diff --git "a/trainer_state.json" "b/trainer_state.json" new file mode 100644--- /dev/null +++ "b/trainer_state.json" @@ -0,0 +1,46764 @@ +{ + "best_metric": 1.1093857288360596, + "best_model_checkpoint": "/home/yuchenl/models/reverse-instruct/prefixgen_flan-base/checkpoint-7750", + "epoch": 8.351293103448276, + "global_step": 7750, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.0, + "learning_rate": 9.999281609195403e-05, + "loss": 3.6408, + "step": 1 + }, + { + "epoch": 0.0, + "learning_rate": 9.998563218390805e-05, + "loss": 3.4784, + "step": 2 + }, + { + "epoch": 0.0, + "learning_rate": 9.997844827586207e-05, + "loss": 3.2234, + "step": 3 + }, + { + "epoch": 0.0, + "learning_rate": 9.99712643678161e-05, + "loss": 3.2107, + "step": 4 + }, + { + "epoch": 0.01, + "learning_rate": 9.996408045977012e-05, + "loss": 2.9868, + "step": 5 + }, + { + "epoch": 0.01, + "learning_rate": 9.995689655172414e-05, + "loss": 3.0116, + "step": 6 + }, + { + "epoch": 0.01, + "learning_rate": 9.994971264367816e-05, + "loss": 3.0382, + "step": 7 + }, + { + "epoch": 0.01, + "learning_rate": 9.99425287356322e-05, + "loss": 2.9334, + "step": 8 + }, + { + "epoch": 0.01, + "learning_rate": 9.993534482758621e-05, + "loss": 2.8864, + "step": 9 + }, + { + "epoch": 0.01, + "learning_rate": 9.992816091954024e-05, + "loss": 2.837, + "step": 10 + }, + { + "epoch": 0.01, + "learning_rate": 9.992097701149426e-05, + "loss": 2.7043, + "step": 11 + }, + { + "epoch": 0.01, + "learning_rate": 9.991379310344829e-05, + "loss": 2.6554, + "step": 12 + }, + { + "epoch": 0.01, + "learning_rate": 9.99066091954023e-05, + "loss": 2.763, + "step": 13 + }, + { + "epoch": 0.02, + "learning_rate": 9.989942528735633e-05, + "loss": 2.6062, + "step": 14 + }, + { + "epoch": 0.02, + "learning_rate": 9.989224137931035e-05, + "loss": 2.6074, + "step": 15 + }, + { + "epoch": 0.02, + "learning_rate": 9.988505747126437e-05, + "loss": 2.6135, + "step": 16 + }, + { + "epoch": 0.02, + "learning_rate": 9.987787356321839e-05, + "loss": 2.7101, + "step": 17 + }, + { + "epoch": 0.02, + "learning_rate": 9.987068965517242e-05, + "loss": 2.6619, + "step": 18 + }, + { + "epoch": 0.02, + "learning_rate": 9.986350574712645e-05, + "loss": 2.4349, + "step": 19 + }, + { + "epoch": 0.02, + "learning_rate": 9.985632183908047e-05, + "loss": 2.5222, + "step": 20 + }, + { + "epoch": 0.02, + "learning_rate": 9.984913793103449e-05, + "loss": 2.5581, + "step": 21 + }, + { + "epoch": 0.02, + "learning_rate": 9.984195402298852e-05, + "loss": 2.4875, + "step": 22 + }, + { + "epoch": 0.02, + "learning_rate": 9.983477011494253e-05, + "loss": 2.542, + "step": 23 + }, + { + "epoch": 0.03, + "learning_rate": 9.982758620689656e-05, + "loss": 2.4864, + "step": 24 + }, + { + "epoch": 0.03, + "learning_rate": 9.982040229885058e-05, + "loss": 2.3995, + "step": 25 + }, + { + "epoch": 0.03, + "learning_rate": 9.98132183908046e-05, + "loss": 2.4846, + "step": 26 + }, + { + "epoch": 0.03, + "learning_rate": 9.980603448275862e-05, + "loss": 2.4176, + "step": 27 + }, + { + "epoch": 0.03, + "learning_rate": 9.979885057471264e-05, + "loss": 2.3857, + "step": 28 + }, + { + "epoch": 0.03, + "learning_rate": 9.979166666666668e-05, + "loss": 2.3896, + "step": 29 + }, + { + "epoch": 0.03, + "learning_rate": 9.97844827586207e-05, + "loss": 2.2703, + "step": 30 + }, + { + "epoch": 0.03, + "learning_rate": 9.977729885057472e-05, + "loss": 2.3825, + "step": 31 + }, + { + "epoch": 0.03, + "learning_rate": 9.977011494252874e-05, + "loss": 2.3935, + "step": 32 + }, + { + "epoch": 0.04, + "learning_rate": 9.976293103448277e-05, + "loss": 2.1955, + "step": 33 + }, + { + "epoch": 0.04, + "learning_rate": 9.975574712643678e-05, + "loss": 2.4273, + "step": 34 + }, + { + "epoch": 0.04, + "learning_rate": 9.974856321839081e-05, + "loss": 2.3376, + "step": 35 + }, + { + "epoch": 0.04, + "learning_rate": 9.974137931034483e-05, + "loss": 2.3951, + "step": 36 + }, + { + "epoch": 0.04, + "learning_rate": 9.973419540229885e-05, + "loss": 2.3591, + "step": 37 + }, + { + "epoch": 0.04, + "learning_rate": 9.972701149425287e-05, + "loss": 2.4121, + "step": 38 + }, + { + "epoch": 0.04, + "learning_rate": 9.97198275862069e-05, + "loss": 2.2227, + "step": 39 + }, + { + "epoch": 0.04, + "learning_rate": 9.971264367816093e-05, + "loss": 2.356, + "step": 40 + }, + { + "epoch": 0.04, + "learning_rate": 9.970545977011495e-05, + "loss": 2.2135, + "step": 41 + }, + { + "epoch": 0.05, + "learning_rate": 9.969827586206897e-05, + "loss": 2.1965, + "step": 42 + }, + { + "epoch": 0.05, + "learning_rate": 9.9691091954023e-05, + "loss": 2.2287, + "step": 43 + }, + { + "epoch": 0.05, + "learning_rate": 9.968390804597702e-05, + "loss": 2.3053, + "step": 44 + }, + { + "epoch": 0.05, + "learning_rate": 9.967672413793104e-05, + "loss": 2.3301, + "step": 45 + }, + { + "epoch": 0.05, + "learning_rate": 9.966954022988506e-05, + "loss": 2.2253, + "step": 46 + }, + { + "epoch": 0.05, + "learning_rate": 9.96623563218391e-05, + "loss": 2.2491, + "step": 47 + }, + { + "epoch": 0.05, + "learning_rate": 9.96551724137931e-05, + "loss": 2.1319, + "step": 48 + }, + { + "epoch": 0.05, + "learning_rate": 9.964798850574714e-05, + "loss": 2.2987, + "step": 49 + }, + { + "epoch": 0.05, + "learning_rate": 9.964080459770116e-05, + "loss": 2.2801, + "step": 50 + }, + { + "epoch": 0.05, + "learning_rate": 9.963362068965518e-05, + "loss": 2.4136, + "step": 51 + }, + { + "epoch": 0.06, + "learning_rate": 9.96264367816092e-05, + "loss": 2.1977, + "step": 52 + }, + { + "epoch": 0.06, + "learning_rate": 9.961925287356322e-05, + "loss": 2.0617, + "step": 53 + }, + { + "epoch": 0.06, + "learning_rate": 9.961206896551725e-05, + "loss": 2.2444, + "step": 54 + }, + { + "epoch": 0.06, + "learning_rate": 9.960488505747126e-05, + "loss": 2.3165, + "step": 55 + }, + { + "epoch": 0.06, + "learning_rate": 9.959770114942529e-05, + "loss": 2.2527, + "step": 56 + }, + { + "epoch": 0.06, + "learning_rate": 9.959051724137931e-05, + "loss": 2.1281, + "step": 57 + }, + { + "epoch": 0.06, + "learning_rate": 9.958333333333335e-05, + "loss": 2.0751, + "step": 58 + }, + { + "epoch": 0.06, + "learning_rate": 9.957614942528735e-05, + "loss": 2.1672, + "step": 59 + }, + { + "epoch": 0.06, + "learning_rate": 9.956896551724139e-05, + "loss": 2.0414, + "step": 60 + }, + { + "epoch": 0.07, + "learning_rate": 9.956178160919541e-05, + "loss": 2.0594, + "step": 61 + }, + { + "epoch": 0.07, + "learning_rate": 9.955459770114943e-05, + "loss": 2.2261, + "step": 62 + }, + { + "epoch": 0.07, + "learning_rate": 9.954741379310345e-05, + "loss": 2.0631, + "step": 63 + }, + { + "epoch": 0.07, + "learning_rate": 9.954022988505748e-05, + "loss": 2.2489, + "step": 64 + }, + { + "epoch": 0.07, + "learning_rate": 9.95330459770115e-05, + "loss": 2.0733, + "step": 65 + }, + { + "epoch": 0.07, + "learning_rate": 9.952586206896552e-05, + "loss": 2.2474, + "step": 66 + }, + { + "epoch": 0.07, + "learning_rate": 9.951867816091954e-05, + "loss": 1.9718, + "step": 67 + }, + { + "epoch": 0.07, + "learning_rate": 9.951149425287358e-05, + "loss": 2.1111, + "step": 68 + }, + { + "epoch": 0.07, + "learning_rate": 9.950431034482758e-05, + "loss": 2.0209, + "step": 69 + }, + { + "epoch": 0.08, + "learning_rate": 9.949712643678162e-05, + "loss": 2.004, + "step": 70 + }, + { + "epoch": 0.08, + "learning_rate": 9.948994252873564e-05, + "loss": 2.0066, + "step": 71 + }, + { + "epoch": 0.08, + "learning_rate": 9.948275862068967e-05, + "loss": 1.9432, + "step": 72 + }, + { + "epoch": 0.08, + "learning_rate": 9.947557471264368e-05, + "loss": 2.0958, + "step": 73 + }, + { + "epoch": 0.08, + "learning_rate": 9.946839080459771e-05, + "loss": 2.1908, + "step": 74 + }, + { + "epoch": 0.08, + "learning_rate": 9.946120689655173e-05, + "loss": 1.9353, + "step": 75 + }, + { + "epoch": 0.08, + "learning_rate": 9.945402298850575e-05, + "loss": 2.1468, + "step": 76 + }, + { + "epoch": 0.08, + "learning_rate": 9.944683908045977e-05, + "loss": 2.1249, + "step": 77 + }, + { + "epoch": 0.08, + "learning_rate": 9.943965517241379e-05, + "loss": 2.1301, + "step": 78 + }, + { + "epoch": 0.09, + "learning_rate": 9.943247126436783e-05, + "loss": 2.0745, + "step": 79 + }, + { + "epoch": 0.09, + "learning_rate": 9.942528735632183e-05, + "loss": 2.0832, + "step": 80 + }, + { + "epoch": 0.09, + "learning_rate": 9.941810344827587e-05, + "loss": 2.0029, + "step": 81 + }, + { + "epoch": 0.09, + "learning_rate": 9.941091954022989e-05, + "loss": 2.0702, + "step": 82 + }, + { + "epoch": 0.09, + "learning_rate": 9.940373563218391e-05, + "loss": 2.0923, + "step": 83 + }, + { + "epoch": 0.09, + "learning_rate": 9.939655172413793e-05, + "loss": 2.0571, + "step": 84 + }, + { + "epoch": 0.09, + "learning_rate": 9.938936781609196e-05, + "loss": 1.9581, + "step": 85 + }, + { + "epoch": 0.09, + "learning_rate": 9.938218390804598e-05, + "loss": 2.0049, + "step": 86 + }, + { + "epoch": 0.09, + "learning_rate": 9.9375e-05, + "loss": 1.9377, + "step": 87 + }, + { + "epoch": 0.09, + "learning_rate": 9.936781609195402e-05, + "loss": 2.1816, + "step": 88 + }, + { + "epoch": 0.1, + "learning_rate": 9.936063218390806e-05, + "loss": 1.9926, + "step": 89 + }, + { + "epoch": 0.1, + "learning_rate": 9.935344827586208e-05, + "loss": 2.1002, + "step": 90 + }, + { + "epoch": 0.1, + "learning_rate": 9.93462643678161e-05, + "loss": 1.9998, + "step": 91 + }, + { + "epoch": 0.1, + "learning_rate": 9.933908045977012e-05, + "loss": 2.0477, + "step": 92 + }, + { + "epoch": 0.1, + "learning_rate": 9.933189655172415e-05, + "loss": 1.8462, + "step": 93 + }, + { + "epoch": 0.1, + "learning_rate": 9.932471264367816e-05, + "loss": 1.8537, + "step": 94 + }, + { + "epoch": 0.1, + "learning_rate": 9.931752873563219e-05, + "loss": 2.0618, + "step": 95 + }, + { + "epoch": 0.1, + "learning_rate": 9.931034482758621e-05, + "loss": 2.1618, + "step": 96 + }, + { + "epoch": 0.1, + "learning_rate": 9.930316091954023e-05, + "loss": 2.0962, + "step": 97 + }, + { + "epoch": 0.11, + "learning_rate": 9.929597701149425e-05, + "loss": 1.7853, + "step": 98 + }, + { + "epoch": 0.11, + "learning_rate": 9.928879310344829e-05, + "loss": 2.1104, + "step": 99 + }, + { + "epoch": 0.11, + "learning_rate": 9.928160919540231e-05, + "loss": 1.958, + "step": 100 + }, + { + "epoch": 0.11, + "learning_rate": 9.927442528735633e-05, + "loss": 2.0069, + "step": 101 + }, + { + "epoch": 0.11, + "learning_rate": 9.926724137931035e-05, + "loss": 1.9288, + "step": 102 + }, + { + "epoch": 0.11, + "learning_rate": 9.926005747126437e-05, + "loss": 2.0293, + "step": 103 + }, + { + "epoch": 0.11, + "learning_rate": 9.925287356321839e-05, + "loss": 2.0081, + "step": 104 + }, + { + "epoch": 0.11, + "learning_rate": 9.924568965517241e-05, + "loss": 2.0315, + "step": 105 + }, + { + "epoch": 0.11, + "learning_rate": 9.923850574712644e-05, + "loss": 1.8656, + "step": 106 + }, + { + "epoch": 0.12, + "learning_rate": 9.923132183908046e-05, + "loss": 1.9063, + "step": 107 + }, + { + "epoch": 0.12, + "learning_rate": 9.922413793103448e-05, + "loss": 1.884, + "step": 108 + }, + { + "epoch": 0.12, + "learning_rate": 9.92169540229885e-05, + "loss": 2.0483, + "step": 109 + }, + { + "epoch": 0.12, + "learning_rate": 9.920977011494254e-05, + "loss": 1.8951, + "step": 110 + }, + { + "epoch": 0.12, + "learning_rate": 9.920258620689656e-05, + "loss": 1.8437, + "step": 111 + }, + { + "epoch": 0.12, + "learning_rate": 9.919540229885058e-05, + "loss": 1.8944, + "step": 112 + }, + { + "epoch": 0.12, + "learning_rate": 9.91882183908046e-05, + "loss": 2.0129, + "step": 113 + }, + { + "epoch": 0.12, + "learning_rate": 9.918103448275863e-05, + "loss": 2.0366, + "step": 114 + }, + { + "epoch": 0.12, + "learning_rate": 9.917385057471264e-05, + "loss": 1.8029, + "step": 115 + }, + { + "epoch": 0.12, + "learning_rate": 9.916666666666667e-05, + "loss": 1.9167, + "step": 116 + }, + { + "epoch": 0.13, + "learning_rate": 9.91594827586207e-05, + "loss": 2.0972, + "step": 117 + }, + { + "epoch": 0.13, + "learning_rate": 9.915229885057471e-05, + "loss": 1.9248, + "step": 118 + }, + { + "epoch": 0.13, + "learning_rate": 9.914511494252873e-05, + "loss": 2.0191, + "step": 119 + }, + { + "epoch": 0.13, + "learning_rate": 9.913793103448277e-05, + "loss": 1.8096, + "step": 120 + }, + { + "epoch": 0.13, + "learning_rate": 9.913074712643679e-05, + "loss": 2.0453, + "step": 121 + }, + { + "epoch": 0.13, + "learning_rate": 9.912356321839081e-05, + "loss": 1.9562, + "step": 122 + }, + { + "epoch": 0.13, + "learning_rate": 9.911637931034483e-05, + "loss": 1.9166, + "step": 123 + }, + { + "epoch": 0.13, + "learning_rate": 9.910919540229886e-05, + "loss": 1.8779, + "step": 124 + }, + { + "epoch": 0.13, + "learning_rate": 9.910201149425288e-05, + "loss": 1.9893, + "step": 125 + }, + { + "epoch": 0.14, + "learning_rate": 9.90948275862069e-05, + "loss": 1.8386, + "step": 126 + }, + { + "epoch": 0.14, + "learning_rate": 9.908764367816092e-05, + "loss": 2.0364, + "step": 127 + }, + { + "epoch": 0.14, + "learning_rate": 9.908045977011494e-05, + "loss": 1.9062, + "step": 128 + }, + { + "epoch": 0.14, + "learning_rate": 9.907327586206897e-05, + "loss": 1.9171, + "step": 129 + }, + { + "epoch": 0.14, + "learning_rate": 9.906609195402299e-05, + "loss": 1.9914, + "step": 130 + }, + { + "epoch": 0.14, + "learning_rate": 9.905890804597702e-05, + "loss": 1.9613, + "step": 131 + }, + { + "epoch": 0.14, + "learning_rate": 9.905172413793104e-05, + "loss": 1.887, + "step": 132 + }, + { + "epoch": 0.14, + "learning_rate": 9.904454022988506e-05, + "loss": 1.9613, + "step": 133 + }, + { + "epoch": 0.14, + "learning_rate": 9.903735632183908e-05, + "loss": 1.7901, + "step": 134 + }, + { + "epoch": 0.15, + "learning_rate": 9.903017241379311e-05, + "loss": 1.9628, + "step": 135 + }, + { + "epoch": 0.15, + "learning_rate": 9.902298850574712e-05, + "loss": 1.8948, + "step": 136 + }, + { + "epoch": 0.15, + "learning_rate": 9.901580459770115e-05, + "loss": 1.8491, + "step": 137 + }, + { + "epoch": 0.15, + "learning_rate": 9.900862068965518e-05, + "loss": 1.8184, + "step": 138 + }, + { + "epoch": 0.15, + "learning_rate": 9.900143678160921e-05, + "loss": 1.9402, + "step": 139 + }, + { + "epoch": 0.15, + "learning_rate": 9.899425287356322e-05, + "loss": 1.7499, + "step": 140 + }, + { + "epoch": 0.15, + "learning_rate": 9.898706896551725e-05, + "loss": 1.9502, + "step": 141 + }, + { + "epoch": 0.15, + "learning_rate": 9.897988505747127e-05, + "loss": 1.8168, + "step": 142 + }, + { + "epoch": 0.15, + "learning_rate": 9.897270114942529e-05, + "loss": 1.9394, + "step": 143 + }, + { + "epoch": 0.16, + "learning_rate": 9.896551724137931e-05, + "loss": 1.8015, + "step": 144 + }, + { + "epoch": 0.16, + "learning_rate": 9.895833333333334e-05, + "loss": 1.7867, + "step": 145 + }, + { + "epoch": 0.16, + "learning_rate": 9.895114942528736e-05, + "loss": 2.0075, + "step": 146 + }, + { + "epoch": 0.16, + "learning_rate": 9.894396551724139e-05, + "loss": 1.9424, + "step": 147 + }, + { + "epoch": 0.16, + "learning_rate": 9.89367816091954e-05, + "loss": 1.8935, + "step": 148 + }, + { + "epoch": 0.16, + "learning_rate": 9.892959770114944e-05, + "loss": 2.0069, + "step": 149 + }, + { + "epoch": 0.16, + "learning_rate": 9.892241379310345e-05, + "loss": 1.8124, + "step": 150 + }, + { + "epoch": 0.16, + "learning_rate": 9.891522988505748e-05, + "loss": 1.7777, + "step": 151 + }, + { + "epoch": 0.16, + "learning_rate": 9.89080459770115e-05, + "loss": 1.9609, + "step": 152 + }, + { + "epoch": 0.16, + "learning_rate": 9.890086206896553e-05, + "loss": 1.9026, + "step": 153 + }, + { + "epoch": 0.17, + "learning_rate": 9.889367816091954e-05, + "loss": 1.8217, + "step": 154 + }, + { + "epoch": 0.17, + "learning_rate": 9.888649425287356e-05, + "loss": 1.8685, + "step": 155 + }, + { + "epoch": 0.17, + "learning_rate": 9.88793103448276e-05, + "loss": 1.8775, + "step": 156 + }, + { + "epoch": 0.17, + "learning_rate": 9.887212643678162e-05, + "loss": 1.9678, + "step": 157 + }, + { + "epoch": 0.17, + "learning_rate": 9.886494252873564e-05, + "loss": 1.99, + "step": 158 + }, + { + "epoch": 0.17, + "learning_rate": 9.885775862068966e-05, + "loss": 1.9254, + "step": 159 + }, + { + "epoch": 0.17, + "learning_rate": 9.885057471264369e-05, + "loss": 1.8703, + "step": 160 + }, + { + "epoch": 0.17, + "learning_rate": 9.88433908045977e-05, + "loss": 1.9275, + "step": 161 + }, + { + "epoch": 0.17, + "learning_rate": 9.883620689655173e-05, + "loss": 1.7517, + "step": 162 + }, + { + "epoch": 0.18, + "learning_rate": 9.882902298850575e-05, + "loss": 1.8092, + "step": 163 + }, + { + "epoch": 0.18, + "learning_rate": 9.882183908045977e-05, + "loss": 1.9814, + "step": 164 + }, + { + "epoch": 0.18, + "learning_rate": 9.881465517241379e-05, + "loss": 1.8693, + "step": 165 + }, + { + "epoch": 0.18, + "learning_rate": 9.880747126436783e-05, + "loss": 1.9109, + "step": 166 + }, + { + "epoch": 0.18, + "learning_rate": 9.880028735632185e-05, + "loss": 1.9231, + "step": 167 + }, + { + "epoch": 0.18, + "learning_rate": 9.879310344827587e-05, + "loss": 1.9621, + "step": 168 + }, + { + "epoch": 0.18, + "learning_rate": 9.878591954022989e-05, + "loss": 1.841, + "step": 169 + }, + { + "epoch": 0.18, + "learning_rate": 9.877873563218392e-05, + "loss": 1.856, + "step": 170 + }, + { + "epoch": 0.18, + "learning_rate": 9.877155172413794e-05, + "loss": 1.8336, + "step": 171 + }, + { + "epoch": 0.19, + "learning_rate": 9.876436781609196e-05, + "loss": 1.8512, + "step": 172 + }, + { + "epoch": 0.19, + "learning_rate": 9.875718390804598e-05, + "loss": 1.8221, + "step": 173 + }, + { + "epoch": 0.19, + "learning_rate": 9.875000000000002e-05, + "loss": 1.7684, + "step": 174 + }, + { + "epoch": 0.19, + "learning_rate": 9.874281609195402e-05, + "loss": 1.7435, + "step": 175 + }, + { + "epoch": 0.19, + "learning_rate": 9.873563218390806e-05, + "loss": 1.7515, + "step": 176 + }, + { + "epoch": 0.19, + "learning_rate": 9.872844827586208e-05, + "loss": 1.9773, + "step": 177 + }, + { + "epoch": 0.19, + "learning_rate": 9.87212643678161e-05, + "loss": 2.0349, + "step": 178 + }, + { + "epoch": 0.19, + "learning_rate": 9.871408045977012e-05, + "loss": 1.8539, + "step": 179 + }, + { + "epoch": 0.19, + "learning_rate": 9.870689655172414e-05, + "loss": 1.8923, + "step": 180 + }, + { + "epoch": 0.2, + "learning_rate": 9.869971264367817e-05, + "loss": 1.6112, + "step": 181 + }, + { + "epoch": 0.2, + "learning_rate": 9.869252873563218e-05, + "loss": 1.8505, + "step": 182 + }, + { + "epoch": 0.2, + "learning_rate": 9.868534482758621e-05, + "loss": 1.6737, + "step": 183 + }, + { + "epoch": 0.2, + "learning_rate": 9.867816091954023e-05, + "loss": 1.8767, + "step": 184 + }, + { + "epoch": 0.2, + "learning_rate": 9.867097701149425e-05, + "loss": 1.7408, + "step": 185 + }, + { + "epoch": 0.2, + "learning_rate": 9.866379310344827e-05, + "loss": 1.8742, + "step": 186 + }, + { + "epoch": 0.2, + "learning_rate": 9.86566091954023e-05, + "loss": 1.7481, + "step": 187 + }, + { + "epoch": 0.2, + "learning_rate": 9.864942528735633e-05, + "loss": 1.8777, + "step": 188 + }, + { + "epoch": 0.2, + "learning_rate": 9.864224137931035e-05, + "loss": 1.9483, + "step": 189 + }, + { + "epoch": 0.2, + "learning_rate": 9.863505747126437e-05, + "loss": 1.8674, + "step": 190 + }, + { + "epoch": 0.21, + "learning_rate": 9.86278735632184e-05, + "loss": 1.7346, + "step": 191 + }, + { + "epoch": 0.21, + "learning_rate": 9.862068965517242e-05, + "loss": 1.8868, + "step": 192 + }, + { + "epoch": 0.21, + "learning_rate": 9.861350574712644e-05, + "loss": 1.8268, + "step": 193 + }, + { + "epoch": 0.21, + "learning_rate": 9.860632183908046e-05, + "loss": 1.9168, + "step": 194 + }, + { + "epoch": 0.21, + "learning_rate": 9.85991379310345e-05, + "loss": 1.9411, + "step": 195 + }, + { + "epoch": 0.21, + "learning_rate": 9.85919540229885e-05, + "loss": 1.8329, + "step": 196 + }, + { + "epoch": 0.21, + "learning_rate": 9.858477011494254e-05, + "loss": 1.8822, + "step": 197 + }, + { + "epoch": 0.21, + "learning_rate": 9.857758620689656e-05, + "loss": 1.8087, + "step": 198 + }, + { + "epoch": 0.21, + "learning_rate": 9.857040229885058e-05, + "loss": 1.7197, + "step": 199 + }, + { + "epoch": 0.22, + "learning_rate": 9.85632183908046e-05, + "loss": 1.7778, + "step": 200 + }, + { + "epoch": 0.22, + "learning_rate": 9.855603448275863e-05, + "loss": 1.7103, + "step": 201 + }, + { + "epoch": 0.22, + "learning_rate": 9.854885057471265e-05, + "loss": 1.7275, + "step": 202 + }, + { + "epoch": 0.22, + "learning_rate": 9.854166666666667e-05, + "loss": 1.8455, + "step": 203 + }, + { + "epoch": 0.22, + "learning_rate": 9.853448275862069e-05, + "loss": 1.7957, + "step": 204 + }, + { + "epoch": 0.22, + "learning_rate": 9.852729885057471e-05, + "loss": 1.7635, + "step": 205 + }, + { + "epoch": 0.22, + "learning_rate": 9.852011494252875e-05, + "loss": 1.9701, + "step": 206 + }, + { + "epoch": 0.22, + "learning_rate": 9.851293103448275e-05, + "loss": 1.9363, + "step": 207 + }, + { + "epoch": 0.22, + "learning_rate": 9.850574712643679e-05, + "loss": 1.7452, + "step": 208 + }, + { + "epoch": 0.23, + "learning_rate": 9.849856321839081e-05, + "loss": 1.9159, + "step": 209 + }, + { + "epoch": 0.23, + "learning_rate": 9.849137931034483e-05, + "loss": 1.8465, + "step": 210 + }, + { + "epoch": 0.23, + "learning_rate": 9.848419540229885e-05, + "loss": 1.755, + "step": 211 + }, + { + "epoch": 0.23, + "learning_rate": 9.847701149425288e-05, + "loss": 1.7364, + "step": 212 + }, + { + "epoch": 0.23, + "learning_rate": 9.84698275862069e-05, + "loss": 1.7857, + "step": 213 + }, + { + "epoch": 0.23, + "learning_rate": 9.846264367816092e-05, + "loss": 1.8462, + "step": 214 + }, + { + "epoch": 0.23, + "learning_rate": 9.845545977011494e-05, + "loss": 1.8195, + "step": 215 + }, + { + "epoch": 0.23, + "learning_rate": 9.844827586206898e-05, + "loss": 1.8959, + "step": 216 + }, + { + "epoch": 0.23, + "learning_rate": 9.844109195402298e-05, + "loss": 1.7709, + "step": 217 + }, + { + "epoch": 0.23, + "learning_rate": 9.843390804597702e-05, + "loss": 1.7623, + "step": 218 + }, + { + "epoch": 0.24, + "learning_rate": 9.842672413793104e-05, + "loss": 1.6908, + "step": 219 + }, + { + "epoch": 0.24, + "learning_rate": 9.841954022988507e-05, + "loss": 1.6525, + "step": 220 + }, + { + "epoch": 0.24, + "learning_rate": 9.841235632183908e-05, + "loss": 1.7343, + "step": 221 + }, + { + "epoch": 0.24, + "learning_rate": 9.840517241379311e-05, + "loss": 1.7878, + "step": 222 + }, + { + "epoch": 0.24, + "learning_rate": 9.839798850574713e-05, + "loss": 1.8513, + "step": 223 + }, + { + "epoch": 0.24, + "learning_rate": 9.839080459770115e-05, + "loss": 1.9581, + "step": 224 + }, + { + "epoch": 0.24, + "learning_rate": 9.838362068965517e-05, + "loss": 1.7482, + "step": 225 + }, + { + "epoch": 0.24, + "learning_rate": 9.837643678160921e-05, + "loss": 1.825, + "step": 226 + }, + { + "epoch": 0.24, + "learning_rate": 9.836925287356323e-05, + "loss": 1.8003, + "step": 227 + }, + { + "epoch": 0.25, + "learning_rate": 9.836206896551725e-05, + "loss": 1.7391, + "step": 228 + }, + { + "epoch": 0.25, + "learning_rate": 9.835488505747127e-05, + "loss": 1.6643, + "step": 229 + }, + { + "epoch": 0.25, + "learning_rate": 9.83477011494253e-05, + "loss": 1.818, + "step": 230 + }, + { + "epoch": 0.25, + "learning_rate": 9.834051724137931e-05, + "loss": 1.7955, + "step": 231 + }, + { + "epoch": 0.25, + "learning_rate": 9.833333333333333e-05, + "loss": 1.6561, + "step": 232 + }, + { + "epoch": 0.25, + "learning_rate": 9.832614942528736e-05, + "loss": 1.7877, + "step": 233 + }, + { + "epoch": 0.25, + "learning_rate": 9.831896551724138e-05, + "loss": 1.8923, + "step": 234 + }, + { + "epoch": 0.25, + "learning_rate": 9.83117816091954e-05, + "loss": 1.7492, + "step": 235 + }, + { + "epoch": 0.25, + "learning_rate": 9.830459770114942e-05, + "loss": 1.7588, + "step": 236 + }, + { + "epoch": 0.26, + "learning_rate": 9.829741379310346e-05, + "loss": 1.6447, + "step": 237 + }, + { + "epoch": 0.26, + "learning_rate": 9.829022988505748e-05, + "loss": 1.7511, + "step": 238 + }, + { + "epoch": 0.26, + "learning_rate": 9.82830459770115e-05, + "loss": 1.8131, + "step": 239 + }, + { + "epoch": 0.26, + "learning_rate": 9.827586206896552e-05, + "loss": 1.7889, + "step": 240 + }, + { + "epoch": 0.26, + "learning_rate": 9.826867816091955e-05, + "loss": 1.8761, + "step": 241 + }, + { + "epoch": 0.26, + "learning_rate": 9.826149425287356e-05, + "loss": 1.7457, + "step": 242 + }, + { + "epoch": 0.26, + "learning_rate": 9.82543103448276e-05, + "loss": 1.6737, + "step": 243 + }, + { + "epoch": 0.26, + "learning_rate": 9.824712643678161e-05, + "loss": 1.8039, + "step": 244 + }, + { + "epoch": 0.26, + "learning_rate": 9.823994252873563e-05, + "loss": 1.7504, + "step": 245 + }, + { + "epoch": 0.27, + "learning_rate": 9.823275862068965e-05, + "loss": 1.7276, + "step": 246 + }, + { + "epoch": 0.27, + "learning_rate": 9.822557471264369e-05, + "loss": 1.8464, + "step": 247 + }, + { + "epoch": 0.27, + "learning_rate": 9.821839080459771e-05, + "loss": 1.622, + "step": 248 + }, + { + "epoch": 0.27, + "learning_rate": 9.821120689655173e-05, + "loss": 2.0104, + "step": 249 + }, + { + "epoch": 0.27, + "learning_rate": 9.820402298850575e-05, + "loss": 1.8472, + "step": 250 + }, + { + "epoch": 0.27, + "eval_loss": 1.5633587837219238, + "eval_runtime": 175.0483, + "eval_samples_per_second": 127.222, + "eval_steps_per_second": 0.663, + "step": 250 + }, + { + "epoch": 0.27, + "learning_rate": 9.819683908045978e-05, + "loss": 1.8997, + "step": 251 + }, + { + "epoch": 0.27, + "learning_rate": 9.81896551724138e-05, + "loss": 1.779, + "step": 252 + }, + { + "epoch": 0.27, + "learning_rate": 9.818247126436782e-05, + "loss": 1.6264, + "step": 253 + }, + { + "epoch": 0.27, + "learning_rate": 9.817528735632184e-05, + "loss": 1.7737, + "step": 254 + }, + { + "epoch": 0.27, + "learning_rate": 9.816810344827588e-05, + "loss": 1.7709, + "step": 255 + }, + { + "epoch": 0.28, + "learning_rate": 9.816091954022988e-05, + "loss": 1.6441, + "step": 256 + }, + { + "epoch": 0.28, + "learning_rate": 9.81537356321839e-05, + "loss": 1.7463, + "step": 257 + }, + { + "epoch": 0.28, + "learning_rate": 9.814655172413794e-05, + "loss": 1.793, + "step": 258 + }, + { + "epoch": 0.28, + "learning_rate": 9.813936781609196e-05, + "loss": 1.8765, + "step": 259 + }, + { + "epoch": 0.28, + "learning_rate": 9.813218390804598e-05, + "loss": 1.8665, + "step": 260 + }, + { + "epoch": 0.28, + "learning_rate": 9.8125e-05, + "loss": 1.7354, + "step": 261 + }, + { + "epoch": 0.28, + "learning_rate": 9.811781609195403e-05, + "loss": 1.7054, + "step": 262 + }, + { + "epoch": 0.28, + "learning_rate": 9.811063218390804e-05, + "loss": 1.696, + "step": 263 + }, + { + "epoch": 0.28, + "learning_rate": 9.810344827586207e-05, + "loss": 1.8727, + "step": 264 + }, + { + "epoch": 0.29, + "learning_rate": 9.80962643678161e-05, + "loss": 1.65, + "step": 265 + }, + { + "epoch": 0.29, + "learning_rate": 9.808908045977013e-05, + "loss": 1.7866, + "step": 266 + }, + { + "epoch": 0.29, + "learning_rate": 9.808189655172414e-05, + "loss": 1.7467, + "step": 267 + }, + { + "epoch": 0.29, + "learning_rate": 9.807471264367817e-05, + "loss": 1.7441, + "step": 268 + }, + { + "epoch": 0.29, + "learning_rate": 9.806752873563219e-05, + "loss": 1.931, + "step": 269 + }, + { + "epoch": 0.29, + "learning_rate": 9.806034482758621e-05, + "loss": 1.7998, + "step": 270 + }, + { + "epoch": 0.29, + "learning_rate": 9.805316091954023e-05, + "loss": 1.7885, + "step": 271 + }, + { + "epoch": 0.29, + "learning_rate": 9.804597701149426e-05, + "loss": 1.7824, + "step": 272 + }, + { + "epoch": 0.29, + "learning_rate": 9.803879310344828e-05, + "loss": 1.7967, + "step": 273 + }, + { + "epoch": 0.3, + "learning_rate": 9.80316091954023e-05, + "loss": 1.7301, + "step": 274 + }, + { + "epoch": 0.3, + "learning_rate": 9.802442528735633e-05, + "loss": 1.6497, + "step": 275 + }, + { + "epoch": 0.3, + "learning_rate": 9.801724137931036e-05, + "loss": 1.7611, + "step": 276 + }, + { + "epoch": 0.3, + "learning_rate": 9.801005747126437e-05, + "loss": 1.7781, + "step": 277 + }, + { + "epoch": 0.3, + "learning_rate": 9.80028735632184e-05, + "loss": 1.8047, + "step": 278 + }, + { + "epoch": 0.3, + "learning_rate": 9.799568965517242e-05, + "loss": 1.7644, + "step": 279 + }, + { + "epoch": 0.3, + "learning_rate": 9.798850574712644e-05, + "loss": 1.7418, + "step": 280 + }, + { + "epoch": 0.3, + "learning_rate": 9.798132183908046e-05, + "loss": 1.5199, + "step": 281 + }, + { + "epoch": 0.3, + "learning_rate": 9.797413793103448e-05, + "loss": 1.7679, + "step": 282 + }, + { + "epoch": 0.3, + "learning_rate": 9.796695402298851e-05, + "loss": 1.6845, + "step": 283 + }, + { + "epoch": 0.31, + "learning_rate": 9.795977011494254e-05, + "loss": 1.6178, + "step": 284 + }, + { + "epoch": 0.31, + "learning_rate": 9.795258620689656e-05, + "loss": 1.6056, + "step": 285 + }, + { + "epoch": 0.31, + "learning_rate": 9.794540229885058e-05, + "loss": 1.7042, + "step": 286 + }, + { + "epoch": 0.31, + "learning_rate": 9.793821839080461e-05, + "loss": 1.6938, + "step": 287 + }, + { + "epoch": 0.31, + "learning_rate": 9.793103448275862e-05, + "loss": 1.7468, + "step": 288 + }, + { + "epoch": 0.31, + "learning_rate": 9.792385057471265e-05, + "loss": 1.6641, + "step": 289 + }, + { + "epoch": 0.31, + "learning_rate": 9.791666666666667e-05, + "loss": 1.9335, + "step": 290 + }, + { + "epoch": 0.31, + "learning_rate": 9.790948275862069e-05, + "loss": 1.8149, + "step": 291 + }, + { + "epoch": 0.31, + "learning_rate": 9.790229885057471e-05, + "loss": 1.778, + "step": 292 + }, + { + "epoch": 0.32, + "learning_rate": 9.789511494252875e-05, + "loss": 1.7528, + "step": 293 + }, + { + "epoch": 0.32, + "learning_rate": 9.788793103448277e-05, + "loss": 1.7736, + "step": 294 + }, + { + "epoch": 0.32, + "learning_rate": 9.788074712643679e-05, + "loss": 1.7251, + "step": 295 + }, + { + "epoch": 0.32, + "learning_rate": 9.78735632183908e-05, + "loss": 1.8076, + "step": 296 + }, + { + "epoch": 0.32, + "learning_rate": 9.786637931034484e-05, + "loss": 1.6561, + "step": 297 + }, + { + "epoch": 0.32, + "learning_rate": 9.785919540229885e-05, + "loss": 1.7889, + "step": 298 + }, + { + "epoch": 0.32, + "learning_rate": 9.785201149425288e-05, + "loss": 1.7608, + "step": 299 + }, + { + "epoch": 0.32, + "learning_rate": 9.78448275862069e-05, + "loss": 1.7713, + "step": 300 + }, + { + "epoch": 0.32, + "learning_rate": 9.783764367816093e-05, + "loss": 1.7083, + "step": 301 + }, + { + "epoch": 0.33, + "learning_rate": 9.783045977011494e-05, + "loss": 1.8089, + "step": 302 + }, + { + "epoch": 0.33, + "learning_rate": 9.782327586206898e-05, + "loss": 1.8062, + "step": 303 + }, + { + "epoch": 0.33, + "learning_rate": 9.7816091954023e-05, + "loss": 1.7153, + "step": 304 + }, + { + "epoch": 0.33, + "learning_rate": 9.780890804597702e-05, + "loss": 1.6875, + "step": 305 + }, + { + "epoch": 0.33, + "learning_rate": 9.780172413793104e-05, + "loss": 1.9258, + "step": 306 + }, + { + "epoch": 0.33, + "learning_rate": 9.779454022988507e-05, + "loss": 1.5609, + "step": 307 + }, + { + "epoch": 0.33, + "learning_rate": 9.778735632183909e-05, + "loss": 1.8102, + "step": 308 + }, + { + "epoch": 0.33, + "learning_rate": 9.77801724137931e-05, + "loss": 1.629, + "step": 309 + }, + { + "epoch": 0.33, + "learning_rate": 9.777298850574713e-05, + "loss": 1.8251, + "step": 310 + }, + { + "epoch": 0.34, + "learning_rate": 9.776580459770115e-05, + "loss": 1.6512, + "step": 311 + }, + { + "epoch": 0.34, + "learning_rate": 9.775862068965517e-05, + "loss": 1.7618, + "step": 312 + }, + { + "epoch": 0.34, + "learning_rate": 9.775143678160919e-05, + "loss": 1.6841, + "step": 313 + }, + { + "epoch": 0.34, + "learning_rate": 9.774425287356323e-05, + "loss": 1.7617, + "step": 314 + }, + { + "epoch": 0.34, + "learning_rate": 9.773706896551725e-05, + "loss": 1.7608, + "step": 315 + }, + { + "epoch": 0.34, + "learning_rate": 9.772988505747127e-05, + "loss": 1.6218, + "step": 316 + }, + { + "epoch": 0.34, + "learning_rate": 9.772270114942529e-05, + "loss": 1.8015, + "step": 317 + }, + { + "epoch": 0.34, + "learning_rate": 9.771551724137932e-05, + "loss": 1.7041, + "step": 318 + }, + { + "epoch": 0.34, + "learning_rate": 9.770833333333334e-05, + "loss": 1.6471, + "step": 319 + }, + { + "epoch": 0.34, + "learning_rate": 9.770114942528736e-05, + "loss": 1.6981, + "step": 320 + }, + { + "epoch": 0.35, + "learning_rate": 9.769396551724138e-05, + "loss": 1.952, + "step": 321 + }, + { + "epoch": 0.35, + "learning_rate": 9.768678160919542e-05, + "loss": 1.6023, + "step": 322 + }, + { + "epoch": 0.35, + "learning_rate": 9.767959770114942e-05, + "loss": 1.5081, + "step": 323 + }, + { + "epoch": 0.35, + "learning_rate": 9.767241379310346e-05, + "loss": 1.6606, + "step": 324 + }, + { + "epoch": 0.35, + "learning_rate": 9.766522988505748e-05, + "loss": 1.8431, + "step": 325 + }, + { + "epoch": 0.35, + "learning_rate": 9.76580459770115e-05, + "loss": 1.7254, + "step": 326 + }, + { + "epoch": 0.35, + "learning_rate": 9.765086206896552e-05, + "loss": 1.7292, + "step": 327 + }, + { + "epoch": 0.35, + "learning_rate": 9.764367816091955e-05, + "loss": 1.6881, + "step": 328 + }, + { + "epoch": 0.35, + "learning_rate": 9.763649425287357e-05, + "loss": 1.7281, + "step": 329 + }, + { + "epoch": 0.36, + "learning_rate": 9.762931034482759e-05, + "loss": 1.6715, + "step": 330 + }, + { + "epoch": 0.36, + "learning_rate": 9.762212643678161e-05, + "loss": 1.6172, + "step": 331 + }, + { + "epoch": 0.36, + "learning_rate": 9.761494252873565e-05, + "loss": 1.6945, + "step": 332 + }, + { + "epoch": 0.36, + "learning_rate": 9.760775862068967e-05, + "loss": 1.7646, + "step": 333 + }, + { + "epoch": 0.36, + "learning_rate": 9.760057471264367e-05, + "loss": 1.6674, + "step": 334 + }, + { + "epoch": 0.36, + "learning_rate": 9.759339080459771e-05, + "loss": 1.8163, + "step": 335 + }, + { + "epoch": 0.36, + "learning_rate": 9.758620689655173e-05, + "loss": 1.625, + "step": 336 + }, + { + "epoch": 0.36, + "learning_rate": 9.757902298850575e-05, + "loss": 1.6459, + "step": 337 + }, + { + "epoch": 0.36, + "learning_rate": 9.757183908045977e-05, + "loss": 1.6311, + "step": 338 + }, + { + "epoch": 0.37, + "learning_rate": 9.75646551724138e-05, + "loss": 1.6803, + "step": 339 + }, + { + "epoch": 0.37, + "learning_rate": 9.755747126436782e-05, + "loss": 1.773, + "step": 340 + }, + { + "epoch": 0.37, + "learning_rate": 9.755028735632184e-05, + "loss": 1.7961, + "step": 341 + }, + { + "epoch": 0.37, + "learning_rate": 9.754310344827586e-05, + "loss": 1.6031, + "step": 342 + }, + { + "epoch": 0.37, + "learning_rate": 9.75359195402299e-05, + "loss": 1.6617, + "step": 343 + }, + { + "epoch": 0.37, + "learning_rate": 9.75287356321839e-05, + "loss": 1.779, + "step": 344 + }, + { + "epoch": 0.37, + "learning_rate": 9.752155172413794e-05, + "loss": 1.7814, + "step": 345 + }, + { + "epoch": 0.37, + "learning_rate": 9.751436781609196e-05, + "loss": 1.6965, + "step": 346 + }, + { + "epoch": 0.37, + "learning_rate": 9.750718390804599e-05, + "loss": 1.7505, + "step": 347 + }, + { + "epoch": 0.38, + "learning_rate": 9.75e-05, + "loss": 1.7439, + "step": 348 + }, + { + "epoch": 0.38, + "learning_rate": 9.749281609195403e-05, + "loss": 1.7691, + "step": 349 + }, + { + "epoch": 0.38, + "learning_rate": 9.748563218390805e-05, + "loss": 1.6586, + "step": 350 + }, + { + "epoch": 0.38, + "learning_rate": 9.747844827586207e-05, + "loss": 1.8051, + "step": 351 + }, + { + "epoch": 0.38, + "learning_rate": 9.747126436781609e-05, + "loss": 1.8312, + "step": 352 + }, + { + "epoch": 0.38, + "learning_rate": 9.746408045977013e-05, + "loss": 1.6712, + "step": 353 + }, + { + "epoch": 0.38, + "learning_rate": 9.745689655172415e-05, + "loss": 1.6697, + "step": 354 + }, + { + "epoch": 0.38, + "learning_rate": 9.744971264367817e-05, + "loss": 1.6022, + "step": 355 + }, + { + "epoch": 0.38, + "learning_rate": 9.744252873563219e-05, + "loss": 1.6665, + "step": 356 + }, + { + "epoch": 0.38, + "learning_rate": 9.743534482758622e-05, + "loss": 1.6402, + "step": 357 + }, + { + "epoch": 0.39, + "learning_rate": 9.742816091954023e-05, + "loss": 1.6916, + "step": 358 + }, + { + "epoch": 0.39, + "learning_rate": 9.742097701149425e-05, + "loss": 1.8259, + "step": 359 + }, + { + "epoch": 0.39, + "learning_rate": 9.741379310344828e-05, + "loss": 1.8369, + "step": 360 + }, + { + "epoch": 0.39, + "learning_rate": 9.74066091954023e-05, + "loss": 1.6638, + "step": 361 + }, + { + "epoch": 0.39, + "learning_rate": 9.739942528735632e-05, + "loss": 1.6858, + "step": 362 + }, + { + "epoch": 0.39, + "learning_rate": 9.739224137931034e-05, + "loss": 1.7461, + "step": 363 + }, + { + "epoch": 0.39, + "learning_rate": 9.738505747126438e-05, + "loss": 1.8144, + "step": 364 + }, + { + "epoch": 0.39, + "learning_rate": 9.73778735632184e-05, + "loss": 1.8188, + "step": 365 + }, + { + "epoch": 0.39, + "learning_rate": 9.737068965517242e-05, + "loss": 1.7085, + "step": 366 + }, + { + "epoch": 0.4, + "learning_rate": 9.736350574712644e-05, + "loss": 1.7598, + "step": 367 + }, + { + "epoch": 0.4, + "learning_rate": 9.735632183908047e-05, + "loss": 1.8256, + "step": 368 + }, + { + "epoch": 0.4, + "learning_rate": 9.734913793103448e-05, + "loss": 1.6635, + "step": 369 + }, + { + "epoch": 0.4, + "learning_rate": 9.734195402298851e-05, + "loss": 1.7059, + "step": 370 + }, + { + "epoch": 0.4, + "learning_rate": 9.733477011494253e-05, + "loss": 1.6487, + "step": 371 + }, + { + "epoch": 0.4, + "learning_rate": 9.732758620689655e-05, + "loss": 1.7755, + "step": 372 + }, + { + "epoch": 0.4, + "learning_rate": 9.732040229885057e-05, + "loss": 1.6829, + "step": 373 + }, + { + "epoch": 0.4, + "learning_rate": 9.731321839080461e-05, + "loss": 1.488, + "step": 374 + }, + { + "epoch": 0.4, + "learning_rate": 9.730603448275863e-05, + "loss": 1.7123, + "step": 375 + }, + { + "epoch": 0.41, + "learning_rate": 9.729885057471265e-05, + "loss": 1.5619, + "step": 376 + }, + { + "epoch": 0.41, + "learning_rate": 9.729166666666667e-05, + "loss": 1.7544, + "step": 377 + }, + { + "epoch": 0.41, + "learning_rate": 9.72844827586207e-05, + "loss": 1.7274, + "step": 378 + }, + { + "epoch": 0.41, + "learning_rate": 9.727729885057471e-05, + "loss": 1.7089, + "step": 379 + }, + { + "epoch": 0.41, + "learning_rate": 9.727011494252874e-05, + "loss": 1.5539, + "step": 380 + }, + { + "epoch": 0.41, + "learning_rate": 9.726293103448276e-05, + "loss": 1.7243, + "step": 381 + }, + { + "epoch": 0.41, + "learning_rate": 9.72557471264368e-05, + "loss": 1.7826, + "step": 382 + }, + { + "epoch": 0.41, + "learning_rate": 9.72485632183908e-05, + "loss": 1.687, + "step": 383 + }, + { + "epoch": 0.41, + "learning_rate": 9.724137931034482e-05, + "loss": 1.8013, + "step": 384 + }, + { + "epoch": 0.41, + "learning_rate": 9.723419540229886e-05, + "loss": 1.609, + "step": 385 + }, + { + "epoch": 0.42, + "learning_rate": 9.722701149425288e-05, + "loss": 1.5471, + "step": 386 + }, + { + "epoch": 0.42, + "learning_rate": 9.72198275862069e-05, + "loss": 1.4634, + "step": 387 + }, + { + "epoch": 0.42, + "learning_rate": 9.721264367816092e-05, + "loss": 1.7784, + "step": 388 + }, + { + "epoch": 0.42, + "learning_rate": 9.720545977011495e-05, + "loss": 1.8076, + "step": 389 + }, + { + "epoch": 0.42, + "learning_rate": 9.719827586206896e-05, + "loss": 1.6707, + "step": 390 + }, + { + "epoch": 0.42, + "learning_rate": 9.7191091954023e-05, + "loss": 1.5263, + "step": 391 + }, + { + "epoch": 0.42, + "learning_rate": 9.718390804597701e-05, + "loss": 1.7067, + "step": 392 + }, + { + "epoch": 0.42, + "learning_rate": 9.717672413793103e-05, + "loss": 1.5773, + "step": 393 + }, + { + "epoch": 0.42, + "learning_rate": 9.716954022988505e-05, + "loss": 1.7735, + "step": 394 + }, + { + "epoch": 0.43, + "learning_rate": 9.716235632183909e-05, + "loss": 1.8536, + "step": 395 + }, + { + "epoch": 0.43, + "learning_rate": 9.715517241379311e-05, + "loss": 1.7299, + "step": 396 + }, + { + "epoch": 0.43, + "learning_rate": 9.714798850574713e-05, + "loss": 1.6539, + "step": 397 + }, + { + "epoch": 0.43, + "learning_rate": 9.714080459770115e-05, + "loss": 1.637, + "step": 398 + }, + { + "epoch": 0.43, + "learning_rate": 9.713362068965518e-05, + "loss": 1.6091, + "step": 399 + }, + { + "epoch": 0.43, + "learning_rate": 9.71264367816092e-05, + "loss": 1.5396, + "step": 400 + }, + { + "epoch": 0.43, + "learning_rate": 9.711925287356322e-05, + "loss": 1.7273, + "step": 401 + }, + { + "epoch": 0.43, + "learning_rate": 9.711206896551724e-05, + "loss": 1.6712, + "step": 402 + }, + { + "epoch": 0.43, + "learning_rate": 9.710488505747128e-05, + "loss": 1.7857, + "step": 403 + }, + { + "epoch": 0.44, + "learning_rate": 9.709770114942529e-05, + "loss": 1.8123, + "step": 404 + }, + { + "epoch": 0.44, + "learning_rate": 9.709051724137932e-05, + "loss": 1.7181, + "step": 405 + }, + { + "epoch": 0.44, + "learning_rate": 9.708333333333334e-05, + "loss": 1.6347, + "step": 406 + }, + { + "epoch": 0.44, + "learning_rate": 9.707614942528736e-05, + "loss": 1.6772, + "step": 407 + }, + { + "epoch": 0.44, + "learning_rate": 9.706896551724138e-05, + "loss": 1.6967, + "step": 408 + }, + { + "epoch": 0.44, + "learning_rate": 9.706178160919541e-05, + "loss": 1.6113, + "step": 409 + }, + { + "epoch": 0.44, + "learning_rate": 9.705459770114943e-05, + "loss": 1.6223, + "step": 410 + }, + { + "epoch": 0.44, + "learning_rate": 9.704741379310344e-05, + "loss": 1.6103, + "step": 411 + }, + { + "epoch": 0.44, + "learning_rate": 9.704022988505747e-05, + "loss": 1.7356, + "step": 412 + }, + { + "epoch": 0.45, + "learning_rate": 9.70330459770115e-05, + "loss": 1.7584, + "step": 413 + }, + { + "epoch": 0.45, + "learning_rate": 9.702586206896553e-05, + "loss": 1.6654, + "step": 414 + }, + { + "epoch": 0.45, + "learning_rate": 9.701867816091954e-05, + "loss": 1.6298, + "step": 415 + }, + { + "epoch": 0.45, + "learning_rate": 9.701149425287357e-05, + "loss": 1.5847, + "step": 416 + }, + { + "epoch": 0.45, + "learning_rate": 9.700431034482759e-05, + "loss": 1.6895, + "step": 417 + }, + { + "epoch": 0.45, + "learning_rate": 9.699712643678161e-05, + "loss": 1.6448, + "step": 418 + }, + { + "epoch": 0.45, + "learning_rate": 9.698994252873563e-05, + "loss": 1.6494, + "step": 419 + }, + { + "epoch": 0.45, + "learning_rate": 9.698275862068966e-05, + "loss": 1.7667, + "step": 420 + }, + { + "epoch": 0.45, + "learning_rate": 9.697557471264368e-05, + "loss": 1.6509, + "step": 421 + }, + { + "epoch": 0.45, + "learning_rate": 9.69683908045977e-05, + "loss": 1.7921, + "step": 422 + }, + { + "epoch": 0.46, + "learning_rate": 9.696120689655173e-05, + "loss": 1.6824, + "step": 423 + }, + { + "epoch": 0.46, + "learning_rate": 9.695402298850576e-05, + "loss": 1.7014, + "step": 424 + }, + { + "epoch": 0.46, + "learning_rate": 9.694683908045977e-05, + "loss": 1.6609, + "step": 425 + }, + { + "epoch": 0.46, + "learning_rate": 9.69396551724138e-05, + "loss": 1.6858, + "step": 426 + }, + { + "epoch": 0.46, + "learning_rate": 9.693247126436782e-05, + "loss": 1.6998, + "step": 427 + }, + { + "epoch": 0.46, + "learning_rate": 9.692528735632185e-05, + "loss": 1.7817, + "step": 428 + }, + { + "epoch": 0.46, + "learning_rate": 9.691810344827586e-05, + "loss": 1.6286, + "step": 429 + }, + { + "epoch": 0.46, + "learning_rate": 9.69109195402299e-05, + "loss": 1.5437, + "step": 430 + }, + { + "epoch": 0.46, + "learning_rate": 9.690373563218392e-05, + "loss": 1.9012, + "step": 431 + }, + { + "epoch": 0.47, + "learning_rate": 9.689655172413794e-05, + "loss": 1.6883, + "step": 432 + }, + { + "epoch": 0.47, + "learning_rate": 9.688936781609196e-05, + "loss": 1.6179, + "step": 433 + }, + { + "epoch": 0.47, + "learning_rate": 9.688218390804599e-05, + "loss": 1.5984, + "step": 434 + }, + { + "epoch": 0.47, + "learning_rate": 9.687500000000001e-05, + "loss": 1.6774, + "step": 435 + }, + { + "epoch": 0.47, + "learning_rate": 9.686781609195402e-05, + "loss": 1.684, + "step": 436 + }, + { + "epoch": 0.47, + "learning_rate": 9.686063218390805e-05, + "loss": 1.6117, + "step": 437 + }, + { + "epoch": 0.47, + "learning_rate": 9.685344827586207e-05, + "loss": 1.7423, + "step": 438 + }, + { + "epoch": 0.47, + "learning_rate": 9.684626436781609e-05, + "loss": 1.6422, + "step": 439 + }, + { + "epoch": 0.47, + "learning_rate": 9.683908045977011e-05, + "loss": 1.4806, + "step": 440 + }, + { + "epoch": 0.48, + "learning_rate": 9.683189655172415e-05, + "loss": 1.6224, + "step": 441 + }, + { + "epoch": 0.48, + "learning_rate": 9.682471264367817e-05, + "loss": 1.7681, + "step": 442 + }, + { + "epoch": 0.48, + "learning_rate": 9.681752873563219e-05, + "loss": 1.8115, + "step": 443 + }, + { + "epoch": 0.48, + "learning_rate": 9.68103448275862e-05, + "loss": 1.7771, + "step": 444 + }, + { + "epoch": 0.48, + "learning_rate": 9.680316091954024e-05, + "loss": 1.587, + "step": 445 + }, + { + "epoch": 0.48, + "learning_rate": 9.679597701149426e-05, + "loss": 1.6953, + "step": 446 + }, + { + "epoch": 0.48, + "learning_rate": 9.678879310344828e-05, + "loss": 1.8054, + "step": 447 + }, + { + "epoch": 0.48, + "learning_rate": 9.67816091954023e-05, + "loss": 1.7724, + "step": 448 + }, + { + "epoch": 0.48, + "learning_rate": 9.677442528735634e-05, + "loss": 1.5853, + "step": 449 + }, + { + "epoch": 0.48, + "learning_rate": 9.676724137931034e-05, + "loss": 1.5508, + "step": 450 + }, + { + "epoch": 0.49, + "learning_rate": 9.676005747126438e-05, + "loss": 1.8387, + "step": 451 + }, + { + "epoch": 0.49, + "learning_rate": 9.67528735632184e-05, + "loss": 1.8235, + "step": 452 + }, + { + "epoch": 0.49, + "learning_rate": 9.674568965517242e-05, + "loss": 1.6972, + "step": 453 + }, + { + "epoch": 0.49, + "learning_rate": 9.673850574712644e-05, + "loss": 1.6589, + "step": 454 + }, + { + "epoch": 0.49, + "learning_rate": 9.673132183908047e-05, + "loss": 1.7245, + "step": 455 + }, + { + "epoch": 0.49, + "learning_rate": 9.672413793103449e-05, + "loss": 1.658, + "step": 456 + }, + { + "epoch": 0.49, + "learning_rate": 9.671695402298851e-05, + "loss": 1.5601, + "step": 457 + }, + { + "epoch": 0.49, + "learning_rate": 9.670977011494253e-05, + "loss": 1.8302, + "step": 458 + }, + { + "epoch": 0.49, + "learning_rate": 9.670258620689657e-05, + "loss": 1.4554, + "step": 459 + }, + { + "epoch": 0.5, + "learning_rate": 9.669540229885059e-05, + "loss": 1.6204, + "step": 460 + }, + { + "epoch": 0.5, + "learning_rate": 9.668821839080459e-05, + "loss": 1.649, + "step": 461 + }, + { + "epoch": 0.5, + "learning_rate": 9.668103448275863e-05, + "loss": 1.7511, + "step": 462 + }, + { + "epoch": 0.5, + "learning_rate": 9.667385057471265e-05, + "loss": 1.7206, + "step": 463 + }, + { + "epoch": 0.5, + "learning_rate": 9.666666666666667e-05, + "loss": 1.7005, + "step": 464 + }, + { + "epoch": 0.5, + "learning_rate": 9.665948275862069e-05, + "loss": 1.6348, + "step": 465 + }, + { + "epoch": 0.5, + "learning_rate": 9.665229885057472e-05, + "loss": 1.6967, + "step": 466 + }, + { + "epoch": 0.5, + "learning_rate": 9.664511494252874e-05, + "loss": 1.65, + "step": 467 + }, + { + "epoch": 0.5, + "learning_rate": 9.663793103448276e-05, + "loss": 1.8468, + "step": 468 + }, + { + "epoch": 0.51, + "learning_rate": 9.663074712643678e-05, + "loss": 1.7807, + "step": 469 + }, + { + "epoch": 0.51, + "learning_rate": 9.662356321839082e-05, + "loss": 1.6233, + "step": 470 + }, + { + "epoch": 0.51, + "learning_rate": 9.661637931034482e-05, + "loss": 1.8081, + "step": 471 + }, + { + "epoch": 0.51, + "learning_rate": 9.660919540229886e-05, + "loss": 1.6363, + "step": 472 + }, + { + "epoch": 0.51, + "learning_rate": 9.660201149425288e-05, + "loss": 1.6465, + "step": 473 + }, + { + "epoch": 0.51, + "learning_rate": 9.65948275862069e-05, + "loss": 1.7132, + "step": 474 + }, + { + "epoch": 0.51, + "learning_rate": 9.658764367816092e-05, + "loss": 1.8031, + "step": 475 + }, + { + "epoch": 0.51, + "learning_rate": 9.658045977011495e-05, + "loss": 1.7559, + "step": 476 + }, + { + "epoch": 0.51, + "learning_rate": 9.657327586206897e-05, + "loss": 1.5607, + "step": 477 + }, + { + "epoch": 0.52, + "learning_rate": 9.656609195402299e-05, + "loss": 1.6494, + "step": 478 + }, + { + "epoch": 0.52, + "learning_rate": 9.655890804597701e-05, + "loss": 1.517, + "step": 479 + }, + { + "epoch": 0.52, + "learning_rate": 9.655172413793105e-05, + "loss": 1.7133, + "step": 480 + }, + { + "epoch": 0.52, + "learning_rate": 9.654454022988507e-05, + "loss": 1.5429, + "step": 481 + }, + { + "epoch": 0.52, + "learning_rate": 9.653735632183909e-05, + "loss": 1.7078, + "step": 482 + }, + { + "epoch": 0.52, + "learning_rate": 9.653017241379311e-05, + "loss": 1.8002, + "step": 483 + }, + { + "epoch": 0.52, + "learning_rate": 9.652298850574714e-05, + "loss": 1.6423, + "step": 484 + }, + { + "epoch": 0.52, + "learning_rate": 9.651580459770115e-05, + "loss": 1.6535, + "step": 485 + }, + { + "epoch": 0.52, + "learning_rate": 9.650862068965518e-05, + "loss": 1.6955, + "step": 486 + }, + { + "epoch": 0.52, + "learning_rate": 9.65014367816092e-05, + "loss": 1.6887, + "step": 487 + }, + { + "epoch": 0.53, + "learning_rate": 9.649425287356322e-05, + "loss": 1.7377, + "step": 488 + }, + { + "epoch": 0.53, + "learning_rate": 9.648706896551724e-05, + "loss": 1.7449, + "step": 489 + }, + { + "epoch": 0.53, + "learning_rate": 9.647988505747126e-05, + "loss": 1.6945, + "step": 490 + }, + { + "epoch": 0.53, + "learning_rate": 9.64727011494253e-05, + "loss": 1.5959, + "step": 491 + }, + { + "epoch": 0.53, + "learning_rate": 9.64655172413793e-05, + "loss": 1.7997, + "step": 492 + }, + { + "epoch": 0.53, + "learning_rate": 9.645833333333334e-05, + "loss": 1.6758, + "step": 493 + }, + { + "epoch": 0.53, + "learning_rate": 9.645114942528736e-05, + "loss": 1.5704, + "step": 494 + }, + { + "epoch": 0.53, + "learning_rate": 9.644396551724139e-05, + "loss": 1.4814, + "step": 495 + }, + { + "epoch": 0.53, + "learning_rate": 9.64367816091954e-05, + "loss": 1.6358, + "step": 496 + }, + { + "epoch": 0.54, + "learning_rate": 9.642959770114943e-05, + "loss": 1.7148, + "step": 497 + }, + { + "epoch": 0.54, + "learning_rate": 9.642241379310345e-05, + "loss": 1.4956, + "step": 498 + }, + { + "epoch": 0.54, + "learning_rate": 9.641522988505747e-05, + "loss": 1.5474, + "step": 499 + }, + { + "epoch": 0.54, + "learning_rate": 9.64080459770115e-05, + "loss": 1.79, + "step": 500 + }, + { + "epoch": 0.54, + "eval_loss": 1.430260181427002, + "eval_runtime": 175.172, + "eval_samples_per_second": 127.132, + "eval_steps_per_second": 0.662, + "step": 500 + }, + { + "epoch": 0.54, + "learning_rate": 9.640086206896553e-05, + "loss": 1.5239, + "step": 501 + }, + { + "epoch": 0.54, + "learning_rate": 9.639367816091955e-05, + "loss": 1.4666, + "step": 502 + }, + { + "epoch": 0.54, + "learning_rate": 9.638649425287357e-05, + "loss": 1.6692, + "step": 503 + }, + { + "epoch": 0.54, + "learning_rate": 9.637931034482759e-05, + "loss": 1.4417, + "step": 504 + }, + { + "epoch": 0.54, + "learning_rate": 9.637212643678162e-05, + "loss": 1.5441, + "step": 505 + }, + { + "epoch": 0.55, + "learning_rate": 9.636494252873563e-05, + "loss": 1.4609, + "step": 506 + }, + { + "epoch": 0.55, + "learning_rate": 9.635775862068966e-05, + "loss": 1.6064, + "step": 507 + }, + { + "epoch": 0.55, + "learning_rate": 9.635057471264368e-05, + "loss": 1.584, + "step": 508 + }, + { + "epoch": 0.55, + "learning_rate": 9.634339080459772e-05, + "loss": 1.6032, + "step": 509 + }, + { + "epoch": 0.55, + "learning_rate": 9.633620689655172e-05, + "loss": 1.6353, + "step": 510 + }, + { + "epoch": 0.55, + "learning_rate": 9.632902298850576e-05, + "loss": 1.6154, + "step": 511 + }, + { + "epoch": 0.55, + "learning_rate": 9.632183908045978e-05, + "loss": 1.6315, + "step": 512 + }, + { + "epoch": 0.55, + "learning_rate": 9.63146551724138e-05, + "loss": 1.4025, + "step": 513 + }, + { + "epoch": 0.55, + "learning_rate": 9.630747126436782e-05, + "loss": 1.5502, + "step": 514 + }, + { + "epoch": 0.55, + "learning_rate": 9.630028735632184e-05, + "loss": 1.5591, + "step": 515 + }, + { + "epoch": 0.56, + "learning_rate": 9.629310344827587e-05, + "loss": 1.7269, + "step": 516 + }, + { + "epoch": 0.56, + "learning_rate": 9.628591954022988e-05, + "loss": 1.5166, + "step": 517 + }, + { + "epoch": 0.56, + "learning_rate": 9.627873563218391e-05, + "loss": 1.8181, + "step": 518 + }, + { + "epoch": 0.56, + "learning_rate": 9.627155172413793e-05, + "loss": 1.5811, + "step": 519 + }, + { + "epoch": 0.56, + "learning_rate": 9.626436781609195e-05, + "loss": 1.6514, + "step": 520 + }, + { + "epoch": 0.56, + "learning_rate": 9.625718390804597e-05, + "loss": 1.6801, + "step": 521 + }, + { + "epoch": 0.56, + "learning_rate": 9.625000000000001e-05, + "loss": 1.6789, + "step": 522 + }, + { + "epoch": 0.56, + "learning_rate": 9.624281609195403e-05, + "loss": 1.6374, + "step": 523 + }, + { + "epoch": 0.56, + "learning_rate": 9.623563218390805e-05, + "loss": 1.7214, + "step": 524 + }, + { + "epoch": 0.57, + "learning_rate": 9.622844827586207e-05, + "loss": 1.6635, + "step": 525 + }, + { + "epoch": 0.57, + "learning_rate": 9.62212643678161e-05, + "loss": 1.6913, + "step": 526 + }, + { + "epoch": 0.57, + "learning_rate": 9.621408045977012e-05, + "loss": 1.631, + "step": 527 + }, + { + "epoch": 0.57, + "learning_rate": 9.620689655172414e-05, + "loss": 1.7091, + "step": 528 + }, + { + "epoch": 0.57, + "learning_rate": 9.619971264367816e-05, + "loss": 1.6151, + "step": 529 + }, + { + "epoch": 0.57, + "learning_rate": 9.61925287356322e-05, + "loss": 1.7173, + "step": 530 + }, + { + "epoch": 0.57, + "learning_rate": 9.61853448275862e-05, + "loss": 1.6798, + "step": 531 + }, + { + "epoch": 0.57, + "learning_rate": 9.617816091954024e-05, + "loss": 1.738, + "step": 532 + }, + { + "epoch": 0.57, + "learning_rate": 9.617097701149426e-05, + "loss": 1.7067, + "step": 533 + }, + { + "epoch": 0.58, + "learning_rate": 9.616379310344828e-05, + "loss": 1.6919, + "step": 534 + }, + { + "epoch": 0.58, + "learning_rate": 9.61566091954023e-05, + "loss": 1.6718, + "step": 535 + }, + { + "epoch": 0.58, + "learning_rate": 9.614942528735633e-05, + "loss": 1.7154, + "step": 536 + }, + { + "epoch": 0.58, + "learning_rate": 9.614224137931035e-05, + "loss": 1.575, + "step": 537 + }, + { + "epoch": 0.58, + "learning_rate": 9.613505747126436e-05, + "loss": 1.6895, + "step": 538 + }, + { + "epoch": 0.58, + "learning_rate": 9.61278735632184e-05, + "loss": 1.713, + "step": 539 + }, + { + "epoch": 0.58, + "learning_rate": 9.612068965517241e-05, + "loss": 1.6883, + "step": 540 + }, + { + "epoch": 0.58, + "learning_rate": 9.611350574712645e-05, + "loss": 1.4939, + "step": 541 + }, + { + "epoch": 0.58, + "learning_rate": 9.610632183908046e-05, + "loss": 1.5997, + "step": 542 + }, + { + "epoch": 0.59, + "learning_rate": 9.609913793103449e-05, + "loss": 1.5292, + "step": 543 + }, + { + "epoch": 0.59, + "learning_rate": 9.609195402298851e-05, + "loss": 1.6089, + "step": 544 + }, + { + "epoch": 0.59, + "learning_rate": 9.608477011494253e-05, + "loss": 1.6393, + "step": 545 + }, + { + "epoch": 0.59, + "learning_rate": 9.607758620689655e-05, + "loss": 1.7276, + "step": 546 + }, + { + "epoch": 0.59, + "learning_rate": 9.607040229885058e-05, + "loss": 1.7307, + "step": 547 + }, + { + "epoch": 0.59, + "learning_rate": 9.60632183908046e-05, + "loss": 1.601, + "step": 548 + }, + { + "epoch": 0.59, + "learning_rate": 9.605603448275862e-05, + "loss": 1.5537, + "step": 549 + }, + { + "epoch": 0.59, + "learning_rate": 9.604885057471265e-05, + "loss": 1.5756, + "step": 550 + }, + { + "epoch": 0.59, + "learning_rate": 9.604166666666668e-05, + "loss": 1.5032, + "step": 551 + }, + { + "epoch": 0.59, + "learning_rate": 9.603448275862069e-05, + "loss": 1.6787, + "step": 552 + }, + { + "epoch": 0.6, + "learning_rate": 9.602729885057472e-05, + "loss": 1.6922, + "step": 553 + }, + { + "epoch": 0.6, + "learning_rate": 9.602011494252874e-05, + "loss": 1.8391, + "step": 554 + }, + { + "epoch": 0.6, + "learning_rate": 9.601293103448276e-05, + "loss": 1.5481, + "step": 555 + }, + { + "epoch": 0.6, + "learning_rate": 9.600574712643678e-05, + "loss": 1.552, + "step": 556 + }, + { + "epoch": 0.6, + "learning_rate": 9.599856321839081e-05, + "loss": 1.5305, + "step": 557 + }, + { + "epoch": 0.6, + "learning_rate": 9.599137931034483e-05, + "loss": 1.6338, + "step": 558 + }, + { + "epoch": 0.6, + "learning_rate": 9.598419540229886e-05, + "loss": 1.5345, + "step": 559 + }, + { + "epoch": 0.6, + "learning_rate": 9.597701149425288e-05, + "loss": 1.5755, + "step": 560 + }, + { + "epoch": 0.6, + "learning_rate": 9.596982758620691e-05, + "loss": 1.5617, + "step": 561 + }, + { + "epoch": 0.61, + "learning_rate": 9.596264367816093e-05, + "loss": 1.4234, + "step": 562 + }, + { + "epoch": 0.61, + "learning_rate": 9.595545977011494e-05, + "loss": 1.6208, + "step": 563 + }, + { + "epoch": 0.61, + "learning_rate": 9.594827586206897e-05, + "loss": 1.6311, + "step": 564 + }, + { + "epoch": 0.61, + "learning_rate": 9.594109195402299e-05, + "loss": 1.7091, + "step": 565 + }, + { + "epoch": 0.61, + "learning_rate": 9.593390804597701e-05, + "loss": 1.5734, + "step": 566 + }, + { + "epoch": 0.61, + "learning_rate": 9.592672413793103e-05, + "loss": 1.4694, + "step": 567 + }, + { + "epoch": 0.61, + "learning_rate": 9.591954022988507e-05, + "loss": 1.74, + "step": 568 + }, + { + "epoch": 0.61, + "learning_rate": 9.591235632183909e-05, + "loss": 1.589, + "step": 569 + }, + { + "epoch": 0.61, + "learning_rate": 9.59051724137931e-05, + "loss": 1.5095, + "step": 570 + }, + { + "epoch": 0.62, + "learning_rate": 9.589798850574713e-05, + "loss": 1.6047, + "step": 571 + }, + { + "epoch": 0.62, + "learning_rate": 9.589080459770116e-05, + "loss": 1.5852, + "step": 572 + }, + { + "epoch": 0.62, + "learning_rate": 9.588362068965517e-05, + "loss": 1.5031, + "step": 573 + }, + { + "epoch": 0.62, + "learning_rate": 9.58764367816092e-05, + "loss": 1.6772, + "step": 574 + }, + { + "epoch": 0.62, + "learning_rate": 9.586925287356322e-05, + "loss": 1.748, + "step": 575 + }, + { + "epoch": 0.62, + "learning_rate": 9.586206896551725e-05, + "loss": 1.6571, + "step": 576 + }, + { + "epoch": 0.62, + "learning_rate": 9.585488505747126e-05, + "loss": 1.6266, + "step": 577 + }, + { + "epoch": 0.62, + "learning_rate": 9.58477011494253e-05, + "loss": 1.4928, + "step": 578 + }, + { + "epoch": 0.62, + "learning_rate": 9.584051724137932e-05, + "loss": 1.7278, + "step": 579 + }, + { + "epoch": 0.62, + "learning_rate": 9.583333333333334e-05, + "loss": 1.5913, + "step": 580 + }, + { + "epoch": 0.63, + "learning_rate": 9.582614942528736e-05, + "loss": 1.7336, + "step": 581 + }, + { + "epoch": 0.63, + "learning_rate": 9.581896551724139e-05, + "loss": 1.4031, + "step": 582 + }, + { + "epoch": 0.63, + "learning_rate": 9.581178160919541e-05, + "loss": 1.6716, + "step": 583 + }, + { + "epoch": 0.63, + "learning_rate": 9.580459770114943e-05, + "loss": 1.7238, + "step": 584 + }, + { + "epoch": 0.63, + "learning_rate": 9.579741379310345e-05, + "loss": 1.6035, + "step": 585 + }, + { + "epoch": 0.63, + "learning_rate": 9.579022988505749e-05, + "loss": 1.4759, + "step": 586 + }, + { + "epoch": 0.63, + "learning_rate": 9.578304597701149e-05, + "loss": 1.6788, + "step": 587 + }, + { + "epoch": 0.63, + "learning_rate": 9.577586206896553e-05, + "loss": 1.5806, + "step": 588 + }, + { + "epoch": 0.63, + "learning_rate": 9.576867816091955e-05, + "loss": 1.5363, + "step": 589 + }, + { + "epoch": 0.64, + "learning_rate": 9.576149425287357e-05, + "loss": 1.5851, + "step": 590 + }, + { + "epoch": 0.64, + "learning_rate": 9.575431034482759e-05, + "loss": 1.4724, + "step": 591 + }, + { + "epoch": 0.64, + "learning_rate": 9.574712643678161e-05, + "loss": 1.6589, + "step": 592 + }, + { + "epoch": 0.64, + "learning_rate": 9.573994252873564e-05, + "loss": 1.452, + "step": 593 + }, + { + "epoch": 0.64, + "learning_rate": 9.573275862068966e-05, + "loss": 1.6493, + "step": 594 + }, + { + "epoch": 0.64, + "learning_rate": 9.572557471264368e-05, + "loss": 1.6436, + "step": 595 + }, + { + "epoch": 0.64, + "learning_rate": 9.57183908045977e-05, + "loss": 1.5655, + "step": 596 + }, + { + "epoch": 0.64, + "learning_rate": 9.571120689655174e-05, + "loss": 1.7301, + "step": 597 + }, + { + "epoch": 0.64, + "learning_rate": 9.570402298850574e-05, + "loss": 1.6627, + "step": 598 + }, + { + "epoch": 0.65, + "learning_rate": 9.569683908045978e-05, + "loss": 1.689, + "step": 599 + }, + { + "epoch": 0.65, + "learning_rate": 9.56896551724138e-05, + "loss": 1.5714, + "step": 600 + }, + { + "epoch": 0.65, + "learning_rate": 9.568247126436782e-05, + "loss": 1.617, + "step": 601 + }, + { + "epoch": 0.65, + "learning_rate": 9.567528735632184e-05, + "loss": 1.725, + "step": 602 + }, + { + "epoch": 0.65, + "learning_rate": 9.566810344827587e-05, + "loss": 1.5442, + "step": 603 + }, + { + "epoch": 0.65, + "learning_rate": 9.566091954022989e-05, + "loss": 1.6059, + "step": 604 + }, + { + "epoch": 0.65, + "learning_rate": 9.565373563218391e-05, + "loss": 1.788, + "step": 605 + }, + { + "epoch": 0.65, + "learning_rate": 9.564655172413793e-05, + "loss": 1.6503, + "step": 606 + }, + { + "epoch": 0.65, + "learning_rate": 9.563936781609197e-05, + "loss": 1.7516, + "step": 607 + }, + { + "epoch": 0.66, + "learning_rate": 9.563218390804599e-05, + "loss": 1.674, + "step": 608 + }, + { + "epoch": 0.66, + "learning_rate": 9.562500000000001e-05, + "loss": 1.6862, + "step": 609 + }, + { + "epoch": 0.66, + "learning_rate": 9.561781609195403e-05, + "loss": 1.6071, + "step": 610 + }, + { + "epoch": 0.66, + "learning_rate": 9.561063218390806e-05, + "loss": 1.6425, + "step": 611 + }, + { + "epoch": 0.66, + "learning_rate": 9.560344827586207e-05, + "loss": 1.5158, + "step": 612 + }, + { + "epoch": 0.66, + "learning_rate": 9.55962643678161e-05, + "loss": 1.6213, + "step": 613 + }, + { + "epoch": 0.66, + "learning_rate": 9.558908045977012e-05, + "loss": 1.488, + "step": 614 + }, + { + "epoch": 0.66, + "learning_rate": 9.558189655172414e-05, + "loss": 1.4998, + "step": 615 + }, + { + "epoch": 0.66, + "learning_rate": 9.557471264367816e-05, + "loss": 1.5206, + "step": 616 + }, + { + "epoch": 0.66, + "learning_rate": 9.556752873563218e-05, + "loss": 1.6261, + "step": 617 + }, + { + "epoch": 0.67, + "learning_rate": 9.556034482758622e-05, + "loss": 1.5845, + "step": 618 + }, + { + "epoch": 0.67, + "learning_rate": 9.555316091954022e-05, + "loss": 1.7546, + "step": 619 + }, + { + "epoch": 0.67, + "learning_rate": 9.554597701149426e-05, + "loss": 1.6384, + "step": 620 + }, + { + "epoch": 0.67, + "learning_rate": 9.553879310344828e-05, + "loss": 1.491, + "step": 621 + }, + { + "epoch": 0.67, + "learning_rate": 9.553160919540231e-05, + "loss": 1.6096, + "step": 622 + }, + { + "epoch": 0.67, + "learning_rate": 9.552442528735632e-05, + "loss": 1.6493, + "step": 623 + }, + { + "epoch": 0.67, + "learning_rate": 9.551724137931035e-05, + "loss": 1.5835, + "step": 624 + }, + { + "epoch": 0.67, + "learning_rate": 9.551005747126437e-05, + "loss": 1.5872, + "step": 625 + }, + { + "epoch": 0.67, + "learning_rate": 9.550287356321839e-05, + "loss": 1.669, + "step": 626 + }, + { + "epoch": 0.68, + "learning_rate": 9.549568965517241e-05, + "loss": 1.6111, + "step": 627 + }, + { + "epoch": 0.68, + "learning_rate": 9.548850574712645e-05, + "loss": 1.6381, + "step": 628 + }, + { + "epoch": 0.68, + "learning_rate": 9.548132183908047e-05, + "loss": 1.4995, + "step": 629 + }, + { + "epoch": 0.68, + "learning_rate": 9.547413793103449e-05, + "loss": 1.4014, + "step": 630 + }, + { + "epoch": 0.68, + "learning_rate": 9.546695402298851e-05, + "loss": 1.7254, + "step": 631 + }, + { + "epoch": 0.68, + "learning_rate": 9.545977011494254e-05, + "loss": 1.6387, + "step": 632 + }, + { + "epoch": 0.68, + "learning_rate": 9.545258620689655e-05, + "loss": 1.5427, + "step": 633 + }, + { + "epoch": 0.68, + "learning_rate": 9.544540229885058e-05, + "loss": 1.5133, + "step": 634 + }, + { + "epoch": 0.68, + "learning_rate": 9.54382183908046e-05, + "loss": 1.5946, + "step": 635 + }, + { + "epoch": 0.69, + "learning_rate": 9.543103448275862e-05, + "loss": 1.495, + "step": 636 + }, + { + "epoch": 0.69, + "learning_rate": 9.542385057471264e-05, + "loss": 1.7668, + "step": 637 + }, + { + "epoch": 0.69, + "learning_rate": 9.541666666666668e-05, + "loss": 1.6433, + "step": 638 + }, + { + "epoch": 0.69, + "learning_rate": 9.54094827586207e-05, + "loss": 1.6788, + "step": 639 + }, + { + "epoch": 0.69, + "learning_rate": 9.540229885057472e-05, + "loss": 1.7401, + "step": 640 + }, + { + "epoch": 0.69, + "learning_rate": 9.539511494252874e-05, + "loss": 1.6755, + "step": 641 + }, + { + "epoch": 0.69, + "learning_rate": 9.538793103448276e-05, + "loss": 1.6758, + "step": 642 + }, + { + "epoch": 0.69, + "learning_rate": 9.538074712643679e-05, + "loss": 1.6314, + "step": 643 + }, + { + "epoch": 0.69, + "learning_rate": 9.53735632183908e-05, + "loss": 1.5977, + "step": 644 + }, + { + "epoch": 0.7, + "learning_rate": 9.536637931034483e-05, + "loss": 1.5623, + "step": 645 + }, + { + "epoch": 0.7, + "learning_rate": 9.535919540229885e-05, + "loss": 1.5266, + "step": 646 + }, + { + "epoch": 0.7, + "learning_rate": 9.535201149425287e-05, + "loss": 1.5716, + "step": 647 + }, + { + "epoch": 0.7, + "learning_rate": 9.53448275862069e-05, + "loss": 1.535, + "step": 648 + }, + { + "epoch": 0.7, + "learning_rate": 9.533764367816093e-05, + "loss": 1.6577, + "step": 649 + }, + { + "epoch": 0.7, + "learning_rate": 9.533045977011495e-05, + "loss": 1.5815, + "step": 650 + }, + { + "epoch": 0.7, + "learning_rate": 9.532327586206897e-05, + "loss": 1.6737, + "step": 651 + }, + { + "epoch": 0.7, + "learning_rate": 9.531609195402299e-05, + "loss": 1.5846, + "step": 652 + }, + { + "epoch": 0.7, + "learning_rate": 9.530890804597702e-05, + "loss": 1.5324, + "step": 653 + }, + { + "epoch": 0.7, + "learning_rate": 9.530172413793104e-05, + "loss": 1.5759, + "step": 654 + }, + { + "epoch": 0.71, + "learning_rate": 9.529454022988506e-05, + "loss": 1.4968, + "step": 655 + }, + { + "epoch": 0.71, + "learning_rate": 9.528735632183908e-05, + "loss": 1.4713, + "step": 656 + }, + { + "epoch": 0.71, + "learning_rate": 9.528017241379312e-05, + "loss": 1.4839, + "step": 657 + }, + { + "epoch": 0.71, + "learning_rate": 9.527298850574712e-05, + "loss": 1.6281, + "step": 658 + }, + { + "epoch": 0.71, + "learning_rate": 9.526580459770116e-05, + "loss": 1.4633, + "step": 659 + }, + { + "epoch": 0.71, + "learning_rate": 9.525862068965518e-05, + "loss": 1.843, + "step": 660 + }, + { + "epoch": 0.71, + "learning_rate": 9.52514367816092e-05, + "loss": 1.5284, + "step": 661 + }, + { + "epoch": 0.71, + "learning_rate": 9.524425287356322e-05, + "loss": 1.5537, + "step": 662 + }, + { + "epoch": 0.71, + "learning_rate": 9.523706896551725e-05, + "loss": 1.4869, + "step": 663 + }, + { + "epoch": 0.72, + "learning_rate": 9.522988505747127e-05, + "loss": 1.6425, + "step": 664 + }, + { + "epoch": 0.72, + "learning_rate": 9.52227011494253e-05, + "loss": 1.385, + "step": 665 + }, + { + "epoch": 0.72, + "learning_rate": 9.521551724137931e-05, + "loss": 1.4226, + "step": 666 + }, + { + "epoch": 0.72, + "learning_rate": 9.520833333333333e-05, + "loss": 1.5344, + "step": 667 + }, + { + "epoch": 0.72, + "learning_rate": 9.520114942528735e-05, + "loss": 1.4217, + "step": 668 + }, + { + "epoch": 0.72, + "learning_rate": 9.519396551724138e-05, + "loss": 1.6276, + "step": 669 + }, + { + "epoch": 0.72, + "learning_rate": 9.518678160919541e-05, + "loss": 1.444, + "step": 670 + }, + { + "epoch": 0.72, + "learning_rate": 9.517959770114943e-05, + "loss": 1.7769, + "step": 671 + }, + { + "epoch": 0.72, + "learning_rate": 9.517241379310345e-05, + "loss": 1.3793, + "step": 672 + }, + { + "epoch": 0.73, + "learning_rate": 9.516522988505747e-05, + "loss": 1.6186, + "step": 673 + }, + { + "epoch": 0.73, + "learning_rate": 9.51580459770115e-05, + "loss": 1.5301, + "step": 674 + }, + { + "epoch": 0.73, + "learning_rate": 9.515086206896552e-05, + "loss": 1.5673, + "step": 675 + }, + { + "epoch": 0.73, + "learning_rate": 9.514367816091954e-05, + "loss": 1.4306, + "step": 676 + }, + { + "epoch": 0.73, + "learning_rate": 9.513649425287356e-05, + "loss": 1.6546, + "step": 677 + }, + { + "epoch": 0.73, + "learning_rate": 9.51293103448276e-05, + "loss": 1.4837, + "step": 678 + }, + { + "epoch": 0.73, + "learning_rate": 9.51221264367816e-05, + "loss": 1.5412, + "step": 679 + }, + { + "epoch": 0.73, + "learning_rate": 9.511494252873564e-05, + "loss": 1.5276, + "step": 680 + }, + { + "epoch": 0.73, + "learning_rate": 9.510775862068966e-05, + "loss": 1.6599, + "step": 681 + }, + { + "epoch": 0.73, + "learning_rate": 9.510057471264368e-05, + "loss": 1.7019, + "step": 682 + }, + { + "epoch": 0.74, + "learning_rate": 9.50933908045977e-05, + "loss": 1.6253, + "step": 683 + }, + { + "epoch": 0.74, + "learning_rate": 9.508620689655173e-05, + "loss": 1.5948, + "step": 684 + }, + { + "epoch": 0.74, + "learning_rate": 9.507902298850575e-05, + "loss": 1.6691, + "step": 685 + }, + { + "epoch": 0.74, + "learning_rate": 9.507183908045977e-05, + "loss": 1.591, + "step": 686 + }, + { + "epoch": 0.74, + "learning_rate": 9.50646551724138e-05, + "loss": 1.7886, + "step": 687 + }, + { + "epoch": 0.74, + "learning_rate": 9.505747126436783e-05, + "loss": 1.705, + "step": 688 + }, + { + "epoch": 0.74, + "learning_rate": 9.505028735632185e-05, + "loss": 1.467, + "step": 689 + }, + { + "epoch": 0.74, + "learning_rate": 9.504310344827587e-05, + "loss": 1.5379, + "step": 690 + }, + { + "epoch": 0.74, + "learning_rate": 9.503591954022989e-05, + "loss": 1.5208, + "step": 691 + }, + { + "epoch": 0.75, + "learning_rate": 9.502873563218391e-05, + "loss": 1.5965, + "step": 692 + }, + { + "epoch": 0.75, + "learning_rate": 9.502155172413793e-05, + "loss": 1.586, + "step": 693 + }, + { + "epoch": 0.75, + "learning_rate": 9.501436781609195e-05, + "loss": 1.5448, + "step": 694 + }, + { + "epoch": 0.75, + "learning_rate": 9.500718390804598e-05, + "loss": 1.4642, + "step": 695 + }, + { + "epoch": 0.75, + "learning_rate": 9.5e-05, + "loss": 1.7731, + "step": 696 + }, + { + "epoch": 0.75, + "learning_rate": 9.499281609195403e-05, + "loss": 1.3554, + "step": 697 + }, + { + "epoch": 0.75, + "learning_rate": 9.498563218390805e-05, + "loss": 1.713, + "step": 698 + }, + { + "epoch": 0.75, + "learning_rate": 9.497844827586208e-05, + "loss": 1.6899, + "step": 699 + }, + { + "epoch": 0.75, + "learning_rate": 9.497126436781609e-05, + "loss": 1.7139, + "step": 700 + }, + { + "epoch": 0.76, + "learning_rate": 9.496408045977012e-05, + "loss": 1.5208, + "step": 701 + }, + { + "epoch": 0.76, + "learning_rate": 9.495689655172414e-05, + "loss": 1.5177, + "step": 702 + }, + { + "epoch": 0.76, + "learning_rate": 9.494971264367817e-05, + "loss": 1.5667, + "step": 703 + }, + { + "epoch": 0.76, + "learning_rate": 9.494252873563218e-05, + "loss": 1.5828, + "step": 704 + }, + { + "epoch": 0.76, + "learning_rate": 9.493534482758622e-05, + "loss": 1.5911, + "step": 705 + }, + { + "epoch": 0.76, + "learning_rate": 9.492816091954024e-05, + "loss": 1.5527, + "step": 706 + }, + { + "epoch": 0.76, + "learning_rate": 9.492097701149426e-05, + "loss": 1.6425, + "step": 707 + }, + { + "epoch": 0.76, + "learning_rate": 9.491379310344828e-05, + "loss": 1.585, + "step": 708 + }, + { + "epoch": 0.76, + "learning_rate": 9.490660919540231e-05, + "loss": 1.5618, + "step": 709 + }, + { + "epoch": 0.77, + "learning_rate": 9.489942528735633e-05, + "loss": 1.6508, + "step": 710 + }, + { + "epoch": 0.77, + "learning_rate": 9.489224137931035e-05, + "loss": 1.4862, + "step": 711 + }, + { + "epoch": 0.77, + "learning_rate": 9.488505747126437e-05, + "loss": 1.4483, + "step": 712 + }, + { + "epoch": 0.77, + "learning_rate": 9.48778735632184e-05, + "loss": 1.5156, + "step": 713 + }, + { + "epoch": 0.77, + "learning_rate": 9.487068965517241e-05, + "loss": 1.6229, + "step": 714 + }, + { + "epoch": 0.77, + "learning_rate": 9.486350574712645e-05, + "loss": 1.4203, + "step": 715 + }, + { + "epoch": 0.77, + "learning_rate": 9.485632183908047e-05, + "loss": 1.583, + "step": 716 + }, + { + "epoch": 0.77, + "learning_rate": 9.484913793103449e-05, + "loss": 1.6089, + "step": 717 + }, + { + "epoch": 0.77, + "learning_rate": 9.48419540229885e-05, + "loss": 1.5844, + "step": 718 + }, + { + "epoch": 0.77, + "learning_rate": 9.483477011494253e-05, + "loss": 1.5861, + "step": 719 + }, + { + "epoch": 0.78, + "learning_rate": 9.482758620689656e-05, + "loss": 1.6348, + "step": 720 + }, + { + "epoch": 0.78, + "learning_rate": 9.482040229885058e-05, + "loss": 1.4959, + "step": 721 + }, + { + "epoch": 0.78, + "learning_rate": 9.48132183908046e-05, + "loss": 1.4648, + "step": 722 + }, + { + "epoch": 0.78, + "learning_rate": 9.480603448275862e-05, + "loss": 1.5212, + "step": 723 + }, + { + "epoch": 0.78, + "learning_rate": 9.479885057471266e-05, + "loss": 1.4943, + "step": 724 + }, + { + "epoch": 0.78, + "learning_rate": 9.479166666666666e-05, + "loss": 1.686, + "step": 725 + }, + { + "epoch": 0.78, + "learning_rate": 9.47844827586207e-05, + "loss": 1.6632, + "step": 726 + }, + { + "epoch": 0.78, + "learning_rate": 9.477729885057472e-05, + "loss": 1.6458, + "step": 727 + }, + { + "epoch": 0.78, + "learning_rate": 9.477011494252874e-05, + "loss": 1.5627, + "step": 728 + }, + { + "epoch": 0.79, + "learning_rate": 9.476293103448276e-05, + "loss": 1.5012, + "step": 729 + }, + { + "epoch": 0.79, + "learning_rate": 9.475574712643679e-05, + "loss": 1.6793, + "step": 730 + }, + { + "epoch": 0.79, + "learning_rate": 9.474856321839081e-05, + "loss": 1.5002, + "step": 731 + }, + { + "epoch": 0.79, + "learning_rate": 9.474137931034483e-05, + "loss": 1.6099, + "step": 732 + }, + { + "epoch": 0.79, + "learning_rate": 9.473419540229885e-05, + "loss": 1.6164, + "step": 733 + }, + { + "epoch": 0.79, + "learning_rate": 9.472701149425289e-05, + "loss": 1.7096, + "step": 734 + }, + { + "epoch": 0.79, + "learning_rate": 9.47198275862069e-05, + "loss": 1.5099, + "step": 735 + }, + { + "epoch": 0.79, + "learning_rate": 9.471264367816093e-05, + "loss": 1.6937, + "step": 736 + }, + { + "epoch": 0.79, + "learning_rate": 9.470545977011495e-05, + "loss": 1.5299, + "step": 737 + }, + { + "epoch": 0.8, + "learning_rate": 9.469827586206898e-05, + "loss": 1.5683, + "step": 738 + }, + { + "epoch": 0.8, + "learning_rate": 9.469109195402299e-05, + "loss": 1.5241, + "step": 739 + }, + { + "epoch": 0.8, + "learning_rate": 9.468390804597702e-05, + "loss": 1.6574, + "step": 740 + }, + { + "epoch": 0.8, + "learning_rate": 9.467672413793104e-05, + "loss": 1.5114, + "step": 741 + }, + { + "epoch": 0.8, + "learning_rate": 9.466954022988506e-05, + "loss": 1.3874, + "step": 742 + }, + { + "epoch": 0.8, + "learning_rate": 9.466235632183908e-05, + "loss": 1.7581, + "step": 743 + }, + { + "epoch": 0.8, + "learning_rate": 9.46551724137931e-05, + "loss": 1.6273, + "step": 744 + }, + { + "epoch": 0.8, + "learning_rate": 9.464798850574714e-05, + "loss": 1.6119, + "step": 745 + }, + { + "epoch": 0.8, + "learning_rate": 9.464080459770114e-05, + "loss": 1.6038, + "step": 746 + }, + { + "epoch": 0.8, + "learning_rate": 9.463362068965518e-05, + "loss": 1.772, + "step": 747 + }, + { + "epoch": 0.81, + "learning_rate": 9.46264367816092e-05, + "loss": 1.5327, + "step": 748 + }, + { + "epoch": 0.81, + "learning_rate": 9.461925287356322e-05, + "loss": 1.5687, + "step": 749 + }, + { + "epoch": 0.81, + "learning_rate": 9.461206896551724e-05, + "loss": 1.506, + "step": 750 + }, + { + "epoch": 0.81, + "eval_loss": 1.3777729272842407, + "eval_runtime": 175.1033, + "eval_samples_per_second": 127.182, + "eval_steps_per_second": 0.662, + "step": 750 + }, + { + "epoch": 0.81, + "learning_rate": 9.460488505747127e-05, + "loss": 1.5582, + "step": 751 + }, + { + "epoch": 0.81, + "learning_rate": 9.459770114942529e-05, + "loss": 1.6529, + "step": 752 + }, + { + "epoch": 0.81, + "learning_rate": 9.459051724137931e-05, + "loss": 1.5583, + "step": 753 + }, + { + "epoch": 0.81, + "learning_rate": 9.458333333333333e-05, + "loss": 1.623, + "step": 754 + }, + { + "epoch": 0.81, + "learning_rate": 9.457614942528737e-05, + "loss": 1.6959, + "step": 755 + }, + { + "epoch": 0.81, + "learning_rate": 9.456896551724139e-05, + "loss": 1.727, + "step": 756 + }, + { + "epoch": 0.82, + "learning_rate": 9.456178160919541e-05, + "loss": 1.6385, + "step": 757 + }, + { + "epoch": 0.82, + "learning_rate": 9.455459770114943e-05, + "loss": 1.4934, + "step": 758 + }, + { + "epoch": 0.82, + "learning_rate": 9.454741379310346e-05, + "loss": 1.518, + "step": 759 + }, + { + "epoch": 0.82, + "learning_rate": 9.454022988505747e-05, + "loss": 1.5588, + "step": 760 + }, + { + "epoch": 0.82, + "learning_rate": 9.45330459770115e-05, + "loss": 1.6052, + "step": 761 + }, + { + "epoch": 0.82, + "learning_rate": 9.452586206896552e-05, + "loss": 1.6805, + "step": 762 + }, + { + "epoch": 0.82, + "learning_rate": 9.451867816091954e-05, + "loss": 1.4634, + "step": 763 + }, + { + "epoch": 0.82, + "learning_rate": 9.451149425287356e-05, + "loss": 1.6382, + "step": 764 + }, + { + "epoch": 0.82, + "learning_rate": 9.45043103448276e-05, + "loss": 1.5971, + "step": 765 + }, + { + "epoch": 0.83, + "learning_rate": 9.449712643678162e-05, + "loss": 1.6411, + "step": 766 + }, + { + "epoch": 0.83, + "learning_rate": 9.448994252873564e-05, + "loss": 1.6737, + "step": 767 + }, + { + "epoch": 0.83, + "learning_rate": 9.448275862068966e-05, + "loss": 1.6202, + "step": 768 + }, + { + "epoch": 0.83, + "learning_rate": 9.447557471264368e-05, + "loss": 1.4343, + "step": 769 + }, + { + "epoch": 0.83, + "learning_rate": 9.446839080459771e-05, + "loss": 1.6018, + "step": 770 + }, + { + "epoch": 0.83, + "learning_rate": 9.446120689655172e-05, + "loss": 1.5763, + "step": 771 + }, + { + "epoch": 0.83, + "learning_rate": 9.445402298850575e-05, + "loss": 1.4457, + "step": 772 + }, + { + "epoch": 0.83, + "learning_rate": 9.444683908045977e-05, + "loss": 1.4884, + "step": 773 + }, + { + "epoch": 0.83, + "learning_rate": 9.44396551724138e-05, + "loss": 1.5127, + "step": 774 + }, + { + "epoch": 0.84, + "learning_rate": 9.443247126436781e-05, + "loss": 1.5489, + "step": 775 + }, + { + "epoch": 0.84, + "learning_rate": 9.442528735632185e-05, + "loss": 1.4205, + "step": 776 + }, + { + "epoch": 0.84, + "learning_rate": 9.441810344827587e-05, + "loss": 1.6028, + "step": 777 + }, + { + "epoch": 0.84, + "learning_rate": 9.441091954022989e-05, + "loss": 1.4818, + "step": 778 + }, + { + "epoch": 0.84, + "learning_rate": 9.440373563218391e-05, + "loss": 1.4916, + "step": 779 + }, + { + "epoch": 0.84, + "learning_rate": 9.439655172413794e-05, + "loss": 1.5316, + "step": 780 + }, + { + "epoch": 0.84, + "learning_rate": 9.438936781609195e-05, + "loss": 1.5629, + "step": 781 + }, + { + "epoch": 0.84, + "learning_rate": 9.438218390804598e-05, + "loss": 1.5828, + "step": 782 + }, + { + "epoch": 0.84, + "learning_rate": 9.4375e-05, + "loss": 1.5734, + "step": 783 + }, + { + "epoch": 0.84, + "learning_rate": 9.436781609195404e-05, + "loss": 1.5112, + "step": 784 + }, + { + "epoch": 0.85, + "learning_rate": 9.436063218390804e-05, + "loss": 1.5648, + "step": 785 + }, + { + "epoch": 0.85, + "learning_rate": 9.435344827586208e-05, + "loss": 1.5525, + "step": 786 + }, + { + "epoch": 0.85, + "learning_rate": 9.43462643678161e-05, + "loss": 1.5529, + "step": 787 + }, + { + "epoch": 0.85, + "learning_rate": 9.433908045977012e-05, + "loss": 1.4473, + "step": 788 + }, + { + "epoch": 0.85, + "learning_rate": 9.433189655172414e-05, + "loss": 1.5747, + "step": 789 + }, + { + "epoch": 0.85, + "learning_rate": 9.432471264367817e-05, + "loss": 1.6325, + "step": 790 + }, + { + "epoch": 0.85, + "learning_rate": 9.43175287356322e-05, + "loss": 1.744, + "step": 791 + }, + { + "epoch": 0.85, + "learning_rate": 9.431034482758621e-05, + "loss": 1.5859, + "step": 792 + }, + { + "epoch": 0.85, + "learning_rate": 9.430316091954023e-05, + "loss": 1.3782, + "step": 793 + }, + { + "epoch": 0.86, + "learning_rate": 9.429597701149425e-05, + "loss": 1.421, + "step": 794 + }, + { + "epoch": 0.86, + "learning_rate": 9.428879310344827e-05, + "loss": 1.8291, + "step": 795 + }, + { + "epoch": 0.86, + "learning_rate": 9.42816091954023e-05, + "loss": 1.472, + "step": 796 + }, + { + "epoch": 0.86, + "learning_rate": 9.427442528735633e-05, + "loss": 1.5368, + "step": 797 + }, + { + "epoch": 0.86, + "learning_rate": 9.426724137931035e-05, + "loss": 1.5258, + "step": 798 + }, + { + "epoch": 0.86, + "learning_rate": 9.426005747126437e-05, + "loss": 1.5386, + "step": 799 + }, + { + "epoch": 0.86, + "learning_rate": 9.425287356321839e-05, + "loss": 1.4233, + "step": 800 + }, + { + "epoch": 0.86, + "learning_rate": 9.424568965517242e-05, + "loss": 1.6067, + "step": 801 + }, + { + "epoch": 0.86, + "learning_rate": 9.423850574712644e-05, + "loss": 1.5855, + "step": 802 + }, + { + "epoch": 0.87, + "learning_rate": 9.423132183908046e-05, + "loss": 1.5093, + "step": 803 + }, + { + "epoch": 0.87, + "learning_rate": 9.422413793103448e-05, + "loss": 1.5549, + "step": 804 + }, + { + "epoch": 0.87, + "learning_rate": 9.421695402298852e-05, + "loss": 1.4401, + "step": 805 + }, + { + "epoch": 0.87, + "learning_rate": 9.420977011494253e-05, + "loss": 1.5909, + "step": 806 + }, + { + "epoch": 0.87, + "learning_rate": 9.420258620689656e-05, + "loss": 1.478, + "step": 807 + }, + { + "epoch": 0.87, + "learning_rate": 9.419540229885058e-05, + "loss": 1.5154, + "step": 808 + }, + { + "epoch": 0.87, + "learning_rate": 9.41882183908046e-05, + "loss": 1.5596, + "step": 809 + }, + { + "epoch": 0.87, + "learning_rate": 9.418103448275862e-05, + "loss": 1.5329, + "step": 810 + }, + { + "epoch": 0.87, + "learning_rate": 9.417385057471265e-05, + "loss": 1.4962, + "step": 811 + }, + { + "epoch": 0.88, + "learning_rate": 9.416666666666667e-05, + "loss": 1.3894, + "step": 812 + }, + { + "epoch": 0.88, + "learning_rate": 9.41594827586207e-05, + "loss": 1.4949, + "step": 813 + }, + { + "epoch": 0.88, + "learning_rate": 9.415229885057471e-05, + "loss": 1.4796, + "step": 814 + }, + { + "epoch": 0.88, + "learning_rate": 9.414511494252875e-05, + "loss": 1.4648, + "step": 815 + }, + { + "epoch": 0.88, + "learning_rate": 9.413793103448277e-05, + "loss": 1.5201, + "step": 816 + }, + { + "epoch": 0.88, + "learning_rate": 9.413074712643679e-05, + "loss": 1.6453, + "step": 817 + }, + { + "epoch": 0.88, + "learning_rate": 9.412356321839081e-05, + "loss": 1.5891, + "step": 818 + }, + { + "epoch": 0.88, + "learning_rate": 9.411637931034483e-05, + "loss": 1.5211, + "step": 819 + }, + { + "epoch": 0.88, + "learning_rate": 9.410919540229885e-05, + "loss": 1.4375, + "step": 820 + }, + { + "epoch": 0.88, + "learning_rate": 9.410201149425287e-05, + "loss": 1.7001, + "step": 821 + }, + { + "epoch": 0.89, + "learning_rate": 9.40948275862069e-05, + "loss": 1.5498, + "step": 822 + }, + { + "epoch": 0.89, + "learning_rate": 9.408764367816092e-05, + "loss": 1.4706, + "step": 823 + }, + { + "epoch": 0.89, + "learning_rate": 9.408045977011495e-05, + "loss": 1.4898, + "step": 824 + }, + { + "epoch": 0.89, + "learning_rate": 9.407327586206897e-05, + "loss": 1.4606, + "step": 825 + }, + { + "epoch": 0.89, + "learning_rate": 9.4066091954023e-05, + "loss": 1.6918, + "step": 826 + }, + { + "epoch": 0.89, + "learning_rate": 9.4058908045977e-05, + "loss": 1.5441, + "step": 827 + }, + { + "epoch": 0.89, + "learning_rate": 9.405172413793104e-05, + "loss": 1.622, + "step": 828 + }, + { + "epoch": 0.89, + "learning_rate": 9.404454022988506e-05, + "loss": 1.5155, + "step": 829 + }, + { + "epoch": 0.89, + "learning_rate": 9.403735632183908e-05, + "loss": 1.5394, + "step": 830 + }, + { + "epoch": 0.9, + "learning_rate": 9.40301724137931e-05, + "loss": 1.5023, + "step": 831 + }, + { + "epoch": 0.9, + "learning_rate": 9.402298850574713e-05, + "loss": 1.3401, + "step": 832 + }, + { + "epoch": 0.9, + "learning_rate": 9.401580459770116e-05, + "loss": 1.667, + "step": 833 + }, + { + "epoch": 0.9, + "learning_rate": 9.400862068965518e-05, + "loss": 1.5199, + "step": 834 + }, + { + "epoch": 0.9, + "learning_rate": 9.40014367816092e-05, + "loss": 1.6075, + "step": 835 + }, + { + "epoch": 0.9, + "learning_rate": 9.399425287356323e-05, + "loss": 1.6661, + "step": 836 + }, + { + "epoch": 0.9, + "learning_rate": 9.398706896551725e-05, + "loss": 1.506, + "step": 837 + }, + { + "epoch": 0.9, + "learning_rate": 9.397988505747127e-05, + "loss": 1.5728, + "step": 838 + }, + { + "epoch": 0.9, + "learning_rate": 9.397270114942529e-05, + "loss": 1.6164, + "step": 839 + }, + { + "epoch": 0.91, + "learning_rate": 9.396551724137932e-05, + "loss": 1.4694, + "step": 840 + }, + { + "epoch": 0.91, + "learning_rate": 9.395833333333333e-05, + "loss": 1.5341, + "step": 841 + }, + { + "epoch": 0.91, + "learning_rate": 9.395114942528737e-05, + "loss": 1.512, + "step": 842 + }, + { + "epoch": 0.91, + "learning_rate": 9.394396551724139e-05, + "loss": 1.6751, + "step": 843 + }, + { + "epoch": 0.91, + "learning_rate": 9.39367816091954e-05, + "loss": 1.6071, + "step": 844 + }, + { + "epoch": 0.91, + "learning_rate": 9.392959770114943e-05, + "loss": 1.5892, + "step": 845 + }, + { + "epoch": 0.91, + "learning_rate": 9.392241379310345e-05, + "loss": 1.4803, + "step": 846 + }, + { + "epoch": 0.91, + "learning_rate": 9.391522988505748e-05, + "loss": 1.6123, + "step": 847 + }, + { + "epoch": 0.91, + "learning_rate": 9.39080459770115e-05, + "loss": 1.7144, + "step": 848 + }, + { + "epoch": 0.91, + "learning_rate": 9.390086206896552e-05, + "loss": 1.5183, + "step": 849 + }, + { + "epoch": 0.92, + "learning_rate": 9.389367816091954e-05, + "loss": 1.5423, + "step": 850 + }, + { + "epoch": 0.92, + "learning_rate": 9.388649425287358e-05, + "loss": 1.485, + "step": 851 + }, + { + "epoch": 0.92, + "learning_rate": 9.387931034482758e-05, + "loss": 1.5169, + "step": 852 + }, + { + "epoch": 0.92, + "learning_rate": 9.387212643678162e-05, + "loss": 1.5442, + "step": 853 + }, + { + "epoch": 0.92, + "learning_rate": 9.386494252873564e-05, + "loss": 1.6011, + "step": 854 + }, + { + "epoch": 0.92, + "learning_rate": 9.385775862068966e-05, + "loss": 1.6278, + "step": 855 + }, + { + "epoch": 0.92, + "learning_rate": 9.385057471264368e-05, + "loss": 1.4918, + "step": 856 + }, + { + "epoch": 0.92, + "learning_rate": 9.384339080459771e-05, + "loss": 1.7782, + "step": 857 + }, + { + "epoch": 0.92, + "learning_rate": 9.383620689655173e-05, + "loss": 1.5899, + "step": 858 + }, + { + "epoch": 0.93, + "learning_rate": 9.382902298850575e-05, + "loss": 1.5812, + "step": 859 + }, + { + "epoch": 0.93, + "learning_rate": 9.382183908045977e-05, + "loss": 1.5808, + "step": 860 + }, + { + "epoch": 0.93, + "learning_rate": 9.38146551724138e-05, + "loss": 1.5099, + "step": 861 + }, + { + "epoch": 0.93, + "learning_rate": 9.380747126436781e-05, + "loss": 1.5657, + "step": 862 + }, + { + "epoch": 0.93, + "learning_rate": 9.380028735632185e-05, + "loss": 1.4138, + "step": 863 + }, + { + "epoch": 0.93, + "learning_rate": 9.379310344827587e-05, + "loss": 1.3937, + "step": 864 + }, + { + "epoch": 0.93, + "learning_rate": 9.37859195402299e-05, + "loss": 1.5289, + "step": 865 + }, + { + "epoch": 0.93, + "learning_rate": 9.377873563218391e-05, + "loss": 1.552, + "step": 866 + }, + { + "epoch": 0.93, + "learning_rate": 9.377155172413794e-05, + "loss": 1.4853, + "step": 867 + }, + { + "epoch": 0.94, + "learning_rate": 9.376436781609196e-05, + "loss": 1.4199, + "step": 868 + }, + { + "epoch": 0.94, + "learning_rate": 9.375718390804598e-05, + "loss": 1.6102, + "step": 869 + }, + { + "epoch": 0.94, + "learning_rate": 9.375e-05, + "loss": 1.4541, + "step": 870 + }, + { + "epoch": 0.94, + "learning_rate": 9.374281609195402e-05, + "loss": 1.5012, + "step": 871 + }, + { + "epoch": 0.94, + "learning_rate": 9.373563218390806e-05, + "loss": 1.4264, + "step": 872 + }, + { + "epoch": 0.94, + "learning_rate": 9.372844827586206e-05, + "loss": 1.5541, + "step": 873 + }, + { + "epoch": 0.94, + "learning_rate": 9.37212643678161e-05, + "loss": 1.446, + "step": 874 + }, + { + "epoch": 0.94, + "learning_rate": 9.371408045977012e-05, + "loss": 1.5946, + "step": 875 + }, + { + "epoch": 0.94, + "learning_rate": 9.370689655172414e-05, + "loss": 1.5695, + "step": 876 + }, + { + "epoch": 0.95, + "learning_rate": 9.369971264367816e-05, + "loss": 1.4992, + "step": 877 + }, + { + "epoch": 0.95, + "learning_rate": 9.369252873563219e-05, + "loss": 1.5713, + "step": 878 + }, + { + "epoch": 0.95, + "learning_rate": 9.368534482758621e-05, + "loss": 1.5074, + "step": 879 + }, + { + "epoch": 0.95, + "learning_rate": 9.367816091954023e-05, + "loss": 1.6129, + "step": 880 + }, + { + "epoch": 0.95, + "learning_rate": 9.367097701149425e-05, + "loss": 1.6247, + "step": 881 + }, + { + "epoch": 0.95, + "learning_rate": 9.366379310344829e-05, + "loss": 1.4352, + "step": 882 + }, + { + "epoch": 0.95, + "learning_rate": 9.365660919540231e-05, + "loss": 1.5264, + "step": 883 + }, + { + "epoch": 0.95, + "learning_rate": 9.364942528735633e-05, + "loss": 1.5686, + "step": 884 + }, + { + "epoch": 0.95, + "learning_rate": 9.364224137931035e-05, + "loss": 1.6303, + "step": 885 + }, + { + "epoch": 0.95, + "learning_rate": 9.363505747126438e-05, + "loss": 1.5117, + "step": 886 + }, + { + "epoch": 0.96, + "learning_rate": 9.362787356321839e-05, + "loss": 1.6003, + "step": 887 + }, + { + "epoch": 0.96, + "learning_rate": 9.362068965517242e-05, + "loss": 1.5778, + "step": 888 + }, + { + "epoch": 0.96, + "learning_rate": 9.361350574712644e-05, + "loss": 1.4555, + "step": 889 + }, + { + "epoch": 0.96, + "learning_rate": 9.360632183908046e-05, + "loss": 1.5057, + "step": 890 + }, + { + "epoch": 0.96, + "learning_rate": 9.359913793103448e-05, + "loss": 1.5419, + "step": 891 + }, + { + "epoch": 0.96, + "learning_rate": 9.359195402298852e-05, + "loss": 1.6326, + "step": 892 + }, + { + "epoch": 0.96, + "learning_rate": 9.358477011494254e-05, + "loss": 1.4839, + "step": 893 + }, + { + "epoch": 0.96, + "learning_rate": 9.357758620689656e-05, + "loss": 1.4438, + "step": 894 + }, + { + "epoch": 0.96, + "learning_rate": 9.357040229885058e-05, + "loss": 1.5228, + "step": 895 + }, + { + "epoch": 0.97, + "learning_rate": 9.35632183908046e-05, + "loss": 1.5877, + "step": 896 + }, + { + "epoch": 0.97, + "learning_rate": 9.355603448275863e-05, + "loss": 1.601, + "step": 897 + }, + { + "epoch": 0.97, + "learning_rate": 9.354885057471264e-05, + "loss": 1.5373, + "step": 898 + }, + { + "epoch": 0.97, + "learning_rate": 9.354166666666667e-05, + "loss": 1.5349, + "step": 899 + }, + { + "epoch": 0.97, + "learning_rate": 9.353448275862069e-05, + "loss": 1.4374, + "step": 900 + }, + { + "epoch": 0.97, + "learning_rate": 9.352729885057471e-05, + "loss": 1.5862, + "step": 901 + }, + { + "epoch": 0.97, + "learning_rate": 9.352011494252873e-05, + "loss": 1.5209, + "step": 902 + }, + { + "epoch": 0.97, + "learning_rate": 9.351293103448277e-05, + "loss": 1.4212, + "step": 903 + }, + { + "epoch": 0.97, + "learning_rate": 9.350574712643679e-05, + "loss": 1.4668, + "step": 904 + }, + { + "epoch": 0.98, + "learning_rate": 9.349856321839081e-05, + "loss": 1.5461, + "step": 905 + }, + { + "epoch": 0.98, + "learning_rate": 9.349137931034483e-05, + "loss": 1.4739, + "step": 906 + }, + { + "epoch": 0.98, + "learning_rate": 9.348419540229886e-05, + "loss": 1.3611, + "step": 907 + }, + { + "epoch": 0.98, + "learning_rate": 9.347701149425287e-05, + "loss": 1.572, + "step": 908 + }, + { + "epoch": 0.98, + "learning_rate": 9.34698275862069e-05, + "loss": 1.3799, + "step": 909 + }, + { + "epoch": 0.98, + "learning_rate": 9.346264367816092e-05, + "loss": 1.468, + "step": 910 + }, + { + "epoch": 0.98, + "learning_rate": 9.345545977011496e-05, + "loss": 1.4859, + "step": 911 + }, + { + "epoch": 0.98, + "learning_rate": 9.344827586206896e-05, + "loss": 1.5521, + "step": 912 + }, + { + "epoch": 0.98, + "learning_rate": 9.3441091954023e-05, + "loss": 1.5032, + "step": 913 + }, + { + "epoch": 0.98, + "learning_rate": 9.343390804597702e-05, + "loss": 1.4978, + "step": 914 + }, + { + "epoch": 0.99, + "learning_rate": 9.342672413793104e-05, + "loss": 1.5997, + "step": 915 + }, + { + "epoch": 0.99, + "learning_rate": 9.341954022988506e-05, + "loss": 1.4763, + "step": 916 + }, + { + "epoch": 0.99, + "learning_rate": 9.341235632183909e-05, + "loss": 1.6007, + "step": 917 + }, + { + "epoch": 0.99, + "learning_rate": 9.340517241379311e-05, + "loss": 1.4255, + "step": 918 + }, + { + "epoch": 0.99, + "learning_rate": 9.339798850574713e-05, + "loss": 1.6812, + "step": 919 + }, + { + "epoch": 0.99, + "learning_rate": 9.339080459770115e-05, + "loss": 1.5859, + "step": 920 + }, + { + "epoch": 0.99, + "learning_rate": 9.338362068965519e-05, + "loss": 1.5098, + "step": 921 + }, + { + "epoch": 0.99, + "learning_rate": 9.33764367816092e-05, + "loss": 1.5437, + "step": 922 + }, + { + "epoch": 0.99, + "learning_rate": 9.336925287356321e-05, + "loss": 1.6254, + "step": 923 + }, + { + "epoch": 1.0, + "learning_rate": 9.336206896551725e-05, + "loss": 1.4907, + "step": 924 + }, + { + "epoch": 1.0, + "learning_rate": 9.335488505747127e-05, + "loss": 1.4065, + "step": 925 + }, + { + "epoch": 1.0, + "learning_rate": 9.334770114942529e-05, + "loss": 1.4974, + "step": 926 + }, + { + "epoch": 1.0, + "learning_rate": 9.334051724137931e-05, + "loss": 1.2799, + "step": 927 + }, + { + "epoch": 1.0, + "learning_rate": 9.333333333333334e-05, + "loss": 1.4336, + "step": 928 + }, + { + "epoch": 1.0, + "learning_rate": 9.332614942528736e-05, + "loss": 1.4368, + "step": 929 + }, + { + "epoch": 1.0, + "learning_rate": 9.331896551724138e-05, + "loss": 1.3628, + "step": 930 + }, + { + "epoch": 1.0, + "learning_rate": 9.33117816091954e-05, + "loss": 1.368, + "step": 931 + }, + { + "epoch": 1.0, + "learning_rate": 9.330459770114944e-05, + "loss": 1.6254, + "step": 932 + }, + { + "epoch": 1.01, + "learning_rate": 9.329741379310344e-05, + "loss": 1.5087, + "step": 933 + }, + { + "epoch": 1.01, + "learning_rate": 9.329022988505748e-05, + "loss": 1.3805, + "step": 934 + }, + { + "epoch": 1.01, + "learning_rate": 9.32830459770115e-05, + "loss": 1.3759, + "step": 935 + }, + { + "epoch": 1.01, + "learning_rate": 9.327586206896552e-05, + "loss": 1.3954, + "step": 936 + }, + { + "epoch": 1.01, + "learning_rate": 9.326867816091954e-05, + "loss": 1.3503, + "step": 937 + }, + { + "epoch": 1.01, + "learning_rate": 9.326149425287357e-05, + "loss": 1.359, + "step": 938 + }, + { + "epoch": 1.01, + "learning_rate": 9.32543103448276e-05, + "loss": 1.433, + "step": 939 + }, + { + "epoch": 1.01, + "learning_rate": 9.324712643678161e-05, + "loss": 1.4088, + "step": 940 + }, + { + "epoch": 1.01, + "learning_rate": 9.323994252873563e-05, + "loss": 1.2375, + "step": 941 + }, + { + "epoch": 1.02, + "learning_rate": 9.323275862068967e-05, + "loss": 1.3418, + "step": 942 + }, + { + "epoch": 1.02, + "learning_rate": 9.322557471264368e-05, + "loss": 1.3579, + "step": 943 + }, + { + "epoch": 1.02, + "learning_rate": 9.321839080459771e-05, + "loss": 1.5596, + "step": 944 + }, + { + "epoch": 1.02, + "learning_rate": 9.321120689655173e-05, + "loss": 1.3729, + "step": 945 + }, + { + "epoch": 1.02, + "learning_rate": 9.320402298850576e-05, + "loss": 1.5689, + "step": 946 + }, + { + "epoch": 1.02, + "learning_rate": 9.319683908045977e-05, + "loss": 1.3989, + "step": 947 + }, + { + "epoch": 1.02, + "learning_rate": 9.318965517241379e-05, + "loss": 1.4159, + "step": 948 + }, + { + "epoch": 1.02, + "learning_rate": 9.318247126436782e-05, + "loss": 1.4714, + "step": 949 + }, + { + "epoch": 1.02, + "learning_rate": 9.317528735632184e-05, + "loss": 1.4553, + "step": 950 + }, + { + "epoch": 1.02, + "learning_rate": 9.316810344827586e-05, + "loss": 1.3799, + "step": 951 + }, + { + "epoch": 1.03, + "learning_rate": 9.316091954022989e-05, + "loss": 1.4451, + "step": 952 + }, + { + "epoch": 1.03, + "learning_rate": 9.315373563218392e-05, + "loss": 1.4166, + "step": 953 + }, + { + "epoch": 1.03, + "learning_rate": 9.314655172413793e-05, + "loss": 1.4545, + "step": 954 + }, + { + "epoch": 1.03, + "learning_rate": 9.313936781609196e-05, + "loss": 1.5023, + "step": 955 + }, + { + "epoch": 1.03, + "learning_rate": 9.313218390804598e-05, + "loss": 1.4376, + "step": 956 + }, + { + "epoch": 1.03, + "learning_rate": 9.3125e-05, + "loss": 1.4761, + "step": 957 + }, + { + "epoch": 1.03, + "learning_rate": 9.311781609195402e-05, + "loss": 1.556, + "step": 958 + }, + { + "epoch": 1.03, + "learning_rate": 9.311063218390805e-05, + "loss": 1.3025, + "step": 959 + }, + { + "epoch": 1.03, + "learning_rate": 9.310344827586207e-05, + "loss": 1.3541, + "step": 960 + }, + { + "epoch": 1.04, + "learning_rate": 9.30962643678161e-05, + "loss": 1.345, + "step": 961 + }, + { + "epoch": 1.04, + "learning_rate": 9.308908045977012e-05, + "loss": 1.4105, + "step": 962 + }, + { + "epoch": 1.04, + "learning_rate": 9.308189655172415e-05, + "loss": 1.3182, + "step": 963 + }, + { + "epoch": 1.04, + "learning_rate": 9.307471264367817e-05, + "loss": 1.4199, + "step": 964 + }, + { + "epoch": 1.04, + "learning_rate": 9.306752873563219e-05, + "loss": 1.5979, + "step": 965 + }, + { + "epoch": 1.04, + "learning_rate": 9.306034482758621e-05, + "loss": 1.5098, + "step": 966 + }, + { + "epoch": 1.04, + "learning_rate": 9.305316091954024e-05, + "loss": 1.3706, + "step": 967 + }, + { + "epoch": 1.04, + "learning_rate": 9.304597701149425e-05, + "loss": 1.6563, + "step": 968 + }, + { + "epoch": 1.04, + "learning_rate": 9.303879310344828e-05, + "loss": 1.4926, + "step": 969 + }, + { + "epoch": 1.05, + "learning_rate": 9.30316091954023e-05, + "loss": 1.2996, + "step": 970 + }, + { + "epoch": 1.05, + "learning_rate": 9.302442528735633e-05, + "loss": 1.5399, + "step": 971 + }, + { + "epoch": 1.05, + "learning_rate": 9.301724137931035e-05, + "loss": 1.3597, + "step": 972 + }, + { + "epoch": 1.05, + "learning_rate": 9.301005747126437e-05, + "loss": 1.4413, + "step": 973 + }, + { + "epoch": 1.05, + "learning_rate": 9.30028735632184e-05, + "loss": 1.5245, + "step": 974 + }, + { + "epoch": 1.05, + "learning_rate": 9.29956896551724e-05, + "loss": 1.5485, + "step": 975 + }, + { + "epoch": 1.05, + "learning_rate": 9.298850574712644e-05, + "loss": 1.4272, + "step": 976 + }, + { + "epoch": 1.05, + "learning_rate": 9.298132183908046e-05, + "loss": 1.4861, + "step": 977 + }, + { + "epoch": 1.05, + "learning_rate": 9.29741379310345e-05, + "loss": 