546, "step": 639 }, { "epoch": 0.18, "learning_rate": 1.8886734571708e-05, "loss": 0.5801, "step": 640 }, { "epoch": 0.18, "learning_rate": 1.8882617496131735e-05, "loss": 0.5638, "step": 641 }, { "epoch": 0.18, "learning_rate": 1.8878493272162914e-05, "loss": 0.573, "step": 642 }, { "epoch": 0.18, "learning_rate": 1.8874361903120562e-05, "loss": 0.5656, "step": 643 }, { "epoch": 0.18, "learning_rate": 1.8870223392329443e-05, "loss": 0.5674, "step": 644 }, { "epoch": 0.18, "learning_rate": 1.8866077743120076e-05, "loss": 0.5718, "step": 645 }, { "epoch": 0.18, "learning_rate": 1.886192495882872e-05, "loss": 0.562, "step": 646 }, { "epoch": 0.18, "learning_rate": 1.8857765042797382e-05, "loss": 0.5739, "step": 647 }, { "epoch": 0.18, "learning_rate": 1.8853597998373795e-05, "loss": 0.5662, "step": 648 }, { "epoch": 0.18, "learning_rate": 1.8849423828911446e-05, "loss": 0.5765, "step": 649 }, { "epoch": 0.18, "learning_rate": 1.8845242537769545e-05, "loss": 0.569, "step": 650 }, { "epoch": 0.18, "learning_rate": 1.8841054128313036e-05, "loss": 0.5758, "step": 651 }, { "epoch": 0.18, "learning_rate": 1.883685860391259e-05, "loss": 0.565, "step": 652 }, { "epoch": 0.18, "learning_rate": 1.8832655967944607e-05, "loss": 0.563, "step": 653 }, { "epoch": 0.18, "learning_rate": 1.8828446223791214e-05, "loss": 0.5688, "step": 654 }, { "epoch": 0.18, "learning_rate": 1.8824229374840242e-05, "loss": 0.5645, "step": 655 }, { "epoch": 0.18, "learning_rate": 1.882000542448526e-05, "loss": 0.562, "step": 656 }, { "epoch": 0.18, "learning_rate": 1.881577437612553e-05, "loss": 0.5637, "step": 657 }, { "epoch": 0.18, "learning_rate": 1.8811536233166056e-05, "loss": 0.562, "step": 658 }, { "epoch": 0.18, "learning_rate": 1.8807290999017524e-05, "loss": 0.5656, "step": 659 }, { "epoch": 0.18, "learning_rate": 1.8803038677096335e-05, "loss": 0.5487, "step": 660 }, { "epoch": 0.18, "learning_rate": 1.8798779270824602e-05, "loss": 0.5624, "step": 661 }, { "epoch": 0.18, "learning_rate": 1.8794512783630126e-05, "loss": 0.5734, "step": 662 }, { "epoch": 0.18, "learning_rate": 1.8790239218946424e-05, "loss": 0.5712, "step": 663 }, { "epoch": 0.18, "learning_rate": 1.878595858021269e-05, "loss": 0.5781, "step": 664 }, { "epoch": 0.18, "learning_rate": 1.878167087087382e-05, "loss": 0.5677, "step": 665 }, { "epoch": 0.18, "learning_rate": 1.87773760943804e-05, "loss": 0.5735, "step": 666 }, { "epoch": 0.18, "learning_rate": 1.8773074254188706e-05, "loss": 0.5652, "step": 667 }, { "epoch": 0.18, "learning_rate": 1.8768765353760688e-05, "loss": 0.564, "step": 668 }, { "epoch": 0.19, "learning_rate": 1.8764449396563994e-05, "loss": 0.5609, "step": 669 }, { "epoch": 0.19, "learning_rate": 1.8760126386071937e-05, "loss": 0.5678, "step": 670 }, { "epoch": 0.19, "learning_rate": 1.8755796325763508e-05, "loss": 0.5777, "step": 671 }, { "epoch": 0.19, "learning_rate": 1.875145921912338e-05, "loss": 0.5729, "step": 672 }, { "epoch": 0.19, "learning_rate": 1.8747115069641893e-05, "loss": 0.5624, "step": 673 }, { "epoch": 0.19, "learning_rate": 1.874276388081505e-05, "loss": 0.5582, "step": 674 }, { "epoch": 0.19, "learning_rate": 1.8738405656144522e-05, "loss": 0.565, "step": 675 }, { "epoch": 0.19, "learning_rate": 1.8734040399137642e-05, "loss": 0.5642, "step": 676 }, { "epoch": 0.19, "learning_rate": 1.8729668113307405e-05, "loss": 0.5708, "step": 677 }, { "epoch": 0.19, "learning_rate": 1.872528880217246e-05, "loss": 0.5528, "step": 678 }, { "epoch": 0.19, "learning_rate": 1.8720902469257108e-05, "loss": 0.578, "step": 679 }, { "epoch": 0.19, "learning_rate": 1.87165091180913e-05, "loss": 0.5596, "step": 680 }, { "epoch": 0.19, "learning_rate": 1.8712108752210646e-05, "loss": 0.5643, "step": 681 }, { "epoch": 0.19, "learning_rate": 1.8707701375156388e-05, "loss": 0.5595, "step": 682 }, { "epoch": 0.19, "learning_rate": 1.8703286990475415e-05, "loss": 0.5683, "step": 683 }, { "epoch": 0.19, "learning_rate": 1.8698865601720255e-05, "loss": 0.5648, "step": 684 }, { "epoch": 0.19, "learning_rate": 1.869443721244908e-05, "loss": 0.5597, "step": 685 }, { "epoch": 0.19, "learning_rate": 1.869000182622568e-05, "loss": 0.5833, "step": 686 }, { "epoch": 0.19, "learning_rate": 1.868555944661949e-05, "loss": 0.5452, "step": 687 }, { "epoch": 0.19, "learning_rate": 1.8681110077205566e-05, "loss": 0.5647, "step": 688 }, { "epoch": 0.19, "learning_rate": 1.8676653721564598e-05, "loss": 0.5806, "step": 689 }, { "epoch": 0.19, "learning_rate": 1.8672190383282883e-05, "loss": 0.5783, "step": 690 }, { "epoch": 0.19, "learning_rate": 1.866772006595235e-05, "loss": 0.5599, "step": 691 }, { "epoch": 0.19, "learning_rate": 1.8663242773170535e-05, "loss": 0.5645, "step": 692 }, { "epoch": 0.19, "learning_rate": 1.86587585085406e-05, "loss": 0.5816, "step": 693 }, { "epoch": 0.19, "learning_rate": 1.8654267275671306e-05, "loss": 0.5656, "step": 694 }, { "epoch": 0.19, "learning_rate": 1.864976907817703e-05, "loss": 0.5589, "step": 695 }, { "epoch": 0.19, "learning_rate": 1.8645263919677747e-05, "loss": 0.561, "step": 696 }, { "epoch": 0.19, "learning_rate": 1.8640751803799036e-05, "loss": 0.5713, "step": 697 }, { "epoch": 0.19, "learning_rate": 1.8636232734172082e-05, "loss": 0.5626, "step": 698 }, { "epoch": 0.19, "learning_rate": 1.8631706714433656e-05, "loss": 0.5767, "step": 699 }, { "epoch": 0.19, "learning_rate": 1.8627173748226127e-05, "loss": 0.5687, "step": 700 }, { "epoch": 0.19, "learning_rate": 1.8622633839197456e-05, "loss": 0.5648, "step": 701 }, { "epoch": 0.19, "learning_rate": 1.8618086991001185e-05, "loss": 0.5651, "step": 702 }, { "epoch": 0.19, "learning_rate": 1.861353320729644e-05, "loss": 0.5518, "step": 703 }, { "epoch": 0.19, "learning_rate": 1.8608972491747946e-05, "loss": 0.5548, "step": 704 }, { "epoch": 0.2, "learning_rate": 1.8604404848025984e-05, "loss": 0.5645, "step": 705 }, { "epoch": 0.2, "learning_rate": 1.8599830279806424e-05, "loss": 0.562, "step": 706 }, { "epoch": 0.2, "learning_rate": 1.85952487907707e-05, "loss": 0.5637, "step": 707 }, { "epoch": 0.2, "learning_rate": 1.8590660384605822e-05, "loss": 0.5573, "step": 708 }, { "epoch": 0.2, "learning_rate": 1.858606506500437e-05, "loss": 0.5714, "step": 709 }, { "epoch": 0.2, "learning_rate": 1.8581462835664475e-05, "loss": 0.5651, "step": 710 }, { "epoch": 0.2, "learning_rate": 1.857685370028984e-05, "loss": 0.5716, "step": 711 }, { "epoch": 0.2, "learning_rate": 1.857223766258972e-05, "loss": 0.5816, "step": 712 }, { "epoch": 0.2, "learning_rate": 1.8567614726278927e-05, "loss": 0.5515, "step": 713 }, { "epoch": 0.2, "learning_rate": 1.8562984895077823e-05, "loss": 0.5501, "step": 714 }, { "epoch": 0.2, "learning_rate": 1.8558348172712318e-05, "loss": 0.5756, "step": 715 }, { "epoch": 0.2, "learning_rate": 1.855370456291388e-05, "loss": 0.5651, "step": 716 }, { "epoch": 0.2, "learning_rate": 1.85490540694195e-05, "loss": 0.5556, "step": 717 }, { "epoch": 0.2, "learning_rate": 1.8544396695971716e-05, "loss": 0.5531, "step": 718 }, { "epoch": 0.2, "learning_rate": 1.8539732446318616e-05, "loss": 0.5499, "step": 719 }, { "epoch": 0.2, "learning_rate": 1.8535061324213802e-05, "loss": 0.5583, "step": 720 }, { "epoch": 0.2, "learning_rate": 1.853038333341642e-05, "loss": 0.5655, "step": 721 }, { "epoch": 0.2, "learning_rate": 1.852569847769113e-05, "loss": 0.566, "step": 722 }, { "epoch": 0.2, "learning_rate": 1.8521006760808135e-05, "loss": 0.5716, "step": 723 }, { "epoch": 0.2, "learning_rate": 1.851630818654315e-05, "loss": 0.584, "step": 724 }, { "epoch": 0.2, "learning_rate": 1.8511602758677402e-05, "loss": 0.5713, "step": 725 }, { "epoch": 0.2, "learning_rate": 1.8506890480997647e-05, "loss": 0.5508, "step": 726 }, { "epoch": 0.2, "learning_rate": 1.8502171357296144e-05, "loss": 0.5649, "step": 727 }, { "epoch": 0.2, "learning_rate": 1.8497445391370662e-05, "loss": 0.5878, "step": 728 }, { "epoch": 0.2, "learning_rate": 1.8492712587024484e-05, "loss": 0.584, "step": 729 }, { "epoch": 0.2, "learning_rate": 1.8487972948066387e-05, "loss": 0.5671, "step": 730 }, { "epoch": 0.2, "learning_rate": 1.848322647831065e-05, "loss": 0.5712, "step": 731 }, { "epoch": 0.2, "learning_rate": 1.8478473181577056e-05, "loss": 0.5585, "step": 732 }, { "epoch": 0.2, "learning_rate": 1.8473713061690874e-05, "loss": 0.5738, "step": 733 }, { "epoch": 0.2, "learning_rate": 1.8468946122482873e-05, "loss": 0.5636, "step": 734 }, { "epoch": 0.2, "learning_rate": 1.8464172367789294e-05, "loss": 0.5727, "step": 735 }, { "epoch": 0.2, "learning_rate": 1.8459391801451882e-05, "loss": 0.5647, "step": 736 }, { "epoch": 0.2, "learning_rate": 1.845460442731785e-05, "loss": 0.57, "step": 737 }, { "epoch": 0.2, "learning_rate": 1.84498102492399e-05, "loss": 0.5731, "step": 738 }, { "epoch": 0.2, "learning_rate": 1.84450092710762e-05, "loss": 0.5557, "step": 739 }, { "epoch": 0.2, "learning_rate": 1.8440201496690396e-05, "loss": 0.5653, "step": 740 }, { "epoch": 0.21, "learning_rate": 1.8435386929951596e-05, "loss": 0.5669, "step": 741 }, { "epoch": 0.21, "learning_rate": 1.843056557473439e-05, "loss": 0.5492, "step": 742 }, { "epoch": 0.21, "learning_rate": 1.8425737434918814e-05, "loss": 0.5476, "step": 743 }, { "epoch": 0.21, "learning_rate": 1.842090251439037e-05, "loss": 0.5619, "step": 744 }, { "epoch": 0.21, "learning_rate": 1.8416060817040028e-05, "loss": 0.5574, "step": 745 }, { "epoch": 0.21, "learning_rate": 1.8411212346764193e-05, "loss": 0.5635, "step": 746 }, { "epoch": 0.21, "learning_rate": 1.8406357107464733e-05, "loss": 0.5648, "step": 747 }, { "epoch": 0.21, "learning_rate": 1.8401495103048957e-05, "loss": 0.5614, "step": 748 }, { "epoch": 0.21, "learning_rate": 1.839662633742962e-05, "loss": 0.5684, "step": 749 }, { "epoch": 0.21, "learning_rate": 1.8391750814524926e-05, "loss": 0.5826, "step": 750 }, { "epoch": 0.21, "learning_rate": 1.8386868538258505e-05, "loss": 0.5576, "step": 751 }, { "epoch": 0.21, "learning_rate": 1.8381979512559427e-05, "loss": 0.5693, "step": 752 }, { "epoch": 0.21, "learning_rate": 1.8377083741362196e-05, "loss": 0.5626, "step": 753 }, { "epoch": 0.21, "learning_rate": 1.8372181228606743e-05, "loss": 0.5675, "step": 754 }, { "epoch": 0.21, "learning_rate": 1.8367271978238422e-05, "loss": 0.5551, "step": 755 }, { "epoch": 0.21, "learning_rate": 1.836235599420801e-05, "loss": 0.5577, "step": 756 }, { "epoch": 0.21, "learning_rate": 1.835743328047171e-05, "loss": 0.57, "step": 757 }, { "epoch": 0.21, "learning_rate": 1.835250384099112e-05, "loss": 0.5656, "step": 758 }, { "epoch": 0.21, "learning_rate": 1.8347567679733285e-05, "loss": 0.5693, "step": 759 }, { "epoch": 0.21, "learning_rate": 1.8342624800670624e-05, "loss": 0.5615, "step": 760 }, { "epoch": 0.21, "learning_rate": 1.8337675207780987e-05, "loss": 0.5629, "step": 761 }, { "epoch": 0.21, "learning_rate": 1.8332718905047614e-05, "loss": 0.5571, "step": 762 }, { "epoch": 0.21, "learning_rate": 1.832775589645915e-05, "loss": 0.5694, "step": 763 }, { "epoch": 0.21, "learning_rate": 1.8322786186009633e-05, "loss": 0.5601, "step": 764 }, { "epoch": 0.21, "learning_rate": 1.83178097776985e-05, "loss": 0.5595, "step": 765 }, { "epoch": 0.21, "learning_rate": 1.8312826675530578e-05, "loss": 0.5659, "step": 766 }, { "epoch": 0.21, "learning_rate": 1.830783688351607e-05, "loss": 0.5712, "step": 767 }, { "epoch": 0.21, "learning_rate": 1.8302840405670573e-05, "loss": 0.5667, "step": 768 }, { "epoch": 0.21, "learning_rate": 1.829783724601507e-05, "loss": 0.5521, "step": 769 }, { "epoch": 0.21, "learning_rate": 1.8292827408575903e-05, "loss": 0.5744, "step": 770 }, { "epoch": 0.21, "learning_rate": 1.8287810897384803e-05, "loss": 0.5591, "step": 771 }, { "epoch": 0.21, "learning_rate": 1.828278771647887e-05, "loss": 0.5779, "step": 772 }, { "epoch": 0.21, "learning_rate": 1.8277757869900562e-05, "loss": 0.5603, "step": 773 }, { "epoch": 0.21, "learning_rate": 1.8272721361697715e-05, "loss": 0.5563, "step": 774 }, { "epoch": 0.21, "learning_rate": 1.8267678195923516e-05, "loss": 0.5776, "step": 775 }, { "epoch": 0.21, "learning_rate": 1.8262628376636517e-05, "loss": 0.5661, "step": 776 }, { "epoch": 0.22, "learning_rate": 1.8257571907900616e-05, "loss": 0.5635, "step": 777 }, { "epoch": 0.22, "learning_rate": 1.825250879378506e-05, "loss": 0.5529, "step": 778 }, { "epoch": 0.22, "learning_rate": 1.8247439038364468e-05, "loss": 0.5705, "step": 779 }, { "epoch": 0.22, "learning_rate": 1.824236264571877e-05, "loss": 0.5707, "step": 780 }, { "epoch": 0.22, "learning_rate": 1.8237279619933265e-05, "loss": 0.556, "step": 781 }, { "epoch": 0.22, "learning_rate": 1.8232189965098567e-05, "loss": 0.5514, "step": 782 }, { "epoch": 0.22, "learning_rate": 1.822709368531065e-05, "loss": 0.5654, "step": 783 }, { "epoch": 0.22, "learning_rate": 1.8221990784670792e-05, "loss": 0.5686, "step": 784 }, { "epoch": 0.22, "learning_rate": 1.8216881267285624e-05, "loss": 0.5629, "step": 785 }, { "epoch": 0.22, "learning_rate": 1.821176513726709e-05, "loss": 0.5604, "step": 786 }, { "epoch": 0.22, "learning_rate": 1.8206642398732453e-05, "loss": 0.5509, "step": 787 }, { "epoch": 0.22, "learning_rate": 1.82015130558043e-05, "loss": 0.5691, "step": 788 }, { "epoch": 0.22, "learning_rate": 1.8196377112610524e-05, "loss": 0.5561, "step": 789 }, { "epoch": 0.22, "learning_rate": 1.819123457328435e-05, "loss": 0.567, "step": 790 }, { "epoch": 0.22, "learning_rate": 1.8186085441964293e-05, "loss": 0.5661, "step": 791 }, { "epoch": 0.22, "learning_rate": 1.818092972279417e-05, "loss": 0.5668, "step": 792 }, { "epoch": 0.22, "learning_rate": 1.8175767419923115e-05, "loss": 0.5658, "step": 793 }, { "epoch": 0.22, "learning_rate": 1.8170598537505553e-05, "loss": 0.5772, "step": 794 }, { "epoch": 0.22, "learning_rate": 1.81654230797012e-05, "loss": 0.5426, "step": 795 }, { "epoch": 0.22, "learning_rate": 1.8160241050675072e-05, "loss": 0.57, "step": 796 }, { "epoch": 0.22, "learning_rate": 1.8155052454597467e-05, "loss": 0.5627, "step": 797 }, { "epoch": 0.22, "learning_rate": 1.8149857295643968e-05, "loss": 0.5705, "step": 798 }, { "epoch": 0.22, "learning_rate": 1.8144655577995442e-05, "loss": 0.5555, "step": 799 }, { "epoch": 0.22, "learning_rate": 1.8139447305838037e-05, "loss": 0.5533, "step": 800 }, { "epoch": 0.22, "learning_rate": 1.8134232483363167e-05, "loss": 0.564, "step": 801 }, { "epoch": 0.22, "learning_rate": 1.8129011114767525e-05, "loss": 0.5628, "step": 802 }, { "epoch": 0.22, "learning_rate": 1.8123783204253072e-05, "loss": 0.5589, "step": 803 }, { "epoch": 0.22, "learning_rate": 1.8118548756027027e-05, "loss": 0.554, "step": 804 }, { "epoch": 0.22, "learning_rate": 1.8113307774301874e-05, "loss": 0.5589, "step": 805 }, { "epoch": 0.22, "learning_rate": 1.8108060263295364e-05, "loss": 0.5769, "step": 806 }, { "epoch": 0.22, "learning_rate": 1.8102806227230485e-05, "loss": 0.5734, "step": 807 }, { "epoch": 0.22, "learning_rate": 1.8097545670335492e-05, "loss": 0.5631, "step": 808 }, { "epoch": 0.22, "learning_rate": 1.8092278596843873e-05, "loss": 0.562, "step": 809 }, { "epoch": 0.22, "learning_rate": 1.8087005010994378e-05, "loss": 0.5787, "step": 810 }, { "epoch": 0.22, "learning_rate": 1.8081724917030983e-05, "loss": 0.5883, "step": 811 }, { "epoch": 0.22, "learning_rate": 1.8076438319202905e-05, "loss": 0.5672, "step": 812 }, { "epoch": 0.23, "learning_rate": 1.80711452217646e-05, "loss": 0.5679, "step": 813 }, { "epoch": 0.23, "learning_rate": 1.8065845628975752e-05, "loss": 0.5655, "step": 814 }, { "epoch": 0.23, "learning_rate": 1.8060539545101268e-05, "loss": 0.5635, "step": 815 }, { "epoch": 0.23, "learning_rate": 1.8055226974411284e-05, "loss": 0.5683, "step": 816 }, { "epoch": 0.23, "learning_rate": 1.804990792118116e-05, "loss": 0.56, "step": 817 }, { "epoch": 0.23, "learning_rate": 1.8044582389691457e-05, "loss": 0.5662, "step": 818 }, { "epoch": 0.23, "learning_rate": 1.8039250384227967e-05, "loss": 0.5719, "step": 819 }, { "epoch": 0.23, "learning_rate": 1.8033911909081685e-05, "loss": 0.5761, "step": 820 }, { "epoch": 0.23, "learning_rate": 1.802856696854881e-05, "loss": 0.5664, "step": 821 }, { "epoch": 0.23, "learning_rate": 1.802321556693075e-05, "loss": 0.556, "step": 822 }, { "epoch": 0.23, "learning_rate": 1.8017857708534107e-05, "loss": 0.5619, "step": 823 }, { "epoch": 0.23, "learning_rate": 1.8012493397670684e-05, "loss": 0.5797, "step": 824 }, { "epoch": 0.23, "learning_rate": 1.800712263865747e-05, "loss": 0.5726, "step": 825 }, { "epoch": 0.23, "learning_rate": 1.8001745435816653e-05, "loss": 0.5582, "step": 826 }, { "epoch": 0.23, "learning_rate": 1.7996361793475595e-05, "loss": 0.5494, "step": 827 }, { "epoch": 0.23, "learning_rate": 1.7990971715966852e-05, "loss": 0.5547, "step": 828 }, { "epoch": 0.23, "learning_rate": 1.798557520762815e-05, "loss": 0.567, "step": 829 }, { "epoch": 0.23, "learning_rate": 1.7980172272802398e-05, "loss": 0.5624, "step": 830 }, { "epoch": 0.23, "learning_rate": 1.7974762915837666e-05, "loss": 0.5657, "step": 831 }, { "epoch": 0.23, "learning_rate": 1.79693471410872e-05, "loss": 0.5778, "step": 832 }, { "epoch": 0.23, "learning_rate": 1.7963924952909414e-05, "loss": 0.5616, "step": 833 }, { "epoch": 0.23, "learning_rate": 1.7958496355667874e-05, "loss": 0.5649, "step": 834 }, { "epoch": 0.23, "learning_rate": 1.7953061353731312e-05, "loss": 0.5562, "step": 835 }, { "epoch": 0.23, "learning_rate": 1.7947619951473607e-05, "loss": 0.563, "step": 836 }, { "epoch": 0.23, "learning_rate": 1.7942172153273792e-05, "loss": 0.5626, "step": 837 }, { "epoch": 0.23, "learning_rate": 1.7936717963516055e-05, "loss": 0.5787, "step": 838 }, { "epoch": 0.23, "learning_rate": 1.7931257386589714e-05, "loss": 0.5629, "step": 839 }, { "epoch": 0.23, "learning_rate": 1.7925790426889237e-05, "loss": 0.5651, "step": 840 }, { "epoch": 0.23, "learning_rate": 1.792031708881422e-05, "loss": 0.5808, "step": 841 }, { "epoch": 0.23, "learning_rate": 1.79148373767694e-05, "loss": 0.5587, "step": 842 }, { "epoch": 0.23, "learning_rate": 1.790935129516464e-05, "loss": 0.5537, "step": 843 }, { "epoch": 0.23, "learning_rate": 1.7903858848414937e-05, "loss": 0.5546, "step": 844 }, { "epoch": 0.23, "learning_rate": 1.789836004094039e-05, "loss": 0.5691, "step": 845 }, { "epoch": 0.23, "learning_rate": 1.7892854877166243e-05, "loss": 0.5676, "step": 846 }, { "epoch": 0.23, "learning_rate": 1.7887343361522832e-05, "loss": 0.5619, "step": 847 }, { "epoch": 0.23, "learning_rate": 1.788182549844562e-05, "loss": 0.557, "step": 848 }, { "epoch": 0.24, "learning_rate": 1.7876301292375173e-05, "loss": 0.5672, "step": 849 }, { "epoch": 0.24, "learning_rate": 1.7870770747757165e-05, "loss": 0.5761, "step": 850 }, { "epoch": 0.24, "learning_rate": 1.7865233869042356e-05, "loss": 0.5717, "step": 851 }, { "epoch": 0.24, "learning_rate": 1.785969066068663e-05, "loss": 0.5571, "step": 852 }, { "epoch": 0.24, "learning_rate": 1.7854141127150946e-05, "loss": 0.5679, "step": 853 }, { "epoch": 0.24, "learning_rate": 1.784858527290135e-05, "loss": 0.5607, "step": 854 }, { "epoch": 0.24, "learning_rate": 1.784302310240899e-05, "loss": 0.5736, "step": 855 }, { "epoch": 0.24, "learning_rate": 1.7837454620150084e-05, "loss": 0.5482, "step": 856 }, { "epoch": 0.24, "learning_rate": 1.783187983060594e-05, "loss": 0.556, "step": 857 }, { "epoch": 0.24, "learning_rate": 1.782629873826293e-05, "loss": 0.5808, "step": 858 }, { "epoch": 0.24, "learning_rate": 1.782071134761251e-05, "loss": 0.5693, "step": 859 }, { "epoch": 0.24, "learning_rate": 1.7815117663151196e-05, "loss": 0.5619, "step": 860 }, { "epoch": 0.24, "learning_rate": 1.7809517689380572e-05, "loss": 0.5721, "step": 861 }, { "epoch": 0.24, "learning_rate": 1.780391143080729e-05, "loss": 0.5619, "step": 862 }, { "epoch": 0.24, "learning_rate": 1.7798298891943047e-05, "loss": 0.564, "step": 863 }, { "epoch": 0.24, "learning_rate": 1.7792680077304606e-05, "loss": 0.558, "step": 864 }, { "epoch": 0.24, "learning_rate": 1.7787054991413774e-05, "loss": 0.5445, "step": 865 }, { "epoch": 0.24, "learning_rate": 1.77814236387974e-05, "loss": 0.5508, "step": 866 }, { "epoch": 0.24, "learning_rate": 1.7775786023987385e-05, "loss": 0.573, "step": 867 }, { "epoch": 0.24, "learning_rate": 1.777014215152067e-05, "loss": 0.563, "step": 868 }, { "epoch": 0.24, "learning_rate": 1.7764492025939233e-05, "loss": 0.5554, "step": 869 }, { "epoch": 0.24, "learning_rate": 1.775883565179007e-05, "loss": 0.5721, "step": 870 }, { "epoch": 0.24, "learning_rate": 1.775317303362522e-05, "loss": 0.5535, "step": 871 }, { "epoch": 0.24, "learning_rate": 1.774750417600174e-05, "loss": 0.5629, "step": 872 }, { "epoch": 0.24, "learning_rate": 1.774182908348172e-05, "loss": 0.5688, "step": 873 }, { "epoch": 0.24, "learning_rate": 1.773614776063225e-05, "loss": 0.555, "step": 874 }, { "epoch": 0.24, "learning_rate": 1.773046021202544e-05, "loss": 0.5787, "step": 875 }, { "epoch": 0.24, "learning_rate": 1.7724766442238423e-05, "loss": 0.5634, "step": 876 }, { "epoch": 0.24, "learning_rate": 1.7719066455853317e-05, "loss": 0.5559, "step": 877 }, { "epoch": 0.24, "learning_rate": 1.7713360257457263e-05, "loss": 0.5635, "step": 878 }, { "epoch": 0.24, "learning_rate": 1.7707647851642387e-05, "loss": 0.563, "step": 879 }, { "epoch": 0.24, "learning_rate": 1.7701929243005818e-05, "loss": 0.5558, "step": 880 }, { "epoch": 0.24, "learning_rate": 1.7696204436149678e-05, "loss": 0.5755, "step": 881 }, { "epoch": 0.24, "learning_rate": 1.7690473435681065e-05, "loss": 0.5601, "step": 882 }, { "epoch": 0.24, "learning_rate": 1.768473624621208e-05, "loss": 0.551, "step": 883 }, { "epoch": 0.24, "learning_rate": 1.7678992872359787e-05, "loss": 0.5636, "step": 884 }, { "epoch": 0.25, "learning_rate": 1.767324331874624e-05, "loss": 0.5702, "step": 885 }, { "epoch": 0.25, "learning_rate": 1.7667487589998456e-05, "loss": 0.5566, "step": 886 }, { "epoch": 0.25, "learning_rate": 1.766172569074843e-05, "loss": 0.5425, "step": 887 }, { "epoch": 0.25, "learning_rate": 1.7655957625633115e-05, "loss": 0.5797, "step": 888 }, { "epoch": 0.25, "learning_rate": 1.7650183399294438e-05, "loss": 0.567, "step": 889 }, { "epoch": 0.25, "learning_rate": 1.764440301637927e-05, "loss": 0.5713, "step": 890 }, { "epoch": 0.25, "learning_rate": 1.763861648153945e-05, "loss": 0.5548, "step": 891 }, { "epoch": 0.25, "learning_rate": 1.7632823799431753e-05, "loss": 0.5593, "step": 892 }, { "epoch": 0.25, "learning_rate": 1.7627024974717914e-05, "loss": 0.5589, "step": 893 }, { "epoch": 0.25, "learning_rate": 1.7621220012064607e-05, "loss": 0.5539, "step": 894 }, { "epoch": 0.25, "learning_rate": 1.761540891614344e-05, "loss": 0.5451, "step": 895 }, { "epoch": 0.25, "learning_rate": 1.7609591691630964e-05, "loss": 0.5704, "step": 896 }, { "epoch": 0.25, "learning_rate": 1.7603768343208665e-05, "loss": 0.5556, "step": 897 }, { "epoch": 0.25, "learning_rate": 1.7597938875562945e-05, "loss": 0.5615, "step": 898 }, { "epoch": 0.25, "learning_rate": 1.7592103293385144e-05, "loss": 0.5622, "step": 899 }, { "epoch": 0.25, "learning_rate": 1.758626160137151e-05, "loss": 0.5546, "step": 900 }, { "epoch": 0.25, "learning_rate": 1.758041380422322e-05, "loss": 0.5709, "step": 901 }, { "epoch": 0.25, "learning_rate": 1.7574559906646354e-05, "loss": 0.5591, "step": 902 }, { "epoch": 0.25, "learning_rate": 1.7568699913351914e-05, "loss": 0.5675, "step": 903 }, { "epoch": 0.25, "learning_rate": 1.756283382905579e-05, "loss": 0.5502, "step": 904 }, { "epoch": 0.25, "learning_rate": 1.755696165847879e-05, "loss": 0.5649, "step": 905 }, { "epoch": 0.25, "learning_rate": 1.755108340634661e-05, "loss": 0.5556, "step": 906 }, { "epoch": 0.25, "learning_rate": 1.7545199077389843e-05, "loss": 0.5744, "step": 907 }, { "epoch": 0.25, "learning_rate": 1.7539308676343972e-05, "loss": 0.5571, "step": 908 }, { "epoch": 0.25, "learning_rate": 1.7533412207949377e-05, "loss": 0.5619, "step": 909 }, { "epoch": 0.25, "learning_rate": 1.7527509676951302e-05, "loss": 0.5596, "step": 910 }, { "epoch": 0.25, "learning_rate": 1.752160108809988e-05, "loss": 0.5646, "step": 911 }, { "epoch": 0.25, "learning_rate": 1.7515686446150123e-05, "loss": 0.5675, "step": 912 }, { "epoch": 0.25, "learning_rate": 1.7509765755861906e-05, "loss": 0.5593, "step": 913 }, { "epoch": 0.25, "learning_rate": 1.7503839021999977e-05, "loss": 0.557, "step": 914 }, { "epoch": 0.25, "learning_rate": 1.7497906249333943e-05, "loss": 0.5576, "step": 915 }, { "epoch": 0.25, "learning_rate": 1.749196744263828e-05, "loss": 0.5553, "step": 916 }, { "epoch": 0.25, "learning_rate": 1.7486022606692307e-05, "loss": 0.5591, "step": 917 }, { "epoch": 0.25, "learning_rate": 1.7480071746280207e-05, "loss": 0.5633, "step": 918 }, { "epoch": 0.25, "learning_rate": 1.7474114866191004e-05, "loss": 0.5628, "step": 919 }, { "epoch": 0.25, "learning_rate": 1.7468151971218564e-05, "loss": 0.5564, "step": 920 }, { "epoch": 0.26, "learning_rate": 1.7462183066161605e-05, "loss": 0.5493, "step": 921 }, { "epoch": 0.26, "learning_rate": 1.745620815582367e-05, "loss": 0.5551, "step": 922 }, { "epoch": 0.26, "learning_rate": 1.7450227245013138e-05, "loss": 0.5683, "step": 923 }, { "epoch": 0.26, "learning_rate": 1.7444240338543227e-05, "loss": 0.556, "step": 924 }, { "epoch": 0.26, "learning_rate": 1.743824744123196e-05, "loss": 0.5555, "step": 925 }, { "epoch": 0.26, "learning_rate": 1.7432248557902205e-05, "loss": 0.5518, "step": 926 }, { "epoch": 0.26, "learning_rate": 1.7426243693381625e-05, "loss": 0.5735, "step": 927 }, { "epoch": 0.26, "learning_rate": 1.742023285250271e-05, "loss": 0.5641, "step": 928 }, { "epoch": 0.26, "learning_rate": 1.7414216040102755e-05, "loss": 0.5705, "step": 929 }, { "epoch": 0.26, "learning_rate": 1.7408193261023866e-05, "loss": 0.5639, "step": 930 }, { "epoch": 0.26, "learning_rate": 1.7402164520112943e-05, "loss": 0.5702, "step": 931 }, { "epoch": 0.26, "learning_rate": 1.739612982222169e-05, "loss": 0.566, "step": 932 }, { "epoch": 0.26, "learning_rate": 1.7390089172206594e-05, "loss": 0.5534, "step": 933 }, { "epoch": 0.26, "learning_rate": 1.738404257492895e-05, "loss": 0.5528, "step": 934 }, { "epoch": 0.26, "learning_rate": 1.737799003525482e-05, "loss": 0.55, "step": 935 }, { "epoch": 0.26, "learning_rate": 1.7371931558055067e-05, "loss": 0.5619, "step": 936 }, { "epoch": 0.26, "learning_rate": 1.7365867148205316e-05, "loss": 0.5826, "step": 937 }, { "epoch": 0.26, "learning_rate": 1.7359796810585982e-05, "loss": 0.5613, "step": 938 }, { "epoch": 0.26, "learning_rate": 1.735372055008223e-05, "loss": 0.5421, "step": 939 }, { "epoch": 0.26, "learning_rate": 1.7347638371584013e-05, "loss": 0.5619, "step": 940 }, { "epoch": 0.26, "learning_rate": 1.734155027998603e-05, "loss": 0.5561, "step": 941 }, { "epoch": 0.26, "learning_rate": 1.7335456280187752e-05, "loss": 0.5581, "step": 942 }, { "epoch": 0.26, "learning_rate": 1.7329356377093393e-05, "loss": 0.5545, "step": 943 }, { "epoch": 0.26, "learning_rate": 1.7323250575611923e-05, "loss": 0.5663, "step": 944 }, { "epoch": 0.26, "learning_rate": 1.731713888065706e-05, "loss": 0.5707, "step": 945 }, { "epoch": 0.26, "learning_rate": 1.7311021297147267e-05, "loss": 0.5557, "step": 946 }, { "epoch": 0.26, "learning_rate": 1.7304897830005734e-05, "loss": 0.5652, "step": 947 }, { "epoch": 0.26, "learning_rate": 1.72987684841604e-05, "loss": 0.5555, "step": 948 }, { "epoch": 0.26, "learning_rate": 1.7292633264543936e-05, "loss": 0.5592, "step": 949 }, { "epoch": 0.26, "learning_rate": 1.7286492176093717e-05, "loss": 0.5571, "step": 950 }, { "epoch": 0.26, "learning_rate": 1.7280345223751872e-05, "loss": 0.5504, "step": 951 }, { "epoch": 0.26, "learning_rate": 1.7274192412465227e-05, "loss": 0.549, "step": 952 }, { "epoch": 0.26, "learning_rate": 1.7268033747185332e-05, "loss": 0.5578, "step": 953 }, { "epoch": 0.26, "learning_rate": 1.7261869232868446e-05, "loss": 0.5605, "step": 954 }, { "epoch": 0.26, "learning_rate": 1.7255698874475537e-05, "loss": 0.5692, "step": 955 }, { "epoch": 0.26, "learning_rate": 1.7249522676972274e-05, "loss": 0.5615, "step": 956 }, { "epoch": 0.26, "learning_rate": 1.7243340645329023e-05, "loss": 0.5488, "step": 957 }, { "epoch": 0.27, "learning_rate": 1.723715278452085e-05, "loss": 0.5593, "step": 958 }, { "epoch": 0.27, "learning_rate": 1.7230959099527512e-05, "loss": 0.574, "step": 959 }, { "epoch": 0.27, "learning_rate": 1.722475959533345e-05, "loss": 0.5533, "step": 960 }, { "epoch": 0.27, "learning_rate": 1.721855427692779e-05, "loss": 0.5563, "step": 961 }, { "epoch": 0.27, "learning_rate": 1.7212343149304328e-05, "loss": 0.5775, "step": 962 }, { "epoch": 0.27, "learning_rate": 1.7206126217461553e-05, "loss": 0.5607, "step": 963 }, { "epoch": 0.27, "learning_rate": 1.719990348640261e-05, "loss": 0.5611, "step": 964 }, { "epoch": 0.27, "learning_rate": 1.7193674961135322e-05, "loss": 0.5613, "step": 965 }, { "epoch": 0.27, "learning_rate": 1.7187440646672162e-05, "loss": 0.5676, "step": 966 }, { "epoch": 0.27, "learning_rate": 1.7181200548030274e-05, "loss": 0.5773, "step": 967 }, { "epoch": 0.27, "learning_rate": 1.7174954670231447e-05, "loss": 0.574, "step": 968 }, { "epoch": 0.27, "learning_rate": 1.7168703018302128e-05, "loss": 0.5495, "step": 969 }, { "epoch": 0.27, "learning_rate": 1.716244559727341e-05, "loss": 0.5573, "step": 970 }, { "epoch": 0.27, "learning_rate": 1.715618241218103e-05, "loss": 0.5621, "step": 971 }, { "epoch": 0.27, "learning_rate": 1.7149913468065357e-05, "loss": 0.5629, "step": 972 }, { "epoch": 0.27, "learning_rate": 1.7143638769971394e-05, "loss": 0.5532, "step": 973 }, { "epoch": 0.27, "learning_rate": 1.713735832294879e-05, "loss": 0.5524, "step": 974 }, { "epoch": 0.27, "learning_rate": 1.7131072132051802e-05, "loss": 0.5652, "step": 975 }, { "epoch": 0.27, "learning_rate": 1.712478020233932e-05, "loss": 0.5634, "step": 976 }, { "epoch": 0.27, "learning_rate": 1.711848253887485e-05, "loss": 0.5622, "step": 977 }, { "epoch": 0.27, "learning_rate": 1.711217914672651e-05, "loss": 0.5718, "step": 978 }, { "epoch": 0.27, "learning_rate": 1.710587003096703e-05, "loss": 0.5641, "step": 979 }, { "epoch": 0.27, "learning_rate": 1.709955519667375e-05, "loss": 0.5594, "step": 980 }, { "epoch": 0.27, "learning_rate": 1.7093234648928608e-05, "loss": 0.5735, "step": 981 }, { "epoch": 0.27, "learning_rate": 1.7086908392818132e-05, "loss": 0.5555, "step": 982 }, { "epoch": 0.27, "learning_rate": 1.7080576433433462e-05, "loss": 0.5764, "step": 983 }, { "epoch": 0.27, "learning_rate": 1.707423877587031e-05, "loss": 0.5622, "step": 984 }, { "epoch": 0.27, "learning_rate": 1.7067895425228994e-05, "loss": 0.5738, "step": 985 }, { "epoch": 0.27, "learning_rate": 1.7061546386614387e-05, "loss": 0.559, "step": 986 }, { "epoch": 0.27, "learning_rate": 1.705519166513596e-05, "loss": 0.5656, "step": 987 }, { "epoch": 0.27, "learning_rate": 1.7048831265907755e-05, "loss": 0.5677, "step": 988 }, { "epoch": 0.27, "learning_rate": 1.7042465194048373e-05, "loss": 0.5491, "step": 989 }, { "epoch": 0.27, "learning_rate": 1.703609345468099e-05, "loss": 0.5563, "step": 990 }, { "epoch": 0.27, "learning_rate": 1.7029716052933336e-05, "loss": 0.5571, "step": 991 }, { "epoch": 0.27, "learning_rate": 1.70233329939377e-05, "loss": 0.5571, "step": 992 }, { "epoch": 0.27, "learning_rate": 1.7016944282830935e-05, "loss": 0.5573, "step": 993 }, { "epoch": 0.28, "learning_rate": 1.701054992475442e-05, "loss": 0.5674, "step": 994 }, { "epoch": 0.28, "learning_rate": 1.7004149924854102e-05, "loss": 0.5509, "step": 995 }, { "epoch": 0.28, "learning_rate": 1.6997744288280445e-05, "loss": 0.5607, "step": 996 }, { "epoch": 0.28, "learning_rate": 1.6991333020188473e-05, "loss": 0.5693, "step": 997 }, { "epoch": 0.28, "learning_rate": 1.698491612573773e-05, "loss": 0.5618, "step": 998 }, { "epoch": 0.28, "learning_rate": 1.697849361009228e-05, "loss": 0.5443, "step": 999 }, { "epoch": 0.28, "learning_rate": 1.6972065478420723e-05, "loss": 0.5553, "step": 1000 }, { "epoch": 0.28, "learning_rate": 1.696563173589618e-05, "loss": 0.5792, "step": 1001 }, { "epoch": 0.28, "learning_rate": 1.6959192387696274e-05, "loss": 0.5601, "step": 1002 }, { "epoch": 0.28, "learning_rate": 1.6952747439003153e-05, "loss": 0.5599, "step": 1003 }, { "epoch": 0.28, "learning_rate": 1.6946296895003465e-05, "loss": 0.5647, "step": 1004 }, { "epoch": 0.28, "learning_rate": 1.693984076088836e-05, "loss": 0.5583, "step": 1005 }, { "epoch": 0.28, "learning_rate": 1.6933379041853496e-05, "loss": 0.5498, "step": 1006 }, { "epoch": 0.28, "learning_rate": 1.6926911743099012e-05, "loss": 0.5549, "step": 1007 }, { "epoch": 0.28, "learning_rate": 1.6920438869829544e-05, "loss": 0.5448, "step": 1008 }, { "epoch": 0.28, "learning_rate": 1.6913960427254218e-05, "loss": 0.5609, "step": 1009 }, { "epoch": 0.28, "learning_rate": 1.6907476420586632e-05, "loss": 0.5439, "step": 1010 }, { "epoch": 0.28, "learning_rate": 1.6900986855044874e-05, "loss": 0.5796, "step": 1011 }, { "epoch": 0.28, "learning_rate": 1.68944917358515e-05, "loss": 0.5659, "step": 1012 }, { "epoch": 0.28, "learning_rate": 1.6887991068233525e-05, "loss": 0.5509, "step": 1013 }, { "epoch": 0.28, "learning_rate": 