{ "best_metric": null, "best_model_checkpoint": null, "epoch": 0.9996349920914953, "eval_steps": 500, "global_step": 2054, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 1.6129032258064518e-07, "loss": 1.2192, "step": 1 }, { "epoch": 0.0, "learning_rate": 3.2258064516129035e-07, "loss": 1.2549, "step": 2 }, { "epoch": 0.0, "learning_rate": 4.838709677419355e-07, "loss": 1.1563, "step": 3 }, { "epoch": 0.0, "learning_rate": 6.451612903225807e-07, "loss": 1.1978, "step": 4 }, { "epoch": 0.0, "learning_rate": 8.064516129032258e-07, "loss": 1.2201, "step": 5 }, { "epoch": 0.0, "learning_rate": 9.67741935483871e-07, "loss": 1.1278, "step": 6 }, { "epoch": 0.0, "learning_rate": 1.1290322580645162e-06, "loss": 1.1482, "step": 7 }, { "epoch": 0.0, "learning_rate": 1.2903225806451614e-06, "loss": 0.9564, "step": 8 }, { "epoch": 0.0, "learning_rate": 1.4516129032258066e-06, "loss": 0.9481, "step": 9 }, { "epoch": 0.0, "learning_rate": 1.6129032258064516e-06, "loss": 0.9288, "step": 10 }, { "epoch": 0.01, "learning_rate": 1.774193548387097e-06, "loss": 0.9088, "step": 11 }, { "epoch": 0.01, "learning_rate": 1.935483870967742e-06, "loss": 0.8557, "step": 12 }, { "epoch": 0.01, "learning_rate": 2.096774193548387e-06, "loss": 0.8403, "step": 13 }, { "epoch": 0.01, "learning_rate": 2.2580645161290324e-06, "loss": 0.751, "step": 14 }, { "epoch": 0.01, "learning_rate": 2.4193548387096776e-06, "loss": 0.9037, "step": 15 }, { "epoch": 0.01, "learning_rate": 2.580645161290323e-06, "loss": 0.8176, "step": 16 }, { "epoch": 0.01, "learning_rate": 2.7419354838709676e-06, "loss": 0.7528, "step": 17 }, { "epoch": 0.01, "learning_rate": 2.903225806451613e-06, "loss": 0.7913, "step": 18 }, { "epoch": 0.01, "learning_rate": 3.0645161290322584e-06, "loss": 0.8018, "step": 19 }, { "epoch": 0.01, "learning_rate": 3.225806451612903e-06, "loss": 0.7531, "step": 20 }, { "epoch": 0.01, "learning_rate": 3.3870967741935484e-06, "loss": 0.709, "step": 21 }, { "epoch": 0.01, "learning_rate": 3.548387096774194e-06, "loss": 0.7455, "step": 22 }, { "epoch": 0.01, "learning_rate": 3.7096774193548392e-06, "loss": 0.7451, "step": 23 }, { "epoch": 0.01, "learning_rate": 3.870967741935484e-06, "loss": 0.6992, "step": 24 }, { "epoch": 0.01, "learning_rate": 4.032258064516129e-06, "loss": 0.7457, "step": 25 }, { "epoch": 0.01, "learning_rate": 4.193548387096774e-06, "loss": 0.7241, "step": 26 }, { "epoch": 0.01, "learning_rate": 4.35483870967742e-06, "loss": 0.8908, "step": 27 }, { "epoch": 0.01, "learning_rate": 4.516129032258065e-06, "loss": 0.7218, "step": 28 }, { "epoch": 0.01, "learning_rate": 4.67741935483871e-06, "loss": 0.7497, "step": 29 }, { "epoch": 0.01, "learning_rate": 4.838709677419355e-06, "loss": 0.64, "step": 30 }, { "epoch": 0.02, "learning_rate": 5e-06, "loss": 0.7045, "step": 31 }, { "epoch": 0.02, "learning_rate": 5.161290322580646e-06, "loss": 0.7464, "step": 32 }, { "epoch": 0.02, "learning_rate": 5.322580645161291e-06, "loss": 0.7223, "step": 33 }, { "epoch": 0.02, "learning_rate": 5.483870967741935e-06, "loss": 0.6487, "step": 34 }, { "epoch": 0.02, "learning_rate": 5.645161290322582e-06, "loss": 0.6197, "step": 35 }, { "epoch": 0.02, "learning_rate": 5.806451612903226e-06, "loss": 0.7225, "step": 36 }, { "epoch": 0.02, "learning_rate": 5.967741935483872e-06, "loss": 0.6427, "step": 37 }, { "epoch": 0.02, "learning_rate": 6.129032258064517e-06, "loss": 0.6769, "step": 38 }, { "epoch": 0.02, "learning_rate": 6.290322580645162e-06, "loss": 0.7286, "step": 39 }, { "epoch": 0.02, "learning_rate": 6.451612903225806e-06, "loss": 0.7176, "step": 40 }, { "epoch": 0.02, "learning_rate": 6.612903225806452e-06, "loss": 0.702, "step": 41 }, { "epoch": 0.02, "learning_rate": 6.774193548387097e-06, "loss": 0.6459, "step": 42 }, { "epoch": 0.02, "learning_rate": 6.935483870967743e-06, "loss": 0.756, "step": 43 }, { "epoch": 0.02, "learning_rate": 7.096774193548388e-06, "loss": 0.6248, "step": 44 }, { "epoch": 0.02, "learning_rate": 7.258064516129033e-06, "loss": 0.6914, "step": 45 }, { "epoch": 0.02, "learning_rate": 7.4193548387096784e-06, "loss": 0.607, "step": 46 }, { "epoch": 0.02, "learning_rate": 7.580645161290323e-06, "loss": 0.9036, "step": 47 }, { "epoch": 0.02, "learning_rate": 7.741935483870968e-06, "loss": 0.6217, "step": 48 }, { "epoch": 0.02, "learning_rate": 7.903225806451613e-06, "loss": 0.6352, "step": 49 }, { "epoch": 0.02, "learning_rate": 8.064516129032258e-06, "loss": 0.6662, "step": 50 }, { "epoch": 0.02, "learning_rate": 8.225806451612904e-06, "loss": 0.6603, "step": 51 }, { "epoch": 0.03, "learning_rate": 8.387096774193549e-06, "loss": 0.6192, "step": 52 }, { "epoch": 0.03, "learning_rate": 8.548387096774194e-06, "loss": 0.6103, "step": 53 }, { "epoch": 0.03, "learning_rate": 8.70967741935484e-06, "loss": 0.655, "step": 54 }, { "epoch": 0.03, "learning_rate": 8.870967741935484e-06, "loss": 0.7075, "step": 55 }, { "epoch": 0.03, "learning_rate": 9.03225806451613e-06, "loss": 0.6654, "step": 56 }, { "epoch": 0.03, "learning_rate": 9.193548387096775e-06, "loss": 0.6309, "step": 57 }, { "epoch": 0.03, "learning_rate": 9.35483870967742e-06, "loss": 0.6893, "step": 58 }, { "epoch": 0.03, "learning_rate": 9.516129032258065e-06, "loss": 0.5963, "step": 59 }, { "epoch": 0.03, "learning_rate": 9.67741935483871e-06, "loss": 0.6744, "step": 60 }, { "epoch": 0.03, "learning_rate": 9.838709677419356e-06, "loss": 0.616, "step": 61 }, { "epoch": 0.03, "learning_rate": 1e-05, "loss": 0.6382, "step": 62 }, { "epoch": 0.03, "learning_rate": 9.999993781852842e-06, "loss": 0.5995, "step": 63 }, { "epoch": 0.03, "learning_rate": 9.999975127426831e-06, "loss": 0.5284, "step": 64 }, { "epoch": 0.03, "learning_rate": 9.999944036768366e-06, "loss": 0.6292, "step": 65 }, { "epoch": 0.03, "learning_rate": 9.999900509954779e-06, "loss": 0.5777, "step": 66 }, { "epoch": 0.03, "learning_rate": 9.999844547094331e-06, "loss": 0.6005, "step": 67 }, { "epoch": 0.03, "learning_rate": 9.999776148326216e-06, "loss": 0.6289, "step": 68 }, { "epoch": 0.03, "learning_rate": 9.99969531382056e-06, "loss": 0.6439, "step": 69 }, { "epoch": 0.03, "learning_rate": 9.99960204377842e-06, "loss": 0.6932, "step": 70 }, { "epoch": 0.03, "learning_rate": 9.999496338431782e-06, "loss": 0.5347, "step": 71 }, { "epoch": 0.04, "learning_rate": 9.999378198043561e-06, "loss": 0.5908, "step": 72 }, { "epoch": 0.04, "learning_rate": 9.999247622907607e-06, "loss": 0.5918, "step": 73 }, { "epoch": 0.04, "learning_rate": 9.99910461334869e-06, "loss": 0.5778, "step": 74 }, { "epoch": 0.04, "learning_rate": 9.998949169722513e-06, "loss": 0.6101, "step": 75 }, { "epoch": 0.04, "learning_rate": 9.998781292415705e-06, "loss": 0.5706, "step": 76 }, { "epoch": 0.04, "learning_rate": 9.998600981845821e-06, "loss": 0.5847, "step": 77 }, { "epoch": 0.04, "learning_rate": 9.99840823846134e-06, "loss": 0.559, "step": 78 }, { "epoch": 0.04, "learning_rate": 9.99820306274166e-06, "loss": 0.6115, "step": 79 }, { "epoch": 0.04, "learning_rate": 9.997985455197114e-06, "loss": 0.5509, "step": 80 }, { "epoch": 0.04, "learning_rate": 9.997755416368943e-06, "loss": 0.5759, "step": 81 }, { "epoch": 0.04, "learning_rate": 9.997512946829314e-06, "loss": 0.5567, "step": 82 }, { "epoch": 0.04, "learning_rate": 9.997258047181312e-06, "loss": 0.5872, "step": 83 }, { "epoch": 0.04, "learning_rate": 9.996990718058939e-06, "loss": 0.5672, "step": 84 }, { "epoch": 0.04, "learning_rate": 9.99671096012711e-06, "loss": 0.6317, "step": 85 }, { "epoch": 0.04, "learning_rate": 9.996418774081658e-06, "loss": 0.5388, "step": 86 }, { "epoch": 0.04, "learning_rate": 9.996114160649323e-06, "loss": 0.5394, "step": 87 }, { "epoch": 0.04, "learning_rate": 9.995797120587758e-06, "loss": 0.5859, "step": 88 }, { "epoch": 0.04, "learning_rate": 9.995467654685525e-06, "loss": 0.5926, "step": 89 }, { "epoch": 0.04, "learning_rate": 9.995125763762089e-06, "loss": 0.5791, "step": 90 }, { "epoch": 0.04, "learning_rate": 9.994771448667823e-06, "loss": 0.5439, "step": 91 }, { "epoch": 0.04, "learning_rate": 9.994404710283999e-06, "loss": 0.5735, "step": 92 }, { "epoch": 0.05, "learning_rate": 9.994025549522792e-06, "loss": 0.5857, "step": 93 }, { "epoch": 0.05, "learning_rate": 9.99363396732727e-06, "loss": 0.486, "step": 94 }, { "epoch": 0.05, "learning_rate": 9.9932299646714e-06, "loss": 0.5475, "step": 95 }, { "epoch": 0.05, "learning_rate": 9.992813542560045e-06, "loss": 0.5374, "step": 96 }, { "epoch": 0.05, "learning_rate": 9.992384702028952e-06, "loss": 0.6348, "step": 97 }, { "epoch": 0.05, "learning_rate": 9.991943444144758e-06, "loss": 0.6051, "step": 98 }, { "epoch": 0.05, "learning_rate": 9.991489770004985e-06, "loss": 0.8908, "step": 99 }, { "epoch": 0.05, "learning_rate": 9.99102368073804e-06, "loss": 0.5701, "step": 100 }, { "epoch": 0.05, "learning_rate": 9.990545177503203e-06, "loss": 0.6349, "step": 101 }, { "epoch": 0.05, "learning_rate": 9.990054261490643e-06, "loss": 0.5175, "step": 102 }, { "epoch": 0.05, "learning_rate": 9.98955093392139e-06, "loss": 0.5489, "step": 103 }, { "epoch": 0.05, "learning_rate": 9.989035196047349e-06, "loss": 0.5223, "step": 104 }, { "epoch": 0.05, "learning_rate": 9.9885070491513e-06, "loss": 0.5839, "step": 105 }, { "epoch": 0.05, "learning_rate": 9.987966494546873e-06, "loss": 0.518, "step": 106 }, { "epoch": 0.05, "learning_rate": 9.987413533578574e-06, "loss": 0.6071, "step": 107 }, { "epoch": 0.05, "learning_rate": 9.986848167621754e-06, "loss": 0.6279, "step": 108 }, { "epoch": 0.05, "learning_rate": 9.98627039808263e-06, "loss": 0.5792, "step": 109 }, { "epoch": 0.05, "learning_rate": 9.985680226398261e-06, "loss": 0.557, "step": 110 }, { "epoch": 0.05, "learning_rate": 9.985077654036559e-06, "loss": 0.5534, "step": 111 }, { "epoch": 0.05, "learning_rate": 9.984462682496274e-06, "loss": 0.5512, "step": 112 }, { "epoch": 0.05, "learning_rate": 9.983835313307003e-06, "loss": 0.5778, "step": 113 }, { "epoch": 0.06, "learning_rate": 9.983195548029173e-06, "loss": 0.5676, "step": 114 }, { "epoch": 0.06, "learning_rate": 9.982543388254047e-06, "loss": 0.5338, "step": 115 }, { "epoch": 0.06, "learning_rate": 9.981878835603718e-06, "loss": 0.513, "step": 116 }, { "epoch": 0.06, "learning_rate": 9.981201891731094e-06, "loss": 0.6279, "step": 117 }, { "epoch": 0.06, "learning_rate": 9.980512558319915e-06, "loss": 0.5986, "step": 118 }, { "epoch": 0.06, "learning_rate": 9.979810837084731e-06, "loss": 0.5036, "step": 119 }, { "epoch": 0.06, "learning_rate": 9.979096729770902e-06, "loss": 0.5615, "step": 120 }, { "epoch": 0.06, "learning_rate": 9.9783702381546e-06, "loss": 0.5644, "step": 121 }, { "epoch": 0.06, "learning_rate": 9.977631364042796e-06, "loss": 0.4897, "step": 122 }, { "epoch": 0.06, "learning_rate": 9.976880109273262e-06, "loss": 0.5298, "step": 123 }, { "epoch": 0.06, "learning_rate": 9.976116475714564e-06, "loss": 0.51, "step": 124 }, { "epoch": 0.06, "learning_rate": 9.975340465266054e-06, "loss": 0.5544, "step": 125 }, { "epoch": 0.06, "learning_rate": 9.974552079857873e-06, "loss": 0.5427, "step": 126 }, { "epoch": 0.06, "learning_rate": 9.973751321450937e-06, "loss": 0.4933, "step": 127 }, { "epoch": 0.06, "learning_rate": 9.972938192036945e-06, "loss": 0.5339, "step": 128 }, { "epoch": 0.06, "learning_rate": 9.972112693638354e-06, "loss": 0.5079, "step": 129 }, { "epoch": 0.06, "learning_rate": 9.971274828308396e-06, "loss": 0.4958, "step": 130 }, { "epoch": 0.06, "learning_rate": 9.970424598131056e-06, "loss": 0.5077, "step": 131 }, { "epoch": 0.06, "learning_rate": 9.96956200522108e-06, "loss": 0.515, "step": 132 }, { "epoch": 0.06, "learning_rate": 9.968687051723958e-06, "loss": 0.5094, "step": 133 }, { "epoch": 0.07, "learning_rate": 9.967799739815925e-06, "loss": 0.5074, "step": 134 }, { "epoch": 0.07, "learning_rate": 9.966900071703957e-06, "loss": 0.5735, "step": 135 }, { "epoch": 0.07, "learning_rate": 9.965988049625763e-06, "loss": 0.5219, "step": 136 }, { "epoch": 0.07, "learning_rate": 9.965063675849773e-06, "loss": 0.5257, "step": 137 }, { "epoch": 0.07, "learning_rate": 9.964126952675148e-06, "loss": 0.5626, "step": 138 }, { "epoch": 0.07, "learning_rate": 9.96317788243176e-06, "loss": 0.5492, "step": 139 }, { "epoch": 0.07, "learning_rate": 9.962216467480192e-06, "loss": 0.5007, "step": 140 }, { "epoch": 0.07, "learning_rate": 9.961242710211733e-06, "loss": 0.5354, "step": 141 }, { "epoch": 0.07, "learning_rate": 9.960256613048367e-06, "loss": 0.5776, "step": 142 }, { "epoch": 0.07, "learning_rate": 9.959258178442774e-06, "loss": 0.5423, "step": 143 }, { "epoch": 0.07, "learning_rate": 9.958247408878322e-06, "loss": 0.5187, "step": 144 }, { "epoch": 0.07, "learning_rate": 9.957224306869053e-06, "loss": 0.4584, "step": 145 }, { "epoch": 0.07, "learning_rate": 9.956188874959686e-06, "loss": 0.4735, "step": 146 }, { "epoch": 0.07, "learning_rate": 9.955141115725613e-06, "loss": 0.5672, "step": 147 }, { "epoch": 0.07, "learning_rate": 9.954081031772878e-06, "loss": 0.475, "step": 148 }, { "epoch": 0.07, "learning_rate": 9.953008625738186e-06, "loss": 0.4807, "step": 149 }, { "epoch": 0.07, "learning_rate": 9.951923900288888e-06, "loss": 0.5423, "step": 150 }, { "epoch": 0.07, "learning_rate": 9.950826858122978e-06, "loss": 0.5453, "step": 151 }, { "epoch": 0.07, "learning_rate": 9.94971750196908e-06, "loss": 0.5321, "step": 152 }, { "epoch": 0.07, "learning_rate": 9.948595834586457e-06, "loss": 0.5081, "step": 153 }, { "epoch": 0.07, "learning_rate": 9.947461858764978e-06, "loss": 0.51, "step": 154 }, { "epoch": 0.08, "learning_rate": 9.94631557732514e-06, "loss": 0.5757, "step": 155 }, { "epoch": 0.08, "learning_rate": 9.945156993118042e-06, "loss": 0.4723, "step": 156 }, { "epoch": 0.08, "learning_rate": 9.943986109025378e-06, "loss": 0.4643, "step": 157 }, { "epoch": 0.08, "learning_rate": 9.942802927959444e-06, "loss": 0.5472, "step": 158 }, { "epoch": 0.08, "learning_rate": 9.941607452863115e-06, "loss": 0.461, "step": 159 }, { "epoch": 0.08, "learning_rate": 9.940399686709849e-06, "loss": 0.5274, "step": 160 }, { "epoch": 0.08, "learning_rate": 9.939179632503673e-06, "loss": 0.5336, "step": 161 }, { "epoch": 0.08, "learning_rate": 9.937947293279178e-06, "loss": 0.5426, "step": 162 }, { "epoch": 0.08, "learning_rate": 9.936702672101509e-06, "loss": 0.4796, "step": 163 }, { "epoch": 0.08, "learning_rate": 9.935445772066362e-06, "loss": 0.569, "step": 164 }, { "epoch": 0.08, "learning_rate": 9.93417659629997e-06, "loss": 0.5274, "step": 165 }, { "epoch": 0.08, "learning_rate": 9.932895147959106e-06, "loss": 0.5466, "step": 166 }, { "epoch": 0.08, "learning_rate": 9.931601430231062e-06, "loss": 0.5335, "step": 167 }, { "epoch": 0.08, "learning_rate": 9.930295446333649e-06, "loss": 0.434, "step": 168 }, { "epoch": 0.08, "learning_rate": 9.928977199515187e-06, "loss": 0.5151, "step": 169 }, { "epoch": 0.08, "learning_rate": 9.927646693054498e-06, "loss": 0.5232, "step": 170 }, { "epoch": 0.08, "learning_rate": 9.926303930260892e-06, "loss": 0.5602, "step": 171 }, { "epoch": 0.08, "learning_rate": 9.924948914474173e-06, "loss": 0.4751, "step": 172 }, { "epoch": 0.08, "learning_rate": 9.923581649064612e-06, "loss": 0.4729, "step": 173 }, { "epoch": 0.08, "learning_rate": 9.922202137432954e-06, "loss": 0.467, "step": 174 }, { "epoch": 0.09, "learning_rate": 9.920810383010402e-06, "loss": 0.4456, "step": 175 }, { "epoch": 0.09, "learning_rate": 9.919406389258607e-06, "loss": 0.4587, "step": 176 }, { "epoch": 0.09, "learning_rate": 9.91799015966967e-06, "loss": 0.4901, "step": 177 }, { "epoch": 0.09, "learning_rate": 9.916561697766114e-06, "loss": 0.4539, "step": 178 }, { "epoch": 0.09, "learning_rate": 9.9151210071009e-06, "loss": 0.468, "step": 179 }, { "epoch": 0.09, "learning_rate": 9.91366809125739e-06, "loss": 0.5305, "step": 180 }, { "epoch": 0.09, "learning_rate": 9.91220295384937e-06, "loss": 0.4561, "step": 181 }, { "epoch": 0.09, "learning_rate": 9.910725598521014e-06, "loss": 0.4869, "step": 182 }, { "epoch": 0.09, "learning_rate": 9.909236028946885e-06, "loss": 0.4663, "step": 183 }, { "epoch": 0.09, "learning_rate": 9.90773424883193e-06, "loss": 0.483, "step": 184 }, { "epoch": 0.09, "learning_rate": 9.906220261911466e-06, "loss": 0.5987, "step": 185 }, { "epoch": 0.09, "learning_rate": 9.904694071951167e-06, "loss": 0.4902, "step": 186 }, { "epoch": 0.09, "learning_rate": 9.903155682747064e-06, "loss": 0.4654, "step": 187 }, { "epoch": 0.09, "learning_rate": 9.901605098125528e-06, "loss": 0.5312, "step": 188 }, { "epoch": 0.09, "learning_rate": 9.90004232194327e-06, "loss": 0.4353, "step": 189 }, { "epoch": 0.09, "learning_rate": 9.89846735808731e-06, "loss": 0.5043, "step": 190 }, { "epoch": 0.09, "learning_rate": 9.896880210474998e-06, "loss": 0.5292, "step": 191 }, { "epoch": 0.09, "learning_rate": 9.895280883053977e-06, "loss": 0.4994, "step": 192 }, { "epoch": 0.09, "learning_rate": 9.89366937980219e-06, "loss": 0.4957, "step": 193 }, { "epoch": 0.09, "learning_rate": 9.892045704727864e-06, "loss": 0.4813, "step": 194 }, { "epoch": 0.09, "learning_rate": 9.890409861869497e-06, "loss": 0.5544, "step": 195 }, { "epoch": 0.1, "learning_rate": 9.888761855295855e-06, "loss": 0.4459, "step": 196 }, { "epoch": 0.1, "learning_rate": 9.887101689105956e-06, "loss": 0.5208, "step": 197 }, { "epoch": 0.1, "learning_rate": 9.885429367429062e-06, "loss": 0.5078, "step": 198 }, { "epoch": 0.1, "learning_rate": 9.883744894424671e-06, "loss": 0.5022, "step": 199 }, { "epoch": 0.1, "learning_rate": 9.882048274282505e-06, "loss": 0.4818, "step": 200 }, { "epoch": 0.1, "learning_rate": 9.880339511222496e-06, "loss": 0.4821, "step": 201 }, { "epoch": 0.1, "learning_rate": 9.878618609494781e-06, "loss": 0.5142, "step": 202 }, { "epoch": 0.1, "learning_rate": 9.876885573379686e-06, "loss": 0.4627, "step": 203 }, { "epoch": 0.1, "learning_rate": 9.875140407187722e-06, "loss": 0.5167, "step": 204 }, { "epoch": 0.1, "learning_rate": 9.873383115259569e-06, "loss": 0.5337, "step": 205 }, { "epoch": 0.1, "learning_rate": 9.871613701966067e-06, "loss": 0.5457, "step": 206 }, { "epoch": 0.1, "learning_rate": 9.869832171708204e-06, "loss": 0.5306, "step": 207 }, { "epoch": 0.1, "learning_rate": 9.86803852891711e-06, "loss": 0.5647, "step": 208 }, { "epoch": 0.1, "learning_rate": 9.866232778054035e-06, "loss": 0.4668, "step": 209 }, { "epoch": 0.1, "learning_rate": 9.86441492361035e-06, "loss": 0.4946, "step": 210 }, { "epoch": 0.1, "learning_rate": 9.86258497010753e-06, "loss": 0.5468, "step": 211 }, { "epoch": 0.1, "learning_rate": 9.860742922097141e-06, "loss": 0.5078, "step": 212 }, { "epoch": 0.1, "learning_rate": 9.858888784160838e-06, "loss": 0.4835, "step": 213 }, { "epoch": 0.1, "learning_rate": 9.857022560910338e-06, "loss": 0.4838, "step": 214 }, { "epoch": 0.1, "learning_rate": 9.855144256987423e-06, "loss": 0.48, "step": 215 }, { "epoch": 0.11, "learning_rate": 9.853253877063922e-06, "loss": 0.4167, "step": 216 }, { "epoch": 0.11, "learning_rate": 9.851351425841697e-06, "loss": 0.5529, "step": 217 }, { "epoch": 0.11, "learning_rate": 9.849436908052636e-06, "loss": 0.468, "step": 218 }, { "epoch": 0.11, "learning_rate": 9.847510328458644e-06, "loss": 0.4922, "step": 219 }, { "epoch": 0.11, "learning_rate": 9.84557169185162e-06, "loss": 0.4475, "step": 220 }, { "epoch": 0.11, "learning_rate": 9.843621003053456e-06, "loss": 0.5408, "step": 221 }, { "epoch": 0.11, "learning_rate": 9.84165826691602e-06, "loss": 0.4252, "step": 222 }, { "epoch": 0.11, "learning_rate": 9.839683488321145e-06, "loss": 0.4622, "step": 223 }, { "epoch": 0.11, "learning_rate": 9.837696672180618e-06, "loss": 0.4871, "step": 224 }, { "epoch": 0.11, "learning_rate": 9.835697823436163e-06, "loss": 0.4572, "step": 225 }, { "epoch": 0.11, "learning_rate": 9.833686947059436e-06, "loss": 0.47, "step": 226 }, { "epoch": 0.11, "learning_rate": 9.831664048052004e-06, "loss": 0.5276, "step": 227 }, { "epoch": 0.11, "learning_rate": 9.829629131445342e-06, "loss": 0.536, "step": 228 }, { "epoch": 0.11, "learning_rate": 9.827582202300815e-06, "loss": 0.4515, "step": 229 }, { "epoch": 0.11, "learning_rate": 9.825523265709667e-06, "loss": 0.4938, "step": 230 }, { "epoch": 0.11, "learning_rate": 9.823452326793004e-06, "loss": 0.4746, "step": 231 }, { "epoch": 0.11, "learning_rate": 9.82136939070179e-06, "loss": 0.8869, "step": 232 }, { "epoch": 0.11, "learning_rate": 9.81927446261682e-06, "loss": 0.5178, "step": 233 }, { "epoch": 0.11, "learning_rate": 9.817167547748729e-06, "loss": 0.4654, "step": 234 }, { "epoch": 0.11, "learning_rate": 9.815048651337956e-06, "loss": 0.4724, "step": 235 }, { "epoch": 0.11, "learning_rate": 9.81291777865475e-06, "loss": 0.4804, "step": 236 }, { "epoch": 0.12, "learning_rate": 9.810774934999136e-06, "loss": 0.474, "step": 237 }, { "epoch": 0.12, "learning_rate": 9.808620125700925e-06, "loss": 0.5092, "step": 238 }, { "epoch": 0.12, "learning_rate": 9.806453356119685e-06, "loss": 0.547, "step": 239 }, { "epoch": 0.12, "learning_rate": 9.80427463164473e-06, "loss": 0.4633, "step": 240 }, { "epoch": 0.12, "learning_rate": 9.802083957695116e-06, "loss": 0.5792, "step": 241 }, { "epoch": 0.12, "learning_rate": 9.799881339719615e-06, "loss": 0.5717, "step": 242 }, { "epoch": 0.12, "learning_rate": 9.797666783196707e-06, "loss": 0.415, "step": 243 }, { "epoch": 0.12, "learning_rate": 9.795440293634566e-06, "loss": 0.5049, "step": 244 }, { "epoch": 0.12, "learning_rate": 9.793201876571052e-06, "loss": 0.4911, "step": 245 }, { "epoch": 0.12, "learning_rate": 9.790951537573686e-06, "loss": 0.4253, "step": 246 }, { "epoch": 0.12, "learning_rate": 9.78868928223964e-06, "loss": 0.4638, "step": 247 }, { "epoch": 0.12, "learning_rate": 9.786415116195733e-06, "loss": 0.5037, "step": 248 }, { "epoch": 0.12, "learning_rate": 9.784129045098405e-06, "loss": 0.4331, "step": 249 }, { "epoch": 0.12, "learning_rate": 9.781831074633703e-06, "loss": 0.5047, "step": 250 }, { "epoch": 0.12, "learning_rate": 9.779521210517277e-06, "loss": 0.5233, "step": 251 }, { "epoch": 0.12, "learning_rate": 9.777199458494356e-06, "loss": 0.5078, "step": 252 }, { "epoch": 0.12, "learning_rate": 9.774865824339738e-06, "loss": 0.4757, "step": 253 }, { "epoch": 0.12, "learning_rate": 9.772520313857777e-06, "loss": 0.4705, "step": 254 }, { "epoch": 0.12, "learning_rate": 9.770162932882363e-06, "loss": 0.4567, "step": 255 }, { "epoch": 0.12, "learning_rate": 9.767793687276913e-06, "loss": 0.4509, "step": 256 }, { "epoch": 0.13, "learning_rate": 9.765412582934355e-06, "loss": 0.4983, "step": 257 }, { "epoch": 0.13, "learning_rate": 9.763019625777111e-06, "loss": 0.4668, "step": 258 }, { "epoch": 0.13, "learning_rate": 9.760614821757085e-06, "loss": 0.4284, "step": 259 }, { "epoch": 0.13, "learning_rate": 9.758198176855648e-06, "loss": 