{ "best_metric": null, "best_model_checkpoint": null, "epoch": 4.996154437778803, "global_step": 2030, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0, "learning_rate": 0.0, "loss": 0.8313, "step": 1 }, { "epoch": 0.0, "learning_rate": 1.6861309868950112e-06, "loss": 0.7773, "step": 2 }, { "epoch": 0.01, "learning_rate": 2.6724543855325485e-06, "loss": 0.7609, "step": 3 }, { "epoch": 0.01, "learning_rate": 3.3722619737900224e-06, "loss": 0.7384, "step": 4 }, { "epoch": 0.01, "learning_rate": 3.915074910131681e-06, "loss": 0.7534, "step": 5 }, { "epoch": 0.01, "learning_rate": 4.358585372427559e-06, "loss": 0.6916, "step": 6 }, { "epoch": 0.02, "learning_rate": 4.733568125293555e-06, "loss": 0.6947, "step": 7 }, { "epoch": 0.02, "learning_rate": 5.058392960685033e-06, "loss": 0.658, "step": 8 }, { "epoch": 0.02, "learning_rate": 5.344908771065097e-06, "loss": 0.6391, "step": 9 }, { "epoch": 0.02, "learning_rate": 5.601205897026694e-06, "loss": 0.6198, "step": 10 }, { "epoch": 0.03, "learning_rate": 5.833054849228712e-06, "loss": 0.6746, "step": 11 }, { "epoch": 0.03, "learning_rate": 6.044716359322571e-06, "loss": 0.6649, "step": 12 }, { "epoch": 0.03, "learning_rate": 6.239426073894737e-06, "loss": 0.6283, "step": 13 }, { "epoch": 0.03, "learning_rate": 6.419699112188566e-06, "loss": 0.6399, "step": 14 }, { "epoch": 0.04, "learning_rate": 6.58752929566423e-06, "loss": 0.6591, "step": 15 }, { "epoch": 0.04, "learning_rate": 6.744523947580045e-06, "loss": 0.6267, "step": 16 }, { "epoch": 0.04, "learning_rate": 6.8919977544141215e-06, "loss": 0.6092, "step": 17 }, { "epoch": 0.04, "learning_rate": 7.031039757960106e-06, "loss": 0.6363, "step": 18 }, { "epoch": 0.05, "learning_rate": 7.162562210501104e-06, "loss": 0.5936, "step": 19 }, { "epoch": 0.05, "learning_rate": 7.287336883921704e-06, "loss": 0.6031, "step": 20 }, { "epoch": 0.05, "learning_rate": 7.406022510826103e-06, "loss": 0.6163, "step": 21 }, { "epoch": 0.05, "learning_rate": 7.519185836123723e-06, "loss": 0.6143, "step": 22 }, { "epoch": 0.06, "learning_rate": 7.627317985247139e-06, "loss": 0.5955, "step": 23 }, { "epoch": 0.06, "learning_rate": 7.730847346217583e-06, "loss": 0.5881, "step": 24 }, { "epoch": 0.06, "learning_rate": 7.830149820263363e-06, "loss": 0.6007, "step": 25 }, { "epoch": 0.06, "learning_rate": 7.925557060789749e-06, "loss": 0.5824, "step": 26 }, { "epoch": 0.07, "learning_rate": 8.017363156597645e-06, "loss": 0.5883, "step": 27 }, { "epoch": 0.07, "learning_rate": 8.105830099083578e-06, "loss": 0.5828, "step": 28 }, { "epoch": 0.07, "learning_rate": 8.191192289631663e-06, "loss": 0.5824, "step": 29 }, { "epoch": 0.07, "learning_rate": 8.273660282559241e-06, "loss": 0.5763, "step": 30 }, { "epoch": 0.08, "learning_rate": 8.353423914104245e-06, "loss": 0.5939, "step": 31 }, { "epoch": 0.08, "learning_rate": 8.430654934475057e-06, "loss": 0.592, "step": 32 }, { "epoch": 0.08, "learning_rate": 8.50550923476126e-06, "loss": 0.603, "step": 33 }, { "epoch": 0.08, "learning_rate": 8.578128741309132e-06, "loss": 0.5891, "step": 34 }, { "epoch": 0.09, "learning_rate": 8.648643035425237e-06, "loss": 0.5685, "step": 35 }, { "epoch": 0.09, "learning_rate": 8.717170744855119e-06, "loss": 0.5659, "step": 36 }, { "epoch": 0.09, "learning_rate": 8.783820744571478e-06, "loss": 0.6099, "step": 37 }, { "epoch": 0.09, "learning_rate": 8.848693197396115e-06, "loss": 0.5657, "step": 38 }, { "epoch": 0.1, "learning_rate": 8.911880459427285e-06, "loss": 0.5931, "step": 39 }, { "epoch": 0.1, "learning_rate": 8.973467870816715e-06, "loss": 0.5864, "step": 40 }, { "epoch": 0.1, "learning_rate": 9.033534448888037e-06, "loss": 0.577, "step": 41 }, { "epoch": 0.1, "learning_rate": 9.092153497721114e-06, "loss": 0.5813, "step": 42 }, { "epoch": 0.11, "learning_rate": 9.149393145999464e-06, "loss": 0.5873, "step": 43 }, { "epoch": 0.11, "learning_rate": 9.205316823018733e-06, "loss": 0.5681, "step": 44 }, { "epoch": 0.11, "learning_rate": 9.259983681196777e-06, "loss": 0.5902, "step": 45 }, { "epoch": 0.11, "learning_rate": 9.31344897214215e-06, "loss": 0.5951, "step": 46 }, { "epoch": 0.12, "learning_rate": 9.365764382275242e-06, "loss": 0.58, "step": 47 }, { "epoch": 0.12, "learning_rate": 9.416978333112594e-06, "loss": 0.5458, "step": 48 }, { "epoch": 0.12, "learning_rate": 9.46713625058711e-06, "loss": 0.5579, "step": 49 }, { "epoch": 0.12, "learning_rate": 9.516280807158374e-06, "loss": 0.6012, "step": 50 }, { "epoch": 0.13, "learning_rate": 9.56445213994667e-06, "loss": 0.5863, "step": 51 }, { "epoch": 0.13, "learning_rate": 9.61168804768476e-06, "loss": 0.5836, "step": 52 }, { "epoch": 0.13, "learning_rate": 9.658024168908768e-06, "loss": 0.5512, "step": 53 }, { "epoch": 0.13, "learning_rate": 9.703494143492656e-06, "loss": 0.5968, "step": 54 }, { "epoch": 0.14, "learning_rate": 9.748129759360394e-06, "loss": 0.5915, "step": 55 }, { "epoch": 0.14, "learning_rate": 9.79196108597859e-06, "loss": 0.5866, "step": 56 }, { "epoch": 0.14, "learning_rate": 9.835016596033651e-06, "loss": 0.5719, "step": 57 }, { "epoch": 0.14, "learning_rate": 9.877323276526673e-06, "loss": 0.5647, "step": 58 }, { "epoch": 0.15, "learning_rate": 9.91890673037156e-06, "loss": 0.5739, "step": 59 }, { "epoch": 0.15, "learning_rate": 9.959791269454251e-06, "loss": 0.5773, "step": 60 }, { "epoch": 0.15, "learning_rate": 1e-05, "loss": 0.5797, "step": 61 }, { "epoch": 0.15, "learning_rate": 1e-05, "loss": 0.5808, "step": 62 }, { "epoch": 0.16, "learning_rate": 9.994921279837482e-06, "loss": 0.5808, "step": 63 }, { "epoch": 0.16, "learning_rate": 9.989842559674962e-06, "loss": 0.5887, "step": 64 }, { "epoch": 0.16, "learning_rate": 9.984763839512443e-06, "loss": 0.5703, "step": 65 }, { "epoch": 0.16, "learning_rate": 9.979685119349925e-06, "loss": 0.5962, "step": 66 }, { "epoch": 0.16, "learning_rate": 9.974606399187405e-06, "loss": 0.567, "step": 67 }, { "epoch": 0.17, "learning_rate": 9.969527679024886e-06, "loss": 0.5719, "step": 68 }, { "epoch": 0.17, "learning_rate": 9.964448958862367e-06, "loss": 0.5709, "step": 69 }, { "epoch": 0.17, "learning_rate": 9.959370238699849e-06, "loss": 0.5876, "step": 70 }, { "epoch": 0.17, "learning_rate": 9.954291518537329e-06, "loss": 0.5661, "step": 71 }, { "epoch": 0.18, "learning_rate": 9.94921279837481e-06, "loss": 0.5889, "step": 72 }, { "epoch": 0.18, "learning_rate": 9.944134078212291e-06, "loss": 0.5644, "step": 73 }, { "epoch": 0.18, "learning_rate": 9.939055358049771e-06, "loss": 0.5726, "step": 74 }, { "epoch": 0.18, "learning_rate": 9.933976637887254e-06, "loss": 0.5644, "step": 75 }, { "epoch": 0.19, "learning_rate": 9.928897917724734e-06, "loss": 0.5885, "step": 76 }, { "epoch": 0.19, "learning_rate": 9.923819197562215e-06, "loss": 0.5656, "step": 77 }, { "epoch": 0.19, "learning_rate": 9.918740477399697e-06, "loss": 0.5621, "step": 78 }, { "epoch": 0.19, "learning_rate": 9.913661757237177e-06, "loss": 0.5715, "step": 79 }, { "epoch": 0.2, "learning_rate": 9.908583037074658e-06, "loss": 0.576, "step": 80 }, { "epoch": 0.2, "learning_rate": 9.90350431691214e-06, "loss": 0.5689, "step": 81 }, { "epoch": 0.2, "learning_rate": 9.89842559674962e-06, "loss": 0.5504, "step": 82 }, { "epoch": 0.2, "learning_rate": 9.8933468765871e-06, "loss": 0.5692, "step": 83 }, { "epoch": 0.21, "learning_rate": 9.888268156424582e-06, "loss": 0.5749, "step": 84 }, { "epoch": 0.21, "learning_rate": 9.883189436262063e-06, "loss": 0.5771, "step": 85 }, { "epoch": 0.21, "learning_rate": 9.878110716099543e-06, "loss": 0.5595, "step": 86 }, { "epoch": 0.21, "learning_rate": 9.873031995937025e-06, "loss": 0.5788, "step": 87 }, { "epoch": 0.22, "learning_rate": 9.867953275774506e-06, "loss": 0.582, "step": 88 }, { "epoch": 0.22, "learning_rate": 9.862874555611986e-06, "loss": 0.5517, "step": 89 }, { "epoch": 0.22, "learning_rate": 9.857795835449467e-06, "loss": 0.5602, "step": 90 }, { "epoch": 0.22, "learning_rate": 9.852717115286949e-06, "loss": 0.5917, "step": 91 }, { "epoch": 0.23, "learning_rate": 9.84763839512443e-06, "loss": 0.5805, "step": 92 }, { "epoch": 0.23, "learning_rate": 9.84255967496191e-06, "loss": 0.5647, "step": 93 }, { "epoch": 0.23, "learning_rate": 9.837480954799391e-06, "loss": 0.5469, "step": 94 }, { "epoch": 0.23, "learning_rate": 9.832402234636873e-06, "loss": 0.5765, "step": 95 }, { "epoch": 0.24, "learning_rate": 9.827323514474352e-06, "loss": 0.5727, "step": 96 }, { "epoch": 0.24, "learning_rate": 9.822244794311834e-06, "loss": 0.5686, "step": 97 }, { "epoch": 0.24, "learning_rate": 9.817166074149315e-06, "loss": 0.5855, "step": 98 }, { "epoch": 0.24, "learning_rate": 9.812087353986797e-06, "loss": 0.566, "step": 99 }, { "epoch": 0.25, "learning_rate": 9.807008633824278e-06, "loss": 0.5924, "step": 100 }, { "epoch": 0.25, "learning_rate": 9.801929913661758e-06, "loss": 0.5295, "step": 101 }, { "epoch": 0.25, "learning_rate": 9.796851193499239e-06, "loss": 0.5833, "step": 102 }, { "epoch": 0.25, "learning_rate": 9.79177247333672e-06, "loss": 0.575, "step": 103 }, { "epoch": 0.26, "learning_rate": 9.786693753174202e-06, "loss": 0.5574, "step": 104 }, { "epoch": 0.26, "learning_rate": 9.781615033011682e-06, "loss": 0.5696, "step": 105 }, { "epoch": 0.26, "learning_rate": 9.776536312849163e-06, "loss": 0.5648, "step": 106 }, { "epoch": 0.26, "learning_rate": 9.771457592686645e-06, "loss": 0.568, "step": 107 }, { "epoch": 0.27, "learning_rate": 9.766378872524124e-06, "loss": 0.5629, "step": 108 }, { "epoch": 0.27, "learning_rate": 9.761300152361606e-06, "loss": 0.5419, "step": 109 }, { "epoch": 0.27, "learning_rate": 9.756221432199087e-06, "loss": 0.5591, "step": 110 }, { "epoch": 0.27, "learning_rate": 9.751142712036567e-06, "loss": 0.5577, "step": 111 }, { "epoch": 0.28, "learning_rate": 9.746063991874048e-06, "loss": 0.5529, "step": 112 }, { "epoch": 0.28, "learning_rate": 9.74098527171153e-06, "loss": 0.576, "step": 113 }, { "epoch": 0.28, "learning_rate": 9.735906551549011e-06, "loss": 0.573, "step": 114 }, { "epoch": 0.28, "learning_rate": 9.730827831386491e-06, "loss": 0.5626, "step": 115 }, { "epoch": 0.29, "learning_rate": 9.725749111223972e-06, "loss": 0.5733, "step": 116 }, { "epoch": 0.29, "learning_rate": 9.720670391061454e-06, "loss": 0.554, "step": 117 }, { "epoch": 0.29, "learning_rate": 9.715591670898933e-06, "loss": 0.5732, "step": 118 }, { "epoch": 0.29, "learning_rate": 9.710512950736415e-06, "loss": 0.5744, "step": 119 }, { "epoch": 0.3, "learning_rate": 9.705434230573896e-06, "loss": 0.5531, "step": 120 }, { "epoch": 0.3, "learning_rate": 9.700355510411376e-06, "loss": 0.5323, "step": 121 }, { "epoch": 0.3, "learning_rate": 9.695276790248857e-06, "loss": 0.5463, "step": 122 }, { "epoch": 0.3, "learning_rate": 9.690198070086339e-06, "loss": 0.5709, "step": 123 }, { "epoch": 0.31, "learning_rate": 9.68511934992382e-06, "loss": 0.5307, "step": 124 }, { "epoch": 0.31, "learning_rate": 9.680040629761302e-06, "loss": 0.5482, "step": 125 }, { "epoch": 0.31, "learning_rate": 9.674961909598783e-06, "loss": 0.5633, "step": 126 }, { "epoch": 0.31, "learning_rate": 9.669883189436263e-06, "loss": 0.5513, "step": 127 }, { "epoch": 0.32, "learning_rate": 9.664804469273744e-06, "loss": 0.5589, "step": 128 }, { "epoch": 0.32, "learning_rate": 9.659725749111226e-06, "loss": 0.5529, "step": 129 }, { "epoch": 0.32, "learning_rate": 9.654647028948705e-06, "loss": 0.553, "step": 130 }, { "epoch": 0.32, "learning_rate": 9.649568308786187e-06, "loss": 0.5624, "step": 131 }, { "epoch": 0.32, "learning_rate": 9.644489588623668e-06, "loss": 0.5494, "step": 132 }, { "epoch": 0.33, "learning_rate": 9.639410868461148e-06, "loss": 0.5552, "step": 133 }, { "epoch": 0.33, "learning_rate": 9.63433214829863e-06, "loss": 0.5723, "step": 134 }, { "epoch": 0.33, "learning_rate": 9.629253428136111e-06, "loss": 0.5713, "step": 135 }, { "epoch": 0.33, "learning_rate": 9.62417470797359e-06, "loss": 0.5663, "step": 136 }, { "epoch": 0.34, "learning_rate": 9.619095987811072e-06, "loss": 0.5614, "step": 137 }, { "epoch": 0.34, "learning_rate": 9.614017267648553e-06, "loss": 0.5323, "step": 138 }, { "epoch": 0.34, "learning_rate": 9.608938547486035e-06, "loss": 0.557, "step": 139 }, { "epoch": 0.34, "learning_rate": 9.603859827323515e-06, "loss": 0.6012, "step": 140 }, { "epoch": 0.35, "learning_rate": 9.598781107160996e-06, "loss": 0.5439, "step": 141 }, { "epoch": 0.35, "learning_rate": 9.593702386998477e-06, "loss": 0.5357, "step": 142 }, { "epoch": 0.35, "learning_rate": 9.588623666835957e-06, "loss": 0.5819, "step": 143 }, { "epoch": 0.35, "learning_rate": 9.583544946673439e-06, "loss": 0.5611, "step": 144 }, { "epoch": 0.36, "learning_rate": 9.57846622651092e-06, "loss": 0.5299, "step": 145 }, { "epoch": 0.36, "learning_rate": 9.5733875063484e-06, "loss": 0.5587, "step": 146 }, { "epoch": 0.36, "learning_rate": 9.568308786185881e-06, "loss": 0.5411, "step": 147 }, { "epoch": 0.36, "learning_rate": 9.563230066023363e-06, "loss": 0.5431, "step": 148 }, { "epoch": 0.37, "learning_rate": 9.558151345860844e-06, "loss": 0.5361, "step": 149 }, { "epoch": 0.37, "learning_rate": 9.553072625698325e-06, "loss": 0.5594, "step": 150 }, { "epoch": 0.37, "learning_rate": 9.547993905535807e-06, "loss": 0.5576, "step": 151 }, { "epoch": 0.37, "learning_rate": 9.542915185373287e-06, "loss": 0.5571, "step": 152 }, { "epoch": 0.38, "learning_rate": 9.537836465210768e-06, "loss": 0.5565, "step": 153 }, { "epoch": 0.38, "learning_rate": 9.53275774504825e-06, "loss": 0.5394, "step": 154 }, { "epoch": 0.38, "learning_rate": 9.52767902488573e-06, "loss": 0.568, "step": 155 }, { "epoch": 0.38, "learning_rate": 9.52260030472321e-06, "loss": 0.5605, "step": 156 }, { "epoch": 0.39, "learning_rate": 9.517521584560692e-06, "loss": 0.5479, "step": 157 }, { "epoch": 0.39, "learning_rate": 9.512442864398172e-06, "loss": 0.5372, "step": 158 }, { "epoch": 0.39, "learning_rate": 9.507364144235653e-06, "loss": 0.5459, "step": 159 }, { "epoch": 0.39, "learning_rate": 9.502285424073135e-06, "loss": 0.5688, "step": 160 }, { "epoch": 0.4, "learning_rate": 9.497206703910616e-06, "loss": 0.5507, "step": 161 }, { "epoch": 0.4, "learning_rate": 9.492127983748096e-06, "loss": 0.5479, "step": 162 }, { "epoch": 0.4, "learning_rate": 9.487049263585577e-06, "loss": 0.5579, "step": 163 }, { "epoch": 0.4, "learning_rate": 9.481970543423059e-06, "loss": 0.524, "step": 164 }, { "epoch": 0.41, "learning_rate": 9.476891823260538e-06, "loss": 0.5549, "step": 165 }, { "epoch": 0.41, "learning_rate": 9.47181310309802e-06, "loss": 0.5627, "step": 166 }, { "epoch": 0.41, "learning_rate": 9.466734382935501e-06, "loss": 0.574, "step": 167 }, { "epoch": 0.41, "learning_rate": 9.461655662772981e-06, "loss": 0.5623, "step": 168 }, { "epoch": 0.42, "learning_rate": 9.456576942610462e-06, "loss": 0.5643, "step": 169 }, { "epoch": 0.42, "learning_rate": 9.451498222447944e-06, "loss": 0.5425, "step": 170 }, { "epoch": 0.42, "learning_rate": 9.446419502285424e-06, "loss": 0.5585, "step": 171 }, { "epoch": 0.42, "learning_rate": 9.441340782122905e-06, "loss": 0.5442, "step": 172 }, { "epoch": 0.43, "learning_rate": 9.436262061960388e-06, "loss": 0.5371, "step": 173 }, { "epoch": 0.43, "learning_rate": 9.431183341797868e-06, "loss": 0.5433, "step": 174 }, { "epoch": 0.43, "learning_rate": 9.42610462163535e-06, "loss": 0.5629, "step": 175 }, { "epoch": 0.43, "learning_rate": 9.42102590147283e-06, "loss": 0.5778, "step": 176 }, { "epoch": 0.44, "learning_rate": 9.41594718131031e-06, "loss": 0.5499, "step": 177 }, { "epoch": 0.44, "learning_rate": 9.410868461147792e-06, "loss": 0.5367, "step": 178 }, { "epoch": 0.44, "learning_rate": 9.405789740985273e-06, "loss": 0.5366, "step": 179 }, { "epoch": 0.44, "learning_rate": 9.400711020822753e-06, "loss": 0.5643, "step": 180 }, { "epoch": 0.45, "learning_rate": 9.395632300660234e-06, "loss": 0.5457, "step": 181 }, { "epoch": 0.45, "learning_rate": 9.390553580497716e-06, "loss": 0.54, "step": 182 }, { "epoch": 0.45, "learning_rate": 9.385474860335197e-06, "loss": 0.5457, "step": 183 }, { "epoch": 0.45, "learning_rate": 9.380396140172677e-06, "loss": 0.5711, "step": 184 }, { "epoch": 0.46, "learning_rate": 9.375317420010158e-06, "loss": 0.5433, "step": 185 }, { "epoch": 0.46, "learning_rate": 9.37023869984764e-06, "loss": 0.5654, "step": 186 }, { "epoch": 0.46, "learning_rate": 9.36515997968512e-06, "loss": 0.5394, "step": 187 }, { "epoch": 0.46, "learning_rate": 9.360081259522601e-06, "loss": 0.5609, "step": 188 }, { "epoch": 0.47, "learning_rate": 9.355002539360082e-06, "loss": 0.546, "step": 189 }, { "epoch": 0.47, "learning_rate": 9.349923819197562e-06, "loss": 0.5402, "step": 190 }, { "epoch": 0.47, "learning_rate": 9.344845099035044e-06, "loss": 0.5309, "step": 191 }, { "epoch": 0.47, "learning_rate": 9.339766378872525e-06, "loss": 0.5672, "step": 192 }, { "epoch": 0.48, "learning_rate": 9.334687658710005e-06, "loss": 0.5638, "step": 193 }, { "epoch": 0.48, "learning_rate": 9.329608938547486e-06, "loss": 0.5408, "step": 194 }, { "epoch": 0.48, "learning_rate": 9.324530218384968e-06, "loss": 0.5349, "step": 195 }, { "epoch": 0.48, "learning_rate": 9.319451498222449e-06, "loss": 0.5358, "step": 196 }, { "epoch": 0.48, "learning_rate": 9.314372778059929e-06, "loss": 0.5445, "step": 197 }, { "epoch": 0.49, "learning_rate": 9.309294057897412e-06, "loss": 0.5689, "step": 198 }, { "epoch": 0.49, "learning_rate": 9.304215337734892e-06, "loss": 0.541, "step": 199 }, { "epoch": 0.49, "learning_rate": 9.299136617572373e-06, "loss": 0.539, "step": 200 }, { "epoch": 0.49, "learning_rate": 9.294057897409854e-06, "loss": 0.5471, "step": 201 }, { "epoch": 0.5, "learning_rate": 9.288979177247334e-06, "loss": 0.513, "step": 202 }, { "epoch": 0.5, "learning_rate": 9.283900457084816e-06, "loss": 0.519, "step": 203 }, { "epoch": 0.5, "learning_rate": 9.278821736922297e-06, "loss": 0.5706, "step": 204 }, { "epoch": 0.5, "learning_rate": 9.273743016759777e-06, "loss": 0.5546, "step": 205 }, { "epoch": 0.51, "learning_rate": 9.268664296597258e-06, "loss": 0.5325, "step": 206 }, { "epoch": 0.51, "learning_rate": 9.26358557643474e-06, "loss": 0.5478, "step": 207 }, { "epoch": 0.51, "learning_rate": 9.258506856272221e-06, "loss": 0.5758, "step": 208 }, { "epoch": 0.51, "learning_rate": 9.2534281361097e-06, "loss": 0.5481, "step": 209 }, { "epoch": 0.52, "learning_rate": 9.248349415947182e-06, "loss": 0.5412, "step": 210 }, { "epoch": 0.52, "learning_rate": 9.243270695784664e-06, "loss": 0.53, "step": 211 }, { "epoch": 0.52, "learning_rate": 9.238191975622143e-06, "loss": 0.5516, "step": 212 }, { "epoch": 0.52, "learning_rate": 9.233113255459625e-06, "loss": 0.5619, "step": 213 }, { "epoch": 0.53, "learning_rate": 9.228034535297106e-06, "loss": 0.5588, "step": 214 }, { "epoch": 0.53, "learning_rate": 9.222955815134586e-06, "loss": 0.5774, "step": 215 }, { "epoch": 0.53, "learning_rate": 9.217877094972067e-06, "loss": 0.5237, "step": 216 }, { "epoch": 0.53, "learning_rate": 9.212798374809549e-06, "loss": 0.5538, "step": 217 }, { "epoch": 0.54, "learning_rate": 9.20771965464703e-06, "loss": 0.5347, "step": 218 }, { "epoch": 0.54, "learning_rate": 9.20264093448451e-06, "loss": 0.5606, "step": 219 }, { "epoch": 0.54, "learning_rate": 9.197562214321991e-06, "loss": 0.5449, "step": 220 }, { "epoch": 0.54, "learning_rate": 9.192483494159473e-06, "loss": 0.5399, "step": 221 }, { "epoch": 0.55, "learning_rate": 9.187404773996954e-06, "loss": 0.5181, "step": 222 }, { "epoch": 0.55, "learning_rate": 9.182326053834436e-06, "loss": 0.545, "step": 223 }, { "epoch": 0.55, "learning_rate": 9.177247333671915e-06, "loss": 0.5559, "step": 224 }, { "epoch": 0.55, "learning_rate": 9.172168613509397e-06, "loss": 0.5419, "step": 225 }, { "epoch": 0.56, "learning_rate": 9.167089893346878e-06, "loss": 0.5559, "step": 226 }, { "epoch": 0.56, "learning_rate": 9.162011173184358e-06, "loss": 0.5528, "step": 227 }, { "epoch": 0.56, "learning_rate": 9.15693245302184e-06, "loss": 0.544, "step": 228 }, { "epoch": 0.56, "learning_rate": 9.15185373285932e-06, "loss": 0.5427, "step": 229 }, { "epoch": 0.57, "learning_rate": 9.146775012696802e-06, "loss": 0.5238, "step": 230 }, { "epoch": 0.57, "learning_rate": 9.141696292534282e-06, "loss": 0.5486, "step": 231 }, { "epoch": 0.57, "learning_rate": 9.136617572371763e-06, "loss": 0.5563, "step": 232 }, { "epoch": 0.57, "learning_rate": 9.131538852209245e-06, "loss": 0.5565, "step": 233 }, { "epoch": 0.58, "learning_rate": 9.126460132046724e-06, "loss": 0.5553, "step": 234 }, { "epoch": 0.58, "learning_rate": 9.121381411884206e-06, "loss": 0.5614, "step": 235 }, { "epoch": 0.58, "learning_rate": 9.116302691721687e-06, "loss": 0.5378, "step": 236 }, { "epoch": 0.58, "learning_rate": 9.111223971559167e-06, "loss": 0.5577, "step": 237 }, { "epoch": 0.59, "learning_rate": 9.106145251396648e-06, "loss": 0.5547, "step": 238 }, { "epoch": 0.59, "learning_rate": 9.10106653123413e-06, "loss": 0.5559, "step": 239 }, { "epoch": 0.59, "learning_rate": 9.09598781107161e-06, "loss": 0.5619, "step": 240 }, { "epoch": 0.59, "learning_rate": 9.090909090909091e-06, "loss": 0.5648, "step": 241 }, { "epoch": 0.6, "learning_rate": 9.085830370746572e-06, "loss": 0.5411, "step": 242 }, { "epoch": 0.6, "learning_rate": 9.080751650584054e-06, "loss": 0.5662, "step": 243 }, { "epoch": 0.6, "learning_rate": 9.075672930421534e-06, "loss": 0.5425, "step": 244 }, { "epoch": 0.6, "learning_rate": 9.070594210259015e-06, "loss": 0.5604, "step": 245 }, { "epoch": 0.61, "learning_rate": 9.065515490096496e-06, "loss": 0.5532, "step": 246 }, { "epoch": 0.61, "learning_rate": 9.060436769933978e-06, "loss": 0.5327, "step": 247 }, { "epoch": 0.61, "learning_rate": 9.05535804977146e-06, "loss": 0.5393, "step": 248 }, { "epoch": 0.61, "learning_rate": 9.050279329608939e-06, "loss": 0.5617, "step": 249 }, { "epoch": 0.62, "learning_rate": 9.04520060944642e-06, "loss": 0.5527, "step": 250 }, { "epoch": 0.62, "learning_rate": 9.040121889283902e-06, "loss": 0.5173, "step": 251 }, { "epoch": 0.62, "learning_rate": 9.035043169121382e-06, "loss": 0.5328, "step": 252 }, { "epoch": 0.62, "learning_rate": 9.029964448958863e-06, "loss": 0.5563, "step": 253 }, { "epoch": 0.63, "learning_rate": 9.024885728796344e-06, "loss": 0.5742, "step": 254 }, { "epoch": 0.63, "learning_rate": 9.019807008633826e-06, "loss": 0.538, "step": 255 }, { "epoch": 0.63, "learning_rate": 9.014728288471306e-06, "loss": 0.5369, "step": 256 }, { "epoch": 0.63, "learning_rate": 9.009649568308787e-06, "loss": 