{ "best_metric": null, "best_model_checkpoint": null, "epoch": 12.849162011173185, "eval_steps": 500, "global_step": 2300, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.01, "learning_rate": 2.0000000000000003e-06, "loss": 0.5639, "step": 1 }, { "epoch": 0.01, "learning_rate": 4.000000000000001e-06, "loss": 0.523, "step": 2 }, { "epoch": 0.02, "learning_rate": 6e-06, "loss": 0.5605, "step": 3 }, { "epoch": 0.02, "learning_rate": 8.000000000000001e-06, "loss": 0.5007, "step": 4 }, { "epoch": 0.03, "learning_rate": 1e-05, "loss": 0.5535, "step": 5 }, { "epoch": 0.03, "learning_rate": 1.2e-05, "loss": 0.5704, "step": 6 }, { "epoch": 0.04, "learning_rate": 1.4e-05, "loss": 0.4885, "step": 7 }, { "epoch": 0.04, "learning_rate": 1.6000000000000003e-05, "loss": 0.5169, "step": 8 }, { "epoch": 0.05, "learning_rate": 1.8e-05, "loss": 0.4672, "step": 9 }, { "epoch": 0.06, "learning_rate": 2e-05, "loss": 0.5092, "step": 10 }, { "epoch": 0.06, "learning_rate": 1.9999999382560078e-05, "loss": 0.4805, "step": 11 }, { "epoch": 0.07, "learning_rate": 1.9999997530240382e-05, "loss": 0.3715, "step": 12 }, { "epoch": 0.07, "learning_rate": 1.9999994443041144e-05, "loss": 0.6066, "step": 13 }, { "epoch": 0.08, "learning_rate": 1.9999990120962743e-05, "loss": 0.5437, "step": 14 }, { "epoch": 0.08, "learning_rate": 1.999998456400572e-05, "loss": 0.5675, "step": 15 }, { "epoch": 0.09, "learning_rate": 1.9999977772170748e-05, "loss": 0.5232, "step": 16 }, { "epoch": 0.09, "learning_rate": 1.9999969745458677e-05, "loss": 0.6899, "step": 17 }, { "epoch": 0.1, "learning_rate": 1.9999960483870494e-05, "loss": 0.5324, "step": 18 }, { "epoch": 0.11, "learning_rate": 1.9999949987407342e-05, "loss": 0.4336, "step": 19 }, { "epoch": 0.11, "learning_rate": 1.999993825607052e-05, "loss": 0.5189, "step": 20 }, { "epoch": 0.12, "learning_rate": 1.9999925289861474e-05, "loss": 0.4484, "step": 21 }, { "epoch": 0.12, "learning_rate": 1.9999911088781804e-05, "loss": 0.4517, "step": 22 }, { "epoch": 0.13, "learning_rate": 1.999989565283327e-05, "loss": 0.422, "step": 23 }, { "epoch": 0.13, "learning_rate": 1.9999878982017772e-05, "loss": 0.4121, "step": 24 }, { "epoch": 0.14, "learning_rate": 1.999986107633737e-05, "loss": 0.6525, "step": 25 }, { "epoch": 0.15, "learning_rate": 1.999984193579428e-05, "loss": 0.5514, "step": 26 }, { "epoch": 0.15, "learning_rate": 1.9999821560390854e-05, "loss": 0.321, "step": 27 }, { "epoch": 0.16, "learning_rate": 1.999979995012962e-05, "loss": 0.3338, "step": 28 }, { "epoch": 0.16, "learning_rate": 1.999977710501324e-05, "loss": 0.4814, "step": 29 }, { "epoch": 0.17, "learning_rate": 1.9999753025044538e-05, "loss": 0.5416, "step": 30 }, { "epoch": 0.17, "learning_rate": 1.9999727710226486e-05, "loss": 0.3857, "step": 31 }, { "epoch": 0.18, "learning_rate": 1.9999701160562214e-05, "loss": 0.2406, "step": 32 }, { "epoch": 0.18, "learning_rate": 1.9999673376054995e-05, "loss": 0.4272, "step": 33 }, { "epoch": 0.19, "learning_rate": 1.9999644356708262e-05, "loss": 0.4427, "step": 34 }, { "epoch": 0.2, "learning_rate": 1.99996141025256e-05, "loss": 0.4703, "step": 35 }, { "epoch": 0.2, "learning_rate": 1.9999582613510742e-05, "loss": 0.3708, "step": 36 }, { "epoch": 0.21, "learning_rate": 1.9999549889667583e-05, "loss": 0.4465, "step": 37 }, { "epoch": 0.21, "learning_rate": 1.999951593100015e-05, "loss": 0.6089, "step": 38 }, { "epoch": 0.22, "learning_rate": 1.9999480737512657e-05, "loss": 0.5205, "step": 39 }, { "epoch": 0.22, "learning_rate": 1.9999444309209432e-05, "loss": 0.439, "step": 40 }, { "epoch": 0.23, "learning_rate": 1.9999406646094984e-05, "loss": 0.4799, "step": 41 }, { "epoch": 0.23, "learning_rate": 1.999936774817396e-05, "loss": 0.4778, "step": 42 }, { "epoch": 0.24, "learning_rate": 1.9999327615451162e-05, "loss": 0.4951, "step": 43 }, { "epoch": 0.25, "learning_rate": 1.999928624793155e-05, "loss": 0.5252, "step": 44 }, { "epoch": 0.25, "learning_rate": 1.999924364562023e-05, "loss": 0.4139, "step": 45 }, { "epoch": 0.26, "learning_rate": 1.999919980852246e-05, "loss": 0.5536, "step": 46 }, { "epoch": 0.26, "learning_rate": 1.999915473664366e-05, "loss": 0.445, "step": 47 }, { "epoch": 0.27, "learning_rate": 1.9999108429989393e-05, "loss": 0.4244, "step": 48 }, { "epoch": 0.27, "learning_rate": 1.9999060888565372e-05, "loss": 0.3665, "step": 49 }, { "epoch": 0.28, "learning_rate": 1.9999012112377473e-05, "loss": 0.4229, "step": 50 }, { "epoch": 0.28, "learning_rate": 1.999896210143172e-05, "loss": 0.3388, "step": 51 }, { "epoch": 0.29, "learning_rate": 1.999891085573429e-05, "loss": 0.4925, "step": 52 }, { "epoch": 0.3, "learning_rate": 1.9998858375291504e-05, "loss": 0.4661, "step": 53 }, { "epoch": 0.3, "learning_rate": 1.999880466010985e-05, "loss": 0.5506, "step": 54 }, { "epoch": 0.31, "learning_rate": 1.9998749710195957e-05, "loss": 0.3348, "step": 55 }, { "epoch": 0.31, "learning_rate": 1.999869352555661e-05, "loss": 0.4395, "step": 56 }, { "epoch": 0.32, "learning_rate": 1.9998636106198752e-05, "loss": 0.4226, "step": 57 }, { "epoch": 0.32, "learning_rate": 1.999857745212947e-05, "loss": 0.3843, "step": 58 }, { "epoch": 0.33, "learning_rate": 1.999851756335601e-05, "loss": 0.3234, "step": 59 }, { "epoch": 0.34, "learning_rate": 1.9998456439885763e-05, "loss": 0.4064, "step": 60 }, { "epoch": 0.34, "learning_rate": 1.999839408172628e-05, "loss": 0.4355, "step": 61 }, { "epoch": 0.35, "learning_rate": 1.999833048888526e-05, "loss": 0.3955, "step": 62 }, { "epoch": 0.35, "learning_rate": 1.999826566137056e-05, "loss": 0.3745, "step": 63 }, { "epoch": 0.36, "learning_rate": 1.9998199599190177e-05, "loss": 0.3199, "step": 64 }, { "epoch": 0.36, "learning_rate": 1.999813230235228e-05, "loss": 0.3629, "step": 65 }, { "epoch": 0.37, "learning_rate": 1.999806377086517e-05, "loss": 0.6275, "step": 66 }, { "epoch": 0.37, "learning_rate": 1.9997994004737314e-05, "loss": 0.466, "step": 67 }, { "epoch": 0.38, "learning_rate": 1.9997923003977328e-05, "loss": 0.4152, "step": 68 }, { "epoch": 0.39, "learning_rate": 1.999785076859398e-05, "loss": 0.3625, "step": 69 }, { "epoch": 0.39, "learning_rate": 1.999777729859618e-05, "loss": 0.4664, "step": 70 }, { "epoch": 0.4, "learning_rate": 1.9997702593993017e-05, "loss": 0.3131, "step": 71 }, { "epoch": 0.4, "learning_rate": 1.9997626654793708e-05, "loss": 0.3116, "step": 72 }, { "epoch": 0.41, "learning_rate": 1.999754948100763e-05, "loss": 0.4347, "step": 73 }, { "epoch": 0.41, "learning_rate": 1.9997471072644314e-05, "loss": 0.346, "step": 74 }, { "epoch": 0.42, "learning_rate": 1.999739142971344e-05, "loss": 0.2731, "step": 75 }, { "epoch": 0.42, "learning_rate": 1.9997310552224848e-05, "loss": 0.4508, "step": 76 }, { "epoch": 0.43, "learning_rate": 1.999722844018852e-05, "loss": 0.3526, "step": 77 }, { "epoch": 0.44, "learning_rate": 1.99971450936146e-05, "loss": 0.2851, "step": 78 }, { "epoch": 0.44, "learning_rate": 1.999706051251338e-05, "loss": 0.3666, "step": 79 }, { "epoch": 0.45, "learning_rate": 1.9996974696895304e-05, "loss": 0.4183, "step": 80 }, { "epoch": 0.45, "learning_rate": 1.999688764677097e-05, "loss": 0.3246, "step": 81 }, { "epoch": 0.46, "learning_rate": 1.9996799362151124e-05, "loss": 0.2945, "step": 82 }, { "epoch": 0.46, "learning_rate": 1.999670984304667e-05, "loss": 0.3642, "step": 83 }, { "epoch": 0.47, "learning_rate": 1.9996619089468664e-05, "loss": 0.5029, "step": 84 }, { "epoch": 0.47, "learning_rate": 1.999652710142831e-05, "loss": 0.3426, "step": 85 }, { "epoch": 0.48, "learning_rate": 1.9996433878936973e-05, "loss": 0.2988, "step": 86 }, { "epoch": 0.49, "learning_rate": 1.999633942200616e-05, "loss": 0.4024, "step": 87 }, { "epoch": 0.49, "learning_rate": 1.9996243730647538e-05, "loss": 0.3864, "step": 88 }, { "epoch": 0.5, "learning_rate": 1.999614680487292e-05, "loss": 0.3703, "step": 89 }, { "epoch": 0.5, "learning_rate": 1.999604864469428e-05, "loss": 0.4415, "step": 90 }, { "epoch": 0.51, "learning_rate": 1.9995949250123737e-05, "loss": 0.3173, "step": 91 }, { "epoch": 0.51, "learning_rate": 1.9995848621173564e-05, "loss": 0.351, "step": 92 }, { "epoch": 0.52, "learning_rate": 1.9995746757856192e-05, "loss": 0.3982, "step": 93 }, { "epoch": 0.53, "learning_rate": 1.999564366018419e-05, "loss": 0.379, "step": 94 }, { "epoch": 0.53, "learning_rate": 1.99955393281703e-05, "loss": 0.2982, "step": 95 }, { "epoch": 0.54, "learning_rate": 1.9995433761827405e-05, "loss": 0.3524, "step": 96 }, { "epoch": 0.54, "learning_rate": 1.9995326961168532e-05, "loss": 0.4431, "step": 97 }, { "epoch": 0.55, "learning_rate": 1.999521892620688e-05, "loss": 0.3808, "step": 98 }, { "epoch": 0.55, "learning_rate": 1.999510965695578e-05, "loss": 0.2937, "step": 99 }, { "epoch": 0.56, "learning_rate": 1.9994999153428737e-05, "loss": 0.2993, "step": 100 }, { "epoch": 0.56, "learning_rate": 1.9994887415639387e-05, "loss": 0.2938, "step": 101 }, { "epoch": 0.57, "learning_rate": 1.9994774443601535e-05, "loss": 0.2689, "step": 102 }, { "epoch": 0.58, "learning_rate": 1.9994660237329125e-05, "loss": 0.4035, "step": 103 }, { "epoch": 0.58, "learning_rate": 1.9994544796836267e-05, "loss": 0.3158, "step": 104 }, { "epoch": 0.59, "learning_rate": 1.999442812213721e-05, "loss": 0.337, "step": 105 }, { "epoch": 0.59, "learning_rate": 1.999431021324637e-05, "loss": 0.3668, "step": 106 }, { "epoch": 0.6, "learning_rate": 1.99941910701783e-05, "loss": 0.4087, "step": 107 }, { "epoch": 0.6, "learning_rate": 1.9994070692947714e-05, "loss": 0.45, "step": 108 }, { "epoch": 0.61, "learning_rate": 1.999394908156948e-05, "loss": 0.3512, "step": 109 }, { "epoch": 0.61, "learning_rate": 1.9993826236058612e-05, "loss": 0.3683, "step": 110 }, { "epoch": 0.62, "learning_rate": 1.9993702156430282e-05, "loss": 0.4958, "step": 111 }, { "epoch": 0.63, "learning_rate": 1.9993576842699817e-05, "loss": 0.3312, "step": 112 }, { "epoch": 0.63, "learning_rate": 1.9993450294882683e-05, "loss": 0.2844, "step": 113 }, { "epoch": 0.64, "learning_rate": 1.9993322512994514e-05, "loss": 0.4746, "step": 114 }, { "epoch": 0.64, "learning_rate": 1.9993193497051084e-05, "loss": 0.3431, "step": 115 }, { "epoch": 0.65, "learning_rate": 1.999306324706833e-05, "loss": 0.3289, "step": 116 }, { "epoch": 0.65, "learning_rate": 1.999293176306233e-05, "loss": 0.371, "step": 117 }, { "epoch": 0.66, "learning_rate": 1.999279904504933e-05, "loss": 0.46, "step": 118 }, { "epoch": 0.66, "learning_rate": 1.999266509304571e-05, "loss": 0.3324, "step": 119 }, { "epoch": 0.67, "learning_rate": 1.9992529907068015e-05, "loss": 0.376, "step": 120 }, { "epoch": 0.68, "learning_rate": 1.999239348713294e-05, "loss": 0.4265, "step": 121 }, { "epoch": 0.68, "learning_rate": 1.999225583325733e-05, "loss": 0.2804, "step": 122 }, { "epoch": 0.69, "learning_rate": 1.9992116945458184e-05, "loss": 0.3307, "step": 123 }, { "epoch": 0.69, "learning_rate": 1.9991976823752655e-05, "loss": 0.3308, "step": 124 }, { "epoch": 0.7, "learning_rate": 1.999183546815804e-05, "loss": 0.2469, "step": 125 }, { "epoch": 0.7, "learning_rate": 1.99916928786918e-05, "loss": 0.3649, "step": 126 }, { "epoch": 0.71, "learning_rate": 1.9991549055371547e-05, "loss": 0.3082, "step": 127 }, { "epoch": 0.72, "learning_rate": 1.999140399821503e-05, "loss": 0.4419, "step": 128 }, { "epoch": 0.72, "learning_rate": 1.999125770724017e-05, "loss": 0.3784, "step": 129 }, { "epoch": 0.73, "learning_rate": 1.9991110182465032e-05, "loss": 0.3559, "step": 130 }, { "epoch": 0.73, "learning_rate": 1.9990961423907832e-05, "loss": 0.4342, "step": 131 }, { "epoch": 0.74, "learning_rate": 1.9990811431586938e-05, "loss": 0.3429, "step": 132 }, { "epoch": 0.74, "learning_rate": 1.9990660205520875e-05, "loss": 0.4045, "step": 133 }, { "epoch": 0.75, "learning_rate": 1.999050774572832e-05, "loss": 0.3441, "step": 134 }, { "epoch": 0.75, "learning_rate": 1.999035405222809e-05, "loss": 0.3062, "step": 135 }, { "epoch": 0.76, "learning_rate": 1.9990199125039174e-05, "loss": 0.3303, "step": 136 }, { "epoch": 0.77, "learning_rate": 1.9990042964180702e-05, "loss": 0.2451, "step": 137 }, { "epoch": 0.77, "learning_rate": 1.9989885569671957e-05, "loss": 0.2744, "step": 138 }, { "epoch": 0.78, "learning_rate": 1.998972694153237e-05, "loss": 0.3415, "step": 139 }, { "epoch": 0.78, "learning_rate": 1.998956707978154e-05, "loss": 0.3089, "step": 140 }, { "epoch": 0.79, "learning_rate": 1.99894059844392e-05, "loss": 0.3302, "step": 141 }, { "epoch": 0.79, "learning_rate": 1.9989243655525248e-05, "loss": 0.3878, "step": 142 }, { "epoch": 0.8, "learning_rate": 1.998908009305973e-05, "loss": 0.3341, "step": 143 }, { "epoch": 0.8, "learning_rate": 1.9988915297062836e-05, "loss": 0.4315, "step": 144 }, { "epoch": 0.81, "learning_rate": 1.998874926755492e-05, "loss": 0.3872, "step": 145 }, { "epoch": 0.82, "learning_rate": 1.9988582004556493e-05, "loss": 0.2623, "step": 146 }, { "epoch": 0.82, "learning_rate": 1.99884135080882e-05, "loss": 0.3137, "step": 147 }, { "epoch": 0.83, "learning_rate": 1.9988243778170853e-05, "loss": 0.2951, "step": 148 }, { "epoch": 0.83, "learning_rate": 1.998807281482541e-05, "loss": 0.3506, "step": 149 }, { "epoch": 0.84, "learning_rate": 1.998790061807298e-05, "loss": 0.398, "step": 150 }, { "epoch": 0.84, "learning_rate": 1.9987727187934838e-05, "loss": 0.4126, "step": 151 }, { "epoch": 0.85, "learning_rate": 1.998755252443239e-05, "loss": 0.2773, "step": 152 }, { "epoch": 0.85, "learning_rate": 1.9987376627587208e-05, "loss": 0.3595, "step": 153 }, { "epoch": 0.86, "learning_rate": 1.998719949742101e-05, "loss": 0.2496, "step": 154 }, { "epoch": 0.87, "learning_rate": 1.9987021133955676e-05, "loss": 0.3718, "step": 155 }, { "epoch": 0.87, "learning_rate": 1.9986841537213227e-05, "loss": 0.3203, "step": 156 }, { "epoch": 0.88, "learning_rate": 1.9986660707215845e-05, "loss": 0.294, "step": 157 }, { "epoch": 0.88, "learning_rate": 1.9986478643985854e-05, "loss": 0.4197, "step": 158 }, { "epoch": 0.89, "learning_rate": 1.9986295347545738e-05, "loss": 0.2606, "step": 159 }, { "epoch": 0.89, "learning_rate": 1.998611081791814e-05, "loss": 0.3505, "step": 160 }, { "epoch": 0.9, "learning_rate": 1.998592505512584e-05, "loss": 0.216, "step": 161 }, { "epoch": 0.91, "learning_rate": 1.998573805919178e-05, "loss": 0.2629, "step": 162 }, { "epoch": 0.91, "learning_rate": 1.9985549830139046e-05, "loss": 0.2815, "step": 163 }, { "epoch": 0.92, "learning_rate": 1.998536036799089e-05, "loss": 0.3153, "step": 164 }, { "epoch": 0.92, "learning_rate": 1.9985169672770706e-05, "loss": 0.2682, "step": 165 }, { "epoch": 0.93, "learning_rate": 1.9984977744502038e-05, "loss": 0.2852, "step": 166 }, { "epoch": 0.93, "learning_rate": 1.9984784583208593e-05, "loss": 0.3352, "step": 167 }, { "epoch": 0.94, "learning_rate": 1.998459018891422e-05, "loss": 0.3192, "step": 168 }, { "epoch": 0.94, "learning_rate": 1.9984394561642927e-05, "loss": 0.3007, "step": 169 }, { "epoch": 0.95, "learning_rate": 1.998419770141887e-05, "loss": 0.3568, "step": 170 }, { "epoch": 0.96, "learning_rate": 1.9983999608266358e-05, "loss": 0.304, "step": 171 }, { "epoch": 0.96, "learning_rate": 1.9983800282209857e-05, "loss": 0.3827, "step": 172 }, { "epoch": 0.97, "learning_rate": 1.9983599723273977e-05, "loss": 0.3288, "step": 173 }, { "epoch": 0.97, "learning_rate": 1.9983397931483488e-05, "loss": 0.3792, "step": 174 }, { "epoch": 0.98, "learning_rate": 1.9983194906863305e-05, "loss": 0.2607, "step": 175 }, { "epoch": 0.98, "learning_rate": 1.99829906494385e-05, "loss": 0.3564, "step": 176 }, { "epoch": 0.99, "learning_rate": 1.9982785159234303e-05, "loss": 0.2249, "step": 177 }, { "epoch": 0.99, "learning_rate": 1.9982578436276084e-05, "loss": 0.4433, "step": 178 }, { "epoch": 1.0, "learning_rate": 1.998237048058937e-05, "loss": 0.2772, "step": 179 }, { "epoch": 1.01, "learning_rate": 1.998216129219984e-05, "loss": 0.2786, "step": 180 }, { "epoch": 1.01, "learning_rate": 1.9981950871133328e-05, "loss": 0.3673, "step": 181 }, { "epoch": 1.02, "learning_rate": 1.998173921741582e-05, "loss": 0.3359, "step": 182 }, { "epoch": 1.02, "learning_rate": 1.9981526331073452e-05, "loss": 0.309, "step": 183 }, { "epoch": 1.03, "learning_rate": 1.9981312212132514e-05, "loss": 0.3069, "step": 184 }, { "epoch": 1.03, "learning_rate": 1.9981096860619444e-05, "loss": 0.355, "step": 185 }, { "epoch": 1.04, "learning_rate": 1.9980880276560834e-05, "loss": 0.3134, "step": 186 }, { "epoch": 1.04, "learning_rate": 1.9980662459983437e-05, "loss": 0.2645, "step": 187 }, { "epoch": 1.05, "learning_rate": 1.998044341091414e-05, "loss": 0.3281, "step": 188 }, { "epoch": 1.06, "learning_rate": 1.998022312938001e-05, "loss": 0.233, "step": 189 }, { "epoch": 1.06, "learning_rate": 1.9980001615408228e-05, "loss": 0.2203, "step": 190 }, { "epoch": 1.07, "learning_rate": 1.9979778869026162e-05, "loss": 0.3071, "step": 191 }, { "epoch": 1.07, "learning_rate": 1.9979554890261316e-05, "loss": 0.2971, "step": 192 }, { "epoch": 1.08, "learning_rate": 1.9979329679141344e-05, "loss": 0.2276, "step": 193 }, { "epoch": 1.08, "learning_rate": 1.9979103235694065e-05, "loss": 0.3139, "step": 194 }, { "epoch": 1.09, "learning_rate": 1.9978875559947435e-05, "loss": 0.2064, "step": 195 }, { "epoch": 1.09, "learning_rate": 1.997864665192957e-05, "loss": 0.3846, "step": 196 }, { "epoch": 1.1, "learning_rate": 1.9978416511668746e-05, "loss": 0.2338, "step": 197 }, { "epoch": 1.11, "learning_rate": 1.997818513919337e-05, "loss": 0.2316, "step": 198 }, { "epoch": 1.11, "learning_rate": 1.997795253453202e-05, "loss": 0.2463, "step": 199 }, { "epoch": 1.12, "learning_rate": 1.9977718697713425e-05, "loss": 0.3939, "step": 200 }, { "epoch": 1.12, "learning_rate": 1.997748362876645e-05, "loss": 0.2862, "step": 201 }, { "epoch": 1.13, "learning_rate": 1.9977247327720128e-05, "loss": 0.3106, "step": 202 }, { "epoch": 1.13, "learning_rate": 1.997700979460364e-05, "loss": 0.2795, "step": 203 }, { "epoch": 1.14, "learning_rate": 1.9976771029446323e-05, "loss": 0.2505, "step": 204 }, { "epoch": 1.15, "learning_rate": 1.9976531032277653e-05, "loss": 0.3097, "step": 205 }, { "epoch": 1.15, "learning_rate": 1.9976289803127273e-05, "loss": 0.2426, "step": 206 }, { "epoch": 1.16, "learning_rate": 1.9976047342024967e-05, "loss": 0.2867, "step": 207 }, { "epoch": 1.16, "learning_rate": 1.9975803649000684e-05, "loss": 0.2614, "step": 208 }, { "epoch": 1.17, "learning_rate": 1.9975558724084506e-05, "loss": 0.4878, "step": 209 }, { "epoch": 1.17, "learning_rate": 1.9975312567306687e-05, "loss": 0.2145, "step": 210 }, { "epoch": 1.18, "learning_rate": 1.997506517869762e-05, "loss": 0.289, "step": 211 }, { "epoch": 1.18, "learning_rate": 1.9974816558287856e-05, "loss": 0.2146, "step": 212 }, { "epoch": 1.19, "learning_rate": 1.9974566706108102e-05, "loss": 0.217, "step": 213 }, { "epoch": 1.2, "learning_rate": 1.99743156221892e-05, "loss": 0.3059, "step": 214 }, { "epoch": 1.2, "learning_rate": 1.9974063306562167e-05, "loss": 0.2464, "step": 215 }, { "epoch": 1.21, "learning_rate": 1.9973809759258155e-05, "loss": 0.3306, "step": 216 }, { "epoch": 1.21, "learning_rate": 1.9973554980308474e-05, "loss": 0.5111, "step": 217 }, { "epoch": 1.22, "learning_rate": 1.9973298969744588e-05, "loss": 0.2556, "step": 218 }, { "epoch": 1.22, "learning_rate": 1.997304172759811e-05, "loss": 0.3047, "step": 219 }, { "epoch": 1.23, "learning_rate": 1.997278325390081e-05, "loss": 0.2128, "step": 220 }, { "epoch": 1.23, "learning_rate": 1.99725235486846e-05, "loss": 0.3684, "step": 221 }, { "epoch": 1.24, "learning_rate": 1.9972262611981556e-05, "loss": 0.2963, "step": 222 }, { "epoch": 1.25, "learning_rate": 1.9972000443823897e-05, "loss": 0.2385, "step": 223 }, { "epoch": 1.25, "learning_rate": 1.9971737044244e-05, "loss": 0.2601, "step": 224 }, { "epoch": 1.26, "learning_rate": 1.9971472413274392e-05, "loss": 0.2066, "step": 225 }, { "epoch": 1.26, "learning_rate": 1.9971206550947748e-05, "loss": 0.2155, "step": 226 }, { "epoch": 1.27, "learning_rate": 1.9970939457296902e-05, "loss": 0.2643, "step": 227 }, { "epoch": 1.27, "learning_rate": 1.9970671132354836e-05, "loss": 0.2058, "step": 228 }, { "epoch": 1.28, "learning_rate": 1.9970401576154684e-05, "loss": 0.254, "step": 229 }, { "epoch": 1.28, "learning_rate": 1.9970130788729737e-05, "loss": 0.2438, "step": 230 }, { "epoch": 1.29, "learning_rate": 1.996985877011343e-05, "loss": 0.2357, "step": 231 }, { "epoch": 1.3, "learning_rate": 1.9969585520339355e-05, "loss": 0.3697, "step": 232 }, { "epoch": 1.3, "learning_rate": 1.9969311039441254e-05, "loss": 0.2996, "step": 233 }, { "epoch": 1.31, "learning_rate": 1.9969035327453024e-05, "loss": 0.1758, "step": 234 }, { "epoch": 1.31, "learning_rate": 1.9968758384408715e-05, "loss": 0.2199, "step": 235 }, { "epoch": 1.32, "learning_rate": 1.9968480210342515e-05, "loss": 0.1951, "step": 236 }, { "epoch": 1.32, "learning_rate": 1.9968200805288788e-05, "loss": 0.3515, "step": 237 }, { "epoch": 1.33, "learning_rate": 1.996792016928203e-05, "loss": 0.2755, "step": 238 }, { "epoch": 1.34, "learning_rate": 1.9967638302356897e-05, "loss": 0.2915, "step": 239 }, { "epoch": 1.34, "learning_rate": 1.99673552045482e-05, "loss": 0.2045, "step": 240 }, { "epoch": 1.35, "learning_rate": 1.9967070875890894e-05, "loss": 0.2172, "step": 241 }, { "epoch": 1.35, "learning_rate": 1.996678531642009e-05, "loss": 0.2972, "step": 242 }, { "epoch": 1.36, "learning_rate": 1.9966498526171053e-05, "loss": 0.2915, "step": 243 }, { "epoch": 1.36, "learning_rate": 1.9966210505179197e-05, "loss": 0.2939, "step": 244 }, { "epoch": 1.37, "learning_rate": 1.996592125348009e-05, "loss": 0.247, "step": 245 }, { "epoch": 1.37, "learning_rate": 1.9965630771109453e-05, "loss": 0.2833, "step": 246 }, { "epoch": 1.38, "learning_rate": 1.9965339058103157e-05, "loss": 0.2683, "step": 247 }, { "epoch": 1.39, "learning_rate": 1.996504611449722e-05, "loss": 0.396, "step": 248 }, { "epoch": 1.39, "learning_rate": 1.996475194032782e-05, "loss": 0.2598, "step": 249 }, { "epoch": 1.4, "learning_rate": 1.9964456535631287e-05, "loss": 0.181, "step": 250 }, { "epoch": 1.4, "learning_rate": 1.9964159900444096e-05, "loss": 0.2426, "step": 251 }, { "epoch": 1.41, "learning_rate": 1.9963862034802876e-05, "loss": 0.2257, "step": 252 }, { "epoch": 1.41, "learning_rate": 1.9963562938744416e-05, "loss": 0.2412, "step": 253 }, { "epoch": 1.42, "learning_rate": 1.996326261230565e-05, "loss": 0.3185, "step": 254 }, { "epoch": 1.42, "learning_rate": 1.9962961055523652e-05, "loss": 0.3034, "step": 255 }, { "epoch": 1.43, "learning_rate": 1.996265826843568e-05, "loss": 0.1797, "step": 256 }, { "epoch": 1.44, "learning_rate": 1.9962354251079114e-05, "loss": 0.1735, "step": 257 }, { "epoch": 1.44, "learning_rate": 1.9962049003491497e-05, "loss": 0.2469, "step": 258 }, { "epoch": 1.45, "learning_rate": 1.9961742525710525e-05, "loss": 0.2262, "step": 259 }, { "epoch": 1.45, "learning_rate": 1.9961434817774042e-05, "loss": 0.2125, "step": 260 }, { "epoch": 1.46, "learning_rate": 1.996112587972005e-05, "loss": 0.2305, "step": 261 }, { "epoch": 1.46, "learning_rate": 1.9960815711586695e-05, "loss": 0.3293, "step": 262 }, { "epoch": 1.47, "learning_rate": 1.9960504313412284e-05, "loss": 0.4421, "step": 263 }, { "epoch": 1.47, "learning_rate": 1.9960191685235263e-05, "loss": 0.2903, "step": 264 }, { "epoch": 1.48, "learning_rate": 1.9959877827094248e-05, "loss": 0.266, "step": 265 }, { "epoch": 1.49, "learning_rate": 1.995956273902799e-05, "loss": 0.3532, "step": 266 }, { "epoch": 1.49, "learning_rate": 1.99592464210754e-05, "loss": 0.22, "step": 267 }, { "epoch": 1.5, "learning_rate": 1.9958928873275542e-05, "loss": 0.2493, "step": 268 }, { "epoch": 1.5, "learning_rate": 1.9958610095667624e-05, "loss": 0.3033, "step": 269 }, { "epoch": 1.51, "learning_rate": 1.9958290088291012e-05, "loss": 0.1894, "step": 270 }, { "epoch": 1.51, "learning_rate": 1.9957968851185228e-05, "loss": 0.2075, "step": 271 }, { "epoch": 1.52, "learning_rate": 1.995764638438994e-05, "loss": 0.2738, "step": 272 }, { "epoch": 1.53, "learning_rate": 1.9957322687944964e-05, "loss": 0.1763, "step": 273 }, { "epoch": 1.53, "learning_rate": 1.9956997761890277e-05, "loss": 0.3084, "step": 274 }, { "epoch": 1.54, "learning_rate": 1.9956671606266003e-05, "loss": 0.2895, "step": 275 }, { "epoch": 1.54, "learning_rate": 1.9956344221112416e-05, "loss": 0.1595, "step": 276 }, { "epoch": 1.55, "learning_rate": 1.9956015606469947e-05, "loss": 0.3185, "step": 277 }, { "epoch": 1.55, "learning_rate": 1.9955685762379172e-05, "loss": 0.161, "step": 278 }, { "epoch": 1.56, "learning_rate": 1.9955354688880827e-05, "loss": 0.3087, "step": 279 }, { "epoch": 1.56, "learning_rate": 1.9955022386015792e-05, "loss": 0.1929, "step": 280 }, { "epoch": 1.57, "learning_rate": 1.9954688853825102e-05, "loss": 0.1983, "step": 281 }, { "epoch": 1.58, "learning_rate": 1.9954354092349953e-05, "loss": 0.2055, "step": 282 }, { "epoch": 1.58, "learning_rate": 1.9954018101631673e-05, "loss": 0.1844, "step": 283 }, { "epoch": 1.59, "learning_rate": 1.9953680881711757e-05, "loss": 0.2409, "step": 284 }, { "epoch": 1.59, "learning_rate": 1.995334243263185e-05, "loss": 0.1854, "step": 285 }, { "epoch": 1.6, "learning_rate": 1.9953002754433743e-05, "loss": 0.1735, "step": 286 }, { "epoch": 1.6, "learning_rate": 1.995266184715939e-05, "loss": 0.213, "step": 287 }, { "epoch": 1.61, "learning_rate": 1.995231971085087e-05, "loss": 0.2475, "step": 288 }, { "epoch": 1.61, "learning_rate": 1.995197634555045e-05, "loss": 0.1749, "step": 289 }, { "epoch": 1.62, "learning_rate": 1.995163175130053e-05, "loss": 0.2438, "step": 290 }, { "epoch": 1.63, "learning_rate": 1.995128592814366e-05, "loss": 0.3207, "step": 291 }, { "epoch": 1.63, "learning_rate": 1.9950938876122542e-05, "loss": 0.2429, "step": 292 }, { "epoch": 1.64, "learning_rate": 1.995059059528004e-05, "loss": 0.2248, "step": 293 }, { "epoch": 1.64, "learning_rate": 1.995024108565915e-05, "loss": 0.3557, "step": 294 }, { "epoch": 1.65, "learning_rate": 1.9949890347303047e-05, "loss": 0.4294, "step": 295 }, { "epoch": 1.65, "learning_rate": 1.9949538380255035e-05, "loss": 0.2187, "step": 296 }, { "epoch": 1.66, "learning_rate": 1.9949185184558577e-05, "loss": 0.1728, "step": 297 }, { "epoch": 1.66, "learning_rate": 1.994883076025729e-05, "loss": 0.1804, "step": 298 }, { "epoch": 1.67, "learning_rate": 1.9948475107394944e-05, "loss": 0.1797, "step": 299 }, { "epoch": 1.68, "learning_rate": 1.9948118226015457e-05, "loss": 0.2488, "step": 300 }, { "epoch": 1.68, "learning_rate": 1.9947760116162894e-05, "loss": 0.1883, "step": 301 }, { "epoch": 1.69, "learning_rate": 1.9947400777881484e-05, "loss": 0.1484, "step": 302 }, { "epoch": 1.69, "learning_rate": 1.9947040211215597e-05, "loss": 0.2413, "step": 303 }, { "epoch": 1.7, "learning_rate": 1.994667841620976e-05, "loss": 0.2169, "step": 304 }, { "epoch": 1.7, "learning_rate": 1.994631539290865e-05, "loss": 0.2571, "step": 305 }, { "epoch": 1.71, "learning_rate": 1.9945951141357098e-05, "loss": 0.2213, "step": 306 }, { "epoch": 1.72, "learning_rate": 1.994558566160008e-05, "loss": 0.2703, "step": 307 }, { "epoch": 1.72, "learning_rate": 1.9945218953682736e-05, "loss": 0.2335, "step": 308 }, { "epoch": 1.73, "learning_rate": 1.9944851017650342e-05, "loss": 0.1548, "step": 309 }, { "epoch": 1.73, "learning_rate": 1.9944481853548335e-05, "loss": 0.2415, "step": 310 }, { "epoch": 1.74, "learning_rate": 1.9944111461422307e-05, "loss": 0.2389, "step": 311 }, { "epoch": 1.74, "learning_rate": 1.9943739841317996e-05, "loss": 0.3185, "step": 312 }, { "epoch": 1.75, "learning_rate": 1.9943366993281286e-05, "loss": 0.2444, "step": 313 }, { "epoch": 1.75, "learning_rate": 1.994299291735823e-05, "loss": 0.2659, "step": 314 }, { "epoch": 1.76, "learning_rate": 1.994261761359501e-05, "loss": 0.2163, "step": 315 }, { "epoch": 1.77, "learning_rate": 1.9942241082037983e-05, "loss": 0.3001, "step": 316 }, { "epoch": 1.77, "learning_rate": 1.994186332273364e-05, "loss": 0.1348, "step": 317 }, { "epoch": 1.78, "learning_rate": 1.9941484335728625e-05, "loss": 0.2498, "step": 318 }, { "epoch": 1.78, "learning_rate": 1.994110412106975e-05, "loss": 0.1647, "step": 319 }, { "epoch": 1.79, "learning_rate": 1.9940722678803958e-05, "loss": 0.3317, "step": 320 }, { "epoch": 1.79, "learning_rate": 1.9940340008978355e-05, "loss": 0.1198, "step": 321 }, { "epoch": 1.8, "learning_rate": 1.9939956111640198e-05, "loss": 0.1596, "step": 322 }, { "epoch": 1.8, "learning_rate": 1.993957098683689e-05, "loss": 0.1335, "step": 323 }, { "epoch": 1.81, "learning_rate": 1.9939184634615993e-05, "loss": 0.1884, "step": 324 }, { "epoch": 1.82, "learning_rate": 1.9938797055025213e-05, "loss": 0.146, "step": 325 }, { "epoch": 1.82, "learning_rate": 1.9938408248112417e-05, "loss": 0.1364, "step": 326 }, { "epoch": 1.83, "learning_rate": 1.993801821392561e-05, "loss": 0.1468, "step": 327 }, { "epoch": 1.83, "learning_rate": 1.9937626952512966e-05, "loss": 0.2124, "step": 328 }, { "epoch": 1.84, "learning_rate": 1.9937234463922794e-05, "loss": 0.1735, "step": 329 }, { "epoch": 1.84, "learning_rate": 1.9936840748203563e-05, "loss": 0.1766, "step": 330 }, { "epoch": 1.85, "learning_rate": 1.9936445805403894e-05, "loss": 0.2854, "step": 331 }, { "epoch": 1.85, "learning_rate": 1.993604963557256e-05, "loss": 0.2184, "step": 332 }, { "epoch": 1.86, "learning_rate": 1.9935652238758478e-05, "loss": 0.2407, "step": 333 }, { "epoch": 1.87, "learning_rate": 1.9935253615010718e-05, "loss": 0.2152, "step": 334 }, { "epoch": 1.87, "learning_rate": 1.9934853764378516e-05, "loss": 0.1597, "step": 335 }, { "epoch": 1.88, "learning_rate": 1.9934452686911244e-05, "loss": 0.2088, "step": 336 }, { "epoch": 1.88, "learning_rate": 1.9934050382658426e-05, "loss": 0.217, "step": 337 }, { "epoch": 1.89, "learning_rate": 1.993364685166975e-05, "loss": 0.1959, "step": 338 }, { "epoch": 1.89, "learning_rate": 1.9933242093995042e-05, "loss": 0.1831, "step": 339 }, { "epoch": 1.9, "learning_rate": 1.9932836109684287e-05, "loss": 0.1404, "step": 340 }, { "epoch": 1.91, "learning_rate": 1.9932428898787615e-05, "loss": 0.164, "step": 341 }, { "epoch": 1.91, "learning_rate": 1.9932020461355315e-05, "loss": 0.181, "step": 342 }, { "epoch": 1.92, "learning_rate": 1.993161079743782e-05, "loss": 0.2156, "step": 343 }, { "epoch": 1.92, "learning_rate": 1.9931199907085727e-05, "loss": 0.1948, "step": 344 }, { "epoch": 1.93, "learning_rate": 1.9930787790349774e-05, "loss": 0.2147, "step": 345 }, { "epoch": 1.93, "learning_rate": 1.9930374447280844e-05, "loss": 0.1909, "step": 346 }, { "epoch": 1.94, "learning_rate": 1.9929959877929987e-05, "loss": 0.1538, "step": 347 }, { "epoch": 1.94, "learning_rate": 1.9929544082348394e-05, "loss": 0.1783, "step": 348 }, { "epoch": 1.95, "learning_rate": 1.9929127060587415e-05, "loss": 0.1604, "step": 349 }, { "epoch": 1.96, "learning_rate": 1.9928708812698544e-05, "loss": 0.1707, "step": 350 }, { "epoch": 1.96, "learning_rate": 1.992828933873343e-05, "loss": 0.1962, "step": 351 }, { "epoch": 1.97, "learning_rate": 1.9927868638743875e-05, "loss": 0.1775, "step": 352 }, { "epoch": 1.97, "learning_rate": 1.9927446712781828e-05, "loss": 0.2387, "step": 353 }, { "epoch": 1.98, "learning_rate": 1.9927023560899394e-05, "loss": 0.1925, "step": 354 }, { "epoch": 1.98, "learning_rate": 1.9926599183148822e-05, "loss": 0.1307, "step": 355 }, { "epoch": 1.99, "learning_rate": 1.9926173579582523e-05, "loss": 0.2718, "step": 356 }, { "epoch": 1.99, "learning_rate": 1.9925746750253054e-05, "loss": 0.2379, "step": 357 }, { "epoch": 2.0, "learning_rate": 1.992531869521312e-05, "loss": 0.2756, "step": 358 }, { "epoch": 2.01, "learning_rate": 1.992488941451558e-05, "loss": 0.1259, "step": 359 }, { "epoch": 2.01, "learning_rate": 1.992445890821345e-05, "loss": 0.3706, "step": 360 }, { "epoch": 2.02, "learning_rate": 1.9924027176359888e-05, "loss": 0.1717, "step": 361 }, { "epoch": 2.02, "learning_rate": 1.9923594219008212e-05, "loss": 0.147, "step": 362 }, { "epoch": 2.03, "learning_rate": 1.992316003621188e-05, "loss": 0.2291, "step": 363 }, { "epoch": 2.03, "learning_rate": 1.9922724628024516e-05, "loss": 0.1919, "step": 364 }, { "epoch": 2.04, "learning_rate": 1.992228799449988e-05, "loss": 0.1486, "step": 365 }, { "epoch": 2.04, "learning_rate": 1.99218501356919e-05, "loss": 0.2451, "step": 366 }, { "epoch": 2.05, "learning_rate": 1.992141105165464e-05, "loss": 0.2576, "step": 367 }, { "epoch": 2.06, "learning_rate": 1.9920970742442324e-05, "loss": 0.1991, "step": 368 }, { "epoch": 2.06, "learning_rate": 1.9920529208109323e-05, "loss": 0.1546, "step": 369 }, { "epoch": 2.07, "learning_rate": 1.9920086448710162e-05, "loss": 0.1228, "step": 370 }, { "epoch": 2.07, "learning_rate": 1.9919642464299517e-05, "loss": 0.1828, "step": 371 }, { "epoch": 2.08, "learning_rate": 1.9919197254932213e-05, "loss": 0.2479, "step": 372 }, { "epoch": 2.08, "learning_rate": 1.9918750820663232e-05, "loss": 0.2211, "step": 373 }, { "epoch": 2.09, "learning_rate": 1.99183031615477e-05, "loss": 0.1876, "step": 374 }, { "epoch": 2.09, "learning_rate": 1.9917854277640895e-05, "loss": 0.2568, "step": 375 }, { "epoch": 2.1, "learning_rate": 1.9917404168998256e-05, "loss": 0.1831, "step": 376 }, { "epoch": 2.11, "learning_rate": 1.991695283567536e-05, "loss": 0.2251, "step": 377 }, { "epoch": 2.11, "learning_rate": 1.9916500277727943e-05, "loss": 0.2557, "step": 378 }, { "epoch": 2.12, "learning_rate": 1.9916046495211893e-05, "loss": 0.1821, "step": 379 }, { "epoch": 2.12, "learning_rate": 1.9915591488183243e-05, "loss": 0.1869, "step": 380 }, { "epoch": 2.13, "learning_rate": 1.9915135256698184e-05, "loss": 0.2026, "step": 381 }, { "epoch": 2.13, "learning_rate": 1.991467780081305e-05, "loss": 0.1645, "step": 382 }, { "epoch": 2.14, "learning_rate": 1.9914219120584337e-05, "loss": 0.2165, "step": 383 }, { "epoch": 2.15, "learning_rate": 1.9913759216068686e-05, "loss": 0.1692, "step": 384 }, { "epoch": 2.15, "learning_rate": 1.9913298087322886e-05, "loss": 0.1669, "step": 385 }, { "epoch": 2.16, "learning_rate": 1.991283573440388e-05, "loss": 0.2576, "step": 386 }, { "epoch": 2.16, "learning_rate": 1.991237215736877e-05, "loss": 0.215, "step": 387 }, { "epoch": 2.17, "learning_rate": 1.9911907356274794e-05, "loss": 0.1832, "step": 388 }, { "epoch": 2.17, "learning_rate": 1.9911441331179358e-05, "loss": 0.1779, "step": 389 }, { "epoch": 2.18, "learning_rate": 1.9910974082140005e-05, "loss": 0.0999, "step": 390 }, { "epoch": 2.18, "learning_rate": 1.9910505609214433e-05, "loss": 0.1463, "step": 391 }, { "epoch": 2.19, "learning_rate": 1.9910035912460496e-05, "loss": 0.1538, "step": 392 }, { "epoch": 2.2, "learning_rate": 1.9909564991936196e-05, "loss": 0.1998, "step": 393 }, { "epoch": 2.2, "learning_rate": 1.9909092847699684e-05, "loss": 0.1502, "step": 394 }, { "epoch": 2.21, "learning_rate": 1.9908619479809267e-05, "loss": 0.228, "step": 395 }, { "epoch": 2.21, "learning_rate": 1.9908144888323398e-05, "loss": 0.2578, "step": 396 }, { "epoch": 2.22, "learning_rate": 1.9907669073300684e-05, "loss": 0.1873, "step": 397 }, { "epoch": 2.22, "learning_rate": 1.990719203479988e-05, "loss": 0.2063, "step": 398 }, { "epoch": 2.23, "learning_rate": 1.99067137728799e-05, "loss": 0.0971, "step": 399 }, { "epoch": 2.23, "learning_rate": 1.99062342875998e-05, "loss": 0.2246, "step": 400 }, { "epoch": 2.24, "learning_rate": 1.990575357901879e-05, "loss": 0.1321, "step": 401 }, { "epoch": 2.25, "learning_rate": 1.9905271647196233e-05, "loss": 0.1664, "step": 402 }, { "epoch": 2.25, "learning_rate": 1.9904788492191645e-05, "loss": 0.2772, "step": 403 }, { "epoch": 2.26, "learning_rate": 1.990430411406468e-05, "loss": 0.1408, "step": 404 }, { "epoch": 2.26, "learning_rate": 1.9903818512875163e-05, "loss": 0.1579, "step": 405 }, { "epoch": 2.27, "learning_rate": 1.990333168868306e-05, "loss": 0.1935, "step": 406 }, { "epoch": 2.27, "learning_rate": 1.990284364154848e-05, "loss": 0.2619, "step": 407 }, { "epoch": 2.28, "learning_rate": 1.9902354371531695e-05, "loss": 0.1168, "step": 408 }, { "epoch": 2.28, "learning_rate": 1.9901863878693123e-05, "loss": 0.1762, "step": 409 }, { "epoch": 2.29, "learning_rate": 1.990137216309334e-05, "loss": 0.1102, "step": 410 }, { "epoch": 2.3, "learning_rate": 1.9900879224793058e-05, "loss": 0.1324, "step": 411 }, { "epoch": 2.3, "learning_rate": 1.9900385063853154e-05, "loss": 0.1264, "step": 412 }, { "epoch": 2.31, "learning_rate": 1.9899889680334653e-05, "loss": 0.1882, "step": 413 }, { "epoch": 2.31, "learning_rate": 1.9899393074298724e-05, "loss": 0.1241, "step": 414 }, { "epoch": 2.32, "learning_rate": 1.989889524580669e-05, "loss": 0.1352, "step": 415 }, { "epoch": 2.32, "learning_rate": 1.9898396194920036e-05, "loss": 0.1855, "step": 416 }, { "epoch": 2.33, "learning_rate": 1.989789592170038e-05, "loss": 0.2264, "step": 417 }, { "epoch": 2.34, "learning_rate": 1.9897394426209507e-05, "loss": 0.201, "step": 418 }, { "epoch": 2.34, "learning_rate": 1.989689170850934e-05, "loss": 0.1425, "step": 419 }, { "epoch": 2.35, "learning_rate": 1.9896387768661958e-05, "loss": 0.1616, "step": 420 }, { "epoch": 2.35, "learning_rate": 1.9895882606729596e-05, "loss": 0.2193, "step": 421 }, { "epoch": 2.36, "learning_rate": 1.9895376222774632e-05, "loss": 0.2111, "step": 422 }, { "epoch": 2.36, "learning_rate": 1.98948686168596e-05, "loss": 0.1014, "step": 423 }, { "epoch": 2.37, "learning_rate": 1.9894359789047188e-05, "loss": 0.2468, "step": 424 }, { "epoch": 2.37, "learning_rate": 1.989384973940022e-05, "loss": 0.2047, "step": 425 }, { "epoch": 2.38, "learning_rate": 1.9893338467981684e-05, "loss": 0.1475, "step": 426 }, { "epoch": 2.39, "learning_rate": 1.989282597485472e-05, "loss": 0.1242, "step": 427 }, { "epoch": 2.39, "learning_rate": 1.9892312260082617e-05, "loss": 0.151, "step": 428 }, { "epoch": 2.4, "learning_rate": 1.9891797323728803e-05, "loss": 0.2166, "step": 429 }, { "epoch": 2.4, "learning_rate": 1.9891281165856876e-05, "loss": 0.1377, "step": 430 }, { "epoch": 2.41, "learning_rate": 1.9890763786530568e-05, "loss": 0.1357, "step": 431 }, { "epoch": 2.41, "learning_rate": 1.989024518581377e-05, "loss": 0.2028, "step": 432 }, { "epoch": 2.42, "learning_rate": 1.9889725363770532e-05, "loss": 0.1114, "step": 433 }, { "epoch": 2.42, "learning_rate": 1.9889204320465033e-05, "loss": 0.1053, "step": 434 }, { "epoch": 2.43, "learning_rate": 1.9888682055961623e-05, "loss": 0.18, "step": 435 }, { "epoch": 2.44, "learning_rate": 1.9888158570324795e-05, "loss": 0.099, "step": 436 }, { "epoch": 2.44, "learning_rate": 1.988763386361919e-05, "loss": 0.0941, "step": 437 }, { "epoch": 2.45, "learning_rate": 1.9887107935909608e-05, "loss": 0.1099, "step": 438 }, { "epoch": 2.45, "learning_rate": 1.988658078726099e-05, "loss": 0.1864, "step": 439 }, { "epoch": 2.46, "learning_rate": 1.9886052417738436e-05, "loss": 0.1232, "step": 440 }, { "epoch": 2.46, "learning_rate": 1.988552282740719e-05, "loss": 0.1273, "step": 441 }, { "epoch": 2.47, "learning_rate": 1.988499201633265e-05, "loss": 0.2043, "step": 442 }, { "epoch": 2.47, "learning_rate": 1.9884459984580368e-05, "loss": 0.1007, "step": 443 }, { "epoch": 2.48, "learning_rate": 1.988392673221604e-05, "loss": 0.1483, "step": 444 }, { "epoch": 2.49, "learning_rate": 1.988339225930552e-05, "loss": 0.1413, "step": 445 }, { "epoch": 2.49, "learning_rate": 1.988285656591481e-05, "loss": 0.1097, "step": 446 }, { "epoch": 2.5, "learning_rate": 1.9882319652110056e-05, "loss": 0.1328, "step": 447 }, { "epoch": 2.5, "learning_rate": 1.9881781517957562e-05, "loss": 0.1057, "step": 448 }, { "epoch": 2.51, "learning_rate": 1.9881242163523787e-05, "loss": 0.1636, "step": 449 }, { "epoch": 2.51, "learning_rate": 1.9880701588875327e-05, "loss": 0.1361, "step": 450 }, { "epoch": 2.52, "learning_rate": 1.988015979407894e-05, "loss": 0.2072, "step": 451 }, { "epoch": 2.53, "learning_rate": 1.9879616779201528e-05, "loss": 0.153, "step": 452 }, { "epoch": 2.53, "learning_rate": 1.9879072544310152e-05, "loss": 0.2256, "step": 453 }, { "epoch": 2.54, "learning_rate": 1.987852708947202e-05, "loss": 0.1375, "step": 454 }, { "epoch": 2.54, "learning_rate": 1.9877980414754484e-05, "loss": 0.1975, "step": 455 }, { "epoch": 2.55, "learning_rate": 1.987743252022505e-05, "loss": 0.151, "step": 456 }, { "epoch": 2.55, "learning_rate": 1.9876883405951378e-05, "loss": 0.1968, "step": 457 }, { "epoch": 2.56, "learning_rate": 1.9876333072001282e-05, "loss": 0.1271, "step": 458 }, { "epoch": 2.56, "learning_rate": 1.9875781518442716e-05, "loss": 0.1277, "step": 459 }, { "epoch": 2.57, "learning_rate": 1.987522874534379e-05, "loss": 0.0985, "step": 460 }, { "epoch": 2.58, "learning_rate": 1.9874674752772773e-05, "loss": 0.1363, "step": 461 }, { "epoch": 2.58, "learning_rate": 1.9874119540798067e-05, "loss": 0.2099, "step": 462 }, { "epoch": 2.59, "learning_rate": 1.987356310948824e-05, "loss": 0.0774, "step": 463 }, { "epoch": 2.59, "learning_rate": 1.9873005458911996e-05, "loss": 0.0869, "step": 464 }, { "epoch": 2.6, "learning_rate": 1.987244658913821e-05, "loss": 0.1587, "step": 465 }, { "epoch": 2.6, "learning_rate": 1.987188650023589e-05, "loss": 0.2892, "step": 466 }, { "epoch": 2.61, "learning_rate": 1.9871325192274198e-05, "loss": 0.2659, "step": 467 }, { "epoch": 2.61, "learning_rate": 1.9870762665322454e-05, "loss": 0.2233, "step": 468 }, { "epoch": 2.62, "learning_rate": 1.9870198919450117e-05, "loss": 0.2656, "step": 469 }, { "epoch": 2.63, "learning_rate": 1.9869633954726807e-05, "loss": 0.079, "step": 470 }, { "epoch": 2.63, "learning_rate": 1.9869067771222288e-05, "loss": 0.1048, "step": 471 }, { "epoch": 2.64, "learning_rate": 1.986850036900648e-05, "loss": 0.1474, "step": 472 }, { "epoch": 2.64, "learning_rate": 1.986793174814945e-05, "loss": 0.2007, "step": 473 }, { "epoch": 2.65, "learning_rate": 1.9867361908721414e-05, "loss": 0.1135, "step": 474 }, { "epoch": 2.65, "learning_rate": 1.986679085079274e-05, "loss": 0.1104, "step": 475 }, { "epoch": 2.66, "learning_rate": 1.9866218574433945e-05, "loss": 0.1643, "step": 476 }, { "epoch": 2.66, "learning_rate": 1.986564507971571e-05, "loss": 0.1662, "step": 477 }, { "epoch": 2.67, "learning_rate": 1.9865070366708835e-05, "loss": 0.1746, "step": 478 }, { "epoch": 2.68, "learning_rate": 1.9864494435484303e-05, "loss": 0.1454, "step": 479 }, { "epoch": 2.68, "learning_rate": 1.9863917286113236e-05, "loss": 0.1159, "step": 480 }, { "epoch": 2.69, "learning_rate": 1.98633389186669e-05, "loss": 0.1677, "step": 481 }, { "epoch": 2.69, "learning_rate": 1.986275933321672e-05, "loss": 0.1902, "step": 482 }, { "epoch": 2.7, "learning_rate": 1.9862178529834264e-05, "loss": 0.1398, "step": 483 }, { "epoch": 2.7, "learning_rate": 1.9861596508591255e-05, "loss": 0.1655, "step": 484 }, { "epoch": 2.71, "learning_rate": 1.986101326955957e-05, "loss": 0.2541, "step": 485 }, { "epoch": 2.72, "learning_rate": 1.9860428812811224e-05, "loss": 0.1434, "step": 486 }, { "epoch": 2.72, "learning_rate": 1.9859843138418394e-05, "loss": 0.2626, "step": 487 }, { "epoch": 2.73, "learning_rate": 1.985925624645341e-05, "loss": 0.1918, "step": 488 }, { "epoch": 2.73, "learning_rate": 1.985866813698874e-05, "loss": 0.1945, "step": 489 }, { "epoch": 2.74, "learning_rate": 1.9858078810097004e-05, "loss": 0.092, "step": 490 }, { "epoch": 2.74, "learning_rate": 1.9857488265850985e-05, "loss": 0.0918, "step": 491 }, { "epoch": 2.75, "learning_rate": 1.985689650432361e-05, "loss": 0.1496, "step": 492 }, { "epoch": 2.75, "learning_rate": 1.985630352558794e-05, "loss": 0.1061, "step": 493 }, { "epoch": 2.76, "learning_rate": 1.985570932971722e-05, "loss": 0.1484, "step": 494 }, { "epoch": 2.77, "learning_rate": 1.985511391678481e-05, "loss": 0.1872, "step": 495 }, { "epoch": 2.77, "learning_rate": 1.9854517286864246e-05, "loss": 0.0736, "step": 496 }, { "epoch": 2.78, "learning_rate": 1.98539194400292e-05, "loss": 0.1345, "step": 497 }, { "epoch": 2.78, "learning_rate": 1.9853320376353496e-05, "loss": 0.0851, "step": 498 }, { "epoch": 2.79, "learning_rate": 1.985272009591112e-05, "loss": 0.1404, "step": 499 }, { "epoch": 2.79, "learning_rate": 1.9852118598776195e-05, "loss": 0.1723, "step": 500 }, { "epoch": 2.8, "learning_rate": 1.9851515885023e-05, "loss": 0.1517, "step": 501 }, { "epoch": 2.8, "learning_rate": 1.985091195472596e-05, "loss": 0.1292, "step": 502 }, { "epoch": 2.81, "learning_rate": 1.9850306807959655e-05, "loss": 0.1611, "step": 503 }, { "epoch": 2.82, "learning_rate": 1.984970044479881e-05, "loss": 0.1259, "step": 504 }, { "epoch": 2.82, "learning_rate": 1.984909286531831e-05, "loss": 0.1214, "step": 505 }, { "epoch": 2.83, "learning_rate": 1.984848406959318e-05, "loss": 0.1818, "step": 506 }, { "epoch": 2.83, "learning_rate": 1.9847874057698596e-05, "loss": 0.1731, "step": 507 }, { "epoch": 2.84, "learning_rate": 1.9847262829709892e-05, "loss": 0.128, "step": 508 }, { "epoch": 2.84, "learning_rate": 1.9846650385702545e-05, "loss": 0.1334, "step": 509 }, { "epoch": 2.85, "learning_rate": 1.9846036725752186e-05, "loss": 0.1911, "step": 510 }, { "epoch": 2.85, "learning_rate": 1.9845421849934596e-05, "loss": 0.0963, "step": 511 }, { "epoch": 2.86, "learning_rate": 1.98448057583257e-05, "loss": 0.1936, "step": 512 }, { "epoch": 2.87, "learning_rate": 1.9844188451001584e-05, "loss": 0.1884, "step": 513 }, { "epoch": 2.87, "learning_rate": 1.9843569928038468e-05, "loss": 0.2155, "step": 514 }, { "epoch": 2.88, "learning_rate": 1.9842950189512746e-05, "loss": 0.0827, "step": 515 }, { "epoch": 2.88, "learning_rate": 1.9842329235500934e-05, "loss": 0.1957, "step": 516 }, { "epoch": 2.89, "learning_rate": 1.984170706607972e-05, "loss": 0.157, "step": 517 }, { "epoch": 2.89, "learning_rate": 1.984108368132594e-05, "loss": 0.1845, "step": 518 }, { "epoch": 2.9, "learning_rate": 1.9840459081316564e-05, "loss": 0.1115, "step": 519 }, { "epoch": 2.91, "learning_rate": 1.9839833266128726e-05, "loss": 0.1511, "step": 520 }, { "epoch": 2.91, "learning_rate": 1.9839206235839707e-05, "loss": 0.1293, "step": 521 }, { "epoch": 2.92, "learning_rate": 1.983857799052694e-05, "loss": 0.1035, "step": 522 }, { "epoch": 2.92, "learning_rate": 1.9837948530268005e-05, "loss": 0.1965, "step": 523 }, { "epoch": 2.93, "learning_rate": 1.983731785514063e-05, "loss": 0.1073, "step": 524 }, { "epoch": 2.93, "learning_rate": 1.98366859652227e-05, "loss": 0.1035, "step": 525 }, { "epoch": 2.94, "learning_rate": 1.9836052860592237e-05, "loss": 0.1495, "step": 526 }, { "epoch": 2.94, "learning_rate": 1.9835418541327436e-05, "loss": 0.1749, "step": 527 }, { "epoch": 2.95, "learning_rate": 1.9834783007506615e-05, "loss": 0.1619, "step": 528 }, { "epoch": 2.96, "learning_rate": 1.9834146259208263e-05, "loss": 0.0671, "step": 529 }, { "epoch": 2.96, "learning_rate": 1.9833508296511003e-05, "loss": 0.1305, "step": 530 }, { "epoch": 2.97, "learning_rate": 1.9832869119493624e-05, "loss": 0.134, "step": 531 }, { "epoch": 2.97, "learning_rate": 1.983222872823505e-05, "loss": 0.1551, "step": 532 }, { "epoch": 2.98, "learning_rate": 1.9831587122814366e-05, "loss": 0.1707, "step": 533 }, { "epoch": 2.98, "learning_rate": 1.9830944303310803e-05, "loss": 0.1848, "step": 534 }, { "epoch": 2.99, "learning_rate": 1.983030026980374e-05, "loss": 0.0982, "step": 535 }, { "epoch": 2.99, "learning_rate": 1.9829655022372703e-05, "loss": 0.1581, "step": 536 }, { "epoch": 3.0, "learning_rate": 1.9829008561097377e-05, "loss": 0.1408, "step": 537 }, { "epoch": 3.01, "learning_rate": 1.9828360886057597e-05, "loss": 0.15, "step": 538 }, { "epoch": 3.01, "learning_rate": 1.9827711997333333e-05, "loss": 0.1012, "step": 539 }, { "epoch": 3.02, "learning_rate": 1.9827061895004718e-05, "loss": 0.0604, "step": 540 }, { "epoch": 3.02, "learning_rate": 1.9826410579152036e-05, "loss": 0.0739, "step": 541 }, { "epoch": 3.03, "learning_rate": 1.9825758049855713e-05, "loss": 0.1071, "step": 542 }, { "epoch": 3.03, "learning_rate": 1.982510430719633e-05, "loss": 0.1145, "step": 543 }, { "epoch": 3.04, "learning_rate": 1.982444935125462e-05, "loss": 0.0661, "step": 544 }, { "epoch": 3.04, "learning_rate": 1.982379318211145e-05, "loss": 0.1223, "step": 545 }, { "epoch": 3.05, "learning_rate": 1.9823135799847865e-05, "loss": 0.1116, "step": 546 }, { "epoch": 3.06, "learning_rate": 1.982247720454503e-05, "loss": 0.0913, "step": 547 }, { "epoch": 3.06, "learning_rate": 1.9821817396284283e-05, "loss": 0.1108, "step": 548 }, { "epoch": 3.07, "learning_rate": 1.9821156375147096e-05, "loss": 0.0921, "step": 549 }, { "epoch": 3.07, "learning_rate": 1.98204941412151e-05, "loss": 0.0739, "step": 550 }, { "epoch": 3.08, "learning_rate": 1.9819830694570078e-05, "loss": 0.0666, "step": 551 }, { "epoch": 3.08, "learning_rate": 1.981916603529395e-05, "loss": 0.1092, "step": 552 }, { "epoch": 3.09, "learning_rate": 1.9818500163468797e-05, "loss": 0.1163, "step": 553 }, { "epoch": 3.09, "learning_rate": 1.9817833079176844e-05, "loss": 0.1506, "step": 554 }, { "epoch": 3.1, "learning_rate": 1.981716478250047e-05, "loss": 0.0556, "step": 555 }, { "epoch": 3.11, "learning_rate": 1.98164952735222e-05, "loss": 0.0885, "step": 556 }, { "epoch": 3.11, "learning_rate": 1.9815824552324713e-05, "loss": 0.0919, "step": 557 }, { "epoch": 3.12, "learning_rate": 1.981515261899083e-05, "loss": 0.191, "step": 558 }, { "epoch": 3.12, "learning_rate": 1.981447947360353e-05, "loss": 0.099, "step": 559 }, { "epoch": 3.13, "learning_rate": 1.981380511624594e-05, "loss": 0.0904, "step": 560 }, { "epoch": 3.13, "learning_rate": 1.9813129547001336e-05, "loss": 0.0759, "step": 561 }, { "epoch": 3.14, "learning_rate": 1.9812452765953137e-05, "loss": 0.0811, "step": 562 }, { "epoch": 3.15, "learning_rate": 1.981177477318492e-05, "loss": 0.1091, "step": 563 }, { "epoch": 3.15, "learning_rate": 1.981109556878041e-05, "loss": 0.1109, "step": 564 }, { "epoch": 3.16, "learning_rate": 1.981041515282348e-05, "loss": 0.2001, "step": 565 }, { "epoch": 3.16, "learning_rate": 1.9809733525398154e-05, "loss": 0.0902, "step": 566 }, { "epoch": 3.17, "learning_rate": 1.98090506865886e-05, "loss": 0.1093, "step": 567 }, { "epoch": 3.17, "learning_rate": 1.9808366636479146e-05, "loss": 0.1084, "step": 568 }, { "epoch": 3.18, "learning_rate": 1.9807681375154265e-05, "loss": 0.1375, "step": 569 }, { "epoch": 3.18, "learning_rate": 1.9806994902698572e-05, "loss": 0.1044, "step": 570 }, { "epoch": 3.19, "learning_rate": 1.9806307219196842e-05, "loss": 0.0925, "step": 571 }, { "epoch": 3.2, "learning_rate": 1.9805618324734e-05, "loss": 0.1341, "step": 572 }, { "epoch": 3.2, "learning_rate": 1.9804928219395107e-05, "loss": 0.1889, "step": 573 }, { "epoch": 3.21, "learning_rate": 1.980423690326539e-05, "loss": 0.0717, "step": 574 }, { "epoch": 3.21, "learning_rate": 1.980354437643021e-05, "loss": 0.0981, "step": 575 }, { "epoch": 3.22, "learning_rate": 1.98028506389751e-05, "loss": 0.1208, "step": 576 }, { "epoch": 3.22, "learning_rate": 1.9802155690985712e-05, "loss": 0.1065, "step": 577 }, { "epoch": 3.23, "learning_rate": 1.9801459532547877e-05, "loss": 0.0922, "step": 578 }, { "epoch": 3.23, "learning_rate": 1.9800762163747557e-05, "loss": 0.1853, "step": 579 }, { "epoch": 3.24, "learning_rate": 1.9800063584670864e-05, "loss": 0.0942, "step": 580 }, { "epoch": 3.25, "learning_rate": 1.9799363795404068e-05, "loss": 0.0982, "step": 581 }, { "epoch": 