0.6037, "step": 260 }, { "epoch": 0.13, "learning_rate": 9.75576969708362e-06, "loss": 0.5167, "step": 261 }, { "epoch": 0.13, "learning_rate": 9.753329388481261e-06, "loss": 0.4794, "step": 262 }, { "epoch": 0.13, "learning_rate": 9.750877257118248e-06, "loss": 0.4821, "step": 263 }, { "epoch": 0.13, "learning_rate": 9.748413309093666e-06, "loss": 0.5635, "step": 264 }, { "epoch": 0.13, "learning_rate": 9.745937550535993e-06, "loss": 0.4534, "step": 265 }, { "epoch": 0.13, "learning_rate": 9.743449987603082e-06, "loss": 0.5183, "step": 266 }, { "epoch": 0.13, "learning_rate": 9.740950626482146e-06, "loss": 0.5157, "step": 267 }, { "epoch": 0.13, "learning_rate": 9.738439473389743e-06, "loss": 0.4602, "step": 268 }, { "epoch": 0.13, "learning_rate": 9.735916534571758e-06, "loss": 0.5344, "step": 269 }, { "epoch": 0.13, "learning_rate": 9.733381816303395e-06, "loss": 0.5232, "step": 270 }, { "epoch": 0.13, "learning_rate": 9.730835324889156e-06, "loss": 0.5116, "step": 271 }, { "epoch": 0.13, "learning_rate": 9.728277066662821e-06, "loss": 0.4966, "step": 272 }, { "epoch": 0.13, "learning_rate": 9.725707047987445e-06, "loss": 0.4792, "step": 273 }, { "epoch": 0.13, "learning_rate": 9.723125275255325e-06, "loss": 0.4423, "step": 274 }, { "epoch": 0.13, "learning_rate": 9.720531754888002e-06, "loss": 0.4348, "step": 275 }, { "epoch": 0.13, "learning_rate": 9.717926493336227e-06, "loss": 0.5003, "step": 276 }, { "epoch": 0.13, "learning_rate": 9.715309497079967e-06, "loss": 0.4557, "step": 277 }, { "epoch": 0.14, "learning_rate": 9.712680772628365e-06, "loss": 0.5306, "step": 278 }, { "epoch": 0.14, "learning_rate": 9.710040326519739e-06, "loss": 0.4837, "step": 279 }, { "epoch": 0.14, "learning_rate": 9.707388165321563e-06, "loss": 0.4841, "step": 280 }, { "epoch": 0.14, "learning_rate": 9.70472429563045e-06, "loss": 0.4443, "step": 281 }, { "epoch": 0.14, "learning_rate": 9.702048724072128e-06, "loss": 0.4825, "step": 282 }, { "epoch": 0.14, "learning_rate": 9.699361457301444e-06, "loss": 0.469, "step": 283 }, { "epoch": 0.14, "learning_rate": 9.69666250200232e-06, "loss": 0.4958, "step": 284 }, { "epoch": 0.14, "learning_rate": 9.693951864887758e-06, "loss": 0.4519, "step": 285 }, { "epoch": 0.14, "learning_rate": 9.691229552699817e-06, "loss": 0.5098, "step": 286 }, { "epoch": 0.14, "learning_rate": 9.688495572209587e-06, "loss": 0.4441, "step": 287 }, { "epoch": 0.14, "learning_rate": 9.68574993021719e-06, "loss": 0.4747, "step": 288 }, { "epoch": 0.14, "learning_rate": 9.682992633551744e-06, "loss": 0.404, "step": 289 }, { "epoch": 0.14, "learning_rate": 9.680223689071364e-06, "loss": 0.546, "step": 290 }, { "epoch": 0.14, "learning_rate": 9.67744310366313e-06, "loss": 0.4115, "step": 291 }, { "epoch": 0.14, "learning_rate": 9.674650884243076e-06, "loss": 0.5182, "step": 292 }, { "epoch": 0.14, "learning_rate": 9.671847037756177e-06, "loss": 0.445, "step": 293 }, { "epoch": 0.14, "learning_rate": 9.669031571176322e-06, "loss": 0.4286, "step": 294 }, { "epoch": 0.14, "learning_rate": 9.666204491506309e-06, "loss": 0.4513, "step": 295 }, { "epoch": 0.14, "learning_rate": 9.663365805777815e-06, "loss": 0.4618, "step": 296 }, { "epoch": 0.14, "learning_rate": 9.660515521051385e-06, "loss": 0.4855, "step": 297 }, { "epoch": 0.15, "learning_rate": 9.657653644416417e-06, "loss": 0.4997, "step": 298 }, { "epoch": 0.15, "learning_rate": 9.65478018299114e-06, "loss": 0.5084, "step": 299 }, { "epoch": 0.15, "learning_rate": 9.651895143922591e-06, "loss": 0.4394, "step": 300 }, { "epoch": 0.15, "learning_rate": 9.648998534386615e-06, "loss": 0.4818, "step": 301 }, { "epoch": 0.15, "learning_rate": 9.646090361587828e-06, "loss": 0.4316, "step": 302 }, { "epoch": 0.15, "learning_rate": 9.643170632759606e-06, "loss": 0.4655, "step": 303 }, { "epoch": 0.15, "learning_rate": 9.640239355164074e-06, "loss": 0.4085, "step": 304 }, { "epoch": 0.15, "learning_rate": 9.637296536092076e-06, "loss": 0.4677, "step": 305 }, { "epoch": 0.15, "learning_rate": 9.634342182863163e-06, "loss": 0.4164, "step": 306 }, { "epoch": 0.15, "learning_rate": 9.631376302825581e-06, "loss": 0.4813, "step": 307 }, { "epoch": 0.15, "learning_rate": 9.628398903356239e-06, "loss": 0.4663, "step": 308 }, { "epoch": 0.15, "learning_rate": 9.625409991860701e-06, "loss": 0.4424, "step": 309 }, { "epoch": 0.15, "learning_rate": 9.622409575773162e-06, "loss": 0.494, "step": 310 }, { "epoch": 0.15, "learning_rate": 9.619397662556434e-06, "loss": 0.4842, "step": 311 }, { "epoch": 0.15, "learning_rate": 9.616374259701927e-06, "loss": 0.4723, "step": 312 }, { "epoch": 0.15, "learning_rate": 9.613339374729622e-06, "loss": 0.5415, "step": 313 }, { "epoch": 0.15, "learning_rate": 9.610293015188067e-06, "loss": 0.4394, "step": 314 }, { "epoch": 0.15, "learning_rate": 9.607235188654348e-06, "loss": 0.4223, "step": 315 }, { "epoch": 0.15, "learning_rate": 9.604165902734069e-06, "loss": 0.416, "step": 316 }, { "epoch": 0.15, "learning_rate": 9.601085165061337e-06, "loss": 0.4437, "step": 317 }, { "epoch": 0.15, "learning_rate": 9.597992983298748e-06, "loss": 0.4749, "step": 318 }, { "epoch": 0.16, "learning_rate": 9.594889365137354e-06, "loss": 0.4145, "step": 319 }, { "epoch": 0.16, "learning_rate": 9.591774318296661e-06, "loss": 0.5126, "step": 320 }, { "epoch": 0.16, "learning_rate": 9.588647850524595e-06, "loss": 0.4154, "step": 321 }, { "epoch": 0.16, "learning_rate": 9.585509969597491e-06, "loss": 0.5082, "step": 322 }, { "epoch": 0.16, "learning_rate": 9.58236068332007e-06, "loss": 0.4945, "step": 323 }, { "epoch": 0.16, "learning_rate": 9.579199999525424e-06, "loss": 0.3587, "step": 324 }, { "epoch": 0.16, "learning_rate": 9.57602792607499e-06, "loss": 0.4053, "step": 325 }, { "epoch": 0.16, "learning_rate": 9.572844470858537e-06, "loss": 0.4756, "step": 326 }, { "epoch": 0.16, "learning_rate": 9.569649641794141e-06, "loss": 0.4666, "step": 327 }, { "epoch": 0.16, "learning_rate": 9.566443446828172e-06, "loss": 0.5079, "step": 328 }, { "epoch": 0.16, "learning_rate": 9.563225893935264e-06, "loss": 0.4539, "step": 329 }, { "epoch": 0.16, "learning_rate": 9.559996991118304e-06, "loss": 0.4166, "step": 330 }, { "epoch": 0.16, "learning_rate": 9.556756746408409e-06, "loss": 0.5392, "step": 331 }, { "epoch": 0.16, "learning_rate": 9.55350516786491e-06, "loss": 0.4721, "step": 332 }, { "epoch": 0.16, "learning_rate": 9.550242263575318e-06, "loss": 0.3855, "step": 333 }, { "epoch": 0.16, "learning_rate": 9.546968041655326e-06, "loss": 0.4763, "step": 334 }, { "epoch": 0.16, "learning_rate": 9.54368251024877e-06, "loss": 0.4338, "step": 335 }, { "epoch": 0.16, "learning_rate": 9.540385677527617e-06, "loss": 0.377, "step": 336 }, { "epoch": 0.16, "learning_rate": 9.537077551691943e-06, "loss": 0.4575, "step": 337 }, { "epoch": 0.16, "learning_rate": 9.533758140969913e-06, "loss": 0.4481, "step": 338 }, { "epoch": 0.16, "learning_rate": 9.530427453617763e-06, "loss": 0.4989, "step": 339 }, { "epoch": 0.17, "learning_rate": 9.527085497919773e-06, "loss": 0.4424, "step": 340 }, { "epoch": 0.17, "learning_rate": 9.523732282188251e-06, "loss": 0.4041, "step": 341 }, { "epoch": 0.17, "learning_rate": 9.520367814763514e-06, "loss": 0.4748, "step": 342 }, { "epoch": 0.17, "learning_rate": 9.51699210401386e-06, "loss": 0.4912, "step": 343 }, { "epoch": 0.17, "learning_rate": 9.513605158335562e-06, "loss": 0.4796, "step": 344 }, { "epoch": 0.17, "learning_rate": 9.510206986152827e-06, "loss": 0.4243, "step": 345 }, { "epoch": 0.17, "learning_rate": 9.506797595917787e-06, "loss": 0.4761, "step": 346 }, { "epoch": 0.17, "learning_rate": 9.50337699611048e-06, "loss": 0.5257, "step": 347 }, { "epoch": 0.17, "learning_rate": 9.499945195238826e-06, "loss": 0.4818, "step": 348 }, { "epoch": 0.17, "learning_rate": 9.496502201838598e-06, "loss": 0.4766, "step": 349 }, { "epoch": 0.17, "learning_rate": 9.493048024473413e-06, "loss": 0.4778, "step": 350 }, { "epoch": 0.17, "learning_rate": 9.489582671734702e-06, "loss": 0.4369, "step": 351 }, { "epoch": 0.17, "learning_rate": 9.486106152241699e-06, "loss": 0.4981, "step": 352 }, { "epoch": 0.17, "learning_rate": 9.482618474641406e-06, "loss": 0.4504, "step": 353 }, { "epoch": 0.17, "learning_rate": 9.47911964760858e-06, "loss": 0.4792, "step": 354 }, { "epoch": 0.17, "learning_rate": 9.475609679845709e-06, "loss": 0.4151, "step": 355 }, { "epoch": 0.17, "learning_rate": 9.472088580082991e-06, "loss": 0.5056, "step": 356 }, { "epoch": 0.17, "learning_rate": 9.468556357078314e-06, "loss": 0.4594, "step": 357 }, { "epoch": 0.17, "learning_rate": 9.46501301961723e-06, "loss": 0.472, "step": 358 }, { "epoch": 0.17, "learning_rate": 9.461458576512936e-06, "loss": 0.465, "step": 359 }, { "epoch": 0.18, "learning_rate": 9.457893036606254e-06, "loss": 0.4459, "step": 360 }, { "epoch": 0.18, "learning_rate": 9.454316408765604e-06, "loss": 0.5096, "step": 361 }, { "epoch": 0.18, "learning_rate": 9.450728701886985e-06, "loss": 0.3734, "step": 362 }, { "epoch": 0.18, "learning_rate": 9.447129924893951e-06, "loss": 0.4289, "step": 363 }, { "epoch": 0.18, "learning_rate": 9.443520086737593e-06, "loss": 0.4122, "step": 364 }, { "epoch": 0.18, "learning_rate": 9.439899196396517e-06, "loss": 0.451, "step": 365 }, { "epoch": 0.18, "learning_rate": 9.436267262876808e-06, "loss": 0.4718, "step": 366 }, { "epoch": 0.18, "learning_rate": 9.43262429521203e-06, "loss": 0.4678, "step": 367 }, { "epoch": 0.18, "learning_rate": 9.428970302463185e-06, "loss": 0.4016, "step": 368 }, { "epoch": 0.18, "learning_rate": 9.425305293718698e-06, "loss": 0.4344, "step": 369 }, { "epoch": 0.18, "learning_rate": 9.421629278094394e-06, "loss": 0.464, "step": 370 }, { "epoch": 0.18, "learning_rate": 9.417942264733478e-06, "loss": 0.5344, "step": 371 }, { "epoch": 0.18, "learning_rate": 9.414244262806503e-06, "loss": 0.4546, "step": 372 }, { "epoch": 0.18, "learning_rate": 9.41053528151136e-06, "loss": 0.5163, "step": 373 }, { "epoch": 0.18, "learning_rate": 9.406815330073244e-06, "loss": 0.4178, "step": 374 }, { "epoch": 0.18, "learning_rate": 9.40308441774464e-06, "loss": 0.4114, "step": 375 }, { "epoch": 0.18, "learning_rate": 9.399342553805289e-06, "loss": 0.4881, "step": 376 }, { "epoch": 0.18, "learning_rate": 9.395589747562179e-06, "loss": 0.4657, "step": 377 }, { "epoch": 0.18, "learning_rate": 9.391826008349507e-06, "loss": 0.4958, "step": 378 }, { "epoch": 0.18, "learning_rate": 9.388051345528668e-06, "loss": 0.4334, "step": 379 }, { "epoch": 0.18, "learning_rate": 9.384265768488226e-06, "loss": 0.4223, "step": 380 }, { "epoch": 0.19, "learning_rate": 9.380469286643892e-06, "loss": 0.475, "step": 381 }, { "epoch": 0.19, "learning_rate": 9.376661909438496e-06, "loss": 0.4064, "step": 382 }, { "epoch": 0.19, "learning_rate": 9.372843646341974e-06, "loss": 0.496, "step": 383 }, { "epoch": 0.19, "learning_rate": 9.369014506851334e-06, "loss": 0.4253, "step": 384 }, { "epoch": 0.19, "learning_rate": 9.365174500490635e-06, "loss": 0.4079, "step": 385 }, { "epoch": 0.19, "learning_rate": 9.36132363681097e-06, "loss": 0.3924, "step": 386 }, { "epoch": 0.19, "learning_rate": 9.357461925390432e-06, "loss": 0.4071, "step": 387 }, { "epoch": 0.19, "learning_rate": 9.353589375834095e-06, "loss": 0.388, "step": 388 }, { "epoch": 0.19, "learning_rate": 9.349705997773997e-06, "loss": 0.4661, "step": 389 }, { "epoch": 0.19, "learning_rate": 9.3458118008691e-06, "loss": 0.4627, "step": 390 }, { "epoch": 0.19, "learning_rate": 9.341906794805285e-06, "loss": 0.4005, "step": 391 }, { "epoch": 0.19, "learning_rate": 9.337990989295306e-06, "loss": 0.4958, "step": 392 }, { "epoch": 0.19, "learning_rate": 9.33406439407879e-06, "loss": 0.4866, "step": 393 }, { "epoch": 0.19, "learning_rate": 9.330127018922195e-06, "loss": 0.4503, "step": 394 }, { "epoch": 0.19, "learning_rate": 9.32617887361879e-06, "loss": 0.4127, "step": 395 }, { "epoch": 0.19, "learning_rate": 9.322219967988638e-06, "loss": 0.4314, "step": 396 }, { "epoch": 0.19, "learning_rate": 9.318250311878558e-06, "loss": 0.4586, "step": 397 }, { "epoch": 0.19, "learning_rate": 9.314269915162115e-06, "loss": 0.4261, "step": 398 }, { "epoch": 0.19, "learning_rate": 9.310278787739587e-06, "loss": 0.3966, "step": 399 }, { "epoch": 0.19, "learning_rate": 9.306276939537938e-06, "loss": 0.4249, "step": 400 }, { "epoch": 0.2, "learning_rate": 9.302264380510802e-06, "loss": 0.4575, "step": 401 }, { "epoch": 0.2, "learning_rate": 9.298241120638451e-06, "loss": 0.5283, "step": 402 }, { "epoch": 0.2, "learning_rate": 9.294207169927776e-06, "loss": 0.8841, "step": 403 }, { "epoch": 0.2, "learning_rate": 9.290162538412257e-06, "loss": 0.4743, "step": 404 }, { "epoch": 0.2, "learning_rate": 9.286107236151935e-06, "loss": 0.4403, "step": 405 }, { "epoch": 0.2, "learning_rate": 9.282041273233402e-06, "loss": 0.3708, "step": 406 }, { "epoch": 0.2, "learning_rate": 9.277964659769756e-06, "loss": 0.5054, "step": 407 }, { "epoch": 0.2, "learning_rate": 9.273877405900594e-06, "loss": 0.399, "step": 408 }, { "epoch": 0.2, "learning_rate": 9.269779521791968e-06, "loss": 0.4877, "step": 409 }, { "epoch": 0.2, "learning_rate": 9.265671017636384e-06, "loss": 0.3744, "step": 410 }, { "epoch": 0.2, "learning_rate": 9.261551903652752e-06, "loss": 0.3817, "step": 411 }, { "epoch": 0.2, "learning_rate": 9.257422190086374e-06, "loss": 0.4992, "step": 412 }, { "epoch": 0.2, "learning_rate": 9.253281887208917e-06, "loss": 0.4625, "step": 413 }, { "epoch": 0.2, "learning_rate": 9.249131005318388e-06, "loss": 0.4457, "step": 414 }, { "epoch": 0.2, "learning_rate": 9.244969554739103e-06, "loss": 0.4685, "step": 415 }, { "epoch": 0.2, "learning_rate": 9.240797545821666e-06, "loss": 0.3672, "step": 416 }, { "epoch": 0.2, "learning_rate": 9.236614988942945e-06, "loss": 0.4137, "step": 417 }, { "epoch": 0.2, "learning_rate": 9.232421894506043e-06, "loss": 0.4062, "step": 418 }, { "epoch": 0.2, "learning_rate": 9.228218272940265e-06, "loss": 0.3911, "step": 419 }, { "epoch": 0.2, "learning_rate": 9.224004134701115e-06, "loss": 0.4697, "step": 420 }, { "epoch": 0.2, "learning_rate": 9.21977949027024e-06, "loss": 0.3766, "step": 421 }, { "epoch": 0.21, "learning_rate": 9.215544350155423e-06, "loss": 0.381, "step": 422 }, { "epoch": 0.21, "learning_rate": 9.211298724890558e-06, "loss": 0.4256, "step": 423 }, { "epoch": 0.21, "learning_rate": 9.207042625035612e-06, "loss": 0.4146, "step": 424 }, { "epoch": 0.21, "learning_rate": 9.202776061176606e-06, "loss": 0.4158, "step": 425 }, { "epoch": 0.21, "learning_rate": 9.198499043925591e-06, "loss": 0.3919, "step": 426 }, { "epoch": 0.21, "learning_rate": 9.194211583920613e-06, "loss": 0.4559, "step": 427 }, { "epoch": 0.21, "learning_rate": 9.1899136918257e-06, "loss": 0.4293, "step": 428 }, { "epoch": 0.21, "learning_rate": 9.18560537833082e-06, "loss": 0.4723, "step": 429 }, { "epoch": 0.21, "learning_rate": 9.18128665415186e-06, "loss": 0.4249, "step": 430 }, { "epoch": 0.21, "learning_rate": 9.176957530030609e-06, "loss": 0.3551, "step": 431 }, { "epoch": 0.21, "learning_rate": 9.172618016734718e-06, "loss": 0.4617, "step": 432 }, { "epoch": 0.21, "learning_rate": 9.168268125057682e-06, "loss": 0.4496, "step": 433 }, { "epoch": 0.21, "learning_rate": 9.163907865818806e-06, "loss": 0.5426, "step": 434 }, { "epoch": 0.21, "learning_rate": 9.159537249863182e-06, "loss": 0.3615, "step": 435 }, { "epoch": 0.21, "learning_rate": 9.155156288061666e-06, "loss": 0.4603, "step": 436 }, { "epoch": 0.21, "learning_rate": 9.150764991310843e-06, "loss": 0.4456, "step": 437 }, { "epoch": 0.21, "learning_rate": 9.146363370533004e-06, "loss": 0.4823, "step": 438 }, { "epoch": 0.21, "learning_rate": 9.141951436676119e-06, "loss": 0.3843, "step": 439 }, { "epoch": 0.21, "learning_rate": 9.137529200713811e-06, "loss": 0.5209, "step": 440 }, { "epoch": 0.21, "learning_rate": 9.133096673645325e-06, "loss": 0.4177, "step": 441 }, { "epoch": 0.22, "learning_rate": 9.128653866495504e-06, "loss": 0.4326, "step": 442 }, { "epoch": 0.22, "learning_rate": 9.124200790314759e-06, "loss": 0.4585, "step": 443 }, { "epoch": 0.22, "learning_rate": 9.119737456179041e-06, "loss": 0.3787, "step": 444 }, { "epoch": 0.22, "learning_rate": 9.115263875189821e-06, "loss": 0.4738, "step": 445 }, { "epoch": 0.22, "learning_rate": 9.110780058474052e-06, "loss": 0.4776, "step": 446 }, { "epoch": 0.22, "learning_rate": 9.106286017184143e-06, "loss": 0.3534, "step": 447 }, { "epoch": 0.22, "learning_rate": 9.101781762497944e-06, "loss": 0.4446, "step": 448 }, { "epoch": 0.22, "learning_rate": 9.0972673056187e-06, "loss": 0.4763, "step": 449 }, { "epoch": 0.22, "learning_rate": 9.092742657775031e-06, "loss": 0.4317, "step": 450 }, { "epoch": 0.22, "learning_rate": 9.088207830220912e-06, "loss": 0.374, "step": 451 }, { "epoch": 0.22, "learning_rate": 9.08366283423563e-06, "loss": 0.444, "step": 452 }, { "epoch": 0.22, "learning_rate": 9.079107681123767e-06, "loss": 0.4994, "step": 453 }, { "epoch": 0.22, "learning_rate": 9.07454238221517e-06, "loss": 0.4153, "step": 454 }, { "epoch": 0.22, "learning_rate": 9.069966948864917e-06, "loss": 0.3836, "step": 455 }, { "epoch": 0.22, "learning_rate": 9.065381392453296e-06, "loss": 0.4191, "step": 456 }, { "epoch": 0.22, "learning_rate": 9.060785724385772e-06, "loss": 0.4765, "step": 457 }, { "epoch": 0.22, "learning_rate": 9.056179956092961e-06, "loss": 0.4056, "step": 458 }, { "epoch": 0.22, "learning_rate": 9.051564099030604e-06, "loss": 0.475, "step": 459 }, { "epoch": 0.22, "learning_rate": 9.04693816467953e-06, "loss": 0.4625, "step": 460 }, { "epoch": 0.22, "learning_rate": 9.042302164545634e-06, "loss": 0.5286, "step": 461 }, { "epoch": 0.22, "learning_rate": 9.03765611015985e-06, "loss": 0.4015, "step": 462 }, { "epoch": 0.23, "learning_rate": 9.033000013078117e-06, "loss": 0.4246, "step": 463 }, { "epoch": 0.23, "learning_rate": 9.028333884881357e-06, "loss": 0.4271, "step": 464 }, { "epoch": 0.23, "learning_rate": 9.023657737175436e-06, "loss": 0.4188, "step": 465 }, { "epoch": 0.23, "learning_rate": 9.018971581591141e-06, "loss": 0.507, "step": 466 }, { "epoch": 0.23, "learning_rate": 9.01427542978416e-06, "loss": 0.4964, "step": 467 }, { "epoch": 0.23, "learning_rate": 9.009569293435035e-06, "loss": 0.4667, "step": 468 }, { "epoch": 0.23, "learning_rate": 9.004853184249143e-06, "loss": 0.4934, "step": 469 }, { "epoch": 0.23, "learning_rate": 9.000127113956673e-06, "loss": 0.391, "step": 470 }, { "epoch": 0.23, "learning_rate": 8.995391094312583e-06, "loss": 0.5229, "step": 471 }, { "epoch": 0.23, "learning_rate": 8.99064513709658e-06, "loss": 0.4339, "step": 472 }, { "epoch": 0.23, "learning_rate": 8.985889254113087e-06, "loss": 0.4718, "step": 473 }, { "epoch": 0.23, "learning_rate": 8.98112345719122e-06, "loss": 0.4498, "step": 474 }, { "epoch": 0.23, "learning_rate": 8.976347758184745e-06, "loss": 0.4055, "step": 475 }, { "epoch": 0.23, "learning_rate": 8.971562168972065e-06, "loss": 0.4508, "step": 476 }, { "epoch": 0.23, "learning_rate": 8.966766701456177e-06, "loss": 0.4449, "step": 477 }, { "epoch": 0.23, "learning_rate": 8.961961367564652e-06, "loss": 0.4367, "step": 478 }, { "epoch": 0.23, "learning_rate": 8.957146179249597e-06, "loss": 0.4255, "step": 479 }, { "epoch": 0.23, "learning_rate": 8.952321148487632e-06, "loss": 0.4779, "step": 480 }, { "epoch": 0.23, "learning_rate": 8.947486287279859e-06, "loss": 0.4826, "step": 481 }, { "epoch": 0.23, "learning_rate": 8.94264160765183e-06, "loss": 0.4542, "step": 482 }, { "epoch": 0.24, "learning_rate": 8.937787121653517e-06, "loss": 0.4143, "step": 483 }, { "epoch": 0.24, "learning_rate": 8.93292284135928e-06, "loss": 0.4695, "step": 484 }, { "epoch": 0.24, "learning_rate": 8.928048778867848e-06, "loss": 0.4252, "step": 485 }, { "epoch": 0.24, "learning_rate": 8.923164946302274e-06, "loss": 0.4098, "step": 486 }, { "epoch": 0.24, "learning_rate": 8.918271355809913e-06, "loss": 0.453, "step": 487 }, { "epoch": 0.24, "learning_rate": 8.913368019562391e-06, "loss": 0.4205, "step": 488 }, { "epoch": 0.24, "learning_rate": 8.908454949755579e-06, "loss": 0.4403, "step": 489 }, { "epoch": 0.24, "learning_rate": 8.903532158609548e-06, "loss": 0.4238, "step": 490 }, { "epoch": 0.24, "learning_rate": 8.898599658368556e-06, "loss": 0.4172, "step": 491 }, { "epoch": 0.24, "learning_rate": 8.893657461301009e-06, "loss": 0.4195, "step": 492 }, { "epoch": 0.24, "learning_rate": 8.88870557969943e-06, "loss": 0.4779, "step": 493 }, { "epoch": 0.24, "learning_rate": 8.883744025880429e-06, "loss": 0.385, "step": 494 }, { "epoch": 0.24, "learning_rate": 8.878772812184676e-06, "loss": 0.3837, "step": 495 }, { "epoch": 0.24, "learning_rate": 8.873791950976865e-06, "loss": 0.401, "step": 496 }, { "epoch": 0.24, "learning_rate": 8.868801454645688e-06, "loss": 0.4662, "step": 497 }, { "epoch": 0.24, "learning_rate": 8.863801335603802e-06, "loss": 0.5271, "step": 498 }, { "epoch": 0.24, "learning_rate": 8.858791606287797e-06, "loss": 0.5115, "step": 499 }, { "epoch": 0.24, "learning_rate": 8.853772279158166e-06, "loss": 0.4664, "step": 500 }, { "epoch": 0.24, "learning_rate": 8.848743366699275e-06, "loss": 0.4199, "step": 501 }, { "epoch": 0.24, "learning_rate": 8.843704881419333e-06, "loss": 0.4195, "step": 502 }, { "epoch": 0.24, "learning_rate": 8.838656835850354e-06, "loss": 0.421, "step": 503 }, { "epoch": 0.25, "learning_rate": 8.833599242548137e-06, "loss": 0.3506, "step": 504 }, { "epoch": 0.25, "learning_rate": 8.828532114092224e-06, "loss": 0.4776, "step": 505 }, { "epoch": 0.25, "learning_rate": 8.823455463085873e-06, "loss": 0.4287, "step": 506 }, { "epoch": 0.25, "learning_rate": 8.818369302156034e-06, "loss": 0.4538, "step": 507 }, { "epoch": 0.25, "learning_rate": 8.813273643953304e-06, "loss": 0.4492, "step": 508 }, { "epoch": 0.25, "learning_rate": 8.808168501151904e-06, "loss": 0.417, "step": 509 }, { "epoch": 0.25, "learning_rate": 8.803053886449644e-06, "loss": 0.399, "step": 510 }, { "epoch": 0.25, "learning_rate": 8.797929812567897e-06, "loss": 0.4184, "step": 511 }, { "epoch": 0.25, "learning_rate": 8.79279629225156e-06, "loss": 0.3958, "step": 512 }, { "epoch": 0.25, "learning_rate": 8.787653338269027e-06, "loss": 0.3497, "step": 513 }, { "epoch": 0.25, "learning_rate": 8.782500963412156e-06, "loss": 0.3725, "step": 514 }, { "epoch": 0.25, "learning_rate": 8.777339180496238e-06, "loss": 0.4604, "step": 515 }, { "epoch": 0.25, "learning_rate": 8.772168002359962e-06, "loss": 0.4581, "step": 516 }, { "epoch": 0.25, "learning_rate": 8.766987441865386e-06, "loss": 0.3341, "step": 517 }, { "epoch": 0.25, "learning_rate": 8.761797511897907e-06, "loss": 0.4443, "step": 518 }, { "epoch": 0.25, "learning_rate": 8.756598225366224e-06, "loss": 0.4766, "step": 519 }, { "epoch": 0.25, "learning_rate": 