0.5357, "step": 257 }, { "epoch": 0.63, "learning_rate": 9.004570848146268e-06, "loss": 0.5502, "step": 258 }, { "epoch": 0.64, "learning_rate": 8.999492127983748e-06, "loss": 0.5462, "step": 259 }, { "epoch": 0.64, "learning_rate": 8.99441340782123e-06, "loss": 0.5504, "step": 260 }, { "epoch": 0.64, "learning_rate": 8.989334687658711e-06, "loss": 0.5333, "step": 261 }, { "epoch": 0.64, "learning_rate": 8.98425596749619e-06, "loss": 0.5569, "step": 262 }, { "epoch": 0.65, "learning_rate": 8.979177247333672e-06, "loss": 0.5411, "step": 263 }, { "epoch": 0.65, "learning_rate": 8.974098527171154e-06, "loss": 0.5619, "step": 264 }, { "epoch": 0.65, "learning_rate": 8.969019807008635e-06, "loss": 0.5497, "step": 265 }, { "epoch": 0.65, "learning_rate": 8.963941086846115e-06, "loss": 0.5394, "step": 266 }, { "epoch": 0.66, "learning_rate": 8.958862366683596e-06, "loss": 0.5379, "step": 267 }, { "epoch": 0.66, "learning_rate": 8.953783646521078e-06, "loss": 0.5394, "step": 268 }, { "epoch": 0.66, "learning_rate": 8.948704926358557e-06, "loss": 0.5461, "step": 269 }, { "epoch": 0.66, "learning_rate": 8.943626206196039e-06, "loss": 0.52, "step": 270 }, { "epoch": 0.67, "learning_rate": 8.93854748603352e-06, "loss": 0.5185, "step": 271 }, { "epoch": 0.67, "learning_rate": 8.933468765871002e-06, "loss": 0.5605, "step": 272 }, { "epoch": 0.67, "learning_rate": 8.928390045708483e-06, "loss": 0.5638, "step": 273 }, { "epoch": 0.67, "learning_rate": 8.923311325545963e-06, "loss": 0.5533, "step": 274 }, { "epoch": 0.68, "learning_rate": 8.918232605383444e-06, "loss": 0.5315, "step": 275 }, { "epoch": 0.68, "learning_rate": 8.913153885220926e-06, "loss": 0.5086, "step": 276 }, { "epoch": 0.68, "learning_rate": 8.908075165058407e-06, "loss": 0.5396, "step": 277 }, { "epoch": 0.68, "learning_rate": 8.902996444895887e-06, "loss": 0.5317, "step": 278 }, { "epoch": 0.69, "learning_rate": 8.897917724733368e-06, "loss": 0.5071, "step": 279 }, { "epoch": 0.69, "learning_rate": 8.89283900457085e-06, "loss": 0.5299, "step": 280 }, { "epoch": 0.69, "learning_rate": 8.88776028440833e-06, "loss": 0.5264, "step": 281 }, { "epoch": 0.69, "learning_rate": 8.88268156424581e-06, "loss": 0.5193, "step": 282 }, { "epoch": 0.7, "learning_rate": 8.877602844083292e-06, "loss": 0.5307, "step": 283 }, { "epoch": 0.7, "learning_rate": 8.872524123920772e-06, "loss": 0.5486, "step": 284 }, { "epoch": 0.7, "learning_rate": 8.867445403758253e-06, "loss": 0.5214, "step": 285 }, { "epoch": 0.7, "learning_rate": 8.862366683595735e-06, "loss": 0.5513, "step": 286 }, { "epoch": 0.71, "learning_rate": 8.857287963433216e-06, "loss": 0.5408, "step": 287 }, { "epoch": 0.71, "learning_rate": 8.852209243270696e-06, "loss": 0.5545, "step": 288 }, { "epoch": 0.71, "learning_rate": 8.847130523108177e-06, "loss": 0.5219, "step": 289 }, { "epoch": 0.71, "learning_rate": 8.842051802945659e-06, "loss": 0.5391, "step": 290 }, { "epoch": 0.72, "learning_rate": 8.836973082783139e-06, "loss": 0.5696, "step": 291 }, { "epoch": 0.72, "learning_rate": 8.83189436262062e-06, "loss": 0.5275, "step": 292 }, { "epoch": 0.72, "learning_rate": 8.826815642458101e-06, "loss": 0.5694, "step": 293 }, { "epoch": 0.72, "learning_rate": 8.821736922295581e-06, "loss": 0.5488, "step": 294 }, { "epoch": 0.73, "learning_rate": 8.816658202133063e-06, "loss": 0.5527, "step": 295 }, { "epoch": 0.73, "learning_rate": 8.811579481970544e-06, "loss": 0.5113, "step": 296 }, { "epoch": 0.73, "learning_rate": 8.806500761808025e-06, "loss": 0.5348, "step": 297 }, { "epoch": 0.73, "learning_rate": 8.801422041645507e-06, "loss": 0.5317, "step": 298 }, { "epoch": 0.74, "learning_rate": 8.796343321482988e-06, "loss": 0.5468, "step": 299 }, { "epoch": 0.74, "learning_rate": 8.791264601320468e-06, "loss": 0.5296, "step": 300 }, { "epoch": 0.74, "learning_rate": 8.78618588115795e-06, "loss": 0.5389, "step": 301 }, { "epoch": 0.74, "learning_rate": 8.78110716099543e-06, "loss": 0.5389, "step": 302 }, { "epoch": 0.75, "learning_rate": 8.77602844083291e-06, "loss": 0.5521, "step": 303 }, { "epoch": 0.75, "learning_rate": 8.770949720670392e-06, "loss": 0.5643, "step": 304 }, { "epoch": 0.75, "learning_rate": 8.765871000507873e-06, "loss": 0.5547, "step": 305 }, { "epoch": 0.75, "learning_rate": 8.760792280345353e-06, "loss": 0.5294, "step": 306 }, { "epoch": 0.76, "learning_rate": 8.755713560182835e-06, "loss": 0.529, "step": 307 }, { "epoch": 0.76, "learning_rate": 8.750634840020316e-06, "loss": 0.5243, "step": 308 }, { "epoch": 0.76, "learning_rate": 8.745556119857796e-06, "loss": 0.5535, "step": 309 }, { "epoch": 0.76, "learning_rate": 8.740477399695277e-06, "loss": 0.5231, "step": 310 }, { "epoch": 0.77, "learning_rate": 8.735398679532759e-06, "loss": 0.5593, "step": 311 }, { "epoch": 0.77, "learning_rate": 8.73031995937024e-06, "loss": 0.5381, "step": 312 }, { "epoch": 0.77, "learning_rate": 8.72524123920772e-06, "loss": 0.5366, "step": 313 }, { "epoch": 0.77, "learning_rate": 8.720162519045201e-06, "loss": 0.531, "step": 314 }, { "epoch": 0.78, "learning_rate": 8.715083798882683e-06, "loss": 0.5481, "step": 315 }, { "epoch": 0.78, "learning_rate": 8.710005078720162e-06, "loss": 0.5441, "step": 316 }, { "epoch": 0.78, "learning_rate": 8.704926358557644e-06, "loss": 0.5211, "step": 317 }, { "epoch": 0.78, "learning_rate": 8.699847638395125e-06, "loss": 0.5169, "step": 318 }, { "epoch": 0.79, "learning_rate": 8.694768918232605e-06, "loss": 0.5435, "step": 319 }, { "epoch": 0.79, "learning_rate": 8.689690198070086e-06, "loss": 0.5349, "step": 320 }, { "epoch": 0.79, "learning_rate": 8.684611477907568e-06, "loss": 0.5487, "step": 321 }, { "epoch": 0.79, "learning_rate": 8.679532757745049e-06, "loss": 0.563, "step": 322 }, { "epoch": 0.79, "learning_rate": 8.67445403758253e-06, "loss": 0.5169, "step": 323 }, { "epoch": 0.8, "learning_rate": 8.669375317420012e-06, "loss": 0.541, "step": 324 }, { "epoch": 0.8, "learning_rate": 8.664296597257492e-06, "loss": 0.5529, "step": 325 }, { "epoch": 0.8, "learning_rate": 8.659217877094973e-06, "loss": 0.5632, "step": 326 }, { "epoch": 0.8, "learning_rate": 8.654139156932455e-06, "loss": 0.5565, "step": 327 }, { "epoch": 0.81, "learning_rate": 8.649060436769934e-06, "loss": 0.537, "step": 328 }, { "epoch": 0.81, "learning_rate": 8.643981716607416e-06, "loss": 0.5667, "step": 329 }, { "epoch": 0.81, "learning_rate": 8.638902996444897e-06, "loss": 0.5482, "step": 330 }, { "epoch": 0.81, "learning_rate": 8.633824276282377e-06, "loss": 0.535, "step": 331 }, { "epoch": 0.82, "learning_rate": 8.628745556119858e-06, "loss": 0.5339, "step": 332 }, { "epoch": 0.82, "learning_rate": 8.62366683595734e-06, "loss": 0.5195, "step": 333 }, { "epoch": 0.82, "learning_rate": 8.618588115794821e-06, "loss": 0.5297, "step": 334 }, { "epoch": 0.82, "learning_rate": 8.613509395632301e-06, "loss": 0.5087, "step": 335 }, { "epoch": 0.83, "learning_rate": 8.608430675469782e-06, "loss": 0.5513, "step": 336 }, { "epoch": 0.83, "learning_rate": 8.603351955307264e-06, "loss": 0.5545, "step": 337 }, { "epoch": 0.83, "learning_rate": 8.598273235144743e-06, "loss": 0.4987, "step": 338 }, { "epoch": 0.83, "learning_rate": 8.593194514982225e-06, "loss": 0.5575, "step": 339 }, { "epoch": 0.84, "learning_rate": 8.588115794819706e-06, "loss": 0.5498, "step": 340 }, { "epoch": 0.84, "learning_rate": 8.583037074657186e-06, "loss": 0.5512, "step": 341 }, { "epoch": 0.84, "learning_rate": 8.577958354494667e-06, "loss": 0.5353, "step": 342 }, { "epoch": 0.84, "learning_rate": 8.572879634332149e-06, "loss": 0.5467, "step": 343 }, { "epoch": 0.85, "learning_rate": 8.56780091416963e-06, "loss": 0.5324, "step": 344 }, { "epoch": 0.85, "learning_rate": 8.56272219400711e-06, "loss": 0.5331, "step": 345 }, { "epoch": 0.85, "learning_rate": 8.557643473844593e-06, "loss": 0.5159, "step": 346 }, { "epoch": 0.85, "learning_rate": 8.552564753682073e-06, "loss": 0.5543, "step": 347 }, { "epoch": 0.86, "learning_rate": 8.547486033519554e-06, "loss": 0.5442, "step": 348 }, { "epoch": 0.86, "learning_rate": 8.542407313357036e-06, "loss": 0.5396, "step": 349 }, { "epoch": 0.86, "learning_rate": 8.537328593194515e-06, "loss": 0.5142, "step": 350 }, { "epoch": 0.86, "learning_rate": 8.532249873031997e-06, "loss": 0.5375, "step": 351 }, { "epoch": 0.87, "learning_rate": 8.527171152869478e-06, "loss": 0.5675, "step": 352 }, { "epoch": 0.87, "learning_rate": 8.522092432706958e-06, "loss": 0.5076, "step": 353 }, { "epoch": 0.87, "learning_rate": 8.51701371254444e-06, "loss": 0.5369, "step": 354 }, { "epoch": 0.87, "learning_rate": 8.511934992381921e-06, "loss": 0.5466, "step": 355 }, { "epoch": 0.88, "learning_rate": 8.506856272219402e-06, "loss": 0.5409, "step": 356 }, { "epoch": 0.88, "learning_rate": 8.501777552056882e-06, "loss": 0.5266, "step": 357 }, { "epoch": 0.88, "learning_rate": 8.496698831894363e-06, "loss": 0.5442, "step": 358 }, { "epoch": 0.88, "learning_rate": 8.491620111731845e-06, "loss": 0.5317, "step": 359 }, { "epoch": 0.89, "learning_rate": 8.486541391569325e-06, "loss": 0.5311, "step": 360 }, { "epoch": 0.89, "learning_rate": 8.481462671406806e-06, "loss": 0.5338, "step": 361 }, { "epoch": 0.89, "learning_rate": 8.476383951244287e-06, "loss": 0.5515, "step": 362 }, { "epoch": 0.89, "learning_rate": 8.471305231081767e-06, "loss": 0.5356, "step": 363 }, { "epoch": 0.9, "learning_rate": 8.466226510919249e-06, "loss": 0.54, "step": 364 }, { "epoch": 0.9, "learning_rate": 8.46114779075673e-06, "loss": 0.5327, "step": 365 }, { "epoch": 0.9, "learning_rate": 8.45606907059421e-06, "loss": 0.5334, "step": 366 }, { "epoch": 0.9, "learning_rate": 8.450990350431691e-06, "loss": 0.4738, "step": 367 }, { "epoch": 0.91, "learning_rate": 8.445911630269173e-06, "loss": 0.54, "step": 368 }, { "epoch": 0.91, "learning_rate": 8.440832910106654e-06, "loss": 0.524, "step": 369 }, { "epoch": 0.91, "learning_rate": 8.435754189944135e-06, "loss": 0.5212, "step": 370 }, { "epoch": 0.91, "learning_rate": 8.430675469781617e-06, "loss": 0.5559, "step": 371 }, { "epoch": 0.92, "learning_rate": 8.425596749619097e-06, "loss": 0.5518, "step": 372 }, { "epoch": 0.92, "learning_rate": 8.420518029456578e-06, "loss": 0.5476, "step": 373 }, { "epoch": 0.92, "learning_rate": 8.41543930929406e-06, "loss": 0.5239, "step": 374 }, { "epoch": 0.92, "learning_rate": 8.41036058913154e-06, "loss": 0.561, "step": 375 }, { "epoch": 0.93, "learning_rate": 8.40528186896902e-06, "loss": 0.5459, "step": 376 }, { "epoch": 0.93, "learning_rate": 8.400203148806502e-06, "loss": 0.5186, "step": 377 }, { "epoch": 0.93, "learning_rate": 8.395124428643982e-06, "loss": 0.5393, "step": 378 }, { "epoch": 0.93, "learning_rate": 8.390045708481463e-06, "loss": 0.5266, "step": 379 }, { "epoch": 0.94, "learning_rate": 8.384966988318945e-06, "loss": 0.574, "step": 380 }, { "epoch": 0.94, "learning_rate": 8.379888268156426e-06, "loss": 0.5413, "step": 381 }, { "epoch": 0.94, "learning_rate": 8.374809547993906e-06, "loss": 0.5287, "step": 382 }, { "epoch": 0.94, "learning_rate": 8.369730827831387e-06, "loss": 0.5395, "step": 383 }, { "epoch": 0.95, "learning_rate": 8.364652107668869e-06, "loss": 0.5498, "step": 384 }, { "epoch": 0.95, "learning_rate": 8.359573387506348e-06, "loss": 0.543, "step": 385 }, { "epoch": 0.95, "learning_rate": 8.35449466734383e-06, "loss": 0.5403, "step": 386 }, { "epoch": 0.95, "learning_rate": 8.349415947181311e-06, "loss": 0.5392, "step": 387 }, { "epoch": 0.95, "learning_rate": 8.344337227018791e-06, "loss": 0.5498, "step": 388 }, { "epoch": 0.96, "learning_rate": 8.339258506856272e-06, "loss": 0.5127, "step": 389 }, { "epoch": 0.96, "learning_rate": 8.334179786693754e-06, "loss": 0.5354, "step": 390 }, { "epoch": 0.96, "learning_rate": 8.329101066531235e-06, "loss": 0.5209, "step": 391 }, { "epoch": 0.96, "learning_rate": 8.324022346368715e-06, "loss": 0.5334, "step": 392 }, { "epoch": 0.97, "learning_rate": 8.318943626206196e-06, "loss": 0.5315, "step": 393 }, { "epoch": 0.97, "learning_rate": 8.313864906043678e-06, "loss": 0.5068, "step": 394 }, { "epoch": 0.97, "learning_rate": 8.30878618588116e-06, "loss": 0.5254, "step": 395 }, { "epoch": 0.97, "learning_rate": 8.30370746571864e-06, "loss": 0.53, "step": 396 }, { "epoch": 0.98, "learning_rate": 8.29862874555612e-06, "loss": 0.5315, "step": 397 }, { "epoch": 0.98, "learning_rate": 8.293550025393602e-06, "loss": 0.5256, "step": 398 }, { "epoch": 0.98, "learning_rate": 8.288471305231083e-06, "loss": 0.5298, "step": 399 }, { "epoch": 0.98, "learning_rate": 8.283392585068563e-06, "loss": 0.5323, "step": 400 }, { "epoch": 0.99, "learning_rate": 8.278313864906044e-06, "loss": 0.4944, "step": 401 }, { "epoch": 0.99, "learning_rate": 8.273235144743526e-06, "loss": 0.5498, "step": 402 }, { "epoch": 0.99, "learning_rate": 8.268156424581007e-06, "loss": 0.5311, "step": 403 }, { "epoch": 0.99, "learning_rate": 8.263077704418487e-06, "loss": 0.5149, "step": 404 }, { "epoch": 1.0, "learning_rate": 8.257998984255968e-06, "loss": 0.5405, "step": 405 }, { "epoch": 1.0, "learning_rate": 8.25292026409345e-06, "loss": 0.5111, "step": 406 }, { "epoch": 1.0, "learning_rate": 8.24784154393093e-06, "loss": 0.4396, "step": 407 }, { "epoch": 1.0, "learning_rate": 8.242762823768411e-06, "loss": 0.3816, "step": 408 }, { "epoch": 1.01, "learning_rate": 8.237684103605892e-06, "loss": 0.3892, "step": 409 }, { "epoch": 1.01, "learning_rate": 8.232605383443372e-06, "loss": 0.4032, "step": 410 }, { "epoch": 1.01, "learning_rate": 8.227526663280854e-06, "loss": 0.4125, "step": 411 }, { "epoch": 1.01, "learning_rate": 8.222447943118335e-06, "loss": 0.4134, "step": 412 }, { "epoch": 1.02, "learning_rate": 8.217369222955815e-06, "loss": 0.3825, "step": 413 }, { "epoch": 1.02, "learning_rate": 8.212290502793296e-06, "loss": 0.395, "step": 414 }, { "epoch": 1.02, "learning_rate": 8.207211782630778e-06, "loss": 0.393, "step": 415 }, { "epoch": 1.02, "learning_rate": 8.202133062468259e-06, "loss": 0.3814, "step": 416 }, { "epoch": 1.03, "learning_rate": 8.197054342305739e-06, "loss": 0.3756, "step": 417 }, { "epoch": 1.03, "learning_rate": 8.19197562214322e-06, "loss": 0.3883, "step": 418 }, { "epoch": 1.03, "learning_rate": 8.186896901980702e-06, "loss": 0.4073, "step": 419 }, { "epoch": 1.03, "learning_rate": 8.181818181818183e-06, "loss": 0.4003, "step": 420 }, { "epoch": 1.04, "learning_rate": 8.176739461655664e-06, "loss": 0.392, "step": 421 }, { "epoch": 1.04, "learning_rate": 8.171660741493144e-06, "loss": 0.4158, "step": 422 }, { "epoch": 1.04, "learning_rate": 8.166582021330626e-06, "loss": 0.3905, "step": 423 }, { "epoch": 1.04, "learning_rate": 8.161503301168107e-06, "loss": 0.4089, "step": 424 }, { "epoch": 1.05, "learning_rate": 8.156424581005588e-06, "loss": 0.394, "step": 425 }, { "epoch": 1.05, "learning_rate": 8.151345860843068e-06, "loss": 0.3882, "step": 426 }, { "epoch": 1.05, "learning_rate": 8.14626714068055e-06, "loss": 0.39, "step": 427 }, { "epoch": 1.05, "learning_rate": 8.141188420518031e-06, "loss": 0.3793, "step": 428 }, { "epoch": 1.06, "learning_rate": 8.13610970035551e-06, "loss": 0.4081, "step": 429 }, { "epoch": 1.06, "learning_rate": 8.131030980192992e-06, "loss": 0.405, "step": 430 }, { "epoch": 1.06, "learning_rate": 8.125952260030474e-06, "loss": 0.4111, "step": 431 }, { "epoch": 1.06, "learning_rate": 8.120873539867953e-06, "loss": 0.3789, "step": 432 }, { "epoch": 1.07, "learning_rate": 8.115794819705435e-06, "loss": 0.404, "step": 433 }, { "epoch": 1.07, "learning_rate": 8.110716099542916e-06, "loss": 0.3955, "step": 434 }, { "epoch": 1.07, "learning_rate": 8.105637379380396e-06, "loss": 0.4075, "step": 435 }, { "epoch": 1.07, "learning_rate": 8.100558659217877e-06, "loss": 0.3859, "step": 436 }, { "epoch": 1.08, "learning_rate": 8.095479939055359e-06, "loss": 0.4091, "step": 437 }, { "epoch": 1.08, "learning_rate": 8.09040121889284e-06, "loss": 0.3853, "step": 438 }, { "epoch": 1.08, "learning_rate": 8.08532249873032e-06, "loss": 0.3964, "step": 439 }, { "epoch": 1.08, "learning_rate": 8.080243778567801e-06, "loss": 0.4037, "step": 440 }, { "epoch": 1.09, "learning_rate": 8.075165058405283e-06, "loss": 0.3971, "step": 441 }, { "epoch": 1.09, "learning_rate": 8.070086338242762e-06, "loss": 0.3836, "step": 442 }, { "epoch": 1.09, "learning_rate": 8.065007618080244e-06, "loss": 0.3749, "step": 443 }, { "epoch": 1.09, "learning_rate": 8.059928897917725e-06, "loss": 0.3965, "step": 444 }, { "epoch": 1.1, "learning_rate": 8.054850177755207e-06, "loss": 0.3838, "step": 445 }, { "epoch": 1.1, "learning_rate": 8.049771457592688e-06, "loss": 0.4052, "step": 446 }, { "epoch": 1.1, "learning_rate": 8.044692737430168e-06, "loss": 0.4281, "step": 447 }, { "epoch": 1.1, "learning_rate": 8.03961401726765e-06, "loss": 0.3732, "step": 448 }, { "epoch": 1.11, "learning_rate": 8.03453529710513e-06, "loss": 0.3821, "step": 449 }, { "epoch": 1.11, "learning_rate": 8.029456576942612e-06, "loss": 0.3883, "step": 450 }, { "epoch": 1.11, "learning_rate": 8.024377856780092e-06, "loss": 0.394, "step": 451 }, { "epoch": 1.11, "learning_rate": 8.019299136617573e-06, "loss": 0.3881, "step": 452 }, { "epoch": 1.11, "learning_rate": 8.014220416455055e-06, "loss": 0.3979, "step": 453 }, { "epoch": 1.12, "learning_rate": 8.009141696292534e-06, "loss": 0.4141, "step": 454 }, { "epoch": 1.12, "learning_rate": 8.004062976130016e-06, "loss": 0.4113, "step": 455 }, { "epoch": 1.12, "learning_rate": 7.998984255967497e-06, "loss": 0.3937, "step": 456 }, { "epoch": 1.12, "learning_rate": 7.993905535804977e-06, "loss": 0.3972, "step": 457 }, { "epoch": 1.13, "learning_rate": 7.988826815642458e-06, "loss": 0.3849, "step": 458 }, { "epoch": 1.13, "learning_rate": 7.98374809547994e-06, "loss": 0.3975, "step": 459 }, { "epoch": 1.13, "learning_rate": 7.978669375317421e-06, "loss": 0.3683, "step": 460 }, { "epoch": 1.13, "learning_rate": 7.973590655154901e-06, "loss": 0.3948, "step": 461 }, { "epoch": 1.14, "learning_rate": 7.968511934992382e-06, "loss": 0.3977, "step": 462 }, { "epoch": 1.14, "learning_rate": 7.963433214829864e-06, "loss": 0.4074, "step": 463 }, { "epoch": 1.14, "learning_rate": 7.958354494667344e-06, "loss": 0.4055, "step": 464 }, { "epoch": 1.14, "learning_rate": 7.953275774504825e-06, "loss": 0.3895, "step": 465 }, { "epoch": 1.15, "learning_rate": 7.948197054342306e-06, "loss": 0.384, "step": 466 }, { "epoch": 1.15, "learning_rate": 7.943118334179786e-06, "loss": 0.402, "step": 467 }, { "epoch": 1.15, "learning_rate": 7.938039614017268e-06, "loss": 0.3963, "step": 468 }, { "epoch": 1.15, "learning_rate": 7.932960893854749e-06, "loss": 0.3947, "step": 469 }, { "epoch": 1.16, "learning_rate": 7.92788217369223e-06, "loss": 0.3777, "step": 470 }, { "epoch": 1.16, "learning_rate": 7.922803453529712e-06, "loss": 0.4022, "step": 471 }, { "epoch": 1.16, "learning_rate": 7.917724733367193e-06, "loss": 0.3766, "step": 472 }, { "epoch": 1.16, "learning_rate": 7.912646013204673e-06, "loss": 0.3925, "step": 473 }, { "epoch": 1.17, "learning_rate": 7.907567293042154e-06, "loss": 0.407, "step": 474 }, { "epoch": 1.17, "learning_rate": 7.902488572879636e-06, "loss": 0.3795, "step": 475 }, { "epoch": 1.17, "learning_rate": 7.897409852717116e-06, "loss": 0.3761, "step": 476 }, { "epoch": 1.17, "learning_rate": 7.892331132554597e-06, "loss": 0.3627, "step": 477 }, { "epoch": 1.18, "learning_rate": 7.887252412392078e-06, "loss": 0.4025, "step": 478 }, { "epoch": 1.18, "learning_rate": 7.882173692229558e-06, "loss": 0.3978, "step": 479 }, { "epoch": 1.18, "learning_rate": 7.87709497206704e-06, "loss": 0.4004, "step": 480 }, { "epoch": 1.18, "learning_rate": 7.872016251904521e-06, "loss": 0.4032, "step": 481 }, { "epoch": 1.19, "learning_rate": 7.866937531742e-06, "loss": 0.3979, "step": 482 }, { "epoch": 1.19, "learning_rate": 7.861858811579482e-06, "loss": 0.3814, "step": 483 }, { "epoch": 1.19, "learning_rate": 7.856780091416964e-06, "loss": 0.4033, "step": 484 }, { "epoch": 1.19, "learning_rate": 7.851701371254445e-06, "loss": 0.4031, "step": 485 }, { "epoch": 1.2, "learning_rate": 7.846622651091925e-06, "loss": 0.3942, "step": 486 }, { "epoch": 1.2, "learning_rate": 7.841543930929406e-06, "loss": 0.3956, "step": 487 }, { "epoch": 1.2, "learning_rate": 7.836465210766888e-06, "loss": 0.3967, "step": 488 }, { "epoch": 1.2, "learning_rate": 7.831386490604367e-06, "loss": 0.4205, "step": 489 }, { "epoch": 1.21, "learning_rate": 7.826307770441849e-06, "loss": 0.399, "step": 490 }, { "epoch": 1.21, "learning_rate": 7.82122905027933e-06, "loss": 0.4096, "step": 491 }, { "epoch": 1.21, "learning_rate": 7.81615033011681e-06, "loss": 0.3968, "step": 492 }, { "epoch": 1.21, "learning_rate": 7.811071609954293e-06, "loss": 0.3874, "step": 493 }, { "epoch": 1.22, "learning_rate": 7.805992889791774e-06, "loss": 0.3917, "step": 494 }, { "epoch": 1.22, "learning_rate": 7.800914169629254e-06, "loss": 0.4003, "step": 495 }, { "epoch": 1.22, "learning_rate": 7.795835449466736e-06, "loss": 0.4142, "step": 496 }, { "epoch": 1.22, "learning_rate": 7.790756729304217e-06, "loss": 0.3964, "step": 497 }, { "epoch": 1.23, "learning_rate": 7.785678009141697e-06, "loss": 0.4104, "step": 498 }, { "epoch": 1.23, "learning_rate": 7.780599288979178e-06, "loss": 0.4102, "step": 499 }, { "epoch": 1.23, "learning_rate": 7.77552056881666e-06, "loss": 0.4037, "step": 500 }, { "epoch": 1.23, "learning_rate": 7.77044184865414e-06, "loss": 0.4176, "step": 501 }, { "epoch": 1.24, "learning_rate": 7.76536312849162e-06, "loss": 0.4097, "step": 502 }, { "epoch": 1.24, "learning_rate": 7.760284408329102e-06, "loss": 0.3883, "step": 503 }, { "epoch": 1.24, "learning_rate": 7.755205688166582e-06, "loss": 0.4085, "step": 504 }, { "epoch": 1.24, "learning_rate": 7.750126968004063e-06, "loss": 0.3932, "step": 505 }, { "epoch": 1.25, "learning_rate": 7.745048247841545e-06, "loss": 0.4039, "step": 506 }, { "epoch": 1.25, "learning_rate": 7.739969527679026e-06, "loss": 0.3993, "step": 507 }, { "epoch": 1.25, "learning_rate": 7.734890807516506e-06, "loss": 0.4074, "step": 508 }, { "epoch": 1.25, "learning_rate": 7.729812087353987e-06, "loss": 0.4274, "step": 509 }, { "epoch": 1.26, "learning_rate": 7.724733367191469e-06, "loss": 0.3943, "step": 510 }, { "epoch": 1.26, "learning_rate": 7.719654647028949e-06, "loss": 0.4115, "step": 511 }, { "epoch": 1.26, "learning_rate": 7.71457592686643e-06, "loss": 0.403, "step": 512 }, { "epoch": 1.26, "learning_rate": 7.709497206703911e-06, "loss": 0.3815, "step": 513 }, { "epoch": 1.27, "learning_rate": 