3.25, "learning_rate": 1.9798662796033588e-05, "loss": 0.0776, "step": 582 }, { "epoch": 3.26, "learning_rate": 1.9797960586645986e-05, "loss": 0.0664, "step": 583 }, { "epoch": 3.26, "learning_rate": 1.9797257167327974e-05, "loss": 0.1272, "step": 584 }, { "epoch": 3.27, "learning_rate": 1.9796552538166416e-05, "loss": 0.0701, "step": 585 }, { "epoch": 3.27, "learning_rate": 1.979584669924833e-05, "loss": 0.0883, "step": 586 }, { "epoch": 3.28, "learning_rate": 1.979513965066088e-05, "loss": 0.1024, "step": 587 }, { "epoch": 3.28, "learning_rate": 1.9794431392491367e-05, "loss": 0.0608, "step": 588 }, { "epoch": 3.29, "learning_rate": 1.9793721924827266e-05, "loss": 0.0782, "step": 589 }, { "epoch": 3.3, "learning_rate": 1.9793011247756177e-05, "loss": 0.0971, "step": 590 }, { "epoch": 3.3, "learning_rate": 1.9792299361365862e-05, "loss": 0.2048, "step": 591 }, { "epoch": 3.31, "learning_rate": 1.9791586265744238e-05, "loss": 0.0907, "step": 592 }, { "epoch": 3.31, "learning_rate": 1.9790871960979358e-05, "loss": 0.1031, "step": 593 }, { "epoch": 3.32, "learning_rate": 1.9790156447159425e-05, "loss": 0.154, "step": 594 }, { "epoch": 3.32, "learning_rate": 1.978943972437281e-05, "loss": 0.0879, "step": 595 }, { "epoch": 3.33, "learning_rate": 1.9788721792708005e-05, "loss": 0.0729, "step": 596 }, { "epoch": 3.34, "learning_rate": 1.9788002652253672e-05, "loss": 0.0564, "step": 597 }, { "epoch": 3.34, "learning_rate": 1.9787282303098618e-05, "loss": 0.0704, "step": 598 }, { "epoch": 3.35, "learning_rate": 1.9786560745331797e-05, "loss": 0.0751, "step": 599 }, { "epoch": 3.35, "learning_rate": 1.978583797904231e-05, "loss": 0.1416, "step": 600 }, { "epoch": 3.36, "learning_rate": 1.9785114004319414e-05, "loss": 0.1005, "step": 601 }, { "epoch": 3.36, "learning_rate": 1.978438882125251e-05, "loss": 0.0836, "step": 602 }, { "epoch": 3.37, "learning_rate": 1.9783662429931147e-05, "loss": 0.0752, "step": 603 }, { "epoch": 3.37, "learning_rate": 1.9782934830445023e-05, "loss": 0.0974, "step": 604 }, { "epoch": 3.38, "learning_rate": 1.9782206022883996e-05, "loss": 0.0733, "step": 605 }, { "epoch": 3.39, "learning_rate": 1.9781476007338058e-05, "loss": 0.0958, "step": 606 }, { "epoch": 3.39, "learning_rate": 1.978074478389736e-05, "loss": 0.0725, "step": 607 }, { "epoch": 3.4, "learning_rate": 1.9780012352652203e-05, "loss": 0.0707, "step": 608 }, { "epoch": 3.4, "learning_rate": 1.9779278713693023e-05, "loss": 0.1142, "step": 609 }, { "epoch": 3.41, "learning_rate": 1.9778543867110428e-05, "loss": 0.0998, "step": 610 }, { "epoch": 3.41, "learning_rate": 1.9777807812995157e-05, "loss": 0.0673, "step": 611 }, { "epoch": 3.42, "learning_rate": 1.97770705514381e-05, "loss": 0.0818, "step": 612 }, { "epoch": 3.42, "learning_rate": 1.9776332082530306e-05, "loss": 0.1001, "step": 613 }, { "epoch": 3.43, "learning_rate": 1.977559240636296e-05, "loss": 0.0681, "step": 614 }, { "epoch": 3.44, "learning_rate": 1.9774851523027414e-05, "loss": 0.2027, "step": 615 }, { "epoch": 3.44, "learning_rate": 1.9774109432615148e-05, "loss": 0.1027, "step": 616 }, { "epoch": 3.45, "learning_rate": 1.977336613521781e-05, "loss": 0.161, "step": 617 }, { "epoch": 3.45, "learning_rate": 1.9772621630927177e-05, "loss": 0.1549, "step": 618 }, { "epoch": 3.46, "learning_rate": 1.9771875919835196e-05, "loss": 0.1264, "step": 619 }, { "epoch": 3.46, "learning_rate": 1.977112900203395e-05, "loss": 0.0572, "step": 620 }, { "epoch": 3.47, "learning_rate": 1.9770380877615677e-05, "loss": 0.1558, "step": 621 }, { "epoch": 3.47, "learning_rate": 1.9769631546672756e-05, "loss": 0.1402, "step": 622 }, { "epoch": 3.48, "learning_rate": 1.9768881009297726e-05, "loss": 0.0823, "step": 623 }, { "epoch": 3.49, "learning_rate": 1.9768129265583265e-05, "loss": 0.1892, "step": 624 }, { "epoch": 3.49, "learning_rate": 1.9767376315622204e-05, "loss": 0.0875, "step": 625 }, { "epoch": 3.5, "learning_rate": 1.9766622159507527e-05, "loss": 0.0798, "step": 626 }, { "epoch": 3.5, "learning_rate": 1.976586679733236e-05, "loss": 0.0497, "step": 627 }, { "epoch": 3.51, "learning_rate": 1.9765110229189987e-05, "loss": 0.1705, "step": 628 }, { "epoch": 3.51, "learning_rate": 1.976435245517383e-05, "loss": 0.1136, "step": 629 }, { "epoch": 3.52, "learning_rate": 1.9763593475377464e-05, "loss": 0.1771, "step": 630 }, { "epoch": 3.53, "learning_rate": 1.9762833289894617e-05, "loss": 0.1926, "step": 631 }, { "epoch": 3.53, "learning_rate": 1.976207189881916e-05, "loss": 0.0468, "step": 632 }, { "epoch": 3.54, "learning_rate": 1.9761309302245114e-05, "loss": 0.1238, "step": 633 }, { "epoch": 3.54, "learning_rate": 1.9760545500266656e-05, "loss": 0.1031, "step": 634 }, { "epoch": 3.55, "learning_rate": 1.9759780492978104e-05, "loss": 0.1139, "step": 635 }, { "epoch": 3.55, "learning_rate": 1.975901428047393e-05, "loss": 0.1061, "step": 636 }, { "epoch": 3.56, "learning_rate": 1.9758246862848746e-05, "loss": 0.0813, "step": 637 }, { "epoch": 3.56, "learning_rate": 1.9757478240197322e-05, "loss": 0.0932, "step": 638 }, { "epoch": 3.57, "learning_rate": 1.9756708412614575e-05, "loss": 0.0627, "step": 639 }, { "epoch": 3.58, "learning_rate": 1.975593738019557e-05, "loss": 0.109, "step": 640 }, { "epoch": 3.58, "learning_rate": 1.9755165143035514e-05, "loss": 0.116, "step": 641 }, { "epoch": 3.59, "learning_rate": 1.975439170122978e-05, "loss": 0.0548, "step": 642 }, { "epoch": 3.59, "learning_rate": 1.9753617054873864e-05, "loss": 0.0871, "step": 643 }, { "epoch": 3.6, "learning_rate": 1.9752841204063438e-05, "loss": 0.0976, "step": 644 }, { "epoch": 3.6, "learning_rate": 1.9752064148894306e-05, "loss": 0.1011, "step": 645 }, { "epoch": 3.61, "learning_rate": 1.9751285889462424e-05, "loss": 0.1058, "step": 646 }, { "epoch": 3.61, "learning_rate": 1.9750506425863896e-05, "loss": 0.0745, "step": 647 }, { "epoch": 3.62, "learning_rate": 1.9749725758194983e-05, "loss": 0.0492, "step": 648 }, { "epoch": 3.63, "learning_rate": 1.9748943886552087e-05, "loss": 0.0692, "step": 649 }, { "epoch": 3.63, "learning_rate": 1.974816081103175e-05, "loss": 0.1467, "step": 650 }, { "epoch": 3.64, "learning_rate": 1.974737653173068e-05, "loss": 0.133, "step": 651 }, { "epoch": 3.64, "learning_rate": 1.974659104874573e-05, "loss": 0.0741, "step": 652 }, { "epoch": 3.65, "learning_rate": 1.974580436217389e-05, "loss": 0.1354, "step": 653 }, { "epoch": 3.65, "learning_rate": 1.9745016472112308e-05, "loss": 0.1162, "step": 654 }, { "epoch": 3.66, "learning_rate": 1.9744227378658283e-05, "loss": 0.0883, "step": 655 }, { "epoch": 3.66, "learning_rate": 1.9743437081909254e-05, "loss": 0.0986, "step": 656 }, { "epoch": 3.67, "learning_rate": 1.9742645581962815e-05, "loss": 0.0641, "step": 657 }, { "epoch": 3.68, "learning_rate": 1.974185287891671e-05, "loss": 0.137, "step": 658 }, { "epoch": 3.68, "learning_rate": 1.974105897286882e-05, "loss": 0.0321, "step": 659 }, { "epoch": 3.69, "learning_rate": 1.974026386391719e-05, "loss": 0.0581, "step": 660 }, { "epoch": 3.69, "learning_rate": 1.973946755216001e-05, "loss": 0.1405, "step": 661 }, { "epoch": 3.7, "learning_rate": 1.97386700376956e-05, "loss": 0.0832, "step": 662 }, { "epoch": 3.7, "learning_rate": 1.973787132062246e-05, "loss": 0.0542, "step": 663 }, { "epoch": 3.71, "learning_rate": 1.973707140103921e-05, "loss": 0.1861, "step": 664 }, { "epoch": 3.72, "learning_rate": 1.9736270279044637e-05, "loss": 0.0502, "step": 665 }, { "epoch": 3.72, "learning_rate": 1.973546795473767e-05, "loss": 0.0985, "step": 666 }, { "epoch": 3.73, "learning_rate": 1.973466442821738e-05, "loss": 0.078, "step": 667 }, { "epoch": 3.73, "learning_rate": 1.9733859699583e-05, "loss": 0.0677, "step": 668 }, { "epoch": 3.74, "learning_rate": 1.9733053768933898e-05, "loss": 0.0727, "step": 669 }, { "epoch": 3.74, "learning_rate": 1.9732246636369605e-05, "loss": 0.0649, "step": 670 }, { "epoch": 3.75, "learning_rate": 1.9731438301989786e-05, "loss": 0.1123, "step": 671 }, { "epoch": 3.75, "learning_rate": 1.9730628765894262e-05, "loss": 0.1167, "step": 672 }, { "epoch": 3.76, "learning_rate": 1.9729818028183003e-05, "loss": 0.0959, "step": 673 }, { "epoch": 3.77, "learning_rate": 1.9729006088956122e-05, "loss": 0.0828, "step": 674 }, { "epoch": 3.77, "learning_rate": 1.9728192948313883e-05, "loss": 0.0889, "step": 675 }, { "epoch": 3.78, "learning_rate": 1.9727378606356704e-05, "loss": 0.0324, "step": 676 }, { "epoch": 3.78, "learning_rate": 1.9726563063185145e-05, "loss": 0.0869, "step": 677 }, { "epoch": 3.79, "learning_rate": 1.9725746318899914e-05, "loss": 0.0462, "step": 678 }, { "epoch": 3.79, "learning_rate": 1.9724928373601867e-05, "loss": 0.0625, "step": 679 }, { "epoch": 3.8, "learning_rate": 1.9724109227392016e-05, "loss": 0.1753, "step": 680 }, { "epoch": 3.8, "learning_rate": 1.9723288880371512e-05, "loss": 0.0273, "step": 681 }, { "epoch": 3.81, "learning_rate": 1.9722467332641656e-05, "loss": 0.0514, "step": 682 }, { "epoch": 3.82, "learning_rate": 1.9721644584303908e-05, "loss": 0.0668, "step": 683 }, { "epoch": 3.82, "learning_rate": 1.972082063545986e-05, "loss": 0.1148, "step": 684 }, { "epoch": 3.83, "learning_rate": 1.9719995486211258e-05, "loss": 0.0646, "step": 685 }, { "epoch": 3.83, "learning_rate": 1.9719169136660002e-05, "loss": 0.0706, "step": 686 }, { "epoch": 3.84, "learning_rate": 1.971834158690814e-05, "loss": 0.0963, "step": 687 }, { "epoch": 3.84, "learning_rate": 1.9717512837057855e-05, "loss": 0.1146, "step": 688 }, { "epoch": 3.85, "learning_rate": 1.9716682887211496e-05, "loss": 0.0939, "step": 689 }, { "epoch": 3.85, "learning_rate": 1.9715851737471548e-05, "loss": 0.0944, "step": 690 }, { "epoch": 3.86, "learning_rate": 1.9715019387940645e-05, "loss": 0.1174, "step": 691 }, { "epoch": 3.87, "learning_rate": 1.971418583872158e-05, "loss": 0.0377, "step": 692 }, { "epoch": 3.87, "learning_rate": 1.971335108991728e-05, "loss": 0.0479, "step": 693 }, { "epoch": 3.88, "learning_rate": 1.971251514163083e-05, "loss": 0.0916, "step": 694 }, { "epoch": 3.88, "learning_rate": 1.971167799396546e-05, "loss": 0.0496, "step": 695 }, { "epoch": 3.89, "learning_rate": 1.9710839647024543e-05, "loss": 0.0853, "step": 696 }, { "epoch": 3.89, "learning_rate": 1.9710000100911605e-05, "loss": 0.0591, "step": 697 }, { "epoch": 3.9, "learning_rate": 1.9709159355730326e-05, "loss": 0.1069, "step": 698 }, { "epoch": 3.91, "learning_rate": 1.9708317411584526e-05, "loss": 0.1103, "step": 699 }, { "epoch": 3.91, "learning_rate": 1.9707474268578172e-05, "loss": 0.0481, "step": 700 }, { "epoch": 3.92, "learning_rate": 1.970662992681538e-05, "loss": 0.0719, "step": 701 }, { "epoch": 3.92, "learning_rate": 1.970578438640042e-05, "loss": 0.0688, "step": 702 }, { "epoch": 3.93, "learning_rate": 1.970493764743771e-05, "loss": 0.1314, "step": 703 }, { "epoch": 3.93, "learning_rate": 1.9704089710031805e-05, "loss": 0.0482, "step": 704 }, { "epoch": 3.94, "learning_rate": 1.9703240574287417e-05, "loss": 0.1034, "step": 705 }, { "epoch": 3.94, "learning_rate": 1.9702390240309402e-05, "loss": 0.067, "step": 706 }, { "epoch": 3.95, "learning_rate": 1.9701538708202775e-05, "loss": 0.1235, "step": 707 }, { "epoch": 3.96, "learning_rate": 1.9700685978072683e-05, "loss": 0.1393, "step": 708 }, { "epoch": 3.96, "learning_rate": 1.9699832050024422e-05, "loss": 0.1117, "step": 709 }, { "epoch": 3.97, "learning_rate": 1.969897692416346e-05, "loss": 0.0433, "step": 710 }, { "epoch": 3.97, "learning_rate": 1.969812060059537e-05, "loss": 0.0442, "step": 711 }, { "epoch": 3.98, "learning_rate": 1.969726307942592e-05, "loss": 0.1218, "step": 712 }, { "epoch": 3.98, "learning_rate": 1.9696404360760993e-05, "loss": 0.1277, "step": 713 }, { "epoch": 3.99, "learning_rate": 1.969554444470663e-05, "loss": 0.0611, "step": 714 }, { "epoch": 3.99, "learning_rate": 1.9694683331369023e-05, "loss": 0.0862, "step": 715 }, { "epoch": 4.0, "learning_rate": 1.969382102085451e-05, "loss": 0.0209, "step": 716 }, { "epoch": 4.01, "learning_rate": 1.9692957513269574e-05, "loss": 0.0519, "step": 717 }, { "epoch": 4.01, "learning_rate": 1.9692092808720846e-05, "loss": 0.0414, "step": 718 }, { "epoch": 4.02, "learning_rate": 1.969122690731511e-05, "loss": 0.0435, "step": 719 }, { "epoch": 4.02, "learning_rate": 1.9690359809159294e-05, "loss": 0.0741, "step": 720 }, { "epoch": 4.03, "learning_rate": 1.9689491514360473e-05, "loss": 0.0338, "step": 721 }, { "epoch": 4.03, "learning_rate": 1.968862202302587e-05, "loss": 0.0371, "step": 722 }, { "epoch": 4.04, "learning_rate": 1.968775133526286e-05, "loss": 0.0732, "step": 723 }, { "epoch": 4.04, "learning_rate": 1.9686879451178962e-05, "loss": 0.1026, "step": 724 }, { "epoch": 4.05, "learning_rate": 1.9686006370881837e-05, "loss": 0.0334, "step": 725 }, { "epoch": 4.06, "learning_rate": 1.968513209447931e-05, "loss": 0.0488, "step": 726 }, { "epoch": 4.06, "learning_rate": 1.9684256622079337e-05, "loss": 0.0816, "step": 727 }, { "epoch": 4.07, "learning_rate": 1.968337995379003e-05, "loss": 0.0459, "step": 728 }, { "epoch": 4.07, "learning_rate": 1.9682502089719643e-05, "loss": 0.0345, "step": 729 }, { "epoch": 4.08, "learning_rate": 1.968162302997659e-05, "loss": 0.045, "step": 730 }, { "epoch": 4.08, "learning_rate": 1.9680742774669416e-05, "loss": 0.0772, "step": 731 }, { "epoch": 4.09, "learning_rate": 1.9679861323906827e-05, "loss": 0.0589, "step": 732 }, { "epoch": 4.09, "learning_rate": 1.9678978677797674e-05, "loss": 0.0465, "step": 733 }, { "epoch": 4.1, "learning_rate": 1.9678094836450945e-05, "loss": 0.0758, "step": 734 }, { "epoch": 4.11, "learning_rate": 1.9677209799975788e-05, "loss": 0.0783, "step": 735 }, { "epoch": 4.11, "learning_rate": 1.96763235684815e-05, "loss": 0.0402, "step": 736 }, { "epoch": 4.12, "learning_rate": 1.967543614207751e-05, "loss": 0.0403, "step": 737 }, { "epoch": 4.12, "learning_rate": 1.967454752087341e-05, "loss": 0.0419, "step": 738 }, { "epoch": 4.13, "learning_rate": 1.9673657704978932e-05, "loss": 0.1074, "step": 739 }, { "epoch": 4.13, "learning_rate": 1.967276669450396e-05, "loss": 0.1179, "step": 740 }, { "epoch": 4.14, "learning_rate": 1.967187448955852e-05, "loss": 0.1052, "step": 741 }, { "epoch": 4.15, "learning_rate": 1.9670981090252794e-05, "loss": 0.0894, "step": 742 }, { "epoch": 4.15, "learning_rate": 1.96700864966971e-05, "loss": 0.0544, "step": 743 }, { "epoch": 4.16, "learning_rate": 1.9669190709001912e-05, "loss": 0.0559, "step": 744 }, { "epoch": 4.16, "learning_rate": 1.9668293727277847e-05, "loss": 0.0536, "step": 745 }, { "epoch": 4.17, "learning_rate": 1.9667395551635676e-05, "loss": 0.06, "step": 746 }, { "epoch": 4.17, "learning_rate": 1.966649618218631e-05, "loss": 0.0517, "step": 747 }, { "epoch": 4.18, "learning_rate": 1.966559561904081e-05, "loss": 0.0374, "step": 748 }, { "epoch": 4.18, "learning_rate": 1.966469386231039e-05, "loss": 0.0613, "step": 749 }, { "epoch": 4.19, "learning_rate": 1.9663790912106395e-05, "loss": 0.0691, "step": 750 }, { "epoch": 4.2, "learning_rate": 1.9662886768540338e-05, "loss": 0.0322, "step": 751 }, { "epoch": 4.2, "learning_rate": 1.9661981431723864e-05, "loss": 0.0687, "step": 752 }, { "epoch": 4.21, "learning_rate": 1.9661074901768778e-05, "loss": 0.0383, "step": 753 }, { "epoch": 4.21, "learning_rate": 1.966016717878702e-05, "loss": 0.026, "step": 754 }, { "epoch": 4.22, "learning_rate": 1.9659258262890683e-05, "loss": 0.0239, "step": 755 }, { "epoch": 4.22, "learning_rate": 1.9658348154192013e-05, "loss": 0.0704, "step": 756 }, { "epoch": 4.23, "learning_rate": 1.965743685280339e-05, "loss": 0.0808, "step": 757 }, { "epoch": 4.23, "learning_rate": 1.9656524358837352e-05, "loss": 0.0817, "step": 758 }, { "epoch": 4.24, "learning_rate": 1.965561067240658e-05, "loss": 0.0218, "step": 759 }, { "epoch": 4.25, "learning_rate": 1.9654695793623908e-05, "loss": 0.0358, "step": 760 }, { "epoch": 4.25, "learning_rate": 1.9653779722602307e-05, "loss": 0.0449, "step": 761 }, { "epoch": 4.26, "learning_rate": 1.96528624594549e-05, "loss": 0.0696, "step": 762 }, { "epoch": 4.26, "learning_rate": 1.9651944004294966e-05, "loss": 0.064, "step": 763 }, { "epoch": 4.27, "learning_rate": 1.9651024357235916e-05, "loss": 0.0845, "step": 764 }, { "epoch": 4.27, "learning_rate": 1.9650103518391318e-05, "loss": 0.0396, "step": 765 }, { "epoch": 4.28, "learning_rate": 1.964918148787488e-05, "loss": 0.0508, "step": 766 }, { "epoch": 4.28, "learning_rate": 1.9648258265800465e-05, "loss": 0.084, "step": 767 }, { "epoch": 4.29, "learning_rate": 1.9647333852282086e-05, "loss": 0.048, "step": 768 }, { "epoch": 4.3, "learning_rate": 1.9646408247433886e-05, "loss": 0.0293, "step": 769 }, { "epoch": 4.3, "learning_rate": 1.9645481451370175e-05, "loss": 0.0952, "step": 770 }, { "epoch": 4.31, "learning_rate": 1.9644553464205395e-05, "loss": 0.0509, "step": 771 }, { "epoch": 4.31, "learning_rate": 1.9643624286054145e-05, "loss": 0.0742, "step": 772 }, { "epoch": 4.32, "learning_rate": 1.9642693917031162e-05, "loss": 0.0653, "step": 773 }, { "epoch": 4.32, "learning_rate": 1.9641762357251343e-05, "loss": 0.0311, "step": 774 }, { "epoch": 4.33, "learning_rate": 1.9640829606829724e-05, "loss": 0.044, "step": 775 }, { "epoch": 4.34, "learning_rate": 1.9639895665881478e-05, "loss": 0.0551, "step": 776 }, { "epoch": 4.34, "learning_rate": 1.963896053452195e-05, "loss": 0.0685, "step": 777 }, { "epoch": 4.35, "learning_rate": 1.9638024212866606e-05, "loss": 0.0477, "step": 778 }, { "epoch": 4.35, "learning_rate": 1.9637086701031075e-05, "loss": 0.0338, "step": 779 }, { "epoch": 4.36, "learning_rate": 1.963614799913113e-05, "loss": 0.0326, "step": 780 }, { "epoch": 4.36, "learning_rate": 1.9635208107282686e-05, "loss": 0.0608, "step": 781 }, { "epoch": 4.37, "learning_rate": 1.963426702560181e-05, "loss": 0.0305, "step": 782 }, { "epoch": 4.37, "learning_rate": 1.9633324754204716e-05, "loss": 0.0226, "step": 783 }, { "epoch": 4.38, "learning_rate": 1.963238129320776e-05, "loss": 0.0346, "step": 784 }, { "epoch": 4.39, "learning_rate": 1.963143664272745e-05, "loss": 0.0407, "step": 785 }, { "epoch": 4.39, "learning_rate": 1.9630490802880437e-05, "loss": 0.0537, "step": 786 }, { "epoch": 4.4, "learning_rate": 1.9629543773783527e-05, "loss": 0.038, "step": 787 }, { "epoch": 4.4, "learning_rate": 1.9628595555553657e-05, "loss": 0.059, "step": 788 }, { "epoch": 4.41, "learning_rate": 1.9627646148307928e-05, "loss": 0.0533, "step": 789 }, { "epoch": 4.41, "learning_rate": 1.962669555216358e-05, "loss": 0.0516, "step": 790 }, { "epoch": 4.42, "learning_rate": 1.9625743767237993e-05, "loss": 0.0454, "step": 791 }, { "epoch": 4.42, "learning_rate": 1.962479079364871e-05, "loss": 0.0218, "step": 792 }, { "epoch": 4.43, "learning_rate": 1.962383663151341e-05, "loss": 0.0682, "step": 793 }, { "epoch": 4.44, "learning_rate": 1.9622881280949915e-05, "loss": 0.0608, "step": 794 }, { "epoch": 4.44, "learning_rate": 1.9621924742076205e-05, "loss": 0.1041, "step": 795 }, { "epoch": 4.45, "learning_rate": 1.9620967015010397e-05, "loss": 0.0766, "step": 796 }, { "epoch": 4.45, "learning_rate": 1.9620008099870762e-05, "loss": 0.0731, "step": 797 }, { "epoch": 4.46, "learning_rate": 1.9619047996775713e-05, "loss": 0.0274, "step": 798 }, { "epoch": 4.46, "learning_rate": 1.961808670584381e-05, "loss": 0.0628, "step": 799 }, { "epoch": 4.47, "learning_rate": 1.9617124227193764e-05, "loss": 0.0753, "step": 800 }, { "epoch": 4.47, "learning_rate": 1.961616056094443e-05, "loss": 0.0279, "step": 801 }, { "epoch": 4.48, "learning_rate": 1.9615195707214805e-05, "loss": 0.0293, "step": 802 }, { "epoch": 4.49, "learning_rate": 1.961422966612404e-05, "loss": 0.025, "step": 803 }, { "epoch": 4.49, "learning_rate": 1.9613262437791425e-05, "loss": 0.0576, "step": 804 }, { "epoch": 4.5, "learning_rate": 1.9612294022336407e-05, "loss": 0.018, "step": 805 }, { "epoch": 4.5, "learning_rate": 1.961132441987857e-05, "loss": 0.0223, "step": 806 }, { "epoch": 4.51, "learning_rate": 1.9610353630537654e-05, "loss": 0.0342, "step": 807 }, { "epoch": 4.51, "learning_rate": 1.960938165443353e-05, "loss": 0.0824, "step": 808 }, { "epoch": 4.52, "learning_rate": 1.9608408491686233e-05, "loss": 0.0379, "step": 809 }, { "epoch": 4.53, "learning_rate": 1.960743414241593e-05, "loss": 0.0168, "step": 810 }, { "epoch": 4.53, "learning_rate": 1.9606458606742952e-05, "loss": 0.0238, "step": 811 }, { "epoch": 4.54, "learning_rate": 1.9605481884787756e-05, "loss": 0.0597, "step": 812 }, { "epoch": 4.54, "learning_rate": 1.960450397667096e-05, "loss": 0.032, "step": 813 }, { "epoch": 4.55, "learning_rate": 1.9603524882513326e-05, "loss": 0.07, "step": 814 }, { "epoch": 4.55, "learning_rate": 1.9602544602435756e-05, "loss": 0.0322, "step": 815 }, { "epoch": 4.56, "learning_rate": 1.9601563136559303e-05, "loss": 0.068, "step": 816 }, { "epoch": 4.56, "learning_rate": 1.960058048500517e-05, "loss": 0.033, "step": 817 }, { "epoch": 4.57, "learning_rate": 1.95995966478947e-05, "loss": 0.0973, "step": 818 }, { "epoch": 4.58, "learning_rate": 1.959861162534938e-05, "loss": 0.0674, "step": 819 }, { "epoch": 4.58, "learning_rate": 1.9597625417490863e-05, "loss": 0.0604, "step": 820 }, { "epoch": 4.59, "learning_rate": 1.9596638024440917e-05, "loss": 0.0547, "step": 821 }, { "epoch": 4.59, "learning_rate": 1.9595649446321484e-05, "loss": 0.0244, "step": 822 }, { "epoch": 4.6, "learning_rate": 1.9594659683254636e-05, "loss": 0.0462, "step": 823 }, { "epoch": 4.6, "learning_rate": 1.9593668735362605e-05, "loss": 0.0333, "step": 824 }, { "epoch": 4.61, "learning_rate": 1.959267660276775e-05, "loss": 0.0609, "step": 825 }, { "epoch": 4.61, "learning_rate": 1.9591683285592595e-05, "loss": 0.0699, "step": 826 }, { "epoch": 4.62, "learning_rate": 1.95906887839598e-05, "loss": 0.0367, "step": 827 }, { "epoch": 4.63, "learning_rate": 1.9589693097992172e-05, "loss": 0.0608, "step": 828 }, { "epoch": 4.63, "learning_rate": 1.9588696227812672e-05, "loss": 0.033, "step": 829 }, { "epoch": 4.64, "learning_rate": 1.9587698173544396e-05, "loss": 0.0559, "step": 830 }, { "epoch": 4.64, "learning_rate": 1.9586698935310594e-05, "loss": 0.1031, "step": 831 }, { "epoch": 4.65, "learning_rate": 1.9585698513234663e-05, "loss": 0.0426, "step": 832 }, { "epoch": 4.65, "learning_rate": 1.958469690744014e-05, "loss": 0.0313, "step": 833 }, { "epoch": 4.66, "learning_rate": 1.9583694118050708e-05, "loss": 0.0537, "step": 834 }, { "epoch": 4.66, "learning_rate": 1.9582690145190203e-05, "loss": 0.0403, "step": 835 }, { "epoch": 4.67, "learning_rate": 1.9581684988982607e-05, "loss": 0.0563, "step": 836 }, { "epoch": 4.68, "learning_rate": 1.9580678649552037e-05, "loss": 0.0237, "step": 837 }, { "epoch": 4.68, "learning_rate": 1.957967112702277e-05, "loss": 0.0185, "step": 838 }, { "epoch": 4.69, "learning_rate": 1.957866242151922e-05, "loss": 0.0516, "step": 839 }, { "epoch": 4.69, "learning_rate": 1.9577652533165952e-05, "loss": 0.0552, "step": 840 }, { "epoch": 4.7, "learning_rate": 1.957664146208767e-05, "loss": 0.0737, "step": 841 }, { "epoch": 4.7, "learning_rate": 1.9575629208409237e-05, "loss": 0.0228, "step": 842 }, { "epoch": 4.71, "learning_rate": 1.9574615772255647e-05, "loss": 0.028, "step": 843 }, { "epoch": 4.72, "learning_rate": 1.9573601153752053e-05, "loss": 0.0879, "step": 844 }, { "epoch": 4.72, "learning_rate": 1.9572585353023744e-05, "loss": 0.067, "step": 845 }, { "epoch": 4.73, "learning_rate": 1.9571568370196163e-05, "loss": 0.0157, "step": 846 }, { "epoch": 4.73, "learning_rate": 1.957055020539489e-05, "loss": 0.0443, "step": 847 }, { "epoch": 4.74, "learning_rate": 1.9569530858745663e-05, "loss": 0.0645, "step": 848 }, { "epoch": 4.74, "learning_rate": 1.956851033037435e-05, "loss": 0.0395, "step": 849 }, { "epoch": 4.75, "learning_rate": 1.9567488620406984e-05, "loss": 0.0201, "step": 850 }, { "epoch": 4.75, "learning_rate": 1.9566465728969725e-05, "loss": 0.0316, "step": 851 }, { "epoch": 4.76, "learning_rate": 1.9565441656188892e-05, "loss": 0.066, "step": 852 }, { "epoch": 4.77, "learning_rate": 1.9564416402190948e-05, "loss": 0.061, "step": 853 }, { "epoch": 4.77, "learning_rate": 1.9563389967102493e-05, "loss": 0.061, "step": 854 }, { "epoch": 4.78, "learning_rate": 1.9562362351050285e-05, "loss": 0.0252, "step": 855 }, { "epoch": 4.78, "learning_rate": 1.9561333554161225e-05, "loss": 0.0261, "step": 856 }, { "epoch": 4.79, "learning_rate": 1.956030357656235e-05, "loss": 0.0206, "step": 857 }, { "epoch": 4.79, "learning_rate": 1.955927241838085e-05, "loss": 0.0246, "step": 858 }, { "epoch": 4.8, "learning_rate": 1.9558240079744064e-05, "loss": 0.0478, "step": 859 }, { "epoch": 4.8, "learning_rate": 1.9557206560779477e-05, "loss": 0.0485, "step": 860 }, { "epoch": 4.81, "learning_rate": 1.9556171861614706e-05, "loss": 0.0788, "step": 861 }, { "epoch": 4.82, "learning_rate": 1.955513598237753e-05, "loss": 0.049, "step": 862 }, { "epoch": 4.82, "learning_rate": 1.955409892319587e-05, "loss": 0.0212, "step": 863 }, { "epoch": 4.83, "learning_rate": 1.955306068419779e-05, "loss": 0.0098, "step": 864 }, { "epoch": 4.83, "learning_rate": 1.9552021265511492e-05, "loss": 0.0415, "step": 865 }, { "epoch": 4.84, "learning_rate": 1.9550980667265344e-05, "loss": 0.0248, "step": 866 }, { "epoch": 4.84, "learning_rate": 1.9549938889587836e-05, "loss": 0.025, "step": 867 }, { "epoch": 4.85, "learning_rate": 1.954889593260762e-05, "loss": 0.152, "step": 868 }, { "epoch": 4.85, "learning_rate": 1.954785179645349e-05, "loss": 0.0324, "step": 869 }, { "epoch": 4.86, "learning_rate": 1.954680648125438e-05, "loss": 0.0479, "step": 870 }, { "epoch": 4.87, "learning_rate": 1.9545759987139383e-05, "loss": 0.0476, "step": 871 }, { "epoch": 4.87, "learning_rate": 