8.751389595202307e-06, "loss": 0.4406, "step": 520 }, { "epoch": 0.25, "learning_rate": 8.746171634361368e-06, "loss": 0.3843, "step": 521 }, { "epoch": 0.25, "learning_rate": 8.740944355821827e-06, "loss": 0.4869, "step": 522 }, { "epoch": 0.25, "learning_rate": 8.73570777258528e-06, "loss": 0.4109, "step": 523 }, { "epoch": 0.26, "learning_rate": 8.730461897676463e-06, "loss": 0.4458, "step": 524 }, { "epoch": 0.26, "learning_rate": 8.725206744143227e-06, "loss": 0.5194, "step": 525 }, { "epoch": 0.26, "learning_rate": 8.719942325056496e-06, "loss": 0.4315, "step": 526 }, { "epoch": 0.26, "learning_rate": 8.714668653510246e-06, "loss": 0.4489, "step": 527 }, { "epoch": 0.26, "learning_rate": 8.70938574262146e-06, "loss": 0.8749, "step": 528 }, { "epoch": 0.26, "learning_rate": 8.704093605530108e-06, "loss": 0.5054, "step": 529 }, { "epoch": 0.26, "learning_rate": 8.698792255399104e-06, "loss": 0.4185, "step": 530 }, { "epoch": 0.26, "learning_rate": 8.69348170541428e-06, "loss": 0.4647, "step": 531 }, { "epoch": 0.26, "learning_rate": 8.688161968784346e-06, "loss": 0.4994, "step": 532 }, { "epoch": 0.26, "learning_rate": 8.682833058740862e-06, "loss": 0.4258, "step": 533 }, { "epoch": 0.26, "learning_rate": 8.67749498853821e-06, "loss": 0.4066, "step": 534 }, { "epoch": 0.26, "learning_rate": 8.672147771453554e-06, "loss": 0.5161, "step": 535 }, { "epoch": 0.26, "learning_rate": 8.666791420786805e-06, "loss": 0.4565, "step": 536 }, { "epoch": 0.26, "learning_rate": 8.661425949860592e-06, "loss": 0.4112, "step": 537 }, { "epoch": 0.26, "learning_rate": 8.656051372020232e-06, "loss": 0.4953, "step": 538 }, { "epoch": 0.26, "learning_rate": 8.650667700633692e-06, "loss": 0.4434, "step": 539 }, { "epoch": 0.26, "learning_rate": 8.645274949091556e-06, "loss": 0.4362, "step": 540 }, { "epoch": 0.26, "learning_rate": 8.639873130806991e-06, "loss": 0.4027, "step": 541 }, { "epoch": 0.26, "learning_rate": 8.634462259215719e-06, "loss": 0.444, "step": 542 }, { "epoch": 0.26, "learning_rate": 8.62904234777598e-06, "loss": 0.4213, "step": 543 }, { "epoch": 0.26, "learning_rate": 8.623613409968492e-06, "loss": 0.4133, "step": 544 }, { "epoch": 0.27, "learning_rate": 8.618175459296434e-06, "loss": 0.4914, "step": 545 }, { "epoch": 0.27, "learning_rate": 8.612728509285395e-06, "loss": 0.4787, "step": 546 }, { "epoch": 0.27, "learning_rate": 8.607272573483348e-06, "loss": 0.4213, "step": 547 }, { "epoch": 0.27, "learning_rate": 8.60180766546062e-06, "loss": 0.4243, "step": 548 }, { "epoch": 0.27, "learning_rate": 8.596333798809852e-06, "loss": 0.3991, "step": 549 }, { "epoch": 0.27, "learning_rate": 8.590850987145964e-06, "loss": 0.4774, "step": 550 }, { "epoch": 0.27, "learning_rate": 8.585359244106132e-06, "loss": 0.4253, "step": 551 }, { "epoch": 0.27, "learning_rate": 8.57985858334974e-06, "loss": 0.4388, "step": 552 }, { "epoch": 0.27, "learning_rate": 8.574349018558357e-06, "loss": 0.428, "step": 553 }, { "epoch": 0.27, "learning_rate": 8.568830563435695e-06, "loss": 0.4605, "step": 554 }, { "epoch": 0.27, "learning_rate": 8.563303231707582e-06, "loss": 0.4296, "step": 555 }, { "epoch": 0.27, "learning_rate": 8.557767037121923e-06, "loss": 0.3986, "step": 556 }, { "epoch": 0.27, "learning_rate": 8.552221993448664e-06, "loss": 0.369, "step": 557 }, { "epoch": 0.27, "learning_rate": 8.546668114479769e-06, "loss": 0.3937, "step": 558 }, { "epoch": 0.27, "learning_rate": 8.541105414029167e-06, "loss": 0.4299, "step": 559 }, { "epoch": 0.27, "learning_rate": 8.535533905932739e-06, "loss": 0.3752, "step": 560 }, { "epoch": 0.27, "learning_rate": 8.529953604048264e-06, "loss": 0.401, "step": 561 }, { "epoch": 0.27, "learning_rate": 8.5243645222554e-06, "loss": 0.3532, "step": 562 }, { "epoch": 0.27, "learning_rate": 8.518766674455642e-06, "loss": 0.421, "step": 563 }, { "epoch": 0.27, "learning_rate": 8.51316007457228e-06, "loss": 0.3972, "step": 564 }, { "epoch": 0.27, "learning_rate": 8.507544736550386e-06, "loss": 0.3793, "step": 565 }, { "epoch": 0.28, "learning_rate": 8.501920674356755e-06, "loss": 0.4539, "step": 566 }, { "epoch": 0.28, "learning_rate": 8.496287901979888e-06, "loss": 0.348, "step": 567 }, { "epoch": 0.28, "learning_rate": 8.490646433429946e-06, "loss": 0.4396, "step": 568 }, { "epoch": 0.28, "learning_rate": 8.484996282738722e-06, "loss": 0.4176, "step": 569 }, { "epoch": 0.28, "learning_rate": 8.479337463959607e-06, "loss": 0.4875, "step": 570 }, { "epoch": 0.28, "learning_rate": 8.473669991167543e-06, "loss": 0.4255, "step": 571 }, { "epoch": 0.28, "learning_rate": 8.467993878459005e-06, "loss": 0.4207, "step": 572 }, { "epoch": 0.28, "learning_rate": 8.462309139951952e-06, "loss": 0.4729, "step": 573 }, { "epoch": 0.28, "learning_rate": 8.456615789785804e-06, "loss": 0.4379, "step": 574 }, { "epoch": 0.28, "learning_rate": 8.450913842121396e-06, "loss": 0.4095, "step": 575 }, { "epoch": 0.28, "learning_rate": 8.445203311140944e-06, "loss": 0.4027, "step": 576 }, { "epoch": 0.28, "learning_rate": 8.439484211048019e-06, "loss": 0.4307, "step": 577 }, { "epoch": 0.28, "learning_rate": 8.433756556067506e-06, "loss": 0.4022, "step": 578 }, { "epoch": 0.28, "learning_rate": 8.428020360445563e-06, "loss": 0.4801, "step": 579 }, { "epoch": 0.28, "learning_rate": 8.422275638449592e-06, "loss": 0.4816, "step": 580 }, { "epoch": 0.28, "learning_rate": 8.416522404368208e-06, "loss": 0.4806, "step": 581 }, { "epoch": 0.28, "learning_rate": 8.410760672511188e-06, "loss": 0.4989, "step": 582 }, { "epoch": 0.28, "learning_rate": 8.404990457209458e-06, "loss": 0.429, "step": 583 }, { "epoch": 0.28, "learning_rate": 8.39921177281503e-06, "loss": 0.4109, "step": 584 }, { "epoch": 0.28, "learning_rate": 8.39342463370099e-06, "loss": 0.4102, "step": 585 }, { "epoch": 0.29, "learning_rate": 8.387629054261454e-06, "loss": 0.3361, "step": 586 }, { "epoch": 0.29, "learning_rate": 8.381825048911525e-06, "loss": 0.4759, "step": 587 }, { "epoch": 0.29, "learning_rate": 8.376012632087266e-06, "loss": 0.4613, "step": 588 }, { "epoch": 0.29, "learning_rate": 8.370191818245667e-06, "loss": 0.3585, "step": 589 }, { "epoch": 0.29, "learning_rate": 8.364362621864595e-06, "loss": 0.4567, "step": 590 }, { "epoch": 0.29, "learning_rate": 8.35852505744277e-06, "loss": 0.4873, "step": 591 }, { "epoch": 0.29, "learning_rate": 8.352679139499731e-06, "loss": 0.4331, "step": 592 }, { "epoch": 0.29, "learning_rate": 8.346824882575783e-06, "loss": 0.4108, "step": 593 }, { "epoch": 0.29, "learning_rate": 8.34096230123198e-06, "loss": 0.3922, "step": 594 }, { "epoch": 0.29, "learning_rate": 8.33509141005008e-06, "loss": 0.4188, "step": 595 }, { "epoch": 0.29, "learning_rate": 8.329212223632511e-06, "loss": 0.461, "step": 596 }, { "epoch": 0.29, "learning_rate": 8.32332475660233e-06, "loss": 0.3882, "step": 597 }, { "epoch": 0.29, "learning_rate": 8.31742902360319e-06, "loss": 0.4028, "step": 598 }, { "epoch": 0.29, "learning_rate": 8.311525039299308e-06, "loss": 0.479, "step": 599 }, { "epoch": 0.29, "learning_rate": 8.305612818375419e-06, "loss": 0.4108, "step": 600 }, { "epoch": 0.29, "learning_rate": 8.299692375536749e-06, "loss": 0.4238, "step": 601 }, { "epoch": 0.29, "learning_rate": 8.29376372550897e-06, "loss": 0.3862, "step": 602 }, { "epoch": 0.29, "learning_rate": 8.28782688303817e-06, "loss": 0.4057, "step": 603 }, { "epoch": 0.29, "learning_rate": 8.281881862890813e-06, "loss": 0.4328, "step": 604 }, { "epoch": 0.29, "learning_rate": 8.275928679853704e-06, "loss": 0.4284, "step": 605 }, { "epoch": 0.29, "learning_rate": 8.269967348733947e-06, "loss": 0.397, "step": 606 }, { "epoch": 0.3, "learning_rate": 8.26399788435892e-06, "loss": 0.3955, "step": 607 }, { "epoch": 0.3, "learning_rate": 8.258020301576224e-06, "loss": 0.4392, "step": 608 }, { "epoch": 0.3, "learning_rate": 8.252034615253657e-06, "loss": 0.3736, "step": 609 }, { "epoch": 0.3, "learning_rate": 8.246040840279165e-06, "loss": 0.4562, "step": 610 }, { "epoch": 0.3, "learning_rate": 8.240038991560823e-06, "loss": 0.4071, "step": 611 }, { "epoch": 0.3, "learning_rate": 8.234029084026782e-06, "loss": 0.3868, "step": 612 }, { "epoch": 0.3, "learning_rate": 8.228011132625234e-06, "loss": 0.3415, "step": 613 }, { "epoch": 0.3, "learning_rate": 8.221985152324385e-06, "loss": 0.4436, "step": 614 }, { "epoch": 0.3, "learning_rate": 8.21595115811241e-06, "loss": 0.3856, "step": 615 }, { "epoch": 0.3, "learning_rate": 8.209909164997409e-06, "loss": 0.4107, "step": 616 }, { "epoch": 0.3, "learning_rate": 8.203859188007388e-06, "loss": 0.4182, "step": 617 }, { "epoch": 0.3, "learning_rate": 8.197801242190204e-06, "loss": 0.3907, "step": 618 }, { "epoch": 0.3, "learning_rate": 8.191735342613533e-06, "loss": 0.3683, "step": 619 }, { "epoch": 0.3, "learning_rate": 8.185661504364845e-06, "loss": 0.4871, "step": 620 }, { "epoch": 0.3, "learning_rate": 8.179579742551341e-06, "loss": 0.5041, "step": 621 }, { "epoch": 0.3, "learning_rate": 8.17349007229994e-06, "loss": 0.423, "step": 622 }, { "epoch": 0.3, "learning_rate": 8.16739250875723e-06, "loss": 0.4195, "step": 623 }, { "epoch": 0.3, "learning_rate": 8.161287067089426e-06, "loss": 0.41, "step": 624 }, { "epoch": 0.3, "learning_rate": 8.155173762482344e-06, "loss": 0.359, "step": 625 }, { "epoch": 0.3, "learning_rate": 8.149052610141357e-06, "loss": 0.4765, "step": 626 }, { "epoch": 0.31, "learning_rate": 8.142923625291352e-06, "loss": 0.4303, "step": 627 }, { "epoch": 0.31, "learning_rate": 8.136786823176703e-06, "loss": 0.4184, "step": 628 }, { "epoch": 0.31, "learning_rate": 8.130642219061224e-06, "loss": 0.4153, "step": 629 }, { "epoch": 0.31, "learning_rate": 8.124489828228136e-06, "loss": 0.4858, "step": 630 }, { "epoch": 0.31, "learning_rate": 8.11832966598003e-06, "loss": 0.3649, "step": 631 }, { "epoch": 0.31, "learning_rate": 8.112161747638823e-06, "loss": 0.4369, "step": 632 }, { "epoch": 0.31, "learning_rate": 8.105986088545722e-06, "loss": 0.4127, "step": 633 }, { "epoch": 0.31, "learning_rate": 8.099802704061194e-06, "loss": 0.3666, "step": 634 }, { "epoch": 0.31, "learning_rate": 8.093611609564913e-06, "loss": 0.4849, "step": 635 }, { "epoch": 0.31, "learning_rate": 8.087412820455738e-06, "loss": 0.3468, "step": 636 }, { "epoch": 0.31, "learning_rate": 8.081206352151659e-06, "loss": 0.4472, "step": 637 }, { "epoch": 0.31, "learning_rate": 8.07499222008977e-06, "loss": 0.4091, "step": 638 }, { "epoch": 0.31, "learning_rate": 8.068770439726224e-06, "loss": 0.4055, "step": 639 }, { "epoch": 0.31, "learning_rate": 8.062541026536204e-06, "loss": 0.4061, "step": 640 }, { "epoch": 0.31, "learning_rate": 8.056303996013868e-06, "loss": 0.4501, "step": 641 }, { "epoch": 0.31, "learning_rate": 8.05005936367233e-06, "loss": 0.4007, "step": 642 }, { "epoch": 0.31, "learning_rate": 8.043807145043604e-06, "loss": 0.4387, "step": 643 }, { "epoch": 0.31, "learning_rate": 8.037547355678578e-06, "loss": 0.4501, "step": 644 }, { "epoch": 0.31, "learning_rate": 8.031280011146968e-06, "loss": 0.4927, "step": 645 }, { "epoch": 0.31, "learning_rate": 8.025005127037282e-06, "loss": 0.3677, "step": 646 }, { "epoch": 0.31, "learning_rate": 8.01872271895678e-06, "loss": 0.3865, "step": 647 }, { "epoch": 0.32, "learning_rate": 8.01243280253144e-06, "loss": 0.3656, "step": 648 }, { "epoch": 0.32, "learning_rate": 8.006135393405911e-06, "loss": 0.3826, "step": 649 }, { "epoch": 0.32, "learning_rate": 7.999830507243478e-06, "loss": 0.4038, "step": 650 }, { "epoch": 0.32, "learning_rate": 7.993518159726028e-06, "loss": 0.4281, "step": 651 }, { "epoch": 0.32, "learning_rate": 7.987198366554002e-06, "loss": 0.4281, "step": 652 }, { "epoch": 0.32, "learning_rate": 7.98087114344636e-06, "loss": 0.4013, "step": 653 }, { "epoch": 0.32, "learning_rate": 7.974536506140546e-06, "loss": 0.3295, "step": 654 }, { "epoch": 0.32, "learning_rate": 7.968194470392444e-06, "loss": 0.3941, "step": 655 }, { "epoch": 0.32, "learning_rate": 7.961845051976334e-06, "loss": 0.4384, "step": 656 }, { "epoch": 0.32, "learning_rate": 7.955488266684865e-06, "loss": 0.4415, "step": 657 }, { "epoch": 0.32, "learning_rate": 7.94912413032901e-06, "loss": 0.4059, "step": 658 }, { "epoch": 0.32, "learning_rate": 7.942752658738023e-06, "loss": 0.3963, "step": 659 }, { "epoch": 0.32, "learning_rate": 7.9363738677594e-06, "loss": 0.3422, "step": 660 }, { "epoch": 0.32, "learning_rate": 7.929987773258847e-06, "loss": 0.4982, "step": 661 }, { "epoch": 0.32, "learning_rate": 7.923594391120237e-06, "loss": 0.4381, "step": 662 }, { "epoch": 0.32, "learning_rate": 7.917193737245563e-06, "loss": 0.3786, "step": 663 }, { "epoch": 0.32, "learning_rate": 7.910785827554909e-06, "loss": 0.372, "step": 664 }, { "epoch": 0.32, "learning_rate": 7.904370677986404e-06, "loss": 0.3435, "step": 665 }, { "epoch": 0.32, "learning_rate": 7.897948304496189e-06, "loss": 0.3963, "step": 666 }, { "epoch": 0.32, "learning_rate": 7.891518723058367e-06, "loss": 0.4531, "step": 667 }, { "epoch": 0.33, "learning_rate": 7.885081949664971e-06, "loss": 0.3754, "step": 668 }, { "epoch": 0.33, "learning_rate": 7.878638000325925e-06, "loss": 0.3951, "step": 669 }, { "epoch": 0.33, "learning_rate": 7.872186891068997e-06, "loss": 0.3546, "step": 670 }, { "epoch": 0.33, "learning_rate": 7.865728637939764e-06, "loss": 0.4296, "step": 671 }, { "epoch": 0.33, "learning_rate": 7.859263257001578e-06, "loss": 0.451, "step": 672 }, { "epoch": 0.33, "learning_rate": 7.852790764335511e-06, "loss": 0.4165, "step": 673 }, { "epoch": 0.33, "learning_rate": 7.846311176040331e-06, "loss": 0.3676, "step": 674 }, { "epoch": 0.33, "learning_rate": 7.839824508232448e-06, "loss": 0.3858, "step": 675 }, { "epoch": 0.33, "learning_rate": 7.833330777045886e-06, "loss": 0.3566, "step": 676 }, { "epoch": 0.33, "learning_rate": 7.826829998632236e-06, "loss": 0.3677, "step": 677 }, { "epoch": 0.33, "learning_rate": 7.820322189160618e-06, "loss": 0.4259, "step": 678 }, { "epoch": 0.33, "learning_rate": 7.813807364817635e-06, "loss": 0.4452, "step": 679 }, { "epoch": 0.33, "learning_rate": 7.807285541807342e-06, "loss": 0.41, "step": 680 }, { "epoch": 0.33, "learning_rate": 7.800756736351204e-06, "loss": 0.3855, "step": 681 }, { "epoch": 0.33, "learning_rate": 7.794220964688048e-06, "loss": 0.3404, "step": 682 }, { "epoch": 0.33, "learning_rate": 7.78767824307403e-06, "loss": 0.4098, "step": 683 }, { "epoch": 0.33, "learning_rate": 7.781128587782595e-06, "loss": 0.5129, "step": 684 }, { "epoch": 0.33, "learning_rate": 7.774572015104427e-06, "loss": 0.4193, "step": 685 }, { "epoch": 0.33, "learning_rate": 7.768008541347423e-06, "loss": 0.3857, "step": 686 }, { "epoch": 0.33, "learning_rate": 7.76143818283664e-06, "loss": 0.3902, "step": 687 }, { "epoch": 0.33, "learning_rate": 7.75486095591426e-06, "loss": 0.4744, "step": 688 }, { "epoch": 0.34, "learning_rate": 7.74827687693955e-06, "loss": 0.5013, "step": 689 }, { "epoch": 0.34, "learning_rate": 7.741685962288817e-06, "loss": 0.3564, "step": 690 }, { "epoch": 0.34, "learning_rate": 7.735088228355373e-06, "loss": 0.4408, "step": 691 }, { "epoch": 0.34, "learning_rate": 7.728483691549491e-06, "loss": 0.3904, "step": 692 }, { "epoch": 0.34, "learning_rate": 7.721872368298365e-06, "loss": 0.4206, "step": 693 }, { "epoch": 0.34, "learning_rate": 7.715254275046062e-06, "loss": 0.495, "step": 694 }, { "epoch": 0.34, "learning_rate": 7.708629428253497e-06, "loss": 0.4536, "step": 695 }, { "epoch": 0.34, "learning_rate": 7.701997844398379e-06, "loss": 0.4444, "step": 696 }, { "epoch": 0.34, "learning_rate": 7.695359539975173e-06, "loss": 0.4655, "step": 697 }, { "epoch": 0.34, "learning_rate": 7.688714531495061e-06, "loss": 0.4186, "step": 698 }, { "epoch": 0.34, "learning_rate": 7.682062835485898e-06, "loss": 0.4582, "step": 699 }, { "epoch": 0.34, "learning_rate": 7.675404468492175e-06, "loss": 0.36, "step": 700 }, { "epoch": 0.34, "learning_rate": 7.668739447074974e-06, "loss": 0.4593, "step": 701 }, { "epoch": 0.34, "learning_rate": 7.66206778781193e-06, "loss": 0.4066, "step": 702 }, { "epoch": 0.34, "learning_rate": 7.655389507297181e-06, "loss": 0.4262, "step": 703 }, { "epoch": 0.34, "learning_rate": 7.648704622141347e-06, "loss": 0.433, "step": 704 }, { "epoch": 0.34, "learning_rate": 7.642013148971465e-06, "loss": 0.4276, "step": 705 }, { "epoch": 0.34, "learning_rate": 7.635315104430959e-06, "loss": 0.4568, "step": 706 }, { "epoch": 0.34, "learning_rate": 7.628610505179602e-06, "loss": 0.4103, "step": 707 }, { "epoch": 0.34, "learning_rate": 7.621899367893466e-06, "loss": 0.3991, "step": 708 }, { "epoch": 0.35, "learning_rate": 7.6151817092648875e-06, "loss": 0.3546, "step": 709 }, { "epoch": 0.35, "learning_rate": 7.608457546002423e-06, "loss": 0.4571, "step": 710 }, { "epoch": 0.35, "learning_rate": 7.601726894830808e-06, "loss": 0.3909, "step": 711 }, { "epoch": 0.35, "learning_rate": 7.594989772490911e-06, "loss": 0.4618, "step": 712 }, { "epoch": 0.35, "learning_rate": 7.588246195739703e-06, "loss": 0.3717, "step": 713 }, { "epoch": 0.35, "learning_rate": 7.581496181350203e-06, "loss": 0.3886, "step": 714 }, { "epoch": 0.35, "learning_rate": 7.574739746111444e-06, "loss": 0.4098, "step": 715 }, { "epoch": 0.35, "learning_rate": 7.567976906828431e-06, "loss": 0.3695, "step": 716 }, { "epoch": 0.35, "learning_rate": 7.561207680322096e-06, "loss": 0.3275, "step": 717 }, { "epoch": 0.35, "learning_rate": 7.554432083429253e-06, "loss": 0.4456, "step": 718 }, { "epoch": 0.35, "learning_rate": 7.547650133002571e-06, "loss": 0.4098, "step": 719 }, { "epoch": 0.35, "learning_rate": 7.540861845910514e-06, "loss": 0.4051, "step": 720 }, { "epoch": 0.35, "learning_rate": 7.534067239037311e-06, "loss": 0.4075, "step": 721 }, { "epoch": 0.35, "learning_rate": 7.527266329282905e-06, "loss": 0.3876, "step": 722 }, { "epoch": 0.35, "learning_rate": 7.5204591335629204e-06, "loss": 0.3257, "step": 723 }, { "epoch": 0.35, "learning_rate": 7.513645668808615e-06, "loss": 0.4198, "step": 724 }, { "epoch": 0.35, "learning_rate": 7.506825951966843e-06, "loss": 0.4357, "step": 725 }, { "epoch": 0.35, "learning_rate": 7.500000000000001e-06, "loss": 0.3709, "step": 726 }, { "epoch": 0.35, "learning_rate": 7.493167829886e-06, "loss": 0.4276, "step": 727 }, { "epoch": 0.35, "learning_rate": 7.486329458618215e-06, "loss": 0.3455, "step": 728 }, { "epoch": 0.35, "learning_rate": 7.479484903205445e-06, "loss": 0.3758, "step": 729 }, { "epoch": 0.36, "learning_rate": 7.4726341806718735e-06, "loss": 0.4782, "step": 730 }, { "epoch": 0.36, "learning_rate": 7.4657773080570206e-06, "loss": 0.4076, "step": 731 }, { "epoch": 0.36, "learning_rate": 7.458914302415702e-06, "loss": 0.3696, "step": 732 }, { "epoch": 0.36, "learning_rate": 7.45204518081799e-06, "loss": 0.3541, "step": 733 }, { "epoch": 0.36, "learning_rate": 7.445169960349167e-06, "loss": 0.461, "step": 734 }, { "epoch": 0.36, "learning_rate": 7.438288658109688e-06, "loss": 0.4215, "step": 735 }, { "epoch": 0.36, "learning_rate": 7.431401291215131e-06, "loss": 0.3863, "step": 736 }, { "epoch": 0.36, "learning_rate": 7.4245078767961635e-06, "loss": 0.4285, "step": 737 }, { "epoch": 0.36, "learning_rate": 7.417608431998487e-06, "loss": 0.4242, "step": 738 }, { "epoch": 0.36, "learning_rate": 7.41070297398281e-06, "loss": 0.402, "step": 739 }, { "epoch": 0.36, "learning_rate": 7.403791519924794e-06, "loss": 0.4413, "step": 740 }, { "epoch": 0.36, "learning_rate": 7.396874087015014e-06, "loss": 0.4552, "step": 741 }, { "epoch": 0.36, "learning_rate": 7.389950692458916e-06, "loss": 0.4598, "step": 742 }, { "epoch": 0.36, "learning_rate": 7.383021353476775e-06, "loss": 0.3512, "step": 743 }, { "epoch": 0.36, "learning_rate": 7.376086087303649e-06, "loss": 0.4817, "step": 744 }, { "epoch": 0.36, "learning_rate": 7.369144911189342e-06, "loss": 0.4078, "step": 745 }, { "epoch": 0.36, "learning_rate": 7.362197842398355e-06, "loss": 0.3901, "step": 746 }, { "epoch": 0.36, "learning_rate": 7.355244898209848e-06, "loss": 0.3953, "step": 747 }, { "epoch": 0.36, "learning_rate": 7.348286095917591e-06, "loss": 0.3492, "step": 748 }, { "epoch": 0.36, "learning_rate": 7.3413214528299295e-06, "loss": 0.447, "step": 749 }, { "epoch": 0.37, "learning_rate": 7.3343509862697295e-06, "loss": 0.3898, "step": 750 }, { "epoch": 0.37, "learning_rate": 7.327374713574349e-06, "loss": 0.4091, "step": 751 }, { "epoch": 0.37, "learning_rate": 7.3203926520955846e-06, "loss": 0.4017, "step": 752 }, { "epoch": 0.37, "learning_rate": 7.313404819199628e-06, "loss": 0.4437, "step": 753 }, { "epoch": 0.37, "learning_rate": 7.30641123226703e-06, "loss": 0.362, "step": 754 }, { "epoch": 0.37, "learning_rate": 7.29941190869265e-06, "loss": 0.4003, "step": 755 }, { "epoch": 0.37, "learning_rate": 7.292406865885619e-06, "loss": 0.3788, "step": 756 }, { "epoch": 0.37, "learning_rate": 7.285396121269293e-06, "loss": 0.3698, "step": 757 }, { "epoch": 0.37, "learning_rate": 7.278379692281209e-06, "loss": 0.4593, "step": 758 }, { "epoch": 0.37, "learning_rate": 7.271357596373039e-06, "loss": 0.4173, "step": 759 }, { "epoch": 0.37, "learning_rate": 7.264329851010554e-06, "loss": 0.45, "step": 760 }, { "epoch": 0.37, "learning_rate": 7.2572964736735786e-06, "loss": 0.3266, "step": 761 }, { "epoch": 0.37, "learning_rate": 7.250257481855941e-06, "loss": 0.3718, "step": 762 }, { "epoch": 0.37, "learning_rate": 7.2432128930654354e-06, "loss": 0.3419, "step": 763 }, { "epoch": 0.37, "learning_rate": 7.2361627248237795e-06, "loss": 0.3864, "step": 764 }, { "epoch": 0.37, "learning_rate": 7.229106994666564e-06, "loss": 0.3824, "step": 765 }, { "epoch": 0.37, "learning_rate": 7.22204572014322e-06, "loss": 0.4794, "step": 766 }, { "epoch": 0.37, "learning_rate": 7.214978918816962e-06, "loss": 0.3943, "step": 767 }, { "epoch": 0.37, "learning_rate": 7.2079066082647566e-06, "loss": 0.3845, "step": 768 }, { "epoch": 0.37, "learning_rate": 7.20082880607727e-06, "loss": 0.3918, "step": 769 }, { "epoch": 0.37, "learning_rate": 7.193745529858827e-06, "loss": 0.3805, "step": 770 }, { "epoch": 0.38, "learning_rate": 7.186656797227371e-06, "loss": 0.4123, "step": 771 }, { "epoch": 0.38, "learning_rate": 7.179562625814414e-06, "loss": 0.368, "step": 772 }, { "epoch": 0.38, "learning_rate": 7.172463033264997e-06, "loss": 0.4368, "step": 773 }, { "epoch": 0.38, "learning_rate": 7.165358037237644e-06, "loss": 0.4315, "step": 774 }, { "epoch": 0.38, "learning_rate": 7.158247655404321e-06, "loss": 0.3946, "step": 775 }, { "epoch": 0.38, "learning_rate": 7.151131905450386e-06, "loss": 0.3579, "step": 776 }, { "epoch": 0.38, "learning_rate": 7.144010805074554e-06, "loss": 0.4301, "step": 777 }, { "epoch": 0.38, "learning_rate": 7.136884371988844e-06, "loss": 0.3966, "step": 778 }, { "epoch": 0.38, "learning_rate": 7.1297526239185375e-06, "loss": 0.3984, "step": 