7.704418486541391e-06, "loss": 0.3973, "step": 514 }, { "epoch": 1.27, "learning_rate": 7.699339766378873e-06, "loss": 0.4109, "step": 515 }, { "epoch": 1.27, "learning_rate": 7.694261046216354e-06, "loss": 0.3958, "step": 516 }, { "epoch": 1.27, "learning_rate": 7.689182326053835e-06, "loss": 0.3944, "step": 517 }, { "epoch": 1.27, "learning_rate": 7.684103605891317e-06, "loss": 0.3924, "step": 518 }, { "epoch": 1.28, "learning_rate": 7.679024885728798e-06, "loss": 0.3916, "step": 519 }, { "epoch": 1.28, "learning_rate": 7.673946165566278e-06, "loss": 0.4175, "step": 520 }, { "epoch": 1.28, "learning_rate": 7.66886744540376e-06, "loss": 0.4123, "step": 521 }, { "epoch": 1.28, "learning_rate": 7.66378872524124e-06, "loss": 0.3993, "step": 522 }, { "epoch": 1.29, "learning_rate": 7.65871000507872e-06, "loss": 0.4006, "step": 523 }, { "epoch": 1.29, "learning_rate": 7.653631284916202e-06, "loss": 0.3907, "step": 524 }, { "epoch": 1.29, "learning_rate": 7.648552564753683e-06, "loss": 0.3958, "step": 525 }, { "epoch": 1.29, "learning_rate": 7.643473844591163e-06, "loss": 0.4081, "step": 526 }, { "epoch": 1.3, "learning_rate": 7.638395124428645e-06, "loss": 0.4031, "step": 527 }, { "epoch": 1.3, "learning_rate": 7.633316404266126e-06, "loss": 0.3824, "step": 528 }, { "epoch": 1.3, "learning_rate": 7.6282376841036065e-06, "loss": 0.4124, "step": 529 }, { "epoch": 1.3, "learning_rate": 7.623158963941087e-06, "loss": 0.3909, "step": 530 }, { "epoch": 1.31, "learning_rate": 7.6180802437785685e-06, "loss": 0.4019, "step": 531 }, { "epoch": 1.31, "learning_rate": 7.613001523616049e-06, "loss": 0.4138, "step": 532 }, { "epoch": 1.31, "learning_rate": 7.6079228034535305e-06, "loss": 0.3998, "step": 533 }, { "epoch": 1.31, "learning_rate": 7.602844083291011e-06, "loss": 0.4033, "step": 534 }, { "epoch": 1.32, "learning_rate": 7.597765363128492e-06, "loss": 0.3855, "step": 535 }, { "epoch": 1.32, "learning_rate": 7.592686642965973e-06, "loss": 0.4134, "step": 536 }, { "epoch": 1.32, "learning_rate": 7.587607922803454e-06, "loss": 0.4203, "step": 537 }, { "epoch": 1.32, "learning_rate": 7.582529202640935e-06, "loss": 0.3959, "step": 538 }, { "epoch": 1.33, "learning_rate": 7.577450482478416e-06, "loss": 0.3971, "step": 539 }, { "epoch": 1.33, "learning_rate": 7.572371762315896e-06, "loss": 0.3931, "step": 540 }, { "epoch": 1.33, "learning_rate": 7.567293042153378e-06, "loss": 0.4029, "step": 541 }, { "epoch": 1.33, "learning_rate": 7.562214321990859e-06, "loss": 0.3986, "step": 542 }, { "epoch": 1.34, "learning_rate": 7.5571356018283405e-06, "loss": 0.3874, "step": 543 }, { "epoch": 1.34, "learning_rate": 7.552056881665821e-06, "loss": 0.394, "step": 544 }, { "epoch": 1.34, "learning_rate": 7.5469781615033025e-06, "loss": 0.3887, "step": 545 }, { "epoch": 1.34, "learning_rate": 7.541899441340783e-06, "loss": 0.3835, "step": 546 }, { "epoch": 1.35, "learning_rate": 7.536820721178264e-06, "loss": 0.4003, "step": 547 }, { "epoch": 1.35, "learning_rate": 7.531742001015745e-06, "loss": 0.4026, "step": 548 }, { "epoch": 1.35, "learning_rate": 7.526663280853226e-06, "loss": 0.4155, "step": 549 }, { "epoch": 1.35, "learning_rate": 7.521584560690707e-06, "loss": 0.4188, "step": 550 }, { "epoch": 1.36, "learning_rate": 7.516505840528188e-06, "loss": 0.4129, "step": 551 }, { "epoch": 1.36, "learning_rate": 7.511427120365668e-06, "loss": 0.3958, "step": 552 }, { "epoch": 1.36, "learning_rate": 7.50634840020315e-06, "loss": 0.3993, "step": 553 }, { "epoch": 1.36, "learning_rate": 7.50126968004063e-06, "loss": 0.4051, "step": 554 }, { "epoch": 1.37, "learning_rate": 7.496190959878112e-06, "loss": 0.3795, "step": 555 }, { "epoch": 1.37, "learning_rate": 7.491112239715592e-06, "loss": 0.4025, "step": 556 }, { "epoch": 1.37, "learning_rate": 7.486033519553073e-06, "loss": 0.4097, "step": 557 }, { "epoch": 1.37, "learning_rate": 7.480954799390554e-06, "loss": 0.4129, "step": 558 }, { "epoch": 1.38, "learning_rate": 7.475876079228035e-06, "loss": 0.3997, "step": 559 }, { "epoch": 1.38, "learning_rate": 7.470797359065516e-06, "loss": 0.4184, "step": 560 }, { "epoch": 1.38, "learning_rate": 7.465718638902997e-06, "loss": 0.3793, "step": 561 }, { "epoch": 1.38, "learning_rate": 7.460639918740477e-06, "loss": 0.4025, "step": 562 }, { "epoch": 1.39, "learning_rate": 7.455561198577959e-06, "loss": 0.4073, "step": 563 }, { "epoch": 1.39, "learning_rate": 7.450482478415439e-06, "loss": 0.3952, "step": 564 }, { "epoch": 1.39, "learning_rate": 7.44540375825292e-06, "loss": 0.3952, "step": 565 }, { "epoch": 1.39, "learning_rate": 7.440325038090401e-06, "loss": 0.4047, "step": 566 }, { "epoch": 1.4, "learning_rate": 7.435246317927884e-06, "loss": 0.3955, "step": 567 }, { "epoch": 1.4, "learning_rate": 7.430167597765364e-06, "loss": 0.4025, "step": 568 }, { "epoch": 1.4, "learning_rate": 7.425088877602845e-06, "loss": 0.3759, "step": 569 }, { "epoch": 1.4, "learning_rate": 7.420010157440326e-06, "loss": 0.4213, "step": 570 }, { "epoch": 1.41, "learning_rate": 7.414931437277807e-06, "loss": 0.3966, "step": 571 }, { "epoch": 1.41, "learning_rate": 7.409852717115288e-06, "loss": 0.4049, "step": 572 }, { "epoch": 1.41, "learning_rate": 7.404773996952769e-06, "loss": 0.3917, "step": 573 }, { "epoch": 1.41, "learning_rate": 7.399695276790249e-06, "loss": 0.405, "step": 574 }, { "epoch": 1.42, "learning_rate": 7.394616556627731e-06, "loss": 0.38, "step": 575 }, { "epoch": 1.42, "learning_rate": 7.3895378364652114e-06, "loss": 0.4071, "step": 576 }, { "epoch": 1.42, "learning_rate": 7.384459116302692e-06, "loss": 0.3789, "step": 577 }, { "epoch": 1.42, "learning_rate": 7.3793803961401734e-06, "loss": 0.3873, "step": 578 }, { "epoch": 1.43, "learning_rate": 7.374301675977654e-06, "loss": 0.4101, "step": 579 }, { "epoch": 1.43, "learning_rate": 7.3692229558151354e-06, "loss": 0.4027, "step": 580 }, { "epoch": 1.43, "learning_rate": 7.364144235652616e-06, "loss": 0.4192, "step": 581 }, { "epoch": 1.43, "learning_rate": 7.359065515490097e-06, "loss": 0.4005, "step": 582 }, { "epoch": 1.43, "learning_rate": 7.353986795327578e-06, "loss": 0.4091, "step": 583 }, { "epoch": 1.44, "learning_rate": 7.348908075165059e-06, "loss": 0.4028, "step": 584 }, { "epoch": 1.44, "learning_rate": 7.34382935500254e-06, "loss": 0.4029, "step": 585 }, { "epoch": 1.44, "learning_rate": 7.338750634840021e-06, "loss": 0.3858, "step": 586 }, { "epoch": 1.44, "learning_rate": 7.333671914677501e-06, "loss": 0.3922, "step": 587 }, { "epoch": 1.45, "learning_rate": 7.328593194514983e-06, "loss": 0.4, "step": 588 }, { "epoch": 1.45, "learning_rate": 7.323514474352463e-06, "loss": 0.3946, "step": 589 }, { "epoch": 1.45, "learning_rate": 7.318435754189945e-06, "loss": 0.3916, "step": 590 }, { "epoch": 1.45, "learning_rate": 7.313357034027425e-06, "loss": 0.4027, "step": 591 }, { "epoch": 1.46, "learning_rate": 7.3082783138649074e-06, "loss": 0.3789, "step": 592 }, { "epoch": 1.46, "learning_rate": 7.303199593702388e-06, "loss": 0.3888, "step": 593 }, { "epoch": 1.46, "learning_rate": 7.298120873539869e-06, "loss": 0.3859, "step": 594 }, { "epoch": 1.46, "learning_rate": 7.29304215337735e-06, "loss": 0.4115, "step": 595 }, { "epoch": 1.47, "learning_rate": 7.287963433214831e-06, "loss": 0.3963, "step": 596 }, { "epoch": 1.47, "learning_rate": 7.282884713052312e-06, "loss": 0.4117, "step": 597 }, { "epoch": 1.47, "learning_rate": 7.277805992889793e-06, "loss": 0.4186, "step": 598 }, { "epoch": 1.47, "learning_rate": 7.272727272727273e-06, "loss": 0.4099, "step": 599 }, { "epoch": 1.48, "learning_rate": 7.267648552564755e-06, "loss": 0.4133, "step": 600 }, { "epoch": 1.48, "learning_rate": 7.262569832402235e-06, "loss": 0.365, "step": 601 }, { "epoch": 1.48, "learning_rate": 7.257491112239717e-06, "loss": 0.4165, "step": 602 }, { "epoch": 1.48, "learning_rate": 7.252412392077197e-06, "loss": 0.3965, "step": 603 }, { "epoch": 1.49, "learning_rate": 7.247333671914678e-06, "loss": 0.3933, "step": 604 }, { "epoch": 1.49, "learning_rate": 7.242254951752159e-06, "loss": 0.4204, "step": 605 }, { "epoch": 1.49, "learning_rate": 7.23717623158964e-06, "loss": 0.4124, "step": 606 }, { "epoch": 1.49, "learning_rate": 7.232097511427121e-06, "loss": 0.3963, "step": 607 }, { "epoch": 1.5, "learning_rate": 7.227018791264602e-06, "loss": 0.4082, "step": 608 }, { "epoch": 1.5, "learning_rate": 7.221940071102082e-06, "loss": 0.3845, "step": 609 }, { "epoch": 1.5, "learning_rate": 7.216861350939564e-06, "loss": 0.4309, "step": 610 }, { "epoch": 1.5, "learning_rate": 7.211782630777044e-06, "loss": 0.4171, "step": 611 }, { "epoch": 1.51, "learning_rate": 7.206703910614526e-06, "loss": 0.3996, "step": 612 }, { "epoch": 1.51, "learning_rate": 7.201625190452006e-06, "loss": 0.4138, "step": 613 }, { "epoch": 1.51, "learning_rate": 7.196546470289487e-06, "loss": 0.4076, "step": 614 }, { "epoch": 1.51, "learning_rate": 7.191467750126968e-06, "loss": 0.3848, "step": 615 }, { "epoch": 1.52, "learning_rate": 7.18638902996445e-06, "loss": 0.4123, "step": 616 }, { "epoch": 1.52, "learning_rate": 7.181310309801931e-06, "loss": 0.3887, "step": 617 }, { "epoch": 1.52, "learning_rate": 7.176231589639412e-06, "loss": 0.4092, "step": 618 }, { "epoch": 1.52, "learning_rate": 7.171152869476893e-06, "loss": 0.3847, "step": 619 }, { "epoch": 1.53, "learning_rate": 7.166074149314374e-06, "loss": 0.4103, "step": 620 }, { "epoch": 1.53, "learning_rate": 7.160995429151854e-06, "loss": 0.3927, "step": 621 }, { "epoch": 1.53, "learning_rate": 7.155916708989336e-06, "loss": 0.3833, "step": 622 }, { "epoch": 1.53, "learning_rate": 7.150837988826816e-06, "loss": 0.3894, "step": 623 }, { "epoch": 1.54, "learning_rate": 7.145759268664298e-06, "loss": 0.4077, "step": 624 }, { "epoch": 1.54, "learning_rate": 7.140680548501778e-06, "loss": 0.4026, "step": 625 }, { "epoch": 1.54, "learning_rate": 7.135601828339259e-06, "loss": 0.4097, "step": 626 }, { "epoch": 1.54, "learning_rate": 7.13052310817674e-06, "loss": 0.3809, "step": 627 }, { "epoch": 1.55, "learning_rate": 7.125444388014221e-06, "loss": 0.4229, "step": 628 }, { "epoch": 1.55, "learning_rate": 7.1203656678517015e-06, "loss": 0.3981, "step": 629 }, { "epoch": 1.55, "learning_rate": 7.115286947689183e-06, "loss": 0.4156, "step": 630 }, { "epoch": 1.55, "learning_rate": 7.1102082275266635e-06, "loss": 0.4075, "step": 631 }, { "epoch": 1.56, "learning_rate": 7.105129507364145e-06, "loss": 0.4094, "step": 632 }, { "epoch": 1.56, "learning_rate": 7.1000507872016255e-06, "loss": 0.3847, "step": 633 }, { "epoch": 1.56, "learning_rate": 7.094972067039106e-06, "loss": 0.3969, "step": 634 }, { "epoch": 1.56, "learning_rate": 7.0898933468765875e-06, "loss": 0.4027, "step": 635 }, { "epoch": 1.57, "learning_rate": 7.084814626714068e-06, "loss": 0.4182, "step": 636 }, { "epoch": 1.57, "learning_rate": 7.0797359065515495e-06, "loss": 0.4007, "step": 637 }, { "epoch": 1.57, "learning_rate": 7.07465718638903e-06, "loss": 0.3938, "step": 638 }, { "epoch": 1.57, "learning_rate": 7.069578466226511e-06, "loss": 0.4158, "step": 639 }, { "epoch": 1.58, "learning_rate": 7.064499746063992e-06, "loss": 0.4165, "step": 640 }, { "epoch": 1.58, "learning_rate": 7.059421025901474e-06, "loss": 0.4231, "step": 641 }, { "epoch": 1.58, "learning_rate": 7.054342305738955e-06, "loss": 0.4078, "step": 642 }, { "epoch": 1.58, "learning_rate": 7.0492635855764355e-06, "loss": 0.4098, "step": 643 }, { "epoch": 1.58, "learning_rate": 7.044184865413917e-06, "loss": 0.3986, "step": 644 }, { "epoch": 1.59, "learning_rate": 7.0391061452513975e-06, "loss": 0.3976, "step": 645 }, { "epoch": 1.59, "learning_rate": 7.034027425088878e-06, "loss": 0.3831, "step": 646 }, { "epoch": 1.59, "learning_rate": 7.0289487049263595e-06, "loss": 0.4123, "step": 647 }, { "epoch": 1.59, "learning_rate": 7.02386998476384e-06, "loss": 0.3991, "step": 648 }, { "epoch": 1.6, "learning_rate": 7.0187912646013215e-06, "loss": 0.3864, "step": 649 }, { "epoch": 1.6, "learning_rate": 7.013712544438802e-06, "loss": 0.3881, "step": 650 }, { "epoch": 1.6, "learning_rate": 7.008633824276283e-06, "loss": 0.3991, "step": 651 }, { "epoch": 1.6, "learning_rate": 7.003555104113764e-06, "loss": 0.3972, "step": 652 }, { "epoch": 1.61, "learning_rate": 6.998476383951245e-06, "loss": 0.3911, "step": 653 }, { "epoch": 1.61, "learning_rate": 6.993397663788726e-06, "loss": 0.3975, "step": 654 }, { "epoch": 1.61, "learning_rate": 6.988318943626207e-06, "loss": 0.4197, "step": 655 }, { "epoch": 1.61, "learning_rate": 6.983240223463687e-06, "loss": 0.3989, "step": 656 }, { "epoch": 1.62, "learning_rate": 6.978161503301169e-06, "loss": 0.3765, "step": 657 }, { "epoch": 1.62, "learning_rate": 6.973082783138649e-06, "loss": 0.3824, "step": 658 }, { "epoch": 1.62, "learning_rate": 6.968004062976131e-06, "loss": 0.4021, "step": 659 }, { "epoch": 1.62, "learning_rate": 6.962925342813611e-06, "loss": 0.3913, "step": 660 }, { "epoch": 1.63, "learning_rate": 6.957846622651092e-06, "loss": 0.3818, "step": 661 }, { "epoch": 1.63, "learning_rate": 6.952767902488573e-06, "loss": 0.4133, "step": 662 }, { "epoch": 1.63, "learning_rate": 6.947689182326054e-06, "loss": 0.3922, "step": 663 }, { "epoch": 1.63, "learning_rate": 6.942610462163535e-06, "loss": 0.4069, "step": 664 }, { "epoch": 1.64, "learning_rate": 6.937531742001016e-06, "loss": 0.4073, "step": 665 }, { "epoch": 1.64, "learning_rate": 6.932453021838498e-06, "loss": 0.4152, "step": 666 }, { "epoch": 1.64, "learning_rate": 6.927374301675979e-06, "loss": 0.3989, "step": 667 }, { "epoch": 1.64, "learning_rate": 6.922295581513459e-06, "loss": 0.3955, "step": 668 }, { "epoch": 1.65, "learning_rate": 6.917216861350941e-06, "loss": 0.412, "step": 669 }, { "epoch": 1.65, "learning_rate": 6.912138141188421e-06, "loss": 0.4054, "step": 670 }, { "epoch": 1.65, "learning_rate": 6.907059421025903e-06, "loss": 0.4265, "step": 671 }, { "epoch": 1.65, "learning_rate": 6.901980700863383e-06, "loss": 0.4129, "step": 672 }, { "epoch": 1.66, "learning_rate": 6.896901980700864e-06, "loss": 0.3943, "step": 673 }, { "epoch": 1.66, "learning_rate": 6.891823260538345e-06, "loss": 0.3943, "step": 674 }, { "epoch": 1.66, "learning_rate": 6.886744540375826e-06, "loss": 0.4089, "step": 675 }, { "epoch": 1.66, "learning_rate": 6.881665820213307e-06, "loss": 0.4037, "step": 676 }, { "epoch": 1.67, "learning_rate": 6.876587100050788e-06, "loss": 0.4173, "step": 677 }, { "epoch": 1.67, "learning_rate": 6.871508379888268e-06, "loss": 0.4082, "step": 678 }, { "epoch": 1.67, "learning_rate": 6.86642965972575e-06, "loss": 0.4146, "step": 679 }, { "epoch": 1.67, "learning_rate": 6.86135093956323e-06, "loss": 0.3858, "step": 680 }, { "epoch": 1.68, "learning_rate": 6.856272219400712e-06, "loss": 0.3876, "step": 681 }, { "epoch": 1.68, "learning_rate": 6.851193499238192e-06, "loss": 0.4116, "step": 682 }, { "epoch": 1.68, "learning_rate": 6.846114779075673e-06, "loss": 0.41, "step": 683 }, { "epoch": 1.68, "learning_rate": 6.841036058913154e-06, "loss": 0.4148, "step": 684 }, { "epoch": 1.69, "learning_rate": 6.835957338750635e-06, "loss": 0.3927, "step": 685 }, { "epoch": 1.69, "learning_rate": 6.8308786185881156e-06, "loss": 0.3993, "step": 686 }, { "epoch": 1.69, "learning_rate": 6.825799898425597e-06, "loss": 0.3994, "step": 687 }, { "epoch": 1.69, "learning_rate": 6.8207211782630776e-06, "loss": 0.4042, "step": 688 }, { "epoch": 1.7, "learning_rate": 6.815642458100559e-06, "loss": 0.3799, "step": 689 }, { "epoch": 1.7, "learning_rate": 6.81056373793804e-06, "loss": 0.4014, "step": 690 }, { "epoch": 1.7, "learning_rate": 6.805485017775522e-06, "loss": 0.3889, "step": 691 }, { "epoch": 1.7, "learning_rate": 6.800406297613002e-06, "loss": 0.3934, "step": 692 }, { "epoch": 1.71, "learning_rate": 6.795327577450484e-06, "loss": 0.4055, "step": 693 }, { "epoch": 1.71, "learning_rate": 6.790248857287964e-06, "loss": 0.3939, "step": 694 }, { "epoch": 1.71, "learning_rate": 6.785170137125445e-06, "loss": 0.3963, "step": 695 }, { "epoch": 1.71, "learning_rate": 6.780091416962926e-06, "loss": 0.4053, "step": 696 }, { "epoch": 1.72, "learning_rate": 6.775012696800407e-06, "loss": 0.3968, "step": 697 }, { "epoch": 1.72, "learning_rate": 6.7699339766378876e-06, "loss": 0.379, "step": 698 }, { "epoch": 1.72, "learning_rate": 6.764855256475369e-06, "loss": 0.3786, "step": 699 }, { "epoch": 1.72, "learning_rate": 6.7597765363128496e-06, "loss": 0.4145, "step": 700 }, { "epoch": 1.73, "learning_rate": 6.754697816150331e-06, "loss": 0.4199, "step": 701 }, { "epoch": 1.73, "learning_rate": 6.7496190959878116e-06, "loss": 0.4059, "step": 702 }, { "epoch": 1.73, "learning_rate": 6.744540375825292e-06, "loss": 0.4179, "step": 703 }, { "epoch": 1.73, "learning_rate": 6.7394616556627736e-06, "loss": 0.4124, "step": 704 }, { "epoch": 1.74, "learning_rate": 6.734382935500254e-06, "loss": 0.3943, "step": 705 }, { "epoch": 1.74, "learning_rate": 6.729304215337736e-06, "loss": 0.4103, "step": 706 }, { "epoch": 1.74, "learning_rate": 6.724225495175216e-06, "loss": 0.3891, "step": 707 }, { "epoch": 1.74, "learning_rate": 6.719146775012697e-06, "loss": 0.409, "step": 708 }, { "epoch": 1.74, "learning_rate": 6.714068054850178e-06, "loss": 0.4119, "step": 709 }, { "epoch": 1.75, "learning_rate": 6.708989334687659e-06, "loss": 0.415, "step": 710 }, { "epoch": 1.75, "learning_rate": 6.70391061452514e-06, "loss": 0.3914, "step": 711 }, { "epoch": 1.75, "learning_rate": 6.698831894362621e-06, "loss": 0.4185, "step": 712 }, { "epoch": 1.75, "learning_rate": 6.693753174200101e-06, "loss": 0.4178, "step": 713 }, { "epoch": 1.76, "learning_rate": 6.688674454037583e-06, "loss": 0.4097, "step": 714 }, { "epoch": 1.76, "learning_rate": 6.683595733875064e-06, "loss": 0.4063, "step": 715 }, { "epoch": 1.76, "learning_rate": 6.678517013712546e-06, "loss": 0.4094, "step": 716 }, { "epoch": 1.76, "learning_rate": 6.673438293550026e-06, "loss": 0.3939, "step": 717 }, { "epoch": 1.77, "learning_rate": 6.668359573387508e-06, "loss": 0.4038, "step": 718 }, { "epoch": 1.77, "learning_rate": 6.663280853224988e-06, "loss": 0.3922, "step": 719 }, { "epoch": 1.77, "learning_rate": 6.658202133062469e-06, "loss": 0.3999, "step": 720 }, { "epoch": 1.77, "learning_rate": 6.65312341289995e-06, "loss": 0.4219, "step": 721 }, { "epoch": 1.78, "learning_rate": 6.648044692737431e-06, "loss": 0.4091, "step": 722 }, { "epoch": 1.78, "learning_rate": 6.642965972574912e-06, "loss": 0.4247, "step": 723 }, { "epoch": 1.78, "learning_rate": 6.637887252412393e-06, "loss": 0.3948, "step": 724 }, { "epoch": 1.78, "learning_rate": 6.632808532249873e-06, "loss": 0.3932, "step": 725 }, { "epoch": 1.79, "learning_rate": 6.627729812087355e-06, "loss": 0.4207, "step": 726 }, { "epoch": 1.79, "learning_rate": 6.622651091924835e-06, "loss": 0.3828, "step": 727 }, { "epoch": 1.79, "learning_rate": 6.617572371762317e-06, "loss": 0.395, "step": 728 }, { "epoch": 1.79, "learning_rate": 6.612493651599797e-06, "loss": 0.4057, "step": 729 }, { "epoch": 1.8, "learning_rate": 6.607414931437278e-06, "loss": 0.3963, "step": 730 }, { "epoch": 1.8, "learning_rate": 6.602336211274759e-06, "loss": 0.4128, "step": 731 }, { "epoch": 1.8, "learning_rate": 6.59725749111224e-06, "loss": 0.4065, "step": 732 }, { "epoch": 1.8, "learning_rate": 6.592178770949721e-06, "loss": 0.3902, "step": 733 }, { "epoch": 1.81, "learning_rate": 6.587100050787202e-06, "loss": 0.386, "step": 734 }, { "epoch": 1.81, "learning_rate": 6.5820213306246825e-06, "loss": 0.4182, "step": 735 }, { "epoch": 1.81, "learning_rate": 6.576942610462164e-06, "loss": 0.4194, "step": 736 }, { "epoch": 1.81, "learning_rate": 6.5718638902996445e-06, "loss": 0.3887, "step": 737 }, { "epoch": 1.82, "learning_rate": 6.566785170137125e-06, "loss": 0.4111, "step": 738 }, { "epoch": 1.82, "learning_rate": 6.561706449974607e-06, "loss": 0.4146, "step": 739 }, { "epoch": 1.82, "learning_rate": 6.556627729812089e-06, "loss": 0.412, "step": 740 }, { "epoch": 1.82, "learning_rate": 6.551549009649569e-06, "loss": 0.409, "step": 741 }, { "epoch": 1.83, "learning_rate": 6.54647028948705e-06, "loss": 0.3854, "step": 742 }, { "epoch": 1.83, "learning_rate": 6.541391569324531e-06, "loss": 0.4012, "step": 743 }, { "epoch": 1.83, "learning_rate": 6.536312849162012e-06, "loss": 0.3926, "step": 744 }, { "epoch": 1.83, "learning_rate": 6.531234128999493e-06, "loss": 0.4191, "step": 745 }, { "epoch": 1.84, "learning_rate": 6.526155408836974e-06, "loss": 0.3938, "step": 746 }, { "epoch": 1.84, "learning_rate": 6.5210766886744545e-06, "loss": 0.404, "step": 747 }, { "epoch": 1.84, "learning_rate": 6.515997968511936e-06, "loss": 0.4217, "step": 748 }, { "epoch": 1.84, "learning_rate": 6.5109192483494165e-06, "loss": 0.3955, "step": 749 }, { "epoch": 1.85, "learning_rate": 6.505840528186897e-06, "loss": 0.3825, "step": 750 }, { "epoch": 1.85, "learning_rate": 6.5007618080243785e-06, "loss": 0.3832, "step": 751 }, { "epoch": 1.85, "learning_rate": 6.495683087861859e-06, "loss": 0.4079, "step": 752 }, { "epoch": 1.85, "learning_rate": 6.4906043676993405e-06, "loss": 0.4081, "step": 753 }, { "epoch": 1.86, "learning_rate": 6.485525647536821e-06, "loss": 0.3941, "step": 754 }, { "epoch": 1.86, "learning_rate": 6.480446927374302e-06, "loss": 0.4284, "step": 755 }, { "epoch": 1.86, "learning_rate": 6.475368207211783e-06, "loss": 0.3916, "step": 756 }, { "epoch": 1.86, "learning_rate": 6.470289487049264e-06, "loss": 0.384, "step": 757 }, { "epoch": 1.87, "learning_rate": 6.465210766886745e-06, "loss": 0.3859, "step": 758 }, { "epoch": 1.87, "learning_rate": 6.460132046724226e-06, "loss": 0.3924, "step": 759 }, { "epoch": 1.87, "learning_rate": 6.455053326561706e-06, "loss": 0.4006, "step": 760 }, { "epoch": 1.87, "learning_rate": 6.449974606399188e-06, "loss": 0.3946, "step": 761 }, { "epoch": 1.88, "learning_rate": 6.444895886236668e-06, "loss": 0.3825, "step": 762 }, { "epoch": 1.88, "learning_rate": 6.43981716607415e-06, "loss": 0.403, "step": 763 }, { "epoch": 1.88, "learning_rate": 6.434738445911631e-06, "loss": 0.3939, "step": 764 }, { "epoch": 1.88, "learning_rate": 6.4296597257491125e-06, "loss": 0.4093, "step": 765 }, { "epoch": 1.89, "learning_rate": 6.424581005586593e-06, "loss": 0.3834, "step": 766 }, { "epoch": 1.89, "learning_rate": 6.419502285424074e-06, "loss": 0.4194, "step": 767 }, { "epoch": 1.89, "learning_rate": 6.414423565261555e-06, "loss": 0.3848, "step": 768 }, { "epoch": 1.89, "learning_rate": 6.409344845099036e-06, "loss": 0.3913, "step": 769 }, { "epoch": 1.9, "learning_rate": 