1.9544712314237716e-05, "loss": 0.0431, "step": 872 }, { "epoch": 4.88, "learning_rate": 1.954366346267876e-05, "loss": 0.0341, "step": 873 }, { "epoch": 4.88, "learning_rate": 1.954261343259204e-05, "loss": 0.0377, "step": 874 }, { "epoch": 4.89, "learning_rate": 1.9541562224107214e-05, "loss": 0.0282, "step": 875 }, { "epoch": 4.89, "learning_rate": 1.9540509837354097e-05, "loss": 0.0283, "step": 876 }, { "epoch": 4.9, "learning_rate": 1.953945627246265e-05, "loss": 0.0298, "step": 877 }, { "epoch": 4.91, "learning_rate": 1.953840152956297e-05, "loss": 0.0823, "step": 878 }, { "epoch": 4.91, "learning_rate": 1.953734560878531e-05, "loss": 0.0185, "step": 879 }, { "epoch": 4.92, "learning_rate": 1.953628851026006e-05, "loss": 0.0144, "step": 880 }, { "epoch": 4.92, "learning_rate": 1.9535230234117756e-05, "loss": 0.0153, "step": 881 }, { "epoch": 4.93, "learning_rate": 1.9534170780489088e-05, "loss": 0.0594, "step": 882 }, { "epoch": 4.93, "learning_rate": 1.9533110149504885e-05, "loss": 0.0314, "step": 883 }, { "epoch": 4.94, "learning_rate": 1.953204834129612e-05, "loss": 0.0256, "step": 884 }, { "epoch": 4.94, "learning_rate": 1.9530985355993913e-05, "loss": 0.0295, "step": 885 }, { "epoch": 4.95, "learning_rate": 1.9529921193729535e-05, "loss": 0.0291, "step": 886 }, { "epoch": 4.96, "learning_rate": 1.9528855854634393e-05, "loss": 0.0411, "step": 887 }, { "epoch": 4.96, "learning_rate": 1.9527789338840043e-05, "loss": 0.0602, "step": 888 }, { "epoch": 4.97, "learning_rate": 1.952672164647819e-05, "loss": 0.0438, "step": 889 }, { "epoch": 4.97, "learning_rate": 1.952565277768068e-05, "loss": 0.0216, "step": 890 }, { "epoch": 4.98, "learning_rate": 1.9524582732579497e-05, "loss": 0.0424, "step": 891 }, { "epoch": 4.98, "learning_rate": 1.9523511511306794e-05, "loss": 0.0231, "step": 892 }, { "epoch": 4.99, "learning_rate": 1.9522439113994847e-05, "loss": 0.0258, "step": 893 }, { "epoch": 4.99, "learning_rate": 1.952136554077608e-05, "loss": 0.0272, "step": 894 }, { "epoch": 5.0, "learning_rate": 1.952029079178307e-05, "loss": 0.0636, "step": 895 }, { "epoch": 5.01, "learning_rate": 1.951921486714854e-05, "loss": 0.0335, "step": 896 }, { "epoch": 5.01, "learning_rate": 1.951813776700535e-05, "loss": 0.015, "step": 897 }, { "epoch": 5.02, "learning_rate": 1.95170594914865e-05, "loss": 0.023, "step": 898 }, { "epoch": 5.02, "learning_rate": 1.951598004072516e-05, "loss": 0.025, "step": 899 }, { "epoch": 5.03, "learning_rate": 1.951489941485462e-05, "loss": 0.0153, "step": 900 }, { "epoch": 5.03, "learning_rate": 1.9513817614008325e-05, "loss": 0.0178, "step": 901 }, { "epoch": 5.04, "learning_rate": 1.951273463831987e-05, "loss": 0.0447, "step": 902 }, { "epoch": 5.04, "learning_rate": 1.9511650487922977e-05, "loss": 0.0521, "step": 903 }, { "epoch": 5.05, "learning_rate": 1.9510565162951538e-05, "loss": 0.018, "step": 904 }, { "epoch": 5.06, "learning_rate": 1.9509478663539573e-05, "loss": 0.0465, "step": 905 }, { "epoch": 5.06, "learning_rate": 1.9508390989821252e-05, "loss": 0.0448, "step": 906 }, { "epoch": 5.07, "learning_rate": 1.9507302141930885e-05, "loss": 0.0213, "step": 907 }, { "epoch": 5.07, "learning_rate": 1.9506212120002938e-05, "loss": 0.0337, "step": 908 }, { "epoch": 5.08, "learning_rate": 1.9505120924172016e-05, "loss": 0.0117, "step": 909 }, { "epoch": 5.08, "learning_rate": 1.9504028554572865e-05, "loss": 0.0126, "step": 910 }, { "epoch": 5.09, "learning_rate": 1.950293501134038e-05, "loss": 0.0063, "step": 911 }, { "epoch": 5.09, "learning_rate": 1.9501840294609602e-05, "loss": 0.0332, "step": 912 }, { "epoch": 5.1, "learning_rate": 1.9500744404515714e-05, "loss": 0.0415, "step": 913 }, { "epoch": 5.11, "learning_rate": 1.9499647341194047e-05, "loss": 0.0377, "step": 914 }, { "epoch": 5.11, "learning_rate": 1.949854910478007e-05, "loss": 0.0175, "step": 915 }, { "epoch": 5.12, "learning_rate": 1.949744969540941e-05, "loss": 0.015, "step": 916 }, { "epoch": 5.12, "learning_rate": 1.9496349113217824e-05, "loss": 0.026, "step": 917 }, { "epoch": 5.13, "learning_rate": 1.9495247358341223e-05, "loss": 0.0332, "step": 918 }, { "epoch": 5.13, "learning_rate": 1.9494144430915663e-05, "loss": 0.0116, "step": 919 }, { "epoch": 5.14, "learning_rate": 1.9493040331077336e-05, "loss": 0.0292, "step": 920 }, { "epoch": 5.15, "learning_rate": 1.9491935058962595e-05, "loss": 0.0198, "step": 921 }, { "epoch": 5.15, "learning_rate": 1.9490828614707917e-05, "loss": 0.0291, "step": 922 }, { "epoch": 5.16, "learning_rate": 1.948972099844994e-05, "loss": 0.0293, "step": 923 }, { "epoch": 5.16, "learning_rate": 1.9488612210325445e-05, "loss": 0.0192, "step": 924 }, { "epoch": 5.17, "learning_rate": 1.9487502250471347e-05, "loss": 0.0116, "step": 925 }, { "epoch": 5.17, "learning_rate": 1.9486391119024716e-05, "loss": 0.0116, "step": 926 }, { "epoch": 5.18, "learning_rate": 1.9485278816122765e-05, "loss": 0.0279, "step": 927 }, { "epoch": 5.18, "learning_rate": 1.9484165341902847e-05, "loss": 0.0553, "step": 928 }, { "epoch": 5.19, "learning_rate": 1.948305069650246e-05, "loss": 0.017, "step": 929 }, { "epoch": 5.2, "learning_rate": 1.9481934880059257e-05, "loss": 0.0385, "step": 930 }, { "epoch": 5.2, "learning_rate": 1.948081789271102e-05, "loss": 0.0222, "step": 931 }, { "epoch": 5.21, "learning_rate": 1.9479699734595693e-05, "loss": 0.0097, "step": 932 }, { "epoch": 5.21, "learning_rate": 1.9478580405851346e-05, "loss": 0.0143, "step": 933 }, { "epoch": 5.22, "learning_rate": 1.947745990661621e-05, "loss": 0.0128, "step": 934 }, { "epoch": 5.22, "learning_rate": 1.9476338237028644e-05, "loss": 0.0432, "step": 935 }, { "epoch": 5.23, "learning_rate": 1.9475215397227167e-05, "loss": 0.0141, "step": 936 }, { "epoch": 5.23, "learning_rate": 1.947409138735044e-05, "loss": 0.0277, "step": 937 }, { "epoch": 5.24, "learning_rate": 1.9472966207537257e-05, "loss": 0.0455, "step": 938 }, { "epoch": 5.25, "learning_rate": 1.9471839857926566e-05, "loss": 0.0113, "step": 939 }, { "epoch": 5.25, "learning_rate": 1.947071233865746e-05, "loss": 0.0112, "step": 940 }, { "epoch": 5.26, "learning_rate": 1.9469583649869174e-05, "loss": 0.0348, "step": 941 }, { "epoch": 5.26, "learning_rate": 1.9468453791701082e-05, "loss": 0.0451, "step": 942 }, { "epoch": 5.27, "learning_rate": 1.9467322764292715e-05, "loss": 0.0123, "step": 943 }, { "epoch": 5.27, "learning_rate": 1.946619056778374e-05, "loss": 0.0346, "step": 944 }, { "epoch": 5.28, "learning_rate": 1.9465057202313972e-05, "loss": 0.0463, "step": 945 }, { "epoch": 5.28, "learning_rate": 1.9463922668023358e-05, "loss": 0.0325, "step": 946 }, { "epoch": 5.29, "learning_rate": 1.9462786965052007e-05, "loss": 0.02, "step": 947 }, { "epoch": 5.3, "learning_rate": 1.9461650093540166e-05, "loss": 0.0236, "step": 948 }, { "epoch": 5.3, "learning_rate": 1.946051205362822e-05, "loss": 0.0248, "step": 949 }, { "epoch": 5.31, "learning_rate": 1.9459372845456706e-05, "loss": 0.0399, "step": 950 }, { "epoch": 5.31, "learning_rate": 1.94582324691663e-05, "loss": 0.0156, "step": 951 }, { "epoch": 5.32, "learning_rate": 1.945709092489783e-05, "loss": 0.0244, "step": 952 }, { "epoch": 5.32, "learning_rate": 1.945594821279226e-05, "loss": 0.0481, "step": 953 }, { "epoch": 5.33, "learning_rate": 1.94548043329907e-05, "loss": 0.0248, "step": 954 }, { "epoch": 5.34, "learning_rate": 1.945365928563441e-05, "loss": 0.0081, "step": 955 }, { "epoch": 5.34, "learning_rate": 1.945251307086478e-05, "loss": 0.0128, "step": 956 }, { "epoch": 5.35, "learning_rate": 1.9451365688823363e-05, "loss": 0.0152, "step": 957 }, { "epoch": 5.35, "learning_rate": 1.9450217139651845e-05, "loss": 0.0393, "step": 958 }, { "epoch": 5.36, "learning_rate": 1.9449067423492055e-05, "loss": 0.0186, "step": 959 }, { "epoch": 5.36, "learning_rate": 1.944791654048597e-05, "loss": 0.0393, "step": 960 }, { "epoch": 5.37, "learning_rate": 1.9446764490775714e-05, "loss": 0.012, "step": 961 }, { "epoch": 5.37, "learning_rate": 1.9445611274503547e-05, "loss": 0.0476, "step": 962 }, { "epoch": 5.38, "learning_rate": 1.944445689181188e-05, "loss": 0.0197, "step": 963 }, { "epoch": 5.39, "learning_rate": 1.944330134284326e-05, "loss": 0.0406, "step": 964 }, { "epoch": 5.39, "learning_rate": 1.944214462774039e-05, "loss": 0.0147, "step": 965 }, { "epoch": 5.4, "learning_rate": 1.944098674664611e-05, "loss": 0.0542, "step": 966 }, { "epoch": 5.4, "learning_rate": 1.94398276997034e-05, "loss": 0.0097, "step": 967 }, { "epoch": 5.41, "learning_rate": 1.9438667487055394e-05, "loss": 0.0106, "step": 968 }, { "epoch": 5.41, "learning_rate": 1.9437506108845358e-05, "loss": 0.0188, "step": 969 }, { "epoch": 5.42, "learning_rate": 1.943634356521671e-05, "loss": 0.0218, "step": 970 }, { "epoch": 5.42, "learning_rate": 1.9435179856313016e-05, "loss": 0.0246, "step": 971 }, { "epoch": 5.43, "learning_rate": 1.9434014982277972e-05, "loss": 0.0272, "step": 972 }, { "epoch": 5.44, "learning_rate": 1.9432848943255432e-05, "loss": 0.0276, "step": 973 }, { "epoch": 5.44, "learning_rate": 1.9431681739389385e-05, "loss": 0.01, "step": 974 }, { "epoch": 5.45, "learning_rate": 1.9430513370823965e-05, "loss": 0.0404, "step": 975 }, { "epoch": 5.45, "learning_rate": 1.9429343837703457e-05, "loss": 0.0262, "step": 976 }, { "epoch": 5.46, "learning_rate": 1.9428173140172278e-05, "loss": 0.0074, "step": 977 }, { "epoch": 5.46, "learning_rate": 1.9427001278374998e-05, "loss": 0.0351, "step": 978 }, { "epoch": 5.47, "learning_rate": 1.9425828252456326e-05, "loss": 0.0248, "step": 979 }, { "epoch": 5.47, "learning_rate": 1.942465406256112e-05, "loss": 0.0214, "step": 980 }, { "epoch": 5.48, "learning_rate": 1.9423478708834376e-05, "loss": 0.0065, "step": 981 }, { "epoch": 5.49, "learning_rate": 1.942230219142124e-05, "loss": 0.029, "step": 982 }, { "epoch": 5.49, "learning_rate": 1.9421124510466993e-05, "loss": 0.0232, "step": 983 }, { "epoch": 5.5, "learning_rate": 1.9419945666117064e-05, "loss": 0.0401, "step": 984 }, { "epoch": 5.5, "learning_rate": 1.9418765658517032e-05, "loss": 0.0048, "step": 985 }, { "epoch": 5.51, "learning_rate": 1.9417584487812605e-05, "loss": 0.0141, "step": 986 }, { "epoch": 5.51, "learning_rate": 1.941640215414965e-05, "loss": 0.0373, "step": 987 }, { "epoch": 5.52, "learning_rate": 1.941521865767417e-05, "loss": 0.0539, "step": 988 }, { "epoch": 5.53, "learning_rate": 1.9414033998532313e-05, "loss": 0.0447, "step": 989 }, { "epoch": 5.53, "learning_rate": 1.9412848176870365e-05, "loss": 0.0396, "step": 990 }, { "epoch": 5.54, "learning_rate": 1.9411661192834768e-05, "loss": 0.0219, "step": 991 }, { "epoch": 5.54, "learning_rate": 1.9410473046572097e-05, "loss": 0.0235, "step": 992 }, { "epoch": 5.55, "learning_rate": 1.9409283738229072e-05, "loss": 0.0277, "step": 993 }, { "epoch": 5.55, "learning_rate": 1.940809326795256e-05, "loss": 0.0112, "step": 994 }, { "epoch": 5.56, "learning_rate": 1.9406901635889573e-05, "loss": 0.0214, "step": 995 }, { "epoch": 5.56, "learning_rate": 1.9405708842187256e-05, "loss": 0.0218, "step": 996 }, { "epoch": 5.57, "learning_rate": 1.9404514886992908e-05, "loss": 0.0113, "step": 997 }, { "epoch": 5.58, "learning_rate": 1.9403319770453972e-05, "loss": 0.0187, "step": 998 }, { "epoch": 5.58, "learning_rate": 1.9402123492718027e-05, "loss": 0.0205, "step": 999 }, { "epoch": 5.59, "learning_rate": 1.94009260539328e-05, "loss": 0.0404, "step": 1000 }, { "epoch": 5.59, "learning_rate": 1.939972745424616e-05, "loss": 0.0351, "step": 1001 }, { "epoch": 5.6, "learning_rate": 1.9398527693806115e-05, "loss": 0.0116, "step": 1002 }, { "epoch": 5.6, "learning_rate": 1.939732677276083e-05, "loss": 0.0335, "step": 1003 }, { "epoch": 5.61, "learning_rate": 1.93961246912586e-05, "loss": 0.012, "step": 1004 }, { "epoch": 5.61, "learning_rate": 1.9394921449447863e-05, "loss": 0.0112, "step": 1005 }, { "epoch": 5.62, "learning_rate": 1.9393717047477213e-05, "loss": 0.0184, "step": 1006 }, { "epoch": 5.63, "learning_rate": 1.939251148549537e-05, "loss": 0.0266, "step": 1007 }, { "epoch": 5.63, "learning_rate": 1.9391304763651216e-05, "loss": 0.0146, "step": 1008 }, { "epoch": 5.64, "learning_rate": 1.9390096882093764e-05, "loss": 0.02, "step": 1009 }, { "epoch": 5.64, "learning_rate": 1.9388887840972167e-05, "loss": 0.0103, "step": 1010 }, { "epoch": 5.65, "learning_rate": 1.9387677640435734e-05, "loss": 0.014, "step": 1011 }, { "epoch": 5.65, "learning_rate": 1.9386466280633906e-05, "loss": 0.0193, "step": 1012 }, { "epoch": 5.66, "learning_rate": 1.9385253761716272e-05, "loss": 0.1235, "step": 1013 }, { "epoch": 5.66, "learning_rate": 1.9384040083832567e-05, "loss": 0.0382, "step": 1014 }, { "epoch": 5.67, "learning_rate": 1.9382825247132662e-05, "loss": 0.0326, "step": 1015 }, { "epoch": 5.68, "learning_rate": 1.9381609251766577e-05, "loss": 0.0105, "step": 1016 }, { "epoch": 5.68, "learning_rate": 1.9380392097884472e-05, "loss": 0.0057, "step": 1017 }, { "epoch": 5.69, "learning_rate": 1.9379173785636647e-05, "loss": 0.0078, "step": 1018 }, { "epoch": 5.69, "learning_rate": 1.9377954315173554e-05, "loss": 0.0279, "step": 1019 }, { "epoch": 5.7, "learning_rate": 1.9376733686645782e-05, "loss": 0.0095, "step": 1020 }, { "epoch": 5.7, "learning_rate": 1.9375511900204063e-05, "loss": 0.0293, "step": 1021 }, { "epoch": 5.71, "learning_rate": 1.9374288955999273e-05, "loss": 0.0257, "step": 1022 }, { "epoch": 5.72, "learning_rate": 1.937306485418243e-05, "loss": 0.018, "step": 1023 }, { "epoch": 5.72, "learning_rate": 1.93718395949047e-05, "loss": 0.0259, "step": 1024 }, { "epoch": 5.73, "learning_rate": 1.9370613178317382e-05, "loss": 0.019, "step": 1025 }, { "epoch": 5.73, "learning_rate": 1.9369385604571928e-05, "loss": 0.0069, "step": 1026 }, { "epoch": 5.74, "learning_rate": 1.936815687381993e-05, "loss": 0.0191, "step": 1027 }, { "epoch": 5.74, "learning_rate": 1.9366926986213115e-05, "loss": 0.0279, "step": 1028 }, { "epoch": 5.75, "learning_rate": 1.936569594190336e-05, "loss": 0.014, "step": 1029 }, { "epoch": 5.75, "learning_rate": 1.9364463741042694e-05, "loss": 0.0075, "step": 1030 }, { "epoch": 5.76, "learning_rate": 1.9363230383783266e-05, "loss": 0.014, "step": 1031 }, { "epoch": 5.77, "learning_rate": 1.9361995870277393e-05, "loss": 0.0492, "step": 1032 }, { "epoch": 5.77, "learning_rate": 1.9360760200677514e-05, "loss": 0.0256, "step": 1033 }, { "epoch": 5.78, "learning_rate": 1.935952337513622e-05, "loss": 0.0112, "step": 1034 }, { "epoch": 5.78, "learning_rate": 1.9358285393806247e-05, "loss": 0.0141, "step": 1035 }, { "epoch": 5.79, "learning_rate": 1.935704625684047e-05, "loss": 0.0536, "step": 1036 }, { "epoch": 5.79, "learning_rate": 1.935580596439191e-05, "loss": 0.006, "step": 1037 }, { "epoch": 5.8, "learning_rate": 1.9354564516613723e-05, "loss": 0.0137, "step": 1038 }, { "epoch": 5.8, "learning_rate": 1.9353321913659214e-05, "loss": 0.0107, "step": 1039 }, { "epoch": 5.81, "learning_rate": 1.9352078155681834e-05, "loss": 0.0067, "step": 1040 }, { "epoch": 5.82, "learning_rate": 1.935083324283517e-05, "loss": 0.0205, "step": 1041 }, { "epoch": 5.82, "learning_rate": 1.934958717527295e-05, "loss": 0.0104, "step": 1042 }, { "epoch": 5.83, "learning_rate": 1.934833995314905e-05, "loss": 0.0107, "step": 1043 }, { "epoch": 5.83, "learning_rate": 1.934709157661749e-05, "loss": 0.014, "step": 1044 }, { "epoch": 5.84, "learning_rate": 1.934584204583243e-05, "loss": 0.0111, "step": 1045 }, { "epoch": 5.84, "learning_rate": 1.9344591360948166e-05, "loss": 0.0147, "step": 1046 }, { "epoch": 5.85, "learning_rate": 1.934333952211915e-05, "loss": 0.0192, "step": 1047 }, { "epoch": 5.85, "learning_rate": 1.934208652949996e-05, "loss": 0.0231, "step": 1048 }, { "epoch": 5.86, "learning_rate": 1.9340832383245336e-05, "loss": 0.0113, "step": 1049 }, { "epoch": 5.87, "learning_rate": 1.9339577083510145e-05, "loss": 0.0066, "step": 1050 }, { "epoch": 5.87, "learning_rate": 1.93383206304494e-05, "loss": 0.022, "step": 1051 }, { "epoch": 5.88, "learning_rate": 1.9337063024218258e-05, "loss": 0.0113, "step": 1052 }, { "epoch": 5.88, "learning_rate": 1.9335804264972018e-05, "loss": 0.02, "step": 1053 }, { "epoch": 5.89, "learning_rate": 1.9334544352866126e-05, "loss": 0.0219, "step": 1054 }, { "epoch": 5.89, "learning_rate": 1.9333283288056163e-05, "loss": 0.0114, "step": 1055 }, { "epoch": 5.9, "learning_rate": 1.9332021070697854e-05, "loss": 0.0082, "step": 1056 }, { "epoch": 5.91, "learning_rate": 1.9330757700947073e-05, "loss": 0.0118, "step": 1057 }, { "epoch": 5.91, "learning_rate": 1.9329493178959823e-05, "loss": 0.0084, "step": 1058 }, { "epoch": 5.92, "learning_rate": 1.9328227504892263e-05, "loss": 0.0304, "step": 1059 }, { "epoch": 5.92, "learning_rate": 1.932696067890069e-05, "loss": 0.0077, "step": 1060 }, { "epoch": 5.93, "learning_rate": 1.9325692701141532e-05, "loss": 0.0125, "step": 1061 }, { "epoch": 5.93, "learning_rate": 1.9324423571771377e-05, "loss": 0.029, "step": 1062 }, { "epoch": 5.94, "learning_rate": 1.9323153290946954e-05, "loss": 0.0219, "step": 1063 }, { "epoch": 5.94, "learning_rate": 1.932188185882511e-05, "loss": 0.0192, "step": 1064 }, { "epoch": 5.95, "learning_rate": 1.9320609275562864e-05, "loss": 0.0164, "step": 1065 }, { "epoch": 5.96, "learning_rate": 1.9319335541317363e-05, "loss": 0.0104, "step": 1066 }, { "epoch": 5.96, "learning_rate": 1.9318060656245896e-05, "loss": 0.0398, "step": 1067 }, { "epoch": 5.97, "learning_rate": 1.93167846205059e-05, "loss": 0.0175, "step": 1068 }, { "epoch": 5.97, "learning_rate": 1.9315507434254938e-05, "loss": 0.0083, "step": 1069 }, { "epoch": 5.98, "learning_rate": 1.9314229097650744e-05, "loss": 0.0095, "step": 1070 }, { "epoch": 5.98, "learning_rate": 1.9312949610851166e-05, "loss": 0.013, "step": 1071 }, { "epoch": 5.99, "learning_rate": 1.9311668974014207e-05, "loss": 0.019, "step": 1072 }, { "epoch": 5.99, "learning_rate": 1.9310387187298014e-05, "loss": 0.0232, "step": 1073 }, { "epoch": 6.0, "learning_rate": 1.9309104250860868e-05, "loss": 0.0082, "step": 1074 }, { "epoch": 6.01, "learning_rate": 1.93078201648612e-05, "loss": 0.0191, "step": 1075 }, { "epoch": 6.01, "learning_rate": 1.9306534929457576e-05, "loss": 0.012, "step": 1076 }, { "epoch": 6.02, "learning_rate": 1.930524854480871e-05, "loss": 0.0117, "step": 1077 }, { "epoch": 6.02, "learning_rate": 1.9303961011073448e-05, "loss": 0.0053, "step": 1078 }, { "epoch": 6.03, "learning_rate": 1.9302672328410795e-05, "loss": 0.007, "step": 1079 }, { "epoch": 6.03, "learning_rate": 1.9301382496979884e-05, "loss": 0.0059, "step": 1080 }, { "epoch": 6.04, "learning_rate": 1.930009151693999e-05, "loss": 0.0094, "step": 1081 }, { "epoch": 6.04, "learning_rate": 1.929879938845054e-05, "loss": 0.006, "step": 1082 }, { "epoch": 6.05, "learning_rate": 1.9297506111671088e-05, "loss": 0.0145, "step": 1083 }, { "epoch": 6.06, "learning_rate": 1.9296211686761347e-05, "loss": 0.0152, "step": 1084 }, { "epoch": 6.06, "learning_rate": 1.9294916113881158e-05, "loss": 0.0222, "step": 1085 }, { "epoch": 6.07, "learning_rate": 1.929361939319051e-05, "loss": 0.009, "step": 1086 }, { "epoch": 6.07, "learning_rate": 1.9292321524849528e-05, "loss": 0.013, "step": 1087 }, { "epoch": 6.08, "learning_rate": 1.9291022509018492e-05, "loss": 0.013, "step": 1088 }, { "epoch": 6.08, "learning_rate": 1.9289722345857806e-05, "loss": 0.0264, "step": 1089 }, { "epoch": 6.09, "learning_rate": 1.928842103552803e-05, "loss": 0.0154, "step": 1090 }, { "epoch": 6.09, "learning_rate": 1.928711857818986e-05, "loss": 0.017, "step": 1091 }, { "epoch": 6.1, "learning_rate": 1.928581497400413e-05, "loss": 0.0151, "step": 1092 }, { "epoch": 6.11, "learning_rate": 1.928451022313182e-05, "loss": 0.0119, "step": 1093 }, { "epoch": 6.11, "learning_rate": 1.9283204325734058e-05, "loss": 0.0163, "step": 1094 }, { "epoch": 6.12, "learning_rate": 1.92818972819721e-05, "loss": 0.0105, "step": 1095 }, { "epoch": 6.12, "learning_rate": 1.9280589092007354e-05, "loss": 0.0167, "step": 1096 }, { "epoch": 6.13, "learning_rate": 1.927927975600136e-05, "loss": 0.0091, "step": 1097 }, { "epoch": 6.13, "learning_rate": 1.927796927411581e-05, "loss": 0.015, "step": 1098 }, { "epoch": 6.14, "learning_rate": 1.9276657646512527e-05, "loss": 0.0053, "step": 1099 }, { "epoch": 6.15, "learning_rate": 1.9275344873353495e-05, "loss": 0.0059, "step": 1100 }, { "epoch": 6.15, "learning_rate": 1.9274030954800808e-05, "loss": 0.0135, "step": 1101 }, { "epoch": 6.16, "learning_rate": 1.9272715891016736e-05, "loss": 0.0051, "step": 1102 }, { "epoch": 6.16, "learning_rate": 1.927139968216366e-05, "loss": 0.0131, "step": 1103 }, { "epoch": 6.17, "learning_rate": 1.927008232840412e-05, "loss": 0.0149, "step": 1104 }, { "epoch": 6.17, "learning_rate": 1.9268763829900798e-05, "loss": 0.0114, "step": 1105 }, { "epoch": 6.18, "learning_rate": 1.9267444186816506e-05, "loss": 0.0049, "step": 1106 }, { "epoch": 6.18, "learning_rate": 1.926612339931421e-05, "loss": 0.0087, "step": 1107 }, { "epoch": 6.19, "learning_rate": 1.9264801467557008e-05, "loss": 0.0986, "step": 1108 }, { "epoch": 6.2, "learning_rate": 1.9263478391708146e-05, "loss": 0.0288, "step": 1109 }, { "epoch": 6.2, "learning_rate": 1.9262154171931003e-05, "loss": 0.0126, "step": 1110 }, { "epoch": 6.21, "learning_rate": 1.9260828808389106e-05, "loss": 0.0082, "step": 1111 }, { "epoch": 6.21, "learning_rate": 1.9259502301246122e-05, "loss": 0.0053, "step": 1112 }, { "epoch": 6.22, "learning_rate": 1.9258174650665862e-05, "loss": 0.0069, "step": 1113 }, { "epoch": 6.22, "learning_rate": 1.9256845856812266e-05, "loss": 0.0056, "step": 1114 }, { "epoch": 6.23, "learning_rate": 1.9255515919849436e-05, "loss": 0.0146, "step": 1115 }, { "epoch": 6.23, "learning_rate": 1.9254184839941593e-05, "loss": 0.0124, "step": 1116 }, { "epoch": 6.24, "learning_rate": 1.9252852617253114e-05, "loss": 0.018, "step": 1117 }, { "epoch": 6.25, "learning_rate": 1.9251519251948512e-05, "loss": 0.026, "step": 1118 }, { "epoch": 6.25, "learning_rate": 1.9250184744192445e-05, "loss": 0.012, "step": 1119 }, { "epoch": 6.26, "learning_rate": 1.9248849094149703e-05, "loss": 0.0248, "step": 1120 }, { "epoch": 6.26, "learning_rate": 1.9247512301985224e-05, "loss": 0.0141, "step": 1121 }, { "epoch": 6.27, "learning_rate": 1.9246174367864086e-05, "loss": 0.0137, "step": 1122 }, { "epoch": 6.27, "learning_rate": 1.924483529195151e-05, "loss": 0.0042, "step": 1123 }, { "epoch": 6.28, "learning_rate": 1.9243495074412853e-05, "loss": 0.0104, "step": 1124 }, { "epoch": 6.28, "learning_rate": 1.924215371541362e-05, "loss": 0.0098, "step": 1125 }, { "epoch": 6.29, "learning_rate": 1.9240811215119447e-05, "loss": 0.0152, "step": 1126 }, { "epoch": 6.3, "learning_rate": 1.923946757369612e-05, "loss": 0.007, "step": 1127 }, { "epoch": 6.3, "learning_rate": 1.923812279130956e-05, "loss": 0.0333, "step": 1128 }, { "epoch": 6.31, "learning_rate": 1.9236776868125836e-05, "loss": 0.013, "step": 1129 }, { "epoch": 6.31, "learning_rate": 1.923542980431115e-05, "loss": 0.0364, "step": 1130 }, { "epoch": 6.32, "learning_rate": 1.9234081600031852e-05, "loss": 0.0083, "step": 1131 }, { "epoch": 6.32, "learning_rate": 1.9232732255454424e-05, "loss": 0.0049, "step": 1132 }, { "epoch": 6.33, "learning_rate": 1.9231381770745492e-05, "loss": 0.0062, "step": 1133 }, { "epoch": 6.34, "learning_rate": 1.923003014607183e-05, "loss": 0.0086, "step": 1134 }, { "epoch": 6.34, "learning_rate": 1.9228677381600352e-05, "loss": 0.0158, "step": 1135 }, { "epoch": 6.35, "learning_rate": 1.9227323477498098e-05, "loss": 0.0119, "step": 1136 }, { "epoch": 6.35, "learning_rate": 1.922596843393226e-05, "loss": 0.0068, "step": 1137 }, { "epoch": 6.36, "learning_rate": 1.9224612251070176e-05, "loss": 0.013, "step": 1138 }, { "epoch": 6.36, "learning_rate": 1.9223254929079313e-05, "loss": 0.0072, "step": 1139 }, { "epoch": 6.37, "learning_rate": 1.922189646812729e-05, "loss": 0.013, "step": 1140 }, { "epoch": 6.37, "learning_rate": 1.9220536868381852e-05, "loss": 0.0068, "step": 1141 }, { "epoch": 6.38, "learning_rate": 1.9219176130010896e-05, "loss": 0.0061, "step": 1142 }, { "epoch": 6.39, "learning_rate": 1.9217814253182464e-05, "loss": 0.0079, "step": 1143 }, { "epoch": 6.39, "learning_rate": 1.9216451238064723e-05, "loss": 0.035, "step": 1144 }, { "epoch": 6.4, "learning_rate": 1.9215087084825992e-05, "loss": 0.0058, "step": 1145 }, { "epoch": 6.4, "learning_rate": 1.9213721793634726e-05, "loss": 0.0094, "step": 1146 }, { "epoch": 6.41, "learning_rate": 1.9212355364659525e-05, "loss": 0.0127, "step": 1147 }, { "epoch": 6.41, "learning_rate": 1.9210987798069124e-05, "loss": 0.0133, "step": 1148 }, { "epoch": 6.42, "learning_rate": 1.9209619094032406e-05, "loss": 0.0293, "step": 1149 }, { "epoch": 6.42, "learning_rate": 1.920824925271838e-05, "loss": 0.0145, "step": 1150 }, { "epoch": 6.43, "learning_rate": 1.9206878274296215e-05, "loss": 0.0066, "step": 1151 }, { "epoch": 6.44, "learning_rate": 1.9205506158935203e-05, "loss": 0.0066, "step": 1152 }, { "epoch": 6.44, "learning_rate": 1.9204132906804788e-05, "loss": 0.012, "step": 1153 }, { "epoch": 6.45, "learning_rate": 1.9202758518074546e-05, "loss": 0.0084, "step": 1154 }, { "epoch": 6.45, "learning_rate": 1.9201382992914202e-05, "loss": 0.0105, "step": 1155 }, { "epoch": 6.46, "learning_rate": 1.920000633149362e-05, "loss": 0.0178, "step": 1156 }, { "epoch": 6.46, "learning_rate": 1.919862853398279e-05, "loss": 0.0148, "step": 1157 }, { "epoch": 6.47, "learning_rate": 1.9197249600551862e-05, "loss": 0.0037, "step": 1158 }, { "epoch": 6.47, "learning_rate": 1.9195869531371116e-05, "loss": 0.0071, "step": 1159 }, { "epoch": 6.48, "learning_rate": 1.9194488326610972e-05, "loss": 0.005, "step": 1160 }, { "epoch": 