779 }, { "epoch": 0.38, "learning_rate": 7.122615578602141e-06, "loss": 0.4493, "step": 780 }, { "epoch": 0.38, "learning_rate": 7.1154732537913305e-06, "loss": 0.3526, "step": 781 }, { "epoch": 0.38, "learning_rate": 7.10832566725092e-06, "loss": 0.4456, "step": 782 }, { "epoch": 0.38, "learning_rate": 7.101172836758808e-06, "loss": 0.4308, "step": 783 }, { "epoch": 0.38, "learning_rate": 7.094014780105931e-06, "loss": 0.3505, "step": 784 }, { "epoch": 0.38, "learning_rate": 7.086851515096233e-06, "loss": 0.413, "step": 785 }, { "epoch": 0.38, "learning_rate": 7.079683059546607e-06, "loss": 0.4649, "step": 786 }, { "epoch": 0.38, "learning_rate": 7.072509431286858e-06, "loss": 0.3979, "step": 787 }, { "epoch": 0.38, "learning_rate": 7.0653306481596565e-06, "loss": 0.416, "step": 788 }, { "epoch": 0.38, "learning_rate": 7.058146728020492e-06, "loss": 0.461, "step": 789 }, { "epoch": 0.38, "learning_rate": 7.0509576887376375e-06, "loss": 0.3427, "step": 790 }, { "epoch": 0.38, "learning_rate": 7.043763548192091e-06, "loss": 0.4073, "step": 791 }, { "epoch": 0.39, "learning_rate": 7.036564324277545e-06, "loss": 0.3446, "step": 792 }, { "epoch": 0.39, "learning_rate": 7.029360034900332e-06, "loss": 0.3571, "step": 793 }, { "epoch": 0.39, "learning_rate": 7.022150697979385e-06, "loss": 0.4208, "step": 794 }, { "epoch": 0.39, "learning_rate": 7.014936331446192e-06, "loss": 0.3589, "step": 795 }, { "epoch": 0.39, "learning_rate": 7.0077169532447474e-06, "loss": 0.3948, "step": 796 }, { "epoch": 0.39, "learning_rate": 7.000492581331516e-06, "loss": 0.3841, "step": 797 }, { "epoch": 0.39, "learning_rate": 6.99326323367538e-06, "loss": 0.3863, "step": 798 }, { "epoch": 0.39, "learning_rate": 6.9860289282575976e-06, "loss": 0.4308, "step": 799 }, { "epoch": 0.39, "learning_rate": 6.978789683071761e-06, "loss": 0.4208, "step": 800 }, { "epoch": 0.39, "learning_rate": 6.971545516123745e-06, "loss": 0.3652, "step": 801 }, { "epoch": 0.39, "learning_rate": 6.96429644543167e-06, "loss": 0.3877, "step": 802 }, { "epoch": 0.39, "learning_rate": 6.957042489025849e-06, "loss": 0.3941, "step": 803 }, { "epoch": 0.39, "learning_rate": 6.949783664948752e-06, "loss": 0.3885, "step": 804 }, { "epoch": 0.39, "learning_rate": 6.942519991254954e-06, "loss": 0.3558, "step": 805 }, { "epoch": 0.39, "learning_rate": 6.9352514860110876e-06, "loss": 0.3709, "step": 806 }, { "epoch": 0.39, "learning_rate": 6.927978167295808e-06, "loss": 0.3525, "step": 807 }, { "epoch": 0.39, "learning_rate": 6.9207000531997445e-06, "loss": 0.4023, "step": 808 }, { "epoch": 0.39, "learning_rate": 6.913417161825449e-06, "loss": 0.4589, "step": 809 }, { "epoch": 0.39, "learning_rate": 6.906129511287358e-06, "loss": 0.4141, "step": 810 }, { "epoch": 0.39, "learning_rate": 6.898837119711746e-06, "loss": 0.4551, "step": 811 }, { "epoch": 0.4, "learning_rate": 6.8915400052366756e-06, "loss": 0.3957, "step": 812 }, { "epoch": 0.4, "learning_rate": 6.884238186011962e-06, "loss": 0.3719, "step": 813 }, { "epoch": 0.4, "learning_rate": 6.876931680199121e-06, "loss": 0.4091, "step": 814 }, { "epoch": 0.4, "learning_rate": 6.86962050597132e-06, "loss": 0.4178, "step": 815 }, { "epoch": 0.4, "learning_rate": 6.862304681513344e-06, "loss": 0.4448, "step": 816 }, { "epoch": 0.4, "learning_rate": 6.854984225021541e-06, "loss": 0.4426, "step": 817 }, { "epoch": 0.4, "learning_rate": 6.847659154703785e-06, "loss": 0.4954, "step": 818 }, { "epoch": 0.4, "learning_rate": 6.840329488779418e-06, "loss": 0.4134, "step": 819 }, { "epoch": 0.4, "learning_rate": 6.832995245479219e-06, "loss": 0.3837, "step": 820 }, { "epoch": 0.4, "learning_rate": 6.825656443045348e-06, "loss": 0.4174, "step": 821 }, { "epoch": 0.4, "learning_rate": 6.818313099731308e-06, "loss": 0.8729, "step": 822 }, { "epoch": 0.4, "learning_rate": 6.810965233801893e-06, "loss": 0.4509, "step": 823 }, { "epoch": 0.4, "learning_rate": 6.803612863533149e-06, "loss": 0.4518, "step": 824 }, { "epoch": 0.4, "learning_rate": 6.796256007212323e-06, "loss": 0.4382, "step": 825 }, { "epoch": 0.4, "learning_rate": 6.788894683137822e-06, "loss": 0.3901, "step": 826 }, { "epoch": 0.4, "learning_rate": 6.781528909619164e-06, "loss": 0.4262, "step": 827 }, { "epoch": 0.4, "learning_rate": 6.774158704976934e-06, "loss": 0.4671, "step": 828 }, { "epoch": 0.4, "learning_rate": 6.766784087542741e-06, "loss": 0.4151, "step": 829 }, { "epoch": 0.4, "learning_rate": 6.759405075659165e-06, "loss": 0.3444, "step": 830 }, { "epoch": 0.4, "learning_rate": 6.752021687679721e-06, "loss": 0.3986, "step": 831 }, { "epoch": 0.4, "learning_rate": 6.744633941968806e-06, "loss": 0.4015, "step": 832 }, { "epoch": 0.41, "learning_rate": 6.737241856901653e-06, "loss": 0.3651, "step": 833 }, { "epoch": 0.41, "learning_rate": 6.7298454508642945e-06, "loss": 0.348, "step": 834 }, { "epoch": 0.41, "learning_rate": 6.722444742253505e-06, "loss": 0.3841, "step": 835 }, { "epoch": 0.41, "learning_rate": 6.715039749476764e-06, "loss": 0.3843, "step": 836 }, { "epoch": 0.41, "learning_rate": 6.707630490952204e-06, "loss": 0.3981, "step": 837 }, { "epoch": 0.41, "learning_rate": 6.700216985108568e-06, "loss": 0.4251, "step": 838 }, { "epoch": 0.41, "learning_rate": 6.692799250385168e-06, "loss": 0.4265, "step": 839 }, { "epoch": 0.41, "learning_rate": 6.6853773052318275e-06, "loss": 0.4161, "step": 840 }, { "epoch": 0.41, "learning_rate": 6.677951168108847e-06, "loss": 0.3546, "step": 841 }, { "epoch": 0.41, "learning_rate": 6.6705208574869504e-06, "loss": 0.3557, "step": 842 }, { "epoch": 0.41, "learning_rate": 6.663086391847242e-06, "loss": 0.4109, "step": 843 }, { "epoch": 0.41, "learning_rate": 6.655647789681167e-06, "loss": 0.4071, "step": 844 }, { "epoch": 0.41, "learning_rate": 6.648205069490451e-06, "loss": 0.4094, "step": 845 }, { "epoch": 0.41, "learning_rate": 6.640758249787067e-06, "loss": 0.4426, "step": 846 }, { "epoch": 0.41, "learning_rate": 6.633307349093183e-06, "loss": 0.3791, "step": 847 }, { "epoch": 0.41, "learning_rate": 6.62585238594112e-06, "loss": 0.4298, "step": 848 }, { "epoch": 0.41, "learning_rate": 6.6183933788732956e-06, "loss": 0.3765, "step": 849 }, { "epoch": 0.41, "learning_rate": 6.610930346442198e-06, "loss": 0.3793, "step": 850 }, { "epoch": 0.41, "learning_rate": 6.603463307210316e-06, "loss": 0.3329, "step": 851 }, { "epoch": 0.41, "learning_rate": 6.595992279750111e-06, "loss": 0.4102, "step": 852 }, { "epoch": 0.42, "learning_rate": 6.588517282643961e-06, "loss": 0.3505, "step": 853 }, { "epoch": 0.42, "learning_rate": 6.58103833448412e-06, "loss": 0.4123, "step": 854 }, { "epoch": 0.42, "learning_rate": 6.5735554538726685e-06, "loss": 0.4085, "step": 855 }, { "epoch": 0.42, "learning_rate": 6.566068659421467e-06, "loss": 0.3655, "step": 856 }, { "epoch": 0.42, "learning_rate": 6.558577969752111e-06, "loss": 0.4414, "step": 857 }, { "epoch": 0.42, "learning_rate": 6.551083403495885e-06, "loss": 0.3594, "step": 858 }, { "epoch": 0.42, "learning_rate": 6.543584979293716e-06, "loss": 0.3045, "step": 859 }, { "epoch": 0.42, "learning_rate": 6.536082715796125e-06, "loss": 0.3168, "step": 860 }, { "epoch": 0.42, "learning_rate": 6.528576631663184e-06, "loss": 0.4117, "step": 861 }, { "epoch": 0.42, "learning_rate": 6.521066745564467e-06, "loss": 0.3579, "step": 862 }, { "epoch": 0.42, "learning_rate": 6.513553076179005e-06, "loss": 0.3516, "step": 863 }, { "epoch": 0.42, "learning_rate": 6.506035642195239e-06, "loss": 0.4375, "step": 864 }, { "epoch": 0.42, "learning_rate": 6.498514462310972e-06, "loss": 0.3825, "step": 865 }, { "epoch": 0.42, "learning_rate": 6.490989555233328e-06, "loss": 0.5245, "step": 866 }, { "epoch": 0.42, "learning_rate": 6.4834609396786976e-06, "loss": 0.4429, "step": 867 }, { "epoch": 0.42, "learning_rate": 6.475928634372695e-06, "loss": 0.3859, "step": 868 }, { "epoch": 0.42, "learning_rate": 6.468392658050113e-06, "loss": 0.3941, "step": 869 }, { "epoch": 0.42, "learning_rate": 6.460853029454879e-06, "loss": 0.5087, "step": 870 }, { "epoch": 0.42, "learning_rate": 6.453309767339998e-06, "loss": 0.4125, "step": 871 }, { "epoch": 0.42, "learning_rate": 6.445762890467517e-06, "loss": 0.4579, "step": 872 }, { "epoch": 0.42, "learning_rate": 6.438212417608473e-06, "loss": 0.4314, "step": 873 }, { "epoch": 0.43, "learning_rate": 6.4306583675428435e-06, "loss": 0.4055, "step": 874 }, { "epoch": 0.43, "learning_rate": 6.4231007590595094e-06, "loss": 0.4092, "step": 875 }, { "epoch": 0.43, "learning_rate": 6.4155396109561995e-06, "loss": 0.4225, "step": 876 }, { "epoch": 0.43, "learning_rate": 6.407974942039446e-06, "loss": 0.424, "step": 877 }, { "epoch": 0.43, "learning_rate": 6.4004067711245366e-06, "loss": 0.4226, "step": 878 }, { "epoch": 0.43, "learning_rate": 6.392835117035472e-06, "loss": 0.4397, "step": 879 }, { "epoch": 0.43, "learning_rate": 6.385259998604918e-06, "loss": 0.4046, "step": 880 }, { "epoch": 0.43, "learning_rate": 6.3776814346741545e-06, "loss": 0.3848, "step": 881 }, { "epoch": 0.43, "learning_rate": 6.370099444093032e-06, "loss": 0.4664, "step": 882 }, { "epoch": 0.43, "learning_rate": 6.362514045719922e-06, "loss": 0.3458, "step": 883 }, { "epoch": 0.43, "learning_rate": 6.354925258421676e-06, "loss": 0.3472, "step": 884 }, { "epoch": 0.43, "learning_rate": 6.34733310107357e-06, "loss": 0.4387, "step": 885 }, { "epoch": 0.43, "learning_rate": 6.3397375925592675e-06, "loss": 0.3829, "step": 886 }, { "epoch": 0.43, "learning_rate": 6.332138751770762e-06, "loss": 0.3625, "step": 887 }, { "epoch": 0.43, "learning_rate": 6.32453659760834e-06, "loss": 0.8532, "step": 888 }, { "epoch": 0.43, "learning_rate": 6.316931148980523e-06, "loss": 0.3862, "step": 889 }, { "epoch": 0.43, "learning_rate": 6.309322424804034e-06, "loss": 0.4541, "step": 890 }, { "epoch": 0.43, "learning_rate": 6.301710444003739e-06, "loss": 0.3938, "step": 891 }, { "epoch": 0.43, "learning_rate": 6.294095225512604e-06, "loss": 0.393, "step": 892 }, { "epoch": 0.43, "learning_rate": 6.286476788271649e-06, "loss": 0.3893, "step": 893 }, { "epoch": 0.44, "learning_rate": 6.2788551512299014e-06, "loss": 0.3263, "step": 894 }, { "epoch": 0.44, "learning_rate": 6.27123033334434e-06, "loss": 0.397, "step": 895 }, { "epoch": 0.44, "learning_rate": 6.263602353579868e-06, "loss": 0.3617, "step": 896 }, { "epoch": 0.44, "learning_rate": 6.255971230909239e-06, "loss": 0.4703, "step": 897 }, { "epoch": 0.44, "learning_rate": 6.248336984313035e-06, "loss": 0.4983, "step": 898 }, { "epoch": 0.44, "learning_rate": 6.240699632779602e-06, "loss": 0.3713, "step": 899 }, { "epoch": 0.44, "learning_rate": 6.23305919530501e-06, "loss": 0.3393, "step": 900 }, { "epoch": 0.44, "learning_rate": 6.2254156908930045e-06, "loss": 0.3588, "step": 901 }, { "epoch": 0.44, "learning_rate": 6.2177691385549595e-06, "loss": 0.4854, "step": 902 }, { "epoch": 0.44, "learning_rate": 6.210119557309834e-06, "loss": 0.4023, "step": 903 }, { "epoch": 0.44, "learning_rate": 6.202466966184112e-06, "loss": 0.3539, "step": 904 }, { "epoch": 0.44, "learning_rate": 6.194811384211769e-06, "loss": 0.4516, "step": 905 }, { "epoch": 0.44, "learning_rate": 6.18715283043422e-06, "loss": 0.3254, "step": 906 }, { "epoch": 0.44, "learning_rate": 6.179491323900273e-06, "loss": 0.4185, "step": 907 }, { "epoch": 0.44, "learning_rate": 6.171826883666075e-06, "loss": 0.354, "step": 908 }, { "epoch": 0.44, "learning_rate": 6.164159528795074e-06, "loss": 0.3496, "step": 909 }, { "epoch": 0.44, "learning_rate": 6.156489278357967e-06, "loss": 0.4513, "step": 910 }, { "epoch": 0.44, "learning_rate": 6.148816151432649e-06, "loss": 0.4228, "step": 911 }, { "epoch": 0.44, "learning_rate": 6.141140167104179e-06, "loss": 0.3718, "step": 912 }, { "epoch": 0.44, "learning_rate": 6.133461344464713e-06, "loss": 0.3767, "step": 913 }, { "epoch": 0.44, "learning_rate": 6.125779702613471e-06, "loss": 0.3719, "step": 914 }, { "epoch": 0.45, "learning_rate": 6.118095260656686e-06, "loss": 0.3446, "step": 915 }, { "epoch": 0.45, "learning_rate": 6.110408037707551e-06, "loss": 0.4016, "step": 916 }, { "epoch": 0.45, "learning_rate": 6.102718052886184e-06, "loss": 0.3238, "step": 917 }, { "epoch": 0.45, "learning_rate": 6.0950253253195656e-06, "loss": 0.3754, "step": 918 }, { "epoch": 0.45, "learning_rate": 6.087329874141501e-06, "loss": 0.3877, "step": 919 }, { "epoch": 0.45, "learning_rate": 6.079631718492569e-06, "loss": 0.4175, "step": 920 }, { "epoch": 0.45, "learning_rate": 6.071930877520076e-06, "loss": 0.3682, "step": 921 }, { "epoch": 0.45, "learning_rate": 6.064227370378007e-06, "loss": 0.444, "step": 922 }, { "epoch": 0.45, "learning_rate": 6.056521216226978e-06, "loss": 0.4347, "step": 923 }, { "epoch": 0.45, "learning_rate": 6.048812434234189e-06, "loss": 0.4807, "step": 924 }, { "epoch": 0.45, "learning_rate": 6.041101043573376e-06, "loss": 0.4093, "step": 925 }, { "epoch": 0.45, "learning_rate": 6.033387063424765e-06, "loss": 0.4801, "step": 926 }, { "epoch": 0.45, "learning_rate": 6.025670512975022e-06, "loss": 0.3258, "step": 927 }, { "epoch": 0.45, "learning_rate": 6.017951411417203e-06, "loss": 0.3949, "step": 928 }, { "epoch": 0.45, "learning_rate": 6.0102297779507136e-06, "loss": 0.3312, "step": 929 }, { "epoch": 0.45, "learning_rate": 6.002505631781257e-06, "loss": 0.4036, "step": 930 }, { "epoch": 0.45, "learning_rate": 5.994778992120779e-06, "loss": 0.4128, "step": 931 }, { "epoch": 0.45, "learning_rate": 5.987049878187437e-06, "loss": 0.4142, "step": 932 }, { "epoch": 0.45, "learning_rate": 5.979318309205535e-06, "loss": 0.4944, "step": 933 }, { "epoch": 0.45, "learning_rate": 5.971584304405489e-06, "loss": 0.4352, "step": 934 }, { "epoch": 0.46, "learning_rate": 5.96384788302377e-06, "loss": 0.3158, "step": 935 }, { "epoch": 0.46, "learning_rate": 5.956109064302862e-06, "loss": 0.3766, "step": 936 }, { "epoch": 0.46, "learning_rate": 5.948367867491207e-06, "loss": 0.5292, "step": 937 }, { "epoch": 0.46, "learning_rate": 5.94062431184317e-06, "loss": 0.3497, "step": 938 }, { "epoch": 0.46, "learning_rate": 5.9328784166189744e-06, "loss": 0.4, "step": 939 }, { "epoch": 0.46, "learning_rate": 5.92513020108467e-06, "loss": 0.3889, "step": 940 }, { "epoch": 0.46, "learning_rate": 5.917379684512071e-06, "loss": 0.3697, "step": 941 }, { "epoch": 0.46, "learning_rate": 5.909626886178721e-06, "loss": 0.3991, "step": 942 }, { "epoch": 0.46, "learning_rate": 5.901871825367835e-06, "loss": 0.4059, "step": 943 }, { "epoch": 0.46, "learning_rate": 5.894114521368259e-06, "loss": 0.4022, "step": 944 }, { "epoch": 0.46, "learning_rate": 5.8863549934744145e-06, "loss": 0.4455, "step": 945 }, { "epoch": 0.46, "learning_rate": 5.878593260986256e-06, "loss": 0.3456, "step": 946 }, { "epoch": 0.46, "learning_rate": 5.870829343209221e-06, "loss": 0.3706, "step": 947 }, { "epoch": 0.46, "learning_rate": 5.863063259454185e-06, "loss": 0.3698, "step": 948 }, { "epoch": 0.46, "learning_rate": 5.855295029037405e-06, "loss": 0.3609, "step": 949 }, { "epoch": 0.46, "learning_rate": 5.8475246712804845e-06, "loss": 0.3735, "step": 950 }, { "epoch": 0.46, "learning_rate": 5.8397522055103125e-06, "loss": 0.4363, "step": 951 }, { "epoch": 0.46, "learning_rate": 5.8319776510590235e-06, "loss": 0.4253, "step": 952 }, { "epoch": 0.46, "learning_rate": 5.824201027263948e-06, "loss": 0.3574, "step": 953 }, { "epoch": 0.46, "learning_rate": 5.816422353467562e-06, "loss": 0.3581, "step": 954 }, { "epoch": 0.46, "learning_rate": 5.808641649017442e-06, "loss": 0.4801, "step": 955 }, { "epoch": 0.47, "learning_rate": 5.800858933266214e-06, "loss": 0.4116, "step": 956 }, { "epoch": 0.47, "learning_rate": 5.793074225571502e-06, "loss": 0.3971, "step": 957 }, { "epoch": 0.47, "learning_rate": 5.785287545295895e-06, "loss": 0.3939, "step": 958 }, { "epoch": 0.47, "learning_rate": 5.77749891180688e-06, "loss": 0.2981, "step": 959 }, { "epoch": 0.47, "learning_rate": 5.7697083444768065e-06, "loss": 0.3903, "step": 960 }, { "epoch": 0.47, "learning_rate": 5.76191586268283e-06, "loss": 0.4466, "step": 961 }, { "epoch": 0.47, "learning_rate": 5.7541214858068705e-06, "loss": 0.4341, "step": 962 }, { "epoch": 0.47, "learning_rate": 5.74632523323556e-06, "loss": 0.3679, "step": 963 }, { "epoch": 0.47, "learning_rate": 5.738527124360199e-06, "loss": 0.3474, "step": 964 }, { "epoch": 0.47, "learning_rate": 5.730727178576703e-06, "loss": 0.3594, "step": 965 }, { "epoch": 0.47, "learning_rate": 5.722925415285555e-06, "loss": 0.4497, "step": 966 }, { "epoch": 0.47, "learning_rate": 5.715121853891759e-06, "loss": 0.4021, "step": 967 }, { "epoch": 0.47, "learning_rate": 5.707316513804793e-06, "loss": 0.3865, "step": 968 }, { "epoch": 0.47, "learning_rate": 5.69950941443856e-06, "loss": 0.3427, "step": 969 }, { "epoch": 0.47, "learning_rate": 5.691700575211335e-06, "loss": 0.4294, "step": 970 }, { "epoch": 0.47, "learning_rate": 5.683890015545724e-06, "loss": 0.3948, "step": 971 }, { "epoch": 0.47, "learning_rate": 5.6760777548686096e-06, "loss": 0.4446, "step": 972 }, { "epoch": 0.47, "learning_rate": 5.6682638126111055e-06, "loss": 0.3924, "step": 973 }, { "epoch": 0.47, "learning_rate": 5.660448208208513e-06, "loss": 0.348, "step": 974 }, { "epoch": 0.47, "learning_rate": 5.65263096110026e-06, "loss": 0.4286, "step": 975 }, { "epoch": 0.47, "learning_rate": 5.644812090729863e-06, "loss": 0.4107, "step": 976 }, { "epoch": 0.48, "learning_rate": 5.636991616544878e-06, "loss": 0.325, "step": 977 }, { "epoch": 0.48, "learning_rate": 5.629169557996848e-06, "loss": 0.3878, "step": 978 }, { "epoch": 0.48, "learning_rate": 5.62134593454126e-06, "loss": 0.3444, "step": 979 }, { "epoch": 0.48, "learning_rate": 5.613520765637489e-06, "loss": 0.3203, "step": 980 }, { "epoch": 0.48, "learning_rate": 5.605694070748755e-06, "loss": 0.3567, "step": 981 }, { "epoch": 0.48, "learning_rate": 5.597865869342075e-06, "loss": 0.3717, "step": 982 }, { "epoch": 0.48, "learning_rate": 5.590036180888212e-06, "loss": 0.4194, "step": 983 }, { "epoch": 0.48, "learning_rate": 5.582205024861629e-06, "loss": 0.447, "step": 984 }, { "epoch": 0.48, "learning_rate": 5.574372420740437e-06, "loss": 0.3865, "step": 985 }, { "epoch": 0.48, "learning_rate": 5.566538388006351e-06, "loss": 0.391, "step": 986 }, { "epoch": 0.48, "learning_rate": 5.558702946144636e-06, "loss": 0.458, "step": 987 }, { "epoch": 0.48, "learning_rate": 5.550866114644068e-06, "loss": 0.3506, "step": 988 }, { "epoch": 0.48, "learning_rate": 5.543027912996872e-06, "loss": 0.4155, "step": 989 }, { "epoch": 0.48, "learning_rate": 5.535188360698687e-06, "loss": 0.4079, "step": 990 }, { "epoch": 0.48, "learning_rate": 5.527347477248508e-06, "loss": 0.3803, "step": 991 }, { "epoch": 0.48, "learning_rate": 5.519505282148644e-06, "loss": 0.4116, "step": 992 }, { "epoch": 0.48, "learning_rate": 5.511661794904659e-06, "loss": 0.377, "step": 993 }, { "epoch": 0.48, "learning_rate": 5.503817035025341e-06, "loss": 0.3665, "step": 994 }, { "epoch": 0.48, "learning_rate": 5.495971022022638e-06, "loss": 0.3157, "step": 995 }, { "epoch": 0.48, "learning_rate": 5.4881237754116135e-06, "loss": 0.3577, "step": 996 }, { "epoch": 0.49, "learning_rate": 5.480275314710401e-06, "loss": 0.3617, "step": 997 }, { "epoch": 0.49, "learning_rate": 5.472425659440157e-06, "loss": 0.3593, "step": 998 }, { "epoch": 0.49, "learning_rate": 5.464574829125002e-06, "loss": 0.3169, "step": 999 }, { "epoch": 0.49, "learning_rate": 5.456722843291987e-06, "loss": 0.3921, "step": 1000 }, { "epoch": 0.49, "learning_rate": 5.448869721471033e-06, "loss": 0.3841, "step": 1001 }, { "epoch": 0.49, "learning_rate": 5.441015483194883e-06, "loss": 0.3915, "step": 1002 }, { "epoch": 0.49, "learning_rate": 5.4331601479990655e-06, "loss": 0.3496, "step": 1003 }, { "epoch": 0.49, "learning_rate": 5.425303735421828e-06, "loss": 0.4248, "step": 1004 }, { "epoch": 0.49, "learning_rate": 5.417446265004107e-06, "loss": 0.3969, "step": 1005 }, { "epoch": 0.49, "learning_rate": 5.409587756289462e-06, "loss": 0.4176, "step": 1006 }, { "epoch": 0.49, "learning_rate": 5.401728228824042e-06, "loss": 0.4176, "step": 1007 }, { "epoch": 0.49, "learning_rate": 5.3938677021565225e-06, "loss": 0.3686, "step": 1008 }, { "epoch": 0.49, "learning_rate": 5.386006195838069e-06, "loss": 0.3953, "step": 1009 }, { "epoch": 0.49, "learning_rate": 5.378143729422285e-06, "loss": 0.3839, "step": 1010 }, { "epoch": 0.49, "learning_rate": 5.370280322465157e-06, "loss": 0.4168, "step": 1011 }, { "epoch": 0.49, "learning_rate": 5.3624159945250155e-06, "loss": 0.3947, "step": 1012 }, { "epoch": 0.49, "learning_rate": 5.354550765162479e-06, "loss": 0.3941, "step": 1013 }, { "epoch": 0.49, "learning_rate": 5.346684653940408e-06, "loss": 0.349, "step": 1014 }, { "epoch": 0.49, "learning_rate": 5.3388176804238614e-06, "loss": 0.3815, "step": 1015 }, { "epoch": 0.49, "learning_rate": 5.330949864180034e-06, "loss": 0.3344, "step": 1016 }, { "epoch": 0.49, "learning_rate": 5.323081224778225e-06, "loss": 0.3417, "step": 1017 }, { "epoch": 0.5, "learning_rate": 5.315211781789775e-06, "loss": 0.3688, "step": 1018 }, { "epoch": 0.5, "learning_rate": 5.307341554788027e-06, "loss": 0.403, "step": 1019 }, { "epoch": 0.5, "learning_rate": 5.299470563348273e-06, "loss": 0.3643, "step": 1020 }, { "epoch": 0.5, "learning_rate": 5.291598827047706e-06, "loss": 0.4343, "step": 1021 }, { "epoch": 0.5, "learning_rate": 5.2837263654653715e-06, "loss": 0.4941, "step": 1022 }, { "epoch": 0.5, "learning_rate": 5.275853198182119e-06, "loss": 0.4315, "step": 1023 }, { "epoch": 0.5, "learning_rate": 5.267979344780555e-06, "loss": 0.4333, "step": 1024 }, { "epoch": 0.5, "learning_rate": 5.2601048248449894e-06, "loss": 0.3629, "step": 1025 }, { "epoch": 0.5, "learning_rate": 5.252229657961394e-06, "loss": 0.4676, "step": 1026 }, { "epoch": 0.5, "learning_rate": 5.2443538637173464e-06, "loss": 0.4025, "step": 1027 }, { "epoch": 0.5, "learning_rate": 5.236477461701985e-06, "loss": 0.3908, "step": 1028 }, { "epoch": 0.5, "learning_rate": 5.2286004715059615e-06, "loss": 0.3876, "step": 1029 }, { "epoch": 0.5, "learning_rate": 5.2207229127213866e-06, "loss": 0.4106, "step": 1030 }, { "epoch": 0.5, "learning_rate": 5.212844804941792e-06, "loss": 0.4578, "step": 1031 }, { "epoch": 0.5, "learning_rate": 5.20496616776207e-06, "loss": 0.3005, "step": 1032 }, { "epoch": 0.5, "learning_rate": 5.197087020778431e-06, "loss": 0.3894, "step": 1033 }, { "epoch": 0.5, "learning_rate": 5.189207383588353e-06, "loss": 0.4441, "step": 1034 }, { "epoch": 0.5, "learning_rate": 5.181327275790532e-06, "loss": 0.3943, "step": 1035 }, { "epoch": 0.5, "learning_rate": 5.173446716984837e-06, "loss": 0.3954, "step": 1036 }, { "epoch": 0.5, "learning_rate": 5.165565726772258e-06, "loss": 0.3319, "step": 1037 }, { "epoch": 0.51, "learning_rate": 