1.688148485742245e-05, "loss": 0.5708, "step": 1014 }, { "epoch": 0.28, "learning_rate": 1.687497310865422e-05, "loss": 0.5414, "step": 1015 }, { "epoch": 0.28, "learning_rate": 1.686845582716925e-05, "loss": 0.5758, "step": 1016 }, { "epoch": 0.28, "learning_rate": 1.6861933018212386e-05, "loss": 0.5473, "step": 1017 }, { "epoch": 0.28, "learning_rate": 1.685540468703295e-05, "loss": 0.5613, "step": 1018 }, { "epoch": 0.28, "learning_rate": 1.684887083888469e-05, "loss": 0.5524, "step": 1019 }, { "epoch": 0.28, "learning_rate": 1.6842331479025796e-05, "loss": 0.5714, "step": 1020 }, { "epoch": 0.28, "learning_rate": 1.6835786612718895e-05, "loss": 0.548, "step": 1021 }, { "epoch": 0.28, "learning_rate": 1.6829236245231054e-05, "loss": 0.5621, "step": 1022 }, { "epoch": 0.28, "learning_rate": 1.6822680381833755e-05, "loss": 0.5547, "step": 1023 }, { "epoch": 0.28, "learning_rate": 1.6816119027802903e-05, "loss": 0.5544, "step": 1024 }, { "epoch": 0.28, "learning_rate": 1.6809552188418828e-05, "loss": 0.5526, "step": 1025 }, { "epoch": 0.28, "learning_rate": 1.680297986896628e-05, "loss": 0.5641, "step": 1026 }, { "epoch": 0.28, "learning_rate": 1.6796402074734404e-05, "loss": 0.563, "step": 1027 }, { "epoch": 0.28, "learning_rate": 1.678981881101676e-05, "loss": 0.5753, "step": 1028 }, { "epoch": 0.28, "learning_rate": 1.6783230083111314e-05, "loss": 0.559, "step": 1029 }, { "epoch": 0.29, "learning_rate": 1.677663589632041e-05, "loss": 0.5489, "step": 1030 }, { "epoch": 0.29, "learning_rate": 1.677003625595081e-05, "loss": 0.5607, "step": 1031 }, { "epoch": 0.29, "learning_rate": 1.6763431167313653e-05, "loss": 0.5603, "step": 1032 }, { "epoch": 0.29, "learning_rate": 1.6756820635724454e-05, "loss": 0.5545, "step": 1033 }, { "epoch": 0.29, "learning_rate": 1.675020466650313e-05, "loss": 0.553, "step": 1034 }, { "epoch": 0.29, "learning_rate": 1.6743583264973953e-05, "loss": 0.5676, "step": 1035 }, { "epoch": 0.29, "learning_rate": 1.6736956436465573e-05, "loss": 0.569, "step": 1036 }, { "epoch": 0.29, "learning_rate": 1.6730324186311016e-05, "loss": 0.5587, "step": 1037 }, { "epoch": 0.29, "learning_rate": 1.6723686519847663e-05, "loss": 0.5591, "step": 1038 }, { "epoch": 0.29, "learning_rate": 1.6717043442417252e-05, "loss": 0.5499, "step": 1039 }, { "epoch": 0.29, "learning_rate": 1.671039495936588e-05, "loss": 0.565, "step": 1040 }, { "epoch": 0.29, "learning_rate": 1.6703741076044e-05, "loss": 0.5617, "step": 1041 }, { "epoch": 0.29, "learning_rate": 1.6697081797806392e-05, "loss": 0.549, "step": 1042 }, { "epoch": 0.29, "learning_rate": 1.66904171300122e-05, "loss": 0.55, "step": 1043 }, { "epoch": 0.29, "learning_rate": 1.6683747078024887e-05, "loss": 0.5585, "step": 1044 }, { "epoch": 0.29, "learning_rate": 1.667707164721226e-05, "loss": 0.5628, "step": 1045 }, { "epoch": 0.29, "learning_rate": 1.667039084294646e-05, "loss": 0.5558, "step": 1046 }, { "epoch": 0.29, "learning_rate": 1.666370467060393e-05, "loss": 0.5623, "step": 1047 }, { "epoch": 0.29, "learning_rate": 1.6657013135565457e-05, "loss": 0.5468, "step": 1048 }, { "epoch": 0.29, "learning_rate": 1.665031624321613e-05, "loss": 0.5591, "step": 1049 }, { "epoch": 0.29, "learning_rate": 1.6643613998945355e-05, "loss": 0.5566, "step": 1050 }, { "epoch": 0.29, "learning_rate": 1.663690640814684e-05, "loss": 0.5608, "step": 1051 }, { "epoch": 0.29, "learning_rate": 1.6630193476218606e-05, "loss": 0.5536, "step": 1052 }, { "epoch": 0.29, "learning_rate": 1.6623475208562953e-05, "loss": 0.5514, "step": 1053 }, { "epoch": 0.29, "learning_rate": 1.6616751610586498e-05, "loss": 0.5741, "step": 1054 }, { "epoch": 0.29, "learning_rate": 1.6610022687700133e-05, "loss": 0.5589, "step": 1055 }, { "epoch": 0.29, "learning_rate": 1.6603288445319035e-05, "loss": 0.56, "step": 1056 }, { "epoch": 0.29, "learning_rate": 1.6596548888862674e-05, "loss": 0.5641, "step": 1057 }, { "epoch": 0.29, "learning_rate": 1.6589804023754784e-05, "loss": 0.5637, "step": 1058 }, { "epoch": 0.29, "learning_rate": 1.6583053855423373e-05, "loss": 0.5633, "step": 1059 }, { "epoch": 0.29, "learning_rate": 1.6576298389300727e-05, "loss": 0.5557, "step": 1060 }, { "epoch": 0.29, "learning_rate": 1.6569537630823385e-05, "loss": 0.5658, "step": 1061 }, { "epoch": 0.29, "learning_rate": 1.656277158543214e-05, "loss": 0.5594, "step": 1062 }, { "epoch": 0.29, "learning_rate": 1.6556000258572066e-05, "loss": 0.5627, "step": 1063 }, { "epoch": 0.29, "learning_rate": 1.6549223655692447e-05, "loss": 0.57, "step": 1064 }, { "epoch": 0.29, "learning_rate": 1.6542441782246855e-05, "loss": 0.5462, "step": 1065 }, { "epoch": 0.3, "learning_rate": 1.6535654643693072e-05, "loss": 0.5599, "step": 1066 }, { "epoch": 0.3, "learning_rate": 1.652886224549313e-05, "loss": 0.5608, "step": 1067 }, { "epoch": 0.3, "learning_rate": 1.6522064593113297e-05, "loss": 0.5487, "step": 1068 }, { "epoch": 0.3, "learning_rate": 1.6515261692024062e-05, "loss": 0.5613, "step": 1069 }, { "epoch": 0.3, "learning_rate": 1.6508453547700138e-05, "loss": 0.5596, "step": 1070 }, { "epoch": 0.3, "learning_rate": 1.6501640165620468e-05, "loss": 0.5487, "step": 1071 }, { "epoch": 0.3, "learning_rate": 1.6494821551268196e-05, "loss": 0.5651, "step": 1072 }, { "epoch": 0.3, "learning_rate": 1.6487997710130685e-05, "loss": 0.5546, "step": 1073 }, { "epoch": 0.3, "learning_rate": 1.6481168647699505e-05, "loss": 0.5501, "step": 1074 }, { "epoch": 0.3, "learning_rate": 1.6474334369470427e-05, "loss": 0.5672, "step": 1075 }, { "epoch": 0.3, "learning_rate": 1.6467494880943415e-05, "loss": 0.5546, "step": 1076 }, { "epoch": 0.3, "learning_rate": 1.6460650187622626e-05, "loss": 0.55, "step": 1077 }, { "epoch": 0.3, "learning_rate": 1.645380029501641e-05, "loss": 0.5498, "step": 1078 }, { "epoch": 0.3, "learning_rate": 1.6446945208637306e-05, "loss": 0.5615, "step": 1079 }, { "epoch": 0.3, "learning_rate": 1.644008493400202e-05, "loss": 0.5555, "step": 1080 }, { "epoch": 0.3, "learning_rate": 1.6433219476631446e-05, "loss": 0.5613, "step": 1081 }, { "epoch": 0.3, "learning_rate": 1.6426348842050635e-05, "loss": 0.5611, "step": 1082 }, { "epoch": 0.3, "learning_rate": 1.6419473035788823e-05, "loss": 0.5648, "step": 1083 }, { "epoch": 0.3, "learning_rate": 1.6412592063379383e-05, "loss": 0.5586, "step": 1084 }, { "epoch": 0.3, "learning_rate": 1.6405705930359873e-05, "loss": 0.5553, "step": 1085 }, { "epoch": 0.3, "learning_rate": 1.6398814642271986e-05, "loss": 0.5493, "step": 1086 }, { "epoch": 0.3, "learning_rate": 1.639191820466156e-05, "loss": 0.5534, "step": 1087 }, { "epoch": 0.3, "learning_rate": 1.6385016623078602e-05, "loss": 0.5584, "step": 1088 }, { "epoch": 0.3, "learning_rate": 1.6378109903077234e-05, "loss": 0.5595, "step": 1089 }, { "epoch": 0.3, "learning_rate": 1.6371198050215716e-05, "loss": 0.5533, "step": 1090 }, { "epoch": 0.3, "learning_rate": 1.636428107005645e-05, "loss": 0.5477, "step": 1091 }, { "epoch": 0.3, "learning_rate": 1.6357358968165962e-05, "loss": 0.5647, "step": 1092 }, { "epoch": 0.3, "learning_rate": 1.6350431750114885e-05, "loss": 0.5662, "step": 1093 }, { "epoch": 0.3, "learning_rate": 1.634349942147799e-05, "loss": 0.553, "step": 1094 }, { "epoch": 0.3, "learning_rate": 1.6336561987834155e-05, "loss": 0.5474, "step": 1095 }, { "epoch": 0.3, "learning_rate": 1.6329619454766347e-05, "loss": 0.5538, "step": 1096 }, { "epoch": 0.3, "learning_rate": 1.632267182786167e-05, "loss": 0.5647, "step": 1097 }, { "epoch": 0.3, "learning_rate": 1.6315719112711295e-05, "loss": 0.5426, "step": 1098 }, { "epoch": 0.3, "learning_rate": 1.6308761314910514e-05, "loss": 0.5501, "step": 1099 }, { "epoch": 0.3, "learning_rate": 1.630179844005869e-05, "loss": 0.556, "step": 1100 }, { "epoch": 0.3, "learning_rate": 1.6294830493759284e-05, "loss": 0.5718, "step": 1101 }, { "epoch": 0.31, "learning_rate": 1.628785748161983e-05, "loss": 0.5663, "step": 1102 }, { "epoch": 0.31, "learning_rate": 1.6280879409251945e-05, "loss": 0.5549, "step": 1103 }, { "epoch": 0.31, "learning_rate": 1.6273896282271323e-05, "loss": 0.5455, "step": 1104 }, { "epoch": 0.31, "learning_rate": 1.6266908106297705e-05, "loss": 0.5613, "step": 1105 }, { "epoch": 0.31, "learning_rate": 1.6259914886954923e-05, "loss": 0.562, "step": 1106 }, { "epoch": 0.31, "learning_rate": 1.6252916629870842e-05, "loss": 0.5419, "step": 1107 }, { "epoch": 0.31, "learning_rate": 1.62459133406774e-05, "loss": 0.5435, "step": 1108 }, { "epoch": 0.31, "learning_rate": 1.623890502501058e-05, "loss": 0.5535, "step": 1109 }, { "epoch": 0.31, "learning_rate": 1.62318916885104e-05, "loss": 0.5531, "step": 1110 }, { "epoch": 0.31, "learning_rate": 1.622487333682093e-05, "loss": 0.5546, "step": 1111 }, { "epoch": 0.31, "learning_rate": 1.6217849975590275e-05, "loss": 0.5472, "step": 1112 }, { "epoch": 0.31, "learning_rate": 1.6210821610470565e-05, "loss": 0.5562, "step": 1113 }, { "epoch": 0.31, "learning_rate": 1.620378824711796e-05, "loss": 0.5594, "step": 1114 }, { "epoch": 0.31, "learning_rate": 1.619674989119265e-05, "loss": 0.5569, "step": 1115 }, { "epoch": 0.31, "learning_rate": 1.6189706548358825e-05, "loss": 0.568, "step": 1116 }, { "epoch": 0.31, "learning_rate": 1.618265822428471e-05, "loss": 0.5559, "step": 1117 }, { "epoch": 0.31, "learning_rate": 1.6175604924642526e-05, "loss": 0.5622, "step": 1118 }, { "epoch": 0.31, "learning_rate": 1.6168546655108494e-05, "loss": 0.5638, "step": 1119 }, { "epoch": 0.31, "learning_rate": 1.6161483421362846e-05, "loss": 0.572, "step": 1120 }, { "epoch": 0.31, "learning_rate": 1.6154415229089805e-05, "loss": 0.5526, "step": 1121 }, { "epoch": 0.31, "learning_rate": 1.6147342083977576e-05, "loss": 0.5598, "step": 1122 }, { "epoch": 0.31, "learning_rate": 1.6140263991718363e-05, "loss": 0.5613, "step": 1123 }, { "epoch": 0.31, "learning_rate": 1.6133180958008343e-05, "loss": 0.5595, "step": 1124 }, { "epoch": 0.31, "learning_rate": 1.6126092988547673e-05, "loss": 0.556, "step": 1125 }, { "epoch": 0.31, "learning_rate": 1.6119000089040482e-05, "loss": 0.5708, "step": 1126 }, { "epoch": 0.31, "learning_rate": 1.6111902265194865e-05, "loss": 0.5614, "step": 1127 }, { "epoch": 0.31, "learning_rate": 1.610479952272288e-05, "loss": 0.5458, "step": 1128 }, { "epoch": 0.31, "learning_rate": 1.6097691867340547e-05, "loss": 0.5596, "step": 1129 }, { "epoch": 0.31, "learning_rate": 1.609057930476783e-05, "loss": 0.5449, "step": 1130 }, { "epoch": 0.31, "learning_rate": 1.608346184072865e-05, "loss": 0.5559, "step": 1131 }, { "epoch": 0.31, "learning_rate": 1.6076339480950875e-05, "loss": 0.562, "step": 1132 }, { "epoch": 0.31, "learning_rate": 1.6069212231166308e-05, "loss": 0.5566, "step": 1133 }, { "epoch": 0.31, "learning_rate": 1.606208009711069e-05, "loss": 0.5586, "step": 1134 }, { "epoch": 0.31, "learning_rate": 1.605494308452369e-05, "loss": 0.5466, "step": 1135 }, { "epoch": 0.31, "learning_rate": 1.60478011991489e-05, "loss": 0.5641, "step": 1136 }, { "epoch": 0.31, "learning_rate": 1.6040654446733838e-05, "loss": 0.5597, "step": 1137 }, { "epoch": 0.32, "learning_rate": 1.6033502833029948e-05, "loss": 0.5404, "step": 1138 }, { "epoch": 0.32, "learning_rate": 1.6026346363792565e-05, "loss": 0.5602, "step": 1139 }, { "epoch": 0.32, "learning_rate": 1.6019185044780948e-05, "loss": 0.5529, "step": 1140 }, { "epoch": 0.32, "learning_rate": 1.6012018881758257e-05, "loss": 0.5608, "step": 1141 }, { "epoch": 0.32, "learning_rate": 1.6004847880491543e-05, "loss": 0.546, "step": 1142 }, { "epoch": 0.32, "learning_rate": 1.5997672046751758e-05, "loss": 0.5484, "step": 1143 }, { "epoch": 0.32, "learning_rate": 1.5990491386313737e-05, "loss": 0.5687, "step": 1144 }, { "epoch": 0.32, "learning_rate": 1.5983305904956198e-05, "loss": 0.5505, "step": 1145 }, { "epoch": 0.32, "learning_rate": 1.5976115608461756e-05, "loss": 0.5501, "step": 1146 }, { "epoch": 0.32, "learning_rate": 1.596892050261688e-05, "loss": 0.5436, "step": 1147 }, { "epoch": 0.32, "learning_rate": 1.5961720593211913e-05, "loss": 0.5544, "step": 1148 }, { "epoch": 0.32, "learning_rate": 1.5954515886041077e-05, "loss": 0.5442, "step": 1149 }, { "epoch": 0.32, "learning_rate": 1.594730638690244e-05, "loss": 0.5608, "step": 1150 }, { "epoch": 0.32, "learning_rate": 1.5940092101597934e-05, "loss": 0.5563, "step": 1151 }, { "epoch": 0.32, "learning_rate": 1.5932873035933344e-05, "loss": 0.5635, "step": 1152 }, { "epoch": 0.32, "learning_rate": 1.5925649195718292e-05, "loss": 0.5763, "step": 1153 }, { "epoch": 0.32, "learning_rate": 1.591842058676626e-05, "loss": 0.5651, "step": 1154 }, { "epoch": 0.32, "learning_rate": 1.591118721489455e-05, "loss": 0.5723, "step": 1155 }, { "epoch": 0.32, "learning_rate": 1.590394908592431e-05, "loss": 0.5592, "step": 1156 }, { "epoch": 0.32, "learning_rate": 1.5896706205680504e-05, "loss": 0.5537, "step": 1157 }, { "epoch": 0.32, "learning_rate": 1.5889458579991936e-05, "loss": 0.5539, "step": 1158 }, { "epoch": 0.32, "learning_rate": 1.588220621469121e-05, "loss": 0.559, "step": 1159 }, { "epoch": 0.32, "learning_rate": 1.5874949115614756e-05, "loss": 0.5448, "step": 1160 }, { "epoch": 0.32, "learning_rate": 1.586768728860281e-05, "loss": 0.5519, "step": 1161 }, { "epoch": 0.32, "learning_rate": 1.5860420739499417e-05, "loss": 0.5671, "step": 1162 }, { "epoch": 0.32, "learning_rate": 1.585314947415242e-05, "loss": 0.559, "step": 1163 }, { "epoch": 0.32, "learning_rate": 1.5845873498413458e-05, "loss": 0.555, "step": 1164 }, { "epoch": 0.32, "learning_rate": 1.5838592818137952e-05, "loss": 0.5484, "step": 1165 }, { "epoch": 0.32, "learning_rate": 1.5831307439185124e-05, "loss": 0.551, "step": 1166 }, { "epoch": 0.32, "learning_rate": 1.5824017367417965e-05, "loss": 0.5647, "step": 1167 }, { "epoch": 0.32, "learning_rate": 1.5816722608703247e-05, "loss": 0.5534, "step": 1168 }, { "epoch": 0.32, "learning_rate": 1.580942316891152e-05, "loss": 0.5508, "step": 1169 }, { "epoch": 0.32, "learning_rate": 1.580211905391709e-05, "loss": 0.559, "step": 1170 }, { "epoch": 0.32, "learning_rate": 1.5794810269598035e-05, "loss": 0.5617, "step": 1171 }, { "epoch": 0.32, "learning_rate": 1.578749682183618e-05, "loss": 0.552, "step": 1172 }, { "epoch": 0.32, "learning_rate": 1.5780178716517115e-05, "loss": 0.5434, "step": 1173 }, { "epoch": 0.33, "learning_rate": 1.5772855959530167e-05, "loss": 0.5659, "step": 1174 }, { "epoch": 0.33, "learning_rate": 1.5765528556768424e-05, "loss": 0.557, "step": 1175 }, { "epoch": 0.33, "learning_rate": 1.5758196514128687e-05, "loss": 0.5559, "step": 1176 }, { "epoch": 0.33, "learning_rate": 1.5750859837511514e-05, "loss": 0.5549, "step": 1177 }, { "epoch": 0.33, "learning_rate": 1.574351853282118e-05, "loss": 0.5368, "step": 1178 }, { "epoch": 0.33, "learning_rate": 1.5736172605965687e-05, "loss": 0.562, "step": 1179 }, { "epoch": 0.33, "learning_rate": 1.5728822062856758e-05, "loss": 0.576, "step": 1180 }, { "epoch": 0.33, "learning_rate": 1.572146690940983e-05, "loss": 0.5572, "step": 1181 }, { "epoch": 0.33, "learning_rate": 1.5714107151544052e-05, "loss": 0.558, "step": 1182 }, { "epoch": 0.33, "learning_rate": 1.570674279518228e-05, "loss": 0.5655, "step": 1183 }, { "epoch": 0.33, "learning_rate": 1.569937384625106e-05, "loss": 0.5651, "step": 1184 }, { "epoch": 0.33, "learning_rate": 1.5692000310680645e-05, "loss": 0.5705, "step": 1185 }, { "epoch": 0.33, "learning_rate": 1.568462219440498e-05, "loss": 0.5391, "step": 1186 }, { "epoch": 0.33, "learning_rate": 1.567723950336169e-05, "loss": 0.5456, "step": 1187 }, { "epoch": 0.33, "learning_rate": 1.5669852243492078e-05, "loss": 0.5504, "step": 1188 }, { "epoch": 0.33, "learning_rate": 1.5662460420741138e-05, "loss": 0.5613, "step": 1189 }, { "epoch": 0.33, "learning_rate": 1.565506404105752e-05, "loss": 0.5618, "step": 1190 }, { "epoch": 0.33, "learning_rate": 1.5647663110393558e-05, "loss": 0.5474, "step": 1191 }, { "epoch": 0.33, "learning_rate": 1.5640257634705232e-05, "loss": 0.5636, "step": 1192 }, { "epoch": 0.33, "learning_rate": 1.563284761995219e-05, "loss": 0.5579, "step": 1193 }, { "epoch": 0.33, "learning_rate": 1.5625433072097728e-05, "loss": 0.5588, "step": 1194 }, { "epoch": 0.33, "learning_rate": 1.5618013997108796e-05, "loss": 0.5635, "step": 1195 }, { "epoch": 0.33, "learning_rate": 1.5610590400955973e-05, "loss": 0.5541, "step": 1196 }, { "epoch": 0.33, "learning_rate": 1.5603162289613503e-05, "loss": 0.5646, "step": 1197 }, { "epoch": 0.33, "learning_rate": 1.5595729669059233e-05, "loss": 0.5522, "step": 1198 }, { "epoch": 0.33, "learning_rate": 1.558829254527466e-05, "loss": 0.5514, "step": 1199 }, { "epoch": 0.33, "learning_rate": 1.5580850924244898e-05, "loss": 0.5583, "step": 1200 }, { "epoch": 0.33, "learning_rate": 1.5573404811958678e-05, "loss": 0.5578, "step": 1201 }, { "epoch": 0.33, "learning_rate": 1.556595421440835e-05, "loss": 0.5641, "step": 1202 }, { "epoch": 0.33, "learning_rate": 1.555849913758987e-05, "loss": 0.5565, "step": 1203 }, { "epoch": 0.33, "learning_rate": 1.5551039587502802e-05, "loss": 0.5303, "step": 1204 }, { "epoch": 0.33, "learning_rate": 1.55435755701503e-05, "loss": 0.572, "step": 1205 }, { "epoch": 0.33, "learning_rate": 1.5536107091539136e-05, "loss": 0.5553, "step": 1206 }, { "epoch": 0.33, "learning_rate": 1.5528634157679647e-05, "loss": 0.5472, "step": 1207 }, { "epoch": 0.33, "learning_rate": 1.5521156774585765e-05, "loss": 0.5599, "step": 1208 }, { "epoch": 0.33, "learning_rate": 1.5513674948275013e-05, "loss": 0.5526, "step": 1209 }, { "epoch": 0.34, "learning_rate": 1.550618868476847e-05, "loss": 0.5582, "step": 1210 }, { "epoch": 0.34, "learning_rate": 1.5498697990090798e-05, "loss": 0.5729, "step": 1211 }, { "epoch": 0.34, "learning_rate": 1.5491202870270226e-05, "loss": 0.5411, "step": 1212 }, { "epoch": 0.34, "learning_rate": 1.5483703331338537e-05, "loss": 0.5644, "step": 1213 }, { "epoch": 0.34, "learning_rate": 1.547619937933108e-05, "loss": 0.5599, "step": 1214 }, { "epoch": 0.34, "learning_rate": 1.546869102028675e-05, "loss": 0.5536, "step": 1215 }, { "epoch": 0.34, "learning_rate": 1.5461178260247983e-05, "loss": 0.5646, "step": 1216 }, { "epoch": 0.34, "learning_rate": 1.5453661105260765e-05, "loss": 0.5574, "step": 1217 }, { "epoch": 0.34, "learning_rate": 1.5446139561374617e-05, "loss": 0.5583, "step": 1218 }, { "epoch": 0.34, "learning_rate": 1.543861363464259e-05, "loss": 0.5593, "step": 1219 }, { "epoch": 0.34, "learning_rate": 1.5431083331121265e-05, "loss": 0.5592, "step": 1220 }, { "epoch": 0.34, "learning_rate": 1.5423548656870747e-05, "loss": 0.5549, "step": 1221 }, { "epoch": 0.34, "learning_rate": 1.5416009617954646e-05, "loss": 0.558, "step": 1222 }, { "epoch": 0.34, "learning_rate": 1.5408466220440105e-05, "loss": 0.5488, "step": 1223 }, { "epoch": 0.34, "learning_rate": 1.540091847039775e-05, "loss": 0.5615, "step": 1224 }, { "epoch": 0.34, "learning_rate": 1.5393366373901733e-05, "loss": 0.5521, "step": 1225 }, { "epoch": 0.34, "learning_rate": 1.5385809937029695e-05, "loss": 0.5574, "step": 1226 }, { "epoch": 0.34, "learning_rate": 1.5378249165862758e-05, "loss": 0.5537, "step": 1227 }, { "epoch": 0.34, "learning_rate": 1.5370684066485555e-05, "loss": 0.5372, "step": 1228 }, { "epoch": 0.34, "learning_rate": 1.5363114644986184e-05, "loss": 0.5641, "step": 1229 }, { "epoch": 0.34, "learning_rate": 1.535554090745623e-05, "loss": 0.5539, "step": 1230 }, { "epoch": 0.34, "learning_rate": 1.5347962859990744e-05, "loss": 0.5515, "step": 1231 }, { "epoch": 0.34, "learning_rate": 1.5340380508688254e-05, "loss": 0.561, "step": 1232 }, { "epoch": 0.34, "learning_rate": 1.5332793859650747e-05, "loss": 0.5535, "step": 1233 }, { "epoch": 0.34, "learning_rate": 1.5325202918983672e-05, "loss": 0.5508, "step": 1234 }, { "epoch": 0.34, "learning_rate": 1.5317607692795925e-05, "loss": 0.556, "step": 1235 }, { "epoch": 0.34, "learning_rate": 1.5310008187199854e-05, "loss": 0.5464, "step": 1236 }, { "epoch": 0.34, "learning_rate": 1.530240440831126e-05, "loss": 0.555, "step": 1237 }, { "epoch": 0.34, "learning_rate": 1.5294796362249368e-05, "loss": 0.5429, "step": 1238 }, { "epoch": 0.34, "learning_rate": 1.5287184055136845e-05, "loss": 0.553, "step": 1239 }, { "epoch": 0.34, "learning_rate": 1.5279567493099788e-05, "loss": 0.5505, "step": 1240 }, { "epoch": 0.34, "learning_rate": 1.527194668226771e-05, "loss": 0.5641, "step": 1241 }, { "epoch": 0.34, "learning_rate": 1.526432162877356e-05, "loss": 0.5514, "step": 1242 }, { "epoch": 0.34, "learning_rate": 1.5256692338753682e-05, "loss": 0.541, "step": 1243 }, { "epoch": 0.34, "learning_rate": 1.5249058818347844e-05, "loss": 0.5604, "step": 1244 }, { "epoch": 0.34, "learning_rate": 1.524142107369921e-05, "loss": 0.5625, "step": 1245 }, { "epoch": 0.35, "learning_rate": 1.5233779110954347e-05, "loss": 0.5515, "step": 1246 }, { "epoch": 0.35, "learning_rate": 1.5226132936263219e-05, "loss": 0.5591, "step": 1247 }, { "epoch": 0.35, "learning_rate": 1.5218482555779167e-05, "loss": 0.5608, "step": 1248 }, { "epoch": 0.35, "learning_rate": 1.5210827975658935e-05, "loss": 0.5581, "step": 1249 }, { "epoch": 0.35, "learning_rate": 1.5203169202062636e-05, "loss": 0.5657, "step": 1250 }, { "epoch": 0.35, "learning_rate": 1.5195506241153755e-05, "loss": 0.5529, "step": 1251 }, { "epoch": 0.35, "learning_rate": 1.5187839099099156e-05, "loss": 0.5593, "step": 1252 }, { "epoch": 0.35, "learning_rate": 1.5180167782069065e-05, "loss": 0.5536, "step": 1253 }, { "epoch": 0.35, "learning_rate": 1.517249229623706e-05, "loss": 0.5576, "step": 1254 }, { "epoch": 0.35, "learning_rate": 1.5164812647780083e-05, "loss": 0.5578, "step": 1255 }, { "epoch": 0.35, "learning_rate": 1.5157128842878421e-05, "loss": 0.5511, "step": 1256 }, { "epoch": 0.35, "learning_rate": 1.5149440887715713e-05, "loss": 0.5604, "step": 1257 }, { "epoch": 0.35, "learning_rate": 1.5141748788478929e-05, "loss": 0.555, "step": 1258 }, { "epoch": 0.35, "learning_rate": 1.5134052551358379e-05, "loss": 0.55, "step": 1259 }, { "epoch": 0.35, "learning_rate": 1.51263521825477e-05, "loss": 0.5493, "step": 1260 }, { "epoch": 0.35, "learning_rate": 1.5118647688243853e-05, "loss": 0.5528, "step": 1261 }, { "epoch": 0.35, "learning_rate": 1.5110939074647128e-05, "loss": 0.5603, "step": 1262 }, { "epoch": 0.35, "learning_rate": 1.5103226347961124e-05, "loss": 0.5614, "step": 1263 }, { "epoch": 0.35, "learning_rate": 1.5095509514392744e-05, "loss": 0.5385, "step": 1264 }, { "epoch": 0.35, "learning_rate": 1.5087788580152207e-05, "loss": 0.549, "step": 1265 }, { "epoch": 0.35, "learning_rate": 1.5080063551453027e-05, "loss": 0.5567, "step": 1266 }, { "epoch": 0.35, "learning_rate": 1.5072334434512008e-05, "loss": 0.5612, "step": 1267 }, { "epoch": 0.35, "learning_rate": 1.5064601235549252e-05, "loss": 0.5681, "step": 1268 }, { "epoch": 0.35, "learning_rate": 1.5056863960788148e-05, "loss": 0.5615, "step": 1269 }, { "epoch": 0.35, "learning_rate": 1.5049122616455356e-05, "loss": 0.5571, "step": 1270 }, { "epoch": 0.35, "learning_rate": 1.5041377208780814e-05, "loss": 0.5589, "step": 1271 }, { "epoch": 0.35, "learning_rate": 1.5033627743997732e-05, "loss": 0.5519, "step": 1272 }, { "epoch": 0.35, "learning_rate": 1.5025874228342585e-05, "loss": 0.5581, "step": 1273 }, { "epoch": 0.35, "learning_rate": 1.5018116668055114e-05, "loss": 0.5475, "step": 1274 }, { "epoch": 0.35, "learning_rate": 1.5010355069378295e-05, "loss": 0.5593, "step": 1275 }, { "epoch": 0.35, "learning_rate": 1.5002589438558377e-05, "loss": 0.5674, "step": 1276 }, { "epoch": 0.35, "learning_rate": 1.499481978184484e-05, "loss": 0.5454, "step": 1277 }, { "epoch": 0.35, "learning_rate": 1.4987046105490413e-05, "loss": 0.5632, "step": 1278 }, { "epoch": 0.35, "learning_rate": 1.497926841575105e-05, "loss": 0.5459, "step": 1279 }, { "epoch": 0.35, "learning_rate": 1.497148671888594e-05, "loss": 0.5691, "step": 1280 }, { "epoch": 0.35, "learning_rate": 1.4963701021157497e-05, "loss": 0.5658, "step": 1281 }, { "epoch": 0.35, "learning_rate": 1.4955911328831357e-05, "loss": 0.5439, "step": 1282 }, { "epoch": 0.36, "learning_rate": 1.4948117648176367e-05, "loss": 0.5487, "step": 1283 }, { "epoch": 0.36, "learning_rate": 1.494031998546458e-05, "loss": 0.5567, "step": 1284 }, { "epoch": 0.36, "learning_rate": 1.4932518346971264e-05, "loss": 0.5666, "step": 1285 }, { "epoch": 0.36, "learning_rate": 1.492471273897488e-05, "loss": 0.5485, "step": 1286 }, { "epoch": 0.36, "learning_rate": 1.4916903167757082e-05, "loss": 0.5542, "step": 1287 }, { "epoch": 0.36, "learning_rate": 1.4909089639602714e-05, "loss": 0.54, "step": 1288 }, { "epoch": 0.36, "learning_rate": 1.490127216079981e-05, "loss": 0.5623, "step": 1289 }, { "epoch": 0.36, "learning_rate": 1.4893450737639581e-05, "loss": 0.5585, "step": 1290 }, { "epoch": 0.36, "learning_rate": 1.4885625376416406e-05, "loss": 0.5659, "step": 1291 }, { "epoch": 0.36, "learning_rate": 1.4877796083427838e-05, "loss": 0.5678, "step": 1292 }, { "epoch": 0.36, "learning_rate": 1.4869962864974599e-05, "loss": 0.5543, "step": 1293 }, { "epoch": 0.36, "learning_rate": 1.4862125727360561e-05, "loss": 0.5579, "step": 1294 }, { "epoch": 0.36, "learning_rate": 1.4854284676892757e-05, "loss": 0.5655, "step": 1295 }, { "epoch": 0.36, "learning_rate": 1.4846439719881361e-05, "loss": 0.5603, "step": 1296 }, { "epoch": 0.36, "learning_rate": 1.4838590862639702e-05, "loss": 0.5406, "step": 1297 }, { "epoch": 0.36, "learning_rate": 1.4830738111484238e-05, "loss": 0.5542, "step": 1298 }, { "epoch": 0.36, "learning_rate": 1.4822881472734563e-05, "loss": 0.5533, "step": 1299 }, { "epoch": 0.36, "learning_rate": 1.4815020952713404e-05, "loss": 0.571, "step": 1300 }, { "epoch": 0.36, "learning_rate": 1.4807156557746609e-05, "loss": 0.5555, "step": 1301 }, { "epoch": 0.36, "learning_rate": 1.4799288294163141e-05, "loss": 0.5686, "step": 1302 }, { "epoch": 0.36, "learning_rate": 1.4791416168295081e-05, "loss": 0.5636, "step": 1303 }, { "epoch": 0.36, "learning_rate": 1.4783540186477616e-05, "loss": 0.5591, "step": 1304 }, { "epoch": 0.36, "learning_rate": 1.4775660355049032e-05, "loss": 0.557, "step": 1305 }, { "epoch": 0.36, "learning_rate": 1.4767776680350728e-05, "loss": 0.5519, "step": 1306 }, { "epoch": 0.36, "learning_rate": 1.4759889168727175e-05, "loss": 0.5634, "step": 1307 }, { "epoch": 0.36, "learning_rate": 1.4751997826525948e-05, "loss": 0.5426, "step": 1308 }, { "epoch": 0.36, "learning_rate": 1.4744102660097696e-05, "loss": 0.5547, "step": 1309 }, { "epoch": 0.36, "learning_rate": 1.473620367579615e-05, "loss": 0.5486, "step": 1310 }, { "epoch": 0.36, "learning_rate": 1.472830087997811e-05, "loss": 0.5464, "step": 1311 }, { "epoch": 0.36, "learning_rate": 1.4720394279003451e-05, "loss": 0.5506, "step": 1312 }, { "epoch": 0.36, "learning_rate": 1.4712483879235097e-05, "loss": 0.5544, "step": 1313 }, { "epoch": 0.36, "learning_rate": 1.4704569687039044e-05, "loss": 0.5681, "step": 1314 }, { "epoch": 0.36, "learning_rate": 1.4696651708784326e-05, "loss": 0.5654, "step": 1315 }, { "epoch": 0.36, "learning_rate": 1.4688729950843035e-05, "loss": 0.5482, "step": 1316 }, { "epoch": 0.36, "learning_rate": 1.4680804419590297e-05, "loss": 0.5478, "step": 1317 }, { "epoch": 0.36, "learning_rate": 1.4672875121404282e-05, "loss": 0.5792, "step": 1318 }, { "epoch": 0.37, "learning_rate": 1.4664942062666183e-05, "loss": 0.552, "step": 1319 }, { "epoch": 0.37, "learning_rate": 1.465700524976023e-05, "loss": 0.5649, "step": 1320 }, { "epoch": 0.37, "learning_rate": 1.4649064689073659e-05, "loss": 0.5445, "step": 1321 }, { "epoch": 0.37, "learning_rate": 1.464112038699674e-05, "loss": 0.5614, "step": 1322 }, { "epoch": 0.37, "learning_rate": 1.4633172349922742e-05, "loss": 0.5593, "step": 1323 }, { "epoch": 0.37, "learning_rate": 1.4625220584247941e-05, "loss": 0.5695, "step": 1324 }, { "epoch": 0.37, "learning_rate": 1.4617265096371616e-05, "loss": 0.5349, "step": 1325 }, { "epoch": 0.37, "learning_rate": 1.4609305892696042e-05, "loss": 0.5501, "step": 1326 }, { "epoch": 0.37, "learning_rate": 1.4601342979626482e-05, "loss": 0.5547, "step": 1327 }, { "epoch": 0.37, "learning_rate": 1.4593376363571185e-05, "loss": 0.5559, "step": 1328 }, { "epoch": 0.37, "learning_rate": 1.4585406050941384e-05, "loss": 0.5558, "step": 1329 }, { "epoch": 0.37, "learning_rate": 1.4577432048151278e-05, "loss": 0.5487, "step": 1330 }, { "epoch": 0.37, "learning_rate": 1.456945436161805e-05, "loss": 0.5599, "step": 1331 }, { "epoch": 0.37, "learning_rate": 1.4561472997761828e-05, "loss": 0.5563, "step": 1332 }, { "epoch": 0.37, "learning_rate": 1.4553487963005712e-05, "loss": 0.5567, "step": 1333 }, { "epoch": 0.37, "learning_rate": 1.454549926377576e-05, "loss": 0.5485, "step": 1334 }, { "epoch": 0.37, "learning_rate": 1.453750690650097e-05, "loss": 0.5498, "step": 1335 }, { "epoch": 0.37, "learning_rate": 1.4529510897613284e-05, "loss": 0.5668, "step": 1336 }, { "epoch": 0.37, "learning_rate": 1.4521511243547588e-05, "loss": 0.5636, "step": 1337 }, { "epoch": 0.37, "learning_rate": 1.4513507950741701e-05, "loss": 0.534, "step": 1338 }, { "epoch": 0.37, "learning_rate": 1.4505501025636367e-05, "loss": 0.5464, "step": 1339 }, { "epoch": 0.37, "learning_rate": 1.4497490474675255e-05, "loss": 0.5404, "step": 1340 }, { "epoch": 0.37, "learning_rate": 1.448947630430495e-05, "loss": 0.559, "step": 1341 }, { "epoch": 0.37, "learning_rate": 1.4481458520974951e-05, "loss": 0.5636, "step": 1342 }, { "epoch": 0.37, "learning_rate": 1.447343713113767e-05, "loss": 0.5518, "step": 1343 }, { "epoch": 0.37, "learning_rate": 1.4465412141248414e-05, "loss": 0.5536, "step": 1344 }, { "epoch": 0.37, "learning_rate": 1.4457383557765385e-05, "loss": 0.5555, "step": 1345 }, { "epoch": 0.37, "learning_rate": 1.4449351387149685e-05, "loss": 0.5465, "step": 1346 }, { "epoch": 0.37, "learning_rate": 1.4441315635865299e-05, "loss": 0.542, "step": 1347 }, { "epoch": 0.37, "learning_rate": 1.4433276310379095e-05, "loss": 0.5422, "step": 1348 }, { "epoch": 0.37, "learning_rate": 1.4425233417160813e-05, "loss": 0.5614, "step": 1349 }, { "epoch": 0.37, "learning_rate": 1.4417186962683072e-05, "loss": 0.5529, "step": 1350 }, { "epoch": 0.37, "learning_rate": 1.440913695342135e-05, "loss": 0.541, "step": 1351 }, { "epoch": 0.37, "learning_rate": 1.4401083395853985e-05, "loss": 0.5629, "step": 1352 }, { "epoch": 0.37, "learning_rate": 1.439302629646218e-05, "loss": 0.5689, "step": 1353 }, { "epoch": 0.37, "learning_rate": 1.4384965661729977e-05, "loss": 0.547, "step": 1354 }, { "epoch": 0.38, "learning_rate": 1.437690149814427e-05, "loss": 0.5647, "step": 1355 }, { "epoch": 0.38, "learning_rate": 1.4368833812194791e-05, "loss": 0.5432, "step": 1356 }, { "epoch": 0.38, "learning_rate": 1.4360762610374104e-05, "loss": 0.5595, "step": 1357 }, { "epoch": 0.38, "learning_rate": 1.435268789917761e-05, "loss": 0.544, "step": 1358 }, { "epoch": 0.38, "learning_rate": 1.4344609685103525e-05, "loss": 0.5541, "step": 1359 }, { "epoch": 0.38, "learning_rate": 1.4336527974652894e-05, "loss": 0.5428, "step": 1360 }, { "epoch": 0.38, "learning_rate": 1.4328442774329565e-05, "loss": 0.558, "step": 1361 }, { "epoch": 0.38, "learning_rate": 1.4320354090640196e-05, "loss": 0.5576, "step": 1362 }, { "epoch": 0.38, "learning_rate": 1.4312261930094262e-05, "loss": 0.5469, "step": 1363 }, { "epoch": 0.38, "learning_rate": 1.4304166299204019e-05, "loss": 0.5484, "step": 1364 }, { "epoch": 0.38, "learning_rate": 1.4296067204484523e-05, "loss": 0.5533, "step": 1365 }, { "epoch": 0.38, "learning_rate": 1.4287964652453619e-05, "loss": 0.5656, "step": 1366 }, { "epoch": 0.38, "learning_rate": 1.427985864963193e-05, "loss": 0.5538, "step": 1367 }, { "epoch": 0.38, "learning_rate": 1.4271749202542862e-05, "loss": 0.549, "step": 1368 }, { "epoch": 0.38, "learning_rate": 1.426363631771259e-05, "loss": 0.541, "step": 1369 }, { "epoch": 0.38, "learning_rate": 1.425552000167005e-05, "loss": 0.5572, "step": 1370 }, { "epoch": 0.38, "learning_rate": 1.4247400260946948e-05, "loss": 0.5565, "step": 1371 }, { "epoch": 0.38, "learning_rate": 1.4239277102077743e-05, "loss": 0.5696, "step": 1372 }, { "epoch": 0.38, "learning_rate": 1.423115053159964e-05, "loss": 0.5532, "step": 1373 }, { "epoch": 0.38, "learning_rate": 1.4223020556052599e-05, "loss": 0.5486, "step": 1374 }, { "epoch": 0.38, "learning_rate": 1.421488718197931e-05, "loss": 0.5402, "step": 1375 }, { "epoch": 0.38, "learning_rate": 1.4206750415925208e-05, "loss": 0.559, "step": 1376 }, { "epoch": 0.38, "learning_rate": 1.4198610264438449e-05, "loss": 0.5299, "step": 1377 }, { "epoch": 0.38, "learning_rate": 1.4190466734069914e-05, "loss": 0.54, "step": 1378 }, { "epoch": 0.38, "learning_rate": 1.4182319831373214e-05, "loss": 0.5542, "step": 1379 }, { "epoch": 0.38, "learning_rate": 1.4174169562904667e-05, "loss": 0.5556, "step": 1380 }, { "epoch": 0.38, "learning_rate": 1.416601593522329e-05, "loss": 0.5654, "step": 1381 }, { "epoch": 0.38, "learning_rate": 1.4157858954890815e-05, "loss": 0.5496, "step": 1382 }, { "epoch": 0.38, "learning_rate": 1.4149698628471676e-05, "loss": 0.5591, "step": 1383 }, { "epoch": 0.38, "learning_rate": 1.4141534962532986e-05, "loss": 0.5613, "step": 1384 }, { "epoch": 0.38, "learning_rate": 1.4133367963644555e-05, "loss": 0.5623, "step": 1385 }, { "epoch": 0.38, "learning_rate": 1.4125197638378873e-05, "loss": 0.5474, "step": 1386 }, { "epoch": 0.38, "learning_rate": 1.4117023993311109e-05, "loss": 0.5577, "step": 1387 }, { "epoch": 0.38, "learning_rate": 1.41088470350191e-05, "loss": 0.5515, "step": 1388 }, { "epoch": 0.38, "learning_rate": 1.410066677008335e-05, "loss": 0.5421, "step": 1389 }, { "epoch": 0.38, "learning_rate": 1.4092483205087022e-05, "loss": 0.5396, "step": 1390 }, { "epoch": 0.39, "learning_rate": 1.4084296346615947e-05, "loss": 0.5555, "step": 1391 }, { "epoch": 0.39, "learning_rate": 1.4076106201258588e-05, "loss": 0.5505, "step": 1392 }, { "epoch": 0.39, "learning_rate": 1.4067912775606063e-05, "loss": 0.5607, "step": 1393 }, { "epoch": 0.39, "learning_rate": 1.4059716076252134e-05, "loss": 0.554, "step": 1394 }, { "epoch": 0.39, "learning_rate": 1.4051516109793193e-05, "loss": 0.5484, "step": 1395 }, { "epoch": 0.39, "learning_rate": 1.4043312882828256e-05, "loss": 0.5491, "step": 1396 }, { "epoch": 0.39, "learning_rate": 1.403510640195897e-05, "loss": 0.5445, "step": 1397 }, { "epoch": 0.39, "learning_rate": 1.4026896673789599e-05, "loss": 0.5519, "step": 1398 }, { "epoch": 0.39, "learning_rate": 1.4018683704927018e-05, "loss": 0.5517, "step": 1399 }, { "epoch": 0.39, "learning_rate": 1.401046750198072e-05, "loss": 0.5545, "step": 1400 }, { "epoch": 0.39, "learning_rate": 1.400224807156278e-05, "loss": 0.5382, "step": 1401 }, { "epoch": 0.39, "learning_rate": 1.3994025420287891e-05, "loss": 0.5526, "step": 1402 }, { "epoch": 0.39, "learning_rate": 1.3985799554773327e-05, "loss": 0.5368, "step": 1403 }, { "epoch": 0.39, "learning_rate": 1.3977570481638954e-05, "loss": 0.5412, "step": 1404 }, { "epoch": 0.39, "learning_rate": 1.3969338207507213e-05, "loss": 0.5531, "step": 1405 }, { "epoch": 0.39, "learning_rate": 1.3961102739003127e-05, "loss": 0.5457, "step": 1406 }, { "epoch": 0.39, "learning_rate": 1.3952864082754289e-05, "loss": 0.5509, "step": 1407 }, { "epoch": 0.39, "learning_rate": 1.3944622245390856e-05, "loss": 0.5466, "step": 1408 }, { "epoch": 0.39, "learning_rate": 1.3936377233545542e-05, "loss": 0.5551, "step": 1409 }, { "epoch": 0.39, "learning_rate": 1.392812905385362e-05, "loss": 0.5545, "step": 1410 }, { "epoch": 0.39, "learning_rate": 1.3919877712952915e-05, "loss": 0.5435, "step": 1411 }, { "epoch": 0.39, "learning_rate": 1.3911623217483787e-05, "loss": 0.5592, "step": 1412 }, { "epoch": 0.39, "learning_rate": 1.3903365574089142e-05, "loss": 0.5656, "step": 1413 }, { "epoch": 0.39, "learning_rate": 1.3895104789414418e-05, "loss": 0.5431, "step": 1414 }, { "epoch": 0.39, "learning_rate": 1.3886840870107577e-05, "loss": 0.5664, "step": 1415 }, { "epoch": 0.39, "learning_rate": 1.387857382281911e-05, "loss": 0.5488, "step": 1416 }, { "epoch": 0.39, "learning_rate": 1.3870303654202022e-05, "loss": 0.5488, "step": 1417 }, { "epoch": 0.39, "learning_rate": 1.386203037091183e-05, "loss": 0.5589, "step": 1418 }, { "epoch": 0.39, "learning_rate": 1.3853753979606552e-05, "loss": 0.563, "step": 1419 }, { "epoch": 0.39, "learning_rate": 1.3845474486946721e-05, "loss": 0.538, "step": 1420 }, { "epoch": 0.39, "learning_rate": 1.3837191899595356e-05, "loss": 0.5375, "step": 1421 }, { "epoch": 0.39, "learning_rate": 1.3828906224217961e-05, "loss": 0.5534, "step": 1422 }, { "epoch": 0.39, "learning_rate": 1.3820617467482541e-05, "loss": 0.5661, "step": 1423 }, { "epoch": 0.39, "learning_rate": 1.381232563605957e-05, "loss": 0.5561, "step": 1424 }, { "epoch": 0.39, "learning_rate": 1.3804030736621993e-05, "loss": 0.5332, "step": 1425 }, { "epoch": 0.39, "learning_rate": 1.3795732775845237e-05, "loss": 0.5445, "step": 1426 }, { "epoch": 0.4, "learning_rate": 1.3787431760407177e-05, "loss": 0.5447, "step": 1427 }, { "epoch": 0.4, "learning_rate": 1.3779127696988161e-05, "loss": 0.5624, "step": 1428 }, { "epoch": 0.4, "learning_rate": 1.3770820592270982e-05, "loss": 0.5403, "step": 1429 }, { "epoch": 0.4, "learning_rate": 1.376251045294088e-05, "loss": 0.5612, "step": 1430 }, { "epoch": 0.4, "learning_rate": 1.3754197285685537e-05, "loss": 0.5509, "step": 1431 }, { "epoch": 0.4, "learning_rate": 1.3745881097195079e-05, "loss": 0.5558, "step": 1432 }, { "epoch": 0.4, "learning_rate": 1.3737561894162054e-05, "loss": 0.5576, "step": 1433 }, { "epoch": 0.4, "learning_rate": 1.3729239683281445e-05, "loss": 0.5483, "step": 1434 }, { "epoch": 0.4, "learning_rate": 1.3720914471250644e-05, "loss": 0.5715, "step": 1435 }, { "epoch": 0.4, "learning_rate": 1.3712586264769465e-05, "loss": 0.5497, "step": 1436 }, { "epoch": 0.4, "learning_rate": 1.370425507054014e-05, "loss": 0.5666, "step": 1437 }, { "epoch": 0.4, "learning_rate": 1.369592089526729e-05, "loss": 0.5471, "step": 1438 }, { "epoch": 0.4, "learning_rate": 1.3687583745657941e-05, "loss": 0.5429, "step": 1439 }, { "epoch": 0.4, "learning_rate": 1.367924362842152e-05, "loss": 0.5477, "step": 1440 }, { "epoch": 0.4, "learning_rate": 1.367090055026983e-05, "loss": 0.5551, "step": 1441 }, { "epoch": 0.4, "learning_rate": 1.3662554517917067e-05, "loss": 0.5397, "step": 1442 }, { "epoch": 0.4, "learning_rate": 1.3654205538079796e-05, "loss": 0.5528, "step": 1443 }, { "epoch": 0.4, "learning_rate": 1.3645853617476963e-05, "loss": 0.5505, "step": 1444 }, { "epoch": 0.4, "learning_rate": 1.3637498762829872e-05, "loss": 0.5603, "step": 1445 }, { "epoch": 0.4, "learning_rate": 1.3629140980862197e-05, "loss": 0.5497, "step": 1446 }, { "epoch": 0.4, "learning_rate": 1.3620780278299956e-05, "loss": 0.5561, "step": 1447 }, { "epoch": 0.4, "learning_rate": 1.3612416661871532e-05, "loss": 0.5613, "step": 1448 }, { "epoch": 0.4, "learning_rate": 1.3604050138307638e-05, "loss": 0.5562, "step": 1449 }, { "epoch": 0.4, "learning_rate": 1.3595680714341338e-05, "loss": 0.5541, "step": 1450 }, { "epoch": 0.4, "learning_rate": 1.3587308396708023e-05, "loss": 0.543, "step": 1451 }, { "epoch": 0.4, "learning_rate": 1.3578933192145421e-05, "loss": 0.5515, "step": 1452 }, { "epoch": 0.4, "learning_rate": 1.357055510739357e-05, "loss": 0.5594, "step": 1453 }, { "epoch": 0.4, "learning_rate": 1.3562174149194844e-05, "loss": 0.5497, "step": 1454 }, { "epoch": 0.4, "learning_rate": 1.355379032429391e-05, "loss": 0.5466, "step": 1455 }, { "epoch": 0.4, "learning_rate": 1.3545403639437753e-05, "loss": 0.5279, "step": 1456 }, { "epoch": 0.4, "learning_rate": 1.3537014101375662e-05, "loss": 0.5531, "step": 1457 }, { "epoch": 0.4, "learning_rate": 1.3528621716859218e-05, "loss": 0.571, "step": 1458 }, { "epoch": 0.4, "learning_rate": 1.3520226492642288e-05, "loss": 0.5629, "step": 1459 }, { "epoch": 0.4, "learning_rate": 1.3511828435481029e-05, "loss": 0.5451, "step": 1460 }, { "epoch": 0.4, "learning_rate": 1.3503427552133884e-05, "loss": 0.5575, "step": 1461 }, { "epoch": 0.4, "learning_rate": 1.3495023849361558e-05, "loss": 0.5472, "step": 1462 }, { "epoch": 0.41, "learning_rate": 1.3486617333927033e-05, "loss": 0.5674, "step": 1463 }, { "epoch": 0.41, "learning_rate": 1.3478208012595552e-05, "loss": 0.5497, "step": 1464 }, { "epoch": 0.41, "learning_rate": 1.3469795892134623e-05, "loss": 0.5564, "step": 1465 }, { "epoch": 0.41, "learning_rate": 1.3461380979313994e-05, "loss": 0.5566, "step": 1466 }, { "epoch": 0.41, "learning_rate": 1.3452963280905667e-05, "loss": 0.569, "step": 1467 }, { "epoch": 0.41, "learning_rate": 1.3444542803683886e-05, "loss": 0.5546, "step": 1468 }, { "epoch": 0.41, "learning_rate": 1.3436119554425133e-05, "loss": 0.5494, "step": 1469 }, { "epoch": 0.41, "learning_rate": 1.3427693539908116e-05, "loss": 0.5504, "step": 1470 }, { "epoch": 0.41, "learning_rate": 1.3419264766913768e-05, "loss": 0.5648, "step": 1471 }, { "epoch": 0.41, "learning_rate": 1.3410833242225252e-05, "loss": 0.5571, "step": 1472 }, { "epoch": 0.41, "learning_rate": 1.3402398972627935e-05, "loss": 0.5445, "step": 1473 }, { "epoch": 0.41, "learning_rate": 1.3393961964909394e-05, "loss": 0.5381, "step": 1474 }, { "epoch": 0.41, "learning_rate": 1.3385522225859415e-05, "loss": 0.5393, "step": 1475 }, { "epoch": 0.41, "learning_rate": 1.3377079762269976e-05, "loss": 0.553, "step": 1476 }, { "epoch": 0.41, "learning_rate": 1.3368634580935252e-05, "loss": 0.5593, "step": 1477 }, { "epoch": 0.41, "learning_rate": 1.3360186688651604e-05, "loss": 0.5584, "step": 1478 }, { "epoch": 0.41, "learning_rate": 1.3351736092217573e-05, "loss": 0.5523, "step": 1479 }, { "epoch": 0.41, "learning_rate": 1.3343282798433877e-05, "loss": 0.5588, "step": 1480 }, { "epoch": 0.41, "learning_rate": 1.3334826814103407e-05, "loss": 0.5473, "step": 1481 }, { "epoch": 0.41, "learning_rate": 1.3326368146031217e-05, "loss": 0.5442, "step": 1482 }, { "epoch": 0.41, "learning_rate": 1.3317906801024523e-05, "loss": 0.5524, "step": 1483 }, { "epoch": 0.41, "learning_rate": 1.3309442785892686e-05, "loss": 0.5427, "step": 1484 }, { "epoch": 0.41, "learning_rate": 1.3300976107447232e-05, "loss": 0.547, "step": 1485 }, { "epoch": 0.41, "learning_rate": 1.3292506772501819e-05, "loss": 0.5446, "step": 1486 }, { "epoch": 0.41, "learning_rate": 1.3284034787872243e-05, "loss": 0.5572, "step": 1487 }, { "epoch": 0.41, "learning_rate": 1.3275560160376435e-05, "loss": 0.5588, "step": 1488 }, { "epoch": 0.41, "learning_rate": 1.3267082896834457e-05, "loss": 0.556, "step": 1489 }, { "epoch": 0.41, "learning_rate": 1.3258603004068484e-05, "loss": 0.5388, "step": 1490 }, { "epoch": 0.41, "learning_rate": 1.3250120488902813e-05, "loss": 0.5735, "step": 1491 }, { "epoch": 0.41, "learning_rate": 1.3241635358163848e-05, "loss": 0.5445, "step": 1492 }, { "epoch": 0.41, "learning_rate": 1.32331476186801e-05, "loss": 0.5642, "step": 1493 }, { "epoch": 0.41, "learning_rate": 1.322465727728218e-05, "loss": 0.5445, "step": 1494 }, { "epoch": 0.41, "learning_rate": 1.321616434080279e-05, "loss": 0.5551, "step": 1495 }, { "epoch": 0.41, "learning_rate": 1.3207668816076722e-05, "loss": 0.5571, "step": 1496 }, { "epoch": 0.41, "learning_rate": 1.3199170709940855e-05, "loss": 0.5535, "step": 1497 }, { "epoch": 0.41, "learning_rate": 1.3190670029234135e-05, "loss": 0.55, "step": 1498 }, { "epoch": 0.42, "learning_rate": 1.3182166780797589e-05, "loss": 0.5429, "step": 1499 }, { "epoch": 0.42, "learning_rate": 1.317366097147431e-05, "loss": 0.5442, "step": 1500 }, { "epoch": 0.42, "learning_rate": 1.3165152608109447e-05, "loss": 0.5568, "step": 1501 }, { "epoch": 0.42, "learning_rate": 1.3156641697550208e-05, "loss": 0.5511, "step": 1502 }, { "epoch": 0.42, "learning_rate": 1.314812824664585e-05, "loss": 0.539, "step": 1503 }, { "epoch": 0.42, "learning_rate": 1.3139612262247673e-05, "loss": 0.5429, "step": 1504 }, { "epoch": 0.42, "learning_rate": 1.3131093751209023e-05, "loss": 0.5535, "step": 1505 }, { "epoch": 0.42, "learning_rate": 1.3122572720385264e-05, "loss": 0.5568, "step": 1506 }, { "epoch": 0.42, "learning_rate": 1.3114049176633806e-05, "loss": 0.5401, "step": 1507 }, { "epoch": 0.42, "learning_rate": 1.3105523126814066e-05, "loss": 0.5403, "step": 1508 }, { "epoch": 0.42, "learning_rate": 1.309699457778749e-05, "loss": 0.5547, "step": 1509 }, { "epoch": 0.42, "learning_rate": 1.3088463536417525e-05, "loss": 0.5546, "step": 1510 }, { "epoch": 0.42, "learning_rate": 1.3079930009569633e-05, "loss": 0.5504, "step": 1511 }, { "epoch": 0.42, "learning_rate": 1.3071394004111266e-05, "loss": 0.5536, "step": 1512 }, { "epoch": 0.42, "learning_rate": 1.3062855526911882e-05, "loss": 0.5606, "step": 1513 }, { "epoch": 0.42, "learning_rate": 1.3054314584842919e-05, "loss": 0.5523, "step": 1514 }, { "epoch": 0.42, "learning_rate": 1.3045771184777807e-05, "loss": 0.5422, "step": 1515 }, { "epoch": 0.42, "learning_rate": 1.3037225333591944e-05, "loss": 0.5287, "step": 1516 }, { "epoch": 0.42, "learning_rate": 1.3028677038162705e-05, "loss": 0.5519, "step": 1517 }, { "epoch": 0.42, "learning_rate": 1.3020126305369435e-05, "loss": 0.5586, "step": 1518 }, { "epoch": 0.42, "learning_rate": 1.3011573142093442e-05, "loss": 0.5508, "step": 1519 }, { "epoch": 0.42, "learning_rate": 1.300301755521798e-05, "loss": 0.5688, "step": 1520 }, { "epoch": 0.42, "learning_rate": 1.2994459551628264e-05, "loss": 0.5421, "step": 1521 }, { "epoch": 0.42, "learning_rate": 1.2985899138211451e-05, "loss": 0.5425, "step": 1522 }, { "epoch": 0.42, "learning_rate": 1.2977336321856633e-05, "loss": 0.5498, "step": 1523 }, { "epoch": 0.42, "learning_rate": 1.2968771109454838e-05, "loss": 0.5584, "step": 1524 }, { "epoch": 0.42, "learning_rate": 1.2960203507899022e-05, "loss": 0.546, "step": 1525 }, { "epoch": 0.42, "learning_rate": 1.295163352408407e-05, "loss": 0.56, "step": 1526 }, { "epoch": 0.42, "learning_rate": 1.2943061164906774e-05, "loss": 0.5447, "step": 1527 }, { "epoch": 0.42, "learning_rate": 1.2934486437265846e-05, "loss": 0.5521, "step": 1528 }, { "epoch": 0.42, "learning_rate": 1.2925909348061898e-05, "loss": 0.5562, "step": 1529 }, { "epoch": 0.42, "learning_rate": 1.2917329904197444e-05, "loss": 0.5538, "step": 1530 }, { "epoch": 0.42, "learning_rate": 1.2908748112576901e-05, "loss": 0.5477, "step": 1531 }, { "epoch": 0.42, "learning_rate": 1.290016398010656e-05, "loss": 0.5524, "step": 1532 }, { "epoch": 0.42, "learning_rate": 1.2891577513694604e-05, "loss": 0.5453, "step": 1533 }, { "epoch": 0.42, "learning_rate": 1.2882988720251101e-05, "loss": 0.5299, "step": 1534 }, { "epoch": 0.43, "learning_rate": 1.2874397606687982e-05, "loss": 0.5606, "step": 1535 }, { "epoch": 0.43, "learning_rate": 1.2865804179919047e-05, "loss": 0.5556, "step": 1536 }, { "epoch": 0.43, "learning_rate": 1.285720844685996e-05, "loss": 0.5552, "step": 1537 }, { "epoch": 0.43, "learning_rate": 1.284861041442824e-05, "loss": 0.5454, "step": 1538 }, { "epoch": 0.43, "learning_rate": 1.2840010089543256e-05, "loss": 0.541, "step": 1539 }, { "epoch": 0.43, "learning_rate": 1.2831407479126226e-05, "loss": 0.5439, "step": 1540 }, { "epoch": 0.43, "learning_rate": 1.2822802590100191e-05, "loss": 0.5593, "step": 1541 }, { "epoch": 0.43, "learning_rate": 1.2814195429390056e-05, "loss": 0.5376, "step": 1542 }, { "epoch": 0.43, "learning_rate": 1.2805586003922523e-05, "loss": 0.5594, "step": 1543 }, { "epoch": 0.43, "learning_rate": 1.2796974320626137e-05, "loss": 0.5473, "step": 1544 }, { "epoch": 0.43, "learning_rate": 1.2788360386431249e-05, "loss": 0.5511, "step": 1545 }, { "epoch": 0.43, "learning_rate": 1.2779744208270026e-05, "loss": 0.5443, "step": 1546 }, { "epoch": 0.43, "learning_rate": 1.2771125793076442e-05, "loss": 0.5463, "step": 1547 }, { "epoch": 0.43, "learning_rate": 1.276250514778627e-05, "loss": 0.5514, "step": 1548 }, { "epoch": 0.43, "learning_rate": 1.2753882279337076e-05, "loss": 0.5633, "step": 1549 }, { "epoch": 0.43, "learning_rate": 1.2745257194668214e-05, "loss": 0.5423, "step": 1550 }, { "epoch": 0.43, "learning_rate": 1.2736629900720832e-05, "loss": 0.5366, "step": 1551 }, { "epoch": 0.43, "learning_rate": 1.2728000404437837e-05, "loss": 0.5474, "step": 1552 }, { "epoch": 0.43, "learning_rate": 1.2719368712763927e-05, "loss": 0.5493, "step": 1553 }, { "epoch": 0.43, "learning_rate": 1.2710734832645557e-05, "loss": 0.5628, "step": 1554 }, { "epoch": 0.43, "learning_rate": 1.2702098771030944e-05, "loss": 0.5374, "step": 1555 }, { "epoch": 0.43, "learning_rate": 1.2693460534870061e-05, "loss": 0.565, "step": 1556 }, { "epoch": 0.43, "learning_rate": 1.2684820131114636e-05, "loss": 0.5493, "step": 1557 }, { "epoch": 0.43, "learning_rate": 1.2676177566718133e-05, "loss": 0.5544, "step": 1558 }, { "epoch": 0.43, "learning_rate": 1.266753284863576e-05, "loss": 0.5427, "step": 1559 }, { "epoch": 0.43, "learning_rate": 1.2658885983824461e-05, "loss": 0.534, "step": 1560 }, { "epoch": 0.43, "learning_rate": 1.2650236979242896e-05, "loss": 0.5563, "step": 1561 }, { "epoch": 0.43, "learning_rate": 1.2641585841851462e-05, "loss": 0.5511, "step": 1562 }, { "epoch": 0.43, "learning_rate": 1.263293257861226e-05, "loss": 0.5462, "step": 1563 }, { "epoch": 0.43, "learning_rate": 1.2624277196489112e-05, "loss": 0.5426, "step": 1564 }, { "epoch": 0.43, "learning_rate": 1.2615619702447535e-05, "loss": 0.5574, "step": 1565 }, { "epoch": 0.43, "learning_rate": 1.2606960103454755e-05, "loss": 0.5453, "step": 1566 }, { "epoch": 0.43, "learning_rate": 1.2598298406479684e-05, "loss": 0.5528, "step": 1567 }, { "epoch": 0.43, "learning_rate": 1.2589634618492931e-05, "loss": 0.5519, "step": 1568 }, { "epoch": 0.43, "learning_rate": 1.2580968746466775e-05, "loss": 0.5554, "step": 1569 }, { "epoch": 0.43, "learning_rate": 1.2572300797375188e-05, "loss": 0.5511, "step": 1570 }, { "epoch": 0.43, "learning_rate": 1.2563630778193805e-05, "loss": 0.5512, "step": 1571 }, { "epoch": 0.44, "learning_rate": 1.255495869589992e-05, "loss": 0.5458, "step": 1572 }, { "epoch": 0.44, "learning_rate": 1.2546284557472505e-05, "loss": 0.5471, "step": 1573 }, { "epoch": 0.44, "learning_rate": 1.253760836989217e-05, "loss": 0.5579, "step": 1574 }, { "epoch": 0.44, "learning_rate": 1.252893014014118e-05, "loss": 0.5481, "step": 1575 }, { "epoch": 0.44, "learning_rate": 1.2520249875203447e-05, "loss": 0.5596, "step": 1576 }, { "epoch": 0.44, "learning_rate": 1.2511567582064516e-05, "loss": 0.5388, "step": 1577 }, { "epoch": 0.44, "learning_rate": 1.250288326771157e-05, "loss": 0.5438, "step": 1578 }, { "epoch": 0.44, "learning_rate": 1.249419693913341e-05, "loss": 0.5538, "step": 1579 }, { "epoch": 0.44, "learning_rate": 1.2485508603320467e-05, "loss": 0.548, "step": 1580 }, { "epoch": 0.44, "learning_rate": 1.2476818267264778e-05, "loss": 0.5539, "step": 1581 }, { "epoch": 0.44, "learning_rate": 1.2468125937959998e-05, "loss": 0.5607, "step": 1582 }, { "epoch": 0.44, "learning_rate": 1.2459431622401383e-05, "loss": 0.5494, "step": 1583 }, { "epoch": 0.44, "learning_rate": 1.2450735327585786e-05, "loss": 0.5528, "step": 1584 }, { "epoch": 0.44, "learning_rate": 1.2442037060511654e-05, "loss": 0.5463, "step": 1585 }, { "epoch": 0.44, "learning_rate": 1.2433336828179024e-05, "loss": 0.5453, "step": 1586 }, { "epoch": 0.44, "learning_rate": 1.2424634637589508e-05, "loss": 0.5512, "step": 1587 }, { "epoch": 0.44, "learning_rate": 1.2415930495746301e-05, "loss": 0.5499, "step": 1588 }, { "epoch": 0.44, "learning_rate": 1.2407224409654166e-05, "loss": 0.5712, "step": 1589 }, { "epoch": 0.44, "learning_rate": 1.2398516386319424e-05, "loss": 0.5459, "step": 1590 }, { "epoch": 0.44, "learning_rate": 1.2389806432749967e-05, "loss": 0.5444, "step": 1591 }, { "epoch": 0.44, "learning_rate": 1.2381094555955231e-05, "loss": 0.5478, "step": 1592 }, { "epoch": 0.44, "learning_rate": 1.2372380762946203e-05, "loss": 0.5541, "step": 1593 }, { "epoch": 0.44, "learning_rate": 1.2363665060735412e-05, "loss": 0.5576, "step": 1594 }, { "epoch": 0.44, "learning_rate": 1.2354947456336928e-05, "loss": 0.551, "step": 1595 }, { "epoch": 0.44, "learning_rate": 1.2346227956766341e-05, "loss": 0.551, "step": 1596 }, { "epoch": 0.44, "learning_rate": 1.2337506569040777e-05, "loss": 0.5553, "step": 1597 }, { "epoch": 0.44, "learning_rate": 1.2328783300178871e-05, "loss": 0.5398, "step": 1598 }, { "epoch": 0.44, "learning_rate": 1.2320058157200785e-05, "loss": 0.5398, "step": 1599 }, { "epoch": 0.44, "learning_rate": 1.2311331147128178e-05, "loss": 0.5603, "step": 1600 }, { "epoch": 0.44, "learning_rate": 1.2302602276984218e-05, "loss": 0.547, "step": 1601 }, { "epoch": 0.44, "learning_rate": 1.2293871553793565e-05, "loss": 0.5473, "step": 1602 }, { "epoch": 0.44, "learning_rate": 1.2285138984582373e-05, "loss": 0.541, "step": 1603 }, { "epoch": 0.44, "learning_rate": 1.2276404576378283e-05, "loss": 0.5545, "step": 1604 }, { "epoch": 0.44, "learning_rate": 1.2267668336210411e-05, "loss": 0.5542, "step": 1605 }, { "epoch": 0.44, "learning_rate": 1.2258930271109355e-05, "loss": 0.5641, "step": 1606 }, { "epoch": 0.44, "learning_rate": 1.2250190388107175e-05, "loss": 0.5395, "step": 1607 }, { "epoch": 0.45, "learning_rate": 1.2241448694237401e-05, "loss": 0.5384, "step": 1608 }, { "epoch": 0.45, "learning_rate": 1.2232705196535006e-05, "loss": 0.5513, "step": 1609 }, { "epoch": 0.45, "learning_rate": 1.222395990203643e-05, "loss": 0.5604, "step": 1610 }, { "epoch": 0.45, "learning_rate": 1.2215212817779556e-05, "loss": 0.5586, "step": 1611 }, { "epoch": 0.45, "learning_rate": 1.22064639508037e-05, "loss": 0.5432, "step": 1612 }, { "epoch": 0.45, "learning_rate": 1.2197713308149616e-05, "loss": 0.5644, "step": 1613 }, { "epoch": 0.45, "learning_rate": 1.2188960896859495e-05, "loss": 0.5455, "step": 1614 }, { "epoch": 0.45, "learning_rate": 1.2180206723976938e-05, "loss": 0.5553, "step": 1615 }, { "epoch": 0.45, "learning_rate": 1.2171450796546973e-05, "loss": 0.5445, "step": 1616 }, { "epoch": 0.45, "learning_rate": 1.2162693121616039e-05, "loss": 0.5586, "step": 1617 }, { "epoch": 0.45, "learning_rate": 1.2153933706231971e-05, "loss": 0.5476, "step": 1618 }, { "epoch": 0.45, "learning_rate": 1.2145172557444024e-05, "loss": 0.5501, "step": 1619 }, { "epoch": 0.45, "learning_rate": 1.2136409682302834e-05, "loss": 0.5486, "step": 1620 }, { "epoch": 0.45, "learning_rate": 1.2127645087860427e-05, "loss": 0.5438, "step": 1621 }, { "epoch": 0.45, "learning_rate": 1.2118878781170213e-05, "loss": 0.5421, "step": 1622 }, { "epoch": 0.45, "learning_rate": 1.2110110769286988e-05, "loss": 0.5542, "step": 1623 }, { "epoch": 0.45, "learning_rate": 1.2101341059266912e-05, "loss": 0.5711, "step": 1624 }, { "epoch": 0.45, "learning_rate": 1.2092569658167514e-05, "loss": 0.5377, "step": 1625 }, { "epoch": 0.45, "learning_rate": 1.2083796573047679e-05, "loss": 0.55, "step": 1626 }, { "epoch": 0.45, "learning_rate": 1.207502181096766e-05, "loss": 0.5514, "step": 1627 }, { "epoch": 0.45, "learning_rate": 1.206624537898905e-05, "loss": 0.551, "step": 1628 }, { "epoch": 0.45, "learning_rate": 1.2057467284174782e-05, "loss": 0.5512, "step": 1629 }, { "epoch": 0.45, "learning_rate": 1.2048687533589137e-05, "loss": 0.546, "step": 1630 }, { "epoch": 0.45, "learning_rate": 1.2039906134297724e-05, "loss": 0.5416, "step": 1631 }, { "epoch": 0.45, "learning_rate": 1.2031123093367476e-05, "loss": 0.5638, "step": 1632 }, { "epoch": 0.45, "learning_rate": 1.2022338417866654e-05, "loss": 0.5643, "step": 1633 }, { "epoch": 0.45, "learning_rate": 1.2013552114864828e-05, "loss": 0.5399, "step": 1634 }, { "epoch": 0.45, "learning_rate": 1.2004764191432882e-05, "loss": 0.5477, "step": 1635 }, { "epoch": 0.45, "learning_rate": 1.1995974654643002e-05, "loss": 0.5409, "step": 1636 }, { "epoch": 0.45, "learning_rate": 1.1987183511568674e-05, "loss": 0.55, "step": 1637 }, { "epoch": 0.45, "learning_rate": 1.1978390769284674e-05, "loss": 0.5516, "step": 1638 }, { "epoch": 0.45, "learning_rate": 1.1969596434867063e-05, "loss": 0.5539, "step": 1639 }, { "epoch": 0.45, "learning_rate": 1.1960800515393191e-05, "loss": 0.5501, "step": 1640 }, { "epoch": 0.45, "learning_rate": 1.1952003017941677e-05, "loss": 0.5494, "step": 1641 }, { "epoch": 0.45, "learning_rate": 1.1943203949592417e-05, "loss": 0.546, "step": 1642 }, { "epoch": 0.45, "learning_rate": 1.193440331742656e-05, "loss": 0.5344, "step": 1643 }, { "epoch": 0.46, "learning_rate": 1.1925601128526522e-05, "loss": 0.5504, "step": 1644 }, { "epoch": 0.46, "learning_rate": 1.1916797389975974e-05, "loss": 0.55, "step": 1645 }, { "epoch": 0.46, "learning_rate": 1.1907992108859822e-05, "loss": 0.5451, "step": 1646 }, { "epoch": 0.46, "learning_rate": 1.1899185292264226e-05, "loss": 0.542, "step": 1647 }, { "epoch": 0.46, "learning_rate": 1.1890376947276581e-05, "loss": 0.5531, "step": 1648 }, { "epoch": 0.46, "learning_rate": 1.1881567080985499e-05, "loss": 0.5472, "step": 1649 }, { "epoch": 0.46, "learning_rate": 1.1872755700480827e-05, "loss": 0.5504, "step": 1650 }, { "epoch": 0.46, "learning_rate": 1.1863942812853635e-05, "loss": 0.5525, "step": 1651 }, { "epoch": 0.46, "learning_rate": 1.1855128425196192e-05, "loss": 0.5671, "step": 1652 }, { "epoch": 0.46, "learning_rate": 1.1846312544601988e-05, "loss": 0.5518, "step": 1653 }, { "epoch": 0.46, "learning_rate": 1.1837495178165706e-05, "loss": 0.5573, "step": 1654 }, { "epoch": 0.46, "learning_rate": 1.1828676332983222e-05, "loss": 0.5393, "step": 1655 }, { "epoch": 0.46, "learning_rate": 1.1819856016151617e-05, "loss": 0.5462, "step": 1656 }, { "epoch": 0.46, "learning_rate": 1.181103423476914e-05, "loss": 0.5614, "step": 1657 }, { "epoch": 0.46, "learning_rate": 1.1802210995935223e-05, "loss": 0.553, "step": 1658 }, { "epoch": 0.46, "learning_rate": 1.1793386306750476e-05, "loss": 0.5556, "step": 1659 }, { "epoch": 0.46, "learning_rate": 1.1784560174316675e-05, "loss": 0.5354, "step": 1660 }, { "epoch": 0.46, "learning_rate": 1.1775732605736751e-05, "loss": 0.5384, "step": 1661 }, { "epoch": 0.46, "learning_rate": 1.1766903608114801e-05, "loss": 0.5593, "step": 1662 }, { "epoch": 0.46, "learning_rate": 1.175807318855606e-05, "loss": 0.5515, "step": 1663 }, { "epoch": 0.46, "learning_rate": 1.1749241354166913e-05, "loss": 0.5488, "step": 1664 }, { "epoch": 0.46, "learning_rate": 1.1740408112054895e-05, "loss": 0.5598, "step": 1665 }, { "epoch": 0.46, "learning_rate": 1.1731573469328653e-05, "loss": 0.5601, "step": 1666 }, { "epoch": 0.46, "learning_rate": 1.172273743309797e-05, "loss": 0.5665, "step": 1667 }, { "epoch": 0.46, "learning_rate": 1.1713900010473762e-05, "loss": 0.5386, "step": 1668 }, { "epoch": 0.46, "learning_rate": 1.1705061208568042e-05, "loss": 0.5524, "step": 1669 }, { "epoch": 0.46, "learning_rate": 1.1696221034493944e-05, "loss": 0.5617, "step": 1670 }, { "epoch": 0.46, "learning_rate": 1.1687379495365703e-05, "loss": 0.5476, "step": 1671 }, { "epoch": 0.46, "learning_rate": 1.1678536598298653e-05, "loss": 0.5667, "step": 1672 }, { "epoch": 0.46, "learning_rate": 1.1669692350409223e-05, "loss": 0.5422, "step": 1673 }, { "epoch": 0.46, "learning_rate": 1.1660846758814926e-05, "loss": 0.5625, "step": 1674 }, { "epoch": 0.46, "learning_rate": 1.1651999830634356e-05, "loss": 0.5704, "step": 1675 }, { "epoch": 0.46, "learning_rate": 1.1643151572987184e-05, "loss": 0.5573, "step": 1676 }, { "epoch": 0.46, "learning_rate": 1.1634301992994157e-05, "loss": 0.546, "step": 1677 }, { "epoch": 0.46, "learning_rate": 1.1625451097777074e-05, "loss": 0.5441, "step": 1678 }, { "epoch": 0.46, "learning_rate": 1.1616598894458799e-05, "loss": 0.5566, "step": 1679 }, { "epoch": 0.47, "learning_rate": 1.1607745390163252e-05, "loss": 0.561, "step": 1680 }, { "epoch": 0.47, "learning_rate": 1.1598890592015395e-05, "loss": 0.5461, "step": 1681 }, { "epoch": 0.47, "learning_rate": 1.159003450714123e-05, "loss": 0.5453, "step": 1682 }, { "epoch": 0.47, "learning_rate": 1.15811771426678e-05, "loss": 0.572, "step": 1683 }, { "epoch": 0.47, "learning_rate": 1.157231850572317e-05, "loss": 0.5549, "step": 1684 }, { "epoch": 0.47, "learning_rate": 1.1563458603436443e-05, "loss": 0.5452, "step": 1685 }, { "epoch": 0.47, "learning_rate": 1.1554597442937726e-05, "loss": 0.5549, "step": 1686 }, { "epoch": 0.47, "learning_rate": 1.154573503135814e-05, "loss": 0.549, "step": 1687 }, { "epoch": 0.47, "learning_rate": 1.1536871375829822e-05, "loss": 0.5503, "step": 1688 }, { "epoch": 0.47, "learning_rate": 1.1528006483485903e-05, "loss": 0.5438, "step": 1689 }, { "epoch": 0.47, "learning_rate": 1.151914036146051e-05, "loss": 0.5528, "step": 1690 }, { "epoch": 0.47, "learning_rate": 1.1510273016888763e-05, "loss": 0.5461, "step": 1691 }, { "epoch": 0.47, "learning_rate": 1.1501404456906762e-05, "loss": 0.5412, "step": 1692 }, { "epoch": 0.47, "learning_rate": 1.1492534688651586e-05, "loss": 0.545, "step": 1693 }, { "epoch": 0.47, "learning_rate": 1.148366371926129e-05, "loss": 0.5425, "step": 1694 }, { "epoch": 0.47, "learning_rate": 1.1474791555874888e-05, "loss": 0.5492, "step": 1695 }, { "epoch": 0.47, "learning_rate": 1.146591820563236e-05, "loss": 0.5522, "step": 1696 }, { "epoch": 0.47, "learning_rate": 1.1457043675674648e-05, "loss": 0.5567, "step": 1697 }, { "epoch": 0.47, "learning_rate": 1.1448167973143627e-05, "loss": 0.5455, "step": 1698 }, { "epoch": 0.47, "learning_rate": 1.1439291105182128e-05, "loss": 0.5326, "step": 1699 }, { "epoch": 0.47, "learning_rate": 1.1430413078933917e-05, "loss": 0.5621, "step": 1700 }, { "epoch": 0.47, "learning_rate": 1.142153390154369e-05, "loss": 0.555, "step": 1701 }, { "epoch": 0.47, "learning_rate": 1.1412653580157079e-05, "loss": 0.5591, "step": 1702 }, { "epoch": 0.47, "learning_rate": 1.1403772121920616e-05, "loss": 0.5422, "step": 1703 }, { "epoch": 0.47, "learning_rate": 1.1394889533981765e-05, "loss": 0.555, "step": 1704 }, { "epoch": 0.47, "learning_rate": 1.1386005823488902e-05, "loss": 0.5395, "step": 1705 }, { "epoch": 0.47, "learning_rate": 1.1377120997591291e-05, "loss": 0.5448, "step": 1706 }, { "epoch": 0.47, "learning_rate": 1.1368235063439103e-05, "loss": 0.5352, "step": 1707 }, { "epoch": 0.47, "learning_rate": 1.1359348028183403e-05, "loss": 0.5399, "step": 1708 }, { "epoch": 0.47, "learning_rate": 1.1350459898976137e-05, "loss": 0.5477, "step": 1709 }, { "epoch": 0.47, "learning_rate": 1.134157068297013e-05, "loss": 0.5418, "step": 1710 }, { "epoch": 0.47, "learning_rate": 1.1332680387319094e-05, "loss": 0.5427, "step": 1711 }, { "epoch": 0.47, "learning_rate": 1.132378901917759e-05, "loss": 0.5471, "step": 1712 }, { "epoch": 0.47, "learning_rate": 1.1314896585701058e-05, "loss": 0.5485, "step": 1713 }, { "epoch": 0.47, "learning_rate": 1.1306003094045792e-05, "loss": 0.5454, "step": 1714 }, { "epoch": 0.47, "learning_rate": 1.1297108551368929e-05, "loss": 0.5499, "step": 1715 }, { "epoch": 0.48, "learning_rate": 1.1288212964828465e-05, "loss": 0.5402, "step": 1716 }, { "epoch": 0.48, "learning_rate": 1.1279316341583227e-05, "loss": 0.5384, "step": 1717 }, { "epoch": 0.48, "learning_rate": 1.1270418688792877e-05, "loss": 0.546, "step": 1718 }, { "epoch": 0.48, "learning_rate": 1.1261520013617913e-05, "loss": 0.5417, "step": 1719 }, { "epoch": 0.48, "learning_rate": 1.125262032321964e-05, "loss": 0.5341, "step": 1720 }, { "epoch": 0.48, "learning_rate": 1.1243719624760203e-05, "loss": 0.5328, "step": 1721 }, { "epoch": 0.48, "learning_rate": 1.1234817925402537e-05, "loss": 0.5418, "step": 1722 }, { "epoch": 0.48, "learning_rate": 1.1225915232310393e-05, "loss": 0.5467, "step": 1723 }, { "epoch": 0.48, "learning_rate": 1.1217011552648316e-05, "loss": 0.5525, "step": 1724 }, { "epoch": 0.48, "learning_rate": 1.1208106893581658e-05, "loss": 0.5466, "step": 1725 }, { "epoch": 0.48, "learning_rate": 1.1199201262276543e-05, "loss": 0.5621, "step": 1726 }, { "epoch": 0.48, "learning_rate": 1.1190294665899882e-05, "loss": 0.5465, "step": 1727 }, { "epoch": 0.48, "learning_rate": 1.1181387111619368e-05, "loss": 0.5525, "step": 1728 }, { "epoch": 0.48, "learning_rate": 1.1172478606603463e-05, "loss": 0.5427, "step": 1729 }, { "epoch": 0.48, "learning_rate": 1.1163569158021392e-05, "loss": 0.5528, "step": 1730 }, { "epoch": 0.48, "learning_rate": 1.115465877304314e-05, "loss": 0.5419, "step": 1731 }, { "epoch": 0.48, "learning_rate": 1.1145747458839444e-05, "loss": 0.5382, "step": 1732 }, { "epoch": 0.48, "learning_rate": 1.1136835222581792e-05, "loss": 0.5368, "step": 1733 }, { "epoch": 0.48, "learning_rate": 1.1127922071442417e-05, "loss": 0.5668, "step": 1734 }, { "epoch": 0.48, "learning_rate": 1.1119008012594275e-05, "loss": 0.5643, "step": 1735 }, { "epoch": 0.48, "learning_rate": 1.1110093053211067e-05, "loss": 0.5342, "step": 1736 }, { "epoch": 0.48, "learning_rate": 1.110117720046721e-05, "loss": 0.5574, "step": 1737 }, { "epoch": 0.48, "learning_rate": 1.1092260461537847e-05, "loss": 0.5425, "step": 1738 }, { "epoch": 0.48, "learning_rate": 1.108334284359883e-05, "loss": 0.5439, "step": 1739 }, { "epoch": 0.48, "learning_rate": 1.1074424353826712e-05, "loss": 0.5529, "step": 1740 }, { "epoch": 0.48, "learning_rate": 1.1065504999398762e-05, "loss": 0.5607, "step": 1741 }, { "epoch": 0.48, "learning_rate": 1.1056584787492936e-05, "loss": 0.5344, "step": 1742 }, { "epoch": 0.48, "learning_rate": 1.1047663725287877e-05, "loss": 0.5461, "step": 1743 }, { "epoch": 0.48, "learning_rate": 1.1038741819962916e-05, "loss": 0.5591, "step": 1744 }, { "epoch": 0.48, "learning_rate": 1.1029819078698068e-05, "loss": 0.5522, "step": 1745 }, { "epoch": 0.48, "learning_rate": 1.1020895508674013e-05, "loss": 0.547, "step": 1746 }, { "epoch": 0.48, "learning_rate": 1.10119711170721e-05, "loss": 0.5366, "step": 1747 }, { "epoch": 0.48, "learning_rate": 1.100304591107434e-05, "loss": 0.5486, "step": 1748 }, { "epoch": 0.48, "learning_rate": 1.09941198978634e-05, "loss": 0.5477, "step": 1749 }, { "epoch": 0.48, "learning_rate": 1.0985193084622595e-05, "loss": 0.5412, "step": 1750 }, { "epoch": 0.48, "learning_rate": 1.0976265478535886e-05, "loss": 0.5426, "step": 1751 }, { "epoch": 0.49, "learning_rate": 1.0967337086787869e-05, "loss": 0.5427, "step": 1752 }, { "epoch": 0.49, "learning_rate": 1.0958407916563772e-05, "loss": 0.563, "step": 1753 }, { "epoch": 0.49, "learning_rate": 1.0949477975049456e-05, "loss": 0.5499, "step": 