1.3045, + "step": 978 + }, + { + "epoch": 1.05, + "learning_rate": 9.29669540229885e-05, + "loss": 1.4303, + "step": 979 + }, + { + "epoch": 1.06, + "learning_rate": 9.295977011494254e-05, + "loss": 1.3779, + "step": 980 + }, + { + "epoch": 1.06, + "learning_rate": 9.295258620689656e-05, + "loss": 1.4016, + "step": 981 + }, + { + "epoch": 1.06, + "learning_rate": 9.294540229885058e-05, + "loss": 1.4774, + "step": 982 + }, + { + "epoch": 1.06, + "learning_rate": 9.29382183908046e-05, + "loss": 1.4633, + "step": 983 + }, + { + "epoch": 1.06, + "learning_rate": 9.293103448275863e-05, + "loss": 1.5939, + "step": 984 + }, + { + "epoch": 1.06, + "learning_rate": 9.292385057471265e-05, + "loss": 1.5071, + "step": 985 + }, + { + "epoch": 1.06, + "learning_rate": 9.291666666666667e-05, + "loss": 1.4575, + "step": 986 + }, + { + "epoch": 1.06, + "learning_rate": 9.290948275862069e-05, + "loss": 1.3384, + "step": 987 + }, + { + "epoch": 1.06, + "learning_rate": 9.290229885057473e-05, + "loss": 1.5578, + "step": 988 + }, + { + "epoch": 1.07, + "learning_rate": 9.289511494252873e-05, + "loss": 1.5364, + "step": 989 + }, + { + "epoch": 1.07, + "learning_rate": 9.288793103448277e-05, + "loss": 1.425, + "step": 990 + }, + { + "epoch": 1.07, + "learning_rate": 9.288074712643679e-05, + "loss": 1.572, + "step": 991 + }, + { + "epoch": 1.07, + "learning_rate": 9.287356321839082e-05, + "loss": 1.5794, + "step": 992 + }, + { + "epoch": 1.07, + "learning_rate": 9.286637931034483e-05, + "loss": 1.5458, + "step": 993 + }, + { + "epoch": 1.07, + "learning_rate": 9.285919540229886e-05, + "loss": 1.411, + "step": 994 + }, + { + "epoch": 1.07, + "learning_rate": 9.285201149425288e-05, + "loss": 1.4714, + "step": 995 + }, + { + "epoch": 1.07, + "learning_rate": 9.28448275862069e-05, + "loss": 1.4592, + "step": 996 + }, + { + "epoch": 1.07, + "learning_rate": 9.283764367816092e-05, + "loss": 1.4343, + "step": 997 + }, + { + "epoch": 1.08, + "learning_rate": 9.283045977011494e-05, + "loss": 1.5557, + "step": 998 + }, + { + "epoch": 1.08, + "learning_rate": 9.282327586206898e-05, + "loss": 1.6324, + "step": 999 + }, + { + "epoch": 1.08, + "learning_rate": 9.281609195402298e-05, + "loss": 1.2437, + "step": 1000 + }, + { + "epoch": 1.08, + "eval_loss": 1.3301737308502197, + "eval_runtime": 175.1331, + "eval_samples_per_second": 127.16, + "eval_steps_per_second": 0.662, + "step": 1000 + }, + { + "epoch": 1.08, + "learning_rate": 9.280890804597702e-05, + "loss": 1.5929, + "step": 1001 + }, + { + "epoch": 1.08, + "learning_rate": 9.280172413793104e-05, + "loss": 1.4603, + "step": 1002 + }, + { + "epoch": 1.08, + "learning_rate": 9.279454022988506e-05, + "loss": 1.5078, + "step": 1003 + }, + { + "epoch": 1.08, + "learning_rate": 9.278735632183908e-05, + "loss": 1.4235, + "step": 1004 + }, + { + "epoch": 1.08, + "learning_rate": 9.278017241379311e-05, + "loss": 1.4624, + "step": 1005 + }, + { + "epoch": 1.08, + "learning_rate": 9.277298850574713e-05, + "loss": 1.5293, + "step": 1006 + }, + { + "epoch": 1.09, + "learning_rate": 9.276580459770115e-05, + "loss": 1.5707, + "step": 1007 + }, + { + "epoch": 1.09, + "learning_rate": 9.275862068965517e-05, + "loss": 1.4992, + "step": 1008 + }, + { + "epoch": 1.09, + "learning_rate": 9.27514367816092e-05, + "loss": 1.3423, + "step": 1009 + }, + { + "epoch": 1.09, + "learning_rate": 9.274425287356323e-05, + "loss": 1.4057, + "step": 1010 + }, + { + "epoch": 1.09, + "learning_rate": 9.273706896551725e-05, + "loss": 1.5242, + "step": 1011 + }, + { + "epoch": 1.09, + "learning_rate": 9.272988505747127e-05, + "loss": 1.517, + "step": 1012 + }, + { + "epoch": 1.09, + "learning_rate": 9.27227011494253e-05, + "loss": 1.4114, + "step": 1013 + }, + { + "epoch": 1.09, + "learning_rate": 9.271551724137931e-05, + "loss": 1.3813, + "step": 1014 + }, + { + "epoch": 1.09, + "learning_rate": 9.270833333333334e-05, + "loss": 1.2556, + "step": 1015 + }, + { + "epoch": 1.09, + "learning_rate": 9.270114942528736e-05, + "loss": 1.4325, + "step": 1016 + }, + { + "epoch": 1.1, + "learning_rate": 9.269396551724138e-05, + "loss": 1.4785, + "step": 1017 + }, + { + "epoch": 1.1, + "learning_rate": 9.26867816091954e-05, + "loss": 1.425, + "step": 1018 + }, + { + "epoch": 1.1, + "learning_rate": 9.267959770114944e-05, + "loss": 1.5479, + "step": 1019 + }, + { + "epoch": 1.1, + "learning_rate": 9.267241379310346e-05, + "loss": 1.3862, + "step": 1020 + }, + { + "epoch": 1.1, + "learning_rate": 9.266522988505748e-05, + "loss": 1.4246, + "step": 1021 + }, + { + "epoch": 1.1, + "learning_rate": 9.26580459770115e-05, + "loss": 1.489, + "step": 1022 + }, + { + "epoch": 1.1, + "learning_rate": 9.265086206896553e-05, + "loss": 1.4895, + "step": 1023 + }, + { + "epoch": 1.1, + "learning_rate": 9.264367816091954e-05, + "loss": 1.5256, + "step": 1024 + }, + { + "epoch": 1.1, + "learning_rate": 9.263649425287356e-05, + "loss": 1.3855, + "step": 1025 + }, + { + "epoch": 1.11, + "learning_rate": 9.262931034482759e-05, + "loss": 1.5242, + "step": 1026 + }, + { + "epoch": 1.11, + "learning_rate": 9.262212643678161e-05, + "loss": 1.5372, + "step": 1027 + }, + { + "epoch": 1.11, + "learning_rate": 9.261494252873563e-05, + "loss": 1.5231, + "step": 1028 + }, + { + "epoch": 1.11, + "learning_rate": 9.260775862068965e-05, + "loss": 1.3292, + "step": 1029 + }, + { + "epoch": 1.11, + "learning_rate": 9.260057471264369e-05, + "loss": 1.4141, + "step": 1030 + }, + { + "epoch": 1.11, + "learning_rate": 9.259339080459771e-05, + "loss": 1.464, + "step": 1031 + }, + { + "epoch": 1.11, + "learning_rate": 9.258620689655173e-05, + "loss": 1.4668, + "step": 1032 + }, + { + "epoch": 1.11, + "learning_rate": 9.257902298850575e-05, + "loss": 1.5955, + "step": 1033 + }, + { + "epoch": 1.11, + "learning_rate": 9.257183908045978e-05, + "loss": 1.6861, + "step": 1034 + }, + { + "epoch": 1.12, + "learning_rate": 9.256465517241379e-05, + "loss": 1.3352, + "step": 1035 + }, + { + "epoch": 1.12, + "learning_rate": 9.255747126436782e-05, + "loss": 1.6471, + "step": 1036 + }, + { + "epoch": 1.12, + "learning_rate": 9.255028735632184e-05, + "loss": 1.4975, + "step": 1037 + }, + { + "epoch": 1.12, + "learning_rate": 9.254310344827586e-05, + "loss": 1.4802, + "step": 1038 + }, + { + "epoch": 1.12, + "learning_rate": 9.253591954022988e-05, + "loss": 1.5387, + "step": 1039 + }, + { + "epoch": 1.12, + "learning_rate": 9.252873563218392e-05, + "loss": 1.4515, + "step": 1040 + }, + { + "epoch": 1.12, + "learning_rate": 9.252155172413794e-05, + "loss": 1.4487, + "step": 1041 + }, + { + "epoch": 1.12, + "learning_rate": 9.251436781609196e-05, + "loss": 1.4784, + "step": 1042 + }, + { + "epoch": 1.12, + "learning_rate": 9.250718390804598e-05, + "loss": 1.4138, + "step": 1043 + }, + { + "epoch": 1.12, + "learning_rate": 9.250000000000001e-05, + "loss": 1.4082, + "step": 1044 + }, + { + "epoch": 1.13, + "learning_rate": 9.249281609195403e-05, + "loss": 1.4212, + "step": 1045 + }, + { + "epoch": 1.13, + "learning_rate": 9.248563218390805e-05, + "loss": 1.4772, + "step": 1046 + }, + { + "epoch": 1.13, + "learning_rate": 9.247844827586207e-05, + "loss": 1.3741, + "step": 1047 + }, + { + "epoch": 1.13, + "learning_rate": 9.247126436781611e-05, + "loss": 1.5511, + "step": 1048 + }, + { + "epoch": 1.13, + "learning_rate": 9.246408045977011e-05, + "loss": 1.4227, + "step": 1049 + }, + { + "epoch": 1.13, + "learning_rate": 9.245689655172413e-05, + "loss": 1.2405, + "step": 1050 + }, + { + "epoch": 1.13, + "learning_rate": 9.244971264367817e-05, + "loss": 1.5107, + "step": 1051 + }, + { + "epoch": 1.13, + "learning_rate": 9.244252873563219e-05, + "loss": 1.4599, + "step": 1052 + }, + { + "epoch": 1.13, + "learning_rate": 9.243534482758621e-05, + "loss": 1.554, + "step": 1053 + }, + { + "epoch": 1.14, + "learning_rate": 9.242816091954023e-05, + "loss": 1.443, + "step": 1054 + }, + { + "epoch": 1.14, + "learning_rate": 9.242097701149426e-05, + "loss": 1.5501, + "step": 1055 + }, + { + "epoch": 1.14, + "learning_rate": 9.241379310344827e-05, + "loss": 1.4234, + "step": 1056 + }, + { + "epoch": 1.14, + "learning_rate": 9.24066091954023e-05, + "loss": 1.4639, + "step": 1057 + }, + { + "epoch": 1.14, + "learning_rate": 9.239942528735632e-05, + "loss": 1.4896, + "step": 1058 + }, + { + "epoch": 1.14, + "learning_rate": 9.239224137931036e-05, + "loss": 1.4753, + "step": 1059 + }, + { + "epoch": 1.14, + "learning_rate": 9.238505747126436e-05, + "loss": 1.4881, + "step": 1060 + }, + { + "epoch": 1.14, + "learning_rate": 9.23778735632184e-05, + "loss": 1.3279, + "step": 1061 + }, + { + "epoch": 1.14, + "learning_rate": 9.237068965517242e-05, + "loss": 1.4328, + "step": 1062 + }, + { + "epoch": 1.15, + "learning_rate": 9.236350574712644e-05, + "loss": 1.4994, + "step": 1063 + }, + { + "epoch": 1.15, + "learning_rate": 9.235632183908046e-05, + "loss": 1.4555, + "step": 1064 + }, + { + "epoch": 1.15, + "learning_rate": 9.234913793103449e-05, + "loss": 1.3189, + "step": 1065 + }, + { + "epoch": 1.15, + "learning_rate": 9.234195402298851e-05, + "loss": 1.4349, + "step": 1066 + }, + { + "epoch": 1.15, + "learning_rate": 9.233477011494253e-05, + "loss": 1.3758, + "step": 1067 + }, + { + "epoch": 1.15, + "learning_rate": 9.232758620689655e-05, + "loss": 1.4617, + "step": 1068 + }, + { + "epoch": 1.15, + "learning_rate": 9.232040229885059e-05, + "loss": 1.3844, + "step": 1069 + }, + { + "epoch": 1.15, + "learning_rate": 9.23132183908046e-05, + "loss": 1.4931, + "step": 1070 + }, + { + "epoch": 1.15, + "learning_rate": 9.230603448275863e-05, + "loss": 1.5209, + "step": 1071 + }, + { + "epoch": 1.16, + "learning_rate": 9.229885057471265e-05, + "loss": 1.4421, + "step": 1072 + }, + { + "epoch": 1.16, + "learning_rate": 9.229166666666668e-05, + "loss": 1.5218, + "step": 1073 + }, + { + "epoch": 1.16, + "learning_rate": 9.228448275862069e-05, + "loss": 1.3788, + "step": 1074 + }, + { + "epoch": 1.16, + "learning_rate": 9.227729885057471e-05, + "loss": 1.4677, + "step": 1075 + }, + { + "epoch": 1.16, + "learning_rate": 9.227011494252874e-05, + "loss": 1.2418, + "step": 1076 + }, + { + "epoch": 1.16, + "learning_rate": 9.226293103448276e-05, + "loss": 1.3719, + "step": 1077 + }, + { + "epoch": 1.16, + "learning_rate": 9.225574712643678e-05, + "loss": 1.5089, + "step": 1078 + }, + { + "epoch": 1.16, + "learning_rate": 9.22485632183908e-05, + "loss": 1.4764, + "step": 1079 + }, + { + "epoch": 1.16, + "learning_rate": 9.224137931034484e-05, + "loss": 1.6048, + "step": 1080 + }, + { + "epoch": 1.16, + "learning_rate": 9.223419540229885e-05, + "loss": 1.4412, + "step": 1081 + }, + { + "epoch": 1.17, + "learning_rate": 9.222701149425288e-05, + "loss": 1.4499, + "step": 1082 + }, + { + "epoch": 1.17, + "learning_rate": 9.22198275862069e-05, + "loss": 1.4286, + "step": 1083 + }, + { + "epoch": 1.17, + "learning_rate": 9.221264367816092e-05, + "loss": 1.4138, + "step": 1084 + }, + { + "epoch": 1.17, + "learning_rate": 9.220545977011494e-05, + "loss": 1.3374, + "step": 1085 + }, + { + "epoch": 1.17, + "learning_rate": 9.219827586206897e-05, + "loss": 1.3949, + "step": 1086 + }, + { + "epoch": 1.17, + "learning_rate": 9.2191091954023e-05, + "loss": 1.3121, + "step": 1087 + }, + { + "epoch": 1.17, + "learning_rate": 9.218390804597701e-05, + "loss": 1.4405, + "step": 1088 + }, + { + "epoch": 1.17, + "learning_rate": 9.217672413793104e-05, + "loss": 1.5512, + "step": 1089 + }, + { + "epoch": 1.17, + "learning_rate": 9.216954022988507e-05, + "loss": 1.5643, + "step": 1090 + }, + { + "epoch": 1.18, + "learning_rate": 9.216235632183909e-05, + "loss": 1.4087, + "step": 1091 + }, + { + "epoch": 1.18, + "learning_rate": 9.215517241379311e-05, + "loss": 1.3514, + "step": 1092 + }, + { + "epoch": 1.18, + "learning_rate": 9.214798850574713e-05, + "loss": 1.4481, + "step": 1093 + }, + { + "epoch": 1.18, + "learning_rate": 9.214080459770116e-05, + "loss": 1.4632, + "step": 1094 + }, + { + "epoch": 1.18, + "learning_rate": 9.213362068965517e-05, + "loss": 1.4347, + "step": 1095 + }, + { + "epoch": 1.18, + "learning_rate": 9.21264367816092e-05, + "loss": 1.4646, + "step": 1096 + }, + { + "epoch": 1.18, + "learning_rate": 9.211925287356322e-05, + "loss": 1.4266, + "step": 1097 + }, + { + "epoch": 1.18, + "learning_rate": 9.211206896551725e-05, + "loss": 1.544, + "step": 1098 + }, + { + "epoch": 1.18, + "learning_rate": 9.210488505747127e-05, + "loss": 1.4576, + "step": 1099 + }, + { + "epoch": 1.19, + "learning_rate": 9.20977011494253e-05, + "loss": 1.6108, + "step": 1100 + }, + { + "epoch": 1.19, + "learning_rate": 9.209051724137932e-05, + "loss": 1.5788, + "step": 1101 + }, + { + "epoch": 1.19, + "learning_rate": 9.208333333333333e-05, + "loss": 1.4562, + "step": 1102 + }, + { + "epoch": 1.19, + "learning_rate": 9.207614942528736e-05, + "loss": 1.2948, + "step": 1103 + }, + { + "epoch": 1.19, + "learning_rate": 9.206896551724138e-05, + "loss": 1.3794, + "step": 1104 + }, + { + "epoch": 1.19, + "learning_rate": 9.206178160919541e-05, + "loss": 1.4898, + "step": 1105 + }, + { + "epoch": 1.19, + "learning_rate": 9.205459770114942e-05, + "loss": 1.52, + "step": 1106 + }, + { + "epoch": 1.19, + "learning_rate": 9.204741379310346e-05, + "loss": 1.6075, + "step": 1107 + }, + { + "epoch": 1.19, + "learning_rate": 9.204022988505748e-05, + "loss": 1.4248, + "step": 1108 + }, + { + "epoch": 1.2, + "learning_rate": 9.20330459770115e-05, + "loss": 1.5089, + "step": 1109 + }, + { + "epoch": 1.2, + "learning_rate": 9.202586206896552e-05, + "loss": 1.3976, + "step": 1110 + }, + { + "epoch": 1.2, + "learning_rate": 9.201867816091955e-05, + "loss": 1.5369, + "step": 1111 + }, + { + "epoch": 1.2, + "learning_rate": 9.201149425287357e-05, + "loss": 1.4875, + "step": 1112 + }, + { + "epoch": 1.2, + "learning_rate": 9.200431034482759e-05, + "loss": 1.4769, + "step": 1113 + }, + { + "epoch": 1.2, + "learning_rate": 9.199712643678161e-05, + "loss": 1.371, + "step": 1114 + }, + { + "epoch": 1.2, + "learning_rate": 9.198994252873564e-05, + "loss": 1.4461, + "step": 1115 + }, + { + "epoch": 1.2, + "learning_rate": 9.198275862068965e-05, + "loss": 1.4361, + "step": 1116 + }, + { + "epoch": 1.2, + "learning_rate": 9.197557471264369e-05, + "loss": 1.412, + "step": 1117 + }, + { + "epoch": 1.2, + "learning_rate": 9.19683908045977e-05, + "loss": 1.46, + "step": 1118 + }, + { + "epoch": 1.21, + "learning_rate": 9.196120689655173e-05, + "loss": 1.4132, + "step": 1119 + }, + { + "epoch": 1.21, + "learning_rate": 9.195402298850575e-05, + "loss": 1.4992, + "step": 1120 + }, + { + "epoch": 1.21, + "learning_rate": 9.194683908045978e-05, + "loss": 1.5052, + "step": 1121 + }, + { + "epoch": 1.21, + "learning_rate": 9.19396551724138e-05, + "loss": 1.3421, + "step": 1122 + }, + { + "epoch": 1.21, + "learning_rate": 9.193247126436782e-05, + "loss": 1.6031, + "step": 1123 + }, + { + "epoch": 1.21, + "learning_rate": 9.192528735632184e-05, + "loss": 1.5445, + "step": 1124 + }, + { + "epoch": 1.21, + "learning_rate": 9.191810344827588e-05, + "loss": 1.4264, + "step": 1125 + }, + { + "epoch": 1.21, + "learning_rate": 9.19109195402299e-05, + "loss": 1.607, + "step": 1126 + }, + { + "epoch": 1.21, + "learning_rate": 9.19037356321839e-05, + "loss": 1.4763, + "step": 1127 + }, + { + "epoch": 1.22, + "learning_rate": 9.189655172413794e-05, + "loss": 1.4555, + "step": 1128 + }, + { + "epoch": 1.22, + "learning_rate": 9.188936781609196e-05, + "loss": 1.354, + "step": 1129 + }, + { + "epoch": 1.22, + "learning_rate": 9.188218390804598e-05, + "loss": 1.4525, + "step": 1130 + }, + { + "epoch": 1.22, + "learning_rate": 9.1875e-05, + "loss": 1.4431, + "step": 1131 + }, + { + "epoch": 1.22, + "learning_rate": 9.186781609195403e-05, + "loss": 1.5217, + "step": 1132 + }, + { + "epoch": 1.22, + "learning_rate": 9.186063218390805e-05, + "loss": 1.3548, + "step": 1133 + }, + { + "epoch": 1.22, + "learning_rate": 9.185344827586207e-05, + "loss": 1.4512, + "step": 1134 + }, + { + "epoch": 1.22, + "learning_rate": 9.184626436781609e-05, + "loss": 1.5786, + "step": 1135 + }, + { + "epoch": 1.22, + "learning_rate": 9.183908045977013e-05, + "loss": 1.4408, + "step": 1136 + }, + { + "epoch": 1.23, + "learning_rate": 9.183189655172413e-05, + "loss": 1.4634, + "step": 1137 + }, + { + "epoch": 1.23, + "learning_rate": 9.182471264367817e-05, + "loss": 1.5375, + "step": 1138 + }, + { + "epoch": 1.23, + "learning_rate": 9.181752873563219e-05, + "loss": 1.6085, + "step": 1139 + }, + { + "epoch": 1.23, + "learning_rate": 9.181034482758622e-05, + "loss": 1.4221, + "step": 1140 + }, + { + "epoch": 1.23, + "learning_rate": 9.180316091954023e-05, + "loss": 1.4979, + "step": 1141 + }, + { + "epoch": 1.23, + "learning_rate": 9.179597701149426e-05, + "loss": 1.3817, + "step": 1142 + }, + { + "epoch": 1.23, + "learning_rate": 9.178879310344828e-05, + "loss": 1.4116, + "step": 1143 + }, + { + "epoch": 1.23, + "learning_rate": 9.17816091954023e-05, + "loss": 1.4554, + "step": 1144 + }, + { + "epoch": 1.23, + "learning_rate": 9.177442528735632e-05, + "loss": 1.317, + "step": 1145 + }, + { + "epoch": 1.23, + "learning_rate": 9.176724137931036e-05, + "loss": 1.4451, + "step": 1146 + }, + { + "epoch": 1.24, + "learning_rate": 9.176005747126438e-05, + "loss": 1.4504, + "step": 1147 + }, + { + "epoch": 1.24, + "learning_rate": 9.17528735632184e-05, + "loss": 1.5818, + "step": 1148 + }, + { + "epoch": 1.24, + "learning_rate": 9.174568965517242e-05, + "loss": 1.4968, + "step": 1149 + }, + { + "epoch": 1.24, + "learning_rate": 9.173850574712645e-05, + "loss": 1.4095, + "step": 1150 + }, + { + "epoch": 1.24, + "learning_rate": 9.173132183908046e-05, + "loss": 1.5121, + "step": 1151 + }, + { + "epoch": 1.24, + "learning_rate": 9.172413793103448e-05, + "loss": 1.5123, + "step": 1152 + }, + { + "epoch": 1.24, + "learning_rate": 9.171695402298851e-05, + "loss": 1.4187, + "step": 1153 + }, + { + "epoch": 1.24, + "learning_rate": 9.170977011494253e-05, + "loss": 1.376, + "step": 1154 + }, + { + "epoch": 1.24, + "learning_rate": 9.170258620689655e-05, + "loss": 1.5094, + "step": 1155 + }, + { + "epoch": 1.25, + "learning_rate": 9.169540229885057e-05, + "loss": 1.3832, + "step": 1156 + }, + { + "epoch": 1.25, + "learning_rate": 9.16882183908046e-05, + "loss": 1.5259, + "step": 1157 + }, + { + "epoch": 1.25, + "learning_rate": 9.168103448275863e-05, + "loss": 1.4222, + "step": 1158 + }, + { + "epoch": 1.25, + "learning_rate": 9.167385057471265e-05, + "loss": 1.4657, + "step": 1159 + }, + { + "epoch": 1.25, + "learning_rate": 9.166666666666667e-05, + "loss": 1.3756, + "step": 1160 + }, + { + "epoch": 1.25, + "learning_rate": 9.16594827586207e-05, + "loss": 1.4908, + "step": 1161 + }, + { + "epoch": 1.25, + "learning_rate": 9.165229885057471e-05, + "loss": 1.5054, + "step": 1162 + }, + { + "epoch": 1.25, + "learning_rate": 9.164511494252874e-05, + "loss": 1.4346, + "step": 1163 + }, + { + "epoch": 1.25, + "learning_rate": 9.163793103448276e-05, + "loss": 1.5154, + "step": 1164 + }, + { + "epoch": 1.26, + "learning_rate": 9.163074712643678e-05, + "loss": 1.4344, + "step": 1165 + }, + { + "epoch": 1.26, + "learning_rate": 9.16235632183908e-05, + "loss": 1.5225, + "step": 1166 + }, + { + "epoch": 1.26, + "learning_rate": 9.161637931034484e-05, + "loss": 1.3334, + "step": 1167 + }, + { + "epoch": 1.26, + "learning_rate": 9.160919540229886e-05, + "loss": 1.311, + "step": 1168 + }, + { + "epoch": 1.26, + "learning_rate": 9.160201149425288e-05, + "loss": 1.2998, + "step": 1169 + }, + { + "epoch": 1.26, + "learning_rate": 9.15948275862069e-05, + "loss": 1.2665, + "step": 1170 + }, + { + "epoch": 1.26, + "learning_rate": 9.158764367816093e-05, + "loss": 1.2956, + "step": 1171 + }, + { + "epoch": 1.26, + "learning_rate": 9.158045977011495e-05, + "loss": 1.3024, + "step": 1172 + }, + { + "epoch": 1.26, + "learning_rate": 9.157327586206897e-05, + "loss": 1.3895, + "step": 1173 + }, + { + "epoch": 1.27, + "learning_rate": 9.156609195402299e-05, + "loss": 1.6706, + "step": 1174 + }, + { + "epoch": 1.27, + "learning_rate": 9.155890804597703e-05, + "loss": 1.4813, + "step": 1175 + }, + { + "epoch": 1.27, + "learning_rate": 9.155172413793103e-05, + "loss": 1.3175, + "step": 1176 + }, + { + "epoch": 1.27, + "learning_rate": 9.154454022988507e-05, + "loss": 1.4444, + "step": 1177 + }, + { + "epoch": 1.27, + "learning_rate": 9.153735632183909e-05, + "loss": 1.3397, + "step": 1178 + }, + { + "epoch": 1.27, + "learning_rate": 9.153017241379311e-05, + "loss": 1.5772, + "step": 1179 + }, + { + "epoch": 1.27, + "learning_rate": 9.152298850574713e-05, + "loss": 1.5516, + "step": 1180 + }, + { + "epoch": 1.27, + "learning_rate": 9.151580459770115e-05, + "loss": 1.5331, + "step": 1181 + }, + { + "epoch": 1.27, + "learning_rate": 9.150862068965518e-05, + "loss": 1.5218, + "step": 1182 + }, + { + "epoch": 1.27, + "learning_rate": 9.150143678160919e-05, + "loss": 1.3901, + "step": 1183 + }, + { + "epoch": 1.28, + "learning_rate": 9.149425287356322e-05, + "loss": 1.5617, + "step": 1184 + }, + { + "epoch": 1.28, + "learning_rate": 9.148706896551724e-05, + "loss": 1.5349, + "step": 1185 + }, + { + "epoch": 1.28, + "learning_rate": 9.147988505747128e-05, + "loss": 1.4885, + "step": 1186 + }, + { + "epoch": 1.28, + "learning_rate": 9.147270114942528e-05, + "loss": 1.3938, + "step": 1187 + }, + { + "epoch": 1.28, + "learning_rate": 9.146551724137932e-05, + "loss": 1.5149, + "step": 1188 + }, + { + "epoch": 1.28, + "learning_rate": 9.145833333333334e-05, + "loss": 1.2119, + "step": 1189 + }, + { + "epoch": 1.28, + "learning_rate": 9.145114942528736e-05, + "loss": 1.5539, + "step": 1190 + }, + { + "epoch": 1.28, + "learning_rate": 9.144396551724138e-05, + "loss": 1.512, + "step": 1191 + }, + { + "epoch": 1.28, + "learning_rate": 9.143678160919541e-05, + "loss": 1.3977, + "step": 1192 + }, + { + "epoch": 1.29, + "learning_rate": 9.142959770114943e-05, + "loss": 1.3444, + "step": 1193 + }, + { + "epoch": 1.29, + "learning_rate": 9.142241379310345e-05, + "loss": 1.4627, + "step": 1194 + }, + { + "epoch": 1.29, + "learning_rate": 9.141522988505747e-05, + "loss": 1.4136, + "step": 1195 + }, + { + "epoch": 1.29, + "learning_rate": 9.140804597701151e-05, + "loss": 1.5238, + "step": 1196 + }, + { + "epoch": 1.29, + "learning_rate": 9.140086206896551e-05, + "loss": 1.2261, + "step": 1197 + }, + { + "epoch": 1.29, + "learning_rate": 9.139367816091955e-05, + "loss": 1.4373, + "step": 1198 + }, + { + "epoch": 1.29, + "learning_rate": 9.138649425287357e-05, + "loss": 1.4041, + "step": 1199 + }, + { + "epoch": 1.29, + "learning_rate": 9.137931034482759e-05, + "loss": 1.526, + "step": 1200 + }, + { + "epoch": 1.29, + "learning_rate": 9.137212643678161e-05, + "loss": 1.5108, + "step": 1201 + }, + { + "epoch": 1.3, + "learning_rate": 9.136494252873564e-05, + "loss": 1.3327, + "step": 1202 + }, + { + "epoch": 1.3, + "learning_rate": 9.135775862068966e-05, + "loss": 1.4855, + "step": 1203 + }, + { + "epoch": 1.3, + "learning_rate": 9.135057471264368e-05, + "loss": 1.4506, + "step": 1204 + }, + { + "epoch": 1.3, + "learning_rate": 9.13433908045977e-05, + "loss": 1.4036, + "step": 1205 + }, + { + "epoch": 1.3, + "learning_rate": 9.133620689655172e-05, + "loss": 1.3744, + "step": 1206 + }, + { + "epoch": 1.3, + "learning_rate": 9.132902298850576e-05, + "loss": 1.4166, + "step": 1207 + }, + { + "epoch": 1.3, + "learning_rate": 9.132183908045977e-05, + "loss": 1.3709, + "step": 1208 + }, + { + "epoch": 1.3, + "learning_rate": 9.13146551724138e-05, + "loss": 1.3784, + "step": 1209 + }, + { + "epoch": 1.3, + "learning_rate": 9.130747126436782e-05, + "loss": 1.5239, + "step": 1210 + }, + { + "epoch": 1.3, + "learning_rate": 9.130028735632184e-05, + "loss": 1.3849, + "step": 1211 + }, + { + "epoch": 1.31, + "learning_rate": 9.129310344827586e-05, + "loss": 1.5548, + "step": 1212 + }, + { + "epoch": 1.31, + "learning_rate": 9.12859195402299e-05, + "loss": 1.477, + "step": 1213 + }, + { + "epoch": 1.31, + "learning_rate": 9.127873563218391e-05, + "loss": 1.6591, + "step": 1214 + }, + { + "epoch": 1.31, + "learning_rate": 9.127155172413793e-05, + "loss": 1.2952, + "step": 1215 + }, + { + "epoch": 1.31, + "learning_rate": 9.126436781609195e-05, + "loss": 1.4211, + "step": 1216 + }, + { + "epoch": 1.31, + "learning_rate": 9.125718390804599e-05, + "loss": 1.399, + "step": 1217 + }, + { + "epoch": 1.31, + "learning_rate": 9.125e-05, + "loss": 1.5205, + "step": 1218 + }, + { + "epoch": 1.31, + "learning_rate": 9.124281609195403e-05, + "loss": 1.5311, + "step": 1219 + }, + { + "epoch": 1.31, + "learning_rate": 9.123563218390805e-05, + "loss": 1.4929, + "step": 1220 + }, + { + "epoch": 1.32, + "learning_rate": 9.122844827586208e-05, + "loss": 1.51, + "step": 1221 + }, + { + "epoch": 1.32, + "learning_rate": 9.122126436781609e-05, + "loss": 1.4232, + "step": 1222 + }, + { + "epoch": 1.32, + "learning_rate": 9.121408045977012e-05, + "loss": 1.5338, + "step": 1223 + }, + { + "epoch": 1.32, + "learning_rate": 9.120689655172414e-05, + "loss": 1.4282, + "step": 1224 + }, + { + "epoch": 1.32, + "learning_rate": 9.119971264367816e-05, + "loss": 1.6039, + "step": 1225 + }, + { + "epoch": 1.32, + "learning_rate": 9.119252873563219e-05, + "loss": 1.5641, + "step": 1226 + }, + { + "epoch": 1.32, + "learning_rate": 9.118534482758622e-05, + "loss": 1.3681, + "step": 1227 + }, + { + "epoch": 1.32, + "learning_rate": 9.117816091954024e-05, + "loss": 1.4473, + "step": 1228 + }, + { + "epoch": 1.32, + "learning_rate": 9.117097701149425e-05, + "loss": 1.4021, + "step": 1229 + }, + { + "epoch": 1.33, + "learning_rate": 9.116379310344828e-05, + "loss": 1.4757, + "step": 1230 + }, + { + "epoch": 1.33, + "learning_rate": 9.11566091954023e-05, + "loss": 1.5302, + "step": 1231 + }, + { + "epoch": 1.33, + "learning_rate": 9.114942528735632e-05, + "loss": 1.5966, + "step": 1232 + }, + { + "epoch": 1.33, + "learning_rate": 9.114224137931034e-05, + "loss": 1.3647, + "step": 1233 + }, + { + "epoch": 1.33, + "learning_rate": 9.113505747126437e-05, + "loss": 1.3676, + "step": 1234 + }, + { + "epoch": 1.33, + "learning_rate": 9.11278735632184e-05, + "loss": 1.4118, + "step": 1235 + }, + { + "epoch": 1.33, + "learning_rate": 9.112068965517242e-05, + "loss": 1.4265, + "step": 1236 + }, + { + "epoch": 1.33, + "learning_rate": 9.111350574712644e-05, + "loss": 1.5343, + "step": 1237 + }, + { + "epoch": 1.33, + "learning_rate": 9.110632183908047e-05, + "loss": 1.2603, + "step": 1238 + }, + { + "epoch": 1.34, + "learning_rate": 9.109913793103449e-05, + "loss": 1.2256, + "step": 1239 + }, + { + "epoch": 1.34, + "learning_rate": 9.109195402298851e-05, + "loss": 1.3417, + "step": 1240 + }, + { + "epoch": 1.34, + "learning_rate": 9.108477011494253e-05, + "loss": 1.4666, + "step": 1241 + }, + { + "epoch": 1.34, + "learning_rate": 9.107758620689656e-05, + "loss": 1.4671, + "step": 1242 + }, + { + "epoch": 1.34, + "learning_rate": 9.107040229885057e-05, + "loss": 1.3937, + "step": 1243 + }, + { + "epoch": 1.34, + "learning_rate": 9.10632183908046e-05, + "loss": 1.451, + "step": 1244 + }, + { + "epoch": 1.34, + "learning_rate": 9.105603448275863e-05, + "loss": 1.3396, + "step": 1245 + }, + { + "epoch": 1.34, + "learning_rate": 9.104885057471265e-05, + "loss": 1.5134, + "step": 1246 + }, + { + "epoch": 1.34, + "learning_rate": 9.104166666666667e-05, + "loss": 1.5019, + "step": 1247 + }, + { + "epoch": 1.34, + "learning_rate": 9.10344827586207e-05, + "loss": 1.4636, + "step": 1248 + }, + { + "epoch": 1.35, + "learning_rate": 9.102729885057472e-05, + "loss": 1.2136, + "step": 1249 + }, + { + "epoch": 1.35, + "learning_rate": 9.102011494252874e-05, + "loss": 1.3242, + "step": 1250 + }, + { + "epoch": 1.35, + "eval_loss": 1.2909470796585083, + "eval_runtime": 177.0697, + "eval_samples_per_second": 125.77, + "eval_steps_per_second": 0.655, + "step": 1250 + }, + { + "epoch": 1.35, + "learning_rate": 9.101293103448276e-05, + "loss": 1.4686, + "step": 1251 + }, + { + "epoch": 1.35, + "learning_rate": 9.10057471264368e-05, + "loss": 1.6025, + "step": 1252 + }, + { + "epoch": 1.35, + "learning_rate": 9.099856321839082e-05, + "loss": 1.3744, + "step": 1253 + }, + { + "epoch": 1.35, + "learning_rate": 9.099137931034482e-05, + "loss": 1.5315, + "step": 1254 + }, + { + "epoch": 1.35, + "learning_rate": 9.098419540229886e-05, + "loss": 1.3637, + "step": 1255 + }, + { + "epoch": 1.35, + "learning_rate": 9.097701149425288e-05, + "loss": 1.3692, + "step": 1256 + }, + { + "epoch": 1.35, + "learning_rate": 9.09698275862069e-05, + "loss": 1.6454, + "step": 1257 + }, + { + "epoch": 1.36, + "learning_rate": 9.096264367816092e-05, + "loss": 1.4928, + "step": 1258 + }, + { + "epoch": 1.36, + "learning_rate": 9.095545977011495e-05, + "loss": 1.3934, + "step": 1259 + }, + { + "epoch": 1.36, + "learning_rate": 9.094827586206897e-05, + "loss": 1.4991, + "step": 1260 + }, + { + "epoch": 1.36, + "learning_rate": 9.094109195402299e-05, + "loss": 1.4768, + "step": 1261 + }, + { + "epoch": 1.36, + "learning_rate": 9.093390804597701e-05, + "loss": 1.4018, + "step": 1262 + }, + { + "epoch": 1.36, + "learning_rate": 9.092672413793105e-05, + "loss": 1.455, + "step": 1263 + }, + { + "epoch": 1.36, + "learning_rate": 9.091954022988505e-05, + "loss": 1.4082, + "step": 1264 + }, + { + "epoch": 1.36, + "learning_rate": 9.091235632183909e-05, + "loss": 1.4935, + "step": 1265 + }, + { + "epoch": 1.36, + "learning_rate": 9.09051724137931e-05, + "loss": 1.4035, + "step": 1266 + }, + { + "epoch": 1.37, + "learning_rate": 9.089798850574714e-05, + "loss": 1.2811, + "step": 1267 + }, + { + "epoch": 1.37, + "learning_rate": 9.089080459770115e-05, + "loss": 1.3477, + "step": 1268 + }, + { + "epoch": 1.37, + "learning_rate": 9.088362068965518e-05, + "loss": 1.5295, + "step": 1269 + }, + { + "epoch": 1.37, + "learning_rate": 9.08764367816092e-05, + "loss": 1.4722, + "step": 1270 + }, + { + "epoch": 1.37, + "learning_rate": 9.086925287356322e-05, + "loss": 1.4295, + "step": 1271 + }, + { + "epoch": 1.37, + "learning_rate": 9.086206896551724e-05, + "loss": 1.4282, + "step": 1272 + }, + { + "epoch": 1.37, + "learning_rate": 9.085488505747128e-05, + "loss": 1.491, + "step": 1273 + }, + { + "epoch": 1.37, + "learning_rate": 9.08477011494253e-05, + "loss": 1.4615, + "step": 1274 + }, + { + "epoch": 1.37, + "learning_rate": 9.084051724137932e-05, + "loss": 1.482, + "step": 1275 + }, + { + "epoch": 1.38, + "learning_rate": 9.083333333333334e-05, + "loss": 1.2898, + "step": 1276 + }, + { + "epoch": 1.38, + "learning_rate": 9.082614942528737e-05, + "loss": 1.5514, + "step": 1277 + }, + { + "epoch": 1.38, + "learning_rate": 9.081896551724138e-05, + "loss": 1.4273, + "step": 1278 + }, + { + "epoch": 1.38, + "learning_rate": 9.081178160919541e-05, + "loss": 1.4274, + "step": 1279 + }, + { + "epoch": 1.38, + "learning_rate": 9.080459770114943e-05, + "loss": 1.4766, + "step": 1280 + }, + { + "epoch": 1.38, + "learning_rate": 9.079741379310345e-05, + "loss": 1.2937, + "step": 1281 + }, + { + "epoch": 1.38, + "learning_rate": 9.079022988505747e-05, + "loss": 1.4587, + "step": 1282 + }, + { + "epoch": 1.38, + "learning_rate": 9.078304597701149e-05, + "loss": 1.3383, + "step": 1283 + }, + { + "epoch": 1.38, + "learning_rate": 9.077586206896553e-05, + "loss": 1.3151, + "step": 1284 + }, + { + "epoch": 1.38, + "learning_rate": 9.076867816091955e-05, + "loss": 1.3269, + "step": 1285 + }, + { + "epoch": 1.39, + "learning_rate": 9.076149425287357e-05, + "loss": 1.4119, + "step": 1286 + }, + { + "epoch": 1.39, + "learning_rate": 9.075431034482759e-05, + "loss": 1.4009, + "step": 1287 + }, + { + "epoch": 1.39, + "learning_rate": 9.074712643678162e-05, + "loss": 1.3423, + "step": 1288 + }, + { + "epoch": 1.39, + "learning_rate": 9.073994252873563e-05, + "loss": 1.3103, + "step": 1289 + }, + { + "epoch": 1.39, + "learning_rate": 9.073275862068966e-05, + "loss": 1.4122, + "step": 1290 + }, + { + "epoch": 1.39, + "learning_rate": 9.072557471264368e-05, + "loss": 1.2902, + "step": 1291 + }, + { + "epoch": 1.39, + "learning_rate": 9.07183908045977e-05, + "loss": 1.3803, + "step": 1292 + }, + { + "epoch": 1.39, + "learning_rate": 9.071120689655172e-05, + "loss": 1.3644, + "step": 1293 + }, + { + "epoch": 1.39, + "learning_rate": 9.070402298850576e-05, + "loss": 1.3242, + "step": 1294 + }, + { + "epoch": 1.4, + "learning_rate": 9.069683908045978e-05, + "loss": 1.5297, + "step": 1295 + }, + { + "epoch": 1.4, + "learning_rate": 9.06896551724138e-05, + "loss": 1.4694, + "step": 1296 + }, + { + "epoch": 1.4, + "learning_rate": 9.068247126436782e-05, + "loss": 1.3208, + "step": 1297 + }, + { + "epoch": 1.4, + "learning_rate": 9.067528735632185e-05, + "loss": 1.4376, + "step": 1298 + }, + { + "epoch": 1.4, + "learning_rate": 9.066810344827587e-05, + "loss": 1.5103, + "step": 1299 + }, + { + "epoch": 1.4, + "learning_rate": 9.066091954022989e-05, + "loss": 1.3953, + "step": 1300 + }, + { + "epoch": 1.4, + "learning_rate": 9.065373563218391e-05, + "loss": 1.4144, + "step": 1301 + }, + { + "epoch": 1.4, + "learning_rate": 9.064655172413795e-05, + "loss": 1.4021, + "step": 1302 + }, + { + "epoch": 1.4, + "learning_rate": 9.063936781609195e-05, + "loss": 1.3711, + "step": 1303 + }, + { + "epoch": 1.41, + "learning_rate": 9.063218390804599e-05, + "loss": 1.3413, + "step": 1304 + }, + { + "epoch": 1.41, + "learning_rate": 9.062500000000001e-05, + "loss": 1.6885, + "step": 1305 + }, + { + "epoch": 1.41, + "learning_rate": 9.061781609195403e-05, + "loss": 1.3736, + "step": 1306 + }, + { + "epoch": 1.41, + "learning_rate": 9.061063218390805e-05, + "loss": 1.3856, + "step": 1307 + }, + { + "epoch": 1.41, + "learning_rate": 9.060344827586207e-05, + "loss": 1.2398, + "step": 1308 + }, + { + "epoch": 1.41, + "learning_rate": 9.05962643678161e-05, + "loss": 1.3059, + "step": 1309 + }, + { + "epoch": 1.41, + "learning_rate": 9.058908045977011e-05, + "loss": 1.4594, + "step": 1310 + }, + { + "epoch": 1.41, + "learning_rate": 9.058189655172414e-05, + "loss": 1.5647, + "step": 1311 + }, + { + "epoch": 1.41, + "learning_rate": 9.057471264367816e-05, + "loss": 1.3783, + "step": 1312 + }, + { + "epoch": 1.41, + "learning_rate": 9.056752873563218e-05, + "loss": 1.4477, + "step": 1313 + }, + { + "epoch": 1.42, + "learning_rate": 9.05603448275862e-05, + "loss": 1.2302, + "step": 1314 + }, + { + "epoch": 1.42, + "learning_rate": 9.055316091954024e-05, + "loss": 1.3961, + "step": 1315 + }, + { + "epoch": 1.42, + "learning_rate": 9.054597701149426e-05, + "loss": 1.355, + "step": 1316 + }, + { + "epoch": 1.42, + "learning_rate": 9.053879310344828e-05, + "loss": 1.4255, + "step": 1317 + }, + { + "epoch": 1.42, + "learning_rate": 9.05316091954023e-05, + "loss": 1.522, + "step": 1318 + }, + { + "epoch": 1.42, + "learning_rate": 9.052442528735633e-05, + "loss": 1.2667, + "step": 1319 + }, + { + "epoch": 1.42, + "learning_rate": 9.051724137931035e-05, + "loss": 1.5569, + "step": 1320 + }, + { + "epoch": 1.42, + "learning_rate": 9.051005747126437e-05, + "loss": 1.5152, + "step": 1321 + }, + { + "epoch": 1.42, + "learning_rate": 9.05028735632184e-05, + "loss": 1.5297, + "step": 1322 + }, + { + "epoch": 1.43, + "learning_rate": 9.049568965517243e-05, + "loss": 1.3628, + "step": 1323 + }, + { + "epoch": 1.43, + "learning_rate": 9.048850574712643e-05, + "loss": 1.3159, + "step": 1324 + }, + { + "epoch": 1.43, + "learning_rate": 9.048132183908047e-05, + "loss": 1.3625, + "step": 1325 + }, + { + "epoch": 1.43, + "learning_rate": 9.047413793103449e-05, + "loss": 1.4356, + "step": 1326 + }, + { + "epoch": 1.43, + "learning_rate": 9.046695402298851e-05, + "loss": 1.319, + "step": 1327 + }, + { + "epoch": 1.43, + "learning_rate": 9.045977011494253e-05, + "loss": 1.4656, + "step": 1328 + }, + { + "epoch": 1.43, + "learning_rate": 9.045258620689656e-05, + "loss": 1.5057, + "step": 1329 + }, + { + "epoch": 1.43, + "learning_rate": 9.044540229885058e-05, + "loss": 1.4322, + "step": 1330 + }, + { + "epoch": 1.43, + "learning_rate": 9.043821839080459e-05, + "loss": 1.6262, + "step": 1331 + }, + { + "epoch": 1.44, + "learning_rate": 9.043103448275862e-05, + "loss": 1.3764, + "step": 1332 + }, + { + "epoch": 1.44, + "learning_rate": 9.042385057471264e-05, + "loss": 1.4636, + "step": 1333 + }, + { + "epoch": 1.44, + "learning_rate": 9.041666666666668e-05, + "loss": 1.494, + "step": 1334 + }, + { + "epoch": 1.44, + "learning_rate": 9.040948275862068e-05, + "loss": 1.4044, + "step": 1335 + }, + { + "epoch": 1.44, + "learning_rate": 9.040229885057472e-05, + "loss": 1.2633, + "step": 1336 + }, + { + "epoch": 1.44, + "learning_rate": 9.039511494252874e-05, + "loss": 1.3541, + "step": 1337 + }, + { + "epoch": 1.44, + "learning_rate": 9.038793103448276e-05, + "loss": 1.5027, + "step": 1338 + }, + { + "epoch": 1.44, + "learning_rate": 9.038074712643678e-05, + "loss": 1.4187, + "step": 1339 + }, + { + "epoch": 1.44, + "learning_rate": 9.037356321839081e-05, + "loss": 1.401, + "step": 1340 + }, + { + "epoch": 1.45, + "learning_rate": 9.036637931034483e-05, + "loss": 1.4683, + "step": 1341 + }, + { + "epoch": 1.45, + "learning_rate": 9.035919540229885e-05, + "loss": 1.3602, + "step": 1342 + }, + { + "epoch": 1.45, + "learning_rate": 9.035201149425287e-05, + "loss": 1.5967, + "step": 1343 + }, + { + "epoch": 1.45, + "learning_rate": 9.034482758620691e-05, + "loss": 1.2882, + "step": 1344 + }, + { + "epoch": 1.45, + "learning_rate": 9.033764367816092e-05, + "loss": 1.3922, + "step": 1345 + }, + { + "epoch": 1.45, + "learning_rate": 9.033045977011495e-05, + "loss": 1.2384, + "step": 1346 + }, + { + "epoch": 1.45, + "learning_rate": 9.032327586206897e-05, + "loss": 1.4727, + "step": 1347 + }, + { + "epoch": 1.45, + "learning_rate": 9.0316091954023e-05, + "loss": 1.2859, + "step": 1348 + }, + { + "epoch": 1.45, + "learning_rate": 9.030890804597701e-05, + "loss": 1.3084, + "step": 1349 + }, + { + "epoch": 1.45, + "learning_rate": 9.030172413793104e-05, + "loss": 1.4549, + "step": 1350 + }, + { + "epoch": 1.46, + "learning_rate": 9.029454022988506e-05, + "loss": 1.3485, + "step": 1351 + }, + { + "epoch": 1.46, + "learning_rate": 9.028735632183908e-05, + "loss": 1.3475, + "step": 1352 + }, + { + "epoch": 1.46, + "learning_rate": 9.02801724137931e-05, + "loss": 1.5141, + "step": 1353 + }, + { + "epoch": 1.46, + "learning_rate": 9.027298850574714e-05, + "loss": 1.5303, + "step": 1354 + }, + { + "epoch": 1.46, + "learning_rate": 9.026580459770116e-05, + "loss": 1.4964, + "step": 1355 + }, + { + "epoch": 1.46, + "learning_rate": 9.025862068965518e-05, + "loss": 1.4403, + "step": 1356 + }, + { + "epoch": 1.46, + "learning_rate": 9.02514367816092e-05, + "loss": 1.5104, + "step": 1357 + }, + { + "epoch": 1.46, + "learning_rate": 9.024425287356322e-05, + "loss": 1.3934, + "step": 1358 + }, + { + "epoch": 1.46, + "learning_rate": 9.023706896551724e-05, + "loss": 1.4699, + "step": 1359 + }, + { + "epoch": 1.47, + "learning_rate": 9.022988505747126e-05, + "loss": 1.3453, + "step": 1360 + }, + { + "epoch": 1.47, + "learning_rate": 9.02227011494253e-05, + "loss": 1.3543, + "step": 1361 + }, + { + "epoch": 1.47, + "learning_rate": 9.021551724137931e-05, + "loss": 1.5285, + "step": 1362 + }, + { + "epoch": 1.47, + "learning_rate": 9.020833333333334e-05, + "loss": 1.3661, + "step": 1363 + }, + { + "epoch": 1.47, + "learning_rate": 9.020114942528736e-05, + "loss": 1.358, + "step": 1364 + }, + { + "epoch": 1.47, + "learning_rate": 9.019396551724139e-05, + "loss": 1.3179, + "step": 1365 + }, + { + "epoch": 1.47, + "learning_rate": 9.018678160919541e-05, + "loss": 1.4702, + "step": 1366 + }, + { + "epoch": 1.47, + "learning_rate": 9.017959770114943e-05, + "loss": 1.3871, + "step": 1367 + }, + { + "epoch": 1.47, + "learning_rate": 9.017241379310345e-05, + "loss": 1.5121, + "step": 1368 + }, + { + "epoch": 1.48, + "learning_rate": 9.016522988505748e-05, + "loss": 1.3397, + "step": 1369 + }, + { + "epoch": 1.48, + "learning_rate": 9.015804597701149e-05, + "loss": 1.4944, + "step": 1370 + }, + { + "epoch": 1.48, + "learning_rate": 9.015086206896552e-05, + "loss": 1.4577, + "step": 1371 + }, + { + "epoch": 1.48, + "learning_rate": 9.014367816091955e-05, + "loss": 1.4595, + "step": 1372 + }, + { + "epoch": 1.48, + "learning_rate": 9.013649425287357e-05, + "loss": 1.3335, + "step": 1373 + }, + { + "epoch": 1.48, + "learning_rate": 9.012931034482759e-05, + "loss": 1.3315, + "step": 1374 + }, + { + "epoch": 1.48, + "learning_rate": 9.012212643678162e-05, + "loss": 1.3824, + "step": 1375 + }, + { + "epoch": 1.48, + "learning_rate": 9.011494252873564e-05, + "loss": 1.3391, + "step": 1376 + }, + { + "epoch": 1.48, + "learning_rate": 9.010775862068966e-05, + "loss": 1.3594, + "step": 1377 + }, + { + "epoch": 1.48, + "learning_rate": 9.010057471264368e-05, + "loss": 1.3991, + "step": 1378 + }, + { + "epoch": 1.49, + "learning_rate": 9.009339080459771e-05, + "loss": 1.4877, + "step": 1379 + }, + { + "epoch": 1.49, + "learning_rate": 9.008620689655173e-05, + "loss": 1.3522, + "step": 1380 + }, + { + "epoch": 1.49, + "learning_rate": 9.007902298850576e-05, + "loss": 1.4826, + "step": 1381 + }, + { + "epoch": 1.49, + "learning_rate": 9.007183908045978e-05, + "loss": 1.396, + "step": 1382 + }, + { + "epoch": 1.49, + "learning_rate": 9.00646551724138e-05, + "loss": 1.4315, + "step": 1383 + }, + { + "epoch": 1.49, + "learning_rate": 9.005747126436782e-05, + "loss": 1.4619, + "step": 1384 + }, + { + "epoch": 1.49, + "learning_rate": 9.005028735632184e-05, + "loss": 1.4531, + "step": 1385 + }, + { + "epoch": 1.49, + "learning_rate": 9.004310344827587e-05, + "loss": 1.3182, + "step": 1386 + }, + { + "epoch": 1.49, + "learning_rate": 9.003591954022989e-05, + "loss": 1.4203, + "step": 1387 + }, + { + "epoch": 1.5, + "learning_rate": 9.002873563218391e-05, + "loss": 1.2644, + "step": 1388 + }, + { + "epoch": 1.5, + "learning_rate": 9.002155172413793e-05, + "loss": 1.3368, + "step": 1389 + }, + { + "epoch": 1.5, + "learning_rate": 9.001436781609197e-05, + "loss": 1.4404, + "step": 1390 + }, + { + "epoch": 1.5, + "learning_rate": 9.000718390804597e-05, + "loss": 1.3544, + "step": 1391 + }, + { + "epoch": 1.5, + "learning_rate": 9e-05, + "loss": 1.4659, + "step": 1392 + }, + { + "epoch": 1.5, + "learning_rate": 8.999281609195403e-05, + "loss": 1.4787, + "step": 1393 + }, + { + "epoch": 1.5, + "learning_rate": 8.998563218390805e-05, + "loss": 1.4552, + "step": 1394 + }, + { + "epoch": 1.5, + "learning_rate": 8.997844827586207e-05, + "loss": 1.425, + "step": 1395 + }, + { + "epoch": 1.5, + "learning_rate": 8.99712643678161e-05, + "loss": 1.5911, + "step": 1396 + }, + { + "epoch": 1.51, + "learning_rate": 8.996408045977012e-05, + "loss": 1.4386, + "step": 1397 + }, + { + "epoch": 1.51, + "learning_rate": 8.995689655172414e-05, + "loss": 1.3529, + "step": 1398 + }, + { + "epoch": 1.51, + "learning_rate": 8.994971264367816e-05, + "loss": 1.5533, + "step": 1399 + }, + { + "epoch": 1.51, + "learning_rate": 8.99425287356322e-05, + "loss": 1.2747, + "step": 1400 + }, + { + "epoch": 1.51, + "learning_rate": 8.993534482758622e-05, + "loss": 1.4004, + "step": 1401 + }, + { + "epoch": 1.51, + "learning_rate": 8.992816091954024e-05, + "loss": 1.2937, + "step": 1402 + }, + { + "epoch": 1.51, + "learning_rate": 8.992097701149426e-05, + "loss": 1.6039, + "step": 1403 + }, + { + "epoch": 1.51, + "learning_rate": 8.991379310344829e-05, + "loss": 1.47, + "step": 1404 + }, + { + "epoch": 1.51, + "learning_rate": 8.99066091954023e-05, + "loss": 1.4178, + "step": 1405 + }, + { + "epoch": 1.52, + "learning_rate": 8.989942528735633e-05, + "loss": 1.3329, + "step": 1406 + }, + { + "epoch": 1.52, + "learning_rate": 8.989224137931035e-05, + "loss": 1.4894, + "step": 1407 + }, + { + "epoch": 1.52, + "learning_rate": 8.988505747126437e-05, + "loss": 1.3958, + "step": 1408 + }, + { + "epoch": 1.52, + "learning_rate": 8.987787356321839e-05, + "loss": 1.3342, + "step": 1409 + }, + { + "epoch": 1.52, + "learning_rate": 8.987068965517241e-05, + "loss": 1.56, + "step": 1410 + }, + { + "epoch": 1.52, + "learning_rate": 8.986350574712645e-05, + "loss": 1.4997, + "step": 1411 + }, + { + "epoch": 1.52, + "learning_rate": 8.985632183908047e-05, + "loss": 1.4553, + "step": 1412 + }, + { + "epoch": 1.52, + "learning_rate": 8.984913793103449e-05, + "loss": 1.393, + "step": 1413 + }, + { + "epoch": 1.52, + "learning_rate": 8.984195402298851e-05, + "loss": 1.4572, + "step": 1414 + }, + { + "epoch": 1.52, + "learning_rate": 8.983477011494254e-05, + "loss": 1.5006, + "step": 1415 + }, + { + "epoch": 1.53, + "learning_rate": 8.982758620689655e-05, + "loss": 1.4153, + "step": 1416 + }, + { + "epoch": 1.53, + "learning_rate": 8.982040229885058e-05, + "loss": 1.3469, + "step": 1417 + }, + { + "epoch": 1.53, + "learning_rate": 8.98132183908046e-05, + "loss": 1.3578, + "step": 1418 + }, + { + "epoch": 1.53, + "learning_rate": 8.980603448275862e-05, + "loss": 1.3775, + "step": 1419 + }, + { + "epoch": 1.53, + "learning_rate": 8.979885057471264e-05, + "loss": 1.5725, + "step": 1420 + }, + { + "epoch": 1.53, + "learning_rate": 8.979166666666668e-05, + "loss": 1.3016, + "step": 1421 + }, + { + "epoch": 1.53, + "learning_rate": 8.97844827586207e-05, + "loss": 1.3063, + "step": 1422 + }, + { + "epoch": 1.53, + "learning_rate": 8.977729885057472e-05, + "loss": 1.3819, + "step": 1423 + }, + { + "epoch": 1.53, + "learning_rate": 8.977011494252874e-05, + "loss": 1.5237, + "step": 1424 + }, + { + "epoch": 1.54, + "learning_rate": 8.976293103448277e-05, + "loss": 1.4311, + "step": 1425 + }, + { + "epoch": 1.54, + "learning_rate": 8.975574712643678e-05, + "loss": 1.2634, + "step": 1426 + }, + { + "epoch": 1.54, + "learning_rate": 8.974856321839081e-05, + "loss": 1.2938, + "step": 1427 + }, + { + "epoch": 1.54, + "learning_rate": 8.974137931034483e-05, + "loss": 1.4306, + "step": 1428 + }, + { + "epoch": 1.54, + "learning_rate": 8.973419540229887e-05, + "loss": 1.3823, + "step": 1429 + }, + { + "epoch": 1.54, + "learning_rate": 8.972701149425287e-05, + "loss": 1.4579, + "step": 1430 + }, + { + "epoch": 1.54, + "learning_rate": 8.97198275862069e-05, + "loss": 1.3593, + "step": 1431 + }, + { + "epoch": 1.54, + "learning_rate": 8.971264367816093e-05, + "loss": 1.4871, + "step": 1432 + }, + { + "epoch": 1.54, + "learning_rate": 8.970545977011495e-05, + "loss": 1.43, + "step": 1433 + }, + { + "epoch": 1.55, + "learning_rate": 8.969827586206897e-05, + "loss": 1.387, + "step": 1434 + }, + { + "epoch": 1.55, + "learning_rate": 8.969109195402299e-05, + "loss": 1.318, + "step": 1435 + }, + { + "epoch": 1.55, + "learning_rate": 8.968390804597702e-05, + "loss": 1.3257, + "step": 1436 + }, + { + "epoch": 1.55, + "learning_rate": 8.967672413793103e-05, + "loss": 1.41, + "step": 1437 + }, + { + "epoch": 1.55, + "learning_rate": 8.966954022988506e-05, + "loss": 1.4196, + "step": 1438 + }, + { + "epoch": 1.55, + "learning_rate": 8.966235632183908e-05, + "loss": 1.3716, + "step": 1439 + }, + { + "epoch": 1.55, + "learning_rate": 8.96551724137931e-05, + "loss": 1.2954, + "step": 1440 + }, + { + "epoch": 1.55, + "learning_rate": 8.964798850574712e-05, + "loss": 1.3865, + "step": 1441 + }, + { + "epoch": 1.55, + "learning_rate": 8.964080459770116e-05, + "loss": 1.4545, + "step": 1442 + }, + { + "epoch": 1.55, + "learning_rate": 8.963362068965518e-05, + "loss": 1.3842, + "step": 1443 + }, + { + "epoch": 1.56, + "learning_rate": 8.96264367816092e-05, + "loss": 1.353, + "step": 1444 + }, + { + "epoch": 1.56, + "learning_rate": 8.961925287356322e-05, + "loss": 1.4777, + "step": 1445 + }, + { + "epoch": 1.56, + "learning_rate": 8.961206896551725e-05, + "loss": 1.4625, + "step": 1446 + }, + { + "epoch": 1.56, + "learning_rate": 8.960488505747127e-05, + "loss": 1.3655, + "step": 1447 + }, + { + "epoch": 1.56, + "learning_rate": 8.959770114942529e-05, + "loss": 1.3577, + "step": 1448 + }, + { + "epoch": 1.56, + "learning_rate": 8.959051724137931e-05, + "loss": 1.4654, + "step": 1449 + }, + { + "epoch": 1.56, + "learning_rate": 8.958333333333335e-05, + "loss": 1.403, + "step": 1450 + }, + { + "epoch": 1.56, + "learning_rate": 8.957614942528735e-05, + "loss": 1.4697, + "step": 1451 + }, + { + "epoch": 1.56, + "learning_rate": 8.956896551724139e-05, + "loss": 1.3141, + "step": 1452 + }, + { + "epoch": 1.57, + "learning_rate": 8.956178160919541e-05, + "loss": 1.3902, + "step": 1453 + }, + { + "epoch": 1.57, + "learning_rate": 8.955459770114943e-05, + "loss": 1.4785, + "step": 1454 + }, + { + "epoch": 1.57, + "learning_rate": 8.954741379310345e-05, + "loss": 1.3883, + "step": 1455 + }, + { + "epoch": 1.57, + "learning_rate": 8.954022988505748e-05, + "loss": 1.483, + "step": 1456 + }, + { + "epoch": 1.57, + "learning_rate": 8.95330459770115e-05, + "loss": 1.2954, + "step": 1457 + }, + { + "epoch": 1.57, + "learning_rate": 8.952586206896552e-05, + "loss": 1.3724, + "step": 1458 + }, + { + "epoch": 1.57, + "learning_rate": 8.951867816091954e-05, + "loss": 1.3271, + "step": 1459 + }, + { + "epoch": 1.57, + "learning_rate": 8.951149425287356e-05, + "loss": 1.3686, + "step": 1460 + }, + { + "epoch": 1.57, + "learning_rate": 8.95043103448276e-05, + "loss": 1.4315, + "step": 1461 + }, + { + "epoch": 1.58, + "learning_rate": 8.94971264367816e-05, + "loss": 1.3159, + "step": 1462 + }, + { + "epoch": 1.58, + "learning_rate": 8.948994252873564e-05, + "loss": 1.3727, + "step": 1463 + }, + { + "epoch": 1.58, + "learning_rate": 8.948275862068966e-05, + "loss": 1.2696, + "step": 1464 + }, + { + "epoch": 1.58, + "learning_rate": 8.947557471264368e-05, + "loss": 1.3887, + "step": 1465 + }, + { + "epoch": 1.58, + "learning_rate": 8.94683908045977e-05, + "loss": 1.5024, + "step": 1466 + }, + { + "epoch": 1.58, + "learning_rate": 8.946120689655173e-05, + "loss": 1.4797, + "step": 1467 + }, + { + "epoch": 1.58, + "learning_rate": 8.945402298850575e-05, + "loss": 1.3433, + "step": 1468 + }, + { + "epoch": 1.58, + "learning_rate": 8.944683908045977e-05, + "loss": 1.4649, + "step": 1469 + }, + { + "epoch": 1.58, + "learning_rate": 8.94396551724138e-05, + "loss": 1.3969, + "step": 1470 + }, + { + "epoch": 1.59, + "learning_rate": 8.943247126436783e-05, + "loss": 1.4491, + "step": 1471 + }, + { + "epoch": 1.59, + "learning_rate": 8.942528735632183e-05, + "loss": 1.1891, + "step": 1472 + }, + { + "epoch": 1.59, + "learning_rate": 8.941810344827587e-05, + "loss": 1.3077, + "step": 1473 + }, + { + "epoch": 1.59, + "learning_rate": 8.941091954022989e-05, + "loss": 1.3393, + "step": 1474 + }, + { + "epoch": 1.59, + "learning_rate": 8.940373563218391e-05, + "loss": 1.3018, + "step": 1475 + }, + { + "epoch": 1.59, + "learning_rate": 8.939655172413793e-05, + "loss": 1.3387, + "step": 1476 + }, + { + "epoch": 1.59, + "learning_rate": 8.938936781609196e-05, + "loss": 1.3829, + "step": 1477 + }, + { + "epoch": 1.59, + "learning_rate": 8.938218390804598e-05, + "loss": 1.3859, + "step": 1478 + }, + { + "epoch": 1.59, + "learning_rate": 8.9375e-05, + "loss": 1.3881, + "step": 1479 + }, + { + "epoch": 1.59, + "learning_rate": 8.936781609195402e-05, + "loss": 1.5317, + "step": 1480 + }, + { + "epoch": 1.6, + "learning_rate": 8.936063218390806e-05, + "loss": 1.4221, + "step": 1481 + }, + { + "epoch": 1.6, + "learning_rate": 8.935344827586208e-05, + "loss": 1.2462, + "step": 1482 + }, + { + "epoch": 1.6, + "learning_rate": 8.93462643678161e-05, + "loss": 1.3449, + "step": 1483 + }, + { + "epoch": 1.6, + "learning_rate": 8.933908045977012e-05, + "loss": 1.2913, + "step": 1484 + }, + { + "epoch": 1.6, + "learning_rate": 8.933189655172414e-05, + "loss": 1.2757, + "step": 1485 + }, + { + "epoch": 1.6, + "learning_rate": 8.932471264367816e-05, + "loss": 1.4442, + "step": 1486 + }, + { + "epoch": 1.6, + "learning_rate": 8.931752873563218e-05, + "loss": 1.4098, + "step": 1487 + }, + { + "epoch": 1.6, + "learning_rate": 8.931034482758621e-05, + "loss": 1.4197, + "step": 1488 + }, + { + "epoch": 1.6, + "learning_rate": 8.930316091954023e-05, + "loss": 1.3052, + "step": 1489 + }, + { + "epoch": 1.61, + "learning_rate": 8.929597701149425e-05, + "loss": 1.4233, + "step": 1490 + }, + { + "epoch": 1.61, + "learning_rate": 8.928879310344827e-05, + "loss": 1.4516, + "step": 1491 + }, + { + "epoch": 1.61, + "learning_rate": 8.928160919540231e-05, + "loss": 1.3994, + "step": 1492 + }, + { + "epoch": 1.61, + "learning_rate": 8.927442528735633e-05, + "loss": 1.4072, + "step": 1493 + }, + { + "epoch": 1.61, + "learning_rate": 8.926724137931035e-05, + "loss": 1.3088, + "step": 1494 + }, + { + "epoch": 1.61, + "learning_rate": 8.926005747126437e-05, + "loss": 1.3607, + "step": 1495 + }, + { + "epoch": 1.61, + "learning_rate": 8.92528735632184e-05, + "loss": 1.3299, + "step": 1496 + }, + { + "epoch": 1.61, + "learning_rate": 8.924568965517241e-05, + "loss": 1.3159, + "step": 1497 + }, + { + "epoch": 1.61, + "learning_rate": 8.923850574712644e-05, + "loss": 1.3702, + "step": 1498 + }, + { + "epoch": 1.62, + "learning_rate": 8.923132183908046e-05, + "loss": 1.4197, + "step": 1499 + }, + { + "epoch": 1.62, + "learning_rate": 8.922413793103448e-05, + "loss": 1.3328, + "step": 1500 + }, + { + "epoch": 1.62, + "eval_loss": 1.2589794397354126, + "eval_runtime": 177.0874, + "eval_samples_per_second": 125.757, + "eval_steps_per_second": 0.655, + "step": 1500 + }, + { + "epoch": 1.62, + "learning_rate": 8.92169540229885e-05, + "loss": 1.3265, + "step": 1501 + }, + { + "epoch": 1.62, + "learning_rate": 8.920977011494254e-05, + "loss": 1.3425, + "step": 1502 + }, + { + "epoch": 1.62, + "learning_rate": 8.920258620689656e-05, + "loss": 1.4413, + "step": 1503 + }, + { + "epoch": 1.62, + "learning_rate": 8.919540229885058e-05, + "loss": 1.205, + "step": 1504 + }, + { + "epoch": 1.62, + "learning_rate": 8.91882183908046e-05, + "loss": 1.3931, + "step": 1505 + }, + { + "epoch": 1.62, + "learning_rate": 8.918103448275863e-05, + "loss": 1.3921, + "step": 1506 + }, + { + "epoch": 1.62, + "learning_rate": 8.917385057471264e-05, + "loss": 1.4956, + "step": 1507 + }, + { + "epoch": 1.62, + "learning_rate": 8.916666666666667e-05, + "loss": 1.3997, + "step": 1508 + }, + { + "epoch": 1.63, + "learning_rate": 8.91594827586207e-05, + "loss": 1.5622, + "step": 1509 + }, + { + "epoch": 1.63, + "learning_rate": 8.915229885057472e-05, + "loss": 1.3711, + "step": 1510 + }, + { + "epoch": 1.63, + "learning_rate": 8.914511494252874e-05, + "loss": 1.4249, + "step": 1511 + }, + { + "epoch": 1.63, + "learning_rate": 8.913793103448276e-05, + "loss": 1.4199, + "step": 1512 + }, + { + "epoch": 1.63, + "learning_rate": 8.913074712643679e-05, + "loss": 1.5126, + "step": 1513 + }, + { + "epoch": 1.63, + "learning_rate": 8.912356321839081e-05, + "loss": 1.2625, + "step": 1514 + }, + { + "epoch": 1.63, + "learning_rate": 8.911637931034483e-05, + "loss": 1.504, + "step": 1515 + }, + { + "epoch": 1.63, + "learning_rate": 8.910919540229885e-05, + "loss": 1.3772, + "step": 1516 + }, + { + "epoch": 1.63, + "learning_rate": 8.910201149425288e-05, + "loss": 1.4032, + "step": 1517 + }, + { + "epoch": 1.64, + "learning_rate": 8.909482758620689e-05, + "loss": 1.4863, + "step": 1518 + }, + { + "epoch": 1.64, + "learning_rate": 8.908764367816093e-05, + "loss": 1.2737, + "step": 1519 + }, + { + "epoch": 1.64, + "learning_rate": 8.908045977011495e-05, + "loss": 1.2577, + "step": 1520 + }, + { + "epoch": 1.64, + "learning_rate": 8.907327586206897e-05, + "loss": 1.4286, + "step": 1521 + }, + { + "epoch": 1.64, + "learning_rate": 8.906609195402299e-05, + "loss": 1.3594, + "step": 1522 + }, + { + "epoch": 1.64, + "learning_rate": 8.905890804597702e-05, + "loss": 1.3774, + "step": 1523 + }, + { + "epoch": 1.64, + "learning_rate": 8.905172413793104e-05, + "loss": 1.4339, + "step": 1524 + }, + { + "epoch": 1.64, + "learning_rate": 8.904454022988506e-05, + "loss": 1.413, + "step": 1525 + }, + { + "epoch": 1.64, + "learning_rate": 8.903735632183908e-05, + "loss": 1.3159, + "step": 1526 + }, + { + "epoch": 1.65, + "learning_rate": 8.903017241379311e-05, + "loss": 1.4205, + "step": 1527 + }, + { + "epoch": 1.65, + "learning_rate": 8.902298850574714e-05, + "loss": 1.3645, + "step": 1528 + }, + { + "epoch": 1.65, + "learning_rate": 8.901580459770116e-05, + "loss": 1.3138, + "step": 1529 + }, + { + "epoch": 1.65, + "learning_rate": 8.900862068965518e-05, + "loss": 1.4426, + "step": 1530 + }, + { + "epoch": 1.65, + "learning_rate": 8.900143678160921e-05, + "loss": 1.3324, + "step": 1531 + }, + { + "epoch": 1.65, + "learning_rate": 8.899425287356322e-05, + "loss": 1.2608, + "step": 1532 + }, + { + "epoch": 1.65, + "learning_rate": 8.898706896551725e-05, + "loss": 1.3263, + "step": 1533 + }, + { + "epoch": 1.65, + "learning_rate": 8.897988505747127e-05, + "loss": 1.405, + "step": 1534 + }, + { + "epoch": 1.65, + "learning_rate": 8.897270114942529e-05, + "loss": 1.4355, + "step": 1535 + }, + { + "epoch": 1.66, + "learning_rate": 8.896551724137931e-05, + "loss": 1.4778, + "step": 1536 + }, + { + "epoch": 1.66, + "learning_rate": 8.895833333333333e-05, + "loss": 1.3459, + "step": 1537 + }, + { + "epoch": 1.66, + "learning_rate": 8.895114942528737e-05, + "loss": 1.3244, + "step": 1538 + }, + { + "epoch": 1.66, + "learning_rate": 8.894396551724137e-05, + "loss": 1.4334, + "step": 1539 + }, + { + "epoch": 1.66, + "learning_rate": 8.89367816091954e-05, + "loss": 1.2527, + "step": 1540 + }, + { + "epoch": 1.66, + "learning_rate": 8.892959770114943e-05, + "loss": 1.405, + "step": 1541 + }, + { + "epoch": 1.66, + "learning_rate": 8.892241379310346e-05, + "loss": 1.4752, + "step": 1542 + }, + { + "epoch": 1.66, + "learning_rate": 8.891522988505747e-05, + "loss": 1.327, + "step": 1543 + }, + { + "epoch": 1.66, + "learning_rate": 8.89080459770115e-05, + "loss": 1.332, + "step": 1544 + }, + { + "epoch": 1.66, + "learning_rate": 8.890086206896552e-05, + "loss": 1.358, + "step": 1545 + }, + { + "epoch": 1.67, + "learning_rate": 8.889367816091954e-05, + "loss": 1.4574, + "step": 1546 + }, + { + "epoch": 1.67, + "learning_rate": 8.888649425287356e-05, + "loss": 1.3887, + "step": 1547 + }, + { + "epoch": 1.67, + "learning_rate": 8.88793103448276e-05, + "loss": 1.3533, + "step": 1548 + }, + { + "epoch": 1.67, + "learning_rate": 8.887212643678162e-05, + "loss": 1.4977, + "step": 1549 + }, + { + "epoch": 1.67, + "learning_rate": 8.886494252873564e-05, + "loss": 1.2965, + "step": 1550 + }, + { + "epoch": 1.67, + "learning_rate": 8.885775862068966e-05, + "loss": 1.4918, + "step": 1551 + }, + { + "epoch": 1.67, + "learning_rate": 8.885057471264369e-05, + "loss": 1.2913, + "step": 1552 + }, + { + "epoch": 1.67, + "learning_rate": 8.88433908045977e-05, + "loss": 1.404, + "step": 1553 + }, + { + "epoch": 1.67, + "learning_rate": 8.883620689655173e-05, + "loss": 1.3876, + "step": 1554 + }, + { + "epoch": 1.68, + "learning_rate": 8.882902298850575e-05, + "loss": 1.3712, + "step": 1555 + }, + { + "epoch": 1.68, + "learning_rate": 8.882183908045979e-05, + "loss": 1.3134, + "step": 1556 + }, + { + "epoch": 1.68, + "learning_rate": 8.881465517241379e-05, + "loss": 1.4034, + "step": 1557 + }, + { + "epoch": 1.68, + "learning_rate": 8.880747126436783e-05, + "loss": 1.3985, + "step": 1558 + }, + { + "epoch": 1.68, + "learning_rate": 8.880028735632185e-05, + "loss": 1.3243, + "step": 1559 + }, + { + "epoch": 1.68, + "learning_rate": 8.879310344827587e-05, + "loss": 1.4042, + "step": 1560 + }, + { + "epoch": 1.68, + "learning_rate": 8.878591954022989e-05, + "loss": 1.3516, + "step": 1561 + }, + { + "epoch": 1.68, + "learning_rate": 8.877873563218391e-05, + "loss": 1.3522, + "step": 1562 + }, + { + "epoch": 1.68, + "learning_rate": 8.877155172413794e-05, + "loss": 1.5283, + "step": 1563 + }, + { + "epoch": 1.69, + "learning_rate": 8.876436781609195e-05, + "loss": 1.3364, + "step": 1564 + }, + { + "epoch": 1.69, + "learning_rate": 8.875718390804598e-05, + "loss": 1.4186, + "step": 1565 + }, + { + "epoch": 1.69, + "learning_rate": 8.875e-05, + "loss": 1.3337, + "step": 1566 + }, + { + "epoch": 1.69, + "learning_rate": 8.874281609195402e-05, + "loss": 1.3191, + "step": 1567 + }, + { + "epoch": 1.69, + "learning_rate": 8.873563218390804e-05, + "loss": 1.3096, + "step": 1568 + }, + { + "epoch": 1.69, + "learning_rate": 8.872844827586208e-05, + "loss": 1.2038, + "step": 1569 + }, + { + "epoch": 1.69, + "learning_rate": 8.87212643678161e-05, + "loss": 1.4247, + "step": 1570 + }, + { + "epoch": 1.69, + "learning_rate": 8.871408045977012e-05, + "loss": 1.312, + "step": 1571 + }, + { + "epoch": 1.69, + "learning_rate": 8.870689655172414e-05, + "loss": 1.3681, + "step": 1572 + }, + { + "epoch": 1.7, + "learning_rate": 8.869971264367817e-05, + "loss": 1.3969, + "step": 1573 + }, + { + "epoch": 1.7, + "learning_rate": 8.869252873563219e-05, + "loss": 1.3964, + "step": 1574 + }, + { + "epoch": 1.7, + "learning_rate": 8.868534482758621e-05, + "loss": 1.4088, + "step": 1575 + }, + { + "epoch": 1.7, + "learning_rate": 8.867816091954023e-05, + "loss": 1.3601, + "step": 1576 + }, + { + "epoch": 1.7, + "learning_rate": 8.867097701149427e-05, + "loss": 1.4604, + "step": 1577 + }, + { + "epoch": 1.7, + "learning_rate": 8.866379310344827e-05, + "loss": 1.353, + "step": 1578 + }, + { + "epoch": 1.7, + "learning_rate": 8.865660919540231e-05, + "loss": 1.3605, + "step": 1579 + }, + { + "epoch": 1.7, + "learning_rate": 8.864942528735633e-05, + "loss": 1.3674, + "step": 1580 + }, + { + "epoch": 1.7, + "learning_rate": 8.864224137931035e-05, + "loss": 1.37, + "step": 1581 + }, + { + "epoch": 1.7, + "learning_rate": 8.863505747126437e-05, + "loss": 1.4239, + "step": 1582 + }, + { + "epoch": 1.71, + "learning_rate": 8.86278735632184e-05, + "loss": 1.3335, + "step": 1583 + }, + { + "epoch": 1.71, + "learning_rate": 8.862068965517242e-05, + "loss": 1.329, + "step": 1584 + }, + { + "epoch": 1.71, + "learning_rate": 8.861350574712644e-05, + "loss": 1.3511, + "step": 1585 + }, + { + "epoch": 1.71, + "learning_rate": 8.860632183908046e-05, + "loss": 1.3276, + "step": 1586 + }, + { + "epoch": 1.71, + "learning_rate": 8.859913793103448e-05, + "loss": 1.3222, + "step": 1587 + }, + { + "epoch": 1.71, + "learning_rate": 8.85919540229885e-05, + "loss": 1.5325, + "step": 1588 + }, + { + "epoch": 1.71, + "learning_rate": 8.858477011494252e-05, + "loss": 1.358, + "step": 1589 + }, + { + "epoch": 1.71, + "learning_rate": 8.857758620689656e-05, + "loss": 1.5073, + "step": 1590 + }, + { + "epoch": 1.71, + "learning_rate": 8.857040229885058e-05, + "loss": 1.2342, + "step": 1591 + }, + { + "epoch": 1.72, + "learning_rate": 8.85632183908046e-05, + "loss": 1.301, + "step": 1592 + }, + { + "epoch": 1.72, + "learning_rate": 8.855603448275862e-05, + "loss": 1.3118, + "step": 1593 + }, + { + "epoch": 1.72, + "learning_rate": 8.854885057471265e-05, + "loss": 1.5299, + "step": 1594 + }, + { + "epoch": 1.72, + "learning_rate": 8.854166666666667e-05, + "loss": 1.3532, + "step": 1595 + }, + { + "epoch": 1.72, + "learning_rate": 8.85344827586207e-05, + "loss": 1.6461, + "step": 1596 + }, + { + "epoch": 1.72, + "learning_rate": 8.852729885057471e-05, + "loss": 1.419, + "step": 1597 + }, + { + "epoch": 1.72, + "learning_rate": 8.852011494252875e-05, + "loss": 1.3641, + "step": 1598 + }, + { + "epoch": 1.72, + "learning_rate": 8.851293103448275e-05, + "loss": 1.3856, + "step": 1599 + }, + { + "epoch": 1.72, + "learning_rate": 8.850574712643679e-05, + "loss": 1.3302, + "step": 1600 + }, + { + "epoch": 1.73, + "learning_rate": 8.849856321839081e-05, + "loss": 1.3699, + "step": 1601 + }, + { + "epoch": 1.73, + "learning_rate": 8.849137931034483e-05, + "loss": 1.4159, + "step": 1602 + }, + { + "epoch": 1.73, + "learning_rate": 8.848419540229885e-05, + "loss": 1.4108, + "step": 1603 + }, + { + "epoch": 1.73, + "learning_rate": 8.847701149425288e-05, + "loss": 1.4251, + "step": 1604 + }, + { + "epoch": 1.73, + "learning_rate": 8.84698275862069e-05, + "loss": 1.4934, + "step": 1605 + }, + { + "epoch": 1.73, + "learning_rate": 8.846264367816092e-05, + "loss": 1.3384, + "step": 1606 + }, + { + "epoch": 1.73, + "learning_rate": 8.845545977011494e-05, + "loss": 1.3538, + "step": 1607 + }, + { + "epoch": 1.73, + "learning_rate": 8.844827586206898e-05, + "loss": 1.351, + "step": 1608 + }, + { + "epoch": 1.73, + "learning_rate": 8.8441091954023e-05, + "loss": 1.2791, + "step": 1609 + }, + { + "epoch": 1.73, + "learning_rate": 8.843390804597702e-05, + "loss": 1.3284, + "step": 1610 + }, + { + "epoch": 1.74, + "learning_rate": 8.842672413793104e-05, + "loss": 1.4522, + "step": 1611 + }, + { + "epoch": 1.74, + "learning_rate": 8.841954022988507e-05, + "loss": 1.3266, + "step": 1612 + }, + { + "epoch": 1.74, + "learning_rate": 8.841235632183908e-05, + "loss": 1.3002, + "step": 1613 + }, + { + "epoch": 1.74, + "learning_rate": 8.84051724137931e-05, + "loss": 1.4184, + "step": 1614 + }, + { + "epoch": 1.74, + "learning_rate": 8.839798850574713e-05, + "loss": 1.3678, + "step": 1615 + }, + { + "epoch": 1.74, + "learning_rate": 8.839080459770115e-05, + "loss": 1.2513, + "step": 1616 + }, + { + "epoch": 1.74, + "learning_rate": 8.838362068965517e-05, + "loss": 1.3796, + "step": 1617 + }, + { + "epoch": 1.74, + "learning_rate": 8.83764367816092e-05, + "loss": 1.3925, + "step": 1618 + }, + { + "epoch": 1.74, + "learning_rate": 8.836925287356323e-05, + "loss": 1.2764, + "step": 1619 + }, + { + "epoch": 1.75, + "learning_rate": 8.836206896551724e-05, + "loss": 1.3609, + "step": 1620 + }, + { + "epoch": 1.75, + "learning_rate": 8.835488505747127e-05, + "loss": 1.408, + "step": 1621 + }, + { + "epoch": 1.75, + "learning_rate": 8.834770114942529e-05, + "loss": 1.2772, + "step": 1622 + }, + { + "epoch": 1.75, + "learning_rate": 8.834051724137932e-05, + "loss": 1.4778, + "step": 1623 + }, + { + "epoch": 1.75, + "learning_rate": 8.833333333333333e-05, + "loss": 1.3918, + "step": 1624 + }, + { + "epoch": 1.75, + "learning_rate": 8.832614942528736e-05, + "loss": 1.3734, + "step": 1625 + }, + { + "epoch": 1.75, + "learning_rate": 8.831896551724138e-05, + "loss": 1.3867, + "step": 1626 + }, + { + "epoch": 1.75, + "learning_rate": 8.83117816091954e-05, + "loss": 1.3179, + "step": 1627 + }, + { + "epoch": 1.75, + "learning_rate": 8.830459770114942e-05, + "loss": 1.4102, + "step": 1628 + }, + { + "epoch": 1.76, + "learning_rate": 8.829741379310346e-05, + "loss": 1.3125, + "step": 1629 + }, + { + "epoch": 1.76, + "learning_rate": 8.829022988505748e-05, + "loss": 1.6106, + "step": 1630 + }, + { + "epoch": 1.76, + "learning_rate": 8.82830459770115e-05, + "loss": 1.2073, + "step": 1631 + }, + { + "epoch": 1.76, + "learning_rate": 8.827586206896552e-05, + "loss": 1.5882, + "step": 1632 + }, + { + "epoch": 1.76, + "learning_rate": 8.826867816091955e-05, + "loss": 1.285, + "step": 1633 + }, + { + "epoch": 1.76, + "learning_rate": 8.826149425287356e-05, + "loss": 1.3932, + "step": 1634 + }, + { + "epoch": 1.76, + "learning_rate": 8.82543103448276e-05, + "loss": 1.4257, + "step": 1635 + }, + { + "epoch": 1.76, + "learning_rate": 8.824712643678161e-05, + "loss": 1.4586, + "step": 1636 + }, + { + "epoch": 1.76, + "learning_rate": 8.823994252873565e-05, + "loss": 1.3362, + "step": 1637 + }, + { + "epoch": 1.77, + "learning_rate": 8.823275862068966e-05, + "loss": 1.4382, + "step": 1638 + }, + { + "epoch": 1.77, + "learning_rate": 8.822557471264368e-05, + "loss": 1.5376, + "step": 1639 + }, + { + "epoch": 1.77, + "learning_rate": 8.821839080459771e-05, + "loss": 1.3965, + "step": 1640 + }, + { + "epoch": 1.77, + "learning_rate": 8.821120689655173e-05, + "loss": 1.2947, + "step": 1641 + }, + { + "epoch": 1.77, + "learning_rate": 8.820402298850575e-05, + "loss": 1.1973, + "step": 1642 + }, + { + "epoch": 1.77, + "learning_rate": 8.819683908045977e-05, + "loss": 1.27, + "step": 1643 + }, + { + "epoch": 1.77, + "learning_rate": 8.81896551724138e-05, + "loss": 1.3466, + "step": 1644 + }, + { + "epoch": 1.77, + "learning_rate": 8.818247126436781e-05, + "loss": 1.2953, + "step": 1645 + }, + { + "epoch": 1.77, + "learning_rate": 8.817528735632184e-05, + "loss": 1.2181, + "step": 1646 + }, + { + "epoch": 1.77, + "learning_rate": 8.816810344827587e-05, + "loss": 1.5173, + "step": 1647 + }, + { + "epoch": 1.78, + "learning_rate": 8.816091954022989e-05, + "loss": 1.4036, + "step": 1648 + }, + { + "epoch": 1.78, + "learning_rate": 8.81537356321839e-05, + "loss": 1.3174, + "step": 1649 + }, + { + "epoch": 1.78, + "learning_rate": 8.814655172413794e-05, + "loss": 1.2907, + "step": 1650 + }, + { + "epoch": 1.78, + "learning_rate": 8.813936781609196e-05, + "loss": 1.2602, + "step": 1651 + }, + { + "epoch": 1.78, + "learning_rate": 8.813218390804598e-05, + "loss": 1.4611, + "step": 1652 + }, + { + "epoch": 1.78, + "learning_rate": 8.8125e-05, + "loss": 1.3872, + "step": 1653 + }, + { + "epoch": 1.78, + "learning_rate": 8.811781609195403e-05, + "loss": 1.3948, + "step": 1654 + }, + { + "epoch": 1.78, + "learning_rate": 8.811063218390805e-05, + "loss": 1.4016, + "step": 1655 + }, + { + "epoch": 1.78, + "learning_rate": 8.810344827586208e-05, + "loss": 1.3181, + "step": 1656 + }, + { + "epoch": 1.79, + "learning_rate": 8.80962643678161e-05, + "loss": 1.3025, + "step": 1657 + }, + { + "epoch": 1.79, + "learning_rate": 8.808908045977013e-05, + "loss": 1.4074, + "step": 1658 + }, + { + "epoch": 1.79, + "learning_rate": 8.808189655172414e-05, + "loss": 1.5307, + "step": 1659 + }, + { + "epoch": 1.79, + "learning_rate": 8.807471264367817e-05, + "loss": 1.3712, + "step": 1660 + }, + { + "epoch": 1.79, + "learning_rate": 8.806752873563219e-05, + "loss": 1.3855, + "step": 1661 + }, + { + "epoch": 1.79, + "learning_rate": 8.806034482758621e-05, + "loss": 1.3687, + "step": 1662 + }, + { + "epoch": 1.79, + "learning_rate": 8.805316091954023e-05, + "loss": 1.3085, + "step": 1663 + }, + { + "epoch": 1.79, + "learning_rate": 8.804597701149425e-05, + "loss": 1.3997, + "step": 1664 + }, + { + "epoch": 1.79, + "learning_rate": 8.803879310344829e-05, + "loss": 1.4641, + "step": 1665 + }, + { + "epoch": 1.8, + "learning_rate": 8.803160919540229e-05, + "loss": 1.4997, + "step": 1666 + }, + { + "epoch": 1.8, + "learning_rate": 8.802442528735633e-05, + "loss": 1.4424, + "step": 1667 + }, + { + "epoch": 1.8, + "learning_rate": 8.801724137931035e-05, + "loss": 1.4012, + "step": 1668 + }, + { + "epoch": 1.8, + "learning_rate": 8.801005747126437e-05, + "loss": 1.3274, + "step": 1669 + }, + { + "epoch": 1.8, + "learning_rate": 8.800287356321839e-05, + "loss": 1.4273, + "step": 1670 + }, + { + "epoch": 1.8, + "learning_rate": 8.799568965517242e-05, + "loss": 1.3356, + "step": 1671 + }, + { + "epoch": 1.8, + "learning_rate": 8.798850574712644e-05, + "loss": 1.3451, + "step": 1672 + }, + { + "epoch": 1.8, + "learning_rate": 8.798132183908046e-05, + "loss": 1.4259, + "step": 1673 + }, + { + "epoch": 1.8, + "learning_rate": 8.797413793103448e-05, + "loss": 1.3763, + "step": 1674 + }, + { + "epoch": 1.8, + "learning_rate": 8.796695402298852e-05, + "loss": 1.3231, + "step": 1675 + }, + { + "epoch": 1.81, + "learning_rate": 8.795977011494254e-05, + "loss": 1.2294, + "step": 1676 + }, + { + "epoch": 1.81, + "learning_rate": 8.795258620689656e-05, + "loss": 1.4068, + "step": 1677 + }, + { + "epoch": 1.81, + "learning_rate": 8.794540229885058e-05, + "loss": 1.2816, + "step": 1678 + }, + { + "epoch": 1.81, + "learning_rate": 8.793821839080461e-05, + "loss": 1.3362, + "step": 1679 + }, + { + "epoch": 1.81, + "learning_rate": 8.793103448275862e-05, + "loss": 1.3873, + "step": 1680 + }, + { + "epoch": 1.81, + "learning_rate": 8.792385057471265e-05, + "loss": 1.4511, + "step": 1681 + }, + { + "epoch": 1.81, + "learning_rate": 8.791666666666667e-05, + "loss": 1.4872, + "step": 1682 + }, + { + "epoch": 1.81, + "learning_rate": 8.790948275862069e-05, + "loss": 1.166, + "step": 1683 + }, + { + "epoch": 1.81, + "learning_rate": 8.790229885057471e-05, + "loss": 1.3778, + "step": 1684 + }, + { + "epoch": 1.82, + "learning_rate": 8.789511494252875e-05, + "loss": 1.4015, + "step": 1685 + }, + { + "epoch": 1.82, + "learning_rate": 8.788793103448277e-05, + "loss": 1.2908, + "step": 1686 + }, + { + "epoch": 1.82, + "learning_rate": 8.788074712643679e-05, + "loss": 1.3595, + "step": 1687 + }, + { + "epoch": 1.82, + "learning_rate": 8.787356321839081e-05, + "loss": 1.423, + "step": 1688 + }, + { + "epoch": 1.82, + "learning_rate": 8.786637931034483e-05, + "loss": 1.4608, + "step": 1689 + }, + { + "epoch": 1.82, + "learning_rate": 8.785919540229886e-05, + "loss": 1.4166, + "step": 1690 + }, + { + "epoch": 1.82, + "learning_rate": 8.785201149425287e-05, + "loss": 1.4369, + "step": 1691 + }, + { + "epoch": 1.82, + "learning_rate": 8.78448275862069e-05, + "loss": 1.2287, + "step": 1692 + }, + { + "epoch": 1.82, + "learning_rate": 8.783764367816092e-05, + "loss": 1.4557, + "step": 1693 + }, + { + "epoch": 1.83, + "learning_rate": 8.783045977011494e-05, + "loss": 1.3556, + "step": 1694 + }, + { + "epoch": 1.83, + "learning_rate": 8.782327586206896e-05, + "loss": 1.3001, + "step": 1695 + }, + { + "epoch": 1.83, + "learning_rate": 8.7816091954023e-05, + "loss": 1.4189, + "step": 1696 + }, + { + "epoch": 1.83, + "learning_rate": 8.780890804597702e-05, + "loss": 1.3659, + "step": 1697 + }, + { + "epoch": 1.83, + "learning_rate": 8.780172413793104e-05, + "loss": 1.319, + "step": 1698 + }, + { + "epoch": 1.83, + "learning_rate": 8.779454022988506e-05, + "loss": 1.3906, + "step": 1699 + }, + { + "epoch": 1.83, + "learning_rate": 8.778735632183909e-05, + "loss": 1.4152, + "step": 1700 + }, + { + "epoch": 1.83, + "learning_rate": 8.77801724137931e-05, + "loss": 1.3866, + "step": 1701 + }, + { + "epoch": 1.83, + "learning_rate": 8.777298850574713e-05, + "loss": 1.3292, + "step": 1702 + }, + { + "epoch": 1.84, + "learning_rate": 8.776580459770115e-05, + "loss": 1.4016, + "step": 1703 + }, + { + "epoch": 1.84, + "learning_rate": 8.775862068965519e-05, + "loss": 1.3779, + "step": 1704 + }, + { + "epoch": 1.84, + "learning_rate": 8.775143678160919e-05, + "loss": 1.3427, + "step": 1705 + }, + { + "epoch": 1.84, + "learning_rate": 8.774425287356323e-05, + "loss": 1.3176, + "step": 1706 + }, + { + "epoch": 1.84, + "learning_rate": 8.773706896551725e-05, + "loss": 1.4951, + "step": 1707 + }, + { + "epoch": 1.84, + "learning_rate": 8.772988505747127e-05, + "loss": 1.4708, + "step": 1708 + }, + { + "epoch": 1.84, + "learning_rate": 8.772270114942529e-05, + "loss": 1.2818, + "step": 1709 + }, + { + "epoch": 1.84, + "learning_rate": 8.771551724137932e-05, + "loss": 1.4901, + "step": 1710 + }, + { + "epoch": 1.84, + "learning_rate": 8.770833333333334e-05, + "loss": 1.5047, + "step": 1711 + }, + { + "epoch": 1.84, + "learning_rate": 8.770114942528736e-05, + "loss": 1.3315, + "step": 1712 + }, + { + "epoch": 1.85, + "learning_rate": 8.769396551724138e-05, + "loss": 1.2887, + "step": 1713 + }, + { + "epoch": 1.85, + "learning_rate": 8.768678160919542e-05, + "loss": 1.3684, + "step": 1714 + }, + { + "epoch": 1.85, + "learning_rate": 8.767959770114942e-05, + "loss": 1.2766, + "step": 1715 + }, + { + "epoch": 1.85, + "learning_rate": 8.767241379310344e-05, + "loss": 1.3095, + "step": 1716 + }, + { + "epoch": 1.85, + "learning_rate": 8.766522988505748e-05, + "loss": 1.2838, + "step": 1717 + }, + { + "epoch": 1.85, + "learning_rate": 8.76580459770115e-05, + "loss": 1.4153, + "step": 1718 + }, + { + "epoch": 1.85, + "learning_rate": 8.765086206896552e-05, + "loss": 1.403, + "step": 1719 + }, + { + "epoch": 1.85, + "learning_rate": 8.764367816091954e-05, + "loss": 1.3951, + "step": 1720 + }, + { + "epoch": 1.85, + "learning_rate": 8.763649425287357e-05, + "loss": 1.4367, + "step": 1721 + }, + { + "epoch": 1.86, + "learning_rate": 8.762931034482759e-05, + "loss": 1.3347, + "step": 1722 + }, + { + "epoch": 1.86, + "learning_rate": 8.762212643678161e-05, + "loss": 1.4585, + "step": 1723 + }, + { + "epoch": 1.86, + "learning_rate": 8.761494252873563e-05, + "loss": 1.2978, + "step": 1724 + }, + { + "epoch": 1.86, + "learning_rate": 8.760775862068967e-05, + "loss": 1.3423, + "step": 1725 + }, + { + "epoch": 1.86, + "learning_rate": 8.760057471264367e-05, + "loss": 1.3301, + "step": 1726 + }, + { + "epoch": 1.86, + "learning_rate": 8.759339080459771e-05, + "loss": 1.3372, + "step": 1727 + }, + { + "epoch": 1.86, + "learning_rate": 8.758620689655173e-05, + "loss": 1.3714, + "step": 1728 + }, + { + "epoch": 1.86, + "learning_rate": 8.757902298850575e-05, + "loss": 1.3546, + "step": 1729 + }, + { + "epoch": 1.86, + "learning_rate": 8.757183908045977e-05, + "loss": 1.356, + "step": 1730 + }, + { + "epoch": 1.87, + "learning_rate": 8.75646551724138e-05, + "loss": 1.2862, + "step": 1731 + }, + { + "epoch": 1.87, + "learning_rate": 8.755747126436782e-05, + "loss": 1.3547, + "step": 1732 + }, + { + "epoch": 1.87, + "learning_rate": 8.755028735632184e-05, + "loss": 1.3681, + "step": 1733 + }, + { + "epoch": 1.87, + "learning_rate": 8.754310344827586e-05, + "loss": 1.4832, + "step": 1734 + }, + { + "epoch": 1.87, + "learning_rate": 8.75359195402299e-05, + "loss": 1.3865, + "step": 1735 + }, + { + "epoch": 1.87, + "learning_rate": 8.752873563218392e-05, + "loss": 1.3687, + "step": 1736 + }, + { + "epoch": 1.87, + "learning_rate": 8.752155172413794e-05, + "loss": 1.3616, + "step": 1737 + }, + { + "epoch": 1.87, + "learning_rate": 8.751436781609196e-05, + "loss": 1.466, + "step": 1738 + }, + { + "epoch": 1.87, + "learning_rate": 8.750718390804599e-05, + "loss": 1.3143, + "step": 1739 + }, + { + "epoch": 1.88, + "learning_rate": 8.75e-05, + "loss": 1.4282, + "step": 1740 + }, + { + "epoch": 1.88, + "learning_rate": 8.749281609195402e-05, + "loss": 1.4714, + "step": 1741 + }, + { + "epoch": 1.88, + "learning_rate": 8.748563218390805e-05, + "loss": 1.3974, + "step": 1742 + }, + { + "epoch": 1.88, + "learning_rate": 8.747844827586207e-05, + "loss": 1.4954, + "step": 1743 + }, + { + "epoch": 1.88, + "learning_rate": 8.74712643678161e-05, + "loss": 1.3781, + "step": 1744 + }, + { + "epoch": 1.88, + "learning_rate": 8.746408045977011e-05, + "loss": 1.345, + "step": 1745 + }, + { + "epoch": 1.88, + "learning_rate": 8.745689655172415e-05, + "loss": 1.5552, + "step": 1746 + }, + { + "epoch": 1.88, + "learning_rate": 8.744971264367815e-05, + "loss": 1.3524, + "step": 1747 + }, + { + "epoch": 1.88, + "learning_rate": 8.744252873563219e-05, + "loss": 1.392, + "step": 1748 + }, + { + "epoch": 1.88, + "learning_rate": 8.743534482758621e-05, + "loss": 1.4707, + "step": 1749 + }, + { + "epoch": 1.89, + "learning_rate": 8.742816091954024e-05, + "loss": 1.3725, + "step": 1750 + }, + { + "epoch": 1.89, + "eval_loss": 1.2655576467514038, + "eval_runtime": 174.9993, + "eval_samples_per_second": 127.258, + "eval_steps_per_second": 0.663, + "step": 1750 + }, + { + "epoch": 1.89, + "learning_rate": 8.742097701149425e-05, + "loss": 1.3911, + "step": 1751 + }, + { + "epoch": 1.89, + "learning_rate": 8.741379310344828e-05, + "loss": 1.3269, + "step": 1752 + }, + { + "epoch": 1.89, + "learning_rate": 8.74066091954023e-05, + "loss": 1.4208, + "step": 1753 + }, + { + "epoch": 1.89, + "learning_rate": 8.739942528735632e-05, + "loss": 1.4376, + "step": 1754 + }, + { + "epoch": 1.89, + "learning_rate": 8.739224137931034e-05, + "loss": 1.4395, + "step": 1755 + }, + { + "epoch": 1.89, + "learning_rate": 8.738505747126438e-05, + "loss": 1.3658, + "step": 1756 + }, + { + "epoch": 1.89, + "learning_rate": 8.73778735632184e-05, + "loss": 1.3612, + "step": 1757 + }, + { + "epoch": 1.89, + "learning_rate": 8.737068965517242e-05, + "loss": 1.4274, + "step": 1758 + }, + { + "epoch": 1.9, + "learning_rate": 8.736350574712644e-05, + "loss": 1.3694, + "step": 1759 + }, + { + "epoch": 1.9, + "learning_rate": 8.735632183908047e-05, + "loss": 1.3364, + "step": 1760 + }, + { + "epoch": 1.9, + "learning_rate": 8.734913793103448e-05, + "loss": 1.2996, + "step": 1761 + }, + { + "epoch": 1.9, + "learning_rate": 8.734195402298851e-05, + "loss": 1.3395, + "step": 1762 + }, + { + "epoch": 1.9, + "learning_rate": 8.733477011494253e-05, + "loss": 1.2919, + "step": 1763 + }, + { + "epoch": 1.9, + "learning_rate": 8.732758620689655e-05, + "loss": 1.3096, + "step": 1764 + }, + { + "epoch": 1.9, + "learning_rate": 8.732040229885057e-05, + "loss": 1.4253, + "step": 1765 + }, + { + "epoch": 1.9, + "learning_rate": 8.73132183908046e-05, + "loss": 1.2895, + "step": 1766 + }, + { + "epoch": 1.9, + "learning_rate": 8.730603448275863e-05, + "loss": 1.3166, + "step": 1767 + }, + { + "epoch": 1.91, + "learning_rate": 8.729885057471265e-05, + "loss": 1.3153, + "step": 1768 + }, + { + "epoch": 1.91, + "learning_rate": 8.729166666666667e-05, + "loss": 1.4923, + "step": 1769 + }, + { + "epoch": 1.91, + "learning_rate": 8.728448275862069e-05, + "loss": 1.4905, + "step": 1770 + }, + { + "epoch": 1.91, + "learning_rate": 8.727729885057472e-05, + "loss": 1.4717, + "step": 1771 + }, + { + "epoch": 1.91, + "learning_rate": 8.727011494252873e-05, + "loss": 1.3973, + "step": 1772 + }, + { + "epoch": 1.91, + "learning_rate": 8.726293103448276e-05, + "loss": 1.3924, + "step": 1773 + }, + { + "epoch": 1.91, + "learning_rate": 8.725574712643678e-05, + "loss": 1.3991, + "step": 1774 + }, + { + "epoch": 1.91, + "learning_rate": 8.72485632183908e-05, + "loss": 1.3084, + "step": 1775 + }, + { + "epoch": 1.91, + "learning_rate": 8.724137931034483e-05, + "loss": 1.483, + "step": 1776 + }, + { + "epoch": 1.91, + "learning_rate": 8.723419540229886e-05, + "loss": 1.3108, + "step": 1777 + }, + { + "epoch": 1.92, + "learning_rate": 8.722701149425288e-05, + "loss": 1.4187, + "step": 1778 + }, + { + "epoch": 1.92, + "learning_rate": 8.72198275862069e-05, + "loss": 1.2198, + "step": 1779 + }, + { + "epoch": 1.92, + "learning_rate": 8.721264367816092e-05, + "loss": 1.369, + "step": 1780 + }, + { + "epoch": 1.92, + "learning_rate": 8.720545977011495e-05, + "loss": 1.2973, + "step": 1781 + }, + { + "epoch": 1.92, + "learning_rate": 8.719827586206896e-05, + "loss": 1.2356, + "step": 1782 + }, + { + "epoch": 1.92, + "learning_rate": 8.7191091954023e-05, + "loss": 1.4941, + "step": 1783 + }, + { + "epoch": 1.92, + "learning_rate": 8.718390804597702e-05, + "loss": 1.2872, + "step": 1784 + }, + { + "epoch": 1.92, + "learning_rate": 8.717672413793105e-05, + "loss": 1.3262, + "step": 1785 + }, + { + "epoch": 1.92, + "learning_rate": 8.716954022988506e-05, + "loss": 1.4396, + "step": 1786 + }, + { + "epoch": 1.93, + "learning_rate": 8.716235632183909e-05, + "loss": 1.3534, + "step": 1787 + }, + { + "epoch": 1.93, + "learning_rate": 8.715517241379311e-05, + "loss": 1.3816, + "step": 1788 + }, + { + "epoch": 1.93, + "learning_rate": 8.714798850574713e-05, + "loss": 1.283, + "step": 1789 + }, + { + "epoch": 1.93, + "learning_rate": 8.714080459770115e-05, + "loss": 1.2187, + "step": 1790 + }, + { + "epoch": 1.93, + "learning_rate": 8.713362068965518e-05, + "loss": 1.3109, + "step": 1791 + }, + { + "epoch": 1.93, + "learning_rate": 8.71264367816092e-05, + "loss": 1.4, + "step": 1792 + }, + { + "epoch": 1.93, + "learning_rate": 8.711925287356321e-05, + "loss": 1.4145, + "step": 1793 + }, + { + "epoch": 1.93, + "learning_rate": 8.711206896551725e-05, + "loss": 1.348, + "step": 1794 + }, + { + "epoch": 1.93, + "learning_rate": 8.710488505747127e-05, + "loss": 1.4377, + "step": 1795 + }, + { + "epoch": 1.94, + "learning_rate": 8.709770114942529e-05, + "loss": 1.4383, + "step": 1796 + }, + { + "epoch": 1.94, + "learning_rate": 8.70905172413793e-05, + "loss": 1.4801, + "step": 1797 + }, + { + "epoch": 1.94, + "learning_rate": 8.708333333333334e-05, + "loss": 1.5821, + "step": 1798 + }, + { + "epoch": 1.94, + "learning_rate": 8.707614942528736e-05, + "loss": 1.3531, + "step": 1799 + }, + { + "epoch": 1.94, + "learning_rate": 8.706896551724138e-05, + "loss": 1.4186, + "step": 1800 + }, + { + "epoch": 1.94, + "learning_rate": 8.70617816091954e-05, + "loss": 1.4206, + "step": 1801 + }, + { + "epoch": 1.94, + "learning_rate": 8.705459770114944e-05, + "loss": 1.421, + "step": 1802 + }, + { + "epoch": 1.94, + "learning_rate": 8.704741379310346e-05, + "loss": 1.468, + "step": 1803 + }, + { + "epoch": 1.94, + "learning_rate": 8.704022988505748e-05, + "loss": 1.3211, + "step": 1804 + }, + { + "epoch": 1.95, + "learning_rate": 8.70330459770115e-05, + "loss": 1.4215, + "step": 1805 + }, + { + "epoch": 1.95, + "learning_rate": 8.702586206896553e-05, + "loss": 1.2769, + "step": 1806 + }, + { + "epoch": 1.95, + "learning_rate": 8.701867816091954e-05, + "loss": 1.3877, + "step": 1807 + }, + { + "epoch": 1.95, + "learning_rate": 8.701149425287357e-05, + "loss": 1.3612, + "step": 1808 + }, + { + "epoch": 1.95, + "learning_rate": 8.700431034482759e-05, + "loss": 1.2655, + "step": 1809 + }, + { + "epoch": 1.95, + "learning_rate": 8.699712643678161e-05, + "loss": 1.6043, + "step": 1810 + }, + { + "epoch": 1.95, + "learning_rate": 8.698994252873563e-05, + "loss": 1.2556, + "step": 1811 + }, + { + "epoch": 1.95, + "learning_rate": 8.698275862068967e-05, + "loss": 1.3997, + "step": 1812 + }, + { + "epoch": 1.95, + "learning_rate": 8.697557471264369e-05, + "loss": 1.4378, + "step": 1813 + }, + { + "epoch": 1.95, + "learning_rate": 8.69683908045977e-05, + "loss": 1.361, + "step": 1814 + }, + { + "epoch": 1.96, + "learning_rate": 8.696120689655173e-05, + "loss": 1.3876, + "step": 1815 + }, + { + "epoch": 1.96, + "learning_rate": 8.695402298850576e-05, + "loss": 1.253, + "step": 1816 + }, + { + "epoch": 1.96, + "learning_rate": 8.694683908045978e-05, + "loss": 1.3852, + "step": 1817 + }, + { + "epoch": 1.96, + "learning_rate": 8.693965517241379e-05, + "loss": 1.3659, + "step": 1818 + }, + { + "epoch": 1.96, + "learning_rate": 8.693247126436782e-05, + "loss": 1.3819, + "step": 1819 + }, + { + "epoch": 1.96, + "learning_rate": 8.692528735632184e-05, + "loss": 1.1919, + "step": 1820 + }, + { + "epoch": 1.96, + "learning_rate": 8.691810344827586e-05, + "loss": 1.3336, + "step": 1821 + }, + { + "epoch": 1.96, + "learning_rate": 8.691091954022988e-05, + "loss": 1.3434, + "step": 1822 + }, + { + "epoch": 1.96, + "learning_rate": 8.690373563218392e-05, + "loss": 1.4059, + "step": 1823 + }, + { + "epoch": 1.97, + "learning_rate": 8.689655172413794e-05, + "loss": 1.4253, + "step": 1824 + }, + { + "epoch": 1.97, + "learning_rate": 8.688936781609196e-05, + "loss": 1.382, + "step": 1825 + }, + { + "epoch": 1.97, + "learning_rate": 8.688218390804598e-05, + "loss": 1.3234, + "step": 1826 + }, + { + "epoch": 1.97, + "learning_rate": 8.687500000000001e-05, + "loss": 1.2294, + "step": 1827 + }, + { + "epoch": 1.97, + "learning_rate": 8.686781609195402e-05, + "loss": 1.3878, + "step": 1828 + }, + { + "epoch": 1.97, + "learning_rate": 8.686063218390805e-05, + "loss": 1.1917, + "step": 1829 + }, + { + "epoch": 1.97, + "learning_rate": 8.685344827586207e-05, + "loss": 1.6016, + "step": 1830 + }, + { + "epoch": 1.97, + "learning_rate": 8.68462643678161e-05, + "loss": 1.4947, + "step": 1831 + }, + { + "epoch": 1.97, + "learning_rate": 8.683908045977011e-05, + "loss": 1.3778, + "step": 1832 + }, + { + "epoch": 1.98, + "learning_rate": 8.683189655172415e-05, + "loss": 1.3418, + "step": 1833 + }, + { + "epoch": 1.98, + "learning_rate": 8.682471264367817e-05, + "loss": 1.3758, + "step": 1834 + }, + { + "epoch": 1.98, + "learning_rate": 8.681752873563219e-05, + "loss": 1.4881, + "step": 1835 + }, + { + "epoch": 1.98, + "learning_rate": 8.681034482758621e-05, + "loss": 1.3473, + "step": 1836 + }, + { + "epoch": 1.98, + "learning_rate": 8.680316091954024e-05, + "loss": 1.3842, + "step": 1837 + }, + { + "epoch": 1.98, + "learning_rate": 8.679597701149426e-05, + "loss": 1.1859, + "step": 1838 + }, + { + "epoch": 1.98, + "learning_rate": 8.678879310344828e-05, + "loss": 1.4672, + "step": 1839 + }, + { + "epoch": 1.98, + "learning_rate": 8.67816091954023e-05, + "loss": 1.4733, + "step": 1840 + }, + { + "epoch": 1.98, + "learning_rate": 8.677442528735634e-05, + "loss": 1.4243, + "step": 1841 + }, + { + "epoch": 1.98, + "learning_rate": 8.676724137931034e-05, + "loss": 1.3751, + "step": 1842 + }, + { + "epoch": 1.99, + "learning_rate": 8.676005747126436e-05, + "loss": 1.3416, + "step": 1843 + }, + { + "epoch": 1.99, + "learning_rate": 8.67528735632184e-05, + "loss": 1.2611, + "step": 1844 + }, + { + "epoch": 1.99, + "learning_rate": 8.674568965517242e-05, + "loss": 1.4535, + "step": 1845 + }, + { + "epoch": 1.99, + "learning_rate": 8.673850574712644e-05, + "loss": 1.4024, + "step": 1846 + }, + { + "epoch": 1.99, + "learning_rate": 8.673132183908046e-05, + "loss": 1.2819, + "step": 1847 + }, + { + "epoch": 1.99, + "learning_rate": 8.672413793103449e-05, + "loss": 1.3787, + "step": 1848 + }, + { + "epoch": 1.99, + "learning_rate": 8.671695402298851e-05, + "loss": 1.3725, + "step": 1849 + }, + { + "epoch": 1.99, + "learning_rate": 8.670977011494253e-05, + "loss": 1.3545, + "step": 1850 + }, + { + "epoch": 1.99, + "learning_rate": 8.670258620689655e-05, + "loss": 1.2847, + "step": 1851 + }, + { + "epoch": 2.0, + "learning_rate": 8.669540229885059e-05, + "loss": 1.3258, + "step": 1852 + }, + { + "epoch": 2.0, + "learning_rate": 8.66882183908046e-05, + "loss": 1.3686, + "step": 1853 + }, + { + "epoch": 2.0, + "learning_rate": 8.668103448275863e-05, + "loss": 1.3049, + "step": 1854 + }, + { + "epoch": 2.0, + "learning_rate": 8.667385057471265e-05, + "loss": 1.2103, + "step": 1855 + }, + { + "epoch": 2.0, + "learning_rate": 8.666666666666667e-05, + "loss": 1.3753, + "step": 1856 + }, + { + "epoch": 2.0, + "learning_rate": 8.665948275862069e-05, + "loss": 1.2118, + "step": 1857 + }, + { + "epoch": 2.0, + "learning_rate": 8.665229885057472e-05, + "loss": 1.4339, + "step": 1858 + }, + { + "epoch": 2.0, + "learning_rate": 8.664511494252874e-05, + "loss": 1.3183, + "step": 1859 + }, + { + "epoch": 2.0, + "learning_rate": 8.663793103448276e-05, + "loss": 1.2153, + "step": 1860 + }, + { + "epoch": 2.01, + "learning_rate": 8.663074712643678e-05, + "loss": 1.3651, + "step": 1861 + }, + { + "epoch": 2.01, + "learning_rate": 8.662356321839082e-05, + "loss": 1.1345, + "step": 1862 + }, + { + "epoch": 2.01, + "learning_rate": 8.661637931034482e-05, + "loss": 1.3293, + "step": 1863 + }, + { + "epoch": 2.01, + "learning_rate": 8.660919540229886e-05, + "loss": 1.4137, + "step": 1864 + }, + { + "epoch": 2.01, + "learning_rate": 8.660201149425288e-05, + "loss": 1.3424, + "step": 1865 + }, + { + "epoch": 2.01, + "learning_rate": 8.659482758620691e-05, + "loss": 1.3307, + "step": 1866 + }, + { + "epoch": 2.01, + "learning_rate": 8.658764367816092e-05, + "loss": 1.2743, + "step": 1867 + }, + { + "epoch": 2.01, + "learning_rate": 8.658045977011494e-05, + "loss": 1.3256, + "step": 1868 + }, + { + "epoch": 2.01, + "learning_rate": 8.657327586206897e-05, + "loss": 1.2204, + "step": 1869 + }, + { + "epoch": 2.02, + "learning_rate": 8.6566091954023e-05, + "loss": 1.2404, + "step": 1870 + }, + { + "epoch": 2.02, + "learning_rate": 8.655890804597701e-05, + "loss": 1.1549, + "step": 1871 + }, + { + "epoch": 2.02, + "learning_rate": 8.655172413793103e-05, + "loss": 1.2175, + "step": 1872 + }, + { + "epoch": 2.02, + "learning_rate": 8.654454022988507e-05, + "loss": 1.3275, + "step": 1873 + }, + { + "epoch": 2.02, + "learning_rate": 8.653735632183907e-05, + "loss": 1.3893, + "step": 1874 + }, + { + "epoch": 2.02, + "learning_rate": 8.653017241379311e-05, + "loss": 1.2763, + "step": 1875 + }, + { + "epoch": 2.02, + "learning_rate": 8.652298850574713e-05, + "loss": 1.4545, + "step": 1876 + }, + { + "epoch": 2.02, + "learning_rate": 8.651580459770115e-05, + "loss": 1.2501, + "step": 1877 + }, + { + "epoch": 2.02, + "learning_rate": 8.650862068965517e-05, + "loss": 1.0996, + "step": 1878 + }, + { + "epoch": 2.02, + "learning_rate": 8.65014367816092e-05, + "loss": 1.2544, + "step": 1879 + }, + { + "epoch": 2.03, + "learning_rate": 8.649425287356322e-05, + "loss": 1.306, + "step": 1880 + }, + { + "epoch": 2.03, + "learning_rate": 8.648706896551724e-05, + "loss": 1.2751, + "step": 1881 + }, + { + "epoch": 2.03, + "learning_rate": 8.647988505747126e-05, + "loss": 1.3639, + "step": 1882 + }, + { + "epoch": 2.03, + "learning_rate": 8.64727011494253e-05, + "loss": 1.266, + "step": 1883 + }, + { + "epoch": 2.03, + "learning_rate": 8.646551724137932e-05, + "loss": 1.3375, + "step": 1884 + }, + { + "epoch": 2.03, + "learning_rate": 8.645833333333334e-05, + "loss": 1.2264, + "step": 1885 + }, + { + "epoch": 2.03, + "learning_rate": 8.645114942528736e-05, + "loss": 1.2286, + "step": 1886 + }, + { + "epoch": 2.03, + "learning_rate": 8.644396551724139e-05, + "loss": 1.3984, + "step": 1887 + }, + { + "epoch": 2.03, + "learning_rate": 8.64367816091954e-05, + "loss": 1.3012, + "step": 1888 + }, + { + "epoch": 2.04, + "learning_rate": 8.642959770114943e-05, + "loss": 1.3997, + "step": 1889 + }, + { + "epoch": 2.04, + "learning_rate": 8.642241379310345e-05, + "loss": 1.3686, + "step": 1890 + }, + { + "epoch": 2.04, + "learning_rate": 8.641522988505747e-05, + "loss": 1.3251, + "step": 1891 + }, + { + "epoch": 2.04, + "learning_rate": 8.64080459770115e-05, + "loss": 1.4239, + "step": 1892 + }, + { + "epoch": 2.04, + "learning_rate": 8.640086206896553e-05, + "loss": 1.2293, + "step": 1893 + }, + { + "epoch": 2.04, + "learning_rate": 8.639367816091955e-05, + "loss": 1.2458, + "step": 1894 + }, + { + "epoch": 2.04, + "learning_rate": 8.638649425287356e-05, + "loss": 1.1903, + "step": 1895 + }, + { + "epoch": 2.04, + "learning_rate": 8.637931034482759e-05, + "loss": 1.3171, + "step": 1896 + }, + { + "epoch": 2.04, + "learning_rate": 8.637212643678161e-05, + "loss": 1.2914, + "step": 1897 + }, + { + "epoch": 2.05, + "learning_rate": 8.636494252873564e-05, + "loss": 1.4362, + "step": 1898 + }, + { + "epoch": 2.05, + "learning_rate": 8.635775862068965e-05, + "loss": 1.3458, + "step": 1899 + }, + { + "epoch": 2.05, + "learning_rate": 8.635057471264368e-05, + "loss": 1.2551, + "step": 1900 + }, + { + "epoch": 2.05, + "learning_rate": 8.63433908045977e-05, + "loss": 1.2737, + "step": 1901 + }, + { + "epoch": 2.05, + "learning_rate": 8.633620689655172e-05, + "loss": 1.324, + "step": 1902 + }, + { + "epoch": 2.05, + "learning_rate": 8.632902298850575e-05, + "loss": 1.2215, + "step": 1903 + }, + { + "epoch": 2.05, + "learning_rate": 8.632183908045978e-05, + "loss": 1.3985, + "step": 1904 + }, + { + "epoch": 2.05, + "learning_rate": 8.63146551724138e-05, + "loss": 1.3441, + "step": 1905 + }, + { + "epoch": 2.05, + "learning_rate": 8.630747126436782e-05, + "loss": 1.2782, + "step": 1906 + }, + { + "epoch": 2.05, + "learning_rate": 8.630028735632184e-05, + "loss": 1.3768, + "step": 1907 + }, + { + "epoch": 2.06, + "learning_rate": 8.629310344827587e-05, + "loss": 1.2701, + "step": 1908 + }, + { + "epoch": 2.06, + "learning_rate": 8.628591954022988e-05, + "loss": 1.2871, + "step": 1909 + }, + { + "epoch": 2.06, + "learning_rate": 8.627873563218391e-05, + "loss": 1.3234, + "step": 1910 + }, + { + "epoch": 2.06, + "learning_rate": 8.627155172413793e-05, + "loss": 1.2619, + "step": 1911 + }, + { + "epoch": 2.06, + "learning_rate": 8.626436781609197e-05, + "loss": 1.4576, + "step": 1912 + }, + { + "epoch": 2.06, + "learning_rate": 8.625718390804598e-05, + "loss": 1.3035, + "step": 1913 + }, + { + "epoch": 2.06, + "learning_rate": 8.625000000000001e-05, + "loss": 1.5041, + "step": 1914 + }, + { + "epoch": 2.06, + "learning_rate": 8.624281609195403e-05, + "loss": 1.3234, + "step": 1915 + }, + { + "epoch": 2.06, + "learning_rate": 8.623563218390805e-05, + "loss": 1.2555, + "step": 1916 + }, + { + "epoch": 2.07, + "learning_rate": 8.622844827586207e-05, + "loss": 1.2724, + "step": 1917 + }, + { + "epoch": 2.07, + "learning_rate": 8.62212643678161e-05, + "loss": 1.2362, + "step": 1918 + }, + { + "epoch": 2.07, + "learning_rate": 8.621408045977012e-05, + "loss": 1.218, + "step": 1919 + }, + { + "epoch": 2.07, + "learning_rate": 8.620689655172413e-05, + "loss": 1.2617, + "step": 1920 + }, + { + "epoch": 2.07, + "learning_rate": 8.619971264367817e-05, + "loss": 1.421, + "step": 1921 + }, + { + "epoch": 2.07, + "learning_rate": 8.619252873563219e-05, + "loss": 1.3063, + "step": 1922 + }, + { + "epoch": 2.07, + "learning_rate": 8.61853448275862e-05, + "loss": 1.2808, + "step": 1923 + }, + { + "epoch": 2.07, + "learning_rate": 8.617816091954023e-05, + "loss": 1.4242, + "step": 1924 + }, + { + "epoch": 2.07, + "learning_rate": 8.617097701149426e-05, + "loss": 1.2642, + "step": 1925 + }, + { + "epoch": 2.08, + "learning_rate": 8.616379310344828e-05, + "loss": 1.1777, + "step": 1926 + }, + { + "epoch": 2.08, + "learning_rate": 8.61566091954023e-05, + "loss": 1.4425, + "step": 1927 + }, + { + "epoch": 2.08, + "learning_rate": 8.614942528735632e-05, + "loss": 1.4835, + "step": 1928 + }, + { + "epoch": 2.08, + "learning_rate": 8.614224137931035e-05, + "loss": 1.3815, + "step": 1929 + }, + { + "epoch": 2.08, + "learning_rate": 8.613505747126438e-05, + "loss": 1.3623, + "step": 1930 + }, + { + "epoch": 2.08, + "learning_rate": 8.61278735632184e-05, + "loss": 1.3538, + "step": 1931 + }, + { + "epoch": 2.08, + "learning_rate": 8.612068965517242e-05, + "loss": 1.3872, + "step": 1932 + }, + { + "epoch": 2.08, + "learning_rate": 8.611350574712645e-05, + "loss": 1.2798, + "step": 1933 + }, + { + "epoch": 2.08, + "learning_rate": 8.610632183908046e-05, + "loss": 1.1757, + "step": 1934 + }, + { + "epoch": 2.09, + "learning_rate": 8.609913793103449e-05, + "loss": 1.3301, + "step": 1935 + }, + { + "epoch": 2.09, + "learning_rate": 8.609195402298851e-05, + "loss": 1.2767, + "step": 1936 + }, + { + "epoch": 2.09, + "learning_rate": 8.608477011494253e-05, + "loss": 1.3303, + "step": 1937 + }, + { + "epoch": 2.09, + "learning_rate": 8.607758620689655e-05, + "loss": 1.2845, + "step": 1938 + }, + { + "epoch": 2.09, + "learning_rate": 8.607040229885059e-05, + "loss": 1.3679, + "step": 1939 + }, + { + "epoch": 2.09, + "learning_rate": 8.60632183908046e-05, + "loss": 1.1678, + "step": 1940 + }, + { + "epoch": 2.09, + "learning_rate": 8.605603448275863e-05, + "loss": 1.2443, + "step": 1941 + }, + { + "epoch": 2.09, + "learning_rate": 8.604885057471265e-05, + "loss": 1.2913, + "step": 1942 + }, + { + "epoch": 2.09, + "learning_rate": 8.604166666666668e-05, + "loss": 1.3243, + "step": 1943 + }, + { + "epoch": 2.09, + "learning_rate": 8.60344827586207e-05, + "loss": 1.2587, + "step": 1944 + }, + { + "epoch": 2.1, + "learning_rate": 8.602729885057471e-05, + "loss": 1.2529, + "step": 1945 + }, + { + "epoch": 2.1, + "learning_rate": 8.602011494252874e-05, + "loss": 1.4313, + "step": 1946 + }, + { + "epoch": 2.1, + "learning_rate": 8.601293103448276e-05, + "loss": 