5.157684324754858e-06, "loss": 0.3792, "step": 1038 }, { "epoch": 0.51, "learning_rate": 5.149802530535724e-06, "loss": 0.8867, "step": 1039 }, { "epoch": 0.51, "learning_rate": 5.141920363718916e-06, "loss": 0.4528, "step": 1040 }, { "epoch": 0.51, "learning_rate": 5.1340378439094276e-06, "loss": 0.4249, "step": 1041 }, { "epoch": 0.51, "learning_rate": 5.126154990713123e-06, "loss": 0.487, "step": 1042 }, { "epoch": 0.51, "learning_rate": 5.118271823736699e-06, "loss": 0.3887, "step": 1043 }, { "epoch": 0.51, "learning_rate": 5.1103883625876335e-06, "loss": 0.4042, "step": 1044 }, { "epoch": 0.51, "learning_rate": 5.102504626874137e-06, "loss": 0.3886, "step": 1045 }, { "epoch": 0.51, "learning_rate": 5.094620636205096e-06, "loss": 0.4687, "step": 1046 }, { "epoch": 0.51, "learning_rate": 5.08673641019004e-06, "loss": 0.4373, "step": 1047 }, { "epoch": 0.51, "learning_rate": 5.078851968439078e-06, "loss": 0.4578, "step": 1048 }, { "epoch": 0.51, "learning_rate": 5.070967330562859e-06, "loss": 0.3001, "step": 1049 }, { "epoch": 0.51, "learning_rate": 5.06308251617252e-06, "loss": 0.3752, "step": 1050 }, { "epoch": 0.51, "learning_rate": 5.05519754487963e-06, "loss": 0.4472, "step": 1051 }, { "epoch": 0.51, "learning_rate": 5.047312436296159e-06, "loss": 0.3402, "step": 1052 }, { "epoch": 0.51, "learning_rate": 5.039427210034411e-06, "loss": 0.3411, "step": 1053 }, { "epoch": 0.51, "learning_rate": 5.031541885706987e-06, "loss": 0.4363, "step": 1054 }, { "epoch": 0.51, "learning_rate": 5.023656482926728e-06, "loss": 0.343, "step": 1055 }, { "epoch": 0.51, "learning_rate": 5.01577102130667e-06, "loss": 0.4239, "step": 1056 }, { "epoch": 0.51, "learning_rate": 5.007885520460001e-06, "loss": 0.4185, "step": 1057 }, { "epoch": 0.51, "learning_rate": 5e-06, "loss": 0.3948, "step": 1058 }, { "epoch": 0.52, "learning_rate": 4.992114479540001e-06, "loss": 0.3264, "step": 1059 }, { "epoch": 0.52, "learning_rate": 4.9842289786933316e-06, "loss": 0.3976, "step": 1060 }, { "epoch": 0.52, "learning_rate": 4.976343517073274e-06, "loss": 0.3837, "step": 1061 }, { "epoch": 0.52, "learning_rate": 4.9684581142930135e-06, "loss": 0.4203, "step": 1062 }, { "epoch": 0.52, "learning_rate": 4.960572789965589e-06, "loss": 0.3696, "step": 1063 }, { "epoch": 0.52, "learning_rate": 4.952687563703841e-06, "loss": 0.3625, "step": 1064 }, { "epoch": 0.52, "learning_rate": 4.944802455120371e-06, "loss": 0.3736, "step": 1065 }, { "epoch": 0.52, "learning_rate": 4.936917483827483e-06, "loss": 0.3429, "step": 1066 }, { "epoch": 0.52, "learning_rate": 4.929032669437142e-06, "loss": 0.8758, "step": 1067 }, { "epoch": 0.52, "learning_rate": 4.921148031560924e-06, "loss": 0.3801, "step": 1068 }, { "epoch": 0.52, "learning_rate": 4.9132635898099625e-06, "loss": 0.397, "step": 1069 }, { "epoch": 0.52, "learning_rate": 4.905379363794907e-06, "loss": 0.3099, "step": 1070 }, { "epoch": 0.52, "learning_rate": 4.897495373125866e-06, "loss": 0.3761, "step": 1071 }, { "epoch": 0.52, "learning_rate": 4.889611637412367e-06, "loss": 0.4288, "step": 1072 }, { "epoch": 0.52, "learning_rate": 4.881728176263302e-06, "loss": 0.3624, "step": 1073 }, { "epoch": 0.52, "learning_rate": 4.873845009286879e-06, "loss": 0.3796, "step": 1074 }, { "epoch": 0.52, "learning_rate": 4.865962156090575e-06, "loss": 0.3496, "step": 1075 }, { "epoch": 0.52, "learning_rate": 4.858079636281086e-06, "loss": 0.3811, "step": 1076 }, { "epoch": 0.52, "learning_rate": 4.850197469464278e-06, "loss": 0.3602, "step": 1077 }, { "epoch": 0.52, "learning_rate": 4.842315675245144e-06, "loss": 0.3994, "step": 1078 }, { "epoch": 0.53, "learning_rate": 4.834434273227743e-06, "loss": 0.3715, "step": 1079 }, { "epoch": 0.53, "learning_rate": 4.826553283015165e-06, "loss": 0.4151, "step": 1080 }, { "epoch": 0.53, "learning_rate": 4.81867272420947e-06, "loss": 0.3352, "step": 1081 }, { "epoch": 0.53, "learning_rate": 4.81079261641165e-06, "loss": 0.348, "step": 1082 }, { "epoch": 0.53, "learning_rate": 4.802912979221569e-06, "loss": 0.4204, "step": 1083 }, { "epoch": 0.53, "learning_rate": 4.79503383223793e-06, "loss": 0.3581, "step": 1084 }, { "epoch": 0.53, "learning_rate": 4.7871551950582105e-06, "loss": 0.4514, "step": 1085 }, { "epoch": 0.53, "learning_rate": 4.779277087278615e-06, "loss": 0.3867, "step": 1086 }, { "epoch": 0.53, "learning_rate": 4.771399528494042e-06, "loss": 0.3624, "step": 1087 }, { "epoch": 0.53, "learning_rate": 4.763522538298018e-06, "loss": 0.4512, "step": 1088 }, { "epoch": 0.53, "learning_rate": 4.755646136282656e-06, "loss": 0.363, "step": 1089 }, { "epoch": 0.53, "learning_rate": 4.747770342038608e-06, "loss": 0.4235, "step": 1090 }, { "epoch": 0.53, "learning_rate": 4.739895175155012e-06, "loss": 0.4407, "step": 1091 }, { "epoch": 0.53, "learning_rate": 4.732020655219447e-06, "loss": 0.369, "step": 1092 }, { "epoch": 0.53, "learning_rate": 4.724146801817882e-06, "loss": 0.4074, "step": 1093 }, { "epoch": 0.53, "learning_rate": 4.71627363453463e-06, "loss": 0.3681, "step": 1094 }, { "epoch": 0.53, "learning_rate": 4.708401172952296e-06, "loss": 0.3726, "step": 1095 }, { "epoch": 0.53, "learning_rate": 4.700529436651729e-06, "loss": 0.3928, "step": 1096 }, { "epoch": 0.53, "learning_rate": 4.692658445211974e-06, "loss": 0.3975, "step": 1097 }, { "epoch": 0.53, "learning_rate": 4.684788218210226e-06, "loss": 0.3575, "step": 1098 }, { "epoch": 0.53, "learning_rate": 4.676918775221776e-06, "loss": 0.3246, "step": 1099 }, { "epoch": 0.54, "learning_rate": 4.669050135819966e-06, "loss": 0.3965, "step": 1100 }, { "epoch": 0.54, "learning_rate": 4.661182319576139e-06, "loss": 0.2961, "step": 1101 }, { "epoch": 0.54, "learning_rate": 4.653315346059592e-06, "loss": 0.3939, "step": 1102 }, { "epoch": 0.54, "learning_rate": 4.645449234837523e-06, "loss": 0.4053, "step": 1103 }, { "epoch": 0.54, "learning_rate": 4.637584005474987e-06, "loss": 0.4008, "step": 1104 }, { "epoch": 0.54, "learning_rate": 4.6297196775348454e-06, "loss": 0.3416, "step": 1105 }, { "epoch": 0.54, "learning_rate": 4.6218562705777185e-06, "loss": 0.3947, "step": 1106 }, { "epoch": 0.54, "learning_rate": 4.6139938041619325e-06, "loss": 0.3747, "step": 1107 }, { "epoch": 0.54, "learning_rate": 4.60613229784348e-06, "loss": 0.432, "step": 1108 }, { "epoch": 0.54, "learning_rate": 4.59827177117596e-06, "loss": 0.413, "step": 1109 }, { "epoch": 0.54, "learning_rate": 4.5904122437105384e-06, "loss": 0.3612, "step": 1110 }, { "epoch": 0.54, "learning_rate": 4.582553734995894e-06, "loss": 0.411, "step": 1111 }, { "epoch": 0.54, "learning_rate": 4.574696264578173e-06, "loss": 0.372, "step": 1112 }, { "epoch": 0.54, "learning_rate": 4.566839852000936e-06, "loss": 0.3369, "step": 1113 }, { "epoch": 0.54, "learning_rate": 4.5589845168051176e-06, "loss": 0.4469, "step": 1114 }, { "epoch": 0.54, "learning_rate": 4.551130278528968e-06, "loss": 0.4058, "step": 1115 }, { "epoch": 0.54, "learning_rate": 4.543277156708013e-06, "loss": 0.3466, "step": 1116 }, { "epoch": 0.54, "learning_rate": 4.535425170874998e-06, "loss": 0.4191, "step": 1117 }, { "epoch": 0.54, "learning_rate": 4.527574340559844e-06, "loss": 0.3677, "step": 1118 }, { "epoch": 0.54, "learning_rate": 4.519724685289598e-06, "loss": 0.4173, "step": 1119 }, { "epoch": 0.55, "learning_rate": 4.5118762245883865e-06, "loss": 0.3343, "step": 1120 }, { "epoch": 0.55, "learning_rate": 4.504028977977364e-06, "loss": 0.4289, "step": 1121 }, { "epoch": 0.55, "learning_rate": 4.4961829649746595e-06, "loss": 0.3244, "step": 1122 }, { "epoch": 0.55, "learning_rate": 4.4883382050953415e-06, "loss": 0.3488, "step": 1123 }, { "epoch": 0.55, "learning_rate": 4.480494717851359e-06, "loss": 0.3875, "step": 1124 }, { "epoch": 0.55, "learning_rate": 4.472652522751493e-06, "loss": 0.4233, "step": 1125 }, { "epoch": 0.55, "learning_rate": 4.464811639301314e-06, "loss": 0.3352, "step": 1126 }, { "epoch": 0.55, "learning_rate": 4.45697208700313e-06, "loss": 0.4133, "step": 1127 }, { "epoch": 0.55, "learning_rate": 4.449133885355934e-06, "loss": 0.3515, "step": 1128 }, { "epoch": 0.55, "learning_rate": 4.441297053855365e-06, "loss": 0.412, "step": 1129 }, { "epoch": 0.55, "learning_rate": 4.4334616119936516e-06, "loss": 0.3981, "step": 1130 }, { "epoch": 0.55, "learning_rate": 4.425627579259565e-06, "loss": 0.3607, "step": 1131 }, { "epoch": 0.55, "learning_rate": 4.4177949751383725e-06, "loss": 0.4057, "step": 1132 }, { "epoch": 0.55, "learning_rate": 4.409963819111789e-06, "loss": 0.326, "step": 1133 }, { "epoch": 0.55, "learning_rate": 4.402134130657925e-06, "loss": 0.3794, "step": 1134 }, { "epoch": 0.55, "learning_rate": 4.3943059292512455e-06, "loss": 0.4136, "step": 1135 }, { "epoch": 0.55, "learning_rate": 4.386479234362512e-06, "loss": 0.4055, "step": 1136 }, { "epoch": 0.55, "learning_rate": 4.37865406545874e-06, "loss": 0.3707, "step": 1137 }, { "epoch": 0.55, "learning_rate": 4.370830442003152e-06, "loss": 0.3609, "step": 1138 }, { "epoch": 0.55, "learning_rate": 4.363008383455124e-06, "loss": 0.4225, "step": 1139 }, { "epoch": 0.55, "learning_rate": 4.35518790927014e-06, "loss": 0.3664, "step": 1140 }, { "epoch": 0.56, "learning_rate": 4.347369038899744e-06, "loss": 0.4215, "step": 1141 }, { "epoch": 0.56, "learning_rate": 4.33955179179149e-06, "loss": 0.3903, "step": 1142 }, { "epoch": 0.56, "learning_rate": 4.331736187388896e-06, "loss": 0.3805, "step": 1143 }, { "epoch": 0.56, "learning_rate": 4.323922245131392e-06, "loss": 0.3112, "step": 1144 }, { "epoch": 0.56, "learning_rate": 4.316109984454278e-06, "loss": 0.3309, "step": 1145 }, { "epoch": 0.56, "learning_rate": 4.308299424788667e-06, "loss": 0.3764, "step": 1146 }, { "epoch": 0.56, "learning_rate": 4.300490585561442e-06, "loss": 0.3724, "step": 1147 }, { "epoch": 0.56, "learning_rate": 4.292683486195208e-06, "loss": 0.3709, "step": 1148 }, { "epoch": 0.56, "learning_rate": 4.284878146108244e-06, "loss": 0.3927, "step": 1149 }, { "epoch": 0.56, "learning_rate": 4.277074584714447e-06, "loss": 0.4639, "step": 1150 }, { "epoch": 0.56, "learning_rate": 4.269272821423298e-06, "loss": 0.4463, "step": 1151 }, { "epoch": 0.56, "learning_rate": 4.261472875639801e-06, "loss": 0.3263, "step": 1152 }, { "epoch": 0.56, "learning_rate": 4.253674766764441e-06, "loss": 0.4157, "step": 1153 }, { "epoch": 0.56, "learning_rate": 4.245878514193131e-06, "loss": 0.424, "step": 1154 }, { "epoch": 0.56, "learning_rate": 4.238084137317171e-06, "loss": 0.3853, "step": 1155 }, { "epoch": 0.56, "learning_rate": 4.230291655523197e-06, "loss": 0.3067, "step": 1156 }, { "epoch": 0.56, "learning_rate": 4.222501088193121e-06, "loss": 0.3961, "step": 1157 }, { "epoch": 0.56, "learning_rate": 4.214712454704107e-06, "loss": 0.3822, "step": 1158 }, { "epoch": 0.56, "learning_rate": 4.206925774428499e-06, "loss": 0.359, "step": 1159 }, { "epoch": 0.56, "learning_rate": 4.1991410667337896e-06, "loss": 0.3708, "step": 1160 }, { "epoch": 0.57, "learning_rate": 4.191358350982559e-06, "loss": 0.2961, "step": 1161 }, { "epoch": 0.57, "learning_rate": 4.183577646532439e-06, "loss": 0.3681, "step": 1162 }, { "epoch": 0.57, "learning_rate": 4.175798972736053e-06, "loss": 0.3094, "step": 1163 }, { "epoch": 0.57, "learning_rate": 4.168022348940978e-06, "loss": 0.3664, "step": 1164 }, { "epoch": 0.57, "learning_rate": 4.160247794489689e-06, "loss": 0.3964, "step": 1165 }, { "epoch": 0.57, "learning_rate": 4.152475328719517e-06, "loss": 0.4465, "step": 1166 }, { "epoch": 0.57, "learning_rate": 4.1447049709625965e-06, "loss": 0.3754, "step": 1167 }, { "epoch": 0.57, "learning_rate": 4.136936740545817e-06, "loss": 0.4411, "step": 1168 }, { "epoch": 0.57, "learning_rate": 4.1291706567907794e-06, "loss": 0.3326, "step": 1169 }, { "epoch": 0.57, "learning_rate": 4.121406739013746e-06, "loss": 0.3382, "step": 1170 }, { "epoch": 0.57, "learning_rate": 4.1136450065255855e-06, "loss": 0.3698, "step": 1171 }, { "epoch": 0.57, "learning_rate": 4.105885478631741e-06, "loss": 0.381, "step": 1172 }, { "epoch": 0.57, "learning_rate": 4.098128174632164e-06, "loss": 0.3655, "step": 1173 }, { "epoch": 0.57, "learning_rate": 4.090373113821281e-06, "loss": 0.3838, "step": 1174 }, { "epoch": 0.57, "learning_rate": 4.082620315487931e-06, "loss": 0.3337, "step": 1175 }, { "epoch": 0.57, "learning_rate": 4.074869798915333e-06, "loss": 0.3522, "step": 1176 }, { "epoch": 0.57, "learning_rate": 4.067121583381027e-06, "loss": 0.38, "step": 1177 }, { "epoch": 0.57, "learning_rate": 4.059375688156833e-06, "loss": 0.3552, "step": 1178 }, { "epoch": 0.57, "learning_rate": 4.0516321325087945e-06, "loss": 0.4275, "step": 1179 }, { "epoch": 0.57, "learning_rate": 4.0438909356971405e-06, "loss": 0.3167, "step": 1180 }, { "epoch": 0.57, "learning_rate": 4.036152116976231e-06, "loss": 0.3997, "step": 1181 }, { "epoch": 0.58, "learning_rate": 4.028415695594512e-06, "loss": 0.3973, "step": 1182 }, { "epoch": 0.58, "learning_rate": 4.020681690794467e-06, "loss": 0.3412, "step": 1183 }, { "epoch": 0.58, "learning_rate": 4.012950121812566e-06, "loss": 0.3955, "step": 1184 }, { "epoch": 0.58, "learning_rate": 4.0052210078792234e-06, "loss": 0.4135, "step": 1185 }, { "epoch": 0.58, "learning_rate": 3.997494368218745e-06, "loss": 0.3746, "step": 1186 }, { "epoch": 0.58, "learning_rate": 3.989770222049286e-06, "loss": 0.372, "step": 1187 }, { "epoch": 0.58, "learning_rate": 3.9820485885827974e-06, "loss": 0.422, "step": 1188 }, { "epoch": 0.58, "learning_rate": 3.974329487024979e-06, "loss": 0.3666, "step": 1189 }, { "epoch": 0.58, "learning_rate": 3.966612936575235e-06, "loss": 0.3932, "step": 1190 }, { "epoch": 0.58, "learning_rate": 3.958898956426625e-06, "loss": 0.3764, "step": 1191 }, { "epoch": 0.58, "learning_rate": 3.9511875657658136e-06, "loss": 0.4445, "step": 1192 }, { "epoch": 0.58, "learning_rate": 3.9434787837730245e-06, "loss": 0.3406, "step": 1193 }, { "epoch": 0.58, "learning_rate": 3.935772629621996e-06, "loss": 0.3369, "step": 1194 }, { "epoch": 0.58, "learning_rate": 3.928069122479925e-06, "loss": 0.3858, "step": 1195 }, { "epoch": 0.58, "learning_rate": 3.920368281507431e-06, "loss": 0.3517, "step": 1196 }, { "epoch": 0.58, "learning_rate": 3.912670125858501e-06, "loss": 0.3563, "step": 1197 }, { "epoch": 0.58, "learning_rate": 3.904974674680436e-06, "loss": 0.3619, "step": 1198 }, { "epoch": 0.58, "learning_rate": 3.897281947113817e-06, "loss": 0.386, "step": 1199 }, { "epoch": 0.58, "learning_rate": 3.88959196229245e-06, "loss": 0.3522, "step": 1200 }, { "epoch": 0.58, "learning_rate": 3.881904739343316e-06, "loss": 0.4112, "step": 1201 }, { "epoch": 0.58, "learning_rate": 3.87422029738653e-06, "loss": 0.3608, "step": 1202 }, { "epoch": 0.59, "learning_rate": 3.866538655535288e-06, "loss": 0.3368, "step": 1203 }, { "epoch": 0.59, "learning_rate": 3.8588598328958225e-06, "loss": 0.5167, "step": 1204 }, { "epoch": 0.59, "learning_rate": 3.851183848567351e-06, "loss": 0.3595, "step": 1205 }, { "epoch": 0.59, "learning_rate": 3.843510721642036e-06, "loss": 0.4077, "step": 1206 }, { "epoch": 0.59, "learning_rate": 3.835840471204927e-06, "loss": 0.3522, "step": 1207 }, { "epoch": 0.59, "learning_rate": 3.828173116333925e-06, "loss": 0.3419, "step": 1208 }, { "epoch": 0.59, "learning_rate": 3.820508676099728e-06, "loss": 0.375, "step": 1209 }, { "epoch": 0.59, "learning_rate": 3.812847169565782e-06, "loss": 0.449, "step": 1210 }, { "epoch": 0.59, "learning_rate": 3.8051886157882335e-06, "loss": 0.4411, "step": 1211 }, { "epoch": 0.59, "learning_rate": 3.7975330338158913e-06, "loss": 0.3631, "step": 1212 }, { "epoch": 0.59, "learning_rate": 3.7898804426901687e-06, "loss": 0.4685, "step": 1213 }, { "epoch": 0.59, "learning_rate": 3.782230861445041e-06, "loss": 0.2624, "step": 1214 }, { "epoch": 0.59, "learning_rate": 3.7745843091069976e-06, "loss": 0.4745, "step": 1215 }, { "epoch": 0.59, "learning_rate": 3.766940804694992e-06, "loss": 0.3969, "step": 1216 }, { "epoch": 0.59, "learning_rate": 3.7593003672204e-06, "loss": 0.3893, "step": 1217 }, { "epoch": 0.59, "learning_rate": 3.751663015686966e-06, "loss": 0.3606, "step": 1218 }, { "epoch": 0.59, "learning_rate": 3.744028769090762e-06, "loss": 0.3993, "step": 1219 }, { "epoch": 0.59, "learning_rate": 3.7363976464201348e-06, "loss": 0.4249, "step": 1220 }, { "epoch": 0.59, "learning_rate": 3.7287696666556607e-06, "loss": 0.4213, "step": 1221 }, { "epoch": 0.59, "learning_rate": 3.7211448487701002e-06, "loss": 0.3312, "step": 1222 }, { "epoch": 0.6, "learning_rate": 3.713523211728351e-06, "loss": 0.298, "step": 1223 }, { "epoch": 0.6, "learning_rate": 3.705904774487396e-06, "loss": 0.3589, "step": 1224 }, { "epoch": 0.6, "learning_rate": 3.6982895559962617e-06, "loss": 0.4603, "step": 1225 }, { "epoch": 0.6, "learning_rate": 3.6906775751959667e-06, "loss": 0.3703, "step": 1226 }, { "epoch": 0.6, "learning_rate": 3.683068851019479e-06, "loss": 0.3201, "step": 1227 }, { "epoch": 0.6, "learning_rate": 3.6754634023916636e-06, "loss": 0.3723, "step": 1228 }, { "epoch": 0.6, "learning_rate": 3.6678612482292403e-06, "loss": 0.3128, "step": 1229 }, { "epoch": 0.6, "learning_rate": 3.6602624074407354e-06, "loss": 0.3866, "step": 1230 }, { "epoch": 0.6, "learning_rate": 3.6526668989264323e-06, "loss": 0.3432, "step": 1231 }, { "epoch": 0.6, "learning_rate": 3.645074741578326e-06, "loss": 0.3725, "step": 1232 }, { "epoch": 0.6, "learning_rate": 3.63748595428008e-06, "loss": 0.3507, "step": 1233 }, { "epoch": 0.6, "learning_rate": 3.62990055590697e-06, "loss": 0.4436, "step": 1234 }, { "epoch": 0.6, "learning_rate": 3.6223185653258467e-06, "loss": 0.3823, "step": 1235 }, { "epoch": 0.6, "learning_rate": 3.6147400013950833e-06, "loss": 0.3862, "step": 1236 }, { "epoch": 0.6, "learning_rate": 3.6071648829645302e-06, "loss": 0.3706, "step": 1237 }, { "epoch": 0.6, "learning_rate": 3.5995932288754655e-06, "loss": 0.3859, "step": 1238 }, { "epoch": 0.6, "learning_rate": 3.5920250579605564e-06, "loss": 0.4121, "step": 1239 }, { "epoch": 0.6, "learning_rate": 3.5844603890438013e-06, "loss": 0.3071, "step": 1240 }, { "epoch": 0.6, "learning_rate": 3.5768992409404914e-06, "loss": 0.3477, "step": 1241 }, { "epoch": 0.6, "learning_rate": 3.5693416324571573e-06, "loss": 0.4027, "step": 1242 }, { "epoch": 0.6, "learning_rate": 3.5617875823915295e-06, "loss": 0.448, "step": 1243 }, { "epoch": 0.61, "learning_rate": 3.5542371095324835e-06, "loss": 0.3864, "step": 1244 }, { "epoch": 0.61, "learning_rate": 3.5466902326600043e-06, "loss": 0.427, "step": 1245 }, { "epoch": 0.61, "learning_rate": 3.539146970545124e-06, "loss": 0.3332, "step": 1246 }, { "epoch": 0.61, "learning_rate": 3.5316073419498886e-06, "loss": 0.3923, "step": 1247 }, { "epoch": 0.61, "learning_rate": 3.524071365627308e-06, "loss": 0.4138, "step": 1248 }, { "epoch": 0.61, "learning_rate": 3.516539060321306e-06, "loss": 0.3787, "step": 1249 }, { "epoch": 0.61, "learning_rate": 3.509010444766674e-06, "loss": 0.3871, "step": 1250 }, { "epoch": 0.61, "learning_rate": 3.501485537689029e-06, "loss": 0.4118, "step": 1251 }, { "epoch": 0.61, "learning_rate": 3.493964357804763e-06, "loss": 0.4118, "step": 1252 }, { "epoch": 0.61, "learning_rate": 3.486446923820996e-06, "loss": 0.4207, "step": 1253 }, { "epoch": 0.61, "learning_rate": 3.478933254435534e-06, "loss": 0.3968, "step": 1254 }, { "epoch": 0.61, "learning_rate": 3.471423368336817e-06, "loss": 0.3417, "step": 1255 }, { "epoch": 0.61, "learning_rate": 3.4639172842038766e-06, "loss": 0.3828, "step": 1256 }, { "epoch": 0.61, "learning_rate": 3.456415020706285e-06, "loss": 0.4013, "step": 1257 }, { "epoch": 0.61, "learning_rate": 3.448916596504116e-06, "loss": 0.4013, "step": 1258 }, { "epoch": 0.61, "learning_rate": 3.4414220302478896e-06, "loss": 0.3622, "step": 1259 }, { "epoch": 0.61, "learning_rate": 3.4339313405785337e-06, "loss": 0.2892, "step": 1260 }, { "epoch": 0.61, "learning_rate": 3.4264445461273323e-06, "loss": 0.3571, "step": 1261 }, { "epoch": 0.61, "learning_rate": 3.4189616655158803e-06, "loss": 0.402, "step": 1262 }, { "epoch": 0.61, "learning_rate": 3.4114827173560407e-06, "loss": 0.3718, "step": 1263 }, { "epoch": 0.62, "learning_rate": 3.4040077202498916e-06, "loss": 0.3568, "step": 1264 }, { "epoch": 0.62, "learning_rate": 3.3965366927896864e-06, "loss": 0.3586, "step": 1265 }, { "epoch": 0.62, "learning_rate": 3.389069653557805e-06, "loss": 0.2979, "step": 1266 }, { "epoch": 0.62, "learning_rate": 3.3816066211267057e-06, "loss": 0.3385, "step": 1267 }, { "epoch": 0.62, "learning_rate": 3.3741476140588825e-06, "loss": 0.345, "step": 1268 }, { "epoch": 0.62, "learning_rate": 3.3666926509068175e-06, "loss": 0.3862, "step": 1269 }, { "epoch": 0.62, "learning_rate": 3.359241750212934e-06, "loss": 0.4201, "step": 1270 }, { "epoch": 0.62, "learning_rate": 3.35179493050955e-06, "loss": 0.3458, "step": 1271 }, { "epoch": 0.62, "learning_rate": 3.344352210318834e-06, "loss": 0.3856, "step": 1272 }, { "epoch": 0.62, "learning_rate": 3.3369136081527586e-06, "loss": 0.3484, "step": 1273 }, { "epoch": 0.62, "learning_rate": 3.3294791425130512e-06, "loss": 0.3691, "step": 1274 }, { "epoch": 0.62, "learning_rate": 3.3220488318911544e-06, "loss": 0.3756, "step": 1275 }, { "epoch": 0.62, "learning_rate": 3.3146226947681724e-06, "loss": 0.3981, "step": 1276 }, { "epoch": 0.62, "learning_rate": 3.3072007496148323e-06, "loss": 0.3685, "step": 1277 }, { "epoch": 0.62, "learning_rate": 3.2997830148914316e-06, "loss": 0.329, "step": 1278 }, { "epoch": 0.62, "learning_rate": 3.2923695090477975e-06, "loss": 0.3898, "step": 1279 }, { "epoch": 0.62, "learning_rate": 3.284960250523237e-06, "loss": 0.3852, "step": 1280 }, { "epoch": 0.62, "learning_rate": 3.2775552577464973e-06, "loss": 0.3369, "step": 1281 }, { "epoch": 0.62, "learning_rate": 3.270154549135708e-06, "loss": 0.3225, "step": 1282 }, { "epoch": 0.62, "learning_rate": 3.262758143098348e-06, "loss": 0.3569, "step": 1283 }, { "epoch": 0.62, "learning_rate": 3.255366058031196e-06, "loss": 0.3308, "step": 1284 }, { "epoch": 0.63, "learning_rate": 3.2479783123202794e-06, "loss": 0.3487, "step": 1285 }, { "epoch": 0.63, "learning_rate": 3.240594924340835e-06, "loss": 0.3741, "step": 1286 }, { "epoch": 0.63, "learning_rate": 3.2332159124572605e-06, "loss": 0.3713, "step": 1287 }, { "epoch": 0.63, "learning_rate": 3.2258412950230665e-06, "loss": 0.4038, "step": 1288 }, { "epoch": 0.63, "learning_rate": 3.2184710903808367e-06, "loss": 0.4433, "step": 1289 }, { "epoch": 0.63, "learning_rate": 3.21110531686218e-06, "loss": 0.4094, "step": 1290 }, { "epoch": 0.63, "learning_rate": 3.203743992787679e-06, "loss": 0.3532, "step": 1291 }, { "epoch": 0.63, "learning_rate": 3.196387136466853e-06, "loss": 0.3548, "step": 1292 }, { "epoch": 0.63, "learning_rate": 3.1890347661981087e-06, "loss": 0.3425, "step": 1293 }, { "epoch": 0.63, "learning_rate": 