6.49, "learning_rate": 1.9193105986441995e-05, "loss": 0.0061, "step": 1161 }, { "epoch": 6.49, "learning_rate": 1.9191722511034884e-05, "loss": 0.0041, "step": 1162 }, { "epoch": 6.5, "learning_rate": 1.9190337900560486e-05, "loss": 0.0064, "step": 1163 }, { "epoch": 6.5, "learning_rate": 1.918895215518978e-05, "loss": 0.0041, "step": 1164 }, { "epoch": 6.51, "learning_rate": 1.918756527509389e-05, "loss": 0.0073, "step": 1165 }, { "epoch": 6.51, "learning_rate": 1.9186177260444078e-05, "loss": 0.011, "step": 1166 }, { "epoch": 6.52, "learning_rate": 1.918478811141175e-05, "loss": 0.0136, "step": 1167 }, { "epoch": 6.53, "learning_rate": 1.9183397828168448e-05, "loss": 0.0209, "step": 1168 }, { "epoch": 6.53, "learning_rate": 1.9182006410885857e-05, "loss": 0.0273, "step": 1169 }, { "epoch": 6.54, "learning_rate": 1.918061385973579e-05, "loss": 0.0079, "step": 1170 }, { "epoch": 6.54, "learning_rate": 1.917922017489023e-05, "loss": 0.0078, "step": 1171 }, { "epoch": 6.55, "learning_rate": 1.917782535652126e-05, "loss": 0.0086, "step": 1172 }, { "epoch": 6.55, "learning_rate": 1.9176429404801132e-05, "loss": 0.0161, "step": 1173 }, { "epoch": 6.56, "learning_rate": 1.9175032319902236e-05, "loss": 0.0043, "step": 1174 }, { "epoch": 6.56, "learning_rate": 1.9173634101997084e-05, "loss": 0.0087, "step": 1175 }, { "epoch": 6.57, "learning_rate": 1.9172234751258345e-05, "loss": 0.0121, "step": 1176 }, { "epoch": 6.58, "learning_rate": 1.917083426785882e-05, "loss": 0.0146, "step": 1177 }, { "epoch": 6.58, "learning_rate": 1.9169432651971455e-05, "loss": 0.0063, "step": 1178 }, { "epoch": 6.59, "learning_rate": 1.9168029903769328e-05, "loss": 0.0028, "step": 1179 }, { "epoch": 6.59, "learning_rate": 1.9166626023425663e-05, "loss": 0.0095, "step": 1180 }, { "epoch": 6.6, "learning_rate": 1.9165221011113823e-05, "loss": 0.017, "step": 1181 }, { "epoch": 6.6, "learning_rate": 1.916381486700731e-05, "loss": 0.0041, "step": 1182 }, { "epoch": 6.61, "learning_rate": 1.9162407591279772e-05, "loss": 0.0133, "step": 1183 }, { "epoch": 6.61, "learning_rate": 1.9160999184104982e-05, "loss": 0.0127, "step": 1184 }, { "epoch": 6.62, "learning_rate": 1.9159589645656863e-05, "loss": 0.0295, "step": 1185 }, { "epoch": 6.63, "learning_rate": 1.9158178976109475e-05, "loss": 0.0035, "step": 1186 }, { "epoch": 6.63, "learning_rate": 1.9156767175637024e-05, "loss": 0.014, "step": 1187 }, { "epoch": 6.64, "learning_rate": 1.9155354244413848e-05, "loss": 0.0133, "step": 1188 }, { "epoch": 6.64, "learning_rate": 1.9153940182614428e-05, "loss": 0.0041, "step": 1189 }, { "epoch": 6.65, "learning_rate": 1.9152524990413378e-05, "loss": 0.0082, "step": 1190 }, { "epoch": 6.65, "learning_rate": 1.915110866798546e-05, "loss": 0.005, "step": 1191 }, { "epoch": 6.66, "learning_rate": 1.9149691215505578e-05, "loss": 0.0073, "step": 1192 }, { "epoch": 6.66, "learning_rate": 1.914827263314877e-05, "loss": 0.0128, "step": 1193 }, { "epoch": 6.67, "learning_rate": 1.9146852921090207e-05, "loss": 0.0073, "step": 1194 }, { "epoch": 6.68, "learning_rate": 1.9145432079505205e-05, "loss": 0.0126, "step": 1195 }, { "epoch": 6.68, "learning_rate": 1.9144010108569233e-05, "loss": 0.0075, "step": 1196 }, { "epoch": 6.69, "learning_rate": 1.9142587008457874e-05, "loss": 0.0071, "step": 1197 }, { "epoch": 6.69, "learning_rate": 1.9141162779346875e-05, "loss": 0.0169, "step": 1198 }, { "epoch": 6.7, "learning_rate": 1.9139737421412102e-05, "loss": 0.0139, "step": 1199 }, { "epoch": 6.7, "learning_rate": 1.9138310934829576e-05, "loss": 0.0052, "step": 1200 }, { "epoch": 6.71, "learning_rate": 1.913688331977545e-05, "loss": 0.0334, "step": 1201 }, { "epoch": 6.72, "learning_rate": 1.913545457642601e-05, "loss": 0.0275, "step": 1202 }, { "epoch": 6.72, "learning_rate": 1.9134024704957698e-05, "loss": 0.0091, "step": 1203 }, { "epoch": 6.73, "learning_rate": 1.9132593705547082e-05, "loss": 0.0106, "step": 1204 }, { "epoch": 6.73, "learning_rate": 1.9131161578370875e-05, "loss": 0.0099, "step": 1205 }, { "epoch": 6.74, "learning_rate": 1.9129728323605926e-05, "loss": 0.0037, "step": 1206 }, { "epoch": 6.74, "learning_rate": 1.912829394142922e-05, "loss": 0.0166, "step": 1207 }, { "epoch": 6.75, "learning_rate": 1.9126858432017896e-05, "loss": 0.0198, "step": 1208 }, { "epoch": 6.75, "learning_rate": 1.9125421795549216e-05, "loss": 0.0094, "step": 1209 }, { "epoch": 6.76, "learning_rate": 1.9123984032200586e-05, "loss": 0.0092, "step": 1210 }, { "epoch": 6.77, "learning_rate": 1.9122545142149555e-05, "loss": 0.0044, "step": 1211 }, { "epoch": 6.77, "learning_rate": 1.9121105125573813e-05, "loss": 0.0047, "step": 1212 }, { "epoch": 6.78, "learning_rate": 1.9119663982651177e-05, "loss": 0.0212, "step": 1213 }, { "epoch": 6.78, "learning_rate": 1.911822171355961e-05, "loss": 0.0135, "step": 1214 }, { "epoch": 6.79, "learning_rate": 1.9116778318477225e-05, "loss": 0.008, "step": 1215 }, { "epoch": 6.79, "learning_rate": 1.9115333797582252e-05, "loss": 0.0065, "step": 1216 }, { "epoch": 6.8, "learning_rate": 1.9113888151053084e-05, "loss": 0.0091, "step": 1217 }, { "epoch": 6.8, "learning_rate": 1.9112441379068232e-05, "loss": 0.0073, "step": 1218 }, { "epoch": 6.81, "learning_rate": 1.911099348180636e-05, "loss": 0.0045, "step": 1219 }, { "epoch": 6.82, "learning_rate": 1.910954445944626e-05, "loss": 0.0047, "step": 1220 }, { "epoch": 6.82, "learning_rate": 1.9108094312166875e-05, "loss": 0.0037, "step": 1221 }, { "epoch": 6.83, "learning_rate": 1.910664304014728e-05, "loss": 0.0037, "step": 1222 }, { "epoch": 6.83, "learning_rate": 1.9105190643566686e-05, "loss": 0.0061, "step": 1223 }, { "epoch": 6.84, "learning_rate": 1.9103737122604444e-05, "loss": 0.014, "step": 1224 }, { "epoch": 6.84, "learning_rate": 1.9102282477440054e-05, "loss": 0.0123, "step": 1225 }, { "epoch": 6.85, "learning_rate": 1.9100826708253148e-05, "loss": 0.0057, "step": 1226 }, { "epoch": 6.85, "learning_rate": 1.909936981522349e-05, "loss": 0.0156, "step": 1227 }, { "epoch": 6.86, "learning_rate": 1.909791179853099e-05, "loss": 0.0059, "step": 1228 }, { "epoch": 6.87, "learning_rate": 1.9096452658355695e-05, "loss": 0.0084, "step": 1229 }, { "epoch": 6.87, "learning_rate": 1.9094992394877792e-05, "loss": 0.0106, "step": 1230 }, { "epoch": 6.88, "learning_rate": 1.909353100827761e-05, "loss": 0.0102, "step": 1231 }, { "epoch": 6.88, "learning_rate": 1.9092068498735607e-05, "loss": 0.0074, "step": 1232 }, { "epoch": 6.89, "learning_rate": 1.909060486643239e-05, "loss": 0.0064, "step": 1233 }, { "epoch": 6.89, "learning_rate": 1.9089140111548695e-05, "loss": 0.0051, "step": 1234 }, { "epoch": 6.9, "learning_rate": 1.908767423426541e-05, "loss": 0.003, "step": 1235 }, { "epoch": 6.91, "learning_rate": 1.908620723476354e-05, "loss": 0.0041, "step": 1236 }, { "epoch": 6.91, "learning_rate": 1.9084739113224253e-05, "loss": 0.0295, "step": 1237 }, { "epoch": 6.92, "learning_rate": 1.908326986982884e-05, "loss": 0.0077, "step": 1238 }, { "epoch": 6.92, "learning_rate": 1.908179950475874e-05, "loss": 0.0047, "step": 1239 }, { "epoch": 6.93, "learning_rate": 1.9080328018195512e-05, "loss": 0.0116, "step": 1240 }, { "epoch": 6.93, "learning_rate": 1.907885541032088e-05, "loss": 0.0067, "step": 1241 }, { "epoch": 6.94, "learning_rate": 1.9077381681316693e-05, "loss": 0.0062, "step": 1242 }, { "epoch": 6.94, "learning_rate": 1.9075906831364933e-05, "loss": 0.0058, "step": 1243 }, { "epoch": 6.95, "learning_rate": 1.9074430860647728e-05, "loss": 0.0033, "step": 1244 }, { "epoch": 6.96, "learning_rate": 1.907295376934734e-05, "loss": 0.0042, "step": 1245 }, { "epoch": 6.96, "learning_rate": 1.907147555764618e-05, "loss": 0.0068, "step": 1246 }, { "epoch": 6.97, "learning_rate": 1.9069996225726784e-05, "loss": 0.0116, "step": 1247 }, { "epoch": 6.97, "learning_rate": 1.906851577377183e-05, "loss": 0.0125, "step": 1248 }, { "epoch": 6.98, "learning_rate": 1.9067034201964142e-05, "loss": 0.0071, "step": 1249 }, { "epoch": 6.98, "learning_rate": 1.9065551510486668e-05, "loss": 0.0089, "step": 1250 }, { "epoch": 6.99, "learning_rate": 1.906406769952251e-05, "loss": 0.005, "step": 1251 }, { "epoch": 6.99, "learning_rate": 1.9062582769254896e-05, "loss": 0.0093, "step": 1252 }, { "epoch": 7.0, "learning_rate": 1.90610967198672e-05, "loss": 0.0069, "step": 1253 }, { "epoch": 7.01, "learning_rate": 1.905960955154293e-05, "loss": 0.0101, "step": 1254 }, { "epoch": 7.01, "learning_rate": 1.9058121264465733e-05, "loss": 0.0068, "step": 1255 }, { "epoch": 7.02, "learning_rate": 1.90566318588194e-05, "loss": 0.0044, "step": 1256 }, { "epoch": 7.02, "learning_rate": 1.9055141334787843e-05, "loss": 0.0056, "step": 1257 }, { "epoch": 7.03, "learning_rate": 1.9053649692555135e-05, "loss": 0.0123, "step": 1258 }, { "epoch": 7.03, "learning_rate": 1.905215693230547e-05, "loss": 0.0053, "step": 1259 }, { "epoch": 7.04, "learning_rate": 1.905066305422319e-05, "loss": 0.0045, "step": 1260 }, { "epoch": 7.04, "learning_rate": 1.9049168058492764e-05, "loss": 0.0059, "step": 1261 }, { "epoch": 7.05, "learning_rate": 1.9047671945298813e-05, "loss": 0.0142, "step": 1262 }, { "epoch": 7.06, "learning_rate": 1.904617471482609e-05, "loss": 0.0049, "step": 1263 }, { "epoch": 7.06, "learning_rate": 1.9044676367259474e-05, "loss": 0.0047, "step": 1264 }, { "epoch": 7.07, "learning_rate": 1.9043176902784007e-05, "loss": 0.0025, "step": 1265 }, { "epoch": 7.07, "learning_rate": 1.904167632158485e-05, "loss": 0.0014, "step": 1266 }, { "epoch": 7.08, "learning_rate": 1.9040174623847297e-05, "loss": 0.0048, "step": 1267 }, { "epoch": 7.08, "learning_rate": 1.9038671809756805e-05, "loss": 0.0038, "step": 1268 }, { "epoch": 7.09, "learning_rate": 1.9037167879498942e-05, "loss": 0.0044, "step": 1269 }, { "epoch": 7.09, "learning_rate": 1.9035662833259433e-05, "loss": 0.0044, "step": 1270 }, { "epoch": 7.1, "learning_rate": 1.9034156671224128e-05, "loss": 0.0046, "step": 1271 }, { "epoch": 7.11, "learning_rate": 1.9032649393579018e-05, "loss": 0.0047, "step": 1272 }, { "epoch": 7.11, "learning_rate": 1.9031141000510243e-05, "loss": 0.0033, "step": 1273 }, { "epoch": 7.12, "learning_rate": 1.9029631492204062e-05, "loss": 0.004, "step": 1274 }, { "epoch": 7.12, "learning_rate": 1.9028120868846888e-05, "loss": 0.0072, "step": 1275 }, { "epoch": 7.13, "learning_rate": 1.9026609130625257e-05, "loss": 0.0055, "step": 1276 }, { "epoch": 7.13, "learning_rate": 1.9025096277725858e-05, "loss": 0.0046, "step": 1277 }, { "epoch": 7.14, "learning_rate": 1.902358231033551e-05, "loss": 0.0075, "step": 1278 }, { "epoch": 7.15, "learning_rate": 1.9022067228641164e-05, "loss": 0.0101, "step": 1279 }, { "epoch": 7.15, "learning_rate": 1.9020551032829918e-05, "loss": 0.0089, "step": 1280 }, { "epoch": 7.16, "learning_rate": 1.9019033723089004e-05, "loss": 0.0064, "step": 1281 }, { "epoch": 7.16, "learning_rate": 1.901751529960579e-05, "loss": 0.004, "step": 1282 }, { "epoch": 7.17, "learning_rate": 1.9015995762567782e-05, "loss": 0.0034, "step": 1283 }, { "epoch": 7.17, "learning_rate": 1.901447511216263e-05, "loss": 0.004, "step": 1284 }, { "epoch": 7.18, "learning_rate": 1.901295334857811e-05, "loss": 0.0027, "step": 1285 }, { "epoch": 7.18, "learning_rate": 1.9011430472002148e-05, "loss": 0.0038, "step": 1286 }, { "epoch": 7.19, "learning_rate": 1.9009906482622794e-05, "loss": 0.0069, "step": 1287 }, { "epoch": 7.2, "learning_rate": 1.900838138062825e-05, "loss": 0.0031, "step": 1288 }, { "epoch": 7.2, "learning_rate": 1.9006855166206834e-05, "loss": 0.0034, "step": 1289 }, { "epoch": 7.21, "learning_rate": 1.9005327839547032e-05, "loss": 0.004, "step": 1290 }, { "epoch": 7.21, "learning_rate": 1.900379940083744e-05, "loss": 0.0036, "step": 1291 }, { "epoch": 7.22, "learning_rate": 1.9002269850266805e-05, "loss": 0.005, "step": 1292 }, { "epoch": 7.22, "learning_rate": 1.900073918802401e-05, "loss": 0.0056, "step": 1293 }, { "epoch": 7.23, "learning_rate": 1.899920741429807e-05, "loss": 0.0103, "step": 1294 }, { "epoch": 7.23, "learning_rate": 1.8997674529278137e-05, "loss": 0.0139, "step": 1295 }, { "epoch": 7.24, "learning_rate": 1.8996140533153517e-05, "loss": 0.0028, "step": 1296 }, { "epoch": 7.25, "learning_rate": 1.8994605426113625e-05, "loss": 0.003, "step": 1297 }, { "epoch": 7.25, "learning_rate": 1.899306920834804e-05, "loss": 0.0029, "step": 1298 }, { "epoch": 7.26, "learning_rate": 1.899153188004646e-05, "loss": 0.0028, "step": 1299 }, { "epoch": 7.26, "learning_rate": 1.898999344139873e-05, "loss": 0.0048, "step": 1300 }, { "epoch": 7.27, "learning_rate": 1.8988453892594823e-05, "loss": 0.0913, "step": 1301 }, { "epoch": 7.27, "learning_rate": 1.8986913233824863e-05, "loss": 0.0046, "step": 1302 }, { "epoch": 7.28, "learning_rate": 1.898537146527909e-05, "loss": 0.0102, "step": 1303 }, { "epoch": 7.28, "learning_rate": 1.8983828587147914e-05, "loss": 0.0116, "step": 1304 }, { "epoch": 7.29, "learning_rate": 1.898228459962184e-05, "loss": 0.0051, "step": 1305 }, { "epoch": 7.3, "learning_rate": 1.8980739502891548e-05, "loss": 0.0039, "step": 1306 }, { "epoch": 7.3, "learning_rate": 1.8979193297147832e-05, "loss": 0.0036, "step": 1307 }, { "epoch": 7.31, "learning_rate": 1.8977645982581633e-05, "loss": 0.0039, "step": 1308 }, { "epoch": 7.31, "learning_rate": 1.897609755938402e-05, "loss": 0.0043, "step": 1309 }, { "epoch": 7.32, "learning_rate": 1.8974548027746208e-05, "loss": 0.0056, "step": 1310 }, { "epoch": 7.32, "learning_rate": 1.8972997387859546e-05, "loss": 0.0093, "step": 1311 }, { "epoch": 7.33, "learning_rate": 1.8971445639915522e-05, "loss": 0.0104, "step": 1312 }, { "epoch": 7.34, "learning_rate": 1.8969892784105756e-05, "loss": 0.0064, "step": 1313 }, { "epoch": 7.34, "learning_rate": 1.8968338820622002e-05, "loss": 0.0064, "step": 1314 }, { "epoch": 7.35, "learning_rate": 1.8966783749656162e-05, "loss": 0.0016, "step": 1315 }, { "epoch": 7.35, "learning_rate": 1.8965227571400267e-05, "loss": 0.0075, "step": 1316 }, { "epoch": 7.36, "learning_rate": 1.896367028604649e-05, "loss": 0.0039, "step": 1317 }, { "epoch": 7.36, "learning_rate": 1.896211189378713e-05, "loss": 0.0183, "step": 1318 }, { "epoch": 7.37, "learning_rate": 1.896055239481463e-05, "loss": 0.0046, "step": 1319 }, { "epoch": 7.37, "learning_rate": 1.895899178932158e-05, "loss": 0.0046, "step": 1320 }, { "epoch": 7.38, "learning_rate": 1.8957430077500683e-05, "loss": 0.0107, "step": 1321 }, { "epoch": 7.39, "learning_rate": 1.8955867259544795e-05, "loss": 0.0036, "step": 1322 }, { "epoch": 7.39, "learning_rate": 1.8954303335646913e-05, "loss": 0.0074, "step": 1323 }, { "epoch": 7.4, "learning_rate": 1.8952738306000152e-05, "loss": 0.0019, "step": 1324 }, { "epoch": 7.4, "learning_rate": 1.8951172170797783e-05, "loss": 0.0046, "step": 1325 }, { "epoch": 7.41, "learning_rate": 1.89496049302332e-05, "loss": 0.0039, "step": 1326 }, { "epoch": 7.41, "learning_rate": 1.8948036584499938e-05, "loss": 0.0072, "step": 1327 }, { "epoch": 7.42, "learning_rate": 1.894646713379167e-05, "loss": 0.0062, "step": 1328 }, { "epoch": 7.42, "learning_rate": 1.894489657830221e-05, "loss": 0.0042, "step": 1329 }, { "epoch": 7.43, "learning_rate": 1.8943324918225495e-05, "loss": 0.003, "step": 1330 }, { "epoch": 7.44, "learning_rate": 1.8941752153755607e-05, "loss": 0.0098, "step": 1331 }, { "epoch": 7.44, "learning_rate": 1.894017828508677e-05, "loss": 0.0256, "step": 1332 }, { "epoch": 7.45, "learning_rate": 1.8938603312413327e-05, "loss": 0.0119, "step": 1333 }, { "epoch": 7.45, "learning_rate": 1.8937027235929778e-05, "loss": 0.0047, "step": 1334 }, { "epoch": 7.46, "learning_rate": 1.8935450055830742e-05, "loss": 0.02, "step": 1335 }, { "epoch": 7.46, "learning_rate": 1.893387177231099e-05, "loss": 0.0075, "step": 1336 }, { "epoch": 7.47, "learning_rate": 1.8932292385565413e-05, "loss": 0.0079, "step": 1337 }, { "epoch": 7.47, "learning_rate": 1.8930711895789053e-05, "loss": 0.0048, "step": 1338 }, { "epoch": 7.48, "learning_rate": 1.8929130303177077e-05, "loss": 0.0047, "step": 1339 }, { "epoch": 7.49, "learning_rate": 1.8927547607924796e-05, "loss": 0.0047, "step": 1340 }, { "epoch": 7.49, "learning_rate": 1.8925963810227648e-05, "loss": 0.0099, "step": 1341 }, { "epoch": 7.5, "learning_rate": 1.892437891028122e-05, "loss": 0.002, "step": 1342 }, { "epoch": 7.5, "learning_rate": 1.8922792908281225e-05, "loss": 0.0231, "step": 1343 }, { "epoch": 7.51, "learning_rate": 1.8921205804423515e-05, "loss": 0.0062, "step": 1344 }, { "epoch": 7.51, "learning_rate": 1.891961759890408e-05, "loss": 0.0039, "step": 1345 }, { "epoch": 7.52, "learning_rate": 1.891802829191904e-05, "loss": 0.0033, "step": 1346 }, { "epoch": 7.53, "learning_rate": 1.8916437883664658e-05, "loss": 0.0059, "step": 1347 }, { "epoch": 7.53, "learning_rate": 1.8914846374337334e-05, "loss": 0.0048, "step": 1348 }, { "epoch": 7.54, "learning_rate": 1.891325376413359e-05, "loss": 0.0028, "step": 1349 }, { "epoch": 7.54, "learning_rate": 1.8911660053250106e-05, "loss": 0.0073, "step": 1350 }, { "epoch": 7.55, "learning_rate": 1.891006524188368e-05, "loss": 0.0023, "step": 1351 }, { "epoch": 7.55, "learning_rate": 1.8908469330231253e-05, "loss": 0.0022, "step": 1352 }, { "epoch": 7.56, "learning_rate": 1.89068723184899e-05, "loss": 0.0037, "step": 1353 }, { "epoch": 7.56, "learning_rate": 1.890527420685684e-05, "loss": 0.0029, "step": 1354 }, { "epoch": 7.57, "learning_rate": 1.8903674995529406e-05, "loss": 0.0067, "step": 1355 }, { "epoch": 7.58, "learning_rate": 1.8902074684705096e-05, "loss": 0.0039, "step": 1356 }, { "epoch": 7.58, "learning_rate": 1.8900473274581518e-05, "loss": 0.0105, "step": 1357 }, { "epoch": 7.59, "learning_rate": 1.889887076535643e-05, "loss": 0.004, "step": 1358 }, { "epoch": 7.59, "learning_rate": 1.8897267157227732e-05, "loss": 0.0051, "step": 1359 }, { "epoch": 7.6, "learning_rate": 1.889566245039344e-05, "loss": 0.0041, "step": 1360 }, { "epoch": 7.6, "learning_rate": 1.8894056645051716e-05, "loss": 0.0057, "step": 1361 }, { "epoch": 7.61, "learning_rate": 1.8892449741400864e-05, "loss": 0.003, "step": 1362 }, { "epoch": 7.61, "learning_rate": 1.889084173963931e-05, "loss": 0.0045, "step": 1363 }, { "epoch": 7.62, "learning_rate": 1.8889232639965633e-05, "loss": 0.0045, "step": 1364 }, { "epoch": 7.63, "learning_rate": 1.8887622442578525e-05, "loss": 0.0021, "step": 1365 }, { "epoch": 7.63, "learning_rate": 1.8886011147676835e-05, "loss": 0.0119, "step": 1366 }, { "epoch": 7.64, "learning_rate": 1.8884398755459534e-05, "loss": 0.0044, "step": 1367 }, { "epoch": 7.64, "learning_rate": 1.8882785266125735e-05, "loss": 0.0059, "step": 1368 }, { "epoch": 7.65, "learning_rate": 1.8881170679874684e-05, "loss": 0.0041, "step": 1369 }, { "epoch": 7.65, "learning_rate": 1.8879554996905766e-05, "loss": 0.0054, "step": 1370 }, { "epoch": 7.66, "learning_rate": 1.8877938217418495e-05, "loss": 0.0043, "step": 1371 }, { "epoch": 7.66, "learning_rate": 1.8876320341612523e-05, "loss": 0.0015, "step": 1372 }, { "epoch": 7.67, "learning_rate": 1.8874701369687642e-05, "loss": 0.0054, "step": 1373 }, { "epoch": 7.68, "learning_rate": 1.887308130184377e-05, "loss": 0.0046, "step": 1374 }, { "epoch": 7.68, "learning_rate": 1.8871460138280972e-05, "loss": 0.0027, "step": 1375 }, { "epoch": 7.69, "learning_rate": 1.8869837879199438e-05, "loss": 0.0056, "step": 1376 }, { "epoch": 7.69, "learning_rate": 1.88682145247995e-05, "loss": 0.0048, "step": 1377 }, { "epoch": 7.7, "learning_rate": 1.8866590075281624e-05, "loss": 0.0042, "step": 1378 }, { "epoch": 7.7, "learning_rate": 1.8864964530846405e-05, "loss": 0.0016, "step": 1379 }, { "epoch": 7.71, "learning_rate": 1.8863337891694583e-05, "loss": 0.0036, "step": 1380 }, { "epoch": 7.72, "learning_rate": 1.8861710158027024e-05, "loss": 0.0027, "step": 1381 }, { "epoch": 7.72, "learning_rate": 1.886008133004474e-05, "loss": 0.004, "step": 1382 }, { "epoch": 7.73, "learning_rate": 1.8858451407948864e-05, "loss": 0.0061, "step": 1383 }, { "epoch": 7.73, "learning_rate": 1.8856820391940675e-05, "loss": 0.0034, "step": 1384 }, { "epoch": 7.74, "learning_rate": 1.8855188282221585e-05, "loss": 0.0037, "step": 1385 }, { "epoch": 7.74, "learning_rate": 1.885355507899314e-05, "loss": 0.0066, "step": 1386 }, { "epoch": 7.75, "learning_rate": 1.8851920782457022e-05, "loss": 0.0046, "step": 1387 }, { "epoch": 7.75, "learning_rate": 1.8850285392815043e-05, "loss": 0.0064, "step": 1388 }, { "epoch": 7.76, "learning_rate": 1.8848648910269157e-05, "loss": 0.0066, "step": 1389 }, { "epoch": 7.77, "learning_rate": 1.8847011335021447e-05, "loss": 0.0026, "step": 1390 }, { "epoch": 7.77, "learning_rate": 1.884537266727414e-05, "loss": 0.0029, "step": 1391 }, { "epoch": 7.78, "learning_rate": 1.8843732907229585e-05, "loss": 0.0034, "step": 1392 }, { "epoch": 7.78, "learning_rate": 1.8842092055090276e-05, "loss": 0.0062, "step": 1393 }, { "epoch": 7.79, "learning_rate": 1.8840450111058837e-05, "loss": 0.0018, "step": 1394 }, { "epoch": 7.79, "learning_rate": 1.883880707533803e-05, "loss": 0.0034, "step": 1395 }, { "epoch": 7.8, "learning_rate": 1.883716294813075e-05, "loss": 0.0056, "step": 1396 }, { "epoch": 7.8, "learning_rate": 1.8835517729640025e-05, "loss": 0.0058, "step": 1397 }, { "epoch": 7.81, "learning_rate": 1.8833871420069022e-05, "loss": 0.0062, "step": 1398 }, { "epoch": 7.82, "learning_rate": 1.8832224019621042e-05, "loss": 0.004, "step": 1399 }, { "epoch": 7.82, "learning_rate": 1.8830575528499513e-05, "loss": 0.0023, "step": 1400 }, { "epoch": 7.83, "learning_rate": 1.8828925946908012e-05, "loss": 0.009, "step": 1401 }, { "epoch": 7.83, "learning_rate": 1.8827275275050233e-05, "loss": 0.0047, "step": 1402 }, { "epoch": 7.84, "learning_rate": 1.8825623513130026e-05, "loss": 0.0024, "step": 1403 }, { "epoch": 7.84, "learning_rate": 1.882397066135135e-05, "loss": 0.0183, "step": 1404 }, { "epoch": 7.85, "learning_rate": 1.882231671991832e-05, "loss": 0.011, "step": 1405 }, { "epoch": 7.85, "learning_rate": 1.882066168903518e-05, "loss": 0.0048, "step": 1406 }, { "epoch": 7.86, "learning_rate": 1.8819005568906305e-05, "loss": 0.0034, "step": 1407 }, { "epoch": 7.87, "learning_rate": 1.8817348359736202e-05, "loss": 0.0088, "step": 1408 }, { "epoch": 7.87, "learning_rate": 1.8815690061729518e-05, "loss": 0.0044, "step": 1409 }, { "epoch": 7.88, "learning_rate": 1.881403067509104e-05, "loss": 0.0017, "step": 1410 }, { "epoch": 7.88, "learning_rate": 1.881237020002567e-05, "loss": 0.0052, "step": 1411 }, { "epoch": 7.89, "learning_rate": 1.8810708636738466e-05, "loss": 0.0038, "step": 1412 }, { "epoch": 7.89, "learning_rate": 1.8809045985434606e-05, "loss": 0.003, "step": 1413 }, { "epoch": 7.9, "learning_rate": 1.8807382246319413e-05, "loss": 0.0022, "step": 1414 }, { "epoch": 7.91, "learning_rate": 1.880571741959833e-05, "loss": 0.0059, "step": 1415 }, { "epoch": 7.91, "learning_rate": 1.880405150547695e-05, "loss": 0.0246, "step": 1416 }, { "epoch": 7.92, "learning_rate": 1.8802384504160994e-05, "loss": 0.0038, "step": 1417 }, { "epoch": 7.92, "learning_rate": 1.8800716415856316e-05, "loss": 0.0025, "step": 1418 }, { "epoch": 7.93, "learning_rate": 1.87990472407689e-05, "loss": 0.0084, "step": 1419 }, { "epoch": 7.93, "learning_rate": 1.8797376979104874e-05, "loss": 0.0039, "step": 1420 }, { "epoch": 7.94, "learning_rate": 1.879570563107049e-05, "loss": 0.0076, "step": 1421 }, { "epoch": 7.94, "learning_rate": 1.8794033196872145e-05, "loss": 0.0075, "step": 1422 }, { "epoch": 7.95, "learning_rate": 1.8792359676716364e-05, "loss": 0.004, "step": 1423 }, { "epoch": 7.96, "learning_rate": 1.8790685070809808e-05, "loss": 0.0018, "step": 1424 }, { "epoch": 7.96, "learning_rate": 1.878900937935926e-05, "loss": 0.0073, "step": 1425 }, { "epoch": 7.97, "learning_rate": 1.8787332602571663e-05, "loss": 0.006, "step": 1426 }, { "epoch": 7.97, "learning_rate": 1.8785654740654065e-05, "loss": 0.0033, "step": 1427 }, { "epoch": 7.98, "learning_rate": 1.8783975793813674e-05, "loss": 0.0265, "step": 1428 }, { "epoch": 7.98, "learning_rate": 1.878229576225781e-05, "loss": 0.005, "step": 1429 }, { "epoch": 7.99, "learning_rate": 1.8780614646193944e-05, "loss": 0.0066, "step": 1430 }, { "epoch": 7.99, "learning_rate": 1.8778932445829668e-05, "loss": 0.006, "step": 1431 }, { "epoch": 8.0, "learning_rate": 1.8777249161372713e-05, "loss": 0.003, "step": 1432 }, { "epoch": 8.01, "learning_rate": 1.8775564793030953e-05, "loss": 0.0042, "step": 1433 }, { "epoch": 8.01, "learning_rate": 1.877387934101238e-05, "loss": 0.0056, "step": 1434 }, { "epoch": 8.02, "learning_rate": 1.8772192805525125e-05, "loss": 0.0045, "step": 1435 }, { "epoch": 8.02, "learning_rate": 1.8770505186777463e-05, "loss": 0.0024, "step": 1436 }, { "epoch": 8.03, "learning_rate": 1.8768816484977787e-05, "loss": 0.0058, "step": 1437 }, { "epoch": 8.03, "learning_rate": 1.8767126700334633e-05, "loss": 0.0019, "step": 1438 }, { "epoch": 8.04, "learning_rate": 1.8765435833056674e-05, "loss": 0.0045, "step": 1439 }, { "epoch": 8.04, "learning_rate": 1.876374388335271e-05, "loss": 0.0043, "step": 1440 }, { "epoch": 8.05, "learning_rate": 1.8762050851431672e-05, "loss": 0.0048, "step": 1441 }, { "epoch": 8.06, "learning_rate": 1.8760356737502633e-05, "loss": 0.0025, "step": 1442 }, { "epoch": 8.06, "learning_rate": 1.8758661541774793e-05, "loss": 0.0038, "step": 1443 }, { "epoch": 8.07, "learning_rate": 1.875696526445749e-05, "loss": 0.0045, "step": 1444 }, { "epoch": 8.07, "learning_rate": 1.8755267905760194e-05, "loss": 0.0026, "step": 1445 }, { "epoch": 8.08, "learning_rate": 1.875356946589251e-05, "loss": 0.0036, "step": 1446 }, { "epoch": 8.08, "learning_rate": 1.875186994506417e-05, "loss": 0.0032, "step": 1447 }, { "epoch": 8.09, "learning_rate": 1.875016934348505e-05, "loss": 0.0056, "step": 1448 }, { "epoch": 8.09, "learning_rate": 1.874846766136515e-05, "loss": 0.004, "step": 1449 }, { "epoch": 8.1, "learning_rate": 1.874676489891461e-05, "loss": 0.0073, "step": 1450 }, { "epoch": 8.11, "learning_rate": 1.8745061056343698e-05, "loss": 0.002, "step": 1451 }, { "epoch": 8.11, "learning_rate": 1.874335613386282e-05, "loss": 0.0037, "step": 1452 }, { "epoch": 8.12, "learning_rate": 1.8741650131682514e-05, "loss": 0.0033, "step": 1453 }, { "epoch": 8.12, "learning_rate": 1.873994305001345e-05, "loss": 0.0029, "step": 1454 }, { "epoch": 8.13, "learning_rate": 1.8738234889066428e-05, "loss": 0.0019, "step": 1455 }, { "epoch": 8.13, "learning_rate": 1.8736525649052394e-05, "loss": 0.0028, "step": 1456 }, { "epoch": 8.14, "learning_rate": 1.873481533018241e-05, "loss": 0.0075, "step": 1457 }, { "epoch": 8.15, "learning_rate": 1.8733103932667687e-05, "loss": 0.0102, "step": 1458 }, { "epoch": 8.15, "learning_rate": 1.8731391456719556e-05, "loss": 0.0046, "step": 1459 }, { "epoch": 8.16, "learning_rate": 1.8729677902549487e-05, "loss": 0.0057, "step": 1460 }, { "epoch": 8.16, "learning_rate": 1.8727963270369088e-05, "loss": 0.0044, "step": 1461 }, { "epoch": 8.17, "learning_rate": 1.87262475603901e-05, "loss": 0.0052, "step": 1462 }, { "epoch": 8.17, "learning_rate": 1.872453077282438e-05, "loss": 0.0155, "step": 1463 }, { "epoch": 8.18, "learning_rate": 1.8722812907883936e-05, "loss": 0.0034, "step": 1464 }, { "epoch": 8.18, "learning_rate": 1.872109396578091e-05, "loss": 0.0047, "step": 1465 }, { "epoch": 8.19, "learning_rate": 1.8719373946727558e-05, "loss": 0.0036, "step": 1466 }, { "epoch": 8.2, "learning_rate": 1.8717652850936293e-05, "loss": 0.0038, "step": 1467 }, { "epoch": 8.2, "learning_rate": 1.8715930678619646e-05, "loss": 0.0017, "step": 1468 }, { "epoch": 8.21, "learning_rate": 1.8714207429990282e-05, "loss": 0.0069, "step": 1469 }, { "epoch": 8.21, "learning_rate": 1.8712483105261006e-05, "loss": 0.005, "step": 1470 }, { "epoch": 8.22, "learning_rate": 1.8710757704644747e-05, "loss": 0.0038, "step": 1471 }, { "epoch": 8.22, "learning_rate": 1.870903122835457e-05, "loss": 0.0074, "step": 1472 }, { "epoch": 8.23, "learning_rate": 1.8707303676603685e-05, "loss": 0.0037, "step": 1473 }, { "epoch": 8.23, "learning_rate": 1.8705575049605415e-05, "loss": 0.0867, "step": 1474 }, { "epoch": 8.24, "learning_rate": 1.8703845347573223e-05, "loss": 0.0033, "step": 1475 }, { "epoch": 8.25, "learning_rate": 1.870211457072071e-05, "loss": 0.0014, "step": 1476 }, { "epoch": 8.25, "learning_rate": 1.8700382719261604e-05, "loss": 0.0021, "step": 1477 }, { "epoch": 8.26, "learning_rate": 1.869864979340977e-05, "loss": 0.0057, "step": 1478 }, { "epoch": 8.26, "learning_rate": 1.8696915793379202e-05, "loss": 0.0072, "step": 1479 }, { "epoch": 8.27, "learning_rate": 1.869518071938403e-05, "loss": 0.0046, "step": 1480 }, { "epoch": 8.27, "learning_rate": 1.8693444571638514e-05, "loss": 0.0027, "step": 1481 }, { "epoch": 8.28, "learning_rate": 1.8691707350357047e-05, "loss": 0.0023, "step": 1482 }, { "epoch": 8.28, "learning_rate": 1.8689969055754152e-05, "loss": 0.0042, "step": 1483 }, { "epoch": 8.29, "learning_rate": 1.8688229688044495e-05, "loss": 0.0127, "step": 1484 }, { "epoch": 8.3, "learning_rate": 1.8686489247442862e-05, "loss": 0.0031, "step": 1485 }, { "epoch": 8.3, "learning_rate": 1.8684747734164177e-05, "loss": 0.0141, "step": 1486 }, { "epoch": 8.31, "learning_rate": 1.8683005148423494e-05, "loss": 0.0028, "step": 1487 }, { "epoch": 8.31, "learning_rate": 1.8681261490436007e-05, "loss": 0.0036, "step": 1488 }, { "epoch": 8.32, "learning_rate": 1.8679516760417032e-05, "loss": 0.0037, "step": 1489 }, { "epoch": 8.32, "learning_rate": 1.8677770958582023e-05, "loss": 0.0057, "step": 1490 }, { "epoch": 8.33, "learning_rate": 1.8676024085146562e-05, "loss": 0.0026, "step": 1491 }, { "epoch": 8.34, "learning_rate": 1.8674276140326376e-05, "loss": 0.0016, "step": 1492 }, { "epoch": 8.34, "learning_rate": 1.867252712433731e-05, "loss": 0.019, "step": 1493 }, { "epoch": 8.35, "learning_rate": 1.8670777037395344e-05, "loss": 0.0032, "step": 1494 }, { "epoch": 8.35, "learning_rate": 1.8669025879716597e-05, "loss": 0.002, "step": 1495 }, { "epoch": 8.36, "learning_rate": 1.8667273651517315e-05, "loss": 0.0101, "step": 1496 }, { "epoch": 8.36, "learning_rate": 1.8665520353013873e-05, "loss": 0.0049, "step": 1497 }, { "epoch": 8.37, "learning_rate": 1.866376598442279e-05, "loss": 0.0026, "step": 1498 }, { "epoch": 8.37, "learning_rate": 1.8662010545960703e-05, "loss": 0.0013, "step": 1499 }, { "epoch": 8.38, "learning_rate": 1.866025403784439e-05, "loss": 0.0015, "step": 1500 }, { "epoch": 8.39, "learning_rate": 1.8658496460290755e-05, "loss": 0.0028, "step": 1501 }, { "epoch": 8.39, "learning_rate": 1.8656737813516845e-05, "loss": 0.0037, "step": 1502 }, { "epoch": 8.4, "learning_rate": 1.8654978097739826e-05, "loss": 0.0033, "step": 1503 }, { "epoch": 8.4, "learning_rate": 1.8653217313177004e-05, "loss": 0.0047, "step": 1504 }, { "epoch": 8.41, "learning_rate": 1.8651455460045812e-05, "loss": 0.0042, "step": 1505 }, { "epoch": 8.41, "learning_rate": 1.8649692538563823e-05, "loss": 0.0017, "step": 1506 }, { "epoch": 8.42, "learning_rate": 1.8647928548948732e-05, "loss": 0.0021, "step": 1507 }, { "epoch": 8.42, "learning_rate": 1.8646163491418375e-05, "loss": 0.0047, "step": 1508 }, { "epoch": 8.43, "learning_rate": 1.864439736619071e-05, "loss": 0.0029, "step": 1509 }, { "epoch": 8.44, "learning_rate": 1.8642630173483835e-05, "loss": 0.0024, "step": 1510 }, { "epoch": 8.44, "learning_rate": 1.8640861913515977e-05, "loss": 0.0036, "step": 1511 }, { "epoch": 8.45, "learning_rate": 1.863909258650549e-05, "loss": 0.003, "step": 1512 }, { "epoch": 8.45, "learning_rate": 1.8637322192670873e-05, "loss": 0.0075, "step": 1513 }, { "epoch": 8.46, "learning_rate": 1.8635550732230748e-05, "loss": 0.004, "step": 1514 }, { "epoch": 8.46, "learning_rate": 1.8633778205403864e-05, "loss": 0.0019, "step": 1515 }, { "epoch": 8.47, "learning_rate": 1.8632004612409105e-05, "loss": 0.0036, "step": 1516 }, { "epoch": 8.47, "learning_rate": 1.8630229953465496e-05, "loss": 0.0013, "step": 1517 }, { "epoch": 8.48, "learning_rate": 1.8628454228792178e-05, "loss": 0.0021, "step": 1518 }, { "epoch": 8.49, "learning_rate": 1.862667743860844e-05, "loss": 0.0013, "step": 1519 }, { "epoch": 8.49, "learning_rate": 1.8624899583133686e-05, "loss": 0.0029, "step": 1520 }, { "epoch": 8.5, "learning_rate": 1.8623120662587467e-05, "loss": 0.0051, "step": 1521 }, { "epoch": 8.5, "learning_rate": 1.862134067718945e-05, "loss": 0.0027, "step": 1522 }, { "epoch": 8.51, "learning_rate": 1.8619559627159452e-05, "loss": 0.0042, "step": 1523 }, { "epoch": 8.51, "learning_rate": 1.8617777512717402e-05, "loss": 0.0026, "step": 1524 }, { "epoch": 8.52, "learning_rate": 1.8615994334083377e-05, "loss": 0.0056, "step": 1525 }, { "epoch": 8.53, "learning_rate": 1.8614210091477572e-05, "loss": 0.0099, "step": 1526 }, { "epoch": 8.53, "learning_rate": 1.8612424785120328e-05, "loss": 0.0011, "step": 1527 }, { "epoch": 8.54, "learning_rate": 1.8610638415232097e-05, "loss": 0.0032, "step": 1528 }, { "epoch": 8.54, "learning_rate": 1.8608850982033482e-05, "loss": 0.0011, "step": 1529 }, { "epoch": 8.55, "learning_rate": 1.8607062485745212e-05, "loss": 0.0031, "step": 1530 }, { "epoch": 8.55, "learning_rate": 1.8605272926588135e-05, "loss": 0.002, "step": 1531 }, { "epoch": 8.56, "learning_rate": 1.860348230478325e-05, "loss": 0.0029, "step": 1532 }, { "epoch": 8.56, "learning_rate": 1.860169062055167e-05, "loss": 0.0025, "step": 1533 }, { "epoch": 8.57, "learning_rate": 1.859989787411465e-05, "loss": 0.0031, "step": 1534 }, { "epoch": 8.58, "learning_rate": 1.8598104065693577e-05, "loss": 0.0017, "step": 1535 }, { "epoch": 8.58, "learning_rate": 1.8596309195509958e-05, "loss": 0.0019, "step": 1536 }, { "epoch": 8.59, "learning_rate": 1.8594513263785435e-05, "loss": 0.002, "step": 1537 }, { "epoch": 8.59, "learning_rate": 1.8592716270741796e-05, "loss": 0.0012, "step": 1538 }, { "epoch": 8.6, "learning_rate": 1.859091821660094e-05, "loss": 0.0037, "step": 1539 }, { "epoch": 8.6, "learning_rate": 1.8589119101584902e-05, "loss": 0.0043, "step": 1540 }, { "epoch": 8.61, "learning_rate": 1.8587318925915855e-05, "loss": 0.0026, "step": 1541 }, { "epoch": 8.61, "learning_rate": 1.8585517689816104e-05, "loss": 0.004, "step": 1542 }, { "epoch": 8.62, "learning_rate": 1.8583715393508072e-05, "loss": 0.0021, "step": 1543 }, { "epoch": 8.63, "learning_rate": 1.8581912037214323e-05, "loss": 0.0027, "step": 1544 }, { "epoch": 8.63, "learning_rate": 1.8580107621157552e-05, "loss": 0.0034, "step": 1545 }, { "epoch": 8.64, "learning_rate": 1.8578302145560586e-05, "loss": 0.0016, "step": 1546 }, { "epoch": 8.64, "learning_rate": 1.857649561064637e-05, "loss": 0.019, "step": 1547 }, { "epoch": 8.65, "learning_rate": 1.8574688016637998e-05, "loss": 0.0037, "step": 1548 }, { "epoch": 8.65, "learning_rate": 1.857287936375868e-05, "loss": 0.0022, "step": 1549 }, { "epoch": 8.66, "learning_rate": 1.857106965223177e-05, "loss": 0.0024, "step": 1550 }, { "epoch": 8.66, "learning_rate": 1.856925888228074e-05, "loss": 0.0024, "step": 1551 }, { "epoch": 8.67, "learning_rate": 1.8567447054129196e-05, "loss": 0.0039, "step": 1552 }, { "epoch": 8.68, "learning_rate": 1.8565634168000884e-05, "loss": 0.0017, "step": 1553 }, { "epoch": 8.68, "learning_rate": 1.8563820224119668e-05, "loss": 0.0044, "step": 1554 }, { "epoch": 8.69, "learning_rate": 1.856200522270955e-05, "loss": 0.0017, "step": 1555 }, { "epoch": 8.69, "learning_rate": 1.8560189163994664e-05, "loss": 0.0028, "step": 1556 }, { "epoch": 8.7, "learning_rate": 1.855837204819927e-05, "loss": 0.0018, "step": 1557 }, { "epoch": 8.7, "learning_rate": 1.8556553875547755e-05, "loss": 0.0057, "step": 1558 }, { "epoch": 8.71, "learning_rate": 1.8554734646264648e-05, "loss": 0.0046, "step": 1559 }, { "epoch": 8.72, "learning_rate": 1.85529143605746e-05, "loss": 0.0045, "step": 1560 }, { "epoch": 8.72, "learning_rate": 1.855109301870239e-05, "loss": 0.003, "step": 1561 }, { "epoch": 8.73, "learning_rate": 1.8549270620872938e-05, "loss": 0.0013, "step": 1562 }, { "epoch": 8.73, "learning_rate": 1.8547447167311284e-05, "loss": 0.0028, "step": 1563 }, { "epoch": 8.74, "learning_rate": 1.854562265824261e-05, "loss": 0.0015, "step": 1564 }, { "epoch": 8.74, "learning_rate": 1.8543797093892212e-05, "loss": 0.0027, "step": 1565 }, { "epoch": 8.75, "learning_rate": 1.8541970474485523e-05, "loss": 0.0011, "step": 1566 }, { "epoch": 8.75, "learning_rate": 1.8540142800248123e-05, "loss": 0.0027, "step": 1567 }, { "epoch": 8.76, "learning_rate": 1.8538314071405694e-05, "loss": 0.0017, "step": 1568 }, { "epoch": 8.77, "learning_rate": 1.853648428818407e-05, "loss": 0.0043, "step": 1569 }, { "epoch": 8.77, "learning_rate": 1.85346534508092e-05, "loss": 0.0033, "step": 1570 }, { "epoch": 8.78, "learning_rate": 1.8532821559507177e-05, "loss": 0.0011, "step": 1571 }, { "epoch": 8.78, "learning_rate": 1.8530988614504216e-05, "loss": 0.0029, "step": 1572 }, { "epoch": 8.79, "learning_rate": 1.8529154616026662e-05, "loss": 0.0031, "step": 1573 }, { "epoch": 8.79, "learning_rate": 1.8527319564300993e-05, "loss": 0.0026, "step": 1574 }, { "epoch": 8.8, "learning_rate": 1.8525483459553813e-05, "loss": 0.002, "step": 1575 }, { "epoch": 8.8, "learning_rate": 1.8523646302011863e-05, "loss": 0.0034, "step": 1576 }, { "epoch": 8.81, "learning_rate": 1.8521808091902012e-05, "loss": 0.0021, "step": 1577 }, { "epoch": 8.82, "learning_rate": 1.851996882945125e-05, "loss": 0.0033, "step": 1578 }, { "epoch": 8.82, "learning_rate": 1.8518128514886705e-05, "loss": 0.0035, "step": 1579 }, { "epoch": 8.83, "learning_rate": 1.8516287148435638e-05, "loss": 0.003, "step": 1580 }, { "epoch": 8.83, "learning_rate": 1.8514444730325435e-05, "loss": 0.0039, "step": 1581 }, { "epoch": 8.84, "learning_rate": 1.851260126078361e-05, "loss": 0.0019, "step": 1582 }, { "epoch": 8.84, "learning_rate": 1.8510756740037807e-05, "loss": 0.0082, "step": 1583 }, { "epoch": 8.85, "learning_rate": 1.850891116831581e-05, "loss": 0.0051, "step": 1584 }, { "epoch": 8.85, "learning_rate": 1.8507064545845513e-05, "loss": 0.0018, "step": 1585 }, { "epoch": 8.86, "learning_rate": 1.8505216872854964e-05, "loss": 0.0037, "step": 1586 }, { "epoch": 8.87, "learning_rate": 1.8503368149572326e-05, "loss": 0.0035, "step": 1587 }, { "epoch": 8.87, "learning_rate": 1.8501518376225887e-05, "loss": 0.0021, "step": 1588 }, { "epoch": 8.88, "learning_rate": 1.849966755304408e-05, "loss": 0.0009, "step": 1589 }, { "epoch": 8.88, "learning_rate": 1.8497815680255452e-05, "loss": 0.0026, "step": 1590 }, { "epoch": 8.89, "learning_rate": 1.849596275808869e-05, "loss": 0.0036, "step": 1591 }, { "epoch": 8.89, "learning_rate": 1.8494108786772613e-05, "loss": 0.0156, "step": 1592 }, { "epoch": 8.9, "learning_rate": 1.849225376653615e-05, "loss": 0.0027, "step": 1593 }, { "epoch": 8.91, "learning_rate": 1.8490397697608394e-05, "loss": 0.0013, "step": 1594 }, { "epoch": 8.91, "learning_rate": 1.848854058021853e-05, "loss": 0.0015, "step": 1595 }, { "epoch": 8.92, "learning_rate": 1.8486682414595903e-05, "loss": 0.0013, "step": 1596 }, { "epoch": 8.92, "learning_rate": 1.848482320096996e-05, "loss": 0.0019, "step": 1597 }, { "epoch": 8.93, "learning_rate": 1.8482962939570302e-05, "loss": 0.006, "step": 1598 }, { "epoch": 8.93, "learning_rate": 1.8481101630626645e-05, "loss": 0.0026, "step": 1599 }, { "epoch": 8.94, "learning_rate": 1.847923927436884e-05, "loss": 0.0042, "step": 1600 }, { "epoch": 8.94, "learning_rate": 1.8477375871026865e-05, "loss": 0.001, "step": 1601 }, { "epoch": 8.95, "learning_rate": 1.8475511420830827e-05, "loss": 0.0056, "step": 1602 }, { "epoch": 8.96, "learning_rate": 1.847364592401096e-05, "loss": 0.0025, "step": 1603 }, { "epoch": 8.96, "learning_rate": 1.8471779380797638e-05, "loss": 0.0011, "step": 1604 }, { "epoch": 8.97, "learning_rate": 1.8469911791421352e-05, "loss": 0.0014, "step": 1605 }, { "epoch": 8.97, "learning_rate": 1.846804315611273e-05, "loss": 0.003, "step": 1606 }, { "epoch": 8.98, "learning_rate": 1.846617347510252e-05, "loss": 0.004, "step": 1607 }, { "epoch": 8.98, "learning_rate": 1.846430274862161e-05, "loss": 0.0043, "step": 1608 }, { "epoch": 8.99, "learning_rate": 1.8462430976901015e-05, "loss": 0.0013, "step": 1609 }, { "epoch": 8.99, "learning_rate": 1.8460558160171866e-05, "loss": 0.002, "step": 1610 }, { "epoch": 9.0, "learning_rate": 1.8458684298665443e-05, "loss": 0.0012, "step": 1611 }, { "epoch": 9.01, "learning_rate": 1.8456809392613145e-05, "loss": 0.0012, "step": 1612 }, { "epoch": 9.01, "learning_rate": 1.8454933442246492e-05, "loss": 0.0027, "step": 1613 }, { "epoch": 9.02, "learning_rate": 1.8453056447797148e-05, "loss": 0.0027, "step": 1614 }, { "epoch": 9.02, "learning_rate": 1.8451178409496903e-05, "loss": 0.0026, "step": 1615 }, { "epoch": 9.03, "learning_rate": 1.844929932757766e-05, "loss": 0.0018, "step": 1616 }, { "epoch": 9.03, "learning_rate": 1.8447419202271476e-05, "loss": 0.0032, "step": 1617 }, { "epoch": 9.04, "learning_rate": 1.8445538033810515e-05, "loss": 0.0026, "step": 1618 }, { "epoch": 9.04, "learning_rate": 1.8443655822427085e-05, "loss": 0.006, "step": 1619 }, { "epoch": 9.05, "learning_rate": 1.844177256835361e-05, "loss": 0.0016, "step": 1620 }, { "epoch": 9.06, "learning_rate": 1.8439888271822654e-05, "loss": 0.0014, "step": 1621 }, { "epoch": 9.06, "learning_rate": 1.8438002933066904e-05, "loss": 0.0009, "step": 1622 }, { "epoch": 9.07, "learning_rate": 1.8436116552319175e-05, "loss": 0.0025, "step": 1623 }, { "epoch": 9.07, "learning_rate": 1.8434229129812417e-05, "loss": 0.0022, "step": 1624 }, { "epoch": 9.08, "learning_rate": 1.8432340665779697e-05, "loss": 0.0077, "step": 1625 }, { "epoch": 9.08, "learning_rate": 1.8430451160454222e-05, "loss": 0.0021, "step": 1626 }, { "epoch": 9.09, "learning_rate": 1.8428560614069324e-05, "loss": 0.0014, "step": 1627 }, { "epoch": 9.09, "learning_rate": 1.8426669026858462e-05, "loss": 0.0019, "step": 1628 }, { "epoch": 9.1, "learning_rate": 1.842477639905522e-05, "loss": 0.003, "step": 1629 }, { "epoch": 9.11, "learning_rate": 1.8422882730893323e-05, "loss": 0.0028, "step": 1630 }, { "epoch": 9.11, "learning_rate": 1.8420988022606607e-05, "loss": 0.0021, "step": 1631 }, { "epoch": 9.12, "learning_rate": 1.8419092274429052e-05, "loss": 0.0025, "step": 1632 }, { "epoch": 9.12, "learning_rate": 1.841719548659476e-05, "loss": 0.0025, "step": 1633 }, { "epoch": 9.13, "learning_rate": 1.841529765933796e-05, "loss": 0.004, "step": 1634 }, { "epoch": 9.13, "learning_rate": 1.841339879289301e-05, "loss": 0.0014, "step": 1635 }, { "epoch": 9.14, "learning_rate": 1.8411498887494396e-05, "loss": 0.0027, "step": 1636 }, { "epoch": 9.15, "learning_rate": 1.8409597943376737e-05, "loss": 0.0013, "step": 1637 }, { "epoch": 9.15, "learning_rate": 1.8407695960774777e-05, "loss": 0.0028, "step": 1638 }, { "epoch": 9.16, "learning_rate": 1.8405792939923385e-05, "loss": 0.0008, "step": 1639 }, { "epoch": 9.16, "learning_rate": 1.8403888881057562e-05, "loss": 0.0015, "step": 1640 }, { "epoch": 9.17, "learning_rate": 1.8401983784412436e-05, "loss": 0.002, "step": 1641 }, { "epoch": 9.17, "learning_rate": 1.8400077650223264e-05, "loss": 0.0025, "step": 1642 }, { "epoch": 9.18, "learning_rate": 1.8398170478725435e-05, "loss": 0.003, "step": 1643 }, { "epoch": 9.18, "learning_rate": 1.839626227015445e-05, "loss": 0.0013, "step": 1644 }, { "epoch": 9.19, "learning_rate": 1.8394353024745965e-05, "loss": 0.0038, "step": 1645 }, { "epoch": 9.2, "learning_rate": 1.8392442742735743e-05, "loss": 0.002, "step": 1646 }, { "epoch": 9.2, "learning_rate": 1.8390531424359676e-05, "loss": 0.0032, "step": 1647 }, { "epoch": 9.21, "learning_rate": 1.838861906985379e-05, "loss": 0.001, "step": 1648 }, { "epoch": 9.21, "learning_rate": 1.8386705679454243e-05, "loss": 0.0022, "step": 1649 }, { "epoch": 9.22, "learning_rate": 1.8384791253397312e-05, "loss": 0.002, "step": 1650 }, { "epoch": 9.22, "learning_rate": 1.8382875791919405e-05, "loss": 0.0015, "step": 1651 }, { "epoch": 9.23, "learning_rate": 1.838095929525706e-05, "loss": 0.0011, "step": 1652 }, { "epoch": 9.23, "learning_rate": 1.8379041763646945e-05, "loss": 0.0025, "step": 1653 }, { "epoch": 9.24, "learning_rate": 1.8377123197325843e-05, "loss": 0.0015, "step": 1654 }, { "epoch": 9.25, "learning_rate": 1.8375203596530683e-05, "loss": 0.0028, "step": 1655 }, { "epoch": 9.25, "learning_rate": 1.837328296149851e-05, "loss": 0.0015, "step": 1656 }, { "epoch": 9.26, "learning_rate": 1.8371361292466496e-05, "loss": 0.0014, "step": 1657 }, { "epoch": 9.26, "learning_rate": 1.8369438589671945e-05, "loss": 0.0033, "step": 1658 }, { "epoch": 9.27, "learning_rate": 1.8367514853352292e-05, "loss": 0.0016, "step": 1659 }, { "epoch": 9.27, "learning_rate": 1.8365590083745085e-05, "loss": 0.0015, "step": 1660 }, { "epoch": 9.28, "learning_rate": 1.8363664281088026e-05, "loss": 0.0012, "step": 1661 }, { "epoch": 9.28, "learning_rate": 1.8361737445618916e-05, "loss": 0.0035, "step": 1662 }, { "epoch": 9.29, "learning_rate": 1.83598095775757e-05, "loss": 0.0008, "step": 1663 }, { "epoch": 9.3, "learning_rate": 1.8357880677196446e-05, "loss": 0.0015, "step": 1664 }, { "epoch": 9.3, "learning_rate": 1.8355950744719348e-05, "loss": 0.0047, "step": 1665 }, { "epoch": 9.31, "learning_rate": 1.8354019780382736e-05, "loss": 0.0012, "step": 1666 }, { "epoch": 9.31, "learning_rate": 1.8352087784425054e-05, "loss": 0.0049, "step": 1667 }, { "epoch": 9.32, "learning_rate": 1.8350154757084882e-05, "loss": 0.0015, "step": 1668 }, { "epoch": 9.32, "learning_rate": 1.834822069860093e-05, "loss": 0.002, "step": 1669 }, { "epoch": 9.33, "learning_rate": 1.8346285609212025e-05, "loss": 0.001, "step": 1670 }, { "epoch": 9.34, "learning_rate": 1.834434948915713e-05, "loss": 0.0014, "step": 1671 }, { "epoch": 9.34, "learning_rate": 1.834241233867533e-05, "loss": 0.0022, "step": 1672 }, { "epoch": 9.35, "learning_rate": 1.834047415800585e-05, "loss": 0.002, "step": 1673 }, { "epoch": 9.35, "learning_rate": 1.8338534947388015e-05, "loss": 0.0027, "step": 1674 }, { "epoch": 9.36, "learning_rate": 1.833659470706131e-05, "loss": 0.0018, "step": 1675 }, { "epoch": 9.36, "learning_rate": 1.8334653437265323e-05, "loss": 0.0035, "step": 1676 }, { "epoch": 9.37, "learning_rate": 1.8332711138239773e-05, "loss": 0.0056, "step": 1677 }, { "epoch": 9.37, "learning_rate": 1.8330767810224525e-05, "loss": 0.0157, "step": 1678 }, { "epoch": 9.38, "learning_rate": 1.8328823453459545e-05, "loss": 0.0008, "step": 1679 }, { "epoch": 9.39, "learning_rate": 1.8326878068184945e-05, "loss": 0.001, "step": 1680 }, { "epoch": 9.39, "learning_rate": 1.8324931654640946e-05, "loss": 0.0021, "step": 1681 }, { "epoch": 9.4, "learning_rate": 1.832298421306792e-05, "loss": 0.0022, "step": 1682 }, { "epoch": 9.4, "learning_rate": 1.8321035743706344e-05, "loss": 0.0137, "step": 1683 }, { "epoch": 9.41, "learning_rate": 1.8319086246796833e-05, "loss": 0.0021, "step": 1684 }, { "epoch": 9.41, "learning_rate": 1.8317135722580125e-05, "loss": 0.0008, "step": 1685 }, { "epoch": 9.42, "learning_rate": 1.831518417129709e-05, "loss": 0.001, "step": 1686 }, { "epoch": 9.42, "learning_rate": 1.8313231593188714e-05, "loss": 0.0026, "step": 1687 }, { "epoch": 9.43, "learning_rate": 1.831127798849613e-05, "loss": 0.0009, "step": 1688 }, { "epoch": 9.44, "learning_rate": 1.8309323357460566e-05, "loss": 0.0029, "step": 1689 }, { "epoch": 9.44, "learning_rate": 1.8307367700323412e-05, "loss": 0.0018, "step": 1690 }, { "epoch": 9.45, "learning_rate": 1.830541101732616e-05, "loss": 0.0018, "step": 1691 }, { "epoch": 9.45, "learning_rate": 1.830345330871044e-05, "loss": 0.0022, "step": 1692 }, { "epoch": 9.46, "learning_rate": 1.8301494574718005e-05, "loss": 0.002, "step": 1693 }, { "epoch": 9.46, "learning_rate": 1.8299534815590735e-05, "loss": 0.0016, "step": 1694 }, { "epoch": 9.47, "learning_rate": 1.8297574031570634e-05, "loss": 0.0015, "step": 1695 }, { "epoch": 9.47, "learning_rate": 1.8295612222899838e-05, "loss": 0.0018, "step": 1696 }, { "epoch": 9.48, "learning_rate": 1.8293649389820606e-05, "loss": 0.0027, "step": 1697 }, { "epoch": 9.49, "learning_rate": 1.8291685532575325e-05, "loss": 0.0009, "step": 1698 }, { "epoch": 9.49, "learning_rate": 1.8289720651406507e-05, "loss": 0.001, "step": 1699 }, { "epoch": 9.5, "learning_rate": 1.828775474655679e-05, "loss": 0.0013, "step": 1700 }, { "epoch": 9.5, "learning_rate": 1.8285787818268943e-05, "loss": 0.0033, "step": 1701 }, { "epoch": 9.51, "learning_rate": 1.8283819866785855e-05, "loss": 0.0014, "step": 1702 }, { "epoch": 9.51, "learning_rate": 1.8281850892350547e-05, "loss": 0.0011, "step": 1703 }, { "epoch": 9.52, "learning_rate": 1.827988089520616e-05, "loss": 0.0007, "step": 1704 }, { "epoch": 9.53, "learning_rate": 1.8277909875595967e-05, "loss": 0.0027, "step": 1705 }, { "epoch": 9.53, "learning_rate": 1.8275937833763367e-05, "loss": 0.0013, "step": 1706 }, { "epoch": 9.54, "learning_rate": 1.827396476995188e-05, "loss": 0.001, "step": 1707 }, { "epoch": 9.54, "learning_rate": 1.827199068440516e-05, "loss": 0.0007, "step": 1708 }, { "epoch": 9.55, "learning_rate": 1.827001557736698e-05, "loss": 0.0013, "step": 1709 }, { "epoch": 9.55, "learning_rate": 1.826803944908124e-05, "loss": 0.0017, "step": 1710 }, { "epoch": 9.56, "learning_rate": 1.8266062299791974e-05, "loss": 0.0008, "step": 1711 }, { "epoch": 9.56, "learning_rate": 1.826408412974333e-05, "loss": 0.0084, "step": 1712 }, { "epoch": 9.57, "learning_rate": 1.826210493917959e-05, "loss": 0.0011, "step": 1713 }, { "epoch": 9.58, "learning_rate": 1.8260124728345163e-05, "loss": 0.0025, "step": 1714 }, { "epoch": 9.58, "learning_rate": 1.825814349748458e-05, "loss": 0.0016, "step": 1715 }, { "epoch": 9.59, "learning_rate": 1.8256161246842497e-05, "loss": 0.0013, "step": 1716 }, { "epoch": 9.59, "learning_rate": 1.82541779766637e-05, "loss": 0.0008, "step": 1717 }, { "epoch": 9.6, "learning_rate": 1.82521936871931e-05, "loss": 0.001, "step": 1718 }, { "epoch": 9.6, "learning_rate": 1.825020837867573e-05, "loss": 0.0018, "step": 1719 }, { "epoch": 9.61, "learning_rate": 1.8248222051356756e-05, "loss": 0.0022, "step": 1720 }, { "epoch": 9.61, "learning_rate": 1.8246234705481458e-05, "loss": 0.0013, "step": 1721 }, { "epoch": 9.62, "learning_rate": 1.8244246341295256e-05, "loss": 0.0012, "step": 1722 }, { "epoch": 9.63, "learning_rate": 1.824225695904369e-05, "loss": 0.0009, "step": 1723 }, { "epoch": 9.63, "learning_rate": 1.824026655897242e-05, "loss": 0.0007, "step": 1724 }, { "epoch": 9.64, "learning_rate": 1.8238275141327237e-05, "loss": 0.011, "step": 1725 }, { "epoch": 9.64, "learning_rate": 1.8236282706354064e-05, "loss": 0.0091, "step": 1726 }, { "epoch": 9.65, "learning_rate": 1.8234289254298934e-05, "loss": 0.0008, "step": 1727 }, { "epoch": 9.65, "learning_rate": 1.823229478540802e-05, "loss": 0.0025, "step": 1728 }, { "epoch": 9.66, "learning_rate": 1.823029929992761e-05, "loss": 0.0022, "step": 1729 }, { "epoch": 9.66, "learning_rate": 1.8228302798104128e-05, "loss": 0.001, "step": 1730 }, { "epoch": 9.67, "learning_rate": 1.8226305280184112e-05, "loss": 0.0017, "step": 1731 }, { "epoch": 9.68, "learning_rate": 1.822430674641424e-05, "loss": 0.001, "step": 1732 }, { "epoch": 9.68, "learning_rate": 1.82223071970413e-05, "loss": 0.0029, "step": 1733 }, { "epoch": 9.69, "learning_rate": 1.822030663231221e-05, "loss": 0.0017, "step": 1734 }, { "epoch": 9.69, "learning_rate": 1.8218305052474025e-05, "loss": 0.0023, "step": 1735 }, { "epoch": 9.7, "learning_rate": 1.821630245777391e-05, "loss": 0.0779, "step": 1736 }, { "epoch": 9.7, "learning_rate": 1.8214298848459158e-05, "loss": 0.001, "step": 1737 }, { "epoch": 9.71, "learning_rate": 1.82122942247772e-05, "loss": 0.0079, "step": 1738 }, { "epoch": 9.72, "learning_rate": 1.8210288586975572e-05, "loss": 0.0012, "step": 1739 }, { "epoch": 9.72, "learning_rate": 1.8208281935301957e-05, "loss": 0.0024, "step": 1740 }, { "epoch": 9.73, "learning_rate": 1.8206274270004147e-05, "loss": 0.0022, "step": 1741 }, { "epoch": 9.73, "learning_rate": 1.8204265591330067e-05, "loss": 0.003, "step": 1742 }, { "epoch": 9.74, "learning_rate": 1.820225589952776e-05, "loss": 0.0012, "step": 1743 }, { "epoch": 9.74, "learning_rate": 1.82002451948454e-05, "loss": 0.0046, "step": 1744 }, { "epoch": 9.75, "learning_rate": 1.8198233477531285e-05, "loss": 0.002, "step": 1745 }, { "epoch": 9.75, "learning_rate": 1.8196220747833844e-05, "loss": 0.0015, "step": 1746 }, { "epoch": 9.76, "learning_rate": 1.8194207006001617e-05, "loss": 0.0069, "step": 1747 }, { "epoch": 9.77, "learning_rate": 1.819219225228328e-05, "loss": 0.0009, "step": 1748 }, { "epoch": 9.77, "learning_rate": 1.8190176486927632e-05, "loss": 0.001, "step": 1749 }, { "epoch": 9.78, "learning_rate": 1.8188159710183595e-05, "loss": 0.0014, "step": 1750 }, { "epoch": 9.78, "learning_rate": 1.8186141922300214e-05, "loss": 0.001, "step": 1751 }, { "epoch": 9.79, "learning_rate": 1.8184123123526664e-05, "loss": 0.0018, "step": 1752 }, { "epoch": 9.79, "learning_rate": 1.8182103314112246e-05, "loss": 0.0023, "step": 1753 }, { "epoch": 9.8, "learning_rate": 1.8180082494306378e-05, "loss": 0.0009, "step": 1754 }, { "epoch": 9.8, "learning_rate": 1.8178060664358605e-05, "loss": 0.001, "step": 1755 }, { "epoch": 9.81, "learning_rate": 1.8176037824518603e-05, "loss": 0.0014, "step": 1756 }, { "epoch": 9.82, "learning_rate": 1.8174013975036168e-05, "loss": 0.0009, "step": 1757 }, { "epoch": 9.82, "learning_rate": 1.8171989116161216e-05, "loss": 0.0024, "step": 1758 }, { "epoch": 9.83, "learning_rate": 1.8169963248143797e-05, "loss": 0.0009, "step": 1759 }, { "epoch": 9.83, "learning_rate": 1.8167936371234084e-05, "loss": 0.0017, "step": 1760 }, { "epoch": 9.84, "learning_rate": 1.8165908485682367e-05, "loss": 0.0023, "step": 1761 }, { "epoch": 9.84, "learning_rate": 1.8163879591739067e-05, "loss": 0.0022, "step": 1762 }, { "epoch": 9.85, "learning_rate": 1.8161849689654727e-05, "loss": 0.0032, "step": 1763 }, { "epoch": 9.85, "learning_rate": 1.815981877968002e-05, "loss": 0.0008, "step": 1764 }, { "epoch": 9.86, "learning_rate": 1.8157786862065735e-05, "loss": 0.0011, "step": 1765 }, { "epoch": 9.87, "learning_rate": 1.8155753937062786e-05, "loss": 0.0019, "step": 1766 }, { "epoch": 9.87, "learning_rate": 1.8153720004922224e-05, "loss": 0.0014, "step": 1767 }, { "epoch": 9.88, "learning_rate": 1.815168506589521e-05, "loss": 0.0015, "step": 1768 }, { "epoch": 9.88, "learning_rate": 1.8149649120233034e-05, "loss": 0.0012, "step": 1769 }, { "epoch": 9.89, "learning_rate": 1.814761216818711e-05, "loss": 0.0012, "step": 1770 }, { "epoch": 9.89, "learning_rate": 1.8145574210008982e-05, "loss": 0.0009, "step": 1771 }, { "epoch": 9.9, "learning_rate": 1.8143535245950306e-05, "loss": 0.0017, "step": 1772 }, { "epoch": 9.91, "learning_rate": 1.8141495276262874e-05, "loss": 0.0011, "step": 1773 }, { "epoch": 9.91, "learning_rate": 1.81394543011986e-05, "loss": 0.0026, "step": 1774 }, { "epoch": 9.92, "learning_rate": 1.8137412321009515e-05, "loss": 0.0032, "step": 1775 }, { "epoch": 9.92, "learning_rate": 1.8135369335947783e-05, "loss": 0.0011, "step": 1776 }, { "epoch": 9.93, "learning_rate": 1.8133325346265683e-05, "loss": 0.0009, "step": 1777 }, { "epoch": 9.93, "learning_rate": 1.813128035221563e-05, "loss": 0.0023, "step": 1778 }, { "epoch": 9.94, "learning_rate": 1.8129234354050155e-05, "loss": 0.005, "step": 1779 }, { "epoch": 9.94, "learning_rate": 1.8127187352021908e-05, "loss": 0.0016, "step": 1780 }, { "epoch": 9.95, "learning_rate": 1.8125139346383672e-05, "loss": 0.002, "step": 1781 }, { "epoch": 9.96, "learning_rate": 1.8123090337388353e-05, "loss": 0.0011, "step": 1782 }, { "epoch": 9.96, "learning_rate": 1.8121040325288977e-05, "loss": 0.0009, "step": 1783 }, { "epoch": 9.97, "learning_rate": 1.81189893103387e-05, "loss": 0.0018, "step": 1784 }, { "epoch": 9.97, "learning_rate": 1.8116937292790796e-05, "loss": 0.0012, "step": 1785 }, { "epoch": 9.98, "learning_rate": 1.8114884272898662e-05, "loss": 0.0023, "step": 1786 }, { "epoch": 9.98, "learning_rate": 1.8112830250915817e-05, "loss": 0.0015, "step": 1787 }, { "epoch": 9.99, "learning_rate": 1.8110775227095918e-05, "loss": 0.002, "step": 1788 }, { "epoch": 9.99, "learning_rate": 1.810871920169273e-05, "loss": 0.0025, "step": 1789 }, { "epoch": 10.0, "learning_rate": 1.810666217496015e-05, "loss": 0.0005, "step": 1790 }, { "epoch": 10.01, "learning_rate": 1.8104604147152195e-05, "loss": 0.0019, "step": 1791 }, { "epoch": 10.01, "learning_rate": 1.8102545118523008e-05, "loss": 0.0009, "step": 1792 }, { "epoch": 10.02, "learning_rate": 1.810048508932685e-05, "loss": 0.0007, "step": 1793 }, { "epoch": 10.02, "learning_rate": 1.8098424059818116e-05, "loss": 0.0012, "step": 1794 }, { "epoch": 10.03, "learning_rate": 1.8096362030251312e-05, "loss": 0.0009, "step": 1795 }, { "epoch": 10.03, "learning_rate": 1.8094299000881078e-05, "loss": 0.0013, "step": 1796 }, { "epoch": 10.04, "learning_rate": 1.809223497196217e-05, "loss": 0.0007, "step": 1797 }, { "epoch": 10.04, "learning_rate": 1.8090169943749477e-05, "loss": 0.001, "step": 1798 }, { "epoch": 10.05, "learning_rate": 1.8088103916497996e-05, "loss": 0.0007, "step": 1799 }, { "epoch": 10.06, "learning_rate": 1.8086036890462865e-05, "loss": 0.0008, "step": 1800 }, { "epoch": 10.06, "learning_rate": 1.8083968865899336e-05, "loss": 0.0018, "step": 1801 }, { "epoch": 10.07, "learning_rate": 1.808189984306278e-05, "loss": 0.0011, "step": 1802 }, { "epoch": 10.07, "learning_rate": 1.8079829822208697e-05, "loss": 0.0007, "step": 1803 }, { "epoch": 10.08, "learning_rate": 1.8077758803592717e-05, "loss": 0.0013, "step": 1804 }, { "epoch": 10.08, "learning_rate": 1.8075686787470575e-05, "loss": 0.0019, "step": 1805 }, { "epoch": 10.09, "learning_rate": 1.8073613774098154e-05, "loss": 0.0018, "step": 1806 }, { "epoch": 10.09, "learning_rate": 1.8071539763731432e-05, "loss": 0.0018, "step": 1807 }, { "epoch": 10.1, "learning_rate": 1.8069464756626534e-05, "loss": 0.0025, "step": 1808 }, { "epoch": 10.11, "learning_rate": 1.8067388753039693e-05, "loss": 0.0018, "step": 1809 }, { "epoch": 10.11, "learning_rate": 1.8065311753227272e-05, "loss": 0.0012, "step": 1810 }, { "epoch": 10.12, "learning_rate": 1.8063233757445756e-05, "loss": 0.0015, "step": 1811 }, { "epoch": 10.12, "learning_rate": 1.8061154765951755e-05, "loss": 0.0022, "step": 1812 }, { "epoch": 10.13, "learning_rate": 1.8059074779001995e-05, "loss": 0.0041, "step": 1813 }, { "epoch": 10.13, "learning_rate": 1.805699379685333e-05, "loss": 0.0004, "step": 1814 }, { "epoch": 10.14, "learning_rate": 1.805491181976274e-05, "loss": 0.0031, "step": 1815 }, { "epoch": 10.15, "learning_rate": 1.8052828847987324e-05, "loss": 0.0026, "step": 1816 }, { "epoch": 10.15, "learning_rate": 1.8050744881784297e-05, "loss": 0.0018, "step": 1817 }, { "epoch": 10.16, "learning_rate": 1.8048659921411012e-05, "loss": 0.0015, "step": 1818 }, { "epoch": 10.16, "learning_rate": 1.8046573967124933e-05, "loss": 0.0007, "step": 1819 }, { "epoch": 10.17, "learning_rate": 1.8044487019183647e-05, "loss": 0.0006, "step": 1820 }, { "epoch": 10.17, "learning_rate": 1.8042399077844875e-05, "loss": 0.0017, "step": 1821 }, { "epoch": 10.18, "learning_rate": 1.8040310143366447e-05, "loss": 0.0019, "step": 1822 }, { "epoch": 10.18, "learning_rate": 1.8038220216006318e-05, "loss": 0.0014, "step": 1823 }, { "epoch": 10.19, "learning_rate": 1.803612929602258e-05, "loss": 0.0014, "step": 1824 }, { "epoch": 10.2, "learning_rate": 1.8034037383673428e-05, "loss": 0.0048, "step": 1825 }, { "epoch": 10.2, "learning_rate": 1.803194447921719e-05, "loss": 0.0005, "step": 1826 }, { "epoch": 10.21, "learning_rate": 1.802985058291231e-05, "loss": 0.0015, "step": 1827 }, { "epoch": 10.21, "learning_rate": 1.8027755695017368e-05, "loss": 0.0018, "step": 1828 }, { "epoch": 10.22, "learning_rate": 1.8025659815791052e-05, "loss": 0.0019, "step": 1829 }, { "epoch": 10.22, "learning_rate": 1.802356294549218e-05, "loss": 0.0019, "step": 1830 }, { "epoch": 10.23, "learning_rate": 1.802146508437969e-05, "loss": 0.001, "step": 1831 }, { "epoch": 10.23, "learning_rate": 1.8019366232712635e-05, "loss": 0.0016, "step": 1832 }, { "epoch": 10.24, "learning_rate": 1.8017266390750215e-05, "loss": 0.001, "step": 1833 }, { "epoch": 10.25, "learning_rate": 1.801516555875172e-05, "loss": 0.0007, "step": 1834 }, { "epoch": 10.25, "learning_rate": 1.8013063736976578e-05, "loss": 0.001, "step": 1835 }, { "epoch": 10.26, "learning_rate": 1.801096092568435e-05, "loss": 0.003, "step": 1836 }, { "epoch": 10.26, "learning_rate": 1.8008857125134697e-05, "loss": 0.0021, "step": 1837 }, { "epoch": 10.27, "learning_rate": 1.800675233558742e-05, "loss": 0.0014, "step": 1838 }, { "epoch": 10.27, "learning_rate": 1.8004646557302434e-05, "loss": 0.0158, "step": 1839 }, { "epoch": 10.28, "learning_rate": 1.8002539790539772e-05, "loss": 0.001, "step": 1840 }, { "epoch": 10.28, "learning_rate": 1.8000432035559597e-05, "loss": 0.001, "step": 1841 }, { "epoch": 10.29, "learning_rate": 1.79983232926222e-05, "loss": 0.0019, "step": 1842 }, { "epoch": 10.3, "learning_rate": 1.799621356198797e-05, "loss": 0.0013, "step": 1843 }, { "epoch": 10.3, "learning_rate": 1.7994102843917445e-05, "loss": 0.001, "step": 1844 }, { "epoch": 10.31, "learning_rate": 1.7991991138671272e-05, "loss": 0.0006, "step": 1845 }, { "epoch": 10.31, "learning_rate": 1.7989878446510215e-05, "loss": 0.0014, "step": 1846 }, { "epoch": 10.32, "learning_rate": 1.798776476769517e-05, "loss": 0.0006, "step": 1847 }, { "epoch": 10.32, "learning_rate": 1.7985650102487154e-05, "loss": 0.0012, "step": 1848 }, { "epoch": 10.33, "learning_rate": 1.79835344511473e-05, "loss": 0.0012, "step": 1849 }, { "epoch": 10.34, "learning_rate": 1.7981417813936866e-05, "loss": 0.0011, "step": 1850 }, { "epoch": 10.34, "learning_rate": 1.7979300191117225e-05, "loss": 0.0013, "step": 1851 }, { "epoch": 10.35, "learning_rate": 1.797718158294989e-05, "loss": 0.0061, "step": 1852 }, { "epoch": 10.35, "learning_rate": 1.7975061989696474e-05, "loss": 0.0014, "step": 1853 }, { "epoch": 10.36, "learning_rate": 1.7972941411618724e-05, "loss": 0.001, "step": 1854 }, { "epoch": 10.36, "learning_rate": 1.7970819848978503e-05, "loss": 0.0019, "step": 1855 }, { "epoch": 10.37, "learning_rate": 1.796869730203781e-05, "loss": 0.0139, "step": 1856 }, { "epoch": 10.37, "learning_rate": 1.7966573771058738e-05, "loss": 0.0029, "step": 1857 }, { "epoch": 10.38, "learning_rate": 1.796444925630353e-05, "loss": 0.0013, "step": 1858 }, { "epoch": 10.39, "learning_rate": 1.7962323758034537e-05, "loss": 0.0009, "step": 1859 }, { "epoch": 10.39, "learning_rate": 1.796019727651422e-05, "loss": 0.0017, "step": 1860 }, { "epoch": 10.4, "learning_rate": 1.795806981200519e-05, "loss": 0.0006, "step": 1861 }, { "epoch": 10.4, "learning_rate": 1.7955941364770155e-05, "loss": 0.0009, "step": 1862 }, { "epoch": 10.41, "learning_rate": 1.7953811935071953e-05, "loss": 0.0014, "step": 1863 }, { "epoch": 10.41, "learning_rate": 1.7951681523173543e-05, "loss": 0.0009, "step": 1864 }, { "epoch": 10.42, "learning_rate": 1.7949550129338006e-05, "loss": 0.0006, "step": 1865 }, { "epoch": 10.42, "learning_rate": 1.7947417753828545e-05, "loss": 0.0012, "step": 1866 }, { "epoch": 10.43, "learning_rate": 1.794528439690848e-05, "loss": 0.002, "step": 1867 }, { "epoch": 10.44, "learning_rate": 1.7943150058841262e-05, "loss": 0.0009, "step": 1868 }, { "epoch": 10.44, "learning_rate": 1.7941014739890447e-05, "loss": 0.002, "step": 1869 }, { "epoch": 10.45, "learning_rate": 1.7938878440319722e-05, "loss": 0.0009, "step": 1870 }, { "epoch": 10.45, "learning_rate": 1.7936741160392898e-05, "loss": 0.0011, "step": 1871 }, { "epoch": 10.46, "learning_rate": 1.7934602900373903e-05, "loss": 0.0026, "step": 1872 }, { "epoch": 10.46, "learning_rate": 1.793246366052679e-05, "loss": 0.0012, "step": 1873 }, { "epoch": 10.47, "learning_rate": 1.793032344111572e-05, "loss": 0.0017, "step": 1874 }, { "epoch": 10.47, "learning_rate": 1.792818224240499e-05, "loss": 0.0008, "step": 1875 }, { "epoch": 10.48, "learning_rate": 1.7926040064659012e-05, "loss": 0.001, "step": 1876 }, { "epoch": 10.49, "learning_rate": 1.792389690814232e-05, "loss": 0.0022, "step": 1877 }, { "epoch": 10.49, "learning_rate": 1.792175277311957e-05, "loss": 0.0007, "step": 1878 }, { "epoch": 10.5, "learning_rate": 1.7919607659855535e-05, "loss": 0.0031, "step": 1879 }, { "epoch": 10.5, "learning_rate": 1.7917461568615104e-05, "loss": 0.0008, "step": 1880 }, { "epoch": 10.51, "learning_rate": 1.7915314499663302e-05, "loss": 0.0012, "step": 1881 }, { "epoch": 10.51, "learning_rate": 1.7913166453265264e-05, "loss": 0.0018, "step": 1882 }, { "epoch": 10.52, "learning_rate": 1.791101742968625e-05, "loss": 0.0014, "step": 1883 }, { "epoch": 10.53, "learning_rate": 1.7908867429191632e-05, "loss": 0.001, "step": 1884 }, { "epoch": 10.53, "learning_rate": 1.7906716452046915e-05, "loss": 0.0009, "step": 1885 }, { "epoch": 10.54, "learning_rate": 1.7904564498517717e-05, "loss": 0.0013, "step": 1886 }, { "epoch": 10.54, "learning_rate": 1.790241156886978e-05, "loss": 0.0021, "step": 1887 }, { "epoch": 10.55, "learning_rate": 1.790025766336896e-05, "loss": 0.0008, "step": 1888 }, { "epoch": 10.55, "learning_rate": 1.7898102782281245e-05, "loss": 0.001, "step": 1889 }, { "epoch": 10.56, "learning_rate": 1.7895946925872733e-05, "loss": 0.0016, "step": 1890 }, { "epoch": 10.56, "learning_rate": 1.789379009440965e-05, "loss": 0.0004, "step": 1891 }, { "epoch": 10.57, "learning_rate": 1.7891632288158333e-05, "loss": 0.0017, "step": 1892 }, { "epoch": 10.58, "learning_rate": 1.788947350738525e-05, "loss": 0.0009, "step": 1893 }, { "epoch": 10.58, "learning_rate": 1.788731375235698e-05, "loss": 0.0007, "step": 1894 }, { "epoch": 10.59, "learning_rate": 1.788515302334023e-05, "loss": 0.0016, "step": 1895 }, { "epoch": 10.59, "learning_rate": 1.7882991320601825e-05, "loss": 0.0018, "step": 1896 }, { "epoch": 10.6, "learning_rate": 1.7880828644408707e-05, "loss": 0.0021, "step": 1897 }, { "epoch": 10.6, "learning_rate": 1.787866499502794e-05, "loss": 0.0043, "step": 1898 }, { "epoch": 10.61, "learning_rate": 1.7876500372726715e-05, "loss": 0.0008, "step": 1899 }, { "epoch": 10.61, "learning_rate": 1.7874334777772326e-05, "loss": 0.0013, "step": 1900 }, { "epoch": 10.62, "learning_rate": 1.7872168210432207e-05, "loss": 0.0012, "step": 1901 }, { "epoch": 10.63, "learning_rate": 1.78700006709739e-05, "loss": 0.0012, "step": 1902 }, { "epoch": 10.63, "learning_rate": 1.786783215966507e-05, "loss": 0.0054, "step": 1903 }, { "epoch": 10.64, "learning_rate": 1.7865662676773504e-05, "loss": 0.0006, "step": 1904 }, { "epoch": 10.64, "learning_rate": 1.78634922225671e-05, "loss": 0.0011, "step": 1905 }, { "epoch": 10.65, "learning_rate": 1.786132079731389e-05, "loss": 0.0011, "step": 1906 }, { "epoch": 10.65, "learning_rate": 1.785914840128202e-05, "loss": 0.0018, "step": 1907 }, { "epoch": 10.66, "learning_rate": 1.785697503473975e-05, "loss": 0.001, "step": 1908 }, { "epoch": 10.66, "learning_rate": 1.7854800697955464e-05, "loss": 0.0008, "step": 1909 }, { "epoch": 10.67, "learning_rate": 1.7852625391197675e-05, "loss": 0.0017, "step": 1910 }, { "epoch": 10.68, "learning_rate": 1.7850449114735e-05, "loss": 0.0021, "step": 1911 }, { "epoch": 10.68, "learning_rate": 1.784827186883618e-05, "loss": 0.0007, "step": 1912 }, { "epoch": 10.69, "learning_rate": 1.7846093653770084e-05, "loss": 0.001, "step": 1913 }, { "epoch": 10.69, "learning_rate": 1.7843914469805698e-05, "loss": 0.0016, "step": 1914 }, { "epoch": 10.7, "learning_rate": 1.784173431721212e-05, "loss": 0.0018, "step": 1915 }, { "epoch": 10.7, "learning_rate": 1.7839553196258573e-05, "loss": 0.0012, "step": 1916 }, { "epoch": 10.71, "learning_rate": 1.78373711072144e-05, "loss": 0.0012, "step": 1917 }, { "epoch": 10.72, "learning_rate": 1.7835188050349064e-05, "loss": 0.0013, "step": 1918 }, { "epoch": 10.72, "learning_rate": 1.7833004025932142e-05, "loss": 0.0011, "step": 1919 }, { "epoch": 10.73, "learning_rate": 1.7830819034233342e-05, "loss": 0.0012, "step": 1920 }, { "epoch": 10.73, "learning_rate": 1.782863307552248e-05, "loss": 0.003, "step": 1921 }, { "epoch": 10.74, "learning_rate": 1.7826446150069493e-05, "loss": 0.0013, "step": 1922 }, { "epoch": 10.74, "learning_rate": 1.7824258258144448e-05, "loss": 0.0008, "step": 1923 }, { "epoch": 10.75, "learning_rate": 1.7822069400017515e-05, "loss": 0.0014, "step": 1924 }, { "epoch": 10.75, "learning_rate": 1.7819879575958997e-05, "loss": 0.0005, "step": 1925 }, { "epoch": 10.76, "learning_rate": 1.7817688786239307e-05, "loss": 0.0016, "step": 1926 }, { "epoch": 10.77, "learning_rate": 1.7815497031128983e-05, "loss": 0.0011, "step": 1927 }, { "epoch": 10.77, "learning_rate": 1.781330431089868e-05, "loss": 0.0007, "step": 1928 }, { "epoch": 10.78, "learning_rate": 1.7811110625819177e-05, "loss": 0.0028, "step": 1929 }, { "epoch": 10.78, "learning_rate": 1.7808915976161364e-05, "loss": 0.0007, "step": 1930 }, { "epoch": 10.79, "learning_rate": 1.7806720362196253e-05, "loss": 0.0009, "step": 1931 }, { "epoch": 10.79, "learning_rate": 1.7804523784194973e-05, "loss": 0.001, "step": 1932 }, { "epoch": 10.8, "learning_rate": 1.7802326242428783e-05, "loss": 0.001, "step": 1933 }, { "epoch": 10.8, "learning_rate": 1.7800127737169047e-05, "loss": 0.0018, "step": 1934 }, { "epoch": 10.81, "learning_rate": 1.7797928268687258e-05, "loss": 0.0024, "step": 1935 }, { "epoch": 10.82, "learning_rate": 1.7795727837255016e-05, "loss": 0.0019, "step": 1936 }, { "epoch": 10.82, "learning_rate": 1.779352644314406e-05, "loss": 0.0008, "step": 1937 }, { "epoch": 10.83, "learning_rate": 1.7791324086626228e-05, "loss": 0.0021, "step": 1938 }, { "epoch": 10.83, "learning_rate": 1.778912076797348e-05, "loss": 0.0006, "step": 1939 }, { "epoch": 10.84, "learning_rate": 1.778691648745791e-05, "loss": 0.0013, "step": 1940 }, { "epoch": 10.84, "learning_rate": 1.778471124535172e-05, "loss": 0.0688, "step": 1941 }, { "epoch": 10.85, "learning_rate": 1.7782505041927218e-05, "loss": 0.0012, "step": 1942 }, { "epoch": 10.85, "learning_rate": 1.7780297877456854e-05, "loss": 0.0012, "step": 1943 }, { "epoch": 10.86, "learning_rate": 1.7778089752213187e-05, "loss": 0.0008, "step": 1944 }, { "epoch": 10.87, "learning_rate": 1.7775880666468893e-05, "loss": 0.0005, "step": 1945 }, { "epoch": 10.87, "learning_rate": 1.777367062049676e-05, "loss": 0.0005, "step": 1946 }, { "epoch": 10.88, "learning_rate": 1.777145961456971e-05, "loss": 0.0008, "step": 1947 }, { "epoch": 10.88, "learning_rate": 1.7769247648960775e-05, "loss": 0.0015, "step": 1948 }, { "epoch": 10.89, "learning_rate": 1.7767034723943103e-05, "loss": 0.0006, "step": 1949 }, { "epoch": 10.89, "learning_rate": 1.7764820839789966e-05, "loss": 0.0008, "step": 1950 }, { "epoch": 10.9, "learning_rate": 1.776260599677475e-05, "loss": 0.0016, "step": 1951 }, { "epoch": 10.91, "learning_rate": 1.7760390195170963e-05, "loss": 0.0008, "step": 1952 }, { "epoch": 10.91, "learning_rate": 1.7758173435252232e-05, "loss": 0.0009, "step": 1953 }, { "epoch": 10.92, "learning_rate": 1.77559557172923e-05, "loss": 0.0013, "step": 1954 }, { "epoch": 10.92, "learning_rate": 1.7753737041565022e-05, "loss": 0.0007, "step": 1955 }, { "epoch": 10.93, "learning_rate": 1.775151740834438e-05, "loss": 0.0013, "step": 1956 }, { "epoch": 10.93, "learning_rate": 1.774929681790448e-05, "loss": 0.0007, "step": 1957 }, { "epoch": 10.94, "learning_rate": 1.774707527051953e-05, "loss": 0.0006, "step": 1958 }, { "epoch": 10.94, "learning_rate": 1.7744852766463867e-05, "loss": 0.0011, "step": 1959 }, { "epoch": 10.95, "learning_rate": 1.7742629306011944e-05, "loss": 0.0013, "step": 1960 }, { "epoch": 10.96, "learning_rate": 1.7740404889438332e-05, "loss": 0.0012, "step": 1961 }, { "epoch": 10.96, "learning_rate": 1.7738179517017718e-05, "loss": 0.0007, "step": 1962 }, { "epoch": 10.97, "learning_rate": 1.773595318902491e-05, "loss": 0.0015, "step": 1963 }, { "epoch": 10.97, "learning_rate": 1.7733725905734832e-05, "loss": 0.0013, "step": 1964 }, { "epoch": 10.98, "learning_rate": 1.7731497667422528e-05, "loss": 0.0021, "step": 1965 }, { "epoch": 10.98, "learning_rate": 1.7729268474363156e-05, "loss": 0.0021, "step": 1966 }, { "epoch": 10.99, "learning_rate": 1.7727038326831998e-05, "loss": 0.0014, "step": 1967 }, { "epoch": 10.99, "learning_rate": 1.7724807225104446e-05, "loss": 0.002, "step": 1968 }, { "epoch": 11.0, "learning_rate": 1.7722575169456023e-05, "loss": 0.0035, "step": 1969 }, { "epoch": 11.01, "learning_rate": 1.7720342160162348e-05, "loss": 0.0012, "step": 1970 }, { "epoch": 11.01, "learning_rate": 1.7718108197499183e-05, "loss": 0.0591, "step": 1971 }, { "epoch": 11.02, "learning_rate": 1.771587328174239e-05, "loss": 0.0013, "step": 1972 }, { "epoch": 11.02, "learning_rate": 1.771363741316795e-05, "loss": 0.0014, "step": 1973 }, { "epoch": 11.03, "learning_rate": 1.7711400592051976e-05, "loss": 0.0039, "step": 1974 }, { "epoch": 11.03, "learning_rate": 1.7709162818670682e-05, "loss": 0.0015, "step": 1975 }, { "epoch": 11.04, "learning_rate": 1.7706924093300405e-05, "loss": 0.0014, "step": 1976 }, { "epoch": 11.04, "learning_rate": 1.7704684416217607e-05, "loss": 0.0006, "step": 1977 }, { "epoch": 11.05, "learning_rate": 1.7702443787698855e-05, "loss": 0.001, "step": 1978 }, { "epoch": 11.06, "learning_rate": 1.770020220802084e-05, "loss": 0.0016, "step": 1979 }, { "epoch": 11.06, "learning_rate": 1.7697959677460373e-05, "loss": 0.002, "step": 1980 }, { "epoch": 11.07, "learning_rate": 1.7695716196294378e-05, "loss": 0.0018, "step": 1981 }, { "epoch": 11.07, "learning_rate": 1.7693471764799902e-05, "loss": 0.0014, "step": 1982 }, { "epoch": 11.08, "learning_rate": 1.76912263832541e-05, "loss": 0.0006, "step": 1983 }, { "epoch": 11.08, "learning_rate": 1.768898005193425e-05, "loss": 0.0043, "step": 1984 }, { "epoch": 11.09, "learning_rate": 1.768673277111775e-05, "loss": 0.0027, "step": 1985 }, { "epoch": 11.09, "learning_rate": 1.768448454108211e-05, "loss": 0.001, "step": 1986 }, { "epoch": 11.1, "learning_rate": 1.768223536210496e-05, "loss": 0.0007, "step": 1987 }, { "epoch": 11.11, "learning_rate": 1.7679985234464045e-05, "loss": 0.0012, "step": 1988 }, { "epoch": 11.11, "learning_rate": 1.7677734158437233e-05, "loss": 0.0019, "step": 1989 }, { "epoch": 11.12, "learning_rate": 1.7675482134302503e-05, "loss": 0.0015, "step": 1990 }, { "epoch": 11.12, "learning_rate": 1.767322916233795e-05, "loss": 0.0021, "step": 1991 }, { "epoch": 11.13, "learning_rate": 1.7670975242821787e-05, "loss": 0.0012, "step": 1992 }, { "epoch": 11.13, "learning_rate": 1.7668720376032356e-05, "loss": 0.0012, "step": 1993 }, { "epoch": 11.14, "learning_rate": 1.76664645622481e-05, "loss": 0.0012, "step": 1994 }, { "epoch": 11.15, "learning_rate": 1.7664207801747583e-05, "loss": 0.0025, "step": 1995 }, { "epoch": 11.15, "learning_rate": 1.766195009480949e-05, "loss": 0.0014, "step": 1996 }, { "epoch": 11.16, "learning_rate": 1.765969144171262e-05, "loss": 0.0012, "step": 1997 }, { "epoch": 11.16, "learning_rate": 1.765743184273589e-05, "loss": 0.0027, "step": 1998 }, { "epoch": 11.17, "learning_rate": 1.7655171298158332e-05, "loss": 0.005, "step": 1999 }, { "epoch": 11.17, "learning_rate": 1.7652909808259102e-05, "loss": 0.0011, "step": 2000 }, { "epoch": 11.18, "learning_rate": 1.7650647373317458e-05, "loss": 0.0006, "step": 2001 }, { "epoch": 11.18, "learning_rate": 1.764838399361279e-05, "loss": 0.0024, "step": 2002 }, { "epoch": 11.19, "learning_rate": 1.7646119669424594e-05, "loss": 0.0026, "step": 2003 }, { "epoch": 11.2, "learning_rate": 1.764385440103249e-05, "loss": 0.0017, "step": 2004 }, { "epoch": 11.2, "learning_rate": 1.764158818871621e-05, "loss": 0.0016, "step": 2005 }, { "epoch": 11.21, "learning_rate": 1.7639321032755604e-05, "loss": 0.0119, "step": 2006 }, { "epoch": 11.21, "learning_rate": 1.7637052933430636e-05, "loss": 0.0031, "step": 2007 }, { "epoch": 11.22, "learning_rate": 1.7634783891021394e-05, "loss": 0.0065, "step": 2008 }, { "epoch": 11.22, "learning_rate": 1.763251390580808e-05, "loss": 0.0032, "step": 2009 }, { "epoch": 11.23, "learning_rate": 1.7630242978071e-05, "loss": 0.0013, "step": 2010 }, { "epoch": 11.23, "learning_rate": 1.7627971108090588e-05, "loss": 0.0025, "step": 2011 }, { "epoch": 11.24, "learning_rate": 1.76256982961474e-05, "loss": 0.0039, "step": 2012 }, { "epoch": 11.25, "learning_rate": 1.7623424542522096e-05, "loss": 0.0019, "step": 2013 }, { "epoch": 11.25, "learning_rate": 1.7621149847495458e-05, "loss": 0.001, "step": 2014 }, { "epoch": 11.26, "learning_rate": 1.7618874211348385e-05, "loss": 0.0007, "step": 2015 }, { "epoch": 11.26, "learning_rate": 1.761659763436189e-05, "loss": 0.0093, "step": 2016 }, { "epoch": 11.27, "learning_rate": 1.7614320116817102e-05, "loss": 0.0012, "step": 2017 }, { "epoch": 11.27, "learning_rate": 1.7612041658995264e-05, "loss": 0.0008, "step": 2018 }, { "epoch": 11.28, "learning_rate": 