6.404266124936517e-06, "loss": 0.4164, "step": 770 }, { "epoch": 1.9, "learning_rate": 6.399187404773998e-06, "loss": 0.4395, "step": 771 }, { "epoch": 1.9, "learning_rate": 6.394108684611478e-06, "loss": 0.3832, "step": 772 }, { "epoch": 1.9, "learning_rate": 6.38902996444896e-06, "loss": 0.4148, "step": 773 }, { "epoch": 1.9, "learning_rate": 6.38395124428644e-06, "loss": 0.4052, "step": 774 }, { "epoch": 1.91, "learning_rate": 6.378872524123922e-06, "loss": 0.3698, "step": 775 }, { "epoch": 1.91, "learning_rate": 6.373793803961402e-06, "loss": 0.4, "step": 776 }, { "epoch": 1.91, "learning_rate": 6.368715083798883e-06, "loss": 0.4169, "step": 777 }, { "epoch": 1.91, "learning_rate": 6.363636363636364e-06, "loss": 0.3908, "step": 778 }, { "epoch": 1.92, "learning_rate": 6.358557643473845e-06, "loss": 0.3898, "step": 779 }, { "epoch": 1.92, "learning_rate": 6.353478923311326e-06, "loss": 0.3902, "step": 780 }, { "epoch": 1.92, "learning_rate": 6.348400203148807e-06, "loss": 0.4, "step": 781 }, { "epoch": 1.92, "learning_rate": 6.343321482986287e-06, "loss": 0.4006, "step": 782 }, { "epoch": 1.93, "learning_rate": 6.338242762823769e-06, "loss": 0.399, "step": 783 }, { "epoch": 1.93, "learning_rate": 6.333164042661249e-06, "loss": 0.4211, "step": 784 }, { "epoch": 1.93, "learning_rate": 6.328085322498731e-06, "loss": 0.4285, "step": 785 }, { "epoch": 1.93, "learning_rate": 6.323006602336211e-06, "loss": 0.3827, "step": 786 }, { "epoch": 1.94, "learning_rate": 6.317927882173692e-06, "loss": 0.3951, "step": 787 }, { "epoch": 1.94, "learning_rate": 6.312849162011173e-06, "loss": 0.3934, "step": 788 }, { "epoch": 1.94, "learning_rate": 6.307770441848655e-06, "loss": 0.3773, "step": 789 }, { "epoch": 1.94, "learning_rate": 6.302691721686136e-06, "loss": 0.406, "step": 790 }, { "epoch": 1.95, "learning_rate": 6.297613001523617e-06, "loss": 0.4013, "step": 791 }, { "epoch": 1.95, "learning_rate": 6.292534281361098e-06, "loss": 0.3974, "step": 792 }, { "epoch": 1.95, "learning_rate": 6.287455561198579e-06, "loss": 0.3868, "step": 793 }, { "epoch": 1.95, "learning_rate": 6.282376841036059e-06, "loss": 0.4122, "step": 794 }, { "epoch": 1.96, "learning_rate": 6.277298120873541e-06, "loss": 0.4108, "step": 795 }, { "epoch": 1.96, "learning_rate": 6.272219400711021e-06, "loss": 0.3956, "step": 796 }, { "epoch": 1.96, "learning_rate": 6.267140680548503e-06, "loss": 0.3991, "step": 797 }, { "epoch": 1.96, "learning_rate": 6.262061960385983e-06, "loss": 0.3983, "step": 798 }, { "epoch": 1.97, "learning_rate": 6.256983240223464e-06, "loss": 0.4118, "step": 799 }, { "epoch": 1.97, "learning_rate": 6.251904520060945e-06, "loss": 0.3994, "step": 800 }, { "epoch": 1.97, "learning_rate": 6.246825799898426e-06, "loss": 0.4046, "step": 801 }, { "epoch": 1.97, "learning_rate": 6.241747079735907e-06, "loss": 0.403, "step": 802 }, { "epoch": 1.98, "learning_rate": 6.236668359573388e-06, "loss": 0.4045, "step": 803 }, { "epoch": 1.98, "learning_rate": 6.2315896394108686e-06, "loss": 0.4007, "step": 804 }, { "epoch": 1.98, "learning_rate": 6.22651091924835e-06, "loss": 0.381, "step": 805 }, { "epoch": 1.98, "learning_rate": 6.2214321990858306e-06, "loss": 0.3833, "step": 806 }, { "epoch": 1.99, "learning_rate": 6.216353478923311e-06, "loss": 0.3867, "step": 807 }, { "epoch": 1.99, "learning_rate": 6.2112747587607926e-06, "loss": 0.4041, "step": 808 }, { "epoch": 1.99, "learning_rate": 6.206196038598273e-06, "loss": 0.4072, "step": 809 }, { "epoch": 1.99, "learning_rate": 6.2011173184357546e-06, "loss": 0.384, "step": 810 }, { "epoch": 2.0, "learning_rate": 6.196038598273235e-06, "loss": 0.3987, "step": 811 }, { "epoch": 2.0, "learning_rate": 6.190959878110716e-06, "loss": 0.4205, "step": 812 }, { "epoch": 2.0, "learning_rate": 6.185881157948198e-06, "loss": 0.3524, "step": 813 }, { "epoch": 2.0, "learning_rate": 6.180802437785679e-06, "loss": 0.28, "step": 814 }, { "epoch": 2.01, "learning_rate": 6.17572371762316e-06, "loss": 0.2603, "step": 815 }, { "epoch": 2.01, "learning_rate": 6.1706449974606406e-06, "loss": 0.2755, "step": 816 }, { "epoch": 2.01, "learning_rate": 6.165566277298122e-06, "loss": 0.2631, "step": 817 }, { "epoch": 2.01, "learning_rate": 6.1604875571356026e-06, "loss": 0.2624, "step": 818 }, { "epoch": 2.02, "learning_rate": 6.155408836973083e-06, "loss": 0.29, "step": 819 }, { "epoch": 2.02, "learning_rate": 6.1503301168105646e-06, "loss": 0.2741, "step": 820 }, { "epoch": 2.02, "learning_rate": 6.145251396648045e-06, "loss": 0.2542, "step": 821 }, { "epoch": 2.02, "learning_rate": 6.1401726764855266e-06, "loss": 0.2615, "step": 822 }, { "epoch": 2.03, "learning_rate": 6.135093956323007e-06, "loss": 0.2655, "step": 823 }, { "epoch": 2.03, "learning_rate": 6.130015236160488e-06, "loss": 0.2671, "step": 824 }, { "epoch": 2.03, "learning_rate": 6.124936515997969e-06, "loss": 0.2687, "step": 825 }, { "epoch": 2.03, "learning_rate": 6.11985779583545e-06, "loss": 0.2482, "step": 826 }, { "epoch": 2.04, "learning_rate": 6.114779075672931e-06, "loss": 0.2761, "step": 827 }, { "epoch": 2.04, "learning_rate": 6.109700355510412e-06, "loss": 0.2514, "step": 828 }, { "epoch": 2.04, "learning_rate": 6.104621635347892e-06, "loss": 0.2577, "step": 829 }, { "epoch": 2.04, "learning_rate": 6.099542915185374e-06, "loss": 0.2529, "step": 830 }, { "epoch": 2.05, "learning_rate": 6.094464195022854e-06, "loss": 0.2686, "step": 831 }, { "epoch": 2.05, "learning_rate": 6.089385474860336e-06, "loss": 0.2565, "step": 832 }, { "epoch": 2.05, "learning_rate": 6.084306754697816e-06, "loss": 0.2655, "step": 833 }, { "epoch": 2.05, "learning_rate": 6.079228034535297e-06, "loss": 0.2719, "step": 834 }, { "epoch": 2.06, "learning_rate": 6.074149314372778e-06, "loss": 0.2365, "step": 835 }, { "epoch": 2.06, "learning_rate": 6.069070594210259e-06, "loss": 0.2572, "step": 836 }, { "epoch": 2.06, "learning_rate": 6.06399187404774e-06, "loss": 0.2489, "step": 837 }, { "epoch": 2.06, "learning_rate": 6.058913153885222e-06, "loss": 0.2597, "step": 838 }, { "epoch": 2.06, "learning_rate": 6.053834433722703e-06, "loss": 0.2655, "step": 839 }, { "epoch": 2.07, "learning_rate": 6.048755713560184e-06, "loss": 0.2638, "step": 840 }, { "epoch": 2.07, "learning_rate": 6.043676993397664e-06, "loss": 0.2556, "step": 841 }, { "epoch": 2.07, "learning_rate": 6.038598273235146e-06, "loss": 0.2667, "step": 842 }, { "epoch": 2.07, "learning_rate": 6.033519553072626e-06, "loss": 0.2705, "step": 843 }, { "epoch": 2.08, "learning_rate": 6.028440832910108e-06, "loss": 0.2649, "step": 844 }, { "epoch": 2.08, "learning_rate": 6.023362112747588e-06, "loss": 0.2749, "step": 845 }, { "epoch": 2.08, "learning_rate": 6.018283392585069e-06, "loss": 0.2393, "step": 846 }, { "epoch": 2.08, "learning_rate": 6.01320467242255e-06, "loss": 0.2678, "step": 847 }, { "epoch": 2.09, "learning_rate": 6.008125952260031e-06, "loss": 0.2559, "step": 848 }, { "epoch": 2.09, "learning_rate": 6.003047232097512e-06, "loss": 0.2548, "step": 849 }, { "epoch": 2.09, "learning_rate": 5.997968511934993e-06, "loss": 0.261, "step": 850 }, { "epoch": 2.09, "learning_rate": 5.9928897917724735e-06, "loss": 0.2729, "step": 851 }, { "epoch": 2.1, "learning_rate": 5.987811071609955e-06, "loss": 0.2736, "step": 852 }, { "epoch": 2.1, "learning_rate": 5.9827323514474355e-06, "loss": 0.2749, "step": 853 }, { "epoch": 2.1, "learning_rate": 5.977653631284917e-06, "loss": 0.2582, "step": 854 }, { "epoch": 2.1, "learning_rate": 5.9725749111223975e-06, "loss": 0.2648, "step": 855 }, { "epoch": 2.11, "learning_rate": 5.967496190959878e-06, "loss": 0.2452, "step": 856 }, { "epoch": 2.11, "learning_rate": 5.9624174707973595e-06, "loss": 0.2766, "step": 857 }, { "epoch": 2.11, "learning_rate": 5.95733875063484e-06, "loss": 0.2644, "step": 858 }, { "epoch": 2.11, "learning_rate": 5.952260030472321e-06, "loss": 0.2667, "step": 859 }, { "epoch": 2.12, "learning_rate": 5.947181310309802e-06, "loss": 0.2761, "step": 860 }, { "epoch": 2.12, "learning_rate": 5.942102590147283e-06, "loss": 0.2533, "step": 861 }, { "epoch": 2.12, "learning_rate": 5.937023869984765e-06, "loss": 0.2765, "step": 862 }, { "epoch": 2.12, "learning_rate": 5.9319451498222455e-06, "loss": 0.2511, "step": 863 }, { "epoch": 2.13, "learning_rate": 5.926866429659727e-06, "loss": 0.2671, "step": 864 }, { "epoch": 2.13, "learning_rate": 5.9217877094972075e-06, "loss": 0.2444, "step": 865 }, { "epoch": 2.13, "learning_rate": 5.916708989334689e-06, "loss": 0.2814, "step": 866 }, { "epoch": 2.13, "learning_rate": 5.9116302691721695e-06, "loss": 0.2519, "step": 867 }, { "epoch": 2.14, "learning_rate": 5.90655154900965e-06, "loss": 0.2581, "step": 868 }, { "epoch": 2.14, "learning_rate": 5.9014728288471315e-06, "loss": 0.2761, "step": 869 }, { "epoch": 2.14, "learning_rate": 5.896394108684612e-06, "loss": 0.2732, "step": 870 }, { "epoch": 2.14, "learning_rate": 5.8913153885220935e-06, "loss": 0.2688, "step": 871 }, { "epoch": 2.15, "learning_rate": 5.886236668359574e-06, "loss": 0.2782, "step": 872 }, { "epoch": 2.15, "learning_rate": 5.881157948197055e-06, "loss": 0.2597, "step": 873 }, { "epoch": 2.15, "learning_rate": 5.876079228034536e-06, "loss": 0.2497, "step": 874 }, { "epoch": 2.15, "learning_rate": 5.871000507872017e-06, "loss": 0.2442, "step": 875 }, { "epoch": 2.16, "learning_rate": 5.865921787709497e-06, "loss": 0.2542, "step": 876 }, { "epoch": 2.16, "learning_rate": 5.860843067546979e-06, "loss": 0.2681, "step": 877 }, { "epoch": 2.16, "learning_rate": 5.855764347384459e-06, "loss": 0.2768, "step": 878 }, { "epoch": 2.16, "learning_rate": 5.850685627221941e-06, "loss": 0.2563, "step": 879 }, { "epoch": 2.17, "learning_rate": 5.845606907059421e-06, "loss": 0.2847, "step": 880 }, { "epoch": 2.17, "learning_rate": 5.840528186896902e-06, "loss": 0.2682, "step": 881 }, { "epoch": 2.17, "learning_rate": 5.835449466734383e-06, "loss": 0.2639, "step": 882 }, { "epoch": 2.17, "learning_rate": 5.830370746571864e-06, "loss": 0.2398, "step": 883 }, { "epoch": 2.18, "learning_rate": 5.825292026409345e-06, "loss": 0.2528, "step": 884 }, { "epoch": 2.18, "learning_rate": 5.820213306246826e-06, "loss": 0.2645, "step": 885 }, { "epoch": 2.18, "learning_rate": 5.815134586084306e-06, "loss": 0.2689, "step": 886 }, { "epoch": 2.18, "learning_rate": 5.810055865921789e-06, "loss": 0.2637, "step": 887 }, { "epoch": 2.19, "learning_rate": 5.804977145759269e-06, "loss": 0.2685, "step": 888 }, { "epoch": 2.19, "learning_rate": 5.799898425596751e-06, "loss": 0.2503, "step": 889 }, { "epoch": 2.19, "learning_rate": 5.794819705434231e-06, "loss": 0.2516, "step": 890 }, { "epoch": 2.19, "learning_rate": 5.789740985271713e-06, "loss": 0.2592, "step": 891 }, { "epoch": 2.2, "learning_rate": 5.784662265109193e-06, "loss": 0.2766, "step": 892 }, { "epoch": 2.2, "learning_rate": 5.779583544946674e-06, "loss": 0.2581, "step": 893 }, { "epoch": 2.2, "learning_rate": 5.774504824784155e-06, "loss": 0.2649, "step": 894 }, { "epoch": 2.2, "learning_rate": 5.769426104621636e-06, "loss": 0.2577, "step": 895 }, { "epoch": 2.21, "learning_rate": 5.764347384459117e-06, "loss": 0.276, "step": 896 }, { "epoch": 2.21, "learning_rate": 5.759268664296598e-06, "loss": 0.2824, "step": 897 }, { "epoch": 2.21, "learning_rate": 5.754189944134078e-06, "loss": 0.2654, "step": 898 }, { "epoch": 2.21, "learning_rate": 5.74911122397156e-06, "loss": 0.2604, "step": 899 }, { "epoch": 2.22, "learning_rate": 5.74403250380904e-06, "loss": 0.2781, "step": 900 }, { "epoch": 2.22, "learning_rate": 5.738953783646522e-06, "loss": 0.2556, "step": 901 }, { "epoch": 2.22, "learning_rate": 5.733875063484002e-06, "loss": 0.2567, "step": 902 }, { "epoch": 2.22, "learning_rate": 5.728796343321483e-06, "loss": 0.2927, "step": 903 }, { "epoch": 2.22, "learning_rate": 5.723717623158964e-06, "loss": 0.2721, "step": 904 }, { "epoch": 2.23, "learning_rate": 5.718638902996445e-06, "loss": 0.2821, "step": 905 }, { "epoch": 2.23, "learning_rate": 5.713560182833926e-06, "loss": 0.2667, "step": 906 }, { "epoch": 2.23, "learning_rate": 5.708481462671407e-06, "loss": 0.2653, "step": 907 }, { "epoch": 2.23, "learning_rate": 5.7034027425088875e-06, "loss": 0.2483, "step": 908 }, { "epoch": 2.24, "learning_rate": 5.698324022346369e-06, "loss": 0.2574, "step": 909 }, { "epoch": 2.24, "learning_rate": 5.6932453021838495e-06, "loss": 0.251, "step": 910 }, { "epoch": 2.24, "learning_rate": 5.68816658202133e-06, "loss": 0.244, "step": 911 }, { "epoch": 2.24, "learning_rate": 5.683087861858812e-06, "loss": 0.2558, "step": 912 }, { "epoch": 2.25, "learning_rate": 5.678009141696294e-06, "loss": 0.2663, "step": 913 }, { "epoch": 2.25, "learning_rate": 5.672930421533774e-06, "loss": 0.2844, "step": 914 }, { "epoch": 2.25, "learning_rate": 5.667851701371255e-06, "loss": 0.2621, "step": 915 }, { "epoch": 2.25, "learning_rate": 5.662772981208736e-06, "loss": 0.2705, "step": 916 }, { "epoch": 2.26, "learning_rate": 5.657694261046217e-06, "loss": 0.2594, "step": 917 }, { "epoch": 2.26, "learning_rate": 5.652615540883698e-06, "loss": 0.2614, "step": 918 }, { "epoch": 2.26, "learning_rate": 5.647536820721179e-06, "loss": 0.2645, "step": 919 }, { "epoch": 2.26, "learning_rate": 5.6424581005586595e-06, "loss": 0.2504, "step": 920 }, { "epoch": 2.27, "learning_rate": 5.637379380396141e-06, "loss": 0.2817, "step": 921 }, { "epoch": 2.27, "learning_rate": 5.6323006602336215e-06, "loss": 0.2384, "step": 922 }, { "epoch": 2.27, "learning_rate": 5.627221940071103e-06, "loss": 0.2648, "step": 923 }, { "epoch": 2.27, "learning_rate": 5.6221432199085835e-06, "loss": 0.2739, "step": 924 }, { "epoch": 2.28, "learning_rate": 5.617064499746064e-06, "loss": 0.2736, "step": 925 }, { "epoch": 2.28, "learning_rate": 5.6119857795835456e-06, "loss": 0.251, "step": 926 }, { "epoch": 2.28, "learning_rate": 5.606907059421026e-06, "loss": 0.264, "step": 927 }, { "epoch": 2.28, "learning_rate": 5.601828339258507e-06, "loss": 0.2723, "step": 928 }, { "epoch": 2.29, "learning_rate": 5.596749619095988e-06, "loss": 0.2679, "step": 929 }, { "epoch": 2.29, "learning_rate": 5.591670898933469e-06, "loss": 0.259, "step": 930 }, { "epoch": 2.29, "learning_rate": 5.58659217877095e-06, "loss": 0.2736, "step": 931 }, { "epoch": 2.29, "learning_rate": 5.581513458608431e-06, "loss": 0.2777, "step": 932 }, { "epoch": 2.3, "learning_rate": 5.576434738445911e-06, "loss": 0.2747, "step": 933 }, { "epoch": 2.3, "learning_rate": 5.571356018283393e-06, "loss": 0.2591, "step": 934 }, { "epoch": 2.3, "learning_rate": 5.566277298120873e-06, "loss": 0.2697, "step": 935 }, { "epoch": 2.3, "learning_rate": 5.5611985779583556e-06, "loss": 0.2699, "step": 936 }, { "epoch": 2.31, "learning_rate": 5.556119857795836e-06, "loss": 0.2683, "step": 937 }, { "epoch": 2.31, "learning_rate": 5.5510411376333176e-06, "loss": 0.2681, "step": 938 }, { "epoch": 2.31, "learning_rate": 5.545962417470798e-06, "loss": 0.2299, "step": 939 }, { "epoch": 2.31, "learning_rate": 5.540883697308279e-06, "loss": 0.266, "step": 940 }, { "epoch": 2.32, "learning_rate": 5.53580497714576e-06, "loss": 0.2633, "step": 941 }, { "epoch": 2.32, "learning_rate": 5.530726256983241e-06, "loss": 0.2598, "step": 942 }, { "epoch": 2.32, "learning_rate": 5.525647536820722e-06, "loss": 0.265, "step": 943 }, { "epoch": 2.32, "learning_rate": 5.520568816658203e-06, "loss": 0.2636, "step": 944 }, { "epoch": 2.33, "learning_rate": 5.515490096495683e-06, "loss": 0.2703, "step": 945 }, { "epoch": 2.33, "learning_rate": 5.510411376333165e-06, "loss": 0.2816, "step": 946 }, { "epoch": 2.33, "learning_rate": 5.505332656170645e-06, "loss": 0.2804, "step": 947 }, { "epoch": 2.33, "learning_rate": 5.500253936008127e-06, "loss": 0.2636, "step": 948 }, { "epoch": 2.34, "learning_rate": 5.495175215845607e-06, "loss": 0.2627, "step": 949 }, { "epoch": 2.34, "learning_rate": 5.490096495683088e-06, "loss": 0.2839, "step": 950 }, { "epoch": 2.34, "learning_rate": 5.485017775520569e-06, "loss": 0.2769, "step": 951 }, { "epoch": 2.34, "learning_rate": 5.47993905535805e-06, "loss": 0.2508, "step": 952 }, { "epoch": 2.35, "learning_rate": 5.474860335195531e-06, "loss": 0.2619, "step": 953 }, { "epoch": 2.35, "learning_rate": 5.469781615033012e-06, "loss": 0.2795, "step": 954 }, { "epoch": 2.35, "learning_rate": 5.4647028948704925e-06, "loss": 0.2843, "step": 955 }, { "epoch": 2.35, "learning_rate": 5.459624174707974e-06, "loss": 0.2768, "step": 956 }, { "epoch": 2.36, "learning_rate": 5.4545454545454545e-06, "loss": 0.2628, "step": 957 }, { "epoch": 2.36, "learning_rate": 5.449466734382936e-06, "loss": 0.2586, "step": 958 }, { "epoch": 2.36, "learning_rate": 5.4443880142204165e-06, "loss": 0.251, "step": 959 }, { "epoch": 2.36, "learning_rate": 5.439309294057897e-06, "loss": 0.2618, "step": 960 }, { "epoch": 2.37, "learning_rate": 5.434230573895379e-06, "loss": 0.2692, "step": 961 }, { "epoch": 2.37, "learning_rate": 5.42915185373286e-06, "loss": 0.2648, "step": 962 }, { "epoch": 2.37, "learning_rate": 5.424073133570341e-06, "loss": 0.2721, "step": 963 }, { "epoch": 2.37, "learning_rate": 5.418994413407822e-06, "loss": 0.28, "step": 964 }, { "epoch": 2.38, "learning_rate": 5.413915693245303e-06, "loss": 0.2542, "step": 965 }, { "epoch": 2.38, "learning_rate": 5.408836973082784e-06, "loss": 0.2703, "step": 966 }, { "epoch": 2.38, "learning_rate": 5.4037582529202645e-06, "loss": 0.2668, "step": 967 }, { "epoch": 2.38, "learning_rate": 5.398679532757746e-06, "loss": 0.2751, "step": 968 }, { "epoch": 2.38, "learning_rate": 5.3936008125952265e-06, "loss": 0.2805, "step": 969 }, { "epoch": 2.39, "learning_rate": 5.388522092432708e-06, "loss": 0.2784, "step": 970 }, { "epoch": 2.39, "learning_rate": 5.3834433722701885e-06, "loss": 0.2906, "step": 971 }, { "epoch": 2.39, "learning_rate": 5.378364652107669e-06, "loss": 0.2608, "step": 972 }, { "epoch": 2.39, "learning_rate": 5.3732859319451505e-06, "loss": 0.2632, "step": 973 }, { "epoch": 2.4, "learning_rate": 5.368207211782631e-06, "loss": 0.2726, "step": 974 }, { "epoch": 2.4, "learning_rate": 5.3631284916201125e-06, "loss": 0.2698, "step": 975 }, { "epoch": 2.4, "learning_rate": 5.358049771457593e-06, "loss": 0.2702, "step": 976 }, { "epoch": 2.4, "learning_rate": 5.352971051295074e-06, "loss": 0.2525, "step": 977 }, { "epoch": 2.41, "learning_rate": 5.347892331132555e-06, "loss": 0.2709, "step": 978 }, { "epoch": 2.41, "learning_rate": 5.342813610970036e-06, "loss": 0.2612, "step": 979 }, { "epoch": 2.41, "learning_rate": 5.337734890807516e-06, "loss": 0.2781, "step": 980 }, { "epoch": 2.41, "learning_rate": 5.332656170644998e-06, "loss": 0.2724, "step": 981 }, { "epoch": 2.42, "learning_rate": 5.327577450482478e-06, "loss": 0.2777, "step": 982 }, { "epoch": 2.42, "learning_rate": 5.32249873031996e-06, "loss": 0.2564, "step": 983 }, { "epoch": 2.42, "learning_rate": 5.31742001015744e-06, "loss": 0.2612, "step": 984 }, { "epoch": 2.42, "learning_rate": 5.3123412899949225e-06, "loss": 0.2629, "step": 985 }, { "epoch": 2.43, "learning_rate": 5.307262569832403e-06, "loss": 0.2732, "step": 986 }, { "epoch": 2.43, "learning_rate": 5.3021838496698845e-06, "loss": 0.2727, "step": 987 }, { "epoch": 2.43, "learning_rate": 5.297105129507365e-06, "loss": 0.2587, "step": 988 }, { "epoch": 2.43, "learning_rate": 5.292026409344846e-06, "loss": 0.2547, "step": 989 }, { "epoch": 2.44, "learning_rate": 5.286947689182327e-06, "loss": 0.2838, "step": 990 }, { "epoch": 2.44, "learning_rate": 5.281868969019808e-06, "loss": 0.2623, "step": 991 }, { "epoch": 2.44, "learning_rate": 5.276790248857289e-06, "loss": 0.2764, "step": 992 }, { "epoch": 2.44, "learning_rate": 5.27171152869477e-06, "loss": 0.2824, "step": 993 }, { "epoch": 2.45, "learning_rate": 5.26663280853225e-06, "loss": 0.2783, "step": 994 }, { "epoch": 2.45, "learning_rate": 5.261554088369732e-06, "loss": 0.2761, "step": 995 }, { "epoch": 2.45, "learning_rate": 5.256475368207212e-06, "loss": 0.2895, "step": 996 }, { "epoch": 2.45, "learning_rate": 5.251396648044693e-06, "loss": 0.2716, "step": 997 }, { "epoch": 2.46, "learning_rate": 5.246317927882174e-06, "loss": 0.2859, "step": 998 }, { "epoch": 2.46, "learning_rate": 5.241239207719655e-06, "loss": 0.2726, "step": 999 }, { "epoch": 2.46, "learning_rate": 5.236160487557136e-06, "loss": 0.2661, "step": 1000 }, { "epoch": 2.46, "learning_rate": 5.231081767394617e-06, "loss": 0.2601, "step": 1001 }, { "epoch": 2.47, "learning_rate": 5.226003047232097e-06, "loss": 0.2528, "step": 1002 }, { "epoch": 2.47, "learning_rate": 5.220924327069579e-06, "loss": 0.2546, "step": 1003 }, { "epoch": 2.47, "learning_rate": 5.215845606907059e-06, "loss": 0.2556, "step": 1004 }, { "epoch": 2.47, "learning_rate": 5.210766886744541e-06, "loss": 0.2713, "step": 1005 }, { "epoch": 2.48, "learning_rate": 5.205688166582021e-06, "loss": 0.2609, "step": 1006 }, { "epoch": 2.48, "learning_rate": 5.200609446419502e-06, "loss": 0.2754, "step": 1007 }, { "epoch": 2.48, "learning_rate": 5.195530726256983e-06, "loss": 0.2668, "step": 1008 }, { "epoch": 2.48, "learning_rate": 5.190452006094464e-06, "loss": 0.2546, "step": 1009 }, { "epoch": 2.49, "learning_rate": 5.185373285931946e-06, "loss": 0.2781, "step": 1010 }, { "epoch": 2.49, "learning_rate": 5.180294565769427e-06, "loss": 0.2825, "step": 1011 }, { "epoch": 2.49, "learning_rate": 5.175215845606908e-06, "loss": 0.2652, "step": 1012 }, { "epoch": 2.49, "learning_rate": 5.170137125444389e-06, "loss": 0.27, "step": 1013 }, { "epoch": 2.5, "learning_rate": 5.165058405281869e-06, "loss": 0.2741, "step": 1014 }, { "epoch": 2.5, "learning_rate": 5.159979685119351e-06, "loss": 0.2799, "step": 1015 }, { "epoch": 2.5, "learning_rate": 5.154900964956831e-06, "loss": 0.2427, "step": 1016 }, { "epoch": 2.5, "learning_rate": 5.149822244794313e-06, "loss": 0.2899, "step": 1017 }, { "epoch": 2.51, "learning_rate": 5.144743524631793e-06, "loss": 0.2753, "step": 1018 }, { "epoch": 2.51, "learning_rate": 5.139664804469274e-06, "loss": 0.2604, "step": 1019 }, { "epoch": 2.51, "learning_rate": 5.134586084306755e-06, "loss": 0.2796, "step": 1020 }, { "epoch": 2.51, "learning_rate": 5.129507364144236e-06, "loss": 0.2713, "step": 1021 }, { "epoch": 2.52, "learning_rate": 5.124428643981717e-06, "loss": 0.2792, "step": 1022 }, { "epoch": 2.52, "learning_rate": 5.119349923819198e-06, "loss": 0.2786, "step": 1023 }, { "epoch": 2.52, "learning_rate": 5.1142712036566785e-06, "loss": 0.272, "step": 1024 }, { "epoch": 2.52, "learning_rate": 5.10919248349416e-06, "loss": 0.2601, "step": 1025 }, { "epoch": 2.53, "learning_rate": 5.1041137633316405e-06, "loss": 0.2647, "step": 1026 }, { "epoch": 2.53, "learning_rate": 5.099035043169122e-06, "loss": 0.2699, "step": 1027 }, { "epoch": 2.53, "learning_rate": 5.0939563230066025e-06, "loss": 0.27, "step": 1028 }, { "epoch": 2.53, "learning_rate": 5.088877602844083e-06, "loss": 0.3028, "step": 1029 }, { "epoch": 2.53, "learning_rate": 5.0837988826815645e-06, "loss": 0.2791, "step": 1030 }, { "epoch": 2.54, "learning_rate": 5.078720162519045e-06, "loss": 0.2602, "step": 1031 }, { "epoch": 2.54, "learning_rate": 5.0736414423565265e-06, "loss": 0.2852, "step": 1032 }, { "epoch": 2.54, "learning_rate": 5.068562722194007e-06, "loss": 0.2538, "step": 1033 }, { "epoch": 2.54, "learning_rate": 5.063484002031488e-06, "loss": 0.2702, "step": 1034 }, { "epoch": 2.55, "learning_rate": 5.05840528186897e-06, "loss": 0.2386, "step": 1035 }, { "epoch": 2.55, "learning_rate": 5.0533265617064505e-06, "loss": 0.2762, "step": 1036 }, { "epoch": 2.55, "learning_rate": 5.048247841543932e-06, "loss": 0.2707, "step": 1037 }, { "epoch": 2.55, "learning_rate": 5.0431691213814125e-06, "loss": 0.2631, "step": 1038 }, { "epoch": 2.56, "learning_rate": 5.038090401218894e-06, "loss": 0.2686, "step": 1039 }, { "epoch": 2.56, "learning_rate": 5.0330116810563745e-06, "loss": 0.2855, "step": 1040 }, { "epoch": 2.56, "learning_rate": 5.027932960893855e-06, "loss": 0.268, "step": 1041 }, { "epoch": 2.56, "learning_rate": 5.0228542407313365e-06, "loss": 0.2594, "step": 1042 }, { "epoch": 2.57, "learning_rate": 5.017775520568817e-06, "loss": 0.3037, "step": 1043 }, { "epoch": 2.57, "learning_rate": 5.0126968004062985e-06, "loss": 0.2639, "step": 1044 }, { "epoch": 2.57, "learning_rate": 5.007618080243779e-06, "loss": 0.2837, "step": 1045 }, { "epoch": 2.57, "learning_rate": 5.00253936008126e-06, "loss": 0.2673, "step": 1046 }, { "epoch": 2.58, "learning_rate": 4.997460639918741e-06, "loss": 0.2689, "step": 1047 }, { "epoch": 2.58, "learning_rate": 4.992381919756222e-06, "loss": 0.2894, "step": 1048 }, { "epoch": 2.58, "learning_rate": 4.987303199593702e-06, "loss": 0.2573, "step": 1049 }, { "epoch": 2.58, "learning_rate": 4.982224479431184e-06, "loss": 0.2637, "step": 1050 }, { "epoch": 2.59, "learning_rate": 4.977145759268664e-06, "loss": 0.2486, "step": 1051 }, { "epoch": 2.59, "learning_rate": 4.972067039106146e-06, "loss": 0.251, "step": 1052 }, { "epoch": 2.59, "learning_rate": 4.966988318943627e-06, "loss": 0.2716, "step": 1053 }, { "epoch": 2.59, "learning_rate": 4.961909598781108e-06, "loss": 0.2554, "step": 1054 }, { "epoch": 2.6, "learning_rate": 4.956830878618588e-06, "loss": 0.2753, "step": 1055 }, { "epoch": 2.6, "learning_rate": 4.95175215845607e-06, "loss": 0.2886, "step": 1056 }, { "epoch": 2.6, "learning_rate": 4.94667343829355e-06, "loss": 0.2714, "step": 1057 }, { "epoch": 2.6, "learning_rate": 4.941594718131032e-06, "loss": 0.2816, "step": 1058 }, { "epoch": 2.61, "learning_rate": 4.936515997968512e-06, "loss": 0.2747, "step": 1059 }, { "epoch": 2.61, "learning_rate": 4.931437277805993e-06, "loss": 0.2896, "step": 1060 }, { "epoch": 2.61, "learning_rate": 4.926358557643474e-06, "loss": 0.2612, "step": 1061 }, { "epoch": 2.61, "learning_rate": 4.921279837480955e-06, "loss": 0.2636, "step": 1062 }, { "epoch": 2.62, "learning_rate": 4.916201117318436e-06, "loss": 0.275, "step": 1063 }, { "epoch": 2.62, "learning_rate": 4.911122397155917e-06, "loss": 0.2681, "step": 1064 }, { "epoch": 2.62, "learning_rate": 4.906043676993398e-06, "loss": 0.2784, "step": 1065 }, { "epoch": 2.62, "learning_rate": 4.900964956830879e-06, "loss": 0.2653, "step": 1066 }, { "epoch": 2.63, "learning_rate": 4.89588623666836e-06, "loss": 0.2731, "step": 1067 }, { "epoch": 2.63, "learning_rate": 4.890807516505841e-06, "loss": 0.268, "step": 1068 }, { "epoch": 2.63, "learning_rate": 4.885728796343322e-06, "loss": 0.2762, "step": 1069 }, { "epoch": 2.63, "learning_rate": 4.880650076180803e-06, "loss": 0.2485, "step": 1070 }, { "epoch": 2.64, "learning_rate": 4.8755713560182834e-06, "loss": 0.2695, "step": 1071 }, { "epoch": 2.64, "learning_rate": 4.870492635855765e-06, "loss": 0.2686, "step": 1072 }, { "epoch": 2.64, "learning_rate": 4.8654139156932454e-06, "loss": 0.2614, "step": 1073 }, { "epoch": 2.64, "learning_rate": 4.860335195530727e-06, "loss": 0.2871, "step": 1074 }, { "epoch": 2.65, "learning_rate": 4.8552564753682074e-06, "loss": 0.2559, "step": 1075 }, { "epoch": 2.65, "learning_rate": 4.850177755205688e-06, "loss": 0.2816, "step": 1076 }, { "epoch": 2.65, "learning_rate": 4.8450990350431694e-06, "loss": 0.2762, "step": 1077 }, { "epoch": 2.65, "learning_rate": 4.840020314880651e-06, "loss": 0.2684, "step": 1078 }, { "epoch": 2.66, "learning_rate": 4.8349415947181314e-06, "loss": 0.2736, "step": 1079 }, { "epoch": 2.66, "learning_rate": 4.829862874555613e-06, "loss": 0.2684, "step": 1080 }, { "epoch": 2.66, "learning_rate": 4.8247841543930934e-06, "loss": 0.2832, "step": 1081 }, { "epoch": 2.66, "learning_rate": 4.819705434230574e-06, "loss": 0.2697, "step": 1082 }, { "epoch": 2.67, "learning_rate": 4.8146267140680554e-06, "loss": 0.2641, "step": 1083 }, { "epoch": 2.67, "learning_rate": 4.809547993905536e-06, "loss": 0.2688, "step": 1084 }, { "epoch": 2.67, "learning_rate": 4.8044692737430175e-06, "loss": 0.283, "step": 1085 }, { "epoch": 2.67, "learning_rate": 4.799390553580498e-06, "loss": 0.2774, "step": 1086 }, { "epoch": 2.68, "learning_rate": 4.794311833417979e-06, "loss": 0.2664, "step": 1087 }, { "epoch": 2.68, "learning_rate": 4.78923311325546e-06, "loss": 0.2651, "step": 1088 }, { "epoch": 2.68, "learning_rate": 4.784154393092941e-06, "loss": 0.2666, "step": 1089 }, { "epoch": 2.68, "learning_rate": 4.779075672930422e-06, "loss": 0.2698, "step": 1090 }, { "epoch": 2.69, "learning_rate": 4.7739969527679035e-06, "loss": 0.2856, "step": 1091 }, { "epoch": 2.69, "learning_rate": 4.768918232605384e-06, "loss": 0.2614, "step": 1092 }, { "epoch": 2.69, "learning_rate": 4.763839512442865e-06, "loss": 0.2751, "step": 1093 }, { "epoch": 2.69, "learning_rate": 4.758760792280346e-06, "loss": 0.265, "step": 1094 }, { "epoch": 2.69, "learning_rate": 4.753682072117827e-06, "loss": 0.2576, "step": 1095 }, { "epoch": 2.7, "learning_rate": 4.748603351955308e-06, "loss": 0.2634, "step": 1096 }, { "epoch": 2.7, "learning_rate": 4.743524631792789e-06, "loss": 0.2757, "step": 1097 }, { "epoch": 2.7, "learning_rate": 4.738445911630269e-06, "loss": 0.2851, "step": 1098 }, { "epoch": 2.7, "learning_rate": 4.733367191467751e-06, "loss": 0.2628, "step": 1099 }, { "epoch": 2.71, "learning_rate": 4.728288471305231e-06, "loss": 0.2678, "step": 1100 }, { "epoch": 2.71, "learning_rate": 4.723209751142712e-06, "loss": 0.2678, "step": 1101 }, { "epoch": 2.71, "learning_rate": 4.718131030980194e-06, "loss": 0.2772, "step": 1102 }, { "epoch": 2.71, "learning_rate": 4.713052310817675e-06, "loss": 0.2381, "step": 1103 }, { "epoch": 2.72, "learning_rate": 4.707973590655155e-06, "loss": 0.2623, "step": 1104 }, { "epoch": 2.72, "learning_rate": 4.702894870492637e-06, "loss": 0.2659, "step": 1105 }, { "epoch": 2.72, "learning_rate": 4.697816150330117e-06, "loss": 0.2533, "step": 1106 }, { "epoch": 2.72, "learning_rate": 4.692737430167599e-06, "loss": 0.2721, "step": 1107 }, { "epoch": 2.73, "learning_rate": 4.687658710005079e-06, "loss": 0.2825, "step": 1108 }, { "epoch": 2.73, "learning_rate": 4.68257998984256e-06, "loss": 0.2803, "step": 1109 }, { "epoch": 2.73, "learning_rate": 4.677501269680041e-06, "loss": 0.2728, "step": 1110 }, { "epoch": 2.73, "learning_rate": 4.672422549517522e-06, "loss": 0.2655, "step": 1111 }, { "epoch": 2.74, "learning_rate": 4.667343829355002e-06, "loss": 0.2789, "step": 1112 }, { "epoch": 2.74, "learning_rate": 4.662265109192484e-06, "loss": 0.2978, "step": 1113 }, { "epoch": 2.74, "learning_rate": 4.657186389029964e-06, "loss": 0.2663, "step": 1114 }, { "epoch": 2.74, "learning_rate": 4.652107668867446e-06, "loss": 0.2586, "step": 1115 }, { "epoch": 2.75, "learning_rate": 4.647028948704927e-06, "loss": 0.2802, "step": 1116 }, { "epoch": 2.75, "learning_rate": 4.641950228542408e-06, "loss": 0.286, "step": 1117 }, { "epoch": 2.75, "learning_rate": 4.636871508379888e-06, "loss": 0.2576, "step": 1118 }, { "epoch": 2.75, "learning_rate": 4.63179278821737e-06, "loss": 0.2785, "step": 1119 }, { "epoch": 2.76, "learning_rate": 4.62671406805485e-06, "loss": 0.272, "step": 1120 }, { "epoch": 2.76, "learning_rate": 4.621635347892332e-06, "loss": 0.2542, "step": 1121 }, { "epoch": 2.76, "learning_rate": 4.616556627729812e-06, "loss": 0.2611, "step": 1122 }, { "epoch": 2.76, "learning_rate": 4.611477907567293e-06, "loss": 0.2673, "step": 1123 }, { "epoch": 2.77, "learning_rate": 4.606399187404774e-06, "loss": 0.254, "step": 1124 }, { "epoch": 2.77, "learning_rate": 4.601320467242255e-06, "loss": 0.2791, "step": 1125 }, { "epoch": 2.77, "learning_rate": 4.596241747079736e-06, "loss": 0.2739, "step": 1126 }, { "epoch": 2.77, "learning_rate": 4.591163026917218e-06, "loss": 0.2769, "step": 1127 }, { "epoch": 2.78, "learning_rate": 4.586084306754698e-06, "loss": 0.2885, "step": 1128 }, { "epoch": 2.78, "learning_rate": 4.581005586592179e-06, "loss": 0.2704, "step": 1129 }, { "epoch": 2.78, "learning_rate": 4.57592686642966e-06, "loss": 0.2581, "step": 1130 }, { "epoch": 2.78, "learning_rate": 4.570848146267141e-06, "loss": 0.2732, "step": 1131 }, { "epoch": 2.79, "learning_rate": 4.565769426104622e-06, "loss": 0.2717, "step": 1132 }, { "epoch": 2.79, "learning_rate": 4.560690705942103e-06, "loss": 0.2643, "step": 1133 }, { "epoch": 2.79, "learning_rate": 4.5556119857795835e-06, "loss": 0.2586, "step": 1134 }, { "epoch": 2.79, "learning_rate": 4.550533265617065e-06, "loss": 0.2667, "step": 1135 }, { "epoch": 2.8, "learning_rate": 4.5454545454545455e-06, "loss": 0.2749, "step": 1136 }, { "epoch": 2.8, "learning_rate": 4.540375825292027e-06, "loss": 0.2804, "step": 1137 }, { "epoch": 2.8, "learning_rate": 4.5352971051295075e-06, "loss": 0.2747, "step": 1138 }, { "epoch": 2.8, "learning_rate": 4.530218384966989e-06, "loss": 0.2744, "step": 1139 }, { "epoch": 2.81, "learning_rate": 4.5251396648044695e-06, "loss": 0.2628, "step": 1140 }, { "epoch": 2.81, "learning_rate": 4.520060944641951e-06, "loss": 0.2754, "step": 1141 }, { "epoch": 2.81, "learning_rate": 4.5149822244794315e-06, "loss": 0.2678, "step": 1142 }, { "epoch": 2.81, "learning_rate": 4.509903504316913e-06, "loss": 0.276, "step": 1143 }, { "epoch": 2.82, "learning_rate": 4.5048247841543935e-06, "loss": 0.2745, "step": 1144 }, { "epoch": 2.82, "learning_rate": 4.499746063991874e-06, "loss": 0.268, "step": 1145 }, { "epoch": 2.82, "learning_rate": 4.4946673438293555e-06, "loss": 0.2633, "step": 1146 }, { "epoch": 2.82, "learning_rate": 4.489588623666836e-06, "loss": 0.2612, "step": 1147 }, { "epoch": 2.83, "learning_rate": 4.4845099035043175e-06, "loss": 0.2829, "step": 1148 }, { "epoch": 2.83, "learning_rate": 4.479431183341798e-06, "loss": 0.2611, "step": 1149 }, { "epoch": 2.83, "learning_rate": 4.474352463179279e-06, "loss": 0.2826, "step": 1150 }, { "epoch": 2.83, "learning_rate": 4.46927374301676e-06, "loss": 0.2718, "step": 1151 }, { "epoch": 2.84, "learning_rate": 4.4641950228542415e-06, "loss": 0.2806, "step": 1152 }, { "epoch": 2.84, "learning_rate": 4.459116302691722e-06, "loss": 0.2861, "step": 1153 }, { "epoch": 2.84, "learning_rate": 4.4540375825292035e-06, "loss": 0.2815, "step": 1154 }, { "epoch": 2.84, "learning_rate": 4.448958862366684e-06, "loss": 0.2479, "step": 1155 }, { "epoch": 2.85, "learning_rate": 4.443880142204165e-06, "loss": 0.2798, "step": 1156 }, { "epoch": 2.85, "learning_rate": 4.438801422041646e-06, "loss": 0.2764, "step": 1157 }, { "epoch": 2.85, "learning_rate": 4.433722701879127e-06, "loss": 0.2448, "step": 1158 }, { "epoch": 2.85, "learning_rate": 4.428643981716608e-06, "loss": 0.2694, "step": 1159 }, { "epoch": 2.85, "learning_rate": 4.423565261554089e-06, "loss": 0.2819, "step": 1160 }, { "epoch": 2.86, "learning_rate": 4.418486541391569e-06, "loss": 0.2437, "step": 1161 }, { "epoch": 2.86, "learning_rate": 4.413407821229051e-06, "loss": 0.2752, "step": 1162 }, { "epoch": 2.86, "learning_rate": 4.408329101066531e-06, "loss": 0.2545, "step": 1163 }, { "epoch": 2.86, "learning_rate": 4.403250380904013e-06, "loss": 0.3022, "step": 1164 }, { "epoch": 2.87, "learning_rate": 4.398171660741494e-06, "loss": 0.2695, "step": 1165 }, { "epoch": 2.87, "learning_rate": 4.393092940578975e-06, "loss": 0.2938, "step": 1166 }, { "epoch": 2.87, "learning_rate": 4.388014220416455e-06, "loss": 0.2798, "step": 1167 }, { "epoch": 2.87, "learning_rate": 4.382935500253937e-06, "loss": 0.2783, "step": 1168 }, { "epoch": 2.88, "learning_rate": 4.377856780091417e-06, "loss": 0.2852, "step": 1169 }, { "epoch": 2.88, "learning_rate": 4.372778059928898e-06, "loss": 0.2465, "step": 1170 }, { "epoch": 2.88, "learning_rate": 4.367699339766379e-06, "loss": 0.2719, "step": 1171 }, { "epoch": 2.88, "learning_rate": 4.36262061960386e-06, "loss": 0.2514, "step": 1172 }, { "epoch": 2.89, "learning_rate": 4.357541899441341e-06, "loss": 0.2806, "step": 1173 }, { "epoch": 2.89, "learning_rate": 4.352463179278822e-06, "loss": 0.2728, "step": 1174 }, { "epoch": 2.89, "learning_rate": 4.3473844591163024e-06, "loss": 0.2765, "step": 1175 }, { "epoch": 2.89, "learning_rate": 4.342305738953784e-06, "loss": 0.2798, "step": 1176 }, { "epoch": 2.9, "learning_rate": 4.337227018791265e-06, "loss": 0.2847, "step": 1177 }, { "epoch": 2.9, "learning_rate": 4.332148298628746e-06, "loss": 0.2852, "step": 1178 }, { "epoch": 2.9, "learning_rate": 4.327069578466227e-06, "loss": 0.2627, "step": 1179 }, { "epoch": 2.9, "learning_rate": 4.321990858303708e-06, "loss": 0.2579, "step": 1180 }, { "epoch": 2.91, "learning_rate": 4.3169121381411884e-06, "loss": 0.273, "step": 1181 }, { "epoch": 2.91, "learning_rate": 4.31183341797867e-06, "loss": 0.2793, "step": 1182 }, { "epoch": 2.91, "learning_rate": 4.3067546978161504e-06, "loss": 0.2636, "step": 1183 }, { "epoch": 2.91, "learning_rate": 4.301675977653632e-06, "loss": 0.27, "step": 1184 }, { "epoch": 2.92, "learning_rate": 4.2965972574911124e-06, "loss": 0.2508, "step": 1185 }, { "epoch": 2.92, "learning_rate": 4.291518537328593e-06, "loss": 0.2656, "step": 1186 }, { "epoch": 2.92, "learning_rate": 4.2864398171660744e-06, "loss": 0.2508, "step": 1187 }, { "epoch": 2.92, "learning_rate": 4.281361097003555e-06, "loss": 0.2637, "step": 1188 }, { "epoch": 2.93, "learning_rate": 4.2762823768410364e-06, "loss": 0.2758, "step": 1189 }, { "epoch": 2.93, "learning_rate": 4.271203656678518e-06, "loss": 0.2652, "step": 1190 }, { "epoch": 2.93, "learning_rate": 4.2661249365159984e-06, "loss": 0.2773, "step": 1191 }, { "epoch": 2.93, "learning_rate": 4.261046216353479e-06, "loss": 0.2665, "step": 1192 }, { "epoch": 2.94, "learning_rate": 4.2559674961909604e-06, "loss": 0.265, "step": 1193 }, { "epoch": 2.94, "learning_rate": 4.250888776028441e-06, "loss": 0.277, "step": 1194 }, { "epoch": 2.94, "learning_rate": 4.2458100558659224e-06, "loss": 0.269, "step": 1195 }, { "epoch": 2.94, "learning_rate": 4.240731335703403e-06, "loss": 0.2678, "step": 1196 }, { "epoch": 2.95, "learning_rate": 4.235652615540884e-06, "loss": 0.2559, "step": 1197 }, { "epoch": 2.95, "learning_rate": 4.230573895378365e-06, "loss": 0.2533, "step": 1198 }, { "epoch": 2.95, "learning_rate": 4.225495175215846e-06, "loss": 0.2441, "step": 1199 }, { "epoch": 2.95, "learning_rate": 4.220416455053327e-06, "loss": 0.2809, "step": 1200 }, { "epoch": 2.96, "learning_rate": 4.2153377348908084e-06, "loss": 0.2529, "step": 1201 }, { "epoch": 2.96, "learning_rate": 4.210259014728289e-06, "loss": 0.265, "step": 1202 }, { "epoch": 2.96, "learning_rate": 4.20518029456577e-06, "loss": 0.2913, "step": 1203 }, { "epoch": 2.96, "learning_rate": 4.200101574403251e-06, "loss": 0.2741, "step": 1204 }, { "epoch": 2.97, "learning_rate": 4.195022854240732e-06, "loss": 0.2764, "step": 1205 }, { "epoch": 2.97, "learning_rate": 4.189944134078213e-06, "loss": 0.2842, "step": 1206 }, { "epoch": 2.97, "learning_rate": 4.184865413915694e-06, "loss": 0.2562, "step": 1207 }, { "epoch": 2.97, "learning_rate": 4.179786693753174e-06, "loss": 0.286, "step": 1208 }, { "epoch": 2.98, "learning_rate": 4.174707973590656e-06, "loss": 0.2703, "step": 1209 }, { "epoch": 2.98, "learning_rate": 4.169629253428136e-06, "loss": 0.2851, "step": 1210 }, { "epoch": 2.98, "learning_rate": 4.164550533265618e-06, "loss": 0.2786, "step": 1211 }, { "epoch": 2.98, "learning_rate": 4.159471813103098e-06, "loss": 0.2661, "step": 1212 }, { "epoch": 2.99, "learning_rate": 4.15439309294058e-06, "loss": 0.2609, "step": 1213 }, { "epoch": 2.99, "learning_rate": 4.14931437277806e-06, "loss": 0.264, "step": 1214 }, { "epoch": 2.99, "learning_rate": 4.144235652615542e-06, "loss": 0.2763, "step": 1215 }, { "epoch": 2.99, "learning_rate": 4.139156932453022e-06, "loss": 0.2716, "step": 1216 }, { "epoch": 3.0, "learning_rate": 4.134078212290504e-06, "loss": 0.2622, "step": 1217 }, { "epoch": 3.0, "learning_rate": 4.128999492127984e-06, "loss": 0.2626, "step": 1218 }, { "epoch": 3.0, "learning_rate": 4.123920771965465e-06, "loss": 0.2556, "step": 1219 }, { "epoch": 3.0, "learning_rate": 4.118842051802946e-06, "loss": 0.1882, "step": 1220 }, { "epoch": 3.01, "learning_rate": 4.113763331640427e-06, "loss": 0.1863, "step": 1221 }, { "epoch": 3.01, "learning_rate": 4.108684611477907e-06, "loss": 0.1694, "step": 1222 }, { "epoch": 3.01, "learning_rate": 4.103605891315389e-06, "loss": 0.1576, "step": 1223 }, { "epoch": 3.01, "learning_rate": 4.098527171152869e-06, "loss": 0.1441, "step": 1224 }, { "epoch": 3.01, "learning_rate": 4.093448450990351e-06, "loss": 0.1785, "step": 1225 }, { "epoch": 3.02, "learning_rate": 4.088369730827832e-06, "loss": 0.1577, "step": 1226 }, { "epoch": 3.02, "learning_rate": 4.083291010665313e-06, "loss": 0.1543, "step": 1227 }, { "epoch": 3.02, "learning_rate": 4.078212290502794e-06, "loss": 0.1725, "step": 1228 }, { "epoch": 3.02, "learning_rate": 4.073133570340275e-06, "loss": 0.1561, "step": 1229 }, { "epoch": 3.03, "learning_rate": 4.068054850177755e-06, "loss": 0.1473, "step": 1230 }, { "epoch": 3.03, "learning_rate": 4.062976130015237e-06, "loss": 0.1607, "step": 1231 }, { "epoch": 3.03, "learning_rate": 4.057897409852717e-06, "loss": 0.1666, "step": 1232 }, { "epoch": 3.03, "learning_rate": 4.052818689690198e-06, "loss": 0.1644, "step": 1233 }, { "epoch": 3.04, "learning_rate": 4.047739969527679e-06, "loss": 0.152, "step": 1234 }, { "epoch": 3.04, "learning_rate": 4.04266124936516e-06, "loss": 0.1615, "step": 1235 }, { "epoch": 3.04, "learning_rate": 4.037582529202641e-06, "loss": 0.1453, "step": 1236 }, { "epoch": 3.04, "learning_rate": 4.032503809040122e-06, "loss": 0.154, "step": 1237 }, { "epoch": 3.05, "learning_rate": 4.027425088877603e-06, "loss": 0.1602, "step": 1238 }, { "epoch": 3.05, "learning_rate": 4.022346368715084e-06, "loss": 0.1498, "step": 1239 }, { "epoch": 3.05, "learning_rate": 4.017267648552565e-06, "loss": 0.1694, "step": 1240 }, { "epoch": 3.05, "learning_rate": 4.012188928390046e-06, "loss": 0.1554, "step": 1241 }, { "epoch": 3.06, "learning_rate": 4.007110208227527e-06, "loss": 0.1495, "step": 1242 }, { "epoch": 3.06, "learning_rate": 4.002031488065008e-06, "loss": 0.1592, "step": 1243 }, { "epoch": 3.06, "learning_rate": 3.9969527679024885e-06, "loss": 0.1391, "step": 1244 }, { "epoch": 3.06, "learning_rate": 3.99187404773997e-06, "loss": 0.1423, "step": 1245 }, { "epoch": 3.07, "learning_rate": 3.9867953275774505e-06, "loss": 0.1515, "step": 1246 }, { "epoch": 3.07, "learning_rate": 3.981716607414932e-06, "loss": 0.1658, "step": 1247 }, { "epoch": 3.07, "learning_rate": 3.9766378872524125e-06, "loss": 0.1414, "step": 1248 }, { "epoch": 3.07, "learning_rate": 3.971559167089893e-06, "loss": 0.1598, "step": 1249 }, { "epoch": 3.08, "learning_rate": 3.9664804469273745e-06, "loss": 0.1622, "step": 1250 }, { "epoch": 3.08, "learning_rate": 3.961401726764856e-06, "loss": 0.1427, "step": 1251 }, { "epoch": 3.08, "learning_rate": 3.9563230066023365e-06, "loss": 0.1577, "step": 1252 }, { "epoch": 3.08, "learning_rate": 3.951244286439818e-06, "loss": 0.1582, "step": 1253 }, { "epoch": 3.09, "learning_rate": 3.9461655662772985e-06, "loss": 0.1614, "step": 1254 }, { "epoch": 3.09, "learning_rate": 3.941086846114779e-06, "loss": 0.1651, "step": 1255 }, { "epoch": 3.09, "learning_rate": 3.9360081259522605e-06, "loss": 0.1524, "step": 1256 }, { "epoch": 3.09, "learning_rate": 3.930929405789741e-06, "loss": 0.1361, "step": 1257 }, { "epoch": 3.1, "learning_rate": 3.9258506856272225e-06, "loss": 0.169, "step": 1258 }, { "epoch": 3.1, "learning_rate": 3.920771965464703e-06, "loss": 0.1447, "step": 1259 }, { "epoch": 3.1, "learning_rate": 3.915693245302184e-06, "loss": 0.1608, "step": 1260 }, { "epoch": 3.1, "learning_rate": 3.910614525139665e-06, "loss": 0.1555, "step": 1261 }, { "epoch": 3.11, "learning_rate": 3.9055358049771465e-06, "loss": 0.1696, "step": 1262 }, { "epoch": 3.11, "learning_rate": 3.900457084814627e-06, "loss": 0.1445, "step": 1263 }, { "epoch": 3.11, "learning_rate": 3.8953783646521085e-06, "loss": 0.1518, "step": 1264 }, { "epoch": 3.11, "learning_rate": 3.890299644489589e-06, "loss": 0.1411, "step": 1265 }, { "epoch": 3.12, "learning_rate": 3.88522092432707e-06, "loss": 0.1481, "step": 1266 }, { "epoch": 3.12, "learning_rate": 3.880142204164551e-06, "loss": 0.1589, "step": 1267 }, { "epoch": 3.12, "learning_rate": 3.875063484002032e-06, "loss": 0.1513, "step": 1268 }, { "epoch": 3.12, "learning_rate": 3.869984763839513e-06, "loss": 0.1707, "step": 1269 }, { "epoch": 3.13, "learning_rate": 3.864906043676994e-06, "loss": 0.1443, "step": 1270 }, { "epoch": 3.13, "learning_rate": 3.859827323514474e-06, "loss": 0.1489, "step": 1271 }, { "epoch": 3.13, "learning_rate": 3.854748603351956e-06, "loss": 0.1409, "step": 1272 }, { "epoch": 3.13, "learning_rate": 3.849669883189436e-06, "loss": 0.1525, "step": 1273 }, { "epoch": 3.14, "learning_rate": 3.844591163026918e-06, "loss": 0.1565, "step": 1274 }, { "epoch": 3.14, "learning_rate": 3.839512442864399e-06, "loss": 0.1618, "step": 1275 }, { "epoch": 3.14, "learning_rate": 3.83443372270188e-06, "loss": 0.1545, "step": 1276 }, { "epoch": 3.14, "learning_rate": 3.82935500253936e-06, "loss": 0.1528, "step": 1277 }, { "epoch": 3.15, "learning_rate": 3.824276282376842e-06, "loss": 0.1635, "step": 