3.181686900268694e-06, "loss": 0.4103, "step": 1294 }, { "epoch": 0.63, "learning_rate": 3.174343556954652e-06, "loss": 0.3554, "step": 1295 }, { "epoch": 0.63, "learning_rate": 3.1670047545207817e-06, "loss": 0.3756, "step": 1296 }, { "epoch": 0.63, "learning_rate": 3.1596705112205816e-06, "loss": 0.3064, "step": 1297 }, { "epoch": 0.63, "learning_rate": 3.1523408452962156e-06, "loss": 0.38, "step": 1298 }, { "epoch": 0.63, "learning_rate": 3.1450157749784592e-06, "loss": 0.3712, "step": 1299 }, { "epoch": 0.63, "learning_rate": 3.1376953184866575e-06, "loss": 0.372, "step": 1300 }, { "epoch": 0.63, "learning_rate": 3.1303794940286823e-06, "loss": 0.3822, "step": 1301 }, { "epoch": 0.63, "learning_rate": 3.1230683198008817e-06, "loss": 0.4507, "step": 1302 }, { "epoch": 0.63, "learning_rate": 3.1157618139880387e-06, "loss": 0.3896, "step": 1303 }, { "epoch": 0.63, "learning_rate": 3.1084599947633252e-06, "loss": 0.3059, "step": 1304 }, { "epoch": 0.64, "learning_rate": 3.1011628802882556e-06, "loss": 0.3663, "step": 1305 }, { "epoch": 0.64, "learning_rate": 3.0938704887126425e-06, "loss": 0.3781, "step": 1306 }, { "epoch": 0.64, "learning_rate": 3.0865828381745515e-06, "loss": 0.3324, "step": 1307 }, { "epoch": 0.64, "learning_rate": 3.0792999468002567e-06, "loss": 0.3561, "step": 1308 }, { "epoch": 0.64, "learning_rate": 3.0720218327041927e-06, "loss": 0.323, "step": 1309 }, { "epoch": 0.64, "learning_rate": 3.0647485139889145e-06, "loss": 0.381, "step": 1310 }, { "epoch": 0.64, "learning_rate": 3.0574800087450483e-06, "loss": 0.3516, "step": 1311 }, { "epoch": 0.64, "learning_rate": 3.050216335051248e-06, "loss": 0.2905, "step": 1312 }, { "epoch": 0.64, "learning_rate": 3.0429575109741503e-06, "loss": 0.3865, "step": 1313 }, { "epoch": 0.64, "learning_rate": 3.035703554568331e-06, "loss": 0.4525, "step": 1314 }, { "epoch": 0.64, "learning_rate": 3.0284544838762552e-06, "loss": 0.3181, "step": 1315 }, { "epoch": 0.64, "learning_rate": 3.0212103169282415e-06, "loss": 0.3449, "step": 1316 }, { "epoch": 0.64, "learning_rate": 3.013971071742404e-06, "loss": 0.3633, "step": 1317 }, { "epoch": 0.64, "learning_rate": 3.006736766324623e-06, "loss": 0.2864, "step": 1318 }, { "epoch": 0.64, "learning_rate": 2.999507418668487e-06, "loss": 0.2893, "step": 1319 }, { "epoch": 0.64, "learning_rate": 2.9922830467552542e-06, "loss": 0.4428, "step": 1320 }, { "epoch": 0.64, "learning_rate": 2.9850636685538104e-06, "loss": 0.3492, "step": 1321 }, { "epoch": 0.64, "learning_rate": 2.9778493020206155e-06, "loss": 0.3708, "step": 1322 }, { "epoch": 0.64, "learning_rate": 2.9706399650996687e-06, "loss": 0.3359, "step": 1323 }, { "epoch": 0.64, "learning_rate": 2.963435675722456e-06, "loss": 0.4106, "step": 1324 }, { "epoch": 0.64, "learning_rate": 2.9562364518079106e-06, "loss": 0.3649, "step": 1325 }, { "epoch": 0.65, "learning_rate": 2.9490423112623646e-06, "loss": 0.5005, "step": 1326 }, { "epoch": 0.65, "learning_rate": 2.941853271979509e-06, "loss": 0.3533, "step": 1327 }, { "epoch": 0.65, "learning_rate": 2.9346693518403456e-06, "loss": 0.3585, "step": 1328 }, { "epoch": 0.65, "learning_rate": 2.9274905687131437e-06, "loss": 0.4246, "step": 1329 }, { "epoch": 0.65, "learning_rate": 2.9203169404533937e-06, "loss": 0.3726, "step": 1330 }, { "epoch": 0.65, "learning_rate": 2.9131484849037683e-06, "loss": 0.3586, "step": 1331 }, { "epoch": 0.65, "learning_rate": 2.9059852198940696e-06, "loss": 0.3244, "step": 1332 }, { "epoch": 0.65, "learning_rate": 2.898827163241195e-06, "loss": 0.3414, "step": 1333 }, { "epoch": 0.65, "learning_rate": 2.89167433274908e-06, "loss": 0.3181, "step": 1334 }, { "epoch": 0.65, "learning_rate": 2.8845267462086707e-06, "loss": 0.3535, "step": 1335 }, { "epoch": 0.65, "learning_rate": 2.877384421397862e-06, "loss": 0.3714, "step": 1336 }, { "epoch": 0.65, "learning_rate": 2.8702473760814642e-06, "loss": 0.3695, "step": 1337 }, { "epoch": 0.65, "learning_rate": 2.863115628011158e-06, "loss": 0.4024, "step": 1338 }, { "epoch": 0.65, "learning_rate": 2.8559891949254477e-06, "loss": 0.4695, "step": 1339 }, { "epoch": 0.65, "learning_rate": 2.848868094549615e-06, "loss": 0.361, "step": 1340 }, { "epoch": 0.65, "learning_rate": 2.8417523445956806e-06, "loss": 0.3284, "step": 1341 }, { "epoch": 0.65, "learning_rate": 2.834641962762358e-06, "loss": 0.3737, "step": 1342 }, { "epoch": 0.65, "learning_rate": 2.827536966735006e-06, "loss": 0.3813, "step": 1343 }, { "epoch": 0.65, "learning_rate": 2.8204373741855874e-06, "loss": 0.3672, "step": 1344 }, { "epoch": 0.65, "learning_rate": 2.8133432027726305e-06, "loss": 0.3218, "step": 1345 }, { "epoch": 0.66, "learning_rate": 2.806254470141174e-06, "loss": 0.3541, "step": 1346 }, { "epoch": 0.66, "learning_rate": 2.7991711939227317e-06, "loss": 0.3734, "step": 1347 }, { "epoch": 0.66, "learning_rate": 2.7920933917352443e-06, "loss": 0.3969, "step": 1348 }, { "epoch": 0.66, "learning_rate": 2.785021081183038e-06, "loss": 0.4129, "step": 1349 }, { "epoch": 0.66, "learning_rate": 2.7779542798567804e-06, "loss": 0.3648, "step": 1350 }, { "epoch": 0.66, "learning_rate": 2.770893005333436e-06, "loss": 0.3673, "step": 1351 }, { "epoch": 0.66, "learning_rate": 2.763837275176224e-06, "loss": 0.4293, "step": 1352 }, { "epoch": 0.66, "learning_rate": 2.7567871069345654e-06, "loss": 0.4108, "step": 1353 }, { "epoch": 0.66, "learning_rate": 2.749742518144061e-06, "loss": 0.3256, "step": 1354 }, { "epoch": 0.66, "learning_rate": 2.7427035263264222e-06, "loss": 0.3676, "step": 1355 }, { "epoch": 0.66, "learning_rate": 2.7356701489894468e-06, "loss": 0.3759, "step": 1356 }, { "epoch": 0.66, "learning_rate": 2.7286424036269626e-06, "loss": 0.4076, "step": 1357 }, { "epoch": 0.66, "learning_rate": 2.721620307718793e-06, "loss": 0.3869, "step": 1358 }, { "epoch": 0.66, "learning_rate": 2.714603878730707e-06, "loss": 0.3317, "step": 1359 }, { "epoch": 0.66, "learning_rate": 2.7075931341143812e-06, "loss": 0.316, "step": 1360 }, { "epoch": 0.66, "learning_rate": 2.700588091307351e-06, "loss": 0.3233, "step": 1361 }, { "epoch": 0.66, "learning_rate": 2.6935887677329727e-06, "loss": 0.4127, "step": 1362 }, { "epoch": 0.66, "learning_rate": 2.6865951808003743e-06, "loss": 0.4078, "step": 1363 }, { "epoch": 0.66, "learning_rate": 2.6796073479044175e-06, "loss": 0.3388, "step": 1364 }, { "epoch": 0.66, "learning_rate": 2.6726252864256502e-06, "loss": 0.4059, "step": 1365 }, { "epoch": 0.66, "learning_rate": 2.66564901373027e-06, "loss": 0.413, "step": 1366 }, { "epoch": 0.67, "learning_rate": 2.658678547170071e-06, "loss": 0.3488, "step": 1367 }, { "epoch": 0.67, "learning_rate": 2.651713904082408e-06, "loss": 0.3779, "step": 1368 }, { "epoch": 0.67, "learning_rate": 2.644755101790152e-06, "loss": 0.3463, "step": 1369 }, { "epoch": 0.67, "learning_rate": 2.6378021576016467e-06, "loss": 0.3876, "step": 1370 }, { "epoch": 0.67, "learning_rate": 2.6308550888106603e-06, "loss": 0.4401, "step": 1371 }, { "epoch": 0.67, "learning_rate": 2.6239139126963543e-06, "loss": 0.3183, "step": 1372 }, { "epoch": 0.67, "learning_rate": 2.6169786465232283e-06, "loss": 0.4357, "step": 1373 }, { "epoch": 0.67, "learning_rate": 2.610049307541085e-06, "loss": 0.3361, "step": 1374 }, { "epoch": 0.67, "learning_rate": 2.6031259129849868e-06, "loss": 0.4027, "step": 1375 }, { "epoch": 0.67, "learning_rate": 2.5962084800752064e-06, "loss": 0.4083, "step": 1376 }, { "epoch": 0.67, "learning_rate": 2.58929702601719e-06, "loss": 0.4011, "step": 1377 }, { "epoch": 0.67, "learning_rate": 2.5823915680015136e-06, "loss": 0.3884, "step": 1378 }, { "epoch": 0.67, "learning_rate": 2.575492123203839e-06, "loss": 0.3811, "step": 1379 }, { "epoch": 0.67, "learning_rate": 2.5685987087848694e-06, "loss": 0.3783, "step": 1380 }, { "epoch": 0.67, "learning_rate": 2.5617113418903137e-06, "loss": 0.3242, "step": 1381 }, { "epoch": 0.67, "learning_rate": 2.554830039650834e-06, "loss": 0.3281, "step": 1382 }, { "epoch": 0.67, "learning_rate": 2.547954819182012e-06, "loss": 0.4068, "step": 1383 }, { "epoch": 0.67, "learning_rate": 2.5410856975842996e-06, "loss": 0.4297, "step": 1384 }, { "epoch": 0.67, "learning_rate": 2.5342226919429807e-06, "loss": 0.3363, "step": 1385 }, { "epoch": 0.67, "learning_rate": 2.5273658193281252e-06, "loss": 0.3093, "step": 1386 }, { "epoch": 0.68, "learning_rate": 2.520515096794554e-06, "loss": 0.3651, "step": 1387 }, { "epoch": 0.68, "learning_rate": 2.5136705413817873e-06, "loss": 0.3881, "step": 1388 }, { "epoch": 0.68, "learning_rate": 2.5068321701140025e-06, "loss": 0.3235, "step": 1389 }, { "epoch": 0.68, "learning_rate": 2.5000000000000015e-06, "loss": 0.4108, "step": 1390 }, { "epoch": 0.68, "learning_rate": 2.493174048033159e-06, "loss": 0.4243, "step": 1391 }, { "epoch": 0.68, "learning_rate": 2.486354331191385e-06, "loss": 0.3373, "step": 1392 }, { "epoch": 0.68, "learning_rate": 2.4795408664370812e-06, "loss": 0.3527, "step": 1393 }, { "epoch": 0.68, "learning_rate": 2.4727336707170973e-06, "loss": 0.3284, "step": 1394 }, { "epoch": 0.68, "learning_rate": 2.465932760962692e-06, "loss": 0.3559, "step": 1395 }, { "epoch": 0.68, "learning_rate": 2.459138154089486e-06, "loss": 0.3886, "step": 1396 }, { "epoch": 0.68, "learning_rate": 2.452349866997429e-06, "loss": 0.4135, "step": 1397 }, { "epoch": 0.68, "learning_rate": 2.4455679165707473e-06, "loss": 0.3716, "step": 1398 }, { "epoch": 0.68, "learning_rate": 2.4387923196779063e-06, "loss": 0.3231, "step": 1399 }, { "epoch": 0.68, "learning_rate": 2.43202309317157e-06, "loss": 0.3708, "step": 1400 }, { "epoch": 0.68, "learning_rate": 2.4252602538885562e-06, "loss": 0.4264, "step": 1401 }, { "epoch": 0.68, "learning_rate": 2.418503818649798e-06, "loss": 0.3862, "step": 1402 }, { "epoch": 0.68, "learning_rate": 2.411753804260298e-06, "loss": 0.3836, "step": 1403 }, { "epoch": 0.68, "learning_rate": 2.40501022750909e-06, "loss": 0.339, "step": 1404 }, { "epoch": 0.68, "learning_rate": 2.3982731051691937e-06, "loss": 0.3781, "step": 1405 }, { "epoch": 0.68, "learning_rate": 2.391542453997578e-06, "loss": 0.3368, "step": 1406 }, { "epoch": 0.68, "learning_rate": 2.3848182907351137e-06, "loss": 0.3276, "step": 1407 }, { "epoch": 0.69, "learning_rate": 2.378100632106536e-06, "loss": 0.3854, "step": 1408 }, { "epoch": 0.69, "learning_rate": 2.3713894948204e-06, "loss": 0.3642, "step": 1409 }, { "epoch": 0.69, "learning_rate": 2.3646848955690426e-06, "loss": 0.299, "step": 1410 }, { "epoch": 0.69, "learning_rate": 2.357986851028537e-06, "loss": 0.371, "step": 1411 }, { "epoch": 0.69, "learning_rate": 2.3512953778586537e-06, "loss": 0.3157, "step": 1412 }, { "epoch": 0.69, "learning_rate": 2.3446104927028196e-06, "loss": 0.3655, "step": 1413 }, { "epoch": 0.69, "learning_rate": 2.337932212188073e-06, "loss": 0.3686, "step": 1414 }, { "epoch": 0.69, "learning_rate": 2.331260552925028e-06, "loss": 0.4312, "step": 1415 }, { "epoch": 0.69, "learning_rate": 2.324595531507827e-06, "loss": 0.3948, "step": 1416 }, { "epoch": 0.69, "learning_rate": 2.317937164514102e-06, "loss": 0.3665, "step": 1417 }, { "epoch": 0.69, "learning_rate": 2.3112854685049397e-06, "loss": 0.3682, "step": 1418 }, { "epoch": 0.69, "learning_rate": 2.3046404600248275e-06, "loss": 0.3938, "step": 1419 }, { "epoch": 0.69, "learning_rate": 2.2980021556016214e-06, "loss": 0.368, "step": 1420 }, { "epoch": 0.69, "learning_rate": 2.2913705717465027e-06, "loss": 0.3484, "step": 1421 }, { "epoch": 0.69, "learning_rate": 2.284745724953939e-06, "loss": 0.4487, "step": 1422 }, { "epoch": 0.69, "learning_rate": 2.2781276317016387e-06, "loss": 0.3965, "step": 1423 }, { "epoch": 0.69, "learning_rate": 2.271516308450511e-06, "loss": 0.376, "step": 1424 }, { "epoch": 0.69, "learning_rate": 2.264911771644629e-06, "loss": 0.3692, "step": 1425 }, { "epoch": 0.69, "learning_rate": 2.258314037711184e-06, "loss": 0.338, "step": 1426 }, { "epoch": 0.69, "learning_rate": 2.2517231230604516e-06, "loss": 0.3329, "step": 1427 }, { "epoch": 0.69, "learning_rate": 2.2451390440857406e-06, "loss": 0.3806, "step": 1428 }, { "epoch": 0.7, "learning_rate": 2.2385618171633612e-06, "loss": 0.3841, "step": 1429 }, { "epoch": 0.7, "learning_rate": 2.2319914586525776e-06, "loss": 0.3353, "step": 1430 }, { "epoch": 0.7, "learning_rate": 2.2254279848955736e-06, "loss": 0.3711, "step": 1431 }, { "epoch": 0.7, "learning_rate": 2.2188714122174064e-06, "loss": 0.3923, "step": 1432 }, { "epoch": 0.7, "learning_rate": 2.212321756925971e-06, "loss": 0.3929, "step": 1433 }, { "epoch": 0.7, "learning_rate": 2.2057790353119533e-06, "loss": 0.3476, "step": 1434 }, { "epoch": 0.7, "learning_rate": 2.1992432636487976e-06, "loss": 0.3043, "step": 1435 }, { "epoch": 0.7, "learning_rate": 2.1927144581926597e-06, "loss": 0.3964, "step": 1436 }, { "epoch": 0.7, "learning_rate": 2.1861926351823675e-06, "loss": 0.3958, "step": 1437 }, { "epoch": 0.7, "learning_rate": 2.1796778108393824e-06, "loss": 0.3637, "step": 1438 }, { "epoch": 0.7, "learning_rate": 2.1731700013677628e-06, "loss": 0.3836, "step": 1439 }, { "epoch": 0.7, "learning_rate": 2.1666692229541126e-06, "loss": 0.3796, "step": 1440 }, { "epoch": 0.7, "learning_rate": 2.160175491767553e-06, "loss": 0.3025, "step": 1441 }, { "epoch": 0.7, "learning_rate": 2.1536888239596714e-06, "loss": 0.3698, "step": 1442 }, { "epoch": 0.7, "learning_rate": 2.1472092356644907e-06, "loss": 0.3858, "step": 1443 }, { "epoch": 0.7, "learning_rate": 2.140736742998424e-06, "loss": 0.3682, "step": 1444 }, { "epoch": 0.7, "learning_rate": 2.1342713620602377e-06, "loss": 0.8992, "step": 1445 }, { "epoch": 0.7, "learning_rate": 2.127813108931007e-06, "loss": 0.3912, "step": 1446 }, { "epoch": 0.7, "learning_rate": 2.1213619996740765e-06, "loss": 0.3978, "step": 1447 }, { "epoch": 0.7, "learning_rate": 2.114918050335029e-06, "loss": 0.4798, "step": 1448 }, { "epoch": 0.71, "learning_rate": 2.108481276941634e-06, "loss": 0.3439, "step": 1449 }, { "epoch": 0.71, "learning_rate": 2.1020516955038118e-06, "loss": 0.3461, "step": 1450 }, { "epoch": 0.71, "learning_rate": 2.095629322013596e-06, "loss": 0.3588, "step": 1451 }, { "epoch": 0.71, "learning_rate": 2.0892141724450925e-06, "loss": 0.3356, "step": 1452 }, { "epoch": 0.71, "learning_rate": 2.082806262754439e-06, "loss": 0.3211, "step": 1453 }, { "epoch": 0.71, "learning_rate": 2.0764056088797646e-06, "loss": 0.4077, "step": 1454 }, { "epoch": 0.71, "learning_rate": 2.0700122267411536e-06, "loss": 0.4667, "step": 1455 }, { "epoch": 0.71, "learning_rate": 2.063626132240602e-06, "loss": 0.3719, "step": 1456 }, { "epoch": 0.71, "learning_rate": 2.0572473412619797e-06, "loss": 0.3693, "step": 1457 }, { "epoch": 0.71, "learning_rate": 2.0508758696709913e-06, "loss": 0.3309, "step": 1458 }, { "epoch": 0.71, "learning_rate": 2.044511733315136e-06, "loss": 0.3283, "step": 1459 }, { "epoch": 0.71, "learning_rate": 2.0381549480236685e-06, "loss": 0.3504, "step": 1460 }, { "epoch": 0.71, "learning_rate": 2.0318055296075587e-06, "loss": 0.4365, "step": 1461 }, { "epoch": 0.71, "learning_rate": 2.0254634938594555e-06, "loss": 0.3871, "step": 1462 }, { "epoch": 0.71, "learning_rate": 2.019128856553641e-06, "loss": 0.3023, "step": 1463 }, { "epoch": 0.71, "learning_rate": 2.012801633446e-06, "loss": 0.356, "step": 1464 }, { "epoch": 0.71, "learning_rate": 2.006481840273973e-06, "loss": 0.3582, "step": 1465 }, { "epoch": 0.71, "learning_rate": 2.000169492756523e-06, "loss": 0.4386, "step": 1466 }, { "epoch": 0.71, "learning_rate": 1.9938646065940914e-06, "loss": 0.3627, "step": 1467 }, { "epoch": 0.71, "learning_rate": 1.98756719746856e-06, "loss": 0.366, "step": 1468 }, { "epoch": 0.71, "learning_rate": 1.9812772810432195e-06, "loss": 0.3976, "step": 1469 }, { "epoch": 0.72, "learning_rate": 1.9749948729627188e-06, "loss": 0.3945, "step": 1470 }, { "epoch": 0.72, "learning_rate": 1.968719988853033e-06, "loss": 0.3179, "step": 1471 }, { "epoch": 0.72, "learning_rate": 1.9624526443214228e-06, "loss": 0.419, "step": 1472 }, { "epoch": 0.72, "learning_rate": 1.956192854956397e-06, "loss": 0.3952, "step": 1473 }, { "epoch": 0.72, "learning_rate": 1.949940636327671e-06, "loss": 0.4736, "step": 1474 }, { "epoch": 0.72, "learning_rate": 1.9436960039861324e-06, "loss": 0.3758, "step": 1475 }, { "epoch": 0.72, "learning_rate": 1.9374589734638e-06, "loss": 0.3581, "step": 1476 }, { "epoch": 0.72, "learning_rate": 1.9312295602737783e-06, "loss": 0.4496, "step": 1477 }, { "epoch": 0.72, "learning_rate": 1.9250077799102323e-06, "loss": 0.3796, "step": 1478 }, { "epoch": 0.72, "learning_rate": 1.9187936478483426e-06, "loss": 0.373, "step": 1479 }, { "epoch": 0.72, "learning_rate": 1.912587179544263e-06, "loss": 0.3574, "step": 1480 }, { "epoch": 0.72, "learning_rate": 1.9063883904350873e-06, "loss": 0.3839, "step": 1481 }, { "epoch": 0.72, "learning_rate": 1.9001972959388071e-06, "loss": 0.3402, "step": 1482 }, { "epoch": 0.72, "learning_rate": 1.8940139114542788e-06, "loss": 0.4588, "step": 1483 }, { "epoch": 0.72, "learning_rate": 1.8878382523611789e-06, "loss": 0.394, "step": 1484 }, { "epoch": 0.72, "learning_rate": 1.881670334019971e-06, "loss": 0.3209, "step": 1485 }, { "epoch": 0.72, "learning_rate": 1.875510171771865e-06, "loss": 0.3459, "step": 1486 }, { "epoch": 0.72, "learning_rate": 1.869357780938778e-06, "loss": 0.3741, "step": 1487 }, { "epoch": 0.72, "learning_rate": 1.8632131768232992e-06, "loss": 0.3459, "step": 1488 }, { "epoch": 0.72, "learning_rate": 1.8570763747086496e-06, "loss": 0.3686, "step": 1489 }, { "epoch": 0.73, "learning_rate": 1.8509473898586432e-06, "loss": 0.4641, "step": 1490 }, { "epoch": 0.73, "learning_rate": 1.8448262375176552e-06, "loss": 0.446, "step": 1491 }, { "epoch": 0.73, "learning_rate": 1.8387129329105742e-06, "loss": 0.4062, "step": 1492 }, { "epoch": 0.73, "learning_rate": 1.8326074912427704e-06, "loss": 0.3975, "step": 1493 }, { "epoch": 0.73, "learning_rate": 1.8265099277000614e-06, "loss": 0.3714, "step": 1494 }, { "epoch": 0.73, "learning_rate": 1.8204202574486611e-06, "loss": 0.3888, "step": 1495 }, { "epoch": 0.73, "learning_rate": 1.814338495635158e-06, "loss": 0.3037, "step": 1496 }, { "epoch": 0.73, "learning_rate": 1.8082646573864682e-06, "loss": 0.3287, "step": 1497 }, { "epoch": 0.73, "learning_rate": 1.8021987578097994e-06, "loss": 0.439, "step": 1498 }, { "epoch": 0.73, "learning_rate": 1.7961408119926133e-06, "loss": 0.3662, "step": 1499 }, { "epoch": 0.73, "learning_rate": 1.7900908350025914e-06, "loss": 0.4124, "step": 1500 }, { "epoch": 0.73, "learning_rate": 1.7840488418875917e-06, "loss": 0.3926, "step": 1501 }, { "epoch": 0.73, "learning_rate": 1.7780148476756148e-06, "loss": 0.3764, "step": 1502 }, { "epoch": 0.73, "learning_rate": 1.771988867374767e-06, "loss": 0.3354, "step": 1503 }, { "epoch": 0.73, "learning_rate": 1.7659709159732203e-06, "loss": 0.3486, "step": 1504 }, { "epoch": 0.73, "learning_rate": 1.7599610084391782e-06, "loss": 0.3574, "step": 1505 }, { "epoch": 0.73, "learning_rate": 1.753959159720836e-06, "loss": 0.365, "step": 1506 }, { "epoch": 0.73, "learning_rate": 1.7479653847463458e-06, "loss": 0.3663, "step": 1507 }, { "epoch": 0.73, "learning_rate": 1.741979698423777e-06, "loss": 0.3806, "step": 1508 }, { "epoch": 0.73, "learning_rate": 1.736002115641081e-06, "loss": 0.3909, "step": 1509 }, { "epoch": 0.73, "learning_rate": 1.7300326512660542e-06, "loss": 0.3205, "step": 1510 }, { "epoch": 0.74, "learning_rate": 1.7240713201462973e-06, "loss": 0.3995, "step": 1511 }, { "epoch": 0.74, "learning_rate": 1.7181181371091893e-06, "loss": 0.3253, "step": 1512 }, { "epoch": 0.74, "learning_rate": 1.7121731169618322e-06, "loss": 0.414, "step": 1513 }, { "epoch": 0.74, "learning_rate": 1.7062362744910321e-06, "loss": 0.3435, "step": 1514 }, { "epoch": 0.74, "learning_rate": 1.7003076244632533e-06, "loss": 0.3566, "step": 1515 }, { "epoch": 0.74, "learning_rate": 1.6943871816245826e-06, "loss": 0.3986, "step": 1516 }, { "epoch": 0.74, "learning_rate": 1.6884749607006938e-06, "loss": 0.4185, "step": 1517 }, { "epoch": 0.74, "learning_rate": 1.6825709763968112e-06, "loss": 0.416, "step": 1518 }, { "epoch": 0.74, "learning_rate": 1.6766752433976725e-06, "loss": 0.3331, "step": 1519 }, { "epoch": 0.74, "learning_rate": 1.670787776367489e-06, "loss": 0.3934, "step": 1520 }, { "epoch": 0.74, "learning_rate": 1.6649085899499196e-06, "loss": 0.3939, "step": 1521 }, { "epoch": 0.74, "learning_rate": 1.6590376987680207e-06, "loss": 0.3012, "step": 1522 }, { "epoch": 0.74, "learning_rate": 1.6531751174242184e-06, "loss": 0.3191, "step": 1523 }, { "epoch": 0.74, "learning_rate": 1.6473208605002705e-06, "loss": 0.3327, "step": 1524 }, { "epoch": 0.74, "learning_rate": 1.6414749425572291e-06, "loss": 0.3982, "step": 1525 }, { "epoch": 0.74, "learning_rate": 1.6356373781354058e-06, "loss": 0.3691, "step": 1526 }, { "epoch": 0.74, "learning_rate": 1.6298081817543338e-06, "loss": 0.3383, "step": 1527 }, { "epoch": 0.74, "learning_rate": 1.6239873679127337e-06, "loss": 0.3761, "step": 1528 }, { "epoch": 0.74, "learning_rate": 1.6181749510884765e-06, "loss": 0.3449, "step": 1529 }, { "epoch": 0.74, "learning_rate": 1.612370945738548e-06, "loss": 0.3714, "step": 1530 }, { "epoch": 0.75, "learning_rate": 1.6065753662990109e-06, "loss": 0.3534, "step": 1531 }, { "epoch": 0.75, "learning_rate": 1.6007882271849718e-06, "loss": 0.3258, "step": 1532 }, { "epoch": 0.75, "learning_rate": 1.5950095427905438e-06, "loss": 0.3906, "step": 1533 }, { "epoch": 0.75, "learning_rate": 1.589239327488812e-06, "loss": 0.3875, "step": 1534 }, { "epoch": 0.75, "learning_rate": 1.5834775956317937e-06, "loss": 0.4015, "step": 1535 }, { "epoch": 0.75, "learning_rate": 1.5777243615504085e-06, "loss": 0.325, "step": 1536 }, { "epoch": 0.75, "learning_rate": 1.571979639554439e-06, "loss": 0.378, "step": 1537 }, { "epoch": 0.75, "learning_rate": 1.566243443932496e-06, "loss": 0.3399, "step": 1538 }, { "epoch": 0.75, "learning_rate": 1.5605157889519818e-06, "loss": 0.4084, "step": 1539 }, { "epoch": 0.75, "learning_rate": 1.5547966888590582e-06, "loss": 0.3618, "step": 1540 }, { "epoch": 0.75, "learning_rate": 1.5490861578786055e-06, "loss": 0.3873, "step": 1541 }, { "epoch": 0.75, "learning_rate": 1.543384210214196e-06, "loss": 0.3771, "step": 1542 }, { "epoch": 0.75, "learning_rate": 1.5376908600480477e-06, "loss": 0.3563, "step": 1543 }, { "epoch": 0.75, "learning_rate": 1.532006121540996e-06, "loss": 0.3416, "step": 1544 }, { "epoch": 0.75, "learning_rate": 1.526330008832458e-06, "loss": 0.3392, "step": 1545 }, { "epoch": 0.75, "learning_rate": 1.5206625360403943e-06, "loss": 0.3816, "step": 1546 }, { "epoch": 0.75, "learning_rate": 1.515003717261278e-06, "loss": 0.3549, "step": 1547 }, { "epoch": 0.75, "learning_rate": 1.5093535665700566e-06, "loss": 