1.1237, + "step": 1947 + }, + { + "epoch": 2.1, + "learning_rate": 8.600574712643678e-05, + "loss": 1.4, + "step": 1948 + }, + { + "epoch": 2.1, + "learning_rate": 8.59985632183908e-05, + "loss": 1.2765, + "step": 1949 + }, + { + "epoch": 2.1, + "learning_rate": 8.599137931034484e-05, + "loss": 1.3575, + "step": 1950 + }, + { + "epoch": 2.1, + "learning_rate": 8.598419540229886e-05, + "loss": 1.3067, + "step": 1951 + }, + { + "epoch": 2.1, + "learning_rate": 8.597701149425288e-05, + "loss": 1.2675, + "step": 1952 + }, + { + "epoch": 2.1, + "learning_rate": 8.59698275862069e-05, + "loss": 1.2993, + "step": 1953 + }, + { + "epoch": 2.11, + "learning_rate": 8.596264367816093e-05, + "loss": 1.3148, + "step": 1954 + }, + { + "epoch": 2.11, + "learning_rate": 8.595545977011494e-05, + "loss": 1.2421, + "step": 1955 + }, + { + "epoch": 2.11, + "learning_rate": 8.594827586206897e-05, + "loss": 1.2608, + "step": 1956 + }, + { + "epoch": 2.11, + "learning_rate": 8.594109195402299e-05, + "loss": 1.4627, + "step": 1957 + }, + { + "epoch": 2.11, + "learning_rate": 8.593390804597701e-05, + "loss": 1.3377, + "step": 1958 + }, + { + "epoch": 2.11, + "learning_rate": 8.592672413793103e-05, + "loss": 1.3478, + "step": 1959 + }, + { + "epoch": 2.11, + "learning_rate": 8.591954022988507e-05, + "loss": 1.3325, + "step": 1960 + }, + { + "epoch": 2.11, + "learning_rate": 8.591235632183909e-05, + "loss": 1.3385, + "step": 1961 + }, + { + "epoch": 2.11, + "learning_rate": 8.590517241379311e-05, + "loss": 1.2657, + "step": 1962 + }, + { + "epoch": 2.12, + "learning_rate": 8.589798850574713e-05, + "loss": 1.1292, + "step": 1963 + }, + { + "epoch": 2.12, + "learning_rate": 8.589080459770116e-05, + "loss": 1.2665, + "step": 1964 + }, + { + "epoch": 2.12, + "learning_rate": 8.588362068965518e-05, + "loss": 1.3056, + "step": 1965 + }, + { + "epoch": 2.12, + "learning_rate": 8.58764367816092e-05, + "loss": 1.2715, + "step": 1966 + }, + { + "epoch": 2.12, + "learning_rate": 8.586925287356322e-05, + "loss": 1.4734, + "step": 1967 + }, + { + "epoch": 2.12, + "learning_rate": 8.586206896551726e-05, + "loss": 1.2634, + "step": 1968 + }, + { + "epoch": 2.12, + "learning_rate": 8.585488505747126e-05, + "loss": 1.3948, + "step": 1969 + }, + { + "epoch": 2.12, + "learning_rate": 8.58477011494253e-05, + "loss": 1.3246, + "step": 1970 + }, + { + "epoch": 2.12, + "learning_rate": 8.584051724137932e-05, + "loss": 1.2935, + "step": 1971 + }, + { + "epoch": 2.12, + "learning_rate": 8.583333333333334e-05, + "loss": 1.1609, + "step": 1972 + }, + { + "epoch": 2.13, + "learning_rate": 8.582614942528736e-05, + "loss": 1.5121, + "step": 1973 + }, + { + "epoch": 2.13, + "learning_rate": 8.581896551724138e-05, + "loss": 1.3211, + "step": 1974 + }, + { + "epoch": 2.13, + "learning_rate": 8.581178160919541e-05, + "loss": 1.3931, + "step": 1975 + }, + { + "epoch": 2.13, + "learning_rate": 8.580459770114942e-05, + "loss": 1.3007, + "step": 1976 + }, + { + "epoch": 2.13, + "learning_rate": 8.579741379310345e-05, + "loss": 1.3131, + "step": 1977 + }, + { + "epoch": 2.13, + "learning_rate": 8.579022988505747e-05, + "loss": 1.1864, + "step": 1978 + }, + { + "epoch": 2.13, + "learning_rate": 8.57830459770115e-05, + "loss": 1.1928, + "step": 1979 + }, + { + "epoch": 2.13, + "learning_rate": 8.577586206896551e-05, + "loss": 1.3049, + "step": 1980 + }, + { + "epoch": 2.13, + "learning_rate": 8.576867816091955e-05, + "loss": 1.2978, + "step": 1981 + }, + { + "epoch": 2.14, + "learning_rate": 8.576149425287357e-05, + "loss": 1.2491, + "step": 1982 + }, + { + "epoch": 2.14, + "learning_rate": 8.575431034482759e-05, + "loss": 1.2608, + "step": 1983 + }, + { + "epoch": 2.14, + "learning_rate": 8.574712643678161e-05, + "loss": 1.2992, + "step": 1984 + }, + { + "epoch": 2.14, + "learning_rate": 8.573994252873564e-05, + "loss": 1.4786, + "step": 1985 + }, + { + "epoch": 2.14, + "learning_rate": 8.573275862068966e-05, + "loss": 1.2918, + "step": 1986 + }, + { + "epoch": 2.14, + "learning_rate": 8.572557471264368e-05, + "loss": 1.4687, + "step": 1987 + }, + { + "epoch": 2.14, + "learning_rate": 8.57183908045977e-05, + "loss": 1.2781, + "step": 1988 + }, + { + "epoch": 2.14, + "learning_rate": 8.571120689655174e-05, + "loss": 1.3464, + "step": 1989 + }, + { + "epoch": 2.14, + "learning_rate": 8.570402298850574e-05, + "loss": 1.1511, + "step": 1990 + }, + { + "epoch": 2.15, + "learning_rate": 8.569683908045978e-05, + "loss": 1.3038, + "step": 1991 + }, + { + "epoch": 2.15, + "learning_rate": 8.56896551724138e-05, + "loss": 1.2305, + "step": 1992 + }, + { + "epoch": 2.15, + "learning_rate": 8.568247126436783e-05, + "loss": 1.3402, + "step": 1993 + }, + { + "epoch": 2.15, + "learning_rate": 8.567528735632184e-05, + "loss": 1.284, + "step": 1994 + }, + { + "epoch": 2.15, + "learning_rate": 8.566810344827587e-05, + "loss": 1.3696, + "step": 1995 + }, + { + "epoch": 2.15, + "learning_rate": 8.566091954022989e-05, + "loss": 1.4212, + "step": 1996 + }, + { + "epoch": 2.15, + "learning_rate": 8.565373563218391e-05, + "loss": 1.345, + "step": 1997 + }, + { + "epoch": 2.15, + "learning_rate": 8.564655172413793e-05, + "loss": 1.145, + "step": 1998 + }, + { + "epoch": 2.15, + "learning_rate": 8.563936781609195e-05, + "loss": 1.1665, + "step": 1999 + }, + { + "epoch": 2.16, + "learning_rate": 8.563218390804599e-05, + "loss": 1.3479, + "step": 2000 + }, + { + "epoch": 2.16, + "eval_loss": 1.2424806356430054, + "eval_runtime": 174.9938, + "eval_samples_per_second": 127.262, + "eval_steps_per_second": 0.663, + "step": 2000 + }, + { + "epoch": 2.16, + "learning_rate": 8.5625e-05, + "loss": 1.2447, + "step": 2001 + }, + { + "epoch": 2.16, + "learning_rate": 8.561781609195403e-05, + "loss": 1.2341, + "step": 2002 + }, + { + "epoch": 2.16, + "learning_rate": 8.561063218390805e-05, + "loss": 1.2475, + "step": 2003 + }, + { + "epoch": 2.16, + "learning_rate": 8.560344827586207e-05, + "loss": 1.3972, + "step": 2004 + }, + { + "epoch": 2.16, + "learning_rate": 8.559626436781609e-05, + "loss": 1.3076, + "step": 2005 + }, + { + "epoch": 2.16, + "learning_rate": 8.558908045977012e-05, + "loss": 1.1969, + "step": 2006 + }, + { + "epoch": 2.16, + "learning_rate": 8.558189655172414e-05, + "loss": 1.3443, + "step": 2007 + }, + { + "epoch": 2.16, + "learning_rate": 8.557471264367816e-05, + "loss": 1.1257, + "step": 2008 + }, + { + "epoch": 2.16, + "learning_rate": 8.556752873563218e-05, + "loss": 1.3162, + "step": 2009 + }, + { + "epoch": 2.17, + "learning_rate": 8.556034482758622e-05, + "loss": 1.2838, + "step": 2010 + }, + { + "epoch": 2.17, + "learning_rate": 8.555316091954024e-05, + "loss": 1.2586, + "step": 2011 + }, + { + "epoch": 2.17, + "learning_rate": 8.554597701149426e-05, + "loss": 1.193, + "step": 2012 + }, + { + "epoch": 2.17, + "learning_rate": 8.553879310344828e-05, + "loss": 1.299, + "step": 2013 + }, + { + "epoch": 2.17, + "learning_rate": 8.553160919540231e-05, + "loss": 1.3021, + "step": 2014 + }, + { + "epoch": 2.17, + "learning_rate": 8.552442528735632e-05, + "loss": 1.2094, + "step": 2015 + }, + { + "epoch": 2.17, + "learning_rate": 8.551724137931035e-05, + "loss": 1.2792, + "step": 2016 + }, + { + "epoch": 2.17, + "learning_rate": 8.551005747126437e-05, + "loss": 1.2199, + "step": 2017 + }, + { + "epoch": 2.17, + "learning_rate": 8.55028735632184e-05, + "loss": 1.2101, + "step": 2018 + }, + { + "epoch": 2.18, + "learning_rate": 8.549568965517241e-05, + "loss": 1.3623, + "step": 2019 + }, + { + "epoch": 2.18, + "learning_rate": 8.548850574712645e-05, + "loss": 1.232, + "step": 2020 + }, + { + "epoch": 2.18, + "learning_rate": 8.548132183908047e-05, + "loss": 1.238, + "step": 2021 + }, + { + "epoch": 2.18, + "learning_rate": 8.547413793103448e-05, + "loss": 1.3642, + "step": 2022 + }, + { + "epoch": 2.18, + "learning_rate": 8.546695402298851e-05, + "loss": 1.2993, + "step": 2023 + }, + { + "epoch": 2.18, + "learning_rate": 8.545977011494253e-05, + "loss": 1.3928, + "step": 2024 + }, + { + "epoch": 2.18, + "learning_rate": 8.545258620689656e-05, + "loss": 1.3201, + "step": 2025 + }, + { + "epoch": 2.18, + "learning_rate": 8.544540229885057e-05, + "loss": 1.3729, + "step": 2026 + }, + { + "epoch": 2.18, + "learning_rate": 8.54382183908046e-05, + "loss": 1.118, + "step": 2027 + }, + { + "epoch": 2.19, + "learning_rate": 8.543103448275862e-05, + "loss": 1.1576, + "step": 2028 + }, + { + "epoch": 2.19, + "learning_rate": 8.542385057471264e-05, + "loss": 1.3309, + "step": 2029 + }, + { + "epoch": 2.19, + "learning_rate": 8.541666666666666e-05, + "loss": 1.269, + "step": 2030 + }, + { + "epoch": 2.19, + "learning_rate": 8.54094827586207e-05, + "loss": 1.3227, + "step": 2031 + }, + { + "epoch": 2.19, + "learning_rate": 8.540229885057472e-05, + "loss": 1.2595, + "step": 2032 + }, + { + "epoch": 2.19, + "learning_rate": 8.539511494252874e-05, + "loss": 1.3958, + "step": 2033 + }, + { + "epoch": 2.19, + "learning_rate": 8.538793103448276e-05, + "loss": 1.1943, + "step": 2034 + }, + { + "epoch": 2.19, + "learning_rate": 8.53807471264368e-05, + "loss": 1.2867, + "step": 2035 + }, + { + "epoch": 2.19, + "learning_rate": 8.53735632183908e-05, + "loss": 1.2429, + "step": 2036 + }, + { + "epoch": 2.2, + "learning_rate": 8.536637931034483e-05, + "loss": 1.2297, + "step": 2037 + }, + { + "epoch": 2.2, + "learning_rate": 8.535919540229885e-05, + "loss": 1.3881, + "step": 2038 + }, + { + "epoch": 2.2, + "learning_rate": 8.535201149425287e-05, + "loss": 1.4413, + "step": 2039 + }, + { + "epoch": 2.2, + "learning_rate": 8.53448275862069e-05, + "loss": 1.2025, + "step": 2040 + }, + { + "epoch": 2.2, + "learning_rate": 8.533764367816093e-05, + "loss": 1.4433, + "step": 2041 + }, + { + "epoch": 2.2, + "learning_rate": 8.533045977011495e-05, + "loss": 1.3146, + "step": 2042 + }, + { + "epoch": 2.2, + "learning_rate": 8.532327586206897e-05, + "loss": 1.2063, + "step": 2043 + }, + { + "epoch": 2.2, + "learning_rate": 8.531609195402299e-05, + "loss": 1.2921, + "step": 2044 + }, + { + "epoch": 2.2, + "learning_rate": 8.530890804597702e-05, + "loss": 1.225, + "step": 2045 + }, + { + "epoch": 2.2, + "learning_rate": 8.530172413793104e-05, + "loss": 1.3326, + "step": 2046 + }, + { + "epoch": 2.21, + "learning_rate": 8.529454022988506e-05, + "loss": 1.3135, + "step": 2047 + }, + { + "epoch": 2.21, + "learning_rate": 8.528735632183908e-05, + "loss": 1.2405, + "step": 2048 + }, + { + "epoch": 2.21, + "learning_rate": 8.52801724137931e-05, + "loss": 1.3764, + "step": 2049 + }, + { + "epoch": 2.21, + "learning_rate": 8.527298850574713e-05, + "loss": 1.1683, + "step": 2050 + }, + { + "epoch": 2.21, + "learning_rate": 8.526580459770115e-05, + "loss": 1.3346, + "step": 2051 + }, + { + "epoch": 2.21, + "learning_rate": 8.525862068965518e-05, + "loss": 1.3072, + "step": 2052 + }, + { + "epoch": 2.21, + "learning_rate": 8.52514367816092e-05, + "loss": 1.2528, + "step": 2053 + }, + { + "epoch": 2.21, + "learning_rate": 8.524425287356322e-05, + "loss": 1.3492, + "step": 2054 + }, + { + "epoch": 2.21, + "learning_rate": 8.523706896551724e-05, + "loss": 1.3043, + "step": 2055 + }, + { + "epoch": 2.22, + "learning_rate": 8.522988505747127e-05, + "loss": 1.3565, + "step": 2056 + }, + { + "epoch": 2.22, + "learning_rate": 8.522270114942528e-05, + "loss": 1.1566, + "step": 2057 + }, + { + "epoch": 2.22, + "learning_rate": 8.521551724137932e-05, + "loss": 1.2549, + "step": 2058 + }, + { + "epoch": 2.22, + "learning_rate": 8.520833333333334e-05, + "loss": 1.4549, + "step": 2059 + }, + { + "epoch": 2.22, + "learning_rate": 8.520114942528737e-05, + "loss": 1.1573, + "step": 2060 + }, + { + "epoch": 2.22, + "learning_rate": 8.519396551724138e-05, + "loss": 1.2963, + "step": 2061 + }, + { + "epoch": 2.22, + "learning_rate": 8.518678160919541e-05, + "loss": 1.34, + "step": 2062 + }, + { + "epoch": 2.22, + "learning_rate": 8.517959770114943e-05, + "loss": 1.4184, + "step": 2063 + }, + { + "epoch": 2.22, + "learning_rate": 8.517241379310345e-05, + "loss": 1.2422, + "step": 2064 + }, + { + "epoch": 2.23, + "learning_rate": 8.516522988505747e-05, + "loss": 1.3054, + "step": 2065 + }, + { + "epoch": 2.23, + "learning_rate": 8.51580459770115e-05, + "loss": 1.1558, + "step": 2066 + }, + { + "epoch": 2.23, + "learning_rate": 8.515086206896553e-05, + "loss": 1.2559, + "step": 2067 + }, + { + "epoch": 2.23, + "learning_rate": 8.514367816091955e-05, + "loss": 1.3212, + "step": 2068 + }, + { + "epoch": 2.23, + "learning_rate": 8.513649425287357e-05, + "loss": 1.3351, + "step": 2069 + }, + { + "epoch": 2.23, + "learning_rate": 8.51293103448276e-05, + "loss": 1.2912, + "step": 2070 + }, + { + "epoch": 2.23, + "learning_rate": 8.51221264367816e-05, + "loss": 1.3096, + "step": 2071 + }, + { + "epoch": 2.23, + "learning_rate": 8.511494252873564e-05, + "loss": 1.1659, + "step": 2072 + }, + { + "epoch": 2.23, + "learning_rate": 8.510775862068966e-05, + "loss": 1.3279, + "step": 2073 + }, + { + "epoch": 2.23, + "learning_rate": 8.510057471264368e-05, + "loss": 1.1562, + "step": 2074 + }, + { + "epoch": 2.24, + "learning_rate": 8.50933908045977e-05, + "loss": 1.2599, + "step": 2075 + }, + { + "epoch": 2.24, + "learning_rate": 8.508620689655172e-05, + "loss": 1.3312, + "step": 2076 + }, + { + "epoch": 2.24, + "learning_rate": 8.507902298850576e-05, + "loss": 1.3044, + "step": 2077 + }, + { + "epoch": 2.24, + "learning_rate": 8.507183908045978e-05, + "loss": 1.3639, + "step": 2078 + }, + { + "epoch": 2.24, + "learning_rate": 8.50646551724138e-05, + "loss": 1.2824, + "step": 2079 + }, + { + "epoch": 2.24, + "learning_rate": 8.505747126436782e-05, + "loss": 1.4359, + "step": 2080 + }, + { + "epoch": 2.24, + "learning_rate": 8.505028735632185e-05, + "loss": 1.2499, + "step": 2081 + }, + { + "epoch": 2.24, + "learning_rate": 8.504310344827586e-05, + "loss": 1.2795, + "step": 2082 + }, + { + "epoch": 2.24, + "learning_rate": 8.503591954022989e-05, + "loss": 1.157, + "step": 2083 + }, + { + "epoch": 2.25, + "learning_rate": 8.502873563218391e-05, + "loss": 1.2204, + "step": 2084 + }, + { + "epoch": 2.25, + "learning_rate": 8.502155172413793e-05, + "loss": 1.3455, + "step": 2085 + }, + { + "epoch": 2.25, + "learning_rate": 8.501436781609195e-05, + "loss": 1.3552, + "step": 2086 + }, + { + "epoch": 2.25, + "learning_rate": 8.500718390804599e-05, + "loss": 1.2139, + "step": 2087 + }, + { + "epoch": 2.25, + "learning_rate": 8.5e-05, + "loss": 1.3734, + "step": 2088 + }, + { + "epoch": 2.25, + "learning_rate": 8.499281609195403e-05, + "loss": 1.2861, + "step": 2089 + }, + { + "epoch": 2.25, + "learning_rate": 8.498563218390805e-05, + "loss": 1.2378, + "step": 2090 + }, + { + "epoch": 2.25, + "learning_rate": 8.497844827586208e-05, + "loss": 1.2053, + "step": 2091 + }, + { + "epoch": 2.25, + "learning_rate": 8.49712643678161e-05, + "loss": 1.4654, + "step": 2092 + }, + { + "epoch": 2.26, + "learning_rate": 8.496408045977012e-05, + "loss": 1.2473, + "step": 2093 + }, + { + "epoch": 2.26, + "learning_rate": 8.495689655172414e-05, + "loss": 1.2543, + "step": 2094 + }, + { + "epoch": 2.26, + "learning_rate": 8.494971264367818e-05, + "loss": 1.248, + "step": 2095 + }, + { + "epoch": 2.26, + "learning_rate": 8.494252873563218e-05, + "loss": 1.4177, + "step": 2096 + }, + { + "epoch": 2.26, + "learning_rate": 8.493534482758622e-05, + "loss": 1.2863, + "step": 2097 + }, + { + "epoch": 2.26, + "learning_rate": 8.492816091954024e-05, + "loss": 1.3413, + "step": 2098 + }, + { + "epoch": 2.26, + "learning_rate": 8.492097701149426e-05, + "loss": 1.3697, + "step": 2099 + }, + { + "epoch": 2.26, + "learning_rate": 8.491379310344828e-05, + "loss": 1.4275, + "step": 2100 + }, + { + "epoch": 2.26, + "learning_rate": 8.49066091954023e-05, + "loss": 1.2797, + "step": 2101 + }, + { + "epoch": 2.27, + "learning_rate": 8.489942528735633e-05, + "loss": 1.3495, + "step": 2102 + }, + { + "epoch": 2.27, + "learning_rate": 8.489224137931034e-05, + "loss": 1.2775, + "step": 2103 + }, + { + "epoch": 2.27, + "learning_rate": 8.488505747126437e-05, + "loss": 1.4852, + "step": 2104 + }, + { + "epoch": 2.27, + "learning_rate": 8.487787356321839e-05, + "loss": 1.1866, + "step": 2105 + }, + { + "epoch": 2.27, + "learning_rate": 8.487068965517243e-05, + "loss": 1.2768, + "step": 2106 + }, + { + "epoch": 2.27, + "learning_rate": 8.486350574712643e-05, + "loss": 1.3432, + "step": 2107 + }, + { + "epoch": 2.27, + "learning_rate": 8.485632183908047e-05, + "loss": 1.2376, + "step": 2108 + }, + { + "epoch": 2.27, + "learning_rate": 8.484913793103449e-05, + "loss": 1.2385, + "step": 2109 + }, + { + "epoch": 2.27, + "learning_rate": 8.484195402298851e-05, + "loss": 1.2185, + "step": 2110 + }, + { + "epoch": 2.27, + "learning_rate": 8.483477011494253e-05, + "loss": 1.2746, + "step": 2111 + }, + { + "epoch": 2.28, + "learning_rate": 8.482758620689656e-05, + "loss": 1.2178, + "step": 2112 + }, + { + "epoch": 2.28, + "learning_rate": 8.482040229885058e-05, + "loss": 1.2588, + "step": 2113 + }, + { + "epoch": 2.28, + "learning_rate": 8.48132183908046e-05, + "loss": 1.1995, + "step": 2114 + }, + { + "epoch": 2.28, + "learning_rate": 8.480603448275862e-05, + "loss": 1.3504, + "step": 2115 + }, + { + "epoch": 2.28, + "learning_rate": 8.479885057471266e-05, + "loss": 1.2687, + "step": 2116 + }, + { + "epoch": 2.28, + "learning_rate": 8.479166666666666e-05, + "loss": 1.4677, + "step": 2117 + }, + { + "epoch": 2.28, + "learning_rate": 8.47844827586207e-05, + "loss": 1.2989, + "step": 2118 + }, + { + "epoch": 2.28, + "learning_rate": 8.477729885057472e-05, + "loss": 1.2697, + "step": 2119 + }, + { + "epoch": 2.28, + "learning_rate": 8.477011494252874e-05, + "loss": 1.2923, + "step": 2120 + }, + { + "epoch": 2.29, + "learning_rate": 8.476293103448276e-05, + "loss": 1.4315, + "step": 2121 + }, + { + "epoch": 2.29, + "learning_rate": 8.475574712643679e-05, + "loss": 1.2558, + "step": 2122 + }, + { + "epoch": 2.29, + "learning_rate": 8.474856321839081e-05, + "loss": 1.2837, + "step": 2123 + }, + { + "epoch": 2.29, + "learning_rate": 8.474137931034483e-05, + "loss": 1.3409, + "step": 2124 + }, + { + "epoch": 2.29, + "learning_rate": 8.473419540229885e-05, + "loss": 1.2228, + "step": 2125 + }, + { + "epoch": 2.29, + "learning_rate": 8.472701149425287e-05, + "loss": 1.2538, + "step": 2126 + }, + { + "epoch": 2.29, + "learning_rate": 8.471982758620691e-05, + "loss": 1.212, + "step": 2127 + }, + { + "epoch": 2.29, + "learning_rate": 8.471264367816091e-05, + "loss": 1.3742, + "step": 2128 + }, + { + "epoch": 2.29, + "learning_rate": 8.470545977011495e-05, + "loss": 1.2927, + "step": 2129 + }, + { + "epoch": 2.3, + "learning_rate": 8.469827586206897e-05, + "loss": 1.2355, + "step": 2130 + }, + { + "epoch": 2.3, + "learning_rate": 8.469109195402299e-05, + "loss": 1.1948, + "step": 2131 + }, + { + "epoch": 2.3, + "learning_rate": 8.468390804597701e-05, + "loss": 1.3205, + "step": 2132 + }, + { + "epoch": 2.3, + "learning_rate": 8.467672413793104e-05, + "loss": 1.1829, + "step": 2133 + }, + { + "epoch": 2.3, + "learning_rate": 8.466954022988506e-05, + "loss": 1.2562, + "step": 2134 + }, + { + "epoch": 2.3, + "learning_rate": 8.466235632183908e-05, + "loss": 1.2123, + "step": 2135 + }, + { + "epoch": 2.3, + "learning_rate": 8.46551724137931e-05, + "loss": 1.3984, + "step": 2136 + }, + { + "epoch": 2.3, + "learning_rate": 8.464798850574714e-05, + "loss": 1.353, + "step": 2137 + }, + { + "epoch": 2.3, + "learning_rate": 8.464080459770116e-05, + "loss": 1.2267, + "step": 2138 + }, + { + "epoch": 2.3, + "learning_rate": 8.463362068965518e-05, + "loss": 1.2747, + "step": 2139 + }, + { + "epoch": 2.31, + "learning_rate": 8.46264367816092e-05, + "loss": 1.1727, + "step": 2140 + }, + { + "epoch": 2.31, + "learning_rate": 8.461925287356323e-05, + "loss": 1.1587, + "step": 2141 + }, + { + "epoch": 2.31, + "learning_rate": 8.461206896551724e-05, + "loss": 1.3151, + "step": 2142 + }, + { + "epoch": 2.31, + "learning_rate": 8.460488505747127e-05, + "loss": 1.3538, + "step": 2143 + }, + { + "epoch": 2.31, + "learning_rate": 8.459770114942529e-05, + "loss": 1.2581, + "step": 2144 + }, + { + "epoch": 2.31, + "learning_rate": 8.459051724137931e-05, + "loss": 1.1913, + "step": 2145 + }, + { + "epoch": 2.31, + "learning_rate": 8.458333333333333e-05, + "loss": 1.1545, + "step": 2146 + }, + { + "epoch": 2.31, + "learning_rate": 8.457614942528737e-05, + "loss": 1.2806, + "step": 2147 + }, + { + "epoch": 2.31, + "learning_rate": 8.456896551724139e-05, + "loss": 1.1498, + "step": 2148 + }, + { + "epoch": 2.32, + "learning_rate": 8.456178160919541e-05, + "loss": 1.3126, + "step": 2149 + }, + { + "epoch": 2.32, + "learning_rate": 8.455459770114943e-05, + "loss": 1.3029, + "step": 2150 + }, + { + "epoch": 2.32, + "learning_rate": 8.454741379310345e-05, + "loss": 1.3038, + "step": 2151 + }, + { + "epoch": 2.32, + "learning_rate": 8.454022988505747e-05, + "loss": 1.3394, + "step": 2152 + }, + { + "epoch": 2.32, + "learning_rate": 8.453304597701149e-05, + "loss": 1.2573, + "step": 2153 + }, + { + "epoch": 2.32, + "learning_rate": 8.452586206896552e-05, + "loss": 1.3224, + "step": 2154 + }, + { + "epoch": 2.32, + "learning_rate": 8.451867816091954e-05, + "loss": 1.2927, + "step": 2155 + }, + { + "epoch": 2.32, + "learning_rate": 8.451149425287356e-05, + "loss": 1.1312, + "step": 2156 + }, + { + "epoch": 2.32, + "learning_rate": 8.450431034482758e-05, + "loss": 1.4351, + "step": 2157 + }, + { + "epoch": 2.33, + "learning_rate": 8.449712643678162e-05, + "loss": 1.2484, + "step": 2158 + }, + { + "epoch": 2.33, + "learning_rate": 8.448994252873564e-05, + "loss": 1.2391, + "step": 2159 + }, + { + "epoch": 2.33, + "learning_rate": 8.448275862068966e-05, + "loss": 1.394, + "step": 2160 + }, + { + "epoch": 2.33, + "learning_rate": 8.447557471264368e-05, + "loss": 1.3922, + "step": 2161 + }, + { + "epoch": 2.33, + "learning_rate": 8.446839080459771e-05, + "loss": 1.201, + "step": 2162 + }, + { + "epoch": 2.33, + "learning_rate": 8.446120689655172e-05, + "loss": 1.2596, + "step": 2163 + }, + { + "epoch": 2.33, + "learning_rate": 8.445402298850575e-05, + "loss": 1.354, + "step": 2164 + }, + { + "epoch": 2.33, + "learning_rate": 8.444683908045977e-05, + "loss": 1.161, + "step": 2165 + }, + { + "epoch": 2.33, + "learning_rate": 8.44396551724138e-05, + "loss": 1.1647, + "step": 2166 + }, + { + "epoch": 2.34, + "learning_rate": 8.443247126436781e-05, + "loss": 1.234, + "step": 2167 + }, + { + "epoch": 2.34, + "learning_rate": 8.442528735632185e-05, + "loss": 1.3965, + "step": 2168 + }, + { + "epoch": 2.34, + "learning_rate": 8.441810344827587e-05, + "loss": 1.31, + "step": 2169 + }, + { + "epoch": 2.34, + "learning_rate": 8.441091954022989e-05, + "loss": 1.3102, + "step": 2170 + }, + { + "epoch": 2.34, + "learning_rate": 8.440373563218391e-05, + "loss": 1.1876, + "step": 2171 + }, + { + "epoch": 2.34, + "learning_rate": 8.439655172413794e-05, + "loss": 1.3516, + "step": 2172 + }, + { + "epoch": 2.34, + "learning_rate": 8.438936781609196e-05, + "loss": 1.4101, + "step": 2173 + }, + { + "epoch": 2.34, + "learning_rate": 8.438218390804598e-05, + "loss": 1.3628, + "step": 2174 + }, + { + "epoch": 2.34, + "learning_rate": 8.4375e-05, + "loss": 1.3027, + "step": 2175 + }, + { + "epoch": 2.34, + "learning_rate": 8.436781609195402e-05, + "loss": 1.2117, + "step": 2176 + }, + { + "epoch": 2.35, + "learning_rate": 8.436063218390805e-05, + "loss": 1.2552, + "step": 2177 + }, + { + "epoch": 2.35, + "learning_rate": 8.435344827586207e-05, + "loss": 1.1555, + "step": 2178 + }, + { + "epoch": 2.35, + "learning_rate": 8.43462643678161e-05, + "loss": 1.2532, + "step": 2179 + }, + { + "epoch": 2.35, + "learning_rate": 8.433908045977012e-05, + "loss": 1.2123, + "step": 2180 + }, + { + "epoch": 2.35, + "learning_rate": 8.433189655172414e-05, + "loss": 1.297, + "step": 2181 + }, + { + "epoch": 2.35, + "learning_rate": 8.432471264367816e-05, + "loss": 1.2599, + "step": 2182 + }, + { + "epoch": 2.35, + "learning_rate": 8.43175287356322e-05, + "loss": 1.2709, + "step": 2183 + }, + { + "epoch": 2.35, + "learning_rate": 8.43103448275862e-05, + "loss": 1.4138, + "step": 2184 + }, + { + "epoch": 2.35, + "learning_rate": 8.430316091954023e-05, + "loss": 1.2531, + "step": 2185 + }, + { + "epoch": 2.36, + "learning_rate": 8.429597701149426e-05, + "loss": 1.2829, + "step": 2186 + }, + { + "epoch": 2.36, + "learning_rate": 8.428879310344829e-05, + "loss": 1.2914, + "step": 2187 + }, + { + "epoch": 2.36, + "learning_rate": 8.42816091954023e-05, + "loss": 1.3795, + "step": 2188 + }, + { + "epoch": 2.36, + "learning_rate": 8.427442528735633e-05, + "loss": 1.263, + "step": 2189 + }, + { + "epoch": 2.36, + "learning_rate": 8.426724137931035e-05, + "loss": 1.2112, + "step": 2190 + }, + { + "epoch": 2.36, + "learning_rate": 8.426005747126437e-05, + "loss": 1.264, + "step": 2191 + }, + { + "epoch": 2.36, + "learning_rate": 8.425287356321839e-05, + "loss": 1.2435, + "step": 2192 + }, + { + "epoch": 2.36, + "learning_rate": 8.424568965517242e-05, + "loss": 1.2306, + "step": 2193 + }, + { + "epoch": 2.36, + "learning_rate": 8.423850574712644e-05, + "loss": 1.2978, + "step": 2194 + }, + { + "epoch": 2.37, + "learning_rate": 8.423132183908047e-05, + "loss": 1.349, + "step": 2195 + }, + { + "epoch": 2.37, + "learning_rate": 8.422413793103449e-05, + "loss": 1.3206, + "step": 2196 + }, + { + "epoch": 2.37, + "learning_rate": 8.421695402298852e-05, + "loss": 1.3482, + "step": 2197 + }, + { + "epoch": 2.37, + "learning_rate": 8.420977011494253e-05, + "loss": 1.3549, + "step": 2198 + }, + { + "epoch": 2.37, + "learning_rate": 8.420258620689656e-05, + "loss": 1.3559, + "step": 2199 + }, + { + "epoch": 2.37, + "learning_rate": 8.419540229885058e-05, + "loss": 1.2455, + "step": 2200 + }, + { + "epoch": 2.37, + "learning_rate": 8.41882183908046e-05, + "loss": 1.1845, + "step": 2201 + }, + { + "epoch": 2.37, + "learning_rate": 8.418103448275862e-05, + "loss": 1.2342, + "step": 2202 + }, + { + "epoch": 2.37, + "learning_rate": 8.417385057471264e-05, + "loss": 1.2189, + "step": 2203 + }, + { + "epoch": 2.38, + "learning_rate": 8.416666666666668e-05, + "loss": 1.259, + "step": 2204 + }, + { + "epoch": 2.38, + "learning_rate": 8.41594827586207e-05, + "loss": 1.274, + "step": 2205 + }, + { + "epoch": 2.38, + "learning_rate": 8.415229885057472e-05, + "loss": 1.3946, + "step": 2206 + }, + { + "epoch": 2.38, + "learning_rate": 8.414511494252874e-05, + "loss": 1.274, + "step": 2207 + }, + { + "epoch": 2.38, + "learning_rate": 8.413793103448277e-05, + "loss": 1.1452, + "step": 2208 + }, + { + "epoch": 2.38, + "learning_rate": 8.413074712643678e-05, + "loss": 1.1401, + "step": 2209 + }, + { + "epoch": 2.38, + "learning_rate": 8.412356321839081e-05, + "loss": 1.2281, + "step": 2210 + }, + { + "epoch": 2.38, + "learning_rate": 8.411637931034483e-05, + "loss": 1.3557, + "step": 2211 + }, + { + "epoch": 2.38, + "learning_rate": 8.410919540229885e-05, + "loss": 1.2136, + "step": 2212 + }, + { + "epoch": 2.38, + "learning_rate": 8.410201149425287e-05, + "loss": 1.2042, + "step": 2213 + }, + { + "epoch": 2.39, + "learning_rate": 8.40948275862069e-05, + "loss": 1.2795, + "step": 2214 + }, + { + "epoch": 2.39, + "learning_rate": 8.408764367816093e-05, + "loss": 1.2942, + "step": 2215 + }, + { + "epoch": 2.39, + "learning_rate": 8.408045977011495e-05, + "loss": 1.2687, + "step": 2216 + }, + { + "epoch": 2.39, + "learning_rate": 8.407327586206897e-05, + "loss": 1.1959, + "step": 2217 + }, + { + "epoch": 2.39, + "learning_rate": 8.4066091954023e-05, + "loss": 1.2575, + "step": 2218 + }, + { + "epoch": 2.39, + "learning_rate": 8.405890804597702e-05, + "loss": 1.3278, + "step": 2219 + }, + { + "epoch": 2.39, + "learning_rate": 8.405172413793104e-05, + "loss": 1.3322, + "step": 2220 + }, + { + "epoch": 2.39, + "learning_rate": 8.404454022988506e-05, + "loss": 1.2011, + "step": 2221 + }, + { + "epoch": 2.39, + "learning_rate": 8.40373563218391e-05, + "loss": 1.2567, + "step": 2222 + }, + { + "epoch": 2.4, + "learning_rate": 8.40301724137931e-05, + "loss": 1.2836, + "step": 2223 + }, + { + "epoch": 2.4, + "learning_rate": 8.402298850574714e-05, + "loss": 1.3375, + "step": 2224 + }, + { + "epoch": 2.4, + "learning_rate": 8.401580459770116e-05, + "loss": 1.3045, + "step": 2225 + }, + { + "epoch": 2.4, + "learning_rate": 8.400862068965518e-05, + "loss": 1.3446, + "step": 2226 + }, + { + "epoch": 2.4, + "learning_rate": 8.40014367816092e-05, + "loss": 1.2602, + "step": 2227 + }, + { + "epoch": 2.4, + "learning_rate": 8.399425287356322e-05, + "loss": 1.3798, + "step": 2228 + }, + { + "epoch": 2.4, + "learning_rate": 8.398706896551725e-05, + "loss": 1.3839, + "step": 2229 + }, + { + "epoch": 2.4, + "learning_rate": 8.397988505747126e-05, + "loss": 1.2581, + "step": 2230 + }, + { + "epoch": 2.4, + "learning_rate": 8.397270114942529e-05, + "loss": 1.431, + "step": 2231 + }, + { + "epoch": 2.41, + "learning_rate": 8.396551724137931e-05, + "loss": 1.4446, + "step": 2232 + }, + { + "epoch": 2.41, + "learning_rate": 8.395833333333333e-05, + "loss": 1.3805, + "step": 2233 + }, + { + "epoch": 2.41, + "learning_rate": 8.395114942528735e-05, + "loss": 1.2666, + "step": 2234 + }, + { + "epoch": 2.41, + "learning_rate": 8.394396551724139e-05, + "loss": 1.212, + "step": 2235 + }, + { + "epoch": 2.41, + "learning_rate": 8.39367816091954e-05, + "loss": 1.2225, + "step": 2236 + }, + { + "epoch": 2.41, + "learning_rate": 8.392959770114943e-05, + "loss": 1.3882, + "step": 2237 + }, + { + "epoch": 2.41, + "learning_rate": 8.392241379310345e-05, + "loss": 1.4532, + "step": 2238 + }, + { + "epoch": 2.41, + "learning_rate": 8.391522988505748e-05, + "loss": 1.2565, + "step": 2239 + }, + { + "epoch": 2.41, + "learning_rate": 8.39080459770115e-05, + "loss": 1.2647, + "step": 2240 + }, + { + "epoch": 2.41, + "learning_rate": 8.390086206896552e-05, + "loss": 1.3328, + "step": 2241 + }, + { + "epoch": 2.42, + "learning_rate": 8.389367816091954e-05, + "loss": 1.3058, + "step": 2242 + }, + { + "epoch": 2.42, + "learning_rate": 8.388649425287358e-05, + "loss": 1.2115, + "step": 2243 + }, + { + "epoch": 2.42, + "learning_rate": 8.387931034482758e-05, + "loss": 1.2474, + "step": 2244 + }, + { + "epoch": 2.42, + "learning_rate": 8.387212643678162e-05, + "loss": 1.3032, + "step": 2245 + }, + { + "epoch": 2.42, + "learning_rate": 8.386494252873564e-05, + "loss": 1.3202, + "step": 2246 + }, + { + "epoch": 2.42, + "learning_rate": 8.385775862068966e-05, + "loss": 1.3869, + "step": 2247 + }, + { + "epoch": 2.42, + "learning_rate": 8.385057471264368e-05, + "loss": 1.232, + "step": 2248 + }, + { + "epoch": 2.42, + "learning_rate": 8.384339080459771e-05, + "loss": 1.431, + "step": 2249 + }, + { + "epoch": 2.42, + "learning_rate": 8.383620689655173e-05, + "loss": 1.1491, + "step": 2250 + }, + { + "epoch": 2.42, + "eval_loss": 1.2094504833221436, + "eval_runtime": 177.9273, + "eval_samples_per_second": 125.163, + "eval_steps_per_second": 0.652, + "step": 2250 + }, + { + "epoch": 2.43, + "learning_rate": 8.382902298850575e-05, + "loss": 1.3244, + "step": 2251 + }, + { + "epoch": 2.43, + "learning_rate": 8.382183908045977e-05, + "loss": 1.1693, + "step": 2252 + }, + { + "epoch": 2.43, + "learning_rate": 8.381465517241379e-05, + "loss": 1.2654, + "step": 2253 + }, + { + "epoch": 2.43, + "learning_rate": 8.380747126436783e-05, + "loss": 1.3616, + "step": 2254 + }, + { + "epoch": 2.43, + "learning_rate": 8.380028735632183e-05, + "loss": 1.1914, + "step": 2255 + }, + { + "epoch": 2.43, + "learning_rate": 8.379310344827587e-05, + "loss": 1.3605, + "step": 2256 + }, + { + "epoch": 2.43, + "learning_rate": 8.378591954022989e-05, + "loss": 1.2821, + "step": 2257 + }, + { + "epoch": 2.43, + "learning_rate": 8.377873563218391e-05, + "loss": 1.2435, + "step": 2258 + }, + { + "epoch": 2.43, + "learning_rate": 8.377155172413793e-05, + "loss": 1.3591, + "step": 2259 + }, + { + "epoch": 2.44, + "learning_rate": 8.376436781609196e-05, + "loss": 1.2959, + "step": 2260 + }, + { + "epoch": 2.44, + "learning_rate": 8.375718390804598e-05, + "loss": 1.2617, + "step": 2261 + }, + { + "epoch": 2.44, + "learning_rate": 8.375e-05, + "loss": 1.3044, + "step": 2262 + }, + { + "epoch": 2.44, + "learning_rate": 8.374281609195402e-05, + "loss": 1.2764, + "step": 2263 + }, + { + "epoch": 2.44, + "learning_rate": 8.373563218390806e-05, + "loss": 1.312, + "step": 2264 + }, + { + "epoch": 2.44, + "learning_rate": 8.372844827586206e-05, + "loss": 1.3094, + "step": 2265 + }, + { + "epoch": 2.44, + "learning_rate": 8.37212643678161e-05, + "loss": 1.2881, + "step": 2266 + }, + { + "epoch": 2.44, + "learning_rate": 8.371408045977012e-05, + "loss": 1.2029, + "step": 2267 + }, + { + "epoch": 2.44, + "learning_rate": 8.370689655172415e-05, + "loss": 1.1726, + "step": 2268 + }, + { + "epoch": 2.45, + "learning_rate": 8.369971264367816e-05, + "loss": 1.249, + "step": 2269 + }, + { + "epoch": 2.45, + "learning_rate": 8.369252873563219e-05, + "loss": 1.2727, + "step": 2270 + }, + { + "epoch": 2.45, + "learning_rate": 8.368534482758621e-05, + "loss": 1.4334, + "step": 2271 + }, + { + "epoch": 2.45, + "learning_rate": 8.367816091954023e-05, + "loss": 1.3494, + "step": 2272 + }, + { + "epoch": 2.45, + "learning_rate": 8.367097701149425e-05, + "loss": 1.2285, + "step": 2273 + }, + { + "epoch": 2.45, + "learning_rate": 8.366379310344829e-05, + "loss": 1.449, + "step": 2274 + }, + { + "epoch": 2.45, + "learning_rate": 8.365660919540231e-05, + "loss": 1.2359, + "step": 2275 + }, + { + "epoch": 2.45, + "learning_rate": 8.364942528735633e-05, + "loss": 1.2286, + "step": 2276 + }, + { + "epoch": 2.45, + "learning_rate": 8.364224137931035e-05, + "loss": 1.4824, + "step": 2277 + }, + { + "epoch": 2.45, + "learning_rate": 8.363505747126437e-05, + "loss": 1.3049, + "step": 2278 + }, + { + "epoch": 2.46, + "learning_rate": 8.362787356321839e-05, + "loss": 1.293, + "step": 2279 + }, + { + "epoch": 2.46, + "learning_rate": 8.362068965517241e-05, + "loss": 1.2172, + "step": 2280 + }, + { + "epoch": 2.46, + "learning_rate": 8.361350574712644e-05, + "loss": 1.3147, + "step": 2281 + }, + { + "epoch": 2.46, + "learning_rate": 8.360632183908046e-05, + "loss": 1.2321, + "step": 2282 + }, + { + "epoch": 2.46, + "learning_rate": 8.359913793103448e-05, + "loss": 1.0903, + "step": 2283 + }, + { + "epoch": 2.46, + "learning_rate": 8.35919540229885e-05, + "loss": 1.2269, + "step": 2284 + }, + { + "epoch": 2.46, + "learning_rate": 8.358477011494254e-05, + "loss": 1.3217, + "step": 2285 + }, + { + "epoch": 2.46, + "learning_rate": 8.357758620689656e-05, + "loss": 1.1997, + "step": 2286 + }, + { + "epoch": 2.46, + "learning_rate": 8.357040229885058e-05, + "loss": 1.3606, + "step": 2287 + }, + { + "epoch": 2.47, + "learning_rate": 8.35632183908046e-05, + "loss": 1.328, + "step": 2288 + }, + { + "epoch": 2.47, + "learning_rate": 8.355603448275863e-05, + "loss": 1.2275, + "step": 2289 + }, + { + "epoch": 2.47, + "learning_rate": 8.354885057471264e-05, + "loss": 1.1985, + "step": 2290 + }, + { + "epoch": 2.47, + "learning_rate": 8.354166666666667e-05, + "loss": 1.2093, + "step": 2291 + }, + { + "epoch": 2.47, + "learning_rate": 8.35344827586207e-05, + "loss": 1.1688, + "step": 2292 + }, + { + "epoch": 2.47, + "learning_rate": 8.352729885057471e-05, + "loss": 1.3609, + "step": 2293 + }, + { + "epoch": 2.47, + "learning_rate": 8.352011494252873e-05, + "loss": 1.3528, + "step": 2294 + }, + { + "epoch": 2.47, + "learning_rate": 8.351293103448277e-05, + "loss": 1.3666, + "step": 2295 + }, + { + "epoch": 2.47, + "learning_rate": 8.350574712643679e-05, + "loss": 1.3869, + "step": 2296 + }, + { + "epoch": 2.48, + "learning_rate": 8.349856321839081e-05, + "loss": 1.3069, + "step": 2297 + }, + { + "epoch": 2.48, + "learning_rate": 8.349137931034483e-05, + "loss": 1.2564, + "step": 2298 + }, + { + "epoch": 2.48, + "learning_rate": 8.348419540229886e-05, + "loss": 1.3394, + "step": 2299 + }, + { + "epoch": 2.48, + "learning_rate": 8.347701149425288e-05, + "loss": 1.2536, + "step": 2300 + }, + { + "epoch": 2.48, + "learning_rate": 8.34698275862069e-05, + "loss": 1.3103, + "step": 2301 + }, + { + "epoch": 2.48, + "learning_rate": 8.346264367816092e-05, + "loss": 1.2541, + "step": 2302 + }, + { + "epoch": 2.48, + "learning_rate": 8.345545977011494e-05, + "loss": 1.2472, + "step": 2303 + }, + { + "epoch": 2.48, + "learning_rate": 8.344827586206896e-05, + "loss": 1.4048, + "step": 2304 + }, + { + "epoch": 2.48, + "learning_rate": 8.344109195402299e-05, + "loss": 1.2119, + "step": 2305 + }, + { + "epoch": 2.48, + "learning_rate": 8.343390804597702e-05, + "loss": 1.4078, + "step": 2306 + }, + { + "epoch": 2.49, + "learning_rate": 8.342672413793104e-05, + "loss": 1.2702, + "step": 2307 + }, + { + "epoch": 2.49, + "learning_rate": 8.341954022988506e-05, + "loss": 1.2733, + "step": 2308 + }, + { + "epoch": 2.49, + "learning_rate": 8.341235632183908e-05, + "loss": 1.28, + "step": 2309 + }, + { + "epoch": 2.49, + "learning_rate": 8.340517241379311e-05, + "loss": 1.2091, + "step": 2310 + }, + { + "epoch": 2.49, + "learning_rate": 8.339798850574712e-05, + "loss": 1.2583, + "step": 2311 + }, + { + "epoch": 2.49, + "learning_rate": 8.339080459770115e-05, + "loss": 1.2633, + "step": 2312 + }, + { + "epoch": 2.49, + "learning_rate": 8.338362068965517e-05, + "loss": 1.4718, + "step": 2313 + }, + { + "epoch": 2.49, + "learning_rate": 8.33764367816092e-05, + "loss": 1.2193, + "step": 2314 + }, + { + "epoch": 2.49, + "learning_rate": 8.336925287356322e-05, + "loss": 1.3204, + "step": 2315 + }, + { + "epoch": 2.5, + "learning_rate": 8.336206896551725e-05, + "loss": 1.2979, + "step": 2316 + }, + { + "epoch": 2.5, + "learning_rate": 8.335488505747127e-05, + "loss": 1.4393, + "step": 2317 + }, + { + "epoch": 2.5, + "learning_rate": 8.334770114942529e-05, + "loss": 1.3064, + "step": 2318 + }, + { + "epoch": 2.5, + "learning_rate": 8.334051724137931e-05, + "loss": 1.2407, + "step": 2319 + }, + { + "epoch": 2.5, + "learning_rate": 8.333333333333334e-05, + "loss": 1.2738, + "step": 2320 + }, + { + "epoch": 2.5, + "learning_rate": 8.332614942528736e-05, + "loss": 1.4598, + "step": 2321 + }, + { + "epoch": 2.5, + "learning_rate": 8.331896551724138e-05, + "loss": 1.3055, + "step": 2322 + }, + { + "epoch": 2.5, + "learning_rate": 8.33117816091954e-05, + "loss": 1.3272, + "step": 2323 + }, + { + "epoch": 2.5, + "learning_rate": 8.330459770114944e-05, + "loss": 1.2148, + "step": 2324 + }, + { + "epoch": 2.51, + "learning_rate": 8.329741379310345e-05, + "loss": 1.3603, + "step": 2325 + }, + { + "epoch": 2.51, + "learning_rate": 8.329022988505748e-05, + "loss": 1.2488, + "step": 2326 + }, + { + "epoch": 2.51, + "learning_rate": 8.32830459770115e-05, + "loss": 1.2018, + "step": 2327 + }, + { + "epoch": 2.51, + "learning_rate": 8.327586206896552e-05, + "loss": 1.2423, + "step": 2328 + }, + { + "epoch": 2.51, + "learning_rate": 8.326867816091954e-05, + "loss": 1.3157, + "step": 2329 + }, + { + "epoch": 2.51, + "learning_rate": 8.326149425287356e-05, + "loss": 1.4452, + "step": 2330 + }, + { + "epoch": 2.51, + "learning_rate": 8.32543103448276e-05, + "loss": 1.18, + "step": 2331 + }, + { + "epoch": 2.51, + "learning_rate": 8.324712643678162e-05, + "loss": 1.251, + "step": 2332 + }, + { + "epoch": 2.51, + "learning_rate": 8.323994252873564e-05, + "loss": 1.2869, + "step": 2333 + }, + { + "epoch": 2.52, + "learning_rate": 8.323275862068966e-05, + "loss": 1.338, + "step": 2334 + }, + { + "epoch": 2.52, + "learning_rate": 8.322557471264369e-05, + "loss": 1.3924, + "step": 2335 + }, + { + "epoch": 2.52, + "learning_rate": 8.32183908045977e-05, + "loss": 1.375, + "step": 2336 + }, + { + "epoch": 2.52, + "learning_rate": 8.321120689655173e-05, + "loss": 1.3629, + "step": 2337 + }, + { + "epoch": 2.52, + "learning_rate": 8.320402298850575e-05, + "loss": 1.2054, + "step": 2338 + }, + { + "epoch": 2.52, + "learning_rate": 8.319683908045977e-05, + "loss": 1.2661, + "step": 2339 + }, + { + "epoch": 2.52, + "learning_rate": 8.318965517241379e-05, + "loss": 1.2559, + "step": 2340 + }, + { + "epoch": 2.52, + "learning_rate": 8.318247126436783e-05, + "loss": 1.3897, + "step": 2341 + }, + { + "epoch": 2.52, + "learning_rate": 8.317528735632185e-05, + "loss": 1.3697, + "step": 2342 + }, + { + "epoch": 2.52, + "learning_rate": 8.316810344827587e-05, + "loss": 1.2651, + "step": 2343 + }, + { + "epoch": 2.53, + "learning_rate": 8.316091954022989e-05, + "loss": 1.1641, + "step": 2344 + }, + { + "epoch": 2.53, + "learning_rate": 8.315373563218392e-05, + "loss": 1.0916, + "step": 2345 + }, + { + "epoch": 2.53, + "learning_rate": 8.314655172413793e-05, + "loss": 1.2947, + "step": 2346 + }, + { + "epoch": 2.53, + "learning_rate": 8.313936781609196e-05, + "loss": 1.3648, + "step": 2347 + }, + { + "epoch": 2.53, + "learning_rate": 8.313218390804598e-05, + "loss": 1.2889, + "step": 2348 + }, + { + "epoch": 2.53, + "learning_rate": 8.312500000000001e-05, + "loss": 1.3367, + "step": 2349 + }, + { + "epoch": 2.53, + "learning_rate": 8.311781609195402e-05, + "loss": 1.4155, + "step": 2350 + }, + { + "epoch": 2.53, + "learning_rate": 8.311063218390806e-05, + "loss": 1.2559, + "step": 2351 + }, + { + "epoch": 2.53, + "learning_rate": 8.310344827586208e-05, + "loss": 1.4425, + "step": 2352 + }, + { + "epoch": 2.54, + "learning_rate": 8.30962643678161e-05, + "loss": 1.2756, + "step": 2353 + }, + { + "epoch": 2.54, + "learning_rate": 8.308908045977012e-05, + "loss": 1.2661, + "step": 2354 + }, + { + "epoch": 2.54, + "learning_rate": 8.308189655172414e-05, + "loss": 1.4411, + "step": 2355 + }, + { + "epoch": 2.54, + "learning_rate": 8.307471264367817e-05, + "loss": 1.3892, + "step": 2356 + }, + { + "epoch": 2.54, + "learning_rate": 8.306752873563218e-05, + "loss": 1.4125, + "step": 2357 + }, + { + "epoch": 2.54, + "learning_rate": 8.306034482758621e-05, + "loss": 1.2999, + "step": 2358 + }, + { + "epoch": 2.54, + "learning_rate": 8.305316091954023e-05, + "loss": 1.261, + "step": 2359 + }, + { + "epoch": 2.54, + "learning_rate": 8.304597701149425e-05, + "loss": 1.3505, + "step": 2360 + }, + { + "epoch": 2.54, + "learning_rate": 8.303879310344827e-05, + "loss": 1.3508, + "step": 2361 + }, + { + "epoch": 2.55, + "learning_rate": 8.30316091954023e-05, + "loss": 1.2622, + "step": 2362 + }, + { + "epoch": 2.55, + "learning_rate": 8.302442528735633e-05, + "loss": 1.2515, + "step": 2363 + }, + { + "epoch": 2.55, + "learning_rate": 8.301724137931035e-05, + "loss": 1.3035, + "step": 2364 + }, + { + "epoch": 2.55, + "learning_rate": 8.301005747126437e-05, + "loss": 1.2281, + "step": 2365 + }, + { + "epoch": 2.55, + "learning_rate": 8.30028735632184e-05, + "loss": 1.2935, + "step": 2366 + }, + { + "epoch": 2.55, + "learning_rate": 8.299568965517242e-05, + "loss": 1.2475, + "step": 2367 + }, + { + "epoch": 2.55, + "learning_rate": 8.298850574712644e-05, + "loss": 1.2773, + "step": 2368 + }, + { + "epoch": 2.55, + "learning_rate": 8.298132183908046e-05, + "loss": 1.3362, + "step": 2369 + }, + { + "epoch": 2.55, + "learning_rate": 8.29741379310345e-05, + "loss": 1.3318, + "step": 2370 + }, + { + "epoch": 2.55, + "learning_rate": 8.29669540229885e-05, + "loss": 1.3271, + "step": 2371 + }, + { + "epoch": 2.56, + "learning_rate": 8.295977011494254e-05, + "loss": 1.3212, + "step": 2372 + }, + { + "epoch": 2.56, + "learning_rate": 8.295258620689656e-05, + "loss": 1.2853, + "step": 2373 + }, + { + "epoch": 2.56, + "learning_rate": 8.294540229885058e-05, + "loss": 1.2335, + "step": 2374 + }, + { + "epoch": 2.56, + "learning_rate": 8.29382183908046e-05, + "loss": 1.3011, + "step": 2375 + }, + { + "epoch": 2.56, + "learning_rate": 8.293103448275863e-05, + "loss": 1.248, + "step": 2376 + }, + { + "epoch": 2.56, + "learning_rate": 8.292385057471265e-05, + "loss": 1.2005, + "step": 2377 + }, + { + "epoch": 2.56, + "learning_rate": 8.291666666666667e-05, + "loss": 1.531, + "step": 2378 + }, + { + "epoch": 2.56, + "learning_rate": 8.290948275862069e-05, + "loss": 1.2306, + "step": 2379 + }, + { + "epoch": 2.56, + "learning_rate": 8.290229885057471e-05, + "loss": 1.2273, + "step": 2380 + }, + { + "epoch": 2.57, + "learning_rate": 8.289511494252875e-05, + "loss": 1.3791, + "step": 2381 + }, + { + "epoch": 2.57, + "learning_rate": 8.288793103448275e-05, + "loss": 1.2564, + "step": 2382 + }, + { + "epoch": 2.57, + "learning_rate": 8.288074712643679e-05, + "loss": 1.154, + "step": 2383 + }, + { + "epoch": 2.57, + "learning_rate": 8.287356321839081e-05, + "loss": 1.1904, + "step": 2384 + }, + { + "epoch": 2.57, + "learning_rate": 8.286637931034483e-05, + "loss": 1.2157, + "step": 2385 + }, + { + "epoch": 2.57, + "learning_rate": 8.285919540229885e-05, + "loss": 1.3315, + "step": 2386 + }, + { + "epoch": 2.57, + "learning_rate": 8.285201149425288e-05, + "loss": 1.2715, + "step": 2387 + }, + { + "epoch": 2.57, + "learning_rate": 8.28448275862069e-05, + "loss": 1.2982, + "step": 2388 + }, + { + "epoch": 2.57, + "learning_rate": 8.283764367816092e-05, + "loss": 1.3423, + "step": 2389 + }, + { + "epoch": 2.58, + "learning_rate": 8.283045977011494e-05, + "loss": 1.3043, + "step": 2390 + }, + { + "epoch": 2.58, + "learning_rate": 8.282327586206898e-05, + "loss": 1.324, + "step": 2391 + }, + { + "epoch": 2.58, + "learning_rate": 8.281609195402298e-05, + "loss": 1.1519, + "step": 2392 + }, + { + "epoch": 2.58, + "learning_rate": 8.280890804597702e-05, + "loss": 1.2586, + "step": 2393 + }, + { + "epoch": 2.58, + "learning_rate": 8.280172413793104e-05, + "loss": 1.2949, + "step": 2394 + }, + { + "epoch": 2.58, + "learning_rate": 8.279454022988507e-05, + "loss": 1.1839, + "step": 2395 + }, + { + "epoch": 2.58, + "learning_rate": 8.278735632183908e-05, + "loss": 1.3391, + "step": 2396 + }, + { + "epoch": 2.58, + "learning_rate": 8.278017241379311e-05, + "loss": 1.382, + "step": 2397 + }, + { + "epoch": 2.58, + "learning_rate": 8.277298850574713e-05, + "loss": 1.3366, + "step": 2398 + }, + { + "epoch": 2.59, + "learning_rate": 8.276580459770115e-05, + "loss": 1.4026, + "step": 2399 + }, + { + "epoch": 2.59, + "learning_rate": 8.275862068965517e-05, + "loss": 1.3373, + "step": 2400 + }, + { + "epoch": 2.59, + "learning_rate": 8.275143678160921e-05, + "loss": 1.2826, + "step": 2401 + }, + { + "epoch": 2.59, + "learning_rate": 8.274425287356323e-05, + "loss": 1.2411, + "step": 2402 + }, + { + "epoch": 2.59, + "learning_rate": 8.273706896551725e-05, + "loss": 1.2881, + "step": 2403 + }, + { + "epoch": 2.59, + "learning_rate": 8.272988505747127e-05, + "loss": 1.1445, + "step": 2404 + }, + { + "epoch": 2.59, + "learning_rate": 8.27227011494253e-05, + "loss": 1.1802, + "step": 2405 + }, + { + "epoch": 2.59, + "learning_rate": 8.271551724137931e-05, + "loss": 1.2591, + "step": 2406 + }, + { + "epoch": 2.59, + "learning_rate": 8.270833333333333e-05, + "loss": 1.1767, + "step": 2407 + }, + { + "epoch": 2.59, + "learning_rate": 8.270114942528736e-05, + "loss": 1.483, + "step": 2408 + }, + { + "epoch": 2.6, + "learning_rate": 8.269396551724138e-05, + "loss": 1.2157, + "step": 2409 + }, + { + "epoch": 2.6, + "learning_rate": 8.26867816091954e-05, + "loss": 1.3647, + "step": 2410 + }, + { + "epoch": 2.6, + "learning_rate": 8.267959770114942e-05, + "loss": 1.3611, + "step": 2411 + }, + { + "epoch": 2.6, + "learning_rate": 8.267241379310346e-05, + "loss": 1.3524, + "step": 2412 + }, + { + "epoch": 2.6, + "learning_rate": 8.266522988505748e-05, + "loss": 1.4742, + "step": 2413 + }, + { + "epoch": 2.6, + "learning_rate": 8.26580459770115e-05, + "loss": 1.0834, + "step": 2414 + }, + { + "epoch": 2.6, + "learning_rate": 8.265086206896552e-05, + "loss": 1.3292, + "step": 2415 + }, + { + "epoch": 2.6, + "learning_rate": 8.264367816091955e-05, + "loss": 1.2581, + "step": 2416 + }, + { + "epoch": 2.6, + "learning_rate": 8.263649425287356e-05, + "loss": 1.2882, + "step": 2417 + }, + { + "epoch": 2.61, + "learning_rate": 8.262931034482759e-05, + "loss": 1.3136, + "step": 2418 + }, + { + "epoch": 2.61, + "learning_rate": 8.262212643678161e-05, + "loss": 1.2103, + "step": 2419 + }, + { + "epoch": 2.61, + "learning_rate": 8.261494252873563e-05, + "loss": 1.3136, + "step": 2420 + }, + { + "epoch": 2.61, + "learning_rate": 8.260775862068965e-05, + "loss": 1.3299, + "step": 2421 + }, + { + "epoch": 2.61, + "learning_rate": 8.260057471264369e-05, + "loss": 1.4672, + "step": 2422 + }, + { + "epoch": 2.61, + "learning_rate": 8.259339080459771e-05, + "loss": 1.2823, + "step": 2423 + }, + { + "epoch": 2.61, + "learning_rate": 8.258620689655173e-05, + "loss": 1.2671, + "step": 2424 + }, + { + "epoch": 2.61, + "learning_rate": 8.257902298850575e-05, + "loss": 1.3184, + "step": 2425 + }, + { + "epoch": 2.61, + "learning_rate": 8.257183908045978e-05, + "loss": 1.3086, + "step": 2426 + }, + { + "epoch": 2.62, + "learning_rate": 8.256465517241379e-05, + "loss": 1.2362, + "step": 2427 + }, + { + "epoch": 2.62, + "learning_rate": 8.255747126436782e-05, + "loss": 1.3059, + "step": 2428 + }, + { + "epoch": 2.62, + "learning_rate": 8.255028735632184e-05, + "loss": 1.2996, + "step": 2429 + }, + { + "epoch": 2.62, + "learning_rate": 8.254310344827588e-05, + "loss": 1.1537, + "step": 2430 + }, + { + "epoch": 2.62, + "learning_rate": 8.253591954022988e-05, + "loss": 1.2807, + "step": 2431 + }, + { + "epoch": 2.62, + "learning_rate": 8.25287356321839e-05, + "loss": 1.2216, + "step": 2432 + }, + { + "epoch": 2.62, + "learning_rate": 8.252155172413794e-05, + "loss": 1.2044, + "step": 2433 + }, + { + "epoch": 2.62, + "learning_rate": 8.251436781609196e-05, + "loss": 1.333, + "step": 2434 + }, + { + "epoch": 2.62, + "learning_rate": 8.250718390804598e-05, + "loss": 1.4068, + "step": 2435 + }, + { + "epoch": 2.62, + "learning_rate": 8.25e-05, + "loss": 1.2454, + "step": 2436 + }, + { + "epoch": 2.63, + "learning_rate": 8.249281609195403e-05, + "loss": 1.3741, + "step": 2437 + }, + { + "epoch": 2.63, + "learning_rate": 8.248563218390804e-05, + "loss": 1.4153, + "step": 2438 + }, + { + "epoch": 2.63, + "learning_rate": 8.247844827586207e-05, + "loss": 1.3141, + "step": 2439 + }, + { + "epoch": 2.63, + "learning_rate": 8.24712643678161e-05, + "loss": 1.4441, + "step": 2440 + }, + { + "epoch": 2.63, + "learning_rate": 8.246408045977011e-05, + "loss": 1.3056, + "step": 2441 + }, + { + "epoch": 2.63, + "learning_rate": 8.245689655172414e-05, + "loss": 1.1552, + "step": 2442 + }, + { + "epoch": 2.63, + "learning_rate": 8.244971264367817e-05, + "loss": 1.2029, + "step": 2443 + }, + { + "epoch": 2.63, + "learning_rate": 8.244252873563219e-05, + "loss": 1.2207, + "step": 2444 + }, + { + "epoch": 2.63, + "learning_rate": 8.243534482758621e-05, + "loss": 1.3188, + "step": 2445 + }, + { + "epoch": 2.64, + "learning_rate": 8.242816091954023e-05, + "loss": 1.5081, + "step": 2446 + }, + { + "epoch": 2.64, + "learning_rate": 8.242097701149426e-05, + "loss": 1.2394, + "step": 2447 + }, + { + "epoch": 2.64, + "learning_rate": 8.241379310344828e-05, + "loss": 1.3644, + "step": 2448 + }, + { + "epoch": 2.64, + "learning_rate": 8.24066091954023e-05, + "loss": 1.3131, + "step": 2449 + }, + { + "epoch": 2.64, + "learning_rate": 8.239942528735632e-05, + "loss": 1.4581, + "step": 2450 + }, + { + "epoch": 2.64, + "learning_rate": 8.239224137931036e-05, + "loss": 1.2847, + "step": 2451 + }, + { + "epoch": 2.64, + "learning_rate": 8.238505747126437e-05, + "loss": 1.3199, + "step": 2452 + }, + { + "epoch": 2.64, + "learning_rate": 8.23778735632184e-05, + "loss": 1.2979, + "step": 2453 + }, + { + "epoch": 2.64, + "learning_rate": 8.237068965517242e-05, + "loss": 1.2058, + "step": 2454 + }, + { + "epoch": 2.65, + "learning_rate": 8.236350574712644e-05, + "loss": 1.2081, + "step": 2455 + }, + { + "epoch": 2.65, + "learning_rate": 8.235632183908046e-05, + "loss": 1.326, + "step": 2456 + }, + { + "epoch": 2.65, + "learning_rate": 8.234913793103448e-05, + "loss": 1.351, + "step": 2457 + }, + { + "epoch": 2.65, + "learning_rate": 8.234195402298851e-05, + "loss": 1.2775, + "step": 2458 + }, + { + "epoch": 2.65, + "learning_rate": 8.233477011494252e-05, + "loss": 1.1068, + "step": 2459 + }, + { + "epoch": 2.65, + "learning_rate": 8.232758620689656e-05, + "loss": 1.2441, + "step": 2460 + }, + { + "epoch": 2.65, + "learning_rate": 8.232040229885058e-05, + "loss": 1.2194, + "step": 2461 + }, + { + "epoch": 2.65, + "learning_rate": 8.231321839080461e-05, + "loss": 1.339, + "step": 2462 + }, + { + "epoch": 2.65, + "learning_rate": 8.230603448275862e-05, + "loss": 1.2096, + "step": 2463 + }, + { + "epoch": 2.66, + "learning_rate": 8.229885057471265e-05, + "loss": 1.1747, + "step": 2464 + }, + { + "epoch": 2.66, + "learning_rate": 8.229166666666667e-05, + "loss": 1.2943, + "step": 2465 + }, + { + "epoch": 2.66, + "learning_rate": 8.228448275862069e-05, + "loss": 1.2618, + "step": 2466 + }, + { + "epoch": 2.66, + "learning_rate": 8.227729885057471e-05, + "loss": 1.3968, + "step": 2467 + }, + { + "epoch": 2.66, + "learning_rate": 8.227011494252874e-05, + "loss": 1.2591, + "step": 2468 + }, + { + "epoch": 2.66, + "learning_rate": 8.226293103448277e-05, + "loss": 1.3228, + "step": 2469 + }, + { + "epoch": 2.66, + "learning_rate": 8.225574712643679e-05, + "loss": 1.4031, + "step": 2470 + }, + { + "epoch": 2.66, + "learning_rate": 8.22485632183908e-05, + "loss": 1.3082, + "step": 2471 + }, + { + "epoch": 2.66, + "learning_rate": 8.224137931034484e-05, + "loss": 1.2119, + "step": 2472 + }, + { + "epoch": 2.66, + "learning_rate": 8.223419540229885e-05, + "loss": 1.3744, + "step": 2473 + }, + { + "epoch": 2.67, + "learning_rate": 8.222701149425288e-05, + "loss": 1.2292, + "step": 2474 + }, + { + "epoch": 2.67, + "learning_rate": 8.22198275862069e-05, + "loss": 1.2239, + "step": 2475 + }, + { + "epoch": 2.67, + "learning_rate": 8.221264367816093e-05, + "loss": 1.2197, + "step": 2476 + }, + { + "epoch": 2.67, + "learning_rate": 8.220545977011494e-05, + "loss": 1.2716, + "step": 2477 + }, + { + "epoch": 2.67, + "learning_rate": 8.219827586206898e-05, + "loss": 1.3839, + "step": 2478 + }, + { + "epoch": 2.67, + "learning_rate": 8.2191091954023e-05, + "loss": 1.3292, + "step": 2479 + }, + { + "epoch": 2.67, + "learning_rate": 8.218390804597702e-05, + "loss": 1.3506, + "step": 2480 + }, + { + "epoch": 2.67, + "learning_rate": 8.217672413793104e-05, + "loss": 1.1985, + "step": 2481 + }, + { + "epoch": 2.67, + "learning_rate": 8.216954022988507e-05, + "loss": 1.2486, + "step": 2482 + }, + { + "epoch": 2.68, + "learning_rate": 8.216235632183909e-05, + "loss": 1.4613, + "step": 2483 + }, + { + "epoch": 2.68, + "learning_rate": 8.21551724137931e-05, + "loss": 1.2804, + "step": 2484 + }, + { + "epoch": 2.68, + "learning_rate": 8.214798850574713e-05, + "loss": 1.3705, + "step": 2485 + }, + { + "epoch": 2.68, + "learning_rate": 8.214080459770115e-05, + "loss": 1.2226, + "step": 2486 + }, + { + "epoch": 2.68, + "learning_rate": 8.213362068965517e-05, + "loss": 1.3299, + "step": 2487 + }, + { + "epoch": 2.68, + "learning_rate": 8.212643678160919e-05, + "loss": 1.2015, + "step": 2488 + }, + { + "epoch": 2.68, + "learning_rate": 8.211925287356323e-05, + "loss": 1.3506, + "step": 2489 + }, + { + "epoch": 2.68, + "learning_rate": 8.211206896551725e-05, + "loss": 1.3122, + "step": 2490 + }, + { + "epoch": 2.68, + "learning_rate": 8.210488505747127e-05, + "loss": 1.3343, + "step": 2491 + }, + { + "epoch": 2.69, + "learning_rate": 8.209770114942529e-05, + "loss": 1.4091, + "step": 2492 + }, + { + "epoch": 2.69, + "learning_rate": 8.209051724137932e-05, + "loss": 1.2206, + "step": 2493 + }, + { + "epoch": 2.69, + "learning_rate": 8.208333333333334e-05, + "loss": 1.252, + "step": 2494 + }, + { + "epoch": 2.69, + "learning_rate": 8.207614942528736e-05, + "loss": 1.2672, + "step": 2495 + }, + { + "epoch": 2.69, + "learning_rate": 8.206896551724138e-05, + "loss": 1.2038, + "step": 2496 + }, + { + "epoch": 2.69, + "learning_rate": 8.206178160919542e-05, + "loss": 1.2026, + "step": 2497 + }, + { + "epoch": 2.69, + "learning_rate": 8.205459770114942e-05, + "loss": 1.3919, + "step": 2498 + }, + { + "epoch": 2.69, + "learning_rate": 8.204741379310346e-05, + "loss": 1.2054, + "step": 2499 + }, + { + "epoch": 2.69, + "learning_rate": 8.204022988505748e-05, + "loss": 1.1658, + "step": 2500 + }, + { + "epoch": 2.69, + "eval_loss": 1.1977629661560059, + "eval_runtime": 174.7818, + "eval_samples_per_second": 127.416, + "eval_steps_per_second": 0.664, + "step": 2500 + }, + { + "epoch": 2.7, + "learning_rate": 8.20330459770115e-05, + "loss": 1.3748, + "step": 2501 + }, + { + "epoch": 2.7, + "learning_rate": 8.202586206896552e-05, + "loss": 1.2139, + "step": 2502 + }, + { + "epoch": 2.7, + "learning_rate": 8.201867816091955e-05, + "loss": 1.2101, + "step": 2503 + }, + { + "epoch": 2.7, + "learning_rate": 8.201149425287357e-05, + "loss": 1.1775, + "step": 2504 + }, + { + "epoch": 2.7, + "learning_rate": 8.200431034482759e-05, + "loss": 1.2846, + "step": 2505 + }, + { + "epoch": 2.7, + "learning_rate": 8.199712643678161e-05, + "loss": 1.3273, + "step": 2506 + }, + { + "epoch": 2.7, + "learning_rate": 8.198994252873565e-05, + "loss": 1.2974, + "step": 2507 + }, + { + "epoch": 2.7, + "learning_rate": 8.198275862068965e-05, + "loss": 1.1519, + "step": 2508 + }, + { + "epoch": 2.7, + "learning_rate": 8.197557471264367e-05, + "loss": 1.2394, + "step": 2509 + }, + { + "epoch": 2.7, + "learning_rate": 8.19683908045977e-05, + "loss": 1.2315, + "step": 2510 + }, + { + "epoch": 2.71, + "learning_rate": 8.196120689655173e-05, + "loss": 1.3863, + "step": 2511 + }, + { + "epoch": 2.71, + "learning_rate": 8.195402298850575e-05, + "loss": 1.2509, + "step": 2512 + }, + { + "epoch": 2.71, + "learning_rate": 8.194683908045977e-05, + "loss": 1.2997, + "step": 2513 + }, + { + "epoch": 2.71, + "learning_rate": 8.19396551724138e-05, + "loss": 1.2153, + "step": 2514 + }, + { + "epoch": 2.71, + "learning_rate": 8.193247126436782e-05, + "loss": 1.2604, + "step": 2515 + }, + { + "epoch": 2.71, + "learning_rate": 8.192528735632184e-05, + "loss": 1.4645, + "step": 2516 + }, + { + "epoch": 2.71, + "learning_rate": 8.191810344827586e-05, + "loss": 1.3843, + "step": 2517 + }, + { + "epoch": 2.71, + "learning_rate": 8.19109195402299e-05, + "loss": 1.2109, + "step": 2518 + }, + { + "epoch": 2.71, + "learning_rate": 8.19037356321839e-05, + "loss": 1.3002, + "step": 2519 + }, + { + "epoch": 2.72, + "learning_rate": 8.189655172413794e-05, + "loss": 1.2464, + "step": 2520 + }, + { + "epoch": 2.72, + "learning_rate": 8.188936781609196e-05, + "loss": 1.282, + "step": 2521 + }, + { + "epoch": 2.72, + "learning_rate": 8.188218390804598e-05, + "loss": 1.3419, + "step": 2522 + }, + { + "epoch": 2.72, + "learning_rate": 8.1875e-05, + "loss": 1.2126, + "step": 2523 + }, + { + "epoch": 2.72, + "learning_rate": 8.186781609195403e-05, + "loss": 1.1807, + "step": 2524 + }, + { + "epoch": 2.72, + "learning_rate": 8.186063218390805e-05, + "loss": 1.1793, + "step": 2525 + }, + { + "epoch": 2.72, + "learning_rate": 8.185344827586207e-05, + "loss": 1.2582, + "step": 2526 + }, + { + "epoch": 2.72, + "learning_rate": 8.184626436781609e-05, + "loss": 1.3749, + "step": 2527 + }, + { + "epoch": 2.72, + "learning_rate": 8.183908045977013e-05, + "loss": 1.3148, + "step": 2528 + }, + { + "epoch": 2.73, + "learning_rate": 8.183189655172415e-05, + "loss": 1.2985, + "step": 2529 + }, + { + "epoch": 2.73, + "learning_rate": 8.182471264367817e-05, + "loss": 1.2491, + "step": 2530 + }, + { + "epoch": 2.73, + "learning_rate": 8.181752873563219e-05, + "loss": 1.2466, + "step": 2531 + }, + { + "epoch": 2.73, + "learning_rate": 8.181034482758622e-05, + "loss": 1.2951, + "step": 2532 + }, + { + "epoch": 2.73, + "learning_rate": 8.180316091954023e-05, + "loss": 1.2867, + "step": 2533 + }, + { + "epoch": 2.73, + "learning_rate": 8.179597701149425e-05, + "loss": 1.3356, + "step": 2534 + }, + { + "epoch": 2.73, + "learning_rate": 8.178879310344828e-05, + "loss": 1.1102, + "step": 2535 + }, + { + "epoch": 2.73, + "learning_rate": 8.17816091954023e-05, + "loss": 1.269, + "step": 2536 + }, + { + "epoch": 2.73, + "learning_rate": 8.177442528735632e-05, + "loss": 1.1567, + "step": 2537 + }, + { + "epoch": 2.73, + "learning_rate": 8.176724137931034e-05, + "loss": 1.3056, + "step": 2538 + }, + { + "epoch": 2.74, + "learning_rate": 8.176005747126438e-05, + "loss": 1.2925, + "step": 2539 + }, + { + "epoch": 2.74, + "learning_rate": 8.175287356321838e-05, + "loss": 1.3632, + "step": 2540 + }, + { + "epoch": 2.74, + "learning_rate": 8.174568965517242e-05, + "loss": 1.299, + "step": 2541 + }, + { + "epoch": 2.74, + "learning_rate": 8.173850574712644e-05, + "loss": 1.301, + "step": 2542 + }, + { + "epoch": 2.74, + "learning_rate": 8.173132183908047e-05, + "loss": 1.2846, + "step": 2543 + }, + { + "epoch": 2.74, + "learning_rate": 8.172413793103448e-05, + "loss": 1.3272, + "step": 2544 + }, + { + "epoch": 2.74, + "learning_rate": 8.171695402298851e-05, + "loss": 1.2125, + "step": 2545 + }, + { + "epoch": 2.74, + "learning_rate": 8.170977011494253e-05, + "loss": 1.3103, + "step": 2546 + }, + { + "epoch": 2.74, + "learning_rate": 8.170258620689655e-05, + "loss": 1.1114, + "step": 2547 + }, + { + "epoch": 2.75, + "learning_rate": 8.169540229885057e-05, + "loss": 1.1497, + "step": 2548 + }, + { + "epoch": 2.75, + "learning_rate": 8.168821839080461e-05, + "loss": 1.2838, + "step": 2549 + }, + { + "epoch": 2.75, + "learning_rate": 8.168103448275863e-05, + "loss": 1.2954, + "step": 2550 + }, + { + "epoch": 2.75, + "learning_rate": 8.167385057471265e-05, + "loss": 1.3162, + "step": 2551 + }, + { + "epoch": 2.75, + "learning_rate": 8.166666666666667e-05, + "loss": 1.4126, + "step": 2552 + }, + { + "epoch": 2.75, + "learning_rate": 8.16594827586207e-05, + "loss": 1.3384, + "step": 2553 + }, + { + "epoch": 2.75, + "learning_rate": 8.165229885057471e-05, + "loss": 1.215, + "step": 2554 + }, + { + "epoch": 2.75, + "learning_rate": 8.164511494252874e-05, + "loss": 1.2611, + "step": 2555 + }, + { + "epoch": 2.75, + "learning_rate": 8.163793103448276e-05, + "loss": 1.202, + "step": 2556 + }, + { + "epoch": 2.76, + "learning_rate": 8.16307471264368e-05, + "loss": 1.1891, + "step": 2557 + }, + { + "epoch": 2.76, + "learning_rate": 8.16235632183908e-05, + "loss": 1.3914, + "step": 2558 + }, + { + "epoch": 2.76, + "learning_rate": 8.161637931034482e-05, + "loss": 1.2055, + "step": 2559 + }, + { + "epoch": 2.76, + "learning_rate": 8.160919540229886e-05, + "loss": 1.3261, + "step": 2560 + }, + { + "epoch": 2.76, + "learning_rate": 8.160201149425288e-05, + "loss": 1.409, + "step": 2561 + }, + { + "epoch": 2.76, + "learning_rate": 8.15948275862069e-05, + "loss": 1.2689, + "step": 2562 + }, + { + "epoch": 2.76, + "learning_rate": 8.158764367816092e-05, + "loss": 1.3361, + "step": 2563 + }, + { + "epoch": 2.76, + "learning_rate": 8.158045977011495e-05, + "loss": 1.2124, + "step": 2564 + }, + { + "epoch": 2.76, + "learning_rate": 8.157327586206896e-05, + "loss": 1.2968, + "step": 2565 + }, + { + "epoch": 2.77, + "learning_rate": 8.1566091954023e-05, + "loss": 1.3741, + "step": 2566 + }, + { + "epoch": 2.77, + "learning_rate": 8.155890804597701e-05, + "loss": 1.3469, + "step": 2567 + }, + { + "epoch": 2.77, + "learning_rate": 8.155172413793103e-05, + "loss": 1.2809, + "step": 2568 + }, + { + "epoch": 2.77, + "learning_rate": 8.154454022988505e-05, + "loss": 1.2831, + "step": 2569 + }, + { + "epoch": 2.77, + "learning_rate": 8.153735632183909e-05, + "loss": 1.2391, + "step": 2570 + }, + { + "epoch": 2.77, + "learning_rate": 8.153017241379311e-05, + "loss": 1.2814, + "step": 2571 + }, + { + "epoch": 2.77, + "learning_rate": 8.152298850574713e-05, + "loss": 1.1979, + "step": 2572 + }, + { + "epoch": 2.77, + "learning_rate": 8.151580459770115e-05, + "loss": 1.3175, + "step": 2573 + }, + { + "epoch": 2.77, + "learning_rate": 8.150862068965518e-05, + "loss": 1.3495, + "step": 2574 + }, + { + "epoch": 2.77, + "learning_rate": 8.15014367816092e-05, + "loss": 1.3169, + "step": 2575 + }, + { + "epoch": 2.78, + "learning_rate": 8.149425287356322e-05, + "loss": 1.381, + "step": 2576 + }, + { + "epoch": 2.78, + "learning_rate": 8.148706896551724e-05, + "loss": 1.3329, + "step": 2577 + }, + { + "epoch": 2.78, + "learning_rate": 8.147988505747128e-05, + "loss": 1.3753, + "step": 2578 + }, + { + "epoch": 2.78, + "learning_rate": 8.147270114942528e-05, + "loss": 1.3071, + "step": 2579 + }, + { + "epoch": 2.78, + "learning_rate": 8.146551724137932e-05, + "loss": 1.2872, + "step": 2580 + }, + { + "epoch": 2.78, + "learning_rate": 8.145833333333334e-05, + "loss": 1.1608, + "step": 2581 + }, + { + "epoch": 2.78, + "learning_rate": 8.145114942528736e-05, + "loss": 1.34, + "step": 2582 + }, + { + "epoch": 2.78, + "learning_rate": 8.144396551724138e-05, + "loss": 1.2532, + "step": 2583 + }, + { + "epoch": 2.78, + "learning_rate": 8.143678160919541e-05, + "loss": 1.2666, + "step": 2584 + }, + { + "epoch": 2.79, + "learning_rate": 8.142959770114943e-05, + "loss": 1.3193, + "step": 2585 + }, + { + "epoch": 2.79, + "learning_rate": 8.142241379310344e-05, + "loss": 1.2796, + "step": 2586 + }, + { + "epoch": 2.79, + "learning_rate": 8.141522988505747e-05, + "loss": 1.34, + "step": 2587 + }, + { + "epoch": 2.79, + "learning_rate": 8.14080459770115e-05, + "loss": 1.3781, + "step": 2588 + }, + { + "epoch": 2.79, + "learning_rate": 8.140086206896553e-05, + "loss": 1.2651, + "step": 2589 + }, + { + "epoch": 2.79, + "learning_rate": 8.139367816091954e-05, + "loss": 1.2992, + "step": 2590 + }, + { + "epoch": 2.79, + "learning_rate": 8.138649425287357e-05, + "loss": 1.3995, + "step": 2591 + }, + { + "epoch": 2.79, + "learning_rate": 8.137931034482759e-05, + "loss": 1.2799, + "step": 2592 + }, + { + "epoch": 2.79, + "learning_rate": 8.137212643678161e-05, + "loss": 1.4251, + "step": 2593 + }, + { + "epoch": 2.8, + "learning_rate": 8.136494252873563e-05, + "loss": 1.157, + "step": 2594 + }, + { + "epoch": 2.8, + "learning_rate": 8.135775862068966e-05, + "loss": 1.2715, + "step": 2595 + }, + { + "epoch": 2.8, + "learning_rate": 8.135057471264368e-05, + "loss": 1.2671, + "step": 2596 + }, + { + "epoch": 2.8, + "learning_rate": 8.13433908045977e-05, + "loss": 1.2511, + "step": 2597 + }, + { + "epoch": 2.8, + "learning_rate": 8.133620689655173e-05, + "loss": 1.3417, + "step": 2598 + }, + { + "epoch": 2.8, + "learning_rate": 8.132902298850576e-05, + "loss": 1.1489, + "step": 2599 + }, + { + "epoch": 2.8, + "learning_rate": 8.132183908045977e-05, + "loss": 1.3118, + "step": 2600 + }, + { + "epoch": 2.8, + "learning_rate": 8.13146551724138e-05, + "loss": 1.1293, + "step": 2601 + }, + { + "epoch": 2.8, + "learning_rate": 8.130747126436782e-05, + "loss": 1.3081, + "step": 2602 + }, + { + "epoch": 2.8, + "learning_rate": 8.130028735632184e-05, + "loss": 1.2582, + "step": 2603 + }, + { + "epoch": 2.81, + "learning_rate": 8.129310344827586e-05, + "loss": 1.2084, + "step": 2604 + }, + { + "epoch": 2.81, + "learning_rate": 8.12859195402299e-05, + "loss": 1.239, + "step": 2605 + }, + { + "epoch": 2.81, + "learning_rate": 8.127873563218391e-05, + "loss": 1.2251, + "step": 2606 + }, + { + "epoch": 2.81, + "learning_rate": 8.127155172413794e-05, + "loss": 1.2771, + "step": 2607 + }, + { + "epoch": 2.81, + "learning_rate": 8.126436781609196e-05, + "loss": 1.2719, + "step": 2608 + }, + { + "epoch": 2.81, + "learning_rate": 8.125718390804599e-05, + "loss": 1.2964, + "step": 2609 + }, + { + "epoch": 2.81, + "learning_rate": 8.125000000000001e-05, + "loss": 1.2688, + "step": 2610 + }, + { + "epoch": 2.81, + "learning_rate": 8.124281609195402e-05, + "loss": 1.1618, + "step": 2611 + }, + { + "epoch": 2.81, + "learning_rate": 8.123563218390805e-05, + "loss": 1.1356, + "step": 2612 + }, + { + "epoch": 2.82, + "learning_rate": 8.122844827586207e-05, + "loss": 1.3099, + "step": 2613 + }, + { + "epoch": 2.82, + "learning_rate": 8.122126436781609e-05, + "loss": 1.2634, + "step": 2614 + }, + { + "epoch": 2.82, + "learning_rate": 8.121408045977011e-05, + "loss": 1.2239, + "step": 2615 + }, + { + "epoch": 2.82, + "learning_rate": 8.120689655172415e-05, + "loss": 1.4031, + "step": 2616 + }, + { + "epoch": 2.82, + "learning_rate": 8.119971264367817e-05, + "loss": 1.4514, + "step": 2617 + }, + { + "epoch": 2.82, + "learning_rate": 8.119252873563219e-05, + "loss": 1.2299, + "step": 2618 + }, + { + "epoch": 2.82, + "learning_rate": 8.11853448275862e-05, + "loss": 1.2926, + "step": 2619 + }, + { + "epoch": 2.82, + "learning_rate": 8.117816091954024e-05, + "loss": 1.3105, + "step": 2620 + }, + { + "epoch": 2.82, + "learning_rate": 8.117097701149425e-05, + "loss": 1.2645, + "step": 2621 + }, + { + "epoch": 2.83, + "learning_rate": 8.116379310344828e-05, + "loss": 1.371, + "step": 2622 + }, + { + "epoch": 2.83, + "learning_rate": 8.11566091954023e-05, + "loss": 1.2351, + "step": 2623 + }, + { + "epoch": 2.83, + "learning_rate": 8.114942528735633e-05, + "loss": 1.3117, + "step": 2624 + }, + { + "epoch": 2.83, + "learning_rate": 8.114224137931034e-05, + "loss": 1.2194, + "step": 2625 + }, + { + "epoch": 2.83, + "learning_rate": 8.113505747126438e-05, + "loss": 1.1997, + "step": 2626 + }, + { + "epoch": 2.83, + "learning_rate": 8.11278735632184e-05, + "loss": 1.2529, + "step": 2627 + }, + { + "epoch": 2.83, + "learning_rate": 8.112068965517242e-05, + "loss": 1.3526, + "step": 2628 + }, + { + "epoch": 2.83, + "learning_rate": 8.111350574712644e-05, + "loss": 1.2649, + "step": 2629 + }, + { + "epoch": 2.83, + "learning_rate": 8.110632183908047e-05, + "loss": 1.2699, + "step": 2630 + }, + { + "epoch": 2.84, + "learning_rate": 8.109913793103449e-05, + "loss": 1.1964, + "step": 2631 + }, + { + "epoch": 2.84, + "learning_rate": 8.109195402298851e-05, + "loss": 1.3121, + "step": 2632 + }, + { + "epoch": 2.84, + "learning_rate": 8.108477011494253e-05, + "loss": 1.3379, + "step": 2633 + }, + { + "epoch": 2.84, + "learning_rate": 8.107758620689657e-05, + "loss": 1.345, + "step": 2634 + }, + { + "epoch": 2.84, + "learning_rate": 8.107040229885057e-05, + "loss": 1.2481, + "step": 2635 + }, + { + "epoch": 2.84, + "learning_rate": 8.106321839080459e-05, + "loss": 1.2379, + "step": 2636 + }, + { + "epoch": 2.84, + "learning_rate": 8.105603448275863e-05, + "loss": 1.2728, + "step": 2637 + }, + { + "epoch": 2.84, + "learning_rate": 8.104885057471265e-05, + "loss": 1.0546, + "step": 2638 + }, + { + "epoch": 2.84, + "learning_rate": 8.104166666666667e-05, + "loss": 1.3036, + "step": 2639 + }, + { + "epoch": 2.84, + "learning_rate": 8.103448275862069e-05, + "loss": 1.3501, + "step": 2640 + }, + { + "epoch": 2.85, + "learning_rate": 8.102729885057472e-05, + "loss": 1.1538, + "step": 2641 + }, + { + "epoch": 2.85, + "learning_rate": 8.102011494252874e-05, + "loss": 1.1907, + "step": 2642 + }, + { + "epoch": 2.85, + "learning_rate": 8.101293103448276e-05, + "loss": 1.3319, + "step": 2643 + }, + { + "epoch": 2.85, + "learning_rate": 8.100574712643678e-05, + "loss": 1.28, + "step": 2644 + }, + { + "epoch": 2.85, + "learning_rate": 8.099856321839082e-05, + "loss": 1.2835, + "step": 2645 + }, + { + "epoch": 2.85, + "learning_rate": 8.099137931034482e-05, + "loss": 1.1317, + "step": 2646 + }, + { + "epoch": 2.85, + "learning_rate": 8.098419540229886e-05, + "loss": 1.2836, + "step": 2647 + }, + { + "epoch": 2.85, + "learning_rate": 8.097701149425288e-05, + "loss": 1.2828, + "step": 2648 + }, + { + "epoch": 2.85, + "learning_rate": 8.09698275862069e-05, + "loss": 1.2004, + "step": 2649 + }, + { + "epoch": 2.86, + "learning_rate": 8.096264367816092e-05, + "loss": 1.1736, + "step": 2650 + }, + { + "epoch": 2.86, + "learning_rate": 8.095545977011495e-05, + "loss": 1.3052, + "step": 2651 + }, + { + "epoch": 2.86, + "learning_rate": 8.094827586206897e-05, + "loss": 1.3433, + "step": 2652 + }, + { + "epoch": 2.86, + "learning_rate": 8.094109195402299e-05, + "loss": 1.4135, + "step": 2653 + }, + { + "epoch": 2.86, + "learning_rate": 8.093390804597701e-05, + "loss": 1.2626, + "step": 2654 + }, + { + "epoch": 2.86, + "learning_rate": 8.092672413793105e-05, + "loss": 1.3275, + "step": 2655 + }, + { + "epoch": 2.86, + "learning_rate": 8.091954022988507e-05, + "loss": 1.4265, + "step": 2656 + }, + { + "epoch": 2.86, + "learning_rate": 8.091235632183909e-05, + "loss": 1.2324, + "step": 2657 + }, + { + "epoch": 2.86, + "learning_rate": 8.090517241379311e-05, + "loss": 1.2377, + "step": 2658 + }, + { + "epoch": 2.87, + "learning_rate": 8.089798850574714e-05, + "loss": 1.0753, + "step": 2659 + }, + { + "epoch": 2.87, + "learning_rate": 8.089080459770115e-05, + "loss": 1.268, + "step": 2660 + }, + { + "epoch": 2.87, + "learning_rate": 8.088362068965518e-05, + "loss": 1.2233, + "step": 2661 + }, + { + "epoch": 2.87, + "learning_rate": 8.08764367816092e-05, + "loss": 1.2752, + "step": 2662 + }, + { + "epoch": 2.87, + "learning_rate": 8.086925287356322e-05, + "loss": 1.158, + "step": 2663 + }, + { + "epoch": 2.87, + "learning_rate": 8.086206896551724e-05, + "loss": 1.3134, + "step": 2664 + }, + { + "epoch": 2.87, + "learning_rate": 8.085488505747126e-05, + "loss": 1.1422, + "step": 2665 + }, + { + "epoch": 2.87, + "learning_rate": 8.08477011494253e-05, + "loss": 1.2205, + "step": 2666 + }, + { + "epoch": 2.87, + "learning_rate": 8.08405172413793e-05, + "loss": 1.3962, + "step": 2667 + }, + { + "epoch": 2.88, + "learning_rate": 8.083333333333334e-05, + "loss": 1.3088, + "step": 2668 + }, + { + "epoch": 2.88, + "learning_rate": 8.082614942528736e-05, + "loss": 1.1464, + "step": 2669 + }, + { + "epoch": 2.88, + "learning_rate": 8.081896551724139e-05, + "loss": 1.366, + "step": 2670 + }, + { + "epoch": 2.88, + "learning_rate": 8.08117816091954e-05, + "loss": 1.2834, + "step": 2671 + }, + { + "epoch": 2.88, + "learning_rate": 8.080459770114943e-05, + "loss": 1.3436, + "step": 2672 + }, + { + "epoch": 2.88, + "learning_rate": 8.079741379310345e-05, + "loss": 1.2513, + "step": 2673 + }, + { + "epoch": 2.88, + "learning_rate": 8.079022988505747e-05, + "loss": 1.2495, + "step": 2674 + }, + { + "epoch": 2.88, + "learning_rate": 8.07830459770115e-05, + "loss": 1.2069, + "step": 2675 + }, + { + "epoch": 2.88, + "learning_rate": 8.077586206896553e-05, + "loss": 1.2793, + "step": 2676 + }, + { + "epoch": 2.88, + "learning_rate": 8.076867816091955e-05, + "loss": 1.3374, + "step": 2677 + }, + { + "epoch": 2.89, + "learning_rate": 8.076149425287357e-05, + "loss": 1.2984, + "step": 2678 + }, + { + "epoch": 2.89, + "learning_rate": 8.075431034482759e-05, + "loss": 1.2688, + "step": 2679 + }, + { + "epoch": 2.89, + "learning_rate": 8.074712643678162e-05, + "loss": 1.2108, + "step": 2680 + }, + { + "epoch": 2.89, + "learning_rate": 8.073994252873563e-05, + "loss": 1.2227, + "step": 2681 + }, + { + "epoch": 2.89, + "learning_rate": 8.073275862068966e-05, + "loss": 1.3259, + "step": 2682 + }, + { + "epoch": 2.89, + "learning_rate": 8.072557471264368e-05, + "loss": 1.2553, + "step": 2683 + }, + { + "epoch": 2.89, + "learning_rate": 8.07183908045977e-05, + "loss": 1.2885, + "step": 2684 + }, + { + "epoch": 2.89, + "learning_rate": 8.071120689655172e-05, + "loss": 1.2432, + "step": 2685 + }, + { + "epoch": 2.89, + "learning_rate": 8.070402298850576e-05, + "loss": 1.1703, + "step": 2686 + }, + { + "epoch": 2.9, + "learning_rate": 8.069683908045978e-05, + "loss": 1.3712, + "step": 2687 + }, + { + "epoch": 2.9, + "learning_rate": 8.06896551724138e-05, + "loss": 1.256, + "step": 2688 + }, + { + "epoch": 2.9, + "learning_rate": 8.068247126436782e-05, + "loss": 1.1551, + "step": 2689 + }, + { + "epoch": 2.9, + "learning_rate": 8.067528735632184e-05, + "loss": 1.261, + "step": 2690 + }, + { + "epoch": 2.9, + "learning_rate": 8.066810344827587e-05, + "loss": 1.2791, + "step": 2691 + }, + { + "epoch": 2.9, + "learning_rate": 8.066091954022988e-05, + "loss": 1.1245, + "step": 2692 + }, + { + "epoch": 2.9, + "learning_rate": 8.065373563218391e-05, + "loss": 1.3446, + "step": 2693 + }, + { + "epoch": 2.9, + "learning_rate": 8.064655172413793e-05, + "loss": 1.5055, + "step": 2694 + }, + { + "epoch": 2.9, + "learning_rate": 8.063936781609195e-05, + "loss": 1.2858, + "step": 2695 + }, + { + "epoch": 2.91, + "learning_rate": 8.063218390804597e-05, + "loss": 1.1917, + "step": 2696 + }, + { + "epoch": 2.91, + "learning_rate": 8.062500000000001e-05, + "loss": 1.2928, + "step": 2697 + }, + { + "epoch": 2.91, + "learning_rate": 8.061781609195403e-05, + "loss": 1.2492, + "step": 2698 + }, + { + "epoch": 2.91, + "learning_rate": 8.061063218390805e-05, + "loss": 1.341, + "step": 2699 + }, + { + "epoch": 2.91, + "learning_rate": 8.060344827586207e-05, + "loss": 1.2015, + "step": 2700 + }, + { + "epoch": 2.91, + "learning_rate": 8.05962643678161e-05, + "loss": 1.2123, + "step": 2701 + }, + { + "epoch": 2.91, + "learning_rate": 8.058908045977011e-05, + "loss": 1.3284, + "step": 2702 + }, + { + "epoch": 2.91, + "learning_rate": 8.058189655172414e-05, + "loss": 1.2892, + "step": 2703 + }, + { + "epoch": 2.91, + "learning_rate": 8.057471264367816e-05, + "loss": 1.2405, + "step": 2704 + }, + { + "epoch": 2.91, + "learning_rate": 8.05675287356322e-05, + "loss": 1.2047, + "step": 2705 + }, + { + "epoch": 2.92, + "learning_rate": 8.05603448275862e-05, + "loss": 1.234, + "step": 2706 + }, + { + "epoch": 2.92, + "learning_rate": 8.055316091954024e-05, + "loss": 1.2443, + "step": 2707 + }, + { + "epoch": 2.92, + "learning_rate": 8.054597701149426e-05, + "loss": 1.4473, + "step": 2708 + }, + { + "epoch": 2.92, + "learning_rate": 8.053879310344828e-05, + "loss": 1.3016, + "step": 2709 + }, + { + "epoch": 2.92, + "learning_rate": 8.05316091954023e-05, + "loss": 1.0993, + "step": 2710 + }, + { + "epoch": 2.92, + "learning_rate": 8.052442528735633e-05, + "loss": 1.0975, + "step": 2711 + }, + { + "epoch": 2.92, + "learning_rate": 8.051724137931035e-05, + "loss": 1.2784, + "step": 2712 + }, + { + "epoch": 2.92, + "learning_rate": 8.051005747126436e-05, + "loss": 1.2597, + "step": 2713 + }, + { + "epoch": 2.92, + "learning_rate": 8.05028735632184e-05, + "loss": 1.2702, + "step": 2714 + }, + { + "epoch": 2.93, + "learning_rate": 8.049568965517241e-05, + "loss": 1.2259, + "step": 2715 + }, + { + "epoch": 2.93, + "learning_rate": 8.048850574712643e-05, + "loss": 1.3561, + "step": 2716 + }, + { + "epoch": 2.93, + "learning_rate": 8.048132183908046e-05, + "loss": 1.2554, + "step": 2717 + }, + { + "epoch": 2.93, + "learning_rate": 8.047413793103449e-05, + "loss": 1.4091, + "step": 2718 + }, + { + "epoch": 2.93, + "learning_rate": 8.046695402298851e-05, + "loss": 1.3244, + "step": 2719 + }, + { + "epoch": 2.93, + "learning_rate": 8.045977011494253e-05, + "loss": 1.3274, + "step": 2720 + }, + { + "epoch": 2.93, + "learning_rate": 8.045258620689655e-05, + "loss": 1.2932, + "step": 2721 + }, + { + "epoch": 2.93, + "learning_rate": 8.044540229885058e-05, + "loss": 1.3708, + "step": 2722 + }, + { + "epoch": 2.93, + "learning_rate": 8.04382183908046e-05, + "loss": 1.3097, + "step": 2723 + }, + { + "epoch": 2.94, + "learning_rate": 8.043103448275862e-05, + "loss": 1.4595, + "step": 2724 + }, + { + "epoch": 2.94, + "learning_rate": 8.042385057471264e-05, + "loss": 1.2902, + "step": 2725 + }, + { + "epoch": 2.94, + "learning_rate": 8.041666666666668e-05, + "loss": 1.3104, + "step": 2726 + }, + { + "epoch": 2.94, + "learning_rate": 8.040948275862069e-05, + "loss": 1.3737, + "step": 2727 + }, + { + "epoch": 2.94, + "learning_rate": 8.040229885057472e-05, + "loss": 1.3263, + "step": 2728 + }, + { + "epoch": 2.94, + "learning_rate": 8.039511494252874e-05, + "loss": 1.1851, + "step": 2729 + }, + { + "epoch": 2.94, + "learning_rate": 8.038793103448276e-05, + "loss": 1.2576, + "step": 2730 + }, + { + "epoch": 2.94, + "learning_rate": 8.038074712643678e-05, + "loss": 1.3161, + "step": 2731 + }, + { + "epoch": 2.94, + "learning_rate": 8.037356321839081e-05, + "loss": 1.3151, + "step": 2732 + }, + { + "epoch": 2.95, + "learning_rate": 8.036637931034483e-05, + "loss": 1.2145, + "step": 2733 + }, + { + "epoch": 2.95, + "learning_rate": 8.035919540229885e-05, + "loss": 1.1746, + "step": 2734 + }, + { + "epoch": 2.95, + "learning_rate": 8.035201149425288e-05, + "loss": 1.3512, + "step": 2735 + }, + { + "epoch": 2.95, + "learning_rate": 8.034482758620691e-05, + "loss": 1.1937, + "step": 2736 + }, + { + "epoch": 2.95, + "learning_rate": 8.033764367816093e-05, + "loss": 1.1644, + "step": 2737 + }, + { + "epoch": 2.95, + "learning_rate": 8.033045977011494e-05, + "loss": 1.321, + "step": 2738 + }, + { + "epoch": 2.95, + "learning_rate": 8.032327586206897e-05, + "loss": 1.1884, + "step": 2739 + }, + { + "epoch": 2.95, + "learning_rate": 8.031609195402299e-05, + "loss": 1.183, + "step": 2740 + }, + { + "epoch": 2.95, + "learning_rate": 8.030890804597701e-05, + "loss": 1.1331, + "step": 2741 + }, + { + "epoch": 2.95, + "learning_rate": 8.030172413793103e-05, + "loss": 1.1793, + "step": 2742 + }, + { + "epoch": 2.96, + "learning_rate": 8.029454022988506e-05, + "loss": 1.3581, + "step": 2743 + }, + { + "epoch": 2.96, + "learning_rate": 8.028735632183909e-05, + "loss": 1.2788, + "step": 2744 + }, + { + "epoch": 2.96, + "learning_rate": 8.02801724137931e-05, + "loss": 1.2185, + "step": 2745 + }, + { + "epoch": 2.96, + "learning_rate": 8.027298850574713e-05, + "loss": 1.2533, + "step": 2746 + }, + { + "epoch": 2.96, + "learning_rate": 8.026580459770116e-05, + "loss": 1.1646, + "step": 2747 + }, + { + "epoch": 2.96, + "learning_rate": 8.025862068965517e-05, + "loss": 1.3855, + "step": 2748 + }, + { + "epoch": 2.96, + "learning_rate": 8.02514367816092e-05, + "loss": 1.4077, + "step": 2749 + }, + { + "epoch": 2.96, + "learning_rate": 8.024425287356322e-05, + "loss": 1.1863, + "step": 2750 + }, + { + "epoch": 2.96, + "eval_loss": 1.1825634241104126, + "eval_runtime": 174.9839, + "eval_samples_per_second": 127.269, + "eval_steps_per_second": 0.663, + "step": 2750 + }, + { + "epoch": 2.96, + "learning_rate": 8.023706896551725e-05, + "loss": 1.2548, + "step": 2751 + }, + { + "epoch": 2.97, + "learning_rate": 8.022988505747126e-05, + "loss": 1.2826, + "step": 2752 + }, + { + "epoch": 2.97, + "learning_rate": 8.02227011494253e-05, + "loss": 1.3104, + "step": 2753 + }, + { + "epoch": 2.97, + "learning_rate": 8.021551724137932e-05, + "loss": 1.3084, + "step": 2754 + }, + { + "epoch": 2.97, + "learning_rate": 8.020833333333334e-05, + "loss": 1.302, + "step": 2755 + }, + { + "epoch": 2.97, + "learning_rate": 8.020114942528736e-05, + "loss": 1.1284, + "step": 2756 + }, + { + "epoch": 2.97, + "learning_rate": 8.019396551724139e-05, + "loss": 1.1899, + "step": 2757 + }, + { + "epoch": 2.97, + "learning_rate": 8.018678160919541e-05, + "loss": 1.2914, + "step": 2758 + }, + { + "epoch": 2.97, + "learning_rate": 8.017959770114943e-05, + "loss": 1.2357, + "step": 2759 + }, + { + "epoch": 2.97, + "learning_rate": 8.017241379310345e-05, + "loss": 1.1962, + "step": 2760 + }, + { + "epoch": 2.98, + "learning_rate": 8.016522988505748e-05, + "loss": 1.3631, + "step": 2761 + }, + { + "epoch": 2.98, + "learning_rate": 8.015804597701149e-05, + "loss": 1.4005, + "step": 2762 + }, + { + "epoch": 2.98, + "learning_rate": 8.015086206896553e-05, + "loss": 1.1662, + "step": 2763 + }, + { + "epoch": 2.98, + "learning_rate": 8.014367816091955e-05, + "loss": 1.1697, + "step": 2764 + }, + { + "epoch": 2.98, + "learning_rate": 8.013649425287357e-05, + "loss": 1.2061, + "step": 2765 + }, + { + "epoch": 2.98, + "learning_rate": 8.012931034482759e-05, + "loss": 1.1452, + "step": 2766 + }, + { + "epoch": 2.98, + "learning_rate": 8.012212643678161e-05, + "loss": 1.2886, + "step": 2767 + }, + { + "epoch": 2.98, + "learning_rate": 8.011494252873564e-05, + "loss": 1.5164, + "step": 2768 + }, + { + "epoch": 2.98, + "learning_rate": 8.010775862068966e-05, + "loss": 1.3053, + "step": 2769 + }, + { + "epoch": 2.98, + "learning_rate": 8.010057471264368e-05, + "loss": 1.395, + "step": 2770 + }, + { + "epoch": 2.99, + "learning_rate": 8.00933908045977e-05, + "loss": 1.2954, + "step": 2771 + }, + { + "epoch": 2.99, + "learning_rate": 8.008620689655174e-05, + "loss": 1.266, + "step": 2772 + }, + { + "epoch": 2.99, + "learning_rate": 8.007902298850574e-05, + "loss": 1.2406, + "step": 2773 + }, + { + "epoch": 2.99, + "learning_rate": 8.007183908045978e-05, + "loss": 1.1915, + "step": 2774 + }, + { + "epoch": 2.99, + "learning_rate": 8.00646551724138e-05, + "loss": 1.2783, + "step": 2775 + }, + { + "epoch": 2.99, + "learning_rate": 8.005747126436782e-05, + "loss": 1.2585, + "step": 2776 + }, + { + "epoch": 2.99, + "learning_rate": 8.005028735632184e-05, + "loss": 1.3092, + "step": 2777 + }, + { + "epoch": 2.99, + "learning_rate": 8.004310344827587e-05, + "loss": 1.3483, + "step": 2778 + }, + { + "epoch": 2.99, + "learning_rate": 8.003591954022989e-05, + "loss": 1.2264, + "step": 2779 + }, + { + "epoch": 3.0, + "learning_rate": 8.002873563218391e-05, + "loss": 1.21, + "step": 2780 + }, + { + "epoch": 3.0, + "learning_rate": 8.002155172413793e-05, + "loss": 1.227, + "step": 2781 + }, + { + "epoch": 3.0, + "learning_rate": 8.001436781609197e-05, + "loss": 1.3343, + "step": 2782 + }, + { + "epoch": 3.0, + "learning_rate": 8.000718390804599e-05, + "loss": 1.186, + "step": 2783 + }, + { + "epoch": 3.0, + "learning_rate": 8e-05, + "loss": 1.2434, + "step": 2784 + }, + { + "epoch": 3.0, + "learning_rate": 7.999281609195403e-05, + "loss": 1.0173, + "step": 2785 + }, + { + "epoch": 3.0, + "learning_rate": 7.998563218390806e-05, + "loss": 1.1693, + "step": 2786 + }, + { + "epoch": 3.0, + "learning_rate": 7.997844827586207e-05, + "loss": 1.2346, + "step": 2787 + }, + { + "epoch": 3.0, + "learning_rate": 7.99712643678161e-05, + "loss": 1.0359, + "step": 2788 + }, + { + "epoch": 3.01, + "learning_rate": 7.996408045977012e-05, + "loss": 1.1109, + "step": 2789 + }, + { + "epoch": 3.01, + "learning_rate": 7.995689655172414e-05, + "loss": 1.0996, + "step": 2790 + }, + { + "epoch": 3.01, + "learning_rate": 7.994971264367816e-05, + "loss": 1.2193, + "step": 2791 + }, + { + "epoch": 3.01, + "learning_rate": 7.994252873563218e-05, + "loss": 1.2449, + "step": 2792 + }, + { + "epoch": 3.01, + "learning_rate": 7.993534482758622e-05, + "loss": 1.2148, + "step": 2793 + }, + { + "epoch": 3.01, + "learning_rate": 7.992816091954022e-05, + "loss": 1.1216, + "step": 2794 + }, + { + "epoch": 3.01, + "learning_rate": 7.992097701149426e-05, + "loss": 1.1813, + "step": 2795 + }, + { + "epoch": 3.01, + "learning_rate": 7.991379310344828e-05, + "loss": 1.3224, + "step": 2796 + }, + { + "epoch": 3.01, + "learning_rate": 7.99066091954023e-05, + "loss": 1.3594, + "step": 2797 + }, + { + "epoch": 3.02, + "learning_rate": 7.989942528735632e-05, + "loss": 1.1329, + "step": 2798 + }, + { + "epoch": 3.02, + "learning_rate": 7.989224137931035e-05, + "loss": 1.1569, + "step": 2799 + }, + { + "epoch": 3.02, + "learning_rate": 7.988505747126437e-05, + "loss": 1.1881, + "step": 2800 + }, + { + "epoch": 3.02, + "learning_rate": 7.987787356321839e-05, + "loss": 1.2726, + "step": 2801 + }, + { + "epoch": 3.02, + "learning_rate": 7.987068965517241e-05, + "loss": 1.2109, + "step": 2802 + }, + { + "epoch": 3.02, + "learning_rate": 7.986350574712645e-05, + "loss": 1.2285, + "step": 2803 + }, + { + "epoch": 3.02, + "learning_rate": 7.985632183908047e-05, + "loss": 1.2728, + "step": 2804 + }, + { + "epoch": 3.02, + "learning_rate": 7.984913793103449e-05, + "loss": 1.2012, + "step": 2805 + }, + { + "epoch": 3.02, + "learning_rate": 7.984195402298851e-05, + "loss": 1.0416, + "step": 2806 + }, + { + "epoch": 3.02, + "learning_rate": 7.983477011494254e-05, + "loss": 1.085, + "step": 2807 + }, + { + "epoch": 3.03, + "learning_rate": 7.982758620689655e-05, + "loss": 1.3538, + "step": 2808 + }, + { + "epoch": 3.03, + "learning_rate": 7.982040229885058e-05, + "loss": 1.2232, + "step": 2809 + }, + { + "epoch": 3.03, + "learning_rate": 7.98132183908046e-05, + "loss": 1.2148, + "step": 2810 + }, + { + "epoch": 3.03, + "learning_rate": 7.980603448275862e-05, + "loss": 1.1712, + "step": 2811 + }, + { + "epoch": 3.03, + "learning_rate": 7.979885057471264e-05, + "loss": 1.336, + "step": 2812 + }, + { + "epoch": 3.03, + "learning_rate": 7.979166666666668e-05, + "loss": 1.2531, + "step": 2813 + }, + { + "epoch": 3.03, + "learning_rate": 7.97844827586207e-05, + "loss": 1.1448, + "step": 2814 + }, + { + "epoch": 3.03, + "learning_rate": 7.97772988505747e-05, + "loss": 1.2608, + "step": 2815 + }, + { + "epoch": 3.03, + "learning_rate": 7.977011494252874e-05, + "loss": 1.1812, + "step": 2816 + }, + { + "epoch": 3.04, + "learning_rate": 7.976293103448276e-05, + "loss": 1.1652, + "step": 2817 + }, + { + "epoch": 3.04, + "learning_rate": 7.975574712643679e-05, + "loss": 1.3375, + "step": 2818 + }, + { + "epoch": 3.04, + "learning_rate": 7.97485632183908e-05, + "loss": 1.2187, + "step": 2819 + }, + { + "epoch": 3.04, + "learning_rate": 7.974137931034483e-05, + "loss": 1.1616, + "step": 2820 + }, + { + "epoch": 3.04, + "learning_rate": 7.973419540229885e-05, + "loss": 1.3118, + "step": 2821 + }, + { + "epoch": 3.04, + "learning_rate": 7.972701149425287e-05, + "loss": 1.0954, + "step": 2822 + }, + { + "epoch": 3.04, + "learning_rate": 7.97198275862069e-05, + "loss": 1.3795, + "step": 2823 + }, + { + "epoch": 3.04, + "learning_rate": 7.971264367816093e-05, + "loss": 1.3123, + "step": 2824 + }, + { + "epoch": 3.04, + "learning_rate": 7.970545977011495e-05, + "loss": 1.249, + "step": 2825 + }, + { + "epoch": 3.05, + "learning_rate": 7.969827586206897e-05, + "loss": 1.3196, + "step": 2826 + }, + { + "epoch": 3.05, + "learning_rate": 7.969109195402299e-05, + "loss": 1.1116, + "step": 2827 + }, + { + "epoch": 3.05, + "learning_rate": 7.968390804597702e-05, + "loss": 1.3032, + "step": 2828 + }, + { + "epoch": 3.05, + "learning_rate": 7.967672413793103e-05, + "loss": 1.3394, + "step": 2829 + }, + { + "epoch": 3.05, + "learning_rate": 7.966954022988506e-05, + "loss": 1.2098, + "step": 2830 + }, + { + "epoch": 3.05, + "learning_rate": 7.966235632183908e-05, + "loss": 1.1494, + "step": 2831 + }, + { + "epoch": 3.05, + "learning_rate": 7.965517241379312e-05, + "loss": 1.0807, + "step": 2832 + }, + { + "epoch": 3.05, + "learning_rate": 7.964798850574712e-05, + "loss": 1.1052, + "step": 2833 + }, + { + "epoch": 3.05, + "learning_rate": 7.964080459770116e-05, + "loss": 1.3979, + "step": 2834 + }, + { + "epoch": 3.05, + "learning_rate": 7.963362068965518e-05, + "loss": 1.2318, + "step": 2835 + }, + { + "epoch": 3.06, + "learning_rate": 7.96264367816092e-05, + "loss": 1.2249, + "step": 2836 + }, + { + "epoch": 3.06, + "learning_rate": 7.961925287356322e-05, + "loss": 1.2965, + "step": 2837 + }, + { + "epoch": 3.06, + "learning_rate": 7.961206896551725e-05, + "loss": 1.2178, + "step": 2838 + }, + { + "epoch": 3.06, + "learning_rate": 7.960488505747127e-05, + "loss": 1.197, + "step": 2839 + }, + { + "epoch": 3.06, + "learning_rate": 7.95977011494253e-05, + "loss": 1.2898, + "step": 2840 + }, + { + "epoch": 3.06, + "learning_rate": 7.959051724137931e-05, + "loss": 1.2391, + "step": 2841 + }, + { + "epoch": 3.06, + "learning_rate": 7.958333333333333e-05, + "loss": 1.1792, + "step": 2842 + }, + { + "epoch": 3.06, + "learning_rate": 7.957614942528735e-05, + "loss": 1.1814, + "step": 2843 + }, + { + "epoch": 3.06, + "learning_rate": 7.956896551724137e-05, + "loss": 1.061, + "step": 2844 + }, + { + "epoch": 3.07, + "learning_rate": 7.956178160919541e-05, + "loss": 1.1868, + "step": 2845 + }, + { + "epoch": 3.07, + "learning_rate": 7.955459770114943e-05, + "loss": 1.339, + "step": 2846 + }, + { + "epoch": 3.07, + "learning_rate": 7.954741379310345e-05, + "loss": 1.2126, + "step": 2847 + }, + { + "epoch": 3.07, + "learning_rate": 7.954022988505747e-05, + "loss": 1.1465, + "step": 2848 + }, + { + "epoch": 3.07, + "learning_rate": 7.95330459770115e-05, + "loss": 1.2782, + "step": 2849 + }, + { + "epoch": 3.07, + "learning_rate": 7.952586206896552e-05, + "loss": 1.1245, + "step": 2850 + }, + { + "epoch": 3.07, + "learning_rate": 7.951867816091954e-05, + "loss": 1.1926, + "step": 2851 + }, + { + "epoch": 3.07, + "learning_rate": 7.951149425287356e-05, + "loss": 1.269, + "step": 2852 + }, + { + "epoch": 3.07, + "learning_rate": 7.95043103448276e-05, + "loss": 1.2283, + "step": 2853 + }, + { + "epoch": 3.08, + "learning_rate": 7.94971264367816e-05, + "loss": 1.3301, + "step": 2854 + }, + { + "epoch": 3.08, + "learning_rate": 7.948994252873564e-05, + "loss": 1.2249, + "step": 2855 + }, + { + "epoch": 3.08, + "learning_rate": 7.948275862068966e-05, + "loss": 1.2011, + "step": 2856 + }, + { + "epoch": 3.08, + "learning_rate": 7.947557471264368e-05, + "loss": 1.2946, + "step": 2857 + }, + { + "epoch": 3.08, + "learning_rate": 7.94683908045977e-05, + "loss": 1.2396, + "step": 2858 + }, + { + "epoch": 3.08, + "learning_rate": 7.946120689655173e-05, + "loss": 1.2196, + "step": 2859 + }, + { + "epoch": 3.08, + "learning_rate": 7.945402298850575e-05, + "loss": 1.1646, + "step": 2860 + }, + { + "epoch": 3.08, + "learning_rate": 7.944683908045977e-05, + "loss": 1.2916, + "step": 2861 + }, + { + "epoch": 3.08, + "learning_rate": 7.94396551724138e-05, + "loss": 1.3029, + "step": 2862 + }, + { + "epoch": 3.09, + "learning_rate": 7.943247126436783e-05, + "loss": 1.1967, + "step": 2863 + }, + { + "epoch": 3.09, + "learning_rate": 7.942528735632185e-05, + "loss": 1.1768, + "step": 2864 + }, + { + "epoch": 3.09, + "learning_rate": 7.941810344827587e-05, + "loss": 1.1682, + "step": 2865 + }, + { + "epoch": 3.09, + "learning_rate": 7.941091954022989e-05, + "loss": 1.2411, + "step": 2866 + }, + { + "epoch": 3.09, + "learning_rate": 7.940373563218391e-05, + "loss": 1.2591, + "step": 2867 + }, + { + "epoch": 3.09, + "learning_rate": 7.939655172413793e-05, + "loss": 1.1, + "step": 2868 + }, + { + "epoch": 3.09, + "learning_rate": 7.938936781609195e-05, + "loss": 1.2965, + "step": 2869 + }, + { + "epoch": 3.09, + "learning_rate": 7.938218390804598e-05, + "loss": 1.186, + "step": 2870 + }, + { + "epoch": 3.09, + "learning_rate": 7.9375e-05, + "loss": 1.1878, + "step": 2871 + }, + { + "epoch": 3.09, + "learning_rate": 7.936781609195403e-05, + "loss": 1.3774, + "step": 2872 + }, + { + "epoch": 3.1, + "learning_rate": 7.936063218390805e-05, + "loss": 1.1966, + "step": 2873 + }, + { + "epoch": 3.1, + "learning_rate": 7.935344827586208e-05, + "loss": 1.2409, + "step": 2874 + }, + { + "epoch": 3.1, + "learning_rate": 7.934626436781609e-05, + "loss": 1.285, + "step": 2875 + }, + { + "epoch": 3.1, + "learning_rate": 7.933908045977012e-05, + "loss": 1.0445, + "step": 2876 + }, + { + "epoch": 3.1, + "learning_rate": 7.933189655172414e-05, + "loss": 1.2145, + "step": 2877 + }, + { + "epoch": 3.1, + "learning_rate": 7.932471264367816e-05, + "loss": 1.2464, + "step": 2878 + }, + { + "epoch": 3.1, + "learning_rate": 7.931752873563218e-05, + "loss": 1.3056, + "step": 2879 + }, + { + "epoch": 3.1, + "learning_rate": 7.931034482758621e-05, + "loss": 1.0777, + "step": 2880 + }, + { + "epoch": 3.1, + "learning_rate": 7.930316091954024e-05, + "loss": 1.0692, + "step": 2881 + }, + { + "epoch": 3.11, + "learning_rate": 7.929597701149426e-05, + "loss": 1.1351, + "step": 2882 + }, + { + "epoch": 3.11, + "learning_rate": 7.928879310344828e-05, + "loss": 1.215, + "step": 2883 + }, + { + "epoch": 3.11, + "learning_rate": 7.928160919540231e-05, + "loss": 1.2159, + "step": 2884 + }, + { + "epoch": 3.11, + "learning_rate": 7.927442528735633e-05, + "loss": 1.241, + "step": 2885 + }, + { + "epoch": 3.11, + "learning_rate": 7.926724137931035e-05, + "loss": 1.1279, + "step": 2886 + }, + { + "epoch": 3.11, + "learning_rate": 7.926005747126437e-05, + "loss": 1.1332, + "step": 2887 + }, + { + "epoch": 3.11, + "learning_rate": 7.92528735632184e-05, + "loss": 1.2291, + "step": 2888 + }, + { + "epoch": 3.11, + "learning_rate": 7.924568965517241e-05, + "loss": 1.1313, + "step": 2889 + }, + { + "epoch": 3.11, + "learning_rate": 7.923850574712645e-05, + "loss": 1.2844, + "step": 2890 + }, + { + "epoch": 3.12, + "learning_rate": 7.923132183908047e-05, + "loss": 1.3935, + "step": 2891 + }, + { + "epoch": 3.12, + "learning_rate": 7.922413793103449e-05, + "loss": 1.1948, + "step": 2892 + }, + { + "epoch": 3.12, + "learning_rate": 7.92169540229885e-05, + "loss": 1.1198, + "step": 2893 + }, + { + "epoch": 3.12, + "learning_rate": 7.920977011494253e-05, + "loss": 1.2094, + "step": 2894 + }, + { + "epoch": 3.12, + "learning_rate": 7.920258620689656e-05, + "loss": 1.1762, + "step": 2895 + }, + { + "epoch": 3.12, + "learning_rate": 7.919540229885058e-05, + "loss": 1.319, + "step": 2896 + }, + { + "epoch": 3.12, + "learning_rate": 7.91882183908046e-05, + "loss": 1.3348, + "step": 2897 + }, + { + "epoch": 3.12, + "learning_rate": 7.918103448275862e-05, + "loss": 1.3097, + "step": 2898 + }, + { + "epoch": 3.12, + "learning_rate": 7.917385057471266e-05, + "loss": 1.2079, + "step": 2899 + }, + { + "epoch": 3.12, + "learning_rate": 7.916666666666666e-05, + "loss": 1.2758, + "step": 2900 + }, + { + "epoch": 3.13, + "learning_rate": 7.91594827586207e-05, + "loss": 1.2086, + "step": 2901 + }, + { + "epoch": 3.13, + "learning_rate": 7.915229885057472e-05, + "loss": 1.1348, + "step": 2902 + }, + { + "epoch": 3.13, + "learning_rate": 7.914511494252874e-05, + "loss": 1.0786, + "step": 2903 + }, + { + "epoch": 3.13, + "learning_rate": 7.913793103448276e-05, + "loss": 1.1583, + "step": 2904 + }, + { + "epoch": 3.13, + "learning_rate": 7.913074712643679e-05, + "loss": 1.213, + "step": 2905 + }, + { + "epoch": 3.13, + "learning_rate": 7.912356321839081e-05, + "loss": 1.2347, + "step": 2906 + }, + { + "epoch": 3.13, + "learning_rate": 7.911637931034483e-05, + "loss": 1.139, + "step": 2907 + }, + { + "epoch": 3.13, + "learning_rate": 7.910919540229885e-05, + "loss": 1.1339, + "step": 2908 + }, + { + "epoch": 3.13, + "learning_rate": 7.910201149425289e-05, + "loss": 1.2597, + "step": 2909 + }, + { + "epoch": 3.14, + "learning_rate": 7.909482758620689e-05, + "loss": 1.1616, + "step": 2910 + }, + { + "epoch": 3.14, + "learning_rate": 7.908764367816093e-05, + "loss": 1.2675, + "step": 2911 + }, + { + "epoch": 3.14, + "learning_rate": 7.908045977011495e-05, + "loss": 1.173, + "step": 2912 + }, + { + "epoch": 3.14, + "learning_rate": 7.907327586206898e-05, + "loss": 1.1352, + "step": 2913 + }, + { + "epoch": 3.14, + "learning_rate": 7.906609195402299e-05, + "loss": 1.0557, + "step": 2914 + }, + { + "epoch": 3.14, + "learning_rate": 7.905890804597702e-05, + "loss": 1.1959, + "step": 2915 + }, + { + "epoch": 3.14, + "learning_rate": 7.905172413793104e-05, + "loss": 1.108, + "step": 2916 + }, + { + "epoch": 3.14, + "learning_rate": 7.904454022988506e-05, + "loss": 1.2691, + "step": 2917 + }, + { + "epoch": 3.14, + "learning_rate": 7.903735632183908e-05, + "loss": 1.3228, + "step": 2918 + }, + { + "epoch": 3.15, + "learning_rate": 7.90301724137931e-05, + "loss": 1.0917, + "step": 2919 + }, + { + "epoch": 3.15, + "learning_rate": 7.902298850574714e-05, + "loss": 1.26, + "step": 2920 + }, + { + "epoch": 3.15, + "learning_rate": 7.901580459770114e-05, + "loss": 1.1995, + "step": 2921 + }, + { + "epoch": 3.15, + "learning_rate": 7.900862068965518e-05, + "loss": 1.3013, + "step": 2922 + }, + { + "epoch": 3.15, + "learning_rate": 7.90014367816092e-05, + "loss": 1.1421, + "step": 2923 + }, + { + "epoch": 3.15, + "learning_rate": 7.899425287356322e-05, + "loss": 1.3039, + "step": 2924 + }, + { + "epoch": 3.15, + "learning_rate": 7.898706896551724e-05, + "loss": 1.1657, + "step": 2925 + }, + { + "epoch": 3.15, + "learning_rate": 7.897988505747127e-05, + "loss": 1.3764, + "step": 2926 + }, + { + "epoch": 3.15, + "learning_rate": 7.897270114942529e-05, + "loss": 1.1918, + "step": 2927 + }, + { + "epoch": 3.16, + "learning_rate": 7.896551724137931e-05, + "loss": 1.1548, + "step": 2928 + }, + { + "epoch": 3.16, + "learning_rate": 7.895833333333333e-05, + "loss": 1.27, + "step": 2929 + }, + { + "epoch": 3.16, + "learning_rate": 7.895114942528737e-05, + "loss": 1.3307, + "step": 2930 + }, + { + "epoch": 3.16, + "learning_rate": 7.894396551724139e-05, + "loss": 1.2354, + "step": 2931 + }, + { + "epoch": 3.16, + "learning_rate": 7.893678160919541e-05, + "loss": 1.1129, + "step": 2932 + }, + { + "epoch": 3.16, + "learning_rate": 7.892959770114943e-05, + "loss": 1.2409, + "step": 2933 + }, + { + "epoch": 3.16, + "learning_rate": 7.892241379310346e-05, + "loss": 1.2664, + "step": 2934 + }, + { + "epoch": 3.16, + "learning_rate": 7.891522988505747e-05, + "loss": 1.2695, + "step": 2935 + }, + { + "epoch": 3.16, + "learning_rate": 7.89080459770115e-05, + "loss": 1.0412, + "step": 2936 + }, + { + "epoch": 3.16, + "learning_rate": 7.890086206896552e-05, + "loss": 1.0813, + "step": 2937 + }, + { + "epoch": 3.17, + "learning_rate": 7.889367816091954e-05, + "loss": 1.1236, + "step": 2938 + }, + { + "epoch": 3.17, + "learning_rate": 7.888649425287356e-05, + "loss": 1.1843, + "step": 2939 + }, + { + "epoch": 3.17, + "learning_rate": 7.88793103448276e-05, + "loss": 1.2129, + "step": 2940 + }, + { + "epoch": 3.17, + "learning_rate": 7.887212643678162e-05, + "loss": 1.1912, + "step": 2941 + }, + { + "epoch": 3.17, + "learning_rate": 7.886494252873564e-05, + "loss": 1.1548, + "step": 2942 + }, + { + "epoch": 3.17, + "learning_rate": 7.885775862068966e-05, + "loss": 1.3233, + "step": 2943 + }, + { + "epoch": 3.17, + "learning_rate": 7.885057471264368e-05, + "loss": 1.0839, + "step": 2944 + }, + { + "epoch": 3.17, + "learning_rate": 7.884339080459771e-05, + "loss": 1.1729, + "step": 2945 + }, + { + "epoch": 3.17, + "learning_rate": 7.883620689655172e-05, + "loss": 1.1594, + "step": 2946 + }, + { + "epoch": 3.18, + "learning_rate": 7.882902298850575e-05, + "loss": 1.3824, + "step": 2947 + }, + { + "epoch": 3.18, + "learning_rate": 7.882183908045977e-05, + "loss": 1.2226, + "step": 2948 + }, + { + "epoch": 3.18, + "learning_rate": 7.88146551724138e-05, + "loss": 1.368, + "step": 2949 + }, + { + "epoch": 3.18, + "learning_rate": 7.880747126436781e-05, + "loss": 1.0972, + "step": 2950 + }, + { + "epoch": 3.18, + "learning_rate": 7.880028735632185e-05, + "loss": 1.1563, + "step": 2951 + }, + { + "epoch": 3.18, + "learning_rate": 7.879310344827587e-05, + "loss": 1.2298, + "step": 2952 + }, + { + "epoch": 3.18, + "learning_rate": 7.878591954022989e-05, + "loss": 1.3334, + "step": 2953 + }, + { + "epoch": 3.18, + "learning_rate": 7.877873563218391e-05, + "loss": 1.2675, + "step": 2954 + }, + { + "epoch": 3.18, + "learning_rate": 7.877155172413794e-05, + "loss": 1.1483, + "step": 2955 + }, + { + "epoch": 3.19, + "learning_rate": 7.876436781609195e-05, + "loss": 1.315, + "step": 2956 + }, + { + "epoch": 3.19, + "learning_rate": 7.875718390804598e-05, + "loss": 1.1844, + "step": 2957 + }, + { + "epoch": 3.19, + "learning_rate": 7.875e-05, + "loss": 1.064, + "step": 2958 + }, + { + "epoch": 3.19, + "learning_rate": 7.874281609195402e-05, + "loss": 1.0911, + "step": 2959 + }, + { + "epoch": 3.19, + "learning_rate": 7.873563218390804e-05, + "loss": 1.2029, + "step": 2960 + }, + { + "epoch": 3.19, + "learning_rate": 7.872844827586208e-05, + "loss": 1.1392, + "step": 2961 + }, + { + "epoch": 3.19, + "learning_rate": 7.87212643678161e-05, + "loss": 1.1229, + "step": 2962 + }, + { + "epoch": 3.19, + "learning_rate": 7.871408045977012e-05, + "loss": 1.1858, + "step": 2963 + }, + { + "epoch": 3.19, + "learning_rate": 7.870689655172414e-05, + "loss": 1.2681, + "step": 2964 + }, + { + "epoch": 3.2, + "learning_rate": 7.869971264367817e-05, + "loss": 1.2173, + "step": 2965 + }, + { + "epoch": 3.2, + "learning_rate": 7.869252873563219e-05, + "loss": 1.1431, + "step": 2966 + }, + { + "epoch": 3.2, + "learning_rate": 7.868534482758621e-05, + "loss": 1.3659, + "step": 2967 + }, + { + "epoch": 3.2, + "learning_rate": 7.867816091954023e-05, + "loss": 1.1492, + "step": 2968 + }, + { + "epoch": 3.2, + "learning_rate": 7.867097701149425e-05, + "loss": 1.2566, + "step": 2969 + }, + { + "epoch": 3.2, + "learning_rate": 7.866379310344827e-05, + "loss": 1.2751, + "step": 2970 + }, + { + "epoch": 3.2, + "learning_rate": 7.86566091954023e-05, + "loss": 1.1807, + "step": 2971 + }, + { + "epoch": 3.2, + "learning_rate": 7.864942528735633e-05, + "loss": 1.2432, + "step": 2972 + }, + { + "epoch": 3.2, + "learning_rate": 7.864224137931035e-05, + "loss": 1.1008, + "step": 2973 + }, + { + "epoch": 3.2, + "learning_rate": 7.863505747126437e-05, + "loss": 0.9788, + "step": 2974 + }, + { + "epoch": 3.21, + "learning_rate": 7.862787356321839e-05, + "loss": 1.3961, + "step": 2975 + }, + { + "epoch": 3.21, + "learning_rate": 7.862068965517242e-05, + "loss": 1.155, + "step": 2976 + }, + { + "epoch": 3.21, + "learning_rate": 7.861350574712644e-05, + "loss": 1.0963, + "step": 2977 + }, + { + "epoch": 3.21, + "learning_rate": 7.860632183908046e-05, + "loss": 1.1184, + "step": 2978 + }, + { + "epoch": 3.21, + "learning_rate": 7.859913793103448e-05, + "loss": 1.1659, + "step": 2979 + }, + { + "epoch": 3.21, + "learning_rate": 7.859195402298852e-05, + "loss": 1.309, + "step": 2980 + }, + { + "epoch": 3.21, + "learning_rate": 7.858477011494252e-05, + "loss": 1.162, + "step": 2981 + }, + { + "epoch": 3.21, + "learning_rate": 7.857758620689656e-05, + "loss": 1.2454, + "step": 2982 + }, + { + "epoch": 3.21, + "learning_rate": 7.857040229885058e-05, + "loss": 1.199, + "step": 2983 + }, + { + "epoch": 3.22, + "learning_rate": 7.85632183908046e-05, + "loss": 1.0903, + "step": 2984 + }, + { + "epoch": 3.22, + "learning_rate": 7.855603448275862e-05, + "loss": 1.2407, + "step": 2985 + }, + { + "epoch": 3.22, + "learning_rate": 7.854885057471265e-05, + "loss": 1.1489, + "step": 2986 + }, + { + "epoch": 3.22, + "learning_rate": 7.854166666666667e-05, + "loss": 1.3018, + "step": 2987 + }, + { + "epoch": 3.22, + "learning_rate": 7.85344827586207e-05, + "loss": 1.1576, + "step": 2988 + }, + { + "epoch": 3.22, + "learning_rate": 7.852729885057471e-05, + "loss": 1.0194, + "step": 2989 + }, + { + "epoch": 3.22, + "learning_rate": 7.852011494252875e-05, + "loss": 1.1454, + "step": 2990 + }, + { + "epoch": 3.22, + "learning_rate": 7.851293103448276e-05, + "loss": 1.1728, + "step": 2991 + }, + { + "epoch": 3.22, + "learning_rate": 7.850574712643679e-05, + "loss": 1.1596, + "step": 2992 + }, + { + "epoch": 3.23, + "learning_rate": 7.849856321839081e-05, + "loss": 1.2792, + "step": 2993 + }, + { + "epoch": 3.23, + "learning_rate": 7.849137931034483e-05, + "loss": 1.2641, + "step": 2994 + }, + { + "epoch": 3.23, + "learning_rate": 7.848419540229885e-05, + "loss": 1.1615, + "step": 2995 + }, + { + "epoch": 3.23, + "learning_rate": 7.847701149425287e-05, + "loss": 1.2541, + "step": 2996 + }, + { + "epoch": 3.23, + "learning_rate": 7.84698275862069e-05, + "loss": 1.2368, + "step": 2997 + }, + { + "epoch": 3.23, + "learning_rate": 7.846264367816092e-05, + "loss": 1.2891, + "step": 2998 + }, + { + "epoch": 3.23, + "learning_rate": 7.845545977011494e-05, + "loss": 1.2478, + "step": 2999 + }, + { + "epoch": 3.23, + "learning_rate": 7.844827586206897e-05, + "loss": 1.1207, + "step": 3000 + }, + { + "epoch": 3.23, + "eval_loss": 1.1803959608078003, + "eval_runtime": 175.0148, + "eval_samples_per_second": 127.246, + "eval_steps_per_second": 0.663, + "step": 3000 + }, + { + "epoch": 3.23, + "learning_rate": 7.8441091954023e-05, + "loss": 1.1048, + "step": 3001 + }, + { + "epoch": 3.23, + "learning_rate": 7.8433908045977e-05, + "loss": 1.1827, + "step": 3002 + }, + { + "epoch": 3.24, + "learning_rate": 7.842672413793104e-05, + "loss": 1.1456, + "step": 3003 + }, + { + "epoch": 3.24, + "learning_rate": 7.841954022988506e-05, + "loss": 1.2044, + "step": 3004 + }, + { + "epoch": 3.24, + "learning_rate": 7.841235632183908e-05, + "loss": 1.2629, + "step": 3005 + }, + { + "epoch": 3.24, + "learning_rate": 7.84051724137931e-05, + "loss": 1.2385, + "step": 3006 + }, + { + "epoch": 3.24, + "learning_rate": 7.839798850574713e-05, + "loss": 1.088, + "step": 3007 + }, + { + "epoch": 3.24, + "learning_rate": 7.839080459770115e-05, + "loss": 1.2932, + "step": 3008 + }, + { + "epoch": 3.24, + "learning_rate": 7.838362068965518e-05, + "loss": 1.2461, + "step": 3009 + }, + { + "epoch": 3.24, + "learning_rate": 7.83764367816092e-05, + "loss": 1.334, + "step": 3010 + }, + { + "epoch": 3.24, + "learning_rate": 7.836925287356323e-05, + "loss": 1.2272, + "step": 3011 + }, + { + "epoch": 3.25, + "learning_rate": 7.836206896551725e-05, + "loss": 1.2031, + "step": 3012 + }, + { + "epoch": 3.25, + "learning_rate": 7.835488505747127e-05, + "loss": 1.1831, + "step": 3013 + }, + { + "epoch": 3.25, + "learning_rate": 7.834770114942529e-05, + "loss": 1.1192, + "step": 3014 + }, + { + "epoch": 3.25, + "learning_rate": 7.834051724137932e-05, + "loss": 1.289, + "step": 3015 + }, + { + "epoch": 3.25, + "learning_rate": 7.833333333333333e-05, + "loss": 1.1703, + "step": 3016 + }, + { + "epoch": 3.25, + "learning_rate": 7.832614942528736e-05, + "loss": 1.2719, + "step": 3017 + }, + { + "epoch": 3.25, + "learning_rate": 7.831896551724139e-05, + "loss": 1.1599, + "step": 3018 + }, + { + "epoch": 3.25, + "learning_rate": 7.83117816091954e-05, + "loss": 1.091, + "step": 3019 + }, + { + "epoch": 3.25, + "learning_rate": 7.830459770114943e-05, + "loss": 1.4283, + "step": 3020 + }, + { + "epoch": 3.26, + "learning_rate": 7.829741379310345e-05, + "loss": 1.1519, + "step": 3021 + }, + { + "epoch": 3.26, + "learning_rate": 7.829022988505748e-05, + "loss": 1.2564, + "step": 3022 + }, + { + "epoch": 3.26, + "learning_rate": 7.828304597701149e-05, + "loss": 1.2364, + "step": 3023 + }, + { + "epoch": 3.26, + "learning_rate": 7.827586206896552e-05, + "loss": 1.1427, + "step": 3024 + }, + { + "epoch": 3.26, + "learning_rate": 7.826867816091954e-05, + "loss": 1.1473, + "step": 3025 + }, + { + "epoch": 3.26, + "learning_rate": 7.826149425287357e-05, + "loss": 1.1605, + "step": 3026 + }, + { + "epoch": 3.26, + "learning_rate": 7.825431034482758e-05, + "loss": 1.3186, + "step": 3027 + }, + { + "epoch": 3.26, + "learning_rate": 7.824712643678162e-05, + "loss": 1.3076, + "step": 3028 + }, + { + "epoch": 3.26, + "learning_rate": 7.823994252873564e-05, + "loss": 1.1829, + "step": 3029 + }, + { + "epoch": 3.27, + "learning_rate": 7.823275862068966e-05, + "loss": 1.1741, + "step": 3030 + }, + { + "epoch": 3.27, + "learning_rate": 7.822557471264368e-05, + "loss": 1.1777, + "step": 3031 + }, + { + "epoch": 3.27, + "learning_rate": 7.821839080459771e-05, + "loss": 1.2441, + "step": 3032 + }, + { + "epoch": 3.27, + "learning_rate": 7.821120689655173e-05, + "loss": 1.1604, + "step": 3033 + }, + { + "epoch": 3.27, + "learning_rate": 7.820402298850575e-05, + "loss": 1.3199, + "step": 3034 + }, + { + "epoch": 3.27, + "learning_rate": 7.819683908045977e-05, + "loss": 1.0695, + "step": 3035 + }, + { + "epoch": 3.27, + "learning_rate": 7.81896551724138e-05, + "loss": 1.1888, + "step": 3036 + }, + { + "epoch": 3.27, + "learning_rate": 7.818247126436781e-05, + "loss": 1.2624, + "step": 3037 + }, + { + "epoch": 3.27, + "learning_rate": 7.817528735632185e-05, + "loss": 1.2036, + "step": 3038 + }, + { + "epoch": 3.27, + "learning_rate": 7.816810344827587e-05, + "loss": 1.213, + "step": 3039 + }, + { + "epoch": 3.28, + "learning_rate": 7.81609195402299e-05, + "loss": 1.3079, + "step": 3040 + }, + { + "epoch": 3.28, + "learning_rate": 7.815373563218391e-05, + "loss": 1.1586, + "step": 3041 + }, + { + "epoch": 3.28, + "learning_rate": 7.814655172413794e-05, + "loss": 1.1354, + "step": 3042 + }, + { + "epoch": 3.28, + "learning_rate": 7.813936781609196e-05, + "loss": 1.2724, + "step": 3043 + }, + { + "epoch": 3.28, + "learning_rate": 7.813218390804598e-05, + "loss": 1.1841, + "step": 3044 + }, + { + "epoch": 3.28, + "learning_rate": 7.8125e-05, + "loss": 1.2174, + "step": 3045 + }, + { + "epoch": 3.28, + "learning_rate": 7.811781609195402e-05, + "loss": 1.1371, + "step": 3046 + }, + { + "epoch": 3.28, + "learning_rate": 7.811063218390806e-05, + "loss": 1.3115, + "step": 3047 + }, + { + "epoch": 3.28, + "learning_rate": 7.810344827586206e-05, + "loss": 1.3885, + "step": 3048 + }, + { + "epoch": 3.29, + "learning_rate": 7.80962643678161e-05, + "loss": 1.2395, + "step": 3049 + }, + { + "epoch": 3.29, + "learning_rate": 7.808908045977012e-05, + "loss": 1.1944, + "step": 3050 + }, + { + "epoch": 3.29, + "learning_rate": 7.808189655172414e-05, + "loss": 1.2173, + "step": 3051 + }, + { + "epoch": 3.29, + "learning_rate": 7.807471264367816e-05, + "loss": 1.2148, + "step": 3052 + }, + { + "epoch": 3.29, + "learning_rate": 7.806752873563219e-05, + "loss": 1.1173, + "step": 3053 + }, + { + "epoch": 3.29, + "learning_rate": 7.806034482758621e-05, + "loss": 1.0479, + "step": 3054 + }, + { + "epoch": 3.29, + "learning_rate": 7.805316091954023e-05, + "loss": 1.3443, + "step": 3055 + }, + { + "epoch": 3.29, + "learning_rate": 7.804597701149425e-05, + "loss": 1.1587, + "step": 3056 + }, + { + "epoch": 3.29, + "learning_rate": 7.803879310344829e-05, + "loss": 1.2402, + "step": 3057 + }, + { + "epoch": 3.3, + "learning_rate": 7.80316091954023e-05, + "loss": 1.2032, + "step": 3058 + }, + { + "epoch": 3.3, + "learning_rate": 7.802442528735633e-05, + "loss": 1.2486, + "step": 3059 + }, + { + "epoch": 3.3, + "learning_rate": 7.801724137931035e-05, + "loss": 1.1392, + "step": 3060 + }, + { + "epoch": 3.3, + "learning_rate": 7.801005747126438e-05, + "loss": 1.1802, + "step": 3061 + }, + { + "epoch": 3.3, + "learning_rate": 7.800287356321839e-05, + "loss": 1.1783, + "step": 3062 + }, + { + "epoch": 3.3, + "learning_rate": 7.799568965517242e-05, + "loss": 1.1795, + "step": 3063 + }, + { + "epoch": 3.3, + "learning_rate": 7.798850574712644e-05, + "loss": 1.2503, + "step": 3064 + }, + { + "epoch": 3.3, + "learning_rate": 7.798132183908046e-05, + "loss": 1.3205, + "step": 3065 + }, + { + "epoch": 3.3, + "learning_rate": 7.797413793103448e-05, + "loss": 1.2572, + "step": 3066 + }, + { + "epoch": 3.3, + "learning_rate": 7.796695402298852e-05, + "loss": 1.2545, + "step": 3067 + }, + { + "epoch": 3.31, + "learning_rate": 7.795977011494254e-05, + "loss": 1.3634, + "step": 3068 + }, + { + "epoch": 3.31, + "learning_rate": 7.795258620689656e-05, + "loss": 1.19, + "step": 3069 + }, + { + "epoch": 3.31, + "learning_rate": 7.794540229885058e-05, + "loss": 1.1954, + "step": 3070 + }, + { + "epoch": 3.31, + "learning_rate": 7.79382183908046e-05, + "loss": 1.1776, + "step": 3071 + }, + { + "epoch": 3.31, + "learning_rate": 7.793103448275862e-05, + "loss": 1.2785, + "step": 3072 + }, + { + "epoch": 3.31, + "learning_rate": 7.792385057471264e-05, + "loss": 1.1959, + "step": 3073 + }, + { + "epoch": 3.31, + "learning_rate": 7.791666666666667e-05, + "loss": 1.1336, + "step": 3074 + }, + { + "epoch": 3.31, + "learning_rate": 7.790948275862069e-05, + "loss": 1.0961, + "step": 3075 + }, + { + "epoch": 3.31, + "learning_rate": 7.790229885057471e-05, + "loss": 1.2022, + "step": 3076 + }, + { + "epoch": 3.32, + "learning_rate": 7.789511494252873e-05, + "loss": 1.3304, + "step": 3077 + }, + { + "epoch": 3.32, + "learning_rate": 7.788793103448277e-05, + "loss": 1.1406, + "step": 3078 + }, + { + "epoch": 3.32, + "learning_rate": 7.788074712643679e-05, + "loss": 1.182, + "step": 3079 + }, + { + "epoch": 3.32, + "learning_rate": 7.787356321839081e-05, + "loss": 1.1728, + "step": 3080 + }, + { + "epoch": 3.32, + "learning_rate": 7.786637931034483e-05, + "loss": 1.2564, + "step": 3081 + }, + { + "epoch": 3.32, + "learning_rate": 7.785919540229886e-05, + "loss": 1.3262, + "step": 3082 + }, + { + "epoch": 3.32, + "learning_rate": 7.785201149425287e-05, + "loss": 1.1604, + "step": 3083 + }, + { + "epoch": 3.32, + "learning_rate": 7.78448275862069e-05, + "loss": 1.2136, + "step": 3084 + }, + { + "epoch": 3.32, + "learning_rate": 7.783764367816092e-05, + "loss": 1.2039, + "step": 3085 + }, + { + "epoch": 3.33, + "learning_rate": 7.783045977011494e-05, + "loss": 1.2196, + "step": 3086 + }, + { + "epoch": 3.33, + "learning_rate": 7.782327586206896e-05, + "loss": 1.1255, + "step": 3087 + }, + { + "epoch": 3.33, + "learning_rate": 7.7816091954023e-05, + "loss": 1.1968, + "step": 3088 + }, + { + "epoch": 3.33, + "learning_rate": 7.780890804597702e-05, + "loss": 1.1711, + "step": 3089 + }, + { + "epoch": 3.33, + "learning_rate": 7.780172413793104e-05, + "loss": 1.2869, + "step": 3090 + }, + { + "epoch": 3.33, + "learning_rate": 7.779454022988506e-05, + "loss": 1.1923, + "step": 3091 + }, + { + "epoch": 3.33, + "learning_rate": 7.778735632183909e-05, + "loss": 1.1422, + "step": 3092 + }, + { + "epoch": 3.33, + "learning_rate": 7.778017241379311e-05, + "loss": 1.2198, + "step": 3093 + }, + { + "epoch": 3.33, + "learning_rate": 7.777298850574713e-05, + "loss": 1.2243, + "step": 3094 + }, + { + "epoch": 3.34, + "learning_rate": 7.776580459770115e-05, + "loss": 1.2639, + "step": 3095 + }, + { + "epoch": 3.34, + "learning_rate": 7.775862068965519e-05, + "loss": 1.377, + "step": 3096 + }, + { + "epoch": 3.34, + "learning_rate": 7.77514367816092e-05, + "loss": 1.1365, + "step": 3097 + }, + { + "epoch": 3.34, + "learning_rate": 7.774425287356321e-05, + "loss": 1.2334, + "step": 3098 + }, + { + "epoch": 3.34, + "learning_rate": 7.773706896551725e-05, + "loss": 1.3776, + "step": 3099 + }, + { + "epoch": 3.34, + "learning_rate": 7.772988505747127e-05, + "loss": 1.0667, + "step": 3100 + }, + { + "epoch": 3.34, + "learning_rate": 7.772270114942529e-05, + "loss": 1.2466, + "step": 3101 + }, + { + "epoch": 3.34, + "learning_rate": 7.771551724137931e-05, + "loss": 1.2702, + "step": 3102 + }, + { + "epoch": 3.34, + "learning_rate": 7.770833333333334e-05, + "loss": 1.2031, + "step": 3103 + }, + { + "epoch": 3.34, + "learning_rate": 7.770114942528735e-05, + "loss": 1.1234, + "step": 3104 + }, + { + "epoch": 3.35, + "learning_rate": 7.769396551724138e-05, + "loss": 1.2148, + "step": 3105 + }, + { + "epoch": 3.35, + "learning_rate": 7.76867816091954e-05, + "loss": 1.2839, + "step": 3106 + }, + { + "epoch": 3.35, + "learning_rate": 7.767959770114944e-05, + "loss": 1.2424, + "step": 3107 + }, + { + "epoch": 3.35, + "learning_rate": 7.767241379310344e-05, + "loss": 1.308, + "step": 3108 + }, + { + "epoch": 3.35, + "learning_rate": 7.766522988505748e-05, + "loss": 1.1645, + "step": 3109 + }, + { + "epoch": 3.35, + "learning_rate": 7.76580459770115e-05, + "loss": 1.2414, + "step": 3110 + }, + { + "epoch": 3.35, + "learning_rate": 7.765086206896552e-05, + "loss": 1.2319, + "step": 3111 + }, + { + "epoch": 3.35, + "learning_rate": 7.764367816091954e-05, + "loss": 1.2205, + "step": 3112 + }, + { + "epoch": 3.35, + "learning_rate": 7.763649425287357e-05, + "loss": 1.2437, + "step": 3113 + }, + { + "epoch": 3.36, + "learning_rate": 7.76293103448276e-05, + "loss": 1.2662, + "step": 3114 + }, + { + "epoch": 3.36, + "learning_rate": 7.762212643678161e-05, + "loss": 1.3907, + "step": 3115 + }, + { + "epoch": 3.36, + "learning_rate": 7.761494252873563e-05, + "loss": 1.1506, + "step": 3116 + }, + { + "epoch": 3.36, + "learning_rate": 7.760775862068967e-05, + "loss": 1.2123, + "step": 3117 + }, + { + "epoch": 3.36, + "learning_rate": 7.760057471264367e-05, + "loss": 1.2759, + "step": 3118 + }, + { + "epoch": 3.36, + "learning_rate": 7.759339080459771e-05, + "loss": 1.1613, + "step": 3119 + }, + { + "epoch": 3.36, + "learning_rate": 7.758620689655173e-05, + "loss": 1.2292, + "step": 3120 + }, + { + "epoch": 3.36, + "learning_rate": 7.757902298850576e-05, + "loss": 1.273, + "step": 3121 + }, + { + "epoch": 3.36, + "learning_rate": 7.757183908045977e-05, + "loss": 1.2076, + "step": 3122 + }, + { + "epoch": 3.37, + "learning_rate": 7.756465517241379e-05, + "loss": 1.2262, + "step": 3123 + }, + { + "epoch": 3.37, + "learning_rate": 7.755747126436782e-05, + "loss": 1.1199, + "step": 3124 + }, + { + "epoch": 3.37, + "learning_rate": 7.755028735632184e-05, + "loss": 1.3091, + "step": 3125 + }, + { + "epoch": 3.37, + "learning_rate": 7.754310344827586e-05, + "loss": 1.2346, + "step": 3126 + }, + { + "epoch": 3.37, + "learning_rate": 7.753591954022988e-05, + "loss": 1.0844, + "step": 3127 + }, + { + "epoch": 3.37, + "learning_rate": 7.752873563218392e-05, + "loss": 1.2244, + "step": 3128 + }, + { + "epoch": 3.37, + "learning_rate": 7.752155172413793e-05, + "loss": 1.1482, + "step": 3129 + }, + { + "epoch": 3.37, + "learning_rate": 7.751436781609196e-05, + "loss": 1.2024, + "step": 3130 + }, + { + "epoch": 3.37, + "learning_rate": 7.750718390804598e-05, + "loss": 1.1775, + "step": 3131 + }, + { + "epoch": 3.38, + "learning_rate": 7.75e-05, + "loss": 1.0369, + "step": 3132 + }, + { + "epoch": 3.38, + "learning_rate": 7.749281609195402e-05, + "loss": 1.2628, + "step": 3133 + }, + { + "epoch": 3.38, + "learning_rate": 7.748563218390805e-05, + "loss": 1.1768, + "step": 3134 + }, + { + "epoch": 3.38, + "learning_rate": 7.747844827586207e-05, + "loss": 1.171, + "step": 3135 + }, + { + "epoch": 3.38, + "learning_rate": 7.74712643678161e-05, + "loss": 1.0621, + "step": 3136 + }, + { + "epoch": 3.38, + "learning_rate": 7.746408045977012e-05, + "loss": 1.2303, + "step": 3137 + }, + { + "epoch": 3.38, + "learning_rate": 7.745689655172415e-05, + "loss": 1.1754, + "step": 3138 + }, + { + "epoch": 3.38, + "learning_rate": 7.744971264367817e-05, + "loss": 1.2885, + "step": 3139 + }, + { + "epoch": 3.38, + "learning_rate": 7.744252873563219e-05, + "loss": 1.2802, + "step": 3140 + }, + { + "epoch": 3.38, + "learning_rate": 7.743534482758621e-05, + "loss": 1.2779, + "step": 3141 + }, + { + "epoch": 3.39, + "learning_rate": 7.742816091954024e-05, + "loss": 1.3205, + "step": 3142 + }, + { + "epoch": 3.39, + "learning_rate": 7.742097701149425e-05, + "loss": 1.1674, + "step": 3143 + }, + { + "epoch": 3.39, + "learning_rate": 7.741379310344828e-05, + "loss": 1.3455, + "step": 3144 + }, + { + "epoch": 3.39, + "learning_rate": 7.74066091954023e-05, + "loss": 1.1374, + "step": 3145 + }, + { + "epoch": 3.39, + "learning_rate": 7.739942528735633e-05, + "loss": 1.2093, + "step": 3146 + }, + { + "epoch": 3.39, + "learning_rate": 7.739224137931035e-05, + "loss": 1.2309, + "step": 3147 + }, + { + "epoch": 3.39, + "learning_rate": 7.738505747126437e-05, + "loss": 1.1772, + "step": 3148 + }, + { + "epoch": 3.39, + "learning_rate": 7.73778735632184e-05, + "loss": 1.1986, + "step": 3149 + }, + { + "epoch": 3.39, + "learning_rate": 7.73706896551724e-05, + "loss": 1.1607, + "step": 3150 + }, + { + "epoch": 3.4, + "learning_rate": 7.736350574712644e-05, + "loss": 1.2251, + "step": 3151 + }, + { + "epoch": 3.4, + "learning_rate": 7.735632183908046e-05, + "loss": 1.222, + "step": 3152 + }, + { + "epoch": 3.4, + "learning_rate": 7.734913793103448e-05, + "loss": 1.144, + "step": 3153 + }, + { + "epoch": 3.4, + "learning_rate": 7.73419540229885e-05, + "loss": 1.2456, + "step": 3154 + }, + { + "epoch": 3.4, + "learning_rate": 7.733477011494254e-05, + "loss": 1.1169, + "step": 3155 + }, + { + "epoch": 3.4, + "learning_rate": 7.732758620689656e-05, + "loss": 1.3077, + "step": 3156 + }, + { + "epoch": 3.4, + "learning_rate": 7.732040229885058e-05, + "loss": 1.0916, + "step": 3157 + }, + { + "epoch": 3.4, + "learning_rate": 7.73132183908046e-05, + "loss": 1.3147, + "step": 3158 + }, + { + "epoch": 3.4, + "learning_rate": 7.730603448275863e-05, + "loss": 1.3965, + "step": 3159 + }, + { + "epoch": 3.41, + "learning_rate": 7.729885057471265e-05, + "loss": 1.0647, + "step": 3160 + }, + { + "epoch": 3.41, + "learning_rate": 7.729166666666667e-05, + "loss": 1.1756, + "step": 3161 + }, + { + "epoch": 3.41, + "learning_rate": 7.728448275862069e-05, + "loss": 1.3105, + "step": 3162 + }, + { + "epoch": 3.41, + "learning_rate": 7.727729885057472e-05, + "loss": 1.1628, + "step": 3163 + }, + { + "epoch": 3.41, + "learning_rate": 7.727011494252873e-05, + "loss": 1.1616, + "step": 3164 + }, + { + "epoch": 3.41, + "learning_rate": 7.726293103448277e-05, + "loss": 1.1514, + "step": 3165 + }, + { + "epoch": 3.41, + "learning_rate": 7.725574712643679e-05, + "loss": 1.1218, + "step": 3166 + }, + { + "epoch": 3.41, + "learning_rate": 7.72485632183908e-05, + "loss": 1.1459, + "step": 3167 + }, + { + "epoch": 3.41, + "learning_rate": 7.724137931034483e-05, + "loss": 1.1339, + "step": 3168 + }, + { + "epoch": 3.41, + "learning_rate": 7.723419540229886e-05, + "loss": 1.2696, + "step": 3169 + }, + { + "epoch": 3.42, + "learning_rate": 7.722701149425288e-05, + "loss": 1.1608, + "step": 3170 + }, + { + "epoch": 3.42, + "learning_rate": 7.72198275862069e-05, + "loss": 1.2282, + "step": 3171 + }, + { + "epoch": 3.42, + "learning_rate": 7.721264367816092e-05, + "loss": 1.2164, + "step": 3172 + }, + { + "epoch": 3.42, + "learning_rate": 7.720545977011494e-05, + "loss": 1.1498, + "step": 3173 + }, + { + "epoch": 3.42, + "learning_rate": 7.719827586206898e-05, + "loss": 1.0548, + "step": 3174 + }, + { + "epoch": 3.42, + "learning_rate": 7.719109195402298e-05, + "loss": 1.1099, + "step": 3175 + }, + { + "epoch": 3.42, + "learning_rate": 7.718390804597702e-05, + "loss": 1.1514, + "step": 3176 + }, + { + "epoch": 3.42, + "learning_rate": 7.717672413793104e-05, + "loss": 1.2937, + "step": 3177 + }, + { + "epoch": 3.42, + "learning_rate": 7.716954022988506e-05, + "loss": 1.2543, + "step": 3178 + }, + { + "epoch": 3.43, + "learning_rate": 7.716235632183908e-05, + "loss": 1.103, + "step": 3179 + }, + { + "epoch": 3.43, + "learning_rate": 7.715517241379311e-05, + "loss": 1.1415, + "step": 3180 + }, + { + "epoch": 3.43, + "learning_rate": 7.714798850574713e-05, + "loss": 1.187, + "step": 3181 + }, + { + "epoch": 3.43, + "learning_rate": 7.714080459770115e-05, + "loss": 1.2064, + "step": 3182 + }, + { + "epoch": 3.43, + "learning_rate": 7.713362068965517e-05, + "loss": 1.2561, + "step": 3183 + }, + { + "epoch": 3.43, + "learning_rate": 7.71264367816092e-05, + "loss": 1.1609, + "step": 3184 + }, + { + "epoch": 3.43, + "learning_rate": 7.711925287356321e-05, + "loss": 1.3689, + "step": 3185 + }, + { + "epoch": 3.43, + "learning_rate": 7.711206896551725e-05, + "loss": 1.3076, + "step": 3186 + }, + { + "epoch": 3.43, + "learning_rate": 7.710488505747127e-05, + "loss": 1.2413, + "step": 3187 + }, + { + "epoch": 3.44, + "learning_rate": 7.70977011494253e-05, + "loss": 1.286, + "step": 3188 + }, + { + "epoch": 3.44, + "learning_rate": 7.709051724137931e-05, + "loss": 1.226, + "step": 3189 + }, + { + "epoch": 3.44, + "learning_rate": 7.708333333333334e-05, + "loss": 1.233, + "step": 3190 + }, + { + "epoch": 3.44, + "learning_rate": 7.707614942528736e-05, + "loss": 1.2012, + "step": 3191 + }, + { + "epoch": 3.44, + "learning_rate": 7.706896551724138e-05, + "loss": 1.2714, + "step": 3192 + }, + { + "epoch": 3.44, + "learning_rate": 7.70617816091954e-05, + "loss": 1.1203, + "step": 3193 + }, + { + "epoch": 3.44, + "learning_rate": 7.705459770114944e-05, + "loss": 1.2947, + "step": 3194 + }, + { + "epoch": 3.44, + "learning_rate": 7.704741379310346e-05, + "loss": 1.2163, + "step": 3195 + }, + { + "epoch": 3.44, + "learning_rate": 7.704022988505748e-05, + "loss": 1.2003, + "step": 3196 + }, + { + "epoch": 3.45, + "learning_rate": 7.70330459770115e-05, + "loss": 1.2618, + "step": 3197 + }, + { + "epoch": 3.45, + "learning_rate": 7.702586206896553e-05, + "loss": 1.1762, + "step": 3198 + }, + { + "epoch": 3.45, + "learning_rate": 7.701867816091954e-05, + "loss": 1.1309, + "step": 3199 + }, + { + "epoch": 3.45, + "learning_rate": 7.701149425287356e-05, + "loss": 1.3137, + "step": 3200 + }, + { + "epoch": 3.45, + "learning_rate": 7.700431034482759e-05, + "loss": 1.2138, + "step": 3201 + }, + { + "epoch": 3.45, + "learning_rate": 7.699712643678161e-05, + "loss": 1.2036, + "step": 3202 + }, + { + "epoch": 3.45, + "learning_rate": 7.698994252873563e-05, + "loss": 1.2136, + "step": 3203 + }, + { + "epoch": 3.45, + "learning_rate": 7.698275862068965e-05, + "loss": 1.2308, + "step": 3204 + }, + { + "epoch": 3.45, + "learning_rate": 7.697557471264369e-05, + "loss": 1.32, + "step": 3205 + }, + { + "epoch": 3.45, + "learning_rate": 7.696839080459771e-05, + "loss": 1.2123, + "step": 3206 + }, + { + "epoch": 3.46, + "learning_rate": 7.696120689655173e-05, + "loss": 1.2292, + "step": 3207 + }, + { + "epoch": 3.46, + "learning_rate": 7.695402298850575e-05, + "loss": 1.1454, + "step": 3208 + }, + { + "epoch": 3.46, + "learning_rate": 7.694683908045978e-05, + "loss": 1.3597, + "step": 3209 + }, + { + "epoch": 3.46, + "learning_rate": 7.693965517241379e-05, + "loss": 1.145, + "step": 3210 + }, + { + "epoch": 3.46, + "learning_rate": 7.693247126436782e-05, + "loss": 1.3209, + "step": 3211 + }, + { + "epoch": 3.46, + "learning_rate": 7.692528735632184e-05, + "loss": 1.3396, + "step": 3212 + }, + { + "epoch": 3.46, + "learning_rate": 7.691810344827586e-05, + "loss": 1.2417, + "step": 3213 + }, + { + "epoch": 3.46, + "learning_rate": 7.691091954022988e-05, + "loss": 1.1885, + "step": 3214 + }, + { + "epoch": 3.46, + "learning_rate": 7.690373563218392e-05, + "loss": 1.1674, + "step": 3215 + }, + { + "epoch": 3.47, + "learning_rate": 7.689655172413794e-05, + "loss": 1.116, + "step": 3216 + }, + { + "epoch": 3.47, + "learning_rate": 7.688936781609196e-05, + "loss": 1.1164, + "step": 3217 + }, + { + "epoch": 3.47, + "learning_rate": 7.688218390804598e-05, + "loss": 1.104, + "step": 3218 + }, + { + "epoch": 3.47, + "learning_rate": 7.687500000000001e-05, + "loss": 1.1392, + "step": 3219 + }, + { + "epoch": 3.47, + "learning_rate": 7.686781609195403e-05, + "loss": 1.1572, + "step": 3220 + }, + { + "epoch": 3.47, + "learning_rate": 7.686063218390805e-05, + "loss": 1.1942, + "step": 3221 + }, + { + "epoch": 3.47, + "learning_rate": 7.685344827586207e-05, + "loss": 1.2713, + "step": 3222 + }, + { + "epoch": 3.47, + "learning_rate": 7.68462643678161e-05, + "loss": 1.1962, + "step": 3223 + }, + { + "epoch": 3.47, + "learning_rate": 7.683908045977011e-05, + "loss": 1.2482, + "step": 3224 + }, + { + "epoch": 3.48, + "learning_rate": 7.683189655172413e-05, + "loss": 1.1721, + "step": 3225 + }, + { + "epoch": 3.48, + "learning_rate": 7.682471264367817e-05, + "loss": 1.1305, + "step": 3226 + }, + { + "epoch": 3.48, + "learning_rate": 7.681752873563219e-05, + "loss": 1.0552, + "step": 3227 + }, + { + "epoch": 3.48, + "learning_rate": 7.681034482758621e-05, + "loss": 1.1739, + "step": 3228 + }, + { + "epoch": 3.48, + "learning_rate": 7.680316091954023e-05, + "loss": 1.2937, + "step": 3229 + }, + { + "epoch": 3.48, + "learning_rate": 7.679597701149426e-05, + "loss": 1.2902, + "step": 3230 + }, + { + "epoch": 3.48, + "learning_rate": 7.678879310344827e-05, + "loss": 1.1323, + "step": 3231 + }, + { + "epoch": 3.48, + "learning_rate": 7.67816091954023e-05, + "loss": 1.0975, + "step": 3232 + }, + { + "epoch": 3.48, + "learning_rate": 7.677442528735632e-05, + "loss": 1.1853, + "step": 3233 + }, + { + "epoch": 3.48, + "learning_rate": 7.676724137931036e-05, + "loss": 1.2368, + "step": 3234 + }, + { + "epoch": 3.49, + "learning_rate": 7.676005747126436e-05, + "loss": 1.188, + "step": 3235 + }, + { + "epoch": 3.49, + "learning_rate": 7.67528735632184e-05, + "loss": 1.1632, + "step": 3236 + }, + { + "epoch": 3.49, + "learning_rate": 7.674568965517242e-05, + "loss": 1.2819, + "step": 3237 + }, + { + "epoch": 3.49, + "learning_rate": 7.673850574712644e-05, + "loss": 1.1755, + "step": 3238 + }, + { + "epoch": 3.49, + "learning_rate": 7.673132183908046e-05, + "loss": 1.2273, + "step": 3239 + }, + { + "epoch": 3.49, + "learning_rate": 7.672413793103449e-05, + "loss": 1.351, + "step": 3240 + }, + { + "epoch": 3.49, + "learning_rate": 7.671695402298851e-05, + "loss": 1.1912, + "step": 3241 + }, + { + "epoch": 3.49, + "learning_rate": 7.670977011494253e-05, + "loss": 1.3015, + "step": 3242 + }, + { + "epoch": 3.49, + "learning_rate": 7.670258620689655e-05, + "loss": 1.212, + "step": 3243 + }, + { + "epoch": 3.5, + "learning_rate": 7.669540229885059e-05, + "loss": 1.1726, + "step": 3244 + }, + { + "epoch": 3.5, + "learning_rate": 7.66882183908046e-05, + "loss": 1.1464, + "step": 3245 + }, + { + "epoch": 3.5, + "learning_rate": 7.668103448275863e-05, + "loss": 1.2547, + "step": 3246 + }, + { + "epoch": 3.5, + "learning_rate": 7.667385057471265e-05, + "loss": 1.2093, + "step": 3247 + }, + { + "epoch": 3.5, + "learning_rate": 7.666666666666667e-05, + "loss": 1.2242, + "step": 3248 + }, + { + "epoch": 3.5, + "learning_rate": 7.665948275862069e-05, + "loss": 1.4255, + "step": 3249 + }, + { + "epoch": 3.5, + "learning_rate": 7.665229885057471e-05, + "loss": 1.3566, + "step": 3250 + }, + { + "epoch": 3.5, + "eval_loss": 1.1692960262298584, + "eval_runtime": 174.939, + "eval_samples_per_second": 127.302, + "eval_steps_per_second": 0.663, + "step": 3250 + }, + { + "epoch": 3.5, + "learning_rate": 7.664511494252874e-05, + "loss": 1.1307, + "step": 3251 + }, + { + "epoch": 3.5, + "learning_rate": 7.663793103448276e-05, + "loss": 1.1797, + "step": 3252 + }, + { + "epoch": 3.51, + "learning_rate": 7.663074712643678e-05, + "loss": 1.2729, + "step": 3253 + }, + { + "epoch": 3.51, + "learning_rate": 7.66235632183908e-05, + "loss": 1.2161, + "step": 3254 + }, + { + "epoch": 3.51, + "learning_rate": 7.661637931034484e-05, + "loss": 1.0519, + "step": 3255 + }, + { + "epoch": 3.51, + "learning_rate": 7.660919540229885e-05, + "loss": 1.2629, + "step": 3256 + }, + { + "epoch": 3.51, + "learning_rate": 7.660201149425288e-05, + "loss": 1.0088, + "step": 3257 + }, + { + "epoch": 3.51, + "learning_rate": 7.65948275862069e-05, + "loss": 1.2711, + "step": 3258 + }, + { + "epoch": 3.51, + "learning_rate": 7.658764367816092e-05, + "loss": 1.2784, + "step": 3259 + }, + { + "epoch": 3.51, + "learning_rate": 7.658045977011494e-05, + "loss": 1.1243, + "step": 3260 + }, + { + "epoch": 3.51, + "learning_rate": 7.657327586206897e-05, + "loss": 1.0514, + "step": 3261 + }, + { + "epoch": 3.52, + "learning_rate": 7.6566091954023e-05, + "loss": 1.1953, + "step": 3262 + }, + { + "epoch": 3.52, + "learning_rate": 7.655890804597701e-05, + "loss": 1.3745, + "step": 3263 + }, + { + "epoch": 3.52, + "learning_rate": 7.655172413793103e-05, + "loss": 1.1514, + "step": 3264 + }, + { + "epoch": 3.52, + "learning_rate": 7.654454022988507e-05, + "loss": 1.1461, + "step": 3265 + }, + { + "epoch": 3.52, + "learning_rate": 7.653735632183908e-05, + "loss": 1.2033, + "step": 3266 + }, + { + "epoch": 3.52, + "learning_rate": 7.653017241379311e-05, + "loss": 1.1248, + "step": 3267 + }, + { + "epoch": 3.52, + "learning_rate": 7.652298850574713e-05, + "loss": 1.1806, + "step": 3268 + }, + { + "epoch": 3.52, + "learning_rate": 7.651580459770116e-05, + "loss": 1.2753, + "step": 3269 + }, + { + "epoch": 3.52, + "learning_rate": 7.650862068965517e-05, + "loss": 1.205, + "step": 3270 + }, + { + "epoch": 3.52, + "learning_rate": 7.65014367816092e-05, + "loss": 1.2543, + "step": 3271 + }, + { + "epoch": 3.53, + "learning_rate": 7.649425287356322e-05, + "loss": 1.267, + "step": 3272 + }, + { + "epoch": 3.53, + "learning_rate": 7.648706896551724e-05, + "loss": 1.1611, + "step": 3273 + }, + { + "epoch": 3.53, + "learning_rate": 7.647988505747127e-05, + "loss": 1.0362, + "step": 3274 + }, + { + "epoch": 3.53, + "learning_rate": 7.64727011494253e-05, + "loss": 1.3882, + "step": 3275 + }, + { + "epoch": 3.53, + "learning_rate": 7.646551724137932e-05, + "loss": 1.3542, + "step": 3276 + }, + { + "epoch": 3.53, + "learning_rate": 7.645833333333333e-05, + "loss": 1.1583, + "step": 3277 + }, + { + "epoch": 3.53, + "learning_rate": 7.645114942528736e-05, + "loss": 1.145, + "step": 3278 + }, + { + "epoch": 3.53, + "learning_rate": 7.644396551724138e-05, + "loss": 1.2055, + "step": 3279 + }, + { + "epoch": 3.53, + "learning_rate": 7.64367816091954e-05, + "loss": 1.1757, + "step": 3280 + }, + { + "epoch": 3.54, + "learning_rate": 7.642959770114942e-05, + "loss": 1.054, + "step": 3281 + }, + { + "epoch": 3.54, + "learning_rate": 7.642241379310345e-05, + "loss": 1.3062, + "step": 3282 + }, + { + "epoch": 3.54, + "learning_rate": 7.641522988505748e-05, + "loss": 1.1833, + "step": 3283 + }, + { + "epoch": 3.54, + "learning_rate": 7.64080459770115e-05, + "loss": 1.1987, + "step": 3284 + }, + { + "epoch": 3.54, + "learning_rate": 7.640086206896552e-05, + "loss": 1.2146, + "step": 3285 + }, + { + "epoch": 3.54, + "learning_rate": 7.639367816091955e-05, + "loss": 1.1924, + "step": 3286 + }, + { + "epoch": 3.54, + "learning_rate": 7.638649425287357e-05, + "loss": 1.1392, + "step": 3287 + }, + { + "epoch": 3.54, + "learning_rate": 7.637931034482759e-05, + "loss": 1.1331, + "step": 3288 + }, + { + "epoch": 3.54, + "learning_rate": 7.637212643678161e-05, + "loss": 1.1555, + "step": 3289 + }, + { + "epoch": 3.55, + "learning_rate": 7.636494252873564e-05, + "loss": 1.2733, + "step": 3290 + }, + { + "epoch": 3.55, + "learning_rate": 7.635775862068965e-05, + "loss": 1.127, + "step": 3291 + }, + { + "epoch": 3.55, + "learning_rate": 7.635057471264369e-05, + "loss": 1.1299, + "step": 3292 + }, + { + "epoch": 3.55, + "learning_rate": 7.63433908045977e-05, + "loss": 1.2517, + "step": 3293 + }, + { + "epoch": 3.55, + "learning_rate": 7.633620689655173e-05, + "loss": 1.2035, + "step": 3294 + }, + { + "epoch": 3.55, + "learning_rate": 7.632902298850575e-05, + "loss": 1.0803, + "step": 3295 + }, + { + "epoch": 3.55, + "learning_rate": 7.632183908045978e-05, + "loss": 1.2195, + "step": 3296 + }, + { + "epoch": 3.55, + "learning_rate": 7.63146551724138e-05, + "loss": 1.2494, + "step": 3297 + }, + { + "epoch": 3.55, + "learning_rate": 7.630747126436782e-05, + "loss": 1.3009, + "step": 3298 + }, + { + "epoch": 3.55, + "learning_rate": 7.630028735632184e-05, + "loss": 1.1145, + "step": 3299 + }, + { + "epoch": 3.56, + "learning_rate": 7.629310344827587e-05, + "loss": 1.0944, + "step": 3300 + }, + { + "epoch": 3.56, + "learning_rate": 7.62859195402299e-05, + "loss": 1.2404, + "step": 3301 + }, + { + "epoch": 3.56, + "learning_rate": 7.62787356321839e-05, + "loss": 1.317, + "step": 3302 + }, + { + "epoch": 3.56, + "learning_rate": 7.627155172413794e-05, + "loss": 1.1631, + "step": 3303 + }, + { + "epoch": 3.56, + "learning_rate": 7.626436781609196e-05, + "loss": 1.0731, + "step": 3304 + }, + { + "epoch": 3.56, + "learning_rate": 7.625718390804598e-05, + "loss": 1.2505, + "step": 3305 + }, + { + "epoch": 3.56, + "learning_rate": 7.625e-05, + "loss": 1.0546, + "step": 3306 + }, + { + "epoch": 3.56, + "learning_rate": 7.624281609195403e-05, + "loss": 1.2825, + "step": 3307 + }, + { + "epoch": 3.56, + "learning_rate": 7.623563218390805e-05, + "loss": 1.1765, + "step": 3308 + }, + { + "epoch": 3.57, + "learning_rate": 7.622844827586207e-05, + "loss": 1.1434, + "step": 3309 + }, + { + "epoch": 3.57, + "learning_rate": 7.622126436781609e-05, + "loss": 1.3837, + "step": 3310 + }, + { + "epoch": 3.57, + "learning_rate": 7.621408045977013e-05, + "loss": 1.2634, + "step": 3311 + }, + { + "epoch": 3.57, + "learning_rate": 7.620689655172413e-05, + "loss": 1.1513, + "step": 3312 + }, + { + "epoch": 3.57, + "learning_rate": 7.619971264367817e-05, + "loss": 1.3915, + "step": 3313 + }, + { + "epoch": 3.57, + "learning_rate": 7.619252873563219e-05, + "loss": 1.2336, + "step": 3314 + }, + { + "epoch": 3.57, + "learning_rate": 7.618534482758622e-05, + "loss": 1.0289, + "step": 3315 + }, + { + "epoch": 3.57, + "learning_rate": 7.617816091954023e-05, + "loss": 1.173, + "step": 3316 + }, + { + "epoch": 3.57, + "learning_rate": 7.617097701149426e-05, + "loss": 1.2133, + "step": 3317 + }, + { + "epoch": 3.58, + "learning_rate": 7.616379310344828e-05, + "loss": 1.2875, + "step": 3318 + }, + { + "epoch": 3.58, + "learning_rate": 7.61566091954023e-05, + "loss": 1.2095, + "step": 3319 + }, + { + "epoch": 3.58, + "learning_rate": 7.614942528735632e-05, + "loss": 1.2051, + "step": 3320 + }, + { + "epoch": 3.58, + "learning_rate": 7.614224137931036e-05, + "loss": 1.191, + "step": 3321 + }, + { + "epoch": 3.58, + "learning_rate": 7.613505747126438e-05, + "loss": 1.0023, + "step": 3322 + }, + { + "epoch": 3.58, + "learning_rate": 7.61278735632184e-05, + "loss": 1.173, + "step": 3323 + }, + { + "epoch": 3.58, + "learning_rate": 7.612068965517242e-05, + "loss": 1.2936, + "step": 3324 + }, + { + "epoch": 3.58, + "learning_rate": 7.611350574712645e-05, + "loss": 1.0576, + "step": 3325 + }, + { + "epoch": 3.58, + "learning_rate": 7.610632183908046e-05, + "loss": 1.1729, + "step": 3326 + }, + { + "epoch": 3.59, + "learning_rate": 7.609913793103448e-05, + "loss": 1.211, + "step": 3327 + }, + { + "epoch": 3.59, + "learning_rate": 7.609195402298851e-05, + "loss": 1.1686, + "step": 3328 + }, + { + "epoch": 3.59, + "learning_rate": 7.608477011494253e-05, + "loss": 1.1301, + "step": 3329 + }, + { + "epoch": 3.59, + "learning_rate": 7.607758620689655e-05, + "loss": 1.1806, + "step": 3330 + }, + { + "epoch": 3.59, + "learning_rate": 7.607040229885057e-05, + "loss": 1.2421, + "step": 3331 + }, + { + "epoch": 3.59, + "learning_rate": 7.60632183908046e-05, + "loss": 1.408, + "step": 3332 + }, + { + "epoch": 3.59, + "learning_rate": 7.605603448275863e-05, + "loss": 1.2397, + "step": 3333 + }, + { + "epoch": 3.59, + "learning_rate": 7.604885057471265e-05, + "loss": 1.1529, + "step": 3334 + }, + { + "epoch": 3.59, + "learning_rate": 7.604166666666667e-05, + "loss": 1.1219, + "step": 3335 + }, + { + "epoch": 3.59, + "learning_rate": 7.60344827586207e-05, + "loss": 1.0995, + "step": 3336 + }, + { + "epoch": 3.6, + "learning_rate": 7.602729885057471e-05, + "loss": 1.2868, + "step": 3337 + }, + { + "epoch": 3.6, + "learning_rate": 7.602011494252874e-05, + "loss": 1.2172, + "step": 3338 + }, + { + "epoch": 3.6, + "learning_rate": 7.601293103448276e-05, + "loss": 1.2422, + "step": 3339 + }, + { + "epoch": 3.6, + "learning_rate": 7.600574712643678e-05, + "loss": 1.276, + "step": 3340 + }, + { + "epoch": 3.6, + "learning_rate": 7.59985632183908e-05, + "loss": 1.1807, + "step": 3341 + }, + { + "epoch": 3.6, + "learning_rate": 7.599137931034484e-05, + "loss": 1.233, + "step": 3342 + }, + { + "epoch": 3.6, + "learning_rate": 7.598419540229886e-05, + "loss": 1.197, + "step": 3343 + }, + { + "epoch": 3.6, + "learning_rate": 7.597701149425288e-05, + "loss": 1.1, + "step": 3344 + }, + { + "epoch": 3.6, + "learning_rate": 7.59698275862069e-05, + "loss": 1.2312, + "step": 3345 + }, + { + "epoch": 3.61, + "learning_rate": 7.596264367816093e-05, + "loss": 1.0522, + "step": 3346 + }, + { + "epoch": 3.61, + "learning_rate": 7.595545977011494e-05, + "loss": 1.2075, + "step": 3347 + }, + { + "epoch": 3.61, + "learning_rate": 7.594827586206897e-05, + "loss": 1.0877, + "step": 3348 + }, + { + "epoch": 3.61, + "learning_rate": 7.594109195402299e-05, + "loss": 1.293, + "step": 3349 + }, + { + "epoch": 3.61, + "learning_rate": 7.593390804597703e-05, + "loss": 1.1977, + "step": 3350 + }, + { + "epoch": 3.61, + "learning_rate": 7.592672413793103e-05, + "loss": 1.2227, + "step": 3351 + }, + { + "epoch": 3.61, + "learning_rate": 7.591954022988507e-05, + "loss": 1.195, + "step": 3352 + }, + { + "epoch": 3.61, + "learning_rate": 7.591235632183909e-05, + "loss": 1.1435, + "step": 3353 + }, + { + "epoch": 3.61, + "learning_rate": 7.590517241379311e-05, + "loss": 1.0711, + "step": 3354 + }, + { + "epoch": 3.62, + "learning_rate": 7.589798850574713e-05, + "loss": 1.1935, + "step": 3355 + }, + { + "epoch": 3.62, + "learning_rate": 7.589080459770115e-05, + "loss": 1.2696, + "step": 3356 + }, + { + "epoch": 3.62, + "learning_rate": 7.588362068965518e-05, + "loss": 1.1577, + "step": 3357 + }, + { + "epoch": 3.62, + "learning_rate": 7.587643678160919e-05, + "loss": 1.3047, + "step": 3358 + }, + { + "epoch": 3.62, + "learning_rate": 7.586925287356322e-05, + "loss": 1.0728, + "step": 3359 + }, + { + "epoch": 3.62, + "learning_rate": 7.586206896551724e-05, + "loss": 1.1921, + "step": 3360 + }, + { + "epoch": 3.62, + "learning_rate": 7.585488505747126e-05, + "loss": 1.2105, + "step": 3361 + }, + { + "epoch": 3.62, + "learning_rate": 7.584770114942528e-05, + "loss": 1.1503, + "step": 3362 + }, + { + "epoch": 3.62, + "learning_rate": 7.584051724137932e-05, + "loss": 1.1652, + "step": 3363 + }, + { + "epoch": 3.62, + "learning_rate": 7.583333333333334e-05, + "loss": 1.157, + "step": 3364 + }, + { + "epoch": 3.63, + "learning_rate": 7.582614942528736e-05, + "loss": 1.277, + "step": 3365 + }, + { + "epoch": 3.63, + "learning_rate": 7.581896551724138e-05, + "loss": 1.207, + "step": 3366 + }, + { + "epoch": 3.63, + "learning_rate": 7.581178160919541e-05, + "loss": 1.1845, + "step": 3367 + }, + { + "epoch": 3.63, + "learning_rate": 7.580459770114943e-05, + "loss": 1.4497, + "step": 3368 + }, + { + "epoch": 3.63, + "learning_rate": 7.579741379310345e-05, + "loss": 1.1412, + "step": 3369 + }, + { + "epoch": 3.63, + "learning_rate": 7.579022988505747e-05, + "loss": 1.0991, + "step": 3370 + }, + { + "epoch": 3.63, + "learning_rate": 7.578304597701151e-05, + "loss": 1.1503, + "step": 3371 + }, + { + "epoch": 3.63, + "learning_rate": 7.577586206896551e-05, + "loss": 1.2433, + "step": 3372 + }, + { + "epoch": 3.63, + "learning_rate": 7.576867816091955e-05, + "loss": 1.172, + "step": 3373 + }, + { + "epoch": 3.64, + "learning_rate": 7.576149425287357e-05, + "loss": 1.0946, + "step": 3374 + }, + { + "epoch": 3.64, + "learning_rate": 7.575431034482759e-05, + "loss": 1.1033, + "step": 3375 + }, + { + "epoch": 3.64, + "learning_rate": 7.574712643678161e-05, + "loss": 1.1796, + "step": 3376 + }, + { + "epoch": 3.64, + "learning_rate": 7.573994252873564e-05, + "loss": 1.2033, + "step": 3377 + }, + { + "epoch": 3.64, + "learning_rate": 7.573275862068966e-05, + "loss": 1.0159, + "step": 3378 + }, + { + "epoch": 3.64, + "learning_rate": 7.572557471264367e-05, + "loss": 1.2782, + "step": 3379 + }, + { + "epoch": 3.64, + "learning_rate": 7.57183908045977e-05, + "loss": 1.206, + "step": 3380 + }, + { + "epoch": 3.64, + "learning_rate": 7.571120689655172e-05, + "loss": 1.2821, + "step": 3381 + }, + { + "epoch": 3.64, + "learning_rate": 7.570402298850576e-05, + "loss": 1.1231, + "step": 3382 + }, + { + "epoch": 3.65, + "learning_rate": 7.569683908045976e-05, + "loss": 1.3277, + "step": 3383 + }, + { + "epoch": 3.65, + "learning_rate": 7.56896551724138e-05, + "loss": 1.1582, + "step": 3384 + }, + { + "epoch": 3.65, + "learning_rate": 7.568247126436782e-05, + "loss": 1.1896, + "step": 3385 + }, + { + "epoch": 3.65, + "learning_rate": 7.567528735632184e-05, + "loss": 1.1995, + "step": 3386 + }, + { + "epoch": 3.65, + "learning_rate": 7.566810344827586e-05, + "loss": 1.1524, + "step": 3387 + }, + { + "epoch": 3.65, + "learning_rate": 7.56609195402299e-05, + "loss": 1.2231, + "step": 3388 + }, + { + "epoch": 3.65, + "learning_rate": 7.565373563218391e-05, + "loss": 1.2053, + "step": 3389 + }, + { + "epoch": 3.65, + "learning_rate": 7.564655172413793e-05, + "loss": 1.2982, + "step": 3390 + }, + { + "epoch": 3.65, + "learning_rate": 7.563936781609195e-05, + "loss": 1.2351, + "step": 3391 + }, + { + "epoch": 3.66, + "learning_rate": 7.563218390804599e-05, + "loss": 1.2333, + "step": 3392 + }, + { + "epoch": 3.66, + "learning_rate": 7.5625e-05, + "loss": 1.189, + "step": 3393 + }, + { + "epoch": 3.66, + "learning_rate": 7.561781609195403e-05, + "loss": 1.2262, + "step": 3394 + }, + { + "epoch": 3.66, + "learning_rate": 7.561063218390805e-05, + "loss": 1.2905, + "step": 3395 + }, + { + "epoch": 3.66, + "learning_rate": 7.560344827586208e-05, + "loss": 1.3174, + "step": 3396 + }, + { + "epoch": 3.66, + "learning_rate": 7.559626436781609e-05, + "loss": 1.1704, + "step": 3397 + }, + { + "epoch": 3.66, + "learning_rate": 7.558908045977012e-05, + "loss": 1.1811, + "step": 3398 + }, + { + "epoch": 3.66, + "learning_rate": 7.558189655172414e-05, + "loss": 1.1066, + "step": 3399 + }, + { + "epoch": 3.66, + "learning_rate": 7.557471264367816e-05, + "loss": 1.1785, + "step": 3400 + }, + { + "epoch": 3.66, + "learning_rate": 7.556752873563218e-05, + "loss": 1.1992, + "step": 3401 + }, + { + "epoch": 3.67, + "learning_rate": 7.556034482758622e-05, + "loss": 1.2109, + "step": 3402 + }, + { + "epoch": 3.67, + "learning_rate": 7.555316091954024e-05, + "loss": 1.2645, + "step": 3403 + }, + { + "epoch": 3.67, + "learning_rate": 7.554597701149425e-05, + "loss": 1.291, + "step": 3404 + }, + { + "epoch": 3.67, + "learning_rate": 7.553879310344828e-05, + "loss": 1.2532, + "step": 3405 + }, + { + "epoch": 3.67, + "learning_rate": 7.55316091954023e-05, + "loss": 1.2267, + "step": 3406 + }, + { + "epoch": 3.67, + "learning_rate": 7.552442528735632e-05, + "loss": 1.1771, + "step": 3407 + }, + { + "epoch": 3.67, + "learning_rate": 7.551724137931034e-05, + "loss": 1.1421, + "step": 3408 + }, + { + "epoch": 3.67, + "learning_rate": 7.551005747126437e-05, + "loss": 1.2071, + "step": 3409 + }, + { + "epoch": 3.67, + "learning_rate": 7.55028735632184e-05, + "loss": 1.0658, + "step": 3410 + }, + { + "epoch": 3.68, + "learning_rate": 7.549568965517242e-05, + "loss": 1.1073, + "step": 3411 + }, + { + "epoch": 3.68, + "learning_rate": 7.548850574712644e-05, + "loss": 1.206, + "step": 3412 + }, + { + "epoch": 3.68, + "learning_rate": 7.548132183908047e-05, + "loss": 1.2321, + "step": 3413 + }, + { + "epoch": 3.68, + "learning_rate": 7.547413793103449e-05, + "loss": 1.3698, + "step": 3414 + }, + { + "epoch": 3.68, + "learning_rate": 7.546695402298851e-05, + "loss": 1.1433, + "step": 3415 + }, + { + "epoch": 3.68, + "learning_rate": 7.545977011494253e-05, + "loss": 1.2725, + "step": 3416 + }, + { + "epoch": 3.68, + "learning_rate": 7.545258620689656e-05, + "loss": 1.1347, + "step": 3417 + }, + { + "epoch": 3.68, + "learning_rate": 7.544540229885057e-05, + "loss": 1.2043, + "step": 3418 + }, + { + "epoch": 3.68, + "learning_rate": 7.54382183908046e-05, + "loss": 1.1828, + "step": 3419 + }, + { + "epoch": 3.69, + "learning_rate": 7.543103448275863e-05, + "loss": 1.2092, + "step": 3420 + }, + { + "epoch": 3.69, + "learning_rate": 7.542385057471265e-05, + "loss": 1.1453, + "step": 3421 + }, + { + "epoch": 3.69, + "learning_rate": 7.541666666666667e-05, + "loss": 1.1544, + "step": 3422 + }, + { + "epoch": 3.69, + "learning_rate": 7.54094827586207e-05, + "loss": 1.1674, + "step": 3423 + }, + { + "epoch": 3.69, + "learning_rate": 7.540229885057472e-05, + "loss": 1.2767, + "step": 3424 + }, + { + "epoch": 3.69, + "learning_rate": 7.539511494252874e-05, + "loss": 1.2168, + "step": 3425 + }, + { + "epoch": 3.69, + "learning_rate": 7.538793103448276e-05, + "loss": 1.291, + "step": 3426 + }, + { + "epoch": 3.69, + "learning_rate": 7.53807471264368e-05, + "loss": 1.2355, + "step": 3427 + }, + { + "epoch": 3.69, + "learning_rate": 7.537356321839081e-05, + "loss": 1.1174, + "step": 3428 + }, + { + "epoch": 3.7, + "learning_rate": 7.536637931034482e-05, + "loss": 1.1411, + "step": 3429 + }, + { + "epoch": 3.7, + "learning_rate": 7.535919540229886e-05, + "loss": 1.0689, + "step": 3430 + }, + { + "epoch": 3.7, + "learning_rate": 7.535201149425288e-05, + "loss": 1.0665, + "step": 3431 + }, + { + "epoch": 3.7, + "learning_rate": 7.53448275862069e-05, + "loss": 1.0996, + "step": 3432 + }, + { + "epoch": 3.7, + "learning_rate": 7.533764367816092e-05, + "loss": 1.1551, + "step": 3433 + }, + { + "epoch": 3.7, + "learning_rate": 7.533045977011495e-05, + "loss": 1.1936, + "step": 3434 + }, + { + "epoch": 3.7, + "learning_rate": 7.532327586206897e-05, + "loss": 1.2669, + "step": 3435 + }, + { + "epoch": 3.7, + "learning_rate": 7.531609195402299e-05, + "loss": 1.2181, + "step": 3436 + }, + { + "epoch": 3.7, + "learning_rate": 7.530890804597701e-05, + "loss": 1.2451, + "step": 3437 + }, + { + "epoch": 3.7, + "learning_rate": 7.530172413793105e-05, + "loss": 1.2317, + "step": 3438 + }, + { + "epoch": 3.71, + "learning_rate": 7.529454022988505e-05, + "loss": 1.209, + "step": 3439 + }, + { + "epoch": 3.71, + "learning_rate": 7.528735632183909e-05, + "loss": 1.2453, + "step": 3440 + }, + { + "epoch": 3.71, + "learning_rate": 7.52801724137931e-05, + "loss": 1.1445, + "step": 3441 + }, + { + "epoch": 3.71, + "learning_rate": 7.527298850574713e-05, + "loss": 1.2509, + "step": 3442 + }, + { + "epoch": 3.71, + "learning_rate": 7.526580459770115e-05, + "loss": 1.253, + "step": 3443 + }, + { + "epoch": 3.71, + "learning_rate": 7.525862068965518e-05, + "loss": 1.1793, + "step": 3444 + }, + { + "epoch": 3.71, + "learning_rate": 7.52514367816092e-05, + "loss": 1.3565, + "step": 3445 + }, + { + "epoch": 3.71, + "learning_rate": 7.524425287356322e-05, + "loss": 1.1696, + "step": 3446 + }, + { + "epoch": 3.71, + "learning_rate": 7.523706896551724e-05, + "loss": 1.3134, + "step": 3447 + }, + { + "epoch": 3.72, + "learning_rate": 7.522988505747128e-05, + "loss": 1.204, + "step": 3448 + }, + { + "epoch": 3.72, + "learning_rate": 7.52227011494253e-05, + "loss": 1.3509, + "step": 3449 + }, + { + "epoch": 3.72, + "learning_rate": 7.521551724137932e-05, + "loss": 1.2508, + "step": 3450 + }, + { + "epoch": 3.72, + "learning_rate": 7.520833333333334e-05, + "loss": 1.0219, + "step": 3451 + }, + { + "epoch": 3.72, + "learning_rate": 7.520114942528737e-05, + "loss": 1.3812, + "step": 3452 + }, + { + "epoch": 3.72, + "learning_rate": 7.519396551724138e-05, + "loss": 1.2875, + "step": 3453 + }, + { + "epoch": 3.72, + "learning_rate": 7.518678160919541e-05, + "loss": 1.3229, + "step": 3454 + }, + { + "epoch": 3.72, + "learning_rate": 7.517959770114943e-05, + "loss": 1.1605, + "step": 3455 + }, + { + "epoch": 3.72, + "learning_rate": 7.517241379310345e-05, + "loss": 1.2429, + "step": 3456 + }, + { + "epoch": 3.73, + "learning_rate": 7.516522988505747e-05, + "loss": 1.2822, + "step": 3457 + }, + { + "epoch": 3.73, + "learning_rate": 7.515804597701149e-05, + "loss": 1.182, + "step": 3458 + }, + { + "epoch": 3.73, + "learning_rate": 7.515086206896553e-05, + "loss": 1.142, + "step": 3459 + }, + { + "epoch": 3.73, + "learning_rate": 7.514367816091953e-05, + "loss": 1.2493, + "step": 3460 + }, + { + "epoch": 3.73, + "learning_rate": 7.513649425287357e-05, + "loss": 1.1149, + "step": 3461 + }, + { + "epoch": 3.73, + "learning_rate": 7.512931034482759e-05, + "loss": 1.0567, + "step": 3462 + }, + { + "epoch": 3.73, + "learning_rate": 7.512212643678162e-05, + "loss": 1.3209, + "step": 3463 + }, + { + "epoch": 3.73, + "learning_rate": 7.511494252873563e-05, + "loss": 1.3146, + "step": 3464 + }, + { + "epoch": 3.73, + "learning_rate": 7.510775862068966e-05, + "loss": 1.1835, + "step": 3465 + }, + { + "epoch": 3.73, + "learning_rate": 7.510057471264368e-05, + "loss": 1.1672, + "step": 3466 + }, + { + "epoch": 3.74, + "learning_rate": 7.50933908045977e-05, + "loss": 1.2502, + "step": 3467 + }, + { + "epoch": 3.74, + "learning_rate": 7.508620689655172e-05, + "loss": 1.1729, + "step": 3468 + }, + { + "epoch": 3.74, + "learning_rate": 7.507902298850576e-05, + "loss": 1.2097, + "step": 3469 + }, + { + "epoch": 3.74, + "learning_rate": 7.507183908045978e-05, + "loss": 1.1222, + "step": 3470 + }, + { + "epoch": 3.74, + "learning_rate": 7.50646551724138e-05, + "loss": 1.1593, + "step": 3471 + }, + { + "epoch": 3.74, + "learning_rate": 7.505747126436782e-05, + "loss": 1.3334, + "step": 3472 + }, + { + "epoch": 3.74, + "learning_rate": 7.505028735632185e-05, + "loss": 1.1911, + "step": 3473 + }, + { + "epoch": 3.74, + "learning_rate": 7.504310344827586e-05, + "loss": 1.2463, + "step": 3474 + }, + { + "epoch": 3.74, + "learning_rate": 7.503591954022989e-05, + "loss": 1.1544, + "step": 3475 + }, + { + "epoch": 3.75, + "learning_rate": 7.502873563218391e-05, + "loss": 1.1799, + "step": 3476 + }, + { + "epoch": 3.75, + "learning_rate": 7.502155172413795e-05, + "loss": 1.1913, + "step": 3477 + }, + { + "epoch": 3.75, + "learning_rate": 7.501436781609195e-05, + "loss": 1.3417, + "step": 3478 + }, + { + "epoch": 3.75, + "learning_rate": 7.500718390804599e-05, + "loss": 1.1074, + "step": 3479 + }, + { + "epoch": 3.75, + "learning_rate": 7.500000000000001e-05, + "loss": 1.2217, + "step": 3480 + }, + { + "epoch": 3.75, + "learning_rate": 7.499281609195403e-05, + "loss": 1.1151, + "step": 3481 + }, + { + "epoch": 3.75, + "learning_rate": 7.498563218390805e-05, + "loss": 1.1776, + "step": 3482 + }, + { + "epoch": 3.75, + "learning_rate": 7.497844827586207e-05, + "loss": 1.1429, + "step": 3483 + }, + { + "epoch": 3.75, + "learning_rate": 7.49712643678161e-05, + "loss": 1.149, + "step": 3484 + }, + { + "epoch": 3.76, + "learning_rate": 7.496408045977011e-05, + "loss": 1.2002, + "step": 3485 + }, + { + "epoch": 3.76, + "learning_rate": 7.495689655172414e-05, + "loss": 1.1788, + "step": 3486 + }, + { + "epoch": 3.76, + "learning_rate": 7.494971264367816e-05, + "loss": 1.2851, + "step": 3487 + }, + { + "epoch": 3.76, + "learning_rate": 7.494252873563218e-05, + "loss": 1.2627, + "step": 3488 + }, + { + "epoch": 3.76, + "learning_rate": 7.49353448275862e-05, + "loss": 1.2551, + "step": 3489 + }, + { + "epoch": 3.76, + "learning_rate": 7.492816091954024e-05, + "loss": 1.1012, + "step": 3490 + }, + { + "epoch": 3.76, + "learning_rate": 7.492097701149426e-05, + "loss": 1.1813, + "step": 3491 + }, + { + "epoch": 3.76, + "learning_rate": 7.491379310344828e-05, + "loss": 1.1614, + "step": 3492 + }, + { + "epoch": 3.76, + "learning_rate": 7.49066091954023e-05, + "loss": 1.0684, + "step": 3493 + }, + { + "epoch": 3.77, + "learning_rate": 7.489942528735633e-05, + "loss": 1.1597, + "step": 3494 + }, + { + "epoch": 3.77, + "learning_rate": 7.489224137931035e-05, + "loss": 1.2429, + "step": 3495 + }, + { + "epoch": 3.77, + "learning_rate": 7.488505747126437e-05, + "loss": 1.1953, + "step": 3496 + }, + { + "epoch": 3.77, + "learning_rate": 7.487787356321839e-05, + "loss": 1.2348, + "step": 3497 + }, + { + "epoch": 3.77, + "learning_rate": 7.487068965517243e-05, + "loss": 1.3037, + "step": 3498 + }, + { + "epoch": 3.77, + "learning_rate": 7.486350574712643e-05, + "loss": 1.3173, + "step": 3499 + }, + { + "epoch": 3.77, + "learning_rate": 7.485632183908047e-05, + "loss": 1.1489, + "step": 3500 + }, + { + "epoch": 3.77, + "eval_loss": 1.161754846572876, + "eval_runtime": 175.0332, + "eval_samples_per_second": 127.233, + "eval_steps_per_second": 0.663, + "step": 3500 + }, + { + "epoch": 3.77, + "learning_rate": 7.484913793103449e-05, + "loss": 1.1923, + "step": 3501 + }, + { + "epoch": 3.77, + "learning_rate": 7.484195402298851e-05, + "loss": 1.1237, + "step": 3502 + }, + { + "epoch": 3.77, + "learning_rate": 7.483477011494253e-05, + "loss": 1.2889, + "step": 3503 + }, + { + "epoch": 3.78, + "learning_rate": 7.482758620689656e-05, + "loss": 1.2489, + "step": 3504 + }, + { + "epoch": 3.78, + "learning_rate": 7.482040229885058e-05, + "loss": 1.2209, + "step": 3505 + }, + { + "epoch": 3.78, + "learning_rate": 7.481321839080459e-05, + "loss": 1.1723, + "step": 3506 + }, + { + "epoch": 3.78, + "learning_rate": 7.480603448275862e-05, + "loss": 1.1421, + "step": 3507 + }, + { + "epoch": 3.78, + "learning_rate": 7.479885057471264e-05, + "loss": 1.1442, + "step": 3508 + }, + { + "epoch": 3.78, + "learning_rate": 7.479166666666668e-05, + "loss": 1.1612, + "step": 3509 + }, + { + "epoch": 3.78, + "learning_rate": 7.478448275862068e-05, + "loss": 1.1736, + "step": 3510 + }, + { + "epoch": 3.78, + "learning_rate": 7.477729885057472e-05, + "loss": 1.3165, + "step": 3511 + }, + { + "epoch": 3.78, + "learning_rate": 7.477011494252874e-05, + "loss": 1.1813, + "step": 3512 + }, + { + "epoch": 3.79, + "learning_rate": 7.476293103448276e-05, + "loss": 1.078, + "step": 3513 + }, + { + "epoch": 3.79, + "learning_rate": 7.475574712643678e-05, + "loss": 1.121, + "step": 3514 + }, + { + "epoch": 3.79, + "learning_rate": 7.474856321839081e-05, + "loss": 1.2293, + "step": 3515 + }, + { + "epoch": 3.79, + "learning_rate": 7.474137931034483e-05, + "loss": 1.3136, + "step": 3516 + }, + { + "epoch": 3.79, + "learning_rate": 7.473419540229885e-05, + "loss": 1.1099, + "step": 3517 + }, + { + "epoch": 3.79, + "learning_rate": 7.472701149425287e-05, + "loss": 1.2038, + "step": 3518 + }, + { + "epoch": 3.79, + "learning_rate": 7.471982758620691e-05, + "loss": 1.2623, + "step": 3519 + }, + { + "epoch": 3.79, + "learning_rate": 7.471264367816091e-05, + "loss": 1.2393, + "step": 3520 + }, + { + "epoch": 3.79, + "learning_rate": 7.470545977011495e-05, + "loss": 1.0465, + "step": 3521 + }, + { + "epoch": 3.8, + "learning_rate": 7.469827586206897e-05, + "loss": 1.2233, + "step": 3522 + }, + { + "epoch": 3.8, + "learning_rate": 7.469109195402299e-05, + "loss": 1.1481, + "step": 3523 + }, + { + "epoch": 3.8, + "learning_rate": 7.468390804597701e-05, + "loss": 1.1158, + "step": 3524 + }, + { + "epoch": 3.8, + "learning_rate": 7.467672413793104e-05, + "loss": 1.2686, + "step": 3525 + }, + { + "epoch": 3.8, + "learning_rate": 7.466954022988506e-05, + "loss": 1.1465, + "step": 3526 + }, + { + "epoch": 3.8, + "learning_rate": 7.466235632183908e-05, + "loss": 1.1753, + "step": 3527 + }, + { + "epoch": 3.8, + "learning_rate": 7.46551724137931e-05, + "loss": 1.2728, + "step": 3528 + }, + { + "epoch": 3.8, + "learning_rate": 7.464798850574714e-05, + "loss": 1.2235, + "step": 3529 + }, + { + "epoch": 3.8, + "learning_rate": 7.464080459770116e-05, + "loss": 1.1431, + "step": 3530 + }, + { + "epoch": 3.8, + "learning_rate": 7.463362068965518e-05, + "loss": 1.1104, + "step": 3531 + }, + { + "epoch": 3.81, + "learning_rate": 7.46264367816092e-05, + "loss": 1.1581, + "step": 3532 + }, + { + "epoch": 3.81, + "learning_rate": 7.461925287356322e-05, + "loss": 1.1951, + "step": 3533 + }, + { + "epoch": 3.81, + "learning_rate": 7.461206896551724e-05, + "loss": 1.1756, + "step": 3534 + }, + { + "epoch": 3.81, + "learning_rate": 7.460488505747126e-05, + "loss": 1.2588, + "step": 3535 + }, + { + "epoch": 3.81, + "learning_rate": 7.45977011494253e-05, + "loss": 1.1712, + "step": 3536 + }, + { + "epoch": 3.81, + "learning_rate": 7.459051724137931e-05, + "loss": 1.3936, + "step": 3537 + }, + { + "epoch": 3.81, + "learning_rate": 7.458333333333333e-05, + "loss": 1.1232, + "step": 3538 + }, + { + "epoch": 3.81, + "learning_rate": 7.457614942528736e-05, + "loss": 1.1059, + "step": 3539 + }, + { + "epoch": 3.81, + "learning_rate": 7.456896551724139e-05, + "loss": 1.277, + "step": 3540 + }, + { + "epoch": 3.82, + "learning_rate": 7.456178160919541e-05, + "loss": 1.2192, + "step": 3541 + }, + { + "epoch": 3.82, + "learning_rate": 7.455459770114943e-05, + "loss": 1.1791, + "step": 3542 + }, + { + "epoch": 3.82, + "learning_rate": 7.454741379310345e-05, + "loss": 1.3069, + "step": 3543 + }, + { + "epoch": 3.82, + "learning_rate": 7.454022988505748e-05, + "loss": 1.1381, + "step": 3544 + }, + { + "epoch": 3.82, + "learning_rate": 7.453304597701149e-05, + "loss": 1.3106, + "step": 3545 + }, + { + "epoch": 3.82, + "learning_rate": 7.452586206896552e-05, + "loss": 1.1511, + "step": 3546 + }, + { + "epoch": 3.82, + "learning_rate": 7.451867816091954e-05, + "loss": 1.2919, + "step": 3547 + }, + { + "epoch": 3.82, + "learning_rate": 7.451149425287357e-05, + "loss": 1.265, + "step": 3548 + }, + { + "epoch": 3.82, + "learning_rate": 7.450431034482759e-05, + "loss": 1.2984, + "step": 3549 + }, + { + "epoch": 3.83, + "learning_rate": 7.449712643678162e-05, + "loss": 1.2031, + "step": 3550 + }, + { + "epoch": 3.83, + "learning_rate": 7.448994252873564e-05, + "loss": 1.1761, + "step": 3551 + }, + { + "epoch": 3.83, + "learning_rate": 7.448275862068966e-05, + "loss": 1.2455, + "step": 3552 + }, + { + "epoch": 3.83, + "learning_rate": 7.447557471264368e-05, + "loss": 1.2256, + "step": 3553 + }, + { + "epoch": 3.83, + "learning_rate": 7.446839080459771e-05, + "loss": 0.9901, + "step": 3554 + }, + { + "epoch": 3.83, + "learning_rate": 7.446120689655172e-05, + "loss": 1.1453, + "step": 3555 + }, + { + "epoch": 3.83, + "learning_rate": 7.445402298850575e-05, + "loss": 1.1659, + "step": 3556 + }, + { + "epoch": 3.83, + "learning_rate": 7.444683908045978e-05, + "loss": 1.1434, + "step": 3557 + }, + { + "epoch": 3.83, + "learning_rate": 7.44396551724138e-05, + "loss": 1.1935, + "step": 3558 + }, + { + "epoch": 3.84, + "learning_rate": 7.443247126436782e-05, + "loss": 1.2115, + "step": 3559 + }, + { + "epoch": 3.84, + "learning_rate": 7.442528735632184e-05, + "loss": 1.2673, + "step": 3560 + }, + { + "epoch": 3.84, + "learning_rate": 7.441810344827587e-05, + "loss": 1.1613, + "step": 3561 + }, + { + "epoch": 3.84, + "learning_rate": 7.441091954022989e-05, + "loss": 1.0391, + "step": 3562 + }, + { + "epoch": 3.84, + "learning_rate": 7.440373563218391e-05, + "loss": 1.1698, + "step": 3563 + }, + { + "epoch": 3.84, + "learning_rate": 7.439655172413793e-05, + "loss": 1.0533, + "step": 3564 + }, + { + "epoch": 3.84, + "learning_rate": 7.438936781609196e-05, + "loss": 1.1852, + "step": 3565 + }, + { + "epoch": 3.84, + "learning_rate": 7.438218390804597e-05, + "loss": 1.1255, + "step": 3566 + }, + { + "epoch": 3.84, + "learning_rate": 7.4375e-05, + "loss": 1.0982, + "step": 3567 + }, + { + "epoch": 3.84, + "learning_rate": 7.436781609195403e-05, + "loss": 1.2835, + "step": 3568 + }, + { + "epoch": 3.85, + "learning_rate": 7.436063218390805e-05, + "loss": 1.2619, + "step": 3569 + }, + { + "epoch": 3.85, + "learning_rate": 7.435344827586207e-05, + "loss": 1.0212, + "step": 3570 + }, + { + "epoch": 3.85, + "learning_rate": 7.43462643678161e-05, + "loss": 1.0998, + "step": 3571 + }, + { + "epoch": 3.85, + "learning_rate": 7.433908045977012e-05, + "loss": 1.1357, + "step": 3572 + }, + { + "epoch": 3.85, + "learning_rate": 7.433189655172414e-05, + "loss": 1.1873, + "step": 3573 + }, + { + "epoch": 3.85, + "learning_rate": 7.432471264367816e-05, + "loss": 1.1476, + "step": 3574 + }, + { + "epoch": 3.85, + "learning_rate": 7.43175287356322e-05, + "loss": 1.2669, + "step": 3575 + }, + { + "epoch": 3.85, + "learning_rate": 7.431034482758622e-05, + "loss": 1.2792, + "step": 3576 + }, + { + "epoch": 3.85, + "learning_rate": 7.430316091954024e-05, + "loss": 1.2621, + "step": 3577 + }, + { + "epoch": 3.86, + "learning_rate": 7.429597701149426e-05, + "loss": 1.2354, + "step": 3578 + }, + { + "epoch": 3.86, + "learning_rate": 7.428879310344829e-05, + "loss": 1.1579, + "step": 3579 + }, + { + "epoch": 3.86, + "learning_rate": 7.42816091954023e-05, + "loss": 1.1244, + "step": 3580 + }, + { + "epoch": 3.86, + "learning_rate": 7.427442528735633e-05, + "loss": 1.2808, + "step": 3581 + }, + { + "epoch": 3.86, + "learning_rate": 7.426724137931035e-05, + "loss": 1.1975, + "step": 3582 + }, + { + "epoch": 3.86, + "learning_rate": 7.426005747126437e-05, + "loss": 1.1508, + "step": 3583 + }, + { + "epoch": 3.86, + "learning_rate": 7.425287356321839e-05, + "loss": 1.1679, + "step": 3584 + }, + { + "epoch": 3.86, + "learning_rate": 7.424568965517241e-05, + "loss": 1.2475, + "step": 3585 + }, + { + "epoch": 3.86, + "learning_rate": 7.423850574712645e-05, + "loss": 1.2245, + "step": 3586 + }, + { + "epoch": 3.87, + "learning_rate": 7.423132183908045e-05, + "loss": 1.2073, + "step": 3587 + }, + { + "epoch": 3.87, + "learning_rate": 7.422413793103449e-05, + "loss": 1.2382, + "step": 3588 + }, + { + "epoch": 3.87, + "learning_rate": 7.42169540229885e-05, + "loss": 1.0748, + "step": 3589 + }, + { + "epoch": 3.87, + "learning_rate": 7.420977011494254e-05, + "loss": 1.14, + "step": 3590 + }, + { + "epoch": 3.87, + "learning_rate": 7.420258620689655e-05, + "loss": 1.1594, + "step": 3591 + }, + { + "epoch": 3.87, + "learning_rate": 7.419540229885058e-05, + "loss": 1.2062, + "step": 3592 + }, + { + "epoch": 3.87, + "learning_rate": 7.41882183908046e-05, + "loss": 1.1135, + "step": 3593 + }, + { + "epoch": 3.87, + "learning_rate": 7.418103448275862e-05, + "loss": 1.16, + "step": 3594 + }, + { + "epoch": 3.87, + "learning_rate": 7.417385057471264e-05, + "loss": 1.2546, + "step": 3595 + }, + { + "epoch": 3.88, + "learning_rate": 7.416666666666668e-05, + "loss": 1.2126, + "step": 3596 + }, + { + "epoch": 3.88, + "learning_rate": 7.41594827586207e-05, + "loss": 1.2927, + "step": 3597 + }, + { + "epoch": 3.88, + "learning_rate": 7.415229885057472e-05, + "loss": 1.1758, + "step": 3598 + }, + { + "epoch": 3.88, + "learning_rate": 7.414511494252874e-05, + "loss": 1.2198, + "step": 3599 + }, + { + "epoch": 3.88, + "learning_rate": 7.413793103448277e-05, + "loss": 1.1761, + "step": 3600 + }, + { + "epoch": 3.88, + "learning_rate": 7.413074712643678e-05, + "loss": 1.1131, + "step": 3601 + }, + { + "epoch": 3.88, + "learning_rate": 7.412356321839081e-05, + "loss": 1.2632, + "step": 3602 + }, + { + "epoch": 3.88, + "learning_rate": 7.411637931034483e-05, + "loss": 1.2701, + "step": 3603 + }, + { + "epoch": 3.88, + "learning_rate": 7.410919540229885e-05, + "loss": 1.2407, + "step": 3604 + }, + { + "epoch": 3.88, + "learning_rate": 7.410201149425287e-05, + "loss": 1.2544, + "step": 3605 + }, + { + "epoch": 3.89, + "learning_rate": 7.40948275862069e-05, + "loss": 1.0976, + "step": 3606 + }, + { + "epoch": 3.89, + "learning_rate": 7.408764367816093e-05, + "loss": 1.2508, + "step": 3607 + }, + { + "epoch": 3.89, + "learning_rate": 7.408045977011495e-05, + "loss": 1.1963, + "step": 3608 + }, + { + "epoch": 3.89, + "learning_rate": 7.407327586206897e-05, + "loss": 1.3103, + "step": 3609 + }, + { + "epoch": 3.89, + "learning_rate": 7.406609195402299e-05, + "loss": 1.2156, + "step": 3610 + }, + { + "epoch": 3.89, + "learning_rate": 7.405890804597702e-05, + "loss": 0.9991, + "step": 3611 + }, + { + "epoch": 3.89, + "learning_rate": 7.405172413793103e-05, + "loss": 1.3263, + "step": 3612 + }, + { + "epoch": 3.89, + "learning_rate": 7.404454022988506e-05, + "loss": 1.1046, + "step": 3613 + }, + { + "epoch": 3.89, + "learning_rate": 7.403735632183908e-05, + "loss": 1.4175, + "step": 3614 + }, + { + "epoch": 3.9, + "learning_rate": 7.40301724137931e-05, + "loss": 1.2921, + "step": 3615 + }, + { + "epoch": 3.9, + "learning_rate": 7.402298850574712e-05, + "loss": 1.1647, + "step": 3616 + }, + { + "epoch": 3.9, + "learning_rate": 7.401580459770116e-05, + "loss": 1.2961, + "step": 3617 + }, + { + "epoch": 3.9, + "learning_rate": 7.400862068965518e-05, + "loss": 1.1125, + "step": 3618 + }, + { + "epoch": 3.9, + "learning_rate": 7.40014367816092e-05, + "loss": 1.1297, + "step": 3619 + }, + { + "epoch": 3.9, + "learning_rate": 7.399425287356322e-05, + "loss": 1.128, + "step": 3620 + }, + { + "epoch": 3.9, + "learning_rate": 7.398706896551725e-05, + "loss": 1.0888, + "step": 3621 + }, + { + "epoch": 3.9, + "learning_rate": 7.397988505747127e-05, + "loss": 1.1846, + "step": 3622 + }, + { + "epoch": 3.9, + "learning_rate": 7.397270114942529e-05, + "loss": 1.1898, + "step": 3623 + }, + { + "epoch": 3.91, + "learning_rate": 7.396551724137931e-05, + "loss": 1.1716, + "step": 3624 + }, + { + "epoch": 3.91, + "learning_rate": 7.395833333333335e-05, + "loss": 1.2592, + "step": 3625 + }, + { + "epoch": 3.91, + "learning_rate": 7.395114942528735e-05, + "loss": 1.2872, + "step": 3626 + }, + { + "epoch": 3.91, + "learning_rate": 7.394396551724139e-05, + "loss": 1.1765, + "step": 3627 + }, + { + "epoch": 3.91, + "learning_rate": 7.393678160919541e-05, + "loss": 1.3245, + "step": 3628 + }, + { + "epoch": 3.91, + "learning_rate": 7.392959770114943e-05, + "loss": 1.1244, + "step": 3629 + }, + { + "epoch": 3.91, + "learning_rate": 7.392241379310345e-05, + "loss": 1.2045, + "step": 3630 + }, + { + "epoch": 3.91, + "learning_rate": 7.391522988505748e-05, + "loss": 1.2294, + "step": 3631 + }, + { + "epoch": 3.91, + "learning_rate": 7.39080459770115e-05, + "loss": 1.1777, + "step": 3632 + }, + { + "epoch": 3.91, + "learning_rate": 7.390086206896552e-05, + "loss": 1.1464, + "step": 3633 + }, + { + "epoch": 3.92, + "learning_rate": 7.389367816091954e-05, + "loss": 1.2475, + "step": 3634 + }, + { + "epoch": 3.92, + "learning_rate": 7.388649425287356e-05, + "loss": 1.2283, + "step": 3635 + }, + { + "epoch": 3.92, + "learning_rate": 7.387931034482758e-05, + "loss": 1.2157, + "step": 3636 + }, + { + "epoch": 3.92, + "learning_rate": 7.38721264367816e-05, + "loss": 1.2239, + "step": 3637 + }, + { + "epoch": 3.92, + "learning_rate": 7.386494252873564e-05, + "loss": 1.18, + "step": 3638 + }, + { + "epoch": 3.92, + "learning_rate": 7.385775862068966e-05, + "loss": 1.2578, + "step": 3639 + }, + { + "epoch": 3.92, + "learning_rate": 7.385057471264368e-05, + "loss": 1.2719, + "step": 3640 + }, + { + "epoch": 3.92, + "learning_rate": 7.38433908045977e-05, + "loss": 1.0371, + "step": 3641 + }, + { + "epoch": 3.92, + "learning_rate": 7.383620689655173e-05, + "loss": 1.2116, + "step": 3642 + }, + { + "epoch": 3.93, + "learning_rate": 7.382902298850575e-05, + "loss": 1.153, + "step": 3643 + }, + { + "epoch": 3.93, + "learning_rate": 7.382183908045977e-05, + "loss": 1.226, + "step": 3644 + }, + { + "epoch": 3.93, + "learning_rate": 7.38146551724138e-05, + "loss": 1.1989, + "step": 3645 + }, + { + "epoch": 3.93, + "learning_rate": 7.380747126436783e-05, + "loss": 1.1812, + "step": 3646 + }, + { + "epoch": 3.93, + "learning_rate": 7.380028735632183e-05, + "loss": 1.0775, + "step": 3647 + }, + { + "epoch": 3.93, + "learning_rate": 7.379310344827587e-05, + "loss": 1.1358, + "step": 3648 + }, + { + "epoch": 3.93, + "learning_rate": 7.378591954022989e-05, + "loss": 1.0682, + "step": 3649 + }, + { + "epoch": 3.93, + "learning_rate": 7.377873563218391e-05, + "loss": 1.1342, + "step": 3650 + }, + { + "epoch": 3.93, + "learning_rate": 7.377155172413793e-05, + "loss": 1.0598, + "step": 3651 + }, + { + "epoch": 3.94, + "learning_rate": 7.376436781609196e-05, + "loss": 1.149, + "step": 3652 + }, + { + "epoch": 3.94, + "learning_rate": 7.375718390804598e-05, + "loss": 1.3031, + "step": 3653 + }, + { + "epoch": 3.94, + "learning_rate": 7.375e-05, + "loss": 1.1953, + "step": 3654 + }, + { + "epoch": 3.94, + "learning_rate": 7.374281609195402e-05, + "loss": 1.1533, + "step": 3655 + }, + { + "epoch": 3.94, + "learning_rate": 7.373563218390806e-05, + "loss": 1.1254, + "step": 3656 + }, + { + "epoch": 3.94, + "learning_rate": 7.372844827586208e-05, + "loss": 1.1414, + "step": 3657 + }, + { + "epoch": 3.94, + "learning_rate": 7.37212643678161e-05, + "loss": 1.0763, + "step": 3658 + }, + { + "epoch": 3.94, + "learning_rate": 7.371408045977012e-05, + "loss": 1.2439, + "step": 3659 + }, + { + "epoch": 3.94, + "learning_rate": 7.370689655172414e-05, + "loss": 1.2521, + "step": 3660 + }, + { + "epoch": 3.95, + "learning_rate": 7.369971264367816e-05, + "loss": 1.1711, + "step": 3661 + }, + { + "epoch": 3.95, + "learning_rate": 7.369252873563218e-05, + "loss": 1.1928, + "step": 3662 + }, + { + "epoch": 3.95, + "learning_rate": 7.368534482758621e-05, + "loss": 1.1058, + "step": 3663 + }, + { + "epoch": 3.95, + "learning_rate": 7.367816091954023e-05, + "loss": 1.3158, + "step": 3664 + }, + { + "epoch": 3.95, + "learning_rate": 7.367097701149425e-05, + "loss": 1.1719, + "step": 3665 + }, + { + "epoch": 3.95, + "learning_rate": 7.366379310344827e-05, + "loss": 1.2282, + "step": 3666 + }, + { + "epoch": 3.95, + "learning_rate": 7.365660919540231e-05, + "loss": 1.2418, + "step": 3667 + }, + { + "epoch": 3.95, + "learning_rate": 7.364942528735632e-05, + "loss": 1.1365, + "step": 3668 + }, + { + "epoch": 3.95, + "learning_rate": 7.364224137931035e-05, + "loss": 1.1179, + "step": 3669 + }, + { + "epoch": 3.95, + "learning_rate": 7.363505747126437e-05, + "loss": 1.2698, + "step": 3670 + }, + { + "epoch": 3.96, + "learning_rate": 7.36278735632184e-05, + "loss": 1.0332, + "step": 3671 + }, + { + "epoch": 3.96, + "learning_rate": 7.362068965517241e-05, + "loss": 1.2381, + "step": 3672 + }, + { + "epoch": 3.96, + "learning_rate": 7.361350574712644e-05, + "loss": 1.1545, + "step": 3673 + }, + { + "epoch": 3.96, + "learning_rate": 7.360632183908046e-05, + "loss": 1.1794, + "step": 3674 + }, + { + "epoch": 3.96, + "learning_rate": 7.359913793103448e-05, + "loss": 1.1628, + "step": 3675 + }, + { + "epoch": 3.96, + "learning_rate": 7.35919540229885e-05, + "loss": 1.1895, + "step": 3676 + }, + { + "epoch": 3.96, + "learning_rate": 7.358477011494254e-05, + "loss": 1.1543, + "step": 3677 + }, + { + "epoch": 3.96, + "learning_rate": 7.357758620689656e-05, + "loss": 1.2884, + "step": 3678 + }, + { + "epoch": 3.96, + "learning_rate": 7.357040229885058e-05, + "loss": 1.0712, + "step": 3679 + }, + { + "epoch": 3.97, + "learning_rate": 7.35632183908046e-05, + "loss": 1.1514, + "step": 3680 + }, + { + "epoch": 3.97, + "learning_rate": 7.355603448275863e-05, + "loss": 1.1658, + "step": 3681 + }, + { + "epoch": 3.97, + "learning_rate": 7.354885057471264e-05, + "loss": 1.2631, + "step": 3682 + }, + { + "epoch": 3.97, + "learning_rate": 7.354166666666667e-05, + "loss": 1.1294, + "step": 3683 + }, + { + "epoch": 3.97, + "learning_rate": 7.35344827586207e-05, + "loss": 1.1804, + "step": 3684 + }, + { + "epoch": 3.97, + "learning_rate": 7.352729885057471e-05, + "loss": 1.2032, + "step": 3685 + }, + { + "epoch": 3.97, + "learning_rate": 7.352011494252874e-05, + "loss": 1.1042, + "step": 3686 + }, + { + "epoch": 3.97, + "learning_rate": 7.351293103448276e-05, + "loss": 1.2022, + "step": 3687 + }, + { + "epoch": 3.97, + "learning_rate": 7.350574712643679e-05, + "loss": 1.1954, + "step": 3688 + }, + { + "epoch": 3.98, + "learning_rate": 7.349856321839081e-05, + "loss": 1.2042, + "step": 3689 + }, + { + "epoch": 3.98, + "learning_rate": 7.349137931034483e-05, + "loss": 1.1698, + "step": 3690 + }, + { + "epoch": 3.98, + "learning_rate": 7.348419540229885e-05, + "loss": 1.1689, + "step": 3691 + }, + { + "epoch": 3.98, + "learning_rate": 7.347701149425288e-05, + "loss": 1.0594, + "step": 3692 + }, + { + "epoch": 3.98, + "learning_rate": 7.346982758620689e-05, + "loss": 1.2087, + "step": 3693 + }, + { + "epoch": 3.98, + "learning_rate": 7.346264367816092e-05, + "loss": 1.2349, + "step": 3694 + }, + { + "epoch": 3.98, + "learning_rate": 7.345545977011495e-05, + "loss": 1.2451, + "step": 3695 + }, + { + "epoch": 3.98, + "learning_rate": 7.344827586206897e-05, + "loss": 1.1681, + "step": 3696 + }, + { + "epoch": 3.98, + "learning_rate": 7.344109195402299e-05, + "loss": 1.3333, + "step": 3697 + }, + { + "epoch": 3.98, + "learning_rate": 7.343390804597702e-05, + "loss": 1.3019, + "step": 3698 + }, + { + "epoch": 3.99, + "learning_rate": 7.342672413793104e-05, + "loss": 1.2647, + "step": 3699 + }, + { + "epoch": 3.99, + "learning_rate": 7.341954022988506e-05, + "loss": 1.131, + "step": 3700 + }, + { + "epoch": 3.99, + "learning_rate": 7.341235632183908e-05, + "loss": 1.1381, + "step": 3701 + }, + { + "epoch": 3.99, + "learning_rate": 7.340517241379311e-05, + "loss": 1.1304, + "step": 3702 + }, + { + "epoch": 3.99, + "learning_rate": 7.339798850574713e-05, + "loss": 1.3721, + "step": 3703 + }, + { + "epoch": 3.99, + "learning_rate": 7.339080459770116e-05, + "loss": 1.163, + "step": 3704 + }, + { + "epoch": 3.99, + "learning_rate": 7.338362068965518e-05, + "loss": 1.1303, + "step": 3705 + }, + { + "epoch": 3.99, + "learning_rate": 7.337643678160921e-05, + "loss": 1.2302, + "step": 3706 + }, + { + "epoch": 3.99, + "learning_rate": 7.336925287356322e-05, + "loss": 1.2248, + "step": 3707 + }, + { + "epoch": 4.0, + "learning_rate": 7.336206896551725e-05, + "loss": 1.2273, + "step": 3708 + }, + { + "epoch": 4.0, + "learning_rate": 7.335488505747127e-05, + "loss": 1.2123, + "step": 3709 + }, + { + "epoch": 4.0, + "learning_rate": 7.334770114942529e-05, + "loss": 1.3825, + "step": 3710 + }, + { + "epoch": 4.0, + "learning_rate": 7.334051724137931e-05, + "loss": 1.1024, + "step": 3711 + }, + { + "epoch": 4.0, + "learning_rate": 7.333333333333333e-05, + "loss": 1.0973, + "step": 3712 + }, + { + "epoch": 4.0, + "learning_rate": 7.332614942528737e-05, + "loss": 1.1419, + "step": 3713 + }, + { + "epoch": 4.0, + "learning_rate": 7.331896551724137e-05, + "loss": 1.0994, + "step": 3714 + }, + { + "epoch": 4.0, + "learning_rate": 7.33117816091954e-05, + "loss": 1.1313, + "step": 3715 + }, + { + "epoch": 4.0, + "learning_rate": 7.330459770114943e-05, + "loss": 1.193, + "step": 3716 + }, + { + "epoch": 4.01, + "learning_rate": 7.329741379310345e-05, + "loss": 1.0857, + "step": 3717 + }, + { + "epoch": 4.01, + "learning_rate": 7.329022988505747e-05, + "loss": 1.1913, + "step": 3718 + }, + { + "epoch": 4.01, + "learning_rate": 7.32830459770115e-05, + "loss": 1.1318, + "step": 3719 + }, + { + "epoch": 4.01, + "learning_rate": 7.327586206896552e-05, + "loss": 1.1475, + "step": 3720 + }, + { + "epoch": 4.01, + "learning_rate": 7.326867816091954e-05, + "loss": 1.1492, + "step": 3721 + }, + { + "epoch": 4.01, + "learning_rate": 7.326149425287356e-05, + "loss": 1.1383, + "step": 3722 + }, + { + "epoch": 4.01, + "learning_rate": 7.32543103448276e-05, + "loss": 1.1312, + "step": 3723 + }, + { + "epoch": 4.01, + "learning_rate": 7.324712643678162e-05, + "loss": 1.047, + "step": 3724 + }, + { + "epoch": 4.01, + "learning_rate": 7.323994252873564e-05, + "loss": 1.1683, + "step": 3725 + }, + { + "epoch": 4.02, + "learning_rate": 7.323275862068966e-05, + "loss": 1.0794, + "step": 3726 + }, + { + "epoch": 4.02, + "learning_rate": 7.322557471264369e-05, + "loss": 1.0123, + "step": 3727 + }, + { + "epoch": 4.02, + "learning_rate": 7.32183908045977e-05, + "loss": 1.1693, + "step": 3728 + }, + { + "epoch": 4.02, + "learning_rate": 7.321120689655173e-05, + "loss": 1.144, + "step": 3729 + }, + { + "epoch": 4.02, + "learning_rate": 7.320402298850575e-05, + "loss": 1.2409, + "step": 3730 + }, + { + "epoch": 4.02, + "learning_rate": 7.319683908045977e-05, + "loss": 1.2648, + "step": 3731 + }, + { + "epoch": 4.02, + "learning_rate": 7.318965517241379e-05, + "loss": 1.2162, + "step": 3732 + }, + { + "epoch": 4.02, + "learning_rate": 7.318247126436783e-05, + "loss": 1.1417, + "step": 3733 + }, + { + "epoch": 4.02, + "learning_rate": 7.317528735632185e-05, + "loss": 1.1733, + "step": 3734 + }, + { + "epoch": 4.02, + "learning_rate": 7.316810344827587e-05, + "loss": 1.1872, + "step": 3735 + }, + { + "epoch": 4.03, + "learning_rate": 7.316091954022989e-05, + "loss": 1.1081, + "step": 3736 + }, + { + "epoch": 4.03, + "learning_rate": 7.315373563218391e-05, + "loss": 1.2408, + "step": 3737 + }, + { + "epoch": 4.03, + "learning_rate": 7.314655172413794e-05, + "loss": 1.1953, + "step": 3738 + }, + { + "epoch": 4.03, + "learning_rate": 7.313936781609195e-05, + "loss": 1.0086, + "step": 3739 + }, + { + "epoch": 4.03, + "learning_rate": 7.313218390804598e-05, + "loss": 1.0958, + "step": 3740 + }, + { + "epoch": 4.03, + "learning_rate": 7.3125e-05, + "loss": 1.2761, + "step": 3741 + }, + { + "epoch": 4.03, + "learning_rate": 7.311781609195402e-05, + "loss": 1.1823, + "step": 3742 + }, + { + "epoch": 4.03, + "learning_rate": 7.311063218390804e-05, + "loss": 1.0146, + "step": 3743 + }, + { + "epoch": 4.03, + "learning_rate": 7.310344827586208e-05, + "loss": 1.1584, + "step": 3744 + }, + { + "epoch": 4.04, + "learning_rate": 7.30962643678161e-05, + "loss": 1.1838, + "step": 3745 + }, + { + "epoch": 4.04, + "learning_rate": 7.308908045977012e-05, + "loss": 1.0343, + "step": 3746 + }, + { + "epoch": 4.04, + "learning_rate": 7.308189655172414e-05, + "loss": 1.1069, + "step": 3747 + }, + { + "epoch": 4.04, + "learning_rate": 7.307471264367817e-05, + "loss": 1.1998, + "step": 3748 + }, + { + "epoch": 4.04, + "learning_rate": 7.306752873563218e-05, + "loss": 1.0923, + "step": 3749 + }, + { + "epoch": 4.04, + "learning_rate": 7.306034482758621e-05, + "loss": 1.0478, + "step": 3750 + }, + { + "epoch": 4.04, + "eval_loss": 1.1569581031799316, + "eval_runtime": 175.1156, + "eval_samples_per_second": 127.173, + "eval_steps_per_second": 0.662, + "step": 3750 + }, + { + "epoch": 4.04, + "learning_rate": 7.305316091954023e-05, + "loss": 1.2024, + "step": 3751 + }, + { + "epoch": 4.04, + "learning_rate": 7.304597701149427e-05, + "loss": 1.1123, + "step": 3752 + }, + { + "epoch": 4.04, + "learning_rate": 7.303879310344827e-05, + "loss": 1.2188, + "step": 3753 + }, + { + "epoch": 4.05, + "learning_rate": 7.303160919540231e-05, + "loss": 1.1154, + "step": 3754 + }, + { + "epoch": 4.05, + "learning_rate": 7.302442528735633e-05, + "loss": 1.1035, + "step": 3755 + }, + { + "epoch": 4.05, + "learning_rate": 7.301724137931035e-05, + "loss": 1.2515, + "step": 3756 + }, + { + "epoch": 4.05, + "learning_rate": 7.301005747126437e-05, + "loss": 1.0554, + "step": 3757 + }, + { + "epoch": 4.05, + "learning_rate": 7.30028735632184e-05, + "loss": 1.2599, + "step": 3758 + }, + { + "epoch": 4.05, + "learning_rate": 7.299568965517242e-05, + "loss": 1.1407, + "step": 3759 + }, + { + "epoch": 4.05, + "learning_rate": 7.298850574712644e-05, + "loss": 1.1521, + "step": 3760 + }, + { + "epoch": 4.05, + "learning_rate": 7.298132183908046e-05, + "loss": 1.189, + "step": 3761 + }, + { + "epoch": 4.05, + "learning_rate": 7.297413793103448e-05, + "loss": 1.1617, + "step": 3762 + }, + { + "epoch": 4.05, + "learning_rate": 7.29669540229885e-05, + "loss": 1.1328, + "step": 3763 + }, + { + "epoch": 4.06, + "learning_rate": 7.295977011494252e-05, + "loss": 1.2031, + "step": 3764 + }, + { + "epoch": 4.06, + "learning_rate": 7.295258620689656e-05, + "loss": 1.1651, + "step": 3765 + }, + { + "epoch": 4.06, + "learning_rate": 7.294540229885058e-05, + "loss": 1.1455, + "step": 3766 + }, + { + "epoch": 4.06, + "learning_rate": 7.29382183908046e-05, + "loss": 1.2032, + "step": 3767 + }, + { + "epoch": 4.06, + "learning_rate": 7.293103448275862e-05, + "loss": 1.1539, + "step": 3768 + }, + { + "epoch": 4.06, + "learning_rate": 7.292385057471265e-05, + "loss": 1.2443, + "step": 3769 + }, + { + "epoch": 4.06, + "learning_rate": 7.291666666666667e-05, + "loss": 1.2005, + "step": 3770 + }, + { + "epoch": 4.06, + "learning_rate": 7.290948275862069e-05, + "loss": 1.1281, + "step": 3771 + }, + { + "epoch": 4.06, + "learning_rate": 7.290229885057471e-05, + "loss": 1.0416, + "step": 3772 + }, + { + "epoch": 4.07, + "learning_rate": 7.289511494252875e-05, + "loss": 1.2659, + "step": 3773 + }, + { + "epoch": 4.07, + "learning_rate": 7.288793103448275e-05, + "loss": 1.0529, + "step": 3774 + }, + { + "epoch": 4.07, + "learning_rate": 7.288074712643679e-05, + "loss": 1.2036, + "step": 3775 + }, + { + "epoch": 4.07, + "learning_rate": 7.287356321839081e-05, + "loss": 1.089, + "step": 3776 + }, + { + "epoch": 4.07, + "learning_rate": 7.286637931034483e-05, + "loss": 1.1242, + "step": 3777 + }, + { + "epoch": 4.07, + "learning_rate": 7.285919540229885e-05, + "loss": 1.1333, + "step": 3778 + }, + { + "epoch": 4.07, + "learning_rate": 7.285201149425288e-05, + "loss": 1.0956, + "step": 3779 + }, + { + "epoch": 4.07, + "learning_rate": 7.28448275862069e-05, + "loss": 1.0874, + "step": 3780 + }, + { + "epoch": 4.07, + "learning_rate": 7.283764367816092e-05, + "loss": 1.0485, + "step": 3781 + }, + { + "epoch": 4.08, + "learning_rate": 7.283045977011494e-05, + "loss": 1.1764, + "step": 3782 + }, + { + "epoch": 4.08, + "learning_rate": 7.282327586206898e-05, + "loss": 1.178, + "step": 3783 + }, + { + "epoch": 4.08, + "learning_rate": 7.2816091954023e-05, + "loss": 1.0412, + "step": 3784 + }, + { + "epoch": 4.08, + "learning_rate": 7.280890804597702e-05, + "loss": 1.1478, + "step": 3785 + }, + { + "epoch": 4.08, + "learning_rate": 7.280172413793104e-05, + "loss": 1.0415, + "step": 3786 + }, + { + "epoch": 4.08, + "learning_rate": 7.279454022988507e-05, + "loss": 0.9833, + "step": 3787 + }, + { + "epoch": 4.08, + "learning_rate": 7.278735632183908e-05, + "loss": 1.2118, + "step": 3788 + }, + { + "epoch": 4.08, + "learning_rate": 7.27801724137931e-05, + "loss": 1.1151, + "step": 3789 + }, + { + "epoch": 4.08, + "learning_rate": 7.277298850574713e-05, + "loss": 1.1894, + "step": 3790 + }, + { + "epoch": 4.09, + "learning_rate": 7.276580459770115e-05, + "loss": 1.0318, + "step": 3791 + }, + { + "epoch": 4.09, + "learning_rate": 7.275862068965517e-05, + "loss": 1.1195, + "step": 3792 + }, + { + "epoch": 4.09, + "learning_rate": 7.27514367816092e-05, + "loss": 1.1974, + "step": 3793 + }, + { + "epoch": 4.09, + "learning_rate": 7.274425287356323e-05, + "loss": 1.1368, + "step": 3794 + }, + { + "epoch": 4.09, + "learning_rate": 7.273706896551723e-05, + "loss": 1.17, + "step": 3795 + }, + { + "epoch": 4.09, + "learning_rate": 7.272988505747127e-05, + "loss": 1.1121, + "step": 3796 + }, + { + "epoch": 4.09, + "learning_rate": 7.272270114942529e-05, + "loss": 1.113, + "step": 3797 + }, + { + "epoch": 4.09, + "learning_rate": 7.271551724137931e-05, + "loss": 1.1428, + "step": 3798 + }, + { + "epoch": 4.09, + "learning_rate": 7.270833333333333e-05, + "loss": 1.1524, + "step": 3799 + }, + { + "epoch": 4.09, + "learning_rate": 7.270114942528736e-05, + "loss": 1.0263, + "step": 3800 + }, + { + "epoch": 4.1, + "learning_rate": 7.269396551724138e-05, + "loss": 1.1614, + "step": 3801 + }, + { + "epoch": 4.1, + "learning_rate": 7.26867816091954e-05, + "loss": 1.1018, + "step": 3802 + }, + { + "epoch": 4.1, + "learning_rate": 7.267959770114942e-05, + "loss": 1.1158, + "step": 3803 + }, + { + "epoch": 4.1, + "learning_rate": 7.267241379310346e-05, + "loss": 1.0895, + "step": 3804 + }, + { + "epoch": 4.1, + "learning_rate": 7.266522988505748e-05, + "loss": 1.036, + "step": 3805 + }, + { + "epoch": 4.1, + "learning_rate": 7.26580459770115e-05, + "loss": 1.1922, + "step": 3806 + }, + { + "epoch": 4.1, + "learning_rate": 7.265086206896552e-05, + "loss": 1.0648, + "step": 3807 + }, + { + "epoch": 4.1, + "learning_rate": 7.264367816091955e-05, + "loss": 1.1997, + "step": 3808 + }, + { + "epoch": 4.1, + "learning_rate": 7.263649425287356e-05, + "loss": 1.2122, + "step": 3809 + }, + { + "epoch": 4.11, + "learning_rate": 7.26293103448276e-05, + "loss": 1.099, + "step": 3810 + }, + { + "epoch": 4.11, + "learning_rate": 7.262212643678161e-05, + "loss": 1.1204, + "step": 3811 + }, + { + "epoch": 4.11, + "learning_rate": 7.261494252873563e-05, + "loss": 1.1577, + "step": 3812 + }, + { + "epoch": 4.11, + "learning_rate": 7.260775862068965e-05, + "loss": 1.181, + "step": 3813 + }, + { + "epoch": 4.11, + "learning_rate": 7.260057471264368e-05, + "loss": 1.1197, + "step": 3814 + }, + { + "epoch": 4.11, + "learning_rate": 7.259339080459771e-05, + "loss": 1.0473, + "step": 3815 + }, + { + "epoch": 4.11, + "learning_rate": 7.258620689655173e-05, + "loss": 1.2628, + "step": 3816 + }, + { + "epoch": 4.11, + "learning_rate": 7.257902298850575e-05, + "loss": 1.102, + "step": 3817 + }, + { + "epoch": 4.11, + "learning_rate": 7.257183908045977e-05, + "loss": 1.0772, + "step": 3818 + }, + { + "epoch": 4.12, + "learning_rate": 7.25646551724138e-05, + "loss": 1.0675, + "step": 3819 + }, + { + "epoch": 4.12, + "learning_rate": 7.255747126436781e-05, + "loss": 1.0466, + "step": 3820 + }, + { + "epoch": 4.12, + "learning_rate": 7.255028735632184e-05, + "loss": 1.159, + "step": 3821 + }, + { + "epoch": 4.12, + "learning_rate": 7.254310344827586e-05, + "loss": 1.0495, + "step": 3822 + }, + { + "epoch": 4.12, + "learning_rate": 7.253591954022989e-05, + "loss": 1.129, + "step": 3823 + }, + { + "epoch": 4.12, + "learning_rate": 7.25287356321839e-05, + "loss": 1.1228, + "step": 3824 + }, + { + "epoch": 4.12, + "learning_rate": 7.252155172413794e-05, + "loss": 1.1452, + "step": 3825 + }, + { + "epoch": 4.12, + "learning_rate": 7.251436781609196e-05, + "loss": 1.267, + "step": 3826 + }, + { + "epoch": 4.12, + "learning_rate": 7.250718390804598e-05, + "loss": 1.1969, + "step": 3827 + }, + { + "epoch": 4.12, + "learning_rate": 7.25e-05, + "loss": 1.1067, + "step": 3828 + }, + { + "epoch": 4.13, + "learning_rate": 7.249281609195403e-05, + "loss": 1.0873, + "step": 3829 + }, + { + "epoch": 4.13, + "learning_rate": 7.248563218390804e-05, + "loss": 1.0749, + "step": 3830 + }, + { + "epoch": 4.13, + "learning_rate": 7.247844827586207e-05, + "loss": 1.032, + "step": 3831 + }, + { + "epoch": 4.13, + "learning_rate": 7.24712643678161e-05, + "loss": 1.2196, + "step": 3832 + }, + { + "epoch": 4.13, + "learning_rate": 7.246408045977013e-05, + "loss": 1.2272, + "step": 3833 + }, + { + "epoch": 4.13, + "learning_rate": 7.245689655172414e-05, + "loss": 1.1323, + "step": 3834 + }, + { + "epoch": 4.13, + "learning_rate": 7.244971264367817e-05, + "loss": 1.1177, + "step": 3835 + }, + { + "epoch": 4.13, + "learning_rate": 7.244252873563219e-05, + "loss": 1.209, + "step": 3836 + }, + { + "epoch": 4.13, + "learning_rate": 7.243534482758621e-05, + "loss": 1.0438, + "step": 3837 + }, + { + "epoch": 4.14, + "learning_rate": 7.242816091954023e-05, + "loss": 1.0607, + "step": 3838 + }, + { + "epoch": 4.14, + "learning_rate": 7.242097701149425e-05, + "loss": 1.2492, + "step": 3839 + }, + { + "epoch": 4.14, + "learning_rate": 7.241379310344828e-05, + "loss": 1.1648, + "step": 3840 + }, + { + "epoch": 4.14, + "learning_rate": 7.240660919540229e-05, + "loss": 1.0505, + "step": 3841 + }, + { + "epoch": 4.14, + "learning_rate": 7.239942528735633e-05, + "loss": 1.1955, + "step": 3842 + }, + { + "epoch": 4.14, + "learning_rate": 7.239224137931035e-05, + "loss": 1.067, + "step": 3843 + }, + { + "epoch": 4.14, + "learning_rate": 7.238505747126437e-05, + "loss": 1.1372, + "step": 3844 + }, + { + "epoch": 4.14, + "learning_rate": 7.237787356321839e-05, + "loss": 1.0275, + "step": 3845 + }, + { + "epoch": 4.14, + "learning_rate": 7.237068965517242e-05, + "loss": 1.3467, + "step": 3846 + }, + { + "epoch": 4.15, + "learning_rate": 7.236350574712644e-05, + "loss": 1.0289, + "step": 3847 + }, + { + "epoch": 4.15, + "learning_rate": 7.235632183908046e-05, + "loss": 1.1114, + "step": 3848 + }, + { + "epoch": 4.15, + "learning_rate": 7.234913793103448e-05, + "loss": 1.1974, + "step": 3849 + }, + { + "epoch": 4.15, + "learning_rate": 7.234195402298852e-05, + "loss": 1.1877, + "step": 3850 + }, + { + "epoch": 4.15, + "learning_rate": 7.233477011494254e-05, + "loss": 1.0293, + "step": 3851 + }, + { + "epoch": 4.15, + "learning_rate": 7.232758620689656e-05, + "loss": 1.109, + "step": 3852 + }, + { + "epoch": 4.15, + "learning_rate": 7.232040229885058e-05, + "loss": 1.0885, + "step": 3853 + }, + { + "epoch": 4.15, + "learning_rate": 7.231321839080461e-05, + "loss": 1.1858, + "step": 3854 + }, + { + "epoch": 4.15, + "learning_rate": 7.230603448275862e-05, + "loss": 1.1862, + "step": 3855 + }, + { + "epoch": 4.16, + "learning_rate": 7.229885057471265e-05, + "loss": 1.1008, + "step": 3856 + }, + { + "epoch": 4.16, + "learning_rate": 7.229166666666667e-05, + "loss": 1.0774, + "step": 3857 + }, + { + "epoch": 4.16, + "learning_rate": 7.228448275862069e-05, + "loss": 1.1211, + "step": 3858 + }, + { + "epoch": 4.16, + "learning_rate": 7.227729885057471e-05, + "loss": 1.1736, + "step": 3859 + }, + { + "epoch": 4.16, + "learning_rate": 7.227011494252875e-05, + "loss": 1.0763, + "step": 3860 + }, + { + "epoch": 4.16, + "learning_rate": 7.226293103448277e-05, + "loss": 1.0848, + "step": 3861 + }, + { + "epoch": 4.16, + "learning_rate": 7.225574712643679e-05, + "loss": 1.1471, + "step": 3862 + }, + { + "epoch": 4.16, + "learning_rate": 7.22485632183908e-05, + "loss": 1.1238, + "step": 3863 + }, + { + "epoch": 4.16, + "learning_rate": 7.224137931034483e-05, + "loss": 1.2497, + "step": 3864 + }, + { + "epoch": 4.16, + "learning_rate": 7.223419540229886e-05, + "loss": 1.1502, + "step": 3865 + }, + { + "epoch": 4.17, + "learning_rate": 7.222701149425287e-05, + "loss": 1.2236, + "step": 3866 + }, + { + "epoch": 4.17, + "learning_rate": 7.22198275862069e-05, + "loss": 1.0537, + "step": 3867 + }, + { + "epoch": 4.17, + "learning_rate": 7.221264367816092e-05, + "loss": 1.1151, + "step": 3868 + }, + { + "epoch": 4.17, + "learning_rate": 7.220545977011494e-05, + "loss": 1.0639, + "step": 3869 + }, + { + "epoch": 4.17, + "learning_rate": 7.219827586206896e-05, + "loss": 1.1286, + "step": 3870 + }, + { + "epoch": 4.17, + "learning_rate": 7.2191091954023e-05, + "loss": 1.1005, + "step": 3871 + }, + { + "epoch": 4.17, + "learning_rate": 7.218390804597702e-05, + "loss": 1.1269, + "step": 3872 + }, + { + "epoch": 4.17, + "learning_rate": 7.217672413793104e-05, + "loss": 1.2707, + "step": 3873 + }, + { + "epoch": 4.17, + "learning_rate": 7.216954022988506e-05, + "loss": 1.2441, + "step": 3874 + }, + { + "epoch": 4.18, + "learning_rate": 7.216235632183909e-05, + "loss": 1.2043, + "step": 3875 + }, + { + "epoch": 4.18, + "learning_rate": 7.21551724137931e-05, + "loss": 1.1256, + "step": 3876 + }, + { + "epoch": 4.18, + "learning_rate": 7.214798850574713e-05, + "loss": 1.1125, + "step": 3877 + }, + { + "epoch": 4.18, + "learning_rate": 7.214080459770115e-05, + "loss": 1.0055, + "step": 3878 + }, + { + "epoch": 4.18, + "learning_rate": 7.213362068965519e-05, + "loss": 1.237, + "step": 3879 + }, + { + "epoch": 4.18, + "learning_rate": 7.212643678160919e-05, + "loss": 1.2673, + "step": 3880 + }, + { + "epoch": 4.18, + "learning_rate": 7.211925287356323e-05, + "loss": 1.1749, + "step": 3881 + }, + { + "epoch": 4.18, + "learning_rate": 7.211206896551725e-05, + "loss": 1.0431, + "step": 3882 + }, + { + "epoch": 4.18, + "learning_rate": 7.210488505747127e-05, + "loss": 1.1833, + "step": 3883 + }, + { + "epoch": 4.19, + "learning_rate": 7.209770114942529e-05, + "loss": 1.1655, + "step": 3884 + }, + { + "epoch": 4.19, + "learning_rate": 7.209051724137932e-05, + "loss": 1.0932, + "step": 3885 + }, + { + "epoch": 4.19, + "learning_rate": 7.208333333333334e-05, + "loss": 1.0558, + "step": 3886 + }, + { + "epoch": 4.19, + "learning_rate": 7.207614942528736e-05, + "loss": 1.2629, + "step": 3887 + }, + { + "epoch": 4.19, + "learning_rate": 7.206896551724138e-05, + "loss": 1.242, + "step": 3888 + }, + { + "epoch": 4.19, + "learning_rate": 7.206178160919542e-05, + "loss": 1.0671, + "step": 3889 + }, + { + "epoch": 4.19, + "learning_rate": 7.205459770114942e-05, + "loss": 1.0388, + "step": 3890 + }, + { + "epoch": 4.19, + "learning_rate": 7.204741379310344e-05, + "loss": 1.2048, + "step": 3891 + }, + { + "epoch": 4.19, + "learning_rate": 7.204022988505748e-05, + "loss": 1.1394, + "step": 3892 + }, + { + "epoch": 4.2, + "learning_rate": 7.20330459770115e-05, + "loss": 1.2693, + "step": 3893 + }, + { + "epoch": 4.2, + "learning_rate": 7.202586206896552e-05, + "loss": 1.122, + "step": 3894 + }, + { + "epoch": 4.2, + "learning_rate": 7.201867816091954e-05, + "loss": 1.0943, + "step": 3895 + }, + { + "epoch": 4.2, + "learning_rate": 7.201149425287357e-05, + "loss": 1.0906, + "step": 3896 + }, + { + "epoch": 4.2, + "learning_rate": 7.200431034482759e-05, + "loss": 1.1582, + "step": 3897 + }, + { + "epoch": 4.2, + "learning_rate": 7.199712643678161e-05, + "loss": 1.2642, + "step": 3898 + }, + { + "epoch": 4.2, + "learning_rate": 7.198994252873563e-05, + "loss": 1.0507, + "step": 3899 + }, + { + "epoch": 4.2, + "learning_rate": 7.198275862068967e-05, + "loss": 1.1536, + "step": 3900 + }, + { + "epoch": 4.2, + "learning_rate": 7.197557471264367e-05, + "loss": 1.1585, + "step": 3901 + }, + { + "epoch": 4.2, + "learning_rate": 7.196839080459771e-05, + "loss": 1.2604, + "step": 3902 + }, + { + "epoch": 4.21, + "learning_rate": 7.196120689655173e-05, + "loss": 1.1578, + "step": 3903 + }, + { + "epoch": 4.21, + "learning_rate": 7.195402298850575e-05, + "loss": 1.1254, + "step": 3904 + }, + { + "epoch": 4.21, + "learning_rate": 7.194683908045977e-05, + "loss": 1.1138, + "step": 3905 + }, + { + "epoch": 4.21, + "learning_rate": 7.19396551724138e-05, + "loss": 1.0903, + "step": 3906 + }, + { + "epoch": 4.21, + "learning_rate": 7.193247126436782e-05, + "loss": 1.2071, + "step": 3907 + }, + { + "epoch": 4.21, + "learning_rate": 7.192528735632184e-05, + "loss": 1.1157, + "step": 3908 + }, + { + "epoch": 4.21, + "learning_rate": 7.191810344827586e-05, + "loss": 1.1782, + "step": 3909 + }, + { + "epoch": 4.21, + "learning_rate": 7.19109195402299e-05, + "loss": 1.1452, + "step": 3910 + }, + { + "epoch": 4.21, + "learning_rate": 7.19037356321839e-05, + "loss": 1.0888, + "step": 3911 + }, + { + "epoch": 4.22, + "learning_rate": 7.189655172413794e-05, + "loss": 1.1149, + "step": 3912 + }, + { + "epoch": 4.22, + "learning_rate": 7.188936781609196e-05, + "loss": 1.1065, + "step": 3913 + }, + { + "epoch": 4.22, + "learning_rate": 7.188218390804599e-05, + "loss": 1.1685, + "step": 3914 + }, + { + "epoch": 4.22, + "learning_rate": 7.1875e-05, + "loss": 1.0071, + "step": 3915 + }, + { + "epoch": 4.22, + "learning_rate": 7.186781609195402e-05, + "loss": 1.1376, + "step": 3916 + }, + { + "epoch": 4.22, + "learning_rate": 7.186063218390805e-05, + "loss": 1.08, + "step": 3917 + }, + { + "epoch": 4.22, + "learning_rate": 7.185344827586207e-05, + "loss": 1.274, + "step": 3918 + }, + { + "epoch": 4.22, + "learning_rate": 7.18462643678161e-05, + "loss": 1.0334, + "step": 3919 + }, + { + "epoch": 4.22, + "learning_rate": 7.183908045977011e-05, + "loss": 1.1701, + "step": 3920 + }, + { + "epoch": 4.23, + "learning_rate": 7.183189655172415e-05, + "loss": 1.0696, + "step": 3921 + }, + { + "epoch": 4.23, + "learning_rate": 7.182471264367815e-05, + "loss": 1.1617, + "step": 3922 + }, + { + "epoch": 4.23, + "learning_rate": 7.181752873563219e-05, + "loss": 1.1142, + "step": 3923 + }, + { + "epoch": 4.23, + "learning_rate": 7.181034482758621e-05, + "loss": 1.2455, + "step": 3924 + }, + { + "epoch": 4.23, + "learning_rate": 7.180316091954023e-05, + "loss": 1.1646, + "step": 3925 + }, + { + "epoch": 4.23, + "learning_rate": 7.179597701149425e-05, + "loss": 1.1188, + "step": 3926 + }, + { + "epoch": 4.23, + "learning_rate": 7.178879310344828e-05, + "loss": 1.1791, + "step": 3927 + }, + { + "epoch": 4.23, + "learning_rate": 7.17816091954023e-05, + "loss": 1.1699, + "step": 3928 + }, + { + "epoch": 4.23, + "learning_rate": 7.177442528735632e-05, + "loss": 1.229, + "step": 3929 + }, + { + "epoch": 4.23, + "learning_rate": 7.176724137931034e-05, + "loss": 1.1202, + "step": 3930 + }, + { + "epoch": 4.24, + "learning_rate": 7.176005747126438e-05, + "loss": 1.1513, + "step": 3931 + }, + { + "epoch": 4.24, + "learning_rate": 7.17528735632184e-05, + "loss": 1.1684, + "step": 3932 + }, + { + "epoch": 4.24, + "learning_rate": 7.174568965517242e-05, + "loss": 1.1103, + "step": 3933 + }, + { + "epoch": 4.24, + "learning_rate": 7.173850574712644e-05, + "loss": 1.1436, + "step": 3934 + }, + { + "epoch": 4.24, + "learning_rate": 7.173132183908047e-05, + "loss": 1.1883, + "step": 3935 + }, + { + "epoch": 4.24, + "learning_rate": 7.172413793103448e-05, + "loss": 1.2135, + "step": 3936 + }, + { + "epoch": 4.24, + "learning_rate": 7.171695402298851e-05, + "loss": 1.1868, + "step": 3937 + }, + { + "epoch": 4.24, + "learning_rate": 7.170977011494253e-05, + "loss": 0.9899, + "step": 3938 + }, + { + "epoch": 4.24, + "learning_rate": 7.170258620689655e-05, + "loss": 1.1799, + "step": 3939 + }, + { + "epoch": 4.25, + "learning_rate": 7.169540229885057e-05, + "loss": 1.1669, + "step": 3940 + }, + { + "epoch": 4.25, + "learning_rate": 7.16882183908046e-05, + "loss": 1.2206, + "step": 3941 + }, + { + "epoch": 4.25, + "learning_rate": 7.168103448275863e-05, + "loss": 1.0568, + "step": 3942 + }, + { + "epoch": 4.25, + "learning_rate": 7.167385057471264e-05, + "loss": 1.1116, + "step": 3943 + }, + { + "epoch": 4.25, + "learning_rate": 7.166666666666667e-05, + "loss": 1.1571, + "step": 3944 + }, + { + "epoch": 4.25, + "learning_rate": 7.165948275862069e-05, + "loss": 1.0176, + "step": 3945 + }, + { + "epoch": 4.25, + "learning_rate": 7.165229885057472e-05, + "loss": 1.0497, + "step": 3946 + }, + { + "epoch": 4.25, + "learning_rate": 7.164511494252873e-05, + "loss": 1.1634, + "step": 3947 + }, + { + "epoch": 4.25, + "learning_rate": 7.163793103448276e-05, + "loss": 1.0053, + "step": 3948 + }, + { + "epoch": 4.26, + "learning_rate": 7.163074712643678e-05, + "loss": 1.2477, + "step": 3949 + }, + { + "epoch": 4.26, + "learning_rate": 7.16235632183908e-05, + "loss": 1.1861, + "step": 3950 + }, + { + "epoch": 4.26, + "learning_rate": 7.161637931034483e-05, + "loss": 1.1932, + "step": 3951 + }, + { + "epoch": 4.26, + "learning_rate": 7.160919540229886e-05, + "loss": 1.2484, + "step": 3952 + }, + { + "epoch": 4.26, + "learning_rate": 7.160201149425288e-05, + "loss": 1.044, + "step": 3953 + }, + { + "epoch": 4.26, + "learning_rate": 7.15948275862069e-05, + "loss": 1.1681, + "step": 3954 + }, + { + "epoch": 4.26, + "learning_rate": 7.158764367816092e-05, + "loss": 1.3042, + "step": 3955 + }, + { + "epoch": 4.26, + "learning_rate": 7.158045977011495e-05, + "loss": 1.2687, + "step": 3956 + }, + { + "epoch": 4.26, + "learning_rate": 7.157327586206896e-05, + "loss": 1.1206, + "step": 3957 + }, + { + "epoch": 4.27, + "learning_rate": 7.1566091954023e-05, + "loss": 1.0185, + "step": 3958 + }, + { + "epoch": 4.27, + "learning_rate": 7.155890804597701e-05, + "loss": 1.0971, + "step": 3959 + }, + { + "epoch": 4.27, + "learning_rate": 7.155172413793105e-05, + "loss": 1.2292, + "step": 3960 + }, + { + "epoch": 4.27, + "learning_rate": 7.154454022988506e-05, + "loss": 1.125, + "step": 3961 + }, + { + "epoch": 4.27, + "learning_rate": 7.153735632183909e-05, + "loss": 1.0664, + "step": 3962 + }, + { + "epoch": 4.27, + "learning_rate": 7.153017241379311e-05, + "loss": 1.023, + "step": 3963 + }, + { + "epoch": 4.27, + "learning_rate": 7.152298850574713e-05, + "loss": 1.1307, + "step": 3964 + }, + { + "epoch": 4.27, + "learning_rate": 7.151580459770115e-05, + "loss": 1.0395, + "step": 3965 + }, + { + "epoch": 4.27, + "learning_rate": 7.150862068965518e-05, + "loss": 1.1769, + "step": 3966 + }, + { + "epoch": 4.27, + "learning_rate": 7.15014367816092e-05, + "loss": 1.137, + "step": 3967 + }, + { + "epoch": 4.28, + "learning_rate": 7.149425287356321e-05, + "loss": 1.1836, + "step": 3968 + }, + { + "epoch": 4.28, + "learning_rate": 7.148706896551725e-05, + "loss": 1.1432, + "step": 3969 + }, + { + "epoch": 4.28, + "learning_rate": 7.147988505747127e-05, + "loss": 1.1902, + "step": 3970 + }, + { + "epoch": 4.28, + "learning_rate": 7.147270114942529e-05, + "loss": 1.0648, + "step": 3971 + }, + { + "epoch": 4.28, + "learning_rate": 7.14655172413793e-05, + "loss": 1.152, + "step": 3972 + }, + { + "epoch": 4.28, + "learning_rate": 7.145833333333334e-05, + "loss": 1.1139, + "step": 3973 + }, + { + "epoch": 4.28, + "learning_rate": 7.145114942528736e-05, + "loss": 1.0753, + "step": 3974 + }, + { + "epoch": 4.28, + "learning_rate": 7.144396551724138e-05, + "loss": 1.1252, + "step": 3975 + }, + { + "epoch": 4.28, + "learning_rate": 7.14367816091954e-05, + "loss": 1.1773, + "step": 3976 + }, + { + "epoch": 4.29, + "learning_rate": 7.142959770114943e-05, + "loss": 1.1396, + "step": 3977 + }, + { + "epoch": 4.29, + "learning_rate": 7.142241379310346e-05, + "loss": 1.1238, + "step": 3978 + }, + { + "epoch": 4.29, + "learning_rate": 7.141522988505748e-05, + "loss": 1.1139, + "step": 3979 + }, + { + "epoch": 4.29, + "learning_rate": 7.14080459770115e-05, + "loss": 1.2236, + "step": 3980 + }, + { + "epoch": 4.29, + "learning_rate": 7.140086206896553e-05, + "loss": 1.144, + "step": 3981 + }, + { + "epoch": 4.29, + "learning_rate": 7.139367816091954e-05, + "loss": 1.1142, + "step": 3982 + }, + { + "epoch": 4.29, + "learning_rate": 7.138649425287357e-05, + "loss": 1.1332, + "step": 3983 + }, + { + "epoch": 4.29, + "learning_rate": 7.137931034482759e-05, + "loss": 1.2022, + "step": 3984 + }, + { + "epoch": 4.29, + "learning_rate": 7.137212643678161e-05, + "loss": 1.2388, + "step": 3985 + }, + { + "epoch": 4.3, + "learning_rate": 7.136494252873563e-05, + "loss": 1.1471, + "step": 3986 + }, + { + "epoch": 4.3, + "learning_rate": 7.135775862068967e-05, + "loss": 1.2228, + "step": 3987 + }, + { + "epoch": 4.3, + "learning_rate": 7.135057471264369e-05, + "loss": 1.0384, + "step": 3988 + }, + { + "epoch": 4.3, + "learning_rate": 7.13433908045977e-05, + "loss": 1.2581, + "step": 3989 + }, + { + "epoch": 4.3, + "learning_rate": 7.133620689655173e-05, + "loss": 1.0964, + "step": 3990 + }, + { + "epoch": 4.3, + "learning_rate": 7.132902298850576e-05, + "loss": 1.1161, + "step": 3991 + }, + { + "epoch": 4.3, + "learning_rate": 7.132183908045977e-05, + "loss": 1.0284, + "step": 3992 + }, + { + "epoch": 4.3, + "learning_rate": 7.131465517241379e-05, + "loss": 1.2357, + "step": 3993 + }, + { + "epoch": 4.3, + "learning_rate": 7.130747126436782e-05, + "loss": 1.2032, + "step": 3994 + }, + { + "epoch": 4.3, + "learning_rate": 7.130028735632184e-05, + "loss": 1.0896, + "step": 3995 + }, + { + "epoch": 4.31, + "learning_rate": 7.129310344827586e-05, + "loss": 1.0999, + "step": 3996 + }, + { + "epoch": 4.31, + "learning_rate": 7.128591954022988e-05, + "loss": 1.1485, + "step": 3997 + }, + { + "epoch": 4.31, + "learning_rate": 7.127873563218392e-05, + "loss": 1.1338, + "step": 3998 + }, + { + "epoch": 4.31, + "learning_rate": 7.127155172413794e-05, + "loss": 1.1272, + "step": 3999 + }, + { + "epoch": 4.31, + "learning_rate": 7.126436781609196e-05, + "loss": 1.1647, + "step": 4000 + }, + { + "epoch": 4.31, + "eval_loss": 1.1495229005813599, + "eval_runtime": 174.849, + "eval_samples_per_second": 127.367, + "eval_steps_per_second": 0.663, + "step": 4000 + }, + { + "epoch": 4.31, + "learning_rate": 7.125718390804598e-05, + "loss": 1.163, + "step": 4001 + }, + { + "epoch": 4.31, + "learning_rate": 7.125000000000001e-05, + "loss": 1.2051, + "step": 4002 + }, + { + "epoch": 4.31, + "learning_rate": 7.124281609195402e-05, + "loss": 0.9934, + "step": 4003 + }, + { + "epoch": 4.31, + "learning_rate": 7.123563218390805e-05, + "loss": 1.1517, + "step": 4004 + }, + { + "epoch": 4.32, + "learning_rate": 7.122844827586207e-05, + "loss": 1.12, + "step": 4005 + }, + { + "epoch": 4.32, + "learning_rate": 7.122126436781609e-05, + "loss": 1.169, + "step": 4006 + }, + { + "epoch": 4.32, + "learning_rate": 7.121408045977011e-05, + "loss": 1.133, + "step": 4007 + }, + { + "epoch": 4.32, + "learning_rate": 7.120689655172415e-05, + "loss": 1.0774, + "step": 4008 + }, + { + "epoch": 4.32, + "learning_rate": 7.119971264367817e-05, + "loss": 1.1029, + "step": 4009 + }, + { + "epoch": 4.32, + "learning_rate": 7.119252873563219e-05, + "loss": 1.1318, + "step": 4010 + }, + { + "epoch": 4.32, + "learning_rate": 7.118534482758621e-05, + "loss": 1.0258, + "step": 4011 + }, + { + "epoch": 4.32, + "learning_rate": 7.117816091954024e-05, + "loss": 1.065, + "step": 4012 + }, + { + "epoch": 4.32, + "learning_rate": 7.117097701149426e-05, + "loss": 1.1374, + "step": 4013 + }, + { + "epoch": 4.33, + "learning_rate": 7.116379310344828e-05, + "loss": 1.1132, + "step": 4014 + }, + { + "epoch": 4.33, + "learning_rate": 7.11566091954023e-05, + "loss": 1.1847, + "step": 4015 + }, + { + "epoch": 4.33, + "learning_rate": 7.114942528735634e-05, + "loss": 1.1502, + "step": 4016 + }, + { + "epoch": 4.33, + "learning_rate": 7.114224137931034e-05, + "loss": 1.0382, + "step": 4017 + }, + { + "epoch": 4.33, + "learning_rate": 7.113505747126436e-05, + "loss": 1.0794, + "step": 4018 + }, + { + "epoch": 4.33, + "learning_rate": 7.11278735632184e-05, + "loss": 1.1552, + "step": 4019 + }, + { + "epoch": 4.33, + "learning_rate": 7.112068965517242e-05, + "loss": 1.2171, + "step": 4020 + }, + { + "epoch": 4.33, + "learning_rate": 7.111350574712644e-05, + "loss": 1.0884, + "step": 4021 + }, + { + "epoch": 4.33, + "learning_rate": 7.110632183908046e-05, + "loss": 1.1831, + "step": 4022 + }, + { + "epoch": 4.34, + "learning_rate": 7.109913793103449e-05, + "loss": 1.0431, + "step": 4023 + }, + { + "epoch": 4.34, + "learning_rate": 7.10919540229885e-05, + "loss": 1.2283, + "step": 4024 + }, + { + "epoch": 4.34, + "learning_rate": 7.108477011494253e-05, + "loss": 1.0834, + "step": 4025 + }, + { + "epoch": 4.34, + "learning_rate": 7.107758620689655e-05, + "loss": 1.2118, + "step": 4026 + }, + { + "epoch": 4.34, + "learning_rate": 7.107040229885059e-05, + "loss": 1.2467, + "step": 4027 + }, + { + "epoch": 4.34, + "learning_rate": 7.10632183908046e-05, + "loss": 1.1573, + "step": 4028 + }, + { + "epoch": 4.34, + "learning_rate": 7.105603448275863e-05, + "loss": 1.1116, + "step": 4029 + }, + { + "epoch": 4.34, + "learning_rate": 7.104885057471265e-05, + "loss": 1.0805, + "step": 4030 + }, + { + "epoch": 4.34, + "learning_rate": 7.104166666666667e-05, + "loss": 1.1142, + "step": 4031 + }, + { + "epoch": 4.34, + "learning_rate": 7.103448275862069e-05, + "loss": 1.1197, + "step": 4032 + }, + { + "epoch": 4.35, + "learning_rate": 7.102729885057472e-05, + "loss": 1.1248, + "step": 4033 + }, + { + "epoch": 4.35, + "learning_rate": 7.102011494252874e-05, + "loss": 1.2187, + "step": 4034 + }, + { + "epoch": 4.35, + "learning_rate": 7.101293103448276e-05, + "loss": 1.2615, + "step": 4035 + }, + { + "epoch": 4.35, + "learning_rate": 7.100574712643678e-05, + "loss": 1.1852, + "step": 4036 + }, + { + "epoch": 4.35, + "learning_rate": 7.099856321839082e-05, + "loss": 1.037, + "step": 4037 + }, + { + "epoch": 4.35, + "learning_rate": 7.099137931034482e-05, + "loss": 1.0485, + "step": 4038 + }, + { + "epoch": 4.35, + "learning_rate": 7.098419540229886e-05, + "loss": 1.0599, + "step": 4039 + }, + { + "epoch": 4.35, + "learning_rate": 7.097701149425288e-05, + "loss": 0.9996, + "step": 4040 + }, + { + "epoch": 4.35, + "learning_rate": 7.096982758620691e-05, + "loss": 1.096, + "step": 4041 + }, + { + "epoch": 4.36, + "learning_rate": 7.096264367816092e-05, + "loss": 1.1126, + "step": 4042 + }, + { + "epoch": 4.36, + "learning_rate": 7.095545977011494e-05, + "loss": 1.2599, + "step": 4043 + }, + { + "epoch": 4.36, + "learning_rate": 7.094827586206897e-05, + "loss": 1.0823, + "step": 4044 + }, + { + "epoch": 4.36, + "learning_rate": 7.094109195402299e-05, + "loss": 1.2323, + "step": 4045 + }, + { + "epoch": 4.36, + "learning_rate": 7.093390804597701e-05, + "loss": 1.1649, + "step": 4046 + }, + { + "epoch": 4.36, + "learning_rate": 7.092672413793103e-05, + "loss": 1.2061, + "step": 4047 + }, + { + "epoch": 4.36, + "learning_rate": 7.091954022988507e-05, + "loss": 1.0977, + "step": 4048 + }, + { + "epoch": 4.36, + "learning_rate": 7.091235632183907e-05, + "loss": 1.0574, + "step": 4049 + }, + { + "epoch": 4.36, + "learning_rate": 7.090517241379311e-05, + "loss": 1.0879, + "step": 4050 + }, + { + "epoch": 4.37, + "learning_rate": 7.089798850574713e-05, + "loss": 1.1421, + "step": 4051 + }, + { + "epoch": 4.37, + "learning_rate": 7.089080459770115e-05, + "loss": 1.1717, + "step": 4052 + }, + { + "epoch": 4.37, + "learning_rate": 7.088362068965517e-05, + "loss": 1.0571, + "step": 4053 + }, + { + "epoch": 4.37, + "learning_rate": 7.08764367816092e-05, + "loss": 1.1351, + "step": 4054 + }, + { + "epoch": 4.37, + "learning_rate": 7.086925287356322e-05, + "loss": 1.0923, + "step": 4055 + }, + { + "epoch": 4.37, + "learning_rate": 7.086206896551724e-05, + "loss": 1.1816, + "step": 4056 + }, + { + "epoch": 4.37, + "learning_rate": 7.085488505747126e-05, + "loss": 1.1073, + "step": 4057 + }, + { + "epoch": 4.37, + "learning_rate": 7.08477011494253e-05, + "loss": 1.1362, + "step": 4058 + }, + { + "epoch": 4.37, + "learning_rate": 7.084051724137932e-05, + "loss": 1.1414, + "step": 4059 + }, + { + "epoch": 4.38, + "learning_rate": 7.083333333333334e-05, + "loss": 1.1686, + "step": 4060 + }, + { + "epoch": 4.38, + "learning_rate": 7.082614942528736e-05, + "loss": 1.1727, + "step": 4061 + }, + { + "epoch": 4.38, + "learning_rate": 7.081896551724139e-05, + "loss": 0.9823, + "step": 4062 + }, + { + "epoch": 4.38, + "learning_rate": 7.08117816091954e-05, + "loss": 1.2271, + "step": 4063 + }, + { + "epoch": 4.38, + "learning_rate": 7.080459770114943e-05, + "loss": 1.1987, + "step": 4064 + }, + { + "epoch": 4.38, + "learning_rate": 7.079741379310345e-05, + "loss": 1.1792, + "step": 4065 + }, + { + "epoch": 4.38, + "learning_rate": 7.079022988505747e-05, + "loss": 1.1573, + "step": 4066 + }, + { + "epoch": 4.38, + "learning_rate": 7.07830459770115e-05, + "loss": 1.0706, + "step": 4067 + }, + { + "epoch": 4.38, + "learning_rate": 7.077586206896553e-05, + "loss": 1.1464, + "step": 4068 + }, + { + "epoch": 4.38, + "learning_rate": 7.076867816091955e-05, + "loss": 1.0635, + "step": 4069 + }, + { + "epoch": 4.39, + "learning_rate": 7.076149425287356e-05, + "loss": 1.108, + "step": 4070 + }, + { + "epoch": 4.39, + "learning_rate": 7.075431034482759e-05, + "loss": 1.1394, + "step": 4071 + }, + { + "epoch": 4.39, + "learning_rate": 7.074712643678161e-05, + "loss": 1.1372, + "step": 4072 + }, + { + "epoch": 4.39, + "learning_rate": 7.073994252873564e-05, + "loss": 1.1654, + "step": 4073 + }, + { + "epoch": 4.39, + "learning_rate": 7.073275862068965e-05, + "loss": 0.9373, + "step": 4074 + }, + { + "epoch": 4.39, + "learning_rate": 7.072557471264368e-05, + "loss": 1.2687, + "step": 4075 + }, + { + "epoch": 4.39, + "learning_rate": 7.07183908045977e-05, + "loss": 0.9949, + "step": 4076 + }, + { + "epoch": 4.39, + "learning_rate": 7.071120689655172e-05, + "loss": 1.2127, + "step": 4077 + }, + { + "epoch": 4.39, + "learning_rate": 7.070402298850574e-05, + "loss": 1.1046, + "step": 4078 + }, + { + "epoch": 4.4, + "learning_rate": 7.069683908045978e-05, + "loss": 1.1432, + "step": 4079 + }, + { + "epoch": 4.4, + "learning_rate": 7.06896551724138e-05, + "loss": 1.0952, + "step": 4080 + }, + { + "epoch": 4.4, + "learning_rate": 7.068247126436782e-05, + "loss": 1.1723, + "step": 4081 + }, + { + "epoch": 4.4, + "learning_rate": 7.067528735632184e-05, + "loss": 1.17, + "step": 4082 + }, + { + "epoch": 4.4, + "learning_rate": 7.066810344827587e-05, + "loss": 1.056, + "step": 4083 + }, + { + "epoch": 4.4, + "learning_rate": 7.066091954022988e-05, + "loss": 1.109, + "step": 4084 + }, + { + "epoch": 4.4, + "learning_rate": 7.065373563218391e-05, + "loss": 1.1935, + "step": 4085 + }, + { + "epoch": 4.4, + "learning_rate": 7.064655172413793e-05, + "loss": 1.0726, + "step": 4086 + }, + { + "epoch": 4.4, + "learning_rate": 7.063936781609195e-05, + "loss": 1.2354, + "step": 4087 + }, + { + "epoch": 4.41, + "learning_rate": 7.063218390804598e-05, + "loss": 1.1518, + "step": 4088 + }, + { + "epoch": 4.41, + "learning_rate": 7.062500000000001e-05, + "loss": 1.2441, + "step": 4089 + }, + { + "epoch": 4.41, + "learning_rate": 7.061781609195403e-05, + "loss": 1.1597, + "step": 4090 + }, + { + "epoch": 4.41, + "learning_rate": 7.061063218390805e-05, + "loss": 1.1266, + "step": 4091 + }, + { + "epoch": 4.41, + "learning_rate": 7.060344827586207e-05, + "loss": 1.025, + "step": 4092 + }, + { + "epoch": 4.41, + "learning_rate": 7.05962643678161e-05, + "loss": 1.1671, + "step": 4093 + }, + { + "epoch": 4.41, + "learning_rate": 7.058908045977012e-05, + "loss": 1.1873, + "step": 4094 + }, + { + "epoch": 4.41, + "learning_rate": 7.058189655172413e-05, + "loss": 1.1252, + "step": 4095 + }, + { + "epoch": 4.41, + "learning_rate": 7.057471264367816e-05, + "loss": 1.1942, + "step": 4096 + }, + { + "epoch": 4.41, + "learning_rate": 7.056752873563219e-05, + "loss": 1.0539, + "step": 4097 + }, + { + "epoch": 4.42, + "learning_rate": 7.05603448275862e-05, + "loss": 1.1224, + "step": 4098 + }, + { + "epoch": 4.42, + "learning_rate": 7.055316091954023e-05, + "loss": 1.0204, + "step": 4099 + }, + { + "epoch": 4.42, + "learning_rate": 7.054597701149426e-05, + "loss": 1.2802, + "step": 4100 + }, + { + "epoch": 4.42, + "learning_rate": 7.053879310344828e-05, + "loss": 1.0389, + "step": 4101 + }, + { + "epoch": 4.42, + "learning_rate": 7.05316091954023e-05, + "loss": 1.0829, + "step": 4102 + }, + { + "epoch": 4.42, + "learning_rate": 7.052442528735632e-05, + "loss": 1.1931, + "step": 4103 + }, + { + "epoch": 4.42, + "learning_rate": 7.051724137931035e-05, + "loss": 1.1, + "step": 4104 + }, + { + "epoch": 4.42, + "learning_rate": 7.051005747126436e-05, + "loss": 1.2188, + "step": 4105 + }, + { + "epoch": 4.42, + "learning_rate": 7.05028735632184e-05, + "loss": 0.986, + "step": 4106 + }, + { + "epoch": 4.43, + "learning_rate": 7.049568965517242e-05, + "loss": 1.2338, + "step": 4107 + }, + { + "epoch": 4.43, + "learning_rate": 7.048850574712645e-05, + "loss": 1.1741, + "step": 4108 + }, + { + "epoch": 4.43, + "learning_rate": 7.048132183908046e-05, + "loss": 1.0364, + "step": 4109 + }, + { + "epoch": 4.43, + "learning_rate": 7.047413793103449e-05, + "loss": 1.1721, + "step": 4110 + }, + { + "epoch": 4.43, + "learning_rate": 7.046695402298851e-05, + "loss": 1.1461, + "step": 4111 + }, + { + "epoch": 4.43, + "learning_rate": 7.045977011494253e-05, + "loss": 1.0592, + "step": 4112 + }, + { + "epoch": 4.43, + "learning_rate": 7.045258620689655e-05, + "loss": 1.1347, + "step": 4113 + }, + { + "epoch": 4.43, + "learning_rate": 7.044540229885058e-05, + "loss": 1.1538, + "step": 4114 + }, + { + "epoch": 4.43, + "learning_rate": 7.04382183908046e-05, + "loss": 1.1418, + "step": 4115 + }, + { + "epoch": 4.44, + "learning_rate": 7.043103448275863e-05, + "loss": 1.0312, + "step": 4116 + }, + { + "epoch": 4.44, + "learning_rate": 7.042385057471265e-05, + "loss": 1.2323, + "step": 4117 + }, + { + "epoch": 4.44, + "learning_rate": 7.041666666666668e-05, + "loss": 1.2411, + "step": 4118 + }, + { + "epoch": 4.44, + "learning_rate": 7.040948275862069e-05, + "loss": 1.0226, + "step": 4119 + }, + { + "epoch": 4.44, + "learning_rate": 7.040229885057471e-05, + "loss": 1.0986, + "step": 4120 + }, + { + "epoch": 4.44, + "learning_rate": 7.039511494252874e-05, + "loss": 1.1433, + "step": 4121 + }, + { + "epoch": 4.44, + "learning_rate": 7.038793103448276e-05, + "loss": 1.0864, + "step": 4122 + }, + { + "epoch": 4.44, + "learning_rate": 7.038074712643678e-05, + "loss": 1.1061, + "step": 4123 + }, + { + "epoch": 4.44, + "learning_rate": 7.03735632183908e-05, + "loss": 1.301, + "step": 4124 + }, + { + "epoch": 4.45, + "learning_rate": 7.036637931034484e-05, + "loss": 1.1457, + "step": 4125 + }, + { + "epoch": 4.45, + "learning_rate": 7.035919540229886e-05, + "loss": 1.0309, + "step": 4126 + }, + { + "epoch": 4.45, + "learning_rate": 7.035201149425288e-05, + "loss": 1.0457, + "step": 4127 + }, + { + "epoch": 4.45, + "learning_rate": 7.03448275862069e-05, + "loss": 1.024, + "step": 4128 + }, + { + "epoch": 4.45, + "learning_rate": 7.033764367816093e-05, + "loss": 1.1099, + "step": 4129 + }, + { + "epoch": 4.45, + "learning_rate": 7.033045977011494e-05, + "loss": 1.1596, + "step": 4130 + }, + { + "epoch": 4.45, + "learning_rate": 7.032327586206897e-05, + "loss": 1.183, + "step": 4131 + }, + { + "epoch": 4.45, + "learning_rate": 7.031609195402299e-05, + "loss": 1.1584, + "step": 4132 + }, + { + "epoch": 4.45, + "learning_rate": 7.030890804597701e-05, + "loss": 1.3119, + "step": 4133 + }, + { + "epoch": 4.45, + "learning_rate": 7.030172413793103e-05, + "loss": 1.2893, + "step": 4134 + }, + { + "epoch": 4.46, + "learning_rate": 7.029454022988507e-05, + "loss": 1.1524, + "step": 4135 + }, + { + "epoch": 4.46, + "learning_rate": 7.028735632183909e-05, + "loss": 1.0715, + "step": 4136 + }, + { + "epoch": 4.46, + "learning_rate": 7.02801724137931e-05, + "loss": 1.0995, + "step": 4137 + }, + { + "epoch": 4.46, + "learning_rate": 7.027298850574713e-05, + "loss": 1.1488, + "step": 4138 + }, + { + "epoch": 4.46, + "learning_rate": 7.026580459770116e-05, + "loss": 1.0486, + "step": 4139 + }, + { + "epoch": 4.46, + "learning_rate": 7.025862068965518e-05, + "loss": 1.1988, + "step": 4140 + }, + { + "epoch": 4.46, + "learning_rate": 7.02514367816092e-05, + "loss": 1.1875, + "step": 4141 + }, + { + "epoch": 4.46, + "learning_rate": 7.024425287356322e-05, + "loss": 1.1307, + "step": 4142 + }, + { + "epoch": 4.46, + "learning_rate": 7.023706896551726e-05, + "loss": 1.1295, + "step": 4143 + }, + { + "epoch": 4.47, + "learning_rate": 7.022988505747126e-05, + "loss": 1.1022, + "step": 4144 + }, + { + "epoch": 4.47, + "learning_rate": 7.02227011494253e-05, + "loss": 1.1644, + "step": 4145 + }, + { + "epoch": 4.47, + "learning_rate": 7.021551724137932e-05, + "loss": 1.2336, + "step": 4146 + }, + { + "epoch": 4.47, + "learning_rate": 7.020833333333334e-05, + "loss": 1.101, + "step": 4147 + }, + { + "epoch": 4.47, + "learning_rate": 7.020114942528736e-05, + "loss": 1.266, + "step": 4148 + }, + { + "epoch": 4.47, + "learning_rate": 7.019396551724138e-05, + "loss": 1.1085, + "step": 4149 + }, + { + "epoch": 4.47, + "learning_rate": 7.018678160919541e-05, + "loss": 1.069, + "step": 4150 + }, + { + "epoch": 4.47, + "learning_rate": 7.017959770114942e-05, + "loss": 1.0578, + "step": 4151 + }, + { + "epoch": 4.47, + "learning_rate": 7.017241379310345e-05, + "loss": 1.2207, + "step": 4152 + }, + { + "epoch": 4.48, + "learning_rate": 7.016522988505747e-05, + "loss": 1.1009, + "step": 4153 + }, + { + "epoch": 4.48, + "learning_rate": 7.01580459770115e-05, + "loss": 1.0234, + "step": 4154 + }, + { + "epoch": 4.48, + "learning_rate": 7.015086206896551e-05, + "loss": 1.1318, + "step": 4155 + }, + { + "epoch": 4.48, + "learning_rate": 7.014367816091955e-05, + "loss": 1.1136, + "step": 4156 + }, + { + "epoch": 4.48, + "learning_rate": 7.013649425287357e-05, + "loss": 1.217, + "step": 4157 + }, + { + "epoch": 4.48, + "learning_rate": 7.012931034482759e-05, + "loss": 1.2161, + "step": 4158 + }, + { + "epoch": 4.48, + "learning_rate": 7.012212643678161e-05, + "loss": 1.1998, + "step": 4159 + }, + { + "epoch": 4.48, + "learning_rate": 7.011494252873564e-05, + "loss": 1.1562, + "step": 4160 + }, + { + "epoch": 4.48, + "learning_rate": 7.010775862068966e-05, + "loss": 1.1373, + "step": 4161 + }, + { + "epoch": 4.48, + "learning_rate": 7.010057471264368e-05, + "loss": 1.1872, + "step": 4162 + }, + { + "epoch": 4.49, + "learning_rate": 7.00933908045977e-05, + "loss": 1.0475, + "step": 4163 + }, + { + "epoch": 4.49, + "learning_rate": 7.008620689655174e-05, + "loss": 1.1964, + "step": 4164 + }, + { + "epoch": 4.49, + "learning_rate": 7.007902298850574e-05, + "loss": 1.1592, + "step": 4165 + }, + { + "epoch": 4.49, + "learning_rate": 7.007183908045978e-05, + "loss": 1.1603, + "step": 4166 + }, + { + "epoch": 4.49, + "learning_rate": 7.00646551724138e-05, + "loss": 1.1989, + "step": 4167 + }, + { + "epoch": 4.49, + "learning_rate": 7.005747126436782e-05, + "loss": 1.1234, + "step": 4168 + }, + { + "epoch": 4.49, + "learning_rate": 7.005028735632184e-05, + "loss": 1.0852, + "step": 4169 + }, + { + "epoch": 4.49, + "learning_rate": 7.004310344827587e-05, + "loss": 1.1214, + "step": 4170 + }, + { + "epoch": 4.49, + "learning_rate": 7.003591954022989e-05, + "loss": 1.1218, + "step": 4171 + }, + { + "epoch": 4.5, + "learning_rate": 7.002873563218391e-05, + "loss": 1.1669, + "step": 4172 + }, + { + "epoch": 4.5, + "learning_rate": 7.002155172413793e-05, + "loss": 1.1595, + "step": 4173 + }, + { + "epoch": 4.5, + "learning_rate": 7.001436781609195e-05, + "loss": 1.028, + "step": 4174 + }, + { + "epoch": 4.5, + "learning_rate": 7.000718390804599e-05, + "loss": 1.1488, + "step": 4175 + }, + { + "epoch": 4.5, + "learning_rate": 7e-05, + "loss": 1.1463, + "step": 4176 + }, + { + "epoch": 4.5, + "learning_rate": 6.999281609195403e-05, + "loss": 1.1466, + "step": 4177 + }, + { + "epoch": 4.5, + "learning_rate": 6.998563218390805e-05, + "loss": 1.1368, + "step": 4178 + }, + { + "epoch": 4.5, + "learning_rate": 6.997844827586207e-05, + "loss": 1.1495, + "step": 4179 + }, + { + "epoch": 4.5, + "learning_rate": 6.997126436781609e-05, + "loss": 1.0486, + "step": 4180 + }, + { + "epoch": 4.51, + "learning_rate": 6.996408045977012e-05, + "loss": 1.0216, + "step": 4181 + }, + { + "epoch": 4.51, + "learning_rate": 6.995689655172414e-05, + "loss": 1.0993, + "step": 4182 + }, + { + "epoch": 4.51, + "learning_rate": 6.994971264367816e-05, + "loss": 1.2366, + "step": 4183 + }, + { + "epoch": 4.51, + "learning_rate": 6.994252873563218e-05, + "loss": 1.1786, + "step": 4184 + }, + { + "epoch": 4.51, + "learning_rate": 6.993534482758622e-05, + "loss": 1.2189, + "step": 4185 + }, + { + "epoch": 4.51, + "learning_rate": 6.992816091954024e-05, + "loss": 1.0896, + "step": 4186 + }, + { + "epoch": 4.51, + "learning_rate": 6.992097701149426e-05, + "loss": 1.1905, + "step": 4187 + }, + { + "epoch": 4.51, + "learning_rate": 6.991379310344828e-05, + "loss": 1.1439, + "step": 4188 + }, + { + "epoch": 4.51, + "learning_rate": 6.990660919540231e-05, + "loss": 1.3324, + "step": 4189 + }, + { + "epoch": 4.52, + "learning_rate": 6.989942528735632e-05, + "loss": 1.3225, + "step": 4190 + }, + { + "epoch": 4.52, + "learning_rate": 6.989224137931035e-05, + "loss": 1.081, + "step": 4191 + }, + { + "epoch": 4.52, + "learning_rate": 6.988505747126437e-05, + "loss": 1.2335, + "step": 4192 + }, + { + "epoch": 4.52, + "learning_rate": 6.98778735632184e-05, + "loss": 0.9801, + "step": 4193 + }, + { + "epoch": 4.52, + "learning_rate": 6.987068965517241e-05, + "loss": 1.1186, + "step": 4194 + }, + { + "epoch": 4.52, + "learning_rate": 6.986350574712645e-05, + "loss": 1.1854, + "step": 4195 + }, + { + "epoch": 4.52, + "learning_rate": 6.985632183908047e-05, + "loss": 1.177, + "step": 4196 + }, + { + "epoch": 4.52, + "learning_rate": 6.984913793103447e-05, + "loss": 1.202, + "step": 4197 + }, + { + "epoch": 4.52, + "learning_rate": 6.984195402298851e-05, + "loss": 1.2036, + "step": 4198 + }, + { + "epoch": 4.52, + "learning_rate": 6.983477011494253e-05, + "loss": 1.073, + "step": 4199 + }, + { + "epoch": 4.53, + "learning_rate": 6.982758620689655e-05, + "loss": 1.1668, + "step": 4200 + }, + { + "epoch": 4.53, + "learning_rate": 6.982040229885057e-05, + "loss": 1.1674, + "step": 4201 + }, + { + "epoch": 4.53, + "learning_rate": 6.98132183908046e-05, + "loss": 1.1308, + "step": 4202 + }, + { + "epoch": 4.53, + "learning_rate": 6.980603448275862e-05, + "loss": 1.1631, + "step": 4203 + }, + { + "epoch": 4.53, + "learning_rate": 6.979885057471264e-05, + "loss": 1.0372, + "step": 4204 + }, + { + "epoch": 4.53, + "learning_rate": 6.979166666666666e-05, + "loss": 1.2676, + "step": 4205 + }, + { + "epoch": 4.53, + "learning_rate": 6.97844827586207e-05, + "loss": 1.1758, + "step": 4206 + }, + { + "epoch": 4.53, + "learning_rate": 6.977729885057472e-05, + "loss": 1.1569, + "step": 4207 + }, + { + "epoch": 4.53, + "learning_rate": 6.977011494252874e-05, + "loss": 1.0875, + "step": 4208 + }, + { + "epoch": 4.54, + "learning_rate": 6.976293103448276e-05, + "loss": 1.3085, + "step": 4209 + }, + { + "epoch": 4.54, + "learning_rate": 6.975574712643679e-05, + "loss": 1.1535, + "step": 4210 + }, + { + "epoch": 4.54, + "learning_rate": 6.97485632183908e-05, + "loss": 1.0686, + "step": 4211 + }, + { + "epoch": 4.54, + "learning_rate": 6.974137931034483e-05, + "loss": 1.1595, + "step": 4212 + }, + { + "epoch": 4.54, + "learning_rate": 6.973419540229885e-05, + "loss": 0.9464, + "step": 4213 + }, + { + "epoch": 4.54, + "learning_rate": 6.972701149425287e-05, + "loss": 1.1814, + "step": 4214 + }, + { + "epoch": 4.54, + "learning_rate": 6.97198275862069e-05, + "loss": 1.1388, + "step": 4215 + }, + { + "epoch": 4.54, + "learning_rate": 6.971264367816093e-05, + "loss": 1.0884, + "step": 4216 + }, + { + "epoch": 4.54, + "learning_rate": 6.970545977011495e-05, + "loss": 1.2149, + "step": 4217 + }, + { + "epoch": 4.55, + "learning_rate": 6.969827586206897e-05, + "loss": 1.1377, + "step": 4218 + }, + { + "epoch": 4.55, + "learning_rate": 6.969109195402299e-05, + "loss": 1.1717, + "step": 4219 + }, + { + "epoch": 4.55, + "learning_rate": 6.968390804597702e-05, + "loss": 1.1058, + "step": 4220 + }, + { + "epoch": 4.55, + "learning_rate": 6.967672413793104e-05, + "loss": 1.2079, + "step": 4221 + }, + { + "epoch": 4.55, + "learning_rate": 6.966954022988506e-05, + "loss": 1.1981, + "step": 4222 + }, + { + "epoch": 4.55, + "learning_rate": 6.966235632183908e-05, + "loss": 1.2002, + "step": 4223 + }, + { + "epoch": 4.55, + "learning_rate": 6.96551724137931e-05, + "loss": 1.1411, + "step": 4224 + }, + { + "epoch": 4.55, + "learning_rate": 6.964798850574713e-05, + "loss": 1.3303, + "step": 4225 + }, + { + "epoch": 4.55, + "learning_rate": 6.964080459770115e-05, + "loss": 1.1202, + "step": 4226 + }, + { + "epoch": 4.55, + "learning_rate": 6.963362068965518e-05, + "loss": 1.1669, + "step": 4227 + }, + { + "epoch": 4.56, + "learning_rate": 6.96264367816092e-05, + "loss": 1.1939, + "step": 4228 + }, + { + "epoch": 4.56, + "learning_rate": 6.961925287356322e-05, + "loss": 1.0749, + "step": 4229 + }, + { + "epoch": 4.56, + "learning_rate": 6.961206896551724e-05, + "loss": 1.1649, + "step": 4230 + }, + { + "epoch": 4.56, + "learning_rate": 6.960488505747127e-05, + "loss": 1.087, + "step": 4231 + }, + { + "epoch": 4.56, + "learning_rate": 6.959770114942528e-05, + "loss": 1.1163, + "step": 4232 + }, + { + "epoch": 4.56, + "learning_rate": 6.959051724137931e-05, + "loss": 1.102, + "step": 4233 + }, + { + "epoch": 4.56, + "learning_rate": 6.958333333333334e-05, + "loss": 1.1607, + "step": 4234 + }, + { + "epoch": 4.56, + "learning_rate": 6.957614942528737e-05, + "loss": 1.1068, + "step": 4235 + }, + { + "epoch": 4.56, + "learning_rate": 6.956896551724138e-05, + "loss": 1.1032, + "step": 4236 + }, + { + "epoch": 4.57, + "learning_rate": 6.956178160919541e-05, + "loss": 1.1677, + "step": 4237 + }, + { + "epoch": 4.57, + "learning_rate": 6.955459770114943e-05, + "loss": 1.1208, + "step": 4238 + }, + { + "epoch": 4.57, + "learning_rate": 6.954741379310345e-05, + "loss": 1.0564, + "step": 4239 + }, + { + "epoch": 4.57, + "learning_rate": 6.954022988505747e-05, + "loss": 1.1492, + "step": 4240 + }, + { + "epoch": 4.57, + "learning_rate": 6.95330459770115e-05, + "loss": 1.1331, + "step": 4241 + }, + { + "epoch": 4.57, + "learning_rate": 6.952586206896552e-05, + "loss": 1.1658, + "step": 4242 + }, + { + "epoch": 4.57, + "learning_rate": 6.951867816091955e-05, + "loss": 1.1136, + "step": 4243 + }, + { + "epoch": 4.57, + "learning_rate": 6.951149425287357e-05, + "loss": 1.2099, + "step": 4244 + }, + { + "epoch": 4.57, + "learning_rate": 6.95043103448276e-05, + "loss": 1.2723, + "step": 4245 + }, + { + "epoch": 4.58, + "learning_rate": 6.94971264367816e-05, + "loss": 1.2565, + "step": 4246 + }, + { + "epoch": 4.58, + "learning_rate": 6.948994252873564e-05, + "loss": 1.1912, + "step": 4247 + }, + { + "epoch": 4.58, + "learning_rate": 6.948275862068966e-05, + "loss": 1.1385, + "step": 4248 + }, + { + "epoch": 4.58, + "learning_rate": 6.947557471264368e-05, + "loss": 1.2068, + "step": 4249 + }, + { + "epoch": 4.58, + "learning_rate": 6.94683908045977e-05, + "loss": 1.1132, + "step": 4250 + }, + { + "epoch": 4.58, + "eval_loss": 1.1465922594070435, + "eval_runtime": 174.9132, + "eval_samples_per_second": 127.32, + "eval_steps_per_second": 0.663, + "step": 4250 + }, + { + "epoch": 4.58, + "learning_rate": 6.946120689655172e-05, + "loss": 1.1652, + "step": 4251 + }, + { + "epoch": 4.58, + "learning_rate": 6.945402298850576e-05, + "loss": 1.1729, + "step": 4252 + }, + { + "epoch": 4.58, + "learning_rate": 6.944683908045978e-05, + "loss": 1.1375, + "step": 4253 + }, + { + "epoch": 4.58, + "learning_rate": 6.94396551724138e-05, + "loss": 1.2798, + "step": 4254 + }, + { + "epoch": 4.59, + "learning_rate": 6.943247126436782e-05, + "loss": 1.189, + "step": 4255 + }, + { + "epoch": 4.59, + "learning_rate": 6.942528735632185e-05, + "loss": 1.003, + "step": 4256 + }, + { + "epoch": 4.59, + "learning_rate": 6.941810344827586e-05, + "loss": 1.2447, + "step": 4257 + }, + { + "epoch": 4.59, + "learning_rate": 6.941091954022989e-05, + "loss": 1.2077, + "step": 4258 + }, + { + "epoch": 4.59, + "learning_rate": 6.940373563218391e-05, + "loss": 1.0849, + "step": 4259 + }, + { + "epoch": 4.59, + "learning_rate": 6.939655172413793e-05, + "loss": 0.989, + "step": 4260 + }, + { + "epoch": 4.59, + "learning_rate": 6.938936781609195e-05, + "loss": 1.2073, + "step": 4261 + }, + { + "epoch": 4.59, + "learning_rate": 6.938218390804599e-05, + "loss": 1.2048, + "step": 4262 + }, + { + "epoch": 4.59, + "learning_rate": 6.9375e-05, + "loss": 1.1709, + "step": 4263 + }, + { + "epoch": 4.59, + "learning_rate": 6.936781609195403e-05, + "loss": 1.1563, + "step": 4264 + }, + { + "epoch": 4.6, + "learning_rate": 6.936063218390805e-05, + "loss": 1.1148, + "step": 4265 + }, + { + "epoch": 4.6, + "learning_rate": 6.935344827586208e-05, + "loss": 1.1845, + "step": 4266 + }, + { + "epoch": 4.6, + "learning_rate": 6.93462643678161e-05, + "loss": 1.1328, + "step": 4267 + }, + { + "epoch": 4.6, + "learning_rate": 6.933908045977012e-05, + "loss": 1.1141, + "step": 4268 + }, + { + "epoch": 4.6, + "learning_rate": 6.933189655172414e-05, + "loss": 1.1102, + "step": 4269 + }, + { + "epoch": 4.6, + "learning_rate": 6.932471264367818e-05, + "loss": 1.0736, + "step": 4270 + }, + { + "epoch": 4.6, + "learning_rate": 6.931752873563218e-05, + "loss": 1.0748, + "step": 4271 + }, + { + "epoch": 4.6, + "learning_rate": 6.931034482758622e-05, + "loss": 1.1142, + "step": 4272 + }, + { + "epoch": 4.6, + "learning_rate": 6.930316091954024e-05, + "loss": 1.0689, + "step": 4273 + }, + { + "epoch": 4.61, + "learning_rate": 6.929597701149426e-05, + "loss": 1.1647, + "step": 4274 + }, + { + "epoch": 4.61, + "learning_rate": 6.928879310344828e-05, + "loss": 1.0849, + "step": 4275 + }, + { + "epoch": 4.61, + "learning_rate": 6.92816091954023e-05, + "loss": 1.1494, + "step": 4276 + }, + { + "epoch": 4.61, + "learning_rate": 6.927442528735633e-05, + "loss": 1.0899, + "step": 4277 + }, + { + "epoch": 4.61, + "learning_rate": 6.926724137931034e-05, + "loss": 1.1129, + "step": 4278 + }, + { + "epoch": 4.61, + "learning_rate": 6.926005747126437e-05, + "loss": 1.109, + "step": 4279 + }, + { + "epoch": 4.61, + "learning_rate": 6.925287356321839e-05, + "loss": 1.0876, + "step": 4280 + }, + { + "epoch": 4.61, + "learning_rate": 6.924568965517241e-05, + "loss": 1.1302, + "step": 4281 + }, + { + "epoch": 4.61, + "learning_rate": 6.923850574712643e-05, + "loss": 1.123, + "step": 4282 + }, + { + "epoch": 4.62, + "learning_rate": 6.923132183908047e-05, + "loss": 1.2032, + "step": 4283 + }, + { + "epoch": 4.62, + "learning_rate": 6.922413793103449e-05, + "loss": 1.1566, + "step": 4284 + }, + { + "epoch": 4.62, + "learning_rate": 6.921695402298851e-05, + "loss": 1.2223, + "step": 4285 + }, + { + "epoch": 4.62, + "learning_rate": 6.920977011494253e-05, + "loss": 1.2627, + "step": 4286 + }, + { + "epoch": 4.62, + "learning_rate": 6.920258620689656e-05, + "loss": 1.173, + "step": 4287 + }, + { + "epoch": 4.62, + "learning_rate": 6.919540229885058e-05, + "loss": 1.0607, + "step": 4288 + }, + { + "epoch": 4.62, + "learning_rate": 6.91882183908046e-05, + "loss": 1.0124, + "step": 4289 + }, + { + "epoch": 4.62, + "learning_rate": 6.918103448275862e-05, + "loss": 1.0976, + "step": 4290 + }, + { + "epoch": 4.62, + "learning_rate": 6.917385057471266e-05, + "loss": 1.1667, + "step": 4291 + }, + { + "epoch": 4.62, + "learning_rate": 6.916666666666666e-05, + "loss": 1.0386, + "step": 4292 + }, + { + "epoch": 4.63, + "learning_rate": 6.91594827586207e-05, + "loss": 1.1833, + "step": 4293 + }, + { + "epoch": 4.63, + "learning_rate": 6.915229885057472e-05, + "loss": 1.1285, + "step": 4294 + }, + { + "epoch": 4.63, + "learning_rate": 6.914511494252874e-05, + "loss": 1.2122, + "step": 4295 + }, + { + "epoch": 4.63, + "learning_rate": 6.913793103448276e-05, + "loss": 1.1617, + "step": 4296 + }, + { + "epoch": 4.63, + "learning_rate": 6.913074712643679e-05, + "loss": 1.0832, + "step": 4297 + }, + { + "epoch": 4.63, + "learning_rate": 6.912356321839081e-05, + "loss": 1.114, + "step": 4298 + }, + { + "epoch": 4.63, + "learning_rate": 6.911637931034482e-05, + "loss": 1.0967, + "step": 4299 + }, + { + "epoch": 4.63, + "learning_rate": 6.910919540229885e-05, + "loss": 1.2245, + "step": 4300 + }, + { + "epoch": 4.63, + "learning_rate": 6.910201149425287e-05, + "loss": 1.1359, + "step": 4301 + }, + { + "epoch": 4.64, + "learning_rate": 6.90948275862069e-05, + "loss": 1.1615, + "step": 4302 + }, + { + "epoch": 4.64, + "learning_rate": 6.908764367816091e-05, + "loss": 1.1609, + "step": 4303 + }, + { + "epoch": 4.64, + "learning_rate": 6.908045977011495e-05, + "loss": 1.0515, + "step": 4304 + }, + { + "epoch": 4.64, + "learning_rate": 6.907327586206897e-05, + "loss": 1.2017, + "step": 4305 + }, + { + "epoch": 4.64, + "learning_rate": 6.906609195402299e-05, + "loss": 1.0405, + "step": 4306 + }, + { + "epoch": 4.64, + "learning_rate": 6.905890804597701e-05, + "loss": 1.1675, + "step": 4307 + }, + { + "epoch": 4.64, + "learning_rate": 6.905172413793104e-05, + "loss": 1.1098, + "step": 4308 + }, + { + "epoch": 4.64, + "learning_rate": 6.904454022988506e-05, + "loss": 1.0448, + "step": 4309 + }, + { + "epoch": 4.64, + "learning_rate": 6.903735632183908e-05, + "loss": 1.0926, + "step": 4310 + }, + { + "epoch": 4.65, + "learning_rate": 6.90301724137931e-05, + "loss": 1.301, + "step": 4311 + }, + { + "epoch": 4.65, + "learning_rate": 6.902298850574714e-05, + "loss": 1.1718, + "step": 4312 + }, + { + "epoch": 4.65, + "learning_rate": 6.901580459770114e-05, + "loss": 1.1101, + "step": 4313 + }, + { + "epoch": 4.65, + "learning_rate": 6.900862068965518e-05, + "loss": 1.0746, + "step": 4314 + }, + { + "epoch": 4.65, + "learning_rate": 6.90014367816092e-05, + "loss": 1.0591, + "step": 4315 + }, + { + "epoch": 4.65, + "learning_rate": 6.899425287356323e-05, + "loss": 1.0937, + "step": 4316 + }, + { + "epoch": 4.65, + "learning_rate": 6.898706896551724e-05, + "loss": 1.086, + "step": 4317 + }, + { + "epoch": 4.65, + "learning_rate": 6.897988505747127e-05, + "loss": 1.2144, + "step": 4318 + }, + { + "epoch": 4.65, + "learning_rate": 6.897270114942529e-05, + "loss": 1.1426, + "step": 4319 + }, + { + "epoch": 4.66, + "learning_rate": 6.896551724137931e-05, + "loss": 1.1138, + "step": 4320 + }, + { + "epoch": 4.66, + "learning_rate": 6.895833333333333e-05, + "loss": 1.1858, + "step": 4321 + }, + { + "epoch": 4.66, + "learning_rate": 6.895114942528737e-05, + "loss": 1.1519, + "step": 4322 + }, + { + "epoch": 4.66, + "learning_rate": 6.894396551724139e-05, + "loss": 1.2948, + "step": 4323 + }, + { + "epoch": 4.66, + "learning_rate": 6.893678160919541e-05, + "loss": 1.1543, + "step": 4324 + }, + { + "epoch": 4.66, + "learning_rate": 6.892959770114943e-05, + "loss": 1.3066, + "step": 4325 + }, + { + "epoch": 4.66, + "learning_rate": 6.892241379310345e-05, + "loss": 1.0365, + "step": 4326 + }, + { + "epoch": 4.66, + "learning_rate": 6.891522988505747e-05, + "loss": 1.0393, + "step": 4327 + }, + { + "epoch": 4.66, + "learning_rate": 6.890804597701149e-05, + "loss": 1.2172, + "step": 4328 + }, + { + "epoch": 4.66, + "learning_rate": 6.890086206896552e-05, + "loss": 1.107, + "step": 4329 + }, + { + "epoch": 4.67, + "learning_rate": 6.889367816091954e-05, + "loss": 1.2154, + "step": 4330 + }, + { + "epoch": 4.67, + "learning_rate": 6.888649425287356e-05, + "loss": 1.0682, + "step": 4331 + }, + { + "epoch": 4.67, + "learning_rate": 6.887931034482758e-05, + "loss": 1.1574, + "step": 4332 + }, + { + "epoch": 4.67, + "learning_rate": 6.887212643678162e-05, + "loss": 1.1973, + "step": 4333 + }, + { + "epoch": 4.67, + "learning_rate": 6.886494252873564e-05, + "loss": 1.2072, + "step": 4334 + }, + { + "epoch": 4.67, + "learning_rate": 6.885775862068966e-05, + "loss": 1.1079, + "step": 4335 + }, + { + "epoch": 4.67, + "learning_rate": 6.885057471264368e-05, + "loss": 1.0478, + "step": 4336 + }, + { + "epoch": 4.67, + "learning_rate": 6.884339080459771e-05, + "loss": 1.1404, + "step": 4337 + }, + { + "epoch": 4.67, + "learning_rate": 6.883620689655172e-05, + "loss": 1.0557, + "step": 4338 + }, + { + "epoch": 4.68, + "learning_rate": 6.882902298850575e-05, + "loss": 1.2109, + "step": 4339 + }, + { + "epoch": 4.68, + "learning_rate": 6.882183908045977e-05, + "loss": 1.1591, + "step": 4340 + }, + { + "epoch": 4.68, + "learning_rate": 6.88146551724138e-05, + "loss": 1.2471, + "step": 4341 + }, + { + "epoch": 4.68, + "learning_rate": 6.880747126436781e-05, + "loss": 1.0521, + "step": 4342 + }, + { + "epoch": 4.68, + "learning_rate": 6.880028735632185e-05, + "loss": 1.1192, + "step": 4343 + }, + { + "epoch": 4.68, + "learning_rate": 6.879310344827587e-05, + "loss": 1.0909, + "step": 4344 + }, + { + "epoch": 4.68, + "learning_rate": 6.878591954022989e-05, + "loss": 0.995, + "step": 4345 + }, + { + "epoch": 4.68, + "learning_rate": 6.877873563218391e-05, + "loss": 1.0413, + "step": 4346 + }, + { + "epoch": 4.68, + "learning_rate": 6.877155172413794e-05, + "loss": 1.277, + "step": 4347 + }, + { + "epoch": 4.69, + "learning_rate": 6.876436781609196e-05, + "loss": 1.2401, + "step": 4348 + }, + { + "epoch": 4.69, + "learning_rate": 6.875718390804598e-05, + "loss": 1.16, + "step": 4349 + }, + { + "epoch": 4.69, + "learning_rate": 6.875e-05, + "loss": 1.1479, + "step": 4350 + }, + { + "epoch": 4.69, + "learning_rate": 6.874281609195402e-05, + "loss": 1.0263, + "step": 4351 + }, + { + "epoch": 4.69, + "learning_rate": 6.873563218390804e-05, + "loss": 1.1386, + "step": 4352 + }, + { + "epoch": 4.69, + "learning_rate": 6.872844827586207e-05, + "loss": 1.1309, + "step": 4353 + }, + { + "epoch": 4.69, + "learning_rate": 6.87212643678161e-05, + "loss": 1.175, + "step": 4354 + }, + { + "epoch": 4.69, + "learning_rate": 6.871408045977012e-05, + "loss": 1.1721, + "step": 4355 + }, + { + "epoch": 4.69, + "learning_rate": 6.870689655172414e-05, + "loss": 1.1667, + "step": 4356 + }, + { + "epoch": 4.7, + "learning_rate": 6.869971264367816e-05, + "loss": 1.1972, + "step": 4357 + }, + { + "epoch": 4.7, + "learning_rate": 6.86925287356322e-05, + "loss": 1.0256, + "step": 4358 + }, + { + "epoch": 4.7, + "learning_rate": 6.86853448275862e-05, + "loss": 1.2464, + "step": 4359 + }, + { + "epoch": 4.7, + "learning_rate": 6.867816091954023e-05, + "loss": 1.0377, + "step": 4360 + }, + { + "epoch": 4.7, + "learning_rate": 6.867097701149425e-05, + "loss": 1.0423, + "step": 4361 + }, + { + "epoch": 4.7, + "learning_rate": 6.866379310344828e-05, + "loss": 1.1078, + "step": 4362 + }, + { + "epoch": 4.7, + "learning_rate": 6.86566091954023e-05, + "loss": 1.1779, + "step": 4363 + }, + { + "epoch": 4.7, + "learning_rate": 6.864942528735633e-05, + "loss": 1.143, + "step": 4364 + }, + { + "epoch": 4.7, + "learning_rate": 6.864224137931035e-05, + "loss": 1.129, + "step": 4365 + }, + { + "epoch": 4.7, + "learning_rate": 6.863505747126437e-05, + "loss": 1.0895, + "step": 4366 + }, + { + "epoch": 4.71, + "learning_rate": 6.862787356321839e-05, + "loss": 0.9187, + "step": 4367 + }, + { + "epoch": 4.71, + "learning_rate": 6.862068965517242e-05, + "loss": 0.9307, + "step": 4368 + }, + { + "epoch": 4.71, + "learning_rate": 6.861350574712644e-05, + "loss": 1.241, + "step": 4369 + }, + { + "epoch": 4.71, + "learning_rate": 6.860632183908046e-05, + "loss": 1.0811, + "step": 4370 + }, + { + "epoch": 4.71, + "learning_rate": 6.859913793103449e-05, + "loss": 1.1751, + "step": 4371 + }, + { + "epoch": 4.71, + "learning_rate": 6.859195402298852e-05, + "loss": 1.2442, + "step": 4372 + }, + { + "epoch": 4.71, + "learning_rate": 6.858477011494253e-05, + "loss": 1.1046, + "step": 4373 + }, + { + "epoch": 4.71, + "learning_rate": 6.857758620689656e-05, + "loss": 1.2011, + "step": 4374 + }, + { + "epoch": 4.71, + "learning_rate": 6.857040229885058e-05, + "loss": 1.1107, + "step": 4375 + }, + { + "epoch": 4.72, + "learning_rate": 6.85632183908046e-05, + "loss": 1.1842, + "step": 4376 + }, + { + "epoch": 4.72, + "learning_rate": 6.855603448275862e-05, + "loss": 1.1103, + "step": 4377 + }, + { + "epoch": 4.72, + "learning_rate": 6.854885057471264e-05, + "loss": 1.1959, + "step": 4378 + }, + { + "epoch": 4.72, + "learning_rate": 6.854166666666667e-05, + "loss": 1.0387, + "step": 4379 + }, + { + "epoch": 4.72, + "learning_rate": 6.85344827586207e-05, + "loss": 1.1494, + "step": 4380 + }, + { + "epoch": 4.72, + "learning_rate": 6.852729885057472e-05, + "loss": 1.0564, + "step": 4381 + }, + { + "epoch": 4.72, + "learning_rate": 6.852011494252874e-05, + "loss": 1.0887, + "step": 4382 + }, + { + "epoch": 4.72, + "learning_rate": 6.851293103448277e-05, + "loss": 1.2623, + "step": 4383 + }, + { + "epoch": 4.72, + "learning_rate": 6.850574712643678e-05, + "loss": 1.018, + "step": 4384 + }, + { + "epoch": 4.73, + "learning_rate": 6.849856321839081e-05, + "loss": 1.2842, + "step": 4385 + }, + { + "epoch": 4.73, + "learning_rate": 6.849137931034483e-05, + "loss": 1.3427, + "step": 4386 + }, + { + "epoch": 4.73, + "learning_rate": 6.848419540229885e-05, + "loss": 1.1589, + "step": 4387 + }, + { + "epoch": 4.73, + "learning_rate": 6.847701149425287e-05, + "loss": 1.2035, + "step": 4388 + }, + { + "epoch": 4.73, + "learning_rate": 6.84698275862069e-05, + "loss": 1.1452, + "step": 4389 + }, + { + "epoch": 4.73, + "learning_rate": 6.846264367816093e-05, + "loss": 1.1534, + "step": 4390 + }, + { + "epoch": 4.73, + "learning_rate": 6.845545977011495e-05, + "loss": 1.1419, + "step": 4391 + }, + { + "epoch": 4.73, + "learning_rate": 6.844827586206897e-05, + "loss": 1.1217, + "step": 4392 + }, + { + "epoch": 4.73, + "learning_rate": 6.8441091954023e-05, + "loss": 1.108, + "step": 4393 + }, + { + "epoch": 4.73, + "learning_rate": 6.8433908045977e-05, + "loss": 1.1381, + "step": 4394 + }, + { + "epoch": 4.74, + "learning_rate": 6.842672413793104e-05, + "loss": 0.9928, + "step": 4395 + }, + { + "epoch": 4.74, + "learning_rate": 6.841954022988506e-05, + "loss": 1.0744, + "step": 4396 + }, + { + "epoch": 4.74, + "learning_rate": 6.84123563218391e-05, + "loss": 1.1847, + "step": 4397 + }, + { + "epoch": 4.74, + "learning_rate": 6.84051724137931e-05, + "loss": 1.1077, + "step": 4398 + }, + { + "epoch": 4.74, + "learning_rate": 6.839798850574714e-05, + "loss": 1.1404, + "step": 4399 + }, + { + "epoch": 4.74, + "learning_rate": 6.839080459770116e-05, + "loss": 1.1018, + "step": 4400 + }, + { + "epoch": 4.74, + "learning_rate": 6.838362068965518e-05, + "loss": 1.1051, + "step": 4401 + }, + { + "epoch": 4.74, + "learning_rate": 6.83764367816092e-05, + "loss": 1.0594, + "step": 4402 + }, + { + "epoch": 4.74, + "learning_rate": 6.836925287356322e-05, + "loss": 1.105, + "step": 4403 + }, + { + "epoch": 4.75, + "learning_rate": 6.836206896551725e-05, + "loss": 1.1171, + "step": 4404 + }, + { + "epoch": 4.75, + "learning_rate": 6.835488505747126e-05, + "loss": 1.0954, + "step": 4405 + }, + { + "epoch": 4.75, + "learning_rate": 6.834770114942529e-05, + "loss": 1.1831, + "step": 4406 + }, + { + "epoch": 4.75, + "learning_rate": 6.834051724137931e-05, + "loss": 1.218, + "step": 4407 + }, + { + "epoch": 4.75, + "learning_rate": 6.833333333333333e-05, + "loss": 1.1704, + "step": 4408 + }, + { + "epoch": 4.75, + "learning_rate": 6.832614942528735e-05, + "loss": 1.0218, + "step": 4409 + }, + { + "epoch": 4.75, + "learning_rate": 6.831896551724139e-05, + "loss": 1.0037, + "step": 4410 + }, + { + "epoch": 4.75, + "learning_rate": 6.83117816091954e-05, + "loss": 1.1492, + "step": 4411 + }, + { + "epoch": 4.75, + "learning_rate": 6.830459770114943e-05, + "loss": 1.196, + "step": 4412 + }, + { + "epoch": 4.76, + "learning_rate": 6.829741379310345e-05, + "loss": 1.1231, + "step": 4413 + }, + { + "epoch": 4.76, + "learning_rate": 6.829022988505748e-05, + "loss": 1.0279, + "step": 4414 + }, + { + "epoch": 4.76, + "learning_rate": 6.82830459770115e-05, + "loss": 0.9989, + "step": 4415 + }, + { + "epoch": 4.76, + "learning_rate": 6.827586206896552e-05, + "loss": 1.1549, + "step": 4416 + }, + { + "epoch": 4.76, + "learning_rate": 6.826867816091954e-05, + "loss": 1.112, + "step": 4417 + }, + { + "epoch": 4.76, + "learning_rate": 6.826149425287358e-05, + "loss": 1.236, + "step": 4418 + }, + { + "epoch": 4.76, + "learning_rate": 6.825431034482758e-05, + "loss": 1.049, + "step": 4419 + }, + { + "epoch": 4.76, + "learning_rate": 6.824712643678162e-05, + "loss": 1.2158, + "step": 4420 + }, + { + "epoch": 4.76, + "learning_rate": 6.823994252873564e-05, + "loss": 1.0153, + "step": 4421 + }, + { + "epoch": 4.77, + "learning_rate": 6.823275862068966e-05, + "loss": 1.3327, + "step": 4422 + }, + { + "epoch": 4.77, + "learning_rate": 6.822557471264368e-05, + "loss": 1.1549, + "step": 4423 + }, + { + "epoch": 4.77, + "learning_rate": 6.821839080459771e-05, + "loss": 1.2384, + "step": 4424 + }, + { + "epoch": 4.77, + "learning_rate": 6.821120689655173e-05, + "loss": 1.1477, + "step": 4425 + }, + { + "epoch": 4.77, + "learning_rate": 6.820402298850575e-05, + "loss": 1.1825, + "step": 4426 + }, + { + "epoch": 4.77, + "learning_rate": 6.819683908045977e-05, + "loss": 1.0439, + "step": 4427 + }, + { + "epoch": 4.77, + "learning_rate": 6.818965517241379e-05, + "loss": 1.2206, + "step": 4428 + }, + { + "epoch": 4.77, + "learning_rate": 6.818247126436783e-05, + "loss": 1.2342, + "step": 4429 + }, + { + "epoch": 4.77, + "learning_rate": 6.817528735632183e-05, + "loss": 1.0989, + "step": 4430 + }, + { + "epoch": 4.77, + "learning_rate": 6.816810344827587e-05, + "loss": 1.1589, + "step": 4431 + }, + { + "epoch": 4.78, + "learning_rate": 6.816091954022989e-05, + "loss": 1.1755, + "step": 4432 + }, + { + "epoch": 4.78, + "learning_rate": 6.815373563218391e-05, + "loss": 1.1865, + "step": 4433 + }, + { + "epoch": 4.78, + "learning_rate": 6.814655172413793e-05, + "loss": 1.1528, + "step": 4434 + }, + { + "epoch": 4.78, + "learning_rate": 6.813936781609196e-05, + "loss": 1.2072, + "step": 4435 + }, + { + "epoch": 4.78, + "learning_rate": 6.813218390804598e-05, + "loss": 1.1475, + "step": 4436 + }, + { + "epoch": 4.78, + "learning_rate": 6.8125e-05, + "loss": 1.135, + "step": 4437 + }, + { + "epoch": 4.78, + "learning_rate": 6.811781609195402e-05, + "loss": 1.0803, + "step": 4438 + }, + { + "epoch": 4.78, + "learning_rate": 6.811063218390806e-05, + "loss": 1.2098, + "step": 4439 + }, + { + "epoch": 4.78, + "learning_rate": 6.810344827586206e-05, + "loss": 1.106, + "step": 4440 + }, + { + "epoch": 4.79, + "learning_rate": 6.80962643678161e-05, + "loss": 1.1044, + "step": 4441 + }, + { + "epoch": 4.79, + "learning_rate": 6.808908045977012e-05, + "loss": 1.1775, + "step": 4442 + }, + { + "epoch": 4.79, + "learning_rate": 6.808189655172414e-05, + "loss": 1.0805, + "step": 4443 + }, + { + "epoch": 4.79, + "learning_rate": 6.807471264367816e-05, + "loss": 1.1127, + "step": 4444 + }, + { + "epoch": 4.79, + "learning_rate": 6.806752873563219e-05, + "loss": 1.2425, + "step": 4445 + }, + { + "epoch": 4.79, + "learning_rate": 6.806034482758621e-05, + "loss": 1.2736, + "step": 4446 + }, + { + "epoch": 4.79, + "learning_rate": 6.805316091954023e-05, + "loss": 1.0685, + "step": 4447 + }, + { + "epoch": 4.79, + "learning_rate": 6.804597701149425e-05, + "loss": 1.0969, + "step": 4448 + }, + { + "epoch": 4.79, + "learning_rate": 6.803879310344829e-05, + "loss": 1.0438, + "step": 4449 + }, + { + "epoch": 4.8, + "learning_rate": 6.803160919540231e-05, + "loss": 1.0889, + "step": 4450 + }, + { + "epoch": 4.8, + "learning_rate": 6.802442528735633e-05, + "loss": 1.1812, + "step": 4451 + }, + { + "epoch": 4.8, + "learning_rate": 6.801724137931035e-05, + "loss": 1.1432, + "step": 4452 + }, + { + "epoch": 4.8, + "learning_rate": 6.801005747126437e-05, + "loss": 1.0662, + "step": 4453 + }, + { + "epoch": 4.8, + "learning_rate": 6.800287356321839e-05, + "loss": 1.1531, + "step": 4454 + }, + { + "epoch": 4.8, + "learning_rate": 6.799568965517241e-05, + "loss": 1.2044, + "step": 4455 + }, + { + "epoch": 4.8, + "learning_rate": 6.798850574712644e-05, + "loss": 1.0123, + "step": 4456 + }, + { + "epoch": 4.8, + "learning_rate": 6.798132183908046e-05, + "loss": 1.023, + "step": 4457 + }, + { + "epoch": 4.8, + "learning_rate": 6.797413793103448e-05, + "loss": 1.264, + "step": 4458 + }, + { + "epoch": 4.8, + "learning_rate": 6.79669540229885e-05, + "loss": 1.0439, + "step": 4459 + }, + { + "epoch": 4.81, + "learning_rate": 6.795977011494254e-05, + "loss": 1.2166, + "step": 4460 + }, + { + "epoch": 4.81, + "learning_rate": 6.795258620689656e-05, + "loss": 1.2086, + "step": 4461 + }, + { + "epoch": 4.81, + "learning_rate": 6.794540229885058e-05, + "loss": 1.0463, + "step": 4462 + }, + { + "epoch": 4.81, + "learning_rate": 6.79382183908046e-05, + "loss": 1.146, + "step": 4463 + }, + { + "epoch": 4.81, + "learning_rate": 6.793103448275863e-05, + "loss": 1.1108, + "step": 4464 + }, + { + "epoch": 4.81, + "learning_rate": 6.792385057471264e-05, + "loss": 1.237, + "step": 4465 + }, + { + "epoch": 4.81, + "learning_rate": 6.791666666666667e-05, + "loss": 1.2563, + "step": 4466 + }, + { + "epoch": 4.81, + "learning_rate": 6.79094827586207e-05, + "loss": 1.2526, + "step": 4467 + }, + { + "epoch": 4.81, + "learning_rate": 6.790229885057471e-05, + "loss": 0.9662, + "step": 4468 + }, + { + "epoch": 4.82, + "learning_rate": 6.789511494252873e-05, + "loss": 1.0607, + "step": 4469 + }, + { + "epoch": 4.82, + "learning_rate": 6.788793103448277e-05, + "loss": 1.0144, + "step": 4470 + }, + { + "epoch": 4.82, + "learning_rate": 6.788074712643679e-05, + "loss": 1.2085, + "step": 4471 + }, + { + "epoch": 4.82, + "learning_rate": 6.787356321839081e-05, + "loss": 1.1406, + "step": 4472 + }, + { + "epoch": 4.82, + "learning_rate": 6.786637931034483e-05, + "loss": 1.1723, + "step": 4473 + }, + { + "epoch": 4.82, + "learning_rate": 6.785919540229886e-05, + "loss": 1.1425, + "step": 4474 + }, + { + "epoch": 4.82, + "learning_rate": 6.785201149425287e-05, + "loss": 1.0895, + "step": 4475 + }, + { + "epoch": 4.82, + "learning_rate": 6.78448275862069e-05, + "loss": 1.2146, + "step": 4476 + }, + { + "epoch": 4.82, + "learning_rate": 6.783764367816092e-05, + "loss": 1.2041, + "step": 4477 + }, + { + "epoch": 4.83, + "learning_rate": 6.783045977011494e-05, + "loss": 1.0958, + "step": 4478 + }, + { + "epoch": 4.83, + "learning_rate": 6.782327586206896e-05, + "loss": 1.0094, + "step": 4479 + }, + { + "epoch": 4.83, + "learning_rate": 6.781609195402298e-05, + "loss": 1.129, + "step": 4480 + }, + { + "epoch": 4.83, + "learning_rate": 6.780890804597702e-05, + "loss": 1.0831, + "step": 4481 + }, + { + "epoch": 4.83, + "learning_rate": 6.780172413793104e-05, + "loss": 1.0751, + "step": 4482 + }, + { + "epoch": 4.83, + "learning_rate": 6.779454022988506e-05, + "loss": 1.2195, + "step": 4483 + }, + { + "epoch": 4.83, + "learning_rate": 6.778735632183908e-05, + "loss": 1.0814, + "step": 4484 + }, + { + "epoch": 4.83, + "learning_rate": 6.778017241379311e-05, + "loss": 1.1297, + "step": 4485 + }, + { + "epoch": 4.83, + "learning_rate": 6.777298850574712e-05, + "loss": 1.162, + "step": 4486 + }, + { + "epoch": 4.84, + "learning_rate": 6.776580459770115e-05, + "loss": 1.1133, + "step": 4487 + }, + { + "epoch": 4.84, + "learning_rate": 6.775862068965517e-05, + "loss": 1.164, + "step": 4488 + }, + { + "epoch": 4.84, + "learning_rate": 6.77514367816092e-05, + "loss": 1.2212, + "step": 4489 + }, + { + "epoch": 4.84, + "learning_rate": 6.774425287356322e-05, + "loss": 1.1877, + "step": 4490 + }, + { + "epoch": 4.84, + "learning_rate": 6.773706896551725e-05, + "loss": 1.0477, + "step": 4491 + }, + { + "epoch": 4.84, + "learning_rate": 6.772988505747127e-05, + "loss": 1.2572, + "step": 4492 + }, + { + "epoch": 4.84, + "learning_rate": 6.772270114942529e-05, + "loss": 1.0967, + "step": 4493 + }, + { + "epoch": 4.84, + "learning_rate": 6.771551724137931e-05, + "loss": 1.1454, + "step": 4494 + }, + { + "epoch": 4.84, + "learning_rate": 6.770833333333334e-05, + "loss": 1.1308, + "step": 4495 + }, + { + "epoch": 4.84, + "learning_rate": 6.770114942528736e-05, + "loss": 1.2556, + "step": 4496 + }, + { + "epoch": 4.85, + "learning_rate": 6.769396551724138e-05, + "loss": 1.0981, + "step": 4497 + }, + { + "epoch": 4.85, + "learning_rate": 6.76867816091954e-05, + "loss": 1.1877, + "step": 4498 + }, + { + "epoch": 4.85, + "learning_rate": 6.767959770114944e-05, + "loss": 1.2237, + "step": 4499 + }, + { + "epoch": 4.85, + "learning_rate": 6.767241379310345e-05, + "loss": 1.1492, + "step": 4500 + }, + { + "epoch": 4.85, + "eval_loss": 1.1355876922607422, + "eval_runtime": 174.9713, + "eval_samples_per_second": 127.278, + "eval_steps_per_second": 0.663, + "step": 4500 + }, + { + "epoch": 4.85, + "learning_rate": 6.766522988505748e-05, + "loss": 1.2047, + "step": 4501 + }, + { + "epoch": 4.85, + "learning_rate": 6.76580459770115e-05, + "loss": 1.2189, + "step": 4502 + }, + { + "epoch": 4.85, + "learning_rate": 6.765086206896552e-05, + "loss": 1.0946, + "step": 4503 + }, + { + "epoch": 4.85, + "learning_rate": 6.764367816091954e-05, + "loss": 1.2649, + "step": 4504 + }, + { + "epoch": 4.85, + "learning_rate": 6.763649425287356e-05, + "loss": 1.0728, + "step": 4505 + }, + { + "epoch": 4.86, + "learning_rate": 6.76293103448276e-05, + "loss": 1.2399, + "step": 4506 + }, + { + "epoch": 4.86, + "learning_rate": 6.76221264367816e-05, + "loss": 1.2673, + "step": 4507 + }, + { + "epoch": 4.86, + "learning_rate": 6.761494252873564e-05, + "loss": 1.2652, + "step": 4508 + }, + { + "epoch": 4.86, + "learning_rate": 6.760775862068966e-05, + "loss": 1.1261, + "step": 4509 + }, + { + "epoch": 4.86, + "learning_rate": 6.760057471264369e-05, + "loss": 1.107, + "step": 4510 + }, + { + "epoch": 4.86, + "learning_rate": 6.75933908045977e-05, + "loss": 1.3166, + "step": 4511 + }, + { + "epoch": 4.86, + "learning_rate": 6.758620689655173e-05, + "loss": 0.9778, + "step": 4512 + }, + { + "epoch": 4.86, + "learning_rate": 6.757902298850575e-05, + "loss": 1.1332, + "step": 4513 + }, + { + "epoch": 4.86, + "learning_rate": 6.757183908045977e-05, + "loss": 1.0484, + "step": 4514 + }, + { + "epoch": 4.87, + "learning_rate": 6.756465517241379e-05, + "loss": 1.1391, + "step": 4515 + }, + { + "epoch": 4.87, + "learning_rate": 6.755747126436782e-05, + "loss": 1.2841, + "step": 4516 + }, + { + "epoch": 4.87, + "learning_rate": 6.755028735632185e-05, + "loss": 1.1855, + "step": 4517 + }, + { + "epoch": 4.87, + "learning_rate": 6.754310344827587e-05, + "loss": 1.2816, + "step": 4518 + }, + { + "epoch": 4.87, + "learning_rate": 6.753591954022989e-05, + "loss": 1.0278, + "step": 4519 + }, + { + "epoch": 4.87, + "learning_rate": 6.752873563218392e-05, + "loss": 1.0994, + "step": 4520 + }, + { + "epoch": 4.87, + "learning_rate": 6.752155172413793e-05, + "loss": 1.1738, + "step": 4521 + }, + { + "epoch": 4.87, + "learning_rate": 6.751436781609196e-05, + "loss": 1.103, + "step": 4522 + }, + { + "epoch": 4.87, + "learning_rate": 6.750718390804598e-05, + "loss": 1.1596, + "step": 4523 + }, + { + "epoch": 4.88, + "learning_rate": 6.750000000000001e-05, + "loss": 1.0804, + "step": 4524 + }, + { + "epoch": 4.88, + "learning_rate": 6.749281609195402e-05, + "loss": 1.0312, + "step": 4525 + }, + { + "epoch": 4.88, + "learning_rate": 6.748563218390806e-05, + "loss": 1.1313, + "step": 4526 + }, + { + "epoch": 4.88, + "learning_rate": 6.747844827586208e-05, + "loss": 1.0796, + "step": 4527 + }, + { + "epoch": 4.88, + "learning_rate": 6.74712643678161e-05, + "loss": 1.1105, + "step": 4528 + }, + { + "epoch": 4.88, + "learning_rate": 6.746408045977012e-05, + "loss": 1.0736, + "step": 4529 + }, + { + "epoch": 4.88, + "learning_rate": 6.745689655172414e-05, + "loss": 1.1823, + "step": 4530 + }, + { + "epoch": 4.88, + "learning_rate": 6.744971264367817e-05, + "loss": 0.993, + "step": 4531 + }, + { + "epoch": 4.88, + "learning_rate": 6.744252873563218e-05, + "loss": 1.107, + "step": 4532 + }, + { + "epoch": 4.88, + "learning_rate": 6.743534482758621e-05, + "loss": 1.0849, + "step": 4533 + }, + { + "epoch": 4.89, + "learning_rate": 6.742816091954023e-05, + "loss": 1.2539, + "step": 4534 + }, + { + "epoch": 4.89, + "learning_rate": 6.742097701149425e-05, + "loss": 1.1143, + "step": 4535 + }, + { + "epoch": 4.89, + "learning_rate": 6.741379310344827e-05, + "loss": 1.1665, + "step": 4536 + }, + { + "epoch": 4.89, + "learning_rate": 6.74066091954023e-05, + "loss": 1.0693, + "step": 4537 + }, + { + "epoch": 4.89, + "learning_rate": 6.739942528735633e-05, + "loss": 1.12, + "step": 4538 + }, + { + "epoch": 4.89, + "learning_rate": 6.739224137931035e-05, + "loss": 1.1935, + "step": 4539 + }, + { + "epoch": 4.89, + "learning_rate": 6.738505747126437e-05, + "loss": 1.002, + "step": 4540 + }, + { + "epoch": 4.89, + "learning_rate": 6.73778735632184e-05, + "loss": 1.0958, + "step": 4541 + }, + { + "epoch": 4.89, + "learning_rate": 6.737068965517242e-05, + "loss": 1.0934, + "step": 4542 + }, + { + "epoch": 4.9, + "learning_rate": 6.736350574712644e-05, + "loss": 1.205, + "step": 4543 + }, + { + "epoch": 4.9, + "learning_rate": 6.735632183908046e-05, + "loss": 1.1968, + "step": 4544 + }, + { + "epoch": 4.9, + "learning_rate": 6.73491379310345e-05, + "loss": 1.242, + "step": 4545 + }, + { + "epoch": 4.9, + "learning_rate": 6.73419540229885e-05, + "loss": 1.0686, + "step": 4546 + }, + { + "epoch": 4.9, + "learning_rate": 6.733477011494254e-05, + "loss": 1.1582, + "step": 4547 + }, + { + "epoch": 4.9, + "learning_rate": 6.732758620689656e-05, + "loss": 1.1105, + "step": 4548 + }, + { + "epoch": 4.9, + "learning_rate": 6.732040229885058e-05, + "loss": 1.1177, + "step": 4549 + }, + { + "epoch": 4.9, + "learning_rate": 6.73132183908046e-05, + "loss": 0.9892, + "step": 4550 + }, + { + "epoch": 4.9, + "learning_rate": 6.730603448275863e-05, + "loss": 1.1659, + "step": 4551 + }, + { + "epoch": 4.91, + "learning_rate": 6.729885057471265e-05, + "loss": 1.1162, + "step": 4552 + }, + { + "epoch": 4.91, + "learning_rate": 6.729166666666667e-05, + "loss": 1.0384, + "step": 4553 + }, + { + "epoch": 4.91, + "learning_rate": 6.728448275862069e-05, + "loss": 1.1939, + "step": 4554 + }, + { + "epoch": 4.91, + "learning_rate": 6.727729885057471e-05, + "loss": 1.1435, + "step": 4555 + }, + { + "epoch": 4.91, + "learning_rate": 6.727011494252873e-05, + "loss": 1.1244, + "step": 4556 + }, + { + "epoch": 4.91, + "learning_rate": 6.726293103448275e-05, + "loss": 1.0446, + "step": 4557 + }, + { + "epoch": 4.91, + "learning_rate": 6.725574712643679e-05, + "loss": 1.0135, + "step": 4558 + }, + { + "epoch": 4.91, + "learning_rate": 6.724856321839081e-05, + "loss": 1.2555, + "step": 4559 + }, + { + "epoch": 4.91, + "learning_rate": 6.724137931034483e-05, + "loss": 1.185, + "step": 4560 + }, + { + "epoch": 4.91, + "learning_rate": 6.723419540229885e-05, + "loss": 1.2159, + "step": 4561 + }, + { + "epoch": 4.92, + "learning_rate": 6.722701149425288e-05, + "loss": 1.1549, + "step": 4562 + }, + { + "epoch": 4.92, + "learning_rate": 6.72198275862069e-05, + "loss": 1.1011, + "step": 4563 + }, + { + "epoch": 4.92, + "learning_rate": 6.721264367816092e-05, + "loss": 1.2169, + "step": 4564 + }, + { + "epoch": 4.92, + "learning_rate": 6.720545977011494e-05, + "loss": 1.0926, + "step": 4565 + }, + { + "epoch": 4.92, + "learning_rate": 6.719827586206898e-05, + "loss": 1.1244, + "step": 4566 + }, + { + "epoch": 4.92, + "learning_rate": 6.719109195402298e-05, + "loss": 1.01, + "step": 4567 + }, + { + "epoch": 4.92, + "learning_rate": 6.718390804597702e-05, + "loss": 1.0923, + "step": 4568 + }, + { + "epoch": 4.92, + "learning_rate": 6.717672413793104e-05, + "loss": 1.0241, + "step": 4569 + }, + { + "epoch": 4.92, + "learning_rate": 6.716954022988506e-05, + "loss": 1.1406, + "step": 4570 + }, + { + "epoch": 4.93, + "learning_rate": 6.716235632183908e-05, + "loss": 1.1702, + "step": 4571 + }, + { + "epoch": 4.93, + "learning_rate": 6.715517241379311e-05, + "loss": 1.0736, + "step": 4572 + }, + { + "epoch": 4.93, + "learning_rate": 6.714798850574713e-05, + "loss": 1.1182, + "step": 4573 + }, + { + "epoch": 4.93, + "learning_rate": 6.714080459770115e-05, + "loss": 1.1763, + "step": 4574 + }, + { + "epoch": 4.93, + "learning_rate": 6.713362068965517e-05, + "loss": 1.1978, + "step": 4575 + }, + { + "epoch": 4.93, + "learning_rate": 6.71264367816092e-05, + "loss": 1.1176, + "step": 4576 + }, + { + "epoch": 4.93, + "learning_rate": 6.711925287356323e-05, + "loss": 1.1762, + "step": 4577 + }, + { + "epoch": 4.93, + "learning_rate": 6.711206896551725e-05, + "loss": 1.1442, + "step": 4578 + }, + { + "epoch": 4.93, + "learning_rate": 6.710488505747127e-05, + "loss": 1.0566, + "step": 4579 + }, + { + "epoch": 4.94, + "learning_rate": 6.70977011494253e-05, + "loss": 1.183, + "step": 4580 + }, + { + "epoch": 4.94, + "learning_rate": 6.709051724137931e-05, + "loss": 1.1885, + "step": 4581 + }, + { + "epoch": 4.94, + "learning_rate": 6.708333333333333e-05, + "loss": 1.2429, + "step": 4582 + }, + { + "epoch": 4.94, + "learning_rate": 6.707614942528736e-05, + "loss": 1.1447, + "step": 4583 + }, + { + "epoch": 4.94, + "learning_rate": 6.706896551724138e-05, + "loss": 1.0714, + "step": 4584 + }, + { + "epoch": 4.94, + "learning_rate": 6.70617816091954e-05, + "loss": 1.0751, + "step": 4585 + }, + { + "epoch": 4.94, + "learning_rate": 6.705459770114942e-05, + "loss": 1.2848, + "step": 4586 + }, + { + "epoch": 4.94, + "learning_rate": 6.704741379310346e-05, + "loss": 1.1642, + "step": 4587 + }, + { + "epoch": 4.94, + "learning_rate": 6.704022988505746e-05, + "loss": 1.0291, + "step": 4588 + }, + { + "epoch": 4.95, + "learning_rate": 6.70330459770115e-05, + "loss": 1.0939, + "step": 4589 + }, + { + "epoch": 4.95, + "learning_rate": 6.702586206896552e-05, + "loss": 1.1922, + "step": 4590 + }, + { + "epoch": 4.95, + "learning_rate": 6.701867816091955e-05, + "loss": 1.1275, + "step": 4591 + }, + { + "epoch": 4.95, + "learning_rate": 6.701149425287356e-05, + "loss": 1.1836, + "step": 4592 + }, + { + "epoch": 4.95, + "learning_rate": 6.700431034482759e-05, + "loss": 1.1169, + "step": 4593 + }, + { + "epoch": 4.95, + "learning_rate": 6.699712643678161e-05, + "loss": 1.2528, + "step": 4594 + }, + { + "epoch": 4.95, + "learning_rate": 6.698994252873563e-05, + "loss": 1.1202, + "step": 4595 + }, + { + "epoch": 4.95, + "learning_rate": 6.698275862068965e-05, + "loss": 1.0874, + "step": 4596 + }, + { + "epoch": 4.95, + "learning_rate": 6.697557471264369e-05, + "loss": 1.1943, + "step": 4597 + }, + { + "epoch": 4.95, + "learning_rate": 6.696839080459771e-05, + "loss": 1.1611, + "step": 4598 + }, + { + "epoch": 4.96, + "learning_rate": 6.696120689655173e-05, + "loss": 1.1378, + "step": 4599 + }, + { + "epoch": 4.96, + "learning_rate": 6.695402298850575e-05, + "loss": 1.1985, + "step": 4600 + }, + { + "epoch": 4.96, + "learning_rate": 6.694683908045978e-05, + "loss": 1.0616, + "step": 4601 + }, + { + "epoch": 4.96, + "learning_rate": 6.693965517241379e-05, + "loss": 1.2466, + "step": 4602 + }, + { + "epoch": 4.96, + "learning_rate": 6.693247126436782e-05, + "loss": 1.0799, + "step": 4603 + }, + { + "epoch": 4.96, + "learning_rate": 6.692528735632184e-05, + "loss": 1.2116, + "step": 4604 + }, + { + "epoch": 4.96, + "learning_rate": 6.691810344827588e-05, + "loss": 1.1868, + "step": 4605 + }, + { + "epoch": 4.96, + "learning_rate": 6.691091954022988e-05, + "loss": 1.2331, + "step": 4606 + }, + { + "epoch": 4.96, + "learning_rate": 6.69037356321839e-05, + "loss": 1.0389, + "step": 4607 + }, + { + "epoch": 4.97, + "learning_rate": 6.689655172413794e-05, + "loss": 1.0709, + "step": 4608 + }, + { + "epoch": 4.97, + "learning_rate": 6.688936781609196e-05, + "loss": 1.2218, + "step": 4609 + }, + { + "epoch": 4.97, + "learning_rate": 6.688218390804598e-05, + "loss": 1.0939, + "step": 4610 + }, + { + "epoch": 4.97, + "learning_rate": 6.6875e-05, + "loss": 1.1217, + "step": 4611 + }, + { + "epoch": 4.97, + "learning_rate": 6.686781609195403e-05, + "loss": 1.1326, + "step": 4612 + }, + { + "epoch": 4.97, + "learning_rate": 6.686063218390804e-05, + "loss": 1.1855, + "step": 4613 + }, + { + "epoch": 4.97, + "learning_rate": 6.685344827586207e-05, + "loss": 1.1419, + "step": 4614 + }, + { + "epoch": 4.97, + "learning_rate": 6.68462643678161e-05, + "loss": 1.1795, + "step": 4615 + }, + { + "epoch": 4.97, + "learning_rate": 6.683908045977011e-05, + "loss": 1.0821, + "step": 4616 + }, + { + "epoch": 4.98, + "learning_rate": 6.683189655172413e-05, + "loss": 1.1984, + "step": 4617 + }, + { + "epoch": 4.98, + "learning_rate": 6.682471264367817e-05, + "loss": 1.2146, + "step": 4618 + }, + { + "epoch": 4.98, + "learning_rate": 6.681752873563219e-05, + "loss": 1.0315, + "step": 4619 + }, + { + "epoch": 4.98, + "learning_rate": 6.681034482758621e-05, + "loss": 1.2613, + "step": 4620 + }, + { + "epoch": 4.98, + "learning_rate": 6.680316091954023e-05, + "loss": 1.2769, + "step": 4621 + }, + { + "epoch": 4.98, + "learning_rate": 6.679597701149426e-05, + "loss": 1.1175, + "step": 4622 + }, + { + "epoch": 4.98, + "learning_rate": 6.678879310344828e-05, + "loss": 1.1, + "step": 4623 + }, + { + "epoch": 4.98, + "learning_rate": 6.67816091954023e-05, + "loss": 1.1105, + "step": 4624 + }, + { + "epoch": 4.98, + "learning_rate": 6.677442528735632e-05, + "loss": 1.213, + "step": 4625 + }, + { + "epoch": 4.98, + "learning_rate": 6.676724137931036e-05, + "loss": 1.1803, + "step": 4626 + }, + { + "epoch": 4.99, + "learning_rate": 6.676005747126437e-05, + "loss": 1.1523, + "step": 4627 + }, + { + "epoch": 4.99, + "learning_rate": 6.67528735632184e-05, + "loss": 1.2064, + "step": 4628 + }, + { + "epoch": 4.99, + "learning_rate": 6.674568965517242e-05, + "loss": 1.152, + "step": 4629 + }, + { + "epoch": 4.99, + "learning_rate": 6.673850574712644e-05, + "loss": 1.1016, + "step": 4630 + }, + { + "epoch": 4.99, + "learning_rate": 6.673132183908046e-05, + "loss": 1.0422, + "step": 4631 + }, + { + "epoch": 4.99, + "learning_rate": 6.672413793103448e-05, + "loss": 1.091, + "step": 4632 + }, + { + "epoch": 4.99, + "learning_rate": 6.671695402298851e-05, + "loss": 1.1418, + "step": 4633 + }, + { + "epoch": 4.99, + "learning_rate": 6.670977011494252e-05, + "loss": 1.1074, + "step": 4634 + }, + { + "epoch": 4.99, + "learning_rate": 6.670258620689655e-05, + "loss": 1.1647, + "step": 4635 + }, + { + "epoch": 5.0, + "learning_rate": 6.669540229885058e-05, + "loss": 1.2271, + "step": 4636 + }, + { + "epoch": 5.0, + "learning_rate": 6.66882183908046e-05, + "loss": 1.1311, + "step": 4637 + }, + { + "epoch": 5.0, + "learning_rate": 6.668103448275862e-05, + "loss": 1.0753, + "step": 4638 + }, + { + "epoch": 5.0, + "learning_rate": 6.667385057471265e-05, + "loss": 1.0922, + "step": 4639 + }, + { + "epoch": 5.0, + "learning_rate": 6.666666666666667e-05, + "loss": 1.0549, + "step": 4640 + }, + { + "epoch": 5.0, + "learning_rate": 6.665948275862069e-05, + "loss": 0.9669, + "step": 4641 + }, + { + "epoch": 5.0, + "learning_rate": 6.665229885057471e-05, + "loss": 1.0888, + "step": 4642 + }, + { + "epoch": 5.0, + "learning_rate": 6.664511494252874e-05, + "loss": 1.2059, + "step": 4643 + }, + { + "epoch": 5.0, + "learning_rate": 6.663793103448276e-05, + "loss": 1.0091, + "step": 4644 + }, + { + "epoch": 5.01, + "learning_rate": 6.663074712643679e-05, + "loss": 1.0333, + "step": 4645 + }, + { + "epoch": 5.01, + "learning_rate": 6.66235632183908e-05, + "loss": 1.0704, + "step": 4646 + }, + { + "epoch": 5.01, + "learning_rate": 6.661637931034484e-05, + "loss": 1.1597, + "step": 4647 + }, + { + "epoch": 5.01, + "learning_rate": 6.660919540229885e-05, + "loss": 0.9208, + "step": 4648 + }, + { + "epoch": 5.01, + "learning_rate": 6.660201149425288e-05, + "loss": 1.0965, + "step": 4649 + }, + { + "epoch": 5.01, + "learning_rate": 6.65948275862069e-05, + "loss": 1.0884, + "step": 4650 + }, + { + "epoch": 5.01, + "learning_rate": 6.658764367816092e-05, + "loss": 1.0456, + "step": 4651 + }, + { + "epoch": 5.01, + "learning_rate": 6.658045977011494e-05, + "loss": 1.0435, + "step": 4652 + }, + { + "epoch": 5.01, + "learning_rate": 6.657327586206897e-05, + "loss": 1.0817, + "step": 4653 + }, + { + "epoch": 5.02, + "learning_rate": 6.6566091954023e-05, + "loss": 1.1119, + "step": 4654 + }, + { + "epoch": 5.02, + "learning_rate": 6.655890804597702e-05, + "loss": 1.2482, + "step": 4655 + }, + { + "epoch": 5.02, + "learning_rate": 6.655172413793104e-05, + "loss": 1.068, + "step": 4656 + }, + { + "epoch": 5.02, + "learning_rate": 6.654454022988507e-05, + "loss": 1.0469, + "step": 4657 + }, + { + "epoch": 5.02, + "learning_rate": 6.653735632183909e-05, + "loss": 1.0946, + "step": 4658 + }, + { + "epoch": 5.02, + "learning_rate": 6.65301724137931e-05, + "loss": 1.1077, + "step": 4659 + }, + { + "epoch": 5.02, + "learning_rate": 6.652298850574713e-05, + "loss": 1.1082, + "step": 4660 + }, + { + "epoch": 5.02, + "learning_rate": 6.651580459770115e-05, + "loss": 1.1327, + "step": 4661 + }, + { + "epoch": 5.02, + "learning_rate": 6.650862068965517e-05, + "loss": 1.2847, + "step": 4662 + }, + { + "epoch": 5.02, + "learning_rate": 6.650143678160919e-05, + "loss": 1.146, + "step": 4663 + }, + { + "epoch": 5.03, + "learning_rate": 6.649425287356323e-05, + "loss": 1.0724, + "step": 4664 + }, + { + "epoch": 5.03, + "learning_rate": 6.648706896551725e-05, + "loss": 1.0341, + "step": 4665 + }, + { + "epoch": 5.03, + "learning_rate": 6.647988505747127e-05, + "loss": 1.0754, + "step": 4666 + }, + { + "epoch": 5.03, + "learning_rate": 6.647270114942529e-05, + "loss": 1.1365, + "step": 4667 + }, + { + "epoch": 5.03, + "learning_rate": 6.646551724137932e-05, + "loss": 1.1054, + "step": 4668 + }, + { + "epoch": 5.03, + "learning_rate": 6.645833333333333e-05, + "loss": 1.0983, + "step": 4669 + }, + { + "epoch": 5.03, + "learning_rate": 6.645114942528736e-05, + "loss": 1.0807, + "step": 4670 + }, + { + "epoch": 5.03, + "learning_rate": 6.644396551724138e-05, + "loss": 0.9906, + "step": 4671 + }, + { + "epoch": 5.03, + "learning_rate": 6.643678160919542e-05, + "loss": 1.0339, + "step": 4672 + }, + { + "epoch": 5.04, + "learning_rate": 6.642959770114942e-05, + "loss": 1.0063, + "step": 4673 + }, + { + "epoch": 5.04, + "learning_rate": 6.642241379310346e-05, + "loss": 0.997, + "step": 4674 + }, + { + "epoch": 5.04, + "learning_rate": 6.641522988505748e-05, + "loss": 1.182, + "step": 4675 + }, + { + "epoch": 5.04, + "learning_rate": 6.64080459770115e-05, + "loss": 1.0751, + "step": 4676 + }, + { + "epoch": 5.04, + "learning_rate": 6.640086206896552e-05, + "loss": 1.1928, + "step": 4677 + }, + { + "epoch": 5.04, + "learning_rate": 6.639367816091955e-05, + "loss": 1.1455, + "step": 4678 + }, + { + "epoch": 5.04, + "learning_rate": 6.638649425287357e-05, + "loss": 1.1105, + "step": 4679 + }, + { + "epoch": 5.04, + "learning_rate": 6.637931034482759e-05, + "loss": 0.9745, + "step": 4680 + }, + { + "epoch": 5.04, + "learning_rate": 6.637212643678161e-05, + "loss": 1.08, + "step": 4681 + }, + { + "epoch": 5.05, + "learning_rate": 6.636494252873565e-05, + "loss": 1.0517, + "step": 4682 + }, + { + "epoch": 5.05, + "learning_rate": 6.635775862068965e-05, + "loss": 1.0745, + "step": 4683 + }, + { + "epoch": 5.05, + "learning_rate": 6.635057471264367e-05, + "loss": 1.1672, + "step": 4684 + }, + { + "epoch": 5.05, + "learning_rate": 6.63433908045977e-05, + "loss": 1.1018, + "step": 4685 + }, + { + "epoch": 5.05, + "learning_rate": 6.633620689655173e-05, + "loss": 1.0135, + "step": 4686 + }, + { + "epoch": 5.05, + "learning_rate": 6.632902298850575e-05, + "loss": 1.085, + "step": 4687 + }, + { + "epoch": 5.05, + "learning_rate": 6.632183908045977e-05, + "loss": 1.0389, + "step": 4688 + }, + { + "epoch": 5.05, + "learning_rate": 6.63146551724138e-05, + "loss": 1.0663, + "step": 4689 + }, + { + "epoch": 5.05, + "learning_rate": 6.630747126436782e-05, + "loss": 1.1106, + "step": 4690 + }, + { + "epoch": 5.05, + "learning_rate": 6.630028735632184e-05, + "loss": 1.1484, + "step": 4691 + }, + { + "epoch": 5.06, + "learning_rate": 6.629310344827586e-05, + "loss": 1.0819, + "step": 4692 + }, + { + "epoch": 5.06, + "learning_rate": 6.62859195402299e-05, + "loss": 1.1441, + "step": 4693 + }, + { + "epoch": 5.06, + "learning_rate": 6.62787356321839e-05, + "loss": 1.1428, + "step": 4694 + }, + { + "epoch": 5.06, + "learning_rate": 6.627155172413794e-05, + "loss": 1.0484, + "step": 4695 + }, + { + "epoch": 5.06, + "learning_rate": 6.626436781609196e-05, + "loss": 1.0372, + "step": 4696 + }, + { + "epoch": 5.06, + "learning_rate": 6.625718390804598e-05, + "loss": 1.0454, + "step": 4697 + }, + { + "epoch": 5.06, + "learning_rate": 6.625e-05, + "loss": 1.1483, + "step": 4698 + }, + { + "epoch": 5.06, + "learning_rate": 6.624281609195403e-05, + "loss": 1.1213, + "step": 4699 + }, + { + "epoch": 5.06, + "learning_rate": 6.623563218390805e-05, + "loss": 1.116, + "step": 4700 + }, + { + "epoch": 5.07, + "learning_rate": 6.622844827586207e-05, + "loss": 1.1103, + "step": 4701 + }, + { + "epoch": 5.07, + "learning_rate": 6.622126436781609e-05, + "loss": 1.1889, + "step": 4702 + }, + { + "epoch": 5.07, + "learning_rate": 6.621408045977013e-05, + "loss": 1.1194, + "step": 4703 + }, + { + "epoch": 5.07, + "learning_rate": 6.620689655172415e-05, + "loss": 1.1361, + "step": 4704 + }, + { + "epoch": 5.07, + "learning_rate": 6.619971264367817e-05, + "loss": 1.0544, + "step": 4705 + }, + { + "epoch": 5.07, + "learning_rate": 6.619252873563219e-05, + "loss": 1.0115, + "step": 4706 + }, + { + "epoch": 5.07, + "learning_rate": 6.618534482758622e-05, + "loss": 1.1469, + "step": 4707 + }, + { + "epoch": 5.07, + "learning_rate": 6.617816091954023e-05, + "loss": 1.0385, + "step": 4708 + }, + { + "epoch": 5.07, + "learning_rate": 6.617097701149425e-05, + "loss": 1.1171, + "step": 4709 + }, + { + "epoch": 5.08, + "learning_rate": 6.616379310344828e-05, + "loss": 1.1997, + "step": 4710 + }, + { + "epoch": 5.08, + "learning_rate": 6.61566091954023e-05, + "loss": 1.1563, + "step": 4711 + }, + { + "epoch": 5.08, + "learning_rate": 6.614942528735632e-05, + "loss": 1.1056, + "step": 4712 + }, + { + "epoch": 5.08, + "learning_rate": 6.614224137931034e-05, + "loss": 1.1, + "step": 4713 + }, + { + "epoch": 5.08, + "learning_rate": 6.613505747126438e-05, + "loss": 1.0777, + "step": 4714 + }, + { + "epoch": 5.08, + "learning_rate": 6.612787356321838e-05, + "loss": 1.0392, + "step": 4715 + }, + { + "epoch": 5.08, + "learning_rate": 6.612068965517242e-05, + "loss": 1.0364, + "step": 4716 + }, + { + "epoch": 5.08, + "learning_rate": 6.611350574712644e-05, + "loss": 1.0646, + "step": 4717 + }, + { + "epoch": 5.08, + "learning_rate": 6.610632183908047e-05, + "loss": 1.0546, + "step": 4718 + }, + { + "epoch": 5.09, + "learning_rate": 6.609913793103448e-05, + "loss": 1.142, + "step": 4719 + }, + { + "epoch": 5.09, + "learning_rate": 6.609195402298851e-05, + "loss": 1.0426, + "step": 4720 + }, + { + "epoch": 5.09, + "learning_rate": 6.608477011494253e-05, + "loss": 1.1313, + "step": 4721 + }, + { + "epoch": 5.09, + "learning_rate": 6.607758620689655e-05, + "loss": 1.1909, + "step": 4722 + }, + { + "epoch": 5.09, + "learning_rate": 6.607040229885057e-05, + "loss": 1.1103, + "step": 4723 + }, + { + "epoch": 5.09, + "learning_rate": 6.606321839080461e-05, + "loss": 1.0795, + "step": 4724 + }, + { + "epoch": 5.09, + "learning_rate": 6.605603448275863e-05, + "loss": 1.1383, + "step": 4725 + }, + { + "epoch": 5.09, + "learning_rate": 6.604885057471265e-05, + "loss": 1.1249, + "step": 4726 + }, + { + "epoch": 5.09, + "learning_rate": 6.604166666666667e-05, + "loss": 1.2232, + "step": 4727 + }, + { + "epoch": 5.09, + "learning_rate": 6.60344827586207e-05, + "loss": 1.2054, + "step": 4728 + }, + { + "epoch": 5.1, + "learning_rate": 6.602729885057471e-05, + "loss": 0.9968, + "step": 4729 + }, + { + "epoch": 5.1, + "learning_rate": 6.602011494252874e-05, + "loss": 1.1168, + "step": 4730 + }, + { + "epoch": 5.1, + "learning_rate": 6.601293103448276e-05, + "loss": 1.1351, + "step": 4731 + }, + { + "epoch": 5.1, + "learning_rate": 6.600574712643678e-05, + "loss": 0.9732, + "step": 4732 + }, + { + "epoch": 5.1, + "learning_rate": 6.59985632183908e-05, + "loss": 1.0726, + "step": 4733 + }, + { + "epoch": 5.1, + "learning_rate": 6.599137931034482e-05, + "loss": 1.0049, + "step": 4734 + }, + { + "epoch": 5.1, + "learning_rate": 6.598419540229886e-05, + "loss": 0.9849, + "step": 4735 + }, + { + "epoch": 5.1, + "learning_rate": 6.597701149425288e-05, + "loss": 1.1047, + "step": 4736 + }, + { + "epoch": 5.1, + "learning_rate": 6.59698275862069e-05, + "loss": 1.1661, + "step": 4737 + }, + { + "epoch": 5.11, + "learning_rate": 6.596264367816092e-05, + "loss": 1.1022, + "step": 4738 + }, + { + "epoch": 5.11, + "learning_rate": 6.595545977011495e-05, + "loss": 1.0603, + "step": 4739 + }, + { + "epoch": 5.11, + "learning_rate": 6.594827586206896e-05, + "loss": 1.0729, + "step": 4740 + }, + { + "epoch": 5.11, + "learning_rate": 6.5941091954023e-05, + "loss": 1.0059, + "step": 4741 + }, + { + "epoch": 5.11, + "learning_rate": 6.593390804597701e-05, + "loss": 1.1558, + "step": 4742 + }, + { + "epoch": 5.11, + "learning_rate": 6.592672413793103e-05, + "loss": 1.0417, + "step": 4743 + }, + { + "epoch": 5.11, + "learning_rate": 6.591954022988505e-05, + "loss": 1.0554, + "step": 4744 + }, + { + "epoch": 5.11, + "learning_rate": 6.591235632183909e-05, + "loss": 1.0245, + "step": 4745 + }, + { + "epoch": 5.11, + "learning_rate": 6.590517241379311e-05, + "loss": 1.0183, + "step": 4746 + }, + { + "epoch": 5.12, + "learning_rate": 6.589798850574713e-05, + "loss": 1.0592, + "step": 4747 + }, + { + "epoch": 5.12, + "learning_rate": 6.589080459770115e-05, + "loss": 1.0897, + "step": 4748 + }, + { + "epoch": 5.12, + "learning_rate": 6.588362068965518e-05, + "loss": 1.0524, + "step": 4749 + }, + { + "epoch": 5.12, + "learning_rate": 6.587643678160919e-05, + "loss": 0.8895, + "step": 4750 + }, + { + "epoch": 5.12, + "eval_loss": 1.140509009361267, + "eval_runtime": 174.9554, + "eval_samples_per_second": 127.29, + "eval_steps_per_second": 0.663, + "step": 4750 + }, + { + "epoch": 5.12, + "learning_rate": 6.586925287356322e-05, + "loss": 1.1008, + "step": 4751 + }, + { + "epoch": 5.12, + "learning_rate": 6.586206896551724e-05, + "loss": 1.159, + "step": 4752 + }, + { + "epoch": 5.12, + "learning_rate": 6.585488505747128e-05, + "loss": 1.195, + "step": 4753 + }, + { + "epoch": 5.12, + "learning_rate": 6.584770114942528e-05, + "loss": 1.1056, + "step": 4754 + }, + { + "epoch": 5.12, + "learning_rate": 6.584051724137932e-05, + "loss": 1.0275, + "step": 4755 + }, + { + "epoch": 5.12, + "learning_rate": 6.583333333333334e-05, + "loss": 1.0757, + "step": 4756 + }, + { + "epoch": 5.13, + "learning_rate": 6.582614942528736e-05, + "loss": 1.0023, + "step": 4757 + }, + { + "epoch": 5.13, + "learning_rate": 6.581896551724138e-05, + "loss": 1.1313, + "step": 4758 + }, + { + "epoch": 5.13, + "learning_rate": 6.581178160919541e-05, + "loss": 0.9653, + "step": 4759 + }, + { + "epoch": 5.13, + "learning_rate": 6.580459770114943e-05, + "loss": 1.0934, + "step": 4760 + }, + { + "epoch": 5.13, + "learning_rate": 6.579741379310344e-05, + "loss": 1.1177, + "step": 4761 + }, + { + "epoch": 5.13, + "learning_rate": 6.579022988505747e-05, + "loss": 1.0865, + "step": 4762 + }, + { + "epoch": 5.13, + "learning_rate": 6.57830459770115e-05, + "loss": 0.9937, + "step": 4763 + }, + { + "epoch": 5.13, + "learning_rate": 6.577586206896551e-05, + "loss": 1.103, + "step": 4764 + }, + { + "epoch": 5.13, + "learning_rate": 6.576867816091954e-05, + "loss": 1.1589, + "step": 4765 + }, + { + "epoch": 5.14, + "learning_rate": 6.576149425287357e-05, + "loss": 1.0759, + "step": 4766 + }, + { + "epoch": 5.14, + "learning_rate": 6.575431034482759e-05, + "loss": 1.2162, + "step": 4767 + }, + { + "epoch": 5.14, + "learning_rate": 6.574712643678161e-05, + "loss": 1.1388, + "step": 4768 + }, + { + "epoch": 5.14, + "learning_rate": 6.573994252873563e-05, + "loss": 1.1968, + "step": 4769 + }, + { + "epoch": 5.14, + "learning_rate": 6.573275862068966e-05, + "loss": 1.105, + "step": 4770 + }, + { + "epoch": 5.14, + "learning_rate": 6.572557471264368e-05, + "loss": 1.0329, + "step": 4771 + }, + { + "epoch": 5.14, + "learning_rate": 6.57183908045977e-05, + "loss": 1.1663, + "step": 4772 + }, + { + "epoch": 5.14, + "learning_rate": 6.571120689655172e-05, + "loss": 1.1355, + "step": 4773 + }, + { + "epoch": 5.14, + "learning_rate": 6.570402298850576e-05, + "loss": 1.0359, + "step": 4774 + }, + { + "epoch": 5.15, + "learning_rate": 6.569683908045977e-05, + "loss": 1.1287, + "step": 4775 + }, + { + "epoch": 5.15, + "learning_rate": 6.56896551724138e-05, + "loss": 1.1151, + "step": 4776 + }, + { + "epoch": 5.15, + "learning_rate": 6.568247126436782e-05, + "loss": 1.1989, + "step": 4777 + }, + { + "epoch": 5.15, + "learning_rate": 6.567528735632184e-05, + "loss": 1.1933, + "step": 4778 + }, + { + "epoch": 5.15, + "learning_rate": 6.566810344827586e-05, + "loss": 1.0967, + "step": 4779 + }, + { + "epoch": 5.15, + "learning_rate": 6.56609195402299e-05, + "loss": 1.1857, + "step": 4780 + }, + { + "epoch": 5.15, + "learning_rate": 6.565373563218391e-05, + "loss": 1.0905, + "step": 4781 + }, + { + "epoch": 5.15, + "learning_rate": 6.564655172413793e-05, + "loss": 1.1482, + "step": 4782 + }, + { + "epoch": 5.15, + "learning_rate": 6.563936781609196e-05, + "loss": 1.1089, + "step": 4783 + }, + { + "epoch": 5.16, + "learning_rate": 6.563218390804599e-05, + "loss": 1.0082, + "step": 4784 + }, + { + "epoch": 5.16, + "learning_rate": 6.562500000000001e-05, + "loss": 1.1491, + "step": 4785 + }, + { + "epoch": 5.16, + "learning_rate": 6.561781609195402e-05, + "loss": 1.0717, + "step": 4786 + }, + { + "epoch": 5.16, + "learning_rate": 6.561063218390805e-05, + "loss": 1.1793, + "step": 4787 + }, + { + "epoch": 5.16, + "learning_rate": 6.560344827586207e-05, + "loss": 1.1604, + "step": 4788 + }, + { + "epoch": 5.16, + "learning_rate": 6.559626436781609e-05, + "loss": 1.165, + "step": 4789 + }, + { + "epoch": 5.16, + "learning_rate": 6.558908045977011e-05, + "loss": 1.0711, + "step": 4790 + }, + { + "epoch": 5.16, + "learning_rate": 6.558189655172414e-05, + "loss": 0.9446, + "step": 4791 + }, + { + "epoch": 5.16, + "learning_rate": 6.557471264367817e-05, + "loss": 1.0246, + "step": 4792 + }, + { + "epoch": 5.16, + "learning_rate": 6.556752873563219e-05, + "loss": 1.1089, + "step": 4793 + }, + { + "epoch": 5.17, + "learning_rate": 6.55603448275862e-05, + "loss": 0.9843, + "step": 4794 + }, + { + "epoch": 5.17, + "learning_rate": 6.555316091954024e-05, + "loss": 1.0757, + "step": 4795 + }, + { + "epoch": 5.17, + "learning_rate": 6.554597701149425e-05, + "loss": 1.0633, + "step": 4796 + }, + { + "epoch": 5.17, + "learning_rate": 6.553879310344828e-05, + "loss": 1.0225, + "step": 4797 + }, + { + "epoch": 5.17, + "learning_rate": 6.55316091954023e-05, + "loss": 1.1337, + "step": 4798 + }, + { + "epoch": 5.17, + "learning_rate": 6.552442528735633e-05, + "loss": 1.0839, + "step": 4799 + }, + { + "epoch": 5.17, + "learning_rate": 6.551724137931034e-05, + "loss": 1.0896, + "step": 4800 + }, + { + "epoch": 5.17, + "learning_rate": 6.551005747126438e-05, + "loss": 1.1041, + "step": 4801 + }, + { + "epoch": 5.17, + "learning_rate": 6.55028735632184e-05, + "loss": 1.1492, + "step": 4802 + }, + { + "epoch": 5.18, + "learning_rate": 6.549568965517242e-05, + "loss": 0.9914, + "step": 4803 + }, + { + "epoch": 5.18, + "learning_rate": 6.548850574712644e-05, + "loss": 1.0541, + "step": 4804 + }, + { + "epoch": 5.18, + "learning_rate": 6.548132183908047e-05, + "loss": 1.0065, + "step": 4805 + }, + { + "epoch": 5.18, + "learning_rate": 6.547413793103449e-05, + "loss": 1.0765, + "step": 4806 + }, + { + "epoch": 5.18, + "learning_rate": 6.546695402298851e-05, + "loss": 1.1851, + "step": 4807 + }, + { + "epoch": 5.18, + "learning_rate": 6.545977011494253e-05, + "loss": 1.1156, + "step": 4808 + }, + { + "epoch": 5.18, + "learning_rate": 6.545258620689656e-05, + "loss": 1.0316, + "step": 4809 + }, + { + "epoch": 5.18, + "learning_rate": 6.544540229885057e-05, + "loss": 1.1214, + "step": 4810 + }, + { + "epoch": 5.18, + "learning_rate": 6.543821839080459e-05, + "loss": 1.1426, + "step": 4811 + }, + { + "epoch": 5.19, + "learning_rate": 6.543103448275863e-05, + "loss": 1.0464, + "step": 4812 + }, + { + "epoch": 5.19, + "learning_rate": 6.542385057471265e-05, + "loss": 1.1475, + "step": 4813 + }, + { + "epoch": 5.19, + "learning_rate": 6.541666666666667e-05, + "loss": 0.9606, + "step": 4814 + }, + { + "epoch": 5.19, + "learning_rate": 6.540948275862069e-05, + "loss": 1.0563, + "step": 4815 + }, + { + "epoch": 5.19, + "learning_rate": 6.540229885057472e-05, + "loss": 1.1257, + "step": 4816 + }, + { + "epoch": 5.19, + "learning_rate": 6.539511494252874e-05, + "loss": 1.131, + "step": 4817 + }, + { + "epoch": 5.19, + "learning_rate": 6.538793103448276e-05, + "loss": 1.163, + "step": 4818 + }, + { + "epoch": 5.19, + "learning_rate": 6.538074712643678e-05, + "loss": 1.1142, + "step": 4819 + }, + { + "epoch": 5.19, + "learning_rate": 6.537356321839082e-05, + "loss": 1.1953, + "step": 4820 + }, + { + "epoch": 5.2, + "learning_rate": 6.536637931034482e-05, + "loss": 1.0292, + "step": 4821 + }, + { + "epoch": 5.2, + "learning_rate": 6.535919540229886e-05, + "loss": 1.0679, + "step": 4822 + }, + { + "epoch": 5.2, + "learning_rate": 6.535201149425288e-05, + "loss": 1.1456, + "step": 4823 + }, + { + "epoch": 5.2, + "learning_rate": 6.53448275862069e-05, + "loss": 1.1157, + "step": 4824 + }, + { + "epoch": 5.2, + "learning_rate": 6.533764367816092e-05, + "loss": 1.096, + "step": 4825 + }, + { + "epoch": 5.2, + "learning_rate": 6.533045977011495e-05, + "loss": 1.0725, + "step": 4826 + }, + { + "epoch": 5.2, + "learning_rate": 6.532327586206897e-05, + "loss": 1.11, + "step": 4827 + }, + { + "epoch": 5.2, + "learning_rate": 6.531609195402299e-05, + "loss": 0.8968, + "step": 4828 + }, + { + "epoch": 5.2, + "learning_rate": 6.530890804597701e-05, + "loss": 1.0679, + "step": 4829 + }, + { + "epoch": 5.2, + "learning_rate": 6.530172413793105e-05, + "loss": 1.0648, + "step": 4830 + }, + { + "epoch": 5.21, + "learning_rate": 6.529454022988505e-05, + "loss": 1.1277, + "step": 4831 + }, + { + "epoch": 5.21, + "learning_rate": 6.528735632183909e-05, + "loss": 1.1486, + "step": 4832 + }, + { + "epoch": 5.21, + "learning_rate": 6.528017241379311e-05, + "loss": 0.9971, + "step": 4833 + }, + { + "epoch": 5.21, + "learning_rate": 6.527298850574714e-05, + "loss": 1.0538, + "step": 4834 + }, + { + "epoch": 5.21, + "learning_rate": 6.526580459770115e-05, + "loss": 1.0343, + "step": 4835 + }, + { + "epoch": 5.21, + "learning_rate": 6.525862068965518e-05, + "loss": 1.135, + "step": 4836 + }, + { + "epoch": 5.21, + "learning_rate": 6.52514367816092e-05, + "loss": 1.1918, + "step": 4837 + }, + { + "epoch": 5.21, + "learning_rate": 6.524425287356322e-05, + "loss": 1.1189, + "step": 4838 + }, + { + "epoch": 5.21, + "learning_rate": 6.523706896551724e-05, + "loss": 1.0734, + "step": 4839 + }, + { + "epoch": 5.22, + "learning_rate": 6.522988505747126e-05, + "loss": 1.091, + "step": 4840 + }, + { + "epoch": 5.22, + "learning_rate": 6.52227011494253e-05, + "loss": 1.0669, + "step": 4841 + }, + { + "epoch": 5.22, + "learning_rate": 6.52155172413793e-05, + "loss": 1.0403, + "step": 4842 + }, + { + "epoch": 5.22, + "learning_rate": 6.520833333333334e-05, + "loss": 1.1977, + "step": 4843 + }, + { + "epoch": 5.22, + "learning_rate": 6.520114942528736e-05, + "loss": 1.0389, + "step": 4844 + }, + { + "epoch": 5.22, + "learning_rate": 6.519396551724138e-05, + "loss": 1.0123, + "step": 4845 + }, + { + "epoch": 5.22, + "learning_rate": 6.51867816091954e-05, + "loss": 1.1556, + "step": 4846 + }, + { + "epoch": 5.22, + "learning_rate": 6.517959770114943e-05, + "loss": 1.1226, + "step": 4847 + }, + { + "epoch": 5.22, + "learning_rate": 6.517241379310345e-05, + "loss": 1.0254, + "step": 4848 + }, + { + "epoch": 5.23, + "learning_rate": 6.516522988505747e-05, + "loss": 1.1024, + "step": 4849 + }, + { + "epoch": 5.23, + "learning_rate": 6.515804597701149e-05, + "loss": 1.2536, + "step": 4850 + }, + { + "epoch": 5.23, + "learning_rate": 6.515086206896553e-05, + "loss": 1.0937, + "step": 4851 + }, + { + "epoch": 5.23, + "learning_rate": 6.514367816091955e-05, + "loss": 1.0049, + "step": 4852 + }, + { + "epoch": 5.23, + "learning_rate": 6.513649425287357e-05, + "loss": 1.1507, + "step": 4853 + }, + { + "epoch": 5.23, + "learning_rate": 6.512931034482759e-05, + "loss": 1.0538, + "step": 4854 + }, + { + "epoch": 5.23, + "learning_rate": 6.512212643678162e-05, + "loss": 1.1726, + "step": 4855 + }, + { + "epoch": 5.23, + "learning_rate": 6.511494252873563e-05, + "loss": 1.1382, + "step": 4856 + }, + { + "epoch": 5.23, + "learning_rate": 6.510775862068966e-05, + "loss": 1.1249, + "step": 4857 + }, + { + "epoch": 5.23, + "learning_rate": 6.510057471264368e-05, + "loss": 1.0358, + "step": 4858 + }, + { + "epoch": 5.24, + "learning_rate": 6.50933908045977e-05, + "loss": 1.1514, + "step": 4859 + }, + { + "epoch": 5.24, + "learning_rate": 6.508620689655172e-05, + "loss": 0.9942, + "step": 4860 + }, + { + "epoch": 5.24, + "learning_rate": 6.507902298850576e-05, + "loss": 1.0105, + "step": 4861 + }, + { + "epoch": 5.24, + "learning_rate": 6.507183908045978e-05, + "loss": 1.021, + "step": 4862 + }, + { + "epoch": 5.24, + "learning_rate": 6.506465517241378e-05, + "loss": 1.0244, + "step": 4863 + }, + { + "epoch": 5.24, + "learning_rate": 6.505747126436782e-05, + "loss": 0.9483, + "step": 4864 + }, + { + "epoch": 5.24, + "learning_rate": 6.505028735632184e-05, + "loss": 1.1946, + "step": 4865 + }, + { + "epoch": 5.24, + "learning_rate": 6.504310344827587e-05, + "loss": 0.9121, + "step": 4866 + }, + { + "epoch": 5.24, + "learning_rate": 6.503591954022988e-05, + "loss": 1.1466, + "step": 4867 + }, + { + "epoch": 5.25, + "learning_rate": 6.502873563218391e-05, + "loss": 1.0901, + "step": 4868 + }, + { + "epoch": 5.25, + "learning_rate": 6.502155172413793e-05, + "loss": 1.0447, + "step": 4869 + }, + { + "epoch": 5.25, + "learning_rate": 6.501436781609195e-05, + "loss": 1.1659, + "step": 4870 + }, + { + "epoch": 5.25, + "learning_rate": 6.500718390804597e-05, + "loss": 0.9779, + "step": 4871 + }, + { + "epoch": 5.25, + "learning_rate": 6.500000000000001e-05, + "loss": 1.0591, + "step": 4872 + }, + { + "epoch": 5.25, + "learning_rate": 6.499281609195403e-05, + "loss": 1.0498, + "step": 4873 + }, + { + "epoch": 5.25, + "learning_rate": 6.498563218390805e-05, + "loss": 0.9905, + "step": 4874 + }, + { + "epoch": 5.25, + "learning_rate": 6.497844827586207e-05, + "loss": 1.1159, + "step": 4875 + }, + { + "epoch": 5.25, + "learning_rate": 6.49712643678161e-05, + "loss": 1.1929, + "step": 4876 + }, + { + "epoch": 5.26, + "learning_rate": 6.496408045977011e-05, + "loss": 1.0016, + "step": 4877 + }, + { + "epoch": 5.26, + "learning_rate": 6.495689655172414e-05, + "loss": 1.167, + "step": 4878 + }, + { + "epoch": 5.26, + "learning_rate": 6.494971264367816e-05, + "loss": 1.038, + "step": 4879 + }, + { + "epoch": 5.26, + "learning_rate": 6.49425287356322e-05, + "loss": 1.0375, + "step": 4880 + }, + { + "epoch": 5.26, + "learning_rate": 6.49353448275862e-05, + "loss": 1.1068, + "step": 4881 + }, + { + "epoch": 5.26, + "learning_rate": 6.492816091954024e-05, + "loss": 1.0441, + "step": 4882 + }, + { + "epoch": 5.26, + "learning_rate": 6.492097701149426e-05, + "loss": 1.0762, + "step": 4883 + }, + { + "epoch": 5.26, + "learning_rate": 6.491379310344828e-05, + "loss": 1.0352, + "step": 4884 + }, + { + "epoch": 5.26, + "learning_rate": 6.49066091954023e-05, + "loss": 1.1727, + "step": 4885 + }, + { + "epoch": 5.27, + "learning_rate": 6.489942528735633e-05, + "loss": 1.1214, + "step": 4886 + }, + { + "epoch": 5.27, + "learning_rate": 6.489224137931035e-05, + "loss": 1.0834, + "step": 4887 + }, + { + "epoch": 5.27, + "learning_rate": 6.488505747126436e-05, + "loss": 1.0087, + "step": 4888 + }, + { + "epoch": 5.27, + "learning_rate": 6.48778735632184e-05, + "loss": 0.9547, + "step": 4889 + }, + { + "epoch": 5.27, + "learning_rate": 6.487068965517241e-05, + "loss": 1.2315, + "step": 4890 + }, + { + "epoch": 5.27, + "learning_rate": 6.486350574712643e-05, + "loss": 1.0568, + "step": 4891 + }, + { + "epoch": 5.27, + "learning_rate": 6.485632183908045e-05, + "loss": 1.1086, + "step": 4892 + }, + { + "epoch": 5.27, + "learning_rate": 6.484913793103449e-05, + "loss": 1.1209, + "step": 4893 + }, + { + "epoch": 5.27, + "learning_rate": 6.484195402298851e-05, + "loss": 1.2878, + "step": 4894 + }, + { + "epoch": 5.27, + "learning_rate": 6.483477011494253e-05, + "loss": 0.9414, + "step": 4895 + }, + { + "epoch": 5.28, + "learning_rate": 6.482758620689655e-05, + "loss": 1.1104, + "step": 4896 + }, + { + "epoch": 5.28, + "learning_rate": 6.482040229885058e-05, + "loss": 1.1693, + "step": 4897 + }, + { + "epoch": 5.28, + "learning_rate": 6.48132183908046e-05, + "loss": 1.1971, + "step": 4898 + }, + { + "epoch": 5.28, + "learning_rate": 6.480603448275862e-05, + "loss": 1.2284, + "step": 4899 + }, + { + "epoch": 5.28, + "learning_rate": 6.479885057471264e-05, + "loss": 1.1142, + "step": 4900 + }, + { + "epoch": 5.28, + "learning_rate": 6.479166666666668e-05, + "loss": 1.2207, + "step": 4901 + }, + { + "epoch": 5.28, + "learning_rate": 6.478448275862069e-05, + "loss": 1.1026, + "step": 4902 + }, + { + "epoch": 5.28, + "learning_rate": 6.477729885057472e-05, + "loss": 1.1226, + "step": 4903 + }, + { + "epoch": 5.28, + "learning_rate": 6.477011494252874e-05, + "loss": 1.0852, + "step": 4904 + }, + { + "epoch": 5.29, + "learning_rate": 6.476293103448276e-05, + "loss": 1.095, + "step": 4905 + }, + { + "epoch": 5.29, + "learning_rate": 6.475574712643678e-05, + "loss": 0.947, + "step": 4906 + }, + { + "epoch": 5.29, + "learning_rate": 6.474856321839081e-05, + "loss": 1.0135, + "step": 4907 + }, + { + "epoch": 5.29, + "learning_rate": 6.474137931034483e-05, + "loss": 1.1627, + "step": 4908 + }, + { + "epoch": 5.29, + "learning_rate": 6.473419540229885e-05, + "loss": 1.0577, + "step": 4909 + }, + { + "epoch": 5.29, + "learning_rate": 6.472701149425287e-05, + "loss": 0.9884, + "step": 4910 + }, + { + "epoch": 5.29, + "learning_rate": 6.471982758620691e-05, + "loss": 1.1594, + "step": 4911 + }, + { + "epoch": 5.29, + "learning_rate": 6.471264367816093e-05, + "loss": 1.0622, + "step": 4912 + }, + { + "epoch": 5.29, + "learning_rate": 6.470545977011494e-05, + "loss": 1.127, + "step": 4913 + }, + { + "epoch": 5.3, + "learning_rate": 6.469827586206897e-05, + "loss": 1.0877, + "step": 4914 + }, + { + "epoch": 5.3, + "learning_rate": 6.469109195402299e-05, + "loss": 1.0667, + "step": 4915 + }, + { + "epoch": 5.3, + "learning_rate": 6.468390804597701e-05, + "loss": 1.1516, + "step": 4916 + }, + { + "epoch": 5.3, + "learning_rate": 6.467672413793103e-05, + "loss": 1.1803, + "step": 4917 + }, + { + "epoch": 5.3, + "learning_rate": 6.466954022988506e-05, + "loss": 1.0038, + "step": 4918 + }, + { + "epoch": 5.3, + "learning_rate": 6.466235632183908e-05, + "loss": 1.0444, + "step": 4919 + }, + { + "epoch": 5.3, + "learning_rate": 6.46551724137931e-05, + "loss": 1.0722, + "step": 4920 + }, + { + "epoch": 5.3, + "learning_rate": 6.464798850574713e-05, + "loss": 1.2137, + "step": 4921 + }, + { + "epoch": 5.3, + "learning_rate": 6.464080459770116e-05, + "loss": 1.2023, + "step": 4922 + }, + { + "epoch": 5.3, + "learning_rate": 6.463362068965517e-05, + "loss": 1.1669, + "step": 4923 + }, + { + "epoch": 5.31, + "learning_rate": 6.46264367816092e-05, + "loss": 1.2369, + "step": 4924 + }, + { + "epoch": 5.31, + "learning_rate": 6.461925287356322e-05, + "loss": 1.1635, + "step": 4925 + }, + { + "epoch": 5.31, + "learning_rate": 6.461206896551724e-05, + "loss": 1.0516, + "step": 4926 + }, + { + "epoch": 5.31, + "learning_rate": 6.460488505747126e-05, + "loss": 1.0621, + "step": 4927 + }, + { + "epoch": 5.31, + "learning_rate": 6.45977011494253e-05, + "loss": 1.1117, + "step": 4928 + }, + { + "epoch": 5.31, + "learning_rate": 6.459051724137932e-05, + "loss": 1.0742, + "step": 4929 + }, + { + "epoch": 5.31, + "learning_rate": 6.458333333333334e-05, + "loss": 1.0259, + "step": 4930 + }, + { + "epoch": 5.31, + "learning_rate": 6.457614942528736e-05, + "loss": 1.1304, + "step": 4931 + }, + { + "epoch": 5.31, + "learning_rate": 6.456896551724139e-05, + "loss": 1.2319, + "step": 4932 + }, + { + "epoch": 5.32, + "learning_rate": 6.456178160919541e-05, + "loss": 1.0291, + "step": 4933 + }, + { + "epoch": 5.32, + "learning_rate": 6.455459770114943e-05, + "loss": 1.1183, + "step": 4934 + }, + { + "epoch": 5.32, + "learning_rate": 6.454741379310345e-05, + "loss": 1.0007, + "step": 4935 + }, + { + "epoch": 5.32, + "learning_rate": 6.454022988505748e-05, + "loss": 1.0941, + "step": 4936 + }, + { + "epoch": 5.32, + "learning_rate": 6.453304597701149e-05, + "loss": 0.9552, + "step": 4937 + }, + { + "epoch": 5.32, + "learning_rate": 6.452586206896553e-05, + "loss": 1.0407, + "step": 4938 + }, + { + "epoch": 5.32, + "learning_rate": 6.451867816091955e-05, + "loss": 1.1499, + "step": 4939 + }, + { + "epoch": 5.32, + "learning_rate": 6.451149425287357e-05, + "loss": 1.0098, + "step": 4940 + }, + { + "epoch": 5.32, + "learning_rate": 6.450431034482759e-05, + "loss": 1.0876, + "step": 4941 + }, + { + "epoch": 5.33, + "learning_rate": 6.44971264367816e-05, + "loss": 1.0765, + "step": 4942 + }, + { + "epoch": 5.33, + "learning_rate": 6.448994252873564e-05, + "loss": 1.1682, + "step": 4943 + }, + { + "epoch": 5.33, + "learning_rate": 6.448275862068965e-05, + "loss": 1.1674, + "step": 4944 + }, + { + "epoch": 5.33, + "learning_rate": 6.447557471264368e-05, + "loss": 0.8806, + "step": 4945 + }, + { + "epoch": 5.33, + "learning_rate": 6.44683908045977e-05, + "loss": 1.0342, + "step": 4946 + }, + { + "epoch": 5.33, + "learning_rate": 6.446120689655174e-05, + "loss": 1.1635, + "step": 4947 + }, + { + "epoch": 5.33, + "learning_rate": 6.445402298850574e-05, + "loss": 1.1994, + "step": 4948 + }, + { + "epoch": 5.33, + "learning_rate": 6.444683908045978e-05, + "loss": 1.1388, + "step": 4949 + }, + { + "epoch": 5.33, + "learning_rate": 6.44396551724138e-05, + "loss": 1.1057, + "step": 4950 + }, + { + "epoch": 5.34, + "learning_rate": 6.443247126436782e-05, + "loss": 1.1703, + "step": 4951 + }, + { + "epoch": 5.34, + "learning_rate": 6.442528735632184e-05, + "loss": 1.1037, + "step": 4952 + }, + { + "epoch": 5.34, + "learning_rate": 6.441810344827587e-05, + "loss": 1.1942, + "step": 4953 + }, + { + "epoch": 5.34, + "learning_rate": 6.441091954022989e-05, + "loss": 1.0582, + "step": 4954 + }, + { + "epoch": 5.34, + "learning_rate": 6.440373563218391e-05, + "loss": 1.1744, + "step": 4955 + }, + { + "epoch": 5.34, + "learning_rate": 6.439655172413793e-05, + "loss": 0.9553, + "step": 4956 + }, + { + "epoch": 5.34, + "learning_rate": 6.438936781609197e-05, + "loss": 1.1064, + "step": 4957 + }, + { + "epoch": 5.34, + "learning_rate": 6.438218390804597e-05, + "loss": 1.124, + "step": 4958 + }, + { + "epoch": 5.34, + "learning_rate": 6.4375e-05, + "loss": 1.0657, + "step": 4959 + }, + { + "epoch": 5.34, + "learning_rate": 6.436781609195403e-05, + "loss": 1.1704, + "step": 4960 + }, + { + "epoch": 5.35, + "learning_rate": 6.436063218390806e-05, + "loss": 0.9817, + "step": 4961 + }, + { + "epoch": 5.35, + "learning_rate": 6.435344827586207e-05, + "loss": 1.0851, + "step": 4962 + }, + { + "epoch": 5.35, + "learning_rate": 6.43462643678161e-05, + "loss": 0.9907, + "step": 4963 + }, + { + "epoch": 5.35, + "learning_rate": 6.433908045977012e-05, + "loss": 1.0712, + "step": 4964 + }, + { + "epoch": 5.35, + "learning_rate": 6.433189655172414e-05, + "loss": 1.117, + "step": 4965 + }, + { + "epoch": 5.35, + "learning_rate": 6.432471264367816e-05, + "loss": 0.9877, + "step": 4966 + }, + { + "epoch": 5.35, + "learning_rate": 6.431752873563218e-05, + "loss": 1.1708, + "step": 4967 + }, + { + "epoch": 5.35, + "learning_rate": 6.431034482758622e-05, + "loss": 0.9473, + "step": 4968 + }, + { + "epoch": 5.35, + "learning_rate": 6.430316091954022e-05, + "loss": 1.1505, + "step": 4969 + }, + { + "epoch": 5.36, + "learning_rate": 6.429597701149426e-05, + "loss": 1.1189, + "step": 4970 + }, + { + "epoch": 5.36, + "learning_rate": 6.428879310344828e-05, + "loss": 1.0979, + "step": 4971 + }, + { + "epoch": 5.36, + "learning_rate": 6.42816091954023e-05, + "loss": 1.0542, + "step": 4972 + }, + { + "epoch": 5.36, + "learning_rate": 6.427442528735632e-05, + "loss": 1.0687, + "step": 4973 + }, + { + "epoch": 5.36, + "learning_rate": 6.426724137931035e-05, + "loss": 1.1049, + "step": 4974 + }, + { + "epoch": 5.36, + "learning_rate": 6.426005747126437e-05, + "loss": 1.1069, + "step": 4975 + }, + { + "epoch": 5.36, + "learning_rate": 6.425287356321839e-05, + "loss": 1.0137, + "step": 4976 + }, + { + "epoch": 5.36, + "learning_rate": 6.424568965517241e-05, + "loss": 1.0302, + "step": 4977 + }, + { + "epoch": 5.36, + "learning_rate": 6.423850574712645e-05, + "loss": 1.1164, + "step": 4978 + }, + { + "epoch": 5.37, + "learning_rate": 6.423132183908047e-05, + "loss": 1.0909, + "step": 4979 + }, + { + "epoch": 5.37, + "learning_rate": 6.422413793103449e-05, + "loss": 1.1021, + "step": 4980 + }, + { + "epoch": 5.37, + "learning_rate": 6.421695402298851e-05, + "loss": 1.1092, + "step": 4981 + }, + { + "epoch": 5.37, + "learning_rate": 6.420977011494254e-05, + "loss": 1.0974, + "step": 4982 + }, + { + "epoch": 5.37, + "learning_rate": 6.420258620689655e-05, + "loss": 1.1679, + "step": 4983 + }, + { + "epoch": 5.37, + "learning_rate": 6.419540229885058e-05, + "loss": 1.0459, + "step": 4984 + }, + { + "epoch": 5.37, + "learning_rate": 6.41882183908046e-05, + "loss": 1.0952, + "step": 4985 + }, + { + "epoch": 5.37, + "learning_rate": 6.418103448275862e-05, + "loss": 1.029, + "step": 4986 + }, + { + "epoch": 5.37, + "learning_rate": 6.417385057471264e-05, + "loss": 1.2097, + "step": 4987 + }, + { + "epoch": 5.38, + "learning_rate": 6.416666666666668e-05, + "loss": 1.0732, + "step": 4988 + }, + { + "epoch": 5.38, + "learning_rate": 6.41594827586207e-05, + "loss": 1.1613, + "step": 4989 + }, + { + "epoch": 5.38, + "learning_rate": 6.41522988505747e-05, + "loss": 1.0576, + "step": 4990 + }, + { + "epoch": 5.38, + "learning_rate": 6.414511494252874e-05, + "loss": 1.0459, + "step": 4991 + }, + { + "epoch": 5.38, + "learning_rate": 6.413793103448276e-05, + "loss": 1.1428, + "step": 4992 + }, + { + "epoch": 5.38, + "learning_rate": 6.413074712643679e-05, + "loss": 1.0187, + "step": 4993 + }, + { + "epoch": 5.38, + "learning_rate": 6.41235632183908e-05, + "loss": 1.1501, + "step": 4994 + }, + { + "epoch": 5.38, + "learning_rate": 6.411637931034483e-05, + "loss": 1.0749, + "step": 4995 + }, + { + "epoch": 5.38, + "learning_rate": 6.410919540229885e-05, + "loss": 1.0077, + "step": 4996 + }, + { + "epoch": 5.38, + "learning_rate": 6.410201149425287e-05, + "loss": 0.9493, + "step": 4997 + }, + { + "epoch": 5.39, + "learning_rate": 6.40948275862069e-05, + "loss": 1.2201, + "step": 4998 + }, + { + "epoch": 5.39, + "learning_rate": 6.408764367816093e-05, + "loss": 1.178, + "step": 4999 + }, + { + "epoch": 5.39, + "learning_rate": 6.408045977011495e-05, + "loss": 1.0481, + "step": 5000 + }, + { + "epoch": 5.39, + "eval_loss": 1.1328884363174438, + "eval_runtime": 174.9271, + "eval_samples_per_second": 127.31, + "eval_steps_per_second": 0.663, + "step": 5000 + }, + { + "epoch": 5.39, + "learning_rate": 6.407327586206897e-05, + "loss": 1.0387, + "step": 5001 + }, + { + "epoch": 5.39, + "learning_rate": 6.406609195402299e-05, + "loss": 1.165, + "step": 5002 + }, + { + "epoch": 5.39, + "learning_rate": 6.405890804597702e-05, + "loss": 0.9785, + "step": 5003 + }, + { + "epoch": 5.39, + "learning_rate": 6.405172413793103e-05, + "loss": 1.0304, + "step": 5004 + }, + { + "epoch": 5.39, + "learning_rate": 6.404454022988506e-05, + "loss": 1.1316, + "step": 5005 + }, + { + "epoch": 5.39, + "learning_rate": 6.403735632183908e-05, + "loss": 1.1274, + "step": 5006 + }, + { + "epoch": 5.4, + "learning_rate": 6.40301724137931e-05, + "loss": 0.996, + "step": 5007 + }, + { + "epoch": 5.4, + "learning_rate": 6.402298850574712e-05, + "loss": 0.9668, + "step": 5008 + }, + { + "epoch": 5.4, + "learning_rate": 6.401580459770116e-05, + "loss": 1.1472, + "step": 5009 + }, + { + "epoch": 5.4, + "learning_rate": 6.400862068965518e-05, + "loss": 1.1809, + "step": 5010 + }, + { + "epoch": 5.4, + "learning_rate": 6.40014367816092e-05, + "loss": 1.0444, + "step": 5011 + }, + { + "epoch": 5.4, + "learning_rate": 6.399425287356322e-05, + "loss": 1.0631, + "step": 5012 + }, + { + "epoch": 5.4, + "learning_rate": 6.398706896551725e-05, + "loss": 1.1078, + "step": 5013 + }, + { + "epoch": 5.4, + "learning_rate": 6.397988505747127e-05, + "loss": 0.9936, + "step": 5014 + }, + { + "epoch": 5.4, + "learning_rate": 6.39727011494253e-05, + "loss": 1.0368, + "step": 5015 + }, + { + "epoch": 5.41, + "learning_rate": 6.396551724137931e-05, + "loss": 0.9484, + "step": 5016 + }, + { + "epoch": 5.41, + "learning_rate": 6.395833333333333e-05, + "loss": 1.1763, + "step": 5017 + }, + { + "epoch": 5.41, + "learning_rate": 6.395114942528735e-05, + "loss": 1.0738, + "step": 5018 + }, + { + "epoch": 5.41, + "learning_rate": 6.394396551724137e-05, + "loss": 1.1237, + "step": 5019 + }, + { + "epoch": 5.41, + "learning_rate": 6.393678160919541e-05, + "loss": 1.0079, + "step": 5020 + }, + { + "epoch": 5.41, + "learning_rate": 6.392959770114943e-05, + "loss": 1.1145, + "step": 5021 + }, + { + "epoch": 5.41, + "learning_rate": 6.392241379310345e-05, + "loss": 1.1018, + "step": 5022 + }, + { + "epoch": 5.41, + "learning_rate": 6.391522988505747e-05, + "loss": 1.1597, + "step": 5023 + }, + { + "epoch": 5.41, + "learning_rate": 6.39080459770115e-05, + "loss": 1.1025, + "step": 5024 + }, + { + "epoch": 5.41, + "learning_rate": 6.390086206896552e-05, + "loss": 1.1021, + "step": 5025 + }, + { + "epoch": 5.42, + "learning_rate": 6.389367816091954e-05, + "loss": 1.2156, + "step": 5026 + }, + { + "epoch": 5.42, + "learning_rate": 6.388649425287356e-05, + "loss": 1.0726, + "step": 5027 + }, + { + "epoch": 5.42, + "learning_rate": 6.38793103448276e-05, + "loss": 1.0283, + "step": 5028 + }, + { + "epoch": 5.42, + "learning_rate": 6.38721264367816e-05, + "loss": 1.1549, + "step": 5029 + }, + { + "epoch": 5.42, + "learning_rate": 6.386494252873564e-05, + "loss": 1.0342, + "step": 5030 + }, + { + "epoch": 5.42, + "learning_rate": 6.385775862068966e-05, + "loss": 1.0164, + "step": 5031 + }, + { + "epoch": 5.42, + "learning_rate": 6.385057471264368e-05, + "loss": 1.1206, + "step": 5032 + }, + { + "epoch": 5.42, + "learning_rate": 6.38433908045977e-05, + "loss": 1.116, + "step": 5033 + }, + { + "epoch": 5.42, + "learning_rate": 6.383620689655173e-05, + "loss": 1.0977, + "step": 5034 + }, + { + "epoch": 5.43, + "learning_rate": 6.382902298850575e-05, + "loss": 1.1162, + "step": 5035 + }, + { + "epoch": 5.43, + "learning_rate": 6.382183908045977e-05, + "loss": 1.1401, + "step": 5036 + }, + { + "epoch": 5.43, + "learning_rate": 6.38146551724138e-05, + "loss": 1.092, + "step": 5037 + }, + { + "epoch": 5.43, + "learning_rate": 6.380747126436783e-05, + "loss": 1.221, + "step": 5038 + }, + { + "epoch": 5.43, + "learning_rate": 6.380028735632184e-05, + "loss": 1.0799, + "step": 5039 + }, + { + "epoch": 5.43, + "learning_rate": 6.379310344827587e-05, + "loss": 1.0501, + "step": 5040 + }, + { + "epoch": 5.43, + "learning_rate": 6.378591954022989e-05, + "loss": 1.1486, + "step": 5041 + }, + { + "epoch": 5.43, + "learning_rate": 6.377873563218391e-05, + "loss": 1.0322, + "step": 5042 + }, + { + "epoch": 5.43, + "learning_rate": 6.377155172413793e-05, + "loss": 1.069, + "step": 5043 + }, + { + "epoch": 5.44, + "learning_rate": 6.376436781609195e-05, + "loss": 0.9251, + "step": 5044 + }, + { + "epoch": 5.44, + "learning_rate": 6.375718390804598e-05, + "loss": 1.1834, + "step": 5045 + }, + { + "epoch": 5.44, + "learning_rate": 6.375e-05, + "loss": 1.1405, + "step": 5046 + }, + { + "epoch": 5.44, + "learning_rate": 6.374281609195402e-05, + "loss": 1.1892, + "step": 5047 + }, + { + "epoch": 5.44, + "learning_rate": 6.373563218390805e-05, + "loss": 0.9881, + "step": 5048 + }, + { + "epoch": 5.44, + "learning_rate": 6.372844827586208e-05, + "loss": 0.9464, + "step": 5049 + }, + { + "epoch": 5.44, + "learning_rate": 6.372126436781609e-05, + "loss": 1.0992, + "step": 5050 + }, + { + "epoch": 5.44, + "learning_rate": 6.371408045977012e-05, + "loss": 0.9588, + "step": 5051 + }, + { + "epoch": 5.44, + "learning_rate": 6.370689655172414e-05, + "loss": 1.05, + "step": 5052 + }, + { + "epoch": 5.45, + "learning_rate": 6.369971264367816e-05, + "loss": 1.1034, + "step": 5053 + }, + { + "epoch": 5.45, + "learning_rate": 6.369252873563218e-05, + "loss": 1.1408, + "step": 5054 + }, + { + "epoch": 5.45, + "learning_rate": 6.368534482758621e-05, + "loss": 1.0318, + "step": 5055 + }, + { + "epoch": 5.45, + "learning_rate": 6.367816091954023e-05, + "loss": 1.0829, + "step": 5056 + }, + { + "epoch": 5.45, + "learning_rate": 6.367097701149426e-05, + "loss": 0.9584, + "step": 5057 + }, + { + "epoch": 5.45, + "learning_rate": 6.366379310344828e-05, + "loss": 1.1267, + "step": 5058 + }, + { + "epoch": 5.45, + "learning_rate": 6.365660919540231e-05, + "loss": 0.9493, + "step": 5059 + }, + { + "epoch": 5.45, + "learning_rate": 6.364942528735633e-05, + "loss": 1.0805, + "step": 5060 + }, + { + "epoch": 5.45, + "learning_rate": 6.364224137931035e-05, + "loss": 1.2106, + "step": 5061 + }, + { + "epoch": 5.45, + "learning_rate": 6.363505747126437e-05, + "loss": 0.9561, + "step": 5062 + }, + { + "epoch": 5.46, + "learning_rate": 6.36278735632184e-05, + "loss": 1.08, + "step": 5063 + }, + { + "epoch": 5.46, + "learning_rate": 6.362068965517241e-05, + "loss": 1.185, + "step": 5064 + }, + { + "epoch": 5.46, + "learning_rate": 6.361350574712644e-05, + "loss": 1.06, + "step": 5065 + }, + { + "epoch": 5.46, + "learning_rate": 6.360632183908047e-05, + "loss": 1.0116, + "step": 5066 + }, + { + "epoch": 5.46, + "learning_rate": 6.359913793103449e-05, + "loss": 1.2167, + "step": 5067 + }, + { + "epoch": 5.46, + "learning_rate": 6.35919540229885e-05, + "loss": 1.1927, + "step": 5068 + }, + { + "epoch": 5.46, + "learning_rate": 6.358477011494253e-05, + "loss": 1.0747, + "step": 5069 + }, + { + "epoch": 5.46, + "learning_rate": 6.357758620689656e-05, + "loss": 0.9798, + "step": 5070 + }, + { + "epoch": 5.46, + "learning_rate": 6.357040229885057e-05, + "loss": 1.0171, + "step": 5071 + }, + { + "epoch": 5.47, + "learning_rate": 6.35632183908046e-05, + "loss": 1.1023, + "step": 5072 + }, + { + "epoch": 5.47, + "learning_rate": 6.355603448275862e-05, + "loss": 1.0526, + "step": 5073 + }, + { + "epoch": 5.47, + "learning_rate": 6.354885057471265e-05, + "loss": 1.0419, + "step": 5074 + }, + { + "epoch": 5.47, + "learning_rate": 6.354166666666666e-05, + "loss": 1.0158, + "step": 5075 + }, + { + "epoch": 5.47, + "learning_rate": 6.35344827586207e-05, + "loss": 0.9852, + "step": 5076 + }, + { + "epoch": 5.47, + "learning_rate": 6.352729885057472e-05, + "loss": 1.0938, + "step": 5077 + }, + { + "epoch": 5.47, + "learning_rate": 6.352011494252874e-05, + "loss": 1.0476, + "step": 5078 + }, + { + "epoch": 5.47, + "learning_rate": 6.351293103448276e-05, + "loss": 1.1278, + "step": 5079 + }, + { + "epoch": 5.47, + "learning_rate": 6.350574712643679e-05, + "loss": 1.1292, + "step": 5080 + }, + { + "epoch": 5.48, + "learning_rate": 6.349856321839081e-05, + "loss": 1.1887, + "step": 5081 + }, + { + "epoch": 5.48, + "learning_rate": 6.349137931034483e-05, + "loss": 1.0806, + "step": 5082 + }, + { + "epoch": 5.48, + "learning_rate": 6.348419540229885e-05, + "loss": 1.1052, + "step": 5083 + }, + { + "epoch": 5.48, + "learning_rate": 6.347701149425289e-05, + "loss": 1.2432, + "step": 5084 + }, + { + "epoch": 5.48, + "learning_rate": 6.346982758620689e-05, + "loss": 1.0821, + "step": 5085 + }, + { + "epoch": 5.48, + "learning_rate": 6.346264367816093e-05, + "loss": 1.0508, + "step": 5086 + }, + { + "epoch": 5.48, + "learning_rate": 6.345545977011495e-05, + "loss": 1.0394, + "step": 5087 + }, + { + "epoch": 5.48, + "learning_rate": 6.344827586206897e-05, + "loss": 1.0659, + "step": 5088 + }, + { + "epoch": 5.48, + "learning_rate": 6.344109195402299e-05, + "loss": 1.1056, + "step": 5089 + }, + { + "epoch": 5.48, + "learning_rate": 6.343390804597702e-05, + "loss": 1.1724, + "step": 5090 + }, + { + "epoch": 5.49, + "learning_rate": 6.342672413793104e-05, + "loss": 0.9551, + "step": 5091 + }, + { + "epoch": 5.49, + "learning_rate": 6.341954022988506e-05, + "loss": 1.0109, + "step": 5092 + }, + { + "epoch": 5.49, + "learning_rate": 6.341235632183908e-05, + "loss": 1.0286, + "step": 5093 + }, + { + "epoch": 5.49, + "learning_rate": 6.34051724137931e-05, + "loss": 1.1774, + "step": 5094 + }, + { + "epoch": 5.49, + "learning_rate": 6.339798850574714e-05, + "loss": 1.1403, + "step": 5095 + }, + { + "epoch": 5.49, + "learning_rate": 6.339080459770114e-05, + "loss": 1.0925, + "step": 5096 + }, + { + "epoch": 5.49, + "learning_rate": 6.338362068965518e-05, + "loss": 1.1542, + "step": 5097 + }, + { + "epoch": 5.49, + "learning_rate": 6.33764367816092e-05, + "loss": 1.0684, + "step": 5098 + }, + { + "epoch": 5.49, + "learning_rate": 6.336925287356322e-05, + "loss": 1.1977, + "step": 5099 + }, + { + "epoch": 5.5, + "learning_rate": 6.336206896551724e-05, + "loss": 0.9802, + "step": 5100 + }, + { + "epoch": 5.5, + "learning_rate": 6.335488505747127e-05, + "loss": 1.0409, + "step": 5101 + }, + { + "epoch": 5.5, + "learning_rate": 6.334770114942529e-05, + "loss": 1.2124, + "step": 5102 + }, + { + "epoch": 5.5, + "learning_rate": 6.334051724137931e-05, + "loss": 1.0451, + "step": 5103 + }, + { + "epoch": 5.5, + "learning_rate": 6.333333333333333e-05, + "loss": 1.1058, + "step": 5104 + }, + { + "epoch": 5.5, + "learning_rate": 6.332614942528737e-05, + "loss": 1.133, + "step": 5105 + }, + { + "epoch": 5.5, + "learning_rate": 6.331896551724139e-05, + "loss": 1.1451, + "step": 5106 + }, + { + "epoch": 5.5, + "learning_rate": 6.331178160919541e-05, + "loss": 1.2712, + "step": 5107 + }, + { + "epoch": 5.5, + "learning_rate": 6.330459770114943e-05, + "loss": 1.1043, + "step": 5108 + }, + { + "epoch": 5.51, + "learning_rate": 6.329741379310346e-05, + "loss": 1.1174, + "step": 5109 + }, + { + "epoch": 5.51, + "learning_rate": 6.329022988505747e-05, + "loss": 1.0825, + "step": 5110 + }, + { + "epoch": 5.51, + "learning_rate": 6.32830459770115e-05, + "loss": 0.9904, + "step": 5111 + }, + { + "epoch": 5.51, + "learning_rate": 6.327586206896552e-05, + "loss": 1.0544, + "step": 5112 + }, + { + "epoch": 5.51, + "learning_rate": 6.326867816091954e-05, + "loss": 1.1249, + "step": 5113 + }, + { + "epoch": 5.51, + "learning_rate": 6.326149425287356e-05, + "loss": 1.0678, + "step": 5114 + }, + { + "epoch": 5.51, + "learning_rate": 6.32543103448276e-05, + "loss": 1.1128, + "step": 5115 + }, + { + "epoch": 5.51, + "learning_rate": 6.324712643678162e-05, + "loss": 1.122, + "step": 5116 + }, + { + "epoch": 5.51, + "learning_rate": 6.323994252873564e-05, + "loss": 1.1859, + "step": 5117 + }, + { + "epoch": 5.52, + "learning_rate": 6.323275862068966e-05, + "loss": 1.1467, + "step": 5118 + }, + { + "epoch": 5.52, + "learning_rate": 6.322557471264368e-05, + "loss": 1.0671, + "step": 5119 + }, + { + "epoch": 5.52, + "learning_rate": 6.32183908045977e-05, + "loss": 1.2412, + "step": 5120 + }, + { + "epoch": 5.52, + "learning_rate": 6.321120689655172e-05, + "loss": 1.1627, + "step": 5121 + }, + { + "epoch": 5.52, + "learning_rate": 6.320402298850575e-05, + "loss": 1.1395, + "step": 5122 + }, + { + "epoch": 5.52, + "learning_rate": 6.319683908045977e-05, + "loss": 1.0834, + "step": 5123 + }, + { + "epoch": 5.52, + "learning_rate": 6.318965517241379e-05, + "loss": 1.1821, + "step": 5124 + }, + { + "epoch": 5.52, + "learning_rate": 6.318247126436781e-05, + "loss": 1.0751, + "step": 5125 + }, + { + "epoch": 5.52, + "learning_rate": 6.317528735632185e-05, + "loss": 1.1949, + "step": 5126 + }, + { + "epoch": 5.52, + "learning_rate": 6.316810344827587e-05, + "loss": 1.1537, + "step": 5127 + }, + { + "epoch": 5.53, + "learning_rate": 6.316091954022989e-05, + "loss": 1.1662, + "step": 5128 + }, + { + "epoch": 5.53, + "learning_rate": 6.315373563218391e-05, + "loss": 1.144, + "step": 5129 + }, + { + "epoch": 5.53, + "learning_rate": 6.314655172413794e-05, + "loss": 1.1052, + "step": 5130 + }, + { + "epoch": 5.53, + "learning_rate": 6.313936781609195e-05, + "loss": 1.026, + "step": 5131 + }, + { + "epoch": 5.53, + "learning_rate": 6.313218390804598e-05, + "loss": 1.137, + "step": 5132 + }, + { + "epoch": 5.53, + "learning_rate": 6.3125e-05, + "loss": 1.1906, + "step": 5133 + }, + { + "epoch": 5.53, + "learning_rate": 6.311781609195402e-05, + "loss": 1.1372, + "step": 5134 + }, + { + "epoch": 5.53, + "learning_rate": 6.311063218390804e-05, + "loss": 1.0291, + "step": 5135 + }, + { + "epoch": 5.53, + "learning_rate": 6.310344827586208e-05, + "loss": 1.1037, + "step": 5136 + }, + { + "epoch": 5.54, + "learning_rate": 6.30962643678161e-05, + "loss": 1.1364, + "step": 5137 + }, + { + "epoch": 5.54, + "learning_rate": 6.308908045977012e-05, + "loss": 1.0944, + "step": 5138 + }, + { + "epoch": 5.54, + "learning_rate": 6.308189655172414e-05, + "loss": 0.9792, + "step": 5139 + }, + { + "epoch": 5.54, + "learning_rate": 6.307471264367817e-05, + "loss": 1.1172, + "step": 5140 + }, + { + "epoch": 5.54, + "learning_rate": 6.306752873563219e-05, + "loss": 0.9859, + "step": 5141 + }, + { + "epoch": 5.54, + "learning_rate": 6.306034482758621e-05, + "loss": 0.9665, + "step": 5142 + }, + { + "epoch": 5.54, + "learning_rate": 6.305316091954023e-05, + "loss": 0.9855, + "step": 5143 + }, + { + "epoch": 5.54, + "learning_rate": 6.304597701149425e-05, + "loss": 1.1356, + "step": 5144 + }, + { + "epoch": 5.54, + "learning_rate": 6.303879310344827e-05, + "loss": 1.2159, + "step": 5145 + }, + { + "epoch": 5.55, + "learning_rate": 6.30316091954023e-05, + "loss": 1.0598, + "step": 5146 + }, + { + "epoch": 5.55, + "learning_rate": 6.302442528735633e-05, + "loss": 1.0976, + "step": 5147 + }, + { + "epoch": 5.55, + "learning_rate": 6.301724137931035e-05, + "loss": 1.0826, + "step": 5148 + }, + { + "epoch": 5.55, + "learning_rate": 6.301005747126437e-05, + "loss": 1.1071, + "step": 5149 + }, + { + "epoch": 5.55, + "learning_rate": 6.300287356321839e-05, + "loss": 1.0782, + "step": 5150 + }, + { + "epoch": 5.55, + "learning_rate": 6.299568965517242e-05, + "loss": 1.029, + "step": 5151 + }, + { + "epoch": 5.55, + "learning_rate": 6.298850574712643e-05, + "loss": 1.2054, + "step": 5152 + }, + { + "epoch": 5.55, + "learning_rate": 6.298132183908046e-05, + "loss": 1.0947, + "step": 5153 + }, + { + "epoch": 5.55, + "learning_rate": 6.297413793103448e-05, + "loss": 1.1321, + "step": 5154 + }, + { + "epoch": 5.55, + "learning_rate": 6.296695402298852e-05, + "loss": 1.1082, + "step": 5155 + }, + { + "epoch": 5.56, + "learning_rate": 6.295977011494252e-05, + "loss": 1.0159, + "step": 5156 + }, + { + "epoch": 5.56, + "learning_rate": 6.295258620689656e-05, + "loss": 1.1315, + "step": 5157 + }, + { + "epoch": 5.56, + "learning_rate": 6.294540229885058e-05, + "loss": 1.0192, + "step": 5158 + }, + { + "epoch": 5.56, + "learning_rate": 6.29382183908046e-05, + "loss": 1.1853, + "step": 5159 + }, + { + "epoch": 5.56, + "learning_rate": 6.293103448275862e-05, + "loss": 1.1089, + "step": 5160 + }, + { + "epoch": 5.56, + "learning_rate": 6.292385057471265e-05, + "loss": 1.1369, + "step": 5161 + }, + { + "epoch": 5.56, + "learning_rate": 6.291666666666667e-05, + "loss": 1.0578, + "step": 5162 + }, + { + "epoch": 5.56, + "learning_rate": 6.29094827586207e-05, + "loss": 1.127, + "step": 5163 + }, + { + "epoch": 5.56, + "learning_rate": 6.290229885057471e-05, + "loss": 1.1356, + "step": 5164 + }, + { + "epoch": 5.57, + "learning_rate": 6.289511494252875e-05, + "loss": 1.0502, + "step": 5165 + }, + { + "epoch": 5.57, + "learning_rate": 6.288793103448275e-05, + "loss": 0.9469, + "step": 5166 + }, + { + "epoch": 5.57, + "learning_rate": 6.288074712643679e-05, + "loss": 1.0883, + "step": 5167 + }, + { + "epoch": 5.57, + "learning_rate": 6.287356321839081e-05, + "loss": 1.1174, + "step": 5168 + }, + { + "epoch": 5.57, + "learning_rate": 6.286637931034483e-05, + "loss": 1.0892, + "step": 5169 + }, + { + "epoch": 5.57, + "learning_rate": 6.285919540229885e-05, + "loss": 1.0547, + "step": 5170 + }, + { + "epoch": 5.57, + "learning_rate": 6.285201149425287e-05, + "loss": 1.1687, + "step": 5171 + }, + { + "epoch": 5.57, + "learning_rate": 6.28448275862069e-05, + "loss": 1.132, + "step": 5172 + }, + { + "epoch": 5.57, + "learning_rate": 6.283764367816092e-05, + "loss": 1.1093, + "step": 5173 + }, + { + "epoch": 5.58, + "learning_rate": 6.283045977011494e-05, + "loss": 1.065, + "step": 5174 + }, + { + "epoch": 5.58, + "learning_rate": 6.282327586206896e-05, + "loss": 1.1354, + "step": 5175 + }, + { + "epoch": 5.58, + "learning_rate": 6.2816091954023e-05, + "loss": 1.1989, + "step": 5176 + }, + { + "epoch": 5.58, + "learning_rate": 6.2808908045977e-05, + "loss": 1.2103, + "step": 5177 + }, + { + "epoch": 5.58, + "learning_rate": 6.280172413793104e-05, + "loss": 1.2893, + "step": 5178 + }, + { + "epoch": 5.58, + "learning_rate": 6.279454022988506e-05, + "loss": 1.0741, + "step": 5179 + }, + { + "epoch": 5.58, + "learning_rate": 6.278735632183908e-05, + "loss": 0.9443, + "step": 5180 + }, + { + "epoch": 5.58, + "learning_rate": 6.27801724137931e-05, + "loss": 1.2173, + "step": 5181 + }, + { + "epoch": 5.58, + "learning_rate": 6.277298850574713e-05, + "loss": 1.1056, + "step": 5182 + }, + { + "epoch": 5.59, + "learning_rate": 6.276580459770115e-05, + "loss": 1.0256, + "step": 5183 + }, + { + "epoch": 5.59, + "learning_rate": 6.275862068965517e-05, + "loss": 1.0292, + "step": 5184 + }, + { + "epoch": 5.59, + "learning_rate": 6.27514367816092e-05, + "loss": 1.0978, + "step": 5185 + }, + { + "epoch": 5.59, + "learning_rate": 6.274425287356323e-05, + "loss": 1.0698, + "step": 5186 + }, + { + "epoch": 5.59, + "learning_rate": 6.273706896551725e-05, + "loss": 1.0908, + "step": 5187 + }, + { + "epoch": 5.59, + "learning_rate": 6.272988505747127e-05, + "loss": 1.0861, + "step": 5188 + }, + { + "epoch": 5.59, + "learning_rate": 6.272270114942529e-05, + "loss": 0.9913, + "step": 5189 + }, + { + "epoch": 5.59, + "learning_rate": 6.271551724137932e-05, + "loss": 1.0763, + "step": 5190 + }, + { + "epoch": 5.59, + "learning_rate": 6.270833333333333e-05, + "loss": 1.0907, + "step": 5191 + }, + { + "epoch": 5.59, + "learning_rate": 6.270114942528736e-05, + "loss": 1.0865, + "step": 5192 + }, + { + "epoch": 5.6, + "learning_rate": 6.269396551724138e-05, + "loss": 0.9985, + "step": 5193 + }, + { + "epoch": 5.6, + "learning_rate": 6.26867816091954e-05, + "loss": 1.1605, + "step": 5194 + }, + { + "epoch": 5.6, + "learning_rate": 6.267959770114943e-05, + "loss": 1.0733, + "step": 5195 + }, + { + "epoch": 5.6, + "learning_rate": 6.267241379310345e-05, + "loss": 1.0435, + "step": 5196 + }, + { + "epoch": 5.6, + "learning_rate": 6.266522988505748e-05, + "loss": 1.0995, + "step": 5197 + }, + { + "epoch": 5.6, + "learning_rate": 6.265804597701149e-05, + "loss": 1.1009, + "step": 5198 + }, + { + "epoch": 5.6, + "learning_rate": 6.265086206896552e-05, + "loss": 1.0824, + "step": 5199 + }, + { + "epoch": 5.6, + "learning_rate": 6.264367816091954e-05, + "loss": 1.0506, + "step": 5200 + }, + { + "epoch": 5.6, + "learning_rate": 6.263649425287356e-05, + "loss": 1.1765, + "step": 5201 + }, + { + "epoch": 5.61, + "learning_rate": 6.262931034482758e-05, + "loss": 1.0463, + "step": 5202 + }, + { + "epoch": 5.61, + "learning_rate": 6.262212643678162e-05, + "loss": 1.1317, + "step": 5203 + }, + { + "epoch": 5.61, + "learning_rate": 6.261494252873564e-05, + "loss": 1.0685, + "step": 5204 + }, + { + "epoch": 5.61, + "learning_rate": 6.260775862068966e-05, + "loss": 1.136, + "step": 5205 + }, + { + "epoch": 5.61, + "learning_rate": 6.260057471264368e-05, + "loss": 0.9761, + "step": 5206 + }, + { + "epoch": 5.61, + "learning_rate": 6.259339080459771e-05, + "loss": 1.1526, + "step": 5207 + }, + { + "epoch": 5.61, + "learning_rate": 6.258620689655173e-05, + "loss": 1.0676, + "step": 5208 + }, + { + "epoch": 5.61, + "learning_rate": 6.257902298850575e-05, + "loss": 1.087, + "step": 5209 + }, + { + "epoch": 5.61, + "learning_rate": 6.257183908045977e-05, + "loss": 1.2156, + "step": 5210 + }, + { + "epoch": 5.62, + "learning_rate": 6.25646551724138e-05, + "loss": 1.0112, + "step": 5211 + }, + { + "epoch": 5.62, + "learning_rate": 6.255747126436781e-05, + "loss": 1.0709, + "step": 5212 + }, + { + "epoch": 5.62, + "learning_rate": 6.255028735632185e-05, + "loss": 1.0231, + "step": 5213 + }, + { + "epoch": 5.62, + "learning_rate": 6.254310344827587e-05, + "loss": 1.064, + "step": 5214 + }, + { + "epoch": 5.62, + "learning_rate": 6.253591954022989e-05, + "loss": 1.0452, + "step": 5215 + }, + { + "epoch": 5.62, + "learning_rate": 6.25287356321839e-05, + "loss": 1.1651, + "step": 5216 + }, + { + "epoch": 5.62, + "learning_rate": 6.252155172413794e-05, + "loss": 1.0169, + "step": 5217 + }, + { + "epoch": 5.62, + "learning_rate": 6.251436781609196e-05, + "loss": 1.0678, + "step": 5218 + }, + { + "epoch": 5.62, + "learning_rate": 6.250718390804598e-05, + "loss": 1.0603, + "step": 5219 + }, + { + "epoch": 5.62, + "learning_rate": 6.25e-05, + "loss": 1.0875, + "step": 5220 + }, + { + "epoch": 5.63, + "learning_rate": 6.249281609195402e-05, + "loss": 1.1091, + "step": 5221 + }, + { + "epoch": 5.63, + "learning_rate": 6.248563218390806e-05, + "loss": 1.0733, + "step": 5222 + }, + { + "epoch": 5.63, + "learning_rate": 6.247844827586206e-05, + "loss": 1.1677, + "step": 5223 + }, + { + "epoch": 5.63, + "learning_rate": 6.24712643678161e-05, + "loss": 1.0889, + "step": 5224 + }, + { + "epoch": 5.63, + "learning_rate": 6.246408045977012e-05, + "loss": 1.1499, + "step": 5225 + }, + { + "epoch": 5.63, + "learning_rate": 6.245689655172414e-05, + "loss": 1.1122, + "step": 5226 + }, + { + "epoch": 5.63, + "learning_rate": 6.244971264367816e-05, + "loss": 1.0844, + "step": 5227 + }, + { + "epoch": 5.63, + "learning_rate": 6.244252873563219e-05, + "loss": 1.075, + "step": 5228 + }, + { + "epoch": 5.63, + "learning_rate": 6.243534482758621e-05, + "loss": 0.9674, + "step": 5229 + }, + { + "epoch": 5.64, + "learning_rate": 6.242816091954023e-05, + "loss": 1.2366, + "step": 5230 + }, + { + "epoch": 5.64, + "learning_rate": 6.242097701149425e-05, + "loss": 1.0461, + "step": 5231 + }, + { + "epoch": 5.64, + "learning_rate": 6.241379310344829e-05, + "loss": 1.032, + "step": 5232 + }, + { + "epoch": 5.64, + "learning_rate": 6.240660919540229e-05, + "loss": 1.1316, + "step": 5233 + }, + { + "epoch": 5.64, + "learning_rate": 6.239942528735633e-05, + "loss": 1.1369, + "step": 5234 + }, + { + "epoch": 5.64, + "learning_rate": 6.239224137931035e-05, + "loss": 1.2038, + "step": 5235 + }, + { + "epoch": 5.64, + "learning_rate": 6.238505747126438e-05, + "loss": 1.1735, + "step": 5236 + }, + { + "epoch": 5.64, + "learning_rate": 6.237787356321839e-05, + "loss": 1.1203, + "step": 5237 + }, + { + "epoch": 5.64, + "learning_rate": 6.237068965517242e-05, + "loss": 1.0442, + "step": 5238 + }, + { + "epoch": 5.65, + "learning_rate": 6.236350574712644e-05, + "loss": 0.9998, + "step": 5239 + }, + { + "epoch": 5.65, + "learning_rate": 6.235632183908046e-05, + "loss": 1.0847, + "step": 5240 + }, + { + "epoch": 5.65, + "learning_rate": 6.234913793103448e-05, + "loss": 1.0983, + "step": 5241 + }, + { + "epoch": 5.65, + "learning_rate": 6.234195402298852e-05, + "loss": 1.122, + "step": 5242 + }, + { + "epoch": 5.65, + "learning_rate": 6.233477011494254e-05, + "loss": 1.0978, + "step": 5243 + }, + { + "epoch": 5.65, + "learning_rate": 6.232758620689656e-05, + "loss": 1.1053, + "step": 5244 + }, + { + "epoch": 5.65, + "learning_rate": 6.232040229885058e-05, + "loss": 1.1495, + "step": 5245 + }, + { + "epoch": 5.65, + "learning_rate": 6.23132183908046e-05, + "loss": 1.043, + "step": 5246 + }, + { + "epoch": 5.65, + "learning_rate": 6.230603448275862e-05, + "loss": 1.1195, + "step": 5247 + }, + { + "epoch": 5.66, + "learning_rate": 6.229885057471264e-05, + "loss": 1.1865, + "step": 5248 + }, + { + "epoch": 5.66, + "learning_rate": 6.229166666666667e-05, + "loss": 1.1334, + "step": 5249 + }, + { + "epoch": 5.66, + "learning_rate": 6.228448275862069e-05, + "loss": 1.1673, + "step": 5250 + }, + { + "epoch": 5.66, + "eval_loss": 1.1272408962249756, + "eval_runtime": 175.0427, + "eval_samples_per_second": 127.226, + "eval_steps_per_second": 0.663, + "step": 5250 + }, + { + "epoch": 5.66, + "learning_rate": 6.227729885057471e-05, + "loss": 1.063, + "step": 5251 + }, + { + "epoch": 5.66, + "learning_rate": 6.227011494252873e-05, + "loss": 1.2029, + "step": 5252 + }, + { + "epoch": 5.66, + "learning_rate": 6.226293103448277e-05, + "loss": 1.2564, + "step": 5253 + }, + { + "epoch": 5.66, + "learning_rate": 6.225574712643679e-05, + "loss": 0.9802, + "step": 5254 + }, + { + "epoch": 5.66, + "learning_rate": 6.224856321839081e-05, + "loss": 1.164, + "step": 5255 + }, + { + "epoch": 5.66, + "learning_rate": 6.224137931034483e-05, + "loss": 1.0914, + "step": 5256 + }, + { + "epoch": 5.66, + "learning_rate": 6.223419540229886e-05, + "loss": 1.0922, + "step": 5257 + }, + { + "epoch": 5.67, + "learning_rate": 6.222701149425287e-05, + "loss": 1.1921, + "step": 5258 + }, + { + "epoch": 5.67, + "learning_rate": 6.22198275862069e-05, + "loss": 1.0447, + "step": 5259 + }, + { + "epoch": 5.67, + "learning_rate": 6.221264367816092e-05, + "loss": 1.0253, + "step": 5260 + }, + { + "epoch": 5.67, + "learning_rate": 6.220545977011494e-05, + "loss": 1.1113, + "step": 5261 + }, + { + "epoch": 5.67, + "learning_rate": 6.219827586206896e-05, + "loss": 0.9231, + "step": 5262 + }, + { + "epoch": 5.67, + "learning_rate": 6.2191091954023e-05, + "loss": 1.1178, + "step": 5263 + }, + { + "epoch": 5.67, + "learning_rate": 6.218390804597702e-05, + "loss": 1.0765, + "step": 5264 + }, + { + "epoch": 5.67, + "learning_rate": 6.217672413793104e-05, + "loss": 1.0726, + "step": 5265 + }, + { + "epoch": 5.67, + "learning_rate": 6.216954022988506e-05, + "loss": 1.1967, + "step": 5266 + }, + { + "epoch": 5.68, + "learning_rate": 6.216235632183909e-05, + "loss": 1.0846, + "step": 5267 + }, + { + "epoch": 5.68, + "learning_rate": 6.215517241379311e-05, + "loss": 1.0237, + "step": 5268 + }, + { + "epoch": 5.68, + "learning_rate": 6.214798850574713e-05, + "loss": 0.9248, + "step": 5269 + }, + { + "epoch": 5.68, + "learning_rate": 6.214080459770115e-05, + "loss": 1.0184, + "step": 5270 + }, + { + "epoch": 5.68, + "learning_rate": 6.213362068965519e-05, + "loss": 1.011, + "step": 5271 + }, + { + "epoch": 5.68, + "learning_rate": 6.21264367816092e-05, + "loss": 1.0488, + "step": 5272 + }, + { + "epoch": 5.68, + "learning_rate": 6.211925287356321e-05, + "loss": 1.0822, + "step": 5273 + }, + { + "epoch": 5.68, + "learning_rate": 6.211206896551725e-05, + "loss": 1.0356, + "step": 5274 + }, + { + "epoch": 5.68, + "learning_rate": 6.210488505747127e-05, + "loss": 1.0262, + "step": 5275 + }, + { + "epoch": 5.69, + "learning_rate": 6.209770114942529e-05, + "loss": 1.0263, + "step": 5276 + }, + { + "epoch": 5.69, + "learning_rate": 6.209051724137931e-05, + "loss": 1.0054, + "step": 5277 + }, + { + "epoch": 5.69, + "learning_rate": 6.208333333333334e-05, + "loss": 1.0256, + "step": 5278 + }, + { + "epoch": 5.69, + "learning_rate": 6.207614942528735e-05, + "loss": 1.1285, + "step": 5279 + }, + { + "epoch": 5.69, + "learning_rate": 6.206896551724138e-05, + "loss": 1.2275, + "step": 5280 + }, + { + "epoch": 5.69, + "learning_rate": 6.20617816091954e-05, + "loss": 1.1974, + "step": 5281 + }, + { + "epoch": 5.69, + "learning_rate": 6.205459770114942e-05, + "loss": 1.1512, + "step": 5282 + }, + { + "epoch": 5.69, + "learning_rate": 6.204741379310344e-05, + "loss": 1.1753, + "step": 5283 + }, + { + "epoch": 5.69, + "learning_rate": 6.204022988505748e-05, + "loss": 0.988, + "step": 5284 + }, + { + "epoch": 5.7, + "learning_rate": 6.20330459770115e-05, + "loss": 1.2968, + "step": 5285 + }, + { + "epoch": 5.7, + "learning_rate": 6.202586206896552e-05, + "loss": 1.1898, + "step": 5286 + }, + { + "epoch": 5.7, + "learning_rate": 6.201867816091954e-05, + "loss": 1.0184, + "step": 5287 + }, + { + "epoch": 5.7, + "learning_rate": 6.201149425287357e-05, + "loss": 1.1044, + "step": 5288 + }, + { + "epoch": 5.7, + "learning_rate": 6.200431034482759e-05, + "loss": 1.0047, + "step": 5289 + }, + { + "epoch": 5.7, + "learning_rate": 6.199712643678161e-05, + "loss": 1.1091, + "step": 5290 + }, + { + "epoch": 5.7, + "learning_rate": 6.198994252873563e-05, + "loss": 1.1383, + "step": 5291 + }, + { + "epoch": 5.7, + "learning_rate": 6.198275862068967e-05, + "loss": 0.9815, + "step": 5292 + }, + { + "epoch": 5.7, + "learning_rate": 6.197557471264367e-05, + "loss": 1.079, + "step": 5293 + }, + { + "epoch": 5.7, + "learning_rate": 6.196839080459771e-05, + "loss": 1.1136, + "step": 5294 + }, + { + "epoch": 5.71, + "learning_rate": 6.196120689655173e-05, + "loss": 1.1703, + "step": 5295 + }, + { + "epoch": 5.71, + "learning_rate": 6.195402298850575e-05, + "loss": 1.1026, + "step": 5296 + }, + { + "epoch": 5.71, + "learning_rate": 6.194683908045977e-05, + "loss": 1.1263, + "step": 5297 + }, + { + "epoch": 5.71, + "learning_rate": 6.193965517241379e-05, + "loss": 1.0903, + "step": 5298 + }, + { + "epoch": 5.71, + "learning_rate": 6.193247126436782e-05, + "loss": 1.1671, + "step": 5299 + }, + { + "epoch": 5.71, + "learning_rate": 6.192528735632184e-05, + "loss": 0.9737, + "step": 5300 + }, + { + "epoch": 5.71, + "learning_rate": 6.191810344827586e-05, + "loss": 1.1081, + "step": 5301 + }, + { + "epoch": 5.71, + "learning_rate": 6.191091954022988e-05, + "loss": 0.9834, + "step": 5302 + }, + { + "epoch": 5.71, + "learning_rate": 6.190373563218392e-05, + "loss": 1.0384, + "step": 5303 + }, + { + "epoch": 5.72, + "learning_rate": 6.189655172413793e-05, + "loss": 1.1108, + "step": 5304 + }, + { + "epoch": 5.72, + "learning_rate": 6.188936781609196e-05, + "loss": 1.0678, + "step": 5305 + }, + { + "epoch": 5.72, + "learning_rate": 6.188218390804598e-05, + "loss": 1.1283, + "step": 5306 + }, + { + "epoch": 5.72, + "learning_rate": 6.1875e-05, + "loss": 1.0887, + "step": 5307 + }, + { + "epoch": 5.72, + "learning_rate": 6.186781609195402e-05, + "loss": 0.938, + "step": 5308 + }, + { + "epoch": 5.72, + "learning_rate": 6.186063218390805e-05, + "loss": 1.1377, + "step": 5309 + }, + { + "epoch": 5.72, + "learning_rate": 6.185344827586207e-05, + "loss": 1.047, + "step": 5310 + }, + { + "epoch": 5.72, + "learning_rate": 6.18462643678161e-05, + "loss": 1.0383, + "step": 5311 + }, + { + "epoch": 5.72, + "learning_rate": 6.183908045977011e-05, + "loss": 1.1534, + "step": 5312 + }, + { + "epoch": 5.73, + "learning_rate": 6.183189655172415e-05, + "loss": 0.919, + "step": 5313 + }, + { + "epoch": 5.73, + "learning_rate": 6.182471264367816e-05, + "loss": 1.1385, + "step": 5314 + }, + { + "epoch": 5.73, + "learning_rate": 6.181752873563219e-05, + "loss": 1.0507, + "step": 5315 + }, + { + "epoch": 5.73, + "learning_rate": 6.181034482758621e-05, + "loss": 1.0704, + "step": 5316 + }, + { + "epoch": 5.73, + "learning_rate": 6.180316091954024e-05, + "loss": 1.1027, + "step": 5317 + }, + { + "epoch": 5.73, + "learning_rate": 6.179597701149425e-05, + "loss": 0.9666, + "step": 5318 + }, + { + "epoch": 5.73, + "learning_rate": 6.178879310344828e-05, + "loss": 1.0656, + "step": 5319 + }, + { + "epoch": 5.73, + "learning_rate": 6.17816091954023e-05, + "loss": 1.1444, + "step": 5320 + }, + { + "epoch": 5.73, + "learning_rate": 6.177442528735632e-05, + "loss": 1.1678, + "step": 5321 + }, + { + "epoch": 5.73, + "learning_rate": 6.176724137931035e-05, + "loss": 1.081, + "step": 5322 + }, + { + "epoch": 5.74, + "learning_rate": 6.176005747126437e-05, + "loss": 0.9816, + "step": 5323 + }, + { + "epoch": 5.74, + "learning_rate": 6.17528735632184e-05, + "loss": 0.9233, + "step": 5324 + }, + { + "epoch": 5.74, + "learning_rate": 6.17456896551724e-05, + "loss": 1.1258, + "step": 5325 + }, + { + "epoch": 5.74, + "learning_rate": 6.173850574712644e-05, + "loss": 1.0466, + "step": 5326 + }, + { + "epoch": 5.74, + "learning_rate": 6.173132183908046e-05, + "loss": 1.0699, + "step": 5327 + }, + { + "epoch": 5.74, + "learning_rate": 6.172413793103448e-05, + "loss": 1.0807, + "step": 5328 + }, + { + "epoch": 5.74, + "learning_rate": 6.17169540229885e-05, + "loss": 1.0232, + "step": 5329 + }, + { + "epoch": 5.74, + "learning_rate": 6.170977011494253e-05, + "loss": 0.9822, + "step": 5330 + }, + { + "epoch": 5.74, + "learning_rate": 6.170258620689656e-05, + "loss": 1.0989, + "step": 5331 + }, + { + "epoch": 5.75, + "learning_rate": 6.169540229885058e-05, + "loss": 1.1683, + "step": 5332 + }, + { + "epoch": 5.75, + "learning_rate": 6.16882183908046e-05, + "loss": 0.9878, + "step": 5333 + }, + { + "epoch": 5.75, + "learning_rate": 6.168103448275863e-05, + "loss": 0.937, + "step": 5334 + }, + { + "epoch": 5.75, + "learning_rate": 6.167385057471265e-05, + "loss": 0.9343, + "step": 5335 + }, + { + "epoch": 5.75, + "learning_rate": 6.166666666666667e-05, + "loss": 0.9645, + "step": 5336 + }, + { + "epoch": 5.75, + "learning_rate": 6.165948275862069e-05, + "loss": 1.1877, + "step": 5337 + }, + { + "epoch": 5.75, + "learning_rate": 6.165229885057472e-05, + "loss": 1.0687, + "step": 5338 + }, + { + "epoch": 5.75, + "learning_rate": 6.164511494252873e-05, + "loss": 1.0973, + "step": 5339 + }, + { + "epoch": 5.75, + "learning_rate": 6.163793103448277e-05, + "loss": 0.9136, + "step": 5340 + }, + { + "epoch": 5.76, + "learning_rate": 6.163074712643679e-05, + "loss": 1.2609, + "step": 5341 + }, + { + "epoch": 5.76, + "learning_rate": 6.16235632183908e-05, + "loss": 1.0306, + "step": 5342 + }, + { + "epoch": 5.76, + "learning_rate": 6.161637931034483e-05, + "loss": 1.1417, + "step": 5343 + }, + { + "epoch": 5.76, + "learning_rate": 6.160919540229886e-05, + "loss": 0.9997, + "step": 5344 + }, + { + "epoch": 5.76, + "learning_rate": 6.160201149425288e-05, + "loss": 1.0398, + "step": 5345 + }, + { + "epoch": 5.76, + "learning_rate": 6.15948275862069e-05, + "loss": 1.0902, + "step": 5346 + }, + { + "epoch": 5.76, + "learning_rate": 6.158764367816092e-05, + "loss": 1.0899, + "step": 5347 + }, + { + "epoch": 5.76, + "learning_rate": 6.158045977011494e-05, + "loss": 1.0503, + "step": 5348 + }, + { + "epoch": 5.76, + "learning_rate": 6.157327586206898e-05, + "loss": 1.242, + "step": 5349 + }, + { + "epoch": 5.77, + "learning_rate": 6.156609195402298e-05, + "loss": 1.0293, + "step": 5350 + }, + { + "epoch": 5.77, + "learning_rate": 6.155890804597702e-05, + "loss": 1.1209, + "step": 5351 + }, + { + "epoch": 5.77, + "learning_rate": 6.155172413793104e-05, + "loss": 1.099, + "step": 5352 + }, + { + "epoch": 5.77, + "learning_rate": 6.154454022988506e-05, + "loss": 1.0574, + "step": 5353 + }, + { + "epoch": 5.77, + "learning_rate": 6.153735632183908e-05, + "loss": 1.2141, + "step": 5354 + }, + { + "epoch": 5.77, + "learning_rate": 6.153017241379311e-05, + "loss": 1.0781, + "step": 5355 + }, + { + "epoch": 5.77, + "learning_rate": 6.152298850574713e-05, + "loss": 1.193, + "step": 5356 + }, + { + "epoch": 5.77, + "learning_rate": 6.151580459770115e-05, + "loss": 0.9457, + "step": 5357 + }, + { + "epoch": 5.77, + "learning_rate": 6.150862068965517e-05, + "loss": 1.0779, + "step": 5358 + }, + { + "epoch": 5.77, + "learning_rate": 6.15014367816092e-05, + "loss": 1.1275, + "step": 5359 + }, + { + "epoch": 5.78, + "learning_rate": 6.149425287356321e-05, + "loss": 1.1364, + "step": 5360 + }, + { + "epoch": 5.78, + "learning_rate": 6.148706896551725e-05, + "loss": 1.0591, + "step": 5361 + }, + { + "epoch": 5.78, + "learning_rate": 6.147988505747127e-05, + "loss": 1.2045, + "step": 5362 + }, + { + "epoch": 5.78, + "learning_rate": 6.14727011494253e-05, + "loss": 0.9731, + "step": 5363 + }, + { + "epoch": 5.78, + "learning_rate": 6.146551724137931e-05, + "loss": 1.0238, + "step": 5364 + }, + { + "epoch": 5.78, + "learning_rate": 6.145833333333334e-05, + "loss": 1.1016, + "step": 5365 + }, + { + "epoch": 5.78, + "learning_rate": 6.145114942528736e-05, + "loss": 1.0366, + "step": 5366 + }, + { + "epoch": 5.78, + "learning_rate": 6.144396551724138e-05, + "loss": 1.1205, + "step": 5367 + }, + { + "epoch": 5.78, + "learning_rate": 6.14367816091954e-05, + "loss": 1.133, + "step": 5368 + }, + { + "epoch": 5.79, + "learning_rate": 6.142959770114944e-05, + "loss": 1.1358, + "step": 5369 + }, + { + "epoch": 5.79, + "learning_rate": 6.142241379310346e-05, + "loss": 1.1065, + "step": 5370 + }, + { + "epoch": 5.79, + "learning_rate": 6.141522988505748e-05, + "loss": 0.9643, + "step": 5371 + }, + { + "epoch": 5.79, + "learning_rate": 6.14080459770115e-05, + "loss": 0.9546, + "step": 5372 + }, + { + "epoch": 5.79, + "learning_rate": 6.140086206896553e-05, + "loss": 1.0237, + "step": 5373 + }, + { + "epoch": 5.79, + "learning_rate": 6.139367816091954e-05, + "loss": 1.0192, + "step": 5374 + }, + { + "epoch": 5.79, + "learning_rate": 6.138649425287356e-05, + "loss": 1.2407, + "step": 5375 + }, + { + "epoch": 5.79, + "learning_rate": 6.137931034482759e-05, + "loss": 1.1407, + "step": 5376 + }, + { + "epoch": 5.79, + "learning_rate": 6.137212643678161e-05, + "loss": 0.9934, + "step": 5377 + }, + { + "epoch": 5.8, + "learning_rate": 6.136494252873563e-05, + "loss": 1.0722, + "step": 5378 + }, + { + "epoch": 5.8, + "learning_rate": 6.135775862068965e-05, + "loss": 1.1837, + "step": 5379 + }, + { + "epoch": 5.8, + "learning_rate": 6.135057471264369e-05, + "loss": 1.0159, + "step": 5380 + }, + { + "epoch": 5.8, + "learning_rate": 6.13433908045977e-05, + "loss": 1.1247, + "step": 5381 + }, + { + "epoch": 5.8, + "learning_rate": 6.133620689655173e-05, + "loss": 1.1102, + "step": 5382 + }, + { + "epoch": 5.8, + "learning_rate": 6.132902298850575e-05, + "loss": 1.0773, + "step": 5383 + }, + { + "epoch": 5.8, + "learning_rate": 6.132183908045978e-05, + "loss": 1.0254, + "step": 5384 + }, + { + "epoch": 5.8, + "learning_rate": 6.131465517241379e-05, + "loss": 1.192, + "step": 5385 + }, + { + "epoch": 5.8, + "learning_rate": 6.130747126436782e-05, + "loss": 1.1378, + "step": 5386 + }, + { + "epoch": 5.8, + "learning_rate": 6.130028735632184e-05, + "loss": 1.0516, + "step": 5387 + }, + { + "epoch": 5.81, + "learning_rate": 6.129310344827586e-05, + "loss": 0.9559, + "step": 5388 + }, + { + "epoch": 5.81, + "learning_rate": 6.128591954022988e-05, + "loss": 1.1092, + "step": 5389 + }, + { + "epoch": 5.81, + "learning_rate": 6.127873563218392e-05, + "loss": 0.9968, + "step": 5390 + }, + { + "epoch": 5.81, + "learning_rate": 6.127155172413794e-05, + "loss": 1.1223, + "step": 5391 + }, + { + "epoch": 5.81, + "learning_rate": 6.126436781609196e-05, + "loss": 1.206, + "step": 5392 + }, + { + "epoch": 5.81, + "learning_rate": 6.125718390804598e-05, + "loss": 1.0347, + "step": 5393 + }, + { + "epoch": 5.81, + "learning_rate": 6.125000000000001e-05, + "loss": 1.0508, + "step": 5394 + }, + { + "epoch": 5.81, + "learning_rate": 6.124281609195402e-05, + "loss": 1.0906, + "step": 5395 + }, + { + "epoch": 5.81, + "learning_rate": 6.123563218390805e-05, + "loss": 0.9143, + "step": 5396 + }, + { + "epoch": 5.82, + "learning_rate": 6.122844827586207e-05, + "loss": 0.948, + "step": 5397 + }, + { + "epoch": 5.82, + "learning_rate": 6.12212643678161e-05, + "loss": 1.1963, + "step": 5398 + }, + { + "epoch": 5.82, + "learning_rate": 6.121408045977011e-05, + "loss": 1.1688, + "step": 5399 + }, + { + "epoch": 5.82, + "learning_rate": 6.120689655172413e-05, + "loss": 1.1317, + "step": 5400 + }, + { + "epoch": 5.82, + "learning_rate": 6.119971264367817e-05, + "loss": 1.1622, + "step": 5401 + }, + { + "epoch": 5.82, + "learning_rate": 6.119252873563219e-05, + "loss": 1.0048, + "step": 5402 + }, + { + "epoch": 5.82, + "learning_rate": 6.118534482758621e-05, + "loss": 1.01, + "step": 5403 + }, + { + "epoch": 5.82, + "learning_rate": 6.117816091954023e-05, + "loss": 1.0984, + "step": 5404 + }, + { + "epoch": 5.82, + "learning_rate": 6.117097701149426e-05, + "loss": 1.2693, + "step": 5405 + }, + { + "epoch": 5.83, + "learning_rate": 6.116379310344827e-05, + "loss": 1.1739, + "step": 5406 + }, + { + "epoch": 5.83, + "learning_rate": 6.11566091954023e-05, + "loss": 1.1022, + "step": 5407 + }, + { + "epoch": 5.83, + "learning_rate": 6.114942528735632e-05, + "loss": 1.0772, + "step": 5408 + }, + { + "epoch": 5.83, + "learning_rate": 6.114224137931034e-05, + "loss": 1.1448, + "step": 5409 + }, + { + "epoch": 5.83, + "learning_rate": 6.113505747126436e-05, + "loss": 1.0697, + "step": 5410 + }, + { + "epoch": 5.83, + "learning_rate": 6.11278735632184e-05, + "loss": 1.2016, + "step": 5411 + }, + { + "epoch": 5.83, + "learning_rate": 6.112068965517242e-05, + "loss": 1.1461, + "step": 5412 + }, + { + "epoch": 5.83, + "learning_rate": 6.111350574712644e-05, + "loss": 1.0034, + "step": 5413 + }, + { + "epoch": 5.83, + "learning_rate": 6.110632183908046e-05, + "loss": 0.9913, + "step": 5414 + }, + { + "epoch": 5.84, + "learning_rate": 6.109913793103449e-05, + "loss": 1.0997, + "step": 5415 + }, + { + "epoch": 5.84, + "learning_rate": 6.109195402298851e-05, + "loss": 1.1997, + "step": 5416 + }, + { + "epoch": 5.84, + "learning_rate": 6.108477011494253e-05, + "loss": 1.1161, + "step": 5417 + }, + { + "epoch": 5.84, + "learning_rate": 6.107758620689655e-05, + "loss": 1.1075, + "step": 5418 + }, + { + "epoch": 5.84, + "learning_rate": 6.107040229885059e-05, + "loss": 1.1553, + "step": 5419 + }, + { + "epoch": 5.84, + "learning_rate": 6.10632183908046e-05, + "loss": 1.0625, + "step": 5420 + }, + { + "epoch": 5.84, + "learning_rate": 6.105603448275863e-05, + "loss": 1.1809, + "step": 5421 + }, + { + "epoch": 5.84, + "learning_rate": 6.104885057471265e-05, + "loss": 1.1841, + "step": 5422 + }, + { + "epoch": 5.84, + "learning_rate": 6.104166666666667e-05, + "loss": 1.1273, + "step": 5423 + }, + { + "epoch": 5.84, + "learning_rate": 6.1034482758620696e-05, + "loss": 1.0382, + "step": 5424 + }, + { + "epoch": 5.85, + "learning_rate": 6.102729885057471e-05, + "loss": 1.0658, + "step": 5425 + }, + { + "epoch": 5.85, + "learning_rate": 6.1020114942528736e-05, + "loss": 1.0265, + "step": 5426 + }, + { + "epoch": 5.85, + "learning_rate": 6.101293103448276e-05, + "loss": 1.0653, + "step": 5427 + }, + { + "epoch": 5.85, + "learning_rate": 6.1005747126436784e-05, + "loss": 0.9597, + "step": 5428 + }, + { + "epoch": 5.85, + "learning_rate": 6.0998563218390804e-05, + "loss": 1.0024, + "step": 5429 + }, + { + "epoch": 5.85, + "learning_rate": 6.099137931034483e-05, + "loss": 1.1368, + "step": 5430 + }, + { + "epoch": 5.85, + "learning_rate": 6.098419540229885e-05, + "loss": 1.0637, + "step": 5431 + }, + { + "epoch": 5.85, + "learning_rate": 6.097701149425288e-05, + "loss": 1.0191, + "step": 5432 + }, + { + "epoch": 5.85, + "learning_rate": 6.09698275862069e-05, + "loss": 1.0917, + "step": 5433 + }, + { + "epoch": 5.86, + "learning_rate": 6.0962643678160926e-05, + "loss": 1.1666, + "step": 5434 + }, + { + "epoch": 5.86, + "learning_rate": 6.095545977011494e-05, + "loss": 1.0362, + "step": 5435 + }, + { + "epoch": 5.86, + "learning_rate": 6.0948275862068973e-05, + "loss": 1.0301, + "step": 5436 + }, + { + "epoch": 5.86, + "learning_rate": 6.094109195402299e-05, + "loss": 0.9649, + "step": 5437 + }, + { + "epoch": 5.86, + "learning_rate": 6.0933908045977014e-05, + "loss": 1.1037, + "step": 5438 + }, + { + "epoch": 5.86, + "learning_rate": 6.0926724137931034e-05, + "loss": 1.0492, + "step": 5439 + }, + { + "epoch": 5.86, + "learning_rate": 6.091954022988506e-05, + "loss": 1.0157, + "step": 5440 + }, + { + "epoch": 5.86, + "learning_rate": 6.091235632183908e-05, + "loss": 1.1995, + "step": 5441 + }, + { + "epoch": 5.86, + "learning_rate": 6.090517241379311e-05, + "loss": 1.0907, + "step": 5442 + }, + { + "epoch": 5.87, + "learning_rate": 6.089798850574713e-05, + "loss": 1.2286, + "step": 5443 + }, + { + "epoch": 5.87, + "learning_rate": 6.0890804597701156e-05, + "loss": 0.9369, + "step": 5444 + }, + { + "epoch": 5.87, + "learning_rate": 6.088362068965518e-05, + "loss": 1.03, + "step": 5445 + }, + { + "epoch": 5.87, + "learning_rate": 6.0876436781609204e-05, + "loss": 1.1218, + "step": 5446 + }, + { + "epoch": 5.87, + "learning_rate": 6.086925287356322e-05, + "loss": 1.2695, + "step": 5447 + }, + { + "epoch": 5.87, + "learning_rate": 6.086206896551725e-05, + "loss": 0.9791, + "step": 5448 + }, + { + "epoch": 5.87, + "learning_rate": 6.0854885057471265e-05, + "loss": 1.0784, + "step": 5449 + }, + { + "epoch": 5.87, + "learning_rate": 6.08477011494253e-05, + "loss": 1.0309, + "step": 5450 + }, + { + "epoch": 5.87, + "learning_rate": 6.084051724137931e-05, + "loss": 0.9948, + "step": 5451 + }, + { + "epoch": 5.88, + "learning_rate": 6.083333333333333e-05, + "loss": 1.2238, + "step": 5452 + }, + { + "epoch": 5.88, + "learning_rate": 6.082614942528736e-05, + "loss": 1.0084, + "step": 5453 + }, + { + "epoch": 5.88, + "learning_rate": 6.081896551724138e-05, + "loss": 1.0032, + "step": 5454 + }, + { + "epoch": 5.88, + "learning_rate": 6.081178160919541e-05, + "loss": 1.0671, + "step": 5455 + }, + { + "epoch": 5.88, + "learning_rate": 6.080459770114942e-05, + "loss": 1.1491, + "step": 5456 + }, + { + "epoch": 5.88, + "learning_rate": 6.0797413793103454e-05, + "loss": 1.0746, + "step": 5457 + }, + { + "epoch": 5.88, + "learning_rate": 6.079022988505747e-05, + "loss": 1.1403, + "step": 5458 + }, + { + "epoch": 5.88, + "learning_rate": 6.07830459770115e-05, + "loss": 1.0888, + "step": 5459 + }, + { + "epoch": 5.88, + "learning_rate": 6.0775862068965515e-05, + "loss": 1.0224, + "step": 5460 + }, + { + "epoch": 5.88, + "learning_rate": 6.076867816091954e-05, + "loss": 1.0764, + "step": 5461 + }, + { + "epoch": 5.89, + "learning_rate": 6.076149425287356e-05, + "loss": 1.0237, + "step": 5462 + }, + { + "epoch": 5.89, + "learning_rate": 6.075431034482759e-05, + "loss": 1.0852, + "step": 5463 + }, + { + "epoch": 5.89, + "learning_rate": 6.074712643678161e-05, + "loss": 1.1523, + "step": 5464 + }, + { + "epoch": 5.89, + "learning_rate": 6.073994252873564e-05, + "loss": 1.2726, + "step": 5465 + }, + { + "epoch": 5.89, + "learning_rate": 6.073275862068966e-05, + "loss": 1.1276, + "step": 5466 + }, + { + "epoch": 5.89, + "learning_rate": 6.0725574712643685e-05, + "loss": 0.9937, + "step": 5467 + }, + { + "epoch": 5.89, + "learning_rate": 6.0718390804597705e-05, + "loss": 1.1257, + "step": 5468 + }, + { + "epoch": 5.89, + "learning_rate": 6.071120689655173e-05, + "loss": 1.0506, + "step": 5469 + }, + { + "epoch": 5.89, + "learning_rate": 6.0704022988505746e-05, + "loss": 1.1634, + "step": 5470 + }, + { + "epoch": 5.9, + "learning_rate": 6.069683908045978e-05, + "loss": 1.2626, + "step": 5471 + }, + { + "epoch": 5.9, + "learning_rate": 6.068965517241379e-05, + "loss": 1.1221, + "step": 5472 + }, + { + "epoch": 5.9, + "learning_rate": 6.068247126436783e-05, + "loss": 1.0878, + "step": 5473 + }, + { + "epoch": 5.9, + "learning_rate": 6.067528735632184e-05, + "loss": 1.0529, + "step": 5474 + }, + { + "epoch": 5.9, + "learning_rate": 6.066810344827587e-05, + "loss": 1.1721, + "step": 5475 + }, + { + "epoch": 5.9, + "learning_rate": 6.066091954022989e-05, + "loss": 1.1784, + "step": 5476 + }, + { + "epoch": 5.9, + "learning_rate": 6.065373563218391e-05, + "loss": 1.0704, + "step": 5477 + }, + { + "epoch": 5.9, + "learning_rate": 6.0646551724137935e-05, + "loss": 1.0054, + "step": 5478 + }, + { + "epoch": 5.9, + "learning_rate": 6.063936781609195e-05, + "loss": 0.9477, + "step": 5479 + }, + { + "epoch": 5.91, + "learning_rate": 6.063218390804598e-05, + "loss": 1.0917, + "step": 5480 + }, + { + "epoch": 5.91, + "learning_rate": 6.0624999999999996e-05, + "loss": 1.1403, + "step": 5481 + }, + { + "epoch": 5.91, + "learning_rate": 6.061781609195403e-05, + "loss": 1.0511, + "step": 5482 + }, + { + "epoch": 5.91, + "learning_rate": 6.0610632183908044e-05, + "loss": 1.0816, + "step": 5483 + }, + { + "epoch": 5.91, + "learning_rate": 6.060344827586207e-05, + "loss": 1.0685, + "step": 5484 + }, + { + "epoch": 5.91, + "learning_rate": 6.059626436781609e-05, + "loss": 1.0096, + "step": 5485 + }, + { + "epoch": 5.91, + "learning_rate": 6.058908045977012e-05, + "loss": 1.0286, + "step": 5486 + }, + { + "epoch": 5.91, + "learning_rate": 6.058189655172414e-05, + "loss": 0.9807, + "step": 5487 + }, + { + "epoch": 5.91, + "learning_rate": 6.0574712643678166e-05, + "loss": 1.0316, + "step": 5488 + }, + { + "epoch": 5.91, + "learning_rate": 6.0567528735632186e-05, + "loss": 1.1211, + "step": 5489 + }, + { + "epoch": 5.92, + "learning_rate": 6.056034482758621e-05, + "loss": 0.999, + "step": 5490 + }, + { + "epoch": 5.92, + "learning_rate": 6.0553160919540233e-05, + "loss": 1.0897, + "step": 5491 + }, + { + "epoch": 5.92, + "learning_rate": 6.054597701149426e-05, + "loss": 1.1588, + "step": 5492 + }, + { + "epoch": 5.92, + "learning_rate": 6.0538793103448274e-05, + "loss": 1.1308, + "step": 5493 + }, + { + "epoch": 5.92, + "learning_rate": 6.053160919540231e-05, + "loss": 1.2118, + "step": 5494 + }, + { + "epoch": 5.92, + "learning_rate": 6.052442528735632e-05, + "loss": 1.1287, + "step": 5495 + }, + { + "epoch": 5.92, + "learning_rate": 6.0517241379310355e-05, + "loss": 1.1745, + "step": 5496 + }, + { + "epoch": 5.92, + "learning_rate": 6.051005747126437e-05, + "loss": 1.1157, + "step": 5497 + }, + { + "epoch": 5.92, + "learning_rate": 6.0502873563218396e-05, + "loss": 1.1076, + "step": 5498 + }, + { + "epoch": 5.93, + "learning_rate": 6.0495689655172416e-05, + "loss": 1.0573, + "step": 5499 + }, + { + "epoch": 5.93, + "learning_rate": 6.0488505747126443e-05, + "loss": 1.0445, + "step": 5500 + }, + { + "epoch": 5.93, + "eval_loss": 1.1248128414154053, + "eval_runtime": 174.8853, + "eval_samples_per_second": 127.341, + "eval_steps_per_second": 0.663, + "step": 5500 + }, + { + "epoch": 5.93, + "learning_rate": 6.0481321839080464e-05, + "loss": 1.0745, + "step": 5501 + }, + { + "epoch": 5.93, + "learning_rate": 6.047413793103448e-05, + "loss": 1.2247, + "step": 5502 + }, + { + "epoch": 5.93, + "learning_rate": 6.046695402298851e-05, + "loss": 1.1577, + "step": 5503 + }, + { + "epoch": 5.93, + "learning_rate": 6.0459770114942525e-05, + "loss": 1.061, + "step": 5504 + }, + { + "epoch": 5.93, + "learning_rate": 6.045258620689656e-05, + "loss": 1.0873, + "step": 5505 + }, + { + "epoch": 5.93, + "learning_rate": 6.044540229885057e-05, + "loss": 1.0792, + "step": 5506 + }, + { + "epoch": 5.93, + "learning_rate": 6.04382183908046e-05, + "loss": 1.1093, + "step": 5507 + }, + { + "epoch": 5.94, + "learning_rate": 6.043103448275862e-05, + "loss": 1.2363, + "step": 5508 + }, + { + "epoch": 5.94, + "learning_rate": 6.042385057471265e-05, + "loss": 1.1226, + "step": 5509 + }, + { + "epoch": 5.94, + "learning_rate": 6.041666666666667e-05, + "loss": 1.1497, + "step": 5510 + }, + { + "epoch": 5.94, + "learning_rate": 6.0409482758620694e-05, + "loss": 1.094, + "step": 5511 + }, + { + "epoch": 5.94, + "learning_rate": 6.0402298850574714e-05, + "loss": 1.026, + "step": 5512 + }, + { + "epoch": 5.94, + "learning_rate": 6.039511494252874e-05, + "loss": 1.1962, + "step": 5513 + }, + { + "epoch": 5.94, + "learning_rate": 6.038793103448276e-05, + "loss": 1.2194, + "step": 5514 + }, + { + "epoch": 5.94, + "learning_rate": 6.038074712643679e-05, + "loss": 1.1638, + "step": 5515 + }, + { + "epoch": 5.94, + "learning_rate": 6.03735632183908e-05, + "loss": 1.0035, + "step": 5516 + }, + { + "epoch": 5.95, + "learning_rate": 6.0366379310344836e-05, + "loss": 1.2732, + "step": 5517 + }, + { + "epoch": 5.95, + "learning_rate": 6.035919540229885e-05, + "loss": 1.1808, + "step": 5518 + }, + { + "epoch": 5.95, + "learning_rate": 6.035201149425288e-05, + "loss": 1.1211, + "step": 5519 + }, + { + "epoch": 5.95, + "learning_rate": 6.03448275862069e-05, + "loss": 1.0481, + "step": 5520 + }, + { + "epoch": 5.95, + "learning_rate": 6.0337643678160924e-05, + "loss": 1.0823, + "step": 5521 + }, + { + "epoch": 5.95, + "learning_rate": 6.0330459770114945e-05, + "loss": 0.9088, + "step": 5522 + }, + { + "epoch": 5.95, + "learning_rate": 6.032327586206897e-05, + "loss": 1.1338, + "step": 5523 + }, + { + "epoch": 5.95, + "learning_rate": 6.031609195402299e-05, + "loss": 1.1568, + "step": 5524 + }, + { + "epoch": 5.95, + "learning_rate": 6.030890804597702e-05, + "loss": 1.0517, + "step": 5525 + }, + { + "epoch": 5.95, + "learning_rate": 6.030172413793104e-05, + "loss": 1.2599, + "step": 5526 + }, + { + "epoch": 5.96, + "learning_rate": 6.029454022988507e-05, + "loss": 1.1267, + "step": 5527 + }, + { + "epoch": 5.96, + "learning_rate": 6.028735632183908e-05, + "loss": 1.1931, + "step": 5528 + }, + { + "epoch": 5.96, + "learning_rate": 6.02801724137931e-05, + "loss": 1.1807, + "step": 5529 + }, + { + "epoch": 5.96, + "learning_rate": 6.027298850574713e-05, + "loss": 1.0577, + "step": 5530 + }, + { + "epoch": 5.96, + "learning_rate": 6.026580459770115e-05, + "loss": 1.0799, + "step": 5531 + }, + { + "epoch": 5.96, + "learning_rate": 6.0258620689655175e-05, + "loss": 1.1626, + "step": 5532 + }, + { + "epoch": 5.96, + "learning_rate": 6.0251436781609195e-05, + "loss": 1.1494, + "step": 5533 + }, + { + "epoch": 5.96, + "learning_rate": 6.024425287356322e-05, + "loss": 1.047, + "step": 5534 + }, + { + "epoch": 5.96, + "learning_rate": 6.023706896551724e-05, + "loss": 1.0219, + "step": 5535 + }, + { + "epoch": 5.97, + "learning_rate": 6.022988505747127e-05, + "loss": 1.0551, + "step": 5536 + }, + { + "epoch": 5.97, + "learning_rate": 6.0222701149425283e-05, + "loss": 1.0248, + "step": 5537 + }, + { + "epoch": 5.97, + "learning_rate": 6.021551724137932e-05, + "loss": 0.9841, + "step": 5538 + }, + { + "epoch": 5.97, + "learning_rate": 6.020833333333333e-05, + "loss": 1.1781, + "step": 5539 + }, + { + "epoch": 5.97, + "learning_rate": 6.0201149425287365e-05, + "loss": 1.0818, + "step": 5540 + }, + { + "epoch": 5.97, + "learning_rate": 6.019396551724138e-05, + "loss": 1.1087, + "step": 5541 + }, + { + "epoch": 5.97, + "learning_rate": 6.0186781609195405e-05, + "loss": 1.1326, + "step": 5542 + }, + { + "epoch": 5.97, + "learning_rate": 6.0179597701149426e-05, + "loss": 0.9828, + "step": 5543 + }, + { + "epoch": 5.97, + "learning_rate": 6.017241379310345e-05, + "loss": 1.1394, + "step": 5544 + }, + { + "epoch": 5.98, + "learning_rate": 6.016522988505747e-05, + "loss": 1.1202, + "step": 5545 + }, + { + "epoch": 5.98, + "learning_rate": 6.01580459770115e-05, + "loss": 1.0304, + "step": 5546 + }, + { + "epoch": 5.98, + "learning_rate": 6.015086206896552e-05, + "loss": 1.0709, + "step": 5547 + }, + { + "epoch": 5.98, + "learning_rate": 6.014367816091955e-05, + "loss": 0.977, + "step": 5548 + }, + { + "epoch": 5.98, + "learning_rate": 6.013649425287357e-05, + "loss": 1.1059, + "step": 5549 + }, + { + "epoch": 5.98, + "learning_rate": 6.0129310344827595e-05, + "loss": 1.1608, + "step": 5550 + }, + { + "epoch": 5.98, + "learning_rate": 6.012212643678161e-05, + "loss": 0.9641, + "step": 5551 + }, + { + "epoch": 5.98, + "learning_rate": 6.011494252873564e-05, + "loss": 1.1772, + "step": 5552 + }, + { + "epoch": 5.98, + "learning_rate": 6.0107758620689656e-05, + "loss": 1.0922, + "step": 5553 + }, + { + "epoch": 5.98, + "learning_rate": 6.0100574712643676e-05, + "loss": 1.1783, + "step": 5554 + }, + { + "epoch": 5.99, + "learning_rate": 6.0093390804597703e-05, + "loss": 1.115, + "step": 5555 + }, + { + "epoch": 5.99, + "learning_rate": 6.0086206896551724e-05, + "loss": 1.0621, + "step": 5556 + }, + { + "epoch": 5.99, + "learning_rate": 6.007902298850575e-05, + "loss": 1.0521, + "step": 5557 + }, + { + "epoch": 5.99, + "learning_rate": 6.007183908045977e-05, + "loss": 1.1833, + "step": 5558 + }, + { + "epoch": 5.99, + "learning_rate": 6.00646551724138e-05, + "loss": 1.0077, + "step": 5559 + }, + { + "epoch": 5.99, + "learning_rate": 6.005747126436781e-05, + "loss": 1.0972, + "step": 5560 + }, + { + "epoch": 5.99, + "learning_rate": 6.0050287356321846e-05, + "loss": 0.9825, + "step": 5561 + }, + { + "epoch": 5.99, + "learning_rate": 6.004310344827586e-05, + "loss": 1.1055, + "step": 5562 + }, + { + "epoch": 5.99, + "learning_rate": 6.003591954022989e-05, + "loss": 0.9601, + "step": 5563 + }, + { + "epoch": 6.0, + "learning_rate": 6.002873563218391e-05, + "loss": 1.0869, + "step": 5564 + }, + { + "epoch": 6.0, + "learning_rate": 6.0021551724137934e-05, + "loss": 1.0258, + "step": 5565 + }, + { + "epoch": 6.0, + "learning_rate": 6.0014367816091954e-05, + "loss": 1.015, + "step": 5566 + }, + { + "epoch": 6.0, + "learning_rate": 6.000718390804598e-05, + "loss": 0.9877, + "step": 5567 + }, + { + "epoch": 6.0, + "learning_rate": 6e-05, + "loss": 1.1982, + "step": 5568 + }, + { + "epoch": 6.0, + "learning_rate": 5.999281609195403e-05, + "loss": 1.0236, + "step": 5569 + }, + { + "epoch": 6.0, + "learning_rate": 5.998563218390805e-05, + "loss": 1.0057, + "step": 5570 + }, + { + "epoch": 6.0, + "learning_rate": 5.9978448275862076e-05, + "loss": 0.9892, + "step": 5571 + }, + { + "epoch": 6.0, + "learning_rate": 5.9971264367816096e-05, + "loss": 0.9694, + "step": 5572 + }, + { + "epoch": 6.01, + "learning_rate": 5.9964080459770123e-05, + "loss": 1.0117, + "step": 5573 + }, + { + "epoch": 6.01, + "learning_rate": 5.995689655172414e-05, + "loss": 1.03, + "step": 5574 + }, + { + "epoch": 6.01, + "learning_rate": 5.994971264367817e-05, + "loss": 1.0375, + "step": 5575 + }, + { + "epoch": 6.01, + "learning_rate": 5.9942528735632184e-05, + "loss": 1.1483, + "step": 5576 + }, + { + "epoch": 6.01, + "learning_rate": 5.993534482758622e-05, + "loss": 1.06, + "step": 5577 + }, + { + "epoch": 6.01, + "learning_rate": 5.992816091954023e-05, + "loss": 1.0307, + "step": 5578 + }, + { + "epoch": 6.01, + "learning_rate": 5.992097701149425e-05, + "loss": 1.0702, + "step": 5579 + }, + { + "epoch": 6.01, + "learning_rate": 5.991379310344828e-05, + "loss": 1.0417, + "step": 5580 + }, + { + "epoch": 6.01, + "learning_rate": 5.99066091954023e-05, + "loss": 0.9722, + "step": 5581 + }, + { + "epoch": 6.02, + "learning_rate": 5.989942528735633e-05, + "loss": 1.0095, + "step": 5582 + }, + { + "epoch": 6.02, + "learning_rate": 5.989224137931034e-05, + "loss": 1.0542, + "step": 5583 + }, + { + "epoch": 6.02, + "learning_rate": 5.9885057471264374e-05, + "loss": 1.0746, + "step": 5584 + }, + { + "epoch": 6.02, + "learning_rate": 5.987787356321839e-05, + "loss": 0.9286, + "step": 5585 + }, + { + "epoch": 6.02, + "learning_rate": 5.987068965517242e-05, + "loss": 1.0598, + "step": 5586 + }, + { + "epoch": 6.02, + "learning_rate": 5.9863505747126435e-05, + "loss": 1.1366, + "step": 5587 + }, + { + "epoch": 6.02, + "learning_rate": 5.985632183908046e-05, + "loss": 1.2048, + "step": 5588 + }, + { + "epoch": 6.02, + "learning_rate": 5.984913793103448e-05, + "loss": 1.1515, + "step": 5589 + }, + { + "epoch": 6.02, + "learning_rate": 5.984195402298851e-05, + "loss": 0.9444, + "step": 5590 + }, + { + "epoch": 6.02, + "learning_rate": 5.983477011494253e-05, + "loss": 0.9898, + "step": 5591 + }, + { + "epoch": 6.03, + "learning_rate": 5.982758620689656e-05, + "loss": 1.1115, + "step": 5592 + }, + { + "epoch": 6.03, + "learning_rate": 5.982040229885058e-05, + "loss": 0.9826, + "step": 5593 + }, + { + "epoch": 6.03, + "learning_rate": 5.9813218390804604e-05, + "loss": 1.0982, + "step": 5594 + }, + { + "epoch": 6.03, + "learning_rate": 5.9806034482758625e-05, + "loss": 1.021, + "step": 5595 + }, + { + "epoch": 6.03, + "learning_rate": 5.979885057471265e-05, + "loss": 0.9549, + "step": 5596 + }, + { + "epoch": 6.03, + "learning_rate": 5.9791666666666665e-05, + "loss": 0.995, + "step": 5597 + }, + { + "epoch": 6.03, + "learning_rate": 5.97844827586207e-05, + "loss": 0.9613, + "step": 5598 + }, + { + "epoch": 6.03, + "learning_rate": 5.977729885057471e-05, + "loss": 1.0945, + "step": 5599 + }, + { + "epoch": 6.03, + "learning_rate": 5.977011494252874e-05, + "loss": 1.0448, + "step": 5600 + }, + { + "epoch": 6.04, + "learning_rate": 5.976293103448276e-05, + "loss": 0.9858, + "step": 5601 + }, + { + "epoch": 6.04, + "learning_rate": 5.975574712643679e-05, + "loss": 1.0439, + "step": 5602 + }, + { + "epoch": 6.04, + "learning_rate": 5.974856321839081e-05, + "loss": 1.0706, + "step": 5603 + }, + { + "epoch": 6.04, + "learning_rate": 5.974137931034483e-05, + "loss": 1.0346, + "step": 5604 + }, + { + "epoch": 6.04, + "learning_rate": 5.9734195402298855e-05, + "loss": 1.0, + "step": 5605 + }, + { + "epoch": 6.04, + "learning_rate": 5.972701149425287e-05, + "loss": 1.0787, + "step": 5606 + }, + { + "epoch": 6.04, + "learning_rate": 5.97198275862069e-05, + "loss": 1.1657, + "step": 5607 + }, + { + "epoch": 6.04, + "learning_rate": 5.9712643678160916e-05, + "loss": 0.9354, + "step": 5608 + }, + { + "epoch": 6.04, + "learning_rate": 5.970545977011495e-05, + "loss": 0.9961, + "step": 5609 + }, + { + "epoch": 6.05, + "learning_rate": 5.9698275862068963e-05, + "loss": 1.0987, + "step": 5610 + }, + { + "epoch": 6.05, + "learning_rate": 5.969109195402299e-05, + "loss": 1.0613, + "step": 5611 + }, + { + "epoch": 6.05, + "learning_rate": 5.968390804597701e-05, + "loss": 1.0613, + "step": 5612 + }, + { + "epoch": 6.05, + "learning_rate": 5.967672413793104e-05, + "loss": 1.1184, + "step": 5613 + }, + { + "epoch": 6.05, + "learning_rate": 5.966954022988506e-05, + "loss": 0.941, + "step": 5614 + }, + { + "epoch": 6.05, + "learning_rate": 5.9662356321839085e-05, + "loss": 1.1046, + "step": 5615 + }, + { + "epoch": 6.05, + "learning_rate": 5.9655172413793106e-05, + "loss": 1.014, + "step": 5616 + }, + { + "epoch": 6.05, + "learning_rate": 5.964798850574713e-05, + "loss": 1.0842, + "step": 5617 + }, + { + "epoch": 6.05, + "learning_rate": 5.964080459770115e-05, + "loss": 0.899, + "step": 5618 + }, + { + "epoch": 6.05, + "learning_rate": 5.963362068965518e-05, + "loss": 0.9635, + "step": 5619 + }, + { + "epoch": 6.06, + "learning_rate": 5.9626436781609194e-05, + "loss": 1.2185, + "step": 5620 + }, + { + "epoch": 6.06, + "learning_rate": 5.961925287356323e-05, + "loss": 0.9841, + "step": 5621 + }, + { + "epoch": 6.06, + "learning_rate": 5.961206896551724e-05, + "loss": 0.96, + "step": 5622 + }, + { + "epoch": 6.06, + "learning_rate": 5.960488505747127e-05, + "loss": 1.1652, + "step": 5623 + }, + { + "epoch": 6.06, + "learning_rate": 5.959770114942529e-05, + "loss": 1.0121, + "step": 5624 + }, + { + "epoch": 6.06, + "learning_rate": 5.9590517241379316e-05, + "loss": 1.08, + "step": 5625 + }, + { + "epoch": 6.06, + "learning_rate": 5.9583333333333336e-05, + "loss": 1.0588, + "step": 5626 + }, + { + "epoch": 6.06, + "learning_rate": 5.957614942528736e-05, + "loss": 1.0183, + "step": 5627 + }, + { + "epoch": 6.06, + "learning_rate": 5.9568965517241383e-05, + "loss": 1.0248, + "step": 5628 + }, + { + "epoch": 6.07, + "learning_rate": 5.956178160919541e-05, + "loss": 1.1527, + "step": 5629 + }, + { + "epoch": 6.07, + "learning_rate": 5.955459770114943e-05, + "loss": 1.0815, + "step": 5630 + }, + { + "epoch": 6.07, + "learning_rate": 5.9547413793103444e-05, + "loss": 0.985, + "step": 5631 + }, + { + "epoch": 6.07, + "learning_rate": 5.954022988505747e-05, + "loss": 1.0529, + "step": 5632 + }, + { + "epoch": 6.07, + "learning_rate": 5.953304597701149e-05, + "loss": 1.0764, + "step": 5633 + }, + { + "epoch": 6.07, + "learning_rate": 5.952586206896552e-05, + "loss": 0.9371, + "step": 5634 + }, + { + "epoch": 6.07, + "learning_rate": 5.951867816091954e-05, + "loss": 1.0577, + "step": 5635 + }, + { + "epoch": 6.07, + "learning_rate": 5.9511494252873566e-05, + "loss": 1.0737, + "step": 5636 + }, + { + "epoch": 6.07, + "learning_rate": 5.950431034482759e-05, + "loss": 1.203, + "step": 5637 + }, + { + "epoch": 6.08, + "learning_rate": 5.9497126436781614e-05, + "loss": 1.097, + "step": 5638 + }, + { + "epoch": 6.08, + "learning_rate": 5.9489942528735634e-05, + "loss": 1.0106, + "step": 5639 + }, + { + "epoch": 6.08, + "learning_rate": 5.948275862068966e-05, + "loss": 1.0958, + "step": 5640 + }, + { + "epoch": 6.08, + "learning_rate": 5.9475574712643675e-05, + "loss": 0.9994, + "step": 5641 + }, + { + "epoch": 6.08, + "learning_rate": 5.946839080459771e-05, + "loss": 0.945, + "step": 5642 + }, + { + "epoch": 6.08, + "learning_rate": 5.946120689655172e-05, + "loss": 1.0502, + "step": 5643 + }, + { + "epoch": 6.08, + "learning_rate": 5.9454022988505756e-05, + "loss": 1.1365, + "step": 5644 + }, + { + "epoch": 6.08, + "learning_rate": 5.944683908045977e-05, + "loss": 1.0124, + "step": 5645 + }, + { + "epoch": 6.08, + "learning_rate": 5.94396551724138e-05, + "loss": 0.9997, + "step": 5646 + }, + { + "epoch": 6.09, + "learning_rate": 5.943247126436782e-05, + "loss": 1.0084, + "step": 5647 + }, + { + "epoch": 6.09, + "learning_rate": 5.9425287356321844e-05, + "loss": 0.9663, + "step": 5648 + }, + { + "epoch": 6.09, + "learning_rate": 5.9418103448275864e-05, + "loss": 1.0161, + "step": 5649 + }, + { + "epoch": 6.09, + "learning_rate": 5.941091954022989e-05, + "loss": 1.142, + "step": 5650 + }, + { + "epoch": 6.09, + "learning_rate": 5.940373563218391e-05, + "loss": 1.0924, + "step": 5651 + }, + { + "epoch": 6.09, + "learning_rate": 5.939655172413794e-05, + "loss": 1.006, + "step": 5652 + }, + { + "epoch": 6.09, + "learning_rate": 5.938936781609196e-05, + "loss": 1.0901, + "step": 5653 + }, + { + "epoch": 6.09, + "learning_rate": 5.9382183908045986e-05, + "loss": 0.8942, + "step": 5654 + }, + { + "epoch": 6.09, + "learning_rate": 5.9375e-05, + "loss": 1.0184, + "step": 5655 + }, + { + "epoch": 6.09, + "learning_rate": 5.936781609195402e-05, + "loss": 1.0124, + "step": 5656 + }, + { + "epoch": 6.1, + "learning_rate": 5.936063218390805e-05, + "loss": 1.0462, + "step": 5657 + }, + { + "epoch": 6.1, + "learning_rate": 5.935344827586207e-05, + "loss": 1.0903, + "step": 5658 + }, + { + "epoch": 6.1, + "learning_rate": 5.9346264367816095e-05, + "loss": 1.1174, + "step": 5659 + }, + { + "epoch": 6.1, + "learning_rate": 5.9339080459770115e-05, + "loss": 1.0506, + "step": 5660 + }, + { + "epoch": 6.1, + "learning_rate": 5.933189655172414e-05, + "loss": 0.9883, + "step": 5661 + }, + { + "epoch": 6.1, + "learning_rate": 5.932471264367816e-05, + "loss": 1.1676, + "step": 5662 + }, + { + "epoch": 6.1, + "learning_rate": 5.931752873563219e-05, + "loss": 1.1317, + "step": 5663 + }, + { + "epoch": 6.1, + "learning_rate": 5.93103448275862e-05, + "loss": 1.0826, + "step": 5664 + }, + { + "epoch": 6.1, + "learning_rate": 5.930316091954024e-05, + "loss": 1.0152, + "step": 5665 + }, + { + "epoch": 6.11, + "learning_rate": 5.929597701149425e-05, + "loss": 1.1665, + "step": 5666 + }, + { + "epoch": 6.11, + "learning_rate": 5.9288793103448284e-05, + "loss": 1.0048, + "step": 5667 + }, + { + "epoch": 6.11, + "learning_rate": 5.92816091954023e-05, + "loss": 1.0494, + "step": 5668 + }, + { + "epoch": 6.11, + "learning_rate": 5.9274425287356325e-05, + "loss": 0.9658, + "step": 5669 + }, + { + "epoch": 6.11, + "learning_rate": 5.9267241379310345e-05, + "loss": 1.0253, + "step": 5670 + }, + { + "epoch": 6.11, + "learning_rate": 5.926005747126437e-05, + "loss": 1.0628, + "step": 5671 + }, + { + "epoch": 6.11, + "learning_rate": 5.925287356321839e-05, + "loss": 1.0566, + "step": 5672 + }, + { + "epoch": 6.11, + "learning_rate": 5.924568965517242e-05, + "loss": 0.9913, + "step": 5673 + }, + { + "epoch": 6.11, + "learning_rate": 5.923850574712644e-05, + "loss": 1.0958, + "step": 5674 + }, + { + "epoch": 6.12, + "learning_rate": 5.923132183908047e-05, + "loss": 1.0772, + "step": 5675 + }, + { + "epoch": 6.12, + "learning_rate": 5.922413793103449e-05, + "loss": 1.1485, + "step": 5676 + }, + { + "epoch": 6.12, + "learning_rate": 5.9216954022988515e-05, + "loss": 1.0009, + "step": 5677 + }, + { + "epoch": 6.12, + "learning_rate": 5.920977011494253e-05, + "loss": 1.0864, + "step": 5678 + }, + { + "epoch": 6.12, + "learning_rate": 5.920258620689656e-05, + "loss": 0.9674, + "step": 5679 + }, + { + "epoch": 6.12, + "learning_rate": 5.9195402298850576e-05, + "loss": 1.1205, + "step": 5680 + }, + { + "epoch": 6.12, + "learning_rate": 5.9188218390804596e-05, + "loss": 1.0828, + "step": 5681 + }, + { + "epoch": 6.12, + "learning_rate": 5.918103448275862e-05, + "loss": 0.9952, + "step": 5682 + }, + { + "epoch": 6.12, + "learning_rate": 5.9173850574712643e-05, + "loss": 1.0522, + "step": 5683 + }, + { + "epoch": 6.12, + "learning_rate": 5.916666666666667e-05, + "loss": 1.0545, + "step": 5684 + }, + { + "epoch": 6.13, + "learning_rate": 5.915948275862069e-05, + "loss": 1.0652, + "step": 5685 + }, + { + "epoch": 6.13, + "learning_rate": 5.915229885057472e-05, + "loss": 0.8521, + "step": 5686 + }, + { + "epoch": 6.13, + "learning_rate": 5.914511494252873e-05, + "loss": 1.1024, + "step": 5687 + }, + { + "epoch": 6.13, + "learning_rate": 5.9137931034482765e-05, + "loss": 1.0815, + "step": 5688 + }, + { + "epoch": 6.13, + "learning_rate": 5.913074712643678e-05, + "loss": 0.9694, + "step": 5689 + }, + { + "epoch": 6.13, + "learning_rate": 5.912356321839081e-05, + "loss": 1.0173, + "step": 5690 + }, + { + "epoch": 6.13, + "learning_rate": 5.9116379310344826e-05, + "loss": 1.1315, + "step": 5691 + }, + { + "epoch": 6.13, + "learning_rate": 5.9109195402298853e-05, + "loss": 1.1071, + "step": 5692 + }, + { + "epoch": 6.13, + "learning_rate": 5.9102011494252874e-05, + "loss": 1.0078, + "step": 5693 + }, + { + "epoch": 6.14, + "learning_rate": 5.90948275862069e-05, + "loss": 1.0243, + "step": 5694 + }, + { + "epoch": 6.14, + "learning_rate": 5.908764367816092e-05, + "loss": 0.9662, + "step": 5695 + }, + { + "epoch": 6.14, + "learning_rate": 5.908045977011495e-05, + "loss": 0.9872, + "step": 5696 + }, + { + "epoch": 6.14, + "learning_rate": 5.907327586206897e-05, + "loss": 1.0857, + "step": 5697 + }, + { + "epoch": 6.14, + "learning_rate": 5.9066091954022996e-05, + "loss": 0.9242, + "step": 5698 + }, + { + "epoch": 6.14, + "learning_rate": 5.9058908045977016e-05, + "loss": 1.1213, + "step": 5699 + }, + { + "epoch": 6.14, + "learning_rate": 5.905172413793104e-05, + "loss": 1.0044, + "step": 5700 + }, + { + "epoch": 6.14, + "learning_rate": 5.904454022988506e-05, + "loss": 0.9805, + "step": 5701 + }, + { + "epoch": 6.14, + "learning_rate": 5.903735632183909e-05, + "loss": 1.0026, + "step": 5702 + }, + { + "epoch": 6.15, + "learning_rate": 5.9030172413793104e-05, + "loss": 1.0295, + "step": 5703 + }, + { + "epoch": 6.15, + "learning_rate": 5.902298850574713e-05, + "loss": 0.8396, + "step": 5704 + }, + { + "epoch": 6.15, + "learning_rate": 5.901580459770115e-05, + "loss": 1.0026, + "step": 5705 + }, + { + "epoch": 6.15, + "learning_rate": 5.900862068965518e-05, + "loss": 1.118, + "step": 5706 + }, + { + "epoch": 6.15, + "learning_rate": 5.90014367816092e-05, + "loss": 0.874, + "step": 5707 + }, + { + "epoch": 6.15, + "learning_rate": 5.899425287356322e-05, + "loss": 1.0512, + "step": 5708 + }, + { + "epoch": 6.15, + "learning_rate": 5.8987068965517246e-05, + "loss": 1.0307, + "step": 5709 + }, + { + "epoch": 6.15, + "learning_rate": 5.897988505747126e-05, + "loss": 1.0573, + "step": 5710 + }, + { + "epoch": 6.15, + "learning_rate": 5.8972701149425294e-05, + "loss": 1.1149, + "step": 5711 + }, + { + "epoch": 6.16, + "learning_rate": 5.896551724137931e-05, + "loss": 1.1389, + "step": 5712 + }, + { + "epoch": 6.16, + "learning_rate": 5.8958333333333334e-05, + "loss": 1.0619, + "step": 5713 + }, + { + "epoch": 6.16, + "learning_rate": 5.8951149425287355e-05, + "loss": 1.2145, + "step": 5714 + }, + { + "epoch": 6.16, + "learning_rate": 5.894396551724138e-05, + "loss": 1.07, + "step": 5715 + }, + { + "epoch": 6.16, + "learning_rate": 5.89367816091954e-05, + "loss": 1.0426, + "step": 5716 + }, + { + "epoch": 6.16, + "learning_rate": 5.892959770114943e-05, + "loss": 1.1604, + "step": 5717 + }, + { + "epoch": 6.16, + "learning_rate": 5.892241379310345e-05, + "loss": 0.99, + "step": 5718 + }, + { + "epoch": 6.16, + "learning_rate": 5.891522988505748e-05, + "loss": 1.0096, + "step": 5719 + }, + { + "epoch": 6.16, + "learning_rate": 5.89080459770115e-05, + "loss": 0.9534, + "step": 5720 + }, + { + "epoch": 6.16, + "learning_rate": 5.8900862068965524e-05, + "loss": 1.0903, + "step": 5721 + }, + { + "epoch": 6.17, + "learning_rate": 5.889367816091954e-05, + "loss": 0.9599, + "step": 5722 + }, + { + "epoch": 6.17, + "learning_rate": 5.888649425287357e-05, + "loss": 0.9459, + "step": 5723 + }, + { + "epoch": 6.17, + "learning_rate": 5.8879310344827585e-05, + "loss": 1.1301, + "step": 5724 + }, + { + "epoch": 6.17, + "learning_rate": 5.887212643678162e-05, + "loss": 1.124, + "step": 5725 + }, + { + "epoch": 6.17, + "learning_rate": 5.886494252873563e-05, + "loss": 1.1191, + "step": 5726 + }, + { + "epoch": 6.17, + "learning_rate": 5.885775862068966e-05, + "loss": 1.0993, + "step": 5727 + }, + { + "epoch": 6.17, + "learning_rate": 5.885057471264368e-05, + "loss": 1.085, + "step": 5728 + }, + { + "epoch": 6.17, + "learning_rate": 5.884339080459771e-05, + "loss": 1.0297, + "step": 5729 + }, + { + "epoch": 6.17, + "learning_rate": 5.883620689655173e-05, + "loss": 0.9604, + "step": 5730 + }, + { + "epoch": 6.18, + "learning_rate": 5.8829022988505754e-05, + "loss": 1.1096, + "step": 5731 + }, + { + "epoch": 6.18, + "learning_rate": 5.8821839080459775e-05, + "loss": 1.105, + "step": 5732 + }, + { + "epoch": 6.18, + "learning_rate": 5.881465517241379e-05, + "loss": 0.9755, + "step": 5733 + }, + { + "epoch": 6.18, + "learning_rate": 5.880747126436782e-05, + "loss": 1.098, + "step": 5734 + }, + { + "epoch": 6.18, + "learning_rate": 5.8800287356321836e-05, + "loss": 0.9542, + "step": 5735 + }, + { + "epoch": 6.18, + "learning_rate": 5.879310344827586e-05, + "loss": 1.0458, + "step": 5736 + }, + { + "epoch": 6.18, + "learning_rate": 5.878591954022988e-05, + "loss": 1.1621, + "step": 5737 + }, + { + "epoch": 6.18, + "learning_rate": 5.877873563218391e-05, + "loss": 1.013, + "step": 5738 + }, + { + "epoch": 6.18, + "learning_rate": 5.877155172413793e-05, + "loss": 1.0485, + "step": 5739 + }, + { + "epoch": 6.19, + "learning_rate": 5.876436781609196e-05, + "loss": 0.9751, + "step": 5740 + }, + { + "epoch": 6.19, + "learning_rate": 5.875718390804598e-05, + "loss": 1.0132, + "step": 5741 + }, + { + "epoch": 6.19, + "learning_rate": 5.8750000000000005e-05, + "loss": 0.937, + "step": 5742 + }, + { + "epoch": 6.19, + "learning_rate": 5.8742816091954025e-05, + "loss": 1.035, + "step": 5743 + }, + { + "epoch": 6.19, + "learning_rate": 5.873563218390805e-05, + "loss": 1.0973, + "step": 5744 + }, + { + "epoch": 6.19, + "learning_rate": 5.8728448275862066e-05, + "loss": 1.0482, + "step": 5745 + }, + { + "epoch": 6.19, + "learning_rate": 5.87212643678161e-05, + "loss": 1.0483, + "step": 5746 + }, + { + "epoch": 6.19, + "learning_rate": 5.8714080459770113e-05, + "loss": 1.0326, + "step": 5747 + }, + { + "epoch": 6.19, + "learning_rate": 5.870689655172415e-05, + "loss": 1.161, + "step": 5748 + }, + { + "epoch": 6.2, + "learning_rate": 5.869971264367816e-05, + "loss": 1.0795, + "step": 5749 + }, + { + "epoch": 6.2, + "learning_rate": 5.869252873563219e-05, + "loss": 1.0934, + "step": 5750 + }, + { + "epoch": 6.2, + "eval_loss": 1.130831241607666, + "eval_runtime": 174.9975, + "eval_samples_per_second": 127.259, + "eval_steps_per_second": 0.663, + "step": 5750 + }, + { + "epoch": 6.2, + "learning_rate": 5.868534482758621e-05, + "loss": 0.9743, + "step": 5751 + }, + { + "epoch": 6.2, + "learning_rate": 5.8678160919540235e-05, + "loss": 1.0365, + "step": 5752 + }, + { + "epoch": 6.2, + "learning_rate": 5.8670977011494256e-05, + "loss": 0.9753, + "step": 5753 + }, + { + "epoch": 6.2, + "learning_rate": 5.866379310344828e-05, + "loss": 0.9607, + "step": 5754 + }, + { + "epoch": 6.2, + "learning_rate": 5.86566091954023e-05, + "loss": 1.0289, + "step": 5755 + }, + { + "epoch": 6.2, + "learning_rate": 5.864942528735633e-05, + "loss": 1.0822, + "step": 5756 + }, + { + "epoch": 6.2, + "learning_rate": 5.864224137931035e-05, + "loss": 1.0452, + "step": 5757 + }, + { + "epoch": 6.2, + "learning_rate": 5.8635057471264364e-05, + "loss": 1.1134, + "step": 5758 + }, + { + "epoch": 6.21, + "learning_rate": 5.862787356321839e-05, + "loss": 0.9971, + "step": 5759 + }, + { + "epoch": 6.21, + "learning_rate": 5.862068965517241e-05, + "loss": 1.1085, + "step": 5760 + }, + { + "epoch": 6.21, + "learning_rate": 5.861350574712644e-05, + "loss": 0.9474, + "step": 5761 + }, + { + "epoch": 6.21, + "learning_rate": 5.860632183908046e-05, + "loss": 1.117, + "step": 5762 + }, + { + "epoch": 6.21, + "learning_rate": 5.8599137931034486e-05, + "loss": 1.1034, + "step": 5763 + }, + { + "epoch": 6.21, + "learning_rate": 5.8591954022988506e-05, + "loss": 1.0277, + "step": 5764 + }, + { + "epoch": 6.21, + "learning_rate": 5.8584770114942533e-05, + "loss": 1.1139, + "step": 5765 + }, + { + "epoch": 6.21, + "learning_rate": 5.8577586206896554e-05, + "loss": 1.1232, + "step": 5766 + }, + { + "epoch": 6.21, + "learning_rate": 5.857040229885058e-05, + "loss": 1.1, + "step": 5767 + }, + { + "epoch": 6.22, + "learning_rate": 5.8563218390804594e-05, + "loss": 1.0679, + "step": 5768 + }, + { + "epoch": 6.22, + "learning_rate": 5.855603448275863e-05, + "loss": 1.0861, + "step": 5769 + }, + { + "epoch": 6.22, + "learning_rate": 5.854885057471264e-05, + "loss": 0.9757, + "step": 5770 + }, + { + "epoch": 6.22, + "learning_rate": 5.8541666666666676e-05, + "loss": 1.1265, + "step": 5771 + }, + { + "epoch": 6.22, + "learning_rate": 5.853448275862069e-05, + "loss": 1.1062, + "step": 5772 + }, + { + "epoch": 6.22, + "learning_rate": 5.8527298850574716e-05, + "loss": 0.9979, + "step": 5773 + }, + { + "epoch": 6.22, + "learning_rate": 5.852011494252874e-05, + "loss": 0.9742, + "step": 5774 + }, + { + "epoch": 6.22, + "learning_rate": 5.8512931034482764e-05, + "loss": 0.9663, + "step": 5775 + }, + { + "epoch": 6.22, + "learning_rate": 5.8505747126436784e-05, + "loss": 1.1025, + "step": 5776 + }, + { + "epoch": 6.23, + "learning_rate": 5.849856321839081e-05, + "loss": 0.9972, + "step": 5777 + }, + { + "epoch": 6.23, + "learning_rate": 5.849137931034483e-05, + "loss": 1.0396, + "step": 5778 + }, + { + "epoch": 6.23, + "learning_rate": 5.848419540229886e-05, + "loss": 1.0569, + "step": 5779 + }, + { + "epoch": 6.23, + "learning_rate": 5.847701149425288e-05, + "loss": 0.8618, + "step": 5780 + }, + { + "epoch": 6.23, + "learning_rate": 5.8469827586206906e-05, + "loss": 0.9411, + "step": 5781 + }, + { + "epoch": 6.23, + "learning_rate": 5.846264367816092e-05, + "loss": 1.1253, + "step": 5782 + }, + { + "epoch": 6.23, + "learning_rate": 5.845545977011494e-05, + "loss": 1.0042, + "step": 5783 + }, + { + "epoch": 6.23, + "learning_rate": 5.844827586206897e-05, + "loss": 1.0362, + "step": 5784 + }, + { + "epoch": 6.23, + "learning_rate": 5.844109195402299e-05, + "loss": 1.0565, + "step": 5785 + }, + { + "epoch": 6.23, + "learning_rate": 5.8433908045977014e-05, + "loss": 0.9755, + "step": 5786 + }, + { + "epoch": 6.24, + "learning_rate": 5.8426724137931035e-05, + "loss": 0.9711, + "step": 5787 + }, + { + "epoch": 6.24, + "learning_rate": 5.841954022988506e-05, + "loss": 1.1372, + "step": 5788 + }, + { + "epoch": 6.24, + "learning_rate": 5.841235632183908e-05, + "loss": 0.9476, + "step": 5789 + }, + { + "epoch": 6.24, + "learning_rate": 5.840517241379311e-05, + "loss": 1.1559, + "step": 5790 + }, + { + "epoch": 6.24, + "learning_rate": 5.839798850574712e-05, + "loss": 1.0165, + "step": 5791 + }, + { + "epoch": 6.24, + "learning_rate": 5.839080459770116e-05, + "loss": 1.1802, + "step": 5792 + }, + { + "epoch": 6.24, + "learning_rate": 5.838362068965517e-05, + "loss": 1.0403, + "step": 5793 + }, + { + "epoch": 6.24, + "learning_rate": 5.83764367816092e-05, + "loss": 0.9368, + "step": 5794 + }, + { + "epoch": 6.24, + "learning_rate": 5.836925287356322e-05, + "loss": 0.9167, + "step": 5795 + }, + { + "epoch": 6.25, + "learning_rate": 5.8362068965517245e-05, + "loss": 1.1061, + "step": 5796 + }, + { + "epoch": 6.25, + "learning_rate": 5.8354885057471265e-05, + "loss": 1.0463, + "step": 5797 + }, + { + "epoch": 6.25, + "learning_rate": 5.834770114942529e-05, + "loss": 1.0001, + "step": 5798 + }, + { + "epoch": 6.25, + "learning_rate": 5.834051724137931e-05, + "loss": 0.9601, + "step": 5799 + }, + { + "epoch": 6.25, + "learning_rate": 5.833333333333334e-05, + "loss": 0.9987, + "step": 5800 + }, + { + "epoch": 6.25, + "learning_rate": 5.832614942528736e-05, + "loss": 1.1015, + "step": 5801 + }, + { + "epoch": 6.25, + "learning_rate": 5.831896551724139e-05, + "loss": 1.1004, + "step": 5802 + }, + { + "epoch": 6.25, + "learning_rate": 5.831178160919541e-05, + "loss": 1.0328, + "step": 5803 + }, + { + "epoch": 6.25, + "learning_rate": 5.8304597701149434e-05, + "loss": 0.9641, + "step": 5804 + }, + { + "epoch": 6.26, + "learning_rate": 5.829741379310345e-05, + "loss": 1.0563, + "step": 5805 + }, + { + "epoch": 6.26, + "learning_rate": 5.829022988505748e-05, + "loss": 1.037, + "step": 5806 + }, + { + "epoch": 6.26, + "learning_rate": 5.8283045977011495e-05, + "loss": 0.9175, + "step": 5807 + }, + { + "epoch": 6.26, + "learning_rate": 5.827586206896552e-05, + "loss": 1.0978, + "step": 5808 + }, + { + "epoch": 6.26, + "learning_rate": 5.826867816091954e-05, + "loss": 1.0062, + "step": 5809 + }, + { + "epoch": 6.26, + "learning_rate": 5.826149425287356e-05, + "loss": 0.8509, + "step": 5810 + }, + { + "epoch": 6.26, + "learning_rate": 5.825431034482759e-05, + "loss": 0.9879, + "step": 5811 + }, + { + "epoch": 6.26, + "learning_rate": 5.824712643678161e-05, + "loss": 1.0784, + "step": 5812 + }, + { + "epoch": 6.26, + "learning_rate": 5.823994252873564e-05, + "loss": 1.0696, + "step": 5813 + }, + { + "epoch": 6.27, + "learning_rate": 5.823275862068965e-05, + "loss": 0.972, + "step": 5814 + }, + { + "epoch": 6.27, + "learning_rate": 5.8225574712643685e-05, + "loss": 1.1314, + "step": 5815 + }, + { + "epoch": 6.27, + "learning_rate": 5.82183908045977e-05, + "loss": 1.0039, + "step": 5816 + }, + { + "epoch": 6.27, + "learning_rate": 5.8211206896551726e-05, + "loss": 1.005, + "step": 5817 + }, + { + "epoch": 6.27, + "learning_rate": 5.8204022988505746e-05, + "loss": 1.1096, + "step": 5818 + }, + { + "epoch": 6.27, + "learning_rate": 5.819683908045977e-05, + "loss": 1.0726, + "step": 5819 + }, + { + "epoch": 6.27, + "learning_rate": 5.818965517241379e-05, + "loss": 1.0228, + "step": 5820 + }, + { + "epoch": 6.27, + "learning_rate": 5.818247126436782e-05, + "loss": 0.9445, + "step": 5821 + }, + { + "epoch": 6.27, + "learning_rate": 5.817528735632184e-05, + "loss": 0.9766, + "step": 5822 + }, + { + "epoch": 6.27, + "learning_rate": 5.816810344827587e-05, + "loss": 1.129, + "step": 5823 + }, + { + "epoch": 6.28, + "learning_rate": 5.816091954022989e-05, + "loss": 1.0291, + "step": 5824 + }, + { + "epoch": 6.28, + "learning_rate": 5.8153735632183915e-05, + "loss": 1.0067, + "step": 5825 + }, + { + "epoch": 6.28, + "learning_rate": 5.814655172413793e-05, + "loss": 0.9747, + "step": 5826 + }, + { + "epoch": 6.28, + "learning_rate": 5.813936781609196e-05, + "loss": 1.0941, + "step": 5827 + }, + { + "epoch": 6.28, + "learning_rate": 5.8132183908045976e-05, + "loss": 1.0912, + "step": 5828 + }, + { + "epoch": 6.28, + "learning_rate": 5.812500000000001e-05, + "loss": 1.0625, + "step": 5829 + }, + { + "epoch": 6.28, + "learning_rate": 5.8117816091954024e-05, + "loss": 0.9467, + "step": 5830 + }, + { + "epoch": 6.28, + "learning_rate": 5.811063218390805e-05, + "loss": 1.1609, + "step": 5831 + }, + { + "epoch": 6.28, + "learning_rate": 5.810344827586207e-05, + "loss": 1.0738, + "step": 5832 + }, + { + "epoch": 6.29, + "learning_rate": 5.80962643678161e-05, + "loss": 1.1052, + "step": 5833 + }, + { + "epoch": 6.29, + "learning_rate": 5.808908045977012e-05, + "loss": 1.0185, + "step": 5834 + }, + { + "epoch": 6.29, + "learning_rate": 5.808189655172413e-05, + "loss": 1.1247, + "step": 5835 + }, + { + "epoch": 6.29, + "learning_rate": 5.8074712643678166e-05, + "loss": 1.0644, + "step": 5836 + }, + { + "epoch": 6.29, + "learning_rate": 5.806752873563218e-05, + "loss": 1.0555, + "step": 5837 + }, + { + "epoch": 6.29, + "learning_rate": 5.806034482758621e-05, + "loss": 1.0954, + "step": 5838 + }, + { + "epoch": 6.29, + "learning_rate": 5.805316091954023e-05, + "loss": 0.9515, + "step": 5839 + }, + { + "epoch": 6.29, + "learning_rate": 5.8045977011494254e-05, + "loss": 1.007, + "step": 5840 + }, + { + "epoch": 6.29, + "learning_rate": 5.8038793103448274e-05, + "loss": 0.8981, + "step": 5841 + }, + { + "epoch": 6.3, + "learning_rate": 5.80316091954023e-05, + "loss": 1.0443, + "step": 5842 + }, + { + "epoch": 6.3, + "learning_rate": 5.802442528735632e-05, + "loss": 1.0703, + "step": 5843 + }, + { + "epoch": 6.3, + "learning_rate": 5.801724137931035e-05, + "loss": 1.1203, + "step": 5844 + }, + { + "epoch": 6.3, + "learning_rate": 5.801005747126437e-05, + "loss": 1.0049, + "step": 5845 + }, + { + "epoch": 6.3, + "learning_rate": 5.8002873563218396e-05, + "loss": 0.9784, + "step": 5846 + }, + { + "epoch": 6.3, + "learning_rate": 5.7995689655172417e-05, + "loss": 1.0304, + "step": 5847 + }, + { + "epoch": 6.3, + "learning_rate": 5.7988505747126444e-05, + "loss": 1.0952, + "step": 5848 + }, + { + "epoch": 6.3, + "learning_rate": 5.798132183908046e-05, + "loss": 1.1092, + "step": 5849 + }, + { + "epoch": 6.3, + "learning_rate": 5.797413793103449e-05, + "loss": 1.0801, + "step": 5850 + }, + { + "epoch": 6.3, + "learning_rate": 5.7966954022988505e-05, + "loss": 1.088, + "step": 5851 + }, + { + "epoch": 6.31, + "learning_rate": 5.795977011494254e-05, + "loss": 1.2121, + "step": 5852 + }, + { + "epoch": 6.31, + "learning_rate": 5.795258620689655e-05, + "loss": 1.0028, + "step": 5853 + }, + { + "epoch": 6.31, + "learning_rate": 5.794540229885058e-05, + "loss": 1.0491, + "step": 5854 + }, + { + "epoch": 6.31, + "learning_rate": 5.79382183908046e-05, + "loss": 1.1225, + "step": 5855 + }, + { + "epoch": 6.31, + "learning_rate": 5.7931034482758627e-05, + "loss": 1.0287, + "step": 5856 + }, + { + "epoch": 6.31, + "learning_rate": 5.792385057471265e-05, + "loss": 1.0631, + "step": 5857 + }, + { + "epoch": 6.31, + "learning_rate": 5.7916666666666674e-05, + "loss": 1.1331, + "step": 5858 + }, + { + "epoch": 6.31, + "learning_rate": 5.7909482758620694e-05, + "loss": 1.0838, + "step": 5859 + }, + { + "epoch": 6.31, + "learning_rate": 5.790229885057471e-05, + "loss": 1.0981, + "step": 5860 + }, + { + "epoch": 6.32, + "learning_rate": 5.789511494252874e-05, + "loss": 0.9271, + "step": 5861 + }, + { + "epoch": 6.32, + "learning_rate": 5.7887931034482755e-05, + "loss": 1.0571, + "step": 5862 + }, + { + "epoch": 6.32, + "learning_rate": 5.788074712643678e-05, + "loss": 1.1911, + "step": 5863 + }, + { + "epoch": 6.32, + "learning_rate": 5.78735632183908e-05, + "loss": 0.9391, + "step": 5864 + }, + { + "epoch": 6.32, + "learning_rate": 5.786637931034483e-05, + "loss": 1.0929, + "step": 5865 + }, + { + "epoch": 6.32, + "learning_rate": 5.785919540229885e-05, + "loss": 1.0826, + "step": 5866 + }, + { + "epoch": 6.32, + "learning_rate": 5.785201149425288e-05, + "loss": 0.974, + "step": 5867 + }, + { + "epoch": 6.32, + "learning_rate": 5.78448275862069e-05, + "loss": 0.882, + "step": 5868 + }, + { + "epoch": 6.32, + "learning_rate": 5.7837643678160925e-05, + "loss": 0.995, + "step": 5869 + }, + { + "epoch": 6.33, + "learning_rate": 5.7830459770114945e-05, + "loss": 1.2428, + "step": 5870 + }, + { + "epoch": 6.33, + "learning_rate": 5.782327586206897e-05, + "loss": 1.1322, + "step": 5871 + }, + { + "epoch": 6.33, + "learning_rate": 5.7816091954022986e-05, + "loss": 1.061, + "step": 5872 + }, + { + "epoch": 6.33, + "learning_rate": 5.780890804597702e-05, + "loss": 1.176, + "step": 5873 + }, + { + "epoch": 6.33, + "learning_rate": 5.780172413793103e-05, + "loss": 1.0045, + "step": 5874 + }, + { + "epoch": 6.33, + "learning_rate": 5.779454022988507e-05, + "loss": 1.1642, + "step": 5875 + }, + { + "epoch": 6.33, + "learning_rate": 5.778735632183908e-05, + "loss": 1.0444, + "step": 5876 + }, + { + "epoch": 6.33, + "learning_rate": 5.778017241379311e-05, + "loss": 1.0711, + "step": 5877 + }, + { + "epoch": 6.33, + "learning_rate": 5.777298850574713e-05, + "loss": 1.0063, + "step": 5878 + }, + { + "epoch": 6.34, + "learning_rate": 5.7765804597701155e-05, + "loss": 0.9733, + "step": 5879 + }, + { + "epoch": 6.34, + "learning_rate": 5.7758620689655175e-05, + "loss": 1.0153, + "step": 5880 + }, + { + "epoch": 6.34, + "learning_rate": 5.77514367816092e-05, + "loss": 1.0097, + "step": 5881 + }, + { + "epoch": 6.34, + "learning_rate": 5.774425287356322e-05, + "loss": 1.0651, + "step": 5882 + }, + { + "epoch": 6.34, + "learning_rate": 5.773706896551725e-05, + "loss": 1.1449, + "step": 5883 + }, + { + "epoch": 6.34, + "learning_rate": 5.772988505747127e-05, + "loss": 1.0829, + "step": 5884 + }, + { + "epoch": 6.34, + "learning_rate": 5.77227011494253e-05, + "loss": 1.1285, + "step": 5885 + }, + { + "epoch": 6.34, + "learning_rate": 5.771551724137931e-05, + "loss": 1.0629, + "step": 5886 + }, + { + "epoch": 6.34, + "learning_rate": 5.770833333333333e-05, + "loss": 1.085, + "step": 5887 + }, + { + "epoch": 6.34, + "learning_rate": 5.770114942528736e-05, + "loss": 1.0683, + "step": 5888 + }, + { + "epoch": 6.35, + "learning_rate": 5.769396551724138e-05, + "loss": 1.0081, + "step": 5889 + }, + { + "epoch": 6.35, + "learning_rate": 5.7686781609195406e-05, + "loss": 1.1091, + "step": 5890 + }, + { + "epoch": 6.35, + "learning_rate": 5.7679597701149426e-05, + "loss": 1.1181, + "step": 5891 + }, + { + "epoch": 6.35, + "learning_rate": 5.767241379310345e-05, + "loss": 1.0552, + "step": 5892 + }, + { + "epoch": 6.35, + "learning_rate": 5.766522988505747e-05, + "loss": 1.038, + "step": 5893 + }, + { + "epoch": 6.35, + "learning_rate": 5.76580459770115e-05, + "loss": 0.9881, + "step": 5894 + }, + { + "epoch": 6.35, + "learning_rate": 5.7650862068965514e-05, + "loss": 1.0186, + "step": 5895 + }, + { + "epoch": 6.35, + "learning_rate": 5.764367816091955e-05, + "loss": 1.0465, + "step": 5896 + }, + { + "epoch": 6.35, + "learning_rate": 5.763649425287356e-05, + "loss": 1.0866, + "step": 5897 + }, + { + "epoch": 6.36, + "learning_rate": 5.762931034482759e-05, + "loss": 1.0081, + "step": 5898 + }, + { + "epoch": 6.36, + "learning_rate": 5.762212643678161e-05, + "loss": 1.0324, + "step": 5899 + }, + { + "epoch": 6.36, + "learning_rate": 5.7614942528735636e-05, + "loss": 1.0558, + "step": 5900 + }, + { + "epoch": 6.36, + "learning_rate": 5.7607758620689656e-05, + "loss": 1.0745, + "step": 5901 + }, + { + "epoch": 6.36, + "learning_rate": 5.760057471264368e-05, + "loss": 1.0889, + "step": 5902 + }, + { + "epoch": 6.36, + "learning_rate": 5.7593390804597704e-05, + "loss": 0.9489, + "step": 5903 + }, + { + "epoch": 6.36, + "learning_rate": 5.758620689655173e-05, + "loss": 1.1228, + "step": 5904 + }, + { + "epoch": 6.36, + "learning_rate": 5.757902298850575e-05, + "loss": 1.1015, + "step": 5905 + }, + { + "epoch": 6.36, + "learning_rate": 5.757183908045978e-05, + "loss": 0.9736, + "step": 5906 + }, + { + "epoch": 6.37, + "learning_rate": 5.756465517241379e-05, + "loss": 1.1111, + "step": 5907 + }, + { + "epoch": 6.37, + "learning_rate": 5.7557471264367826e-05, + "loss": 0.9775, + "step": 5908 + }, + { + "epoch": 6.37, + "learning_rate": 5.755028735632184e-05, + "loss": 1.0782, + "step": 5909 + }, + { + "epoch": 6.37, + "learning_rate": 5.754310344827587e-05, + "loss": 0.9526, + "step": 5910 + }, + { + "epoch": 6.37, + "learning_rate": 5.7535919540229887e-05, + "loss": 0.9618, + "step": 5911 + }, + { + "epoch": 6.37, + "learning_rate": 5.752873563218391e-05, + "loss": 1.0148, + "step": 5912 + }, + { + "epoch": 6.37, + "learning_rate": 5.7521551724137934e-05, + "loss": 1.059, + "step": 5913 + }, + { + "epoch": 6.37, + "learning_rate": 5.7514367816091954e-05, + "loss": 1.039, + "step": 5914 + }, + { + "epoch": 6.37, + "learning_rate": 5.750718390804598e-05, + "loss": 1.0168, + "step": 5915 + }, + { + "epoch": 6.38, + "learning_rate": 5.7499999999999995e-05, + "loss": 1.0706, + "step": 5916 + }, + { + "epoch": 6.38, + "learning_rate": 5.749281609195403e-05, + "loss": 1.0661, + "step": 5917 + }, + { + "epoch": 6.38, + "learning_rate": 5.748563218390804e-05, + "loss": 1.1251, + "step": 5918 + }, + { + "epoch": 6.38, + "learning_rate": 5.7478448275862076e-05, + "loss": 1.0101, + "step": 5919 + }, + { + "epoch": 6.38, + "learning_rate": 5.747126436781609e-05, + "loss": 0.9423, + "step": 5920 + }, + { + "epoch": 6.38, + "learning_rate": 5.746408045977012e-05, + "loss": 1.0841, + "step": 5921 + }, + { + "epoch": 6.38, + "learning_rate": 5.745689655172414e-05, + "loss": 1.1213, + "step": 5922 + }, + { + "epoch": 6.38, + "learning_rate": 5.7449712643678164e-05, + "loss": 1.0226, + "step": 5923 + }, + { + "epoch": 6.38, + "learning_rate": 5.7442528735632185e-05, + "loss": 1.0616, + "step": 5924 + }, + { + "epoch": 6.38, + "learning_rate": 5.743534482758621e-05, + "loss": 1.1241, + "step": 5925 + }, + { + "epoch": 6.39, + "learning_rate": 5.742816091954023e-05, + "loss": 1.1143, + "step": 5926 + }, + { + "epoch": 6.39, + "learning_rate": 5.742097701149426e-05, + "loss": 1.0472, + "step": 5927 + }, + { + "epoch": 6.39, + "learning_rate": 5.741379310344828e-05, + "loss": 0.9622, + "step": 5928 + }, + { + "epoch": 6.39, + "learning_rate": 5.7406609195402307e-05, + "loss": 1.0723, + "step": 5929 + }, + { + "epoch": 6.39, + "learning_rate": 5.739942528735632e-05, + "loss": 1.1755, + "step": 5930 + }, + { + "epoch": 6.39, + "learning_rate": 5.7392241379310354e-05, + "loss": 1.012, + "step": 5931 + }, + { + "epoch": 6.39, + "learning_rate": 5.738505747126437e-05, + "loss": 1.0596, + "step": 5932 + }, + { + "epoch": 6.39, + "learning_rate": 5.73778735632184e-05, + "loss": 1.1069, + "step": 5933 + }, + { + "epoch": 6.39, + "learning_rate": 5.7370689655172415e-05, + "loss": 1.1258, + "step": 5934 + }, + { + "epoch": 6.4, + "learning_rate": 5.736350574712644e-05, + "loss": 1.0416, + "step": 5935 + }, + { + "epoch": 6.4, + "learning_rate": 5.735632183908046e-05, + "loss": 1.0771, + "step": 5936 + }, + { + "epoch": 6.4, + "learning_rate": 5.734913793103448e-05, + "loss": 1.091, + "step": 5937 + }, + { + "epoch": 6.4, + "learning_rate": 5.734195402298851e-05, + "loss": 1.1027, + "step": 5938 + }, + { + "epoch": 6.4, + "learning_rate": 5.733477011494252e-05, + "loss": 1.0417, + "step": 5939 + }, + { + "epoch": 6.4, + "learning_rate": 5.732758620689656e-05, + "loss": 0.9391, + "step": 5940 + }, + { + "epoch": 6.4, + "learning_rate": 5.732040229885057e-05, + "loss": 1.0552, + "step": 5941 + }, + { + "epoch": 6.4, + "learning_rate": 5.7313218390804605e-05, + "loss": 1.0922, + "step": 5942 + }, + { + "epoch": 6.4, + "learning_rate": 5.730603448275862e-05, + "loss": 0.9435, + "step": 5943 + }, + { + "epoch": 6.41, + "learning_rate": 5.7298850574712645e-05, + "loss": 1.1008, + "step": 5944 + }, + { + "epoch": 6.41, + "learning_rate": 5.7291666666666666e-05, + "loss": 1.045, + "step": 5945 + }, + { + "epoch": 6.41, + "learning_rate": 5.728448275862069e-05, + "loss": 1.0595, + "step": 5946 + }, + { + "epoch": 6.41, + "learning_rate": 5.727729885057471e-05, + "loss": 1.017, + "step": 5947 + }, + { + "epoch": 6.41, + "learning_rate": 5.727011494252874e-05, + "loss": 1.0083, + "step": 5948 + }, + { + "epoch": 6.41, + "learning_rate": 5.726293103448276e-05, + "loss": 1.0494, + "step": 5949 + }, + { + "epoch": 6.41, + "learning_rate": 5.725574712643679e-05, + "loss": 1.0457, + "step": 5950 + }, + { + "epoch": 6.41, + "learning_rate": 5.724856321839081e-05, + "loss": 1.1546, + "step": 5951 + }, + { + "epoch": 6.41, + "learning_rate": 5.7241379310344835e-05, + "loss": 1.025, + "step": 5952 + }, + { + "epoch": 6.41, + "learning_rate": 5.723419540229885e-05, + "loss": 0.9876, + "step": 5953 + }, + { + "epoch": 6.42, + "learning_rate": 5.722701149425288e-05, + "loss": 1.1188, + "step": 5954 + }, + { + "epoch": 6.42, + "learning_rate": 5.7219827586206896e-05, + "loss": 0.9946, + "step": 5955 + }, + { + "epoch": 6.42, + "learning_rate": 5.721264367816093e-05, + "loss": 1.0931, + "step": 5956 + }, + { + "epoch": 6.42, + "learning_rate": 5.720545977011494e-05, + "loss": 1.0279, + "step": 5957 + }, + { + "epoch": 6.42, + "learning_rate": 5.719827586206897e-05, + "loss": 0.8934, + "step": 5958 + }, + { + "epoch": 6.42, + "learning_rate": 5.719109195402299e-05, + "loss": 1.0775, + "step": 5959 + }, + { + "epoch": 6.42, + "learning_rate": 5.718390804597702e-05, + "loss": 0.9921, + "step": 5960 + }, + { + "epoch": 6.42, + "learning_rate": 5.717672413793104e-05, + "loss": 1.0735, + "step": 5961 + }, + { + "epoch": 6.42, + "learning_rate": 5.7169540229885065e-05, + "loss": 1.1075, + "step": 5962 + }, + { + "epoch": 6.43, + "learning_rate": 5.7162356321839086e-05, + "loss": 1.006, + "step": 5963 + }, + { + "epoch": 6.43, + "learning_rate": 5.71551724137931e-05, + "loss": 1.0649, + "step": 5964 + }, + { + "epoch": 6.43, + "learning_rate": 5.714798850574713e-05, + "loss": 1.1333, + "step": 5965 + }, + { + "epoch": 6.43, + "learning_rate": 5.7140804597701147e-05, + "loss": 1.0245, + "step": 5966 + }, + { + "epoch": 6.43, + "learning_rate": 5.7133620689655174e-05, + "loss": 1.0154, + "step": 5967 + }, + { + "epoch": 6.43, + "learning_rate": 5.7126436781609194e-05, + "loss": 1.0553, + "step": 5968 + }, + { + "epoch": 6.43, + "learning_rate": 5.711925287356322e-05, + "loss": 1.0655, + "step": 5969 + }, + { + "epoch": 6.43, + "learning_rate": 5.711206896551724e-05, + "loss": 1.053, + "step": 5970 + }, + { + "epoch": 6.43, + "learning_rate": 5.710488505747127e-05, + "loss": 0.9419, + "step": 5971 + }, + { + "epoch": 6.44, + "learning_rate": 5.709770114942529e-05, + "loss": 1.0498, + "step": 5972 + }, + { + "epoch": 6.44, + "learning_rate": 5.7090517241379316e-05, + "loss": 1.0603, + "step": 5973 + }, + { + "epoch": 6.44, + "learning_rate": 5.7083333333333336e-05, + "loss": 0.9393, + "step": 5974 + }, + { + "epoch": 6.44, + "learning_rate": 5.707614942528736e-05, + "loss": 1.0295, + "step": 5975 + }, + { + "epoch": 6.44, + "learning_rate": 5.706896551724138e-05, + "loss": 0.9837, + "step": 5976 + }, + { + "epoch": 6.44, + "learning_rate": 5.706178160919541e-05, + "loss": 1.1724, + "step": 5977 + }, + { + "epoch": 6.44, + "learning_rate": 5.7054597701149424e-05, + "loss": 0.8285, + "step": 5978 + }, + { + "epoch": 6.44, + "learning_rate": 5.704741379310345e-05, + "loss": 1.139, + "step": 5979 + }, + { + "epoch": 6.44, + "learning_rate": 5.704022988505747e-05, + "loss": 1.0744, + "step": 5980 + }, + { + "epoch": 6.45, + "learning_rate": 5.70330459770115e-05, + "loss": 1.0131, + "step": 5981 + }, + { + "epoch": 6.45, + "learning_rate": 5.702586206896552e-05, + "loss": 1.079, + "step": 5982 + }, + { + "epoch": 6.45, + "learning_rate": 5.7018678160919546e-05, + "loss": 1.064, + "step": 5983 + }, + { + "epoch": 6.45, + "learning_rate": 5.7011494252873567e-05, + "loss": 1.0182, + "step": 5984 + }, + { + "epoch": 6.45, + "learning_rate": 5.7004310344827594e-05, + "loss": 0.9474, + "step": 5985 + }, + { + "epoch": 6.45, + "learning_rate": 5.6997126436781614e-05, + "loss": 0.8902, + "step": 5986 + }, + { + "epoch": 6.45, + "learning_rate": 5.698994252873564e-05, + "loss": 1.0452, + "step": 5987 + }, + { + "epoch": 6.45, + "learning_rate": 5.6982758620689655e-05, + "loss": 0.9659, + "step": 5988 + }, + { + "epoch": 6.45, + "learning_rate": 5.6975574712643675e-05, + "loss": 1.1754, + "step": 5989 + }, + { + "epoch": 6.45, + "learning_rate": 5.69683908045977e-05, + "loss": 1.1415, + "step": 5990 + }, + { + "epoch": 6.46, + "learning_rate": 5.696120689655172e-05, + "loss": 1.0027, + "step": 5991 + }, + { + "epoch": 6.46, + "learning_rate": 5.695402298850575e-05, + "loss": 1.0196, + "step": 5992 + }, + { + "epoch": 6.46, + "learning_rate": 5.694683908045977e-05, + "loss": 1.1016, + "step": 5993 + }, + { + "epoch": 6.46, + "learning_rate": 5.69396551724138e-05, + "loss": 1.107, + "step": 5994 + }, + { + "epoch": 6.46, + "learning_rate": 5.693247126436782e-05, + "loss": 1.0142, + "step": 5995 + }, + { + "epoch": 6.46, + "learning_rate": 5.6925287356321844e-05, + "loss": 1.0895, + "step": 5996 + }, + { + "epoch": 6.46, + "learning_rate": 5.6918103448275865e-05, + "loss": 1.0962, + "step": 5997 + }, + { + "epoch": 6.46, + "learning_rate": 5.691091954022989e-05, + "loss": 1.0163, + "step": 5998 + }, + { + "epoch": 6.46, + "learning_rate": 5.6903735632183905e-05, + "loss": 1.1508, + "step": 5999 + }, + { + "epoch": 6.47, + "learning_rate": 5.689655172413794e-05, + "loss": 0.9543, + "step": 6000 + }, + { + "epoch": 6.47, + "eval_loss": 1.1217094659805298, + "eval_runtime": 175.0853, + "eval_samples_per_second": 127.195, + "eval_steps_per_second": 0.663, + "step": 6000 + }, + { + "epoch": 6.47, + "learning_rate": 5.688936781609195e-05, + "loss": 0.9669, + "step": 6001 + }, + { + "epoch": 6.47, + "learning_rate": 5.688218390804598e-05, + "loss": 1.0901, + "step": 6002 + }, + { + "epoch": 6.47, + "learning_rate": 5.6875e-05, + "loss": 1.1566, + "step": 6003 + }, + { + "epoch": 6.47, + "learning_rate": 5.686781609195403e-05, + "loss": 0.9803, + "step": 6004 + }, + { + "epoch": 6.47, + "learning_rate": 5.686063218390805e-05, + "loss": 1.1198, + "step": 6005 + }, + { + "epoch": 6.47, + "learning_rate": 5.6853448275862075e-05, + "loss": 0.9964, + "step": 6006 + }, + { + "epoch": 6.47, + "learning_rate": 5.6846264367816095e-05, + "loss": 1.0614, + "step": 6007 + }, + { + "epoch": 6.47, + "learning_rate": 5.683908045977012e-05, + "loss": 1.039, + "step": 6008 + }, + { + "epoch": 6.48, + "learning_rate": 5.683189655172414e-05, + "loss": 1.1221, + "step": 6009 + }, + { + "epoch": 6.48, + "learning_rate": 5.682471264367817e-05, + "loss": 1.0135, + "step": 6010 + }, + { + "epoch": 6.48, + "learning_rate": 5.681752873563218e-05, + "loss": 1.1094, + "step": 6011 + }, + { + "epoch": 6.48, + "learning_rate": 5.681034482758622e-05, + "loss": 1.0321, + "step": 6012 + }, + { + "epoch": 6.48, + "learning_rate": 5.680316091954023e-05, + "loss": 1.0417, + "step": 6013 + }, + { + "epoch": 6.48, + "learning_rate": 5.679597701149425e-05, + "loss": 1.1514, + "step": 6014 + }, + { + "epoch": 6.48, + "learning_rate": 5.678879310344828e-05, + "loss": 1.0664, + "step": 6015 + }, + { + "epoch": 6.48, + "learning_rate": 5.67816091954023e-05, + "loss": 1.1353, + "step": 6016 + }, + { + "epoch": 6.48, + "learning_rate": 5.6774425287356325e-05, + "loss": 1.0803, + "step": 6017 + }, + { + "epoch": 6.48, + "learning_rate": 5.6767241379310346e-05, + "loss": 1.0093, + "step": 6018 + }, + { + "epoch": 6.49, + "learning_rate": 5.676005747126437e-05, + "loss": 1.0313, + "step": 6019 + }, + { + "epoch": 6.49, + "learning_rate": 5.6752873563218386e-05, + "loss": 1.0118, + "step": 6020 + }, + { + "epoch": 6.49, + "learning_rate": 5.674568965517242e-05, + "loss": 0.939, + "step": 6021 + }, + { + "epoch": 6.49, + "learning_rate": 5.6738505747126434e-05, + "loss": 1.0109, + "step": 6022 + }, + { + "epoch": 6.49, + "learning_rate": 5.673132183908047e-05, + "loss": 0.9889, + "step": 6023 + }, + { + "epoch": 6.49, + "learning_rate": 5.672413793103448e-05, + "loss": 1.003, + "step": 6024 + }, + { + "epoch": 6.49, + "learning_rate": 5.671695402298851e-05, + "loss": 1.1435, + "step": 6025 + }, + { + "epoch": 6.49, + "learning_rate": 5.670977011494253e-05, + "loss": 1.1528, + "step": 6026 + }, + { + "epoch": 6.49, + "learning_rate": 5.6702586206896556e-05, + "loss": 1.0906, + "step": 6027 + }, + { + "epoch": 6.5, + "learning_rate": 5.6695402298850576e-05, + "loss": 1.0377, + "step": 6028 + }, + { + "epoch": 6.5, + "learning_rate": 5.66882183908046e-05, + "loss": 1.0349, + "step": 6029 + }, + { + "epoch": 6.5, + "learning_rate": 5.668103448275862e-05, + "loss": 1.0416, + "step": 6030 + }, + { + "epoch": 6.5, + "learning_rate": 5.667385057471265e-05, + "loss": 1.1135, + "step": 6031 + }, + { + "epoch": 6.5, + "learning_rate": 5.666666666666667e-05, + "loss": 1.1054, + "step": 6032 + }, + { + "epoch": 6.5, + "learning_rate": 5.66594827586207e-05, + "loss": 1.0752, + "step": 6033 + }, + { + "epoch": 6.5, + "learning_rate": 5.665229885057471e-05, + "loss": 1.1288, + "step": 6034 + }, + { + "epoch": 6.5, + "learning_rate": 5.6645114942528745e-05, + "loss": 1.1823, + "step": 6035 + }, + { + "epoch": 6.5, + "learning_rate": 5.663793103448276e-05, + "loss": 1.0426, + "step": 6036 + }, + { + "epoch": 6.51, + "learning_rate": 5.663074712643679e-05, + "loss": 1.0559, + "step": 6037 + }, + { + "epoch": 6.51, + "learning_rate": 5.6623563218390806e-05, + "loss": 0.9906, + "step": 6038 + }, + { + "epoch": 6.51, + "learning_rate": 5.6616379310344827e-05, + "loss": 1.0652, + "step": 6039 + }, + { + "epoch": 6.51, + "learning_rate": 5.6609195402298854e-05, + "loss": 1.028, + "step": 6040 + }, + { + "epoch": 6.51, + "learning_rate": 5.6602011494252874e-05, + "loss": 0.9316, + "step": 6041 + }, + { + "epoch": 6.51, + "learning_rate": 5.65948275862069e-05, + "loss": 0.8983, + "step": 6042 + }, + { + "epoch": 6.51, + "learning_rate": 5.6587643678160915e-05, + "loss": 1.057, + "step": 6043 + }, + { + "epoch": 6.51, + "learning_rate": 5.658045977011495e-05, + "loss": 0.946, + "step": 6044 + }, + { + "epoch": 6.51, + "learning_rate": 5.657327586206896e-05, + "loss": 1.0759, + "step": 6045 + }, + { + "epoch": 6.52, + "learning_rate": 5.6566091954022996e-05, + "loss": 0.9644, + "step": 6046 + }, + { + "epoch": 6.52, + "learning_rate": 5.655890804597701e-05, + "loss": 1.0693, + "step": 6047 + }, + { + "epoch": 6.52, + "learning_rate": 5.6551724137931037e-05, + "loss": 1.0789, + "step": 6048 + }, + { + "epoch": 6.52, + "learning_rate": 5.654454022988506e-05, + "loss": 1.0315, + "step": 6049 + }, + { + "epoch": 6.52, + "learning_rate": 5.6537356321839084e-05, + "loss": 1.0856, + "step": 6050 + }, + { + "epoch": 6.52, + "learning_rate": 5.6530172413793104e-05, + "loss": 0.9896, + "step": 6051 + }, + { + "epoch": 6.52, + "learning_rate": 5.652298850574713e-05, + "loss": 1.1634, + "step": 6052 + }, + { + "epoch": 6.52, + "learning_rate": 5.651580459770115e-05, + "loss": 1.0027, + "step": 6053 + }, + { + "epoch": 6.52, + "learning_rate": 5.650862068965518e-05, + "loss": 0.9956, + "step": 6054 + }, + { + "epoch": 6.52, + "learning_rate": 5.65014367816092e-05, + "loss": 0.981, + "step": 6055 + }, + { + "epoch": 6.53, + "learning_rate": 5.6494252873563226e-05, + "loss": 0.9855, + "step": 6056 + }, + { + "epoch": 6.53, + "learning_rate": 5.648706896551724e-05, + "loss": 1.0055, + "step": 6057 + }, + { + "epoch": 6.53, + "learning_rate": 5.6479885057471274e-05, + "loss": 1.0494, + "step": 6058 + }, + { + "epoch": 6.53, + "learning_rate": 5.647270114942529e-05, + "loss": 0.9225, + "step": 6059 + }, + { + "epoch": 6.53, + "learning_rate": 5.6465517241379314e-05, + "loss": 0.9988, + "step": 6060 + }, + { + "epoch": 6.53, + "learning_rate": 5.6458333333333335e-05, + "loss": 0.9932, + "step": 6061 + }, + { + "epoch": 6.53, + "learning_rate": 5.645114942528736e-05, + "loss": 1.073, + "step": 6062 + }, + { + "epoch": 6.53, + "learning_rate": 5.644396551724138e-05, + "loss": 1.1182, + "step": 6063 + }, + { + "epoch": 6.53, + "learning_rate": 5.643678160919541e-05, + "loss": 1.0196, + "step": 6064 + }, + { + "epoch": 6.54, + "learning_rate": 5.642959770114943e-05, + "loss": 1.0166, + "step": 6065 + }, + { + "epoch": 6.54, + "learning_rate": 5.642241379310344e-05, + "loss": 1.1583, + "step": 6066 + }, + { + "epoch": 6.54, + "learning_rate": 5.641522988505748e-05, + "loss": 1.0176, + "step": 6067 + }, + { + "epoch": 6.54, + "learning_rate": 5.640804597701149e-05, + "loss": 1.1012, + "step": 6068 + }, + { + "epoch": 6.54, + "learning_rate": 5.6400862068965524e-05, + "loss": 0.9893, + "step": 6069 + }, + { + "epoch": 6.54, + "learning_rate": 5.639367816091954e-05, + "loss": 1.1353, + "step": 6070 + }, + { + "epoch": 6.54, + "learning_rate": 5.6386494252873565e-05, + "loss": 1.0464, + "step": 6071 + }, + { + "epoch": 6.54, + "learning_rate": 5.6379310344827585e-05, + "loss": 1.1248, + "step": 6072 + }, + { + "epoch": 6.54, + "learning_rate": 5.637212643678161e-05, + "loss": 0.9355, + "step": 6073 + }, + { + "epoch": 6.55, + "learning_rate": 5.636494252873563e-05, + "loss": 1.1159, + "step": 6074 + }, + { + "epoch": 6.55, + "learning_rate": 5.635775862068966e-05, + "loss": 1.0782, + "step": 6075 + }, + { + "epoch": 6.55, + "learning_rate": 5.635057471264368e-05, + "loss": 1.0558, + "step": 6076 + }, + { + "epoch": 6.55, + "learning_rate": 5.634339080459771e-05, + "loss": 1.0161, + "step": 6077 + }, + { + "epoch": 6.55, + "learning_rate": 5.633620689655173e-05, + "loss": 1.0828, + "step": 6078 + }, + { + "epoch": 6.55, + "learning_rate": 5.6329022988505755e-05, + "loss": 1.1198, + "step": 6079 + }, + { + "epoch": 6.55, + "learning_rate": 5.632183908045977e-05, + "loss": 1.0646, + "step": 6080 + }, + { + "epoch": 6.55, + "learning_rate": 5.63146551724138e-05, + "loss": 1.1865, + "step": 6081 + }, + { + "epoch": 6.55, + "learning_rate": 5.6307471264367816e-05, + "loss": 1.0534, + "step": 6082 + }, + { + "epoch": 6.55, + "learning_rate": 5.630028735632184e-05, + "loss": 1.0166, + "step": 6083 + }, + { + "epoch": 6.56, + "learning_rate": 5.629310344827586e-05, + "loss": 0.956, + "step": 6084 + }, + { + "epoch": 6.56, + "learning_rate": 5.628591954022989e-05, + "loss": 1.1601, + "step": 6085 + }, + { + "epoch": 6.56, + "learning_rate": 5.627873563218391e-05, + "loss": 1.1201, + "step": 6086 + }, + { + "epoch": 6.56, + "learning_rate": 5.627155172413794e-05, + "loss": 1.0191, + "step": 6087 + }, + { + "epoch": 6.56, + "learning_rate": 5.626436781609196e-05, + "loss": 0.9398, + "step": 6088 + }, + { + "epoch": 6.56, + "learning_rate": 5.6257183908045985e-05, + "loss": 1.1152, + "step": 6089 + }, + { + "epoch": 6.56, + "learning_rate": 5.6250000000000005e-05, + "loss": 1.0186, + "step": 6090 + }, + { + "epoch": 6.56, + "learning_rate": 5.624281609195402e-05, + "loss": 0.943, + "step": 6091 + }, + { + "epoch": 6.56, + "learning_rate": 5.6235632183908046e-05, + "loss": 1.0402, + "step": 6092 + }, + { + "epoch": 6.57, + "learning_rate": 5.6228448275862066e-05, + "loss": 1.1208, + "step": 6093 + }, + { + "epoch": 6.57, + "learning_rate": 5.622126436781609e-05, + "loss": 1.0238, + "step": 6094 + }, + { + "epoch": 6.57, + "learning_rate": 5.6214080459770114e-05, + "loss": 1.0603, + "step": 6095 + }, + { + "epoch": 6.57, + "learning_rate": 5.620689655172414e-05, + "loss": 0.9859, + "step": 6096 + }, + { + "epoch": 6.57, + "learning_rate": 5.619971264367816e-05, + "loss": 1.097, + "step": 6097 + }, + { + "epoch": 6.57, + "learning_rate": 5.619252873563219e-05, + "loss": 1.1381, + "step": 6098 + }, + { + "epoch": 6.57, + "learning_rate": 5.618534482758621e-05, + "loss": 1.1366, + "step": 6099 + }, + { + "epoch": 6.57, + "learning_rate": 5.6178160919540236e-05, + "loss": 0.9486, + "step": 6100 + }, + { + "epoch": 6.57, + "learning_rate": 5.617097701149425e-05, + "loss": 1.1826, + "step": 6101 + }, + { + "epoch": 6.58, + "learning_rate": 5.616379310344828e-05, + "loss": 1.0205, + "step": 6102 + }, + { + "epoch": 6.58, + "learning_rate": 5.6156609195402297e-05, + "loss": 1.1491, + "step": 6103 + }, + { + "epoch": 6.58, + "learning_rate": 5.614942528735633e-05, + "loss": 0.9998, + "step": 6104 + }, + { + "epoch": 6.58, + "learning_rate": 5.6142241379310344e-05, + "loss": 1.0235, + "step": 6105 + }, + { + "epoch": 6.58, + "learning_rate": 5.613505747126437e-05, + "loss": 0.9625, + "step": 6106 + }, + { + "epoch": 6.58, + "learning_rate": 5.612787356321839e-05, + "loss": 1.0625, + "step": 6107 + }, + { + "epoch": 6.58, + "learning_rate": 5.612068965517242e-05, + "loss": 0.963, + "step": 6108 + }, + { + "epoch": 6.58, + "learning_rate": 5.611350574712644e-05, + "loss": 1.0102, + "step": 6109 + }, + { + "epoch": 6.58, + "learning_rate": 5.6106321839080466e-05, + "loss": 1.017, + "step": 6110 + }, + { + "epoch": 6.59, + "learning_rate": 5.6099137931034486e-05, + "loss": 1.1421, + "step": 6111 + }, + { + "epoch": 6.59, + "learning_rate": 5.609195402298851e-05, + "loss": 0.9578, + "step": 6112 + }, + { + "epoch": 6.59, + "learning_rate": 5.6084770114942534e-05, + "loss": 1.0632, + "step": 6113 + }, + { + "epoch": 6.59, + "learning_rate": 5.607758620689656e-05, + "loss": 0.9803, + "step": 6114 + }, + { + "epoch": 6.59, + "learning_rate": 5.6070402298850574e-05, + "loss": 1.0632, + "step": 6115 + }, + { + "epoch": 6.59, + "learning_rate": 5.6063218390804595e-05, + "loss": 1.0102, + "step": 6116 + }, + { + "epoch": 6.59, + "learning_rate": 5.605603448275862e-05, + "loss": 1.1157, + "step": 6117 + }, + { + "epoch": 6.59, + "learning_rate": 5.604885057471264e-05, + "loss": 1.0868, + "step": 6118 + }, + { + "epoch": 6.59, + "learning_rate": 5.604166666666667e-05, + "loss": 1.0336, + "step": 6119 + }, + { + "epoch": 6.59, + "learning_rate": 5.603448275862069e-05, + "loss": 1.0937, + "step": 6120 + }, + { + "epoch": 6.6, + "learning_rate": 5.6027298850574717e-05, + "loss": 1.0009, + "step": 6121 + }, + { + "epoch": 6.6, + "learning_rate": 5.602011494252874e-05, + "loss": 0.9811, + "step": 6122 + }, + { + "epoch": 6.6, + "learning_rate": 5.6012931034482764e-05, + "loss": 1.0167, + "step": 6123 + }, + { + "epoch": 6.6, + "learning_rate": 5.600574712643678e-05, + "loss": 0.9856, + "step": 6124 + }, + { + "epoch": 6.6, + "learning_rate": 5.599856321839081e-05, + "loss": 1.0846, + "step": 6125 + }, + { + "epoch": 6.6, + "learning_rate": 5.5991379310344825e-05, + "loss": 0.9939, + "step": 6126 + }, + { + "epoch": 6.6, + "learning_rate": 5.598419540229886e-05, + "loss": 1.0709, + "step": 6127 + }, + { + "epoch": 6.6, + "learning_rate": 5.597701149425287e-05, + "loss": 1.1756, + "step": 6128 + }, + { + "epoch": 6.6, + "learning_rate": 5.59698275862069e-05, + "loss": 1.0571, + "step": 6129 + }, + { + "epoch": 6.61, + "learning_rate": 5.596264367816092e-05, + "loss": 0.9588, + "step": 6130 + }, + { + "epoch": 6.61, + "learning_rate": 5.595545977011495e-05, + "loss": 1.0802, + "step": 6131 + }, + { + "epoch": 6.61, + "learning_rate": 5.594827586206897e-05, + "loss": 0.9583, + "step": 6132 + }, + { + "epoch": 6.61, + "learning_rate": 5.5941091954022994e-05, + "loss": 0.9979, + "step": 6133 + }, + { + "epoch": 6.61, + "learning_rate": 5.5933908045977015e-05, + "loss": 1.0027, + "step": 6134 + }, + { + "epoch": 6.61, + "learning_rate": 5.592672413793104e-05, + "loss": 1.0204, + "step": 6135 + }, + { + "epoch": 6.61, + "learning_rate": 5.591954022988506e-05, + "loss": 1.1959, + "step": 6136 + }, + { + "epoch": 6.61, + "learning_rate": 5.591235632183909e-05, + "loss": 1.0359, + "step": 6137 + }, + { + "epoch": 6.61, + "learning_rate": 5.59051724137931e-05, + "loss": 1.0219, + "step": 6138 + }, + { + "epoch": 6.62, + "learning_rate": 5.5897988505747137e-05, + "loss": 1.0247, + "step": 6139 + }, + { + "epoch": 6.62, + "learning_rate": 5.589080459770115e-05, + "loss": 0.9021, + "step": 6140 + }, + { + "epoch": 6.62, + "learning_rate": 5.5883620689655184e-05, + "loss": 1.0927, + "step": 6141 + }, + { + "epoch": 6.62, + "learning_rate": 5.58764367816092e-05, + "loss": 1.1379, + "step": 6142 + }, + { + "epoch": 6.62, + "learning_rate": 5.586925287356322e-05, + "loss": 1.0424, + "step": 6143 + }, + { + "epoch": 6.62, + "learning_rate": 5.5862068965517245e-05, + "loss": 0.948, + "step": 6144 + }, + { + "epoch": 6.62, + "learning_rate": 5.5854885057471265e-05, + "loss": 1.0661, + "step": 6145 + }, + { + "epoch": 6.62, + "learning_rate": 5.584770114942529e-05, + "loss": 1.0662, + "step": 6146 + }, + { + "epoch": 6.62, + "learning_rate": 5.5840517241379306e-05, + "loss": 0.94, + "step": 6147 + }, + { + "epoch": 6.62, + "learning_rate": 5.583333333333334e-05, + "loss": 1.1471, + "step": 6148 + }, + { + "epoch": 6.63, + "learning_rate": 5.582614942528735e-05, + "loss": 1.0862, + "step": 6149 + }, + { + "epoch": 6.63, + "learning_rate": 5.581896551724139e-05, + "loss": 1.0164, + "step": 6150 + }, + { + "epoch": 6.63, + "learning_rate": 5.58117816091954e-05, + "loss": 1.0653, + "step": 6151 + }, + { + "epoch": 6.63, + "learning_rate": 5.580459770114943e-05, + "loss": 1.1261, + "step": 6152 + }, + { + "epoch": 6.63, + "learning_rate": 5.579741379310345e-05, + "loss": 1.0425, + "step": 6153 + }, + { + "epoch": 6.63, + "learning_rate": 5.5790229885057475e-05, + "loss": 0.9438, + "step": 6154 + }, + { + "epoch": 6.63, + "learning_rate": 5.5783045977011496e-05, + "loss": 1.0679, + "step": 6155 + }, + { + "epoch": 6.63, + "learning_rate": 5.577586206896552e-05, + "loss": 0.9296, + "step": 6156 + }, + { + "epoch": 6.63, + "learning_rate": 5.576867816091954e-05, + "loss": 1.0796, + "step": 6157 + }, + { + "epoch": 6.64, + "learning_rate": 5.576149425287357e-05, + "loss": 1.1309, + "step": 6158 + }, + { + "epoch": 6.64, + "learning_rate": 5.575431034482759e-05, + "loss": 1.2335, + "step": 6159 + }, + { + "epoch": 6.64, + "learning_rate": 5.574712643678162e-05, + "loss": 0.9533, + "step": 6160 + }, + { + "epoch": 6.64, + "learning_rate": 5.573994252873563e-05, + "loss": 1.0361, + "step": 6161 + }, + { + "epoch": 6.64, + "learning_rate": 5.5732758620689665e-05, + "loss": 1.0049, + "step": 6162 + }, + { + "epoch": 6.64, + "learning_rate": 5.572557471264368e-05, + "loss": 1.0657, + "step": 6163 + }, + { + "epoch": 6.64, + "learning_rate": 5.5718390804597706e-05, + "loss": 1.0774, + "step": 6164 + }, + { + "epoch": 6.64, + "learning_rate": 5.5711206896551726e-05, + "loss": 1.0758, + "step": 6165 + }, + { + "epoch": 6.64, + "learning_rate": 5.570402298850575e-05, + "loss": 1.045, + "step": 6166 + }, + { + "epoch": 6.65, + "learning_rate": 5.569683908045977e-05, + "loss": 1.0984, + "step": 6167 + }, + { + "epoch": 6.65, + "learning_rate": 5.5689655172413794e-05, + "loss": 1.024, + "step": 6168 + }, + { + "epoch": 6.65, + "learning_rate": 5.568247126436782e-05, + "loss": 1.0207, + "step": 6169 + }, + { + "epoch": 6.65, + "learning_rate": 5.5675287356321834e-05, + "loss": 1.0813, + "step": 6170 + }, + { + "epoch": 6.65, + "learning_rate": 5.566810344827587e-05, + "loss": 1.1186, + "step": 6171 + }, + { + "epoch": 6.65, + "learning_rate": 5.566091954022988e-05, + "loss": 1.0855, + "step": 6172 + }, + { + "epoch": 6.65, + "learning_rate": 5.565373563218391e-05, + "loss": 0.9496, + "step": 6173 + }, + { + "epoch": 6.65, + "learning_rate": 5.564655172413793e-05, + "loss": 1.1971, + "step": 6174 + }, + { + "epoch": 6.65, + "learning_rate": 5.5639367816091956e-05, + "loss": 1.0359, + "step": 6175 + }, + { + "epoch": 6.66, + "learning_rate": 5.5632183908045976e-05, + "loss": 1.0503, + "step": 6176 + }, + { + "epoch": 6.66, + "learning_rate": 5.5625000000000004e-05, + "loss": 1.0828, + "step": 6177 + }, + { + "epoch": 6.66, + "learning_rate": 5.5617816091954024e-05, + "loss": 1.0284, + "step": 6178 + }, + { + "epoch": 6.66, + "learning_rate": 5.561063218390805e-05, + "loss": 0.985, + "step": 6179 + }, + { + "epoch": 6.66, + "learning_rate": 5.560344827586207e-05, + "loss": 1.0249, + "step": 6180 + }, + { + "epoch": 6.66, + "learning_rate": 5.55962643678161e-05, + "loss": 1.0546, + "step": 6181 + }, + { + "epoch": 6.66, + "learning_rate": 5.558908045977011e-05, + "loss": 1.1561, + "step": 6182 + }, + { + "epoch": 6.66, + "learning_rate": 5.5581896551724146e-05, + "loss": 1.0172, + "step": 6183 + }, + { + "epoch": 6.66, + "learning_rate": 5.557471264367816e-05, + "loss": 1.1746, + "step": 6184 + }, + { + "epoch": 6.66, + "learning_rate": 5.556752873563219e-05, + "loss": 1.1404, + "step": 6185 + }, + { + "epoch": 6.67, + "learning_rate": 5.556034482758621e-05, + "loss": 1.1008, + "step": 6186 + }, + { + "epoch": 6.67, + "learning_rate": 5.5553160919540234e-05, + "loss": 0.993, + "step": 6187 + }, + { + "epoch": 6.67, + "learning_rate": 5.5545977011494254e-05, + "loss": 1.1299, + "step": 6188 + }, + { + "epoch": 6.67, + "learning_rate": 5.553879310344828e-05, + "loss": 0.9971, + "step": 6189 + }, + { + "epoch": 6.67, + "learning_rate": 5.55316091954023e-05, + "loss": 1.034, + "step": 6190 + }, + { + "epoch": 6.67, + "learning_rate": 5.552442528735633e-05, + "loss": 1.0361, + "step": 6191 + }, + { + "epoch": 6.67, + "learning_rate": 5.551724137931035e-05, + "loss": 0.9602, + "step": 6192 + }, + { + "epoch": 6.67, + "learning_rate": 5.551005747126436e-05, + "loss": 1.1168, + "step": 6193 + }, + { + "epoch": 6.67, + "learning_rate": 5.5502873563218396e-05, + "loss": 1.0516, + "step": 6194 + }, + { + "epoch": 6.68, + "learning_rate": 5.549568965517241e-05, + "loss": 1.1007, + "step": 6195 + }, + { + "epoch": 6.68, + "learning_rate": 5.548850574712644e-05, + "loss": 1.0756, + "step": 6196 + }, + { + "epoch": 6.68, + "learning_rate": 5.548132183908046e-05, + "loss": 1.2267, + "step": 6197 + }, + { + "epoch": 6.68, + "learning_rate": 5.5474137931034485e-05, + "loss": 1.0941, + "step": 6198 + }, + { + "epoch": 6.68, + "learning_rate": 5.5466954022988505e-05, + "loss": 1.0808, + "step": 6199 + }, + { + "epoch": 6.68, + "learning_rate": 5.545977011494253e-05, + "loss": 1.1335, + "step": 6200 + }, + { + "epoch": 6.68, + "learning_rate": 5.545258620689655e-05, + "loss": 1.0486, + "step": 6201 + }, + { + "epoch": 6.68, + "learning_rate": 5.544540229885058e-05, + "loss": 1.1141, + "step": 6202 + }, + { + "epoch": 6.68, + "learning_rate": 5.54382183908046e-05, + "loss": 1.0249, + "step": 6203 + }, + { + "epoch": 6.69, + "learning_rate": 5.543103448275863e-05, + "loss": 1.1379, + "step": 6204 + }, + { + "epoch": 6.69, + "learning_rate": 5.542385057471264e-05, + "loss": 0.9932, + "step": 6205 + }, + { + "epoch": 6.69, + "learning_rate": 5.5416666666666674e-05, + "loss": 0.9671, + "step": 6206 + }, + { + "epoch": 6.69, + "learning_rate": 5.540948275862069e-05, + "loss": 1.0914, + "step": 6207 + }, + { + "epoch": 6.69, + "learning_rate": 5.540229885057472e-05, + "loss": 1.1219, + "step": 6208 + }, + { + "epoch": 6.69, + "learning_rate": 5.5395114942528735e-05, + "loss": 0.9678, + "step": 6209 + }, + { + "epoch": 6.69, + "learning_rate": 5.538793103448276e-05, + "loss": 1.0692, + "step": 6210 + }, + { + "epoch": 6.69, + "learning_rate": 5.538074712643678e-05, + "loss": 1.089, + "step": 6211 + }, + { + "epoch": 6.69, + "learning_rate": 5.537356321839081e-05, + "loss": 0.9387, + "step": 6212 + }, + { + "epoch": 6.7, + "learning_rate": 5.536637931034483e-05, + "loss": 0.9337, + "step": 6213 + }, + { + "epoch": 6.7, + "learning_rate": 5.535919540229886e-05, + "loss": 1.0405, + "step": 6214 + }, + { + "epoch": 6.7, + "learning_rate": 5.535201149425288e-05, + "loss": 1.1114, + "step": 6215 + }, + { + "epoch": 6.7, + "learning_rate": 5.5344827586206905e-05, + "loss": 1.0294, + "step": 6216 + }, + { + "epoch": 6.7, + "learning_rate": 5.5337643678160925e-05, + "loss": 1.1103, + "step": 6217 + }, + { + "epoch": 6.7, + "learning_rate": 5.533045977011494e-05, + "loss": 1.0576, + "step": 6218 + }, + { + "epoch": 6.7, + "learning_rate": 5.5323275862068966e-05, + "loss": 0.9804, + "step": 6219 + }, + { + "epoch": 6.7, + "learning_rate": 5.5316091954022986e-05, + "loss": 1.0246, + "step": 6220 + }, + { + "epoch": 6.7, + "learning_rate": 5.530890804597701e-05, + "loss": 1.0502, + "step": 6221 + }, + { + "epoch": 6.7, + "learning_rate": 5.530172413793103e-05, + "loss": 1.0094, + "step": 6222 + }, + { + "epoch": 6.71, + "learning_rate": 5.529454022988506e-05, + "loss": 1.0199, + "step": 6223 + }, + { + "epoch": 6.71, + "learning_rate": 5.528735632183908e-05, + "loss": 0.9919, + "step": 6224 + }, + { + "epoch": 6.71, + "learning_rate": 5.528017241379311e-05, + "loss": 0.9078, + "step": 6225 + }, + { + "epoch": 6.71, + "learning_rate": 5.527298850574713e-05, + "loss": 1.2196, + "step": 6226 + }, + { + "epoch": 6.71, + "learning_rate": 5.5265804597701155e-05, + "loss": 0.9471, + "step": 6227 + }, + { + "epoch": 6.71, + "learning_rate": 5.525862068965517e-05, + "loss": 1.0178, + "step": 6228 + }, + { + "epoch": 6.71, + "learning_rate": 5.52514367816092e-05, + "loss": 1.0104, + "step": 6229 + }, + { + "epoch": 6.71, + "learning_rate": 5.5244252873563216e-05, + "loss": 1.151, + "step": 6230 + }, + { + "epoch": 6.71, + "learning_rate": 5.523706896551725e-05, + "loss": 1.1873, + "step": 6231 + }, + { + "epoch": 6.72, + "learning_rate": 5.5229885057471264e-05, + "loss": 0.9787, + "step": 6232 + }, + { + "epoch": 6.72, + "learning_rate": 5.522270114942529e-05, + "loss": 0.9593, + "step": 6233 + }, + { + "epoch": 6.72, + "learning_rate": 5.521551724137931e-05, + "loss": 1.0806, + "step": 6234 + }, + { + "epoch": 6.72, + "learning_rate": 5.520833333333334e-05, + "loss": 1.0923, + "step": 6235 + }, + { + "epoch": 6.72, + "learning_rate": 5.520114942528736e-05, + "loss": 1.0285, + "step": 6236 + }, + { + "epoch": 6.72, + "learning_rate": 5.5193965517241386e-05, + "loss": 1.1884, + "step": 6237 + }, + { + "epoch": 6.72, + "learning_rate": 5.5186781609195406e-05, + "loss": 1.0991, + "step": 6238 + }, + { + "epoch": 6.72, + "learning_rate": 5.517959770114943e-05, + "loss": 1.0595, + "step": 6239 + }, + { + "epoch": 6.72, + "learning_rate": 5.517241379310345e-05, + "loss": 0.9657, + "step": 6240 + }, + { + "epoch": 6.73, + "learning_rate": 5.516522988505748e-05, + "loss": 1.1194, + "step": 6241 + }, + { + "epoch": 6.73, + "learning_rate": 5.5158045977011494e-05, + "loss": 1.1193, + "step": 6242 + }, + { + "epoch": 6.73, + "learning_rate": 5.515086206896553e-05, + "loss": 1.0348, + "step": 6243 + }, + { + "epoch": 6.73, + "learning_rate": 5.514367816091954e-05, + "loss": 0.9764, + "step": 6244 + }, + { + "epoch": 6.73, + "learning_rate": 5.513649425287356e-05, + "loss": 1.0495, + "step": 6245 + }, + { + "epoch": 6.73, + "learning_rate": 5.512931034482759e-05, + "loss": 1.158, + "step": 6246 + }, + { + "epoch": 6.73, + "learning_rate": 5.512212643678161e-05, + "loss": 1.0561, + "step": 6247 + }, + { + "epoch": 6.73, + "learning_rate": 5.5114942528735636e-05, + "loss": 0.9615, + "step": 6248 + }, + { + "epoch": 6.73, + "learning_rate": 5.5107758620689656e-05, + "loss": 1.0021, + "step": 6249 + }, + { + "epoch": 6.73, + "learning_rate": 5.5100574712643684e-05, + "loss": 1.025, + "step": 6250 + }, + { + "epoch": 6.73, + "eval_loss": 1.117545247077942, + "eval_runtime": 174.8486, + "eval_samples_per_second": 127.367, + "eval_steps_per_second": 0.663, + "step": 6250 + }, + { + "epoch": 6.74, + "learning_rate": 5.50933908045977e-05, + "loss": 0.8953, + "step": 6251 + }, + { + "epoch": 6.74, + "learning_rate": 5.508620689655173e-05, + "loss": 1.0414, + "step": 6252 + }, + { + "epoch": 6.74, + "learning_rate": 5.5079022988505745e-05, + "loss": 0.9767, + "step": 6253 + }, + { + "epoch": 6.74, + "learning_rate": 5.507183908045977e-05, + "loss": 1.0836, + "step": 6254 + }, + { + "epoch": 6.74, + "learning_rate": 5.506465517241379e-05, + "loss": 1.0086, + "step": 6255 + }, + { + "epoch": 6.74, + "learning_rate": 5.505747126436782e-05, + "loss": 1.0134, + "step": 6256 + }, + { + "epoch": 6.74, + "learning_rate": 5.505028735632184e-05, + "loss": 1.1314, + "step": 6257 + }, + { + "epoch": 6.74, + "learning_rate": 5.5043103448275866e-05, + "loss": 1.1198, + "step": 6258 + }, + { + "epoch": 6.74, + "learning_rate": 5.503591954022989e-05, + "loss": 1.0125, + "step": 6259 + }, + { + "epoch": 6.75, + "learning_rate": 5.5028735632183914e-05, + "loss": 1.042, + "step": 6260 + }, + { + "epoch": 6.75, + "learning_rate": 5.5021551724137934e-05, + "loss": 1.1313, + "step": 6261 + }, + { + "epoch": 6.75, + "learning_rate": 5.501436781609196e-05, + "loss": 1.0674, + "step": 6262 + }, + { + "epoch": 6.75, + "learning_rate": 5.500718390804598e-05, + "loss": 1.0167, + "step": 6263 + }, + { + "epoch": 6.75, + "learning_rate": 5.500000000000001e-05, + "loss": 1.0745, + "step": 6264 + }, + { + "epoch": 6.75, + "learning_rate": 5.499281609195402e-05, + "loss": 1.0522, + "step": 6265 + }, + { + "epoch": 6.75, + "learning_rate": 5.4985632183908056e-05, + "loss": 1.0563, + "step": 6266 + }, + { + "epoch": 6.75, + "learning_rate": 5.497844827586207e-05, + "loss": 1.0518, + "step": 6267 + }, + { + "epoch": 6.75, + "learning_rate": 5.49712643678161e-05, + "loss": 1.043, + "step": 6268 + }, + { + "epoch": 6.76, + "learning_rate": 5.496408045977012e-05, + "loss": 0.9904, + "step": 6269 + }, + { + "epoch": 6.76, + "learning_rate": 5.495689655172414e-05, + "loss": 1.0492, + "step": 6270 + }, + { + "epoch": 6.76, + "learning_rate": 5.4949712643678165e-05, + "loss": 1.0346, + "step": 6271 + }, + { + "epoch": 6.76, + "learning_rate": 5.4942528735632185e-05, + "loss": 1.0989, + "step": 6272 + }, + { + "epoch": 6.76, + "learning_rate": 5.493534482758621e-05, + "loss": 0.9788, + "step": 6273 + }, + { + "epoch": 6.76, + "learning_rate": 5.4928160919540226e-05, + "loss": 1.2192, + "step": 6274 + }, + { + "epoch": 6.76, + "learning_rate": 5.492097701149426e-05, + "loss": 1.0108, + "step": 6275 + }, + { + "epoch": 6.76, + "learning_rate": 5.491379310344827e-05, + "loss": 0.9346, + "step": 6276 + }, + { + "epoch": 6.76, + "learning_rate": 5.49066091954023e-05, + "loss": 1.1031, + "step": 6277 + }, + { + "epoch": 6.77, + "learning_rate": 5.489942528735632e-05, + "loss": 1.2541, + "step": 6278 + }, + { + "epoch": 6.77, + "learning_rate": 5.489224137931035e-05, + "loss": 1.2263, + "step": 6279 + }, + { + "epoch": 6.77, + "learning_rate": 5.488505747126437e-05, + "loss": 1.1321, + "step": 6280 + }, + { + "epoch": 6.77, + "learning_rate": 5.4877873563218395e-05, + "loss": 1.0324, + "step": 6281 + }, + { + "epoch": 6.77, + "learning_rate": 5.4870689655172415e-05, + "loss": 1.0848, + "step": 6282 + }, + { + "epoch": 6.77, + "learning_rate": 5.486350574712644e-05, + "loss": 1.0155, + "step": 6283 + }, + { + "epoch": 6.77, + "learning_rate": 5.485632183908046e-05, + "loss": 0.9424, + "step": 6284 + }, + { + "epoch": 6.77, + "learning_rate": 5.484913793103449e-05, + "loss": 1.0183, + "step": 6285 + }, + { + "epoch": 6.77, + "learning_rate": 5.48419540229885e-05, + "loss": 1.1187, + "step": 6286 + }, + { + "epoch": 6.77, + "learning_rate": 5.483477011494254e-05, + "loss": 1.1093, + "step": 6287 + }, + { + "epoch": 6.78, + "learning_rate": 5.482758620689655e-05, + "loss": 1.0486, + "step": 6288 + }, + { + "epoch": 6.78, + "learning_rate": 5.4820402298850585e-05, + "loss": 1.0938, + "step": 6289 + }, + { + "epoch": 6.78, + "learning_rate": 5.48132183908046e-05, + "loss": 0.9779, + "step": 6290 + }, + { + "epoch": 6.78, + "learning_rate": 5.4806034482758625e-05, + "loss": 1.0463, + "step": 6291 + }, + { + "epoch": 6.78, + "learning_rate": 5.4798850574712645e-05, + "loss": 1.1258, + "step": 6292 + }, + { + "epoch": 6.78, + "learning_rate": 5.479166666666667e-05, + "loss": 1.1797, + "step": 6293 + }, + { + "epoch": 6.78, + "learning_rate": 5.478448275862069e-05, + "loss": 1.1501, + "step": 6294 + }, + { + "epoch": 6.78, + "learning_rate": 5.4777298850574706e-05, + "loss": 1.1577, + "step": 6295 + }, + { + "epoch": 6.78, + "learning_rate": 5.477011494252874e-05, + "loss": 1.0942, + "step": 6296 + }, + { + "epoch": 6.79, + "learning_rate": 5.4762931034482754e-05, + "loss": 1.1721, + "step": 6297 + }, + { + "epoch": 6.79, + "learning_rate": 5.475574712643679e-05, + "loss": 1.1516, + "step": 6298 + }, + { + "epoch": 6.79, + "learning_rate": 5.47485632183908e-05, + "loss": 1.1081, + "step": 6299 + }, + { + "epoch": 6.79, + "learning_rate": 5.474137931034483e-05, + "loss": 0.977, + "step": 6300 + }, + { + "epoch": 6.79, + "learning_rate": 5.473419540229885e-05, + "loss": 1.0127, + "step": 6301 + }, + { + "epoch": 6.79, + "learning_rate": 5.4727011494252876e-05, + "loss": 0.9777, + "step": 6302 + }, + { + "epoch": 6.79, + "learning_rate": 5.4719827586206896e-05, + "loss": 0.9875, + "step": 6303 + }, + { + "epoch": 6.79, + "learning_rate": 5.471264367816092e-05, + "loss": 0.9568, + "step": 6304 + }, + { + "epoch": 6.79, + "learning_rate": 5.4705459770114944e-05, + "loss": 1.0508, + "step": 6305 + }, + { + "epoch": 6.8, + "learning_rate": 5.469827586206897e-05, + "loss": 1.0283, + "step": 6306 + }, + { + "epoch": 6.8, + "learning_rate": 5.469109195402299e-05, + "loss": 1.0286, + "step": 6307 + }, + { + "epoch": 6.8, + "learning_rate": 5.468390804597702e-05, + "loss": 1.0494, + "step": 6308 + }, + { + "epoch": 6.8, + "learning_rate": 5.467672413793103e-05, + "loss": 0.9099, + "step": 6309 + }, + { + "epoch": 6.8, + "learning_rate": 5.4669540229885065e-05, + "loss": 1.106, + "step": 6310 + }, + { + "epoch": 6.8, + "learning_rate": 5.466235632183908e-05, + "loss": 0.9731, + "step": 6311 + }, + { + "epoch": 6.8, + "learning_rate": 5.465517241379311e-05, + "loss": 1.0614, + "step": 6312 + }, + { + "epoch": 6.8, + "learning_rate": 5.4647988505747126e-05, + "loss": 0.9916, + "step": 6313 + }, + { + "epoch": 6.8, + "learning_rate": 5.4640804597701154e-05, + "loss": 0.8874, + "step": 6314 + }, + { + "epoch": 6.8, + "learning_rate": 5.4633620689655174e-05, + "loss": 1.0159, + "step": 6315 + }, + { + "epoch": 6.81, + "learning_rate": 5.46264367816092e-05, + "loss": 1.1026, + "step": 6316 + }, + { + "epoch": 6.81, + "learning_rate": 5.461925287356322e-05, + "loss": 1.0687, + "step": 6317 + }, + { + "epoch": 6.81, + "learning_rate": 5.461206896551725e-05, + "loss": 1.0243, + "step": 6318 + }, + { + "epoch": 6.81, + "learning_rate": 5.460488505747127e-05, + "loss": 1.0087, + "step": 6319 + }, + { + "epoch": 6.81, + "learning_rate": 5.4597701149425296e-05, + "loss": 1.0058, + "step": 6320 + }, + { + "epoch": 6.81, + "learning_rate": 5.4590517241379316e-05, + "loss": 1.0549, + "step": 6321 + }, + { + "epoch": 6.81, + "learning_rate": 5.458333333333333e-05, + "loss": 1.1233, + "step": 6322 + }, + { + "epoch": 6.81, + "learning_rate": 5.457614942528736e-05, + "loss": 1.0619, + "step": 6323 + }, + { + "epoch": 6.81, + "learning_rate": 5.456896551724138e-05, + "loss": 1.0749, + "step": 6324 + }, + { + "epoch": 6.82, + "learning_rate": 5.4561781609195404e-05, + "loss": 1.1496, + "step": 6325 + }, + { + "epoch": 6.82, + "learning_rate": 5.4554597701149425e-05, + "loss": 1.0124, + "step": 6326 + }, + { + "epoch": 6.82, + "learning_rate": 5.454741379310345e-05, + "loss": 0.8623, + "step": 6327 + }, + { + "epoch": 6.82, + "learning_rate": 5.454022988505747e-05, + "loss": 1.1124, + "step": 6328 + }, + { + "epoch": 6.82, + "learning_rate": 5.45330459770115e-05, + "loss": 1.0321, + "step": 6329 + }, + { + "epoch": 6.82, + "learning_rate": 5.452586206896552e-05, + "loss": 1.0326, + "step": 6330 + }, + { + "epoch": 6.82, + "learning_rate": 5.4518678160919546e-05, + "loss": 1.018, + "step": 6331 + }, + { + "epoch": 6.82, + "learning_rate": 5.451149425287356e-05, + "loss": 0.9983, + "step": 6332 + }, + { + "epoch": 6.82, + "learning_rate": 5.4504310344827594e-05, + "loss": 1.1853, + "step": 6333 + }, + { + "epoch": 6.83, + "learning_rate": 5.449712643678161e-05, + "loss": 1.0428, + "step": 6334 + }, + { + "epoch": 6.83, + "learning_rate": 5.448994252873564e-05, + "loss": 1.0186, + "step": 6335 + }, + { + "epoch": 6.83, + "learning_rate": 5.4482758620689655e-05, + "loss": 0.9819, + "step": 6336 + }, + { + "epoch": 6.83, + "learning_rate": 5.447557471264368e-05, + "loss": 1.1288, + "step": 6337 + }, + { + "epoch": 6.83, + "learning_rate": 5.44683908045977e-05, + "loss": 1.0186, + "step": 6338 + }, + { + "epoch": 6.83, + "learning_rate": 5.446120689655173e-05, + "loss": 1.0477, + "step": 6339 + }, + { + "epoch": 6.83, + "learning_rate": 5.445402298850575e-05, + "loss": 0.9602, + "step": 6340 + }, + { + "epoch": 6.83, + "learning_rate": 5.444683908045978e-05, + "loss": 1.0217, + "step": 6341 + }, + { + "epoch": 6.83, + "learning_rate": 5.44396551724138e-05, + "loss": 1.0453, + "step": 6342 + }, + { + "epoch": 6.84, + "learning_rate": 5.4432471264367824e-05, + "loss": 1.0214, + "step": 6343 + }, + { + "epoch": 6.84, + "learning_rate": 5.4425287356321845e-05, + "loss": 1.027, + "step": 6344 + }, + { + "epoch": 6.84, + "learning_rate": 5.441810344827587e-05, + "loss": 1.1219, + "step": 6345 + }, + { + "epoch": 6.84, + "learning_rate": 5.4410919540229885e-05, + "loss": 0.9754, + "step": 6346 + }, + { + "epoch": 6.84, + "learning_rate": 5.4403735632183905e-05, + "loss": 1.1379, + "step": 6347 + }, + { + "epoch": 6.84, + "learning_rate": 5.439655172413793e-05, + "loss": 1.0776, + "step": 6348 + }, + { + "epoch": 6.84, + "learning_rate": 5.438936781609195e-05, + "loss": 1.081, + "step": 6349 + }, + { + "epoch": 6.84, + "learning_rate": 5.438218390804598e-05, + "loss": 1.0098, + "step": 6350 + }, + { + "epoch": 6.84, + "learning_rate": 5.4375e-05, + "loss": 1.1059, + "step": 6351 + }, + { + "epoch": 6.84, + "learning_rate": 5.436781609195403e-05, + "loss": 1.0823, + "step": 6352 + }, + { + "epoch": 6.85, + "learning_rate": 5.436063218390805e-05, + "loss": 1.0838, + "step": 6353 + }, + { + "epoch": 6.85, + "learning_rate": 5.4353448275862075e-05, + "loss": 0.9799, + "step": 6354 + }, + { + "epoch": 6.85, + "learning_rate": 5.434626436781609e-05, + "loss": 1.0852, + "step": 6355 + }, + { + "epoch": 6.85, + "learning_rate": 5.433908045977012e-05, + "loss": 1.083, + "step": 6356 + }, + { + "epoch": 6.85, + "learning_rate": 5.4331896551724136e-05, + "loss": 1.082, + "step": 6357 + }, + { + "epoch": 6.85, + "learning_rate": 5.432471264367816e-05, + "loss": 0.9006, + "step": 6358 + }, + { + "epoch": 6.85, + "learning_rate": 5.431752873563218e-05, + "loss": 1.0364, + "step": 6359 + }, + { + "epoch": 6.85, + "learning_rate": 5.431034482758621e-05, + "loss": 1.0405, + "step": 6360 + }, + { + "epoch": 6.85, + "learning_rate": 5.430316091954023e-05, + "loss": 1.1602, + "step": 6361 + }, + { + "epoch": 6.86, + "learning_rate": 5.429597701149426e-05, + "loss": 1.0361, + "step": 6362 + }, + { + "epoch": 6.86, + "learning_rate": 5.428879310344828e-05, + "loss": 1.0461, + "step": 6363 + }, + { + "epoch": 6.86, + "learning_rate": 5.4281609195402305e-05, + "loss": 1.081, + "step": 6364 + }, + { + "epoch": 6.86, + "learning_rate": 5.4274425287356325e-05, + "loss": 0.9712, + "step": 6365 + }, + { + "epoch": 6.86, + "learning_rate": 5.426724137931035e-05, + "loss": 1.0655, + "step": 6366 + }, + { + "epoch": 6.86, + "learning_rate": 5.4260057471264366e-05, + "loss": 0.9804, + "step": 6367 + }, + { + "epoch": 6.86, + "learning_rate": 5.42528735632184e-05, + "loss": 1.0547, + "step": 6368 + }, + { + "epoch": 6.86, + "learning_rate": 5.4245689655172414e-05, + "loss": 1.0691, + "step": 6369 + }, + { + "epoch": 6.86, + "learning_rate": 5.423850574712645e-05, + "loss": 1.0758, + "step": 6370 + }, + { + "epoch": 6.87, + "learning_rate": 5.423132183908046e-05, + "loss": 0.9973, + "step": 6371 + }, + { + "epoch": 6.87, + "learning_rate": 5.422413793103448e-05, + "loss": 1.2121, + "step": 6372 + }, + { + "epoch": 6.87, + "learning_rate": 5.421695402298851e-05, + "loss": 1.134, + "step": 6373 + }, + { + "epoch": 6.87, + "learning_rate": 5.420977011494253e-05, + "loss": 0.9656, + "step": 6374 + }, + { + "epoch": 6.87, + "learning_rate": 5.4202586206896556e-05, + "loss": 1.0611, + "step": 6375 + }, + { + "epoch": 6.87, + "learning_rate": 5.4195402298850576e-05, + "loss": 0.9661, + "step": 6376 + }, + { + "epoch": 6.87, + "learning_rate": 5.41882183908046e-05, + "loss": 1.0287, + "step": 6377 + }, + { + "epoch": 6.87, + "learning_rate": 5.418103448275862e-05, + "loss": 1.1416, + "step": 6378 + }, + { + "epoch": 6.87, + "learning_rate": 5.417385057471265e-05, + "loss": 0.9983, + "step": 6379 + }, + { + "epoch": 6.88, + "learning_rate": 5.4166666666666664e-05, + "loss": 0.9891, + "step": 6380 + }, + { + "epoch": 6.88, + "learning_rate": 5.415948275862069e-05, + "loss": 0.9814, + "step": 6381 + }, + { + "epoch": 6.88, + "learning_rate": 5.415229885057471e-05, + "loss": 0.9638, + "step": 6382 + }, + { + "epoch": 6.88, + "learning_rate": 5.414511494252874e-05, + "loss": 1.0166, + "step": 6383 + }, + { + "epoch": 6.88, + "learning_rate": 5.413793103448276e-05, + "loss": 1.0024, + "step": 6384 + }, + { + "epoch": 6.88, + "learning_rate": 5.4130747126436786e-05, + "loss": 1.1205, + "step": 6385 + }, + { + "epoch": 6.88, + "learning_rate": 5.4123563218390806e-05, + "loss": 0.974, + "step": 6386 + }, + { + "epoch": 6.88, + "learning_rate": 5.4116379310344834e-05, + "loss": 0.9846, + "step": 6387 + }, + { + "epoch": 6.88, + "learning_rate": 5.4109195402298854e-05, + "loss": 1.0009, + "step": 6388 + }, + { + "epoch": 6.88, + "learning_rate": 5.410201149425288e-05, + "loss": 0.9992, + "step": 6389 + }, + { + "epoch": 6.89, + "learning_rate": 5.4094827586206894e-05, + "loss": 1.0018, + "step": 6390 + }, + { + "epoch": 6.89, + "learning_rate": 5.408764367816093e-05, + "loss": 1.0629, + "step": 6391 + }, + { + "epoch": 6.89, + "learning_rate": 5.408045977011494e-05, + "loss": 1.0822, + "step": 6392 + }, + { + "epoch": 6.89, + "learning_rate": 5.4073275862068976e-05, + "loss": 0.9687, + "step": 6393 + }, + { + "epoch": 6.89, + "learning_rate": 5.406609195402299e-05, + "loss": 1.0212, + "step": 6394 + }, + { + "epoch": 6.89, + "learning_rate": 5.4058908045977016e-05, + "loss": 0.9975, + "step": 6395 + }, + { + "epoch": 6.89, + "learning_rate": 5.405172413793104e-05, + "loss": 1.012, + "step": 6396 + }, + { + "epoch": 6.89, + "learning_rate": 5.4044540229885064e-05, + "loss": 0.9336, + "step": 6397 + }, + { + "epoch": 6.89, + "learning_rate": 5.4037356321839084e-05, + "loss": 1.061, + "step": 6398 + }, + { + "epoch": 6.9, + "learning_rate": 5.40301724137931e-05, + "loss": 1.0662, + "step": 6399 + }, + { + "epoch": 6.9, + "learning_rate": 5.402298850574713e-05, + "loss": 0.9656, + "step": 6400 + }, + { + "epoch": 6.9, + "learning_rate": 5.4015804597701145e-05, + "loss": 1.0502, + "step": 6401 + }, + { + "epoch": 6.9, + "learning_rate": 5.400862068965518e-05, + "loss": 1.0792, + "step": 6402 + }, + { + "epoch": 6.9, + "learning_rate": 5.400143678160919e-05, + "loss": 0.9891, + "step": 6403 + }, + { + "epoch": 6.9, + "learning_rate": 5.399425287356322e-05, + "loss": 1.0102, + "step": 6404 + }, + { + "epoch": 6.9, + "learning_rate": 5.398706896551724e-05, + "loss": 0.9995, + "step": 6405 + }, + { + "epoch": 6.9, + "learning_rate": 5.397988505747127e-05, + "loss": 1.0263, + "step": 6406 + }, + { + "epoch": 6.9, + "learning_rate": 5.397270114942529e-05, + "loss": 1.1729, + "step": 6407 + }, + { + "epoch": 6.91, + "learning_rate": 5.3965517241379314e-05, + "loss": 1.065, + "step": 6408 + }, + { + "epoch": 6.91, + "learning_rate": 5.3958333333333335e-05, + "loss": 1.0267, + "step": 6409 + }, + { + "epoch": 6.91, + "learning_rate": 5.395114942528736e-05, + "loss": 0.9825, + "step": 6410 + }, + { + "epoch": 6.91, + "learning_rate": 5.394396551724138e-05, + "loss": 1.0047, + "step": 6411 + }, + { + "epoch": 6.91, + "learning_rate": 5.393678160919541e-05, + "loss": 1.038, + "step": 6412 + }, + { + "epoch": 6.91, + "learning_rate": 5.392959770114942e-05, + "loss": 1.1524, + "step": 6413 + }, + { + "epoch": 6.91, + "learning_rate": 5.392241379310346e-05, + "loss": 1.2557, + "step": 6414 + }, + { + "epoch": 6.91, + "learning_rate": 5.391522988505747e-05, + "loss": 1.0533, + "step": 6415 + }, + { + "epoch": 6.91, + "learning_rate": 5.3908045977011504e-05, + "loss": 1.0904, + "step": 6416 + }, + { + "epoch": 6.91, + "learning_rate": 5.390086206896552e-05, + "loss": 1.1196, + "step": 6417 + }, + { + "epoch": 6.92, + "learning_rate": 5.3893678160919545e-05, + "loss": 1.0574, + "step": 6418 + }, + { + "epoch": 6.92, + "learning_rate": 5.3886494252873565e-05, + "loss": 0.9686, + "step": 6419 + }, + { + "epoch": 6.92, + "learning_rate": 5.387931034482759e-05, + "loss": 1.0746, + "step": 6420 + }, + { + "epoch": 6.92, + "learning_rate": 5.387212643678161e-05, + "loss": 1.0864, + "step": 6421 + }, + { + "epoch": 6.92, + "learning_rate": 5.386494252873564e-05, + "loss": 1.1116, + "step": 6422 + }, + { + "epoch": 6.92, + "learning_rate": 5.385775862068966e-05, + "loss": 1.1256, + "step": 6423 + }, + { + "epoch": 6.92, + "learning_rate": 5.3850574712643674e-05, + "loss": 1.0463, + "step": 6424 + }, + { + "epoch": 6.92, + "learning_rate": 5.384339080459771e-05, + "loss": 1.0999, + "step": 6425 + }, + { + "epoch": 6.92, + "learning_rate": 5.383620689655172e-05, + "loss": 0.9604, + "step": 6426 + }, + { + "epoch": 6.93, + "learning_rate": 5.382902298850575e-05, + "loss": 1.162, + "step": 6427 + }, + { + "epoch": 6.93, + "learning_rate": 5.382183908045977e-05, + "loss": 0.9651, + "step": 6428 + }, + { + "epoch": 6.93, + "learning_rate": 5.3814655172413795e-05, + "loss": 1.0392, + "step": 6429 + }, + { + "epoch": 6.93, + "learning_rate": 5.3807471264367816e-05, + "loss": 0.9868, + "step": 6430 + }, + { + "epoch": 6.93, + "learning_rate": 5.380028735632184e-05, + "loss": 1.1109, + "step": 6431 + }, + { + "epoch": 6.93, + "learning_rate": 5.379310344827586e-05, + "loss": 1.1029, + "step": 6432 + }, + { + "epoch": 6.93, + "learning_rate": 5.378591954022989e-05, + "loss": 0.9239, + "step": 6433 + }, + { + "epoch": 6.93, + "learning_rate": 5.377873563218391e-05, + "loss": 1.1201, + "step": 6434 + }, + { + "epoch": 6.93, + "learning_rate": 5.377155172413794e-05, + "loss": 1.1565, + "step": 6435 + }, + { + "epoch": 6.94, + "learning_rate": 5.376436781609195e-05, + "loss": 1.0128, + "step": 6436 + }, + { + "epoch": 6.94, + "learning_rate": 5.3757183908045985e-05, + "loss": 0.9912, + "step": 6437 + }, + { + "epoch": 6.94, + "learning_rate": 5.375e-05, + "loss": 0.9622, + "step": 6438 + }, + { + "epoch": 6.94, + "learning_rate": 5.3742816091954026e-05, + "loss": 1.1005, + "step": 6439 + }, + { + "epoch": 6.94, + "learning_rate": 5.3735632183908046e-05, + "loss": 1.0061, + "step": 6440 + }, + { + "epoch": 6.94, + "learning_rate": 5.372844827586207e-05, + "loss": 1.055, + "step": 6441 + }, + { + "epoch": 6.94, + "learning_rate": 5.3721264367816094e-05, + "loss": 0.9883, + "step": 6442 + }, + { + "epoch": 6.94, + "learning_rate": 5.371408045977012e-05, + "loss": 0.9426, + "step": 6443 + }, + { + "epoch": 6.94, + "learning_rate": 5.370689655172414e-05, + "loss": 1.105, + "step": 6444 + }, + { + "epoch": 6.95, + "learning_rate": 5.369971264367817e-05, + "loss": 1.0524, + "step": 6445 + }, + { + "epoch": 6.95, + "learning_rate": 5.369252873563219e-05, + "loss": 1.0652, + "step": 6446 + }, + { + "epoch": 6.95, + "learning_rate": 5.3685344827586215e-05, + "loss": 1.1084, + "step": 6447 + }, + { + "epoch": 6.95, + "learning_rate": 5.3678160919540236e-05, + "loss": 1.0244, + "step": 6448 + }, + { + "epoch": 6.95, + "learning_rate": 5.367097701149425e-05, + "loss": 1.0019, + "step": 6449 + }, + { + "epoch": 6.95, + "learning_rate": 5.3663793103448276e-05, + "loss": 0.9667, + "step": 6450 + }, + { + "epoch": 6.95, + "learning_rate": 5.36566091954023e-05, + "loss": 0.9655, + "step": 6451 + }, + { + "epoch": 6.95, + "learning_rate": 5.3649425287356324e-05, + "loss": 1.0928, + "step": 6452 + }, + { + "epoch": 6.95, + "learning_rate": 5.3642241379310344e-05, + "loss": 1.0623, + "step": 6453 + }, + { + "epoch": 6.95, + "learning_rate": 5.363505747126437e-05, + "loss": 1.0413, + "step": 6454 + }, + { + "epoch": 6.96, + "learning_rate": 5.362787356321839e-05, + "loss": 1.0874, + "step": 6455 + }, + { + "epoch": 6.96, + "learning_rate": 5.362068965517242e-05, + "loss": 0.9831, + "step": 6456 + }, + { + "epoch": 6.96, + "learning_rate": 5.361350574712644e-05, + "loss": 1.0602, + "step": 6457 + }, + { + "epoch": 6.96, + "learning_rate": 5.3606321839080466e-05, + "loss": 1.1761, + "step": 6458 + }, + { + "epoch": 6.96, + "learning_rate": 5.359913793103448e-05, + "loss": 1.0938, + "step": 6459 + }, + { + "epoch": 6.96, + "learning_rate": 5.3591954022988514e-05, + "loss": 1.0045, + "step": 6460 + }, + { + "epoch": 6.96, + "learning_rate": 5.358477011494253e-05, + "loss": 1.0449, + "step": 6461 + }, + { + "epoch": 6.96, + "learning_rate": 5.3577586206896554e-05, + "loss": 1.029, + "step": 6462 + }, + { + "epoch": 6.96, + "learning_rate": 5.3570402298850574e-05, + "loss": 1.1574, + "step": 6463 + }, + { + "epoch": 6.97, + "learning_rate": 5.35632183908046e-05, + "loss": 1.054, + "step": 6464 + }, + { + "epoch": 6.97, + "learning_rate": 5.355603448275862e-05, + "loss": 1.1117, + "step": 6465 + }, + { + "epoch": 6.97, + "learning_rate": 5.354885057471265e-05, + "loss": 1.0238, + "step": 6466 + }, + { + "epoch": 6.97, + "learning_rate": 5.354166666666667e-05, + "loss": 1.066, + "step": 6467 + }, + { + "epoch": 6.97, + "learning_rate": 5.3534482758620696e-05, + "loss": 1.154, + "step": 6468 + }, + { + "epoch": 6.97, + "learning_rate": 5.352729885057472e-05, + "loss": 1.0993, + "step": 6469 + }, + { + "epoch": 6.97, + "learning_rate": 5.3520114942528744e-05, + "loss": 0.9557, + "step": 6470 + }, + { + "epoch": 6.97, + "learning_rate": 5.351293103448276e-05, + "loss": 1.046, + "step": 6471 + }, + { + "epoch": 6.97, + "learning_rate": 5.350574712643679e-05, + "loss": 1.0969, + "step": 6472 + }, + { + "epoch": 6.98, + "learning_rate": 5.3498563218390805e-05, + "loss": 1.1116, + "step": 6473 + }, + { + "epoch": 6.98, + "learning_rate": 5.3491379310344825e-05, + "loss": 0.9621, + "step": 6474 + }, + { + "epoch": 6.98, + "learning_rate": 5.348419540229885e-05, + "loss": 0.9254, + "step": 6475 + }, + { + "epoch": 6.98, + "learning_rate": 5.347701149425287e-05, + "loss": 1.0929, + "step": 6476 + }, + { + "epoch": 6.98, + "learning_rate": 5.34698275862069e-05, + "loss": 1.0519, + "step": 6477 + }, + { + "epoch": 6.98, + "learning_rate": 5.346264367816092e-05, + "loss": 1.1411, + "step": 6478 + }, + { + "epoch": 6.98, + "learning_rate": 5.345545977011495e-05, + "loss": 1.1393, + "step": 6479 + }, + { + "epoch": 6.98, + "learning_rate": 5.344827586206896e-05, + "loss": 0.98, + "step": 6480 + }, + { + "epoch": 6.98, + "learning_rate": 5.3441091954022994e-05, + "loss": 0.9179, + "step": 6481 + }, + { + "epoch": 6.98, + "learning_rate": 5.343390804597701e-05, + "loss": 1.025, + "step": 6482 + }, + { + "epoch": 6.99, + "learning_rate": 5.342672413793104e-05, + "loss": 0.9716, + "step": 6483 + }, + { + "epoch": 6.99, + "learning_rate": 5.3419540229885055e-05, + "loss": 0.9947, + "step": 6484 + }, + { + "epoch": 6.99, + "learning_rate": 5.341235632183908e-05, + "loss": 0.9688, + "step": 6485 + }, + { + "epoch": 6.99, + "learning_rate": 5.34051724137931e-05, + "loss": 1.0866, + "step": 6486 + }, + { + "epoch": 6.99, + "learning_rate": 5.339798850574713e-05, + "loss": 1.0649, + "step": 6487 + }, + { + "epoch": 6.99, + "learning_rate": 5.339080459770115e-05, + "loss": 1.1101, + "step": 6488 + }, + { + "epoch": 6.99, + "learning_rate": 5.338362068965518e-05, + "loss": 1.0818, + "step": 6489 + }, + { + "epoch": 6.99, + "learning_rate": 5.33764367816092e-05, + "loss": 1.0209, + "step": 6490 + }, + { + "epoch": 6.99, + "learning_rate": 5.3369252873563225e-05, + "loss": 0.9706, + "step": 6491 + }, + { + "epoch": 7.0, + "learning_rate": 5.3362068965517245e-05, + "loss": 1.095, + "step": 6492 + }, + { + "epoch": 7.0, + "learning_rate": 5.335488505747127e-05, + "loss": 1.1279, + "step": 6493 + }, + { + "epoch": 7.0, + "learning_rate": 5.3347701149425286e-05, + "loss": 1.0811, + "step": 6494 + }, + { + "epoch": 7.0, + "learning_rate": 5.334051724137932e-05, + "loss": 1.1887, + "step": 6495 + }, + { + "epoch": 7.0, + "learning_rate": 5.333333333333333e-05, + "loss": 1.0668, + "step": 6496 + }, + { + "epoch": 7.0, + "learning_rate": 5.332614942528737e-05, + "loss": 0.9668, + "step": 6497 + }, + { + "epoch": 7.0, + "learning_rate": 5.331896551724138e-05, + "loss": 1.0666, + "step": 6498 + }, + { + "epoch": 7.0, + "learning_rate": 5.331178160919541e-05, + "loss": 1.0622, + "step": 6499 + }, + { + "epoch": 7.0, + "learning_rate": 5.330459770114943e-05, + "loss": 1.0509, + "step": 6500 + }, + { + "epoch": 7.0, + "eval_loss": 1.1146588325500488, + "eval_runtime": 174.7453, + "eval_samples_per_second": 127.443, + "eval_steps_per_second": 0.664, + "step": 6500 + }, + { + "epoch": 7.01, + "learning_rate": 5.329741379310345e-05, + "loss": 1.0175, + "step": 6501 + }, + { + "epoch": 7.01, + "learning_rate": 5.3290229885057475e-05, + "loss": 0.9454, + "step": 6502 + }, + { + "epoch": 7.01, + "learning_rate": 5.328304597701149e-05, + "loss": 0.9892, + "step": 6503 + }, + { + "epoch": 7.01, + "learning_rate": 5.327586206896552e-05, + "loss": 0.9587, + "step": 6504 + }, + { + "epoch": 7.01, + "learning_rate": 5.3268678160919536e-05, + "loss": 1.0235, + "step": 6505 + }, + { + "epoch": 7.01, + "learning_rate": 5.326149425287357e-05, + "loss": 0.9395, + "step": 6506 + }, + { + "epoch": 7.01, + "learning_rate": 5.3254310344827584e-05, + "loss": 1.0422, + "step": 6507 + }, + { + "epoch": 7.01, + "learning_rate": 5.324712643678161e-05, + "loss": 0.9253, + "step": 6508 + }, + { + "epoch": 7.01, + "learning_rate": 5.323994252873563e-05, + "loss": 0.9644, + "step": 6509 + }, + { + "epoch": 7.02, + "learning_rate": 5.323275862068966e-05, + "loss": 0.9801, + "step": 6510 + }, + { + "epoch": 7.02, + "learning_rate": 5.322557471264368e-05, + "loss": 1.0042, + "step": 6511 + }, + { + "epoch": 7.02, + "learning_rate": 5.3218390804597706e-05, + "loss": 0.9627, + "step": 6512 + }, + { + "epoch": 7.02, + "learning_rate": 5.3211206896551726e-05, + "loss": 0.9603, + "step": 6513 + }, + { + "epoch": 7.02, + "learning_rate": 5.320402298850575e-05, + "loss": 0.9646, + "step": 6514 + }, + { + "epoch": 7.02, + "learning_rate": 5.3196839080459773e-05, + "loss": 0.9987, + "step": 6515 + }, + { + "epoch": 7.02, + "learning_rate": 5.31896551724138e-05, + "loss": 1.0853, + "step": 6516 + }, + { + "epoch": 7.02, + "learning_rate": 5.3182471264367814e-05, + "loss": 1.1225, + "step": 6517 + }, + { + "epoch": 7.02, + "learning_rate": 5.317528735632185e-05, + "loss": 1.1213, + "step": 6518 + }, + { + "epoch": 7.02, + "learning_rate": 5.316810344827586e-05, + "loss": 1.0062, + "step": 6519 + }, + { + "epoch": 7.03, + "learning_rate": 5.3160919540229895e-05, + "loss": 1.07, + "step": 6520 + }, + { + "epoch": 7.03, + "learning_rate": 5.315373563218391e-05, + "loss": 1.0111, + "step": 6521 + }, + { + "epoch": 7.03, + "learning_rate": 5.3146551724137936e-05, + "loss": 0.9864, + "step": 6522 + }, + { + "epoch": 7.03, + "learning_rate": 5.3139367816091956e-05, + "loss": 0.998, + "step": 6523 + }, + { + "epoch": 7.03, + "learning_rate": 5.3132183908045983e-05, + "loss": 0.9946, + "step": 6524 + }, + { + "epoch": 7.03, + "learning_rate": 5.3125000000000004e-05, + "loss": 1.0458, + "step": 6525 + }, + { + "epoch": 7.03, + "learning_rate": 5.311781609195402e-05, + "loss": 0.9896, + "step": 6526 + }, + { + "epoch": 7.03, + "learning_rate": 5.311063218390805e-05, + "loss": 0.8706, + "step": 6527 + }, + { + "epoch": 7.03, + "learning_rate": 5.3103448275862065e-05, + "loss": 1.0906, + "step": 6528 + }, + { + "epoch": 7.04, + "learning_rate": 5.30962643678161e-05, + "loss": 0.9478, + "step": 6529 + }, + { + "epoch": 7.04, + "learning_rate": 5.308908045977011e-05, + "loss": 1.0178, + "step": 6530 + }, + { + "epoch": 7.04, + "learning_rate": 5.308189655172414e-05, + "loss": 1.1054, + "step": 6531 + }, + { + "epoch": 7.04, + "learning_rate": 5.307471264367816e-05, + "loss": 1.0192, + "step": 6532 + }, + { + "epoch": 7.04, + "learning_rate": 5.306752873563219e-05, + "loss": 0.9789, + "step": 6533 + }, + { + "epoch": 7.04, + "learning_rate": 5.306034482758621e-05, + "loss": 0.8487, + "step": 6534 + }, + { + "epoch": 7.04, + "learning_rate": 5.3053160919540234e-05, + "loss": 0.9644, + "step": 6535 + }, + { + "epoch": 7.04, + "learning_rate": 5.3045977011494254e-05, + "loss": 0.9919, + "step": 6536 + }, + { + "epoch": 7.04, + "learning_rate": 5.303879310344828e-05, + "loss": 1.0013, + "step": 6537 + }, + { + "epoch": 7.05, + "learning_rate": 5.30316091954023e-05, + "loss": 0.9551, + "step": 6538 + }, + { + "epoch": 7.05, + "learning_rate": 5.302442528735633e-05, + "loss": 0.9681, + "step": 6539 + }, + { + "epoch": 7.05, + "learning_rate": 5.301724137931034e-05, + "loss": 1.0211, + "step": 6540 + }, + { + "epoch": 7.05, + "learning_rate": 5.3010057471264376e-05, + "loss": 0.9541, + "step": 6541 + }, + { + "epoch": 7.05, + "learning_rate": 5.300287356321839e-05, + "loss": 1.1185, + "step": 6542 + }, + { + "epoch": 7.05, + "learning_rate": 5.299568965517242e-05, + "loss": 1.0829, + "step": 6543 + }, + { + "epoch": 7.05, + "learning_rate": 5.298850574712644e-05, + "loss": 0.982, + "step": 6544 + }, + { + "epoch": 7.05, + "learning_rate": 5.2981321839080464e-05, + "loss": 1.106, + "step": 6545 + }, + { + "epoch": 7.05, + "learning_rate": 5.2974137931034485e-05, + "loss": 1.0742, + "step": 6546 + }, + { + "epoch": 7.05, + "learning_rate": 5.296695402298851e-05, + "loss": 0.9861, + "step": 6547 + }, + { + "epoch": 7.06, + "learning_rate": 5.295977011494253e-05, + "loss": 1.0516, + "step": 6548 + }, + { + "epoch": 7.06, + "learning_rate": 5.295258620689656e-05, + "loss": 1.037, + "step": 6549 + }, + { + "epoch": 7.06, + "learning_rate": 5.294540229885058e-05, + "loss": 0.9494, + "step": 6550 + }, + { + "epoch": 7.06, + "learning_rate": 5.293821839080459e-05, + "loss": 0.9203, + "step": 6551 + }, + { + "epoch": 7.06, + "learning_rate": 5.293103448275862e-05, + "loss": 0.9334, + "step": 6552 + }, + { + "epoch": 7.06, + "learning_rate": 5.292385057471264e-05, + "loss": 1.0919, + "step": 6553 + }, + { + "epoch": 7.06, + "learning_rate": 5.291666666666667e-05, + "loss": 1.0706, + "step": 6554 + }, + { + "epoch": 7.06, + "learning_rate": 5.290948275862069e-05, + "loss": 1.1438, + "step": 6555 + }, + { + "epoch": 7.06, + "learning_rate": 5.2902298850574715e-05, + "loss": 0.9285, + "step": 6556 + }, + { + "epoch": 7.07, + "learning_rate": 5.2895114942528735e-05, + "loss": 1.0867, + "step": 6557 + }, + { + "epoch": 7.07, + "learning_rate": 5.288793103448276e-05, + "loss": 0.9559, + "step": 6558 + }, + { + "epoch": 7.07, + "learning_rate": 5.288074712643678e-05, + "loss": 0.9433, + "step": 6559 + }, + { + "epoch": 7.07, + "learning_rate": 5.287356321839081e-05, + "loss": 0.9605, + "step": 6560 + }, + { + "epoch": 7.07, + "learning_rate": 5.2866379310344823e-05, + "loss": 1.0258, + "step": 6561 + }, + { + "epoch": 7.07, + "learning_rate": 5.285919540229886e-05, + "loss": 1.049, + "step": 6562 + }, + { + "epoch": 7.07, + "learning_rate": 5.285201149425287e-05, + "loss": 0.99, + "step": 6563 + }, + { + "epoch": 7.07, + "learning_rate": 5.2844827586206905e-05, + "loss": 1.0339, + "step": 6564 + }, + { + "epoch": 7.07, + "learning_rate": 5.283764367816092e-05, + "loss": 0.9389, + "step": 6565 + }, + { + "epoch": 7.08, + "learning_rate": 5.2830459770114945e-05, + "loss": 1.0379, + "step": 6566 + }, + { + "epoch": 7.08, + "learning_rate": 5.2823275862068966e-05, + "loss": 1.0096, + "step": 6567 + }, + { + "epoch": 7.08, + "learning_rate": 5.281609195402299e-05, + "loss": 1.047, + "step": 6568 + }, + { + "epoch": 7.08, + "learning_rate": 5.280890804597701e-05, + "loss": 1.0232, + "step": 6569 + }, + { + "epoch": 7.08, + "learning_rate": 5.280172413793104e-05, + "loss": 0.9991, + "step": 6570 + }, + { + "epoch": 7.08, + "learning_rate": 5.279454022988506e-05, + "loss": 0.9895, + "step": 6571 + }, + { + "epoch": 7.08, + "learning_rate": 5.278735632183909e-05, + "loss": 1.0188, + "step": 6572 + }, + { + "epoch": 7.08, + "learning_rate": 5.278017241379311e-05, + "loss": 1.0123, + "step": 6573 + }, + { + "epoch": 7.08, + "learning_rate": 5.2772988505747135e-05, + "loss": 0.8861, + "step": 6574 + }, + { + "epoch": 7.09, + "learning_rate": 5.276580459770115e-05, + "loss": 1.1234, + "step": 6575 + }, + { + "epoch": 7.09, + "learning_rate": 5.275862068965518e-05, + "loss": 1.0116, + "step": 6576 + }, + { + "epoch": 7.09, + "learning_rate": 5.2751436781609196e-05, + "loss": 1.0084, + "step": 6577 + }, + { + "epoch": 7.09, + "learning_rate": 5.2744252873563216e-05, + "loss": 0.9802, + "step": 6578 + }, + { + "epoch": 7.09, + "learning_rate": 5.2737068965517243e-05, + "loss": 1.0453, + "step": 6579 + }, + { + "epoch": 7.09, + "learning_rate": 5.2729885057471264e-05, + "loss": 1.1268, + "step": 6580 + }, + { + "epoch": 7.09, + "learning_rate": 5.272270114942529e-05, + "loss": 1.0273, + "step": 6581 + }, + { + "epoch": 7.09, + "learning_rate": 5.271551724137931e-05, + "loss": 0.9575, + "step": 6582 + }, + { + "epoch": 7.09, + "learning_rate": 5.270833333333334e-05, + "loss": 0.9953, + "step": 6583 + }, + { + "epoch": 7.09, + "learning_rate": 5.270114942528735e-05, + "loss": 1.0146, + "step": 6584 + }, + { + "epoch": 7.1, + "learning_rate": 5.2693965517241386e-05, + "loss": 0.9326, + "step": 6585 + }, + { + "epoch": 7.1, + "learning_rate": 5.26867816091954e-05, + "loss": 0.9978, + "step": 6586 + }, + { + "epoch": 7.1, + "learning_rate": 5.267959770114943e-05, + "loss": 0.969, + "step": 6587 + }, + { + "epoch": 7.1, + "learning_rate": 5.267241379310345e-05, + "loss": 0.9636, + "step": 6588 + }, + { + "epoch": 7.1, + "learning_rate": 5.2665229885057474e-05, + "loss": 1.0479, + "step": 6589 + }, + { + "epoch": 7.1, + "learning_rate": 5.2658045977011494e-05, + "loss": 0.9209, + "step": 6590 + }, + { + "epoch": 7.1, + "learning_rate": 5.265086206896552e-05, + "loss": 0.9747, + "step": 6591 + }, + { + "epoch": 7.1, + "learning_rate": 5.264367816091954e-05, + "loss": 1.0925, + "step": 6592 + }, + { + "epoch": 7.1, + "learning_rate": 5.263649425287357e-05, + "loss": 0.9555, + "step": 6593 + }, + { + "epoch": 7.11, + "learning_rate": 5.262931034482759e-05, + "loss": 1.0021, + "step": 6594 + }, + { + "epoch": 7.11, + "learning_rate": 5.2622126436781616e-05, + "loss": 1.0177, + "step": 6595 + }, + { + "epoch": 7.11, + "learning_rate": 5.2614942528735636e-05, + "loss": 1.0793, + "step": 6596 + }, + { + "epoch": 7.11, + "learning_rate": 5.2607758620689663e-05, + "loss": 0.9951, + "step": 6597 + }, + { + "epoch": 7.11, + "learning_rate": 5.260057471264368e-05, + "loss": 1.011, + "step": 6598 + }, + { + "epoch": 7.11, + "learning_rate": 5.259339080459771e-05, + "loss": 1.0425, + "step": 6599 + }, + { + "epoch": 7.11, + "learning_rate": 5.2586206896551724e-05, + "loss": 0.9612, + "step": 6600 + }, + { + "epoch": 7.11, + "learning_rate": 5.257902298850576e-05, + "loss": 0.9497, + "step": 6601 + }, + { + "epoch": 7.11, + "learning_rate": 5.257183908045977e-05, + "loss": 1.1233, + "step": 6602 + }, + { + "epoch": 7.12, + "learning_rate": 5.256465517241379e-05, + "loss": 1.0948, + "step": 6603 + }, + { + "epoch": 7.12, + "learning_rate": 5.255747126436782e-05, + "loss": 1.0798, + "step": 6604 + }, + { + "epoch": 7.12, + "learning_rate": 5.255028735632184e-05, + "loss": 1.0215, + "step": 6605 + }, + { + "epoch": 7.12, + "learning_rate": 5.254310344827587e-05, + "loss": 0.8939, + "step": 6606 + }, + { + "epoch": 7.12, + "learning_rate": 5.253591954022988e-05, + "loss": 0.929, + "step": 6607 + }, + { + "epoch": 7.12, + "learning_rate": 5.2528735632183914e-05, + "loss": 1.0801, + "step": 6608 + }, + { + "epoch": 7.12, + "learning_rate": 5.252155172413793e-05, + "loss": 1.0666, + "step": 6609 + }, + { + "epoch": 7.12, + "learning_rate": 5.251436781609196e-05, + "loss": 1.0847, + "step": 6610 + }, + { + "epoch": 7.12, + "learning_rate": 5.2507183908045975e-05, + "loss": 1.059, + "step": 6611 + }, + { + "epoch": 7.12, + "learning_rate": 5.25e-05, + "loss": 0.9438, + "step": 6612 + }, + { + "epoch": 7.13, + "learning_rate": 5.249281609195402e-05, + "loss": 0.9188, + "step": 6613 + }, + { + "epoch": 7.13, + "learning_rate": 5.248563218390805e-05, + "loss": 1.1258, + "step": 6614 + }, + { + "epoch": 7.13, + "learning_rate": 5.247844827586207e-05, + "loss": 0.9951, + "step": 6615 + }, + { + "epoch": 7.13, + "learning_rate": 5.24712643678161e-05, + "loss": 0.9989, + "step": 6616 + }, + { + "epoch": 7.13, + "learning_rate": 5.246408045977012e-05, + "loss": 1.0076, + "step": 6617 + }, + { + "epoch": 7.13, + "learning_rate": 5.2456896551724144e-05, + "loss": 1.0493, + "step": 6618 + }, + { + "epoch": 7.13, + "learning_rate": 5.2449712643678165e-05, + "loss": 0.9685, + "step": 6619 + }, + { + "epoch": 7.13, + "learning_rate": 5.244252873563219e-05, + "loss": 1.0027, + "step": 6620 + }, + { + "epoch": 7.13, + "learning_rate": 5.2435344827586205e-05, + "loss": 0.945, + "step": 6621 + }, + { + "epoch": 7.14, + "learning_rate": 5.242816091954024e-05, + "loss": 0.8866, + "step": 6622 + }, + { + "epoch": 7.14, + "learning_rate": 5.242097701149425e-05, + "loss": 1.0703, + "step": 6623 + }, + { + "epoch": 7.14, + "learning_rate": 5.241379310344828e-05, + "loss": 0.9786, + "step": 6624 + }, + { + "epoch": 7.14, + "learning_rate": 5.24066091954023e-05, + "loss": 1.0349, + "step": 6625 + }, + { + "epoch": 7.14, + "learning_rate": 5.239942528735633e-05, + "loss": 1.1314, + "step": 6626 + }, + { + "epoch": 7.14, + "learning_rate": 5.239224137931035e-05, + "loss": 1.0625, + "step": 6627 + }, + { + "epoch": 7.14, + "learning_rate": 5.238505747126437e-05, + "loss": 1.1573, + "step": 6628 + }, + { + "epoch": 7.14, + "learning_rate": 5.2377873563218395e-05, + "loss": 0.9212, + "step": 6629 + }, + { + "epoch": 7.14, + "learning_rate": 5.237068965517241e-05, + "loss": 1.0927, + "step": 6630 + }, + { + "epoch": 7.15, + "learning_rate": 5.236350574712644e-05, + "loss": 1.0401, + "step": 6631 + }, + { + "epoch": 7.15, + "learning_rate": 5.2356321839080456e-05, + "loss": 0.9249, + "step": 6632 + }, + { + "epoch": 7.15, + "learning_rate": 5.234913793103448e-05, + "loss": 1.0602, + "step": 6633 + }, + { + "epoch": 7.15, + "learning_rate": 5.2341954022988503e-05, + "loss": 0.9885, + "step": 6634 + }, + { + "epoch": 7.15, + "learning_rate": 5.233477011494253e-05, + "loss": 1.0385, + "step": 6635 + }, + { + "epoch": 7.15, + "learning_rate": 5.232758620689655e-05, + "loss": 0.9661, + "step": 6636 + }, + { + "epoch": 7.15, + "learning_rate": 5.232040229885058e-05, + "loss": 0.9751, + "step": 6637 + }, + { + "epoch": 7.15, + "learning_rate": 5.23132183908046e-05, + "loss": 1.0358, + "step": 6638 + }, + { + "epoch": 7.15, + "learning_rate": 5.2306034482758625e-05, + "loss": 0.9761, + "step": 6639 + }, + { + "epoch": 7.16, + "learning_rate": 5.2298850574712646e-05, + "loss": 0.9574, + "step": 6640 + }, + { + "epoch": 7.16, + "learning_rate": 5.229166666666667e-05, + "loss": 1.0587, + "step": 6641 + }, + { + "epoch": 7.16, + "learning_rate": 5.228448275862069e-05, + "loss": 1.0423, + "step": 6642 + }, + { + "epoch": 7.16, + "learning_rate": 5.227729885057472e-05, + "loss": 1.0942, + "step": 6643 + }, + { + "epoch": 7.16, + "learning_rate": 5.2270114942528734e-05, + "loss": 0.953, + "step": 6644 + }, + { + "epoch": 7.16, + "learning_rate": 5.226293103448277e-05, + "loss": 0.9426, + "step": 6645 + }, + { + "epoch": 7.16, + "learning_rate": 5.225574712643678e-05, + "loss": 1.0307, + "step": 6646 + }, + { + "epoch": 7.16, + "learning_rate": 5.224856321839081e-05, + "loss": 0.9911, + "step": 6647 + }, + { + "epoch": 7.16, + "learning_rate": 5.224137931034483e-05, + "loss": 0.9622, + "step": 6648 + }, + { + "epoch": 7.16, + "learning_rate": 5.2234195402298856e-05, + "loss": 0.996, + "step": 6649 + }, + { + "epoch": 7.17, + "learning_rate": 5.2227011494252876e-05, + "loss": 0.9623, + "step": 6650 + }, + { + "epoch": 7.17, + "learning_rate": 5.22198275862069e-05, + "loss": 1.0756, + "step": 6651 + }, + { + "epoch": 7.17, + "learning_rate": 5.2212643678160923e-05, + "loss": 1.0665, + "step": 6652 + }, + { + "epoch": 7.17, + "learning_rate": 5.220545977011494e-05, + "loss": 0.9539, + "step": 6653 + }, + { + "epoch": 7.17, + "learning_rate": 5.219827586206897e-05, + "loss": 0.9981, + "step": 6654 + }, + { + "epoch": 7.17, + "learning_rate": 5.2191091954022984e-05, + "loss": 1.0116, + "step": 6655 + }, + { + "epoch": 7.17, + "learning_rate": 5.218390804597701e-05, + "loss": 0.8857, + "step": 6656 + }, + { + "epoch": 7.17, + "learning_rate": 5.217672413793103e-05, + "loss": 1.0361, + "step": 6657 + }, + { + "epoch": 7.17, + "learning_rate": 5.216954022988506e-05, + "loss": 1.0722, + "step": 6658 + }, + { + "epoch": 7.18, + "learning_rate": 5.216235632183908e-05, + "loss": 1.0119, + "step": 6659 + }, + { + "epoch": 7.18, + "learning_rate": 5.2155172413793106e-05, + "loss": 0.9998, + "step": 6660 + }, + { + "epoch": 7.18, + "learning_rate": 5.214798850574713e-05, + "loss": 1.0665, + "step": 6661 + }, + { + "epoch": 7.18, + "learning_rate": 5.2140804597701154e-05, + "loss": 0.9824, + "step": 6662 + }, + { + "epoch": 7.18, + "learning_rate": 5.2133620689655174e-05, + "loss": 0.9022, + "step": 6663 + }, + { + "epoch": 7.18, + "learning_rate": 5.21264367816092e-05, + "loss": 1.0212, + "step": 6664 + }, + { + "epoch": 7.18, + "learning_rate": 5.2119252873563215e-05, + "loss": 0.9575, + "step": 6665 + }, + { + "epoch": 7.18, + "learning_rate": 5.211206896551725e-05, + "loss": 0.9778, + "step": 6666 + }, + { + "epoch": 7.18, + "learning_rate": 5.210488505747126e-05, + "loss": 0.9687, + "step": 6667 + }, + { + "epoch": 7.19, + "learning_rate": 5.2097701149425296e-05, + "loss": 1.0588, + "step": 6668 + }, + { + "epoch": 7.19, + "learning_rate": 5.209051724137931e-05, + "loss": 1.0559, + "step": 6669 + }, + { + "epoch": 7.19, + "learning_rate": 5.208333333333334e-05, + "loss": 0.9345, + "step": 6670 + }, + { + "epoch": 7.19, + "learning_rate": 5.207614942528736e-05, + "loss": 1.07, + "step": 6671 + }, + { + "epoch": 7.19, + "learning_rate": 5.2068965517241384e-05, + "loss": 1.014, + "step": 6672 + }, + { + "epoch": 7.19, + "learning_rate": 5.2061781609195404e-05, + "loss": 0.9394, + "step": 6673 + }, + { + "epoch": 7.19, + "learning_rate": 5.205459770114943e-05, + "loss": 1.0994, + "step": 6674 + }, + { + "epoch": 7.19, + "learning_rate": 5.204741379310345e-05, + "loss": 1.0746, + "step": 6675 + }, + { + "epoch": 7.19, + "learning_rate": 5.204022988505748e-05, + "loss": 1.0035, + "step": 6676 + }, + { + "epoch": 7.2, + "learning_rate": 5.20330459770115e-05, + "loss": 0.9427, + "step": 6677 + }, + { + "epoch": 7.2, + "learning_rate": 5.2025862068965526e-05, + "loss": 0.9108, + "step": 6678 + }, + { + "epoch": 7.2, + "learning_rate": 5.201867816091954e-05, + "loss": 0.9719, + "step": 6679 + }, + { + "epoch": 7.2, + "learning_rate": 5.201149425287356e-05, + "loss": 0.9116, + "step": 6680 + }, + { + "epoch": 7.2, + "learning_rate": 5.200431034482759e-05, + "loss": 0.9843, + "step": 6681 + }, + { + "epoch": 7.2, + "learning_rate": 5.199712643678161e-05, + "loss": 0.9931, + "step": 6682 + }, + { + "epoch": 7.2, + "learning_rate": 5.1989942528735635e-05, + "loss": 1.0146, + "step": 6683 + }, + { + "epoch": 7.2, + "learning_rate": 5.1982758620689655e-05, + "loss": 1.1528, + "step": 6684 + }, + { + "epoch": 7.2, + "learning_rate": 5.197557471264368e-05, + "loss": 1.0194, + "step": 6685 + }, + { + "epoch": 7.2, + "learning_rate": 5.19683908045977e-05, + "loss": 0.8993, + "step": 6686 + }, + { + "epoch": 7.21, + "learning_rate": 5.196120689655173e-05, + "loss": 0.8653, + "step": 6687 + }, + { + "epoch": 7.21, + "learning_rate": 5.195402298850574e-05, + "loss": 1.0997, + "step": 6688 + }, + { + "epoch": 7.21, + "learning_rate": 5.194683908045978e-05, + "loss": 0.9837, + "step": 6689 + }, + { + "epoch": 7.21, + "learning_rate": 5.193965517241379e-05, + "loss": 1.0272, + "step": 6690 + }, + { + "epoch": 7.21, + "learning_rate": 5.1932471264367824e-05, + "loss": 0.9338, + "step": 6691 + }, + { + "epoch": 7.21, + "learning_rate": 5.192528735632184e-05, + "loss": 0.9642, + "step": 6692 + }, + { + "epoch": 7.21, + "learning_rate": 5.1918103448275865e-05, + "loss": 0.8924, + "step": 6693 + }, + { + "epoch": 7.21, + "learning_rate": 5.1910919540229885e-05, + "loss": 0.8871, + "step": 6694 + }, + { + "epoch": 7.21, + "learning_rate": 5.190373563218391e-05, + "loss": 1.0496, + "step": 6695 + }, + { + "epoch": 7.22, + "learning_rate": 5.189655172413793e-05, + "loss": 1.0115, + "step": 6696 + }, + { + "epoch": 7.22, + "learning_rate": 5.188936781609196e-05, + "loss": 1.0428, + "step": 6697 + }, + { + "epoch": 7.22, + "learning_rate": 5.188218390804598e-05, + "loss": 0.8683, + "step": 6698 + }, + { + "epoch": 7.22, + "learning_rate": 5.187500000000001e-05, + "loss": 1.0189, + "step": 6699 + }, + { + "epoch": 7.22, + "learning_rate": 5.186781609195403e-05, + "loss": 1.0908, + "step": 6700 + }, + { + "epoch": 7.22, + "learning_rate": 5.1860632183908055e-05, + "loss": 1.0084, + "step": 6701 + }, + { + "epoch": 7.22, + "learning_rate": 5.185344827586207e-05, + "loss": 0.8885, + "step": 6702 + }, + { + "epoch": 7.22, + "learning_rate": 5.18462643678161e-05, + "loss": 0.9679, + "step": 6703 + }, + { + "epoch": 7.22, + "learning_rate": 5.1839080459770116e-05, + "loss": 0.9825, + "step": 6704 + }, + { + "epoch": 7.23, + "learning_rate": 5.1831896551724136e-05, + "loss": 1.0435, + "step": 6705 + }, + { + "epoch": 7.23, + "learning_rate": 5.182471264367816e-05, + "loss": 1.0579, + "step": 6706 + }, + { + "epoch": 7.23, + "learning_rate": 5.1817528735632183e-05, + "loss": 0.994, + "step": 6707 + }, + { + "epoch": 7.23, + "learning_rate": 5.181034482758621e-05, + "loss": 1.031, + "step": 6708 + }, + { + "epoch": 7.23, + "learning_rate": 5.180316091954023e-05, + "loss": 1.0833, + "step": 6709 + }, + { + "epoch": 7.23, + "learning_rate": 5.179597701149426e-05, + "loss": 0.9406, + "step": 6710 + }, + { + "epoch": 7.23, + "learning_rate": 5.178879310344827e-05, + "loss": 1.0009, + "step": 6711 + }, + { + "epoch": 7.23, + "learning_rate": 5.1781609195402305e-05, + "loss": 1.0334, + "step": 6712 + }, + { + "epoch": 7.23, + "learning_rate": 5.177442528735632e-05, + "loss": 1.0126, + "step": 6713 + }, + { + "epoch": 7.23, + "learning_rate": 5.176724137931035e-05, + "loss": 0.993, + "step": 6714 + }, + { + "epoch": 7.24, + "learning_rate": 5.1760057471264366e-05, + "loss": 1.0343, + "step": 6715 + }, + { + "epoch": 7.24, + "learning_rate": 5.1752873563218393e-05, + "loss": 1.0174, + "step": 6716 + }, + { + "epoch": 7.24, + "learning_rate": 5.1745689655172414e-05, + "loss": 1.0166, + "step": 6717 + }, + { + "epoch": 7.24, + "learning_rate": 5.173850574712644e-05, + "loss": 1.042, + "step": 6718 + }, + { + "epoch": 7.24, + "learning_rate": 5.173132183908046e-05, + "loss": 1.2527, + "step": 6719 + }, + { + "epoch": 7.24, + "learning_rate": 5.172413793103449e-05, + "loss": 1.0606, + "step": 6720 + }, + { + "epoch": 7.24, + "learning_rate": 5.171695402298851e-05, + "loss": 0.9451, + "step": 6721 + }, + { + "epoch": 7.24, + "learning_rate": 5.1709770114942536e-05, + "loss": 1.1013, + "step": 6722 + }, + { + "epoch": 7.24, + "learning_rate": 5.1702586206896556e-05, + "loss": 1.0215, + "step": 6723 + }, + { + "epoch": 7.25, + "learning_rate": 5.169540229885058e-05, + "loss": 1.0545, + "step": 6724 + }, + { + "epoch": 7.25, + "learning_rate": 5.16882183908046e-05, + "loss": 0.986, + "step": 6725 + }, + { + "epoch": 7.25, + "learning_rate": 5.168103448275863e-05, + "loss": 0.9683, + "step": 6726 + }, + { + "epoch": 7.25, + "learning_rate": 5.1673850574712644e-05, + "loss": 0.9436, + "step": 6727 + }, + { + "epoch": 7.25, + "learning_rate": 5.166666666666667e-05, + "loss": 0.9022, + "step": 6728 + }, + { + "epoch": 7.25, + "learning_rate": 5.165948275862069e-05, + "loss": 1.0521, + "step": 6729 + }, + { + "epoch": 7.25, + "learning_rate": 5.165229885057471e-05, + "loss": 1.0821, + "step": 6730 + }, + { + "epoch": 7.25, + "learning_rate": 5.164511494252874e-05, + "loss": 0.9664, + "step": 6731 + }, + { + "epoch": 7.25, + "learning_rate": 5.163793103448276e-05, + "loss": 0.9814, + "step": 6732 + }, + { + "epoch": 7.26, + "learning_rate": 5.1630747126436786e-05, + "loss": 0.9894, + "step": 6733 + }, + { + "epoch": 7.26, + "learning_rate": 5.16235632183908e-05, + "loss": 1.0864, + "step": 6734 + }, + { + "epoch": 7.26, + "learning_rate": 5.1616379310344834e-05, + "loss": 0.9224, + "step": 6735 + }, + { + "epoch": 7.26, + "learning_rate": 5.160919540229885e-05, + "loss": 0.9704, + "step": 6736 + }, + { + "epoch": 7.26, + "learning_rate": 5.1602011494252874e-05, + "loss": 1.0363, + "step": 6737 + }, + { + "epoch": 7.26, + "learning_rate": 5.1594827586206895e-05, + "loss": 1.0371, + "step": 6738 + }, + { + "epoch": 7.26, + "learning_rate": 5.158764367816092e-05, + "loss": 1.052, + "step": 6739 + }, + { + "epoch": 7.26, + "learning_rate": 5.158045977011494e-05, + "loss": 0.9682, + "step": 6740 + }, + { + "epoch": 7.26, + "learning_rate": 5.157327586206897e-05, + "loss": 0.9944, + "step": 6741 + }, + { + "epoch": 7.27, + "learning_rate": 5.156609195402299e-05, + "loss": 0.9578, + "step": 6742 + }, + { + "epoch": 7.27, + "learning_rate": 5.155890804597702e-05, + "loss": 1.0562, + "step": 6743 + }, + { + "epoch": 7.27, + "learning_rate": 5.155172413793104e-05, + "loss": 1.0097, + "step": 6744 + }, + { + "epoch": 7.27, + "learning_rate": 5.1544540229885064e-05, + "loss": 1.0711, + "step": 6745 + }, + { + "epoch": 7.27, + "learning_rate": 5.153735632183908e-05, + "loss": 0.9455, + "step": 6746 + }, + { + "epoch": 7.27, + "learning_rate": 5.153017241379311e-05, + "loss": 1.043, + "step": 6747 + }, + { + "epoch": 7.27, + "learning_rate": 5.1522988505747125e-05, + "loss": 0.9212, + "step": 6748 + }, + { + "epoch": 7.27, + "learning_rate": 5.151580459770116e-05, + "loss": 1.0621, + "step": 6749 + }, + { + "epoch": 7.27, + "learning_rate": 5.150862068965517e-05, + "loss": 1.0277, + "step": 6750 + }, + { + "epoch": 7.27, + "eval_loss": 1.1148173809051514, + "eval_runtime": 175.0491, + "eval_samples_per_second": 127.221, + "eval_steps_per_second": 0.663, + "step": 6750 + }, + { + "epoch": 7.27, + "learning_rate": 5.15014367816092e-05, + "loss": 1.0256, + "step": 6751 + }, + { + "epoch": 7.28, + "learning_rate": 5.149425287356322e-05, + "loss": 0.9657, + "step": 6752 + }, + { + "epoch": 7.28, + "learning_rate": 5.148706896551725e-05, + "loss": 1.0485, + "step": 6753 + }, + { + "epoch": 7.28, + "learning_rate": 5.147988505747127e-05, + "loss": 1.0443, + "step": 6754 + }, + { + "epoch": 7.28, + "learning_rate": 5.1472701149425294e-05, + "loss": 1.0487, + "step": 6755 + }, + { + "epoch": 7.28, + "learning_rate": 5.1465517241379315e-05, + "loss": 0.9916, + "step": 6756 + }, + { + "epoch": 7.28, + "learning_rate": 5.145833333333333e-05, + "loss": 0.9667, + "step": 6757 + }, + { + "epoch": 7.28, + "learning_rate": 5.145114942528736e-05, + "loss": 1.0246, + "step": 6758 + }, + { + "epoch": 7.28, + "learning_rate": 5.1443965517241376e-05, + "loss": 0.9833, + "step": 6759 + }, + { + "epoch": 7.28, + "learning_rate": 5.14367816091954e-05, + "loss": 0.9738, + "step": 6760 + }, + { + "epoch": 7.29, + "learning_rate": 5.142959770114942e-05, + "loss": 0.9162, + "step": 6761 + }, + { + "epoch": 7.29, + "learning_rate": 5.142241379310345e-05, + "loss": 0.9891, + "step": 6762 + }, + { + "epoch": 7.29, + "learning_rate": 5.141522988505747e-05, + "loss": 1.0443, + "step": 6763 + }, + { + "epoch": 7.29, + "learning_rate": 5.14080459770115e-05, + "loss": 1.0191, + "step": 6764 + }, + { + "epoch": 7.29, + "learning_rate": 5.140086206896552e-05, + "loss": 1.04, + "step": 6765 + }, + { + "epoch": 7.29, + "learning_rate": 5.1393678160919545e-05, + "loss": 1.1587, + "step": 6766 + }, + { + "epoch": 7.29, + "learning_rate": 5.1386494252873565e-05, + "loss": 1.0605, + "step": 6767 + }, + { + "epoch": 7.29, + "learning_rate": 5.137931034482759e-05, + "loss": 1.0593, + "step": 6768 + }, + { + "epoch": 7.29, + "learning_rate": 5.1372126436781606e-05, + "loss": 0.9252, + "step": 6769 + }, + { + "epoch": 7.3, + "learning_rate": 5.136494252873564e-05, + "loss": 0.9918, + "step": 6770 + }, + { + "epoch": 7.3, + "learning_rate": 5.1357758620689653e-05, + "loss": 1.0294, + "step": 6771 + }, + { + "epoch": 7.3, + "learning_rate": 5.135057471264369e-05, + "loss": 1.1194, + "step": 6772 + }, + { + "epoch": 7.3, + "learning_rate": 5.13433908045977e-05, + "loss": 0.955, + "step": 6773 + }, + { + "epoch": 7.3, + "learning_rate": 5.133620689655173e-05, + "loss": 1.0915, + "step": 6774 + }, + { + "epoch": 7.3, + "learning_rate": 5.132902298850575e-05, + "loss": 1.0556, + "step": 6775 + }, + { + "epoch": 7.3, + "learning_rate": 5.1321839080459775e-05, + "loss": 1.0159, + "step": 6776 + }, + { + "epoch": 7.3, + "learning_rate": 5.1314655172413796e-05, + "loss": 1.0332, + "step": 6777 + }, + { + "epoch": 7.3, + "learning_rate": 5.130747126436782e-05, + "loss": 0.99, + "step": 6778 + }, + { + "epoch": 7.3, + "learning_rate": 5.130028735632184e-05, + "loss": 0.9987, + "step": 6779 + }, + { + "epoch": 7.31, + "learning_rate": 5.129310344827587e-05, + "loss": 0.9916, + "step": 6780 + }, + { + "epoch": 7.31, + "learning_rate": 5.128591954022989e-05, + "loss": 0.9349, + "step": 6781 + }, + { + "epoch": 7.31, + "learning_rate": 5.1278735632183904e-05, + "loss": 0.9681, + "step": 6782 + }, + { + "epoch": 7.31, + "learning_rate": 5.127155172413793e-05, + "loss": 1.0919, + "step": 6783 + }, + { + "epoch": 7.31, + "learning_rate": 5.126436781609195e-05, + "loss": 1.0483, + "step": 6784 + }, + { + "epoch": 7.31, + "learning_rate": 5.125718390804598e-05, + "loss": 1.0185, + "step": 6785 + }, + { + "epoch": 7.31, + "learning_rate": 5.125e-05, + "loss": 1.0481, + "step": 6786 + }, + { + "epoch": 7.31, + "learning_rate": 5.1242816091954026e-05, + "loss": 1.0282, + "step": 6787 + }, + { + "epoch": 7.31, + "learning_rate": 5.1235632183908046e-05, + "loss": 1.0415, + "step": 6788 + }, + { + "epoch": 7.32, + "learning_rate": 5.1228448275862073e-05, + "loss": 1.0125, + "step": 6789 + }, + { + "epoch": 7.32, + "learning_rate": 5.1221264367816094e-05, + "loss": 0.8421, + "step": 6790 + }, + { + "epoch": 7.32, + "learning_rate": 5.121408045977012e-05, + "loss": 1.0115, + "step": 6791 + }, + { + "epoch": 7.32, + "learning_rate": 5.1206896551724134e-05, + "loss": 1.0079, + "step": 6792 + }, + { + "epoch": 7.32, + "learning_rate": 5.119971264367817e-05, + "loss": 1.0108, + "step": 6793 + }, + { + "epoch": 7.32, + "learning_rate": 5.119252873563218e-05, + "loss": 1.0056, + "step": 6794 + }, + { + "epoch": 7.32, + "learning_rate": 5.1185344827586216e-05, + "loss": 0.8705, + "step": 6795 + }, + { + "epoch": 7.32, + "learning_rate": 5.117816091954023e-05, + "loss": 0.9745, + "step": 6796 + }, + { + "epoch": 7.32, + "learning_rate": 5.1170977011494256e-05, + "loss": 0.8842, + "step": 6797 + }, + { + "epoch": 7.33, + "learning_rate": 5.116379310344828e-05, + "loss": 1.0564, + "step": 6798 + }, + { + "epoch": 7.33, + "learning_rate": 5.1156609195402304e-05, + "loss": 0.9968, + "step": 6799 + }, + { + "epoch": 7.33, + "learning_rate": 5.1149425287356324e-05, + "loss": 1.1384, + "step": 6800 + }, + { + "epoch": 7.33, + "learning_rate": 5.114224137931035e-05, + "loss": 1.0537, + "step": 6801 + }, + { + "epoch": 7.33, + "learning_rate": 5.113505747126437e-05, + "loss": 1.13, + "step": 6802 + }, + { + "epoch": 7.33, + "learning_rate": 5.11278735632184e-05, + "loss": 1.0782, + "step": 6803 + }, + { + "epoch": 7.33, + "learning_rate": 5.112068965517242e-05, + "loss": 1.0151, + "step": 6804 + }, + { + "epoch": 7.33, + "learning_rate": 5.1113505747126446e-05, + "loss": 0.978, + "step": 6805 + }, + { + "epoch": 7.33, + "learning_rate": 5.110632183908046e-05, + "loss": 1.0884, + "step": 6806 + }, + { + "epoch": 7.34, + "learning_rate": 5.109913793103448e-05, + "loss": 0.9779, + "step": 6807 + }, + { + "epoch": 7.34, + "learning_rate": 5.109195402298851e-05, + "loss": 1.0346, + "step": 6808 + }, + { + "epoch": 7.34, + "learning_rate": 5.108477011494253e-05, + "loss": 1.0262, + "step": 6809 + }, + { + "epoch": 7.34, + "learning_rate": 5.1077586206896554e-05, + "loss": 1.0634, + "step": 6810 + }, + { + "epoch": 7.34, + "learning_rate": 5.1070402298850575e-05, + "loss": 1.1286, + "step": 6811 + }, + { + "epoch": 7.34, + "learning_rate": 5.10632183908046e-05, + "loss": 1.0917, + "step": 6812 + }, + { + "epoch": 7.34, + "learning_rate": 5.105603448275862e-05, + "loss": 1.0322, + "step": 6813 + }, + { + "epoch": 7.34, + "learning_rate": 5.104885057471265e-05, + "loss": 0.9766, + "step": 6814 + }, + { + "epoch": 7.34, + "learning_rate": 5.104166666666666e-05, + "loss": 1.0616, + "step": 6815 + }, + { + "epoch": 7.34, + "learning_rate": 5.10344827586207e-05, + "loss": 0.9443, + "step": 6816 + }, + { + "epoch": 7.35, + "learning_rate": 5.102729885057471e-05, + "loss": 1.0551, + "step": 6817 + }, + { + "epoch": 7.35, + "learning_rate": 5.102011494252874e-05, + "loss": 0.9889, + "step": 6818 + }, + { + "epoch": 7.35, + "learning_rate": 5.101293103448276e-05, + "loss": 1.0786, + "step": 6819 + }, + { + "epoch": 7.35, + "learning_rate": 5.1005747126436785e-05, + "loss": 0.982, + "step": 6820 + }, + { + "epoch": 7.35, + "learning_rate": 5.0998563218390805e-05, + "loss": 0.9591, + "step": 6821 + }, + { + "epoch": 7.35, + "learning_rate": 5.099137931034483e-05, + "loss": 1.0986, + "step": 6822 + }, + { + "epoch": 7.35, + "learning_rate": 5.098419540229885e-05, + "loss": 1.0637, + "step": 6823 + }, + { + "epoch": 7.35, + "learning_rate": 5.097701149425288e-05, + "loss": 1.0919, + "step": 6824 + }, + { + "epoch": 7.35, + "learning_rate": 5.09698275862069e-05, + "loss": 0.9729, + "step": 6825 + }, + { + "epoch": 7.36, + "learning_rate": 5.096264367816093e-05, + "loss": 1.127, + "step": 6826 + }, + { + "epoch": 7.36, + "learning_rate": 5.095545977011494e-05, + "loss": 0.9785, + "step": 6827 + }, + { + "epoch": 7.36, + "learning_rate": 5.0948275862068974e-05, + "loss": 1.0048, + "step": 6828 + }, + { + "epoch": 7.36, + "learning_rate": 5.094109195402299e-05, + "loss": 1.0879, + "step": 6829 + }, + { + "epoch": 7.36, + "learning_rate": 5.093390804597702e-05, + "loss": 0.9481, + "step": 6830 + }, + { + "epoch": 7.36, + "learning_rate": 5.0926724137931035e-05, + "loss": 1.0158, + "step": 6831 + }, + { + "epoch": 7.36, + "learning_rate": 5.091954022988506e-05, + "loss": 1.1505, + "step": 6832 + }, + { + "epoch": 7.36, + "learning_rate": 5.091235632183908e-05, + "loss": 1.0452, + "step": 6833 + }, + { + "epoch": 7.36, + "learning_rate": 5.09051724137931e-05, + "loss": 0.986, + "step": 6834 + }, + { + "epoch": 7.37, + "learning_rate": 5.089798850574713e-05, + "loss": 1.0944, + "step": 6835 + }, + { + "epoch": 7.37, + "learning_rate": 5.089080459770115e-05, + "loss": 0.9713, + "step": 6836 + }, + { + "epoch": 7.37, + "learning_rate": 5.088362068965518e-05, + "loss": 1.0049, + "step": 6837 + }, + { + "epoch": 7.37, + "learning_rate": 5.087643678160919e-05, + "loss": 0.9049, + "step": 6838 + }, + { + "epoch": 7.37, + "learning_rate": 5.0869252873563225e-05, + "loss": 1.0621, + "step": 6839 + }, + { + "epoch": 7.37, + "learning_rate": 5.086206896551724e-05, + "loss": 1.0409, + "step": 6840 + }, + { + "epoch": 7.37, + "learning_rate": 5.0854885057471266e-05, + "loss": 0.9962, + "step": 6841 + }, + { + "epoch": 7.37, + "learning_rate": 5.0847701149425286e-05, + "loss": 1.0312, + "step": 6842 + }, + { + "epoch": 7.37, + "learning_rate": 5.084051724137931e-05, + "loss": 1.1638, + "step": 6843 + }, + { + "epoch": 7.38, + "learning_rate": 5.0833333333333333e-05, + "loss": 1.1501, + "step": 6844 + }, + { + "epoch": 7.38, + "learning_rate": 5.082614942528736e-05, + "loss": 1.0804, + "step": 6845 + }, + { + "epoch": 7.38, + "learning_rate": 5.081896551724138e-05, + "loss": 0.9343, + "step": 6846 + }, + { + "epoch": 7.38, + "learning_rate": 5.081178160919541e-05, + "loss": 0.9748, + "step": 6847 + }, + { + "epoch": 7.38, + "learning_rate": 5.080459770114943e-05, + "loss": 1.0666, + "step": 6848 + }, + { + "epoch": 7.38, + "learning_rate": 5.0797413793103455e-05, + "loss": 1.1227, + "step": 6849 + }, + { + "epoch": 7.38, + "learning_rate": 5.079022988505747e-05, + "loss": 1.0193, + "step": 6850 + }, + { + "epoch": 7.38, + "learning_rate": 5.07830459770115e-05, + "loss": 1.0558, + "step": 6851 + }, + { + "epoch": 7.38, + "learning_rate": 5.0775862068965516e-05, + "loss": 1.0492, + "step": 6852 + }, + { + "epoch": 7.38, + "learning_rate": 5.076867816091955e-05, + "loss": 1.0242, + "step": 6853 + }, + { + "epoch": 7.39, + "learning_rate": 5.0761494252873564e-05, + "loss": 1.0597, + "step": 6854 + }, + { + "epoch": 7.39, + "learning_rate": 5.075431034482759e-05, + "loss": 1.0652, + "step": 6855 + }, + { + "epoch": 7.39, + "learning_rate": 5.074712643678161e-05, + "loss": 1.1194, + "step": 6856 + }, + { + "epoch": 7.39, + "learning_rate": 5.073994252873564e-05, + "loss": 0.9059, + "step": 6857 + }, + { + "epoch": 7.39, + "learning_rate": 5.073275862068966e-05, + "loss": 1.002, + "step": 6858 + }, + { + "epoch": 7.39, + "learning_rate": 5.072557471264367e-05, + "loss": 1.0218, + "step": 6859 + }, + { + "epoch": 7.39, + "learning_rate": 5.0718390804597706e-05, + "loss": 0.964, + "step": 6860 + }, + { + "epoch": 7.39, + "learning_rate": 5.071120689655172e-05, + "loss": 1.0712, + "step": 6861 + }, + { + "epoch": 7.39, + "learning_rate": 5.0704022988505753e-05, + "loss": 1.0044, + "step": 6862 + }, + { + "epoch": 7.4, + "learning_rate": 5.069683908045977e-05, + "loss": 1.0994, + "step": 6863 + }, + { + "epoch": 7.4, + "learning_rate": 5.0689655172413794e-05, + "loss": 1.0167, + "step": 6864 + }, + { + "epoch": 7.4, + "learning_rate": 5.0682471264367814e-05, + "loss": 0.935, + "step": 6865 + }, + { + "epoch": 7.4, + "learning_rate": 5.067528735632184e-05, + "loss": 1.0464, + "step": 6866 + }, + { + "epoch": 7.4, + "learning_rate": 5.066810344827586e-05, + "loss": 1.0065, + "step": 6867 + }, + { + "epoch": 7.4, + "learning_rate": 5.066091954022989e-05, + "loss": 1.0118, + "step": 6868 + }, + { + "epoch": 7.4, + "learning_rate": 5.065373563218391e-05, + "loss": 1.065, + "step": 6869 + }, + { + "epoch": 7.4, + "learning_rate": 5.0646551724137936e-05, + "loss": 0.9964, + "step": 6870 + }, + { + "epoch": 7.4, + "learning_rate": 5.063936781609196e-05, + "loss": 1.0626, + "step": 6871 + }, + { + "epoch": 7.41, + "learning_rate": 5.0632183908045984e-05, + "loss": 1.0659, + "step": 6872 + }, + { + "epoch": 7.41, + "learning_rate": 5.0625e-05, + "loss": 1.0633, + "step": 6873 + }, + { + "epoch": 7.41, + "learning_rate": 5.061781609195403e-05, + "loss": 0.9771, + "step": 6874 + }, + { + "epoch": 7.41, + "learning_rate": 5.0610632183908045e-05, + "loss": 1.0195, + "step": 6875 + }, + { + "epoch": 7.41, + "learning_rate": 5.060344827586208e-05, + "loss": 1.1723, + "step": 6876 + }, + { + "epoch": 7.41, + "learning_rate": 5.059626436781609e-05, + "loss": 0.9927, + "step": 6877 + }, + { + "epoch": 7.41, + "learning_rate": 5.058908045977012e-05, + "loss": 1.0536, + "step": 6878 + }, + { + "epoch": 7.41, + "learning_rate": 5.058189655172414e-05, + "loss": 0.9797, + "step": 6879 + }, + { + "epoch": 7.41, + "learning_rate": 5.057471264367817e-05, + "loss": 1.0106, + "step": 6880 + }, + { + "epoch": 7.41, + "learning_rate": 5.056752873563219e-05, + "loss": 1.1637, + "step": 6881 + }, + { + "epoch": 7.42, + "learning_rate": 5.0560344827586214e-05, + "loss": 1.0799, + "step": 6882 + }, + { + "epoch": 7.42, + "learning_rate": 5.0553160919540234e-05, + "loss": 0.9857, + "step": 6883 + }, + { + "epoch": 7.42, + "learning_rate": 5.054597701149425e-05, + "loss": 1.1092, + "step": 6884 + }, + { + "epoch": 7.42, + "learning_rate": 5.053879310344828e-05, + "loss": 1.0502, + "step": 6885 + }, + { + "epoch": 7.42, + "learning_rate": 5.0531609195402295e-05, + "loss": 0.9921, + "step": 6886 + }, + { + "epoch": 7.42, + "learning_rate": 5.052442528735632e-05, + "loss": 1.0586, + "step": 6887 + }, + { + "epoch": 7.42, + "learning_rate": 5.051724137931034e-05, + "loss": 1.0296, + "step": 6888 + }, + { + "epoch": 7.42, + "learning_rate": 5.051005747126437e-05, + "loss": 1.0264, + "step": 6889 + }, + { + "epoch": 7.42, + "learning_rate": 5.050287356321839e-05, + "loss": 1.0229, + "step": 6890 + }, + { + "epoch": 7.43, + "learning_rate": 5.049568965517242e-05, + "loss": 0.8932, + "step": 6891 + }, + { + "epoch": 7.43, + "learning_rate": 5.048850574712644e-05, + "loss": 0.9455, + "step": 6892 + }, + { + "epoch": 7.43, + "learning_rate": 5.0481321839080465e-05, + "loss": 1.0989, + "step": 6893 + }, + { + "epoch": 7.43, + "learning_rate": 5.0474137931034485e-05, + "loss": 1.06, + "step": 6894 + }, + { + "epoch": 7.43, + "learning_rate": 5.046695402298851e-05, + "loss": 1.1409, + "step": 6895 + }, + { + "epoch": 7.43, + "learning_rate": 5.0459770114942526e-05, + "loss": 0.9345, + "step": 6896 + }, + { + "epoch": 7.43, + "learning_rate": 5.045258620689656e-05, + "loss": 0.9535, + "step": 6897 + }, + { + "epoch": 7.43, + "learning_rate": 5.044540229885057e-05, + "loss": 0.9861, + "step": 6898 + }, + { + "epoch": 7.43, + "learning_rate": 5.04382183908046e-05, + "loss": 1.0738, + "step": 6899 + }, + { + "epoch": 7.44, + "learning_rate": 5.043103448275862e-05, + "loss": 1.1152, + "step": 6900 + }, + { + "epoch": 7.44, + "learning_rate": 5.042385057471265e-05, + "loss": 0.9634, + "step": 6901 + }, + { + "epoch": 7.44, + "learning_rate": 5.041666666666667e-05, + "loss": 0.9096, + "step": 6902 + }, + { + "epoch": 7.44, + "learning_rate": 5.0409482758620695e-05, + "loss": 0.9029, + "step": 6903 + }, + { + "epoch": 7.44, + "learning_rate": 5.0402298850574715e-05, + "loss": 1.037, + "step": 6904 + }, + { + "epoch": 7.44, + "learning_rate": 5.039511494252874e-05, + "loss": 0.9681, + "step": 6905 + }, + { + "epoch": 7.44, + "learning_rate": 5.038793103448276e-05, + "loss": 1.1895, + "step": 6906 + }, + { + "epoch": 7.44, + "learning_rate": 5.038074712643679e-05, + "loss": 0.9227, + "step": 6907 + }, + { + "epoch": 7.44, + "learning_rate": 5.037356321839081e-05, + "loss": 0.9878, + "step": 6908 + }, + { + "epoch": 7.45, + "learning_rate": 5.0366379310344824e-05, + "loss": 0.9085, + "step": 6909 + }, + { + "epoch": 7.45, + "learning_rate": 5.035919540229885e-05, + "loss": 1.059, + "step": 6910 + }, + { + "epoch": 7.45, + "learning_rate": 5.035201149425287e-05, + "loss": 0.9807, + "step": 6911 + }, + { + "epoch": 7.45, + "learning_rate": 5.03448275862069e-05, + "loss": 0.9976, + "step": 6912 + }, + { + "epoch": 7.45, + "learning_rate": 5.033764367816092e-05, + "loss": 0.9396, + "step": 6913 + }, + { + "epoch": 7.45, + "learning_rate": 5.0330459770114946e-05, + "loss": 1.0608, + "step": 6914 + }, + { + "epoch": 7.45, + "learning_rate": 5.0323275862068966e-05, + "loss": 0.9633, + "step": 6915 + }, + { + "epoch": 7.45, + "learning_rate": 5.031609195402299e-05, + "loss": 0.9523, + "step": 6916 + }, + { + "epoch": 7.45, + "learning_rate": 5.030890804597701e-05, + "loss": 0.9911, + "step": 6917 + }, + { + "epoch": 7.45, + "learning_rate": 5.030172413793104e-05, + "loss": 0.9733, + "step": 6918 + }, + { + "epoch": 7.46, + "learning_rate": 5.0294540229885054e-05, + "loss": 0.9874, + "step": 6919 + }, + { + "epoch": 7.46, + "learning_rate": 5.028735632183909e-05, + "loss": 0.9551, + "step": 6920 + }, + { + "epoch": 7.46, + "learning_rate": 5.02801724137931e-05, + "loss": 0.9339, + "step": 6921 + }, + { + "epoch": 7.46, + "learning_rate": 5.027298850574713e-05, + "loss": 1.0234, + "step": 6922 + }, + { + "epoch": 7.46, + "learning_rate": 5.026580459770115e-05, + "loss": 1.034, + "step": 6923 + }, + { + "epoch": 7.46, + "learning_rate": 5.0258620689655176e-05, + "loss": 0.8733, + "step": 6924 + }, + { + "epoch": 7.46, + "learning_rate": 5.0251436781609196e-05, + "loss": 1.0742, + "step": 6925 + }, + { + "epoch": 7.46, + "learning_rate": 5.024425287356322e-05, + "loss": 0.9396, + "step": 6926 + }, + { + "epoch": 7.46, + "learning_rate": 5.0237068965517244e-05, + "loss": 0.9596, + "step": 6927 + }, + { + "epoch": 7.47, + "learning_rate": 5.022988505747127e-05, + "loss": 1.0633, + "step": 6928 + }, + { + "epoch": 7.47, + "learning_rate": 5.022270114942529e-05, + "loss": 1.0082, + "step": 6929 + }, + { + "epoch": 7.47, + "learning_rate": 5.021551724137932e-05, + "loss": 0.9978, + "step": 6930 + }, + { + "epoch": 7.47, + "learning_rate": 5.020833333333333e-05, + "loss": 0.9157, + "step": 6931 + }, + { + "epoch": 7.47, + "learning_rate": 5.0201149425287366e-05, + "loss": 0.9496, + "step": 6932 + }, + { + "epoch": 7.47, + "learning_rate": 5.019396551724138e-05, + "loss": 1.0308, + "step": 6933 + }, + { + "epoch": 7.47, + "learning_rate": 5.018678160919541e-05, + "loss": 1.1011, + "step": 6934 + }, + { + "epoch": 7.47, + "learning_rate": 5.0179597701149427e-05, + "loss": 0.9661, + "step": 6935 + }, + { + "epoch": 7.47, + "learning_rate": 5.017241379310345e-05, + "loss": 0.9305, + "step": 6936 + }, + { + "epoch": 7.48, + "learning_rate": 5.0165229885057474e-05, + "loss": 1.0121, + "step": 6937 + }, + { + "epoch": 7.48, + "learning_rate": 5.0158045977011494e-05, + "loss": 0.9276, + "step": 6938 + }, + { + "epoch": 7.48, + "learning_rate": 5.015086206896552e-05, + "loss": 1.0747, + "step": 6939 + }, + { + "epoch": 7.48, + "learning_rate": 5.0143678160919535e-05, + "loss": 0.9251, + "step": 6940 + }, + { + "epoch": 7.48, + "learning_rate": 5.013649425287357e-05, + "loss": 0.9408, + "step": 6941 + }, + { + "epoch": 7.48, + "learning_rate": 5.012931034482758e-05, + "loss": 0.9635, + "step": 6942 + }, + { + "epoch": 7.48, + "learning_rate": 5.0122126436781616e-05, + "loss": 1.0224, + "step": 6943 + }, + { + "epoch": 7.48, + "learning_rate": 5.011494252873563e-05, + "loss": 1.0198, + "step": 6944 + }, + { + "epoch": 7.48, + "learning_rate": 5.010775862068966e-05, + "loss": 0.9353, + "step": 6945 + }, + { + "epoch": 7.48, + "learning_rate": 5.010057471264368e-05, + "loss": 0.9815, + "step": 6946 + }, + { + "epoch": 7.49, + "learning_rate": 5.0093390804597704e-05, + "loss": 1.0662, + "step": 6947 + }, + { + "epoch": 7.49, + "learning_rate": 5.0086206896551725e-05, + "loss": 0.9805, + "step": 6948 + }, + { + "epoch": 7.49, + "learning_rate": 5.007902298850575e-05, + "loss": 1.0552, + "step": 6949 + }, + { + "epoch": 7.49, + "learning_rate": 5.007183908045977e-05, + "loss": 1.0281, + "step": 6950 + }, + { + "epoch": 7.49, + "learning_rate": 5.00646551724138e-05, + "loss": 0.9489, + "step": 6951 + }, + { + "epoch": 7.49, + "learning_rate": 5.005747126436782e-05, + "loss": 1.0148, + "step": 6952 + }, + { + "epoch": 7.49, + "learning_rate": 5.0050287356321847e-05, + "loss": 0.9424, + "step": 6953 + }, + { + "epoch": 7.49, + "learning_rate": 5.004310344827586e-05, + "loss": 0.9586, + "step": 6954 + }, + { + "epoch": 7.49, + "learning_rate": 5.0035919540229894e-05, + "loss": 1.0563, + "step": 6955 + }, + { + "epoch": 7.5, + "learning_rate": 5.002873563218391e-05, + "loss": 0.9862, + "step": 6956 + }, + { + "epoch": 7.5, + "learning_rate": 5.002155172413794e-05, + "loss": 1.0398, + "step": 6957 + }, + { + "epoch": 7.5, + "learning_rate": 5.0014367816091955e-05, + "loss": 1.0415, + "step": 6958 + }, + { + "epoch": 7.5, + "learning_rate": 5.000718390804598e-05, + "loss": 1.104, + "step": 6959 + }, + { + "epoch": 7.5, + "learning_rate": 5e-05, + "loss": 0.9473, + "step": 6960 + }, + { + "epoch": 7.5, + "learning_rate": 4.999281609195402e-05, + "loss": 1.0502, + "step": 6961 + }, + { + "epoch": 7.5, + "learning_rate": 4.998563218390805e-05, + "loss": 0.9693, + "step": 6962 + }, + { + "epoch": 7.5, + "learning_rate": 4.997844827586207e-05, + "loss": 1.0267, + "step": 6963 + }, + { + "epoch": 7.5, + "learning_rate": 4.99712643678161e-05, + "loss": 0.8999, + "step": 6964 + }, + { + "epoch": 7.51, + "learning_rate": 4.996408045977012e-05, + "loss": 1.0305, + "step": 6965 + }, + { + "epoch": 7.51, + "learning_rate": 4.9956896551724145e-05, + "loss": 0.8928, + "step": 6966 + }, + { + "epoch": 7.51, + "learning_rate": 4.9949712643678165e-05, + "loss": 1.0175, + "step": 6967 + }, + { + "epoch": 7.51, + "learning_rate": 4.9942528735632185e-05, + "loss": 0.9065, + "step": 6968 + }, + { + "epoch": 7.51, + "learning_rate": 4.993534482758621e-05, + "loss": 1.1373, + "step": 6969 + }, + { + "epoch": 7.51, + "learning_rate": 4.992816091954023e-05, + "loss": 0.9547, + "step": 6970 + }, + { + "epoch": 7.51, + "learning_rate": 4.992097701149426e-05, + "loss": 1.0709, + "step": 6971 + }, + { + "epoch": 7.51, + "learning_rate": 4.991379310344828e-05, + "loss": 1.0553, + "step": 6972 + }, + { + "epoch": 7.51, + "learning_rate": 4.99066091954023e-05, + "loss": 0.8698, + "step": 6973 + }, + { + "epoch": 7.52, + "learning_rate": 4.989942528735632e-05, + "loss": 1.0267, + "step": 6974 + }, + { + "epoch": 7.52, + "learning_rate": 4.989224137931035e-05, + "loss": 1.0886, + "step": 6975 + }, + { + "epoch": 7.52, + "learning_rate": 4.988505747126437e-05, + "loss": 1.0081, + "step": 6976 + }, + { + "epoch": 7.52, + "learning_rate": 4.987787356321839e-05, + "loss": 0.915, + "step": 6977 + }, + { + "epoch": 7.52, + "learning_rate": 4.9870689655172416e-05, + "loss": 1.0735, + "step": 6978 + }, + { + "epoch": 7.52, + "learning_rate": 4.9863505747126436e-05, + "loss": 1.1602, + "step": 6979 + }, + { + "epoch": 7.52, + "learning_rate": 4.985632183908046e-05, + "loss": 1.1181, + "step": 6980 + }, + { + "epoch": 7.52, + "learning_rate": 4.984913793103448e-05, + "loss": 0.9521, + "step": 6981 + }, + { + "epoch": 7.52, + "learning_rate": 4.984195402298851e-05, + "loss": 1.0264, + "step": 6982 + }, + { + "epoch": 7.52, + "learning_rate": 4.983477011494253e-05, + "loss": 1.0676, + "step": 6983 + }, + { + "epoch": 7.53, + "learning_rate": 4.982758620689655e-05, + "loss": 1.1338, + "step": 6984 + }, + { + "epoch": 7.53, + "learning_rate": 4.982040229885058e-05, + "loss": 1.0815, + "step": 6985 + }, + { + "epoch": 7.53, + "learning_rate": 4.98132183908046e-05, + "loss": 0.9829, + "step": 6986 + }, + { + "epoch": 7.53, + "learning_rate": 4.9806034482758626e-05, + "loss": 0.9991, + "step": 6987 + }, + { + "epoch": 7.53, + "learning_rate": 4.9798850574712646e-05, + "loss": 1.1359, + "step": 6988 + }, + { + "epoch": 7.53, + "learning_rate": 4.979166666666667e-05, + "loss": 1.0149, + "step": 6989 + }, + { + "epoch": 7.53, + "learning_rate": 4.978448275862069e-05, + "loss": 0.9448, + "step": 6990 + }, + { + "epoch": 7.53, + "learning_rate": 4.9777298850574714e-05, + "loss": 0.9806, + "step": 6991 + }, + { + "epoch": 7.53, + "learning_rate": 4.977011494252874e-05, + "loss": 1.0158, + "step": 6992 + }, + { + "epoch": 7.54, + "learning_rate": 4.976293103448276e-05, + "loss": 1.0693, + "step": 6993 + }, + { + "epoch": 7.54, + "learning_rate": 4.975574712643679e-05, + "loss": 0.9903, + "step": 6994 + }, + { + "epoch": 7.54, + "learning_rate": 4.974856321839081e-05, + "loss": 1.0958, + "step": 6995 + }, + { + "epoch": 7.54, + "learning_rate": 4.9741379310344836e-05, + "loss": 1.0341, + "step": 6996 + }, + { + "epoch": 7.54, + "learning_rate": 4.9734195402298856e-05, + "loss": 0.9626, + "step": 6997 + }, + { + "epoch": 7.54, + "learning_rate": 4.9727011494252876e-05, + "loss": 1.0051, + "step": 6998 + }, + { + "epoch": 7.54, + "learning_rate": 4.9719827586206897e-05, + "loss": 1.0504, + "step": 6999 + }, + { + "epoch": 7.54, + "learning_rate": 4.971264367816092e-05, + "loss": 1.0625, + "step": 7000 + }, + { + "epoch": 7.54, + "eval_loss": 1.11503267288208, + "eval_runtime": 174.9778, + "eval_samples_per_second": 127.273, + "eval_steps_per_second": 0.663, + "step": 7000 + }, + { + "epoch": 7.54, + "learning_rate": 4.9705459770114944e-05, + "loss": 1.0303, + "step": 7001 + }, + { + "epoch": 7.55, + "learning_rate": 4.9698275862068964e-05, + "loss": 1.0135, + "step": 7002 + }, + { + "epoch": 7.55, + "learning_rate": 4.969109195402299e-05, + "loss": 0.9595, + "step": 7003 + }, + { + "epoch": 7.55, + "learning_rate": 4.968390804597701e-05, + "loss": 1.0272, + "step": 7004 + }, + { + "epoch": 7.55, + "learning_rate": 4.967672413793104e-05, + "loss": 0.8923, + "step": 7005 + }, + { + "epoch": 7.55, + "learning_rate": 4.966954022988506e-05, + "loss": 1.0887, + "step": 7006 + }, + { + "epoch": 7.55, + "learning_rate": 4.966235632183908e-05, + "loss": 0.9638, + "step": 7007 + }, + { + "epoch": 7.55, + "learning_rate": 4.9655172413793107e-05, + "loss": 1.007, + "step": 7008 + }, + { + "epoch": 7.55, + "learning_rate": 4.964798850574713e-05, + "loss": 0.9785, + "step": 7009 + }, + { + "epoch": 7.55, + "learning_rate": 4.9640804597701154e-05, + "loss": 1.0082, + "step": 7010 + }, + { + "epoch": 7.55, + "learning_rate": 4.9633620689655174e-05, + "loss": 1.09, + "step": 7011 + }, + { + "epoch": 7.56, + "learning_rate": 4.9626436781609195e-05, + "loss": 1.0733, + "step": 7012 + }, + { + "epoch": 7.56, + "learning_rate": 4.961925287356322e-05, + "loss": 1.1149, + "step": 7013 + }, + { + "epoch": 7.56, + "learning_rate": 4.961206896551724e-05, + "loss": 1.053, + "step": 7014 + }, + { + "epoch": 7.56, + "learning_rate": 4.960488505747127e-05, + "loss": 1.037, + "step": 7015 + }, + { + "epoch": 7.56, + "learning_rate": 4.959770114942529e-05, + "loss": 1.101, + "step": 7016 + }, + { + "epoch": 7.56, + "learning_rate": 4.9590517241379317e-05, + "loss": 0.9093, + "step": 7017 + }, + { + "epoch": 7.56, + "learning_rate": 4.958333333333334e-05, + "loss": 1.0164, + "step": 7018 + }, + { + "epoch": 7.56, + "learning_rate": 4.957614942528736e-05, + "loss": 0.9814, + "step": 7019 + }, + { + "epoch": 7.56, + "learning_rate": 4.9568965517241384e-05, + "loss": 1.0212, + "step": 7020 + }, + { + "epoch": 7.57, + "learning_rate": 4.9561781609195405e-05, + "loss": 0.941, + "step": 7021 + }, + { + "epoch": 7.57, + "learning_rate": 4.955459770114943e-05, + "loss": 1.0229, + "step": 7022 + }, + { + "epoch": 7.57, + "learning_rate": 4.954741379310345e-05, + "loss": 1.1289, + "step": 7023 + }, + { + "epoch": 7.57, + "learning_rate": 4.954022988505747e-05, + "loss": 0.9912, + "step": 7024 + }, + { + "epoch": 7.57, + "learning_rate": 4.953304597701149e-05, + "loss": 1.0324, + "step": 7025 + }, + { + "epoch": 7.57, + "learning_rate": 4.952586206896552e-05, + "loss": 1.1303, + "step": 7026 + }, + { + "epoch": 7.57, + "learning_rate": 4.951867816091954e-05, + "loss": 1.0259, + "step": 7027 + }, + { + "epoch": 7.57, + "learning_rate": 4.951149425287356e-05, + "loss": 1.0756, + "step": 7028 + }, + { + "epoch": 7.57, + "learning_rate": 4.950431034482759e-05, + "loss": 1.028, + "step": 7029 + }, + { + "epoch": 7.58, + "learning_rate": 4.949712643678161e-05, + "loss": 1.0757, + "step": 7030 + }, + { + "epoch": 7.58, + "learning_rate": 4.9489942528735635e-05, + "loss": 0.9738, + "step": 7031 + }, + { + "epoch": 7.58, + "learning_rate": 4.9482758620689655e-05, + "loss": 1.0931, + "step": 7032 + }, + { + "epoch": 7.58, + "learning_rate": 4.947557471264368e-05, + "loss": 1.0197, + "step": 7033 + }, + { + "epoch": 7.58, + "learning_rate": 4.94683908045977e-05, + "loss": 0.9087, + "step": 7034 + }, + { + "epoch": 7.58, + "learning_rate": 4.946120689655172e-05, + "loss": 1.0031, + "step": 7035 + }, + { + "epoch": 7.58, + "learning_rate": 4.945402298850575e-05, + "loss": 1.0444, + "step": 7036 + }, + { + "epoch": 7.58, + "learning_rate": 4.944683908045977e-05, + "loss": 1.0832, + "step": 7037 + }, + { + "epoch": 7.58, + "learning_rate": 4.94396551724138e-05, + "loss": 0.9592, + "step": 7038 + }, + { + "epoch": 7.59, + "learning_rate": 4.943247126436782e-05, + "loss": 0.8916, + "step": 7039 + }, + { + "epoch": 7.59, + "learning_rate": 4.9425287356321845e-05, + "loss": 1.0688, + "step": 7040 + }, + { + "epoch": 7.59, + "learning_rate": 4.9418103448275865e-05, + "loss": 1.0419, + "step": 7041 + }, + { + "epoch": 7.59, + "learning_rate": 4.9410919540229886e-05, + "loss": 1.1186, + "step": 7042 + }, + { + "epoch": 7.59, + "learning_rate": 4.940373563218391e-05, + "loss": 0.9779, + "step": 7043 + }, + { + "epoch": 7.59, + "learning_rate": 4.939655172413793e-05, + "loss": 1.1136, + "step": 7044 + }, + { + "epoch": 7.59, + "learning_rate": 4.938936781609196e-05, + "loss": 0.9962, + "step": 7045 + }, + { + "epoch": 7.59, + "learning_rate": 4.938218390804598e-05, + "loss": 0.9279, + "step": 7046 + }, + { + "epoch": 7.59, + "learning_rate": 4.937500000000001e-05, + "loss": 0.914, + "step": 7047 + }, + { + "epoch": 7.59, + "learning_rate": 4.936781609195403e-05, + "loss": 0.965, + "step": 7048 + }, + { + "epoch": 7.6, + "learning_rate": 4.936063218390805e-05, + "loss": 0.9745, + "step": 7049 + }, + { + "epoch": 7.6, + "learning_rate": 4.935344827586207e-05, + "loss": 1.0249, + "step": 7050 + }, + { + "epoch": 7.6, + "learning_rate": 4.934626436781609e-05, + "loss": 0.958, + "step": 7051 + }, + { + "epoch": 7.6, + "learning_rate": 4.9339080459770116e-05, + "loss": 1.192, + "step": 7052 + }, + { + "epoch": 7.6, + "learning_rate": 4.9331896551724136e-05, + "loss": 1.1329, + "step": 7053 + }, + { + "epoch": 7.6, + "learning_rate": 4.932471264367816e-05, + "loss": 0.9941, + "step": 7054 + }, + { + "epoch": 7.6, + "learning_rate": 4.9317528735632184e-05, + "loss": 0.9786, + "step": 7055 + }, + { + "epoch": 7.6, + "learning_rate": 4.931034482758621e-05, + "loss": 1.0737, + "step": 7056 + }, + { + "epoch": 7.6, + "learning_rate": 4.930316091954023e-05, + "loss": 1.0222, + "step": 7057 + }, + { + "epoch": 7.61, + "learning_rate": 4.929597701149425e-05, + "loss": 1.1016, + "step": 7058 + }, + { + "epoch": 7.61, + "learning_rate": 4.928879310344828e-05, + "loss": 1.1114, + "step": 7059 + }, + { + "epoch": 7.61, + "learning_rate": 4.92816091954023e-05, + "loss": 1.0352, + "step": 7060 + }, + { + "epoch": 7.61, + "learning_rate": 4.9274425287356326e-05, + "loss": 1.0707, + "step": 7061 + }, + { + "epoch": 7.61, + "learning_rate": 4.9267241379310346e-05, + "loss": 0.9052, + "step": 7062 + }, + { + "epoch": 7.61, + "learning_rate": 4.926005747126437e-05, + "loss": 1.0516, + "step": 7063 + }, + { + "epoch": 7.61, + "learning_rate": 4.9252873563218394e-05, + "loss": 0.9266, + "step": 7064 + }, + { + "epoch": 7.61, + "learning_rate": 4.9245689655172414e-05, + "loss": 1.0286, + "step": 7065 + }, + { + "epoch": 7.61, + "learning_rate": 4.923850574712644e-05, + "loss": 0.9445, + "step": 7066 + }, + { + "epoch": 7.62, + "learning_rate": 4.923132183908046e-05, + "loss": 1.1068, + "step": 7067 + }, + { + "epoch": 7.62, + "learning_rate": 4.922413793103449e-05, + "loss": 0.9497, + "step": 7068 + }, + { + "epoch": 7.62, + "learning_rate": 4.921695402298851e-05, + "loss": 1.0052, + "step": 7069 + }, + { + "epoch": 7.62, + "learning_rate": 4.9209770114942536e-05, + "loss": 0.9676, + "step": 7070 + }, + { + "epoch": 7.62, + "learning_rate": 4.9202586206896556e-05, + "loss": 1.0179, + "step": 7071 + }, + { + "epoch": 7.62, + "learning_rate": 4.9195402298850577e-05, + "loss": 1.0444, + "step": 7072 + }, + { + "epoch": 7.62, + "learning_rate": 4.9188218390804604e-05, + "loss": 0.9195, + "step": 7073 + }, + { + "epoch": 7.62, + "learning_rate": 4.9181034482758624e-05, + "loss": 1.0662, + "step": 7074 + }, + { + "epoch": 7.62, + "learning_rate": 4.917385057471265e-05, + "loss": 1.0273, + "step": 7075 + }, + { + "epoch": 7.62, + "learning_rate": 4.9166666666666665e-05, + "loss": 1.026, + "step": 7076 + }, + { + "epoch": 7.63, + "learning_rate": 4.915948275862069e-05, + "loss": 1.0813, + "step": 7077 + }, + { + "epoch": 7.63, + "learning_rate": 4.915229885057471e-05, + "loss": 0.9455, + "step": 7078 + }, + { + "epoch": 7.63, + "learning_rate": 4.914511494252874e-05, + "loss": 0.8656, + "step": 7079 + }, + { + "epoch": 7.63, + "learning_rate": 4.913793103448276e-05, + "loss": 0.9352, + "step": 7080 + }, + { + "epoch": 7.63, + "learning_rate": 4.913074712643678e-05, + "loss": 0.9914, + "step": 7081 + }, + { + "epoch": 7.63, + "learning_rate": 4.912356321839081e-05, + "loss": 1.0423, + "step": 7082 + }, + { + "epoch": 7.63, + "learning_rate": 4.911637931034483e-05, + "loss": 0.9478, + "step": 7083 + }, + { + "epoch": 7.63, + "learning_rate": 4.9109195402298854e-05, + "loss": 1.0276, + "step": 7084 + }, + { + "epoch": 7.63, + "learning_rate": 4.9102011494252875e-05, + "loss": 1.0798, + "step": 7085 + }, + { + "epoch": 7.64, + "learning_rate": 4.90948275862069e-05, + "loss": 1.0519, + "step": 7086 + }, + { + "epoch": 7.64, + "learning_rate": 4.908764367816092e-05, + "loss": 1.0047, + "step": 7087 + }, + { + "epoch": 7.64, + "learning_rate": 4.908045977011494e-05, + "loss": 1.0041, + "step": 7088 + }, + { + "epoch": 7.64, + "learning_rate": 4.907327586206897e-05, + "loss": 0.9759, + "step": 7089 + }, + { + "epoch": 7.64, + "learning_rate": 4.906609195402299e-05, + "loss": 1.0385, + "step": 7090 + }, + { + "epoch": 7.64, + "learning_rate": 4.905890804597702e-05, + "loss": 0.9588, + "step": 7091 + }, + { + "epoch": 7.64, + "learning_rate": 4.905172413793104e-05, + "loss": 0.9706, + "step": 7092 + }, + { + "epoch": 7.64, + "learning_rate": 4.9044540229885064e-05, + "loss": 0.9375, + "step": 7093 + }, + { + "epoch": 7.64, + "learning_rate": 4.9037356321839085e-05, + "loss": 1.06, + "step": 7094 + }, + { + "epoch": 7.65, + "learning_rate": 4.9030172413793105e-05, + "loss": 0.9202, + "step": 7095 + }, + { + "epoch": 7.65, + "learning_rate": 4.902298850574713e-05, + "loss": 1.0227, + "step": 7096 + }, + { + "epoch": 7.65, + "learning_rate": 4.901580459770115e-05, + "loss": 0.9691, + "step": 7097 + }, + { + "epoch": 7.65, + "learning_rate": 4.900862068965518e-05, + "loss": 1.0735, + "step": 7098 + }, + { + "epoch": 7.65, + "learning_rate": 4.90014367816092e-05, + "loss": 1.0181, + "step": 7099 + }, + { + "epoch": 7.65, + "learning_rate": 4.899425287356322e-05, + "loss": 0.9875, + "step": 7100 + }, + { + "epoch": 7.65, + "learning_rate": 4.898706896551724e-05, + "loss": 1.0864, + "step": 7101 + }, + { + "epoch": 7.65, + "learning_rate": 4.897988505747127e-05, + "loss": 1.0311, + "step": 7102 + }, + { + "epoch": 7.65, + "learning_rate": 4.897270114942529e-05, + "loss": 1.0943, + "step": 7103 + }, + { + "epoch": 7.66, + "learning_rate": 4.896551724137931e-05, + "loss": 1.1329, + "step": 7104 + }, + { + "epoch": 7.66, + "learning_rate": 4.8958333333333335e-05, + "loss": 0.9961, + "step": 7105 + }, + { + "epoch": 7.66, + "learning_rate": 4.8951149425287356e-05, + "loss": 0.9803, + "step": 7106 + }, + { + "epoch": 7.66, + "learning_rate": 4.894396551724138e-05, + "loss": 1.1001, + "step": 7107 + }, + { + "epoch": 7.66, + "learning_rate": 4.89367816091954e-05, + "loss": 1.1907, + "step": 7108 + }, + { + "epoch": 7.66, + "learning_rate": 4.892959770114942e-05, + "loss": 0.954, + "step": 7109 + }, + { + "epoch": 7.66, + "learning_rate": 4.892241379310345e-05, + "loss": 1.0949, + "step": 7110 + }, + { + "epoch": 7.66, + "learning_rate": 4.891522988505747e-05, + "loss": 0.9176, + "step": 7111 + }, + { + "epoch": 7.66, + "learning_rate": 4.89080459770115e-05, + "loss": 1.1104, + "step": 7112 + }, + { + "epoch": 7.66, + "learning_rate": 4.890086206896552e-05, + "loss": 1.0917, + "step": 7113 + }, + { + "epoch": 7.67, + "learning_rate": 4.8893678160919545e-05, + "loss": 0.9956, + "step": 7114 + }, + { + "epoch": 7.67, + "learning_rate": 4.8886494252873566e-05, + "loss": 1.0493, + "step": 7115 + }, + { + "epoch": 7.67, + "learning_rate": 4.8879310344827586e-05, + "loss": 1.011, + "step": 7116 + }, + { + "epoch": 7.67, + "learning_rate": 4.887212643678161e-05, + "loss": 1.0034, + "step": 7117 + }, + { + "epoch": 7.67, + "learning_rate": 4.886494252873563e-05, + "loss": 0.9198, + "step": 7118 + }, + { + "epoch": 7.67, + "learning_rate": 4.885775862068966e-05, + "loss": 0.9831, + "step": 7119 + }, + { + "epoch": 7.67, + "learning_rate": 4.885057471264368e-05, + "loss": 0.9945, + "step": 7120 + }, + { + "epoch": 7.67, + "learning_rate": 4.884339080459771e-05, + "loss": 0.9779, + "step": 7121 + }, + { + "epoch": 7.67, + "learning_rate": 4.883620689655173e-05, + "loss": 1.1121, + "step": 7122 + }, + { + "epoch": 7.68, + "learning_rate": 4.882902298850575e-05, + "loss": 1.1004, + "step": 7123 + }, + { + "epoch": 7.68, + "learning_rate": 4.8821839080459776e-05, + "loss": 0.8267, + "step": 7124 + }, + { + "epoch": 7.68, + "learning_rate": 4.8814655172413796e-05, + "loss": 1.0163, + "step": 7125 + }, + { + "epoch": 7.68, + "learning_rate": 4.880747126436782e-05, + "loss": 1.1237, + "step": 7126 + }, + { + "epoch": 7.68, + "learning_rate": 4.8800287356321837e-05, + "loss": 1.0122, + "step": 7127 + }, + { + "epoch": 7.68, + "learning_rate": 4.8793103448275864e-05, + "loss": 0.9966, + "step": 7128 + }, + { + "epoch": 7.68, + "learning_rate": 4.8785919540229884e-05, + "loss": 0.9906, + "step": 7129 + }, + { + "epoch": 7.68, + "learning_rate": 4.877873563218391e-05, + "loss": 0.9511, + "step": 7130 + }, + { + "epoch": 7.68, + "learning_rate": 4.877155172413793e-05, + "loss": 1.0408, + "step": 7131 + }, + { + "epoch": 7.69, + "learning_rate": 4.876436781609195e-05, + "loss": 1.101, + "step": 7132 + }, + { + "epoch": 7.69, + "learning_rate": 4.875718390804598e-05, + "loss": 1.0171, + "step": 7133 + }, + { + "epoch": 7.69, + "learning_rate": 4.875e-05, + "loss": 0.9945, + "step": 7134 + }, + { + "epoch": 7.69, + "learning_rate": 4.8742816091954026e-05, + "loss": 1.0386, + "step": 7135 + }, + { + "epoch": 7.69, + "learning_rate": 4.8735632183908047e-05, + "loss": 0.9957, + "step": 7136 + }, + { + "epoch": 7.69, + "learning_rate": 4.8728448275862074e-05, + "loss": 1.14, + "step": 7137 + }, + { + "epoch": 7.69, + "learning_rate": 4.8721264367816094e-05, + "loss": 0.9311, + "step": 7138 + }, + { + "epoch": 7.69, + "learning_rate": 4.8714080459770114e-05, + "loss": 0.9787, + "step": 7139 + }, + { + "epoch": 7.69, + "learning_rate": 4.870689655172414e-05, + "loss": 1.0126, + "step": 7140 + }, + { + "epoch": 7.7, + "learning_rate": 4.869971264367816e-05, + "loss": 0.9241, + "step": 7141 + }, + { + "epoch": 7.7, + "learning_rate": 4.869252873563219e-05, + "loss": 0.9952, + "step": 7142 + }, + { + "epoch": 7.7, + "learning_rate": 4.868534482758621e-05, + "loss": 0.9612, + "step": 7143 + }, + { + "epoch": 7.7, + "learning_rate": 4.8678160919540236e-05, + "loss": 0.9995, + "step": 7144 + }, + { + "epoch": 7.7, + "learning_rate": 4.8670977011494257e-05, + "loss": 1.102, + "step": 7145 + }, + { + "epoch": 7.7, + "learning_rate": 4.866379310344828e-05, + "loss": 1.1467, + "step": 7146 + }, + { + "epoch": 7.7, + "learning_rate": 4.8656609195402304e-05, + "loss": 0.8934, + "step": 7147 + }, + { + "epoch": 7.7, + "learning_rate": 4.8649425287356324e-05, + "loss": 1.0612, + "step": 7148 + }, + { + "epoch": 7.7, + "learning_rate": 4.864224137931035e-05, + "loss": 1.0369, + "step": 7149 + }, + { + "epoch": 7.7, + "learning_rate": 4.863505747126437e-05, + "loss": 1.107, + "step": 7150 + }, + { + "epoch": 7.71, + "learning_rate": 4.86278735632184e-05, + "loss": 1.1016, + "step": 7151 + }, + { + "epoch": 7.71, + "learning_rate": 4.862068965517241e-05, + "loss": 1.0646, + "step": 7152 + }, + { + "epoch": 7.71, + "learning_rate": 4.861350574712644e-05, + "loss": 1.0841, + "step": 7153 + }, + { + "epoch": 7.71, + "learning_rate": 4.860632183908046e-05, + "loss": 1.0367, + "step": 7154 + }, + { + "epoch": 7.71, + "learning_rate": 4.859913793103448e-05, + "loss": 0.9667, + "step": 7155 + }, + { + "epoch": 7.71, + "learning_rate": 4.859195402298851e-05, + "loss": 1.0278, + "step": 7156 + }, + { + "epoch": 7.71, + "learning_rate": 4.858477011494253e-05, + "loss": 0.9661, + "step": 7157 + }, + { + "epoch": 7.71, + "learning_rate": 4.8577586206896555e-05, + "loss": 1.0164, + "step": 7158 + }, + { + "epoch": 7.71, + "learning_rate": 4.8570402298850575e-05, + "loss": 1.0808, + "step": 7159 + }, + { + "epoch": 7.72, + "learning_rate": 4.85632183908046e-05, + "loss": 1.079, + "step": 7160 + }, + { + "epoch": 7.72, + "learning_rate": 4.855603448275862e-05, + "loss": 1.0146, + "step": 7161 + }, + { + "epoch": 7.72, + "learning_rate": 4.854885057471264e-05, + "loss": 0.9948, + "step": 7162 + }, + { + "epoch": 7.72, + "learning_rate": 4.854166666666667e-05, + "loss": 0.9774, + "step": 7163 + }, + { + "epoch": 7.72, + "learning_rate": 4.853448275862069e-05, + "loss": 0.9031, + "step": 7164 + }, + { + "epoch": 7.72, + "learning_rate": 4.852729885057472e-05, + "loss": 0.956, + "step": 7165 + }, + { + "epoch": 7.72, + "learning_rate": 4.852011494252874e-05, + "loss": 0.9929, + "step": 7166 + }, + { + "epoch": 7.72, + "learning_rate": 4.8512931034482765e-05, + "loss": 1.0253, + "step": 7167 + }, + { + "epoch": 7.72, + "learning_rate": 4.8505747126436785e-05, + "loss": 1.0148, + "step": 7168 + }, + { + "epoch": 7.73, + "learning_rate": 4.8498563218390805e-05, + "loss": 1.0856, + "step": 7169 + }, + { + "epoch": 7.73, + "learning_rate": 4.849137931034483e-05, + "loss": 1.0447, + "step": 7170 + }, + { + "epoch": 7.73, + "learning_rate": 4.848419540229885e-05, + "loss": 0.98, + "step": 7171 + }, + { + "epoch": 7.73, + "learning_rate": 4.847701149425288e-05, + "loss": 0.9943, + "step": 7172 + }, + { + "epoch": 7.73, + "learning_rate": 4.84698275862069e-05, + "loss": 0.9338, + "step": 7173 + }, + { + "epoch": 7.73, + "learning_rate": 4.846264367816093e-05, + "loss": 1.1309, + "step": 7174 + }, + { + "epoch": 7.73, + "learning_rate": 4.845545977011495e-05, + "loss": 1.0672, + "step": 7175 + }, + { + "epoch": 7.73, + "learning_rate": 4.844827586206897e-05, + "loss": 0.9174, + "step": 7176 + }, + { + "epoch": 7.73, + "learning_rate": 4.8441091954022995e-05, + "loss": 0.9718, + "step": 7177 + }, + { + "epoch": 7.73, + "learning_rate": 4.843390804597701e-05, + "loss": 1.0382, + "step": 7178 + }, + { + "epoch": 7.74, + "learning_rate": 4.8426724137931036e-05, + "loss": 0.9585, + "step": 7179 + }, + { + "epoch": 7.74, + "learning_rate": 4.8419540229885056e-05, + "loss": 0.9187, + "step": 7180 + }, + { + "epoch": 7.74, + "learning_rate": 4.841235632183908e-05, + "loss": 0.9703, + "step": 7181 + }, + { + "epoch": 7.74, + "learning_rate": 4.84051724137931e-05, + "loss": 0.967, + "step": 7182 + }, + { + "epoch": 7.74, + "learning_rate": 4.839798850574713e-05, + "loss": 0.952, + "step": 7183 + }, + { + "epoch": 7.74, + "learning_rate": 4.839080459770115e-05, + "loss": 1.0075, + "step": 7184 + }, + { + "epoch": 7.74, + "learning_rate": 4.838362068965517e-05, + "loss": 1.1302, + "step": 7185 + }, + { + "epoch": 7.74, + "learning_rate": 4.83764367816092e-05, + "loss": 1.0704, + "step": 7186 + }, + { + "epoch": 7.74, + "learning_rate": 4.836925287356322e-05, + "loss": 1.0115, + "step": 7187 + }, + { + "epoch": 7.75, + "learning_rate": 4.8362068965517246e-05, + "loss": 1.1536, + "step": 7188 + }, + { + "epoch": 7.75, + "learning_rate": 4.8354885057471266e-05, + "loss": 0.9613, + "step": 7189 + }, + { + "epoch": 7.75, + "learning_rate": 4.834770114942529e-05, + "loss": 0.9932, + "step": 7190 + }, + { + "epoch": 7.75, + "learning_rate": 4.834051724137931e-05, + "loss": 0.9728, + "step": 7191 + }, + { + "epoch": 7.75, + "learning_rate": 4.8333333333333334e-05, + "loss": 0.9776, + "step": 7192 + }, + { + "epoch": 7.75, + "learning_rate": 4.832614942528736e-05, + "loss": 1.0862, + "step": 7193 + }, + { + "epoch": 7.75, + "learning_rate": 4.831896551724138e-05, + "loss": 1.1487, + "step": 7194 + }, + { + "epoch": 7.75, + "learning_rate": 4.831178160919541e-05, + "loss": 1.0125, + "step": 7195 + }, + { + "epoch": 7.75, + "learning_rate": 4.830459770114943e-05, + "loss": 1.2353, + "step": 7196 + }, + { + "epoch": 7.76, + "learning_rate": 4.829741379310345e-05, + "loss": 1.0359, + "step": 7197 + }, + { + "epoch": 7.76, + "learning_rate": 4.8290229885057476e-05, + "loss": 1.0713, + "step": 7198 + }, + { + "epoch": 7.76, + "learning_rate": 4.8283045977011496e-05, + "loss": 1.0671, + "step": 7199 + }, + { + "epoch": 7.76, + "learning_rate": 4.827586206896552e-05, + "loss": 1.1038, + "step": 7200 + }, + { + "epoch": 7.76, + "learning_rate": 4.8268678160919544e-05, + "loss": 0.9691, + "step": 7201 + }, + { + "epoch": 7.76, + "learning_rate": 4.826149425287357e-05, + "loss": 1.1368, + "step": 7202 + }, + { + "epoch": 7.76, + "learning_rate": 4.825431034482759e-05, + "loss": 1.0618, + "step": 7203 + }, + { + "epoch": 7.76, + "learning_rate": 4.824712643678161e-05, + "loss": 0.8616, + "step": 7204 + }, + { + "epoch": 7.76, + "learning_rate": 4.823994252873563e-05, + "loss": 0.9886, + "step": 7205 + }, + { + "epoch": 7.77, + "learning_rate": 4.823275862068965e-05, + "loss": 1.1138, + "step": 7206 + }, + { + "epoch": 7.77, + "learning_rate": 4.822557471264368e-05, + "loss": 1.0271, + "step": 7207 + }, + { + "epoch": 7.77, + "learning_rate": 4.82183908045977e-05, + "loss": 1.0958, + "step": 7208 + }, + { + "epoch": 7.77, + "learning_rate": 4.8211206896551727e-05, + "loss": 1.1192, + "step": 7209 + }, + { + "epoch": 7.77, + "learning_rate": 4.820402298850575e-05, + "loss": 1.0006, + "step": 7210 + }, + { + "epoch": 7.77, + "learning_rate": 4.8196839080459774e-05, + "loss": 1.003, + "step": 7211 + }, + { + "epoch": 7.77, + "learning_rate": 4.8189655172413794e-05, + "loss": 1.0033, + "step": 7212 + }, + { + "epoch": 7.77, + "learning_rate": 4.8182471264367815e-05, + "loss": 0.9696, + "step": 7213 + }, + { + "epoch": 7.77, + "learning_rate": 4.817528735632184e-05, + "loss": 0.9649, + "step": 7214 + }, + { + "epoch": 7.77, + "learning_rate": 4.816810344827586e-05, + "loss": 0.9965, + "step": 7215 + }, + { + "epoch": 7.78, + "learning_rate": 4.816091954022989e-05, + "loss": 1.0876, + "step": 7216 + }, + { + "epoch": 7.78, + "learning_rate": 4.815373563218391e-05, + "loss": 0.9566, + "step": 7217 + }, + { + "epoch": 7.78, + "learning_rate": 4.8146551724137937e-05, + "loss": 1.0602, + "step": 7218 + }, + { + "epoch": 7.78, + "learning_rate": 4.813936781609196e-05, + "loss": 1.0401, + "step": 7219 + }, + { + "epoch": 7.78, + "learning_rate": 4.813218390804598e-05, + "loss": 1.1323, + "step": 7220 + }, + { + "epoch": 7.78, + "learning_rate": 4.8125000000000004e-05, + "loss": 0.9675, + "step": 7221 + }, + { + "epoch": 7.78, + "learning_rate": 4.8117816091954025e-05, + "loss": 0.9777, + "step": 7222 + }, + { + "epoch": 7.78, + "learning_rate": 4.811063218390805e-05, + "loss": 1.0848, + "step": 7223 + }, + { + "epoch": 7.78, + "learning_rate": 4.810344827586207e-05, + "loss": 0.9969, + "step": 7224 + }, + { + "epoch": 7.79, + "learning_rate": 4.80962643678161e-05, + "loss": 1.036, + "step": 7225 + }, + { + "epoch": 7.79, + "learning_rate": 4.808908045977012e-05, + "loss": 1.1186, + "step": 7226 + }, + { + "epoch": 7.79, + "learning_rate": 4.808189655172414e-05, + "loss": 1.1007, + "step": 7227 + }, + { + "epoch": 7.79, + "learning_rate": 4.807471264367817e-05, + "loss": 0.9601, + "step": 7228 + }, + { + "epoch": 7.79, + "learning_rate": 4.806752873563218e-05, + "loss": 0.9874, + "step": 7229 + }, + { + "epoch": 7.79, + "learning_rate": 4.806034482758621e-05, + "loss": 1.0623, + "step": 7230 + }, + { + "epoch": 7.79, + "learning_rate": 4.805316091954023e-05, + "loss": 1.0692, + "step": 7231 + }, + { + "epoch": 7.79, + "learning_rate": 4.8045977011494255e-05, + "loss": 1.0272, + "step": 7232 + }, + { + "epoch": 7.79, + "learning_rate": 4.8038793103448275e-05, + "loss": 1.0408, + "step": 7233 + }, + { + "epoch": 7.8, + "learning_rate": 4.80316091954023e-05, + "loss": 1.0561, + "step": 7234 + }, + { + "epoch": 7.8, + "learning_rate": 4.802442528735632e-05, + "loss": 1.0289, + "step": 7235 + }, + { + "epoch": 7.8, + "learning_rate": 4.801724137931034e-05, + "loss": 1.0568, + "step": 7236 + }, + { + "epoch": 7.8, + "learning_rate": 4.801005747126437e-05, + "loss": 1.0123, + "step": 7237 + }, + { + "epoch": 7.8, + "learning_rate": 4.800287356321839e-05, + "loss": 1.0412, + "step": 7238 + }, + { + "epoch": 7.8, + "learning_rate": 4.799568965517242e-05, + "loss": 0.9721, + "step": 7239 + }, + { + "epoch": 7.8, + "learning_rate": 4.798850574712644e-05, + "loss": 1.0164, + "step": 7240 + }, + { + "epoch": 7.8, + "learning_rate": 4.7981321839080465e-05, + "loss": 0.998, + "step": 7241 + }, + { + "epoch": 7.8, + "learning_rate": 4.7974137931034485e-05, + "loss": 0.9909, + "step": 7242 + }, + { + "epoch": 7.8, + "learning_rate": 4.7966954022988506e-05, + "loss": 1.018, + "step": 7243 + }, + { + "epoch": 7.81, + "learning_rate": 4.795977011494253e-05, + "loss": 1.0485, + "step": 7244 + }, + { + "epoch": 7.81, + "learning_rate": 4.795258620689655e-05, + "loss": 1.0083, + "step": 7245 + }, + { + "epoch": 7.81, + "learning_rate": 4.794540229885058e-05, + "loss": 1.0753, + "step": 7246 + }, + { + "epoch": 7.81, + "learning_rate": 4.79382183908046e-05, + "loss": 1.0601, + "step": 7247 + }, + { + "epoch": 7.81, + "learning_rate": 4.793103448275863e-05, + "loss": 1.0777, + "step": 7248 + }, + { + "epoch": 7.81, + "learning_rate": 4.792385057471265e-05, + "loss": 1.0505, + "step": 7249 + }, + { + "epoch": 7.81, + "learning_rate": 4.791666666666667e-05, + "loss": 0.9891, + "step": 7250 + }, + { + "epoch": 7.81, + "eval_loss": 1.1126320362091064, + "eval_runtime": 174.8661, + "eval_samples_per_second": 127.355, + "eval_steps_per_second": 0.663, + "step": 7250 + }, + { + "epoch": 7.81, + "learning_rate": 4.7909482758620695e-05, + "loss": 1.0277, + "step": 7251 + }, + { + "epoch": 7.81, + "learning_rate": 4.7902298850574716e-05, + "loss": 1.0468, + "step": 7252 + }, + { + "epoch": 7.82, + "learning_rate": 4.789511494252874e-05, + "loss": 1.0631, + "step": 7253 + }, + { + "epoch": 7.82, + "learning_rate": 4.788793103448276e-05, + "loss": 0.9974, + "step": 7254 + }, + { + "epoch": 7.82, + "learning_rate": 4.788074712643678e-05, + "loss": 0.9734, + "step": 7255 + }, + { + "epoch": 7.82, + "learning_rate": 4.7873563218390804e-05, + "loss": 1.1092, + "step": 7256 + }, + { + "epoch": 7.82, + "learning_rate": 4.786637931034483e-05, + "loss": 0.9315, + "step": 7257 + }, + { + "epoch": 7.82, + "learning_rate": 4.785919540229885e-05, + "loss": 1.0662, + "step": 7258 + }, + { + "epoch": 7.82, + "learning_rate": 4.785201149425287e-05, + "loss": 0.9673, + "step": 7259 + }, + { + "epoch": 7.82, + "learning_rate": 4.78448275862069e-05, + "loss": 0.948, + "step": 7260 + }, + { + "epoch": 7.82, + "learning_rate": 4.783764367816092e-05, + "loss": 0.9841, + "step": 7261 + }, + { + "epoch": 7.83, + "learning_rate": 4.7830459770114946e-05, + "loss": 1.0013, + "step": 7262 + }, + { + "epoch": 7.83, + "learning_rate": 4.7823275862068966e-05, + "loss": 1.0015, + "step": 7263 + }, + { + "epoch": 7.83, + "learning_rate": 4.781609195402299e-05, + "loss": 0.9875, + "step": 7264 + }, + { + "epoch": 7.83, + "learning_rate": 4.7808908045977014e-05, + "loss": 0.9409, + "step": 7265 + }, + { + "epoch": 7.83, + "learning_rate": 4.7801724137931034e-05, + "loss": 1.062, + "step": 7266 + }, + { + "epoch": 7.83, + "learning_rate": 4.779454022988506e-05, + "loss": 1.147, + "step": 7267 + }, + { + "epoch": 7.83, + "learning_rate": 4.778735632183908e-05, + "loss": 0.9217, + "step": 7268 + }, + { + "epoch": 7.83, + "learning_rate": 4.778017241379311e-05, + "loss": 0.9934, + "step": 7269 + }, + { + "epoch": 7.83, + "learning_rate": 4.777298850574713e-05, + "loss": 0.9402, + "step": 7270 + }, + { + "epoch": 7.84, + "learning_rate": 4.7765804597701156e-05, + "loss": 1.0957, + "step": 7271 + }, + { + "epoch": 7.84, + "learning_rate": 4.7758620689655176e-05, + "loss": 1.0946, + "step": 7272 + }, + { + "epoch": 7.84, + "learning_rate": 4.7751436781609196e-05, + "loss": 1.031, + "step": 7273 + }, + { + "epoch": 7.84, + "learning_rate": 4.7744252873563224e-05, + "loss": 0.9431, + "step": 7274 + }, + { + "epoch": 7.84, + "learning_rate": 4.7737068965517244e-05, + "loss": 0.9719, + "step": 7275 + }, + { + "epoch": 7.84, + "learning_rate": 4.772988505747127e-05, + "loss": 0.9684, + "step": 7276 + }, + { + "epoch": 7.84, + "learning_rate": 4.772270114942529e-05, + "loss": 1.0297, + "step": 7277 + }, + { + "epoch": 7.84, + "learning_rate": 4.771551724137931e-05, + "loss": 1.0337, + "step": 7278 + }, + { + "epoch": 7.84, + "learning_rate": 4.770833333333334e-05, + "loss": 1.1328, + "step": 7279 + }, + { + "epoch": 7.84, + "learning_rate": 4.770114942528736e-05, + "loss": 1.0087, + "step": 7280 + }, + { + "epoch": 7.85, + "learning_rate": 4.769396551724138e-05, + "loss": 0.9817, + "step": 7281 + }, + { + "epoch": 7.85, + "learning_rate": 4.76867816091954e-05, + "loss": 1.0426, + "step": 7282 + }, + { + "epoch": 7.85, + "learning_rate": 4.767959770114943e-05, + "loss": 1.0959, + "step": 7283 + }, + { + "epoch": 7.85, + "learning_rate": 4.767241379310345e-05, + "loss": 1.032, + "step": 7284 + }, + { + "epoch": 7.85, + "learning_rate": 4.7665229885057474e-05, + "loss": 1.1284, + "step": 7285 + }, + { + "epoch": 7.85, + "learning_rate": 4.7658045977011495e-05, + "loss": 0.9389, + "step": 7286 + }, + { + "epoch": 7.85, + "learning_rate": 4.765086206896552e-05, + "loss": 1.04, + "step": 7287 + }, + { + "epoch": 7.85, + "learning_rate": 4.764367816091954e-05, + "loss": 0.9273, + "step": 7288 + }, + { + "epoch": 7.85, + "learning_rate": 4.763649425287356e-05, + "loss": 1.0303, + "step": 7289 + }, + { + "epoch": 7.86, + "learning_rate": 4.762931034482759e-05, + "loss": 0.9603, + "step": 7290 + }, + { + "epoch": 7.86, + "learning_rate": 4.762212643678161e-05, + "loss": 1.0018, + "step": 7291 + }, + { + "epoch": 7.86, + "learning_rate": 4.761494252873564e-05, + "loss": 1.0556, + "step": 7292 + }, + { + "epoch": 7.86, + "learning_rate": 4.760775862068966e-05, + "loss": 0.9886, + "step": 7293 + }, + { + "epoch": 7.86, + "learning_rate": 4.760057471264368e-05, + "loss": 0.9591, + "step": 7294 + }, + { + "epoch": 7.86, + "learning_rate": 4.7593390804597705e-05, + "loss": 1.0842, + "step": 7295 + }, + { + "epoch": 7.86, + "learning_rate": 4.7586206896551725e-05, + "loss": 0.9631, + "step": 7296 + }, + { + "epoch": 7.86, + "learning_rate": 4.757902298850575e-05, + "loss": 0.91, + "step": 7297 + }, + { + "epoch": 7.86, + "learning_rate": 4.757183908045977e-05, + "loss": 1.0265, + "step": 7298 + }, + { + "epoch": 7.87, + "learning_rate": 4.75646551724138e-05, + "loss": 0.983, + "step": 7299 + }, + { + "epoch": 7.87, + "learning_rate": 4.755747126436782e-05, + "loss": 0.9232, + "step": 7300 + }, + { + "epoch": 7.87, + "learning_rate": 4.755028735632184e-05, + "loss": 1.0204, + "step": 7301 + }, + { + "epoch": 7.87, + "learning_rate": 4.754310344827587e-05, + "loss": 0.9495, + "step": 7302 + }, + { + "epoch": 7.87, + "learning_rate": 4.753591954022989e-05, + "loss": 1.08, + "step": 7303 + }, + { + "epoch": 7.87, + "learning_rate": 4.7528735632183915e-05, + "loss": 0.9313, + "step": 7304 + }, + { + "epoch": 7.87, + "learning_rate": 4.7521551724137935e-05, + "loss": 0.9486, + "step": 7305 + }, + { + "epoch": 7.87, + "learning_rate": 4.7514367816091955e-05, + "loss": 1.0991, + "step": 7306 + }, + { + "epoch": 7.87, + "learning_rate": 4.7507183908045976e-05, + "loss": 1.0822, + "step": 7307 + }, + { + "epoch": 7.88, + "learning_rate": 4.75e-05, + "loss": 1.0179, + "step": 7308 + }, + { + "epoch": 7.88, + "learning_rate": 4.749281609195402e-05, + "loss": 1.0553, + "step": 7309 + }, + { + "epoch": 7.88, + "learning_rate": 4.748563218390804e-05, + "loss": 0.9751, + "step": 7310 + }, + { + "epoch": 7.88, + "learning_rate": 4.747844827586207e-05, + "loss": 0.9419, + "step": 7311 + }, + { + "epoch": 7.88, + "learning_rate": 4.747126436781609e-05, + "loss": 1.0597, + "step": 7312 + }, + { + "epoch": 7.88, + "learning_rate": 4.746408045977012e-05, + "loss": 1.0926, + "step": 7313 + }, + { + "epoch": 7.88, + "learning_rate": 4.745689655172414e-05, + "loss": 0.9497, + "step": 7314 + }, + { + "epoch": 7.88, + "learning_rate": 4.7449712643678165e-05, + "loss": 1.0778, + "step": 7315 + }, + { + "epoch": 7.88, + "learning_rate": 4.7442528735632186e-05, + "loss": 1.1739, + "step": 7316 + }, + { + "epoch": 7.88, + "learning_rate": 4.7435344827586206e-05, + "loss": 0.9623, + "step": 7317 + }, + { + "epoch": 7.89, + "learning_rate": 4.742816091954023e-05, + "loss": 1.0417, + "step": 7318 + }, + { + "epoch": 7.89, + "learning_rate": 4.742097701149425e-05, + "loss": 1.0814, + "step": 7319 + }, + { + "epoch": 7.89, + "learning_rate": 4.741379310344828e-05, + "loss": 1.0313, + "step": 7320 + }, + { + "epoch": 7.89, + "learning_rate": 4.74066091954023e-05, + "loss": 0.9606, + "step": 7321 + }, + { + "epoch": 7.89, + "learning_rate": 4.739942528735633e-05, + "loss": 0.9928, + "step": 7322 + }, + { + "epoch": 7.89, + "learning_rate": 4.739224137931035e-05, + "loss": 1.0856, + "step": 7323 + }, + { + "epoch": 7.89, + "learning_rate": 4.738505747126437e-05, + "loss": 1.0125, + "step": 7324 + }, + { + "epoch": 7.89, + "learning_rate": 4.7377873563218396e-05, + "loss": 1.0265, + "step": 7325 + }, + { + "epoch": 7.89, + "learning_rate": 4.7370689655172416e-05, + "loss": 0.9685, + "step": 7326 + }, + { + "epoch": 7.9, + "learning_rate": 4.736350574712644e-05, + "loss": 0.9203, + "step": 7327 + }, + { + "epoch": 7.9, + "learning_rate": 4.735632183908046e-05, + "loss": 0.9786, + "step": 7328 + }, + { + "epoch": 7.9, + "learning_rate": 4.734913793103449e-05, + "loss": 0.9671, + "step": 7329 + }, + { + "epoch": 7.9, + "learning_rate": 4.734195402298851e-05, + "loss": 0.9525, + "step": 7330 + }, + { + "epoch": 7.9, + "learning_rate": 4.733477011494253e-05, + "loss": 0.9606, + "step": 7331 + }, + { + "epoch": 7.9, + "learning_rate": 4.732758620689655e-05, + "loss": 0.9487, + "step": 7332 + }, + { + "epoch": 7.9, + "learning_rate": 4.732040229885057e-05, + "loss": 1.0757, + "step": 7333 + }, + { + "epoch": 7.9, + "learning_rate": 4.73132183908046e-05, + "loss": 1.007, + "step": 7334 + }, + { + "epoch": 7.9, + "learning_rate": 4.730603448275862e-05, + "loss": 1.0049, + "step": 7335 + }, + { + "epoch": 7.91, + "learning_rate": 4.7298850574712646e-05, + "loss": 0.9589, + "step": 7336 + }, + { + "epoch": 7.91, + "learning_rate": 4.7291666666666666e-05, + "loss": 0.9984, + "step": 7337 + }, + { + "epoch": 7.91, + "learning_rate": 4.7284482758620694e-05, + "loss": 1.0677, + "step": 7338 + }, + { + "epoch": 7.91, + "learning_rate": 4.7277298850574714e-05, + "loss": 0.9897, + "step": 7339 + }, + { + "epoch": 7.91, + "learning_rate": 4.7270114942528734e-05, + "loss": 0.8935, + "step": 7340 + }, + { + "epoch": 7.91, + "learning_rate": 4.726293103448276e-05, + "loss": 1.0717, + "step": 7341 + }, + { + "epoch": 7.91, + "learning_rate": 4.725574712643678e-05, + "loss": 0.9565, + "step": 7342 + }, + { + "epoch": 7.91, + "learning_rate": 4.724856321839081e-05, + "loss": 1.0243, + "step": 7343 + }, + { + "epoch": 7.91, + "learning_rate": 4.724137931034483e-05, + "loss": 0.9964, + "step": 7344 + }, + { + "epoch": 7.91, + "learning_rate": 4.7234195402298856e-05, + "loss": 1.0767, + "step": 7345 + }, + { + "epoch": 7.92, + "learning_rate": 4.7227011494252876e-05, + "loss": 0.9673, + "step": 7346 + }, + { + "epoch": 7.92, + "learning_rate": 4.72198275862069e-05, + "loss": 1.0543, + "step": 7347 + }, + { + "epoch": 7.92, + "learning_rate": 4.7212643678160924e-05, + "loss": 1.0453, + "step": 7348 + }, + { + "epoch": 7.92, + "learning_rate": 4.7205459770114944e-05, + "loss": 1.0195, + "step": 7349 + }, + { + "epoch": 7.92, + "learning_rate": 4.719827586206897e-05, + "loss": 1.0252, + "step": 7350 + }, + { + "epoch": 7.92, + "learning_rate": 4.719109195402299e-05, + "loss": 0.9975, + "step": 7351 + }, + { + "epoch": 7.92, + "learning_rate": 4.718390804597702e-05, + "loss": 1.112, + "step": 7352 + }, + { + "epoch": 7.92, + "learning_rate": 4.717672413793104e-05, + "loss": 0.884, + "step": 7353 + }, + { + "epoch": 7.92, + "learning_rate": 4.716954022988506e-05, + "loss": 0.9423, + "step": 7354 + }, + { + "epoch": 7.93, + "learning_rate": 4.7162356321839086e-05, + "loss": 1.0485, + "step": 7355 + }, + { + "epoch": 7.93, + "learning_rate": 4.715517241379311e-05, + "loss": 1.0248, + "step": 7356 + }, + { + "epoch": 7.93, + "learning_rate": 4.714798850574713e-05, + "loss": 1.0551, + "step": 7357 + }, + { + "epoch": 7.93, + "learning_rate": 4.714080459770115e-05, + "loss": 0.9358, + "step": 7358 + }, + { + "epoch": 7.93, + "learning_rate": 4.7133620689655175e-05, + "loss": 1.0154, + "step": 7359 + }, + { + "epoch": 7.93, + "learning_rate": 4.7126436781609195e-05, + "loss": 1.0133, + "step": 7360 + }, + { + "epoch": 7.93, + "learning_rate": 4.711925287356322e-05, + "loss": 0.9681, + "step": 7361 + }, + { + "epoch": 7.93, + "learning_rate": 4.711206896551724e-05, + "loss": 0.9573, + "step": 7362 + }, + { + "epoch": 7.93, + "learning_rate": 4.710488505747126e-05, + "loss": 0.9675, + "step": 7363 + }, + { + "epoch": 7.94, + "learning_rate": 4.709770114942529e-05, + "loss": 1.0185, + "step": 7364 + }, + { + "epoch": 7.94, + "learning_rate": 4.709051724137931e-05, + "loss": 0.9235, + "step": 7365 + }, + { + "epoch": 7.94, + "learning_rate": 4.708333333333334e-05, + "loss": 1.0778, + "step": 7366 + }, + { + "epoch": 7.94, + "learning_rate": 4.707614942528736e-05, + "loss": 0.9064, + "step": 7367 + }, + { + "epoch": 7.94, + "learning_rate": 4.7068965517241385e-05, + "loss": 0.9902, + "step": 7368 + }, + { + "epoch": 7.94, + "learning_rate": 4.7061781609195405e-05, + "loss": 1.0058, + "step": 7369 + }, + { + "epoch": 7.94, + "learning_rate": 4.7054597701149425e-05, + "loss": 0.993, + "step": 7370 + }, + { + "epoch": 7.94, + "learning_rate": 4.704741379310345e-05, + "loss": 1.0834, + "step": 7371 + }, + { + "epoch": 7.94, + "learning_rate": 4.704022988505747e-05, + "loss": 0.9844, + "step": 7372 + }, + { + "epoch": 7.95, + "learning_rate": 4.70330459770115e-05, + "loss": 1.041, + "step": 7373 + }, + { + "epoch": 7.95, + "learning_rate": 4.702586206896552e-05, + "loss": 1.0077, + "step": 7374 + }, + { + "epoch": 7.95, + "learning_rate": 4.701867816091954e-05, + "loss": 1.0618, + "step": 7375 + }, + { + "epoch": 7.95, + "learning_rate": 4.701149425287357e-05, + "loss": 1.2406, + "step": 7376 + }, + { + "epoch": 7.95, + "learning_rate": 4.700431034482759e-05, + "loss": 1.0746, + "step": 7377 + }, + { + "epoch": 7.95, + "learning_rate": 4.6997126436781615e-05, + "loss": 0.9933, + "step": 7378 + }, + { + "epoch": 7.95, + "learning_rate": 4.6989942528735635e-05, + "loss": 0.9793, + "step": 7379 + }, + { + "epoch": 7.95, + "learning_rate": 4.698275862068966e-05, + "loss": 0.9375, + "step": 7380 + }, + { + "epoch": 7.95, + "learning_rate": 4.697557471264368e-05, + "loss": 1.0005, + "step": 7381 + }, + { + "epoch": 7.95, + "learning_rate": 4.69683908045977e-05, + "loss": 1.0652, + "step": 7382 + }, + { + "epoch": 7.96, + "learning_rate": 4.696120689655172e-05, + "loss": 0.8993, + "step": 7383 + }, + { + "epoch": 7.96, + "learning_rate": 4.695402298850575e-05, + "loss": 1.0526, + "step": 7384 + }, + { + "epoch": 7.96, + "learning_rate": 4.694683908045977e-05, + "loss": 1.1018, + "step": 7385 + }, + { + "epoch": 7.96, + "learning_rate": 4.693965517241379e-05, + "loss": 0.9594, + "step": 7386 + }, + { + "epoch": 7.96, + "learning_rate": 4.693247126436782e-05, + "loss": 1.0314, + "step": 7387 + }, + { + "epoch": 7.96, + "learning_rate": 4.692528735632184e-05, + "loss": 1.1035, + "step": 7388 + }, + { + "epoch": 7.96, + "learning_rate": 4.6918103448275865e-05, + "loss": 0.9792, + "step": 7389 + }, + { + "epoch": 7.96, + "learning_rate": 4.6910919540229886e-05, + "loss": 0.9652, + "step": 7390 + }, + { + "epoch": 7.96, + "learning_rate": 4.6903735632183906e-05, + "loss": 1.0579, + "step": 7391 + }, + { + "epoch": 7.97, + "learning_rate": 4.689655172413793e-05, + "loss": 1.0456, + "step": 7392 + }, + { + "epoch": 7.97, + "learning_rate": 4.6889367816091954e-05, + "loss": 1.0434, + "step": 7393 + }, + { + "epoch": 7.97, + "learning_rate": 4.688218390804598e-05, + "loss": 0.9964, + "step": 7394 + }, + { + "epoch": 7.97, + "learning_rate": 4.6875e-05, + "loss": 0.9771, + "step": 7395 + }, + { + "epoch": 7.97, + "learning_rate": 4.686781609195403e-05, + "loss": 0.9369, + "step": 7396 + }, + { + "epoch": 7.97, + "learning_rate": 4.686063218390805e-05, + "loss": 0.8845, + "step": 7397 + }, + { + "epoch": 7.97, + "learning_rate": 4.685344827586207e-05, + "loss": 0.9771, + "step": 7398 + }, + { + "epoch": 7.97, + "learning_rate": 4.6846264367816096e-05, + "loss": 1.052, + "step": 7399 + }, + { + "epoch": 7.97, + "learning_rate": 4.6839080459770116e-05, + "loss": 0.9952, + "step": 7400 + }, + { + "epoch": 7.98, + "learning_rate": 4.683189655172414e-05, + "loss": 1.1322, + "step": 7401 + }, + { + "epoch": 7.98, + "learning_rate": 4.6824712643678164e-05, + "loss": 0.9935, + "step": 7402 + }, + { + "epoch": 7.98, + "learning_rate": 4.681752873563219e-05, + "loss": 1.0076, + "step": 7403 + }, + { + "epoch": 7.98, + "learning_rate": 4.681034482758621e-05, + "loss": 1.0117, + "step": 7404 + }, + { + "epoch": 7.98, + "learning_rate": 4.680316091954023e-05, + "loss": 0.9865, + "step": 7405 + }, + { + "epoch": 7.98, + "learning_rate": 4.679597701149426e-05, + "loss": 1.0887, + "step": 7406 + }, + { + "epoch": 7.98, + "learning_rate": 4.678879310344828e-05, + "loss": 1.1389, + "step": 7407 + }, + { + "epoch": 7.98, + "learning_rate": 4.67816091954023e-05, + "loss": 0.9779, + "step": 7408 + }, + { + "epoch": 7.98, + "learning_rate": 4.677442528735632e-05, + "loss": 1.0786, + "step": 7409 + }, + { + "epoch": 7.98, + "learning_rate": 4.6767241379310346e-05, + "loss": 1.0842, + "step": 7410 + }, + { + "epoch": 7.99, + "learning_rate": 4.676005747126437e-05, + "loss": 1.0247, + "step": 7411 + }, + { + "epoch": 7.99, + "learning_rate": 4.6752873563218394e-05, + "loss": 1.0463, + "step": 7412 + }, + { + "epoch": 7.99, + "learning_rate": 4.6745689655172414e-05, + "loss": 1.0909, + "step": 7413 + }, + { + "epoch": 7.99, + "learning_rate": 4.6738505747126435e-05, + "loss": 0.9393, + "step": 7414 + }, + { + "epoch": 7.99, + "learning_rate": 4.673132183908046e-05, + "loss": 1.027, + "step": 7415 + }, + { + "epoch": 7.99, + "learning_rate": 4.672413793103448e-05, + "loss": 0.9964, + "step": 7416 + }, + { + "epoch": 7.99, + "learning_rate": 4.671695402298851e-05, + "loss": 0.9947, + "step": 7417 + }, + { + "epoch": 7.99, + "learning_rate": 4.670977011494253e-05, + "loss": 1.0449, + "step": 7418 + }, + { + "epoch": 7.99, + "learning_rate": 4.6702586206896556e-05, + "loss": 1.0294, + "step": 7419 + }, + { + "epoch": 8.0, + "learning_rate": 4.669540229885058e-05, + "loss": 0.9672, + "step": 7420 + }, + { + "epoch": 8.0, + "learning_rate": 4.66882183908046e-05, + "loss": 1.0068, + "step": 7421 + }, + { + "epoch": 8.0, + "learning_rate": 4.6681034482758624e-05, + "loss": 1.0203, + "step": 7422 + }, + { + "epoch": 8.0, + "learning_rate": 4.6673850574712645e-05, + "loss": 1.0558, + "step": 7423 + }, + { + "epoch": 8.0, + "learning_rate": 4.666666666666667e-05, + "loss": 1.0974, + "step": 7424 + }, + { + "epoch": 8.0, + "learning_rate": 4.665948275862069e-05, + "loss": 0.9962, + "step": 7425 + }, + { + "epoch": 8.0, + "learning_rate": 4.665229885057472e-05, + "loss": 0.9582, + "step": 7426 + }, + { + "epoch": 8.0, + "learning_rate": 4.664511494252874e-05, + "loss": 1.0929, + "step": 7427 + }, + { + "epoch": 8.0, + "learning_rate": 4.663793103448276e-05, + "loss": 0.9682, + "step": 7428 + }, + { + "epoch": 8.01, + "learning_rate": 4.663074712643679e-05, + "loss": 1.0076, + "step": 7429 + }, + { + "epoch": 8.01, + "learning_rate": 4.662356321839081e-05, + "loss": 1.072, + "step": 7430 + }, + { + "epoch": 8.01, + "learning_rate": 4.6616379310344834e-05, + "loss": 0.9885, + "step": 7431 + }, + { + "epoch": 8.01, + "learning_rate": 4.6609195402298855e-05, + "loss": 1.0686, + "step": 7432 + }, + { + "epoch": 8.01, + "learning_rate": 4.660201149425288e-05, + "loss": 1.0034, + "step": 7433 + }, + { + "epoch": 8.01, + "learning_rate": 4.6594827586206895e-05, + "loss": 1.0511, + "step": 7434 + }, + { + "epoch": 8.01, + "learning_rate": 4.658764367816092e-05, + "loss": 0.9646, + "step": 7435 + }, + { + "epoch": 8.01, + "learning_rate": 4.658045977011494e-05, + "loss": 0.9378, + "step": 7436 + }, + { + "epoch": 8.01, + "learning_rate": 4.657327586206896e-05, + "loss": 1.0604, + "step": 7437 + }, + { + "epoch": 8.02, + "learning_rate": 4.656609195402299e-05, + "loss": 1.0424, + "step": 7438 + }, + { + "epoch": 8.02, + "learning_rate": 4.655890804597701e-05, + "loss": 0.9497, + "step": 7439 + }, + { + "epoch": 8.02, + "learning_rate": 4.655172413793104e-05, + "loss": 0.8656, + "step": 7440 + }, + { + "epoch": 8.02, + "learning_rate": 4.654454022988506e-05, + "loss": 0.9348, + "step": 7441 + }, + { + "epoch": 8.02, + "learning_rate": 4.6537356321839085e-05, + "loss": 0.9574, + "step": 7442 + }, + { + "epoch": 8.02, + "learning_rate": 4.6530172413793105e-05, + "loss": 0.9993, + "step": 7443 + }, + { + "epoch": 8.02, + "learning_rate": 4.6522988505747125e-05, + "loss": 0.9898, + "step": 7444 + }, + { + "epoch": 8.02, + "learning_rate": 4.651580459770115e-05, + "loss": 0.9878, + "step": 7445 + }, + { + "epoch": 8.02, + "learning_rate": 4.650862068965517e-05, + "loss": 0.9864, + "step": 7446 + }, + { + "epoch": 8.02, + "learning_rate": 4.65014367816092e-05, + "loss": 1.0721, + "step": 7447 + }, + { + "epoch": 8.03, + "learning_rate": 4.649425287356322e-05, + "loss": 0.9667, + "step": 7448 + }, + { + "epoch": 8.03, + "learning_rate": 4.648706896551725e-05, + "loss": 0.8704, + "step": 7449 + }, + { + "epoch": 8.03, + "learning_rate": 4.647988505747127e-05, + "loss": 0.9959, + "step": 7450 + }, + { + "epoch": 8.03, + "learning_rate": 4.647270114942529e-05, + "loss": 0.953, + "step": 7451 + }, + { + "epoch": 8.03, + "learning_rate": 4.6465517241379315e-05, + "loss": 0.7955, + "step": 7452 + }, + { + "epoch": 8.03, + "learning_rate": 4.6458333333333335e-05, + "loss": 0.8674, + "step": 7453 + }, + { + "epoch": 8.03, + "learning_rate": 4.645114942528736e-05, + "loss": 0.9946, + "step": 7454 + }, + { + "epoch": 8.03, + "learning_rate": 4.644396551724138e-05, + "loss": 0.887, + "step": 7455 + }, + { + "epoch": 8.03, + "learning_rate": 4.643678160919541e-05, + "loss": 0.9718, + "step": 7456 + }, + { + "epoch": 8.04, + "learning_rate": 4.642959770114943e-05, + "loss": 0.9228, + "step": 7457 + }, + { + "epoch": 8.04, + "learning_rate": 4.642241379310345e-05, + "loss": 0.9474, + "step": 7458 + }, + { + "epoch": 8.04, + "learning_rate": 4.641522988505747e-05, + "loss": 0.9579, + "step": 7459 + }, + { + "epoch": 8.04, + "learning_rate": 4.640804597701149e-05, + "loss": 1.0679, + "step": 7460 + }, + { + "epoch": 8.04, + "learning_rate": 4.640086206896552e-05, + "loss": 0.7979, + "step": 7461 + }, + { + "epoch": 8.04, + "learning_rate": 4.639367816091954e-05, + "loss": 0.9111, + "step": 7462 + }, + { + "epoch": 8.04, + "learning_rate": 4.6386494252873566e-05, + "loss": 1.0788, + "step": 7463 + }, + { + "epoch": 8.04, + "learning_rate": 4.6379310344827586e-05, + "loss": 1.0463, + "step": 7464 + }, + { + "epoch": 8.04, + "learning_rate": 4.637212643678161e-05, + "loss": 0.894, + "step": 7465 + }, + { + "epoch": 8.05, + "learning_rate": 4.6364942528735634e-05, + "loss": 1.0801, + "step": 7466 + }, + { + "epoch": 8.05, + "learning_rate": 4.6357758620689654e-05, + "loss": 0.9113, + "step": 7467 + }, + { + "epoch": 8.05, + "learning_rate": 4.635057471264368e-05, + "loss": 1.0417, + "step": 7468 + }, + { + "epoch": 8.05, + "learning_rate": 4.63433908045977e-05, + "loss": 1.087, + "step": 7469 + }, + { + "epoch": 8.05, + "learning_rate": 4.633620689655173e-05, + "loss": 1.1112, + "step": 7470 + }, + { + "epoch": 8.05, + "learning_rate": 4.632902298850575e-05, + "loss": 1.0076, + "step": 7471 + }, + { + "epoch": 8.05, + "learning_rate": 4.632183908045977e-05, + "loss": 1.0591, + "step": 7472 + }, + { + "epoch": 8.05, + "learning_rate": 4.6314655172413796e-05, + "loss": 0.9369, + "step": 7473 + }, + { + "epoch": 8.05, + "learning_rate": 4.6307471264367816e-05, + "loss": 0.9081, + "step": 7474 + }, + { + "epoch": 8.05, + "learning_rate": 4.6300287356321844e-05, + "loss": 0.9704, + "step": 7475 + }, + { + "epoch": 8.06, + "learning_rate": 4.6293103448275864e-05, + "loss": 1.0531, + "step": 7476 + }, + { + "epoch": 8.06, + "learning_rate": 4.628591954022989e-05, + "loss": 0.9415, + "step": 7477 + }, + { + "epoch": 8.06, + "learning_rate": 4.627873563218391e-05, + "loss": 0.9468, + "step": 7478 + }, + { + "epoch": 8.06, + "learning_rate": 4.627155172413793e-05, + "loss": 0.9751, + "step": 7479 + }, + { + "epoch": 8.06, + "learning_rate": 4.626436781609196e-05, + "loss": 1.0684, + "step": 7480 + }, + { + "epoch": 8.06, + "learning_rate": 4.625718390804598e-05, + "loss": 0.9572, + "step": 7481 + }, + { + "epoch": 8.06, + "learning_rate": 4.6250000000000006e-05, + "loss": 0.8977, + "step": 7482 + }, + { + "epoch": 8.06, + "learning_rate": 4.6242816091954026e-05, + "loss": 0.7713, + "step": 7483 + }, + { + "epoch": 8.06, + "learning_rate": 4.6235632183908054e-05, + "loss": 1.0573, + "step": 7484 + }, + { + "epoch": 8.07, + "learning_rate": 4.622844827586207e-05, + "loss": 1.0946, + "step": 7485 + }, + { + "epoch": 8.07, + "learning_rate": 4.6221264367816094e-05, + "loss": 0.941, + "step": 7486 + }, + { + "epoch": 8.07, + "learning_rate": 4.6214080459770114e-05, + "loss": 0.9579, + "step": 7487 + }, + { + "epoch": 8.07, + "learning_rate": 4.6206896551724135e-05, + "loss": 1.1289, + "step": 7488 + }, + { + "epoch": 8.07, + "learning_rate": 4.619971264367816e-05, + "loss": 0.9853, + "step": 7489 + }, + { + "epoch": 8.07, + "learning_rate": 4.619252873563218e-05, + "loss": 1.027, + "step": 7490 + }, + { + "epoch": 8.07, + "learning_rate": 4.618534482758621e-05, + "loss": 0.9734, + "step": 7491 + }, + { + "epoch": 8.07, + "learning_rate": 4.617816091954023e-05, + "loss": 1.0523, + "step": 7492 + }, + { + "epoch": 8.07, + "learning_rate": 4.617097701149426e-05, + "loss": 0.9659, + "step": 7493 + }, + { + "epoch": 8.08, + "learning_rate": 4.616379310344828e-05, + "loss": 1.0226, + "step": 7494 + }, + { + "epoch": 8.08, + "learning_rate": 4.61566091954023e-05, + "loss": 0.9844, + "step": 7495 + }, + { + "epoch": 8.08, + "learning_rate": 4.6149425287356324e-05, + "loss": 0.9254, + "step": 7496 + }, + { + "epoch": 8.08, + "learning_rate": 4.6142241379310345e-05, + "loss": 0.9129, + "step": 7497 + }, + { + "epoch": 8.08, + "learning_rate": 4.613505747126437e-05, + "loss": 0.9898, + "step": 7498 + }, + { + "epoch": 8.08, + "learning_rate": 4.612787356321839e-05, + "loss": 0.9694, + "step": 7499 + }, + { + "epoch": 8.08, + "learning_rate": 4.612068965517242e-05, + "loss": 1.0461, + "step": 7500 + }, + { + "epoch": 8.08, + "eval_loss": 1.1138375997543335, + "eval_runtime": 174.8351, + "eval_samples_per_second": 127.377, + "eval_steps_per_second": 0.663, + "step": 7500 + }, + { + "epoch": 8.08, + "learning_rate": 4.611350574712644e-05, + "loss": 0.9547, + "step": 7501 + }, + { + "epoch": 8.08, + "learning_rate": 4.610632183908046e-05, + "loss": 1.0331, + "step": 7502 + }, + { + "epoch": 8.09, + "learning_rate": 4.609913793103449e-05, + "loss": 1.0057, + "step": 7503 + }, + { + "epoch": 8.09, + "learning_rate": 4.609195402298851e-05, + "loss": 1.0079, + "step": 7504 + }, + { + "epoch": 8.09, + "learning_rate": 4.6084770114942534e-05, + "loss": 0.8894, + "step": 7505 + }, + { + "epoch": 8.09, + "learning_rate": 4.6077586206896555e-05, + "loss": 0.9457, + "step": 7506 + }, + { + "epoch": 8.09, + "learning_rate": 4.607040229885058e-05, + "loss": 0.9433, + "step": 7507 + }, + { + "epoch": 8.09, + "learning_rate": 4.60632183908046e-05, + "loss": 0.993, + "step": 7508 + }, + { + "epoch": 8.09, + "learning_rate": 4.605603448275862e-05, + "loss": 0.9948, + "step": 7509 + }, + { + "epoch": 8.09, + "learning_rate": 4.604885057471265e-05, + "loss": 0.9573, + "step": 7510 + }, + { + "epoch": 8.09, + "learning_rate": 4.604166666666666e-05, + "loss": 0.9964, + "step": 7511 + }, + { + "epoch": 8.09, + "learning_rate": 4.603448275862069e-05, + "loss": 0.9623, + "step": 7512 + }, + { + "epoch": 8.1, + "learning_rate": 4.602729885057471e-05, + "loss": 1.0218, + "step": 7513 + }, + { + "epoch": 8.1, + "learning_rate": 4.602011494252874e-05, + "loss": 0.9848, + "step": 7514 + }, + { + "epoch": 8.1, + "learning_rate": 4.601293103448276e-05, + "loss": 1.0189, + "step": 7515 + }, + { + "epoch": 8.1, + "learning_rate": 4.6005747126436785e-05, + "loss": 0.9384, + "step": 7516 + }, + { + "epoch": 8.1, + "learning_rate": 4.5998563218390805e-05, + "loss": 0.9654, + "step": 7517 + }, + { + "epoch": 8.1, + "learning_rate": 4.5991379310344826e-05, + "loss": 1.0207, + "step": 7518 + }, + { + "epoch": 8.1, + "learning_rate": 4.598419540229885e-05, + "loss": 0.9007, + "step": 7519 + }, + { + "epoch": 8.1, + "learning_rate": 4.597701149425287e-05, + "loss": 1.052, + "step": 7520 + }, + { + "epoch": 8.1, + "learning_rate": 4.59698275862069e-05, + "loss": 0.9498, + "step": 7521 + }, + { + "epoch": 8.11, + "learning_rate": 4.596264367816092e-05, + "loss": 0.9161, + "step": 7522 + }, + { + "epoch": 8.11, + "learning_rate": 4.595545977011495e-05, + "loss": 1.0213, + "step": 7523 + }, + { + "epoch": 8.11, + "learning_rate": 4.594827586206897e-05, + "loss": 1.0392, + "step": 7524 + }, + { + "epoch": 8.11, + "learning_rate": 4.594109195402299e-05, + "loss": 0.9998, + "step": 7525 + }, + { + "epoch": 8.11, + "learning_rate": 4.5933908045977015e-05, + "loss": 0.9283, + "step": 7526 + }, + { + "epoch": 8.11, + "learning_rate": 4.5926724137931036e-05, + "loss": 0.995, + "step": 7527 + }, + { + "epoch": 8.11, + "learning_rate": 4.591954022988506e-05, + "loss": 0.9475, + "step": 7528 + }, + { + "epoch": 8.11, + "learning_rate": 4.591235632183908e-05, + "loss": 0.8755, + "step": 7529 + }, + { + "epoch": 8.11, + "learning_rate": 4.590517241379311e-05, + "loss": 1.0187, + "step": 7530 + }, + { + "epoch": 8.12, + "learning_rate": 4.589798850574713e-05, + "loss": 0.9136, + "step": 7531 + }, + { + "epoch": 8.12, + "learning_rate": 4.589080459770115e-05, + "loss": 0.9433, + "step": 7532 + }, + { + "epoch": 8.12, + "learning_rate": 4.588362068965518e-05, + "loss": 1.0472, + "step": 7533 + }, + { + "epoch": 8.12, + "learning_rate": 4.58764367816092e-05, + "loss": 0.9143, + "step": 7534 + }, + { + "epoch": 8.12, + "learning_rate": 4.5869252873563225e-05, + "loss": 1.0155, + "step": 7535 + }, + { + "epoch": 8.12, + "learning_rate": 4.586206896551724e-05, + "loss": 0.9028, + "step": 7536 + }, + { + "epoch": 8.12, + "learning_rate": 4.5854885057471266e-05, + "loss": 0.9717, + "step": 7537 + }, + { + "epoch": 8.12, + "learning_rate": 4.5847701149425286e-05, + "loss": 0.9927, + "step": 7538 + }, + { + "epoch": 8.12, + "learning_rate": 4.5840517241379314e-05, + "loss": 0.9666, + "step": 7539 + }, + { + "epoch": 8.12, + "learning_rate": 4.5833333333333334e-05, + "loss": 1.0666, + "step": 7540 + }, + { + "epoch": 8.13, + "learning_rate": 4.5826149425287354e-05, + "loss": 1.059, + "step": 7541 + }, + { + "epoch": 8.13, + "learning_rate": 4.581896551724138e-05, + "loss": 0.939, + "step": 7542 + }, + { + "epoch": 8.13, + "learning_rate": 4.58117816091954e-05, + "loss": 0.9218, + "step": 7543 + }, + { + "epoch": 8.13, + "learning_rate": 4.580459770114943e-05, + "loss": 1.0226, + "step": 7544 + }, + { + "epoch": 8.13, + "learning_rate": 4.579741379310345e-05, + "loss": 0.985, + "step": 7545 + }, + { + "epoch": 8.13, + "learning_rate": 4.5790229885057476e-05, + "loss": 1.0277, + "step": 7546 + }, + { + "epoch": 8.13, + "learning_rate": 4.5783045977011496e-05, + "loss": 0.9803, + "step": 7547 + }, + { + "epoch": 8.13, + "learning_rate": 4.577586206896552e-05, + "loss": 0.9288, + "step": 7548 + }, + { + "epoch": 8.13, + "learning_rate": 4.5768678160919544e-05, + "loss": 1.0004, + "step": 7549 + }, + { + "epoch": 8.14, + "learning_rate": 4.5761494252873564e-05, + "loss": 1.0234, + "step": 7550 + }, + { + "epoch": 8.14, + "learning_rate": 4.575431034482759e-05, + "loss": 1.0168, + "step": 7551 + }, + { + "epoch": 8.14, + "learning_rate": 4.574712643678161e-05, + "loss": 0.972, + "step": 7552 + }, + { + "epoch": 8.14, + "learning_rate": 4.573994252873564e-05, + "loss": 0.8853, + "step": 7553 + }, + { + "epoch": 8.14, + "learning_rate": 4.573275862068966e-05, + "loss": 0.9396, + "step": 7554 + }, + { + "epoch": 8.14, + "learning_rate": 4.572557471264368e-05, + "loss": 0.993, + "step": 7555 + }, + { + "epoch": 8.14, + "learning_rate": 4.5718390804597706e-05, + "loss": 0.9985, + "step": 7556 + }, + { + "epoch": 8.14, + "learning_rate": 4.571120689655173e-05, + "loss": 0.9428, + "step": 7557 + }, + { + "epoch": 8.14, + "learning_rate": 4.5704022988505754e-05, + "loss": 0.9071, + "step": 7558 + }, + { + "epoch": 8.15, + "learning_rate": 4.5696839080459774e-05, + "loss": 0.957, + "step": 7559 + }, + { + "epoch": 8.15, + "learning_rate": 4.5689655172413794e-05, + "loss": 0.8961, + "step": 7560 + }, + { + "epoch": 8.15, + "learning_rate": 4.568247126436782e-05, + "loss": 1.0842, + "step": 7561 + }, + { + "epoch": 8.15, + "learning_rate": 4.567528735632184e-05, + "loss": 1.1176, + "step": 7562 + }, + { + "epoch": 8.15, + "learning_rate": 4.566810344827586e-05, + "loss": 1.0029, + "step": 7563 + }, + { + "epoch": 8.15, + "learning_rate": 4.566091954022988e-05, + "loss": 1.0697, + "step": 7564 + }, + { + "epoch": 8.15, + "learning_rate": 4.565373563218391e-05, + "loss": 1.0369, + "step": 7565 + }, + { + "epoch": 8.15, + "learning_rate": 4.564655172413793e-05, + "loss": 1.0381, + "step": 7566 + }, + { + "epoch": 8.15, + "learning_rate": 4.563936781609196e-05, + "loss": 1.0463, + "step": 7567 + }, + { + "epoch": 8.16, + "learning_rate": 4.563218390804598e-05, + "loss": 0.9479, + "step": 7568 + }, + { + "epoch": 8.16, + "learning_rate": 4.5625e-05, + "loss": 0.9294, + "step": 7569 + }, + { + "epoch": 8.16, + "learning_rate": 4.5617816091954025e-05, + "loss": 1.1005, + "step": 7570 + }, + { + "epoch": 8.16, + "learning_rate": 4.5610632183908045e-05, + "loss": 1.0324, + "step": 7571 + }, + { + "epoch": 8.16, + "learning_rate": 4.560344827586207e-05, + "loss": 0.9918, + "step": 7572 + }, + { + "epoch": 8.16, + "learning_rate": 4.559626436781609e-05, + "loss": 0.9347, + "step": 7573 + }, + { + "epoch": 8.16, + "learning_rate": 4.558908045977012e-05, + "loss": 0.999, + "step": 7574 + }, + { + "epoch": 8.16, + "learning_rate": 4.558189655172414e-05, + "loss": 1.1092, + "step": 7575 + }, + { + "epoch": 8.16, + "learning_rate": 4.557471264367816e-05, + "loss": 0.8642, + "step": 7576 + }, + { + "epoch": 8.16, + "learning_rate": 4.556752873563219e-05, + "loss": 1.1086, + "step": 7577 + }, + { + "epoch": 8.17, + "learning_rate": 4.556034482758621e-05, + "loss": 1.0199, + "step": 7578 + }, + { + "epoch": 8.17, + "learning_rate": 4.5553160919540235e-05, + "loss": 1.0746, + "step": 7579 + }, + { + "epoch": 8.17, + "learning_rate": 4.5545977011494255e-05, + "loss": 1.019, + "step": 7580 + }, + { + "epoch": 8.17, + "learning_rate": 4.553879310344828e-05, + "loss": 0.9561, + "step": 7581 + }, + { + "epoch": 8.17, + "learning_rate": 4.55316091954023e-05, + "loss": 0.979, + "step": 7582 + }, + { + "epoch": 8.17, + "learning_rate": 4.552442528735632e-05, + "loss": 0.973, + "step": 7583 + }, + { + "epoch": 8.17, + "learning_rate": 4.551724137931035e-05, + "loss": 0.9804, + "step": 7584 + }, + { + "epoch": 8.17, + "learning_rate": 4.551005747126437e-05, + "loss": 1.0095, + "step": 7585 + }, + { + "epoch": 8.17, + "learning_rate": 4.55028735632184e-05, + "loss": 0.8732, + "step": 7586 + }, + { + "epoch": 8.18, + "learning_rate": 4.549568965517241e-05, + "loss": 0.9874, + "step": 7587 + }, + { + "epoch": 8.18, + "learning_rate": 4.548850574712644e-05, + "loss": 0.981, + "step": 7588 + }, + { + "epoch": 8.18, + "learning_rate": 4.548132183908046e-05, + "loss": 0.9069, + "step": 7589 + }, + { + "epoch": 8.18, + "learning_rate": 4.5474137931034485e-05, + "loss": 0.9647, + "step": 7590 + }, + { + "epoch": 8.18, + "learning_rate": 4.5466954022988506e-05, + "loss": 0.9075, + "step": 7591 + }, + { + "epoch": 8.18, + "learning_rate": 4.5459770114942526e-05, + "loss": 0.9253, + "step": 7592 + }, + { + "epoch": 8.18, + "learning_rate": 4.545258620689655e-05, + "loss": 0.993, + "step": 7593 + }, + { + "epoch": 8.18, + "learning_rate": 4.5445402298850573e-05, + "loss": 0.9988, + "step": 7594 + }, + { + "epoch": 8.18, + "learning_rate": 4.54382183908046e-05, + "loss": 0.902, + "step": 7595 + }, + { + "epoch": 8.19, + "learning_rate": 4.543103448275862e-05, + "loss": 0.9502, + "step": 7596 + }, + { + "epoch": 8.19, + "learning_rate": 4.542385057471265e-05, + "loss": 0.9616, + "step": 7597 + }, + { + "epoch": 8.19, + "learning_rate": 4.541666666666667e-05, + "loss": 1.0319, + "step": 7598 + }, + { + "epoch": 8.19, + "learning_rate": 4.540948275862069e-05, + "loss": 0.9684, + "step": 7599 + }, + { + "epoch": 8.19, + "learning_rate": 4.5402298850574716e-05, + "loss": 1.0846, + "step": 7600 + }, + { + "epoch": 8.19, + "learning_rate": 4.5395114942528736e-05, + "loss": 0.865, + "step": 7601 + }, + { + "epoch": 8.19, + "learning_rate": 4.538793103448276e-05, + "loss": 1.0544, + "step": 7602 + }, + { + "epoch": 8.19, + "learning_rate": 4.5380747126436783e-05, + "loss": 0.8431, + "step": 7603 + }, + { + "epoch": 8.19, + "learning_rate": 4.537356321839081e-05, + "loss": 0.9283, + "step": 7604 + }, + { + "epoch": 8.2, + "learning_rate": 4.536637931034483e-05, + "loss": 0.8685, + "step": 7605 + }, + { + "epoch": 8.2, + "learning_rate": 4.535919540229885e-05, + "loss": 1.0887, + "step": 7606 + }, + { + "epoch": 8.2, + "learning_rate": 4.535201149425288e-05, + "loss": 1.0476, + "step": 7607 + }, + { + "epoch": 8.2, + "learning_rate": 4.53448275862069e-05, + "loss": 0.9858, + "step": 7608 + }, + { + "epoch": 8.2, + "learning_rate": 4.5337643678160926e-05, + "loss": 0.9459, + "step": 7609 + }, + { + "epoch": 8.2, + "learning_rate": 4.5330459770114946e-05, + "loss": 0.9499, + "step": 7610 + }, + { + "epoch": 8.2, + "learning_rate": 4.532327586206897e-05, + "loss": 1.0527, + "step": 7611 + }, + { + "epoch": 8.2, + "learning_rate": 4.5316091954022993e-05, + "loss": 1.0637, + "step": 7612 + }, + { + "epoch": 8.2, + "learning_rate": 4.5308908045977014e-05, + "loss": 1.0346, + "step": 7613 + }, + { + "epoch": 8.2, + "learning_rate": 4.5301724137931034e-05, + "loss": 0.9632, + "step": 7614 + }, + { + "epoch": 8.21, + "learning_rate": 4.5294540229885054e-05, + "loss": 0.948, + "step": 7615 + }, + { + "epoch": 8.21, + "learning_rate": 4.528735632183908e-05, + "loss": 0.9069, + "step": 7616 + }, + { + "epoch": 8.21, + "learning_rate": 4.52801724137931e-05, + "loss": 1.0628, + "step": 7617 + }, + { + "epoch": 8.21, + "learning_rate": 4.527298850574713e-05, + "loss": 0.9768, + "step": 7618 + }, + { + "epoch": 8.21, + "learning_rate": 4.526580459770115e-05, + "loss": 0.9601, + "step": 7619 + }, + { + "epoch": 8.21, + "learning_rate": 4.5258620689655176e-05, + "loss": 1.0222, + "step": 7620 + }, + { + "epoch": 8.21, + "learning_rate": 4.52514367816092e-05, + "loss": 1.085, + "step": 7621 + }, + { + "epoch": 8.21, + "learning_rate": 4.524425287356322e-05, + "loss": 1.1073, + "step": 7622 + }, + { + "epoch": 8.21, + "learning_rate": 4.5237068965517244e-05, + "loss": 0.9762, + "step": 7623 + }, + { + "epoch": 8.22, + "learning_rate": 4.5229885057471264e-05, + "loss": 1.0372, + "step": 7624 + }, + { + "epoch": 8.22, + "learning_rate": 4.522270114942529e-05, + "loss": 1.0758, + "step": 7625 + }, + { + "epoch": 8.22, + "learning_rate": 4.521551724137931e-05, + "loss": 1.0439, + "step": 7626 + }, + { + "epoch": 8.22, + "learning_rate": 4.520833333333334e-05, + "loss": 1.0258, + "step": 7627 + }, + { + "epoch": 8.22, + "learning_rate": 4.520114942528736e-05, + "loss": 0.9902, + "step": 7628 + }, + { + "epoch": 8.22, + "learning_rate": 4.519396551724138e-05, + "loss": 1.0974, + "step": 7629 + }, + { + "epoch": 8.22, + "learning_rate": 4.518678160919541e-05, + "loss": 0.9416, + "step": 7630 + }, + { + "epoch": 8.22, + "learning_rate": 4.517959770114943e-05, + "loss": 0.9749, + "step": 7631 + }, + { + "epoch": 8.22, + "learning_rate": 4.5172413793103454e-05, + "loss": 1.0134, + "step": 7632 + }, + { + "epoch": 8.23, + "learning_rate": 4.5165229885057474e-05, + "loss": 0.9762, + "step": 7633 + }, + { + "epoch": 8.23, + "learning_rate": 4.51580459770115e-05, + "loss": 0.9105, + "step": 7634 + }, + { + "epoch": 8.23, + "learning_rate": 4.515086206896552e-05, + "loss": 1.0839, + "step": 7635 + }, + { + "epoch": 8.23, + "learning_rate": 4.514367816091954e-05, + "loss": 0.9779, + "step": 7636 + }, + { + "epoch": 8.23, + "learning_rate": 4.513649425287357e-05, + "loss": 1.0778, + "step": 7637 + }, + { + "epoch": 8.23, + "learning_rate": 4.512931034482759e-05, + "loss": 1.0757, + "step": 7638 + }, + { + "epoch": 8.23, + "learning_rate": 4.512212643678161e-05, + "loss": 0.9273, + "step": 7639 + }, + { + "epoch": 8.23, + "learning_rate": 4.511494252873563e-05, + "loss": 0.9661, + "step": 7640 + }, + { + "epoch": 8.23, + "learning_rate": 4.510775862068966e-05, + "loss": 0.8998, + "step": 7641 + }, + { + "epoch": 8.23, + "learning_rate": 4.510057471264368e-05, + "loss": 0.9764, + "step": 7642 + }, + { + "epoch": 8.24, + "learning_rate": 4.5093390804597705e-05, + "loss": 1.058, + "step": 7643 + }, + { + "epoch": 8.24, + "learning_rate": 4.5086206896551725e-05, + "loss": 0.9348, + "step": 7644 + }, + { + "epoch": 8.24, + "learning_rate": 4.5079022988505745e-05, + "loss": 1.0302, + "step": 7645 + }, + { + "epoch": 8.24, + "learning_rate": 4.507183908045977e-05, + "loss": 1.0052, + "step": 7646 + }, + { + "epoch": 8.24, + "learning_rate": 4.506465517241379e-05, + "loss": 0.9134, + "step": 7647 + }, + { + "epoch": 8.24, + "learning_rate": 4.505747126436782e-05, + "loss": 0.9718, + "step": 7648 + }, + { + "epoch": 8.24, + "learning_rate": 4.505028735632184e-05, + "loss": 1.1, + "step": 7649 + }, + { + "epoch": 8.24, + "learning_rate": 4.504310344827587e-05, + "loss": 1.0535, + "step": 7650 + }, + { + "epoch": 8.24, + "learning_rate": 4.503591954022989e-05, + "loss": 1.017, + "step": 7651 + }, + { + "epoch": 8.25, + "learning_rate": 4.502873563218391e-05, + "loss": 0.9489, + "step": 7652 + }, + { + "epoch": 8.25, + "learning_rate": 4.5021551724137935e-05, + "loss": 1.0483, + "step": 7653 + }, + { + "epoch": 8.25, + "learning_rate": 4.5014367816091955e-05, + "loss": 0.9684, + "step": 7654 + }, + { + "epoch": 8.25, + "learning_rate": 4.500718390804598e-05, + "loss": 1.0493, + "step": 7655 + }, + { + "epoch": 8.25, + "learning_rate": 4.5e-05, + "loss": 0.9933, + "step": 7656 + }, + { + "epoch": 8.25, + "learning_rate": 4.499281609195402e-05, + "loss": 0.8568, + "step": 7657 + }, + { + "epoch": 8.25, + "learning_rate": 4.498563218390805e-05, + "loss": 1.0122, + "step": 7658 + }, + { + "epoch": 8.25, + "learning_rate": 4.497844827586207e-05, + "loss": 0.9679, + "step": 7659 + }, + { + "epoch": 8.25, + "learning_rate": 4.49712643678161e-05, + "loss": 0.9873, + "step": 7660 + }, + { + "epoch": 8.26, + "learning_rate": 4.496408045977012e-05, + "loss": 1.0343, + "step": 7661 + }, + { + "epoch": 8.26, + "learning_rate": 4.4956896551724145e-05, + "loss": 1.0173, + "step": 7662 + }, + { + "epoch": 8.26, + "learning_rate": 4.4949712643678165e-05, + "loss": 1.0254, + "step": 7663 + }, + { + "epoch": 8.26, + "learning_rate": 4.4942528735632186e-05, + "loss": 0.9278, + "step": 7664 + }, + { + "epoch": 8.26, + "learning_rate": 4.4935344827586206e-05, + "loss": 0.9503, + "step": 7665 + }, + { + "epoch": 8.26, + "learning_rate": 4.492816091954023e-05, + "loss": 1.0142, + "step": 7666 + }, + { + "epoch": 8.26, + "learning_rate": 4.4920977011494253e-05, + "loss": 1.0556, + "step": 7667 + }, + { + "epoch": 8.26, + "learning_rate": 4.4913793103448274e-05, + "loss": 0.9451, + "step": 7668 + }, + { + "epoch": 8.26, + "learning_rate": 4.49066091954023e-05, + "loss": 1.0549, + "step": 7669 + }, + { + "epoch": 8.27, + "learning_rate": 4.489942528735632e-05, + "loss": 0.9531, + "step": 7670 + }, + { + "epoch": 8.27, + "learning_rate": 4.489224137931035e-05, + "loss": 0.9537, + "step": 7671 + }, + { + "epoch": 8.27, + "learning_rate": 4.488505747126437e-05, + "loss": 1.0769, + "step": 7672 + }, + { + "epoch": 8.27, + "learning_rate": 4.487787356321839e-05, + "loss": 1.051, + "step": 7673 + }, + { + "epoch": 8.27, + "learning_rate": 4.4870689655172416e-05, + "loss": 1.0428, + "step": 7674 + }, + { + "epoch": 8.27, + "learning_rate": 4.4863505747126436e-05, + "loss": 1.0975, + "step": 7675 + }, + { + "epoch": 8.27, + "learning_rate": 4.4856321839080463e-05, + "loss": 0.9532, + "step": 7676 + }, + { + "epoch": 8.27, + "learning_rate": 4.4849137931034484e-05, + "loss": 0.9564, + "step": 7677 + }, + { + "epoch": 8.27, + "learning_rate": 4.484195402298851e-05, + "loss": 1.0876, + "step": 7678 + }, + { + "epoch": 8.27, + "learning_rate": 4.483477011494253e-05, + "loss": 0.9782, + "step": 7679 + }, + { + "epoch": 8.28, + "learning_rate": 4.482758620689655e-05, + "loss": 0.9883, + "step": 7680 + }, + { + "epoch": 8.28, + "learning_rate": 4.482040229885058e-05, + "loss": 0.9349, + "step": 7681 + }, + { + "epoch": 8.28, + "learning_rate": 4.48132183908046e-05, + "loss": 1.0465, + "step": 7682 + }, + { + "epoch": 8.28, + "learning_rate": 4.4806034482758626e-05, + "loss": 0.9285, + "step": 7683 + }, + { + "epoch": 8.28, + "learning_rate": 4.4798850574712646e-05, + "loss": 0.9709, + "step": 7684 + }, + { + "epoch": 8.28, + "learning_rate": 4.4791666666666673e-05, + "loss": 1.0386, + "step": 7685 + }, + { + "epoch": 8.28, + "learning_rate": 4.4784482758620694e-05, + "loss": 1.0085, + "step": 7686 + }, + { + "epoch": 8.28, + "learning_rate": 4.4777298850574714e-05, + "loss": 0.9606, + "step": 7687 + }, + { + "epoch": 8.28, + "learning_rate": 4.477011494252874e-05, + "loss": 0.9414, + "step": 7688 + }, + { + "epoch": 8.29, + "learning_rate": 4.476293103448276e-05, + "loss": 0.9647, + "step": 7689 + }, + { + "epoch": 8.29, + "learning_rate": 4.475574712643678e-05, + "loss": 0.9912, + "step": 7690 + }, + { + "epoch": 8.29, + "learning_rate": 4.47485632183908e-05, + "loss": 1.058, + "step": 7691 + }, + { + "epoch": 8.29, + "learning_rate": 4.474137931034483e-05, + "loss": 0.9513, + "step": 7692 + }, + { + "epoch": 8.29, + "learning_rate": 4.473419540229885e-05, + "loss": 1.004, + "step": 7693 + }, + { + "epoch": 8.29, + "learning_rate": 4.472701149425288e-05, + "loss": 1.0232, + "step": 7694 + }, + { + "epoch": 8.29, + "learning_rate": 4.47198275862069e-05, + "loss": 1.0495, + "step": 7695 + }, + { + "epoch": 8.29, + "learning_rate": 4.471264367816092e-05, + "loss": 0.9506, + "step": 7696 + }, + { + "epoch": 8.29, + "learning_rate": 4.4705459770114944e-05, + "loss": 0.979, + "step": 7697 + }, + { + "epoch": 8.3, + "learning_rate": 4.4698275862068965e-05, + "loss": 0.9571, + "step": 7698 + }, + { + "epoch": 8.3, + "learning_rate": 4.469109195402299e-05, + "loss": 0.9837, + "step": 7699 + }, + { + "epoch": 8.3, + "learning_rate": 4.468390804597701e-05, + "loss": 1.0242, + "step": 7700 + }, + { + "epoch": 8.3, + "learning_rate": 4.467672413793104e-05, + "loss": 0.9517, + "step": 7701 + }, + { + "epoch": 8.3, + "learning_rate": 4.466954022988506e-05, + "loss": 0.9442, + "step": 7702 + }, + { + "epoch": 8.3, + "learning_rate": 4.466235632183908e-05, + "loss": 0.9901, + "step": 7703 + }, + { + "epoch": 8.3, + "learning_rate": 4.465517241379311e-05, + "loss": 1.0766, + "step": 7704 + }, + { + "epoch": 8.3, + "learning_rate": 4.464798850574713e-05, + "loss": 0.9253, + "step": 7705 + }, + { + "epoch": 8.3, + "learning_rate": 4.4640804597701154e-05, + "loss": 1.0061, + "step": 7706 + }, + { + "epoch": 8.3, + "learning_rate": 4.4633620689655175e-05, + "loss": 1.1051, + "step": 7707 + }, + { + "epoch": 8.31, + "learning_rate": 4.46264367816092e-05, + "loss": 1.0811, + "step": 7708 + }, + { + "epoch": 8.31, + "learning_rate": 4.461925287356322e-05, + "loss": 0.9746, + "step": 7709 + }, + { + "epoch": 8.31, + "learning_rate": 4.461206896551724e-05, + "loss": 1.0103, + "step": 7710 + }, + { + "epoch": 8.31, + "learning_rate": 4.460488505747127e-05, + "loss": 1.0266, + "step": 7711 + }, + { + "epoch": 8.31, + "learning_rate": 4.459770114942529e-05, + "loss": 0.9628, + "step": 7712 + }, + { + "epoch": 8.31, + "learning_rate": 4.459051724137932e-05, + "loss": 0.9585, + "step": 7713 + }, + { + "epoch": 8.31, + "learning_rate": 4.458333333333334e-05, + "loss": 0.9327, + "step": 7714 + }, + { + "epoch": 8.31, + "learning_rate": 4.457614942528736e-05, + "loss": 0.9266, + "step": 7715 + }, + { + "epoch": 8.31, + "learning_rate": 4.456896551724138e-05, + "loss": 0.8572, + "step": 7716 + }, + { + "epoch": 8.32, + "learning_rate": 4.4561781609195405e-05, + "loss": 0.9099, + "step": 7717 + }, + { + "epoch": 8.32, + "learning_rate": 4.4554597701149425e-05, + "loss": 0.9218, + "step": 7718 + }, + { + "epoch": 8.32, + "learning_rate": 4.4547413793103446e-05, + "loss": 1.0721, + "step": 7719 + }, + { + "epoch": 8.32, + "learning_rate": 4.454022988505747e-05, + "loss": 1.0048, + "step": 7720 + }, + { + "epoch": 8.32, + "learning_rate": 4.453304597701149e-05, + "loss": 1.065, + "step": 7721 + }, + { + "epoch": 8.32, + "learning_rate": 4.452586206896552e-05, + "loss": 0.8147, + "step": 7722 + }, + { + "epoch": 8.32, + "learning_rate": 4.451867816091954e-05, + "loss": 1.0858, + "step": 7723 + }, + { + "epoch": 8.32, + "learning_rate": 4.451149425287357e-05, + "loss": 1.0037, + "step": 7724 + }, + { + "epoch": 8.32, + "learning_rate": 4.450431034482759e-05, + "loss": 1.01, + "step": 7725 + }, + { + "epoch": 8.33, + "learning_rate": 4.449712643678161e-05, + "loss": 0.9551, + "step": 7726 + }, + { + "epoch": 8.33, + "learning_rate": 4.4489942528735635e-05, + "loss": 1.0854, + "step": 7727 + }, + { + "epoch": 8.33, + "learning_rate": 4.4482758620689656e-05, + "loss": 1.0389, + "step": 7728 + }, + { + "epoch": 8.33, + "learning_rate": 4.447557471264368e-05, + "loss": 1.0289, + "step": 7729 + }, + { + "epoch": 8.33, + "learning_rate": 4.44683908045977e-05, + "loss": 0.9777, + "step": 7730 + }, + { + "epoch": 8.33, + "learning_rate": 4.446120689655173e-05, + "loss": 0.9955, + "step": 7731 + }, + { + "epoch": 8.33, + "learning_rate": 4.445402298850575e-05, + "loss": 1.1103, + "step": 7732 + }, + { + "epoch": 8.33, + "learning_rate": 4.444683908045977e-05, + "loss": 0.9058, + "step": 7733 + }, + { + "epoch": 8.33, + "learning_rate": 4.44396551724138e-05, + "loss": 0.919, + "step": 7734 + }, + { + "epoch": 8.34, + "learning_rate": 4.443247126436782e-05, + "loss": 0.9992, + "step": 7735 + }, + { + "epoch": 8.34, + "learning_rate": 4.4425287356321845e-05, + "loss": 1.0393, + "step": 7736 + }, + { + "epoch": 8.34, + "learning_rate": 4.4418103448275866e-05, + "loss": 1.0574, + "step": 7737 + }, + { + "epoch": 8.34, + "learning_rate": 4.441091954022989e-05, + "loss": 1.0479, + "step": 7738 + }, + { + "epoch": 8.34, + "learning_rate": 4.440373563218391e-05, + "loss": 1.0727, + "step": 7739 + }, + { + "epoch": 8.34, + "learning_rate": 4.4396551724137933e-05, + "loss": 1.176, + "step": 7740 + }, + { + "epoch": 8.34, + "learning_rate": 4.4389367816091954e-05, + "loss": 1.0236, + "step": 7741 + }, + { + "epoch": 8.34, + "learning_rate": 4.4382183908045974e-05, + "loss": 0.9522, + "step": 7742 + }, + { + "epoch": 8.34, + "learning_rate": 4.4375e-05, + "loss": 1.0426, + "step": 7743 + }, + { + "epoch": 8.34, + "learning_rate": 4.436781609195402e-05, + "loss": 0.939, + "step": 7744 + }, + { + "epoch": 8.35, + "learning_rate": 4.436063218390805e-05, + "loss": 0.9887, + "step": 7745 + }, + { + "epoch": 8.35, + "learning_rate": 4.435344827586207e-05, + "loss": 1.0409, + "step": 7746 + }, + { + "epoch": 8.35, + "learning_rate": 4.4346264367816096e-05, + "loss": 0.9707, + "step": 7747 + }, + { + "epoch": 8.35, + "learning_rate": 4.4339080459770116e-05, + "loss": 1.0074, + "step": 7748 + }, + { + "epoch": 8.35, + "learning_rate": 4.433189655172414e-05, + "loss": 1.2111, + "step": 7749 + }, + { + "epoch": 8.35, + "learning_rate": 4.4324712643678164e-05, + "loss": 1.0093, + "step": 7750 + }, + { + "epoch": 8.35, + "eval_loss": 1.1093857288360596, + "eval_runtime": 174.9753, + "eval_samples_per_second": 127.275, + "eval_steps_per_second": 0.663, + "step": 7750 + } + ], + "max_steps": 13920, + "num_train_epochs": 15, + "total_flos": 9.996595569229824e+17, + "trial_name": null, + "trial_params": null +}