1.7609762261177742e-05, "loss": 0.0011, "step": 2019 }, { "epoch": 11.28, "learning_rate": 1.760748192364602e-05, "loss": 0.001, "step": 2020 }, { "epoch": 11.29, "learning_rate": 1.7605200646681678e-05, "loss": 0.0011, "step": 2021 }, { "epoch": 11.3, "learning_rate": 1.760291843056644e-05, "loss": 0.001, "step": 2022 }, { "epoch": 11.3, "learning_rate": 1.7600635275582127e-05, "loss": 0.0014, "step": 2023 }, { "epoch": 11.31, "learning_rate": 1.7598351182010677e-05, "loss": 0.0013, "step": 2024 }, { "epoch": 11.31, "learning_rate": 1.7596066150134153e-05, "loss": 0.0011, "step": 2025 }, { "epoch": 11.32, "learning_rate": 1.759378018023473e-05, "loss": 0.0012, "step": 2026 }, { "epoch": 11.32, "learning_rate": 1.7591493272594694e-05, "loss": 0.0008, "step": 2027 }, { "epoch": 11.33, "learning_rate": 1.7589205427496452e-05, "loss": 0.0016, "step": 2028 }, { "epoch": 11.34, "learning_rate": 1.7586916645222526e-05, "loss": 0.0019, "step": 2029 }, { "epoch": 11.34, "learning_rate": 1.7584626926055553e-05, "loss": 0.0015, "step": 2030 }, { "epoch": 11.35, "learning_rate": 1.7582336270278287e-05, "loss": 0.0008, "step": 2031 }, { "epoch": 11.35, "learning_rate": 1.7580044678173593e-05, "loss": 0.0012, "step": 2032 }, { "epoch": 11.36, "learning_rate": 1.757775215002446e-05, "loss": 0.0015, "step": 2033 }, { "epoch": 11.36, "learning_rate": 1.7575458686113983e-05, "loss": 0.0009, "step": 2034 }, { "epoch": 11.37, "learning_rate": 1.757316428672538e-05, "loss": 0.0018, "step": 2035 }, { "epoch": 11.37, "learning_rate": 1.757086895214198e-05, "loss": 0.0011, "step": 2036 }, { "epoch": 11.38, "learning_rate": 1.756857268264723e-05, "loss": 0.001, "step": 2037 }, { "epoch": 11.39, "learning_rate": 1.7566275478524694e-05, "loss": 0.0015, "step": 2038 }, { "epoch": 11.39, "learning_rate": 1.7563977340058043e-05, "loss": 0.0007, "step": 2039 }, { "epoch": 11.4, "learning_rate": 1.756167826753108e-05, "loss": 0.0007, "step": 2040 }, { "epoch": 11.4, "learning_rate": 1.75593782612277e-05, "loss": 0.0007, "step": 2041 }, { "epoch": 11.41, "learning_rate": 1.7557077321431936e-05, "loss": 0.0024, "step": 2042 }, { "epoch": 11.41, "learning_rate": 1.7554775448427918e-05, "loss": 0.0009, "step": 2043 }, { "epoch": 11.42, "learning_rate": 1.755247264249991e-05, "loss": 0.0012, "step": 2044 }, { "epoch": 11.42, "learning_rate": 1.7550168903932273e-05, "loss": 0.0006, "step": 2045 }, { "epoch": 11.43, "learning_rate": 1.7547864233009494e-05, "loss": 0.0006, "step": 2046 }, { "epoch": 11.44, "learning_rate": 1.754555863001617e-05, "loss": 0.0009, "step": 2047 }, { "epoch": 11.44, "learning_rate": 1.7543252095237017e-05, "loss": 0.0011, "step": 2048 }, { "epoch": 11.45, "learning_rate": 1.7540944628956865e-05, "loss": 0.001, "step": 2049 }, { "epoch": 11.45, "learning_rate": 1.753863623146066e-05, "loss": 0.0006, "step": 2050 }, { "epoch": 11.46, "learning_rate": 1.7536326903033454e-05, "loss": 0.0016, "step": 2051 }, { "epoch": 11.46, "learning_rate": 1.753401664396043e-05, "loss": 0.0009, "step": 2052 }, { "epoch": 11.47, "learning_rate": 1.7531705454526872e-05, "loss": 0.0011, "step": 2053 }, { "epoch": 11.47, "learning_rate": 1.7529393335018186e-05, "loss": 0.0008, "step": 2054 }, { "epoch": 11.48, "learning_rate": 1.752708028571989e-05, "loss": 0.0007, "step": 2055 }, { "epoch": 11.49, "learning_rate": 1.7524766306917617e-05, "loss": 0.0013, "step": 2056 }, { "epoch": 11.49, "learning_rate": 1.752245139889712e-05, "loss": 0.0013, "step": 2057 }, { "epoch": 11.5, "learning_rate": 1.7520135561944257e-05, "loss": 0.0008, "step": 2058 }, { "epoch": 11.5, "learning_rate": 1.7517818796345008e-05, "loss": 0.0008, "step": 2059 }, { "epoch": 11.51, "learning_rate": 1.7515501102385468e-05, "loss": 0.0011, "step": 2060 }, { "epoch": 11.51, "learning_rate": 1.751318248035184e-05, "loss": 0.0007, "step": 2061 }, { "epoch": 11.52, "learning_rate": 1.751086293053045e-05, "loss": 0.001, "step": 2062 }, { "epoch": 11.53, "learning_rate": 1.750854245320773e-05, "loss": 0.0008, "step": 2063 }, { "epoch": 11.53, "learning_rate": 1.750622104867024e-05, "loss": 0.0018, "step": 2064 }, { "epoch": 11.54, "learning_rate": 1.750389871720463e-05, "loss": 0.0014, "step": 2065 }, { "epoch": 11.54, "learning_rate": 1.75015754590977e-05, "loss": 0.0014, "step": 2066 }, { "epoch": 11.55, "learning_rate": 1.7499251274636328e-05, "loss": 0.0011, "step": 2067 }, { "epoch": 11.55, "learning_rate": 1.749692616410753e-05, "loss": 0.0011, "step": 2068 }, { "epoch": 11.56, "learning_rate": 1.7494600127798427e-05, "loss": 0.0018, "step": 2069 }, { "epoch": 11.56, "learning_rate": 1.749227316599626e-05, "loss": 0.0016, "step": 2070 }, { "epoch": 11.57, "learning_rate": 1.7489945278988377e-05, "loss": 0.0006, "step": 2071 }, { "epoch": 11.58, "learning_rate": 1.7487616467062247e-05, "loss": 0.001, "step": 2072 }, { "epoch": 11.58, "learning_rate": 1.7485286730505444e-05, "loss": 0.002, "step": 2073 }, { "epoch": 11.59, "learning_rate": 1.748295606960567e-05, "loss": 0.0007, "step": 2074 }, { "epoch": 11.59, "learning_rate": 1.7480624484650733e-05, "loss": 0.0024, "step": 2075 }, { "epoch": 11.6, "learning_rate": 1.747829197592855e-05, "loss": 0.0005, "step": 2076 }, { "epoch": 11.6, "learning_rate": 1.7475958543727164e-05, "loss": 0.001, "step": 2077 }, { "epoch": 11.61, "learning_rate": 1.747362418833472e-05, "loss": 0.001, "step": 2078 }, { "epoch": 11.61, "learning_rate": 1.747128891003949e-05, "loss": 0.0009, "step": 2079 }, { "epoch": 11.62, "learning_rate": 1.7468952709129848e-05, "loss": 0.001, "step": 2080 }, { "epoch": 11.63, "learning_rate": 1.7466615585894286e-05, "loss": 0.0008, "step": 2081 }, { "epoch": 11.63, "learning_rate": 1.7464277540621416e-05, "loss": 0.0005, "step": 2082 }, { "epoch": 11.64, "learning_rate": 1.746193857359995e-05, "loss": 0.0005, "step": 2083 }, { "epoch": 11.64, "learning_rate": 1.745959868511873e-05, "loss": 0.0016, "step": 2084 }, { "epoch": 11.65, "learning_rate": 1.7457257875466697e-05, "loss": 0.0011, "step": 2085 }, { "epoch": 11.65, "learning_rate": 1.7454916144932923e-05, "loss": 0.0013, "step": 2086 }, { "epoch": 11.66, "learning_rate": 1.7452573493806573e-05, "loss": 0.0025, "step": 2087 }, { "epoch": 11.66, "learning_rate": 1.7450229922376945e-05, "loss": 0.0015, "step": 2088 }, { "epoch": 11.67, "learning_rate": 1.7447885430933435e-05, "loss": 0.0008, "step": 2089 }, { "epoch": 11.68, "learning_rate": 1.744554001976556e-05, "loss": 0.0006, "step": 2090 }, { "epoch": 11.68, "learning_rate": 1.7443193689162957e-05, "loss": 0.0021, "step": 2091 }, { "epoch": 11.69, "learning_rate": 1.7440846439415363e-05, "loss": 0.0009, "step": 2092 }, { "epoch": 11.69, "learning_rate": 1.7438498270812636e-05, "loss": 0.0005, "step": 2093 }, { "epoch": 11.7, "learning_rate": 1.7436149183644754e-05, "loss": 0.0011, "step": 2094 }, { "epoch": 11.7, "learning_rate": 1.7433799178201786e-05, "loss": 0.0006, "step": 2095 }, { "epoch": 11.71, "learning_rate": 1.7431448254773943e-05, "loss": 0.0033, "step": 2096 }, { "epoch": 11.72, "learning_rate": 1.7429096413651533e-05, "loss": 0.0017, "step": 2097 }, { "epoch": 11.72, "learning_rate": 1.7426743655124973e-05, "loss": 0.001, "step": 2098 }, { "epoch": 11.73, "learning_rate": 1.742438997948481e-05, "loss": 0.0019, "step": 2099 }, { "epoch": 11.73, "learning_rate": 1.742203538702169e-05, "loss": 0.0005, "step": 2100 }, { "epoch": 11.74, "learning_rate": 1.7419679878026375e-05, "loss": 0.0039, "step": 2101 }, { "epoch": 11.74, "learning_rate": 1.7417323452789746e-05, "loss": 0.0016, "step": 2102 }, { "epoch": 11.75, "learning_rate": 1.741496611160279e-05, "loss": 0.0011, "step": 2103 }, { "epoch": 11.75, "learning_rate": 1.7412607854756613e-05, "loss": 0.0006, "step": 2104 }, { "epoch": 11.76, "learning_rate": 1.7410248682542428e-05, "loss": 0.0005, "step": 2105 }, { "epoch": 11.77, "learning_rate": 1.7407888595251567e-05, "loss": 0.0012, "step": 2106 }, { "epoch": 11.77, "learning_rate": 1.7405527593175474e-05, "loss": 0.0012, "step": 2107 }, { "epoch": 11.78, "learning_rate": 1.74031656766057e-05, "loss": 0.0008, "step": 2108 }, { "epoch": 11.78, "learning_rate": 1.7400802845833918e-05, "loss": 0.0021, "step": 2109 }, { "epoch": 11.79, "learning_rate": 1.7398439101151908e-05, "loss": 0.0009, "step": 2110 }, { "epoch": 11.79, "learning_rate": 1.739607444285156e-05, "loss": 0.0014, "step": 2111 }, { "epoch": 11.8, "learning_rate": 1.7393708871224887e-05, "loss": 0.0006, "step": 2112 }, { "epoch": 11.8, "learning_rate": 1.7391342386564e-05, "loss": 0.0015, "step": 2113 }, { "epoch": 11.81, "learning_rate": 1.738897498916114e-05, "loss": 0.0005, "step": 2114 }, { "epoch": 11.82, "learning_rate": 1.738660667930865e-05, "loss": 0.0016, "step": 2115 }, { "epoch": 11.82, "learning_rate": 1.7384237457298987e-05, "loss": 0.0009, "step": 2116 }, { "epoch": 11.83, "learning_rate": 1.7381867323424718e-05, "loss": 0.0006, "step": 2117 }, { "epoch": 11.83, "learning_rate": 1.7379496277978535e-05, "loss": 0.0023, "step": 2118 }, { "epoch": 11.84, "learning_rate": 1.7377124321253226e-05, "loss": 0.0014, "step": 2119 }, { "epoch": 11.84, "learning_rate": 1.73747514535417e-05, "loss": 0.0012, "step": 2120 }, { "epoch": 11.85, "learning_rate": 1.737237767513698e-05, "loss": 0.0007, "step": 2121 }, { "epoch": 11.85, "learning_rate": 1.7370002986332195e-05, "loss": 0.0012, "step": 2122 }, { "epoch": 11.86, "learning_rate": 1.7367627387420595e-05, "loss": 0.0024, "step": 2123 }, { "epoch": 11.87, "learning_rate": 1.7365250878695538e-05, "loss": 0.0006, "step": 2124 }, { "epoch": 11.87, "learning_rate": 1.736287346045049e-05, "loss": 0.0011, "step": 2125 }, { "epoch": 11.88, "learning_rate": 1.7360495132979037e-05, "loss": 0.0014, "step": 2126 }, { "epoch": 11.88, "learning_rate": 1.7358115896574874e-05, "loss": 0.0018, "step": 2127 }, { "epoch": 11.89, "learning_rate": 1.7355735751531808e-05, "loss": 0.0015, "step": 2128 }, { "epoch": 11.89, "learning_rate": 1.7353354698143755e-05, "loss": 0.0011, "step": 2129 }, { "epoch": 11.9, "learning_rate": 1.735097273670475e-05, "loss": 0.0006, "step": 2130 }, { "epoch": 11.91, "learning_rate": 1.7348589867508937e-05, "loss": 0.001, "step": 2131 }, { "epoch": 11.91, "learning_rate": 1.7346206090850572e-05, "loss": 0.0018, "step": 2132 }, { "epoch": 11.92, "learning_rate": 1.7343821407024016e-05, "loss": 0.0016, "step": 2133 }, { "epoch": 11.92, "learning_rate": 1.7341435816323756e-05, "loss": 0.0009, "step": 2134 }, { "epoch": 11.93, "learning_rate": 1.7339049319044384e-05, "loss": 0.0011, "step": 2135 }, { "epoch": 11.93, "learning_rate": 1.7336661915480602e-05, "loss": 0.0012, "step": 2136 }, { "epoch": 11.94, "learning_rate": 1.733427360592722e-05, "loss": 0.0009, "step": 2137 }, { "epoch": 11.94, "learning_rate": 1.7331884390679173e-05, "loss": 0.0011, "step": 2138 }, { "epoch": 11.95, "learning_rate": 1.73294942700315e-05, "loss": 0.001, "step": 2139 }, { "epoch": 11.96, "learning_rate": 1.732710324427935e-05, "loss": 0.0011, "step": 2140 }, { "epoch": 11.96, "learning_rate": 1.7324711313717985e-05, "loss": 0.0009, "step": 2141 }, { "epoch": 11.97, "learning_rate": 1.732231847864278e-05, "loss": 0.0043, "step": 2142 }, { "epoch": 11.97, "learning_rate": 1.7319924739349224e-05, "loss": 0.0008, "step": 2143 }, { "epoch": 11.98, "learning_rate": 1.7317530096132914e-05, "loss": 0.0003, "step": 2144 }, { "epoch": 11.98, "learning_rate": 1.7315134549289556e-05, "loss": 0.0013, "step": 2145 }, { "epoch": 11.99, "learning_rate": 1.7312738099114973e-05, "loss": 0.0006, "step": 2146 }, { "epoch": 11.99, "learning_rate": 1.7310340745905103e-05, "loss": 0.001, "step": 2147 }, { "epoch": 12.0, "learning_rate": 1.7307942489955985e-05, "loss": 0.0022, "step": 2148 }, { "epoch": 12.01, "learning_rate": 1.7305543331563776e-05, "loss": 0.0009, "step": 2149 }, { "epoch": 12.01, "learning_rate": 1.7303143271024744e-05, "loss": 0.0009, "step": 2150 }, { "epoch": 12.02, "learning_rate": 1.7300742308635265e-05, "loss": 0.0013, "step": 2151 }, { "epoch": 12.02, "learning_rate": 1.7298340444691836e-05, "loss": 0.0101, "step": 2152 }, { "epoch": 12.03, "learning_rate": 1.729593767949105e-05, "loss": 0.0007, "step": 2153 }, { "epoch": 12.03, "learning_rate": 1.7293534013329618e-05, "loss": 0.0007, "step": 2154 }, { "epoch": 12.04, "learning_rate": 1.7291129446504376e-05, "loss": 0.0009, "step": 2155 }, { "epoch": 12.04, "learning_rate": 1.728872397931225e-05, "loss": 0.0006, "step": 2156 }, { "epoch": 12.05, "learning_rate": 1.7286317612050284e-05, "loss": 0.0008, "step": 2157 }, { "epoch": 12.06, "learning_rate": 1.7283910345015645e-05, "loss": 0.0027, "step": 2158 }, { "epoch": 12.06, "learning_rate": 1.7281502178505596e-05, "loss": 0.001, "step": 2159 }, { "epoch": 12.07, "learning_rate": 1.7279093112817517e-05, "loss": 0.001, "step": 2160 }, { "epoch": 12.07, "learning_rate": 1.7276683148248893e-05, "loss": 0.0006, "step": 2161 }, { "epoch": 12.08, "learning_rate": 1.7274272285097336e-05, "loss": 0.0016, "step": 2162 }, { "epoch": 12.08, "learning_rate": 1.7271860523660553e-05, "loss": 0.004, "step": 2163 }, { "epoch": 12.09, "learning_rate": 1.726944786423637e-05, "loss": 0.001, "step": 2164 }, { "epoch": 12.09, "learning_rate": 1.7267034307122717e-05, "loss": 0.0013, "step": 2165 }, { "epoch": 12.1, "learning_rate": 1.7264619852617645e-05, "loss": 0.0018, "step": 2166 }, { "epoch": 12.11, "learning_rate": 1.7262204501019307e-05, "loss": 0.0009, "step": 2167 }, { "epoch": 12.11, "learning_rate": 1.7259788252625968e-05, "loss": 0.0009, "step": 2168 }, { "epoch": 12.12, "learning_rate": 1.7257371107736007e-05, "loss": 0.0007, "step": 2169 }, { "epoch": 12.12, "learning_rate": 1.7254953066647915e-05, "loss": 0.0006, "step": 2170 }, { "epoch": 12.13, "learning_rate": 1.725253412966029e-05, "loss": 0.0011, "step": 2171 }, { "epoch": 12.13, "learning_rate": 1.725011429707184e-05, "loss": 0.0011, "step": 2172 }, { "epoch": 12.14, "learning_rate": 1.7247693569181385e-05, "loss": 0.0004, "step": 2173 }, { "epoch": 12.15, "learning_rate": 1.7245271946287858e-05, "loss": 0.0007, "step": 2174 }, { "epoch": 12.15, "learning_rate": 1.72428494286903e-05, "loss": 0.001, "step": 2175 }, { "epoch": 12.16, "learning_rate": 1.7240426016687863e-05, "loss": 0.0006, "step": 2176 }, { "epoch": 12.16, "learning_rate": 1.7238001710579805e-05, "loss": 0.0009, "step": 2177 }, { "epoch": 12.17, "learning_rate": 1.7235576510665507e-05, "loss": 0.0012, "step": 2178 }, { "epoch": 12.17, "learning_rate": 1.723315041724444e-05, "loss": 0.0009, "step": 2179 }, { "epoch": 12.18, "learning_rate": 1.723072343061621e-05, "loss": 0.0007, "step": 2180 }, { "epoch": 12.18, "learning_rate": 1.722829555108051e-05, "loss": 0.001, "step": 2181 }, { "epoch": 12.19, "learning_rate": 1.7225866778937168e-05, "loss": 0.0004, "step": 2182 }, { "epoch": 12.2, "learning_rate": 1.722343711448609e-05, "loss": 0.0007, "step": 2183 }, { "epoch": 12.2, "learning_rate": 1.7221006558027325e-05, "loss": 0.0005, "step": 2184 }, { "epoch": 12.21, "learning_rate": 1.721857510986101e-05, "loss": 0.0009, "step": 2185 }, { "epoch": 12.21, "learning_rate": 1.7216142770287403e-05, "loss": 0.0007, "step": 2186 }, { "epoch": 12.22, "learning_rate": 1.7213709539606864e-05, "loss": 0.0006, "step": 2187 }, { "epoch": 12.22, "learning_rate": 1.7211275418119875e-05, "loss": 0.0012, "step": 2188 }, { "epoch": 12.23, "learning_rate": 1.7208840406127016e-05, "loss": 0.0008, "step": 2189 }, { "epoch": 12.23, "learning_rate": 1.7206404503928983e-05, "loss": 0.0005, "step": 2190 }, { "epoch": 12.24, "learning_rate": 1.720396771182658e-05, "loss": 0.0013, "step": 2191 }, { "epoch": 12.25, "learning_rate": 1.7201530030120722e-05, "loss": 0.0016, "step": 2192 }, { "epoch": 12.25, "learning_rate": 1.719909145911243e-05, "loss": 0.0005, "step": 2193 }, { "epoch": 12.26, "learning_rate": 1.719665199910285e-05, "loss": 0.0007, "step": 2194 }, { "epoch": 12.26, "learning_rate": 1.719421165039321e-05, "loss": 0.0009, "step": 2195 }, { "epoch": 12.27, "learning_rate": 1.7191770413284873e-05, "loss": 0.0006, "step": 2196 }, { "epoch": 12.27, "learning_rate": 1.7189328288079302e-05, "loss": 0.0009, "step": 2197 }, { "epoch": 12.28, "learning_rate": 1.7186885275078068e-05, "loss": 0.0006, "step": 2198 }, { "epoch": 12.28, "learning_rate": 1.7184441374582855e-05, "loss": 0.0007, "step": 2199 }, { "epoch": 12.29, "learning_rate": 1.7181996586895456e-05, "loss": 0.0013, "step": 2200 }, { "epoch": 12.3, "learning_rate": 1.7179550912317768e-05, "loss": 0.0008, "step": 2201 }, { "epoch": 12.3, "learning_rate": 1.7177104351151812e-05, "loss": 0.0009, "step": 2202 }, { "epoch": 12.31, "learning_rate": 1.7174656903699702e-05, "loss": 0.0007, "step": 2203 }, { "epoch": 12.31, "learning_rate": 1.7172208570263664e-05, "loss": 0.0007, "step": 2204 }, { "epoch": 12.32, "learning_rate": 1.7169759351146047e-05, "loss": 0.001, "step": 2205 }, { "epoch": 12.32, "learning_rate": 1.7167309246649298e-05, "loss": 0.0005, "step": 2206 }, { "epoch": 12.33, "learning_rate": 1.716485825707597e-05, "loss": 0.0015, "step": 2207 }, { "epoch": 12.34, "learning_rate": 1.7162406382728737e-05, "loss": 0.0022, "step": 2208 }, { "epoch": 12.34, "learning_rate": 1.7159953623910374e-05, "loss": 0.0006, "step": 2209 }, { "epoch": 12.35, "learning_rate": 1.7157499980923767e-05, "loss": 0.0007, "step": 2210 }, { "epoch": 12.35, "learning_rate": 1.7155045454071914e-05, "loss": 0.0009, "step": 2211 }, { "epoch": 12.36, "learning_rate": 1.715259004365791e-05, "loss": 0.0007, "step": 2212 }, { "epoch": 12.36, "learning_rate": 1.715013374998498e-05, "loss": 0.0007, "step": 2213 }, { "epoch": 12.37, "learning_rate": 1.7147676573356446e-05, "loss": 0.0007, "step": 2214 }, { "epoch": 12.37, "learning_rate": 1.714521851407573e-05, "loss": 0.0007, "step": 2215 }, { "epoch": 12.38, "learning_rate": 1.7142759572446383e-05, "loss": 0.0014, "step": 2216 }, { "epoch": 12.39, "learning_rate": 1.7140299748772046e-05, "loss": 0.0016, "step": 2217 }, { "epoch": 12.39, "learning_rate": 1.7137839043356486e-05, "loss": 0.0005, "step": 2218 }, { "epoch": 12.4, "learning_rate": 1.7135377456503564e-05, "loss": 0.0005, "step": 2219 }, { "epoch": 12.4, "learning_rate": 1.7132914988517263e-05, "loss": 0.0009, "step": 2220 }, { "epoch": 12.41, "learning_rate": 1.7130451639701664e-05, "loss": 0.0005, "step": 2221 }, { "epoch": 12.41, "learning_rate": 1.712798741036096e-05, "loss": 0.0021, "step": 2222 }, { "epoch": 12.42, "learning_rate": 1.7125522300799456e-05, "loss": 0.0004, "step": 2223 }, { "epoch": 12.42, "learning_rate": 1.712305631132156e-05, "loss": 0.0007, "step": 2224 }, { "epoch": 12.43, "learning_rate": 1.71205894422318e-05, "loss": 0.0008, "step": 2225 }, { "epoch": 12.44, "learning_rate": 1.7118121693834796e-05, "loss": 0.0005, "step": 2226 }, { "epoch": 12.44, "learning_rate": 1.711565306643529e-05, "loss": 0.001, "step": 2227 }, { "epoch": 12.45, "learning_rate": 1.7113183560338123e-05, "loss": 0.0005, "step": 2228 }, { "epoch": 12.45, "learning_rate": 1.7110713175848256e-05, "loss": 0.0012, "step": 2229 }, { "epoch": 12.46, "learning_rate": 1.710824191327075e-05, "loss": 0.0008, "step": 2230 }, { "epoch": 12.46, "learning_rate": 1.710576977291077e-05, "loss": 0.0004, "step": 2231 }, { "epoch": 12.47, "learning_rate": 1.7103296755073608e-05, "loss": 0.001, "step": 2232 }, { "epoch": 12.47, "learning_rate": 1.7100822860064638e-05, "loss": 0.0019, "step": 2233 }, { "epoch": 12.48, "learning_rate": 1.7098348088189364e-05, "loss": 0.0007, "step": 2234 }, { "epoch": 12.49, "learning_rate": 1.709587243975339e-05, "loss": 0.0008, "step": 2235 }, { "epoch": 12.49, "learning_rate": 1.709339591506243e-05, "loss": 0.0007, "step": 2236 }, { "epoch": 12.5, "learning_rate": 1.70909185144223e-05, "loss": 0.0004, "step": 2237 }, { "epoch": 12.5, "learning_rate": 1.7088440238138936e-05, "loss": 0.0006, "step": 2238 }, { "epoch": 12.51, "learning_rate": 1.708596108651837e-05, "loss": 0.0004, "step": 2239 }, { "epoch": 12.51, "learning_rate": 1.708348105986675e-05, "loss": 0.0011, "step": 2240 }, { "epoch": 12.52, "learning_rate": 1.7081000158490328e-05, "loss": 0.0009, "step": 2241 }, { "epoch": 12.53, "learning_rate": 1.7078518382695467e-05, "loss": 0.0009, "step": 2242 }, { "epoch": 12.53, "learning_rate": 1.7076035732788633e-05, "loss": 0.0012, "step": 2243 }, { "epoch": 12.54, "learning_rate": 1.707355220907641e-05, "loss": 0.0007, "step": 2244 }, { "epoch": 12.54, "learning_rate": 1.7071067811865477e-05, "loss": 0.0006, "step": 2245 }, { "epoch": 12.55, "learning_rate": 1.7068582541462632e-05, "loss": 0.0006, "step": 2246 }, { "epoch": 12.55, "learning_rate": 1.706609639817477e-05, "loss": 0.001, "step": 2247 }, { "epoch": 12.56, "learning_rate": 1.7063609382308905e-05, "loss": 0.0059, "step": 2248 }, { "epoch": 12.56, "learning_rate": 1.7061121494172156e-05, "loss": 0.0005, "step": 2249 }, { "epoch": 12.57, "learning_rate": 1.705863273407174e-05, "loss": 0.001, "step": 2250 }, { "epoch": 12.58, "learning_rate": 1.7056143102314995e-05, "loss": 0.0027, "step": 2251 }, { "epoch": 12.58, "learning_rate": 1.7053652599209353e-05, "loss": 0.0009, "step": 2252 }, { "epoch": 12.59, "learning_rate": 1.705116122506237e-05, "loss": 0.0005, "step": 2253 }, { "epoch": 12.59, "learning_rate": 1.7048668980181696e-05, "loss": 0.0009, "step": 2254 }, { "epoch": 12.6, "learning_rate": 1.7046175864875098e-05, "loss": 0.0008, "step": 2255 }, { "epoch": 12.6, "learning_rate": 1.704368187945044e-05, "loss": 0.0013, "step": 2256 }, { "epoch": 12.61, "learning_rate": 1.7041187024215696e-05, "loss": 0.0019, "step": 2257 }, { "epoch": 12.61, "learning_rate": 1.7038691299478963e-05, "loss": 0.0008, "step": 2258 }, { "epoch": 12.62, "learning_rate": 1.703619470554842e-05, "loss": 0.0013, "step": 2259 }, { "epoch": 12.63, "learning_rate": 1.7033697242732376e-05, "loss": 0.0006, "step": 2260 }, { "epoch": 12.63, "learning_rate": 1.7031198911339236e-05, "loss": 0.001, "step": 2261 }, { "epoch": 12.64, "learning_rate": 1.7028699711677508e-05, "loss": 0.0013, "step": 2262 }, { "epoch": 12.64, "learning_rate": 1.702619964405582e-05, "loss": 0.0027, "step": 2263 }, { "epoch": 12.65, "learning_rate": 1.7023698708782895e-05, "loss": 0.0007, "step": 2264 }, { "epoch": 12.65, "learning_rate": 1.702119690616757e-05, "loss": 0.0022, "step": 2265 }, { "epoch": 12.66, "learning_rate": 1.7018694236518792e-05, "loss": 0.001, "step": 2266 }, { "epoch": 12.66, "learning_rate": 1.7016190700145604e-05, "loss": 0.0008, "step": 2267 }, { "epoch": 12.67, "learning_rate": 1.7013686297357165e-05, "loss": 0.0009, "step": 2268 }, { "epoch": 12.68, "learning_rate": 1.7011181028462745e-05, "loss": 0.0013, "step": 2269 }, { "epoch": 12.68, "learning_rate": 1.7008674893771708e-05, "loss": 0.0014, "step": 2270 }, { "epoch": 12.69, "learning_rate": 1.7006167893593525e-05, "loss": 0.0007, "step": 2271 }, { "epoch": 12.69, "learning_rate": 1.7003660028237793e-05, "loss": 0.0005, "step": 2272 }, { "epoch": 12.7, "learning_rate": 1.70011512980142e-05, "loss": 0.0049, "step": 2273 }, { "epoch": 12.7, "learning_rate": 1.6998641703232535e-05, "loss": 0.0009, "step": 2274 }, { "epoch": 12.71, "learning_rate": 1.699613124420272e-05, "loss": 0.0059, "step": 2275 }, { "epoch": 12.72, "learning_rate": 1.699361992123475e-05, "loss": 0.002, "step": 2276 }, { "epoch": 12.72, "learning_rate": 1.699110773463875e-05, "loss": 0.0039, "step": 2277 }, { "epoch": 12.73, "learning_rate": 1.6988594684724947e-05, "loss": 0.0016, "step": 2278 }, { "epoch": 12.73, "learning_rate": 1.6986080771803667e-05, "loss": 0.0019, "step": 2279 }, { "epoch": 12.74, "learning_rate": 1.698356599618535e-05, "loss": 0.0025, "step": 2280 }, { "epoch": 12.74, "learning_rate": 1.6981050358180546e-05, "loss": 0.0013, "step": 2281 }, { "epoch": 12.75, "learning_rate": 1.69785338580999e-05, "loss": 0.0013, "step": 2282 }, { "epoch": 12.75, "learning_rate": 1.697601649625417e-05, "loss": 0.0023, "step": 2283 }, { "epoch": 12.76, "learning_rate": 1.6973498272954223e-05, "loss": 0.0018, "step": 2284 }, { "epoch": 12.77, "learning_rate": 1.6970979188511028e-05, "loss": 0.0576, "step": 2285 }, { "epoch": 12.77, "learning_rate": 1.696845924323566e-05, "loss": 0.0012, "step": 2286 }, { "epoch": 12.78, "learning_rate": 1.69659384374393e-05, "loss": 0.0015, "step": 2287 }, { "epoch": 12.78, "learning_rate": 1.6963416771433246e-05, "loss": 0.0015, "step": 2288 }, { "epoch": 12.79, "learning_rate": 1.6960894245528884e-05, "loss": 0.0012, "step": 2289 }, { "epoch": 12.79, "learning_rate": 1.695837086003772e-05, "loss": 0.001, "step": 2290 }, { "epoch": 12.8, "learning_rate": 1.695584661527136e-05, "loss": 0.0042, "step": 2291 }, { "epoch": 12.8, "learning_rate": 1.6953321511541523e-05, "loss": 0.0018, "step": 2292 }, { "epoch": 12.81, "learning_rate": 1.6950795549160022e-05, "loss": 0.0005, "step": 2293 }, { "epoch": 12.82, "learning_rate": 1.6948268728438784e-05, "loss": 0.0013, "step": 2294 }, { "epoch": 12.82, "learning_rate": 1.694574104968985e-05, "loss": 0.001, "step": 2295 }, { "epoch": 12.83, "learning_rate": 1.6943212513225344e-05, "loss": 0.0007, "step": 2296 }, { "epoch": 12.83, "learning_rate": 1.6940683119357522e-05, "loss": 0.0012, "step": 2297 }, { "epoch": 12.84, "learning_rate": 1.693815286839873e-05, "loss": 0.0022, "step": 2298 }, { "epoch": 12.84, "learning_rate": 1.6935621760661416e-05, "loss": 0.0044, "step": 2299 }, { "epoch": 12.85, "learning_rate": 1.693308979645815e-05, "loss": 0.002, "step": 2300 } ], "logging_steps": 1.0, "max_steps": 8950, "num_input_tokens_seen": 0, "num_train_epochs": 50, "save_steps": 100, "total_flos": 3.735091242860544e+17, "train_batch_size": 8, "trial_name": null, "trial_params": null }