0.4088, "step": 1548 }, { "epoch": 0.75, "learning_rate": 1.5037120980201153e-06, "loss": 0.3939, "step": 1549 }, { "epoch": 0.75, "learning_rate": 1.4980793256432474e-06, "loss": 0.3842, "step": 1550 }, { "epoch": 0.75, "learning_rate": 1.4924552634496154e-06, "loss": 0.3482, "step": 1551 }, { "epoch": 0.76, "learning_rate": 1.4868399254277205e-06, "loss": 0.2773, "step": 1552 }, { "epoch": 0.76, "learning_rate": 1.4812333255443605e-06, "loss": 0.36, "step": 1553 }, { "epoch": 0.76, "learning_rate": 1.4756354777446004e-06, "loss": 0.4135, "step": 1554 }, { "epoch": 0.76, "learning_rate": 1.4700463959517363e-06, "loss": 0.3333, "step": 1555 }, { "epoch": 0.76, "learning_rate": 1.4644660940672628e-06, "loss": 0.3759, "step": 1556 }, { "epoch": 0.76, "learning_rate": 1.4588945859708343e-06, "loss": 0.3486, "step": 1557 }, { "epoch": 0.76, "learning_rate": 1.453331885520234e-06, "loss": 0.3396, "step": 1558 }, { "epoch": 0.76, "learning_rate": 1.447778006551337e-06, "loss": 0.3867, "step": 1559 }, { "epoch": 0.76, "learning_rate": 1.4422329628780795e-06, "loss": 0.3323, "step": 1560 }, { "epoch": 0.76, "learning_rate": 1.4366967682924194e-06, "loss": 0.3809, "step": 1561 }, { "epoch": 0.76, "learning_rate": 1.4311694365643048e-06, "loss": 0.3242, "step": 1562 }, { "epoch": 0.76, "learning_rate": 1.4256509814416431e-06, "loss": 0.4013, "step": 1563 }, { "epoch": 0.76, "learning_rate": 1.4201414166502596e-06, "loss": 0.4185, "step": 1564 }, { "epoch": 0.76, "learning_rate": 1.4146407558938695e-06, "loss": 0.3505, "step": 1565 }, { "epoch": 0.76, "learning_rate": 1.4091490128540374e-06, "loss": 0.4752, "step": 1566 }, { "epoch": 0.76, "learning_rate": 1.4036662011901507e-06, "loss": 0.3088, "step": 1567 }, { "epoch": 0.76, "learning_rate": 1.3981923345393816e-06, "loss": 0.4216, "step": 1568 }, { "epoch": 0.76, "learning_rate": 1.3927274265166534e-06, "loss": 0.3298, "step": 1569 }, { "epoch": 0.76, "learning_rate": 1.3872714907146074e-06, "loss": 0.3943, "step": 1570 }, { "epoch": 0.76, "learning_rate": 1.3818245407035675e-06, "loss": 0.4364, "step": 1571 }, { "epoch": 0.77, "learning_rate": 1.3763865900315076e-06, "loss": 0.4085, "step": 1572 }, { "epoch": 0.77, "learning_rate": 1.3709576522240214e-06, "loss": 0.3177, "step": 1573 }, { "epoch": 0.77, "learning_rate": 1.3655377407842813e-06, "loss": 0.332, "step": 1574 }, { "epoch": 0.77, "learning_rate": 1.3601268691930097e-06, "loss": 0.3554, "step": 1575 }, { "epoch": 0.77, "learning_rate": 1.3547250509084453e-06, "loss": 0.4192, "step": 1576 }, { "epoch": 0.77, "learning_rate": 1.3493322993663088e-06, "loss": 0.3311, "step": 1577 }, { "epoch": 0.77, "learning_rate": 1.3439486279797682e-06, "loss": 0.3638, "step": 1578 }, { "epoch": 0.77, "learning_rate": 1.3385740501394084e-06, "loss": 0.3155, "step": 1579 }, { "epoch": 0.77, "learning_rate": 1.3332085792131966e-06, "loss": 0.3601, "step": 1580 }, { "epoch": 0.77, "learning_rate": 1.3278522285464463e-06, "loss": 0.3654, "step": 1581 }, { "epoch": 0.77, "learning_rate": 1.32250501146179e-06, "loss": 0.3286, "step": 1582 }, { "epoch": 0.77, "learning_rate": 1.3171669412591393e-06, "loss": 0.376, "step": 1583 }, { "epoch": 0.77, "learning_rate": 1.311838031215657e-06, "loss": 0.4085, "step": 1584 }, { "epoch": 0.77, "learning_rate": 1.3065182945857218e-06, "loss": 0.3403, "step": 1585 }, { "epoch": 0.77, "learning_rate": 1.3012077446008969e-06, "loss": 0.3693, "step": 1586 }, { "epoch": 0.77, "learning_rate": 1.2959063944698935e-06, "loss": 0.3079, "step": 1587 }, { "epoch": 0.77, "learning_rate": 1.290614257378542e-06, "loss": 0.3093, "step": 1588 }, { "epoch": 0.77, "learning_rate": 1.2853313464897572e-06, "loss": 0.3815, "step": 1589 }, { "epoch": 0.77, "learning_rate": 1.2800576749435068e-06, "loss": 0.3401, "step": 1590 }, { "epoch": 0.77, "learning_rate": 1.274793255856776e-06, "loss": 0.4596, "step": 1591 }, { "epoch": 0.77, "learning_rate": 1.2695381023235387e-06, "loss": 0.3958, "step": 1592 }, { "epoch": 0.78, "learning_rate": 1.2642922274147202e-06, "loss": 0.4166, "step": 1593 }, { "epoch": 0.78, "learning_rate": 1.2590556441781725e-06, "loss": 0.2547, "step": 1594 }, { "epoch": 0.78, "learning_rate": 1.2538283656386318e-06, "loss": 0.4047, "step": 1595 }, { "epoch": 0.78, "learning_rate": 1.2486104047976937e-06, "loss": 0.3651, "step": 1596 }, { "epoch": 0.78, "learning_rate": 1.2434017746337773e-06, "loss": 0.297, "step": 1597 }, { "epoch": 0.78, "learning_rate": 1.2382024881020937e-06, "loss": 0.3624, "step": 1598 }, { "epoch": 0.78, "learning_rate": 1.2330125581346148e-06, "loss": 0.3859, "step": 1599 }, { "epoch": 0.78, "learning_rate": 1.2278319976400393e-06, "loss": 0.3367, "step": 1600 }, { "epoch": 0.78, "learning_rate": 1.2226608195037648e-06, "loss": 0.4073, "step": 1601 }, { "epoch": 0.78, "learning_rate": 1.2174990365878448e-06, "loss": 0.3855, "step": 1602 }, { "epoch": 0.78, "learning_rate": 1.2123466617309742e-06, "loss": 0.4206, "step": 1603 }, { "epoch": 0.78, "learning_rate": 1.2072037077484416e-06, "loss": 0.3013, "step": 1604 }, { "epoch": 0.78, "learning_rate": 1.2020701874321044e-06, "loss": 0.3837, "step": 1605 }, { "epoch": 0.78, "learning_rate": 1.1969461135503573e-06, "loss": 0.4004, "step": 1606 }, { "epoch": 0.78, "learning_rate": 1.1918314988480978e-06, "loss": 0.3864, "step": 1607 }, { "epoch": 0.78, "learning_rate": 1.1867263560466968e-06, "loss": 0.3812, "step": 1608 }, { "epoch": 0.78, "learning_rate": 1.1816306978439668e-06, "loss": 0.3987, "step": 1609 }, { "epoch": 0.78, "learning_rate": 1.1765445369141276e-06, "loss": 0.3626, "step": 1610 }, { "epoch": 0.78, "learning_rate": 1.1714678859077788e-06, "loss": 0.3545, "step": 1611 }, { "epoch": 0.78, "learning_rate": 1.1664007574518655e-06, "loss": 0.4129, "step": 1612 }, { "epoch": 0.79, "learning_rate": 1.1613431641496475e-06, "loss": 0.3326, "step": 1613 }, { "epoch": 0.79, "learning_rate": 1.1562951185806675e-06, "loss": 0.3767, "step": 1614 }, { "epoch": 0.79, "learning_rate": 1.1512566333007247e-06, "loss": 0.4145, "step": 1615 }, { "epoch": 0.79, "learning_rate": 1.1462277208418338e-06, "loss": 0.3716, "step": 1616 }, { "epoch": 0.79, "learning_rate": 1.1412083937122031e-06, "loss": 0.3486, "step": 1617 }, { "epoch": 0.79, "learning_rate": 1.136198664396198e-06, "loss": 0.364, "step": 1618 }, { "epoch": 0.79, "learning_rate": 1.1311985453543134e-06, "loss": 0.4053, "step": 1619 }, { "epoch": 0.79, "learning_rate": 1.1262080490231375e-06, "loss": 0.4488, "step": 1620 }, { "epoch": 0.79, "learning_rate": 1.1212271878153268e-06, "loss": 0.4062, "step": 1621 }, { "epoch": 0.79, "learning_rate": 1.1162559741195733e-06, "loss": 0.3609, "step": 1622 }, { "epoch": 0.79, "learning_rate": 1.111294420300571e-06, "loss": 0.3606, "step": 1623 }, { "epoch": 0.79, "learning_rate": 1.1063425386989913e-06, "loss": 0.3441, "step": 1624 }, { "epoch": 0.79, "learning_rate": 1.101400341631444e-06, "loss": 0.3595, "step": 1625 }, { "epoch": 0.79, "learning_rate": 1.0964678413904529e-06, "loss": 0.4387, "step": 1626 }, { "epoch": 0.79, "learning_rate": 1.0915450502444226e-06, "loss": 0.3861, "step": 1627 }, { "epoch": 0.79, "learning_rate": 1.0866319804376086e-06, "loss": 0.3664, "step": 1628 }, { "epoch": 0.79, "learning_rate": 1.0817286441900883e-06, "loss": 0.3523, "step": 1629 }, { "epoch": 0.79, "learning_rate": 1.076835053697728e-06, "loss": 0.4245, "step": 1630 }, { "epoch": 0.79, "learning_rate": 1.071951221132153e-06, "loss": 0.3622, "step": 1631 }, { "epoch": 0.79, "learning_rate": 1.0670771586407208e-06, "loss": 0.2966, "step": 1632 }, { "epoch": 0.79, "learning_rate": 1.0622128783464853e-06, "loss": 0.4502, "step": 1633 }, { "epoch": 0.8, "learning_rate": 1.057358392348171e-06, "loss": 0.3678, "step": 1634 }, { "epoch": 0.8, "learning_rate": 1.0525137127201407e-06, "loss": 0.3976, "step": 1635 }, { "epoch": 0.8, "learning_rate": 1.0476788515123687e-06, "loss": 0.4188, "step": 1636 }, { "epoch": 0.8, "learning_rate": 1.0428538207504057e-06, "loss": 0.3832, "step": 1637 }, { "epoch": 0.8, "learning_rate": 1.0380386324353508e-06, "loss": 0.3431, "step": 1638 }, { "epoch": 0.8, "learning_rate": 1.0332332985438248e-06, "loss": 0.3646, "step": 1639 }, { "epoch": 0.8, "learning_rate": 1.028437831027937e-06, "loss": 0.3236, "step": 1640 }, { "epoch": 0.8, "learning_rate": 1.0236522418152562e-06, "loss": 0.3467, "step": 1641 }, { "epoch": 0.8, "learning_rate": 1.0188765428087815e-06, "loss": 0.4123, "step": 1642 }, { "epoch": 0.8, "learning_rate": 1.0141107458869132e-06, "loss": 0.4197, "step": 1643 }, { "epoch": 0.8, "learning_rate": 1.0093548629034216e-06, "loss": 0.378, "step": 1644 }, { "epoch": 0.8, "learning_rate": 1.0046089056874175e-06, "loss": 0.3415, "step": 1645 }, { "epoch": 0.8, "learning_rate": 9.998728860433277e-07, "loss": 0.4136, "step": 1646 }, { "epoch": 0.8, "learning_rate": 9.951468157508575e-07, "loss": 0.2793, "step": 1647 }, { "epoch": 0.8, "learning_rate": 9.90430706564967e-07, "loss": 0.3604, "step": 1648 }, { "epoch": 0.8, "learning_rate": 9.857245702158413e-07, "loss": 0.3854, "step": 1649 }, { "epoch": 0.8, "learning_rate": 9.810284184088592e-07, "loss": 0.3139, "step": 1650 }, { "epoch": 0.8, "learning_rate": 9.76342262824566e-07, "loss": 0.4093, "step": 1651 }, { "epoch": 0.8, "learning_rate": 9.71666115118644e-07, "loss": 0.3384, "step": 1652 }, { "epoch": 0.8, "learning_rate": 9.669999869218827e-07, "loss": 0.376, "step": 1653 }, { "epoch": 0.8, "learning_rate": 9.62343889840151e-07, "loss": 0.4085, "step": 1654 }, { "epoch": 0.81, "learning_rate": 9.57697835454367e-07, "loss": 0.3524, "step": 1655 }, { "epoch": 0.81, "learning_rate": 9.530618353204718e-07, "loss": 0.3509, "step": 1656 }, { "epoch": 0.81, "learning_rate": 9.484359009693972e-07, "loss": 0.2863, "step": 1657 }, { "epoch": 0.81, "learning_rate": 9.438200439070388e-07, "loss": 0.2944, "step": 1658 }, { "epoch": 0.81, "learning_rate": 9.392142756142292e-07, "loss": 0.3319, "step": 1659 }, { "epoch": 0.81, "learning_rate": 9.346186075467056e-07, "loss": 0.3909, "step": 1660 }, { "epoch": 0.81, "learning_rate": 9.300330511350841e-07, "loss": 0.4045, "step": 1661 }, { "epoch": 0.81, "learning_rate": 9.254576177848313e-07, "loss": 0.4076, "step": 1662 }, { "epoch": 0.81, "learning_rate": 9.208923188762337e-07, "loss": 0.3543, "step": 1663 }, { "epoch": 0.81, "learning_rate": 9.163371657643716e-07, "loss": 0.4252, "step": 1664 }, { "epoch": 0.81, "learning_rate": 9.117921697790899e-07, "loss": 0.4512, "step": 1665 }, { "epoch": 0.81, "learning_rate": 9.072573422249692e-07, "loss": 0.3472, "step": 1666 }, { "epoch": 0.81, "learning_rate": 9.027326943813014e-07, "loss": 0.4484, "step": 1667 }, { "epoch": 0.81, "learning_rate": 8.982182375020565e-07, "loss": 0.4159, "step": 1668 }, { "epoch": 0.81, "learning_rate": 8.93713982815857e-07, "loss": 0.3285, "step": 1669 }, { "epoch": 0.81, "learning_rate": 8.892199415259501e-07, "loss": 0.3718, "step": 1670 }, { "epoch": 0.81, "learning_rate": 8.847361248101799e-07, "loss": 0.3935, "step": 1671 }, { "epoch": 0.81, "learning_rate": 8.802625438209606e-07, "loss": 0.3761, "step": 1672 }, { "epoch": 0.81, "learning_rate": 8.757992096852441e-07, "loss": 0.3942, "step": 1673 }, { "epoch": 0.81, "learning_rate": 8.713461335044981e-07, "loss": 0.364, "step": 1674 }, { "epoch": 0.82, "learning_rate": 8.669033263546756e-07, "loss": 0.3377, "step": 1675 }, { "epoch": 0.82, "learning_rate": 8.624707992861897e-07, "loss": 0.3696, "step": 1676 }, { "epoch": 0.82, "learning_rate": 8.580485633238822e-07, "loss": 0.3632, "step": 1677 }, { "epoch": 0.82, "learning_rate": 8.536366294669979e-07, "loss": 0.4541, "step": 1678 }, { "epoch": 0.82, "learning_rate": 8.492350086891587e-07, "loss": 0.3334, "step": 1679 }, { "epoch": 0.82, "learning_rate": 8.448437119383352e-07, "loss": 0.4105, "step": 1680 }, { "epoch": 0.82, "learning_rate": 8.40462750136819e-07, "loss": 0.3315, "step": 1681 }, { "epoch": 0.82, "learning_rate": 8.360921341811956e-07, "loss": 0.4004, "step": 1682 }, { "epoch": 0.82, "learning_rate": 8.317318749423192e-07, "loss": 0.4009, "step": 1683 }, { "epoch": 0.82, "learning_rate": 8.273819832652824e-07, "loss": 0.3653, "step": 1684 }, { "epoch": 0.82, "learning_rate": 8.230424699693923e-07, "loss": 0.4274, "step": 1685 }, { "epoch": 0.82, "learning_rate": 8.187133458481416e-07, "loss": 0.3502, "step": 1686 }, { "epoch": 0.82, "learning_rate": 8.143946216691817e-07, "loss": 0.3484, "step": 1687 }, { "epoch": 0.82, "learning_rate": 8.100863081742999e-07, "loss": 0.3295, "step": 1688 }, { "epoch": 0.82, "learning_rate": 8.05788416079386e-07, "loss": 0.3655, "step": 1689 }, { "epoch": 0.82, "learning_rate": 8.015009560744114e-07, "loss": 0.4699, "step": 1690 }, { "epoch": 0.82, "learning_rate": 7.972239388233959e-07, "loss": 0.3242, "step": 1691 }, { "epoch": 0.82, "learning_rate": 7.92957374964391e-07, "loss": 0.3797, "step": 1692 }, { "epoch": 0.82, "learning_rate": 7.887012751094447e-07, "loss": 0.4384, "step": 1693 }, { "epoch": 0.82, "learning_rate": 7.844556498445788e-07, "loss": 0.3491, "step": 1694 }, { "epoch": 0.82, "learning_rate": 7.802205097297633e-07, "loss": 0.3298, "step": 1695 }, { "epoch": 0.83, "learning_rate": 7.759958652988858e-07, "loss": 0.3594, "step": 1696 }, { "epoch": 0.83, "learning_rate": 7.717817270597339e-07, "loss": 0.373, "step": 1697 }, { "epoch": 0.83, "learning_rate": 7.675781054939585e-07, "loss": 0.2689, "step": 1698 }, { "epoch": 0.83, "learning_rate": 7.633850110570551e-07, "loss": 0.4125, "step": 1699 }, { "epoch": 0.83, "learning_rate": 7.592024541783344e-07, "loss": 0.3297, "step": 1700 }, { "epoch": 0.83, "learning_rate": 7.550304452608981e-07, "loss": 0.307, "step": 1701 }, { "epoch": 0.83, "learning_rate": 7.508689946816128e-07, "loss": 0.402, "step": 1702 }, { "epoch": 0.83, "learning_rate": 7.467181127910833e-07, "loss": 0.3604, "step": 1703 }, { "epoch": 0.83, "learning_rate": 7.425778099136272e-07, "loss": 0.3839, "step": 1704 }, { "epoch": 0.83, "learning_rate": 7.384480963472496e-07, "loss": 0.3747, "step": 1705 }, { "epoch": 0.83, "learning_rate": 7.343289823636168e-07, "loss": 0.3999, "step": 1706 }, { "epoch": 0.83, "learning_rate": 7.302204782080324e-07, "loss": 0.3276, "step": 1707 }, { "epoch": 0.83, "learning_rate": 7.261225940994088e-07, "loss": 0.3233, "step": 1708 }, { "epoch": 0.83, "learning_rate": 7.22035340230245e-07, "loss": 0.4009, "step": 1709 }, { "epoch": 0.83, "learning_rate": 7.179587267665999e-07, "loss": 0.3874, "step": 1710 }, { "epoch": 0.83, "learning_rate": 7.138927638480659e-07, "loss": 0.4132, "step": 1711 }, { "epoch": 0.83, "learning_rate": 7.098374615877452e-07, "loss": 0.4454, "step": 1712 }, { "epoch": 0.83, "learning_rate": 7.057928300722244e-07, "loss": 0.4429, "step": 1713 }, { "epoch": 0.83, "learning_rate": 7.017588793615499e-07, "loss": 0.3965, "step": 1714 }, { "epoch": 0.83, "learning_rate": 6.977356194891999e-07, "loss": 0.2947, "step": 1715 }, { "epoch": 0.84, "learning_rate": 6.937230604620642e-07, "loss": 0.3592, "step": 1716 }, { "epoch": 0.84, "learning_rate": 6.897212122604147e-07, "loss": 0.344, "step": 1717 }, { "epoch": 0.84, "learning_rate": 6.857300848378857e-07, "loss": 0.3808, "step": 1718 }, { "epoch": 0.84, "learning_rate": 6.81749688121443e-07, "loss": 0.3346, "step": 1719 }, { "epoch": 0.84, "learning_rate": 6.777800320113642e-07, "loss": 0.3592, "step": 1720 }, { "epoch": 0.84, "learning_rate": 6.738211263812111e-07, "loss": 0.3767, "step": 1721 }, { "epoch": 0.84, "learning_rate": 6.698729810778065e-07, "loss": 0.3378, "step": 1722 }, { "epoch": 0.84, "learning_rate": 6.659356059212107e-07, "loss": 0.4169, "step": 1723 }, { "epoch": 0.84, "learning_rate": 6.62009010704695e-07, "loss": 0.4049, "step": 1724 }, { "epoch": 0.84, "learning_rate": 6.580932051947181e-07, "loss": 0.3898, "step": 1725 }, { "epoch": 0.84, "learning_rate": 6.541881991309013e-07, "loss": 0.3931, "step": 1726 }, { "epoch": 0.84, "learning_rate": 6.502940022260041e-07, "loss": 0.2963, "step": 1727 }, { "epoch": 0.84, "learning_rate": 6.464106241659051e-07, "loss": 0.4189, "step": 1728 }, { "epoch": 0.84, "learning_rate": 6.425380746095699e-07, "loss": 0.3476, "step": 1729 }, { "epoch": 0.84, "learning_rate": 6.386763631890313e-07, "loss": 0.3116, "step": 1730 }, { "epoch": 0.84, "learning_rate": 6.348254995093656e-07, "loss": 0.3728, "step": 1731 }, { "epoch": 0.84, "learning_rate": 6.309854931486675e-07, "loss": 0.3052, "step": 1732 }, { "epoch": 0.84, "learning_rate": 6.271563536580266e-07, "loss": 0.356, "step": 1733 }, { "epoch": 0.84, "learning_rate": 6.233380905615049e-07, "loss": 0.3549, "step": 1734 }, { "epoch": 0.84, "learning_rate": 6.195307133561101e-07, "loss": 0.3997, "step": 1735 }, { "epoch": 0.84, "learning_rate": 6.157342315117754e-07, "loss": 0.3807, "step": 1736 }, { "epoch": 0.85, "learning_rate": 6.119486544713332e-07, "loss": 0.3796, "step": 1737 }, { "epoch": 0.85, "learning_rate": 6.081739916504948e-07, "loss": 0.3872, "step": 1738 }, { "epoch": 0.85, "learning_rate": 6.04410252437822e-07, "loss": 0.3975, "step": 1739 }, { "epoch": 0.85, "learning_rate": 6.006574461947107e-07, "loss": 0.3017, "step": 1740 }, { "epoch": 0.85, "learning_rate": 5.969155822553607e-07, "loss": 0.3659, "step": 1741 }, { "epoch": 0.85, "learning_rate": 5.931846699267558e-07, "loss": 0.3782, "step": 1742 }, { "epoch": 0.85, "learning_rate": 5.894647184886415e-07, "loss": 0.3614, "step": 1743 }, { "epoch": 0.85, "learning_rate": 5.857557371934991e-07, "loss": 0.3534, "step": 1744 }, { "epoch": 0.85, "learning_rate": 5.820577352665252e-07, "loss": 0.4125, "step": 1745 }, { "epoch": 0.85, "learning_rate": 5.783707219056078e-07, "loss": 0.3714, "step": 1746 }, { "epoch": 0.85, "learning_rate": 5.746947062813047e-07, "loss": 0.3498, "step": 1747 }, { "epoch": 0.85, "learning_rate": 5.710296975368163e-07, "loss": 0.3777, "step": 1748 }, { "epoch": 0.85, "learning_rate": 5.673757047879702e-07, "loss": 0.3221, "step": 1749 }, { "epoch": 0.85, "learning_rate": 5.637327371231921e-07, "loss": 0.3699, "step": 1750 }, { "epoch": 0.85, "learning_rate": 5.601008036034844e-07, "loss": 0.4939, "step": 1751 }, { "epoch": 0.85, "learning_rate": 5.564799132624065e-07, "loss": 0.4079, "step": 1752 }, { "epoch": 0.85, "learning_rate": 5.5287007510605e-07, "loss": 0.3514, "step": 1753 }, { "epoch": 0.85, "learning_rate": 5.492712981130171e-07, "loss": 0.3952, "step": 1754 }, { "epoch": 0.85, "learning_rate": 5.456835912343977e-07, "loss": 0.4358, "step": 1755 }, { "epoch": 0.85, "learning_rate": 5.42106963393747e-07, "loss": 0.3496, "step": 1756 }, { "epoch": 0.86, "learning_rate": 5.385414234870645e-07, "loss": 0.3829, "step": 1757 }, { "epoch": 0.86, "learning_rate": 5.349869803827717e-07, "loss": 0.3437, "step": 1758 }, { "epoch": 0.86, "learning_rate": 5.314436429216874e-07, "loss": 0.4028, "step": 1759 }, { "epoch": 0.86, "learning_rate": 5.279114199170094e-07, "loss": 0.3054, "step": 1760 }, { "epoch": 0.86, "learning_rate": 5.243903201542927e-07, "loss": 0.368, "step": 1761 }, { "epoch": 0.86, "learning_rate": 5.208803523914213e-07, "loss": 0.373, "step": 1762 }, { "epoch": 0.86, "learning_rate": 5.173815253585951e-07, "loss": 0.3975, "step": 1763 }, { "epoch": 0.86, "learning_rate": 5.138938477583017e-07, "loss": 0.3918, "step": 1764 }, { "epoch": 0.86, "learning_rate": 5.104173282652985e-07, "loss": 0.3919, "step": 1765 }, { "epoch": 0.86, "learning_rate": 5.0695197552659e-07, "loss": 0.3868, "step": 1766 }, { "epoch": 0.86, "learning_rate": 5.034977981614048e-07, "loss": 0.3925, "step": 1767 }, { "epoch": 0.86, "learning_rate": 5.000548047611764e-07, "loss": 0.3314, "step": 1768 }, { "epoch": 0.86, "learning_rate": 4.966230038895192e-07, "loss": 0.3975, "step": 1769 }, { "epoch": 0.86, "learning_rate": 4.93202404082213e-07, "loss": 0.3455, "step": 1770 }, { "epoch": 0.86, "learning_rate": 4.897930138471746e-07, "loss": 0.3233, "step": 1771 }, { "epoch": 0.86, "learning_rate": 4.863948416644382e-07, "loss": 0.3989, "step": 1772 }, { "epoch": 0.86, "learning_rate": 4.830078959861395e-07, "loss": 0.3117, "step": 1773 }, { "epoch": 0.86, "learning_rate": 4.796321852364877e-07, "loss": 0.3743, "step": 1774 }, { "epoch": 0.86, "learning_rate": 4.762677178117503e-07, "loss": 0.3994, "step": 1775 }, { "epoch": 0.86, "learning_rate": 4.7291450208022836e-07, "loss": 0.407, "step": 1776 }, { "epoch": 0.86, "learning_rate": 4.695725463822376e-07, "loss": 0.4135, "step": 1777 }, { "epoch": 0.87, "learning_rate": 4.6624185903008713e-07, "loss": 0.3153, "step": 1778 }, { "epoch": 0.87, "learning_rate": 4.62922448308058e-07, "loss": 0.3721, "step": 1779 }, { "epoch": 0.87, "learning_rate": 4.596143224723842e-07, "loss": 0.3957, "step": 1780 }, { "epoch": 0.87, "learning_rate": 4.563174897512307e-07, "loss": 0.4356, "step": 1781 }, { "epoch": 0.87, "learning_rate": 4.5303195834467463e-07, "loss": 0.3406, "step": 1782 }, { "epoch": 0.87, "learning_rate": 4.49757736424683e-07, "loss": 0.3842, "step": 1783 }, { "epoch": 0.87, "learning_rate": 4.4649483213509257e-07, "loss": 0.3812, "step": 1784 }, { "epoch": 0.87, "learning_rate": 4.4324325359159146e-07, "loss": 0.3788, "step": 1785 }, { "epoch": 0.87, "learning_rate": 4.4000300888169753e-07, "loss": 0.3892, "step": 1786 }, { "epoch": 0.87, "learning_rate": 4.367741060647379e-07, "loss": 0.2955, "step": 1787 }, { "epoch": 0.87, "learning_rate": 4.3355655317182944e-07, "loss": 0.3675, "step": 1788 }, { "epoch": 0.87, "learning_rate": 4.3035035820585935e-07, "loss": 0.3766, "step": 1789 }, { "epoch": 0.87, "learning_rate": 4.271555291414636e-07, "loss": 0.3677, "step": 1790 }, { "epoch": 0.87, "learning_rate": 4.239720739250108e-07, "loss": 0.378, "step": 1791 }, { "epoch": 0.87, "learning_rate": 4.2080000047457716e-07, "loss": 0.3211, "step": 1792 }, { "epoch": 0.87, "learning_rate": 4.176393166799303e-07, "loss": 0.3723, "step": 1793 }, { "epoch": 0.87, "learning_rate": 4.144900304025101e-07, "loss": 0.3447, "step": 1794 }, { "epoch": 0.87, "learning_rate": 4.1135214947540524e-07, "loss": 0.3207, "step": 1795 }, { "epoch": 0.87, "learning_rate": 4.082256817033392e-07, "loss": 0.3887, "step": 1796 }, { "epoch": 0.87, "learning_rate": 4.0511063486264655e-07, "loss": 0.3212, "step": 1797 }, { "epoch": 0.88, "learning_rate": 4.020070167012541e-07, "loss": 0.3544, "step": 1798 }, { "epoch": 0.88, "learning_rate": 3.98914834938664e-07, "loss": 0.3498, "step": 1799 }, { "epoch": 0.88, "learning_rate": 3.9583409726593246e-07, "loss": 0.845, "step": 1800 }, { "epoch": 0.88, "learning_rate": 3.9276481134565224e-07, "loss": 0.3047, "step": 1801 }, { "epoch": 0.88, "learning_rate": 3.8970698481193225e-07, "loss": 0.3535, "step": 1802 }, { "epoch": 0.88, "learning_rate": 3.8666062527037804e-07, "loss": 0.3755, "step": 1803 }, { "epoch": 