1754 }, { "epoch": 0.49, "learning_rate": 1.0940547269431396e-05, "loss": 0.5541, "step": 1755 }, { "epoch": 0.49, "learning_rate": 1.0931615806896686e-05, "loss": 0.5424, "step": 1756 }, { "epoch": 0.49, "learning_rate": 1.092268359463302e-05, "loss": 0.5412, "step": 1757 }, { "epoch": 0.49, "learning_rate": 1.091375063982871e-05, "loss": 0.5381, "step": 1758 }, { "epoch": 0.49, "learning_rate": 1.090481694967266e-05, "loss": 0.5489, "step": 1759 }, { "epoch": 0.49, "learning_rate": 1.0895882531354357e-05, "loss": 0.5409, "step": 1760 }, { "epoch": 0.49, "learning_rate": 1.088694739206388e-05, "loss": 0.5366, "step": 1761 }, { "epoch": 0.49, "learning_rate": 1.0878011538991898e-05, "loss": 0.5522, "step": 1762 }, { "epoch": 0.49, "learning_rate": 1.0869074979329639e-05, "loss": 0.5532, "step": 1763 }, { "epoch": 0.49, "learning_rate": 1.0860137720268906e-05, "loss": 0.5252, "step": 1764 }, { "epoch": 0.49, "learning_rate": 1.0851199769002066e-05, "loss": 0.5508, "step": 1765 }, { "epoch": 0.49, "learning_rate": 1.0842261132722043e-05, "loss": 0.5488, "step": 1766 }, { "epoch": 0.49, "learning_rate": 1.0833321818622311e-05, "loss": 0.5356, "step": 1767 }, { "epoch": 0.49, "learning_rate": 1.0824381833896892e-05, "loss": 0.5365, "step": 1768 }, { "epoch": 0.49, "learning_rate": 1.0815441185740338e-05, "loss": 0.538, "step": 1769 }, { "epoch": 0.49, "learning_rate": 1.0806499881347752e-05, "loss": 0.5472, "step": 1770 }, { "epoch": 0.49, "learning_rate": 1.079755792791475e-05, "loss": 0.5508, "step": 1771 }, { "epoch": 0.49, "learning_rate": 1.0788615332637478e-05, "loss": 0.5588, "step": 1772 }, { "epoch": 0.49, "learning_rate": 1.077967210271259e-05, "loss": 0.5309, "step": 1773 }, { "epoch": 0.49, "learning_rate": 1.0770728245337267e-05, "loss": 0.5498, "step": 1774 }, { "epoch": 0.49, "learning_rate": 1.0761783767709182e-05, "loss": 0.5422, "step": 1775 }, { "epoch": 0.49, "learning_rate": 1.0752838677026506e-05, "loss": 0.5474, "step": 1776 }, { "epoch": 0.49, "learning_rate": 1.0743892980487911e-05, "loss": 0.5509, "step": 1777 }, { "epoch": 0.49, "learning_rate": 1.0734946685292552e-05, "loss": 0.5572, "step": 1778 }, { "epoch": 0.49, "learning_rate": 1.072599979864007e-05, "loss": 0.547, "step": 1779 }, { "epoch": 0.49, "learning_rate": 1.0717052327730573e-05, "loss": 0.5523, "step": 1780 }, { "epoch": 0.49, "learning_rate": 1.0708104279764648e-05, "loss": 0.5441, "step": 1781 }, { "epoch": 0.49, "learning_rate": 1.0699155661943347e-05, "loss": 0.5437, "step": 1782 }, { "epoch": 0.49, "learning_rate": 1.0690206481468174e-05, "loss": 0.5456, "step": 1783 }, { "epoch": 0.49, "learning_rate": 1.0681256745541087e-05, "loss": 0.5569, "step": 1784 }, { "epoch": 0.49, "learning_rate": 1.0672306461364497e-05, "loss": 0.5462, "step": 1785 }, { "epoch": 0.49, "learning_rate": 1.0663355636141248e-05, "loss": 0.5412, "step": 1786 }, { "epoch": 0.49, "learning_rate": 1.0654404277074626e-05, "loss": 0.5539, "step": 1787 }, { "epoch": 0.5, "learning_rate": 1.0645452391368346e-05, "loss": 0.5457, "step": 1788 }, { "epoch": 0.5, "learning_rate": 1.0636499986226538e-05, "loss": 0.5483, "step": 1789 }, { "epoch": 0.5, "learning_rate": 1.0627547068853765e-05, "loss": 0.5313, "step": 1790 }, { "epoch": 0.5, "learning_rate": 1.0618593646454993e-05, "loss": 0.5556, "step": 1791 }, { "epoch": 0.5, "learning_rate": 1.0609639726235592e-05, "loss": 0.5362, "step": 1792 }, { "epoch": 0.5, "learning_rate": 1.0600685315401336e-05, "loss": 0.5484, "step": 1793 }, { "epoch": 0.5, "learning_rate": 1.0591730421158398e-05, "loss": 0.5369, "step": 1794 }, { "epoch": 0.5, "learning_rate": 1.0582775050713333e-05, "loss": 0.5515, "step": 1795 }, { "epoch": 0.5, "learning_rate": 1.0573819211273084e-05, "loss": 0.5491, "step": 1796 }, { "epoch": 0.5, "learning_rate": 1.0564862910044967e-05, "loss": 0.5484, "step": 1797 }, { "epoch": 0.5, "learning_rate": 1.0555906154236676e-05, "loss": 0.5475, "step": 1798 }, { "epoch": 0.5, "learning_rate": 1.0546948951056268e-05, "loss": 0.5497, "step": 1799 }, { "epoch": 0.5, "learning_rate": 1.0537991307712157e-05, "loss": 0.5379, "step": 1800 }, { "epoch": 0.5, "learning_rate": 1.052903323141311e-05, "loss": 0.5626, "step": 1801 }, { "epoch": 0.5, "learning_rate": 1.0520074729368253e-05, "loss": 0.5464, "step": 1802 }, { "epoch": 0.5, "learning_rate": 1.0511115808787042e-05, "loss": 0.5508, "step": 1803 }, { "epoch": 0.5, "learning_rate": 1.0502156476879277e-05, "loss": 0.5461, "step": 1804 }, { "epoch": 0.5, "learning_rate": 1.049319674085509e-05, "loss": 0.5576, "step": 1805 }, { "epoch": 0.5, "learning_rate": 1.0484236607924932e-05, "loss": 0.5556, "step": 1806 }, { "epoch": 0.5, "learning_rate": 1.047527608529958e-05, "loss": 0.5477, "step": 1807 }, { "epoch": 0.5, "learning_rate": 1.0466315180190121e-05, "loss": 0.5505, "step": 1808 }, { "epoch": 0.5, "learning_rate": 1.0457353899807947e-05, "loss": 0.5631, "step": 1809 }, { "epoch": 0.5, "learning_rate": 1.0448392251364757e-05, "loss": 0.541, "step": 1810 }, { "epoch": 0.5, "learning_rate": 1.0439430242072547e-05, "loss": 0.5481, "step": 1811 }, { "epoch": 0.5, "learning_rate": 1.0430467879143601e-05, "loss": 0.5421, "step": 1812 }, { "epoch": 0.5, "learning_rate": 1.0421505169790487e-05, "loss": 0.542, "step": 1813 }, { "epoch": 0.5, "learning_rate": 1.041254212122605e-05, "loss": 0.5428, "step": 1814 }, { "epoch": 0.5, "learning_rate": 1.0403578740663412e-05, "loss": 0.5428, "step": 1815 }, { "epoch": 0.5, "learning_rate": 1.0394615035315963e-05, "loss": 0.5388, "step": 1816 }, { "epoch": 0.5, "learning_rate": 1.038565101239735e-05, "loss": 0.5561, "step": 1817 }, { "epoch": 0.5, "learning_rate": 1.0376686679121473e-05, "loss": 0.5498, "step": 1818 }, { "epoch": 0.5, "learning_rate": 1.0367722042702494e-05, "loss": 0.5487, "step": 1819 }, { "epoch": 0.5, "learning_rate": 1.0358757110354807e-05, "loss": 0.5579, "step": 1820 }, { "epoch": 0.5, "learning_rate": 1.034979188929305e-05, "loss": 0.5491, "step": 1821 }, { "epoch": 0.5, "learning_rate": 1.034082638673209e-05, "loss": 0.5404, "step": 1822 }, { "epoch": 0.5, "learning_rate": 1.0331860609887023e-05, "loss": 0.5404, "step": 1823 }, { "epoch": 0.51, "learning_rate": 1.0322894565973168e-05, "loss": 0.5474, "step": 1824 }, { "epoch": 0.51, "learning_rate": 1.0313928262206052e-05, "loss": 0.5391, "step": 1825 }, { "epoch": 0.51, "learning_rate": 1.0304961705801415e-05, "loss": 0.5472, "step": 1826 }, { "epoch": 0.51, "learning_rate": 1.0295994903975201e-05, "loss": 0.5396, "step": 1827 }, { "epoch": 0.51, "learning_rate": 1.0287027863943557e-05, "loss": 0.5473, "step": 1828 }, { "epoch": 0.51, "learning_rate": 1.0278060592922807e-05, "loss": 0.5314, "step": 1829 }, { "epoch": 0.51, "learning_rate": 1.026909309812947e-05, "loss": 0.5479, "step": 1830 }, { "epoch": 0.51, "learning_rate": 1.0260125386780254e-05, "loss": 0.5453, "step": 1831 }, { "epoch": 0.51, "learning_rate": 1.0251157466092019e-05, "loss": 0.549, "step": 1832 }, { "epoch": 0.51, "learning_rate": 1.0242189343281816e-05, "loss": 0.5526, "step": 1833 }, { "epoch": 0.51, "learning_rate": 1.0233221025566844e-05, "loss": 0.555, "step": 1834 }, { "epoch": 0.51, "learning_rate": 1.0224252520164466e-05, "loss": 0.5447, "step": 1835 }, { "epoch": 0.51, "learning_rate": 1.0215283834292193e-05, "loss": 0.543, "step": 1836 }, { "epoch": 0.51, "learning_rate": 1.0206314975167684e-05, "loss": 0.5495, "step": 1837 }, { "epoch": 0.51, "learning_rate": 1.0197345950008731e-05, "loss": 0.5369, "step": 1838 }, { "epoch": 0.51, "learning_rate": 1.0188376766033268e-05, "loss": 0.5365, "step": 1839 }, { "epoch": 0.51, "learning_rate": 1.0179407430459352e-05, "loss": 0.5436, "step": 1840 }, { "epoch": 0.51, "learning_rate": 1.0170437950505164e-05, "loss": 0.5436, "step": 1841 }, { "epoch": 0.51, "learning_rate": 1.0161468333388997e-05, "loss": 0.5353, "step": 1842 }, { "epoch": 0.51, "learning_rate": 1.015249858632926e-05, "loss": 0.5361, "step": 1843 }, { "epoch": 0.51, "learning_rate": 1.0143528716544464e-05, "loss": 0.5453, "step": 1844 }, { "epoch": 0.51, "learning_rate": 1.0134558731253221e-05, "loss": 0.5516, "step": 1845 }, { "epoch": 0.51, "learning_rate": 1.0125588637674228e-05, "loss": 0.5403, "step": 1846 }, { "epoch": 0.51, "learning_rate": 1.011661844302628e-05, "loss": 0.5445, "step": 1847 }, { "epoch": 0.51, "learning_rate": 1.0107648154528248e-05, "loss": 0.5513, "step": 1848 }, { "epoch": 0.51, "learning_rate": 1.0098677779399078e-05, "loss": 0.5403, "step": 1849 }, { "epoch": 0.51, "learning_rate": 1.0089707324857783e-05, "loss": 0.5611, "step": 1850 }, { "epoch": 0.51, "learning_rate": 1.0080736798123447e-05, "loss": 0.5527, "step": 1851 }, { "epoch": 0.51, "learning_rate": 1.007176620641521e-05, "loss": 0.5692, "step": 1852 }, { "epoch": 0.51, "learning_rate": 1.006279555695226e-05, "loss": 0.5319, "step": 1853 }, { "epoch": 0.51, "learning_rate": 1.0053824856953833e-05, "loss": 0.546, "step": 1854 }, { "epoch": 0.51, "learning_rate": 1.0044854113639213e-05, "loss": 0.5381, "step": 1855 }, { "epoch": 0.51, "learning_rate": 1.003588333422771e-05, "loss": 0.5372, "step": 1856 }, { "epoch": 0.51, "learning_rate": 1.002691252593866e-05, "loss": 0.5527, "step": 1857 }, { "epoch": 0.51, "learning_rate": 1.0017941695991438e-05, "loss": 0.5376, "step": 1858 }, { "epoch": 0.51, "learning_rate": 1.0008970851605419e-05, "loss": 0.5401, "step": 1859 }, { "epoch": 0.52, "learning_rate": 1e-05, "loss": 0.5516, "step": 1860 }, { "epoch": 0.52, "learning_rate": 9.991029148394583e-06, "loss": 0.5454, "step": 1861 }, { "epoch": 0.52, "learning_rate": 9.982058304008565e-06, "loss": 0.5344, "step": 1862 }, { "epoch": 0.52, "learning_rate": 9.973087474061342e-06, "loss": 0.543, "step": 1863 }, { "epoch": 0.52, "learning_rate": 9.964116665772295e-06, "loss": 0.542, "step": 1864 }, { "epoch": 0.52, "learning_rate": 9.955145886360789e-06, "loss": 0.544, "step": 1865 }, { "epoch": 0.52, "learning_rate": 9.946175143046168e-06, "loss": 0.5519, "step": 1866 }, { "epoch": 0.52, "learning_rate": 9.937204443047742e-06, "loss": 0.5561, "step": 1867 }, { "epoch": 0.52, "learning_rate": 9.928233793584792e-06, "loss": 0.5409, "step": 1868 }, { "epoch": 0.52, "learning_rate": 9.919263201876558e-06, "loss": 0.5477, "step": 1869 }, { "epoch": 0.52, "learning_rate": 9.91029267514222e-06, "loss": 0.5493, "step": 1870 }, { "epoch": 0.52, "learning_rate": 9.901322220600927e-06, "loss": 0.5502, "step": 1871 }, { "epoch": 0.52, "learning_rate": 9.892351845471753e-06, "loss": 0.5408, "step": 1872 }, { "epoch": 0.52, "learning_rate": 9.88338155697372e-06, "loss": 0.5576, "step": 1873 }, { "epoch": 0.52, "learning_rate": 9.874411362325772e-06, "loss": 0.5409, "step": 1874 }, { "epoch": 0.52, "learning_rate": 9.865441268746782e-06, "loss": 0.5472, "step": 1875 }, { "epoch": 0.52, "learning_rate": 9.856471283455537e-06, "loss": 0.5651, "step": 1876 }, { "epoch": 0.52, "learning_rate": 9.847501413670742e-06, "loss": 0.5342, "step": 1877 }, { "epoch": 0.52, "learning_rate": 9.838531666611005e-06, "loss": 0.5467, "step": 1878 }, { "epoch": 0.52, "learning_rate": 9.829562049494838e-06, "loss": 0.5442, "step": 1879 }, { "epoch": 0.52, "learning_rate": 9.820592569540653e-06, "loss": 0.548, "step": 1880 }, { "epoch": 0.52, "learning_rate": 9.811623233966737e-06, "loss": 0.5319, "step": 1881 }, { "epoch": 0.52, "learning_rate": 9.802654049991274e-06, "loss": 0.5438, "step": 1882 }, { "epoch": 0.52, "learning_rate": 9.79368502483232e-06, "loss": 0.5356, "step": 1883 }, { "epoch": 0.52, "learning_rate": 9.784716165707808e-06, "loss": 0.5453, "step": 1884 }, { "epoch": 0.52, "learning_rate": 9.775747479835536e-06, "loss": 0.5552, "step": 1885 }, { "epoch": 0.52, "learning_rate": 9.76677897443316e-06, "loss": 0.5356, "step": 1886 }, { "epoch": 0.52, "learning_rate": 9.757810656718187e-06, "loss": 0.5503, "step": 1887 }, { "epoch": 0.52, "learning_rate": 9.748842533907983e-06, "loss": 0.547, "step": 1888 }, { "epoch": 0.52, "learning_rate": 9.739874613219752e-06, "loss": 0.5466, "step": 1889 }, { "epoch": 0.52, "learning_rate": 9.730906901870531e-06, "loss": 0.5395, "step": 1890 }, { "epoch": 0.52, "learning_rate": 9.721939407077196e-06, "loss": 0.542, "step": 1891 }, { "epoch": 0.52, "learning_rate": 9.712972136056448e-06, "loss": 0.5338, "step": 1892 }, { "epoch": 0.52, "learning_rate": 9.7040050960248e-06, "loss": 0.5523, "step": 1893 }, { "epoch": 0.52, "learning_rate": 9.695038294198588e-06, "loss": 0.5342, "step": 1894 }, { "epoch": 0.52, "learning_rate": 9.68607173779395e-06, "loss": 0.5437, "step": 1895 }, { "epoch": 0.52, "learning_rate": 9.677105434026834e-06, "loss": 0.5477, "step": 1896 }, { "epoch": 0.53, "learning_rate": 9.668139390112977e-06, "loss": 0.5374, "step": 1897 }, { "epoch": 0.53, "learning_rate": 9.659173613267915e-06, "loss": 0.554, "step": 1898 }, { "epoch": 0.53, "learning_rate": 9.650208110706954e-06, "loss": 0.5447, "step": 1899 }, { "epoch": 0.53, "learning_rate": 9.641242889645196e-06, "loss": 0.5425, "step": 1900 }, { "epoch": 0.53, "learning_rate": 9.632277957297509e-06, "loss": 0.547, "step": 1901 }, { "epoch": 0.53, "learning_rate": 9.623313320878529e-06, "loss": 0.5492, "step": 1902 }, { "epoch": 0.53, "learning_rate": 9.614348987602656e-06, "loss": 0.535, "step": 1903 }, { "epoch": 0.53, "learning_rate": 9.60538496468404e-06, "loss": 0.5379, "step": 1904 }, { "epoch": 0.53, "learning_rate": 9.596421259336592e-06, "loss": 0.5638, "step": 1905 }, { "epoch": 0.53, "learning_rate": 9.587457878773953e-06, "loss": 0.5493, "step": 1906 }, { "epoch": 0.53, "learning_rate": 9.578494830209518e-06, "loss": 0.5313, "step": 1907 }, { "epoch": 0.53, "learning_rate": 9.569532120856399e-06, "loss": 0.5413, "step": 1908 }, { "epoch": 0.53, "learning_rate": 9.560569757927456e-06, "loss": 0.556, "step": 1909 }, { "epoch": 0.53, "learning_rate": 9.551607748635247e-06, "loss": 0.5517, "step": 1910 }, { "epoch": 0.53, "learning_rate": 9.542646100192056e-06, "loss": 0.5399, "step": 1911 }, { "epoch": 0.53, "learning_rate": 9.533684819809884e-06, "loss": 0.5398, "step": 1912 }, { "epoch": 0.53, "learning_rate": 9.524723914700422e-06, "loss": 0.5401, "step": 1913 }, { "epoch": 0.53, "learning_rate": 9.51576339207507e-06, "loss": 0.5463, "step": 1914 }, { "epoch": 0.53, "learning_rate": 9.506803259144914e-06, "loss": 0.5434, "step": 1915 }, { "epoch": 0.53, "learning_rate": 9.497843523120726e-06, "loss": 0.5319, "step": 1916 }, { "epoch": 0.53, "learning_rate": 9.488884191212961e-06, "loss": 0.548, "step": 1917 }, { "epoch": 0.53, "learning_rate": 9.479925270631752e-06, "loss": 0.5477, "step": 1918 }, { "epoch": 0.53, "learning_rate": 9.470966768586892e-06, "loss": 0.5448, "step": 1919 }, { "epoch": 0.53, "learning_rate": 9.46200869228785e-06, "loss": 0.5369, "step": 1920 }, { "epoch": 0.53, "learning_rate": 9.453051048943736e-06, "loss": 0.5526, "step": 1921 }, { "epoch": 0.53, "learning_rate": 9.444093845763327e-06, "loss": 0.5433, "step": 1922 }, { "epoch": 0.53, "learning_rate": 9.435137089955035e-06, "loss": 0.5406, "step": 1923 }, { "epoch": 0.53, "learning_rate": 9.426180788726918e-06, "loss": 0.5459, "step": 1924 }, { "epoch": 0.53, "learning_rate": 9.417224949286669e-06, "loss": 0.5343, "step": 1925 }, { "epoch": 0.53, "learning_rate": 9.408269578841607e-06, "loss": 0.5557, "step": 1926 }, { "epoch": 0.53, "learning_rate": 9.399314684598665e-06, "loss": 0.553, "step": 1927 }, { "epoch": 0.53, "learning_rate": 9.390360273764411e-06, "loss": 0.548, "step": 1928 }, { "epoch": 0.53, "learning_rate": 9.381406353545009e-06, "loss": 0.5417, "step": 1929 }, { "epoch": 0.53, "learning_rate": 9.372452931146234e-06, "loss": 0.5473, "step": 1930 }, { "epoch": 0.53, "learning_rate": 9.363500013773462e-06, "loss": 0.5529, "step": 1931 }, { "epoch": 0.53, "learning_rate": 9.354547608631659e-06, "loss": 0.5557, "step": 1932 }, { "epoch": 0.54, "learning_rate": 9.345595722925377e-06, "loss": 0.5324, "step": 1933 }, { "epoch": 0.54, "learning_rate": 9.336644363858754e-06, "loss": 0.549, "step": 1934 }, { "epoch": 0.54, "learning_rate": 9.327693538635507e-06, "loss": 0.5454, "step": 1935 }, { "epoch": 0.54, "learning_rate": 9.318743254458913e-06, "loss": 0.5493, "step": 1936 }, { "epoch": 0.54, "learning_rate": 9.309793518531831e-06, "loss": 0.5394, "step": 1937 }, { "epoch": 0.54, "learning_rate": 9.300844338056658e-06, "loss": 0.5375, "step": 1938 }, { "epoch": 0.54, "learning_rate": 9.291895720235355e-06, "loss": 0.5542, "step": 1939 }, { "epoch": 0.54, "learning_rate": 9.282947672269429e-06, "loss": 0.5575, "step": 1940 }, { "epoch": 0.54, "learning_rate": 9.274000201359935e-06, "loss": 0.5408, "step": 1941 }, { "epoch": 0.54, "learning_rate": 9.26505331470745e-06, "loss": 0.5397, "step": 1942 }, { "epoch": 0.54, "learning_rate": 9.256107019512094e-06, "loss": 0.558, "step": 1943 }, { "epoch": 0.54, "learning_rate": 9.247161322973499e-06, "loss": 0.5551, "step": 1944 }, { "epoch": 0.54, "learning_rate": 9.238216232290821e-06, "loss": 0.5526, "step": 1945 }, { "epoch": 0.54, "learning_rate": 9.229271754662734e-06, "loss": 0.5293, "step": 1946 }, { "epoch": 0.54, "learning_rate": 9.220327897287411e-06, "loss": 0.5489, "step": 1947 }, { "epoch": 0.54, "learning_rate": 9.211384667362527e-06, "loss": 0.5474, "step": 1948 }, { "epoch": 0.54, "learning_rate": 9.202442072085255e-06, "loss": 0.5537, "step": 1949 }, { "epoch": 0.54, "learning_rate": 9.193500118652253e-06, "loss": 0.5544, "step": 1950 }, { "epoch": 0.54, "learning_rate": 9.184558814259664e-06, "loss": 0.5312, "step": 1951 }, { "epoch": 0.54, "learning_rate": 9.17561816610311e-06, "loss": 0.54, "step": 1952 }, { "epoch": 0.54, "learning_rate": 9.166678181377689e-06, "loss": 0.5429, "step": 1953 }, { "epoch": 0.54, "learning_rate": 9.157738867277957e-06, "loss": 0.5472, "step": 1954 }, { "epoch": 0.54, "learning_rate": 9.14880023099794e-06, "loss": 0.545, "step": 1955 }, { "epoch": 0.54, "learning_rate": 9.139862279731097e-06, "loss": 0.5459, "step": 1956 }, { "epoch": 0.54, "learning_rate": 9.130925020670365e-06, "loss": 0.5513, "step": 1957 }, { "epoch": 0.54, "learning_rate": 9.121988461008104e-06, "loss": 0.5284, "step": 1958 }, { "epoch": 0.54, "learning_rate": 9.11305260793612e-06, "loss": 0.5501, "step": 1959 }, { "epoch": 0.54, "learning_rate": 9.104117468645648e-06, "loss": 0.5457, "step": 1960 }, { "epoch": 0.54, "learning_rate": 9.095183050327344e-06, "loss": 0.5502, "step": 1961 }, { "epoch": 0.54, "learning_rate": 9.086249360171291e-06, "loss": 0.5418, "step": 1962 }, { "epoch": 0.54, "learning_rate": 9.07731640536698e-06, "loss": 0.537, "step": 1963 }, { "epoch": 0.54, "learning_rate": 9.06838419310332e-06, "loss": 0.5314, "step": 1964 }, { "epoch": 0.54, "learning_rate": 9.059452730568604e-06, "loss": 0.5456, "step": 1965 }, { "epoch": 0.54, "learning_rate": 9.050522024950549e-06, "loss": 0.5459, "step": 1966 }, { "epoch": 0.54, "learning_rate": 9.041592083436233e-06, "loss": 0.5525, "step": 1967 }, { "epoch": 0.54, "learning_rate": 9.032662913212135e-06, "loss": 0.5401, "step": 1968 }, { "epoch": 0.55, "learning_rate": 9.023734521464117e-06, "loss": 0.5477, "step": 1969 }, { "epoch": 0.55, "learning_rate": 9.014806915377407e-06, "loss": 0.55, "step": 1970 }, { "epoch": 0.55, "learning_rate": 9.005880102136601e-06, "loss": 0.539, "step": 1971 }, { "epoch": 0.55, "learning_rate": 8.996954088925664e-06, "loss": 0.526, "step": 1972 }, { "epoch": 0.55, "learning_rate": 8.988028882927904e-06, "loss": 0.5524, "step": 1973 }, { "epoch": 0.55, "learning_rate": 8.97910449132599e-06, "loss": 0.5494, "step": 1974 }, { "epoch": 0.55, "learning_rate": 8.970180921301934e-06, "loss": 0.5442, "step": 1975 }, { "epoch": 0.55, "learning_rate": 8.961258180037085e-06, "loss": 0.5332, "step": 1976 }, { "epoch": 0.55, "learning_rate": 8.952336274712128e-06, "loss": 0.5459, "step": 1977 }, { "epoch": 0.55, "learning_rate": 8.943415212507069e-06, "loss": 0.5413, "step": 1978 }, { "epoch": 0.55, "learning_rate": 8.934495000601241e-06, "loss": 0.5425, "step": 1979 }, { "epoch": 0.55, "learning_rate": 8.92557564617329e-06, "loss": 0.5523, "step": 1980 }, { "epoch": 0.55, "learning_rate": 8.916657156401172e-06, "loss": 0.547, "step": 1981 }, { "epoch": 0.55, "learning_rate": 8.907739538462154e-06, "loss": 0.5444, "step": 1982 }, { "epoch": 0.55, "learning_rate": 8.898822799532794e-06, "loss": 0.5516, "step": 1983 }, { "epoch": 0.55, "learning_rate": 8.889906946788936e-06, "loss": 0.5489, "step": 1984 }, { "epoch": 0.55, "learning_rate": 8.880991987405728e-06, "loss": 0.5359, "step": 1985 }, { "epoch": 0.55, "learning_rate": 8.872077928557588e-06, "loss": 0.5412, "step": 1986 }, { "epoch": 0.55, "learning_rate": 8.863164777418208e-06, "loss": 0.543, "step": 1987 }, { "epoch": 0.55, "learning_rate": 8.854252541160557e-06, "loss": 0.5371, "step": 1988 }, { "epoch": 0.55, "learning_rate": 8.845341226956864e-06, "loss": 0.5505, "step": 1989 }, { "epoch": 0.55, "learning_rate": 8.836430841978611e-06, "loss": 0.5481, "step": 1990 }, { "epoch": 0.55, "learning_rate": 8.827521393396538e-06, "loss": 0.5288, "step": 1991 }, { "epoch": 0.55, "learning_rate": 8.818612888380634e-06, "loss": 0.5437, "step": 1992 }, { "epoch": 0.55, "learning_rate": 8.80970533410012e-06, "loss": 0.5485, "step": 1993 }, { "epoch": 0.55, "learning_rate": 8.800798737723459e-06, "loss": 0.5272, "step": 1994 }, { "epoch": 0.55, "learning_rate": 8.791893106418347e-06, "loss": 0.5578, "step": 1995 }, { "epoch": 0.55, "learning_rate": 8.782988447351685e-06, "loss": 0.5542, "step": 1996 }, { "epoch": 0.55, "learning_rate": 8.77408476768961e-06, "loss": 0.5427, "step": 1997 }, { "epoch": 0.55, "learning_rate": 8.765182074597464e-06, "loss": 0.5338, "step": 1998 }, { "epoch": 0.55, "learning_rate": 8.756280375239798e-06, "loss": 0.541, "step": 1999 }, { "epoch": 0.55, "learning_rate": 8.747379676780361e-06, "loss": 0.5411, "step": 2000 }, { "epoch": 0.55, "learning_rate": 8.738479986382092e-06, "loss": 0.5418, "step": 2001 }, { "epoch": 0.55, "learning_rate": 8.729581311207125e-06, "loss": 0.5654, "step": 2002 }, { "epoch": 0.55, "learning_rate": 8.720683658416777e-06, "loss": 0.5422, "step": 2003 }, { "epoch": 0.55, "learning_rate": 8.711787035171537e-06, "loss": 0.5408, "step": 2004 }, { "epoch": 0.56, "learning_rate": 8.702891448631073e-06, "loss": 0.5546, "step": 2005 }, { "epoch": 0.56, "learning_rate": 8.693996905954213e-06, "loss": 0.5452, "step": 2006 }, { "epoch": 0.56, "learning_rate": 8.685103414298945e-06, "loss": 0.5316, "step": 2007 }, { "epoch": 0.56, "learning_rate": 8.676210980822414e-06, "loss": 0.5487, "step": 2008 }, { "epoch": 0.56, "learning_rate": 8.667319612680909e-06, "loss": 0.5493, "step": 2009 }, { "epoch": 0.56, "learning_rate": 8.658429317029868e-06, "loss": 0.543, "step": 2010 }, { "epoch": 0.56, "learning_rate": 8.649540101023865e-06, "loss": 0.5304, "step": 2011 }, { "epoch": 0.56, "learning_rate": 8.640651971816602e-06, "loss": 0.5332, "step": 2012 }, { "epoch": 0.56, "learning_rate": 8.6317649365609e-06, "loss": 0.55, "step": 2013 }, { "epoch": 0.56, "learning_rate": 8.622879002408712e-06, "loss": 0.5407, "step": 2014 }, { "epoch": 0.56, "learning_rate": 8.613994176511103e-06, "loss": 0.5452, "step": 2015 }, { "epoch": 0.56, "learning_rate": 8.605110466018236e-06, "loss": 0.5361, "step": 2016 }, { "epoch": 0.56, "learning_rate": 8.59622787807939e-06, "loss": 0.55, "step": 2017 }, { "epoch": 0.56, "learning_rate": 8.587346419842928e-06, "loss": 0.5554, "step": 2018 }, { "epoch": 0.56, "learning_rate": 8.578466098456312e-06, "loss": 0.5324, "step": 2019 }, { "epoch": 0.56, "learning_rate": 8.569586921066085e-06, "loss": 0.5416, "step": 2020 }, { "epoch": 0.56, "learning_rate": 8.560708894817875e-06, "loss": 0.5434, "step": 2021 }, { "epoch": 0.56, "learning_rate": 8.551832026856373e-06, "loss": 0.5475, "step": 2022 }, { "epoch": 0.56, "learning_rate": 8.542956324325357e-06, "loss": 0.5461, "step": 2023 }, { "epoch": 0.56, "learning_rate": 8.534081794367642e-06, "loss": 0.5364, "step": 2024 }, { "epoch": 0.56, "learning_rate": 8.525208444125115e-06, "loss": 0.5387, "step": 2025 }, { "epoch": 0.56, "learning_rate": 8.516336280738713e-06, "loss": 0.5378, "step": 2026 }, { "epoch": 0.56, "learning_rate": 8.507465311348415e-06, "loss": 0.5464, "step": 2027 }, { "epoch": 0.56, "learning_rate": 8.49859554309324e-06, "loss": 0.5381, "step": 2028 }, { "epoch": 0.56, "learning_rate": 8.48972698311124e-06, "loss": 0.5459, "step": 2029 }, { "epoch": 0.56, "learning_rate": 8.480859638539492e-06, "loss": 0.539, "step": 2030 }, { "epoch": 0.56, "learning_rate": 8.471993516514102e-06, "loss": 0.5542, "step": 2031 }, { "epoch": 0.56, "learning_rate": 8.463128624170182e-06, "loss": 0.5369, "step": 2032 }, { "epoch": 0.56, "learning_rate": 8.454264968641863e-06, "loss": 0.5384, "step": 2033 }, { "epoch": 0.56, "learning_rate": 8.445402557062281e-06, "loss": 0.5467, "step": 2034 }, { "epoch": 0.56, "learning_rate": 8.436541396563562e-06, "loss": 0.5428, "step": 2035 }, { "epoch": 0.56, "learning_rate": 8.427681494276832e-06, "loss": 0.5562, "step": 2036 }, { "epoch": 0.56, "learning_rate": 8.418822857332205e-06, "loss": 0.5341, "step": 2037 }, { "epoch": 0.56, "learning_rate": 8.409965492858772e-06, "loss": 0.5294, "step": 2038 }, { "epoch": 0.56, "learning_rate": 8.401109407984606e-06, "loss": 0.5518, "step": 2039 }, { "epoch": 0.56, "learning_rate": 8.392254609836753e-06, "loss": 0.5445, "step": 2040 }, { "epoch": 0.57, "learning_rate": 8.383401105541203e-06, "loss": 0.5387, "step": 2041 }, { "epoch": 0.57, "learning_rate": 8.37454890222293e-06, "loss": 0.5317, "step": 2042 }, { "epoch": 0.57, "learning_rate": 8.365698007005845e-06, "loss": 0.5421, "step": 2043 }, { "epoch": 0.57, "learning_rate": 8.356848427012816e-06, "loss": 0.5479, "step": 2044 }, { "epoch": 0.57, "learning_rate": 8.348000169365646e-06, "loss": 0.5358, "step": 2045 }, { "epoch": 0.57, "learning_rate": 8.339153241185079e-06, "loss": 0.5381, "step": 2046 }, { "epoch": 0.57, "learning_rate": 8.330307649590782e-06, "loss": 0.55, "step": 2047 }, { "epoch": 0.57, "learning_rate": 8.32146340170135e-06, "loss": 0.5593, "step": 2048 }, { "epoch": 0.57, "learning_rate": 8.312620504634302e-06, "loss": 0.5528, "step": 2049 }, { "epoch": 0.57, "learning_rate": 8.303778965506058e-06, "loss": 0.5346, "step": 2050 }, { "epoch": 0.57, "learning_rate": 8.29493879143196e-06, "loss": 0.5203, "step": 2051 }, { "epoch": 0.57, "learning_rate": 8.286099989526243e-06, "loss": 0.5279, "step": 2052 }, { "epoch": 0.57, "learning_rate": 8.277262566902032e-06, "loss": 0.5381, "step": 2053 }, { "epoch": 0.57, "learning_rate": 8.26842653067135e-06, "loss": 0.5552, "step": 2054 }, { "epoch": 0.57, "learning_rate": 8.259591887945108e-06, "loss": 0.5242, "step": 2055 }, { "epoch": 0.57, "learning_rate": 8.250758645833085e-06, "loss": 0.5583, "step": 2056 }, { "epoch": 0.57, "learning_rate": 8.241926811443946e-06, "loss": 0.5423, "step": 2057 }, { "epoch": 0.57, "learning_rate": 8.233096391885205e-06, "loss": 0.5428, "step": 2058 }, { "epoch": 0.57, "learning_rate": 8.224267394263252e-06, "loss": 0.5299, "step": 2059 }, { "epoch": 0.57, "learning_rate": 8.215439825683329e-06, "loss": 0.5476, "step": 2060 }, { "epoch": 0.57, "learning_rate": 8.206613693249526e-06, "loss": 0.5419, "step": 2061 }, { "epoch": 0.57, "learning_rate": 8.19778900406478e-06, "loss": 0.5443, "step": 2062 }, { "epoch": 0.57, "learning_rate": 8.188965765230866e-06, "loss": 0.5433, "step": 2063 }, { "epoch": 0.57, "learning_rate": 8.180143983848388e-06, "loss": 0.5276, "step": 2064 }, { "epoch": 0.57, "learning_rate": 8.17132366701678e-06, "loss": 0.5453, "step": 2065 }, { "epoch": 0.57, "learning_rate": 8.162504821834296e-06, "loss": 0.5389, "step": 2066 }, { "epoch": 0.57, "learning_rate": 8.153687455398013e-06, "loss": 0.5417, "step": 2067 }, { "epoch": 0.57, "learning_rate": 8.144871574803808e-06, "loss": 0.5322, "step": 2068 }, { "epoch": 0.57, "learning_rate": 8.13605718714637e-06, "loss": 0.5481, "step": 2069 }, { "epoch": 0.57, "learning_rate": 8.127244299519174e-06, "loss": 0.5588, "step": 2070 }, { "epoch": 0.57, "learning_rate": 8.118432919014504e-06, "loss": 0.5512, "step": 2071 }, { "epoch": 0.57, "learning_rate": 8.109623052723422e-06, "loss": 0.5302, "step": 2072 }, { "epoch": 0.57, "learning_rate": 8.100814707735774e-06, "loss": 0.544, "step": 2073 }, { "epoch": 0.57, "learning_rate": 8.092007891140181e-06, "loss": 0.5503, "step": 2074 }, { "epoch": 0.57, "learning_rate": 8.08320261002403e-06, "loss": 0.5513, "step": 2075 }, { "epoch": 0.57, "learning_rate": 8.07439887147348e-06, "loss": 0.5479, "step": 2076 }, { "epoch": 0.58, "learning_rate": 8.065596682573444e-06, "loss": 0.5385, "step": 2077 }, { "epoch": 0.58, "learning_rate": 8.056796050407588e-06, "loss": 0.5453, "step": 2078 }, { "epoch": 0.58, "learning_rate": 8.047996982058323e-06, "loss": 0.551, "step": 2079 }, { "epoch": 0.58, "learning_rate": 8.039199484606814e-06, "loss": 0.5318, "step": 2080 }, { "epoch": 0.58, "learning_rate": 8.030403565132942e-06, "loss": 0.5341, "step": 2081 }, { "epoch": 0.58, "learning_rate": 8.02160923071533e-06, "loss": 0.5398, "step": 2082 }, { "epoch": 0.58, "learning_rate": 8.012816488431328e-06, "loss": 0.5494, "step": 2083 }, { "epoch": 0.58, "learning_rate": 8.004025345356998e-06, "loss": 0.5487, "step": 2084 }, { "epoch": 0.58, "learning_rate": 7.99523580856712e-06, "loss": 0.5245, "step": 2085 }, { "epoch": 0.58, "learning_rate": 7.986447885135175e-06, "loss": 0.5568, "step": 2086 }, { "epoch": 0.58, "learning_rate": 7.977661582133349e-06, "loss": 0.5387, "step": 2087 }, { "epoch": 0.58, "learning_rate": 7.968876906632527e-06, "loss": 0.5391, "step": 2088 }, { "epoch": 0.58, "learning_rate": 7.960093865702281e-06, "loss": 0.5416, "step": 2089 }, { "epoch": 0.58, "learning_rate": 7.951312466410867e-06, "loss": 0.5334, "step": 2090 }, { "epoch": 0.58, "learning_rate": 7.942532715825223e-06, "loss": 0.554, "step": 2091 }, { "epoch": 0.58, "learning_rate": 7.933754621010956e-06, "loss": 0.5327, "step": 2092 }, { "epoch": 0.58, "learning_rate": 7.924978189032342e-06, "loss": 0.5475, "step": 2093 }, { "epoch": 0.58, "learning_rate": 7.916203426952323e-06, "loss": 0.5391, "step": 2094 }, { "epoch": 0.58, "learning_rate": 7.907430341832487e-06, "loss": 0.5499, "step": 2095 }, { "epoch": 0.58, "learning_rate": 7.89865894073309e-06, "loss": 0.549, "step": 2096 }, { "epoch": 0.58, "learning_rate": 7.889889230713017e-06, "loss": 0.5293, "step": 2097 }, { "epoch": 0.58, "learning_rate": 7.881121218829789e-06, "loss": 0.5278, "step": 2098 }, { "epoch": 0.58, "learning_rate": 7.872354912139578e-06, "loss": 0.5554, "step": 2099 }, { "epoch": 0.58, "learning_rate": 7.863590317697169e-06, "loss": 0.5451, "step": 2100 }, { "epoch": 0.58, "learning_rate": 7.854827442555977e-06, "loss": 0.5505, "step": 2101 }, { "epoch": 0.58, "learning_rate": 7.846066293768029e-06, "loss": 0.5642, "step": 2102 }, { "epoch": 0.58, "learning_rate": 7.837306878383966e-06, "loss": 0.5302, "step": 2103 }, { "epoch": 0.58, "learning_rate": 7.82854920345303e-06, "loss": 0.5636, "step": 2104 }, { "epoch": 0.58, "learning_rate": 7.819793276023065e-06, "loss": 0.5518, "step": 2105 }, { "epoch": 0.58, "learning_rate": 7.811039103140509e-06, "loss": 0.5457, "step": 2106 }, { "epoch": 0.58, "learning_rate": 7.802286691850382e-06, "loss": 0.5459, "step": 2107 }, { "epoch": 0.58, "learning_rate": 7.793536049196301e-06, "loss": 0.5369, "step": 2108 }, { "epoch": 0.58, "learning_rate": 7.78478718222045e-06, "loss": 0.5451, "step": 2109 }, { "epoch": 0.58, "learning_rate": 7.776040097963573e-06, "loss": 0.5427, "step": 2110 }, { "epoch": 0.58, "learning_rate": 7.767294803464996e-06, "loss": 0.5392, "step": 2111 }, { "epoch": 0.58, "learning_rate": 7.758551305762602e-06, "loss": 0.5413, "step": 2112 }, { "epoch": 0.59, "learning_rate": 7.749809611892825e-06, "loss": 0.5504, "step": 2113 }, { "epoch": 0.59, "learning_rate": 7.741069728890648e-06, "loss": 0.5361, "step": 2114 }, { "epoch": 0.59, "learning_rate": 7.732331663789592e-06, "loss": 0.5544, "step": 2115 }, { "epoch": 0.59, "learning_rate": 7.723595423621722e-06, "loss": 0.5345, "step": 2116 }, { "epoch": 0.59, "learning_rate": 7.71486101541763e-06, "loss": 0.5439, "step": 2117 }, { "epoch": 0.59, "learning_rate": 7.706128446206439e-06, "loss": 0.5591, "step": 2118 }, { "epoch": 0.59, "learning_rate": 7.697397723015784e-06, "loss": 0.5372, "step": 2119 }, { "epoch": 0.59, "learning_rate": 7.688668852871825e-06, "loss": 0.5412, "step": 2120 }, { "epoch": 0.59, "learning_rate": 7.679941842799219e-06, "loss": 0.5344, "step": 2121 }, { "epoch": 0.59, "learning_rate": 7.67121669982113e-06, "loss": 0.5439, "step": 2122 }, { "epoch": 0.59, "learning_rate": 7.662493430959226e-06, "loss": 0.554, "step": 2123 }, { "epoch": 0.59, "learning_rate": 7.65377204323366e-06, "loss": 0.5317, "step": 2124 }, { "epoch": 0.59, "learning_rate": 7.645052543663074e-06, "loss": 0.5311, "step": 2125 }, { "epoch": 0.59, "learning_rate": 7.636334939264591e-06, "loss": 0.5514, "step": 2126 }, { "epoch": 0.59, "learning_rate": 7.627619237053799e-06, "loss": 0.5436, "step": 2127 }, { "epoch": 0.59, "learning_rate": 7.6189054440447715e-06, "loss": 0.5513, "step": 2128 }, { "epoch": 0.59, "learning_rate": 7.610193567250036e-06, "loss": 0.5329, "step": 2129 }, { "epoch": 0.59, "learning_rate": 7.601483613680578e-06, "loss": 0.5423, "step": 2130 }, { "epoch": 0.59, "learning_rate": 7.59277559034584e-06, "loss": 0.5467, "step": 2131 }, { "epoch": 0.59, "learning_rate": 7.584069504253703e-06, "loss": 0.5406, "step": 2132 }, { "epoch": 0.59, "learning_rate": 7.575365362410495e-06, "loss": 0.5245, "step": 2133 }, { "epoch": 0.59, "learning_rate": 7.56666317182098e-06, "loss": 0.5474, "step": 2134 }, { "epoch": 0.59, "learning_rate": 7.557962939488349e-06, "loss": 0.5457, "step": 2135 }, { "epoch": 0.59, "learning_rate": 7.549264672414216e-06, "loss": 0.5542, "step": 2136 }, { "epoch": 0.59, "learning_rate": 7.540568377598623e-06, "loss": 0.5392, "step": 2137 }, { "epoch": 0.59, "learning_rate": 7.531874062040008e-06, "loss": 0.5362, "step": 2138 }, { "epoch": 0.59, "learning_rate": 7.523181732735225e-06, "loss": 0.5425, "step": 2139 }, { "epoch": 0.59, "learning_rate": 7.514491396679536e-06, "loss": 0.5553, "step": 2140 }, { "epoch": 0.59, "learning_rate": 7.505803060866591e-06, "loss": 0.5543, "step": 2141 }, { "epoch": 0.59, "learning_rate": 7.4971167322884316e-06, "loss": 0.535, "step": 2142 }, { "epoch": 0.59, "learning_rate": 7.488432417935486e-06, "loss": 0.55, "step": 2143 }, { "epoch": 0.59, "learning_rate": 7.479750124796556e-06, "loss": 0.5439, "step": 2144 }, { "epoch": 0.59, "learning_rate": 7.471069859858824e-06, "loss": 0.546, "step": 2145 }, { "epoch": 0.59, "learning_rate": 7.462391630107834e-06, "loss": 0.5356, "step": 2146 }, { "epoch": 0.59, "learning_rate": 7.4537154425274984e-06, "loss": 0.5374, "step": 2147 }, { "epoch": 0.59, "learning_rate": 7.4450413041000776e-06, "loss": 0.5432, "step": 2148 }, { "epoch": 0.6, "learning_rate": 7.436369221806201e-06, "loss": 0.5475, "step": 2149 }, { "epoch": 0.6, "learning_rate": 7.427699202624814e-06, "loss": 0.5392, "step": 2150 }, { "epoch": 0.6, "learning_rate": 7.419031253533228e-06, "loss": 0.5421, "step": 2151 }, { "epoch": 0.6, "learning_rate": 7.410365381507072e-06, "loss": 0.5317, "step": 2152 }, { "epoch": 0.6, "learning_rate": 7.401701593520316e-06, "loss": 0.5449, "step": 2153 }, { "epoch": 0.6, "learning_rate": 7.393039896545251e-06, "loss": 0.5513, "step": 2154 }, { "epoch": 0.6, "learning_rate": 7.384380297552468e-06, "loss": 0.5474, "step": 2155 }, { "epoch": 0.6, "learning_rate": 7.3757228035108915e-06, "loss": 0.5427, "step": 2156 }, { "epoch": 0.6, "learning_rate": 7.367067421387742e-06, "loss": 0.5491, "step": 2157 }, { "epoch": 0.6, "learning_rate": 7.358414158148541e-06, "loss": 0.5448, "step": 2158 }, { "epoch": 0.6, "learning_rate": 7.349763020757106e-06, "loss": 0.5302, "step": 2159 }, { "epoch": 0.6, "learning_rate": 7.341114016175543e-06, "loss": 0.5447, "step": 2160 }, { "epoch": 0.6, "learning_rate": 7.3324671513642424e-06, "loss": 0.5413, "step": 2161 }, { "epoch": 0.6, "learning_rate": 7.323822433281871e-06, "loss": 0.5433, "step": 2162 }, { "epoch": 0.6, "learning_rate": 7.315179868885367e-06, "loss": 0.5296, "step": 2163 }, { "epoch": 0.6, "learning_rate": 7.306539465129938e-06, "loss": 0.5424, "step": 2164 }, { "epoch": 0.6, "learning_rate": 7.297901228969057e-06, "loss": 0.5417, "step": 2165 }, { "epoch": 0.6, "learning_rate": 7.289265167354449e-06, "loss": 0.5493, "step": 2166 }, { "epoch": 0.6, "learning_rate": 7.280631287236077e-06, "loss": 0.5236, "step": 2167 }, { "epoch": 0.6, "learning_rate": 7.271999595562165e-06, "loss": 0.5502, "step": 2168 }, { "epoch": 0.6, "learning_rate": 7.263370099279173e-06, "loss": 0.5465, "step": 2169 }, { "epoch": 0.6, "learning_rate": 7.254742805331786e-06, "loss": 0.5451, "step": 2170 }, { "epoch": 0.6, "learning_rate": 7.2461177206629285e-06, "loss": 0.5354, "step": 2171 }, { "epoch": 0.6, "learning_rate": 7.237494852213734e-06, "loss": 0.5457, "step": 2172 }, { "epoch": 0.6, "learning_rate": 7.228874206923561e-06, "loss": 0.5315, "step": 2173 }, { "epoch": 0.6, "learning_rate": 7.220255791729977e-06, "loss": 0.5573, "step": 2174 }, { "epoch": 0.6, "learning_rate": 7.211639613568755e-06, "loss": 0.5338, "step": 2175 }, { "epoch": 0.6, "learning_rate": 7.203025679373868e-06, "loss": 0.534, "step": 2176 }, { "epoch": 0.6, "learning_rate": 7.19441399607748e-06, "loss": 0.5463, "step": 2177 }, { "epoch": 0.6, "learning_rate": 7.1858045706099486e-06, "loss": 0.5526, "step": 2178 }, { "epoch": 0.6, "learning_rate": 7.17719740989981e-06, "loss": 0.5528, "step": 2179 }, { "epoch": 0.6, "learning_rate": 7.168592520873778e-06, "loss": 0.5518, "step": 2180 }, { "epoch": 0.6, "learning_rate": 7.159989910456745e-06, "loss": 0.5335, "step": 2181 }, { "epoch": 0.6, "learning_rate": 7.1513895855717604e-06, "loss": 0.5377, "step": 2182 }, { "epoch": 0.6, "learning_rate": 7.142791553140045e-06, "loss": 0.5371, "step": 2183 }, { "epoch": 0.6, "learning_rate": 7.134195820080956e-06, "loss": 0.5448, "step": 2184 }, { "epoch": 0.61, "learning_rate": 7.125602393312021e-06, "loss": 0.5517, "step": 2185 }, { "epoch": 0.61, "learning_rate": 7.117011279748901e-06, "loss": 0.5582, "step": 2186 }, { "epoch": 0.61, "learning_rate": 7.108422486305398e-06, "loss": 0.5471, "step": 2187 }, { "epoch": 0.61, "learning_rate": 7.099836019893447e-06, "loss": 0.5437, "step": 2188 }, { "epoch": 0.61, "learning_rate": 7.0912518874231055e-06, "loss": 0.5491, "step": 2189 }, { "epoch": 0.61, "learning_rate": 7.082670095802557e-06, "loss": 0.5431, "step": 2190 }, { "epoch": 0.61, "learning_rate": 7.074090651938106e-06, "loss": 0.5292, "step": 2191 }, { "epoch": 0.61, "learning_rate": 7.065513562734157e-06, "loss": 0.5271, "step": 2192 }, { "epoch": 0.61, "learning_rate": 7.056938835093226e-06, "loss": 0.5397, "step": 2193 }, { "epoch": 0.61, "learning_rate": 7.0483664759159355e-06, "loss": 0.5382, "step": 2194 }, { "epoch": 0.61, "learning_rate": 7.039796492100981e-06, "loss": 0.566, "step": 2195 }, { "epoch": 0.61, "learning_rate": 7.031228890545166e-06, "loss": 0.5361, "step": 2196 }, { "epoch": 0.61, "learning_rate": 7.02266367814337e-06, "loss": 0.5206, "step": 2197 }, { "epoch": 0.61, "learning_rate": 7.014100861788551e-06, "loss": 0.5367, "step": 2198 }, { "epoch": 0.61, "learning_rate": 7.005540448371735e-06, "loss": 0.5433, "step": 2199 }, { "epoch": 0.61, "learning_rate": 6.996982444782021e-06, "loss": 0.5391, "step": 2200 }, { "epoch": 0.61, "learning_rate": 6.988426857906562e-06, "loss": 0.5437, "step": 2201 }, { "epoch": 0.61, "learning_rate": 6.979873694630566e-06, "loss": 0.5509, "step": 2202 }, { "epoch": 0.61, "learning_rate": 6.971322961837299e-06, "loss": 0.5424, "step": 2203 }, { "epoch": 0.61, "learning_rate": 6.9627746664080605e-06, "loss": 0.5409, "step": 2204 }, { "epoch": 0.61, "learning_rate": 6.954228815222195e-06, "loss": 0.5428, "step": 2205 }, { "epoch": 0.61, "learning_rate": 6.945685415157084e-06, "loss": 0.5433, "step": 2206 }, { "epoch": 0.61, "learning_rate": 6.937144473088122e-06, "loss": 0.554, "step": 2207 }, { "epoch": 0.61, "learning_rate": 6.928605995888737e-06, "loss": 0.5411, "step": 2208 }, { "epoch": 0.61, "learning_rate": 6.92006999043037e-06, "loss": 0.5521, "step": 2209 }, { "epoch": 0.61, "learning_rate": 6.911536463582475e-06, "loss": 0.5454, "step": 2210 }, { "epoch": 0.61, "learning_rate": 6.9030054222125165e-06, "loss": 0.5372, "step": 2211 }, { "epoch": 0.61, "learning_rate": 6.894476873185936e-06, "loss": 0.5486, "step": 2212 }, { "epoch": 0.61, "learning_rate": 6.8859508233661976e-06, "loss": 0.5482, "step": 2213 }, { "epoch": 0.61, "learning_rate": 6.877427279614737e-06, "loss": 0.5448, "step": 2214 }, { "epoch": 0.61, "learning_rate": 6.868906248790981e-06, "loss": 0.5397, "step": 2215 }, { "epoch": 0.61, "learning_rate": 6.860387737752327e-06, "loss": 0.5311, "step": 2216 }, { "epoch": 0.61, "learning_rate": 6.851871753354154e-06, "loss": 0.5475, "step": 2217 }, { "epoch": 0.61, "learning_rate": 6.843358302449795e-06, "loss": 0.5379, "step": 2218 }, { "epoch": 0.61, "learning_rate": 6.834847391890556e-06, "loss": 0.5504, "step": 2219 }, { "epoch": 0.61, "learning_rate": 6.826339028525692e-06, "loss": 0.5355, "step": 2220 }, { "epoch": 0.61, "learning_rate": 6.817833219202411e-06, "loss": 0.5571, "step": 2221 }, { "epoch": 0.62, "learning_rate": 6.8093299707658654e-06, "loss": 0.5425, "step": 2222 }, { "epoch": 0.62, "learning_rate": 6.80082929005915e-06, "loss": 0.5513, "step": 2223 }, { "epoch": 0.62, "learning_rate": 6.792331183923281e-06, "loss": 0.5365, "step": 2224 }, { "epoch": 0.62, "learning_rate": 6.783835659197211e-06, "loss": 0.5439, "step": 2225 }, { "epoch": 0.62, "learning_rate": 6.775342722717821e-06, "loss": 0.5551, "step": 2226 }, { "epoch": 0.62, "learning_rate": 6.7668523813199e-06, "loss": 0.5424, "step": 2227 }, { "epoch": 0.62, "learning_rate": 6.758364641836155e-06, "loss": 0.5435, "step": 2228 }, { "epoch": 0.62, "learning_rate": 6.7498795110971905e-06, "loss": 0.5373, "step": 2229 }, { "epoch": 0.62, "learning_rate": 6.741396995931519e-06, "loss": 0.5466, "step": 2230 }, { "epoch": 0.62, "learning_rate": 6.732917103165546e-06, "loss": 0.5377, "step": 2231 }, { "epoch": 0.62, "learning_rate": 6.724439839623567e-06, "loss": 0.5509, "step": 2232 }, { "epoch": 0.62, "learning_rate": 6.715965212127761e-06, "loss": 0.539, "step": 2233 }, { "epoch": 0.62, "learning_rate": 6.707493227498187e-06, "loss": 0.5519, "step": 2234 }, { "epoch": 0.62, "learning_rate": 6.699023892552772e-06, "loss": 0.5384, "step": 2235 }, { "epoch": 0.62, "learning_rate": 6.690557214107317e-06, "loss": 0.5399, "step": 2236 }, { "epoch": 0.62, "learning_rate": 6.682093198975481e-06, "loss": 0.5293, "step": 2237 }, { "epoch": 0.62, "learning_rate": 6.673631853968784e-06, "loss": 0.5347, "step": 2238 }, { "epoch": 0.62, "learning_rate": 6.665173185896594e-06, "loss": 0.547, "step": 2239 }, { "epoch": 0.62, "learning_rate": 6.656717201566127e-06, "loss": 0.5553, "step": 2240 }, { "epoch": 0.62, "learning_rate": 6.648263907782431e-06, "loss": 0.5363, "step": 2241 }, { "epoch": 0.62, "learning_rate": 6.6398133113484e-06, "loss": 0.53, "step": 2242 }, { "epoch": 0.62, "learning_rate": 6.63136541906475e-06, "loss": 0.5434, "step": 2243 }, { "epoch": 0.62, "learning_rate": 6.6229202377300265e-06, "loss": 0.5397, "step": 2244 }, { "epoch": 0.62, "learning_rate": 6.61447777414059e-06, "loss": 0.5344, "step": 2245 }, { "epoch": 0.62, "learning_rate": 6.60603803509061e-06, "loss": 0.5227, "step": 2246 }, { "epoch": 0.62, "learning_rate": 6.597601027372069e-06, "loss": 0.556, "step": 2247 }, { "epoch": 0.62, "learning_rate": 6.58916675777475e-06, "loss": 0.5386, "step": 2248 }, { "epoch": 0.62, "learning_rate": 6.580735233086233e-06, "loss": 0.5492, "step": 2249 }, { "epoch": 0.62, "learning_rate": 6.572306460091886e-06, "loss": 0.5284, "step": 2250 }, { "epoch": 0.62, "learning_rate": 6.563880445574873e-06, "loss": 0.546, "step": 2251 }, { "epoch": 0.62, "learning_rate": 6.555457196316118e-06, "loss": 0.5388, "step": 2252 }, { "epoch": 0.62, "learning_rate": 6.547036719094335e-06, "loss": 0.5363, "step": 2253 }, { "epoch": 0.62, "learning_rate": 6.538619020686009e-06, "loss": 0.5377, "step": 2254 }, { "epoch": 0.62, "learning_rate": 6.530204107865379e-06, "loss": 0.546, "step": 2255 }, { "epoch": 0.62, "learning_rate": 6.521791987404447e-06, "loss": 0.5438, "step": 2256 }, { "epoch": 0.62, "learning_rate": 6.513382666072969e-06, "loss": 0.5531, "step": 2257 }, { "epoch": 0.63, "learning_rate": 6.504976150638446e-06, "loss": 0.5509, "step": 2258 }, { "epoch": 0.63, "learning_rate": 6.496572447866121e-06, "loss": 0.5424, "step": 2259 }, { "epoch": 0.63, "learning_rate": 6.488171564518973e-06, "loss": 0.532, "step": 2260 }, { "epoch": 0.63, "learning_rate": 6.479773507357716e-06, "loss": 0.5449, "step": 2261 }, { "epoch": 0.63, "learning_rate": 6.471378283140783e-06, "loss": 0.536, "step": 2262 }, { "epoch": 0.63, "learning_rate": 6.462985898624341e-06, "loss": 0.5298, "step": 2263 }, { "epoch": 0.63, "learning_rate": 6.454596360562249e-06, "loss": 0.541, "step": 2264 }, { "epoch": 0.63, "learning_rate": 6.446209675706094e-06, "loss": 0.5283, "step": 2265 }, { "epoch": 0.63, "learning_rate": 6.437825850805158e-06, "loss": 0.5355, "step": 2266 }, { "epoch": 0.63, "learning_rate": 6.429444892606429e-06, "loss": 0.5391, "step": 2267 }, { "epoch": 0.63, "learning_rate": 6.421066807854585e-06, "loss": 0.5329, "step": 2268 }, { "epoch": 0.63, "learning_rate": 6.412691603291979e-06, "loss": 0.5434, "step": 2269 }, { "epoch": 0.63, "learning_rate": 6.404319285658664e-06, "loss": 0.5431, "step": 2270 }, { "epoch": 0.63, "learning_rate": 6.395949861692365e-06, "loss": 0.5435, "step": 2271 }, { "epoch": 0.63, "learning_rate": 6.387583338128471e-06, "loss": 0.5393, "step": 2272 }, { "epoch": 0.63, "learning_rate": 6.379219721700045e-06, "loss": 0.5454, "step": 2273 }, { "epoch": 0.63, "learning_rate": 6.370859019137807e-06, "loss": 0.5484, "step": 2274 }, { "epoch": 0.63, "learning_rate": 6.362501237170129e-06, "loss": 0.5391, "step": 2275 }, { "epoch": 0.63, "learning_rate": 6.35414638252304e-06, "loss": 0.5366, "step": 2276 }, { "epoch": 0.63, "learning_rate": 6.345794461920206e-06, "loss": 0.5539, "step": 2277 }, { "epoch": 0.63, "learning_rate": 6.337445482082935e-06, "loss": 0.5477, "step": 2278 }, { "epoch": 0.63, "learning_rate": 6.3290994497301705e-06, "loss": 0.5343, "step": 2279 }, { "epoch": 0.63, "learning_rate": 6.3207563715784845e-06, "loss": 0.5367, "step": 2280 }, { "epoch": 0.63, "learning_rate": 6.312416254342062e-06, "loss": 0.5341, "step": 2281 }, { "epoch": 0.63, "learning_rate": 6.304079104732712e-06, "loss": 0.5487, "step": 2282 }, { "epoch": 0.63, "learning_rate": 6.295744929459861e-06, "loss": 0.5462, "step": 2283 }, { "epoch": 0.63, "learning_rate": 6.287413735230534e-06, "loss": 0.5494, "step": 2284 }, { "epoch": 0.63, "learning_rate": 6.2790855287493605e-06, "loss": 0.5322, "step": 2285 }, { "epoch": 0.63, "learning_rate": 6.270760316718559e-06, "loss": 0.545, "step": 2286 }, { "epoch": 0.63, "learning_rate": 6.262438105837947e-06, "loss": 0.5355, "step": 2287 }, { "epoch": 0.63, "learning_rate": 6.254118902804923e-06, "loss": 0.545, "step": 2288 }, { "epoch": 0.63, "learning_rate": 6.245802714314464e-06, "loss": 0.533, "step": 2289 }, { "epoch": 0.63, "learning_rate": 6.237489547059123e-06, "loss": 0.541, "step": 2290 }, { "epoch": 0.63, "learning_rate": 6.2291794077290226e-06, "loss": 0.5496, "step": 2291 }, { "epoch": 0.63, "learning_rate": 6.220872303011842e-06, "loss": 0.551, "step": 2292 }, { "epoch": 0.63, "learning_rate": 6.212568239592827e-06, "loss": 0.5398, "step": 2293 }, { "epoch": 0.64, "learning_rate": 6.204267224154766e-06, "loss": 0.5451, "step": 2294 }, { "epoch": 0.64, "learning_rate": 6.1959692633780076e-06, "loss": 0.5346, "step": 2295 }, { "epoch": 0.64, "learning_rate": 6.187674363940432e-06, "loss": 0.5503, "step": 2296 }, { "epoch": 0.64, "learning_rate": 6.179382532517464e-06, "loss": 0.5334, "step": 2297 }, { "epoch": 0.64, "learning_rate": 6.17109377578204e-06, "loss": 0.55, "step": 2298 }, { "epoch": 0.64, "learning_rate": 6.162808100404648e-06, "loss": 0.5326, "step": 2299 }, { "epoch": 0.64, "learning_rate": 6.15452551305328e-06, "loss": 0.5459, "step": 2300 }, { "epoch": 0.64, "learning_rate": 6.1462460203934495e-06, "loss": 0.5438, "step": 2301 }, { "epoch": 0.64, "learning_rate": 6.137969629088174e-06, "loss": 0.5388, "step": 2302 }, { "epoch": 0.64, "learning_rate": 6.129696345797982e-06, "loss": 0.5422, "step": 2303 }, { "epoch": 0.64, "learning_rate": 6.121426177180894e-06, "loss": 0.538, "step": 2304 }, { "epoch": 0.64, "learning_rate": 6.113159129892427e-06, "loss": 0.539, "step": 2305 }, { "epoch": 0.64, "learning_rate": 6.104895210585586e-06, "loss": 0.533, "step": 2306 }, { "epoch": 0.64, "learning_rate": 6.096634425910859e-06, "loss": 0.5349, "step": 2307 }, { "epoch": 0.64, "learning_rate": 6.088376782516219e-06, "loss": 0.5298, "step": 2308 }, { "epoch": 0.64, "learning_rate": 6.08012228704709e-06, "loss": 0.5428, "step": 2309 }, { "epoch": 0.64, "learning_rate": 6.0718709461463805e-06, "loss": 0.5392, "step": 2310 }, { "epoch": 0.64, "learning_rate": 6.06362276645446e-06, "loss": 0.5228, "step": 2311 }, { "epoch": 0.64, "learning_rate": 6.055377754609146e-06, "loss": 0.5335, "step": 2312 }, { "epoch": 0.64, "learning_rate": 6.047135917245712e-06, "loss": 0.5425, "step": 2313 }, { "epoch": 0.64, "learning_rate": 6.038897260996875e-06, "loss": 0.5257, "step": 2314 }, { "epoch": 0.64, "learning_rate": 6.03066179249279e-06, "loss": 0.5281, "step": 2315 }, { "epoch": 0.64, "learning_rate": 6.02242951836105e-06, "loss": 0.5301, "step": 2316 }, { "epoch": 0.64, "learning_rate": 6.014200445226674e-06, "loss": 0.5477, "step": 2317 }, { "epoch": 0.64, "learning_rate": 6.005974579712111e-06, "loss": 0.5467, "step": 2318 }, { "epoch": 0.64, "learning_rate": 5.99775192843722e-06, "loss": 0.5468, "step": 2319 }, { "epoch": 0.64, "learning_rate": 5.989532498019286e-06, "loss": 0.5461, "step": 2320 }, { "epoch": 0.64, "learning_rate": 5.981316295072983e-06, "loss": 0.5363, "step": 2321 }, { "epoch": 0.64, "learning_rate": 5.973103326210403e-06, "loss": 0.5334, "step": 2322 }, { "epoch": 0.64, "learning_rate": 5.96489359804103e-06, "loss": 0.5563, "step": 2323 }, { "epoch": 0.64, "learning_rate": 5.956687117171746e-06, "loss": 0.5302, "step": 2324 }, { "epoch": 0.64, "learning_rate": 5.948483890206813e-06, "loss": 0.5457, "step": 2325 }, { "epoch": 0.64, "learning_rate": 5.940283923747867e-06, "loss": 0.5347, "step": 2326 }, { "epoch": 0.64, "learning_rate": 5.932087224393939e-06, "loss": 0.5392, "step": 2327 }, { "epoch": 0.64, "learning_rate": 5.9238937987414155e-06, "loss": 0.55, "step": 2328 }, { "epoch": 0.64, "learning_rate": 5.915703653384057e-06, "loss": 0.5257, "step": 2329 }, { "epoch": 0.65, "learning_rate": 5.907516794912977e-06, "loss": 0.5524, "step": 2330 }, { "epoch": 0.65, "learning_rate": 5.899333229916655e-06, "loss": 0.5406, "step": 2331 }, { "epoch": 0.65, "learning_rate": 5.8911529649809045e-06, "loss": 0.535, "step": 2332 }, { "epoch": 0.65, "learning_rate": 5.882976006688893e-06, "loss": 0.5344, "step": 2333 }, { "epoch": 0.65, "learning_rate": 5.874802361621128e-06, "loss": 0.5429, "step": 2334 }, { "epoch": 0.65, "learning_rate": 5.866632036355444e-06, "loss": 0.5374, "step": 2335 }, { "epoch": 0.65, "learning_rate": 5.858465037467014e-06, "loss": 0.5444, "step": 2336 }, { "epoch": 0.65, "learning_rate": 5.850301371528329e-06, "loss": 0.5389, "step": 2337 }, { "epoch": 0.65, "learning_rate": 5.842141045109188e-06, "loss": 0.5482, "step": 2338 }, { "epoch": 0.65, "learning_rate": 5.833984064776713e-06, "loss": 0.5412, "step": 2339 }, { "epoch": 0.65, "learning_rate": 5.8258304370953365e-06, "loss": 0.557, "step": 2340 }, { "epoch": 0.65, "learning_rate": 5.817680168626784e-06, "loss": 0.5367, "step": 2341 }, { "epoch": 0.65, "learning_rate": 5.8095332659300895e-06, "loss": 0.5378, "step": 2342 }, { "epoch": 0.65, "learning_rate": 5.801389735561558e-06, "loss": 0.5422, "step": 2343 }, { "epoch": 0.65, "learning_rate": 5.793249584074798e-06, "loss": 0.5456, "step": 2344 }, { "epoch": 0.65, "learning_rate": 5.785112818020691e-06, "loss": 0.5423, "step": 2345 }, { "epoch": 0.65, "learning_rate": 5.776979443947402e-06, "loss": 0.5326, "step": 2346 }, { "epoch": 0.65, "learning_rate": 5.7688494684003595e-06, "loss": 0.5379, "step": 2347 }, { "epoch": 0.65, "learning_rate": 5.7607228979222614e-06, "loss": 0.5429, "step": 2348 }, { "epoch": 0.65, "learning_rate": 5.752599739053055e-06, "loss": 0.5344, "step": 2349 }, { "epoch": 0.65, "learning_rate": 5.7444799983299535e-06, "loss": 0.5302, "step": 2350 }, { "epoch": 0.65, "learning_rate": 5.736363682287414e-06, "loss": 0.5508, "step": 2351 }, { "epoch": 0.65, "learning_rate": 5.72825079745714e-06, "loss": 0.5557, "step": 2352 }, { "epoch": 0.65, "learning_rate": 5.720141350368072e-06, "loss": 0.543, "step": 2353 }, { "epoch": 0.65, "learning_rate": 5.7120353475463855e-06, "loss": 0.55, "step": 2354 }, { "epoch": 0.65, "learning_rate": 5.70393279551548e-06, "loss": 0.5384, "step": 2355 }, { "epoch": 0.65, "learning_rate": 5.695833700795985e-06, "loss": 0.5286, "step": 2356 }, { "epoch": 0.65, "learning_rate": 5.6877380699057405e-06, "loss": 0.5456, "step": 2357 }, { "epoch": 0.65, "learning_rate": 5.6796459093598046e-06, "loss": 0.5436, "step": 2358 }, { "epoch": 0.65, "learning_rate": 5.671557225670439e-06, "loss": 0.5396, "step": 2359 }, { "epoch": 0.65, "learning_rate": 5.663472025347112e-06, "loss": 0.5522, "step": 2360 }, { "epoch": 0.65, "learning_rate": 5.655390314896474e-06, "loss": 0.5297, "step": 2361 }, { "epoch": 0.65, "learning_rate": 5.647312100822391e-06, "loss": 0.5363, "step": 2362 }, { "epoch": 0.65, "learning_rate": 5.639237389625896e-06, "loss": 0.5408, "step": 2363 }, { "epoch": 0.65, "learning_rate": 5.6311661878052105e-06, "loss": 0.5336, "step": 2364 }, { "epoch": 0.65, "learning_rate": 5.623098501855735e-06, "loss": 0.5341, "step": 2365 }, { "epoch": 0.66, "learning_rate": 5.615034338270028e-06, "loss": 0.5428, "step": 2366 }, { "epoch": 0.66, "learning_rate": 5.606973703537826e-06, "loss": 0.5472, "step": 2367 }, { "epoch": 0.66, "learning_rate": 5.598916604146019e-06, "loss": 0.5359, "step": 2368 }, { "epoch": 0.66, "learning_rate": 5.590863046578655e-06, "loss": 0.5457, "step": 2369 }, { "epoch": 0.66, "learning_rate": 5.5828130373169274e-06, "loss": 0.5398, "step": 2370 }, { "epoch": 0.66, "learning_rate": 5.574766582839189e-06, "loss": 0.535, "step": 2371 }, { "epoch": 0.66, "learning_rate": 5.5667236896209085e-06, "loss": 0.5515, "step": 2372 }, { "epoch": 0.66, "learning_rate": 5.558684364134703e-06, "loss": 0.5397, "step": 2373 }, { "epoch": 0.66, "learning_rate": 5.550648612850318e-06, "loss": 0.5477, "step": 2374 }, { "epoch": 0.66, "learning_rate": 5.542616442234618e-06, "loss": 0.5388, "step": 2375 }, { "epoch": 0.66, "learning_rate": 5.53458785875159e-06, "loss": 0.5215, "step": 2376 }, { "epoch": 0.66, "learning_rate": 5.5265628688623305e-06, "loss": 0.5422, "step": 2377 }, { "epoch": 0.66, "learning_rate": 5.518541479025048e-06, "loss": 0.5352, "step": 2378 }, { "epoch": 0.66, "learning_rate": 5.510523695695052e-06, "loss": 0.5546, "step": 2379 }, { "epoch": 0.66, "learning_rate": 5.5025095253247465e-06, "loss": 0.5448, "step": 2380 }, { "epoch": 0.66, "learning_rate": 5.494498974363633e-06, "loss": 0.5434, "step": 2381 }, { "epoch": 0.66, "learning_rate": 5.486492049258304e-06, "loss": 0.554, "step": 2382 }, { "epoch": 0.66, "learning_rate": 5.478488756452416e-06, "loss": 0.5227, "step": 2383 }, { "epoch": 0.66, "learning_rate": 5.470489102386722e-06, "loss": 0.5379, "step": 2384 }, { "epoch": 0.66, "learning_rate": 5.462493093499037e-06, "loss": 0.542, "step": 2385 }, { "epoch": 0.66, "learning_rate": 5.454500736224241e-06, "loss": 0.5346, "step": 2386 }, { "epoch": 0.66, "learning_rate": 5.446512036994287e-06, "loss": 0.5371, "step": 2387 }, { "epoch": 0.66, "learning_rate": 5.438527002238177e-06, "loss": 0.5274, "step": 2388 }, { "epoch": 0.66, "learning_rate": 5.430545638381956e-06, "loss": 0.5223, "step": 2389 }, { "epoch": 0.66, "learning_rate": 5.422567951848723e-06, "loss": 0.5521, "step": 2390 }, { "epoch": 0.66, "learning_rate": 5.414593949058619e-06, "loss": 0.5351, "step": 2391 }, { "epoch": 0.66, "learning_rate": 5.406623636428816e-06, "loss": 0.5435, "step": 2392 }, { "epoch": 0.66, "learning_rate": 5.398657020373521e-06, "loss": 0.5473, "step": 2393 }, { "epoch": 0.66, "learning_rate": 5.390694107303961e-06, "loss": 0.5284, "step": 2394 }, { "epoch": 0.66, "learning_rate": 5.382734903628386e-06, "loss": 0.5574, "step": 2395 }, { "epoch": 0.66, "learning_rate": 5.37477941575206e-06, "loss": 0.5555, "step": 2396 }, { "epoch": 0.66, "learning_rate": 5.36682765007726e-06, "loss": 0.541, "step": 2397 }, { "epoch": 0.66, "learning_rate": 5.35887961300326e-06, "loss": 0.5412, "step": 2398 }, { "epoch": 0.66, "learning_rate": 5.350935310926344e-06, "loss": 0.5536, "step": 2399 }, { "epoch": 0.66, "learning_rate": 5.342994750239776e-06, "loss": 0.5512, "step": 2400 }, { "epoch": 0.66, "learning_rate": 5.335057937333821e-06, "loss": 0.5536, "step": 2401 }, { "epoch": 0.67, "learning_rate": 5.32712487859572e-06, "loss": 0.5351, "step": 2402 }, { "epoch": 0.67, "learning_rate": 5.319195580409704e-06, "loss": 0.5507, "step": 2403 }, { "epoch": 0.67, "learning_rate": 5.311270049156967e-06, "loss": 0.5369, "step": 2404 }, { "epoch": 0.67, "learning_rate": 5.303348291215679e-06, "loss": 0.54, "step": 2405 }, { "epoch": 0.67, "learning_rate": 5.2954303129609606e-06, "loss": 0.5405, "step": 2406 }, { "epoch": 0.67, "learning_rate": 5.287516120764906e-06, "loss": 0.5278, "step": 2407 }, { "epoch": 0.67, "learning_rate": 5.279605720996553e-06, "loss": 0.5367, "step": 2408 }, { "epoch": 0.67, "learning_rate": 5.271699120021892e-06, "loss": 0.5383, "step": 2409 }, { "epoch": 0.67, "learning_rate": 5.263796324203854e-06, "loss": 0.5427, "step": 2410 }, { "epoch": 0.67, "learning_rate": 5.2558973399023075e-06, "loss": 0.5353, "step": 2411 }, { "epoch": 0.67, "learning_rate": 5.248002173474055e-06, "loss": 0.5334, "step": 2412 }, { "epoch": 0.67, "learning_rate": 5.240110831272827e-06, "loss": 0.534, "step": 2413 }, { "epoch": 0.67, "learning_rate": 5.2322233196492745e-06, "loss": 0.5432, "step": 2414 }, { "epoch": 0.67, "learning_rate": 5.2243396449509685e-06, "loss": 0.5208, "step": 2415 }, { "epoch": 0.67, "learning_rate": 5.216459813522388e-06, "loss": 0.5336, "step": 2416 }, { "epoch": 0.67, "learning_rate": 5.208583831704925e-06, "loss": 0.5357, "step": 2417 }, { "epoch": 0.67, "learning_rate": 5.2007117058368605e-06, "loss": 0.534, "step": 2418 }, { "epoch": 0.67, "learning_rate": 5.192843442253393e-06, "loss": 0.539, "step": 2419 }, { "epoch": 0.67, "learning_rate": 5.1849790472865955e-06, "loss": 0.5378, "step": 2420 }, { "epoch": 0.67, "learning_rate": 5.177118527265438e-06, "loss": 0.5521, "step": 2421 }, { "epoch": 0.67, "learning_rate": 5.169261888515769e-06, "loss": 0.5348, "step": 2422 }, { "epoch": 0.67, "learning_rate": 5.161409137360304e-06, "loss": 0.541, "step": 2423 }, { "epoch": 0.67, "learning_rate": 5.153560280118644e-06, "loss": 0.5325, "step": 2424 }, { "epoch": 0.67, "learning_rate": 5.145715323107247e-06, "loss": 0.548, "step": 2425 }, { "epoch": 0.67, "learning_rate": 5.137874272639442e-06, "loss": 0.5412, "step": 2426 }, { "epoch": 0.67, "learning_rate": 5.1300371350254005e-06, "loss": 0.5322, "step": 2427 }, { "epoch": 0.67, "learning_rate": 5.122203916572164e-06, "loss": 0.538, "step": 2428 }, { "epoch": 0.67, "learning_rate": 5.114374623583598e-06, "loss": 0.5469, "step": 2429 }, { "epoch": 0.67, "learning_rate": 5.106549262360423e-06, "loss": 0.528, "step": 2430 }, { "epoch": 0.67, "learning_rate": 5.098727839200192e-06, "loss": 0.547, "step": 2431 }, { "epoch": 0.67, "learning_rate": 5.090910360397287e-06, "loss": 0.5387, "step": 2432 }, { "epoch": 0.67, "learning_rate": 5.083096832242922e-06, "loss": 0.5335, "step": 2433 }, { "epoch": 0.67, "learning_rate": 5.075287261025124e-06, "loss": 0.5498, "step": 2434 }, { "epoch": 0.67, "learning_rate": 5.067481653028738e-06, "loss": 0.5496, "step": 2435 }, { "epoch": 0.67, "learning_rate": 5.059680014535421e-06, "loss": 0.5392, "step": 2436 }, { "epoch": 0.67, "learning_rate": 5.051882351823636e-06, "loss": 0.5348, "step": 2437 }, { "epoch": 0.68, "learning_rate": 5.044088671168644e-06, "loss": 0.541, "step": 2438 }, { "epoch": 0.68, "learning_rate": 5.036298978842506e-06, "loss": 0.5501, "step": 2439 }, { "epoch": 0.68, "learning_rate": 5.0285132811140644e-06, "loss": 0.553, "step": 2440 }, { "epoch": 0.68, "learning_rate": 5.020731584248956e-06, "loss": 0.5396, "step": 2441 }, { "epoch": 0.68, "learning_rate": 5.012953894509591e-06, "loss": 0.5392, "step": 2442 }, { "epoch": 0.68, "learning_rate": 5.005180218155159e-06, "loss": 0.5387, "step": 2443 }, { "epoch": 0.68, "learning_rate": 4.997410561441624e-06, "loss": 0.5407, "step": 2444 }, { "epoch": 0.68, "learning_rate": 4.989644930621708e-06, "loss": 0.5482, "step": 2445 }, { "epoch": 0.68, "learning_rate": 4.981883331944893e-06, "loss": 0.5253, "step": 2446 }, { "epoch": 0.68, "learning_rate": 4.974125771657416e-06, "loss": 0.5404, "step": 2447 }, { "epoch": 0.68, "learning_rate": 4.966372256002271e-06, "loss": 0.5392, "step": 2448 }, { "epoch": 0.68, "learning_rate": 4.95862279121919e-06, "loss": 0.5415, "step": 2449 }, { "epoch": 0.68, "learning_rate": 4.950877383544647e-06, "loss": 0.5365, "step": 2450 }, { "epoch": 0.68, "learning_rate": 4.943136039211854e-06, "loss": 0.5338, "step": 2451 }, { "epoch": 0.68, "learning_rate": 4.935398764450748e-06, "loss": 0.541, "step": 2452 }, { "epoch": 0.68, "learning_rate": 4.927665565487995e-06, "loss": 0.5303, "step": 2453 }, { "epoch": 0.68, "learning_rate": 4.919936448546977e-06, "loss": 0.5313, "step": 2454 }, { "epoch": 0.68, "learning_rate": 4.912211419847795e-06, "loss": 0.5517, "step": 2455 }, { "epoch": 0.68, "learning_rate": 4.904490485607257e-06, "loss": 0.5383, "step": 2456 }, { "epoch": 0.68, "learning_rate": 4.896773652038882e-06, "loss": 0.5377, "step": 2457 }, { "epoch": 0.68, "learning_rate": 4.8890609253528756e-06, "loss": 0.5492, "step": 2458 }, { "epoch": 0.68, "learning_rate": 4.881352311756147e-06, "loss": 0.5136, "step": 2459 }, { "epoch": 0.68, "learning_rate": 4.873647817452302e-06, "loss": 0.5446, "step": 2460 }, { "epoch": 0.68, "learning_rate": 4.865947448641624e-06, "loss": 0.5416, "step": 2461 }, { "epoch": 0.68, "learning_rate": 4.858251211521076e-06, "loss": 0.5491, "step": 2462 }, { "epoch": 0.68, "learning_rate": 4.85055911228429e-06, "loss": 0.5306, "step": 2463 }, { "epoch": 0.68, "learning_rate": 4.8428711571215815e-06, "loss": 0.535, "step": 2464 }, { "epoch": 0.68, "learning_rate": 4.835187352219921e-06, "loss": 0.5479, "step": 2465 }, { "epoch": 0.68, "learning_rate": 4.827507703762945e-06, "loss": 0.5374, "step": 2466 }, { "epoch": 0.68, "learning_rate": 4.8198322179309395e-06, "loss": 0.5458, "step": 2467 }, { "epoch": 0.68, "learning_rate": 4.812160900900846e-06, "loss": 0.5261, "step": 2468 }, { "epoch": 0.68, "learning_rate": 4.8044937588462485e-06, "loss": 0.5508, "step": 2469 }, { "epoch": 0.68, "learning_rate": 4.796830797937368e-06, "loss": 0.5339, "step": 2470 }, { "epoch": 0.68, "learning_rate": 4.789172024341068e-06, "loss": 0.5514, "step": 2471 }, { "epoch": 0.68, "learning_rate": 4.781517444220836e-06, "loss": 0.5351, "step": 2472 }, { "epoch": 0.68, "learning_rate": 4.7738670637367855e-06, "loss": 0.5383, "step": 2473 }, { "epoch": 0.69, "learning_rate": 4.766220889045658e-06, "loss": 0.5349, "step": 2474 }, { "epoch": 0.69, "learning_rate": 4.758578926300791e-06, "loss": 0.5494, "step": 2475 }, { "epoch": 0.69, "learning_rate": 4.750941181652157e-06, "loss": 0.5337, "step": 2476 }, { "epoch": 0.69, "learning_rate": 4.743307661246318e-06, "loss": 0.5334, "step": 2477 }, { "epoch": 0.69, "learning_rate": 4.7356783712264405e-06, "loss": 0.5461, "step": 2478 }, { "epoch": 0.69, "learning_rate": 4.728053317732293e-06, "loss": 0.5444, "step": 2479 }, { "epoch": 0.69, "learning_rate": 4.720432506900219e-06, "loss": 0.5391, "step": 2480 }, { "epoch": 0.69, "learning_rate": 4.712815944863161e-06, "loss": 0.5289, "step": 2481 }, { "epoch": 0.69, "learning_rate": 4.705203637750637e-06, "loss": 0.5336, "step": 2482 }, { "epoch": 0.69, "learning_rate": 4.697595591688744e-06, "loss": 0.5474, "step": 2483 }, { "epoch": 0.69, "learning_rate": 4.689991812800144e-06, "loss": 0.5421, "step": 2484 }, { "epoch": 0.69, "learning_rate": 4.682392307204079e-06, "loss": 0.533, "step": 2485 }, { "epoch": 0.69, "learning_rate": 4.674797081016332e-06, "loss": 0.541, "step": 2486 }, { "epoch": 0.69, "learning_rate": 4.667206140349255e-06, "loss": 0.5434, "step": 2487 }, { "epoch": 0.69, "learning_rate": 4.659619491311749e-06, "loss": 0.5329, "step": 2488 }, { "epoch": 0.69, "learning_rate": 4.652037140009259e-06, "loss": 0.531, "step": 2489 }, { "epoch": 0.69, "learning_rate": 4.6444590925437736e-06, "loss": 0.5424, "step": 2490 }, { "epoch": 0.69, "learning_rate": 4.6368853550138184e-06, "loss": 0.5538, "step": 2491 }, { "epoch": 0.69, "learning_rate": 4.629315933514446e-06, "loss": 0.5671, "step": 2492 }, { "epoch": 0.69, "learning_rate": 4.621750834137242e-06, "loss": 0.5414, "step": 2493 }, { "epoch": 0.69, "learning_rate": 4.614190062970309e-06, "loss": 0.5299, "step": 2494 }, { "epoch": 0.69, "learning_rate": 4.606633626098267e-06, "loss": 0.5395, "step": 2495 }, { "epoch": 0.69, "learning_rate": 4.599081529602254e-06, "loss": 0.5462, "step": 2496 }, { "epoch": 0.69, "learning_rate": 4.591533779559902e-06, "loss": 0.5409, "step": 2497 }, { "epoch": 0.69, "learning_rate": 4.583990382045357e-06, "loss": 0.539, "step": 2498 }, { "epoch": 0.69, "learning_rate": 4.576451343129258e-06, "loss": 0.5415, "step": 2499 }, { "epoch": 0.69, "learning_rate": 4.5689166688787335e-06, "loss": 0.5408, "step": 2500 }, { "epoch": 0.69, "learning_rate": 4.5613863653574086e-06, "loss": 0.5521, "step": 2501 }, { "epoch": 0.69, "learning_rate": 4.553860438625387e-06, "loss": 0.5342, "step": 2502 }, { "epoch": 0.69, "learning_rate": 4.5463388947392385e-06, "loss": 0.5441, "step": 2503 }, { "epoch": 0.69, "learning_rate": 4.538821739752022e-06, "loss": 0.5334, "step": 2504 }, { "epoch": 0.69, "learning_rate": 4.531308979713255e-06, "loss": 0.5355, "step": 2505 }, { "epoch": 0.69, "learning_rate": 4.523800620668921e-06, "loss": 0.5424, "step": 2506 }, { "epoch": 0.69, "learning_rate": 4.516296668661464e-06, "loss": 0.5247, "step": 2507 }, { "epoch": 0.69, "learning_rate": 4.508797129729777e-06, "loss": 0.5338, "step": 2508 }, { "epoch": 0.69, "learning_rate": 4.5013020099092056e-06, "loss": 0.534, "step": 2509 }, { "epoch": 0.7, "learning_rate": 4.493811315231534e-06, "loss": 0.5437, "step": 2510 }, { "epoch": 0.7, "learning_rate": 4.48632505172499e-06, "loss": 0.5235, "step": 2511 }, { "epoch": 0.7, "learning_rate": 4.4788432254142345e-06, "loss": 0.5364, "step": 2512 }, { "epoch": 0.7, "learning_rate": 4.471365842320354e-06, "loss": 0.5429, "step": 2513 }, { "epoch": 0.7, "learning_rate": 4.463892908460869e-06, "loss": 0.5385, "step": 2514 }, { "epoch": 0.7, "learning_rate": 4.456424429849702e-06, "loss": 0.5212, "step": 2515 }, { "epoch": 0.7, "learning_rate": 4.448960412497201e-06, "loss": 0.5341, "step": 2516 }, { "epoch": 0.7, "learning_rate": 4.441500862410132e-06, "loss": 0.5418, "step": 2517 }, { "epoch": 0.7, "learning_rate": 4.434045785591652e-06, "loss": 0.5531, "step": 2518 }, { "epoch": 0.7, "learning_rate": 4.426595188041327e-06, "loss": 0.5254, "step": 2519 }, { "epoch": 0.7, "learning_rate": 4.419149075755107e-06, "loss": 0.5238, "step": 2520 }, { "epoch": 0.7, "learning_rate": 4.411707454725344e-06, "loss": 0.5429, "step": 2521 }, { "epoch": 0.7, "learning_rate": 4.404270330940771e-06, "loss": 0.5512, "step": 2522 }, { "epoch": 0.7, "learning_rate": 4.396837710386503e-06, "loss": 0.5299, "step": 2523 }, { "epoch": 0.7, "learning_rate": 4.3894095990440276e-06, "loss": 0.5323, "step": 2524 }, { "epoch": 0.7, "learning_rate": 4.3819860028912095e-06, "loss": 0.5444, "step": 2525 }, { "epoch": 0.7, "learning_rate": 4.374566927902275e-06, "loss": 0.5352, "step": 2526 }, { "epoch": 0.7, "learning_rate": 4.367152380047813e-06, "loss": 0.5368, "step": 2527 }, { "epoch": 0.7, "learning_rate": 4.35974236529477e-06, "loss": 0.5382, "step": 2528 }, { "epoch": 0.7, "learning_rate": 4.352336889606444e-06, "loss": 0.5414, "step": 2529 }, { "epoch": 0.7, "learning_rate": 4.344935958942479e-06, "loss": 0.5388, "step": 2530 }, { "epoch": 0.7, "learning_rate": 4.337539579258867e-06, "loss": 0.5339, "step": 2531 }, { "epoch": 0.7, "learning_rate": 4.330147756507922e-06, "loss": 0.5409, "step": 2532 }, { "epoch": 0.7, "learning_rate": 4.3227604966383115e-06, "loss": 0.5315, "step": 2533 }, { "epoch": 0.7, "learning_rate": 4.315377805595019e-06, "loss": 0.5401, "step": 2534 }, { "epoch": 0.7, "learning_rate": 4.3079996893193536e-06, "loss": 0.5372, "step": 2535 }, { "epoch": 0.7, "learning_rate": 4.300626153748943e-06, "loss": 0.5491, "step": 2536 }, { "epoch": 0.7, "learning_rate": 4.293257204817724e-06, "loss": 0.5237, "step": 2537 }, { "epoch": 0.7, "learning_rate": 4.28589284845595e-06, "loss": 0.5396, "step": 2538 }, { "epoch": 0.7, "learning_rate": 4.278533090590172e-06, "loss": 0.5415, "step": 2539 }, { "epoch": 0.7, "learning_rate": 4.271177937143245e-06, "loss": 0.5534, "step": 2540 }, { "epoch": 0.7, "learning_rate": 4.263827394034313e-06, "loss": 0.5394, "step": 2541 }, { "epoch": 0.7, "learning_rate": 4.2564814671788235e-06, "loss": 0.5361, "step": 2542 }, { "epoch": 0.7, "learning_rate": 4.24914016248849e-06, "loss": 0.5368, "step": 2543 }, { "epoch": 0.7, "learning_rate": 4.241803485871315e-06, "loss": 0.5389, "step": 2544 }, { "epoch": 0.7, "learning_rate": 4.23447144323158e-06, "loss": 0.5391, "step": 2545 }, { "epoch": 0.7, "learning_rate": 4.227144040469834e-06, "loss": 0.5378, "step": 2546 }, { "epoch": 0.71, "learning_rate": 4.219821283482889e-06, "loss": 0.5461, "step": 2547 }, { "epoch": 0.71, "learning_rate": 4.212503178163824e-06, "loss": 0.5387, "step": 2548 }, { "epoch": 0.71, "learning_rate": 4.2051897304019694e-06, "loss": 0.5308, "step": 2549 }, { "epoch": 0.71, "learning_rate": 4.197880946082912e-06, "loss": 0.5213, "step": 2550 }, { "epoch": 0.71, "learning_rate": 4.190576831088482e-06, "loss": 0.5454, "step": 2551 }, { "epoch": 0.71, "learning_rate": 4.183277391296753e-06, "loss": 0.5494, "step": 2552 }, { "epoch": 0.71, "learning_rate": 4.17598263258204e-06, "loss": 0.5347, "step": 2553 }, { "epoch": 0.71, "learning_rate": 4.168692560814882e-06, "loss": 0.5345, "step": 2554 }, { "epoch": 0.71, "learning_rate": 4.161407181862052e-06, "loss": 0.5336, "step": 2555 }, { "epoch": 0.71, "learning_rate": 4.1541265015865475e-06, "loss": 0.548, "step": 2556 }, { "epoch": 0.71, "learning_rate": 4.1468505258475785e-06, "loss": 0.5206, "step": 2557 }, { "epoch": 0.71, "learning_rate": 4.139579260500581e-06, "loss": 0.5454, "step": 2558 }, { "epoch": 0.71, "learning_rate": 4.132312711397193e-06, "loss": 0.5228, "step": 2559 }, { "epoch": 0.71, "learning_rate": 4.12505088438525e-06, "loss": 0.5383, "step": 2560 }, { "epoch": 0.71, "learning_rate": 4.117793785308796e-06, "loss": 0.5358, "step": 2561 }, { "epoch": 0.71, "learning_rate": 4.110541420008069e-06, "loss": 0.5429, "step": 2562 }, { "epoch": 0.71, "learning_rate": 4.103293794319496e-06, "loss": 0.5313, "step": 2563 }, { "epoch": 0.71, "learning_rate": 4.096050914075692e-06, "loss": 0.5329, "step": 2564 }, { "epoch": 0.71, "learning_rate": 4.0888127851054495e-06, "loss": 0.5318, "step": 2565 }, { "epoch": 0.71, "learning_rate": 4.081579413233742e-06, "loss": 0.5339, "step": 2566 }, { "epoch": 0.71, "learning_rate": 4.074350804281708e-06, "loss": 0.5288, "step": 2567 }, { "epoch": 0.71, "learning_rate": 4.06712696406666e-06, "loss": 0.541, "step": 2568 }, { "epoch": 0.71, "learning_rate": 4.059907898402068e-06, "loss": 0.5303, "step": 2569 }, { "epoch": 0.71, "learning_rate": 4.0526936130975636e-06, "loss": 0.5382, "step": 2570 }, { "epoch": 0.71, "learning_rate": 4.045484113958929e-06, "loss": 0.5532, "step": 2571 }, { "epoch": 0.71, "learning_rate": 4.038279406788091e-06, "loss": 0.5203, "step": 2572 }, { "epoch": 0.71, "learning_rate": 4.031079497383124e-06, "loss": 0.546, "step": 2573 }, { "epoch": 0.71, "learning_rate": 4.023884391538244e-06, "loss": 0.5366, "step": 2574 }, { "epoch": 0.71, "learning_rate": 4.0166940950437995e-06, "loss": 0.5323, "step": 2575 }, { "epoch": 0.71, "learning_rate": 4.009508613686268e-06, "loss": 0.5307, "step": 2576 }, { "epoch": 0.71, "learning_rate": 4.0023279532482466e-06, "loss": 0.5469, "step": 2577 }, { "epoch": 0.71, "learning_rate": 3.995152119508459e-06, "loss": 0.5388, "step": 2578 }, { "epoch": 0.71, "learning_rate": 3.987981118241745e-06, "loss": 0.5387, "step": 2579 }, { "epoch": 0.71, "learning_rate": 3.980814955219053e-06, "loss": 0.5338, "step": 2580 }, { "epoch": 0.71, "learning_rate": 3.973653636207437e-06, "loss": 0.5382, "step": 2581 }, { "epoch": 0.71, "learning_rate": 3.966497166970056e-06, "loss": 0.5367, "step": 2582 }, { "epoch": 0.72, "learning_rate": 3.959345553266163e-06, "loss": 0.5479, "step": 2583 }, { "epoch": 0.72, "learning_rate": 3.9521988008511046e-06, "loss": 0.5255, "step": 2584 }, { "epoch": 0.72, "learning_rate": 3.945056915476315e-06, "loss": 0.5392, "step": 2585 }, { "epoch": 0.72, "learning_rate": 3.937919902889312e-06, "loss": 0.5336, "step": 2586 }, { "epoch": 0.72, "learning_rate": 3.930787768833692e-06, "loss": 0.5256, "step": 2587 }, { "epoch": 0.72, "learning_rate": 3.9236605190491294e-06, "loss": 0.5455, "step": 2588 }, { "epoch": 0.72, "learning_rate": 3.916538159271353e-06, "loss": 0.5195, "step": 2589 }, { "epoch": 0.72, "learning_rate": 3.909420695232175e-06, "loss": 0.5407, "step": 2590 }, { "epoch": 0.72, "learning_rate": 3.902308132659457e-06, "loss": 0.5376, "step": 2591 }, { "epoch": 0.72, "learning_rate": 3.8952004772771216e-06, "loss": 0.5317, "step": 2592 }, { "epoch": 0.72, "learning_rate": 3.888097734805138e-06, "loss": 0.5292, "step": 2593 }, { "epoch": 0.72, "learning_rate": 3.880999910959521e-06, "loss": 0.5446, "step": 2594 }, { "epoch": 0.72, "learning_rate": 3.8739070114523296e-06, "loss": 0.5416, "step": 2595 }, { "epoch": 0.72, "learning_rate": 3.86681904199166e-06, "loss": 0.5355, "step": 2596 }, { "epoch": 0.72, "learning_rate": 3.859736008281642e-06, "loss": 0.5394, "step": 2597 }, { "epoch": 0.72, "learning_rate": 3.852657916022424e-06, "loss": 0.5336, "step": 2598 }, { "epoch": 0.72, "learning_rate": 3.845584770910201e-06, "loss": 0.5351, "step": 2599 }, { "epoch": 0.72, "learning_rate": 3.838516578637157e-06, "loss": 0.5357, "step": 2600 }, { "epoch": 0.72, "learning_rate": 3.831453344891508e-06, "loss": 0.5421, "step": 2601 }, { "epoch": 0.72, "learning_rate": 3.824395075357478e-06, "loss": 0.5339, "step": 2602 }, { "epoch": 0.72, "learning_rate": 3.817341775715291e-06, "loss": 0.5427, "step": 2603 }, { "epoch": 0.72, "learning_rate": 3.810293451641175e-06, "loss": 0.5348, "step": 2604 }, { "epoch": 0.72, "learning_rate": 3.8032501088073536e-06, "loss": 0.53, "step": 2605 }, { "epoch": 0.72, "learning_rate": 3.796211752882041e-06, "loss": 0.5432, "step": 2606 }, { "epoch": 0.72, "learning_rate": 3.7891783895294374e-06, "loss": 0.5327, "step": 2607 }, { "epoch": 0.72, "learning_rate": 3.7821500244097276e-06, "loss": 0.5394, "step": 2608 }, { "epoch": 0.72, "learning_rate": 3.7751266631790707e-06, "loss": 0.5362, "step": 2609 }, { "epoch": 0.72, "learning_rate": 3.768108311489602e-06, "loss": 0.5426, "step": 2610 }, { "epoch": 0.72, "learning_rate": 3.7610949749894256e-06, "loss": 0.535, "step": 2611 }, { "epoch": 0.72, "learning_rate": 3.754086659322602e-06, "loss": 0.5412, "step": 2612 }, { "epoch": 0.72, "learning_rate": 3.7470833701291608e-06, "loss": 0.5444, "step": 2613 }, { "epoch": 0.72, "learning_rate": 3.7400851130450788e-06, "loss": 0.534, "step": 2614 }, { "epoch": 0.72, "learning_rate": 3.733091893702294e-06, "loss": 0.5372, "step": 2615 }, { "epoch": 0.72, "learning_rate": 3.726103717728683e-06, "loss": 0.5494, "step": 2616 }, { "epoch": 0.72, "learning_rate": 3.7191205907480563e-06, "loss": 0.5471, "step": 2617 }, { "epoch": 0.72, "learning_rate": 3.712142518380174e-06, "loss": 0.5417, "step": 2618 }, { "epoch": 0.73, "learning_rate": 3.705169506240721e-06, "loss": 0.5293, "step": 2619 }, { "epoch": 0.73, "learning_rate": 3.6982015599413148e-06, "loss": 0.5214, "step": 2620 }, { "epoch": 0.73, "learning_rate": 3.69123868508949e-06, "loss": 0.5494, "step": 2621 }, { "epoch": 0.73, "learning_rate": 3.684280887288707e-06, "loss": 0.5365, "step": 2622 }, { "epoch": 0.73, "learning_rate": 3.6773281721383337e-06, "loss": 0.542, "step": 2623 }, { "epoch": 0.73, "learning_rate": 3.670380545233653e-06, "loss": 0.5406, "step": 2624 }, { "epoch": 0.73, "learning_rate": 3.6634380121658484e-06, "loss": 0.5437, "step": 2625 }, { "epoch": 0.73, "learning_rate": 3.656500578522009e-06, "loss": 0.5399, "step": 2626 }, { "epoch": 0.73, "learning_rate": 3.649568249885115e-06, "loss": 0.5533, "step": 2627 }, { "epoch": 0.73, "learning_rate": 3.6426410318340445e-06, "loss": 0.5293, "step": 2628 }, { "epoch": 0.73, "learning_rate": 3.6357189299435538e-06, "loss": 0.5552, "step": 2629 }, { "epoch": 0.73, "learning_rate": 3.6288019497842852e-06, "loss": 0.5353, "step": 2630 }, { "epoch": 0.73, "learning_rate": 3.6218900969227688e-06, "loss": 0.5517, "step": 2631 }, { "epoch": 0.73, "learning_rate": 3.6149833769213973e-06, "loss": 0.5278, "step": 2632 }, { "epoch": 0.73, "learning_rate": 3.6080817953384404e-06, "loss": 0.526, "step": 2633 }, { "epoch": 0.73, "learning_rate": 3.60118535772802e-06, "loss": 0.531, "step": 2634 }, { "epoch": 0.73, "learning_rate": 3.5942940696401308e-06, "loss": 0.5474, "step": 2635 }, { "epoch": 0.73, "learning_rate": 3.5874079366206195e-06, "loss": 0.5432, "step": 2636 }, { "epoch": 0.73, "learning_rate": 3.580526964211183e-06, "loss": 0.536, "step": 2637 }, { "epoch": 0.73, "learning_rate": 3.573651157949366e-06, "loss": 0.5382, "step": 2638 }, { "epoch": 0.73, "learning_rate": 3.5667805233685572e-06, "loss": 0.5351, "step": 2639 }, { "epoch": 0.73, "learning_rate": 3.559915065997981e-06, "loss": 0.5339, "step": 2640 }, { "epoch": 0.73, "learning_rate": 3.553054791362697e-06, "loss": 0.5261, "step": 2641 }, { "epoch": 0.73, "learning_rate": 3.546199704983592e-06, "loss": 0.5439, "step": 2642 }, { "epoch": 0.73, "learning_rate": 3.5393498123773786e-06, "loss": 0.5421, "step": 2643 }, { "epoch": 0.73, "learning_rate": 3.5325051190565895e-06, "loss": 0.5451, "step": 2644 }, { "epoch": 0.73, "learning_rate": 3.525665630529579e-06, "loss": 0.5261, "step": 2645 }, { "epoch": 0.73, "learning_rate": 3.5188313523004946e-06, "loss": 0.5306, "step": 2646 }, { "epoch": 0.73, "learning_rate": 3.512002289869315e-06, "loss": 0.5487, "step": 2647 }, { "epoch": 0.73, "learning_rate": 3.505178448731805e-06, "loss": 0.5358, "step": 2648 }, { "epoch": 0.73, "learning_rate": 3.4983598343795343e-06, "loss": 0.5277, "step": 2649 }, { "epoch": 0.73, "learning_rate": 3.4915464522998656e-06, "loss": 0.5234, "step": 2650 }, { "epoch": 0.73, "learning_rate": 3.4847383079759446e-06, "loss": 0.5407, "step": 2651 }, { "epoch": 0.73, "learning_rate": 3.477935406886709e-06, "loss": 0.5299, "step": 2652 }, { "epoch": 0.73, "learning_rate": 3.4711377545068747e-06, "loss": 0.5419, "step": 2653 }, { "epoch": 0.73, "learning_rate": 3.4643453563069328e-06, "loss": 0.5282, "step": 2654 }, { "epoch": 0.74, "learning_rate": 3.4575582177531462e-06, "loss": 0.5363, "step": 2655 }, { "epoch": 0.74, "learning_rate": 3.4507763443075537e-06, "loss": 0.5337, "step": 2656 }, { "epoch": 0.74, "learning_rate": 3.4439997414279403e-06, "loss": 0.5268, "step": 2657 }, { "epoch": 0.74, "learning_rate": 3.437228414567859e-06, "loss": 0.5346, "step": 2658 }, { "epoch": 0.74, "learning_rate": 3.4304623691766193e-06, "loss": 0.5283, "step": 2659 }, { "epoch": 0.74, "learning_rate": 3.423701610699275e-06, "loss": 0.5432, "step": 2660 }, { "epoch": 0.74, "learning_rate": 3.4169461445766274e-06, "loss": 0.5442, "step": 2661 }, { "epoch": 0.74, "learning_rate": 3.4101959762452188e-06, "loss": 0.5348, "step": 2662 }, { "epoch": 0.74, "learning_rate": 3.403451111137328e-06, "loss": 0.5254, "step": 2663 }, { "epoch": 0.74, "learning_rate": 3.3967115546809647e-06, "loss": 0.544, "step": 2664 }, { "epoch": 0.74, "learning_rate": 3.3899773122998704e-06, "loss": 0.5349, "step": 2665 }, { "epoch": 0.74, "learning_rate": 3.383248389413504e-06, "loss": 0.5363, "step": 2666 }, { "epoch": 0.74, "learning_rate": 3.376524791437047e-06, "loss": 0.5192, "step": 2667 }, { "epoch": 0.74, "learning_rate": 3.3698065237814006e-06, "loss": 0.5393, "step": 2668 }, { "epoch": 0.74, "learning_rate": 3.3630935918531614e-06, "loss": 0.5364, "step": 2669 }, { "epoch": 0.74, "learning_rate": 3.3563860010546477e-06, "loss": 0.5349, "step": 2670 }, { "epoch": 0.74, "learning_rate": 3.349683756783868e-06, "loss": 0.5383, "step": 2671 }, { "epoch": 0.74, "learning_rate": 3.342986864434542e-06, "loss": 0.5326, "step": 2672 }, { "epoch": 0.74, "learning_rate": 3.3362953293960722e-06, "loss": 0.5397, "step": 2673 }, { "epoch": 0.74, "learning_rate": 3.329609157053544e-06, "loss": 0.548, "step": 2674 }, { "epoch": 0.74, "learning_rate": 3.3229283527877397e-06, "loss": 0.5464, "step": 2675 }, { "epoch": 0.74, "learning_rate": 3.316252921975116e-06, "loss": 0.524, "step": 2676 }, { "epoch": 0.74, "learning_rate": 3.3095828699878052e-06, "loss": 0.5508, "step": 2677 }, { "epoch": 0.74, "learning_rate": 3.3029182021936113e-06, "loss": 0.5404, "step": 2678 }, { "epoch": 0.74, "learning_rate": 3.296258923956005e-06, "loss": 0.5363, "step": 2679 }, { "epoch": 0.74, "learning_rate": 3.2896050406341205e-06, "loss": 0.5333, "step": 2680 }, { "epoch": 0.74, "learning_rate": 3.2829565575827506e-06, "loss": 0.5321, "step": 2681 }, { "epoch": 0.74, "learning_rate": 3.2763134801523398e-06, "loss": 0.5436, "step": 2682 }, { "epoch": 0.74, "learning_rate": 3.269675813688985e-06, "loss": 0.535, "step": 2683 }, { "epoch": 0.74, "learning_rate": 3.2630435635344283e-06, "loss": 0.5369, "step": 2684 }, { "epoch": 0.74, "learning_rate": 3.2564167350260536e-06, "loss": 0.5349, "step": 2685 }, { "epoch": 0.74, "learning_rate": 3.2497953334968756e-06, "loss": 0.5415, "step": 2686 }, { "epoch": 0.74, "learning_rate": 3.2431793642755447e-06, "loss": 0.5252, "step": 2687 }, { "epoch": 0.74, "learning_rate": 3.2365688326863496e-06, "loss": 0.5507, "step": 2688 }, { "epoch": 0.74, "learning_rate": 3.2299637440491904e-06, "loss": 0.5194, "step": 2689 }, { "epoch": 0.74, "learning_rate": 3.223364103679594e-06, "loss": 0.5381, "step": 2690 }, { "epoch": 0.75, "learning_rate": 3.216769916888692e-06, "loss": 0.5391, "step": 2691 }, { "epoch": 0.75, "learning_rate": 3.2101811889832423e-06, "loss": 0.5332, "step": 2692 }, { "epoch": 0.75, "learning_rate": 3.203597925265598e-06, "loss": 0.5488, "step": 2693 }, { "epoch": 0.75, "learning_rate": 3.1970201310337224e-06, "loss": 0.5339, "step": 2694 }, { "epoch": 0.75, "learning_rate": 3.190447811581172e-06, "loss": 0.526, "step": 2695 }, { "epoch": 0.75, "learning_rate": 3.183880972197101e-06, "loss": 0.5296, "step": 2696 }, { "epoch": 0.75, "learning_rate": 3.1773196181662504e-06, "loss": 0.5454, "step": 2697 }, { "epoch": 0.75, "learning_rate": 3.1707637547689486e-06, "loss": 0.5354, "step": 2698 }, { "epoch": 0.75, "learning_rate": 3.1642133872811053e-06, "loss": 0.5405, "step": 2699 }, { "epoch": 0.75, "learning_rate": 3.1576685209742065e-06, "loss": 0.5361, "step": 2700 }, { "epoch": 0.75, "learning_rate": 3.151129161115313e-06, "loss": 0.5508, "step": 2701 }, { "epoch": 0.75, "learning_rate": 3.144595312967055e-06, "loss": 0.5361, "step": 2702 }, { "epoch": 0.75, "learning_rate": 3.138066981787614e-06, "loss": 0.5214, "step": 2703 }, { "epoch": 0.75, "learning_rate": 3.131544172830754e-06, "loss": 0.5479, "step": 2704 }, { "epoch": 0.75, "learning_rate": 3.125026891345779e-06, "loss": 0.5444, "step": 2705 }, { "epoch": 0.75, "learning_rate": 3.1185151425775506e-06, "loss": 0.5243, "step": 2706 }, { "epoch": 0.75, "learning_rate": 3.112008931766479e-06, "loss": 0.5403, "step": 2707 }, { "epoch": 0.75, "learning_rate": 3.105508264148508e-06, "loss": 0.5455, "step": 2708 }, { "epoch": 0.75, "learning_rate": 3.099013144955131e-06, "loss": 0.5505, "step": 2709 }, { "epoch": 0.75, "learning_rate": 3.0925235794133725e-06, "loss": 0.5318, "step": 2710 }, { "epoch": 0.75, "learning_rate": 3.086039572745788e-06, "loss": 0.5407, "step": 2711 }, { "epoch": 0.75, "learning_rate": 3.0795611301704577e-06, "loss": 0.529, "step": 2712 }, { "epoch": 0.75, "learning_rate": 3.0730882569009936e-06, "loss": 0.5406, "step": 2713 }, { "epoch": 0.75, "learning_rate": 3.066620958146508e-06, "loss": 0.5332, "step": 2714 }, { "epoch": 0.75, "learning_rate": 3.0601592391116406e-06, "loss": 0.5183, "step": 2715 }, { "epoch": 0.75, "learning_rate": 3.053703104996537e-06, "loss": 0.538, "step": 2716 }, { "epoch": 0.75, "learning_rate": 3.0472525609968484e-06, "loss": 0.5441, "step": 2717 }, { "epoch": 0.75, "learning_rate": 3.0408076123037276e-06, "loss": 0.5478, "step": 2718 }, { "epoch": 0.75, "learning_rate": 3.034368264103823e-06, "loss": 0.5382, "step": 2719 }, { "epoch": 0.75, "learning_rate": 3.027934521579278e-06, "loss": 0.5462, "step": 2720 }, { "epoch": 0.75, "learning_rate": 3.0215063899077224e-06, "loss": 0.5503, "step": 2721 }, { "epoch": 0.75, "learning_rate": 3.0150838742622735e-06, "loss": 0.5338, "step": 2722 }, { "epoch": 0.75, "learning_rate": 3.0086669798115264e-06, "loss": 0.5394, "step": 2723 }, { "epoch": 0.75, "learning_rate": 3.002255711719554e-06, "loss": 0.5253, "step": 2724 }, { "epoch": 0.75, "learning_rate": 2.9958500751459042e-06, "loss": 0.5438, "step": 2725 }, { "epoch": 0.75, "learning_rate": 2.9894500752455834e-06, "loss": 0.5289, "step": 2726 }, { "epoch": 0.76, "learning_rate": 2.98305571716907e-06, "loss": 0.528, "step": 2727 }, { "epoch": 0.76, "learning_rate": 2.976667006062298e-06, "loss": 0.5272, "step": 2728 }, { "epoch": 0.76, "learning_rate": 2.9702839470666654e-06, "loss": 0.5589, "step": 2729 }, { "epoch": 0.76, "learning_rate": 2.963906545319015e-06, "loss": 0.5373, "step": 2730 }, { "epoch": 0.76, "learning_rate": 2.9575348059516297e-06, "loss": 0.5277, "step": 2731 }, { "epoch": 0.76, "learning_rate": 2.951168734092248e-06, "loss": 0.5327, "step": 2732 }, { "epoch": 0.76, "learning_rate": 2.94480833486404e-06, "loss": 0.5412, "step": 2733 }, { "epoch": 0.76, "learning_rate": 2.9384536133856144e-06, "loss": 0.5356, "step": 2734 }, { "epoch": 0.76, "learning_rate": 2.9321045747710098e-06, "loss": 0.5305, "step": 2735 }, { "epoch": 0.76, "learning_rate": 2.9257612241296883e-06, "loss": 0.5338, "step": 2736 }, { "epoch": 0.76, "learning_rate": 2.9194235665665406e-06, "loss": 0.5272, "step": 2737 }, { "epoch": 0.76, "learning_rate": 2.9130916071818693e-06, "loss": 0.5382, "step": 2738 }, { "epoch": 0.76, "learning_rate": 2.906765351071397e-06, "loss": 0.5304, "step": 2739 }, { "epoch": 0.76, "learning_rate": 2.900444803326251e-06, "loss": 0.5337, "step": 2740 }, { "epoch": 0.76, "learning_rate": 2.8941299690329705e-06, "loss": 0.5369, "step": 2741 }, { "epoch": 0.76, "learning_rate": 2.8878208532734953e-06, "loss": 0.5478, "step": 2742 }, { "epoch": 0.76, "learning_rate": 2.881517461125155e-06, "loss": 0.5381, "step": 2743 }, { "epoch": 0.76, "learning_rate": 2.875219797660681e-06, "loss": 0.5434, "step": 2744 }, { "epoch": 0.76, "learning_rate": 2.868927867948199e-06, "loss": 0.5379, "step": 2745 }, { "epoch": 0.76, "learning_rate": 2.862641677051211e-06, "loss": 0.5307, "step": 2746 }, { "epoch": 0.76, "learning_rate": 2.856361230028608e-06, "loss": 0.5301, "step": 2747 }, { "epoch": 0.76, "learning_rate": 2.850086531934649e-06, "loss": 0.5452, "step": 2748 }, { "epoch": 0.76, "learning_rate": 2.8438175878189743e-06, "loss": 0.533, "step": 2749 }, { "epoch": 0.76, "learning_rate": 2.837554402726592e-06, "loss": 0.5343, "step": 2750 }, { "epoch": 0.76, "learning_rate": 2.831296981697874e-06, "loss": 0.5405, "step": 2751 }, { "epoch": 0.76, "learning_rate": 2.8250453297685575e-06, "loss": 0.5305, "step": 2752 }, { "epoch": 0.76, "learning_rate": 2.8187994519697314e-06, "loss": 0.5453, "step": 2753 }, { "epoch": 0.76, "learning_rate": 2.812559353327842e-06, "loss": 0.5446, "step": 2754 }, { "epoch": 0.76, "learning_rate": 2.8063250388646814e-06, "loss": 0.5265, "step": 2755 }, { "epoch": 0.76, "learning_rate": 2.80009651359739e-06, "loss": 0.5433, "step": 2756 }, { "epoch": 0.76, "learning_rate": 2.7938737825384487e-06, "loss": 0.5333, "step": 2757 }, { "epoch": 0.76, "learning_rate": 2.7876568506956736e-06, "loss": 0.5399, "step": 2758 }, { "epoch": 0.76, "learning_rate": 2.781445723072218e-06, "loss": 0.519, "step": 2759 }, { "epoch": 0.76, "learning_rate": 2.7752404046665516e-06, "loss": 0.5415, "step": 2760 }, { "epoch": 0.76, "learning_rate": 2.7690409004724883e-06, "loss": 0.5338, "step": 2761 }, { "epoch": 0.76, "learning_rate": 2.7628472154791495e-06, "loss": 0.5524, "step": 2762 }, { "epoch": 0.77, "learning_rate": 2.7566593546709784e-06, "loss": 0.5281, "step": 2763 }, { "epoch": 0.77, "learning_rate": 2.7504773230277282e-06, "loss": 0.5427, "step": 2764 }, { "epoch": 0.77, "learning_rate": 2.744301125524468e-06, "loss": 0.5273, "step": 2765 }, { "epoch": 0.77, "learning_rate": 2.738130767131557e-06, "loss": 0.5462, "step": 2766 }, { "epoch": 0.77, "learning_rate": 2.731966252814672e-06, "loss": 0.5323, "step": 2767 }, { "epoch": 0.77, "learning_rate": 2.7258075875347767e-06, "loss": 0.539, "step": 2768 }, { "epoch": 0.77, "learning_rate": 2.7196547762481275e-06, "loss": 0.5573, "step": 2769 }, { "epoch": 0.77, "learning_rate": 2.713507823906284e-06, "loss": 0.5471, "step": 2770 }, { "epoch": 0.77, "learning_rate": 2.7073667354560686e-06, "loss": 0.5215, "step": 2771 }, { "epoch": 0.77, "learning_rate": 2.7012315158395995e-06, "loss": 0.5242, "step": 2772 }, { "epoch": 0.77, "learning_rate": 2.695102169994267e-06, "loss": 0.5406, "step": 2773 }, { "epoch": 0.77, "learning_rate": 2.688978702852737e-06, "loss": 0.5334, "step": 2774 }, { "epoch": 0.77, "learning_rate": 2.682861119342941e-06, "loss": 0.5364, "step": 2775 }, { "epoch": 0.77, "learning_rate": 2.67674942438808e-06, "loss": 0.5288, "step": 2776 }, { "epoch": 0.77, "learning_rate": 2.6706436229066102e-06, "loss": 0.5504, "step": 2777 }, { "epoch": 0.77, "learning_rate": 2.6645437198122503e-06, "loss": 0.538, "step": 2778 }, { "epoch": 0.77, "learning_rate": 2.6584497200139703e-06, "loss": 0.5499, "step": 2779 }, { "epoch": 0.77, "learning_rate": 2.652361628415988e-06, "loss": 0.5341, "step": 2780 }, { "epoch": 0.77, "learning_rate": 2.6462794499177702e-06, "loss": 0.5499, "step": 2781 }, { "epoch": 0.77, "learning_rate": 2.6402031894140235e-06, "loss": 0.558, "step": 2782 }, { "epoch": 0.77, "learning_rate": 2.634132851794686e-06, "loss": 0.5295, "step": 2783 }, { "epoch": 0.77, "learning_rate": 2.6280684419449365e-06, "loss": 0.55, "step": 2784 }, { "epoch": 0.77, "learning_rate": 2.6220099647451804e-06, "loss": 0.5281, "step": 2785 }, { "epoch": 0.77, "learning_rate": 2.615957425071054e-06, "loss": 0.5363, "step": 2786 }, { "epoch": 0.77, "learning_rate": 2.6099108277934105e-06, "loss": 0.5411, "step": 2787 }, { "epoch": 0.77, "learning_rate": 2.6038701777783173e-06, "loss": 0.5458, "step": 2788 }, { "epoch": 0.77, "learning_rate": 2.59783547988706e-06, "loss": 0.5346, "step": 2789 }, { "epoch": 0.77, "learning_rate": 2.591806738976136e-06, "loss": 0.554, "step": 2790 }, { "epoch": 0.77, "learning_rate": 2.5857839598972457e-06, "loss": 0.5575, "step": 2791 }, { "epoch": 0.77, "learning_rate": 2.579767147497292e-06, "loss": 0.5321, "step": 2792 }, { "epoch": 0.77, "learning_rate": 2.573756306618378e-06, "loss": 0.522, "step": 2793 }, { "epoch": 0.77, "learning_rate": 2.5677514420977976e-06, "loss": 0.5484, "step": 2794 }, { "epoch": 0.77, "learning_rate": 2.56175255876804e-06, "loss": 0.5433, "step": 2795 }, { "epoch": 0.77, "learning_rate": 2.555759661456776e-06, "loss": 0.5329, "step": 2796 }, { "epoch": 0.77, "learning_rate": 2.549772754986862e-06, "loss": 0.5337, "step": 2797 }, { "epoch": 0.77, "learning_rate": 2.5437918441763334e-06, "loss": 0.5342, "step": 2798 }, { "epoch": 0.78, "learning_rate": 2.5378169338384017e-06, "loss": 0.5512, "step": 2799 }, { "epoch": 0.78, "learning_rate": 2.5318480287814406e-06, "loss": 0.5365, "step": 2800 }, { "epoch": 0.78, "learning_rate": 2.5258851338089995e-06, "loss": 0.5422, "step": 2801 }, { "epoch": 0.78, "learning_rate": 2.5199282537197943e-06, "loss": 0.5234, "step": 2802 }, { "epoch": 0.78, "learning_rate": 2.513977393307693e-06, "loss": 0.5444, "step": 2803 }, { "epoch": 0.78, "learning_rate": 2.5080325573617227e-06, "loss": 0.5535, "step": 2804 }, { "epoch": 0.78, "learning_rate": 2.502093750666058e-06, "loss": 0.5418, "step": 2805 }, { "epoch": 0.78, "learning_rate": 2.4961609780000263e-06, "loss": 0.5182, "step": 2806 }, { "epoch": 0.78, "learning_rate": 2.4902342441380965e-06, "loss": 0.5231, "step": 2807 }, { "epoch": 0.78, "learning_rate": 2.48431355384988e-06, "loss": 0.5395, "step": 2808 }, { "epoch": 0.78, "learning_rate": 2.478398911900122e-06, "loss": 0.534, "step": 2809 }, { "epoch": 0.78, "learning_rate": 2.472490323048702e-06, "loss": 0.5282, "step": 2810 }, { "epoch": 0.78, "learning_rate": 2.4665877920506263e-06, "loss": 0.5281, "step": 2811 }, { "epoch": 0.78, "learning_rate": 2.4606913236560283e-06, "loss": 0.5392, "step": 2812 }, { "epoch": 0.78, "learning_rate": 2.454800922610161e-06, "loss": 0.5451, "step": 2813 }, { "epoch": 0.78, "learning_rate": 2.4489165936533944e-06, "loss": 0.5179, "step": 2814 }, { "epoch": 0.78, "learning_rate": 2.4430383415212135e-06, "loss": 0.5349, "step": 2815 }, { "epoch": 0.78, "learning_rate": 2.437166170944215e-06, "loss": 0.5343, "step": 2816 }, { "epoch": 0.78, "learning_rate": 2.4313000866480886e-06, "loss": 0.5361, "step": 2817 }, { "epoch": 0.78, "learning_rate": 2.425440093353645e-06, "loss": 0.556, "step": 2818 }, { "epoch": 0.78, "learning_rate": 2.419586195776781e-06, "loss": 0.5169, "step": 2819 }, { "epoch": 0.78, "learning_rate": 2.4137383986284913e-06, "loss": 0.5327, "step": 2820 }, { "epoch": 0.78, "learning_rate": 2.4078967066148582e-06, "loss": 0.5326, "step": 2821 }, { "epoch": 0.78, "learning_rate": 2.4020611244370583e-06, "loss": 0.5481, "step": 2822 }, { "epoch": 0.78, "learning_rate": 2.396231656791339e-06, "loss": 0.5368, "step": 2823 }, { "epoch": 0.78, "learning_rate": 2.3904083083690388e-06, "loss": 0.5369, "step": 2824 }, { "epoch": 0.78, "learning_rate": 2.3845910838565646e-06, "loss": 0.5437, "step": 2825 }, { "epoch": 0.78, "learning_rate": 2.3787799879353958e-06, "loss": 0.5376, "step": 2826 }, { "epoch": 0.78, "learning_rate": 2.372975025282088e-06, "loss": 0.5373, "step": 2827 }, { "epoch": 0.78, "learning_rate": 2.3671762005682486e-06, "loss": 0.5228, "step": 2828 }, { "epoch": 0.78, "learning_rate": 2.3613835184605527e-06, "loss": 0.5469, "step": 2829 }, { "epoch": 0.78, "learning_rate": 2.355596983620729e-06, "loss": 0.5301, "step": 2830 }, { "epoch": 0.78, "learning_rate": 2.349816600705563e-06, "loss": 0.535, "step": 2831 }, { "epoch": 0.78, "learning_rate": 2.344042374366885e-06, "loss": 0.5222, "step": 2832 }, { "epoch": 0.78, "learning_rate": 2.3382743092515734e-06, "loss": 0.5198, "step": 2833 }, { "epoch": 0.78, "learning_rate": 2.332512410001547e-06, "loss": 0.5382, "step": 2834 }, { "epoch": 0.78, "learning_rate": 2.3267566812537645e-06, "loss": 0.5447, "step": 2835 }, { "epoch": 0.79, "learning_rate": 2.321007127640216e-06, "loss": 0.53, "step": 2836 }, { "epoch": 0.79, "learning_rate": 2.315263753787923e-06, "loss": 0.5225, "step": 2837 }, { "epoch": 0.79, "learning_rate": 2.3095265643189357e-06, "loss": 0.5432, "step": 2838 }, { "epoch": 0.79, "learning_rate": 2.3037955638503274e-06, "loss": 0.5445, "step": 2839 }, { "epoch": 0.79, "learning_rate": 2.2980707569941853e-06, "loss": 0.5329, "step": 2840 }, { "epoch": 0.79, "learning_rate": 2.292352148357616e-06, "loss": 0.5238, "step": 2841 }, { "epoch": 0.79, "learning_rate": 2.2866397425427387e-06, "loss": 0.5437, "step": 2842 }, { "epoch": 0.79, "learning_rate": 2.280933544146684e-06, "loss": 0.5272, "step": 2843 }, { "epoch": 0.79, "learning_rate": 2.2752335577615837e-06, "loss": 0.5362, "step": 2844 }, { "epoch": 0.79, "learning_rate": 2.2695397879745627e-06, "loss": 0.5343, "step": 2845 }, { "epoch": 0.79, "learning_rate": 2.2638522393677564e-06, "loss": 0.528, "step": 2846 }, { "epoch": 0.79, "learning_rate": 2.258170916518284e-06, "loss": 0.5444, "step": 2847 }, { "epoch": 0.79, "learning_rate": 2.2524958239982607e-06, "loss": 0.5281, "step": 2848 }, { "epoch": 0.79, "learning_rate": 2.2468269663747833e-06, "loss": 0.5284, "step": 2849 }, { "epoch": 0.79, "learning_rate": 2.2411643482099334e-06, "loss": 0.5292, "step": 2850 }, { "epoch": 0.79, "learning_rate": 2.23550797406077e-06, "loss": 0.5536, "step": 2851 }, { "epoch": 0.79, "learning_rate": 2.2298578484793288e-06, "loss": 0.5311, "step": 2852 }, { "epoch": 0.79, "learning_rate": 2.2242139760126146e-06, "loss": 0.5387, "step": 2853 }, { "epoch": 0.79, "learning_rate": 2.218576361202602e-06, "loss": 0.5342, "step": 2854 }, { "epoch": 0.79, "learning_rate": 2.212945008586229e-06, "loss": 0.5363, "step": 2855 }, { "epoch": 0.79, "learning_rate": 2.2073199226953968e-06, "loss": 0.5446, "step": 2856 }, { "epoch": 0.79, "learning_rate": 2.201701108056954e-06, "loss": 0.5326, "step": 2857 }, { "epoch": 0.79, "learning_rate": 2.1960885691927093e-06, "loss": 0.5317, "step": 2858 }, { "epoch": 0.79, "learning_rate": 2.1904823106194263e-06, "loss": 0.52, "step": 2859 }, { "epoch": 0.79, "learning_rate": 2.1848823368488057e-06, "loss": 0.5482, "step": 2860 }, { "epoch": 0.79, "learning_rate": 2.1792886523874955e-06, "loss": 0.5331, "step": 2861 }, { "epoch": 0.79, "learning_rate": 2.1737012617370756e-06, "loss": 0.5405, "step": 2862 }, { "epoch": 0.79, "learning_rate": 2.1681201693940667e-06, "loss": 0.5225, "step": 2863 }, { "epoch": 0.79, "learning_rate": 2.162545379849921e-06, "loss": 0.5384, "step": 2864 }, { "epoch": 0.79, "learning_rate": 2.1569768975910153e-06, "loss": 0.5357, "step": 2865 }, { "epoch": 0.79, "learning_rate": 2.151414727098654e-06, "loss": 0.539, "step": 2866 }, { "epoch": 0.79, "learning_rate": 2.1458588728490594e-06, "loss": 0.5311, "step": 2867 }, { "epoch": 0.79, "learning_rate": 2.140309339313371e-06, "loss": 0.5424, "step": 2868 }, { "epoch": 0.79, "learning_rate": 2.134766130957644e-06, "loss": 0.5293, "step": 2869 }, { "epoch": 0.79, "learning_rate": 2.1292292522428394e-06, "loss": 0.5282, "step": 2870 }, { "epoch": 0.79, "learning_rate": 2.1236987076248284e-06, "loss": 0.5185, "step": 2871 }, { "epoch": 0.8, "learning_rate": 2.118174501554381e-06, "loss": 0.5393, "step": 2872 }, { "epoch": 0.8, "learning_rate": 2.1126566384771728e-06, "loss": 0.5478, "step": 2873 }, { "epoch": 0.8, "learning_rate": 2.1071451228337605e-06, "loss": 0.5354, "step": 2874 }, { "epoch": 0.8, "learning_rate": 2.1016399590596105e-06, "loss": 0.5336, "step": 2875 }, { "epoch": 0.8, "learning_rate": 2.096141151585066e-06, "loss": 0.5276, "step": 2876 }, { "epoch": 0.8, "learning_rate": 2.0906487048353587e-06, "loss": 0.5383, "step": 2877 }, { "epoch": 0.8, "learning_rate": 2.085162623230601e-06, "loss": 0.5526, "step": 2878 }, { "epoch": 0.8, "learning_rate": 2.0796829111857854e-06, "loss": 0.537, "step": 2879 }, { "epoch": 0.8, "learning_rate": 2.0742095731107693e-06, "loss": 0.5347, "step": 2880 }, { "epoch": 0.8, "learning_rate": 2.0687426134102893e-06, "loss": 0.5371, "step": 2881 }, { "epoch": 0.8, "learning_rate": 2.063282036483948e-06, "loss": 0.5404, "step": 2882 }, { "epoch": 0.8, "learning_rate": 2.057827846726206e-06, "loss": 0.5339, "step": 2883 }, { "epoch": 0.8, "learning_rate": 2.0523800485263968e-06, "loss": 0.5259, "step": 2884 }, { "epoch": 0.8, "learning_rate": 2.0469386462686925e-06, "loss": 0.5381, "step": 2885 }, { "epoch": 0.8, "learning_rate": 2.041503644332129e-06, "loss": 0.5302, "step": 2886 }, { "epoch": 0.8, "learning_rate": 2.03607504709059e-06, "loss": 0.5314, "step": 2887 }, { "epoch": 0.8, "learning_rate": 2.0306528589128014e-06, "loss": 0.5312, "step": 2888 }, { "epoch": 0.8, "learning_rate": 2.025237084162337e-06, "loss": 0.5213, "step": 2889 }, { "epoch": 0.8, "learning_rate": 2.019827727197605e-06, "loss": 0.5444, "step": 2890 }, { "epoch": 0.8, "learning_rate": 2.0144247923718507e-06, "loss": 0.5334, "step": 2891 }, { "epoch": 0.8, "learning_rate": 2.009028284033149e-06, "loss": 0.5463, "step": 2892 }, { "epoch": 0.8, "learning_rate": 2.0036382065244054e-06, "loss": 0.5205, "step": 2893 }, { "epoch": 0.8, "learning_rate": 1.9982545641833483e-06, "loss": 0.5313, "step": 2894 }, { "epoch": 0.8, "learning_rate": 1.99287736134253e-06, "loss": 0.5458, "step": 2895 }, { "epoch": 0.8, "learning_rate": 1.98750660232932e-06, "loss": 0.5368, "step": 2896 }, { "epoch": 0.8, "learning_rate": 1.982142291465896e-06, "loss": 0.5349, "step": 2897 }, { "epoch": 0.8, "learning_rate": 1.976784433069253e-06, "loss": 0.5217, "step": 2898 }, { "epoch": 0.8, "learning_rate": 1.97143303145119e-06, "loss": 0.5296, "step": 2899 }, { "epoch": 0.8, "learning_rate": 1.9660880909183166e-06, "loss": 0.5347, "step": 2900 }, { "epoch": 0.8, "learning_rate": 1.9607496157720364e-06, "loss": 0.5354, "step": 2901 }, { "epoch": 0.8, "learning_rate": 1.9554176103085475e-06, "loss": 0.5254, "step": 2902 }, { "epoch": 0.8, "learning_rate": 1.950092078818846e-06, "loss": 0.5389, "step": 2903 }, { "epoch": 0.8, "learning_rate": 1.9447730255887174e-06, "loss": 0.5304, "step": 2904 }, { "epoch": 0.8, "learning_rate": 1.939460454898735e-06, "loss": 0.5396, "step": 2905 }, { "epoch": 0.8, "learning_rate": 1.9341543710242516e-06, "loss": 0.5321, "step": 2906 }, { "epoch": 0.8, "learning_rate": 1.928854778235402e-06, "loss": 0.5289, "step": 2907 }, { "epoch": 0.81, "learning_rate": 1.923561680797097e-06, "loss": 0.5314, "step": 2908 }, { "epoch": 0.81, "learning_rate": 1.91827508296902e-06, "loss": 0.5484, "step": 2909 }, { "epoch": 0.81, "learning_rate": 1.9129949890056244e-06, "loss": 0.5328, "step": 2910 }, { "epoch": 0.81, "learning_rate": 1.9077214031561274e-06, "loss": 0.5365, "step": 2911 }, { "epoch": 0.81, "learning_rate": 1.9024543296645116e-06, "loss": 0.5248, "step": 2912 }, { "epoch": 0.81, "learning_rate": 1.897193772769519e-06, "loss": 0.5538, "step": 2913 }, { "epoch": 0.81, "learning_rate": 1.891939736704641e-06, "loss": 0.5286, "step": 2914 }, { "epoch": 0.81, "learning_rate": 1.8866922256981258e-06, "loss": 0.5174, "step": 2915 }, { "epoch": 0.81, "learning_rate": 1.881451243972976e-06, "loss": 0.5307, "step": 2916 }, { "epoch": 0.81, "learning_rate": 1.8762167957469301e-06, "loss": 0.5331, "step": 2917 }, { "epoch": 0.81, "learning_rate": 1.8709888852324754e-06, "loss": 0.5415, "step": 2918 }, { "epoch": 0.81, "learning_rate": 1.8657675166368361e-06, "loss": 0.5214, "step": 2919 }, { "epoch": 0.81, "learning_rate": 1.8605526941619656e-06, "loss": 0.559, "step": 2920 }, { "epoch": 0.81, "learning_rate": 1.8553444220045592e-06, "loss": 0.5392, "step": 2921 }, { "epoch": 0.81, "learning_rate": 1.8501427043560338e-06, "loss": 0.5361, "step": 2922 }, { "epoch": 0.81, "learning_rate": 1.8449475454025356e-06, "loss": 0.5297, "step": 2923 }, { "epoch": 0.81, "learning_rate": 1.839758949324929e-06, "loss": 0.5217, "step": 2924 }, { "epoch": 0.81, "learning_rate": 1.8345769202988007e-06, "loss": 0.5368, "step": 2925 }, { "epoch": 0.81, "learning_rate": 1.829401462494449e-06, "loss": 0.5231, "step": 2926 }, { "epoch": 0.81, "learning_rate": 1.8242325800768867e-06, "loss": 0.5401, "step": 2927 }, { "epoch": 0.81, "learning_rate": 1.8190702772058321e-06, "loss": 0.5201, "step": 2928 }, { "epoch": 0.81, "learning_rate": 1.813914558035711e-06, "loss": 0.533, "step": 2929 }, { "epoch": 0.81, "learning_rate": 1.808765426715653e-06, "loss": 0.5281, "step": 2930 }, { "epoch": 0.81, "learning_rate": 1.8036228873894745e-06, "loss": 0.5423, "step": 2931 }, { "epoch": 0.81, "learning_rate": 1.7984869441957043e-06, "loss": 0.5275, "step": 2932 }, { "epoch": 0.81, "learning_rate": 1.793357601267549e-06, "loss": 0.5361, "step": 2933 }, { "epoch": 0.81, "learning_rate": 1.7882348627329115e-06, "loss": 0.5351, "step": 2934 }, { "epoch": 0.81, "learning_rate": 1.783118732714375e-06, "loss": 0.5366, "step": 2935 }, { "epoch": 0.81, "learning_rate": 1.7780092153292093e-06, "loss": 0.5307, "step": 2936 }, { "epoch": 0.81, "learning_rate": 1.7729063146893555e-06, "loss": 0.5364, "step": 2937 }, { "epoch": 0.81, "learning_rate": 1.767810034901435e-06, "loss": 0.5407, "step": 2938 }, { "epoch": 0.81, "learning_rate": 1.7627203800667404e-06, "loss": 0.5519, "step": 2939 }, { "epoch": 0.81, "learning_rate": 1.7576373542812296e-06, "loss": 0.5387, "step": 2940 }, { "epoch": 0.81, "learning_rate": 1.7525609616355355e-06, "loss": 0.5215, "step": 2941 }, { "epoch": 0.81, "learning_rate": 1.7474912062149385e-06, "loss": 0.5216, "step": 2942 }, { "epoch": 0.81, "learning_rate": 1.7424280920993886e-06, "loss": 0.5361, "step": 2943 }, { "epoch": 0.82, "learning_rate": 1.737371623363485e-06, "loss": 0.5397, "step": 2944 }, { "epoch": 0.82, "learning_rate": 1.7323218040764833e-06, "loss": 0.5262, "step": 2945 }, { "epoch": 0.82, "learning_rate": 1.7272786383022855e-06, "loss": 0.53, "step": 2946 }, { "epoch": 0.82, "learning_rate": 1.7222421300994384e-06, "loss": 0.5413, "step": 2947 }, { "epoch": 0.82, "learning_rate": 1.7172122835211337e-06, "loss": 0.5272, "step": 2948 }, { "epoch": 0.82, "learning_rate": 1.7121891026151983e-06, "loss": 0.5324, "step": 2949 }, { "epoch": 0.82, "learning_rate": 1.7071725914241e-06, "loss": 0.5304, "step": 2950 }, { "epoch": 0.82, "learning_rate": 1.702162753984934e-06, "loss": 0.542, "step": 2951 }, { "epoch": 0.82, "learning_rate": 1.6971595943294272e-06, "loss": 0.539, "step": 2952 }, { "epoch": 0.82, "learning_rate": 1.6921631164839348e-06, "loss": 0.5356, "step": 2953 }, { "epoch": 0.82, "learning_rate": 1.6871733244694277e-06, "loss": 0.5405, "step": 2954 }, { "epoch": 0.82, "learning_rate": 1.6821902223015019e-06, "loss": 0.5436, "step": 2955 }, { "epoch": 0.82, "learning_rate": 1.677213813990367e-06, "loss": 0.5407, "step": 2956 }, { "epoch": 0.82, "learning_rate": 1.6722441035408522e-06, "loss": 0.5274, "step": 2957 }, { "epoch": 0.82, "learning_rate": 1.6672810949523887e-06, "loss": 0.532, "step": 2958 }, { "epoch": 0.82, "learning_rate": 1.6623247922190155e-06, "loss": 0.5438, "step": 2959 }, { "epoch": 0.82, "learning_rate": 1.6573751993293774e-06, "loss": 0.538, "step": 2960 }, { "epoch": 0.82, "learning_rate": 1.6524323202667182e-06, "loss": 0.5325, "step": 2961 }, { "epoch": 0.82, "learning_rate": 1.6474961590088789e-06, "loss": 0.5458, "step": 2962 }, { "epoch": 0.82, "learning_rate": 1.6425667195282947e-06, "loss": 0.5217, "step": 2963 }, { "epoch": 0.82, "learning_rate": 1.6376440057919907e-06, "loss": 0.5364, "step": 2964 }, { "epoch": 0.82, "learning_rate": 1.6327280217615793e-06, "loss": 0.5402, "step": 2965 }, { "epoch": 0.82, "learning_rate": 1.627818771393258e-06, "loss": 0.5436, "step": 2966 }, { "epoch": 0.82, "learning_rate": 1.6229162586378044e-06, "loss": 0.5336, "step": 2967 }, { "epoch": 0.82, "learning_rate": 1.6180204874405737e-06, "loss": 0.54, "step": 2968 }, { "epoch": 0.82, "learning_rate": 1.6131314617414972e-06, "loss": 0.5459, "step": 2969 }, { "epoch": 0.82, "learning_rate": 1.608249185475078e-06, "loss": 0.5363, "step": 2970 }, { "epoch": 0.82, "learning_rate": 1.6033736625703832e-06, "loss": 0.5277, "step": 2971 }, { "epoch": 0.82, "learning_rate": 1.5985048969510465e-06, "loss": 0.5354, "step": 2972 }, { "epoch": 0.82, "learning_rate": 1.5936428925352698e-06, "loss": 0.5294, "step": 2973 }, { "epoch": 0.82, "learning_rate": 1.5887876532358082e-06, "loss": 0.5424, "step": 2974 }, { "epoch": 0.82, "learning_rate": 1.5839391829599725e-06, "loss": 0.5375, "step": 2975 }, { "epoch": 0.82, "learning_rate": 1.579097485609631e-06, "loss": 0.5318, "step": 2976 }, { "epoch": 0.82, "learning_rate": 1.5742625650811904e-06, "loss": 0.5458, "step": 2977 }, { "epoch": 0.82, "learning_rate": 1.5694344252656147e-06, "loss": 0.5335, "step": 2978 }, { "epoch": 0.82, "learning_rate": 1.5646130700484064e-06, "loss": 0.5504, "step": 2979 }, { "epoch": 0.83, "learning_rate": 1.5597985033096086e-06, "loss": 0.531, "step": 2980 }, { "epoch": 0.83, "learning_rate": 1.5549907289238031e-06, "loss": 0.5284, "step": 2981 }, { "epoch": 0.83, "learning_rate": 1.5501897507601016e-06, "loss": 0.547, "step": 2982 }, { "epoch": 0.83, "learning_rate": 1.54539557268215e-06, "loss": 0.5189, "step": 2983 }, { "epoch": 0.83, "learning_rate": 1.5406081985481193e-06, "loss": 0.5347, "step": 2984 }, { "epoch": 0.83, "learning_rate": 1.535827632210707e-06, "loss": 0.5341, "step": 2985 }, { "epoch": 0.83, "learning_rate": 1.5310538775171313e-06, "loss": 0.5296, "step": 2986 }, { "epoch": 0.83, "learning_rate": 1.5262869383091295e-06, "loss": 0.5445, "step": 2987 }, { "epoch": 0.83, "learning_rate": 1.5215268184229458e-06, "loss": 0.537, "step": 2988 }, { "epoch": 0.83, "learning_rate": 1.5167735216893508e-06, "loss": 0.5278, "step": 2989 }, { "epoch": 0.83, "learning_rate": 1.5120270519336167e-06, "loss": 0.5502, "step": 2990 }, { "epoch": 0.83, "learning_rate": 1.5072874129755177e-06, "loss": 0.5537, "step": 2991 }, { "epoch": 0.83, "learning_rate": 1.5025546086293386e-06, "loss": 0.5437, "step": 2992 }, { "epoch": 0.83, "learning_rate": 1.4978286427038602e-06, "loss": 0.5377, "step": 2993 }, { "epoch": 0.83, "learning_rate": 1.4931095190023559e-06, "loss": 0.5383, "step": 2994 }, { "epoch": 0.83, "learning_rate": 1.4883972413226e-06, "loss": 0.5431, "step": 2995 }, { "epoch": 0.83, "learning_rate": 1.4836918134568546e-06, "loss": 0.5458, "step": 2996 }, { "epoch": 0.83, "learning_rate": 1.478993239191865e-06, "loss": 0.5121, "step": 2997 }, { "epoch": 0.83, "learning_rate": 1.4743015223088719e-06, "loss": 0.5394, "step": 2998 }, { "epoch": 0.83, "learning_rate": 1.4696166665835853e-06, "loss": 0.5268, "step": 2999 }, { "epoch": 0.83, "learning_rate": 1.4649386757862005e-06, "loss": 0.5384, "step": 3000 }, { "epoch": 0.83, "learning_rate": 1.4602675536813859e-06, "loss": 0.5381, "step": 3001 }, { "epoch": 0.83, "learning_rate": 1.4556033040282835e-06, "loss": 0.5317, "step": 3002 }, { "epoch": 0.83, "learning_rate": 1.450945930580503e-06, "loss": 0.5328, "step": 3003 }, { "epoch": 0.83, "learning_rate": 1.4462954370861215e-06, "loss": 0.5412, "step": 3004 }, { "epoch": 0.83, "learning_rate": 1.4416518272876811e-06, "loss": 0.5218, "step": 3005 }, { "epoch": 0.83, "learning_rate": 1.4370151049221793e-06, "loss": 0.5154, "step": 3006 }, { "epoch": 0.83, "learning_rate": 1.4323852737210765e-06, "loss": 0.547, "step": 3007 }, { "epoch": 0.83, "learning_rate": 1.4277623374102822e-06, "loss": 0.5468, "step": 3008 }, { "epoch": 0.83, "learning_rate": 1.4231462997101618e-06, "loss": 0.5299, "step": 3009 }, { "epoch": 0.83, "learning_rate": 1.4185371643355284e-06, "loss": 0.5304, "step": 3010 }, { "epoch": 0.83, "learning_rate": 1.4139349349956332e-06, "loss": 0.5358, "step": 3011 }, { "epoch": 0.83, "learning_rate": 1.4093396153941785e-06, "loss": 0.5402, "step": 3012 }, { "epoch": 0.83, "learning_rate": 1.4047512092293003e-06, "loss": 0.5212, "step": 3013 }, { "epoch": 0.83, "learning_rate": 1.4001697201935782e-06, "loss": 0.5435, "step": 3014 }, { "epoch": 0.83, "learning_rate": 1.3955951519740186e-06, "loss": 0.5185, "step": 3015 }, { "epoch": 0.84, "learning_rate": 1.3910275082520575e-06, "loss": 0.5366, "step": 3016 }, { "epoch": 0.84, "learning_rate": 1.3864667927035612e-06, "loss": 0.5452, "step": 3017 }, { "epoch": 0.84, "learning_rate": 1.3819130089988209e-06, "loss": 0.5242, "step": 3018 }, { "epoch": 0.84, "learning_rate": 1.377366160802549e-06, "loss": 0.5323, "step": 3019 }, { "epoch": 0.84, "learning_rate": 1.3728262517738756e-06, "loss": 0.547, "step": 3020 }, { "epoch": 0.84, "learning_rate": 1.3682932855663455e-06, "loss": 0.5312, "step": 3021 }, { "epoch": 0.84, "learning_rate": 1.363767265827919e-06, "loss": 0.5216, "step": 3022 }, { "epoch": 0.84, "learning_rate": 1.359248196200963e-06, "loss": 0.5315, "step": 3023 }, { "epoch": 0.84, "learning_rate": 1.3547360803222543e-06, "loss": 0.5259, "step": 3024 }, { "epoch": 0.84, "learning_rate": 1.3502309218229715e-06, "loss": 0.5385, "step": 3025 }, { "epoch": 0.84, "learning_rate": 1.3457327243286943e-06, "loss": 0.5312, "step": 3026 }, { "epoch": 0.84, "learning_rate": 1.341241491459404e-06, "loss": 0.5391, "step": 3027 }, { "epoch": 0.84, "learning_rate": 1.3367572268294692e-06, "loss": 0.5246, "step": 3028 }, { "epoch": 0.84, "learning_rate": 1.3322799340476545e-06, "loss": 0.5437, "step": 3029 }, { "epoch": 0.84, "learning_rate": 1.3278096167171194e-06, "loss": 0.535, "step": 3030 }, { "epoch": 0.84, "learning_rate": 1.3233462784354046e-06, "loss": 0.5312, "step": 3031 }, { "epoch": 0.84, "learning_rate": 1.318889922794433e-06, "loss": 0.525, "step": 3032 }, { "epoch": 0.84, "learning_rate": 1.3144405533805138e-06, "loss": 0.5236, "step": 3033 }, { "epoch": 0.84, "learning_rate": 1.3099981737743238e-06, "loss": 0.522, "step": 3034 }, { "epoch": 0.84, "learning_rate": 1.3055627875509247e-06, "loss": 0.5402, "step": 3035 }, { "epoch": 0.84, "learning_rate": 1.3011343982797464e-06, "loss": 0.5353, "step": 3036 }, { "epoch": 0.84, "learning_rate": 1.2967130095245883e-06, "loss": 0.5342, "step": 3037 }, { "epoch": 0.84, "learning_rate": 1.2922986248436154e-06, "loss": 0.5348, "step": 3038 }, { "epoch": 0.84, "learning_rate": 1.2878912477893569e-06, "loss": 0.5417, "step": 3039 }, { "epoch": 0.84, "learning_rate": 1.2834908819087011e-06, "loss": 0.5541, "step": 3040 }, { "epoch": 0.84, "learning_rate": 1.2790975307428954e-06, "loss": 0.5329, "step": 3041 }, { "epoch": 0.84, "learning_rate": 1.2747111978275428e-06, "loss": 0.5217, "step": 3042 }, { "epoch": 0.84, "learning_rate": 1.2703318866925962e-06, "loss": 0.5314, "step": 3043 }, { "epoch": 0.84, "learning_rate": 1.2659596008623609e-06, "loss": 0.534, "step": 3044 }, { "epoch": 0.84, "learning_rate": 1.261594343855479e-06, "loss": 0.5299, "step": 3045 }, { "epoch": 0.84, "learning_rate": 1.2572361191849514e-06, "loss": 0.5294, "step": 3046 }, { "epoch": 0.84, "learning_rate": 1.252884930358107e-06, "loss": 0.5512, "step": 3047 }, { "epoch": 0.84, "learning_rate": 1.2485407808766193e-06, "loss": 0.5423, "step": 3048 }, { "epoch": 0.84, "learning_rate": 1.2442036742364927e-06, "loss": 0.5441, "step": 3049 }, { "epoch": 0.84, "learning_rate": 1.2398736139280687e-06, "loss": 0.5185, "step": 3050 }, { "epoch": 0.84, "learning_rate": 1.23555060343601e-06, "loss": 0.5374, "step": 3051 }, { "epoch": 0.85, "learning_rate": 1.2312346462393144e-06, "loss": 0.5284, "step": 3052 }, { "epoch": 0.85, "learning_rate": 1.2269257458112983e-06, "loss": 0.5404, "step": 3053 }, { "epoch": 0.85, "learning_rate": 1.2226239056195999e-06, "loss": 0.5432, "step": 3054 }, { "epoch": 0.85, "learning_rate": 1.2183291291261835e-06, "loss": 0.5439, "step": 3055 }, { "epoch": 0.85, "learning_rate": 1.2140414197873128e-06, "loss": 0.5405, "step": 3056 }, { "epoch": 0.85, "learning_rate": 1.2097607810535784e-06, "loss": 0.5352, "step": 3057 }, { "epoch": 0.85, "learning_rate": 1.2054872163698728e-06, "loss": 0.5358, "step": 3058 }, { "epoch": 0.85, "learning_rate": 1.2012207291754008e-06, "loss": 0.5268, "step": 3059 }, { "epoch": 0.85, "learning_rate": 1.1969613229036658e-06, "loss": 0.5279, "step": 3060 }, { "epoch": 0.85, "learning_rate": 1.1927090009824793e-06, "loss": 0.528, "step": 3061 }, { "epoch": 0.85, "learning_rate": 1.188463766833945e-06, "loss": 0.5419, "step": 3062 }, { "epoch": 0.85, "learning_rate": 1.1842256238744687e-06, "loss": 0.5313, "step": 3063 }, { "epoch": 0.85, "learning_rate": 1.1799945755147445e-06, "loss": 0.54, "step": 3064 }, { "epoch": 0.85, "learning_rate": 1.17577062515976e-06, "loss": 0.5375, "step": 3065 }, { "epoch": 0.85, "learning_rate": 1.1715537762087891e-06, "loss": 0.5329, "step": 3066 }, { "epoch": 0.85, "learning_rate": 1.1673440320553941e-06, "loss": 0.5219, "step": 3067 }, { "epoch": 0.85, "learning_rate": 1.1631413960874127e-06, "loss": 0.5282, "step": 3068 }, { "epoch": 0.85, "learning_rate": 1.1589458716869684e-06, "loss": 0.5308, "step": 3069 }, { "epoch": 0.85, "learning_rate": 1.154757462230457e-06, "loss": 0.5439, "step": 3070 }, { "epoch": 0.85, "learning_rate": 1.1505761710885555e-06, "loss": 0.529, "step": 3071 }, { "epoch": 0.85, "learning_rate": 1.1464020016262056e-06, "loss": 0.5423, "step": 3072 }, { "epoch": 0.85, "learning_rate": 1.1422349572026237e-06, "loss": 0.5328, "step": 3073 }, { "epoch": 0.85, "learning_rate": 1.1380750411712827e-06, "loss": 0.5379, "step": 3074 }, { "epoch": 0.85, "learning_rate": 1.133922256879927e-06, "loss": 0.5326, "step": 3075 }, { "epoch": 0.85, "learning_rate": 1.1297766076705597e-06, "loss": 0.5262, "step": 3076 }, { "epoch": 0.85, "learning_rate": 1.125638096879441e-06, "loss": 0.5387, "step": 3077 }, { "epoch": 0.85, "learning_rate": 1.1215067278370883e-06, "loss": 0.5333, "step": 3078 }, { "epoch": 0.85, "learning_rate": 1.1173825038682683e-06, "loss": 0.5395, "step": 3079 }, { "epoch": 0.85, "learning_rate": 1.1132654282920019e-06, "loss": 0.5291, "step": 3080 }, { "epoch": 0.85, "learning_rate": 1.1091555044215518e-06, "loss": 0.5464, "step": 3081 }, { "epoch": 0.85, "learning_rate": 1.1050527355644314e-06, "loss": 0.5433, "step": 3082 }, { "epoch": 0.85, "learning_rate": 1.1009571250223904e-06, "loss": 0.5363, "step": 3083 }, { "epoch": 0.85, "learning_rate": 1.0968686760914248e-06, "loss": 0.5285, "step": 3084 }, { "epoch": 0.85, "learning_rate": 1.092787392061756e-06, "loss": 0.5367, "step": 3085 }, { "epoch": 0.85, "learning_rate": 1.0887132762178488e-06, "loss": 0.5542, "step": 3086 }, { "epoch": 0.85, "learning_rate": 1.0846463318383983e-06, "loss": 0.5334, "step": 3087 }, { "epoch": 0.86, "learning_rate": 1.0805865621963251e-06, "loss": 0.5303, "step": 3088 }, { "epoch": 0.86, "learning_rate": 1.0765339705587785e-06, "loss": 0.5383, "step": 3089 }, { "epoch": 0.86, "learning_rate": 1.0724885601871315e-06, "loss": 0.5313, "step": 3090 }, { "epoch": 0.86, "learning_rate": 1.0684503343369722e-06, "loss": 0.5251, "step": 3091 }, { "epoch": 0.86, "learning_rate": 1.0644192962581124e-06, "loss": 0.5317, "step": 3092 }, { "epoch": 0.86, "learning_rate": 1.0603954491945801e-06, "loss": 0.5206, "step": 3093 }, { "epoch": 0.86, "learning_rate": 1.0563787963846117e-06, "loss": 0.5359, "step": 3094 }, { "epoch": 0.86, "learning_rate": 1.0523693410606583e-06, "loss": 0.5368, "step": 3095 }, { "epoch": 0.86, "learning_rate": 1.0483670864493777e-06, "loss": 0.5331, "step": 3096 }, { "epoch": 0.86, "learning_rate": 1.0443720357716303e-06, "loss": 0.5247, "step": 3097 }, { "epoch": 0.86, "learning_rate": 1.0403841922424806e-06, "loss": 0.5531, "step": 3098 }, { "epoch": 0.86, "learning_rate": 1.036403559071195e-06, "loss": 0.5419, "step": 3099 }, { "epoch": 0.86, "learning_rate": 1.0324301394612357e-06, "loss": 0.5365, "step": 3100 }, { "epoch": 0.86, "learning_rate": 1.02846393661026e-06, "loss": 0.5392, "step": 3101 }, { "epoch": 0.86, "learning_rate": 1.0245049537101115e-06, "loss": 0.5294, "step": 3102 }, { "epoch": 0.86, "learning_rate": 1.020553193946836e-06, "loss": 0.5444, "step": 3103 }, { "epoch": 0.86, "learning_rate": 1.0166086605006564e-06, "loss": 0.5308, "step": 3104 }, { "epoch": 0.86, "learning_rate": 1.0126713565459834e-06, "loss": 0.536, "step": 3105 }, { "epoch": 0.86, "learning_rate": 1.00874128525141e-06, "loss": 0.5292, "step": 3106 }, { "epoch": 0.86, "learning_rate": 1.0048184497797087e-06, "loss": 0.5393, "step": 3107 }, { "epoch": 0.86, "learning_rate": 1.000902853287825e-06, "loss": 0.5398, "step": 3108 }, { "epoch": 0.86, "learning_rate": 9.969944989268843e-07, "loss": 0.5371, "step": 3109 }, { "epoch": 0.86, "learning_rate": 9.930933898421802e-07, "loss": 0.5255, "step": 3110 }, { "epoch": 0.86, "learning_rate": 9.89199529173177e-07, "loss": 0.5453, "step": 3111 }, { "epoch": 0.86, "learning_rate": 9.853129200535094e-07, "loss": 0.5396, "step": 3112 }, { "epoch": 0.86, "learning_rate": 9.814335656109675e-07, "loss": 0.5497, "step": 3113 }, { "epoch": 0.86, "learning_rate": 9.775614689675106e-07, "loss": 0.5309, "step": 3114 }, { "epoch": 0.86, "learning_rate": 9.736966332392538e-07, "loss": 0.5357, "step": 3115 }, { "epoch": 0.86, "learning_rate": 9.698390615364695e-07, "loss": 0.5303, "step": 3116 }, { "epoch": 0.86, "learning_rate": 9.659887569635862e-07, "loss": 0.5404, "step": 3117 }, { "epoch": 0.86, "learning_rate": 9.62145722619182e-07, "loss": 0.5389, "step": 3118 }, { "epoch": 0.86, "learning_rate": 9.583099615959834e-07, "loss": 0.5437, "step": 3119 }, { "epoch": 0.86, "learning_rate": 9.544814769808663e-07, "loss": 0.5281, "step": 3120 }, { "epoch": 0.86, "learning_rate": 9.506602718548496e-07, "loss": 0.5428, "step": 3121 }, { "epoch": 0.86, "learning_rate": 9.468463492930924e-07, "loss": 0.5423, "step": 3122 }, { "epoch": 0.86, "learning_rate": 9.430397123648949e-07, "loss": 0.5274, "step": 3123 }, { "epoch": 0.87, "learning_rate": 9.392403641336967e-07, "loss": 0.5418, "step": 3124 }, { "epoch": 0.87, "learning_rate": 9.354483076570642e-07, "loss": 0.5396, "step": 3125 }, { "epoch": 0.87, "learning_rate": 9.316635459867008e-07, "loss": 0.5434, "step": 3126 }, { "epoch": 0.87, "learning_rate": 9.278860821684388e-07, "loss": 0.5307, "step": 3127 }, { "epoch": 0.87, "learning_rate": 9.2411591924224e-07, "loss": 0.5151, "step": 3128 }, { "epoch": 0.87, "learning_rate": 9.203530602421862e-07, "loss": 0.53, "step": 3129 }, { "epoch": 0.87, "learning_rate": 9.165975081964851e-07, "loss": 0.5418, "step": 3130 }, { "epoch": 0.87, "learning_rate": 9.12849266127458e-07, "loss": 0.5356, "step": 3131 }, { "epoch": 0.87, "learning_rate": 9.091083370515508e-07, "loss": 0.5323, "step": 3132 }, { "epoch": 0.87, "learning_rate": 9.053747239793187e-07, "loss": 0.5386, "step": 3133 }, { "epoch": 0.87, "learning_rate": 9.016484299154338e-07, "loss": 0.5439, "step": 3134 }, { "epoch": 0.87, "learning_rate": 8.979294578586739e-07, "loss": 0.5458, "step": 3135 }, { "epoch": 0.87, "learning_rate": 8.942178108019262e-07, "loss": 0.5407, "step": 3136 }, { "epoch": 0.87, "learning_rate": 8.905134917321845e-07, "loss": 0.5409, "step": 3137 }, { "epoch": 0.87, "learning_rate": 8.868165036305431e-07, "loss": 0.5436, "step": 3138 }, { "epoch": 0.87, "learning_rate": 8.831268494721968e-07, "loss": 0.5298, "step": 3139 }, { "epoch": 0.87, "learning_rate": 8.794445322264389e-07, "loss": 0.5271, "step": 3140 }, { "epoch": 0.87, "learning_rate": 8.757695548566603e-07, "loss": 0.5354, "step": 3141 }, { "epoch": 0.87, "learning_rate": 8.721019203203407e-07, "loss": 0.5446, "step": 3142 }, { "epoch": 0.87, "learning_rate": 8.684416315690502e-07, "loss": 0.5273, "step": 3143 }, { "epoch": 0.87, "learning_rate": 8.647886915484549e-07, "loss": 0.5346, "step": 3144 }, { "epoch": 0.87, "learning_rate": 8.611431031983009e-07, "loss": 0.5234, "step": 3145 }, { "epoch": 0.87, "learning_rate": 8.575048694524168e-07, "loss": 0.5402, "step": 3146 }, { "epoch": 0.87, "learning_rate": 8.538739932387197e-07, "loss": 0.5415, "step": 3147 }, { "epoch": 0.87, "learning_rate": 8.502504774791931e-07, "loss": 0.5252, "step": 3148 }, { "epoch": 0.87, "learning_rate": 8.466343250899101e-07, "loss": 0.5175, "step": 3149 }, { "epoch": 0.87, "learning_rate": 8.430255389810093e-07, "loss": 0.5425, "step": 3150 }, { "epoch": 0.87, "learning_rate": 8.394241220567067e-07, "loss": 0.5371, "step": 3151 }, { "epoch": 0.87, "learning_rate": 8.35830077215285e-07, "loss": 0.5369, "step": 3152 }, { "epoch": 0.87, "learning_rate": 8.322434073490949e-07, "loss": 0.5429, "step": 3153 }, { "epoch": 0.87, "learning_rate": 8.286641153445507e-07, "loss": 0.5337, "step": 3154 }, { "epoch": 0.87, "learning_rate": 8.250922040821318e-07, "loss": 0.5384, "step": 3155 }, { "epoch": 0.87, "learning_rate": 8.215276764363755e-07, "loss": 0.5311, "step": 3156 }, { "epoch": 0.87, "learning_rate": 8.179705352758794e-07, "loss": 0.5404, "step": 3157 }, { "epoch": 0.87, "learning_rate": 8.144207834632956e-07, "loss": 0.5271, "step": 3158 }, { "epoch": 0.87, "learning_rate": 8.108784238553235e-07, "loss": 0.5283, "step": 3159 }, { "epoch": 0.87, "learning_rate": 8.073434593027263e-07, "loss": 0.5408, "step": 3160 }, { "epoch": 0.88, "learning_rate": 8.03815892650307e-07, "loss": 0.5475, "step": 3161 }, { "epoch": 0.88, "learning_rate": 8.002957267369161e-07, "loss": 0.5143, "step": 3162 }, { "epoch": 0.88, "learning_rate": 7.967829643954495e-07, "loss": 0.5502, "step": 3163 }, { "epoch": 0.88, "learning_rate": 7.932776084528471e-07, "loss": 0.5303, "step": 3164 }, { "epoch": 0.88, "learning_rate": 7.897796617300813e-07, "loss": 0.5366, "step": 3165 }, { "epoch": 0.88, "learning_rate": 7.86289127042168e-07, "loss": 0.5242, "step": 3166 }, { "epoch": 0.88, "learning_rate": 7.828060071981592e-07, "loss": 0.5277, "step": 3167 }, { "epoch": 0.88, "learning_rate": 7.793303050011325e-07, "loss": 0.5349, "step": 3168 }, { "epoch": 0.88, "learning_rate": 7.758620232482083e-07, "loss": 0.522, "step": 3169 }, { "epoch": 0.88, "learning_rate": 7.724011647305207e-07, "loss": 0.5321, "step": 3170 }, { "epoch": 0.88, "learning_rate": 7.689477322332395e-07, "loss": 0.5212, "step": 3171 }, { "epoch": 0.88, "learning_rate": 7.655017285355559e-07, "loss": 0.5383, "step": 3172 }, { "epoch": 0.88, "learning_rate": 7.620631564106828e-07, "loss": 0.5348, "step": 3173 }, { "epoch": 0.88, "learning_rate": 7.586320186258522e-07, "loss": 0.5505, "step": 3174 }, { "epoch": 0.88, "learning_rate": 7.55208317942312e-07, "loss": 0.5087, "step": 3175 }, { "epoch": 0.88, "learning_rate": 7.517920571153281e-07, "loss": 0.538, "step": 3176 }, { "epoch": 0.88, "learning_rate": 7.483832388941748e-07, "loss": 0.5387, "step": 3177 }, { "epoch": 0.88, "learning_rate": 7.449818660221419e-07, "loss": 0.5454, "step": 3178 }, { "epoch": 0.88, "learning_rate": 7.415879412365223e-07, "loss": 0.5387, "step": 3179 }, { "epoch": 0.88, "learning_rate": 7.3820146726862e-07, "loss": 0.529, "step": 3180 }, { "epoch": 0.88, "learning_rate": 7.348224468437404e-07, "loss": 0.5258, "step": 3181 }, { "epoch": 0.88, "learning_rate": 7.314508826811884e-07, "loss": 0.5289, "step": 3182 }, { "epoch": 0.88, "learning_rate": 7.280867774942712e-07, "loss": 0.5475, "step": 3183 }, { "epoch": 0.88, "learning_rate": 7.247301339902913e-07, "loss": 0.5389, "step": 3184 }, { "epoch": 0.88, "learning_rate": 7.213809548705509e-07, "loss": 0.5369, "step": 3185 }, { "epoch": 0.88, "learning_rate": 7.180392428303395e-07, "loss": 0.5318, "step": 3186 }, { "epoch": 0.88, "learning_rate": 7.14705000558944e-07, "loss": 0.5398, "step": 3187 }, { "epoch": 0.88, "learning_rate": 7.113782307396288e-07, "loss": 0.5486, "step": 3188 }, { "epoch": 0.88, "learning_rate": 7.08058936049657e-07, "loss": 0.5325, "step": 3189 }, { "epoch": 0.88, "learning_rate": 7.047471191602672e-07, "loss": 0.5328, "step": 3190 }, { "epoch": 0.88, "learning_rate": 7.014427827366865e-07, "loss": 0.5376, "step": 3191 }, { "epoch": 0.88, "learning_rate": 6.981459294381176e-07, "loss": 0.5332, "step": 3192 }, { "epoch": 0.88, "learning_rate": 6.948565619177427e-07, "loss": 0.5286, "step": 3193 }, { "epoch": 0.88, "learning_rate": 6.915746828227199e-07, "loss": 0.5486, "step": 3194 }, { "epoch": 0.88, "learning_rate": 6.883002947941808e-07, "loss": 0.5306, "step": 3195 }, { "epoch": 0.88, "learning_rate": 6.850334004672276e-07, "loss": 0.5494, "step": 3196 }, { "epoch": 0.89, "learning_rate": 6.81774002470933e-07, "loss": 0.5252, "step": 3197 }, { "epoch": 0.89, "learning_rate": 6.785221034283373e-07, "loss": 0.5334, "step": 3198 }, { "epoch": 0.89, "learning_rate": 6.752777059564431e-07, "loss": 0.534, "step": 3199 }, { "epoch": 0.89, "learning_rate": 6.720408126662181e-07, "loss": 0.5314, "step": 3200 }, { "epoch": 0.89, "learning_rate": 6.688114261625933e-07, "loss": 0.5343, "step": 3201 }, { "epoch": 0.89, "learning_rate": 6.655895490444541e-07, "loss": 0.5176, "step": 3202 }, { "epoch": 0.89, "learning_rate": 6.623751839046455e-07, "loss": 0.5372, "step": 3203 }, { "epoch": 0.89, "learning_rate": 6.59168333329967e-07, "loss": 0.5204, "step": 3204 }, { "epoch": 0.89, "learning_rate": 6.559689999011676e-07, "loss": 0.5311, "step": 3205 }, { "epoch": 0.89, "learning_rate": 6.527771861929499e-07, "loss": 0.5384, "step": 3206 }, { "epoch": 0.89, "learning_rate": 6.49592894773965e-07, "loss": 0.5339, "step": 3207 }, { "epoch": 0.89, "learning_rate": 6.464161282068094e-07, "loss": 0.5396, "step": 3208 }, { "epoch": 0.89, "learning_rate": 6.432468890480226e-07, "loss": 0.5307, "step": 3209 }, { "epoch": 0.89, "learning_rate": 6.400851798480889e-07, "loss": 0.5489, "step": 3210 }, { "epoch": 0.89, "learning_rate": 6.369310031514309e-07, "loss": 0.5354, "step": 3211 }, { "epoch": 0.89, "learning_rate": 6.337843614964112e-07, "loss": 0.5445, "step": 3212 }, { "epoch": 0.89, "learning_rate": 6.306452574153255e-07, "loss": 0.5381, "step": 3213 }, { "epoch": 0.89, "learning_rate": 6.275136934344072e-07, "loss": 0.5278, "step": 3214 }, { "epoch": 0.89, "learning_rate": 6.243896720738196e-07, "loss": 0.5246, "step": 3215 }, { "epoch": 0.89, "learning_rate": 6.212731958476526e-07, "loss": 0.5328, "step": 3216 }, { "epoch": 0.89, "learning_rate": 6.181642672639321e-07, "loss": 0.5358, "step": 3217 }, { "epoch": 0.89, "learning_rate": 6.150628888246035e-07, "loss": 0.5336, "step": 3218 }, { "epoch": 0.89, "learning_rate": 6.119690630255392e-07, "loss": 0.5325, "step": 3219 }, { "epoch": 0.89, "learning_rate": 6.088827923565321e-07, "loss": 0.5515, "step": 3220 }, { "epoch": 0.89, "learning_rate": 6.058040793012965e-07, "loss": 0.5354, "step": 3221 }, { "epoch": 0.89, "learning_rate": 6.027329263374604e-07, "loss": 0.5314, "step": 3222 }, { "epoch": 0.89, "learning_rate": 5.996693359365724e-07, "loss": 0.5365, "step": 3223 }, { "epoch": 0.89, "learning_rate": 5.966133105640937e-07, "loss": 0.531, "step": 3224 }, { "epoch": 0.89, "learning_rate": 5.935648526793969e-07, "loss": 0.5311, "step": 3225 }, { "epoch": 0.89, "learning_rate": 5.905239647357652e-07, "loss": 0.5336, "step": 3226 }, { "epoch": 0.89, "learning_rate": 5.874906491803922e-07, "loss": 0.5393, "step": 3227 }, { "epoch": 0.89, "learning_rate": 5.844649084543697e-07, "loss": 0.5333, "step": 3228 }, { "epoch": 0.89, "learning_rate": 5.81446744992702e-07, "loss": 0.5411, "step": 3229 }, { "epoch": 0.89, "learning_rate": 5.784361612242905e-07, "loss": 0.5314, "step": 3230 }, { "epoch": 0.89, "learning_rate": 5.754331595719398e-07, "loss": 0.5288, "step": 3231 }, { "epoch": 0.89, "learning_rate": 5.724377424523509e-07, "loss": 0.5262, "step": 3232 }, { "epoch": 0.9, "learning_rate": 5.694499122761222e-07, "loss": 0.5338, "step": 3233 }, { "epoch": 0.9, "learning_rate": 5.664696714477436e-07, "loss": 0.5397, "step": 3234 }, { "epoch": 0.9, "learning_rate": 5.634970223656023e-07, "loss": 0.5395, "step": 3235 }, { "epoch": 0.9, "learning_rate": 5.605319674219712e-07, "loss": 0.5232, "step": 3236 }, { "epoch": 0.9, "learning_rate": 5.575745090030138e-07, "loss": 0.5421, "step": 3237 }, { "epoch": 0.9, "learning_rate": 5.54624649488782e-07, "loss": 0.5451, "step": 3238 }, { "epoch": 0.9, "learning_rate": 5.516823912532088e-07, "loss": 0.535, "step": 3239 }, { "epoch": 0.9, "learning_rate": 5.487477366641114e-07, "loss": 0.5237, "step": 3240 }, { "epoch": 0.9, "learning_rate": 5.458206880831863e-07, "loss": 0.5247, "step": 3241 }, { "epoch": 0.9, "learning_rate": 5.429012478660156e-07, "loss": 0.5413, "step": 3242 }, { "epoch": 0.9, "learning_rate": 5.399894183620513e-07, "loss": 0.5424, "step": 3243 }, { "epoch": 0.9, "learning_rate": 5.370852019146244e-07, "loss": 0.5334, "step": 3244 }, { "epoch": 0.9, "learning_rate": 5.341886008609343e-07, "loss": 0.5293, "step": 3245 }, { "epoch": 0.9, "learning_rate": 5.312996175320584e-07, "loss": 0.5353, "step": 3246 }, { "epoch": 0.9, "learning_rate": 5.284182542529382e-07, "loss": 0.5387, "step": 3247 }, { "epoch": 0.9, "learning_rate": 5.255445133423875e-07, "loss": 0.5504, "step": 3248 }, { "epoch": 0.9, "learning_rate": 5.226783971130823e-07, "loss": 0.5204, "step": 3249 }, { "epoch": 0.9, "learning_rate": 5.198199078715649e-07, "loss": 0.5293, "step": 3250 }, { "epoch": 0.9, "learning_rate": 5.169690479182376e-07, "loss": 0.5272, "step": 3251 }, { "epoch": 0.9, "learning_rate": 5.141258195473642e-07, "loss": 0.5373, "step": 3252 }, { "epoch": 0.9, "learning_rate": 5.112902250470663e-07, "loss": 0.5361, "step": 3253 }, { "epoch": 0.9, "learning_rate": 5.084622666993244e-07, "loss": 0.5196, "step": 3254 }, { "epoch": 0.9, "learning_rate": 5.056419467799711e-07, "loss": 0.5352, "step": 3255 }, { "epoch": 0.9, "learning_rate": 5.02829267558691e-07, "loss": 0.5422, "step": 3256 }, { "epoch": 0.9, "learning_rate": 5.0002423129902e-07, "loss": 0.5341, "step": 3257 }, { "epoch": 0.9, "learning_rate": 4.972268402583479e-07, "loss": 0.526, "step": 3258 }, { "epoch": 0.9, "learning_rate": 4.944370966879087e-07, "loss": 0.5441, "step": 3259 }, { "epoch": 0.9, "learning_rate": 4.916550028327793e-07, "loss": 0.5318, "step": 3260 }, { "epoch": 0.9, "learning_rate": 4.88880560931887e-07, "loss": 0.539, "step": 3261 }, { "epoch": 0.9, "learning_rate": 4.86113773217991e-07, "loss": 0.5165, "step": 3262 }, { "epoch": 0.9, "learning_rate": 4.833546419177015e-07, "loss": 0.5366, "step": 3263 }, { "epoch": 0.9, "learning_rate": 4.806031692514612e-07, "loss": 0.5479, "step": 3264 }, { "epoch": 0.9, "learning_rate": 4.778593574335488e-07, "loss": 0.5359, "step": 3265 }, { "epoch": 0.9, "learning_rate": 4.751232086720825e-07, "loss": 0.5311, "step": 3266 }, { "epoch": 0.9, "learning_rate": 4.7239472516900864e-07, "loss": 0.5309, "step": 3267 }, { "epoch": 0.9, "learning_rate": 4.6967390912010857e-07, "loss": 0.5356, "step": 3268 }, { "epoch": 0.91, "learning_rate": 4.669607627149897e-07, "loss": 0.5424, "step": 3269 }, { "epoch": 0.91, "learning_rate": 4.6425528813709097e-07, "loss": 0.5393, "step": 3270 }, { "epoch": 0.91, "learning_rate": 4.61557487563673e-07, "loss": 0.521, "step": 3271 }, { "epoch": 0.91, "learning_rate": 4.588673631658269e-07, "loss": 0.523, "step": 3272 }, { "epoch": 0.91, "learning_rate": 4.561849171084565e-07, "loss": 0.5352, "step": 3273 }, { "epoch": 0.91, "learning_rate": 4.535101515502971e-07, "loss": 0.5415, "step": 3274 }, { "epoch": 0.91, "learning_rate": 4.508430686438969e-07, "loss": 0.535, "step": 3275 }, { "epoch": 0.91, "learning_rate": 4.481836705356224e-07, "loss": 0.5261, "step": 3276 }, { "epoch": 0.91, "learning_rate": 4.455319593656571e-07, "loss": 0.5211, "step": 3277 }, { "epoch": 0.91, "learning_rate": 4.428879372679962e-07, "loss": 0.5364, "step": 3278 }, { "epoch": 0.91, "learning_rate": 4.4025160637044874e-07, "loss": 0.5217, "step": 3279 }, { "epoch": 0.91, "learning_rate": 4.3762296879463204e-07, "loss": 0.5239, "step": 3280 }, { "epoch": 0.91, "learning_rate": 4.3500202665597403e-07, "loss": 0.5423, "step": 3281 }, { "epoch": 0.91, "learning_rate": 4.323887820637096e-07, "loss": 0.5327, "step": 3282 }, { "epoch": 0.91, "learning_rate": 4.297832371208799e-07, "loss": 0.5341, "step": 3283 }, { "epoch": 0.91, "learning_rate": 4.271853939243276e-07, "loss": 0.5149, "step": 3284 }, { "epoch": 0.91, "learning_rate": 4.24595254564697e-07, "loss": 0.5308, "step": 3285 }, { "epoch": 0.91, "learning_rate": 4.2201282112643403e-07, "loss": 0.537, "step": 3286 }, { "epoch": 0.91, "learning_rate": 4.1943809568778416e-07, "loss": 0.5353, "step": 3287 }, { "epoch": 0.91, "learning_rate": 4.168710803207865e-07, "loss": 0.5155, "step": 3288 }, { "epoch": 0.91, "learning_rate": 4.1431177709127743e-07, "loss": 0.5429, "step": 3289 }, { "epoch": 0.91, "learning_rate": 4.117601880588895e-07, "loss": 0.5129, "step": 3290 }, { "epoch": 0.91, "learning_rate": 4.092163152770412e-07, "loss": 0.539, "step": 3291 }, { "epoch": 0.91, "learning_rate": 4.06680160792946e-07, "loss": 0.5384, "step": 3292 }, { "epoch": 0.91, "learning_rate": 4.041517266476058e-07, "loss": 0.5313, "step": 3293 }, { "epoch": 0.91, "learning_rate": 4.016310148758051e-07, "loss": 0.5344, "step": 3294 }, { "epoch": 0.91, "learning_rate": 3.991180275061213e-07, "loss": 0.5307, "step": 3295 }, { "epoch": 0.91, "learning_rate": 3.966127665609065e-07, "loss": 0.5335, "step": 3296 }, { "epoch": 0.91, "learning_rate": 3.941152340563004e-07, "loss": 0.5307, "step": 3297 }, { "epoch": 0.91, "learning_rate": 3.916254320022228e-07, "loss": 0.5401, "step": 3298 }, { "epoch": 0.91, "learning_rate": 3.8914336240237217e-07, "loss": 0.5335, "step": 3299 }, { "epoch": 0.91, "learning_rate": 3.8666902725422394e-07, "loss": 0.5309, "step": 3300 }, { "epoch": 0.91, "learning_rate": 3.842024285490287e-07, "loss": 0.5341, "step": 3301 }, { "epoch": 0.91, "learning_rate": 3.817435682718096e-07, "loss": 0.5367, "step": 3302 }, { "epoch": 0.91, "learning_rate": 3.792924484013649e-07, "loss": 0.5248, "step": 3303 }, { "epoch": 0.91, "learning_rate": 3.768490709102635e-07, "loss": 0.5318, "step": 3304 }, { "epoch": 0.92, "learning_rate": 3.7441343776484116e-07, "loss": 0.5233, "step": 3305 }, { "epoch": 0.92, "learning_rate": 3.719855509252035e-07, "loss": 0.5168, "step": 3306 }, { "epoch": 0.92, "learning_rate": 3.695654123452208e-07, "loss": 0.5424, "step": 3307 }, { "epoch": 0.92, "learning_rate": 3.671530239725285e-07, "loss": 0.5194, "step": 3308 }, { "epoch": 0.92, "learning_rate": 3.6474838774852694e-07, "loss": 0.5258, "step": 3309 }, { "epoch": 0.92, "learning_rate": 3.6235150560837376e-07, "loss": 0.5202, "step": 3310 }, { "epoch": 0.92, "learning_rate": 3.599623794809881e-07, "loss": 0.5286, "step": 3311 }, { "epoch": 0.92, "learning_rate": 3.5758101128905096e-07, "loss": 0.5299, "step": 3312 }, { "epoch": 0.92, "learning_rate": 3.552074029489938e-07, "loss": 0.5428, "step": 3313 }, { "epoch": 0.92, "learning_rate": 3.5284155637100526e-07, "loss": 0.5258, "step": 3314 }, { "epoch": 0.92, "learning_rate": 3.5048347345903235e-07, "loss": 0.5297, "step": 3315 }, { "epoch": 0.92, "learning_rate": 3.4813315611076813e-07, "loss": 0.5271, "step": 3316 }, { "epoch": 0.92, "learning_rate": 3.457906062176597e-07, "loss": 0.5318, "step": 3317 }, { "epoch": 0.92, "learning_rate": 3.434558256649012e-07, "loss": 0.5416, "step": 3318 }, { "epoch": 0.92, "learning_rate": 3.4112881633143524e-07, "loss": 0.5365, "step": 3319 }, { "epoch": 0.92, "learning_rate": 3.3880958008995046e-07, "loss": 0.5325, "step": 3320 }, { "epoch": 0.92, "learning_rate": 3.3649811880688055e-07, "loss": 0.5315, "step": 3321 }, { "epoch": 0.92, "learning_rate": 3.3419443434240083e-07, "loss": 0.5414, "step": 3322 }, { "epoch": 0.92, "learning_rate": 3.318985285504284e-07, "loss": 0.5307, "step": 3323 }, { "epoch": 0.92, "learning_rate": 3.2961040327862183e-07, "loss": 0.5456, "step": 3324 }, { "epoch": 0.92, "learning_rate": 3.2733006036837713e-07, "loss": 0.5312, "step": 3325 }, { "epoch": 0.92, "learning_rate": 3.2505750165482853e-07, "loss": 0.5221, "step": 3326 }, { "epoch": 0.92, "learning_rate": 3.22792728966842e-07, "loss": 0.5291, "step": 3327 }, { "epoch": 0.92, "learning_rate": 3.205357441270229e-07, "loss": 0.528, "step": 3328 }, { "epoch": 0.92, "learning_rate": 3.182865489517073e-07, "loss": 0.5385, "step": 3329 }, { "epoch": 0.92, "learning_rate": 3.1604514525095833e-07, "loss": 0.5282, "step": 3330 }, { "epoch": 0.92, "learning_rate": 3.138115348285753e-07, "loss": 0.5284, "step": 3331 }, { "epoch": 0.92, "learning_rate": 3.115857194820826e-07, "loss": 0.5347, "step": 3332 }, { "epoch": 0.92, "learning_rate": 3.093677010027307e-07, "loss": 0.5453, "step": 3333 }, { "epoch": 0.92, "learning_rate": 3.071574811754985e-07, "loss": 0.5318, "step": 3334 }, { "epoch": 0.92, "learning_rate": 3.049550617790853e-07, "loss": 0.5411, "step": 3335 }, { "epoch": 0.92, "learning_rate": 3.0276044458591335e-07, "loss": 0.5291, "step": 3336 }, { "epoch": 0.92, "learning_rate": 3.005736313621288e-07, "loss": 0.5379, "step": 3337 }, { "epoch": 0.92, "learning_rate": 2.98394623867595e-07, "loss": 0.537, "step": 3338 }, { "epoch": 0.92, "learning_rate": 2.9622342385589256e-07, "loss": 0.5326, "step": 3339 }, { "epoch": 0.92, "learning_rate": 2.9406003307432485e-07, "loss": 0.5099, "step": 3340 }, { "epoch": 0.93, "learning_rate": 2.9190445326390483e-07, "loss": 0.5312, "step": 3341 }, { "epoch": 0.93, "learning_rate": 2.8975668615935815e-07, "loss": 0.5397, "step": 3342 }, { "epoch": 0.93, "learning_rate": 2.8761673348913e-07, "loss": 0.5238, "step": 3343 }, { "epoch": 0.93, "learning_rate": 2.8548459697536943e-07, "loss": 0.5368, "step": 3344 }, { "epoch": 0.93, "learning_rate": 2.8336027833394175e-07, "loss": 0.5236, "step": 3345 }, { "epoch": 0.93, "learning_rate": 2.8124377927441606e-07, "loss": 0.5284, "step": 3346 }, { "epoch": 0.93, "learning_rate": 2.7913510150007095e-07, "loss": 0.5491, "step": 3347 }, { "epoch": 0.93, "learning_rate": 2.7703424670788903e-07, "loss": 0.5344, "step": 3348 }, { "epoch": 0.93, "learning_rate": 2.74941216588559e-07, "loss": 0.5363, "step": 3349 }, { "epoch": 0.93, "learning_rate": 2.7285601282647234e-07, "loss": 0.5324, "step": 3350 }, { "epoch": 0.93, "learning_rate": 2.7077863709972227e-07, "loss": 0.5378, "step": 3351 }, { "epoch": 0.93, "learning_rate": 2.687090910801005e-07, "loss": 0.5302, "step": 3352 }, { "epoch": 0.93, "learning_rate": 2.666473764330979e-07, "loss": 0.5322, "step": 3353 }, { "epoch": 0.93, "learning_rate": 2.6459349481790633e-07, "loss": 0.5385, "step": 3354 }, { "epoch": 0.93, "learning_rate": 2.625474478874079e-07, "loss": 0.5301, "step": 3355 }, { "epoch": 0.93, "learning_rate": 2.605092372881879e-07, "loss": 0.531, "step": 3356 }, { "epoch": 0.93, "learning_rate": 2.5847886466051855e-07, "loss": 0.5349, "step": 3357 }, { "epoch": 0.93, "learning_rate": 2.5645633163836727e-07, "loss": 0.5181, "step": 3358 }, { "epoch": 0.93, "learning_rate": 2.544416398493899e-07, "loss": 0.5358, "step": 3359 }, { "epoch": 0.93, "learning_rate": 2.524347909149349e-07, "loss": 0.5278, "step": 3360 }, { "epoch": 0.93, "learning_rate": 2.504357864500373e-07, "loss": 0.5312, "step": 3361 }, { "epoch": 0.93, "learning_rate": 2.484446280634201e-07, "loss": 0.5262, "step": 3362 }, { "epoch": 0.93, "learning_rate": 2.4646131735749254e-07, "loss": 0.5408, "step": 3363 }, { "epoch": 0.93, "learning_rate": 2.4448585592834804e-07, "loss": 0.5357, "step": 3364 }, { "epoch": 0.93, "learning_rate": 2.425182453657604e-07, "loss": 0.5208, "step": 3365 }, { "epoch": 0.93, "learning_rate": 2.4055848725318963e-07, "loss": 0.5443, "step": 3366 }, { "epoch": 0.93, "learning_rate": 2.386065831677742e-07, "loss": 0.5321, "step": 3367 }, { "epoch": 0.93, "learning_rate": 2.3666253468033195e-07, "loss": 0.5232, "step": 3368 }, { "epoch": 0.93, "learning_rate": 2.3472634335535926e-07, "loss": 0.523, "step": 3369 }, { "epoch": 0.93, "learning_rate": 2.327980107510297e-07, "loss": 0.536, "step": 3370 }, { "epoch": 0.93, "learning_rate": 2.308775384191897e-07, "loss": 0.5198, "step": 3371 }, { "epoch": 0.93, "learning_rate": 2.2896492790536518e-07, "loss": 0.5365, "step": 3372 }, { "epoch": 0.93, "learning_rate": 2.2706018074875046e-07, "loss": 0.5355, "step": 3373 }, { "epoch": 0.93, "learning_rate": 2.2516329848221497e-07, "loss": 0.539, "step": 3374 }, { "epoch": 0.93, "learning_rate": 2.2327428263229756e-07, "loss": 0.5155, "step": 3375 }, { "epoch": 0.93, "learning_rate": 2.2139313471920555e-07, "loss": 0.5311, "step": 3376 }, { "epoch": 0.94, "learning_rate": 2.1951985625681348e-07, "loss": 0.5268, "step": 3377 }, { "epoch": 0.94, "learning_rate": 2.176544487526666e-07, "loss": 0.5348, "step": 3378 }, { "epoch": 0.94, "learning_rate": 2.1579691370797408e-07, "loss": 0.5384, "step": 3379 }, { "epoch": 0.94, "learning_rate": 2.1394725261760784e-07, "loss": 0.5173, "step": 3380 }, { "epoch": 0.94, "learning_rate": 2.1210546697010726e-07, "loss": 0.5304, "step": 3381 }, { "epoch": 0.94, "learning_rate": 2.1027155824766886e-07, "loss": 0.5271, "step": 3382 }, { "epoch": 0.94, "learning_rate": 2.0844552792615325e-07, "loss": 0.5305, "step": 3383 }, { "epoch": 0.94, "learning_rate": 2.0662737747508154e-07, "loss": 0.5353, "step": 3384 }, { "epoch": 0.94, "learning_rate": 2.0481710835763e-07, "loss": 0.5442, "step": 3385 }, { "epoch": 0.94, "learning_rate": 2.0301472203063664e-07, "loss": 0.5442, "step": 3386 }, { "epoch": 0.94, "learning_rate": 2.0122021994459007e-07, "loss": 0.5278, "step": 3387 }, { "epoch": 0.94, "learning_rate": 1.994336035436395e-07, "loss": 0.5213, "step": 3388 }, { "epoch": 0.94, "learning_rate": 1.9765487426558705e-07, "loss": 0.5161, "step": 3389 }, { "epoch": 0.94, "learning_rate": 1.9588403354188324e-07, "loss": 0.5311, "step": 3390 }, { "epoch": 0.94, "learning_rate": 1.9412108279763587e-07, "loss": 0.5363, "step": 3391 }, { "epoch": 0.94, "learning_rate": 1.9236602345160006e-07, "loss": 0.5392, "step": 3392 }, { "epoch": 0.94, "learning_rate": 1.9061885691618043e-07, "loss": 0.5351, "step": 3393 }, { "epoch": 0.94, "learning_rate": 1.8887958459742894e-07, "loss": 0.535, "step": 3394 }, { "epoch": 0.94, "learning_rate": 1.8714820789504816e-07, "loss": 0.539, "step": 3395 }, { "epoch": 0.94, "learning_rate": 1.8542472820238134e-07, "loss": 0.5255, "step": 3396 }, { "epoch": 0.94, "learning_rate": 1.8370914690642117e-07, "loss": 0.534, "step": 3397 }, { "epoch": 0.94, "learning_rate": 1.8200146538780327e-07, "loss": 0.5364, "step": 3398 }, { "epoch": 0.94, "learning_rate": 1.803016850208028e-07, "loss": 0.539, "step": 3399 }, { "epoch": 0.94, "learning_rate": 1.7860980717333886e-07, "loss": 0.5275, "step": 3400 }, { "epoch": 0.94, "learning_rate": 1.769258332069712e-07, "loss": 0.5348, "step": 3401 }, { "epoch": 0.94, "learning_rate": 1.7524976447689578e-07, "loss": 0.539, "step": 3402 }, { "epoch": 0.94, "learning_rate": 1.7358160233195143e-07, "loss": 0.5373, "step": 3403 }, { "epoch": 0.94, "learning_rate": 1.7192134811461093e-07, "loss": 0.5356, "step": 3404 }, { "epoch": 0.94, "learning_rate": 1.7026900316098217e-07, "loss": 0.5336, "step": 3405 }, { "epoch": 0.94, "learning_rate": 1.6862456880081146e-07, "loss": 0.5308, "step": 3406 }, { "epoch": 0.94, "learning_rate": 1.669880463574758e-07, "loss": 0.5356, "step": 3407 }, { "epoch": 0.94, "learning_rate": 1.6535943714798607e-07, "loss": 0.5441, "step": 3408 }, { "epoch": 0.94, "learning_rate": 1.6373874248298726e-07, "loss": 0.5372, "step": 3409 }, { "epoch": 0.94, "learning_rate": 1.6212596366674937e-07, "loss": 0.5299, "step": 3410 }, { "epoch": 0.94, "learning_rate": 1.605211019971775e-07, "loss": 0.5382, "step": 3411 }, { "epoch": 0.94, "learning_rate": 1.5892415876580192e-07, "loss": 0.5418, "step": 3412 }, { "epoch": 0.95, "learning_rate": 1.5733513525778343e-07, "loss": 0.541, "step": 3413 }, { "epoch": 0.95, "learning_rate": 1.5575403275190693e-07, "loss": 0.5266, "step": 3414 }, { "epoch": 0.95, "learning_rate": 1.5418085252058456e-07, "loss": 0.5405, "step": 3415 }, { "epoch": 0.95, "learning_rate": 1.526155958298492e-07, "loss": 0.5441, "step": 3416 }, { "epoch": 0.95, "learning_rate": 1.5105826393936208e-07, "loss": 0.5366, "step": 3417 }, { "epoch": 0.95, "learning_rate": 1.4950885810240401e-07, "loss": 0.5309, "step": 3418 }, { "epoch": 0.95, "learning_rate": 1.4796737956587758e-07, "loss": 0.5245, "step": 3419 }, { "epoch": 0.95, "learning_rate": 1.4643382957030717e-07, "loss": 0.5376, "step": 3420 }, { "epoch": 0.95, "learning_rate": 1.449082093498344e-07, "loss": 0.5375, "step": 3421 }, { "epoch": 0.95, "learning_rate": 1.4339052013221943e-07, "loss": 0.5372, "step": 3422 }, { "epoch": 0.95, "learning_rate": 1.4188076313884414e-07, "loss": 0.5239, "step": 3423 }, { "epoch": 0.95, "learning_rate": 1.4037893958469994e-07, "loss": 0.5408, "step": 3424 }, { "epoch": 0.95, "learning_rate": 1.3888505067839897e-07, "loss": 0.5276, "step": 3425 }, { "epoch": 0.95, "learning_rate": 1.373990976221673e-07, "loss": 0.5374, "step": 3426 }, { "epoch": 0.95, "learning_rate": 1.3592108161184058e-07, "loss": 0.5398, "step": 3427 }, { "epoch": 0.95, "learning_rate": 1.344510038368707e-07, "loss": 0.5312, "step": 3428 }, { "epoch": 0.95, "learning_rate": 1.329888654803213e-07, "loss": 0.5254, "step": 3429 }, { "epoch": 0.95, "learning_rate": 1.315346677188656e-07, "loss": 0.5481, "step": 3430 }, { "epoch": 0.95, "learning_rate": 1.300884117227874e-07, "loss": 0.547, "step": 3431 }, { "epoch": 0.95, "learning_rate": 1.2865009865597687e-07, "loss": 0.5259, "step": 3432 }, { "epoch": 0.95, "learning_rate": 1.2721972967593366e-07, "loss": 0.5319, "step": 3433 }, { "epoch": 0.95, "learning_rate": 1.2579730593376472e-07, "loss": 0.5318, "step": 3434 }, { "epoch": 0.95, "learning_rate": 1.2438282857418327e-07, "loss": 0.5403, "step": 3435 }, { "epoch": 0.95, "learning_rate": 1.2297629873550544e-07, "loss": 0.5105, "step": 3436 }, { "epoch": 0.95, "learning_rate": 1.2157771754965353e-07, "loss": 0.5335, "step": 3437 }, { "epoch": 0.95, "learning_rate": 1.20187086142155e-07, "loss": 0.5322, "step": 3438 }, { "epoch": 0.95, "learning_rate": 1.1880440563213247e-07, "loss": 0.5258, "step": 3439 }, { "epoch": 0.95, "learning_rate": 1.1742967713231801e-07, "loss": 0.52, "step": 3440 }, { "epoch": 0.95, "learning_rate": 1.160629017490389e-07, "loss": 0.5295, "step": 3441 }, { "epoch": 0.95, "learning_rate": 1.1470408058222527e-07, "loss": 0.5183, "step": 3442 }, { "epoch": 0.95, "learning_rate": 1.1335321472540462e-07, "loss": 0.5342, "step": 3443 }, { "epoch": 0.95, "learning_rate": 1.1201030526569956e-07, "loss": 0.541, "step": 3444 }, { "epoch": 0.95, "learning_rate": 1.1067535328383672e-07, "loss": 0.5373, "step": 3445 }, { "epoch": 0.95, "learning_rate": 1.0934835985413227e-07, "loss": 0.5368, "step": 3446 }, { "epoch": 0.95, "learning_rate": 1.0802932604450089e-07, "loss": 0.5382, "step": 3447 }, { "epoch": 0.95, "learning_rate": 1.0671825291645122e-07, "loss": 0.5319, "step": 3448 }, { "epoch": 0.96, "learning_rate": 1.054151415250837e-07, "loss": 0.5144, "step": 3449 }, { "epoch": 0.96, "learning_rate": 1.0411999291909391e-07, "loss": 0.5487, "step": 3450 }, { "epoch": 0.96, "learning_rate": 1.0283280814076701e-07, "loss": 0.5337, "step": 3451 }, { "epoch": 0.96, "learning_rate": 1.0155358822597993e-07, "loss": 0.5172, "step": 3452 }, { "epoch": 0.96, "learning_rate": 1.0028233420420141e-07, "loss": 0.518, "step": 3453 }, { "epoch": 0.96, "learning_rate": 9.901904709848976e-08, "loss": 0.5484, "step": 3454 }, { "epoch": 0.96, "learning_rate": 9.776372792548838e-08, "loss": 0.5361, "step": 3455 }, { "epoch": 0.96, "learning_rate": 9.651637769542921e-08, "loss": 0.5364, "step": 3456 }, { "epoch": 0.96, "learning_rate": 9.527699741213481e-08, "loss": 0.5258, "step": 3457 }, { "epoch": 0.96, "learning_rate": 9.404558807301067e-08, "loss": 0.5241, "step": 3458 }, { "epoch": 0.96, "learning_rate": 9.282215066904632e-08, "loss": 0.5345, "step": 3459 }, { "epoch": 0.96, "learning_rate": 9.160668618481971e-08, "loss": 0.5292, "step": 3460 }, { "epoch": 0.96, "learning_rate": 9.039919559848953e-08, "loss": 0.5359, "step": 3461 }, { "epoch": 0.96, "learning_rate": 8.919967988179957e-08, "loss": 0.5316, "step": 3462 }, { "epoch": 0.96, "learning_rate": 8.800814000007207e-08, "loss": 0.5399, "step": 3463 }, { "epoch": 0.96, "learning_rate": 8.682457691221447e-08, "loss": 0.5278, "step": 3464 }, { "epoch": 0.96, "learning_rate": 8.56489915707126e-08, "loss": 0.5329, "step": 3465 }, { "epoch": 0.96, "learning_rate": 8.448138492163416e-08, "loss": 0.5357, "step": 3466 }, { "epoch": 0.96, "learning_rate": 8.332175790462305e-08, "loss": 0.5471, "step": 3467 }, { "epoch": 0.96, "learning_rate": 8.217011145290388e-08, "loss": 0.5263, "step": 3468 }, { "epoch": 0.96, "learning_rate": 8.10264464932764e-08, "loss": 0.5294, "step": 3469 }, { "epoch": 0.96, "learning_rate": 7.989076394612106e-08, "loss": 0.5392, "step": 3470 }, { "epoch": 0.96, "learning_rate": 7.876306472539008e-08, "loss": 0.5153, "step": 3471 }, { "epoch": 0.96, "learning_rate": 7.764334973861531e-08, "loss": 0.536, "step": 3472 }, { "epoch": 0.96, "learning_rate": 7.653161988689705e-08, "loss": 0.5384, "step": 3473 }, { "epoch": 0.96, "learning_rate": 7.54278760649152e-08, "loss": 0.5369, "step": 3474 }, { "epoch": 0.96, "learning_rate": 7.433211916092143e-08, "loss": 0.538, "step": 3475 }, { "epoch": 0.96, "learning_rate": 7.324435005673813e-08, "loss": 0.5439, "step": 3476 }, { "epoch": 0.96, "learning_rate": 7.216456962776064e-08, "loss": 0.5233, "step": 3477 }, { "epoch": 0.96, "learning_rate": 7.109277874295495e-08, "loss": 0.5273, "step": 3478 }, { "epoch": 0.96, "learning_rate": 7.002897826485889e-08, "loss": 0.536, "step": 3479 }, { "epoch": 0.96, "learning_rate": 6.897316904957652e-08, "loss": 0.5073, "step": 3480 }, { "epoch": 0.96, "learning_rate": 6.792535194678485e-08, "loss": 0.543, "step": 3481 }, { "epoch": 0.96, "learning_rate": 6.688552779972712e-08, "loss": 0.5217, "step": 3482 }, { "epoch": 0.96, "learning_rate": 6.585369744521287e-08, "loss": 0.529, "step": 3483 }, { "epoch": 0.96, "learning_rate": 6.482986171362005e-08, "loss": 0.5319, "step": 3484 }, { "epoch": 0.96, "learning_rate": 6.381402142889404e-08, "loss": 0.5361, "step": 3485 }, { "epoch": 0.97, "learning_rate": 6.280617740854311e-08, "loss": 0.5218, "step": 3486 }, { "epoch": 0.97, "learning_rate": 6.180633046364181e-08, "loss": 0.5323, "step": 3487 }, { "epoch": 0.97, "learning_rate": 6.081448139882983e-08, "loss": 0.518, "step": 3488 }, { "epoch": 0.97, "learning_rate": 5.983063101231091e-08, "loss": 0.5406, "step": 3489 }, { "epoch": 0.97, "learning_rate": 5.885478009584611e-08, "loss": 0.5343, "step": 3490 }, { "epoch": 0.97, "learning_rate": 5.7886929434767256e-08, "loss": 0.5367, "step": 3491 }, { "epoch": 0.97, "learning_rate": 5.69270798079613e-08, "loss": 0.5261, "step": 3492 }, { "epoch": 0.97, "learning_rate": 5.597523198787924e-08, "loss": 0.5137, "step": 3493 }, { "epoch": 0.97, "learning_rate": 5.5031386740532764e-08, "loss": 0.5508, "step": 3494 }, { "epoch": 0.97, "learning_rate": 5.409554482549206e-08, "loss": 0.5372, "step": 3495 }, { "epoch": 0.97, "learning_rate": 5.316770699588691e-08, "loss": 0.5333, "step": 3496 }, { "epoch": 0.97, "learning_rate": 5.2247873998406697e-08, "loss": 0.525, "step": 3497 }, { "epoch": 0.97, "learning_rate": 5.133604657329594e-08, "loss": 0.5391, "step": 3498 }, { "epoch": 0.97, "learning_rate": 5.043222545436099e-08, "loss": 0.5311, "step": 3499 }, { "epoch": 0.97, "learning_rate": 4.9536411368963366e-08, "loss": 0.5279, "step": 3500 }, { "epoch": 0.97, "learning_rate": 4.8648605038016385e-08, "loss": 0.5228, "step": 3501 }, { "epoch": 0.97, "learning_rate": 4.7768807175996304e-08, "loss": 0.542, "step": 3502 }, { "epoch": 0.97, "learning_rate": 4.689701849092898e-08, "loss": 0.5381, "step": 3503 }, { "epoch": 0.97, "learning_rate": 4.603323968439766e-08, "loss": 0.5459, "step": 3504 }, { "epoch": 0.97, "learning_rate": 4.5177471451538503e-08, "loss": 0.5318, "step": 3505 }, { "epoch": 0.97, "learning_rate": 4.432971448104173e-08, "loss": 0.5269, "step": 3506 }, { "epoch": 0.97, "learning_rate": 4.348996945514827e-08, "loss": 0.5466, "step": 3507 }, { "epoch": 0.97, "learning_rate": 4.2658237049655325e-08, "loss": 0.5511, "step": 3508 }, { "epoch": 0.97, "learning_rate": 4.183451793390747e-08, "loss": 0.5321, "step": 3509 }, { "epoch": 0.97, "learning_rate": 4.101881277080333e-08, "loss": 0.5423, "step": 3510 }, { "epoch": 0.97, "learning_rate": 4.021112221679113e-08, "loss": 0.54, "step": 3511 }, { "epoch": 0.97, "learning_rate": 3.941144692186982e-08, "loss": 0.5346, "step": 3512 }, { "epoch": 0.97, "learning_rate": 3.861978752958795e-08, "loss": 0.5282, "step": 3513 }, { "epoch": 0.97, "learning_rate": 3.7836144677041444e-08, "loss": 0.5276, "step": 3514 }, { "epoch": 0.97, "learning_rate": 3.706051899487806e-08, "loss": 0.5309, "step": 3515 }, { "epoch": 0.97, "learning_rate": 3.629291110729072e-08, "loss": 0.5408, "step": 3516 }, { "epoch": 0.97, "learning_rate": 3.553332163202083e-08, "loss": 0.5478, "step": 3517 }, { "epoch": 0.97, "learning_rate": 3.478175118035831e-08, "loss": 0.5361, "step": 3518 }, { "epoch": 0.97, "learning_rate": 3.4038200357137116e-08, "loss": 0.5332, "step": 3519 }, { "epoch": 0.97, "learning_rate": 3.3302669760739706e-08, "loss": 0.5334, "step": 3520 }, { "epoch": 0.97, "learning_rate": 3.257515998309258e-08, "loss": 0.5274, "step": 3521 }, { "epoch": 0.98, "learning_rate": 3.1855671609668516e-08, "loss": 0.5389, "step": 3522 }, { "epoch": 0.98, "learning_rate": 3.114420521948325e-08, "loss": 0.5204, "step": 3523 }, { "epoch": 0.98, "learning_rate": 3.044076138509877e-08, "loss": 0.5262, "step": 3524 }, { "epoch": 0.98, "learning_rate": 2.9745340672620028e-08, "loss": 0.5461, "step": 3525 }, { "epoch": 0.98, "learning_rate": 2.9057943641693787e-08, "loss": 0.5374, "step": 3526 }, { "epoch": 0.98, "learning_rate": 2.8378570845511988e-08, "loss": 0.5134, "step": 3527 }, { "epoch": 0.98, "learning_rate": 2.77072228308084e-08, "loss": 0.5256, "step": 3528 }, { "epoch": 0.98, "learning_rate": 2.7043900137858624e-08, "loss": 0.536, "step": 3529 }, { "epoch": 0.98, "learning_rate": 2.6388603300478987e-08, "loss": 0.5329, "step": 3530 }, { "epoch": 0.98, "learning_rate": 2.5741332846026535e-08, "loss": 0.5366, "step": 3531 }, { "epoch": 0.98, "learning_rate": 2.5102089295400144e-08, "loss": 0.5221, "step": 3532 }, { "epoch": 0.98, "learning_rate": 2.4470873163040532e-08, "loss": 0.5385, "step": 3533 }, { "epoch": 0.98, "learning_rate": 2.384768495692358e-08, "loss": 0.5429, "step": 3534 }, { "epoch": 0.98, "learning_rate": 2.3232525178570332e-08, "loss": 0.5442, "step": 3535 }, { "epoch": 0.98, "learning_rate": 2.26253943230359e-08, "loss": 0.5295, "step": 3536 }, { "epoch": 0.98, "learning_rate": 2.202629287891722e-08, "loss": 0.5397, "step": 3537 }, { "epoch": 0.98, "learning_rate": 2.1435221328347522e-08, "loss": 0.5356, "step": 3538 }, { "epoch": 0.98, "learning_rate": 2.0852180146999635e-08, "loss": 0.5357, "step": 3539 }, { "epoch": 0.98, "learning_rate": 2.0277169804082674e-08, "loss": 0.5307, "step": 3540 }, { "epoch": 0.98, "learning_rate": 1.971019076234204e-08, "loss": 0.5372, "step": 3541 }, { "epoch": 0.98, "learning_rate": 1.9151243478061632e-08, "loss": 0.5361, "step": 3542 }, { "epoch": 0.98, "learning_rate": 1.860032840106163e-08, "loss": 0.5417, "step": 3543 }, { "epoch": 0.98, "learning_rate": 1.8057445974696274e-08, "loss": 0.535, "step": 3544 }, { "epoch": 0.98, "learning_rate": 1.7522596635857202e-08, "loss": 0.5246, "step": 3545 }, { "epoch": 0.98, "learning_rate": 1.6995780814972328e-08, "loss": 0.5324, "step": 3546 }, { "epoch": 0.98, "learning_rate": 1.64769989360003e-08, "loss": 0.5313, "step": 3547 }, { "epoch": 0.98, "learning_rate": 1.5966251416438262e-08, "loss": 0.5354, "step": 3548 }, { "epoch": 0.98, "learning_rate": 1.5463538667316313e-08, "loss": 0.5195, "step": 3549 }, { "epoch": 0.98, "learning_rate": 1.4968861093198617e-08, "loss": 0.5362, "step": 3550 }, { "epoch": 0.98, "learning_rate": 1.4482219092183392e-08, "loss": 0.5255, "step": 3551 }, { "epoch": 0.98, "learning_rate": 1.40036130559007e-08, "loss": 0.5701, "step": 3552 }, { "epoch": 0.98, "learning_rate": 1.3533043369514664e-08, "loss": 0.5226, "step": 3553 }, { "epoch": 0.98, "learning_rate": 1.307051041172236e-08, "loss": 0.5408, "step": 3554 }, { "epoch": 0.98, "learning_rate": 1.2616014554752698e-08, "loss": 0.5406, "step": 3555 }, { "epoch": 0.98, "learning_rate": 1.2169556164366436e-08, "loss": 0.5557, "step": 3556 }, { "epoch": 0.98, "learning_rate": 1.173113559985506e-08, "loss": 0.5357, "step": 3557 }, { "epoch": 0.99, "learning_rate": 1.1300753214045223e-08, "loss": 0.5252, "step": 3558 }, { "epoch": 0.99, "learning_rate": 1.0878409353289876e-08, "loss": 0.5294, "step": 3559 }, { "epoch": 0.99, "learning_rate": 1.0464104357477133e-08, "loss": 0.5409, "step": 3560 }, { "epoch": 0.99, "learning_rate": 1.0057838560022514e-08, "loss": 0.5265, "step": 3561 }, { "epoch": 0.99, "learning_rate": 9.659612287874487e-09, "loss": 0.5201, "step": 3562 }, { "epoch": 0.99, "learning_rate": 9.269425861510029e-09, "loss": 0.5378, "step": 3563 }, { "epoch": 0.99, "learning_rate": 8.887279594935737e-09, "loss": 0.5327, "step": 3564 }, { "epoch": 0.99, "learning_rate": 8.513173795687835e-09, "loss": 0.5413, "step": 3565 }, { "epoch": 0.99, "learning_rate": 8.147108764834377e-09, "loss": 0.5324, "step": 3566 }, { "epoch": 0.99, "learning_rate": 7.789084796969715e-09, "loss": 0.5353, "step": 3567 }, { "epoch": 0.99, "learning_rate": 7.439102180216706e-09, "loss": 0.532, "step": 3568 }, { "epoch": 0.99, "learning_rate": 7.0971611962300515e-09, "loss": 0.5331, "step": 3569 }, { "epoch": 0.99, "learning_rate": 6.763262120189629e-09, "loss": 0.5477, "step": 3570 }, { "epoch": 0.99, "learning_rate": 6.4374052208049375e-09, "loss": 0.5178, "step": 3571 }, { "epoch": 0.99, "learning_rate": 6.119590760313987e-09, "loss": 0.524, "step": 3572 }, { "epoch": 0.99, "learning_rate": 5.8098189944799655e-09, "loss": 0.5306, "step": 3573 }, { "epoch": 0.99, "learning_rate": 5.508090172596792e-09, "loss": 0.5282, "step": 3574 }, { "epoch": 0.99, "learning_rate": 5.214404537483564e-09, "loss": 0.5194, "step": 3575 }, { "epoch": 0.99, "learning_rate": 4.928762325489001e-09, "loss": 0.522, "step": 3576 }, { "epoch": 0.99, "learning_rate": 4.651163766484779e-09, "loss": 0.5283, "step": 3577 }, { "epoch": 0.99, "learning_rate": 4.381609083872196e-09, "loss": 0.5251, "step": 3578 }, { "epoch": 0.99, "learning_rate": 4.120098494579949e-09, "loss": 0.5228, "step": 3579 }, { "epoch": 0.99, "learning_rate": 3.866632209060805e-09, "loss": 0.5336, "step": 3580 }, { "epoch": 0.99, "learning_rate": 3.6212104312949304e-09, "loss": 0.5288, "step": 3581 }, { "epoch": 0.99, "learning_rate": 3.3838333587887797e-09, "loss": 0.53, "step": 3582 }, { "epoch": 0.99, "learning_rate": 3.154501182573988e-09, "loss": 0.5423, "step": 3583 }, { "epoch": 0.99, "learning_rate": 2.93321408720737e-09, "loss": 0.5295, "step": 3584 }, { "epoch": 0.99, "learning_rate": 2.7199722507742497e-09, "loss": 0.5349, "step": 3585 }, { "epoch": 0.99, "learning_rate": 2.514775844882911e-09, "loss": 0.5296, "step": 3586 }, { "epoch": 0.99, "learning_rate": 2.3176250346679253e-09, "loss": 0.5274, "step": 3587 }, { "epoch": 0.99, "learning_rate": 2.128519978786825e-09, "loss": 0.5349, "step": 3588 }, { "epoch": 0.99, "learning_rate": 1.9474608294267618e-09, "loss": 0.5323, "step": 3589 }, { "epoch": 0.99, "learning_rate": 1.7744477322956256e-09, "loss": 0.5306, "step": 3590 }, { "epoch": 0.99, "learning_rate": 1.6094808266275963e-09, "loss": 0.5281, "step": 3591 }, { "epoch": 0.99, "learning_rate": 1.4525602451831433e-09, "loss": 0.5384, "step": 3592 }, { "epoch": 0.99, "learning_rate": 1.3036861142456947e-09, "loss": 0.5266, "step": 3593 }, { "epoch": 1.0, "learning_rate": 1.1628585536216374e-09, "loss": 0.5248, "step": 3594 }, { "epoch": 1.0, "learning_rate": 1.0300776766458687e-09, "loss": 0.5438, "step": 3595 }, { "epoch": 1.0, "learning_rate": 9.05343590175134e-10, "loss": 0.5269, "step": 3596 }, { "epoch": 1.0, "learning_rate": 7.886563945891379e-10, "loss": 0.53, "step": 3597 }, { "epoch": 1.0, "learning_rate": 6.800161837938746e-10, "loss": 0.531, "step": 3598 }, { "epoch": 1.0, "learning_rate": 5.794230452205174e-10, "loss": 0.5355, "step": 3599 }, { "epoch": 1.0, "learning_rate": 4.86877059819868e-10, "loss": 0.5171, "step": 3600 }, { "epoch": 1.0, "learning_rate": 4.023783020723482e-10, "loss": 0.5426, "step": 3601 }, { "epoch": 1.0, "learning_rate": 3.259268399768978e-10, "loss": 0.5293, "step": 3602 }, { "epoch": 1.0, "learning_rate": 2.575227350598564e-10, "loss": 0.5348, "step": 3603 }, { "epoch": 1.0, "learning_rate": 1.9716604236941217e-10, "loss": 0.5366, "step": 3604 }, { "epoch": 1.0, "learning_rate": 1.4485681048004296e-10, "loss": 0.5226, "step": 3605 }, { "epoch": 1.0, "learning_rate": 1.0059508148696495e-10, "loss": 0.5302, "step": 3606 }, { "epoch": 1.0, "learning_rate": 6.438089100946343e-11, "loss": 0.5377, "step": 3607 }, { "epoch": 1.0, "learning_rate": 3.621426819311324e-11, "loss": 0.5365, "step": 3608 }, { "epoch": 1.0, "learning_rate": 1.6095235705337884e-11, "loss": 0.5246, "step": 3609 }, { "epoch": 1.0, "learning_rate": 4.023809735409501e-12, "loss": 0.5257, "step": 3610 }, { "epoch": 1.0, "learning_rate": 0.0, "loss": 0.5284, "step": 3611 }, { "epoch": 1.0, "step": 3611, "total_flos": 0.0, "train_loss": 0.1944329670280408, "train_runtime": 7973.1948, "train_samples_per_second": 232.4, "train_steps_per_second": 0.453 } ], "logging_steps": 1.0, "max_steps": 3611, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "total_flos": 0.0, "train_batch_size": 16, "trial_name": null, "trial_params": null }