1278 }, { "epoch": 3.15, "learning_rate": 3.819197562214322e-06, "loss": 0.1557, "step": 1279 }, { "epoch": 3.15, "learning_rate": 3.8141188420518033e-06, "loss": 0.1492, "step": 1280 }, { "epoch": 3.15, "learning_rate": 3.8090401218892843e-06, "loss": 0.1702, "step": 1281 }, { "epoch": 3.16, "learning_rate": 3.8039614017267653e-06, "loss": 0.1575, "step": 1282 }, { "epoch": 3.16, "learning_rate": 3.798882681564246e-06, "loss": 0.1631, "step": 1283 }, { "epoch": 3.16, "learning_rate": 3.793803961401727e-06, "loss": 0.1385, "step": 1284 }, { "epoch": 3.16, "learning_rate": 3.788725241239208e-06, "loss": 0.1543, "step": 1285 }, { "epoch": 3.17, "learning_rate": 3.783646521076689e-06, "loss": 0.1501, "step": 1286 }, { "epoch": 3.17, "learning_rate": 3.7785678009141703e-06, "loss": 0.1565, "step": 1287 }, { "epoch": 3.17, "learning_rate": 3.7734890807516513e-06, "loss": 0.1655, "step": 1288 }, { "epoch": 3.17, "learning_rate": 3.768410360589132e-06, "loss": 0.1481, "step": 1289 }, { "epoch": 3.17, "learning_rate": 3.763331640426613e-06, "loss": 0.1457, "step": 1290 }, { "epoch": 3.18, "learning_rate": 3.758252920264094e-06, "loss": 0.1682, "step": 1291 }, { "epoch": 3.18, "learning_rate": 3.753174200101575e-06, "loss": 0.1561, "step": 1292 }, { "epoch": 3.18, "learning_rate": 3.748095479939056e-06, "loss": 0.155, "step": 1293 }, { "epoch": 3.18, "learning_rate": 3.7430167597765364e-06, "loss": 0.1565, "step": 1294 }, { "epoch": 3.19, "learning_rate": 3.7379380396140174e-06, "loss": 0.1671, "step": 1295 }, { "epoch": 3.19, "learning_rate": 3.7328593194514984e-06, "loss": 0.1603, "step": 1296 }, { "epoch": 3.19, "learning_rate": 3.7277805992889794e-06, "loss": 0.1684, "step": 1297 }, { "epoch": 3.19, "learning_rate": 3.72270187912646e-06, "loss": 0.1578, "step": 1298 }, { "epoch": 3.2, "learning_rate": 3.717623158963942e-06, "loss": 0.1657, "step": 1299 }, { "epoch": 3.2, "learning_rate": 3.7125444388014224e-06, "loss": 0.141, "step": 1300 }, { "epoch": 3.2, "learning_rate": 3.7074657186389034e-06, "loss": 0.167, "step": 1301 }, { "epoch": 3.2, "learning_rate": 3.7023869984763844e-06, "loss": 0.1702, "step": 1302 }, { "epoch": 3.21, "learning_rate": 3.6973082783138654e-06, "loss": 0.1557, "step": 1303 }, { "epoch": 3.21, "learning_rate": 3.692229558151346e-06, "loss": 0.172, "step": 1304 }, { "epoch": 3.21, "learning_rate": 3.687150837988827e-06, "loss": 0.1782, "step": 1305 }, { "epoch": 3.21, "learning_rate": 3.682072117826308e-06, "loss": 0.1609, "step": 1306 }, { "epoch": 3.22, "learning_rate": 3.676993397663789e-06, "loss": 0.1478, "step": 1307 }, { "epoch": 3.22, "learning_rate": 3.67191467750127e-06, "loss": 0.1472, "step": 1308 }, { "epoch": 3.22, "learning_rate": 3.6668359573387506e-06, "loss": 0.1519, "step": 1309 }, { "epoch": 3.22, "learning_rate": 3.6617572371762316e-06, "loss": 0.1563, "step": 1310 }, { "epoch": 3.23, "learning_rate": 3.6566785170137126e-06, "loss": 0.1775, "step": 1311 }, { "epoch": 3.23, "learning_rate": 3.651599796851194e-06, "loss": 0.1589, "step": 1312 }, { "epoch": 3.23, "learning_rate": 3.646521076688675e-06, "loss": 0.1561, "step": 1313 }, { "epoch": 3.23, "learning_rate": 3.641442356526156e-06, "loss": 0.1641, "step": 1314 }, { "epoch": 3.24, "learning_rate": 3.6363636363636366e-06, "loss": 0.1753, "step": 1315 }, { "epoch": 3.24, "learning_rate": 3.6312849162011176e-06, "loss": 0.1515, "step": 1316 }, { "epoch": 3.24, "learning_rate": 3.6262061960385986e-06, "loss": 0.1553, "step": 1317 }, { "epoch": 3.24, "learning_rate": 3.6211274758760796e-06, "loss": 0.1478, "step": 1318 }, { "epoch": 3.25, "learning_rate": 3.6160487557135606e-06, "loss": 0.1382, "step": 1319 }, { "epoch": 3.25, "learning_rate": 3.610970035551041e-06, "loss": 0.1652, "step": 1320 }, { "epoch": 3.25, "learning_rate": 3.605891315388522e-06, "loss": 0.1579, "step": 1321 }, { "epoch": 3.25, "learning_rate": 3.600812595226003e-06, "loss": 0.1425, "step": 1322 }, { "epoch": 3.26, "learning_rate": 3.595733875063484e-06, "loss": 0.1498, "step": 1323 }, { "epoch": 3.26, "learning_rate": 3.5906551549009656e-06, "loss": 0.1742, "step": 1324 }, { "epoch": 3.26, "learning_rate": 3.5855764347384466e-06, "loss": 0.1671, "step": 1325 }, { "epoch": 3.26, "learning_rate": 3.580497714575927e-06, "loss": 0.1586, "step": 1326 }, { "epoch": 3.27, "learning_rate": 3.575418994413408e-06, "loss": 0.1755, "step": 1327 }, { "epoch": 3.27, "learning_rate": 3.570340274250889e-06, "loss": 0.1785, "step": 1328 }, { "epoch": 3.27, "learning_rate": 3.56526155408837e-06, "loss": 0.1594, "step": 1329 }, { "epoch": 3.27, "learning_rate": 3.5601828339258507e-06, "loss": 0.1605, "step": 1330 }, { "epoch": 3.28, "learning_rate": 3.5551041137633317e-06, "loss": 0.154, "step": 1331 }, { "epoch": 3.28, "learning_rate": 3.5500253936008127e-06, "loss": 0.1586, "step": 1332 }, { "epoch": 3.28, "learning_rate": 3.5449466734382937e-06, "loss": 0.1665, "step": 1333 }, { "epoch": 3.28, "learning_rate": 3.5398679532757747e-06, "loss": 0.1692, "step": 1334 }, { "epoch": 3.29, "learning_rate": 3.5347892331132553e-06, "loss": 0.1471, "step": 1335 }, { "epoch": 3.29, "learning_rate": 3.529710512950737e-06, "loss": 0.1583, "step": 1336 }, { "epoch": 3.29, "learning_rate": 3.5246317927882178e-06, "loss": 0.1674, "step": 1337 }, { "epoch": 3.29, "learning_rate": 3.5195530726256988e-06, "loss": 0.1732, "step": 1338 }, { "epoch": 3.3, "learning_rate": 3.5144743524631798e-06, "loss": 0.1442, "step": 1339 }, { "epoch": 3.3, "learning_rate": 3.5093956323006608e-06, "loss": 0.1549, "step": 1340 }, { "epoch": 3.3, "learning_rate": 3.5043169121381413e-06, "loss": 0.1699, "step": 1341 }, { "epoch": 3.3, "learning_rate": 3.4992381919756223e-06, "loss": 0.1632, "step": 1342 }, { "epoch": 3.31, "learning_rate": 3.4941594718131033e-06, "loss": 0.1594, "step": 1343 }, { "epoch": 3.31, "learning_rate": 3.4890807516505843e-06, "loss": 0.1469, "step": 1344 }, { "epoch": 3.31, "learning_rate": 3.4840020314880653e-06, "loss": 0.1371, "step": 1345 }, { "epoch": 3.31, "learning_rate": 3.478923311325546e-06, "loss": 0.1596, "step": 1346 }, { "epoch": 3.32, "learning_rate": 3.473844591163027e-06, "loss": 0.1641, "step": 1347 }, { "epoch": 3.32, "learning_rate": 3.468765871000508e-06, "loss": 0.1476, "step": 1348 }, { "epoch": 3.32, "learning_rate": 3.4636871508379893e-06, "loss": 0.1521, "step": 1349 }, { "epoch": 3.32, "learning_rate": 3.4586084306754703e-06, "loss": 0.1585, "step": 1350 }, { "epoch": 3.33, "learning_rate": 3.4535297105129513e-06, "loss": 0.1665, "step": 1351 }, { "epoch": 3.33, "learning_rate": 3.448450990350432e-06, "loss": 0.1745, "step": 1352 }, { "epoch": 3.33, "learning_rate": 3.443372270187913e-06, "loss": 0.1692, "step": 1353 }, { "epoch": 3.33, "learning_rate": 3.438293550025394e-06, "loss": 0.1561, "step": 1354 }, { "epoch": 3.33, "learning_rate": 3.433214829862875e-06, "loss": 0.15, "step": 1355 }, { "epoch": 3.34, "learning_rate": 3.428136109700356e-06, "loss": 0.163, "step": 1356 }, { "epoch": 3.34, "learning_rate": 3.4230573895378365e-06, "loss": 0.1649, "step": 1357 }, { "epoch": 3.34, "learning_rate": 3.4179786693753175e-06, "loss": 0.1472, "step": 1358 }, { "epoch": 3.34, "learning_rate": 3.4128999492127985e-06, "loss": 0.1575, "step": 1359 }, { "epoch": 3.35, "learning_rate": 3.4078212290502795e-06, "loss": 0.1541, "step": 1360 }, { "epoch": 3.35, "learning_rate": 3.402742508887761e-06, "loss": 0.1634, "step": 1361 }, { "epoch": 3.35, "learning_rate": 3.397663788725242e-06, "loss": 0.1695, "step": 1362 }, { "epoch": 3.35, "learning_rate": 3.3925850685627225e-06, "loss": 0.1499, "step": 1363 }, { "epoch": 3.36, "learning_rate": 3.3875063484002035e-06, "loss": 0.1714, "step": 1364 }, { "epoch": 3.36, "learning_rate": 3.3824276282376845e-06, "loss": 0.1647, "step": 1365 }, { "epoch": 3.36, "learning_rate": 3.3773489080751655e-06, "loss": 0.1645, "step": 1366 }, { "epoch": 3.36, "learning_rate": 3.372270187912646e-06, "loss": 0.1619, "step": 1367 }, { "epoch": 3.37, "learning_rate": 3.367191467750127e-06, "loss": 0.1595, "step": 1368 }, { "epoch": 3.37, "learning_rate": 3.362112747587608e-06, "loss": 0.1558, "step": 1369 }, { "epoch": 3.37, "learning_rate": 3.357034027425089e-06, "loss": 0.1633, "step": 1370 }, { "epoch": 3.37, "learning_rate": 3.35195530726257e-06, "loss": 0.163, "step": 1371 }, { "epoch": 3.38, "learning_rate": 3.3468765871000507e-06, "loss": 0.1535, "step": 1372 }, { "epoch": 3.38, "learning_rate": 3.341797866937532e-06, "loss": 0.1384, "step": 1373 }, { "epoch": 3.38, "learning_rate": 3.336719146775013e-06, "loss": 0.1604, "step": 1374 }, { "epoch": 3.38, "learning_rate": 3.331640426612494e-06, "loss": 0.161, "step": 1375 }, { "epoch": 3.39, "learning_rate": 3.326561706449975e-06, "loss": 0.1594, "step": 1376 }, { "epoch": 3.39, "learning_rate": 3.321482986287456e-06, "loss": 0.1548, "step": 1377 }, { "epoch": 3.39, "learning_rate": 3.3164042661249367e-06, "loss": 0.1413, "step": 1378 }, { "epoch": 3.39, "learning_rate": 3.3113255459624177e-06, "loss": 0.1543, "step": 1379 }, { "epoch": 3.4, "learning_rate": 3.3062468257998987e-06, "loss": 0.1651, "step": 1380 }, { "epoch": 3.4, "learning_rate": 3.3011681056373797e-06, "loss": 0.1528, "step": 1381 }, { "epoch": 3.4, "learning_rate": 3.2960893854748607e-06, "loss": 0.1658, "step": 1382 }, { "epoch": 3.4, "learning_rate": 3.2910106653123412e-06, "loss": 0.1567, "step": 1383 }, { "epoch": 3.41, "learning_rate": 3.2859319451498222e-06, "loss": 0.1668, "step": 1384 }, { "epoch": 3.41, "learning_rate": 3.2808532249873037e-06, "loss": 0.147, "step": 1385 }, { "epoch": 3.41, "learning_rate": 3.2757745048247847e-06, "loss": 0.1657, "step": 1386 }, { "epoch": 3.41, "learning_rate": 3.2706957846622657e-06, "loss": 0.1615, "step": 1387 }, { "epoch": 3.42, "learning_rate": 3.2656170644997467e-06, "loss": 0.159, "step": 1388 }, { "epoch": 3.42, "learning_rate": 3.2605383443372272e-06, "loss": 0.1579, "step": 1389 }, { "epoch": 3.42, "learning_rate": 3.2554596241747082e-06, "loss": 0.1646, "step": 1390 }, { "epoch": 3.42, "learning_rate": 3.2503809040121892e-06, "loss": 0.1461, "step": 1391 }, { "epoch": 3.43, "learning_rate": 3.2453021838496702e-06, "loss": 0.1488, "step": 1392 }, { "epoch": 3.43, "learning_rate": 3.240223463687151e-06, "loss": 0.1697, "step": 1393 }, { "epoch": 3.43, "learning_rate": 3.235144743524632e-06, "loss": 0.1637, "step": 1394 }, { "epoch": 3.43, "learning_rate": 3.230066023362113e-06, "loss": 0.1574, "step": 1395 }, { "epoch": 3.44, "learning_rate": 3.224987303199594e-06, "loss": 0.1567, "step": 1396 }, { "epoch": 3.44, "learning_rate": 3.219908583037075e-06, "loss": 0.1551, "step": 1397 }, { "epoch": 3.44, "learning_rate": 3.2148298628745562e-06, "loss": 0.1668, "step": 1398 }, { "epoch": 3.44, "learning_rate": 3.209751142712037e-06, "loss": 0.1682, "step": 1399 }, { "epoch": 3.45, "learning_rate": 3.204672422549518e-06, "loss": 0.1545, "step": 1400 }, { "epoch": 3.45, "learning_rate": 3.199593702386999e-06, "loss": 0.1599, "step": 1401 }, { "epoch": 3.45, "learning_rate": 3.19451498222448e-06, "loss": 0.1458, "step": 1402 }, { "epoch": 3.45, "learning_rate": 3.189436262061961e-06, "loss": 0.1613, "step": 1403 }, { "epoch": 3.46, "learning_rate": 3.1843575418994414e-06, "loss": 0.1649, "step": 1404 }, { "epoch": 3.46, "learning_rate": 3.1792788217369224e-06, "loss": 0.1467, "step": 1405 }, { "epoch": 3.46, "learning_rate": 3.1742001015744034e-06, "loss": 0.1617, "step": 1406 }, { "epoch": 3.46, "learning_rate": 3.1691213814118844e-06, "loss": 0.1537, "step": 1407 }, { "epoch": 3.47, "learning_rate": 3.1640426612493654e-06, "loss": 0.1642, "step": 1408 }, { "epoch": 3.47, "learning_rate": 3.158963941086846e-06, "loss": 0.1431, "step": 1409 }, { "epoch": 3.47, "learning_rate": 3.1538852209243274e-06, "loss": 0.1608, "step": 1410 }, { "epoch": 3.47, "learning_rate": 3.1488065007618084e-06, "loss": 0.1673, "step": 1411 }, { "epoch": 3.48, "learning_rate": 3.1437277805992894e-06, "loss": 0.1635, "step": 1412 }, { "epoch": 3.48, "learning_rate": 3.1386490604367704e-06, "loss": 0.1533, "step": 1413 }, { "epoch": 3.48, "learning_rate": 3.1335703402742514e-06, "loss": 0.1747, "step": 1414 }, { "epoch": 3.48, "learning_rate": 3.128491620111732e-06, "loss": 0.1561, "step": 1415 }, { "epoch": 3.49, "learning_rate": 3.123412899949213e-06, "loss": 0.17, "step": 1416 }, { "epoch": 3.49, "learning_rate": 3.118334179786694e-06, "loss": 0.1628, "step": 1417 }, { "epoch": 3.49, "learning_rate": 3.113255459624175e-06, "loss": 0.1556, "step": 1418 }, { "epoch": 3.49, "learning_rate": 3.1081767394616556e-06, "loss": 0.1503, "step": 1419 }, { "epoch": 3.49, "learning_rate": 3.1030980192991366e-06, "loss": 0.1596, "step": 1420 }, { "epoch": 3.5, "learning_rate": 3.0980192991366176e-06, "loss": 0.1568, "step": 1421 }, { "epoch": 3.5, "learning_rate": 3.092940578974099e-06, "loss": 0.1691, "step": 1422 }, { "epoch": 3.5, "learning_rate": 3.08786185881158e-06, "loss": 0.1481, "step": 1423 }, { "epoch": 3.5, "learning_rate": 3.082783138649061e-06, "loss": 0.1558, "step": 1424 }, { "epoch": 3.51, "learning_rate": 3.0777044184865416e-06, "loss": 0.1569, "step": 1425 }, { "epoch": 3.51, "learning_rate": 3.0726256983240226e-06, "loss": 0.1494, "step": 1426 }, { "epoch": 3.51, "learning_rate": 3.0675469781615036e-06, "loss": 0.1599, "step": 1427 }, { "epoch": 3.51, "learning_rate": 3.0624682579989846e-06, "loss": 0.1572, "step": 1428 }, { "epoch": 3.52, "learning_rate": 3.0573895378364656e-06, "loss": 0.146, "step": 1429 }, { "epoch": 3.52, "learning_rate": 3.052310817673946e-06, "loss": 0.1619, "step": 1430 }, { "epoch": 3.52, "learning_rate": 3.047232097511427e-06, "loss": 0.1518, "step": 1431 }, { "epoch": 3.52, "learning_rate": 3.042153377348908e-06, "loss": 0.1599, "step": 1432 }, { "epoch": 3.53, "learning_rate": 3.037074657186389e-06, "loss": 0.1638, "step": 1433 }, { "epoch": 3.53, "learning_rate": 3.03199593702387e-06, "loss": 0.1465, "step": 1434 }, { "epoch": 3.53, "learning_rate": 3.0269172168613516e-06, "loss": 0.1475, "step": 1435 }, { "epoch": 3.53, "learning_rate": 3.021838496698832e-06, "loss": 0.1556, "step": 1436 }, { "epoch": 3.54, "learning_rate": 3.016759776536313e-06, "loss": 0.1618, "step": 1437 }, { "epoch": 3.54, "learning_rate": 3.011681056373794e-06, "loss": 0.1656, "step": 1438 }, { "epoch": 3.54, "learning_rate": 3.006602336211275e-06, "loss": 0.1628, "step": 1439 }, { "epoch": 3.54, "learning_rate": 3.001523616048756e-06, "loss": 0.1488, "step": 1440 }, { "epoch": 3.55, "learning_rate": 2.9964448958862367e-06, "loss": 0.1606, "step": 1441 }, { "epoch": 3.55, "learning_rate": 2.9913661757237177e-06, "loss": 0.1576, "step": 1442 }, { "epoch": 3.55, "learning_rate": 2.9862874555611987e-06, "loss": 0.1619, "step": 1443 }, { "epoch": 3.55, "learning_rate": 2.9812087353986797e-06, "loss": 0.1479, "step": 1444 }, { "epoch": 3.56, "learning_rate": 2.9761300152361603e-06, "loss": 0.154, "step": 1445 }, { "epoch": 3.56, "learning_rate": 2.9710512950736413e-06, "loss": 0.1542, "step": 1446 }, { "epoch": 3.56, "learning_rate": 2.9659725749111227e-06, "loss": 0.1667, "step": 1447 }, { "epoch": 3.56, "learning_rate": 2.9608938547486037e-06, "loss": 0.1705, "step": 1448 }, { "epoch": 3.57, "learning_rate": 2.9558151345860847e-06, "loss": 0.1614, "step": 1449 }, { "epoch": 3.57, "learning_rate": 2.9507364144235657e-06, "loss": 0.1558, "step": 1450 }, { "epoch": 3.57, "learning_rate": 2.9456576942610467e-06, "loss": 0.1584, "step": 1451 }, { "epoch": 3.57, "learning_rate": 2.9405789740985273e-06, "loss": 0.1526, "step": 1452 }, { "epoch": 3.58, "learning_rate": 2.9355002539360083e-06, "loss": 0.1638, "step": 1453 }, { "epoch": 3.58, "learning_rate": 2.9304215337734893e-06, "loss": 0.1706, "step": 1454 }, { "epoch": 3.58, "learning_rate": 2.9253428136109703e-06, "loss": 0.1619, "step": 1455 }, { "epoch": 3.58, "learning_rate": 2.920264093448451e-06, "loss": 0.1579, "step": 1456 }, { "epoch": 3.59, "learning_rate": 2.915185373285932e-06, "loss": 0.1674, "step": 1457 }, { "epoch": 3.59, "learning_rate": 2.910106653123413e-06, "loss": 0.1682, "step": 1458 }, { "epoch": 3.59, "learning_rate": 2.9050279329608943e-06, "loss": 0.1473, "step": 1459 }, { "epoch": 3.59, "learning_rate": 2.8999492127983753e-06, "loss": 0.1522, "step": 1460 }, { "epoch": 3.6, "learning_rate": 2.8948704926358563e-06, "loss": 0.1618, "step": 1461 }, { "epoch": 3.6, "learning_rate": 2.889791772473337e-06, "loss": 0.1612, "step": 1462 }, { "epoch": 3.6, "learning_rate": 2.884713052310818e-06, "loss": 0.146, "step": 1463 }, { "epoch": 3.6, "learning_rate": 2.879634332148299e-06, "loss": 0.1502, "step": 1464 }, { "epoch": 3.61, "learning_rate": 2.87455561198578e-06, "loss": 0.1529, "step": 1465 }, { "epoch": 3.61, "learning_rate": 2.869476891823261e-06, "loss": 0.1635, "step": 1466 }, { "epoch": 3.61, "learning_rate": 2.8643981716607415e-06, "loss": 0.1493, "step": 1467 }, { "epoch": 3.61, "learning_rate": 2.8593194514982225e-06, "loss": 0.1652, "step": 1468 }, { "epoch": 3.62, "learning_rate": 2.8542407313357035e-06, "loss": 0.1543, "step": 1469 }, { "epoch": 3.62, "learning_rate": 2.8491620111731845e-06, "loss": 0.1458, "step": 1470 }, { "epoch": 3.62, "learning_rate": 2.844083291010665e-06, "loss": 0.1603, "step": 1471 }, { "epoch": 3.62, "learning_rate": 2.839004570848147e-06, "loss": 0.1626, "step": 1472 }, { "epoch": 3.63, "learning_rate": 2.8339258506856275e-06, "loss": 0.1639, "step": 1473 }, { "epoch": 3.63, "learning_rate": 2.8288471305231085e-06, "loss": 0.1595, "step": 1474 }, { "epoch": 3.63, "learning_rate": 2.8237684103605895e-06, "loss": 0.1536, "step": 1475 }, { "epoch": 3.63, "learning_rate": 2.8186896901980705e-06, "loss": 0.162, "step": 1476 }, { "epoch": 3.64, "learning_rate": 2.8136109700355515e-06, "loss": 0.1541, "step": 1477 }, { "epoch": 3.64, "learning_rate": 2.808532249873032e-06, "loss": 0.1593, "step": 1478 }, { "epoch": 3.64, "learning_rate": 2.803453529710513e-06, "loss": 0.1536, "step": 1479 }, { "epoch": 3.64, "learning_rate": 2.798374809547994e-06, "loss": 0.1669, "step": 1480 }, { "epoch": 3.64, "learning_rate": 2.793296089385475e-06, "loss": 0.1659, "step": 1481 }, { "epoch": 3.65, "learning_rate": 2.7882173692229556e-06, "loss": 0.1717, "step": 1482 }, { "epoch": 3.65, "learning_rate": 2.7831386490604366e-06, "loss": 0.1773, "step": 1483 }, { "epoch": 3.65, "learning_rate": 2.778059928897918e-06, "loss": 0.1503, "step": 1484 }, { "epoch": 3.65, "learning_rate": 2.772981208735399e-06, "loss": 0.165, "step": 1485 }, { "epoch": 3.66, "learning_rate": 2.76790248857288e-06, "loss": 0.1492, "step": 1486 }, { "epoch": 3.66, "learning_rate": 2.762823768410361e-06, "loss": 0.169, "step": 1487 }, { "epoch": 3.66, "learning_rate": 2.7577450482478416e-06, "loss": 0.1594, "step": 1488 }, { "epoch": 3.66, "learning_rate": 2.7526663280853226e-06, "loss": 0.1609, "step": 1489 }, { "epoch": 3.67, "learning_rate": 2.7475876079228036e-06, "loss": 0.1545, "step": 1490 }, { "epoch": 3.67, "learning_rate": 2.7425088877602846e-06, "loss": 0.1486, "step": 1491 }, { "epoch": 3.67, "learning_rate": 2.7374301675977656e-06, "loss": 0.1563, "step": 1492 }, { "epoch": 3.67, "learning_rate": 2.7323514474352462e-06, "loss": 0.1708, "step": 1493 }, { "epoch": 3.68, "learning_rate": 2.7272727272727272e-06, "loss": 0.153, "step": 1494 }, { "epoch": 3.68, "learning_rate": 2.7221940071102082e-06, "loss": 0.1496, "step": 1495 }, { "epoch": 3.68, "learning_rate": 2.7171152869476897e-06, "loss": 0.1642, "step": 1496 }, { "epoch": 3.68, "learning_rate": 2.7120365667851707e-06, "loss": 0.1691, "step": 1497 }, { "epoch": 3.69, "learning_rate": 2.7069578466226517e-06, "loss": 0.1734, "step": 1498 }, { "epoch": 3.69, "learning_rate": 2.7018791264601322e-06, "loss": 0.1501, "step": 1499 }, { "epoch": 3.69, "learning_rate": 2.6968004062976132e-06, "loss": 0.1498, "step": 1500 }, { "epoch": 3.69, "learning_rate": 2.6917216861350942e-06, "loss": 0.1529, "step": 1501 }, { "epoch": 3.7, "learning_rate": 2.6866429659725752e-06, "loss": 0.1727, "step": 1502 }, { "epoch": 3.7, "learning_rate": 2.6815642458100562e-06, "loss": 0.1671, "step": 1503 }, { "epoch": 3.7, "learning_rate": 2.676485525647537e-06, "loss": 0.1503, "step": 1504 }, { "epoch": 3.7, "learning_rate": 2.671406805485018e-06, "loss": 0.1538, "step": 1505 }, { "epoch": 3.71, "learning_rate": 2.666328085322499e-06, "loss": 0.1657, "step": 1506 }, { "epoch": 3.71, "learning_rate": 2.66124936515998e-06, "loss": 0.154, "step": 1507 }, { "epoch": 3.71, "learning_rate": 2.6561706449974612e-06, "loss": 0.1589, "step": 1508 }, { "epoch": 3.71, "learning_rate": 2.6510919248349422e-06, "loss": 0.1843, "step": 1509 }, { "epoch": 3.72, "learning_rate": 2.646013204672423e-06, "loss": 0.1662, "step": 1510 }, { "epoch": 3.72, "learning_rate": 2.640934484509904e-06, "loss": 0.1494, "step": 1511 }, { "epoch": 3.72, "learning_rate": 2.635855764347385e-06, "loss": 0.17, "step": 1512 }, { "epoch": 3.72, "learning_rate": 2.630777044184866e-06, "loss": 0.1682, "step": 1513 }, { "epoch": 3.73, "learning_rate": 2.6256983240223464e-06, "loss": 0.17, "step": 1514 }, { "epoch": 3.73, "learning_rate": 2.6206196038598274e-06, "loss": 0.1639, "step": 1515 }, { "epoch": 3.73, "learning_rate": 2.6155408836973084e-06, "loss": 0.1591, "step": 1516 }, { "epoch": 3.73, "learning_rate": 2.6104621635347894e-06, "loss": 0.1444, "step": 1517 }, { "epoch": 3.74, "learning_rate": 2.6053834433722704e-06, "loss": 0.1486, "step": 1518 }, { "epoch": 3.74, "learning_rate": 2.600304723209751e-06, "loss": 0.1553, "step": 1519 }, { "epoch": 3.74, "learning_rate": 2.595226003047232e-06, "loss": 0.1596, "step": 1520 }, { "epoch": 3.74, "learning_rate": 2.5901472828847134e-06, "loss": 0.1674, "step": 1521 }, { "epoch": 3.75, "learning_rate": 2.5850685627221944e-06, "loss": 0.1577, "step": 1522 }, { "epoch": 3.75, "learning_rate": 2.5799898425596754e-06, "loss": 0.1491, "step": 1523 }, { "epoch": 3.75, "learning_rate": 2.5749111223971564e-06, "loss": 0.1534, "step": 1524 }, { "epoch": 3.75, "learning_rate": 2.569832402234637e-06, "loss": 0.1568, "step": 1525 }, { "epoch": 3.76, "learning_rate": 2.564753682072118e-06, "loss": 0.1421, "step": 1526 }, { "epoch": 3.76, "learning_rate": 2.559674961909599e-06, "loss": 0.1537, "step": 1527 }, { "epoch": 3.76, "learning_rate": 2.55459624174708e-06, "loss": 0.1635, "step": 1528 }, { "epoch": 3.76, "learning_rate": 2.549517521584561e-06, "loss": 0.1481, "step": 1529 }, { "epoch": 3.77, "learning_rate": 2.5444388014220416e-06, "loss": 0.1447, "step": 1530 }, { "epoch": 3.77, "learning_rate": 2.5393600812595226e-06, "loss": 0.146, "step": 1531 }, { "epoch": 3.77, "learning_rate": 2.5342813610970036e-06, "loss": 0.1693, "step": 1532 }, { "epoch": 3.77, "learning_rate": 2.529202640934485e-06, "loss": 0.172, "step": 1533 }, { "epoch": 3.78, "learning_rate": 2.524123920771966e-06, "loss": 0.1555, "step": 1534 }, { "epoch": 3.78, "learning_rate": 2.519045200609447e-06, "loss": 0.1689, "step": 1535 }, { "epoch": 3.78, "learning_rate": 2.5139664804469276e-06, "loss": 0.157, "step": 1536 }, { "epoch": 3.78, "learning_rate": 2.5088877602844086e-06, "loss": 0.1659, "step": 1537 }, { "epoch": 3.79, "learning_rate": 2.5038090401218896e-06, "loss": 0.139, "step": 1538 }, { "epoch": 3.79, "learning_rate": 2.4987303199593706e-06, "loss": 0.1512, "step": 1539 }, { "epoch": 3.79, "learning_rate": 2.493651599796851e-06, "loss": 0.1498, "step": 1540 }, { "epoch": 3.79, "learning_rate": 2.488572879634332e-06, "loss": 0.1532, "step": 1541 }, { "epoch": 3.8, "learning_rate": 2.4834941594718136e-06, "loss": 0.1495, "step": 1542 }, { "epoch": 3.8, "learning_rate": 2.478415439309294e-06, "loss": 0.1507, "step": 1543 }, { "epoch": 3.8, "learning_rate": 2.473336719146775e-06, "loss": 0.1525, "step": 1544 }, { "epoch": 3.8, "learning_rate": 2.468257998984256e-06, "loss": 0.1637, "step": 1545 }, { "epoch": 3.8, "learning_rate": 2.463179278821737e-06, "loss": 0.1651, "step": 1546 }, { "epoch": 3.81, "learning_rate": 2.458100558659218e-06, "loss": 0.1802, "step": 1547 }, { "epoch": 3.81, "learning_rate": 2.453021838496699e-06, "loss": 0.1486, "step": 1548 }, { "epoch": 3.81, "learning_rate": 2.44794311833418e-06, "loss": 0.1537, "step": 1549 }, { "epoch": 3.81, "learning_rate": 2.442864398171661e-06, "loss": 0.1707, "step": 1550 }, { "epoch": 3.82, "learning_rate": 2.4377856780091417e-06, "loss": 0.1409, "step": 1551 }, { "epoch": 3.82, "learning_rate": 2.4327069578466227e-06, "loss": 0.1434, "step": 1552 }, { "epoch": 3.82, "learning_rate": 2.4276282376841037e-06, "loss": 0.1589, "step": 1553 }, { "epoch": 3.82, "learning_rate": 2.4225495175215847e-06, "loss": 0.1592, "step": 1554 }, { "epoch": 3.83, "learning_rate": 2.4174707973590657e-06, "loss": 0.165, "step": 1555 }, { "epoch": 3.83, "learning_rate": 2.4123920771965467e-06, "loss": 0.143, "step": 1556 }, { "epoch": 3.83, "learning_rate": 2.4073133570340277e-06, "loss": 0.1509, "step": 1557 }, { "epoch": 3.83, "learning_rate": 2.4022346368715087e-06, "loss": 0.1682, "step": 1558 }, { "epoch": 3.84, "learning_rate": 2.3971559167089893e-06, "loss": 0.1582, "step": 1559 }, { "epoch": 3.84, "learning_rate": 2.3920771965464703e-06, "loss": 0.1592, "step": 1560 }, { "epoch": 3.84, "learning_rate": 2.3869984763839517e-06, "loss": 0.1408, "step": 1561 }, { "epoch": 3.84, "learning_rate": 2.3819197562214323e-06, "loss": 0.1594, "step": 1562 }, { "epoch": 3.85, "learning_rate": 2.3768410360589133e-06, "loss": 0.1546, "step": 1563 }, { "epoch": 3.85, "learning_rate": 2.3717623158963943e-06, "loss": 0.16, "step": 1564 }, { "epoch": 3.85, "learning_rate": 2.3666835957338753e-06, "loss": 0.1414, "step": 1565 }, { "epoch": 3.85, "learning_rate": 2.361604875571356e-06, "loss": 0.159, "step": 1566 }, { "epoch": 3.86, "learning_rate": 2.3565261554088373e-06, "loss": 0.1529, "step": 1567 }, { "epoch": 3.86, "learning_rate": 2.3514474352463183e-06, "loss": 0.1498, "step": 1568 }, { "epoch": 3.86, "learning_rate": 2.3463687150837993e-06, "loss": 0.1726, "step": 1569 }, { "epoch": 3.86, "learning_rate": 2.34128999492128e-06, "loss": 0.1595, "step": 1570 }, { "epoch": 3.87, "learning_rate": 2.336211274758761e-06, "loss": 0.1526, "step": 1571 }, { "epoch": 3.87, "learning_rate": 2.331132554596242e-06, "loss": 0.1468, "step": 1572 }, { "epoch": 3.87, "learning_rate": 2.326053834433723e-06, "loss": 0.155, "step": 1573 }, { "epoch": 3.87, "learning_rate": 2.320975114271204e-06, "loss": 0.1667, "step": 1574 }, { "epoch": 3.88, "learning_rate": 2.315896394108685e-06, "loss": 0.1534, "step": 1575 }, { "epoch": 3.88, "learning_rate": 2.310817673946166e-06, "loss": 0.1658, "step": 1576 }, { "epoch": 3.88, "learning_rate": 2.3057389537836465e-06, "loss": 0.1454, "step": 1577 }, { "epoch": 3.88, "learning_rate": 2.3006602336211275e-06, "loss": 0.1636, "step": 1578 }, { "epoch": 3.89, "learning_rate": 2.295581513458609e-06, "loss": 0.1599, "step": 1579 }, { "epoch": 3.89, "learning_rate": 2.2905027932960895e-06, "loss": 0.1624, "step": 1580 }, { "epoch": 3.89, "learning_rate": 2.2854240731335705e-06, "loss": 0.1588, "step": 1581 }, { "epoch": 3.89, "learning_rate": 2.2803453529710515e-06, "loss": 0.1573, "step": 1582 }, { "epoch": 3.9, "learning_rate": 2.2752666328085325e-06, "loss": 0.1522, "step": 1583 }, { "epoch": 3.9, "learning_rate": 2.2701879126460135e-06, "loss": 0.1592, "step": 1584 }, { "epoch": 3.9, "learning_rate": 2.2651091924834945e-06, "loss": 0.1395, "step": 1585 }, { "epoch": 3.9, "learning_rate": 2.2600304723209755e-06, "loss": 0.1514, "step": 1586 }, { "epoch": 3.91, "learning_rate": 2.2549517521584565e-06, "loss": 0.158, "step": 1587 }, { "epoch": 3.91, "learning_rate": 2.249873031995937e-06, "loss": 0.1439, "step": 1588 }, { "epoch": 3.91, "learning_rate": 2.244794311833418e-06, "loss": 0.1692, "step": 1589 }, { "epoch": 3.91, "learning_rate": 2.239715591670899e-06, "loss": 0.1636, "step": 1590 }, { "epoch": 3.92, "learning_rate": 2.23463687150838e-06, "loss": 0.1447, "step": 1591 }, { "epoch": 3.92, "learning_rate": 2.229558151345861e-06, "loss": 0.1543, "step": 1592 }, { "epoch": 3.92, "learning_rate": 2.224479431183342e-06, "loss": 0.1546, "step": 1593 }, { "epoch": 3.92, "learning_rate": 2.219400711020823e-06, "loss": 0.1618, "step": 1594 }, { "epoch": 3.93, "learning_rate": 2.214321990858304e-06, "loss": 0.1534, "step": 1595 }, { "epoch": 3.93, "learning_rate": 2.2092432706957846e-06, "loss": 0.154, "step": 1596 }, { "epoch": 3.93, "learning_rate": 2.2041645505332656e-06, "loss": 0.1649, "step": 1597 }, { "epoch": 3.93, "learning_rate": 2.199085830370747e-06, "loss": 0.1562, "step": 1598 }, { "epoch": 3.94, "learning_rate": 2.1940071102082276e-06, "loss": 0.169, "step": 1599 }, { "epoch": 3.94, "learning_rate": 2.1889283900457086e-06, "loss": 0.1497, "step": 1600 }, { "epoch": 3.94, "learning_rate": 2.1838496698831896e-06, "loss": 0.1587, "step": 1601 }, { "epoch": 3.94, "learning_rate": 2.1787709497206706e-06, "loss": 0.1603, "step": 1602 }, { "epoch": 3.95, "learning_rate": 2.1736922295581512e-06, "loss": 0.1556, "step": 1603 }, { "epoch": 3.95, "learning_rate": 2.1686135093956326e-06, "loss": 0.1485, "step": 1604 }, { "epoch": 3.95, "learning_rate": 2.1635347892331136e-06, "loss": 0.1524, "step": 1605 }, { "epoch": 3.95, "learning_rate": 2.1584560690705942e-06, "loss": 0.1682, "step": 1606 }, { "epoch": 3.96, "learning_rate": 2.1533773489080752e-06, "loss": 0.1476, "step": 1607 }, { "epoch": 3.96, "learning_rate": 2.1482986287455562e-06, "loss": 0.1631, "step": 1608 }, { "epoch": 3.96, "learning_rate": 2.1432199085830372e-06, "loss": 0.1591, "step": 1609 }, { "epoch": 3.96, "learning_rate": 2.1381411884205182e-06, "loss": 0.1619, "step": 1610 }, { "epoch": 3.96, "learning_rate": 2.1330624682579992e-06, "loss": 0.1756, "step": 1611 }, { "epoch": 3.97, "learning_rate": 2.1279837480954802e-06, "loss": 0.1543, "step": 1612 }, { "epoch": 3.97, "learning_rate": 2.1229050279329612e-06, "loss": 0.1632, "step": 1613 }, { "epoch": 3.97, "learning_rate": 2.117826307770442e-06, "loss": 0.1572, "step": 1614 }, { "epoch": 3.97, "learning_rate": 2.112747587607923e-06, "loss": 0.1601, "step": 1615 }, { "epoch": 3.98, "learning_rate": 2.1076688674454042e-06, "loss": 0.1638, "step": 1616 }, { "epoch": 3.98, "learning_rate": 2.102590147282885e-06, "loss": 0.1558, "step": 1617 }, { "epoch": 3.98, "learning_rate": 2.097511427120366e-06, "loss": 0.1624, "step": 1618 }, { "epoch": 3.98, "learning_rate": 2.092432706957847e-06, "loss": 0.156, "step": 1619 }, { "epoch": 3.99, "learning_rate": 2.087353986795328e-06, "loss": 0.159, "step": 1620 }, { "epoch": 3.99, "learning_rate": 2.082275266632809e-06, "loss": 0.1576, "step": 1621 }, { "epoch": 3.99, "learning_rate": 2.07719654647029e-06, "loss": 0.158, "step": 1622 }, { "epoch": 3.99, "learning_rate": 2.072117826307771e-06, "loss": 0.1472, "step": 1623 }, { "epoch": 4.0, "learning_rate": 2.067039106145252e-06, "loss": 0.1614, "step": 1624 }, { "epoch": 4.0, "learning_rate": 2.0619603859827324e-06, "loss": 0.1725, "step": 1625 }, { "epoch": 4.0, "learning_rate": 2.0568816658202134e-06, "loss": 0.0988, "step": 1626 }, { "epoch": 4.0, "learning_rate": 2.0518029456576944e-06, "loss": 0.0918, "step": 1627 }, { "epoch": 4.01, "learning_rate": 2.0467242254951754e-06, "loss": 0.0865, "step": 1628 }, { "epoch": 4.01, "learning_rate": 2.0416455053326564e-06, "loss": 0.1001, "step": 1629 }, { "epoch": 4.01, "learning_rate": 2.0365667851701374e-06, "loss": 0.0915, "step": 1630 }, { "epoch": 4.01, "learning_rate": 2.0314880650076184e-06, "loss": 0.0875, "step": 1631 }, { "epoch": 4.02, "learning_rate": 2.026409344845099e-06, "loss": 0.0819, "step": 1632 }, { "epoch": 4.02, "learning_rate": 2.02133062468258e-06, "loss": 0.0942, "step": 1633 }, { "epoch": 4.02, "learning_rate": 2.016251904520061e-06, "loss": 0.0836, "step": 1634 }, { "epoch": 4.02, "learning_rate": 2.011173184357542e-06, "loss": 0.0947, "step": 1635 }, { "epoch": 4.03, "learning_rate": 2.006094464195023e-06, "loss": 0.0887, "step": 1636 }, { "epoch": 4.03, "learning_rate": 2.001015744032504e-06, "loss": 0.0844, "step": 1637 }, { "epoch": 4.03, "learning_rate": 1.995937023869985e-06, "loss": 0.102, "step": 1638 }, { "epoch": 4.03, "learning_rate": 1.990858303707466e-06, "loss": 0.0786, "step": 1639 }, { "epoch": 4.04, "learning_rate": 1.9857795835449465e-06, "loss": 0.0908, "step": 1640 }, { "epoch": 4.04, "learning_rate": 1.980700863382428e-06, "loss": 0.0864, "step": 1641 }, { "epoch": 4.04, "learning_rate": 1.975622143219909e-06, "loss": 0.0879, "step": 1642 }, { "epoch": 4.04, "learning_rate": 1.9705434230573895e-06, "loss": 0.0928, "step": 1643 }, { "epoch": 4.05, "learning_rate": 1.9654647028948705e-06, "loss": 0.0745, "step": 1644 }, { "epoch": 4.05, "learning_rate": 1.9603859827323515e-06, "loss": 0.0958, "step": 1645 }, { "epoch": 4.05, "learning_rate": 1.9553072625698325e-06, "loss": 0.0766, "step": 1646 }, { "epoch": 4.05, "learning_rate": 1.9502285424073135e-06, "loss": 0.0934, "step": 1647 }, { "epoch": 4.06, "learning_rate": 1.9451498222447945e-06, "loss": 0.0835, "step": 1648 }, { "epoch": 4.06, "learning_rate": 1.9400711020822755e-06, "loss": 0.0869, "step": 1649 }, { "epoch": 4.06, "learning_rate": 1.9349923819197565e-06, "loss": 0.08, "step": 1650 }, { "epoch": 4.06, "learning_rate": 1.929913661757237e-06, "loss": 0.0831, "step": 1651 }, { "epoch": 4.07, "learning_rate": 1.924834941594718e-06, "loss": 0.0834, "step": 1652 }, { "epoch": 4.07, "learning_rate": 1.9197562214321996e-06, "loss": 0.0821, "step": 1653 }, { "epoch": 4.07, "learning_rate": 1.91467750126968e-06, "loss": 0.0873, "step": 1654 }, { "epoch": 4.07, "learning_rate": 1.909598781107161e-06, "loss": 0.0882, "step": 1655 }, { "epoch": 4.08, "learning_rate": 1.9045200609446421e-06, "loss": 0.0919, "step": 1656 }, { "epoch": 4.08, "learning_rate": 1.899441340782123e-06, "loss": 0.0944, "step": 1657 }, { "epoch": 4.08, "learning_rate": 1.894362620619604e-06, "loss": 0.0845, "step": 1658 }, { "epoch": 4.08, "learning_rate": 1.8892839004570851e-06, "loss": 0.1031, "step": 1659 }, { "epoch": 4.09, "learning_rate": 1.884205180294566e-06, "loss": 0.0908, "step": 1660 }, { "epoch": 4.09, "learning_rate": 1.879126460132047e-06, "loss": 0.0824, "step": 1661 }, { "epoch": 4.09, "learning_rate": 1.874047739969528e-06, "loss": 0.0948, "step": 1662 }, { "epoch": 4.09, "learning_rate": 1.8689690198070087e-06, "loss": 0.0797, "step": 1663 }, { "epoch": 4.1, "learning_rate": 1.8638902996444897e-06, "loss": 0.0894, "step": 1664 }, { "epoch": 4.1, "learning_rate": 1.858811579481971e-06, "loss": 0.0846, "step": 1665 }, { "epoch": 4.1, "learning_rate": 1.8537328593194517e-06, "loss": 0.0907, "step": 1666 }, { "epoch": 4.1, "learning_rate": 1.8486541391569327e-06, "loss": 0.0915, "step": 1667 }, { "epoch": 4.11, "learning_rate": 1.8435754189944135e-06, "loss": 0.0799, "step": 1668 }, { "epoch": 4.11, "learning_rate": 1.8384966988318945e-06, "loss": 0.0797, "step": 1669 }, { "epoch": 4.11, "learning_rate": 1.8334179786693753e-06, "loss": 0.0716, "step": 1670 }, { "epoch": 4.11, "learning_rate": 1.8283392585068563e-06, "loss": 0.1113, "step": 1671 }, { "epoch": 4.12, "learning_rate": 1.8232605383443375e-06, "loss": 0.0769, "step": 1672 }, { "epoch": 4.12, "learning_rate": 1.8181818181818183e-06, "loss": 0.0967, "step": 1673 }, { "epoch": 4.12, "learning_rate": 1.8131030980192993e-06, "loss": 0.0828, "step": 1674 }, { "epoch": 4.12, "learning_rate": 1.8080243778567803e-06, "loss": 0.0896, "step": 1675 }, { "epoch": 4.12, "learning_rate": 1.802945657694261e-06, "loss": 0.0857, "step": 1676 }, { "epoch": 4.13, "learning_rate": 1.797866937531742e-06, "loss": 0.0951, "step": 1677 }, { "epoch": 4.13, "learning_rate": 1.7927882173692233e-06, "loss": 0.0856, "step": 1678 }, { "epoch": 4.13, "learning_rate": 1.787709497206704e-06, "loss": 0.08, "step": 1679 }, { "epoch": 4.13, "learning_rate": 1.782630777044185e-06, "loss": 0.0797, "step": 1680 }, { "epoch": 4.14, "learning_rate": 1.7775520568816659e-06, "loss": 0.0823, "step": 1681 }, { "epoch": 4.14, "learning_rate": 1.7724733367191469e-06, "loss": 0.0998, "step": 1682 }, { "epoch": 4.14, "learning_rate": 1.7673946165566277e-06, "loss": 0.0828, "step": 1683 }, { "epoch": 4.14, "learning_rate": 1.7623158963941089e-06, "loss": 0.0913, "step": 1684 }, { "epoch": 4.15, "learning_rate": 1.7572371762315899e-06, "loss": 0.0904, "step": 1685 }, { "epoch": 4.15, "learning_rate": 1.7521584560690707e-06, "loss": 0.0818, "step": 1686 }, { "epoch": 4.15, "learning_rate": 1.7470797359065517e-06, "loss": 0.0777, "step": 1687 }, { "epoch": 4.15, "learning_rate": 1.7420010157440327e-06, "loss": 0.0882, "step": 1688 }, { "epoch": 4.16, "learning_rate": 1.7369222955815135e-06, "loss": 0.0806, "step": 1689 }, { "epoch": 4.16, "learning_rate": 1.7318435754189947e-06, "loss": 0.0766, "step": 1690 }, { "epoch": 4.16, "learning_rate": 1.7267648552564757e-06, "loss": 0.092, "step": 1691 }, { "epoch": 4.16, "learning_rate": 1.7216861350939565e-06, "loss": 0.0832, "step": 1692 }, { "epoch": 4.17, "learning_rate": 1.7166074149314375e-06, "loss": 0.0909, "step": 1693 }, { "epoch": 4.17, "learning_rate": 1.7115286947689182e-06, "loss": 0.0841, "step": 1694 }, { "epoch": 4.17, "learning_rate": 1.7064499746063992e-06, "loss": 0.0905, "step": 1695 }, { "epoch": 4.17, "learning_rate": 1.7013712544438805e-06, "loss": 0.0908, "step": 1696 }, { "epoch": 4.18, "learning_rate": 1.6962925342813612e-06, "loss": 0.0802, "step": 1697 }, { "epoch": 4.18, "learning_rate": 1.6912138141188422e-06, "loss": 0.0781, "step": 1698 }, { "epoch": 4.18, "learning_rate": 1.686135093956323e-06, "loss": 0.0704, "step": 1699 }, { "epoch": 4.18, "learning_rate": 1.681056373793804e-06, "loss": 0.0903, "step": 1700 }, { "epoch": 4.19, "learning_rate": 1.675977653631285e-06, "loss": 0.0842, "step": 1701 }, { "epoch": 4.19, "learning_rate": 1.670898933468766e-06, "loss": 0.0838, "step": 1702 }, { "epoch": 4.19, "learning_rate": 1.665820213306247e-06, "loss": 0.0813, "step": 1703 }, { "epoch": 4.19, "learning_rate": 1.660741493143728e-06, "loss": 0.0835, "step": 1704 }, { "epoch": 4.2, "learning_rate": 1.6556627729812088e-06, "loss": 0.0904, "step": 1705 }, { "epoch": 4.2, "learning_rate": 1.6505840528186898e-06, "loss": 0.0933, "step": 1706 }, { "epoch": 4.2, "learning_rate": 1.6455053326561706e-06, "loss": 0.0875, "step": 1707 }, { "epoch": 4.2, "learning_rate": 1.6404266124936518e-06, "loss": 0.0889, "step": 1708 }, { "epoch": 4.21, "learning_rate": 1.6353478923311328e-06, "loss": 0.0889, "step": 1709 }, { "epoch": 4.21, "learning_rate": 1.6302691721686136e-06, "loss": 0.0858, "step": 1710 }, { "epoch": 4.21, "learning_rate": 1.6251904520060946e-06, "loss": 0.0862, "step": 1711 }, { "epoch": 4.21, "learning_rate": 1.6201117318435754e-06, "loss": 0.089, "step": 1712 }, { "epoch": 4.22, "learning_rate": 1.6150330116810564e-06, "loss": 0.0847, "step": 1713 }, { "epoch": 4.22, "learning_rate": 1.6099542915185374e-06, "loss": 0.0777, "step": 1714 }, { "epoch": 4.22, "learning_rate": 1.6048755713560184e-06, "loss": 0.093, "step": 1715 }, { "epoch": 4.22, "learning_rate": 1.5997968511934994e-06, "loss": 0.0924, "step": 1716 }, { "epoch": 4.23, "learning_rate": 1.5947181310309804e-06, "loss": 0.0904, "step": 1717 }, { "epoch": 4.23, "learning_rate": 1.5896394108684612e-06, "loss": 0.0813, "step": 1718 }, { "epoch": 4.23, "learning_rate": 1.5845606907059422e-06, "loss": 0.0893, "step": 1719 }, { "epoch": 4.23, "learning_rate": 1.579481970543423e-06, "loss": 0.0802, "step": 1720 }, { "epoch": 4.24, "learning_rate": 1.5744032503809042e-06, "loss": 0.0845, "step": 1721 }, { "epoch": 4.24, "learning_rate": 1.5693245302183852e-06, "loss": 0.0774, "step": 1722 }, { "epoch": 4.24, "learning_rate": 1.564245810055866e-06, "loss": 0.0887, "step": 1723 }, { "epoch": 4.24, "learning_rate": 1.559167089893347e-06, "loss": 0.0827, "step": 1724 }, { "epoch": 4.25, "learning_rate": 1.5540883697308278e-06, "loss": 0.0817, "step": 1725 }, { "epoch": 4.25, "learning_rate": 1.5490096495683088e-06, "loss": 0.0902, "step": 1726 }, { "epoch": 4.25, "learning_rate": 1.54393092940579e-06, "loss": 0.0891, "step": 1727 }, { "epoch": 4.25, "learning_rate": 1.5388522092432708e-06, "loss": 0.085, "step": 1728 }, { "epoch": 4.26, "learning_rate": 1.5337734890807518e-06, "loss": 0.0829, "step": 1729 }, { "epoch": 4.26, "learning_rate": 1.5286947689182328e-06, "loss": 0.0819, "step": 1730 }, { "epoch": 4.26, "learning_rate": 1.5236160487557136e-06, "loss": 0.0863, "step": 1731 }, { "epoch": 4.26, "learning_rate": 1.5185373285931946e-06, "loss": 0.0795, "step": 1732 }, { "epoch": 4.27, "learning_rate": 1.5134586084306758e-06, "loss": 0.085, "step": 1733 }, { "epoch": 4.27, "learning_rate": 1.5083798882681566e-06, "loss": 0.0783, "step": 1734 }, { "epoch": 4.27, "learning_rate": 1.5033011681056376e-06, "loss": 0.0776, "step": 1735 }, { "epoch": 4.27, "learning_rate": 1.4982224479431184e-06, "loss": 0.0774, "step": 1736 }, { "epoch": 4.28, "learning_rate": 1.4931437277805994e-06, "loss": 0.0868, "step": 1737 }, { "epoch": 4.28, "learning_rate": 1.4880650076180802e-06, "loss": 0.0884, "step": 1738 }, { "epoch": 4.28, "learning_rate": 1.4829862874555614e-06, "loss": 0.0822, "step": 1739 }, { "epoch": 4.28, "learning_rate": 1.4779075672930424e-06, "loss": 0.0842, "step": 1740 }, { "epoch": 4.28, "learning_rate": 1.4728288471305234e-06, "loss": 0.0939, "step": 1741 }, { "epoch": 4.29, "learning_rate": 1.4677501269680042e-06, "loss": 0.0943, "step": 1742 }, { "epoch": 4.29, "learning_rate": 1.4626714068054852e-06, "loss": 0.0845, "step": 1743 }, { "epoch": 4.29, "learning_rate": 1.457592686642966e-06, "loss": 0.0871, "step": 1744 }, { "epoch": 4.29, "learning_rate": 1.4525139664804472e-06, "loss": 0.0877, "step": 1745 }, { "epoch": 4.3, "learning_rate": 1.4474352463179282e-06, "loss": 0.084, "step": 1746 }, { "epoch": 4.3, "learning_rate": 1.442356526155409e-06, "loss": 0.0922, "step": 1747 }, { "epoch": 4.3, "learning_rate": 1.43727780599289e-06, "loss": 0.0762, "step": 1748 }, { "epoch": 4.3, "learning_rate": 1.4321990858303707e-06, "loss": 0.0835, "step": 1749 }, { "epoch": 4.31, "learning_rate": 1.4271203656678517e-06, "loss": 0.0918, "step": 1750 }, { "epoch": 4.31, "learning_rate": 1.4220416455053325e-06, "loss": 0.0913, "step": 1751 }, { "epoch": 4.31, "learning_rate": 1.4169629253428137e-06, "loss": 0.0854, "step": 1752 }, { "epoch": 4.31, "learning_rate": 1.4118842051802947e-06, "loss": 0.0846, "step": 1753 }, { "epoch": 4.32, "learning_rate": 1.4068054850177757e-06, "loss": 0.0857, "step": 1754 }, { "epoch": 4.32, "learning_rate": 1.4017267648552565e-06, "loss": 0.0861, "step": 1755 }, { "epoch": 4.32, "learning_rate": 1.3966480446927375e-06, "loss": 0.0908, "step": 1756 }, { "epoch": 4.32, "learning_rate": 1.3915693245302183e-06, "loss": 0.0901, "step": 1757 }, { "epoch": 4.33, "learning_rate": 1.3864906043676995e-06, "loss": 0.0921, "step": 1758 }, { "epoch": 4.33, "learning_rate": 1.3814118842051805e-06, "loss": 0.0902, "step": 1759 }, { "epoch": 4.33, "learning_rate": 1.3763331640426613e-06, "loss": 0.0985, "step": 1760 }, { "epoch": 4.33, "learning_rate": 1.3712544438801423e-06, "loss": 0.0906, "step": 1761 }, { "epoch": 4.34, "learning_rate": 1.3661757237176231e-06, "loss": 0.0791, "step": 1762 }, { "epoch": 4.34, "learning_rate": 1.3610970035551041e-06, "loss": 0.0803, "step": 1763 }, { "epoch": 4.34, "learning_rate": 1.3560182833925853e-06, "loss": 0.0884, "step": 1764 }, { "epoch": 4.34, "learning_rate": 1.3509395632300661e-06, "loss": 0.085, "step": 1765 }, { "epoch": 4.35, "learning_rate": 1.3458608430675471e-06, "loss": 0.09, "step": 1766 }, { "epoch": 4.35, "learning_rate": 1.3407821229050281e-06, "loss": 0.0788, "step": 1767 }, { "epoch": 4.35, "learning_rate": 1.335703402742509e-06, "loss": 0.0846, "step": 1768 }, { "epoch": 4.35, "learning_rate": 1.33062468257999e-06, "loss": 0.0796, "step": 1769 }, { "epoch": 4.36, "learning_rate": 1.3255459624174711e-06, "loss": 0.0872, "step": 1770 }, { "epoch": 4.36, "learning_rate": 1.320467242254952e-06, "loss": 0.0854, "step": 1771 }, { "epoch": 4.36, "learning_rate": 1.315388522092433e-06, "loss": 0.092, "step": 1772 }, { "epoch": 4.36, "learning_rate": 1.3103098019299137e-06, "loss": 0.0779, "step": 1773 }, { "epoch": 4.37, "learning_rate": 1.3052310817673947e-06, "loss": 0.0858, "step": 1774 }, { "epoch": 4.37, "learning_rate": 1.3001523616048755e-06, "loss": 0.0793, "step": 1775 }, { "epoch": 4.37, "learning_rate": 1.2950736414423567e-06, "loss": 0.087, "step": 1776 }, { "epoch": 4.37, "learning_rate": 1.2899949212798377e-06, "loss": 0.0889, "step": 1777 }, { "epoch": 4.38, "learning_rate": 1.2849162011173185e-06, "loss": 0.0951, "step": 1778 }, { "epoch": 4.38, "learning_rate": 1.2798374809547995e-06, "loss": 0.0787, "step": 1779 }, { "epoch": 4.38, "learning_rate": 1.2747587607922805e-06, "loss": 0.0745, "step": 1780 }, { "epoch": 4.38, "learning_rate": 1.2696800406297613e-06, "loss": 0.0855, "step": 1781 }, { "epoch": 4.39, "learning_rate": 1.2646013204672425e-06, "loss": 0.0893, "step": 1782 }, { "epoch": 4.39, "learning_rate": 1.2595226003047235e-06, "loss": 0.0913, "step": 1783 }, { "epoch": 4.39, "learning_rate": 1.2544438801422043e-06, "loss": 0.0956, "step": 1784 }, { "epoch": 4.39, "learning_rate": 1.2493651599796853e-06, "loss": 0.0818, "step": 1785 }, { "epoch": 4.4, "learning_rate": 1.244286439817166e-06, "loss": 0.084, "step": 1786 }, { "epoch": 4.4, "learning_rate": 1.239207719654647e-06, "loss": 0.0881, "step": 1787 }, { "epoch": 4.4, "learning_rate": 1.234128999492128e-06, "loss": 0.093, "step": 1788 }, { "epoch": 4.4, "learning_rate": 1.229050279329609e-06, "loss": 0.0862, "step": 1789 }, { "epoch": 4.41, "learning_rate": 1.22397155916709e-06, "loss": 0.0832, "step": 1790 }, { "epoch": 4.41, "learning_rate": 1.2188928390045709e-06, "loss": 0.0865, "step": 1791 }, { "epoch": 4.41, "learning_rate": 1.2138141188420519e-06, "loss": 0.0855, "step": 1792 }, { "epoch": 4.41, "learning_rate": 1.2087353986795329e-06, "loss": 0.0788, "step": 1793 }, { "epoch": 4.42, "learning_rate": 1.2036566785170139e-06, "loss": 0.0842, "step": 1794 }, { "epoch": 4.42, "learning_rate": 1.1985779583544947e-06, "loss": 0.0724, "step": 1795 }, { "epoch": 4.42, "learning_rate": 1.1934992381919759e-06, "loss": 0.0787, "step": 1796 }, { "epoch": 4.42, "learning_rate": 1.1884205180294567e-06, "loss": 0.0793, "step": 1797 }, { "epoch": 4.43, "learning_rate": 1.1833417978669377e-06, "loss": 0.0856, "step": 1798 }, { "epoch": 4.43, "learning_rate": 1.1782630777044187e-06, "loss": 0.0825, "step": 1799 }, { "epoch": 4.43, "learning_rate": 1.1731843575418997e-06, "loss": 0.0869, "step": 1800 }, { "epoch": 4.43, "learning_rate": 1.1681056373793804e-06, "loss": 0.0834, "step": 1801 }, { "epoch": 4.44, "learning_rate": 1.1630269172168614e-06, "loss": 0.0862, "step": 1802 }, { "epoch": 4.44, "learning_rate": 1.1579481970543424e-06, "loss": 0.0863, "step": 1803 }, { "epoch": 4.44, "learning_rate": 1.1528694768918232e-06, "loss": 0.0918, "step": 1804 }, { "epoch": 4.44, "learning_rate": 1.1477907567293044e-06, "loss": 0.0827, "step": 1805 }, { "epoch": 4.44, "learning_rate": 1.1427120365667852e-06, "loss": 0.0717, "step": 1806 }, { "epoch": 4.45, "learning_rate": 1.1376333164042662e-06, "loss": 0.0847, "step": 1807 }, { "epoch": 4.45, "learning_rate": 1.1325545962417472e-06, "loss": 0.0878, "step": 1808 }, { "epoch": 4.45, "learning_rate": 1.1274758760792282e-06, "loss": 0.0892, "step": 1809 }, { "epoch": 4.45, "learning_rate": 1.122397155916709e-06, "loss": 0.0874, "step": 1810 }, { "epoch": 4.46, "learning_rate": 1.11731843575419e-06, "loss": 0.0879, "step": 1811 }, { "epoch": 4.46, "learning_rate": 1.112239715591671e-06, "loss": 0.0906, "step": 1812 }, { "epoch": 4.46, "learning_rate": 1.107160995429152e-06, "loss": 0.0859, "step": 1813 }, { "epoch": 4.46, "learning_rate": 1.1020822752666328e-06, "loss": 0.0863, "step": 1814 }, { "epoch": 4.47, "learning_rate": 1.0970035551041138e-06, "loss": 0.0822, "step": 1815 }, { "epoch": 4.47, "learning_rate": 1.0919248349415948e-06, "loss": 0.0876, "step": 1816 }, { "epoch": 4.47, "learning_rate": 1.0868461147790756e-06, "loss": 0.0811, "step": 1817 }, { "epoch": 4.47, "learning_rate": 1.0817673946165568e-06, "loss": 0.0898, "step": 1818 }, { "epoch": 4.48, "learning_rate": 1.0766886744540376e-06, "loss": 0.087, "step": 1819 }, { "epoch": 4.48, "learning_rate": 1.0716099542915186e-06, "loss": 0.0767, "step": 1820 }, { "epoch": 4.48, "learning_rate": 1.0665312341289996e-06, "loss": 0.0864, "step": 1821 }, { "epoch": 4.48, "learning_rate": 1.0614525139664806e-06, "loss": 0.0771, "step": 1822 }, { "epoch": 4.49, "learning_rate": 1.0563737938039614e-06, "loss": 0.0847, "step": 1823 }, { "epoch": 4.49, "learning_rate": 1.0512950736414424e-06, "loss": 0.0794, "step": 1824 }, { "epoch": 4.49, "learning_rate": 1.0462163534789234e-06, "loss": 0.0807, "step": 1825 }, { "epoch": 4.49, "learning_rate": 1.0411376333164044e-06, "loss": 0.0922, "step": 1826 }, { "epoch": 4.5, "learning_rate": 1.0360589131538854e-06, "loss": 0.0801, "step": 1827 }, { "epoch": 4.5, "learning_rate": 1.0309801929913662e-06, "loss": 0.0883, "step": 1828 }, { "epoch": 4.5, "learning_rate": 1.0259014728288472e-06, "loss": 0.074, "step": 1829 }, { "epoch": 4.5, "learning_rate": 1.0208227526663282e-06, "loss": 0.0821, "step": 1830 }, { "epoch": 4.51, "learning_rate": 1.0157440325038092e-06, "loss": 0.0878, "step": 1831 }, { "epoch": 4.51, "learning_rate": 1.01066531234129e-06, "loss": 0.0866, "step": 1832 }, { "epoch": 4.51, "learning_rate": 1.005586592178771e-06, "loss": 0.0872, "step": 1833 }, { "epoch": 4.51, "learning_rate": 1.000507872016252e-06, "loss": 0.0826, "step": 1834 }, { "epoch": 4.52, "learning_rate": 9.95429151853733e-07, "loss": 0.0913, "step": 1835 }, { "epoch": 4.52, "learning_rate": 9.90350431691214e-07, "loss": 0.0791, "step": 1836 }, { "epoch": 4.52, "learning_rate": 9.852717115286948e-07, "loss": 0.0773, "step": 1837 }, { "epoch": 4.52, "learning_rate": 9.801929913661758e-07, "loss": 0.096, "step": 1838 }, { "epoch": 4.53, "learning_rate": 9.751142712036568e-07, "loss": 0.086, "step": 1839 }, { "epoch": 4.53, "learning_rate": 9.700355510411378e-07, "loss": 0.0902, "step": 1840 }, { "epoch": 4.53, "learning_rate": 9.649568308786186e-07, "loss": 0.097, "step": 1841 }, { "epoch": 4.53, "learning_rate": 9.598781107160998e-07, "loss": 0.0708, "step": 1842 }, { "epoch": 4.54, "learning_rate": 9.547993905535806e-07, "loss": 0.0875, "step": 1843 }, { "epoch": 4.54, "learning_rate": 9.497206703910615e-07, "loss": 0.082, "step": 1844 }, { "epoch": 4.54, "learning_rate": 9.446419502285426e-07, "loss": 0.0837, "step": 1845 }, { "epoch": 4.54, "learning_rate": 9.395632300660235e-07, "loss": 0.085, "step": 1846 }, { "epoch": 4.55, "learning_rate": 9.344845099035044e-07, "loss": 0.0864, "step": 1847 }, { "epoch": 4.55, "learning_rate": 9.294057897409855e-07, "loss": 0.0775, "step": 1848 }, { "epoch": 4.55, "learning_rate": 9.243270695784664e-07, "loss": 0.0784, "step": 1849 }, { "epoch": 4.55, "learning_rate": 9.192483494159473e-07, "loss": 0.0827, "step": 1850 }, { "epoch": 4.56, "learning_rate": 9.141696292534281e-07, "loss": 0.0858, "step": 1851 }, { "epoch": 4.56, "learning_rate": 9.090909090909091e-07, "loss": 0.1012, "step": 1852 }, { "epoch": 4.56, "learning_rate": 9.040121889283901e-07, "loss": 0.0812, "step": 1853 }, { "epoch": 4.56, "learning_rate": 8.98933468765871e-07, "loss": 0.0833, "step": 1854 }, { "epoch": 4.57, "learning_rate": 8.93854748603352e-07, "loss": 0.0896, "step": 1855 }, { "epoch": 4.57, "learning_rate": 8.887760284408329e-07, "loss": 0.0837, "step": 1856 }, { "epoch": 4.57, "learning_rate": 8.836973082783138e-07, "loss": 0.0867, "step": 1857 }, { "epoch": 4.57, "learning_rate": 8.786185881157949e-07, "loss": 0.0863, "step": 1858 }, { "epoch": 4.58, "learning_rate": 8.735398679532758e-07, "loss": 0.0811, "step": 1859 }, { "epoch": 4.58, "learning_rate": 8.684611477907567e-07, "loss": 0.0766, "step": 1860 }, { "epoch": 4.58, "learning_rate": 8.633824276282378e-07, "loss": 0.0787, "step": 1861 }, { "epoch": 4.58, "learning_rate": 8.583037074657187e-07, "loss": 0.0856, "step": 1862 }, { "epoch": 4.59, "learning_rate": 8.532249873031996e-07, "loss": 0.0814, "step": 1863 }, { "epoch": 4.59, "learning_rate": 8.481462671406806e-07, "loss": 0.08, "step": 1864 }, { "epoch": 4.59, "learning_rate": 8.430675469781615e-07, "loss": 0.0954, "step": 1865 }, { "epoch": 4.59, "learning_rate": 8.379888268156425e-07, "loss": 0.0809, "step": 1866 }, { "epoch": 4.59, "learning_rate": 8.329101066531235e-07, "loss": 0.0888, "step": 1867 }, { "epoch": 4.6, "learning_rate": 8.278313864906044e-07, "loss": 0.0788, "step": 1868 }, { "epoch": 4.6, "learning_rate": 8.227526663280853e-07, "loss": 0.0813, "step": 1869 }, { "epoch": 4.6, "learning_rate": 8.176739461655664e-07, "loss": 0.09, "step": 1870 }, { "epoch": 4.6, "learning_rate": 8.125952260030473e-07, "loss": 0.0825, "step": 1871 }, { "epoch": 4.61, "learning_rate": 8.075165058405282e-07, "loss": 0.0929, "step": 1872 }, { "epoch": 4.61, "learning_rate": 8.024377856780092e-07, "loss": 0.0793, "step": 1873 }, { "epoch": 4.61, "learning_rate": 7.973590655154902e-07, "loss": 0.0821, "step": 1874 }, { "epoch": 4.61, "learning_rate": 7.922803453529711e-07, "loss": 0.0895, "step": 1875 }, { "epoch": 4.62, "learning_rate": 7.872016251904521e-07, "loss": 0.0891, "step": 1876 }, { "epoch": 4.62, "learning_rate": 7.82122905027933e-07, "loss": 0.0867, "step": 1877 }, { "epoch": 4.62, "learning_rate": 7.770441848654139e-07, "loss": 0.0831, "step": 1878 }, { "epoch": 4.62, "learning_rate": 7.71965464702895e-07, "loss": 0.0892, "step": 1879 }, { "epoch": 4.63, "learning_rate": 7.668867445403759e-07, "loss": 0.085, "step": 1880 }, { "epoch": 4.63, "learning_rate": 7.618080243778568e-07, "loss": 0.0833, "step": 1881 }, { "epoch": 4.63, "learning_rate": 7.567293042153379e-07, "loss": 0.0814, "step": 1882 }, { "epoch": 4.63, "learning_rate": 7.516505840528188e-07, "loss": 0.0812, "step": 1883 }, { "epoch": 4.64, "learning_rate": 7.465718638902997e-07, "loss": 0.0925, "step": 1884 }, { "epoch": 4.64, "learning_rate": 7.414931437277807e-07, "loss": 0.0909, "step": 1885 }, { "epoch": 4.64, "learning_rate": 7.364144235652617e-07, "loss": 0.0841, "step": 1886 }, { "epoch": 4.64, "learning_rate": 7.313357034027426e-07, "loss": 0.0745, "step": 1887 }, { "epoch": 4.65, "learning_rate": 7.262569832402236e-07, "loss": 0.076, "step": 1888 }, { "epoch": 4.65, "learning_rate": 7.211782630777045e-07, "loss": 0.0843, "step": 1889 }, { "epoch": 4.65, "learning_rate": 7.160995429151854e-07, "loss": 0.0902, "step": 1890 }, { "epoch": 4.65, "learning_rate": 7.110208227526663e-07, "loss": 0.0761, "step": 1891 }, { "epoch": 4.66, "learning_rate": 7.059421025901474e-07, "loss": 0.0841, "step": 1892 }, { "epoch": 4.66, "learning_rate": 7.008633824276283e-07, "loss": 0.0952, "step": 1893 }, { "epoch": 4.66, "learning_rate": 6.957846622651092e-07, "loss": 0.0952, "step": 1894 }, { "epoch": 4.66, "learning_rate": 6.907059421025903e-07, "loss": 0.0911, "step": 1895 }, { "epoch": 4.67, "learning_rate": 6.856272219400712e-07, "loss": 0.0823, "step": 1896 }, { "epoch": 4.67, "learning_rate": 6.805485017775521e-07, "loss": 0.0861, "step": 1897 }, { "epoch": 4.67, "learning_rate": 6.754697816150331e-07, "loss": 0.0712, "step": 1898 }, { "epoch": 4.67, "learning_rate": 6.703910614525141e-07, "loss": 0.086, "step": 1899 }, { "epoch": 4.68, "learning_rate": 6.65312341289995e-07, "loss": 0.0926, "step": 1900 }, { "epoch": 4.68, "learning_rate": 6.60233621127476e-07, "loss": 0.0887, "step": 1901 }, { "epoch": 4.68, "learning_rate": 6.551549009649568e-07, "loss": 0.0825, "step": 1902 }, { "epoch": 4.68, "learning_rate": 6.500761808024377e-07, "loss": 0.08, "step": 1903 }, { "epoch": 4.69, "learning_rate": 6.449974606399188e-07, "loss": 0.0848, "step": 1904 }, { "epoch": 4.69, "learning_rate": 6.399187404773997e-07, "loss": 0.0798, "step": 1905 }, { "epoch": 4.69, "learning_rate": 6.348400203148806e-07, "loss": 0.0821, "step": 1906 }, { "epoch": 4.69, "learning_rate": 6.297613001523617e-07, "loss": 0.0807, "step": 1907 }, { "epoch": 4.7, "learning_rate": 6.246825799898426e-07, "loss": 0.0842, "step": 1908 }, { "epoch": 4.7, "learning_rate": 6.196038598273235e-07, "loss": 0.0911, "step": 1909 }, { "epoch": 4.7, "learning_rate": 6.145251396648045e-07, "loss": 0.0856, "step": 1910 }, { "epoch": 4.7, "learning_rate": 6.094464195022854e-07, "loss": 0.0813, "step": 1911 }, { "epoch": 4.71, "learning_rate": 6.043676993397664e-07, "loss": 0.0915, "step": 1912 }, { "epoch": 4.71, "learning_rate": 5.992889791772473e-07, "loss": 0.08, "step": 1913 }, { "epoch": 4.71, "learning_rate": 5.942102590147283e-07, "loss": 0.0902, "step": 1914 }, { "epoch": 4.71, "learning_rate": 5.891315388522093e-07, "loss": 0.0822, "step": 1915 }, { "epoch": 4.72, "learning_rate": 5.840528186896902e-07, "loss": 0.0923, "step": 1916 }, { "epoch": 4.72, "learning_rate": 5.789740985271712e-07, "loss": 0.0757, "step": 1917 }, { "epoch": 4.72, "learning_rate": 5.738953783646522e-07, "loss": 0.0802, "step": 1918 }, { "epoch": 4.72, "learning_rate": 5.688166582021331e-07, "loss": 0.0888, "step": 1919 }, { "epoch": 4.73, "learning_rate": 5.637379380396141e-07, "loss": 0.0707, "step": 1920 }, { "epoch": 4.73, "learning_rate": 5.58659217877095e-07, "loss": 0.0858, "step": 1921 }, { "epoch": 4.73, "learning_rate": 5.53580497714576e-07, "loss": 0.0843, "step": 1922 }, { "epoch": 4.73, "learning_rate": 5.485017775520569e-07, "loss": 0.0773, "step": 1923 }, { "epoch": 4.74, "learning_rate": 5.434230573895378e-07, "loss": 0.0904, "step": 1924 }, { "epoch": 4.74, "learning_rate": 5.383443372270188e-07, "loss": 0.0908, "step": 1925 }, { "epoch": 4.74, "learning_rate": 5.332656170644998e-07, "loss": 0.0804, "step": 1926 }, { "epoch": 4.74, "learning_rate": 5.281868969019807e-07, "loss": 0.0826, "step": 1927 }, { "epoch": 4.75, "learning_rate": 5.231081767394617e-07, "loss": 0.0973, "step": 1928 }, { "epoch": 4.75, "learning_rate": 5.180294565769427e-07, "loss": 0.0708, "step": 1929 }, { "epoch": 4.75, "learning_rate": 5.129507364144236e-07, "loss": 0.0754, "step": 1930 }, { "epoch": 4.75, "learning_rate": 5.078720162519046e-07, "loss": 0.0853, "step": 1931 }, { "epoch": 4.75, "learning_rate": 5.027932960893855e-07, "loss": 0.0876, "step": 1932 }, { "epoch": 4.76, "learning_rate": 4.977145759268665e-07, "loss": 0.0768, "step": 1933 }, { "epoch": 4.76, "learning_rate": 4.926358557643474e-07, "loss": 0.0909, "step": 1934 }, { "epoch": 4.76, "learning_rate": 4.875571356018284e-07, "loss": 0.0806, "step": 1935 }, { "epoch": 4.76, "learning_rate": 4.824784154393093e-07, "loss": 0.0802, "step": 1936 }, { "epoch": 4.77, "learning_rate": 4.773996952767903e-07, "loss": 0.088, "step": 1937 }, { "epoch": 4.77, "learning_rate": 4.723209751142713e-07, "loss": 0.0695, "step": 1938 }, { "epoch": 4.77, "learning_rate": 4.672422549517522e-07, "loss": 0.0835, "step": 1939 }, { "epoch": 4.77, "learning_rate": 4.621635347892332e-07, "loss": 0.0808, "step": 1940 }, { "epoch": 4.78, "learning_rate": 4.5708481462671407e-07, "loss": 0.072, "step": 1941 }, { "epoch": 4.78, "learning_rate": 4.5200609446419507e-07, "loss": 0.0747, "step": 1942 }, { "epoch": 4.78, "learning_rate": 4.46927374301676e-07, "loss": 0.086, "step": 1943 }, { "epoch": 4.78, "learning_rate": 4.418486541391569e-07, "loss": 0.0864, "step": 1944 }, { "epoch": 4.79, "learning_rate": 4.367699339766379e-07, "loss": 0.0811, "step": 1945 }, { "epoch": 4.79, "learning_rate": 4.316912138141189e-07, "loss": 0.0872, "step": 1946 }, { "epoch": 4.79, "learning_rate": 4.266124936515998e-07, "loss": 0.0772, "step": 1947 }, { "epoch": 4.79, "learning_rate": 4.2153377348908076e-07, "loss": 0.0866, "step": 1948 }, { "epoch": 4.8, "learning_rate": 4.1645505332656176e-07, "loss": 0.0657, "step": 1949 }, { "epoch": 4.8, "learning_rate": 4.1137633316404265e-07, "loss": 0.0781, "step": 1950 }, { "epoch": 4.8, "learning_rate": 4.0629761300152366e-07, "loss": 0.09, "step": 1951 }, { "epoch": 4.8, "learning_rate": 4.012188928390046e-07, "loss": 0.0759, "step": 1952 }, { "epoch": 4.81, "learning_rate": 3.9614017267648555e-07, "loss": 0.0883, "step": 1953 }, { "epoch": 4.81, "learning_rate": 3.910614525139665e-07, "loss": 0.0825, "step": 1954 }, { "epoch": 4.81, "learning_rate": 3.859827323514475e-07, "loss": 0.0748, "step": 1955 }, { "epoch": 4.81, "learning_rate": 3.809040121889284e-07, "loss": 0.0841, "step": 1956 }, { "epoch": 4.82, "learning_rate": 3.758252920264094e-07, "loss": 0.0831, "step": 1957 }, { "epoch": 4.82, "learning_rate": 3.7074657186389034e-07, "loss": 0.0774, "step": 1958 }, { "epoch": 4.82, "learning_rate": 3.656678517013713e-07, "loss": 0.067, "step": 1959 }, { "epoch": 4.82, "learning_rate": 3.6058913153885224e-07, "loss": 0.0844, "step": 1960 }, { "epoch": 4.83, "learning_rate": 3.5551041137633313e-07, "loss": 0.0846, "step": 1961 }, { "epoch": 4.83, "learning_rate": 3.5043169121381413e-07, "loss": 0.083, "step": 1962 }, { "epoch": 4.83, "learning_rate": 3.4535297105129513e-07, "loss": 0.0836, "step": 1963 }, { "epoch": 4.83, "learning_rate": 3.4027425088877603e-07, "loss": 0.0794, "step": 1964 }, { "epoch": 4.84, "learning_rate": 3.3519553072625703e-07, "loss": 0.076, "step": 1965 }, { "epoch": 4.84, "learning_rate": 3.30116810563738e-07, "loss": 0.0802, "step": 1966 }, { "epoch": 4.84, "learning_rate": 3.2503809040121887e-07, "loss": 0.089, "step": 1967 }, { "epoch": 4.84, "learning_rate": 3.1995937023869987e-07, "loss": 0.0835, "step": 1968 }, { "epoch": 4.85, "learning_rate": 3.1488065007618087e-07, "loss": 0.0782, "step": 1969 }, { "epoch": 4.85, "learning_rate": 3.0980192991366177e-07, "loss": 0.0881, "step": 1970 }, { "epoch": 4.85, "learning_rate": 3.047232097511427e-07, "loss": 0.0927, "step": 1971 }, { "epoch": 4.85, "learning_rate": 2.9964448958862366e-07, "loss": 0.071, "step": 1972 }, { "epoch": 4.86, "learning_rate": 2.9456576942610466e-07, "loss": 0.0733, "step": 1973 }, { "epoch": 4.86, "learning_rate": 2.894870492635856e-07, "loss": 0.0837, "step": 1974 }, { "epoch": 4.86, "learning_rate": 2.8440832910106656e-07, "loss": 0.0777, "step": 1975 }, { "epoch": 4.86, "learning_rate": 2.793296089385475e-07, "loss": 0.0861, "step": 1976 }, { "epoch": 4.87, "learning_rate": 2.7425088877602845e-07, "loss": 0.0824, "step": 1977 }, { "epoch": 4.87, "learning_rate": 2.691721686135094e-07, "loss": 0.0927, "step": 1978 }, { "epoch": 4.87, "learning_rate": 2.6409344845099035e-07, "loss": 0.0899, "step": 1979 }, { "epoch": 4.87, "learning_rate": 2.5901472828847135e-07, "loss": 0.0926, "step": 1980 }, { "epoch": 4.88, "learning_rate": 2.539360081259523e-07, "loss": 0.0826, "step": 1981 }, { "epoch": 4.88, "learning_rate": 2.4885728796343325e-07, "loss": 0.083, "step": 1982 }, { "epoch": 4.88, "learning_rate": 2.437785678009142e-07, "loss": 0.0763, "step": 1983 }, { "epoch": 4.88, "learning_rate": 2.3869984763839514e-07, "loss": 0.091, "step": 1984 }, { "epoch": 4.89, "learning_rate": 2.336211274758761e-07, "loss": 0.0782, "step": 1985 }, { "epoch": 4.89, "learning_rate": 2.2854240731335704e-07, "loss": 0.0836, "step": 1986 }, { "epoch": 4.89, "learning_rate": 2.23463687150838e-07, "loss": 0.0862, "step": 1987 }, { "epoch": 4.89, "learning_rate": 2.1838496698831896e-07, "loss": 0.0913, "step": 1988 }, { "epoch": 4.9, "learning_rate": 2.133062468257999e-07, "loss": 0.1003, "step": 1989 }, { "epoch": 4.9, "learning_rate": 2.0822752666328088e-07, "loss": 0.0909, "step": 1990 }, { "epoch": 4.9, "learning_rate": 2.0314880650076183e-07, "loss": 0.0931, "step": 1991 }, { "epoch": 4.9, "learning_rate": 1.9807008633824278e-07, "loss": 0.0819, "step": 1992 }, { "epoch": 4.91, "learning_rate": 1.9299136617572375e-07, "loss": 0.0937, "step": 1993 }, { "epoch": 4.91, "learning_rate": 1.879126460132047e-07, "loss": 0.0854, "step": 1994 }, { "epoch": 4.91, "learning_rate": 1.8283392585068564e-07, "loss": 0.0823, "step": 1995 }, { "epoch": 4.91, "learning_rate": 1.7775520568816657e-07, "loss": 0.0843, "step": 1996 }, { "epoch": 4.91, "learning_rate": 1.7267648552564757e-07, "loss": 0.0743, "step": 1997 }, { "epoch": 4.92, "learning_rate": 1.6759776536312851e-07, "loss": 0.071, "step": 1998 }, { "epoch": 4.92, "learning_rate": 1.6251904520060944e-07, "loss": 0.0929, "step": 1999 }, { "epoch": 4.92, "learning_rate": 1.5744032503809044e-07, "loss": 0.0722, "step": 2000 }, { "epoch": 4.92, "learning_rate": 1.5236160487557136e-07, "loss": 0.0908, "step": 2001 }, { "epoch": 4.93, "learning_rate": 1.4728288471305233e-07, "loss": 0.0942, "step": 2002 }, { "epoch": 4.93, "learning_rate": 1.4220416455053328e-07, "loss": 0.0907, "step": 2003 }, { "epoch": 4.93, "learning_rate": 1.3712544438801423e-07, "loss": 0.0708, "step": 2004 }, { "epoch": 4.93, "learning_rate": 1.3204672422549517e-07, "loss": 0.0815, "step": 2005 }, { "epoch": 4.94, "learning_rate": 1.2696800406297615e-07, "loss": 0.0839, "step": 2006 }, { "epoch": 4.94, "learning_rate": 1.218892839004571e-07, "loss": 0.0835, "step": 2007 }, { "epoch": 4.94, "learning_rate": 1.1681056373793804e-07, "loss": 0.0857, "step": 2008 }, { "epoch": 4.94, "learning_rate": 1.11731843575419e-07, "loss": 0.087, "step": 2009 }, { "epoch": 4.95, "learning_rate": 1.0665312341289995e-07, "loss": 0.0794, "step": 2010 }, { "epoch": 4.95, "learning_rate": 1.0157440325038091e-07, "loss": 0.0758, "step": 2011 }, { "epoch": 4.95, "learning_rate": 9.649568308786187e-08, "loss": 0.076, "step": 2012 }, { "epoch": 4.95, "learning_rate": 9.141696292534282e-08, "loss": 0.0835, "step": 2013 }, { "epoch": 4.96, "learning_rate": 8.633824276282378e-08, "loss": 0.0756, "step": 2014 }, { "epoch": 4.96, "learning_rate": 8.125952260030472e-08, "loss": 0.0772, "step": 2015 }, { "epoch": 4.96, "learning_rate": 7.618080243778568e-08, "loss": 0.0842, "step": 2016 }, { "epoch": 4.96, "learning_rate": 7.110208227526664e-08, "loss": 0.0891, "step": 2017 }, { "epoch": 4.97, "learning_rate": 6.602336211274759e-08, "loss": 0.083, "step": 2018 }, { "epoch": 4.97, "learning_rate": 6.094464195022855e-08, "loss": 0.0835, "step": 2019 }, { "epoch": 4.97, "learning_rate": 5.58659217877095e-08, "loss": 0.0791, "step": 2020 }, { "epoch": 4.97, "learning_rate": 5.078720162519046e-08, "loss": 0.0902, "step": 2021 }, { "epoch": 4.98, "learning_rate": 4.570848146267141e-08, "loss": 0.0846, "step": 2022 }, { "epoch": 4.98, "learning_rate": 4.062976130015236e-08, "loss": 0.0875, "step": 2023 }, { "epoch": 4.98, "learning_rate": 3.555104113763332e-08, "loss": 0.0782, "step": 2024 }, { "epoch": 4.98, "learning_rate": 3.0472320975114274e-08, "loss": 0.0814, "step": 2025 }, { "epoch": 4.99, "learning_rate": 2.539360081259523e-08, "loss": 0.0878, "step": 2026 }, { "epoch": 4.99, "learning_rate": 2.031488065007618e-08, "loss": 0.0918, "step": 2027 }, { "epoch": 4.99, "learning_rate": 1.5236160487557137e-08, "loss": 0.0815, "step": 2028 }, { "epoch": 4.99, "learning_rate": 1.015744032503809e-08, "loss": 0.0864, "step": 2029 }, { "epoch": 5.0, "learning_rate": 5.078720162519045e-09, "loss": 0.0935, "step": 2030 }, { "epoch": 5.0, "step": 2030, "total_flos": 275750222733312.0, "train_loss": 0.29390622800206906, "train_runtime": 153365.1337, "train_samples_per_second": 1.695, "train_steps_per_second": 0.013 } ], "max_steps": 2030, "num_train_epochs": 5, "total_flos": 275750222733312.0, "trial_name": null, "trial_params": null }