0.88, "learning_rate": 3.8362574029807477e-07, "loss": 0.3217, "step": 1804 }, { "epoch": 0.88, "learning_rate": 3.8060233744356634e-07, "loss": 0.3336, "step": 1805 }, { "epoch": 0.88, "learning_rate": 3.775904242268391e-07, "loss": 0.3501, "step": 1806 }, { "epoch": 0.88, "learning_rate": 3.745900081393e-07, "loss": 0.3538, "step": 1807 }, { "epoch": 0.88, "learning_rate": 3.716010966437611e-07, "loss": 0.3392, "step": 1808 }, { "epoch": 0.88, "learning_rate": 3.6862369717441895e-07, "loss": 0.3496, "step": 1809 }, { "epoch": 0.88, "learning_rate": 3.656578171368369e-07, "loss": 0.3951, "step": 1810 }, { "epoch": 0.88, "learning_rate": 3.627034639079258e-07, "loss": 0.3595, "step": 1811 }, { "epoch": 0.88, "learning_rate": 3.5976064483592754e-07, "loss": 0.2795, "step": 1812 }, { "epoch": 0.88, "learning_rate": 3.5682936724039497e-07, "loss": 0.4008, "step": 1813 }, { "epoch": 0.88, "learning_rate": 3.539096384121743e-07, "loss": 0.3322, "step": 1814 }, { "epoch": 0.88, "learning_rate": 3.5100146561338645e-07, "loss": 0.3612, "step": 1815 }, { "epoch": 0.88, "learning_rate": 3.4810485607740975e-07, "loss": 0.3433, "step": 1816 }, { "epoch": 0.88, "learning_rate": 3.4521981700886276e-07, "loss": 0.3009, "step": 1817 }, { "epoch": 0.88, "learning_rate": 3.423463555835843e-07, "loss": 0.3315, "step": 1818 }, { "epoch": 0.89, "learning_rate": 3.3948447894861624e-07, "loss": 0.3734, "step": 1819 }, { "epoch": 0.89, "learning_rate": 3.366341942221868e-07, "loss": 0.3183, "step": 1820 }, { "epoch": 0.89, "learning_rate": 3.3379550849369114e-07, "loss": 0.3467, "step": 1821 }, { "epoch": 0.89, "learning_rate": 3.309684288236775e-07, "loss": 0.3124, "step": 1822 }, { "epoch": 0.89, "learning_rate": 3.28152962243824e-07, "loss": 0.3581, "step": 1823 }, { "epoch": 0.89, "learning_rate": 3.253491157569244e-07, "loss": 0.2892, "step": 1824 }, { "epoch": 0.89, "learning_rate": 3.2255689633687084e-07, "loss": 0.3414, "step": 1825 }, { "epoch": 0.89, "learning_rate": 3.1977631092863613e-07, "loss": 0.4158, "step": 1826 }, { "epoch": 0.89, "learning_rate": 3.170073664482559e-07, "loss": 0.3336, "step": 1827 }, { "epoch": 0.89, "learning_rate": 3.142500697828116e-07, "loss": 0.3151, "step": 1828 }, { "epoch": 0.89, "learning_rate": 3.115044277904139e-07, "loss": 0.3275, "step": 1829 }, { "epoch": 0.89, "learning_rate": 3.0877044730018515e-07, "loss": 0.311, "step": 1830 }, { "epoch": 0.89, "learning_rate": 3.0604813511224243e-07, "loss": 0.4183, "step": 1831 }, { "epoch": 0.89, "learning_rate": 3.033374979976811e-07, "loss": 0.4054, "step": 1832 }, { "epoch": 0.89, "learning_rate": 3.006385426985575e-07, "loss": 0.3335, "step": 1833 }, { "epoch": 0.89, "learning_rate": 2.979512759278719e-07, "loss": 0.4085, "step": 1834 }, { "epoch": 0.89, "learning_rate": 2.9527570436955255e-07, "loss": 0.3868, "step": 1835 }, { "epoch": 0.89, "learning_rate": 2.926118346784379e-07, "loss": 0.4755, "step": 1836 }, { "epoch": 0.89, "learning_rate": 2.8995967348026235e-07, "loss": 0.4625, "step": 1837 }, { "epoch": 0.89, "learning_rate": 2.873192273716369e-07, "loss": 0.3671, "step": 1838 }, { "epoch": 0.89, "learning_rate": 2.8469050292003476e-07, "loss": 0.3524, "step": 1839 }, { "epoch": 0.9, "learning_rate": 2.8207350666377366e-07, "loss": 0.3396, "step": 1840 }, { "epoch": 0.9, "learning_rate": 2.7946824511200067e-07, "loss": 0.3077, "step": 1841 }, { "epoch": 0.9, "learning_rate": 2.768747247446757e-07, "loss": 0.3491, "step": 1842 }, { "epoch": 0.9, "learning_rate": 2.7429295201255643e-07, "loss": 0.4363, "step": 1843 }, { "epoch": 0.9, "learning_rate": 2.7172293333717846e-07, "loss": 0.3564, "step": 1844 }, { "epoch": 0.9, "learning_rate": 2.691646751108451e-07, "loss": 0.368, "step": 1845 }, { "epoch": 0.9, "learning_rate": 2.666181836966053e-07, "loss": 0.3167, "step": 1846 }, { "epoch": 0.9, "learning_rate": 2.6408346542824317e-07, "loss": 0.2819, "step": 1847 }, { "epoch": 0.9, "learning_rate": 2.615605266102589e-07, "loss": 0.349, "step": 1848 }, { "epoch": 0.9, "learning_rate": 2.5904937351785454e-07, "loss": 0.3918, "step": 1849 }, { "epoch": 0.9, "learning_rate": 2.5655001239691836e-07, "loss": 0.3981, "step": 1850 }, { "epoch": 0.9, "learning_rate": 2.5406244946400706e-07, "loss": 0.3805, "step": 1851 }, { "epoch": 0.9, "learning_rate": 2.515866909063347e-07, "loss": 0.3066, "step": 1852 }, { "epoch": 0.9, "learning_rate": 2.491227428817539e-07, "loss": 0.3756, "step": 1853 }, { "epoch": 0.9, "learning_rate": 2.466706115187406e-07, "loss": 0.3604, "step": 1854 }, { "epoch": 0.9, "learning_rate": 2.442303029163806e-07, "loss": 0.4005, "step": 1855 }, { "epoch": 0.9, "learning_rate": 2.4180182314435305e-07, "loss": 0.383, "step": 1856 }, { "epoch": 0.9, "learning_rate": 2.393851782429157e-07, "loss": 0.3805, "step": 1857 }, { "epoch": 0.9, "learning_rate": 2.369803742228899e-07, "loss": 0.4134, "step": 1858 }, { "epoch": 0.9, "learning_rate": 2.345874170656459e-07, "loss": 0.3783, "step": 1859 }, { "epoch": 0.91, "learning_rate": 2.322063127230878e-07, "loss": 0.3746, "step": 1860 }, { "epoch": 0.91, "learning_rate": 2.2983706711763808e-07, "loss": 0.3906, "step": 1861 }, { "epoch": 0.91, "learning_rate": 2.274796861422246e-07, "loss": 0.3895, "step": 1862 }, { "epoch": 0.91, "learning_rate": 2.2513417566026209e-07, "loss": 0.4892, "step": 1863 }, { "epoch": 0.91, "learning_rate": 2.2280054150564501e-07, "loss": 0.3668, "step": 1864 }, { "epoch": 0.91, "learning_rate": 2.2047878948272373e-07, "loss": 0.3599, "step": 1865 }, { "epoch": 0.91, "learning_rate": 2.1816892536629775e-07, "loss": 0.3715, "step": 1866 }, { "epoch": 0.91, "learning_rate": 2.1587095490159638e-07, "loss": 0.4082, "step": 1867 }, { "epoch": 0.91, "learning_rate": 2.1358488380426757e-07, "loss": 0.3556, "step": 1868 }, { "epoch": 0.91, "learning_rate": 2.113107177603607e-07, "loss": 0.3248, "step": 1869 }, { "epoch": 0.91, "learning_rate": 2.090484624263167e-07, "loss": 0.4169, "step": 1870 }, { "epoch": 0.91, "learning_rate": 2.06798123428949e-07, "loss": 0.4268, "step": 1871 }, { "epoch": 0.91, "learning_rate": 2.0455970636543364e-07, "loss": 0.3803, "step": 1872 }, { "epoch": 0.91, "learning_rate": 2.0233321680329432e-07, "loss": 0.3739, "step": 1873 }, { "epoch": 0.91, "learning_rate": 2.0011866028038617e-07, "loss": 0.4066, "step": 1874 }, { "epoch": 0.91, "learning_rate": 1.9791604230488427e-07, "loss": 0.4043, "step": 1875 }, { "epoch": 0.91, "learning_rate": 1.9572536835527013e-07, "loss": 0.3702, "step": 1876 }, { "epoch": 0.91, "learning_rate": 1.9354664388031685e-07, "loss": 0.3536, "step": 1877 }, { "epoch": 0.91, "learning_rate": 1.9137987429907635e-07, "loss": 0.3859, "step": 1878 }, { "epoch": 0.91, "learning_rate": 1.892250650008648e-07, "loss": 0.3465, "step": 1879 }, { "epoch": 0.91, "learning_rate": 1.8708222134525168e-07, "loss": 0.3588, "step": 1880 }, { "epoch": 0.92, "learning_rate": 1.84951348662043e-07, "loss": 0.3701, "step": 1881 }, { "epoch": 0.92, "learning_rate": 1.8283245225127145e-07, "loss": 0.3143, "step": 1882 }, { "epoch": 0.92, "learning_rate": 1.8072553738318012e-07, "loss": 0.3384, "step": 1883 }, { "epoch": 0.92, "learning_rate": 1.7863060929821208e-07, "loss": 0.3667, "step": 1884 }, { "epoch": 0.92, "learning_rate": 1.7654767320699596e-07, "loss": 0.311, "step": 1885 }, { "epoch": 0.92, "learning_rate": 1.7447673429033361e-07, "loss": 0.3292, "step": 1886 }, { "epoch": 0.92, "learning_rate": 1.724177976991853e-07, "loss": 0.4148, "step": 1887 }, { "epoch": 0.92, "learning_rate": 1.7037086855465902e-07, "loss": 0.3741, "step": 1888 }, { "epoch": 0.92, "learning_rate": 1.6833595194799767e-07, "loss": 0.405, "step": 1889 }, { "epoch": 0.92, "learning_rate": 1.6631305294056655e-07, "loss": 0.3785, "step": 1890 }, { "epoch": 0.92, "learning_rate": 1.6430217656383806e-07, "loss": 0.3515, "step": 1891 }, { "epoch": 0.92, "learning_rate": 1.6230332781938253e-07, "loss": 0.3749, "step": 1892 }, { "epoch": 0.92, "learning_rate": 1.6031651167885465e-07, "loss": 0.3727, "step": 1893 }, { "epoch": 0.92, "learning_rate": 1.583417330839798e-07, "loss": 0.3692, "step": 1894 }, { "epoch": 0.92, "learning_rate": 1.5637899694654456e-07, "loss": 0.3235, "step": 1895 }, { "epoch": 0.92, "learning_rate": 1.544283081483805e-07, "loss": 0.8461, "step": 1896 }, { "epoch": 0.92, "learning_rate": 1.5248967154135708e-07, "loss": 0.3479, "step": 1897 }, { "epoch": 0.92, "learning_rate": 1.5056309194736385e-07, "loss": 0.4171, "step": 1898 }, { "epoch": 0.92, "learning_rate": 1.4864857415830436e-07, "loss": 0.3317, "step": 1899 }, { "epoch": 0.92, "learning_rate": 1.4674612293607893e-07, "loss": 0.4031, "step": 1900 }, { "epoch": 0.93, "learning_rate": 1.4485574301257688e-07, "loss": 0.3466, "step": 1901 }, { "epoch": 0.93, "learning_rate": 1.4297743908966212e-07, "loss": 0.3667, "step": 1902 }, { "epoch": 0.93, "learning_rate": 1.4111121583916254e-07, "loss": 0.3184, "step": 1903 }, { "epoch": 0.93, "learning_rate": 1.3925707790285848e-07, "loss": 0.3604, "step": 1904 }, { "epoch": 0.93, "learning_rate": 1.3741502989247146e-07, "loss": 0.36, "step": 1905 }, { "epoch": 0.93, "learning_rate": 1.3558507638965158e-07, "loss": 0.3773, "step": 1906 }, { "epoch": 0.93, "learning_rate": 1.337672219459668e-07, "loss": 0.3169, "step": 1907 }, { "epoch": 0.93, "learning_rate": 1.3196147108289148e-07, "loss": 0.449, "step": 1908 }, { "epoch": 0.93, "learning_rate": 1.3016782829179564e-07, "loss": 0.4222, "step": 1909 }, { "epoch": 0.93, "learning_rate": 1.2838629803393343e-07, "loss": 0.3947, "step": 1910 }, { "epoch": 0.93, "learning_rate": 1.2661688474043145e-07, "loss": 0.4156, "step": 1911 }, { "epoch": 0.93, "learning_rate": 1.2485959281227865e-07, "loss": 0.3312, "step": 1912 }, { "epoch": 0.93, "learning_rate": 1.2311442662031493e-07, "loss": 0.3798, "step": 1913 }, { "epoch": 0.93, "learning_rate": 1.2138139050522024e-07, "loss": 0.399, "step": 1914 }, { "epoch": 0.93, "learning_rate": 1.1966048877750435e-07, "loss": 0.4002, "step": 1915 }, { "epoch": 0.93, "learning_rate": 1.1795172571749503e-07, "loss": 0.3067, "step": 1916 }, { "epoch": 0.93, "learning_rate": 1.1625510557532916e-07, "loss": 0.2976, "step": 1917 }, { "epoch": 0.93, "learning_rate": 1.1457063257093892e-07, "loss": 0.3223, "step": 1918 }, { "epoch": 0.93, "learning_rate": 1.1289831089404568e-07, "loss": 0.3551, "step": 1919 }, { "epoch": 0.93, "learning_rate": 1.1123814470414607e-07, "loss": 0.3206, "step": 1920 }, { "epoch": 0.93, "learning_rate": 1.0959013813050368e-07, "loss": 0.3882, "step": 1921 }, { "epoch": 0.94, "learning_rate": 1.0795429527213685e-07, "loss": 0.3233, "step": 1922 }, { "epoch": 0.94, "learning_rate": 1.0633062019780981e-07, "loss": 0.4037, "step": 1923 }, { "epoch": 0.94, "learning_rate": 1.0471911694602321e-07, "loss": 0.329, "step": 1924 }, { "epoch": 0.94, "learning_rate": 1.0311978952500301e-07, "loss": 0.3167, "step": 1925 }, { "epoch": 0.94, "learning_rate": 1.0153264191269052e-07, "loss": 0.4101, "step": 1926 }, { "epoch": 0.94, "learning_rate": 9.99576780567324e-08, "loss": 0.3057, "step": 1927 }, { "epoch": 0.94, "learning_rate": 9.839490187447176e-08, "loss": 0.3706, "step": 1928 }, { "epoch": 0.94, "learning_rate": 9.684431725293763e-08, "loss": 0.4363, "step": 1929 }, { "epoch": 0.94, "learning_rate": 9.530592804883498e-08, "loss": 0.4211, "step": 1930 }, { "epoch": 0.94, "learning_rate": 9.37797380885358e-08, "loss": 0.3386, "step": 1931 }, { "epoch": 0.94, "learning_rate": 9.226575116807023e-08, "loss": 0.364, "step": 1932 }, { "epoch": 0.94, "learning_rate": 9.076397105311497e-08, "loss": 0.4193, "step": 1933 }, { "epoch": 0.94, "learning_rate": 8.927440147898703e-08, "loss": 0.4174, "step": 1934 }, { "epoch": 0.94, "learning_rate": 8.779704615063001e-08, "loss": 0.3397, "step": 1935 }, { "epoch": 0.94, "learning_rate": 8.633190874261011e-08, "loss": 0.3515, "step": 1936 }, { "epoch": 0.94, "learning_rate": 8.487899289910284e-08, "loss": 0.284, "step": 1937 }, { "epoch": 0.94, "learning_rate": 8.343830223388638e-08, "loss": 0.3996, "step": 1938 }, { "epoch": 0.94, "learning_rate": 8.20098403303321e-08, "loss": 0.3508, "step": 1939 }, { "epoch": 0.94, "learning_rate": 8.059361074139293e-08, "loss": 0.3328, "step": 1940 }, { "epoch": 0.94, "learning_rate": 7.918961698959892e-08, "loss": 0.3377, "step": 1941 }, { "epoch": 0.95, "learning_rate": 7.779786256704669e-08, "loss": 0.3321, "step": 1942 }, { "epoch": 0.95, "learning_rate": 7.641835093538885e-08, "loss": 0.3276, "step": 1943 }, { "epoch": 0.95, "learning_rate": 7.505108552582852e-08, "loss": 0.4176, "step": 1944 }, { "epoch": 0.95, "learning_rate": 7.369606973910869e-08, "loss": 0.3407, "step": 1945 }, { "epoch": 0.95, "learning_rate": 7.235330694550402e-08, "loss": 0.3639, "step": 1946 }, { "epoch": 0.95, "learning_rate": 7.102280048481403e-08, "loss": 0.3516, "step": 1947 }, { "epoch": 0.95, "learning_rate": 6.970455366635154e-08, "loss": 0.2783, "step": 1948 }, { "epoch": 0.95, "learning_rate": 6.839856976893822e-08, "loss": 0.3215, "step": 1949 }, { "epoch": 0.95, "learning_rate": 6.710485204089456e-08, "loss": 0.3735, "step": 1950 }, { "epoch": 0.95, "learning_rate": 6.582340370003048e-08, "loss": 0.3453, "step": 1951 }, { "epoch": 0.95, "learning_rate": 6.45542279336403e-08, "loss": 0.3638, "step": 1952 }, { "epoch": 0.95, "learning_rate": 6.329732789849275e-08, "loss": 0.2722, "step": 1953 }, { "epoch": 0.95, "learning_rate": 6.20527067208232e-08, "loss": 0.328, "step": 1954 }, { "epoch": 0.95, "learning_rate": 6.082036749632702e-08, "loss": 0.3812, "step": 1955 }, { "epoch": 0.95, "learning_rate": 5.96003132901507e-08, "loss": 0.4249, "step": 1956 }, { "epoch": 0.95, "learning_rate": 5.8392547136885133e-08, "loss": 0.3168, "step": 1957 }, { "epoch": 0.95, "learning_rate": 5.7197072040557356e-08, "loss": 0.3758, "step": 1958 }, { "epoch": 0.95, "learning_rate": 5.6013890974623286e-08, "loss": 0.3527, "step": 1959 }, { "epoch": 0.95, "learning_rate": 5.484300688195998e-08, "loss": 0.3632, "step": 1960 }, { "epoch": 0.95, "learning_rate": 5.368442267486007e-08, "loss": 0.3541, "step": 1961 }, { "epoch": 0.95, "learning_rate": 5.253814123502232e-08, "loss": 0.4355, "step": 1962 }, { "epoch": 0.96, "learning_rate": 5.140416541354498e-08, "loss": 0.3477, "step": 1963 }, { "epoch": 0.96, "learning_rate": 5.028249803091967e-08, "loss": 0.4051, "step": 1964 }, { "epoch": 0.96, "learning_rate": 4.91731418770236e-08, "loss": 0.3348, "step": 1965 }, { "epoch": 0.96, "learning_rate": 4.807609971111238e-08, "loss": 0.376, "step": 1966 }, { "epoch": 0.96, "learning_rate": 4.699137426181444e-08, "loss": 0.3842, "step": 1967 }, { "epoch": 0.96, "learning_rate": 4.591896822712216e-08, "loss": 0.3797, "step": 1968 }, { "epoch": 0.96, "learning_rate": 4.485888427438745e-08, "loss": 0.405, "step": 1969 }, { "epoch": 0.96, "learning_rate": 4.381112504031337e-08, "loss": 0.3976, "step": 1970 }, { "epoch": 0.96, "learning_rate": 4.2775693130948094e-08, "loss": 0.3887, "step": 1971 }, { "epoch": 0.96, "learning_rate": 4.1752591121678733e-08, "loss": 0.3716, "step": 1972 }, { "epoch": 0.96, "learning_rate": 4.074182155722583e-08, "loss": 0.3972, "step": 1973 }, { "epoch": 0.96, "learning_rate": 3.974338695163393e-08, "loss": 0.3936, "step": 1974 }, { "epoch": 0.96, "learning_rate": 3.8757289788268756e-08, "loss": 0.3317, "step": 1975 }, { "epoch": 0.96, "learning_rate": 3.7783532519808376e-08, "loss": 0.353, "step": 1976 }, { "epoch": 0.96, "learning_rate": 3.6822117568240945e-08, "loss": 0.3945, "step": 1977 }, { "epoch": 0.96, "learning_rate": 3.5873047324852526e-08, "loss": 0.3268, "step": 1978 }, { "epoch": 0.96, "learning_rate": 3.493632415022763e-08, "loss": 0.3933, "step": 1979 }, { "epoch": 0.96, "learning_rate": 3.4011950374238655e-08, "loss": 0.3937, "step": 1980 }, { "epoch": 0.96, "learning_rate": 3.309992829604314e-08, "loss": 0.3078, "step": 1981 }, { "epoch": 0.96, "learning_rate": 3.220026018407541e-08, "loss": 0.3895, "step": 1982 }, { "epoch": 0.97, "learning_rate": 3.1312948276043254e-08, "loss": 0.359, "step": 1983 }, { "epoch": 0.97, "learning_rate": 3.043799477892129e-08, "loss": 0.3391, "step": 1984 }, { "epoch": 0.97, "learning_rate": 2.957540186894481e-08, "loss": 0.3608, "step": 1985 }, { "epoch": 0.97, "learning_rate": 2.8725171691605934e-08, "loss": 0.3642, "step": 1986 }, { "epoch": 0.97, "learning_rate": 2.788730636164749e-08, "loss": 0.4653, "step": 1987 }, { "epoch": 0.97, "learning_rate": 2.706180796305691e-08, "loss": 0.3841, "step": 1988 }, { "epoch": 0.97, "learning_rate": 2.624867854906288e-08, "loss": 0.3107, "step": 1989 }, { "epoch": 0.97, "learning_rate": 2.5447920142128712e-08, "loss": 0.3954, "step": 1990 }, { "epoch": 0.97, "learning_rate": 2.4659534733947333e-08, "loss": 0.3017, "step": 1991 }, { "epoch": 0.97, "learning_rate": 2.388352428543794e-08, "loss": 0.3332, "step": 1992 }, { "epoch": 0.97, "learning_rate": 2.311989072673937e-08, "loss": 0.3202, "step": 1993 }, { "epoch": 0.97, "learning_rate": 2.236863595720562e-08, "loss": 0.3456, "step": 1994 }, { "epoch": 0.97, "learning_rate": 2.1629761845401442e-08, "loss": 0.3739, "step": 1995 }, { "epoch": 0.97, "learning_rate": 2.0903270229098992e-08, "loss": 0.3975, "step": 1996 }, { "epoch": 0.97, "learning_rate": 2.0189162915270065e-08, "loss": 0.3334, "step": 1997 }, { "epoch": 0.97, "learning_rate": 1.9487441680084983e-08, "loss": 0.3305, "step": 1998 }, { "epoch": 0.97, "learning_rate": 1.8798108268905934e-08, "loss": 0.3725, "step": 1999 }, { "epoch": 0.97, "learning_rate": 1.8121164396283643e-08, "loss": 0.3798, "step": 2000 }, { "epoch": 0.97, "learning_rate": 1.7456611745952923e-08, "loss": 0.298, "step": 2001 }, { "epoch": 0.97, "learning_rate": 1.6804451970827697e-08, "loss": 0.4196, "step": 2002 }, { "epoch": 0.97, "learning_rate": 1.6164686692998198e-08, "loss": 0.3477, "step": 2003 }, { "epoch": 0.98, "learning_rate": 1.5537317503727113e-08, "loss": 0.2906, "step": 2004 }, { "epoch": 0.98, "learning_rate": 1.4922345963442886e-08, "loss": 0.3621, "step": 2005 }, { "epoch": 0.98, "learning_rate": 1.431977360173975e-08, "loss": 0.3149, "step": 2006 }, { "epoch": 0.98, "learning_rate": 1.372960191737105e-08, "loss": 0.3879, "step": 2007 }, { "epoch": 0.98, "learning_rate": 1.315183237824591e-08, "loss": 0.3936, "step": 2008 }, { "epoch": 0.98, "learning_rate": 1.2586466421427579e-08, "loss": 0.2993, "step": 2009 }, { "epoch": 0.98, "learning_rate": 1.2033505453127314e-08, "loss": 0.4249, "step": 2010 }, { "epoch": 0.98, "learning_rate": 1.1492950848701612e-08, "loss": 0.4134, "step": 2011 }, { "epoch": 0.98, "learning_rate": 1.0964803952650539e-08, "loss": 0.3871, "step": 2012 }, { "epoch": 0.98, "learning_rate": 1.0449066078611069e-08, "loss": 0.4088, "step": 2013 }, { "epoch": 0.98, "learning_rate": 9.945738509358205e-09, "loss": 0.4053, "step": 2014 }, { "epoch": 0.98, "learning_rate": 9.454822496796635e-09, "loss": 0.3628, "step": 2015 }, { "epoch": 0.98, "learning_rate": 8.976319261962407e-09, "loss": 0.3554, "step": 2016 }, { "epoch": 0.98, "learning_rate": 8.510229995016828e-09, "loss": 0.3447, "step": 2017 }, { "epoch": 0.98, "learning_rate": 8.056555855243675e-09, "loss": 0.4152, "step": 2018 }, { "epoch": 0.98, "learning_rate": 7.615297971049208e-09, "loss": 0.387, "step": 2019 }, { "epoch": 0.98, "learning_rate": 7.186457439954941e-09, "loss": 0.436, "step": 2020 }, { "epoch": 0.98, "learning_rate": 6.770035328599322e-09, "loss": 0.334, "step": 2021 }, { "epoch": 0.98, "learning_rate": 6.366032672731059e-09, "loss": 0.4071, "step": 2022 }, { "epoch": 0.98, "learning_rate": 5.974450477210236e-09, "loss": 0.4691, "step": 2023 }, { "epoch": 0.99, "learning_rate": 5.5952897160016505e-09, "loss": 0.3232, "step": 2024 }, { "epoch": 0.99, "learning_rate": 5.228551332178145e-09, "loss": 0.3886, "step": 2025 }, { "epoch": 0.99, "learning_rate": 4.874236237911723e-09, "loss": 0.3194, "step": 2026 }, { "epoch": 0.99, "learning_rate": 4.532345314475772e-09, "loss": 0.3258, "step": 2027 }, { "epoch": 0.99, "learning_rate": 4.202879412242289e-09, "loss": 0.3641, "step": 2028 }, { "epoch": 0.99, "learning_rate": 3.885839350677434e-09, "loss": 0.3037, "step": 2029 }, { "epoch": 0.99, "learning_rate": 3.5812259183426457e-09, "loss": 0.3848, "step": 2030 }, { "epoch": 0.99, "learning_rate": 3.2890398728901985e-09, "loss": 0.3251, "step": 2031 }, { "epoch": 0.99, "learning_rate": 3.009281941062092e-09, "loss": 0.3706, "step": 2032 }, { "epoch": 0.99, "learning_rate": 2.741952818688387e-09, "loss": 0.3063, "step": 2033 }, { "epoch": 0.99, "learning_rate": 2.4870531706872037e-09, "loss": 0.8502, "step": 2034 }, { "epoch": 0.99, "learning_rate": 2.2445836310580616e-09, "loss": 0.3561, "step": 2035 }, { "epoch": 0.99, "learning_rate": 2.0145448028874305e-09, "loss": 0.3352, "step": 2036 }, { "epoch": 0.99, "learning_rate": 1.796937258339848e-09, "loss": 0.3193, "step": 2037 }, { "epoch": 0.99, "learning_rate": 1.591761538662362e-09, "loss": 0.2998, "step": 2038 }, { "epoch": 0.99, "learning_rate": 1.3990181541800874e-09, "loss": 0.3013, "step": 2039 }, { "epoch": 0.99, "learning_rate": 1.2187075842956531e-09, "loss": 0.4533, "step": 2040 }, { "epoch": 0.99, "learning_rate": 1.0508302774875357e-09, "loss": 0.3677, "step": 2041 }, { "epoch": 0.99, "learning_rate": 8.953866513111698e-10, "loss": 0.3568, "step": 2042 }, { "epoch": 0.99, "learning_rate": 7.523770923945072e-10, "loss": 0.3982, "step": 2043 }, { "epoch": 0.99, "learning_rate": 6.218019564391276e-10, "loss": 0.317, "step": 2044 }, { "epoch": 1.0, "learning_rate": 5.03661568219127e-10, "loss": 0.3866, "step": 2045 }, { "epoch": 1.0, "learning_rate": 3.9795622158111945e-10, "loss": 0.3334, "step": 2046 }, { "epoch": 1.0, "learning_rate": 3.0468617944090506e-10, "loss": 0.2627, "step": 2047 }, { "epoch": 1.0, "learning_rate": 2.2385167378513594e-10, "loss": 0.3184, "step": 2048 }, { "epoch": 1.0, "learning_rate": 1.5545290567020588e-10, "loss": 0.3161, "step": 2049 }, { "epoch": 1.0, "learning_rate": 9.949004522225025e-11, "loss": 0.3464, "step": 2050 }, { "epoch": 1.0, "learning_rate": 5.596323163437056e-11, "loss": 0.3441, "step": 2051 }, { "epoch": 1.0, "learning_rate": 2.4872573169965052e-11, "loss": 0.4618, "step": 2052 }, { "epoch": 1.0, "learning_rate": 6.2181471588429466e-12, "loss": 0.4219, "step": 2053 }, { "epoch": 1.0, "learning_rate": 0.0, "loss": 0.8657, "step": 2054 }, { "epoch": 1.0, "step": 2054, "total_flos": 9426473892708352.0, "train_loss": 0.4201592078256514, "train_runtime": 86062.9592, "train_samples_per_second": 6.112, "train_steps_per_second": 0.024 } ], "logging_steps": 1.0, "max_steps": 2054, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 1000, "total_flos": 9426473892708352.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }